| .. | .. |
|---|
| 1 | +// SPDX-License-Identifier: GPL-2.0-only |
|---|
| 1 | 2 | /* |
|---|
| 2 | 3 | * common.c - C code for kernel entry and exit |
|---|
| 3 | 4 | * Copyright (c) 2015 Andrew Lutomirski |
|---|
| 4 | | - * GPL v2 |
|---|
| 5 | 5 | * |
|---|
| 6 | 6 | * Based on asm and ptrace code by many authors. The code here originated |
|---|
| 7 | 7 | * in ptrace.c and signal.c. |
|---|
| .. | .. |
|---|
| 10 | 10 | #include <linux/kernel.h> |
|---|
| 11 | 11 | #include <linux/sched.h> |
|---|
| 12 | 12 | #include <linux/sched/task_stack.h> |
|---|
| 13 | +#include <linux/entry-common.h> |
|---|
| 13 | 14 | #include <linux/mm.h> |
|---|
| 14 | 15 | #include <linux/smp.h> |
|---|
| 15 | 16 | #include <linux/errno.h> |
|---|
| 16 | 17 | #include <linux/ptrace.h> |
|---|
| 17 | | -#include <linux/tracehook.h> |
|---|
| 18 | | -#include <linux/audit.h> |
|---|
| 19 | | -#include <linux/seccomp.h> |
|---|
| 20 | | -#include <linux/signal.h> |
|---|
| 21 | 18 | #include <linux/export.h> |
|---|
| 22 | | -#include <linux/context_tracking.h> |
|---|
| 23 | | -#include <linux/user-return-notifier.h> |
|---|
| 24 | 19 | #include <linux/nospec.h> |
|---|
| 25 | | -#include <linux/uprobes.h> |
|---|
| 26 | | -#include <linux/livepatch.h> |
|---|
| 27 | 20 | #include <linux/syscalls.h> |
|---|
| 21 | +#include <linux/uaccess.h> |
|---|
| 22 | + |
|---|
| 23 | +#ifdef CONFIG_XEN_PV |
|---|
| 24 | +#include <xen/xen-ops.h> |
|---|
| 25 | +#include <xen/events.h> |
|---|
| 26 | +#endif |
|---|
| 28 | 27 | |
|---|
| 29 | 28 | #include <asm/desc.h> |
|---|
| 30 | 29 | #include <asm/traps.h> |
|---|
| 31 | 30 | #include <asm/vdso.h> |
|---|
| 32 | | -#include <linux/uaccess.h> |
|---|
| 33 | 31 | #include <asm/cpufeature.h> |
|---|
| 32 | +#include <asm/fpu/api.h> |
|---|
| 34 | 33 | #include <asm/nospec-branch.h> |
|---|
| 35 | | - |
|---|
| 36 | | -#define CREATE_TRACE_POINTS |
|---|
| 37 | | -#include <trace/events/syscalls.h> |
|---|
| 38 | | - |
|---|
| 39 | | -#ifdef CONFIG_CONTEXT_TRACKING |
|---|
| 40 | | -/* Called on entry from user mode with IRQs off. */ |
|---|
| 41 | | -__visible inline void enter_from_user_mode(void) |
|---|
| 42 | | -{ |
|---|
| 43 | | - CT_WARN_ON(ct_state() != CONTEXT_USER); |
|---|
| 44 | | - user_exit_irqoff(); |
|---|
| 45 | | -} |
|---|
| 46 | | -#else |
|---|
| 47 | | -static inline void enter_from_user_mode(void) {} |
|---|
| 48 | | -#endif |
|---|
| 49 | | - |
|---|
| 50 | | -static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch) |
|---|
| 51 | | -{ |
|---|
| 52 | | -#ifdef CONFIG_X86_64 |
|---|
| 53 | | - if (arch == AUDIT_ARCH_X86_64) { |
|---|
| 54 | | - audit_syscall_entry(regs->orig_ax, regs->di, |
|---|
| 55 | | - regs->si, regs->dx, regs->r10); |
|---|
| 56 | | - } else |
|---|
| 57 | | -#endif |
|---|
| 58 | | - { |
|---|
| 59 | | - audit_syscall_entry(regs->orig_ax, regs->bx, |
|---|
| 60 | | - regs->cx, regs->dx, regs->si); |
|---|
| 61 | | - } |
|---|
| 62 | | -} |
|---|
| 63 | | - |
|---|
| 64 | | -/* |
|---|
| 65 | | - * Returns the syscall nr to run (which should match regs->orig_ax) or -1 |
|---|
| 66 | | - * to skip the syscall. |
|---|
| 67 | | - */ |
|---|
| 68 | | -static long syscall_trace_enter(struct pt_regs *regs) |
|---|
| 69 | | -{ |
|---|
| 70 | | - u32 arch = in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; |
