From 5e2aad2460bd38d0777052486893b32902efcdcd Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Mon, 22 Jun 2015 07:55:18 -0400 Subject: x86/compat: Remove unneeded #include Including sys_ia32.h is not needed in signal.c. Signed-off-by: Brian Gerst Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1434974121-32575-10-git-send-email-brgerst@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/signal.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86/kernel/signal.c') diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 206996c1669d..6c22aad8b909 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -35,7 +35,6 @@ #ifdef CONFIG_X86_64 #include #include -#include #endif /* CONFIG_X86_64 */ #include -- cgit v1.2.3 From 1f484aa6904697f390027c12fba130fa94b20831 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Fri, 3 Jul 2015 12:44:23 -0700 Subject: x86/entry: Move C entry and exit code to arch/x86/entry/common.c The entry and exit C helpers were confusingly scattered between ptrace.c and signal.c, even though they aren't specific to ptrace or signal handling. Move them together in a new file. This change just moves code around. It doesn't change anything. Signed-off-by: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: Denys Vlasenko Cc: Frederic Weisbecker Cc: H. Peter Anvin Cc: Kees Cook Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: paulmck@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/324d686821266544d8572423cc281f961da445f4.1435952415.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/entry/Makefile | 1 + arch/x86/entry/common.c | 253 ++++++++++++++++++++++++++++++++++++++++++ arch/x86/include/asm/signal.h | 1 + arch/x86/kernel/ptrace.c | 202 +-------------------------------- arch/x86/kernel/signal.c | 28 +---- 5 files changed, 257 insertions(+), 228 deletions(-) create mode 100644 arch/x86/entry/common.c (limited to 'arch/x86/kernel/signal.c') diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index 7a144971db79..bd55dedd7614 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -2,6 +2,7 @@ # Makefile for the x86 low level entry code # obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o +obj-y += common.o obj-y += vdso/ obj-y += vsyscall/ diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c new file mode 100644 index 000000000000..917d0c3cb851 --- /dev/null +++ b/arch/x86/entry/common.c @@ -0,0 +1,253 @@ +/* + * common.c - C code for kernel entry and exit + * Copyright (c) 2015 Andrew Lutomirski + * GPL v2 + * + * Based on asm and ptrace code by many authors. The code here originated + * in ptrace.c and signal.c. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#define CREATE_TRACE_POINTS +#include + +static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch) +{ +#ifdef CONFIG_X86_64 + if (arch == AUDIT_ARCH_X86_64) { + audit_syscall_entry(regs->orig_ax, regs->di, + regs->si, regs->dx, regs->r10); + } else +#endif + { + audit_syscall_entry(regs->orig_ax, regs->bx, + regs->cx, regs->dx, regs->si); + } +} + +/* + * 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 + */ +unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch) +{ + unsigned long ret = 0; + u32 work; + + BUG_ON(regs != task_pt_regs(current)); + + work = ACCESS_ONCE(current_thread_info()->flags) & + _TIF_WORK_SYSCALL_ENTRY; + + /* + * If TIF_NOHZ is set, we are required to call user_exit() before + * doing anything that could touch RCU. + */ + if (work & _TIF_NOHZ) { + user_exit(); + work &= ~_TIF_NOHZ; + } + +#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. + */ + if (work & _TIF_SECCOMP) { + struct seccomp_data sd; + + sd.arch = arch; + sd.nr = regs->orig_ax; + sd.instruction_pointer = regs->ip; +#ifdef CONFIG_X86_64 + if (arch == AUDIT_ARCH_X86_64) { + sd.args[0] = regs->di; + sd.args[1] = regs->si; + sd.args[2] = regs->dx; + sd.args[3] = regs->r10; + sd.args[4] = regs->r8; + sd.args[5] = regs->r9; + } else +#endif + { + sd.args[0] = regs->bx; + sd.args[1] = regs->cx; + sd.args[2] = regs->dx; + sd.args[3] = regs->si; + sd.args[4] = regs->di; + 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) +{ + long ret = 0; + u32 work = ACCESS_ONCE(current_thread_info()->flags) & + _TIF_WORK_SYSCALL_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; + } +#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); + + do_audit_syscall_entry(regs, 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); +} + +void syscall_trace_leave(struct pt_regs *regs) +{ + bool step; + + /* + * We may come here right after calling schedule_user() + * or do_notify_resume(), in which case we can be in RCU + * user mode. + */ + user_exit(); + + audit_syscall_exit(regs); + + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) + trace_sys_exit(regs, regs->ax); + + /* + * If TIF_SYSCALL_EMU is set, we only get here because of + * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP). + * We already reported this syscall instruction in + * syscall_trace_enter(). + */ + step = unlikely(test_thread_flag(TIF_SINGLESTEP)) && + !test_thread_flag(TIF_SYSCALL_EMU); + if (step || test_thread_flag(TIF_SYSCALL_TRACE)) + tracehook_report_syscall_exit(regs, step); + + user_enter(); +} + +/* + * notification of userspace execution resumption + * - triggered by the TIF_WORK_MASK flags + */ +__visible void +do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) +{ + user_exit(); + + if (thread_info_flags & _TIF_UPROBE) + uprobe_notify_resume(regs); + + /* deal with pending signal delivery */ + if (thread_info_flags & _TIF_SIGPENDING) + do_signal(regs); + + if (thread_info_flags & _TIF_NOTIFY_RESUME) { + clear_thread_flag(TIF_NOTIFY_RESUME); + tracehook_notify_resume(regs); + } + if (thread_info_flags & _TIF_USER_RETURN_NOTIFY) + fire_user_return_notifiers(); + + user_enter(); +} diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 31eab867e6d3..b42408bcf6b5 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -30,6 +30,7 @@ typedef sigset_t compat_sigset_t; #endif /* __ASSEMBLY__ */ #include #ifndef __ASSEMBLY__ +extern void do_signal(struct pt_regs *regs); extern void do_notify_resume(struct pt_regs *, void *, __u32); #define __ARCH_HAS_SA_RESTORER diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 7155957b3c25..558f50edebca 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -37,12 +37,10 @@ #include #include #include +#include #include "tls.h" -#define CREATE_TRACE_POINTS -#include - enum x86_regset { REGSET_GENERAL, REGSET_FP, @@ -1444,201 +1442,3 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, /* Send us the fake SIGTRAP */ force_sig_info(SIGTRAP, &info, tsk); } - -static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch) -{ -#ifdef CONFIG_X86_64 - if (arch == AUDIT_ARCH_X86_64) { - audit_syscall_entry(regs->orig_ax, regs->di, - regs->si, regs->dx, regs->r10); - } else -#endif - { - audit_syscall_entry(regs->orig_ax, regs->bx, - regs->cx, regs->dx, regs->si); - } -} - -/* - * 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 - */ -unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch) -{ - unsigned long ret = 0; - u32 work; - - BUG_ON(regs != task_pt_regs(current)); - - work = ACCESS_ONCE(current_thread_info()->flags) & - _TIF_WORK_SYSCALL_ENTRY; - - /* - * If TIF_NOHZ is set, we are required to