diff options
Diffstat (limited to 'arch/x86/include/asm/syscall_wrapper.h')
| -rw-r--r-- | arch/x86/include/asm/syscall_wrapper.h | 287 |
1 files changed, 155 insertions, 132 deletions
diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index e2389ce9bf58..a84333adeef2 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -8,6 +8,50 @@ struct pt_regs; +extern long __x64_sys_ni_syscall(const struct pt_regs *regs); +extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); + +/* + * Instead of the generic __SYSCALL_DEFINEx() definition, the x86 version takes + * struct pt_regs *regs as the only argument of the syscall stub(s) named as: + * __x64_sys_*() - 64-bit native syscall + * __ia32_sys_*() - 32-bit native syscall or common compat syscall + * __ia32_compat_sys_*() - 32-bit compat syscall + * __x32_compat_sys_*() - 64-bit X32 compat syscall + * + * The registers are decoded according to the ABI: + * 64-bit: RDI, RSI, RDX, R10, R8, R9 + * 32-bit: EBX, ECX, EDX, ESI, EDI, EBP + * + * The stub then passes the decoded arguments to the __se_sys_*() wrapper to + * perform sign-extension (omitted for zero-argument syscalls). Finally the + * arguments are passed to the __do_sys_*() function which is the actual + * syscall. These wrappers are marked as inline so the compiler can optimize + * the functions where appropriate. + * + * Example assembly (slightly re-ordered for better readability): + * + * <__x64_sys_recv>: <-- syscall with 4 parameters + * callq <__fentry__> + * + * mov 0x70(%rdi),%rdi <-- decode regs->di + * mov 0x68(%rdi),%rsi <-- decode regs->si + * mov 0x60(%rdi),%rdx <-- decode regs->dx + * mov 0x38(%rdi),%rcx <-- decode regs->r10 + * + * xor %r9d,%r9d <-- clear %r9 + * xor %r8d,%r8d <-- clear %r8 + * + * callq __sys_recvfrom <-- do the actual work in __sys_recvfrom() + * which takes 6 arguments + * + * cltq <-- extend return value to 64-bit + * retq <-- return + * + * This approach avoids leaking random user-provided register content down + * the call chain. + */ + /* Mapping of registers to parameters for syscalls on x86-64 and x32 */ #define SC_X86_64_REGS_TO_ARGS(x, ...) \ __MAP(x,__SC_ARGS \ @@ -21,68 +65,96 @@ struct pt_regs; ,,(unsigned int)regs->dx,,(unsigned int)regs->si \ ,,(unsigned int)regs->di,,(unsigned int)regs->bp) -#ifdef CONFIG_IA32_EMULATION -/* - * For IA32 emulation, we need to handle "compat" syscalls *and* create - * additional wrappers (aptly named __ia32_sys_xyzzy) which decode the - * ia32 regs in the proper order for shared or "common" syscalls. As some - * syscalls may not be implemented, we need to expand COND_SYSCALL in - * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this - * case as well. - */ -#define __IA32_COMPAT_SYS_STUB0(x, name) \ - asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs);\ - ALLOW_ERROR_INJECTION(__ia32_compat_sys_##name, ERRNO); \ - asmlinkage long __ia32_compat_sys_##name(const struct pt_regs *regs)\ +#define __SYS_STUB0(abi, name) \ + long __##abi##_##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(__##abi##_##name, ERRNO); \ + long __##abi##_##name(const struct pt_regs *regs) \ + __alias(__do_##name); + +#define __SYS_STUBx(abi, name, ...) \ + long __##abi##_##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(__##abi##_##name, ERRNO); \ + long __##abi##_##name(const