|---|
| 71 | | - |
|---|
| 72 | | - struct thread_info *ti = current_thread_info(); |
|---|
| 73 | | - unsigned long ret = 0; |
|---|
| 74 | | - bool emulated = false; |
|---|
| 75 | | - u32 work; |
|---|
| 76 | | - |
|---|
| 77 | | - if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) |
|---|
| 78 | | - BUG_ON(regs != task_pt_regs(current)); |
|---|
| 79 | | - |
|---|
| 80 | | - work = READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; |
|---|
| 81 | | - |
|---|
| 82 | | - if (unlikely(work & _TIF_SYSCALL_EMU)) |
|---|
| 83 | | - emulated = true; |
|---|
| 84 | | - |
|---|
| 85 | | - if ((emulated || (work & _TIF_SYSCALL_TRACE)) && |
|---|
| 86 | | - tracehook_report_syscall_entry(regs)) |
|---|
| 87 | | - return -1L; |
|---|
| 88 | | - |
|---|
| 89 | | - if (emulated) |
|---|
| 90 | | - return -1L; |
|---|
| 91 | | - |
|---|
| 92 | | -#ifdef CONFIG_SECCOMP |
|---|
| 93 | | - /* |
|---|
| 94 | | - * Do seccomp after ptrace, to catch any tracer changes. |
|---|
| 95 | | - */ |
|---|
| 96 | | - if (work & _TIF_SECCOMP) { |
|---|
| 97 | | - struct seccomp_data sd; |
|---|
| 98 | | - |
|---|
| 99 | | - sd.arch = arch; |
|---|
| 100 | | - sd.nr = regs->orig_ax; |
|---|
| 101 | | - sd.instruction_pointer = regs->ip; |
|---|
| 102 | | -#ifdef CONFIG_X86_64 |
|---|
| 103 | | - if (arch == AUDIT_ARCH_X86_64) { |
|---|
| 104 | | - sd.args[0] = regs->di; |
|---|
| 105 | | - sd.args[1] = regs->si; |
|---|
| 106 | | - sd.args[2] = regs->dx; |
|---|
| 107 | | - sd.args[3] = regs->r10; |
|---|
| 108 | | - sd.args[4] = regs->r8; |
|---|
| 109 | | - sd.args[5] = regs->r9; |
|---|
| 110 | | - } else |
|---|
| 111 | | -#endif |
|---|
| 112 | | - { |
|---|
| 113 | | - sd.args[0] = regs->bx; |
|---|
| 114 | | - sd.args[1] = regs->cx; |
|---|
| 115 | | - sd.args[2] = regs->dx; |
|---|
| 116 | | - sd.args[3] = regs->si; |
|---|
| 117 | | - sd.args[4] = regs->di; |
|---|
| 118 | | - sd.args[5] = regs->bp; |
|---|
| 119 | | - } |
|---|
| 120 | | - |
|---|
| 121 | | - ret = __secure_computing(&sd); |
|---|
| 122 | | - if (ret == -1) |
|---|
| 123 | | - return ret; |
|---|
| 124 | | - } |
|---|
| 125 | | -#endif |
|---|
| 126 | | - |
|---|
| 127 | | - if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) |
|---|
| 128 | | - trace_sys_enter(regs, regs->orig_ax); |
|---|
| 129 | | - |
|---|
| 130 | | - do_audit_syscall_entry(regs, arch); |
|---|
| 131 | | - |
|---|
| 132 | | - return ret ?: regs->orig_ax; |
|---|
| 133 | | -} |
|---|
| 134 | | - |
|---|
| 135 | | -#define EXIT_TO_USERMODE_LOOP_FLAGS \ |
|---|
| 136 | | - (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ |
|---|
| 137 | | - _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING) |
|---|
| 138 | | - |
|---|
| 139 | | -static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) |
|---|
| 140 | | -{ |
|---|
| 141 | | - /* |
|---|
| 142 | | - * In order to return to user mode, we need to have IRQs off with |
|---|
| 143 | | - * none of EXIT_TO_USERMODE_LOOP_FLAGS set. Several of these flags |
|---|
| 144 | | - * can be set at any time on preemptable kernels if we have IRQs on, |
|---|
| 145 | | - * so we need to loop. Disabling preemption wouldn't help: doing the |
|---|
| 146 | | - * work to clear some of the flags can sleep. |
|---|
| 147 | | - */ |