call user_exit() before - * doing anything that could touch RCU. - */ - if (work & _TIF_NOHZ) { - user_exit(); - work &= ~_TIF_NOHZ; - } - -#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. - */ - if (work & _TIF_SECCOMP) { - struct seccomp_data sd; - - sd.arch = arch; - sd.nr = regs->orig_ax; - sd.instruction_pointer = regs->ip; -#ifdef CONFIG_X86_64 - if (arch == AUDIT_ARCH_X86_64) { - sd.args[0] = regs->di; - sd.args[1] = regs->si; - sd.args[2] = regs->dx; - sd.args[3] = regs->r10; - sd.args[4] = regs->r8; - sd.args[5] = regs->r9; - } else -#endif - { - sd.args[0] = regs->bx; - sd.args[1] = regs->cx; - sd.args[2] = regs->dx; - sd.args[3] = regs->si; - sd.args[4] = regs->di; - 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) -{ - long ret = 0; - u32 work = ACCESS_ONCE(current_thread_info()->flags) & - _TIF_WORK_SYSCALL_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; - } -#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); - - do_audit_syscall_entry(regs, 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); -} - -void syscall_trace_leave(struct pt_regs *regs) -{ - bool step; - - /* - * We may come here right after calling schedule_user() - * or do_notify_resume(), in which case we can be in RCU - * user mode. - */ - user_exit(); - - audit_syscall_exit(regs); - - if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) - trace_sys_exit(regs, regs->ax); - - /* - * If TIF_SYSCALL_EMU is set, we only get here because of - * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP). - * We already reported this syscall instruction in - * syscall_trace_enter(). - */ - step = unlikely(test_thread_flag(TIF_SINGLESTEP)) && - !test_thread_flag(TIF_SYSCALL_EMU); - if (step || test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, step); - - user_enter(); -} diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 6c22aad8b909..7e88cc782712 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -700,7 +700,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ -static void do_signal(struct pt_regs *regs) +void do_signal(struct pt_regs *regs) { struct ksignal ksig; @@ -735,32 +735,6 @@ static void do_signal(struct pt_regs *regs) restore_saved_sigmask(); } -/* - * notification of userspace execution resumption - * - triggered by the TIF_WORK_MASK flags - */ -__visible void -do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) -{ - user_exit(); - - if (thread_info_flags & _TIF_UPROBE) - uprobe_notify_resume(regs); - - /* deal with pending signal delivery */ - if (thread_info_flags & _TIF_SIGPENDING) - do_signal(regs); - - if (thread_info_flags & _TIF_NOTIFY_RESUME) { - clear_thread_flag(TIF_NOTIFY_RESUME); - tracehook_notify_resume(regs); - } - if (thread_info_flags & _TIF_USER_RETURN_NOTIFY) - fire_user_return_notifiers(); - - user_enter(); -} - void signal_fault(struct pt_regs *regs, void __user *frame, char *where) { struct task_struct *me = current; -- cgit v1.2.3 From 5ed92a8ab71f8865ba07811429c988c72299b315 Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Wed, 29 Jul 2015 01:41:19 -0400 Subject: x86/vm86: Use the normal pt_regs area for vm86 Change to use the normal pt_regs area to enter and exit vm86 mode. This is done by increasing the padding at the top of the stack to make room for the extra vm86 segment slots in the IRET frame. It then saves the 32-bit regs in the off-stack vm86 data, and copies in the vm86 regs. Exiting back to 32-bit mode does the reverse. This allows removing the hacks to jump directly into the exit asm code due to having to change the stack pointer. Returning normally from the vm86 syscall and the exception handlers