struct pt_regs *regs) \ { \ - return __se_compat_sys_##name(); \ + return __se_##name(__VA_ARGS__); \ } -#define __IA32_COMPAT_SYS_STUBx(x, name, ...) \ - asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs);\ - ALLOW_ERROR_INJECTION(__ia32_compat_sys##name, ERRNO); \ - asmlinkage long __ia32_compat_sys##name(const struct pt_regs *regs)\ +#define __COND_SYSCALL(abi, name) \ + __weak long __##abi##_##name(const struct pt_regs *__unused) \ { \ - return __se_compat_sys##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__));\ + return sys_ni_syscall(); \ } +#define __SYS_NI(abi, name) \ + SYSCALL_ALIAS(__##abi##_##name, sys_ni_posix_timers); + +#ifdef CONFIG_X86_64 +#define __X64_SYS_STUB0(name) \ + __SYS_STUB0(x64, sys_##name) + +#define __X64_SYS_STUBx(x, name, ...) \ + __SYS_STUBx(x64, sys##name, \ + SC_X86_64_REGS_TO_ARGS(x, __VA_ARGS__)) + +#define __X64_COND_SYSCALL(name) \ + __COND_SYSCALL(x64, sys_##name) + +#define __X64_SYS_NI(name) \ + __SYS_NI(x64, sys_##name) +#else /* CONFIG_X86_64 */ +#define __X64_SYS_STUB0(name) +#define __X64_SYS_STUBx(x, name, ...) +#define __X64_COND_SYSCALL(name) +#define __X64_SYS_NI(name) +#endif /* CONFIG_X86_64 */ + +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) +#define __IA32_SYS_STUB0(name) \ + __SYS_STUB0(ia32, sys_##name) + #define __IA32_SYS_STUBx(x, name, ...) \ - asmlinkage long __ia32_sys##name(const struct pt_regs *regs); \ - ALLOW_ERROR_INJECTION(__ia32_sys##name, ERRNO); \ - asmlinkage long __ia32_sys##name(const struct pt_regs *regs) \ - { \ - return __se_sys##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__));\ - } + __SYS_STUBx(ia32, sys##name, \ + SC_IA32_REGS_TO_ARGS(x, __VA_ARGS__)) + +#define __IA32_COND_SYSCALL(name) \ + __COND_SYSCALL(ia32, sys_##name) +#define __IA32_SYS_NI(name) \ + __SYS_NI(ia32, sys_##name) +#else /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ +#define __IA32_SYS_STUB0(name) +#define __IA32_SYS_STUBx(x, name, ...) +#define __IA32_COND_SYSCALL(name) +#define __IA32_SYS_NI(name) +#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ + +#ifdef CONFIG_IA32_EMULATION /* - * To keep the naming coherent, re-define SYSCALL_DEFINE0 to create an alias - * named __ia32_sys_*() + * For IA32 emulation, we need to handle "compat" syscalls *and* create + * additional wrappers (aptly named __ia32_sys_xyzzy) which decode the + * ia32 regs in the proper order for shared or "common" syscalls. As some + * syscalls may not be implemented, we need to expand COND_SYSCALL in + * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this + * case as well. */ +#define __IA32_COMPAT_SYS_STUB0(name) \ + __SYS_STUB0(ia32, compat_sys_##name) -#define SYSCALL_DEFINE0(sname) \ - SYSCALL_METADATA(_##sname, 0); \ - asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\ - ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ - SYSCALL_ALIAS(__ia32_sys_##sname, __x64_sys_##sname); \ - asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused) +#define __IA32_COMPAT_SYS_STUBx(x, name, ...) \ + __SYS_STUBx(ia32, compat_sys##name, \ + SC_IA32_REGS_TO_ARGS(x, __VA_ARGS__)) -#define COND_SYSCALL(name) \ - asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused) \ - { \ - return sys_ni_syscall(); \ - } \ - asmlinkage __weak long __ia32_sys_##name(const struct pt_regs *__unused)\ - { \ - return sys_ni_syscall(); \ - } +#define __IA32_COMPAT_COND_SYSCALL(name) \ + __COND_SYSCALL(ia32, compat_sys_##name) -#define SYS_NI(name) \ - SYSCALL_ALIAS(__x64_sys_##name, sys_ni_posix_timers); \ - SYSCALL_ALIAS(__ia32_sys_##name, sys_ni_posix_timers) +#define __IA32_COMPAT_SYS_NI(name) \ + __SYS_NI(ia32, compat_sys_##name) #else /* CONFIG_IA32_EMULATION */ +#define __IA32_COMPAT_SYS_STUB0(name) #define __IA32_COMPAT_SYS_STUBx(x, name, ...) -#define __IA32_SYS_STUBx(x, fullname, name, ...) +#define __IA32_COMPAT_COND_SYSCALL(name) +#define __IA32_COMPAT_SYS_NI(name) #endif /* CONFIG_IA32_EMULATION */ @@ -92,25 +164,23 @@ struct pt_regs; * of the x86-64-style parameter ordering of x32 syscalls. The syscalls common * with x86_64 obviously do not need such care. */ -#define __X32_COMPAT_SYS_STUB0(x, name, ...) \ - asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs);\ - ALLOW_ERROR_INJECTION(__x32_compat_sys_##name, ERRNO); \ - asmlinkage long __x32_compat_sys_##name(const struct pt_regs *regs)\ - { \ - return __se_compat_sys_##name();\ - } +#define __X32_COMPAT_SYS_STUB0(name) \ + __SYS_STUB0(x32, compat_sys_##name) #define __X32_COMPAT_SYS_STUBx(x, name, ...) \ - asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs);\ - ALLOW_ERROR_INJECTION(__x32_compat_sys##name, ERRNO); \ - asmlinkage long __x32_compat_sys##name(const struct pt_regs *regs)\ - { \ - return __se_compat_sys##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\ - } + __SYS_STUBx(x32, compat_sys##name, \ + SC_X86_64_REGS_TO_ARGS(x, __VA_ARGS__)) + +#define __X32_COMPAT_COND_SYSCALL(name) \ + __COND_SYSCALL(x32, compat_sys_##name) +#define __X32_COMPAT_SYS_NI(name) \ + __SYS_NI(x32, compat_sys_##name) #else /* CONFIG_X86_X32 */ -#define __X32_COMPAT_SYS_STUB0(x, name) +#define __X32_COMPAT_SYS_STUB0(name) #define __X32_COMPAT_SYS_STUBx(x, name, ...) +#define __X32_COMPAT_COND_SYSCALL(name) +#define __X32_COMPAT_SYS_NI(name) #endif /* CONFIG_X86_X32 */ @@ -121,15 +191,12 @@ struct pt_regs; * of them. */ #define COMPAT_SYSCALL_DEFINE0(name) \ - static long __se_compat_sys_##name(void); \ - static inline long __do_compat_sys_##name(void); \ - __IA32_COMPAT_SYS_STUB0(x, name) \ - __X32_COMPAT_SYS_STUB0(x, name) \ - static long __se_compat_sys_##name(void) \ - { \ - return __do_compat_sys_##name(); \ - } \ - static inline long __do_compat_sys_##name(void) + static long \ + __do_compat_sys_##name(const struct pt_regs *__unused); \ + __IA32_COMPAT_SYS_STUB0(name) \ + __X32_COMPAT_SYS_STUB0(name) \ + static long \ + __do_compat_sys_##name(const struct pt_regs *__unused) #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ @@ -148,58 +215,19 @@ struct pt_regs; * kernel/time/posix-stubs.c to cover this case as well. */ #define COND_SYSCALL_COMPAT(name) \ - cond_syscall(__ia32_compat_sys_##name); \ - cond_syscall(__x32_compat_sys_##name) + __IA32_COMPAT_COND_SYSCALL(name) \ + __X32_COMPAT_COND_SYSCALL(name) #define COMPAT_SYS_NI(name) \ - SYSCALL_ALIAS(__ia32_compat_sys_##name, sys_ni_posix_timers); \ - SYSCALL_ALIAS(__x32_compat_sys_##name, sys_ni_posix_timers) + __IA32_COMPAT_SYS_NI(name) \ + __X32_COMPAT_SYS_NI(name) #endif /* CONFIG_COMPAT */ - -/* - * Instead of the generic __SYSCALL_DEFINEx() definition, this macro takes - * struct pt_regs *regs as the