|---|
| 148 | | - while (true) { |
|---|
| 149 | | - /* We have work to do. */ |
|---|
| 150 | | - local_irq_enable(); |
|---|
| 151 | | - |
|---|
| 152 | | - if (cached_flags & _TIF_NEED_RESCHED) |
|---|
| 153 | | - schedule(); |
|---|
| 154 | | - |
|---|
| 155 | | - if (cached_flags & _TIF_UPROBE) |
|---|
| 156 | | - uprobe_notify_resume(regs); |
|---|
| 157 | | - |
|---|
| 158 | | - if (cached_flags & _TIF_PATCH_PENDING) |
|---|
| 159 | | - klp_update_patch_state(current); |
|---|
| 160 | | - |
|---|
| 161 | | - /* deal with pending signal delivery */ |
|---|
| 162 | | - if (cached_flags & _TIF_SIGPENDING) |
|---|
| 163 | | - do_signal(regs); |
|---|
| 164 | | - |
|---|
| 165 | | - if (cached_flags & _TIF_NOTIFY_RESUME) { |
|---|
| 166 | | - clear_thread_flag(TIF_NOTIFY_RESUME); |
|---|
| 167 | | - tracehook_notify_resume(regs); |
|---|
| 168 | | - rseq_handle_notify_resume(NULL, regs); |
|---|
| 169 | | - } |
|---|
| 170 | | - |
|---|
| 171 | | - if (cached_flags & _TIF_USER_RETURN_NOTIFY) |
|---|
| 172 | | - fire_user_return_notifiers(); |
|---|
| 173 | | - |
|---|
| 174 | | - /* Disable IRQs and retry */ |
|---|
| 175 | | - local_irq_disable(); |
|---|
| 176 | | - |
|---|
| 177 | | - cached_flags = READ_ONCE(current_thread_info()->flags); |
|---|
| 178 | | - |
|---|
| 179 | | - if (!(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS)) |
|---|
| 180 | | - break; |
|---|
| 181 | | - } |
|---|
| 182 | | -} |
|---|
| 183 | | - |
|---|
| 184 | | -/* Called with IRQs disabled. */ |
|---|
| 185 | | -__visible inline void prepare_exit_to_usermode(struct pt_regs *regs) |
|---|
| 186 | | -{ |
|---|
| 187 | | - struct thread_info *ti = current_thread_info(); |
|---|
| 188 | | - u32 cached_flags; |
|---|
| 189 | | - |
|---|
| 190 | | - addr_limit_user_check(); |
|---|
| 191 | | - |
|---|
| 192 | | - lockdep_assert_irqs_disabled(); |
|---|
| 193 | | - lockdep_sys_exit(); |
|---|
| 194 | | - |
|---|
| 195 | | - cached_flags = READ_ONCE(ti->flags); |
|---|
| 196 | | - |
|---|
| 197 | | - if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS)) |
|---|
| 198 | | - exit_to_usermode_loop(regs, cached_flags); |
|---|
| 199 | | - |
|---|
| 200 | | -#ifdef CONFIG_COMPAT |
|---|
| 201 | | - /* |
|---|
| 202 | | - * Compat syscalls set TS_COMPAT. Make sure we clear it before |
|---|
| 203 | | - * returning to user mode. We need to clear it *after* signal |
|---|
| 204 | | - * handling, because syscall restart has a fixup for compat |
|---|
| 205 | | - * syscalls. The fixup is exercised by the ptrace_syscall_32 |
|---|
| 206 | | - * selftest. |
|---|
| 207 | | - * |
|---|
| 208 | | - * We also need to clear TS_REGS_POKED_I386: the 32-bit tracer |
|---|
| 209 | | - * special case only applies after poking regs and before the |
|---|
| 210 | | - * very next return to user mode. |
|---|
| 211 | | - */ |
|---|
| 212 | | - ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED); |
|---|
| 213 | | -#endif |
|---|
| 214 | | - |
|---|
| 215 | | - user_enter_irqoff(); |
|---|
| 216 | | - |
|---|
| 217 | | - mds_user_clear_cpu_buffers(); |
|---|
| 218 | | -} |
|---|
| 219 | | - |
|---|
| 220 | | -#define SYSCALL_EXIT_WORK_FLAGS \ |
|---|
| 221 | | - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ |
|---|
| 222 | | - _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT) |