allows things like ptrace and auditing to work properly. Signed-off-by: Brian Gerst Acked-by: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1438148483-11932-5-git-send-email-brgerst@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_32.S | 24 +------- arch/x86/include/asm/thread_info.h | 11 ++-- arch/x86/include/asm/vm86.h | 6 +- arch/x86/kernel/signal.c | 3 + arch/x86/kernel/vm86_32.c | 110 +++++++++++++++---------------------- 5 files changed, 60 insertions(+), 94 deletions(-) (limited to 'arch/x86/kernel/signal.c') diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 21dc60a60b5f..f940e24acaf0 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -525,34 +525,12 @@ work_resched: work_notifysig: # deal with pending signals and # notify-resume requests -#ifdef CONFIG_VM86 - testl $X86_EFLAGS_VM, PT_EFLAGS(%esp) - movl %esp, %eax - jnz work_notifysig_v86 # returning to kernel-space or - # vm86-space -1: -#else - movl %esp, %eax -#endif TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) - movb PT_CS(%esp), %bl - andb $SEGMENT_RPL_MASK, %bl - cmpb $USER_RPL, %bl - jb resume_kernel + movl %esp, %eax xorl %edx, %edx call do_notify_resume jmp resume_userspace - -#ifdef CONFIG_VM86 - ALIGN -work_notifysig_v86: - pushl %ecx # save ti_flags for do_notify_resume - call save_v86_state # %eax contains pt_regs pointer - popl %ecx - movl %eax, %esp - jmp 1b -#endif END(work_pending) # perform syscall exit tracing diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 225ee545e1a0..fdad5c244350 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -27,14 +27,17 @@ * Without this offset, that can result in a page fault. (We are * careful that, in this case, the value we read doesn't matter.) * - * In vm86 mode, the hardware frame is much longer still, but we neither - * access the extra members from NMI context, nor do we write such a - * frame at sp0 at all. + * In vm86 mode, the hardware frame is much longer still, so add 16 + * bytes to make room for the real-mode segments. * * x86_64 has a fixed-length stack frame. */ #ifdef CONFIG_X86_32 -# define TOP_OF_KERNEL_STACK_PADDING 8 +# ifdef CONFIG_VM86 +# define TOP_OF_KERNEL_STACK_PADDING 16 +# else +# define TOP_OF_KERNEL_STACK_PADDING 8 +# endif #else # define TOP_OF_KERNEL_STACK_PADDING 0 #endif diff --git a/arch/x86/include/asm/vm86.h b/arch/x86/include/asm/vm86.h index 226d6c157ebc..e45386eee17a 100644 --- a/arch/x86/include/asm/vm86.h +++ b/arch/x86/include/asm/vm86.h @@ -29,7 +29,7 @@ struct kernel_vm86_regs { struct vm86 { struct vm86plus_struct __user *vm86_info; - struct pt_regs *regs32; + struct pt_regs regs32; unsigned long v86flags; unsigned long v86mask; unsigned long saved_sp0; @@ -46,7 +46,7 @@ struct vm86 { void handle_vm86_fault(struct kernel_vm86_regs *, long); int handle_vm86_trap(struct kernel_vm86_regs *, long, int); -struct pt_regs *save_v86_state(struct kernel_vm86_regs *); +void save_v86_state(struct kernel_vm86_regs *, int); struct task_struct; void release_vm86_irqs(struct task_struct *); @@ -69,6 +69,8 @@ static inline int handle_vm86_trap(struct kernel_vm86_regs *a, long b, int c) return 0; } +static inline void save_v86_state(struct kernel_vm86_regs *a, int b) { } + #define free_vm86(t) do { } while(0) #endif /* CONFIG_VM86 */ diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 7e88cc782712..bfd736e80c89 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -635,6 +635,9 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) bool stepping, failed; struct fpu *fpu = ¤t->thread.fpu; + if (v8086_mode(regs)) + save_v86_state((struct kernel_vm86_regs *) regs, VM86_SIGNAL); + /* Are