diff options
Diffstat (limited to 'arch')
77 files changed, 1143 insertions, 1279 deletions
diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h index 83a91f976330..35ab97e4bb9b 100644 --- a/arch/um/include/shared/kern_util.h +++ b/arch/um/include/shared/kern_util.h @@ -22,7 +22,8 @@ extern int kmalloc_ok; extern unsigned long alloc_stack(int order, int atomic); extern void free_stack(unsigned long stack, int order); -extern int do_signal(void); +struct pt_regs; +extern void do_signal(struct pt_regs *regs); extern void interrupt_end(void); extern void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs); diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 68b9119841cd..a6d922672b9f 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -90,12 +90,14 @@ void *__switch_to(struct task_struct *from, struct task_struct *to) void interrupt_end(void) { + struct pt_regs *regs = ¤t->thread.regs; + if (need_resched()) schedule(); if (test_thread_flag(TIF_SIGPENDING)) - do_signal(); + do_signal(regs); if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME)) - tracehook_notify_resume(¤t->thread.regs); + tracehook_notify_resume(regs); } void exit_thread(void) diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c index 4f60e4aad790..57acbd67d85d 100644 --- a/arch/um/kernel/signal.c +++ b/arch/um/kernel/signal.c @@ -64,7 +64,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) signal_setup_done(err, ksig, singlestep); } -static int kern_do_signal(struct pt_regs *regs) +void do_signal(struct pt_regs *regs) { struct ksignal ksig; int handled_sig = 0; @@ -110,10 +110,4 @@ static int kern_do_signal(struct pt_regs *regs) */ if (!handled_sig) restore_saved_sigmask(); - return handled_sig; -} - -int do_signal(void) -{ - return kern_do_signal(¤t->thread.regs); } diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c index f1b3eb14b855..2077248e8a72 100644 --- a/arch/um/kernel/tlb.c +++ b/arch/um/kernel/tlb.c @@ -291,7 +291,7 @@ void fix_range_common(struct mm_struct *mm, unsigned long start_addr, /* We are under mmap_sem, release it such that current can terminate */ up_write(¤t->mm->mmap_sem); force_sig(SIGKILL, current); - do_signal(); + do_signal(¤t->thread.regs); } } diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 557232f758b6..d8a9fce6ee2e 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -173,7 +173,7 @@ static void bad_segv(struct faultinfo fi, unsigned long ip) void fatal_sigsegv(void) { force_sigsegv(SIGSEGV, current); - do_signal(); + do_signal(¤t->thread.regs); /* * This is to tell gcc that we're not returning - do_signal * can, in general, return, but in this case, it's not, since diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b3a1a5d77d92..798658048db3 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -133,7 +133,7 @@ config X86 select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_SYSCALL_TRACEPOINTS - select HAVE_UID16 if X86_32 + select HAVE_UID16 if X86_32 || IA32_EMULATION select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_USER_RETURN_NOTIFIER select IRQ_FORCED_THREADING @@ -1002,19 +1002,41 @@ config X86_THERMAL_VECTOR def_bool y depends on X86_MCE_INTEL -config VM86 - bool "Enable VM86 support" if EXPERT - default y +config X86_LEGACY_VM86 + bool "Legacy VM86 support (obsolete)" + default n depends on X86_32 ---help--- - This option is required by programs like DOSEMU to run - 16-bit real mode legacy code on x86 processors. It also may - be needed by software like XFree86 to initialize some video - cards via BIOS. Disabling this option saves about 6K. + This option allows user programs to put the CPU into V8086 + mode, which is an 80286-era approximation of 16-bit real mode. + + Some very old versions of X and/or vbetool require this option + for user mode setting. Similarly, DOSEMU will use it if + available to accelerate real mode DOS programs. However, any + recent version of DOSEMU, X, or vbetool should be fully + functional even without kernel VM86 support, as they will all + fall back to (pretty well performing) software emulation. + + Anything that works on a 64-bit kernel is unlikely to need + this option, as 64-bit kernels don't, and can't, support V8086 + mode. This