|---|
| 223 | | - |
|---|
| 224 | | -static void syscall_slow_exit_work(struct pt_regs *regs, u32 cached_flags) |
|---|
| 225 | | -{ |
|---|
| 226 | | - bool step; |
|---|
| 227 | | - |
|---|
| 228 | | - audit_syscall_exit(regs); |
|---|
| 229 | | - |
|---|
| 230 | | - if (cached_flags & _TIF_SYSCALL_TRACEPOINT) |
|---|
| 231 | | - trace_sys_exit(regs, regs->ax); |
|---|
| 232 | | - |
|---|
| 233 | | - /* |
|---|
| 234 | | - * If TIF_SYSCALL_EMU is set, we only get here because of |
|---|
| 235 | | - * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP). |
|---|
| 236 | | - * We already reported this syscall instruction in |
|---|
| 237 | | - * syscall_trace_enter(). |
|---|
| 238 | | - */ |
|---|
| 239 | | - step = unlikely( |
|---|
| 240 | | - (cached_flags & (_TIF_SINGLESTEP | _TIF_SYSCALL_EMU)) |
|---|
| 241 | | - == _TIF_SINGLESTEP); |
|---|
| 242 | | - if (step || cached_flags & _TIF_SYSCALL_TRACE) |
|---|
| 243 | | - tracehook_report_syscall_exit(regs, step); |
|---|
| 244 | | -} |
|---|
| 245 | | - |
|---|
| 246 | | -/* |
|---|
| 247 | | - * Called with IRQs on and fully valid regs. Returns with IRQs off in a |
|---|
| 248 | | - * state such that we can immediately switch to user mode. |
|---|
| 249 | | - */ |
|---|
| 250 | | -__visible inline void syscall_return_slowpath(struct pt_regs *regs) |
|---|
| 251 | | -{ |
|---|
| 252 | | - struct thread_info *ti = current_thread_info(); |
|---|
| 253 | | - u32 cached_flags = READ_ONCE(ti->flags); |
|---|
| 254 | | - |
|---|
| 255 | | - CT_WARN_ON(ct_state() != CONTEXT_KERNEL); |
|---|
| 256 | | - |
|---|
| 257 | | - if (IS_ENABLED(CONFIG_PROVE_LOCKING) && |
|---|
| 258 | | - WARN(irqs_disabled(), "syscall %ld left IRQs disabled", regs->orig_ax)) |
|---|
| 259 | | - local_irq_enable(); |
|---|
| 260 | | - |
|---|
| 261 | | - rseq_syscall(regs); |
|---|
| 262 | | - |
|---|
| 263 | | - /* |
|---|
| 264 | | - * First do one-time work. If these work items are enabled, we |
|---|
| 265 | | - * want to run them exactly once per syscall exit with IRQs on. |
|---|
| 266 | | - */ |
|---|
| 267 | | - if (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS)) |
|---|
| 268 | | - syscall_slow_exit_work(regs, cached_flags); |
|---|
| 269 | | - |
|---|
| 270 | | - local_irq_disable(); |
|---|
| 271 | | - prepare_exit_to_usermode(regs); |
|---|
| 272 | | -} |
|---|
| 34 | +#include <asm/io_bitmap.h> |
|---|
| 35 | +#include <asm/syscall.h> |
|---|
| 36 | +#include <asm/irq_stack.h> |
|---|
| 273 | 37 | |
|---|
| 274 | 38 | #ifdef CONFIG_X86_64 |
|---|
| 275 | | -__visible void do_syscall_64(unsigned long nr, struct pt_regs *regs) |
|---|
| 39 | +__visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs) |
|---|
| 276 | 40 | { |
|---|
| 277 | | - struct thread_info *ti; |
|---|
| 41 | + nr = syscall_enter_from_user_mode(regs, nr); |
|---|
| 278 | 42 | |
|---|
| 279 | | - enter_from_user_mode(); |
|---|
| 280 | | - local_irq_enable(); |
|---|
| 281 | | - ti = current_thread_info(); |
|---|
| 282 | | - if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) |
|---|
| 283 | | - nr = syscall_trace_enter(regs); |
|---|
| 284 | | - |
|---|
| 285 | | - /* |
|---|
| 286 | | - * NB: Native and x32 syscalls are dispatched from the same |
|---|
| 287 | | - * table. The only functional difference is the x32 bit in |