we from a system call? */ if (syscall_get_nr(current, regs) >= 0) { /* If so, check system call restarting.. */ diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 696ef767f2be..ffe98eceda77 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -50,6 +50,7 @@ #include #include #include +#include /* * Known problems: @@ -87,10 +88,9 @@ #define SAFE_MASK (0xDD5) #define RETURN_MASK (0xDFF) -struct pt_regs *save_v86_state(struct kernel_vm86_regs *regs) +void save_v86_state(struct kernel_vm86_regs *regs, int retval) { struct tss_struct *tss; - struct pt_regs *ret; struct task_struct *tsk = current; struct vm86plus_struct __user *user; struct vm86 *vm86 = current->thread.vm86; @@ -149,11 +149,11 @@ struct pt_regs *save_v86_state(struct kernel_vm86_regs *regs) vm86->saved_sp0 = 0; put_cpu(); - ret = vm86->regs32; + memcpy(®s->pt, &vm86->regs32, sizeof(struct pt_regs)); - lazy_load_gs(ret->gs); + lazy_load_gs(vm86->regs32.gs); - return ret; + regs->pt.ax = retval; } static void mark_screen_rdonly(struct mm_struct *mm) @@ -228,7 +228,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *v86, bool plus) struct task_struct *tsk = current; struct vm86 *vm86 = tsk->thread.vm86; struct kernel_vm86_regs vm86regs; - struct pt_regs *regs32 = current_pt_regs(); + struct pt_regs *regs = current_pt_regs(); unsigned long err = 0; if (!vm86) { @@ -287,7 +287,8 @@ static long do_sys_vm86(struct vm86plus_struct __user *v86, bool plus) } else memset(&vm86->vm86plus, 0, sizeof(struct vm86plus_info_struct)); - vm86->regs32 = regs32; + + memcpy(&vm86->regs32, regs, sizeof(struct pt_regs)); vm86->vm86_info = v86; /* @@ -297,10 +298,10 @@ static long do_sys_vm86(struct vm86plus_struct __user *v86, bool plus) */ VEFLAGS = vm86regs.pt.flags; vm86regs.pt.flags &= SAFE_MASK; - vm86regs.pt.flags |= regs32->flags & ~SAFE_MASK; + vm86regs.pt.flags |= regs->flags & ~SAFE_MASK; vm86regs.pt.flags |= X86_VM_MASK; - vm86regs.pt.orig_ax = regs32->orig_ax; + vm86regs.pt.orig_ax = regs->orig_ax; switch (vm86->cpu_type) { case CPU_286: @@ -318,15 +319,14 @@ static long do_sys_vm86(struct vm86plus_struct __user *v86, bool plus) } /* - * Save old state, set default return value (%ax) to 0 (VM86_SIGNAL) + * Save old state */ - regs32->ax = VM86_SIGNAL; vm86->saved_sp0 = tsk->thread.sp0; - lazy_save_gs(regs32->gs); + lazy_save_gs(vm86->regs32.gs); tss = &per_cpu(cpu_tss, get_cpu()); - /* Set new sp0 right below 32-bit regs */ - tsk->thread.sp0 = (unsigned long) regs32; + /* make room for real-mode segments */ + tsk->thread.sp0 += 16; if (cpu_has_sep) tsk->thread.sysenter_cs = 0; load_sp0(tss, &tsk->thread); @@ -335,41 +335,14 @@ static long do_sys_vm86(struct vm86plus_struct __user *v86, bool plus) if (vm86->flags & VM86_SCREEN_BITMAP) mark_screen_rdonly(tsk->mm); - /*call __audit_syscall_exit since we do not exit via the normal paths */ -#ifdef CONFIG_AUDITSYSCALL - if (unlikely(current->audit_context)) - __audit_syscall_exit(1, 0); -#endif - - __asm__ __volatile__( - "movl %0,%%esp\n\t" - "movl %1,%%ebp\n\t" -#ifdef CONFIG_X86_32_LAZY_GS - "mov %2, %%gs\n\t" -#endif - "jmp resume_userspace" - : /* no outputs */ - :"r" (&vm86regs), "r" (task_thread_info(tsk)), "r" (0)); - unreachable(); /* we never return here */ -} - -static inline void return_to_32bit(struct kernel_vm86_regs *regs16, int retval) -{ - struct pt_regs *regs32; - - regs32 = save_v86_state(regs16); - regs32->ax = retval; - __asm__ __volatile__("movl %0,%%esp\n\t" - "movl %1,%%ebp\n\t" - "jmp resume_userspace" - : : "r" (regs32), "r" (current_thread_info())); + memcpy((struct kernel_vm86_regs *)regs, &vm86regs, sizeof(vm86regs)); + force_iret(); + return