diff options
Diffstat (limited to 'arch/x86/entry')
| -rw-r--r-- | arch/x86/entry/common.c | 129 | ||||
| -rw-r--r-- | arch/x86/entry/entry_64.S | 55 | ||||
| -rw-r--r-- | arch/x86/entry/syscall_32.c | 10 | ||||
| -rw-r--r-- | arch/x86/entry/syscall_64.c | 13 | ||||
| -rw-r--r-- | arch/x86/entry/syscalls/syscall_64.tbl | 16 | ||||
| -rw-r--r-- | arch/x86/entry/syscalls/syscalltbl.sh | 58 | ||||
| -rw-r--r-- | arch/x86/entry/vsyscall/vsyscall_64.c | 2 |
7 files changed, 143 insertions, 140 deletions
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 57be07f27f37..cef47fe7817e 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -22,6 +22,7 @@ #include <linux/user-return-notifier.h> #include <linux/nospec.h> #include <linux/uprobes.h> +#include <linux/syscalls.h> #include <asm/desc.h> #include <asm/traps.h> @@ -64,22 +65,16 @@ static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch) } /* - * We can return 0 to resume the syscall or anything else to go to phase - * 2. If we resume the syscall, we need to put something appropriate in - * regs->orig_ax. - * - * NB: We don't have full pt_regs here, but regs->orig_ax and regs->ax - * are fully functional. - * - * For phase 2's benefit, our return value is: - * 0: resume the syscall - * 1: go to phase 2; no seccomp phase 2 needed - * anything else: go to phase 2; pass return value to seccomp + * Returns the syscall nr to run (which should match regs->orig_ax) or -1 + * to skip the syscall. */ -unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch) +long syscall_trace_enter(struct pt_regs *regs) { + u32 arch = is_ia32_task() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; + struct thread_info *ti = pt_regs_to_thread_info(regs); unsigned long ret = 0; + bool emulated = false; u32 work; if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) @@ -98,11 +93,29 @@ unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch) } #endif + /* + * If we stepped into a sysenter/syscall insn, it trapped in + * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP. + * If user-mode had set TF itself, then it's still clear from + * do_debug() and we need to set it again to restore the user + * state. If we entered on the slow path, TF was already set. + */ + if (work & _TIF_SINGLESTEP) + regs->flags |= X86_EFLAGS_TF; + + if (unlikely(work & _TIF_SYSCALL_EMU)) + emulated = true; + + if ((emulated || (work & _TIF_SYSCALL_TRACE)) && + tracehook_report_syscall_entry(regs)) + return -1L; + + if (emulated) + return -1L; + #ifdef CONFIG_SECCOMP /* - * Do seccomp first -- it should minimize exposure of other - * code, and keeping seccomp fast is probably more valuable - * than the rest of this. + * Do seccomp after ptrace, to catch any tracer changes. */ if (work & _TIF_SECCOMP) { struct seccomp_data sd; @@ -129,79 +142,12 @@ unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch) sd.args[5] = regs->bp; } - BUILD_BUG_ON(SECCOMP_PHASE1_OK != 0); - BUILD_BUG_ON(SECCOMP_PHASE1_SKIP != 1); - - ret = seccomp_phase1(&sd); - if (ret == SECCOMP_PHASE1_SKIP) { - regs->orig_ax = -1; - ret = 0; - } else if (ret != SECCOMP_PHASE1_OK) { - return ret; /* Go directly to phase 2 */ - } - - work &= ~_TIF_SECCOMP; - } -#endif - - /* Do our best to finish without phase 2. */ - if (work == 0) - return ret; /* seccomp and/or nohz only (ret == 0 here) */ - -#ifdef CONFIG_AUDITSYSCALL - if (work == _TIF_SYSCALL_AUDIT) { - /* - * If there is no more work to be done except auditing, - * then audit in phase 1. Phase 2 always audits, so, if - * we audit