|---|
| 288 | | - * regs->orig_ax, which changes the behavior of some syscalls. |
|---|
| 289 | | - */ |
|---|
| 290 | | - nr &= __SYSCALL_MASK; |
|---|
| 43 | + instrumentation_begin(); |
|---|
| 291 | 44 | if (likely(nr < NR_syscalls)) { |
|---|
| 292 | 45 | nr = array_index_nospec(nr, NR_syscalls); |
|---|
| 293 | 46 | regs->ax = sys_call_table[nr](regs); |
|---|
| 47 | +#ifdef CONFIG_X86_X32_ABI |
|---|
| 48 | + } else if (likely((nr & __X32_SYSCALL_BIT) && |
|---|
| 49 | + (nr & ~__X32_SYSCALL_BIT) < X32_NR_syscalls)) { |
|---|
| 50 | + nr = array_index_nospec(nr & ~__X32_SYSCALL_BIT, |
|---|
| 51 | + X32_NR_syscalls); |
|---|
| 52 | + regs->ax = x32_sys_call_table[nr](regs); |
|---|
| 53 | +#endif |
|---|
| 294 | 54 | } |
|---|
| 295 | | - |
|---|
| 296 | | - syscall_return_slowpath(regs); |
|---|
| 55 | + instrumentation_end(); |
|---|
| 56 | + syscall_exit_to_user_mode(regs); |
|---|
| 297 | 57 | } |
|---|
| 298 | 58 | #endif |
|---|
| 299 | 59 | |
|---|
| 300 | 60 | #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) |
|---|
| 301 | | -/* |
|---|
| 302 | | - * Does a 32-bit syscall. Called with IRQs on in CONTEXT_KERNEL. Does |
|---|
| 303 | | - * all entry and exit work and returns with IRQs off. This function is |
|---|
| 304 | | - * extremely hot in workloads that use it, and it's usually called from |
|---|
| 305 | | - * do_fast_syscall_32, so forcibly inline it to improve performance. |
|---|
| 306 | | - */ |
|---|
| 307 | | -static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) |
|---|
| 61 | +static __always_inline unsigned int syscall_32_enter(struct pt_regs *regs) |
|---|
| 308 | 62 | { |
|---|
| 309 | | - struct thread_info *ti = current_thread_info(); |
|---|
| 310 | | - unsigned int nr = (unsigned int)regs->orig_ax; |
|---|
| 63 | + if (IS_ENABLED(CONFIG_IA32_EMULATION)) |
|---|
| 64 | + current_thread_info()->status |= TS_COMPAT; |
|---|
| 311 | 65 | |
|---|
| 312 | | -#ifdef CONFIG_IA32_EMULATION |
|---|
| 313 | | - ti->status |= TS_COMPAT; |
|---|
| 314 | | -#endif |
|---|
| 66 | + return (unsigned int)regs->orig_ax; |
|---|
| 67 | +} |
|---|
| 315 | 68 | |
|---|
| 316 | | - if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) { |
|---|
| 317 | | - /* |
|---|
| 318 | | - * Subtlety here: if ptrace pokes something larger than |
|---|
| 319 | | - * 2^32-1 into orig_ax, this truncates it. This may or |
|---|
| 320 | | - * may not be necessary, but it matches the old asm |
|---|
| 321 | | - * behavior. |
|---|
| 322 | | - */ |
|---|
| 323 | | - nr = syscall_trace_enter(regs); |
|---|
| 324 | | - } |
|---|
| 325 | | - |
|---|
| 69 | +/* |
|---|
| 70 | + * Invoke a 32-bit syscall. Called with IRQs on in CONTEXT_KERNEL. |
|---|
| 71 | + */ |
|---|
| 72 | +static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, |
|---|
| 73 | + unsigned int nr) |
|---|
| 74 | +{ |
|---|
| 326 | 75 | if (likely(nr < IA32_NR_syscalls)) { |
|---|
| 327 | 76 | nr = array_index_nospec(nr, IA32_NR_syscalls); |
|---|
| 328 | | -#ifdef CONFIG_IA32_EMULATION |
|---|
| 329 | 77 | regs->ax = ia32_sys_call_table[nr](regs); |
|---|
| 330 | | -#else |
|---|
| 331 | | - /* |
|---|
| 332 | | - * It's possible that a 32-bit syscall implementation |
|---|
| 333 | | - * takes a 64-bit parameter but nonetheless assumes that |
|---|
