From fa697140f9a20119a9ec8fd7460cc4314fbdaff3 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Thu, 5 Apr 2018 11:53:02 +0200 Subject: syscalls/x86: Use 'struct pt_regs' based syscall calling convention for 64-bit syscalls Let's make use of ARCH_HAS_SYSCALL_WRAPPER=y on pure 64-bit x86-64 systems: Each syscall defines a stub which takes struct pt_regs as its only argument. It decodes just those parameters it needs, e.g: asmlinkage long sys_xyzzy(const struct pt_regs *regs) { return SyS_xyzzy(regs->di, regs->si, regs->dx); } This approach avoids leaking random user-provided register content down the call chain. For example, for sys_recv() which is a 4-parameter syscall, the assembly now is (in slightly reordered fashion): : callq <__fentry__> /* decode regs->di, ->si, ->dx and ->r10 */ mov 0x70(%rdi),%rdi mov 0x68(%rdi),%rsi mov 0x60(%rdi),%rdx mov 0x38(%rdi),%rcx [ SyS_recv() is automatically inlined by the compiler, as it is not [yet] used anywhere else ] /* clear %r9 and %r8, the 5th and 6th args */ xor %r9d,%r9d xor %r8d,%r8d /* do the actual work */ callq __sys_recvfrom /* cleanup and return */ cltq retq The only valid place in an x86-64 kernel which rightfully calls a syscall function on its own -- vsyscall -- needs to be modified to pass struct pt_regs onwards as well. To keep the syscall table generation working independent of SYSCALL_PTREGS being enabled, the stubs are named the same as the "original" syscall stubs, i.e. sys_*(). This patch is based on an original proof-of-concept | From: Linus Torvalds | Signed-off-by: Linus Torvalds and was split up and heavily modified by me, in particular to base it on ARCH_HAS_SYSCALL_WRAPPER, to limit it to 64-bit-only for the time being, and to update the vsyscall to the new calling convention. Signed-off-by: Dominik Brodowski Acked-by: Linus Torvalds Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180405095307.3730-4-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- arch/x86/include/asm/syscall_wrapper.h | 70 ++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) create mode 100644 arch/x86/include/asm/syscall_wrapper.h (limited to 'arch/x86/include/asm/syscall_wrapper.h') diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h new file mode 100644 index 000000000000..702bdee377af --- /dev/null +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * syscall_wrapper.h - x86 specific wrappers to syscall definitions + */ + +#ifndef _ASM_X86_SYSCALL_WRAPPER_H +#define _ASM_X86_SYSCALL_WRAPPER_H + +/* + * Instead of the generic __SYSCALL_DEFINEx() definition, this macro takes + * struct pt_regs *regs as the only argument of the syscall stub named + * sys_*(). It decodes just the registers it needs and passes them on to + * the SyS_*() wrapper and then to the SYSC_*() function doing the actual job. + * These wrappers and functions are inlined, meaning that the assembly looks + * as follows (slightly re-ordered): + * + * : <-- 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. + * + * As the generic SYSCALL_DEFINE0() macro does not decode any parameters for + * obvious reasons, and passing struct pt_regs *regs to it in %rdi does not + * hurt, there is no need to override it. + */ +#define __SYSCALL_DEFINEx(x, name, ...) \ + asmlinkage long sys##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(sys##name, ERRNO); \ + static long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + asmlinkage long sys##name(const struct pt_regs *regs) \ + { \ + return SyS##name(__MAP(x,__SC_ARGS \ + ,,regs->di,,regs->si,,regs->dx \ + ,,regs->r10,,regs->r8,,regs->r9)); \ + } \ + static long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + { \ + long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ + __MAP(x,__SC_TEST,__VA_ARGS__); \ + __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \ + return ret; \ + } \ + static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + +/* + * For VSYSCALLS, we need to declare these three syscalls with the new + * pt_regs-based calling convention for in-kernel use. + */ +struct pt_regs; +asmlinkage long sys_getcpu(const struct pt_regs *regs); /* di,si,dx */ +asmlinkage long sys_gettimeofday(const struct pt_regs *regs); /* di,si */ +asmlinkage long sys_time(const struct pt_regs *regs); /* di */ + +#endif /* _ASM_X86_SYSCALL_WRAPPER_H */ -- cgit