regs->ax; } static inline void set_IF(struct kernel_vm86_regs *regs) { VEFLAGS |= X86_EFLAGS_VIF; - if (VEFLAGS & X86_EFLAGS_VIP) - return_to_32bit(regs, VM86_STI); } static inline void clear_IF(struct kernel_vm86_regs *regs) @@ -549,7 +522,7 @@ static void do_int(struct kernel_vm86_regs *regs, int i, return; cannot_handle: - return_to_32bit(regs, VM86_INTx + (i << 8)); + save_v86_state(regs, VM86_INTx + (i << 8)); } int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno) @@ -558,11 +531,7 @@ int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno) if (vm86->vm86plus.is_vm86pus) { if ((trapno == 3) || (trapno == 1)) { - vm86->regs32->ax = VM86_TRAP + (trapno << 8); - /* setting this flag forces the code in entry_32.S to - the path where we call save_v86_state() and change - the stack pointer to regs32 */ - set_thread_flag(TIF_NOTIFY_RESUME); + save_v86_state(regs, VM86_TRAP + (trapno << 8)); return 0; } do_int(regs, trapno, (unsigned char __user *) (regs->pt.ss << 4), SP(regs)); @@ -588,12 +557,6 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) #define CHECK_IF_IN_TRAP \ if (vmpi->vm86dbg_active && vmpi->vm86dbg_TFpendig) \ newflags |= X86_EFLAGS_TF -#define VM86_FAULT_RETURN do { \ - if (vmpi->force_return_for_pic && (VEFLAGS & (X86_EFLAGS_IF | X86_EFLAGS_VIF))) \ - return_to_32bit(regs, VM86_PICRETURN); \ - if (orig_flags & X86_EFLAGS_TF) \ - handle_vm86_trap(regs, 0, 1); \ - return; } while (0) orig_flags = *(unsigned short *)®s->pt.flags; @@ -632,7 +595,7 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) SP(regs) -= 2; } IP(regs) = ip; - VM86_FAULT_RETURN; + goto vm86_fault_return; /* popf */ case 0x9d: @@ -652,7 +615,7 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) else set_vflags_short(newflags, regs); - VM86_FAULT_RETURN; + goto check_vip; } /* int xx */ @@ -660,8 +623,10 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) int intno = popb(csp, ip, simulate_sigsegv); IP(regs) = ip; if (vmpi->vm86dbg_active) { - if ((1 << (intno & 7)) & vmpi->vm86dbg_intxxtab[intno >> 3]) - return_to_32bit(regs, VM86_INTx + (intno << 8)); + if ((1 << (intno & 7)) & vmpi->vm86dbg_intxxtab[intno >> 3]) { + save_v86_state(regs, VM86_INTx + (intno << 8)); + return; + } } do_int(regs, intno, ssp, sp); return; @@ -692,14 +657,14 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) } else { set_vflags_short(newflags, regs); } - VM86_FAULT_RETURN; + goto check_vip; } /* cli */ case 0xfa: IP(regs) = ip; clear_IF(regs); - VM86_FAULT_RETURN; + goto vm86_fault_return; /* sti */ /* @@ -711,12 +676,27 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) case 0xfb: IP(regs) = ip; set_IF(regs); - VM86_FAULT_RETURN; + goto check_vip; default: - return_to_32bit(regs, VM86_UNKNOWN); + save_v86_state(regs, VM86_UNKNOWN); + } + + return; + +check_vip: + if (VEFLAGS & X86_EFLAGS_VIP) { + save_v86_state(regs, VM86_STI); + return; } +vm86_fault_return: + if (vmpi->force_return_for_pic && (VEFLAGS & (X86_EFLAGS_IF | X86_EFLAGS_VIF))) { + save_v86_state(regs, VM86_PICRETURN); + return; + } + if (orig_flags & X86_EFLAGS_TF) + handle_vm86_trap(regs, 0, X86_TRAP_DB); return; simulate_sigsegv: @@ -730,7 +710,7 @@ simulate_sigsegv: * should be a mixture of the two, but how do we * get the information? [KD] */ - return_to_32bit(regs, VM86_UNKNOWN); + save_v86_state(regs, VM86_UNKNOWN); } /* ---------------- vm86 special IRQ passing stuff ----------------- */ -- cgit v1.2.3 From ba3e127ec105e790eeec4034d9769e018e4a1b54 Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Wed, 29 Jul 2015 01:41:21 -0400 Subject: x86/vm86: Clean up vm86.h includes vm86.h was being