| 334 | | - * the high bits are zero. Make sure we zero-extend all |
|---|
| 335 | | - * of the args. |
|---|
| 336 | | - */ |
|---|
| 337 | | - regs->ax = ia32_sys_call_table[nr]( |
|---|
| 338 | | - (unsigned int)regs->bx, (unsigned int)regs->cx, |
|---|
| 339 | | - (unsigned int)regs->dx, (unsigned int)regs->si, |
|---|
| 340 | | - (unsigned int)regs->di, (unsigned int)regs->bp); |
|---|
| 341 | | -#endif /* CONFIG_IA32_EMULATION */ |
|---|
| 342 | 78 | } |
|---|
| 343 | | - |
|---|
| 344 | | - syscall_return_slowpath(regs); |
|---|
| 345 | 79 | } |
|---|
| 346 | 80 | |
|---|
| 347 | 81 | /* Handles int $0x80 */ |
|---|
| 348 | | -__visible void do_int80_syscall_32(struct pt_regs *regs) |
|---|
| 82 | +__visible noinstr void do_int80_syscall_32(struct pt_regs *regs) |
|---|
| 349 | 83 | { |
|---|
| 350 | | - enter_from_user_mode(); |
|---|
| 351 | | - local_irq_enable(); |
|---|
| 352 | | - do_syscall_32_irqs_on(regs); |
|---|
| 84 | + unsigned int nr = syscall_32_enter(regs); |
|---|
| 85 | + |
|---|
| 86 | + /* |
|---|
| 87 | + * Subtlety here: if ptrace pokes something larger than 2^32-1 into |
|---|
| 88 | + * orig_ax, the unsigned int return value truncates it. This may |
|---|
| 89 | + * or may not be necessary, but it matches the old asm behavior. |
|---|
| 90 | + */ |
|---|
| 91 | + nr = (unsigned int)syscall_enter_from_user_mode(regs, nr); |
|---|
| 92 | + instrumentation_begin(); |
|---|
| 93 | + |
|---|
| 94 | + do_syscall_32_irqs_on(regs, nr); |
|---|
| 95 | + |
|---|
| 96 | + instrumentation_end(); |
|---|
| 97 | + syscall_exit_to_user_mode(regs); |
|---|
| 98 | +} |
|---|
| 99 | + |
|---|
| 100 | +static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) |
|---|
| 101 | +{ |
|---|
| 102 | + unsigned int nr = syscall_32_enter(regs); |
|---|
| 103 | + int res; |
|---|
| 104 | + |
|---|
| 105 | + /* |
|---|
| 106 | + * This cannot use syscall_enter_from_user_mode() as it has to |
|---|
| 107 | + * fetch EBP before invoking any of the syscall entry work |
|---|
| 108 | + * functions. |
|---|
| 109 | + */ |
|---|
| 110 | + syscall_enter_from_user_mode_prepare(regs); |
|---|
| 111 | + |
|---|
| 112 | + instrumentation_begin(); |
|---|
| 113 | + /* Fetch EBP from where the vDSO stashed it. */ |
|---|
| 114 | + if (IS_ENABLED(CONFIG_X86_64)) { |
|---|
| 115 | + /* |
|---|
| 116 | + * Micro-optimization: the pointer we're following is |
|---|
| 117 | + * explicitly 32 bits, so it can't be out of range. |
|---|
| 118 | + */ |
|---|
| 119 | + res = __get_user(*(u32 *)®s->bp, |
|---|
| 120 | + (u32 __user __force *)(unsigned long)(u32)regs->sp); |
|---|
| 121 | + } else { |
|---|
| 122 | + res = get_user(*(u32 *)®s->bp, |
|---|
| 123 | + (u32 __user __force *)(unsigned long)(u32)regs->sp); |
|---|
| 124 | + } |
|---|
| 125 | + |
|---|
| 126 | + if (res) { |
|---|
| 127 | + /* User code screwed up. */ |
|---|
| 128 | + regs->ax = -EFAULT; |
|---|
| 129 | + |
|---|
| 130 | + local_irq_disable(); |
|---|
| 131 | + instrumentation_end(); |
|---|
| 132 | + irqentry_exit_to_user_mode(regs); |
|---|
| 133 | + return false; |
|---|
| 134 | + } |
|---|
| 135 | + |
|---|
| 136 | + /* The case truncates any ptrace induced syscall nr > 2^32 -1 */ |
|---|
| 137 | + nr = (unsigned int)syscall_enter_from_user_mode_work(regs, nr); |
|---|
| 138 | + |
|---|