option is also unrelated to 16-bit protected mode + and is not needed to run most 16-bit programs under Wine. + + Enabling this option adds considerable attack surface to the + kernel and slows down system calls and exception handling. + + Unless you use very old userspace or need the last drop of + performance in your real mode DOS games and can't use KVM, + say N here. + +config VM86 + bool + default X86_LEGACY_VM86 config X86_16BIT bool "Enable support for 16-bit segments" if EXPERT default y + depends on MODIFY_LDT_SYSCALL ---help--- This option is required by programs like Wine to run 16-bit protected mode legacy code on x86 processors. Disabling @@ -1509,6 +1531,7 @@ config X86_RESERVE_LOW config MATH_EMULATION bool + depends on MODIFY_LDT_SYSCALL prompt "Math emulation" if X86_32 ---help--- Linux can emulate a math coprocessor (used for floating point @@ -2053,6 +2076,22 @@ config CMDLINE_OVERRIDE This is used to work around broken boot loaders. This should be set to 'N' under normal conditions. +config MODIFY_LDT_SYSCALL + bool "Enable the LDT (local descriptor table)" if EXPERT + default y + ---help--- + Linux can allow user programs to install a per-process x86 + Local Descriptor Table (LDT) using the modify_ldt(2) system + call. This is required to run 16-bit or segmented code such as + DOSEMU or some Wine programs. It is also used by some very old + threading libraries. + + Enabling this feature adds a small amount of overhead to + context switches and increases the low-level kernel attack + surface. Disabling it removes the modify_ldt(2) system call. + + Saying 'N' here may make sense for embedded or server kernels. + source "kernel/livepatch/Kconfig" endmenu @@ -2522,7 +2561,7 @@ config IA32_EMULATION depends on X86_64 select BINFMT_ELF select COMPAT_BINFMT_ELF - select HAVE_UID16 + select ARCH_WANT_OLD_COMPAT_IPC ---help--- Include code to run legacy 32-bit programs under a 64-bit kernel. You should likely turn this on, unless you're @@ -2536,7 +2575,7 @@ config IA32_AOUT config X86_X32 bool "x32 ABI for 64-bit mode" - depends on X86_64 && IA32_EMULATION + depends on X86_64 ---help--- Include code to run binaries for the x32 native 32-bit ABI for 64-bit processors. An x32 process gets access to the @@ -2550,7 +2589,6 @@ config X86_X32 config COMPAT def_bool y depends on IA32_EMULATION || X86_X32 - select ARCH_WANT_OLD_COMPAT_IPC if COMPAT config COMPAT_FOR_U64_ALIGNMENT diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 118e6debc483..054ff969fcdb 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -39,6 +39,16 @@ ifdef CONFIG_X86_NEED_RELOCS LDFLAGS_vmlinux := --emit-relocs endif +# +# Prevent GCC from generating any FP code by mistake. +# +# This must happen before we try the -mpreferred-stack-boundary, see: +# +# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383 +# +KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow +KBUILD_CFLAGS += $(call cc-option,-mno-avx,) + ifeq ($(CONFIG_X86_32),y) BITS := 32 UTS_MACHINE := i386 @@ -167,9 +177,6 @@ KBUILD_CFLAGS += -pipe KBUILD_CFLAGS += -Wno-sign-compare # KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -# prevent gcc from generating any FP code by mistake -KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -KBUILD_CFLAGS += $(call cc-option,-mno-avx,) KBUILD_CFLAGS += $(mflags-y) KBUILD_AFLAGS += $(mflags-y) diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c index d7b1f655b3ef..6a9b96b4624d 100644 --- a/arch/x86/boot/compressed/aslr.c +++ b/arch/x86/boot/compressed/aslr.c @@ -82,7 +82,7 @@ static unsigned long get_random_long(void) if (has_cpuflag(X86_FEATURE_TSC)) { debug_putstr(" RDTSC"); - rdtscll(raw); + raw = rdtsc(); random ^= raw; use_i8254 = false; diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index 7a144971db79..bd55dedd7614 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -2,6 +2,7 @@ # Makefile for the x86 low level entry code # obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o +obj-y += common.o obj-y += vdso/ obj-y += vsyscall/ diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index f4e6308c4200..3c71dd947c7b 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -135,9 +135,6 @@ For 32-bit we have