implicitly included in alot of places via processor.h, which in turn got it from math_emu.h. Break that chain and explicitly include vm86.h in all files that need it. Also remove unused vm86 field from math_emu_info. Signed-off-by: Brian Gerst Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1438148483-11932-7-git-send-email-brgerst@gmail.com [ Fixed build failure. ] Signed-off-by: Ingo Molnar --- arch/x86/include/asm/math_emu.h | 6 +----- arch/x86/include/asm/syscalls.h | 1 + arch/x86/kernel/process_32.c | 1 + arch/x86/kernel/signal.c | 1 + arch/x86/kernel/traps.c | 1 + arch/x86/kernel/vm86_32.c | 1 + arch/x86/math-emu/get_address.c | 1 + arch/x86/mm/fault.c | 1 + drivers/scsi/dpt_i2o.c | 3 +++ 9 files changed, 11 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel/signal.c') diff --git a/arch/x86/include/asm/math_emu.h b/arch/x86/include/asm/math_emu.h index 031f6266f425..0d9b14f60d2c 100644 --- a/arch/x86/include/asm/math_emu.h +++ b/arch/x86/include/asm/math_emu.h @@ -2,7 +2,6 @@ #define _ASM_X86_MATH_EMU_H #include -#include /* This structure matches the layout of the data saved to the stack following a device-not-present interrupt, part of it saved @@ -10,9 +9,6 @@ */ struct math_emu_info { long ___orig_eip; - union { - struct pt_regs *regs; - struct kernel_vm86_regs *vm86; - }; + struct pt_regs *regs; }; #endif /* _ASM_X86_MATH_EMU_H */ diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 592a6a672e07..91dfcafe27a6 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -37,6 +37,7 @@ asmlinkage long sys_get_thread_area(struct user_desc __user *); asmlinkage unsigned long sys_sigreturn(void); /* kernel/vm86_32.c */ +struct vm86_struct; asmlinkage long sys_vm86old(struct vm86_struct __user *); asmlinkage long sys_vm86(unsigned long, unsigned long); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index f73c962fe636..c13df2c735f8 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -53,6 +53,7 @@ #include #include #include +#include asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread"); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index bfd736e80c89..07eb84407036 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -31,6 +31,7 @@ #include #include #include +#include #ifdef CONFIG_X86_64 #include diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 8e65d8a9b8db..86a82eafb96f 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -62,6 +62,7 @@ #include #include #include +#include #ifdef CONFIG_X86_64 #include diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index ffe98eceda77..0de1f66ad001 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -51,6 +51,7 @@ #include #include #include +#include /* * Known problems: diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c index 6ef5e99380f9..a2eefb121a5f 100644 --- a/arch/x86/math-emu/get_address.c +++ b/arch/x86/math-emu/get_address.c @@ -21,6 +21,7 @@ #include #include +#include #include "fpu_system.h" #include "exception.h" diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 34a368d2d533..eef44d9a3f77 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -20,6 +20,7 @@ #include /* kmemcheck_*(), ... */ #include /* VSYSCALL_ADDR */ #include /* emulate_vsyscall */ +#include /* struct vm86 */ #define CREATE_TRACE_POINTS #include diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c index f35ed53adaac..d4cda5e9600e 100644 --- a/drivers/scsi/dpt_i2o.c +++ b/drivers/scsi/dpt_i2o.c @@ -1924,6 +1924,9 @@ static void adpt_alpha_info(sysInfo_S* si) #endif #if defined __i386__ + +#include + static void adpt_i386_info(sysInfo_S* si) { // This is all the info we need for now -- cgit v1.2.3