| 139 | + /* Now this is just like a normal syscall. */ |
|---|
| 140 | + do_syscall_32_irqs_on(regs, nr); |
|---|
| 141 | + |
|---|
| 142 | + instrumentation_end(); |
|---|
| 143 | + syscall_exit_to_user_mode(regs); |
|---|
| 144 | + return true; |
|---|
| 353 | 145 | } |
|---|
| 354 | 146 | |
|---|
| 355 | 147 | /* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */ |
|---|
| 356 | | -__visible long do_fast_syscall_32(struct pt_regs *regs) |
|---|
| 148 | +__visible noinstr long do_fast_syscall_32(struct pt_regs *regs) |
|---|
| 357 | 149 | { |
|---|
| 358 | 150 | /* |
|---|
| 359 | 151 | * Called using the internal vDSO SYSENTER/SYSCALL32 calling |
|---|
| 360 | 152 | * convention. Adjust regs so it looks like we entered using int80. |
|---|
| 361 | 153 | */ |
|---|
| 362 | | - |
|---|
| 363 | 154 | unsigned long landing_pad = (unsigned long)current->mm->context.vdso + |
|---|
| 364 | | - vdso_image_32.sym_int80_landing_pad; |
|---|
| 155 | + vdso_image_32.sym_int80_landing_pad; |
|---|
| 365 | 156 | |
|---|
| 366 | 157 | /* |
|---|
| 367 | 158 | * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward |
|---|
| .. | .. |
|---|
| 370 | 161 | */ |
|---|
| 371 | 162 | regs->ip = landing_pad; |
|---|
| 372 | 163 | |
|---|
| 373 | | - enter_from_user_mode(); |
|---|
| 374 | | - |
|---|
| 375 | | - local_irq_enable(); |
|---|
| 376 | | - |
|---|
| 377 | | - /* Fetch EBP from where the vDSO stashed it. */ |
|---|
| 378 | | - if ( |
|---|
| 379 | | -#ifdef CONFIG_X86_64 |
|---|
| 380 | | - /* |
|---|
| 381 | | - * Micro-optimization: the pointer we're following is explicitly |
|---|
| 382 | | - * 32 bits, so it can't be out of range. |
|---|
| 383 | | - */ |
|---|
| 384 | | - __get_user(*(u32 *)®s->bp, |
|---|
| 385 | | - (u32 __user __force *)(unsigned long)(u32)regs->sp) |
|---|
| 386 | | -#else |
|---|
| 387 | | - get_user(*(u32 *)®s->bp, |
|---|
| 388 | | - (u32 __user __force *)(unsigned long)(u32)regs->sp) |
|---|
| 389 | | -#endif |
|---|
| 390 | | - ) { |
|---|
| 391 | | - |
|---|
| 392 | | - /* User code screwed up. */ |
|---|
| 393 | | - local_irq_disable(); |
|---|
| 394 | | - regs->ax = -EFAULT; |
|---|
| 395 | | - prepare_exit_to_usermode(regs); |
|---|
| 396 | | - return 0; /* Keep it simple: use IRET. */ |
|---|
| 397 | | - } |
|---|
| 398 | | - |
|---|
| 399 | | - /* Now this is just like a normal syscall. */ |
|---|
| 400 | | - do_syscall_32_irqs_on(regs); |
|---|
| 164 | + /* Invoke the syscall. If it failed, keep it simple: use IRET. */ |
|---|
| 165 | + if (!__do_fast_syscall_32(regs)) |
|---|
| 166 | + return 0; |
|---|
| 401 | 167 | |
|---|
| 402 | 168 | #ifdef CONFIG_X86_64 |
|---|
| 403 | 169 | /* |
|---|
| .. | .. |
|---|
| 429 | 195 | (regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0; |
|---|
| 430 | 196 | #endif |
|---|
| 431 | 197 | } |
|---|
| 198 | + |
|---|
| 199 | +/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */ |
|---|
| 200 | +__visible noinstr long do_SYSENTER_32(struct pt_regs *regs) |
|---|
| 201 | +{ |
|---|
| 202 | + /* SYSENTER loses RSP, but the vDSO saved it in RBP. */ |
|---|
| 203 | + regs->sp = regs->bp; |
|---|
| 204 | + |
|---|
| 205 | + /* SYSENTER clobbers EFLAGS.IF. Assume it was set in usermode. */ |
|---|
| 206 | + regs->flags |= X86_EFLAGS_IF; |
|---|
| 207 | + |
|---|