here, then we can't go on to phase 2. - */ - do_audit_syscall_entry(regs, arch); - return 0; - } -#endif - - return 1; /* Something is enabled that we can't handle in phase 1 */ -} - -/* Returns the syscall nr to run (which should match regs->orig_ax). */ -long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch, - unsigned long phase1_result) -{ - struct thread_info *ti = pt_regs_to_thread_info(regs); - long ret = 0; - u32 work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; - - if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) - BUG_ON(regs != task_pt_regs(current)); - - /* - * If we stepped into a sysenter/syscall insn, it trapped in - * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP. - * If user-mode had set TF itself, then it's still clear from - * do_debug() and we need to set it again to restore the user - * state. If we entered on the slow path, TF was already set. - */ - if (work & _TIF_SINGLESTEP) - regs->flags |= X86_EFLAGS_TF; - -#ifdef CONFIG_SECCOMP - /* - * Call seccomp_phase2 before running the other hooks so that - * they can see any changes made by a seccomp tracer. - */ - if (phase1_result > 1 && seccomp_phase2(phase1_result)) { - /* seccomp failures shouldn't expose any additional code. */ - return -1; + ret = __secure_computing(&sd); + if (ret == -1) + return ret; } #endif - if (unlikely(work & _TIF_SYSCALL_EMU)) - ret = -1L; - - if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) && - tracehook_report_syscall_entry(regs)) - ret = -1L; - if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->orig_ax); @@ -210,17 +156,6 @@ long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch, return ret ?: regs->orig_ax; } -long syscall_trace_enter(struct pt_regs *regs) -{ - u32 arch = is_ia32_task() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; - unsigned long phase1_result = syscall_trace_enter_phase1(regs, arch); - - if (phase1_result == 0) - return regs->orig_ax; - else - return syscall_trace_enter_phase2(regs, arch, phase1_result); -} - #define EXIT_TO_USERMODE_LOOP_FLAGS \ (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY) @@ -274,6 +209,8 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) struct thread_info *ti = pt_regs_to_thread_info(regs); u32 cached_flags; + addr_limit_user_check(); + if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled())) local_irq_disable(); diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index cb827c07c780..0a86120c1016 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -187,12 +187,19 @@ entry_SYSCALL_64_fastpath: sbb %rcx, %rcx /* array_index_mask_nospec() */ and %rcx, %rax movq %r10, %rcx + + /* + * This call instruction is handled specially in stub_ptregs_64. + * It might end up jumping to the slow path. If it jumps, RAX is + * clobbered. + */ #ifdef CONFIG_RETPOLINE movq sys_call_table(, %rax, 8), %rax call __x86_indirect_thunk_rax #else call *sys_call_table(, %rax, 8) #endif +.Lentry_SYSCALL_64_after_fastpath_call: movq %rax, RAX(%rsp) 1: @@ -256,25 +263,13 @@ GLOBAL(int_ret_from_sys_call_irqs_off) /* Do syscall entry tracing */ tracesys: - movq %rsp, %rdi - movl $AUDIT_ARCH_X86_64, %esi - call syscall_trace_enter_phase1 - test %rax, %rax - jnz tracesys_phase2 /* if needed, run the slow path */ - RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */ - movq ORIG_RAX(%rsp), %rax - jmp entry_SYSCALL_64_fastpath /* and return to the fast path */ - -tracesys_phase2: SAVE_EXTRA_REGS movq %rsp, %rdi - movl $AUDIT_ARCH_X86_64, %esi - movq %rax, %rdx - call