only argument of the syscall stub named - * __x64_sys_*(). It decodes just the registers it needs and passes them on to - * the __se_sys_*() wrapper performing sign extension and then to the - * __do_sys_*() function doing the actual job. These wrappers and functions - * are inlined (at least in very most cases), meaning that the assembly looks - * as follows (slightly re-ordered for better readability): - * - * <__x64_sys_recv>: <-- syscall with 4 parameters - * callq <__fentry__> - * - * mov 0x70(%rdi),%rdi <-- decode regs->di - * mov 0x68(%rdi),%rsi <-- decode regs->si - * mov 0x60(%rdi),%rdx <-- decode regs->dx - * mov 0x38(%rdi),%rcx <-- decode regs->r10 - * - * xor %r9d,%r9d <-- clear %r9 - * xor %r8d,%r8d <-- clear %r8 - * - * callq __sys_recvfrom <-- do the actual work in __sys_recvfrom() - * which takes 6 arguments - * - * cltq <-- extend return value to 64-bit - * retq <-- return - * - * This approach avoids leaking random user-provided register content down - * the call chain. - * - * If IA32_EMULATION is enabled, this macro generates an additional wrapper - * named __ia32_sys_*() which decodes the struct pt_regs *regs according - * to the i386 calling convention (bx, cx, dx, si, di, bp). - */ #define __SYSCALL_DEFINEx(x, name, ...) \ - asmlinkage long __x64_sys##name(const struct pt_regs *regs); \ - ALLOW_ERROR_INJECTION(__x64_sys##name, ERRNO); \ static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ - asmlinkage long __x64_sys##name(const struct pt_regs *regs) \ - { \ - return __se_sys##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\ - } \ + __X64_SYS_STUBx(x, name, __VA_ARGS__) \ __IA32_SYS_STUBx(x, name, __VA_ARGS__) \ static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ { \ @@ -217,33 +245,28 @@ struct pt_regs; * SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() and SYS_NI() * macros to work correctly. */ -#ifndef SYSCALL_DEFINE0 #define SYSCALL_DEFINE0(sname) \ SYSCALL_METADATA(_##sname, 0); \ - asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused);\ - ALLOW_ERROR_INJECTION(__x64_sys_##sname, ERRNO); \ - asmlinkage long __x64_sys_##sname(const struct pt_regs *__unused) -#endif - -#ifndef COND_SYSCALL -#define COND_SYSCALL(name) \ - asmlinkage __weak long __x64_sys_##name(const struct pt_regs *__unused) \ - { \ - return sys_ni_syscall(); \ - } -#endif + static long __do_sys_##sname(const struct pt_regs *__unused); \ + __X64_SYS_STUB0(sname) \ + __IA32_SYS_STUB0(sname) \ + static long __do_sys_##sname(const struct pt_regs *__unused) + +#define COND_SYSCALL(name) \ + __X64_COND_SYSCALL(name) \ + __IA32_COND_SYSCALL(name) -#ifndef SYS_NI -#define SYS_NI(name) SYSCALL_ALIAS(__x64_sys_##name, sys_ni_posix_timers); -#endif +#define SYS_NI(name) \ + __X64_SYS_NI(name) \ + __IA32_SYS_NI(name) /* * For VSYSCALLS, we need to declare these three syscalls with the new * pt_regs-based calling convention for in-kernel use. */ -asmlinkage long __x64_sys_getcpu(const struct pt_regs *regs); -asmlinkage long __x64_sys_gettimeofday(const struct pt_regs *regs); -asmlinkage long __x64_sys_time(const struct pt_regs *regs); +long __x64_sys_getcpu(const struct pt_regs *regs); +long __x64_sys_gettimeofday(const struct pt_regs *regs); +long __x64_sys_time(const struct pt_regs *regs); #endif /* _ASM_X86_SYSCALL_WRAPPER_H */ |