| 208 | + return do_fast_syscall_32(regs); |
|---|
| 209 | +} |
|---|
| 432 | 210 | #endif |
|---|
| 211 | + |
|---|
| 212 | +SYSCALL_DEFINE0(ni_syscall) |
|---|
| 213 | +{ |
|---|
| 214 | + return -ENOSYS; |
|---|
| 215 | +} |
|---|
| 216 | + |
|---|
| 217 | +#ifdef CONFIG_XEN_PV |
|---|
| 218 | +#ifndef CONFIG_PREEMPTION |
|---|
| 219 | +/* |
|---|
| 220 | + * Some hypercalls issued by the toolstack can take many 10s of |
|---|
| 221 | + * seconds. Allow tasks running hypercalls via the privcmd driver to |
|---|
| 222 | + * be voluntarily preempted even if full kernel preemption is |
|---|
| 223 | + * disabled. |
|---|
| 224 | + * |
|---|
| 225 | + * Such preemptible hypercalls are bracketed by |
|---|
| 226 | + * xen_preemptible_hcall_begin() and xen_preemptible_hcall_end() |
|---|
| 227 | + * calls. |
|---|
| 228 | + */ |
|---|
| 229 | +DEFINE_PER_CPU(bool, xen_in_preemptible_hcall); |
|---|
| 230 | +EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall); |
|---|
| 231 | + |
|---|
| 232 | +/* |
|---|
| 233 | + * In case of scheduling the flag must be cleared and restored after |
|---|
| 234 | + * returning from schedule as the task might move to a different CPU. |
|---|
| 235 | + */ |
|---|
| 236 | +static __always_inline bool get_and_clear_inhcall(void) |
|---|
| 237 | +{ |
|---|
| 238 | + bool inhcall = __this_cpu_read(xen_in_preemptible_hcall); |
|---|
| 239 | + |
|---|
| 240 | + __this_cpu_write(xen_in_preemptible_hcall, false); |
|---|
| 241 | + return inhcall; |
|---|
| 242 | +} |
|---|
| 243 | + |
|---|
| 244 | +static __always_inline void restore_inhcall(bool inhcall) |
|---|
| 245 | +{ |
|---|
| 246 | + __this_cpu_write(xen_in_preemptible_hcall, inhcall); |
|---|
| 247 | +} |
|---|
| 248 | +#else |
|---|
| 249 | +static __always_inline bool get_and_clear_inhcall(void) { return false; } |
|---|
| 250 | +static __always_inline void restore_inhcall(bool inhcall) { } |
|---|
| 251 | +#endif |
|---|
| 252 | + |
|---|
| 253 | +static void __xen_pv_evtchn_do_upcall(void) |
|---|
| 254 | +{ |
|---|
| 255 | + irq_enter_rcu(); |
|---|
| 256 | + inc_irq_stat(irq_hv_callback_count); |
|---|
| 257 | + |
|---|
| 258 | + xen_hvm_evtchn_do_upcall(); |
|---|
| 259 | + |
|---|
| 260 | + irq_exit_rcu(); |
|---|
| 261 | +} |
|---|
| 262 | + |
|---|
| 263 | +__visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs) |
|---|
| 264 | +{ |
|---|
| 265 | + struct pt_regs *old_regs; |
|---|
| 266 | + bool inhcall; |
|---|
| 267 | + irqentry_state_t state; |
|---|
| 268 | + |
|---|
| 269 | + state = irqentry_enter(regs); |
|---|
| 270 | + old_regs = set_irq_regs(regs); |
|---|
| 271 | + |
|---|
| 272 | + instrumentation_begin(); |
|---|
| 273 | + run_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs); |
|---|
| 274 | + instrumentation_end(); |
|---|
| 275 | + |
|---|
| 276 | + set_irq_regs(old_regs); |
|---|
| 277 | + |
|---|
| 278 | + inhcall = get_and_clear_inhcall(); |
|---|
| 279 | + if (inhcall && !WARN_ON_ONCE(state.exit_rcu)) { |
|---|
| 280 | + instrumentation_begin(); |
|---|
| 281 | + irqentry_exit_cond_resched(); |
|---|
| 282 | + instrumentation_end(); |
|---|
| 283 | + restore_inhcall(inhcall); |
|---|
| 284 | + } else { |
|---|
| 285 | + irqentry_exit(regs, state); |
|---|
| 286 | + } |
|---|
| 287 | +} |
|---|
| 288 | +#endif /* CONFIG_XEN_PV */ |
|---|