syscall_trace_enter_phase2 + call syscall_trace_enter /* * Reload registers from stack in case ptrace changed them. - * We don't reload %rax because syscall_trace_entry_phase2() returned + * We don't reload %rax because syscall_trace_enter() returned * the value it wants us to use in the table lookup. */ RESTORE_C_REGS_EXCEPT_RAX @@ -399,6 +394,38 @@ opportunistic_sysret_failed: jmp restore_c_regs_and_iret END(entry_SYSCALL_64) +ENTRY(stub_ptregs_64) + /* + * Syscalls marked as needing ptregs land here. + * If we are on the fast path, we need to save the extra regs. + * If we are on the slow path, the extra regs are already saved. + * + * RAX stores a pointer to the C function implementing the syscall. + */ + cmpq $.Lentry_SYSCALL_64_after_fastpath_call, (%rsp) + jne 1f + + /* Called from fast path -- pop return address and jump to slow path */ + popq %rax + jmp tracesys /* called from fast path */ + +1: + /* Called from C */ + jmp *%rax /* called from C */ +END(stub_ptregs_64) + +.macro ptregs_stub func +ENTRY(ptregs_\func) + leaq \func(%rip), %rax + jmp stub_ptregs_64 +END(ptregs_\func) +.endm + +/* Instantiate ptregs_stub for each ptregs-using syscall */ +#define __SYSCALL_64_QUAL_(sym) +#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_stub sym +#define __SYSCALL_64(nr, sym, qual) __SYSCALL_64_QUAL_##qual(sym) +#include <asm/syscalls_64.h> .macro FORK_LIKE func ENTRY(stub_\func) diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index 9a6649857106..8f895ee13a1c 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -6,17 +6,11 @@ #include <asm/asm-offsets.h> #include <asm/syscall.h> -#ifdef CONFIG_IA32_EMULATION -#define SYM(sym, compat) compat -#else -#define SYM(sym, compat) sym -#endif - -#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage long SYM(sym, compat)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; +#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; #include <asm/syscalls_32.h> #undef __SYSCALL_I386 -#define __SYSCALL_I386(nr, sym, compat) [nr] = SYM(sym, compat), +#define __SYSCALL_I386(nr, sym, qual) [nr] = sym, extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index 41283d22be7a..9dbc5abb6162 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -6,19 +6,14 @@ #include <asm/asm-offsets.h> #include <asm/syscall.h> -#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat) +#define __SYSCALL_64_QUAL_(sym) sym +#define __SYSCALL_64_QUAL_ptregs(sym) ptregs_##sym -#ifdef CONFIG_X86_X32_ABI -# define __SYSCALL_X32(nr, sym, compat) __SYSCALL_64(nr, sym, compat) -#else -# define __SYSCALL_X32(nr, sym, compat) /* nothing */ -#endif - -#define __SYSCALL_64(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; +#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long __SYSCALL_64_QUAL_##qual(sym)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #include <asm/syscalls_64.h> #undef __SYSCALL_64 -#define __SYSCALL_64(nr, sym, compat) [nr] = sym, +#define __SYSCALL_64(nr, sym, qual) [nr] = __SYSCALL_64_QUAL_##qual(sym), extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 314a90bfc09c..aa51cdd2a11a 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -21,7 +21,7 @@ 12 common brk sys_brk 13 64 rt_sigaction sys_rt_sigaction 14 common rt_sigprocmask sys_rt_sigprocmask -15 64 rt_sigreturn stub_rt_sigreturn +15 64 rt_sigreturn stub_rt_sigreturn/ptregs 16 64 ioctl sys_ioctl 17 common pread64 sys_pread64 18 common pwrite64 sys_pwrite64 @@ -62,10 +62,10 @@ 53 common socketpair sys_socketpair 54 64 setsockopt sys_setsockopt 55 64 getsockopt sys_getsockopt -56 common clone stub_clone -57 common fork stub_fork -58 common vfork stub_vfork -59 64 execve stub_execve +56 common clone stub_clone/ptregs +57 common fork stub_fork/ptregs +58 common vfork stub_vfork/ptregs +59 64 execve stub_execve/ptregs 60 common exit sys_exit 61 common wait4 sys_wait4 62 common kill sys_kill @@ -328,7 +328,7 @@ 319 common memfd_create sys_memfd_create 320 common kexec_file_load sys_kexec_file_load 321 common bpf sys_bpf -322 64 execveat stub_execveat +322 64 execveat stub_execveat/ptregs 323 common userfaultfd sys_userfaultfd 324 common membarrier sys_membarrier 325 common mlock2 sys_mlock2 @@ -345,7 +345,7 @@ 517 x32 recvfrom compat_sys_recvfrom 518 x32 sendmsg compat_sys_sendmsg 519 x32 recvmsg compat_sys_recvmsg -520 x32 execve stub_x32_execve +520 x32 execve stub_x32_execve/ptregs 521 x32 ptrace compat_sys_ptrace 522 x32 rt_sigpending compat_sys_rt_sigpending 523 x32 rt_sigtimedwait compat_sys_rt_sigtimedwait @@ -370,4 +370,4 @@ 542 x32 getsockopt compat_sys_getsockopt 543 x32 io_setup compat_sys_io_setup 544 x32 io_submit compat_sys_io_submit -545 x32 execveat stub_x32_execveat +545 x32 execveat stub_x32_execveat/ptregs diff --git a/arch/x86/entry/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh index 0e7f8ec071e7..cd3d3015d7df 100644 --- a/arch/x86/entry/syscalls/syscalltbl.sh +++ b/arch/x86/entry/syscalls/syscalltbl.sh @@ -3,13 +3,63 @@ in="$1" out="$2" +syscall_macro() { + abi="$1" + nr="$2" + entry="$3" + + # Entry can be either just a function name or "function/qualifier" + real_entry="${entry%%/*}" + qualifier="${entry:${#real_entry}}" # Strip the function name + qualifier="${qualifier:1}" # Strip the slash, if any + + echo "__SYSCALL_${abi}($nr, $real_entry, $qualifier)" +} + +emit() { + abi="$1" + nr="$2" + entry="$3" + compat="$4" + + if [ "$abi" == "64" -a -n "$compat" ]; then + echo "a compat entry for a 64-bit syscall makes no sense" >&2 + exit 1 + fi + + if [ -z "$compat" ]; then + if [ -n "$entry" ]; then + syscall_macro "$abi" "$nr" "$entry" + fi + else + echo "#ifdef CONFIG_X86_32" + if [ -n "$entry" ]; then + syscall_macro "$abi" "$nr" "$entry" + fi + echo "#else" + syscall_macro "$abi" "$nr" "$compat" + echo "#endif" + fi +} + grep '^[0-9]' "$in" | sort -n | ( while read nr abi name entry compat; do abi=`echo "$abi" | tr '[a-z]' '[A-Z]'` - if [ -n "$compat" ]; then - echo "__SYSCALL_${abi}($nr, $entry, $compat)" - elif [ -n "$entry" ]; then - echo "__SYSCALL_${abi}($nr, $entry, $entry)" + if [ "$abi" == "COMMON" -o "$abi" == "64" ]; then + # COMMON is the same as 64, except that we don't expect X32 + # programs to use it. Our expectation has nothing to do with + # any generated code, so treat them the same. + emit 64 "$nr" "$entry" "$compat" + elif [ "$abi" == "X32" ]; then + # X32 is equivalent to 64 on an X32-compatible kernel. + echo "#ifdef CONFIG_X86_X32_ABI" + emit 64 "$nr" "$entry" "$compat" + echo "#endif" + elif [ "$abi" == "I386" ]; then + emit "$abi" "$nr" "$entry" "$compat" + else + echo "Unknown abi $abi" >&2 + exit 1 fi done ) > "$out" diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 2d359991a273..8054f25d9b42 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -213,7 +213,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) */ regs->orig_ax = syscall_nr; regs->ax = -ENOSYS; - tmp = secure_computing(); + tmp = secure_computing(NULL); if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { warn_bad_vsyscall(KERN_DEBUG, regs, "seccomp tried to change syscall nr or ip"); |