the following conventions - kernel is built with movq %rbp, 4*8+\offset(%rsp) movq %rbx, 5*8+\offset(%rsp) .endm - .macro SAVE_EXTRA_REGS_RBP offset=0 - movq %rbp, 4*8+\offset(%rsp) - .endm .macro RESTORE_EXTRA_REGS offset=0 movq 0*8+\offset(%rsp), %r15 @@ -193,12 +190,6 @@ For 32-bit we have the following conventions - kernel is built with .macro RESTORE_C_REGS_EXCEPT_RCX_R11 RESTORE_C_REGS_HELPER 1,0,0,1,1 .endm - .macro RESTORE_RSI_RDI - RESTORE_C_REGS_HELPER 0,0,0,0,0 - .endm - .macro RESTORE_RSI_RDI_RDX - RESTORE_C_REGS_HELPER 0,0,0,0,1 - .endm .macro REMOVE_PT_GPREGS_FROM_STACK addskip=0 subq $-(15*8+\addskip), %rsp diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c new file mode 100644 index 000000000000..80dcc9261ca3 --- /dev/null +++ b/arch/x86/entry/common.c @@ -0,0 +1,318 @@ +/* + * 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 <linux/kernel.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/errno.h> +#include <linux/ptrace.h> +#include <linux/tracehook.h> +#include <linux/audit.h> +#include <linux/seccomp.h> +#include <linux/signal.h> +#include <linux/export.h> +#include <linux/context_tracking.h> +#include <linux/user-return-notifier.h> +#include <linux/uprobes.h> + +#include <asm/desc.h> +#include <asm/traps.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/syscalls.h> + +#ifdef CONFIG_CONTEXT_TRACKING +/* Called on entry from user mode with IRQs off. */ +__visible void enter_from_user_mode(void) +{ + CT_WARN_ON(ct_state() != CONTEXT_USER); + user_exit(); +} +#endif + +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; + +#ifdef CONFIG_CONTEXT_TRACKING + /* + * If TIF_NOHZ is set, we are required to call user_exit() before + * doing anything that could touch RCU. + */ + if (work & _TIF_NOHZ) { + enter_from_user_mode(); + work &= ~_TIF_NOHZ; + } +#endif + +#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); +} + +static struct thread_info *pt_regs_to_thread_info(struct pt_regs *regs) +{ + unsigned long top_of_stack = + (unsigned long)(regs + 1) + TOP_OF_KERNEL_STACK_PADDING; + return (struct thread_info *)(top_of_stack - THREAD_SIZE); +} + +/* Called with IRQs disabled. */ +__visible void prepare_exit_to_usermode(struct pt_regs *regs) +{ + if (WARN_ON(!irqs_disabled())) + local_irq_disable(); + + /* + * In order to return to user mode, we need to have IRQs off with + * none of _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_USER_RETURN_NOTIFY, + * _TIF_UPROBE, or _TIF_NEED_RESCHED set. Several of these flags + * can be set at any time on preemptable kernels if we have IRQs on, + * so we need to loop. Disabling preemption wouldn't help: doing the + * work to clear some of the flags can sleep. + */ + while (true) { + u32 cached_flags = + READ_ONCE(pt_regs_to_thread_info(regs)->flags); + + if (!(cached_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | + _TIF_UPROBE | _TIF_NEED_RESCHED | + _TIF_USER_RETURN_NOTIFY))) + break; + + /* We have work to do. */ + local_irq_enable(); + + if (cached_flags & _TIF_NEED_RESCHED) + schedule(); + + if (cached_flags & _TIF_UPROBE) + uprobe_notify_resume(regs); + + /* deal with pending signal delivery */ + if (cached_flags & _TIF_SIGPENDING) + do_signal(regs); + + if (cached_flags & _TIF_NOTIFY_RESUME) { + clear_thread_flag(TIF_NOTIFY_RESUME); + tracehook_notify_resume(regs); + } + + if (cached_flags & _TIF_USER_RETURN_NOTIFY) + fire_user_return_notifiers(); + + /* Disable IRQs and retry */ + local_irq_disable(); + } + + user_enter(); +} + +/* + * Called with IRQs on and fully valid regs. Returns with IRQs off in a + * state such that we can immediately switch to user mode. + */ +__visible void syscall_return_slowpath(struct pt_regs *regs) +{ + struct thread_info *ti = pt_regs_to_thread_info(regs); + u32 cached_flags = READ_ONCE(ti->flags); + bool step; + + CT_WARN_ON(ct_state() != CONTEXT_KERNEL); + + if (WARN(irqs_disabled(), "syscall %ld left IRQs disabled", + regs->orig_ax)) + local_irq_enable(); + + /* + * First do one-time work. If these work items are enabled, we + * want to run them exactly once per syscall exit with IRQs on. + */ + if (cached_flags & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | + _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT)) { + audit_syscall_exit(regs); + + if (cached_flags & _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( + (cached_flags & (_TIF_SINGLESTEP | _TIF_SYSCALL_EMU)) + == _TIF_SINGLESTEP); + if (step || cached_flags & _TIF_SYSCALL_TRACE) + tracehook_report_syscall_exit(regs, step); + } + +#ifdef CONFIG_COMPAT + /* + * Compat syscalls set TS_COMPAT. Make sure we clear it before + * returning to user mode. + */ + ti->status &= ~TS_COMPAT; +#endif + + local_irq_disable(); + prepare_exit_to_usermode(regs); +} diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 21dc60a60b5f..b2909bf8cf70 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -45,16 +45,6 @@ #include <asm/asm.h> #include <asm/smap.h> -/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ -#include <linux/elf-em.h> -#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE) -#define __AUDIT_ARCH_LE 0x40000000 - -#ifndef CONFIG_AUDITSYSCALL -# define sysenter_audit syscall_trace_entry -# define sysexit_audit syscall_exit_work -#endif - .section .entry.text, "ax" /* @@ -266,14 +256,10 @@ ret_from_intr: ENTRY(resume_userspace) LOCKDEP_SYS_EXIT - DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt - # setting need_resched or sigpending - # between sampling and the iret + DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - andl $_TIF_WORK_MASK, %ecx # is there any work to be done on - # int/exception return? - jne work_pending + movl %esp, %eax + call prepare_exit_to_usermode jmp restore_all END(ret_from_exception) @@ -339,7 +325,7 @@ sysenter_past_esp: GET_THREAD_INFO(%ebp) testl $_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp) - jnz sysenter_audit + jnz syscall_trace_entry sysenter_do_call: cmpl $(NR_syscalls), %eax jae sysenter_badsys @@ -351,7 +337,7 @@ sysenter_after_call: TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx testl $_TIF_ALLWORK_MASK, %ecx - jnz sysexit_audit + jnz syscall_exit_work_irqs_off sysenter_exit: /* if something modifies registers it must also disable sysexit */ movl PT_EIP(%esp), %edx @@ -362,40 +348,6 @@ sysenter_exit: PTGS_TO_GS ENABLE_INTERRUPTS_SYSEXIT -#ifdef CONFIG_AUDITSYSCALL -sysenter_audit: - testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), TI_flags(%ebp) - jnz syscall_trace_entry - /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */ - movl PT_EBX(%esp), %edx /* ebx/a0: 2nd arg to audit */ - /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */ - pushl PT_ESI(%esp) /* a3: 5th arg */ - pushl PT_EDX+4(%esp) /* a2: 4th arg */ - call __audit_syscall_entry - popl %ecx /* get that remapped edx off the stack */ - popl %ecx /* get that remapped esi off the stack */ - movl PT_EAX(%esp), %eax /* reload syscall number */ - jmp sysenter_do_call - -sysexit_audit: - testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx - jnz syscall_exit_work - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_ANY) - movl %eax, %edx /* second arg, syscall return value */ - cmpl $-MAX_ERRNO, %eax /* is it an error ? */ - setbe %al /* 1 if so, 0 if not */ - movzbl %al, %eax /* zero-extend that */ - call __audit_syscall_exit - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx - jnz syscall_exit_work - movl PT_EAX(%esp), %eax /* reload syscall return value */ - jmp sysenter_exit -#endif - .pushsection .fixup, "ax" 2: movl $0, PT_FS(%esp) jmp 1b @@ -421,13 +373,7 @@ syscall_after_call: movl %eax, PT_EAX(%esp) # store the return value syscall_exit: LOCKDEP_SYS_EXIT - DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt - # setting need_resched or sigpending - # between sampling and the iret - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - testl $_TIF_ALLWORK_MASK, %ecx # current->work - jnz syscall_exit_work + jmp syscall_exit_work restore_all: TRACE_IRQS_IRET @@ -504,57 +450,6 @@ ldt_ss: #endif ENDPROC(entry_INT80_32) - # perform work that needs to be done immediately before resumption - ALIGN -work_pending: - testb $_TIF_NEED_RESCHED, %cl - jz work_notifysig -work_resched: - call schedule - LOCKDEP_SYS_EXIT - DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt - # setting need_resched or sigpending - # between sampling and the iret - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - andl $_TIF_WORK_MASK, %ecx # is there any work to be done other - # than syscall tracing? - jz restore_all - testb $_TIF_NEED_RESCHED, %cl - jnz 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 - 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 ALIGN syscall_trace_entry: @@ -569,15 +464,14 @@ END(syscall_trace_entry) # perform syscall exit tracing ALIGN -syscall_exit_work: - testl $_TIF_WORK_SYSCALL_EXIT, %ecx - jz work_pending +syscall_exit_work_irqs_off: TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_ANY) # could let syscall_trace_leave() call - # schedule() instead + ENABLE_INTERRUPTS(CLBR_ANY) + +syscall_exit_work: movl %esp, %eax - call syscall_trace_leave - jmp resume_userspace + call syscall_return_slowpath + jmp restore_all END(syscall_exit_work) syscall_fault: diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 8cb3e438f21e..d3033183ed70 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -33,7 +33,6 @@ #include <asm/paravirt.h> #include <asm/percpu.h> #include <asm/asm.h> -#include <asm/context_tracking.h> #include <asm/smap.h> #include <asm/pgtable_types.h> #include <linux/err.h> @@ -229,6 +228,11 @@ entry_SYSCALL_64_fastpath: */ USERGS_SYSRET64 +GLOBAL(int_ret_from_sys_call_irqs_off) + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + jmp int_ret_from_sys_call + /* Do syscall entry tracing */ tracesys: movq %rsp, %rdi @@ -272,69 +276,11 @@ tracesys_phase2: * Has correct iret frame. */ GLOBAL(int_ret_from_sys_call) - DISABLE_INTERRUPTS(CLBR_NONE) -int_ret_from_sys_call_irqs_off: /* jumps come here from the irqs-off SYSRET path */ - TRACE_IRQS_OFF - movl $_TIF_ALLWORK_MASK, %edi - /* edi: mask to check */ -GLOBAL(int_with_check) - LOCKDEP_SYS_EXIT_IRQ - GET_THREAD_INFO(%rcx) - movl TI_flags(%rcx), %edx - andl %edi, %edx - jnz int_careful - andl $~TS_COMPAT, TI_status(%rcx) - jmp syscall_return - - /* - * Either reschedule or signal or syscall exit tracking needed. - * First do a reschedule test. - * edx: work, edi: workmask - */ -int_careful: - bt $TIF_NEED_RESCHED, %edx - jnc int_very_careful - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - pushq %rdi - SCHEDULE_USER - popq %rdi - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - jmp int_with_check - - /* handle signals and tracing -- both require a full pt_regs */ -int_very_careful: - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) SAVE_EXTRA_REGS - /* Check for syscall exit trace */ - testl $_TIF_WORK_SYSCALL_EXIT, %edx - jz int_signal - pushq %rdi - leaq 8(%rsp), %rdi /* &ptregs -> arg1 */ - call syscall_trace_leave - popq %rdi - andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU), %edi - jmp int_restore_rest - -int_signal: - testl $_TIF_DO_NOTIFY_MASK, %edx - jz 1f - movq %rsp, %rdi /* &ptregs -> arg1 */ - xorl %esi, %esi /* oldset -> arg2 */ - call do_notify_resume -1: movl $_TIF_WORK_MASK, %edi -int_restore_rest: + movq %rsp, %rdi + call syscall_return_slowpath /* returns with IRQs disabled */ RESTORE_EXTRA_REGS - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - jmp int_with_check - -syscall_return: - /* The IRETQ could re-enable interrupts: */ - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_IRETQ + TRACE_IRQS_IRETQ /* we're about to change IF */ /* * Try to use SYSRET instead of IRET if we're returning to @@ -555,23 +501,22 @@ END(irq_entries_start) /* 0(%rsp): ~(interrupt number) */ .macro interrupt func cld - /* - * Since nothing in interrupt handling code touches r12...r15 members - * of "struct pt_regs", and since interrupts can nest, we can save - * four stack slots and simultaneously provide - * an unwind-friendly stack layout by saving "truncated" pt_regs - * exactly up to rbp slot, without these members. - */ - ALLOC_PT_GPREGS_ON_STACK -RBP - SAVE_C_REGS -RBP - /* this goes to 0(%rsp) for unwinder, not for saving the value: */ - SAVE_EXTRA_REGS_RBP -RBP - - leaq -RBP(%rsp), %rdi /* arg1 for \func (pointer to pt_regs) */ + ALLOC_PT_GPREGS_ON_STACK + SAVE_C_REGS + SAVE_EXTRA_REGS - testb $3, CS-RBP(%rsp) + testb $3, CS(%rsp) jz 1f + + /* + * IRQ from user mode. Switch to kernel gsbase and inform context + * tracking that we're in kernel mode. + */ SWAPGS +#ifdef CONFIG_CONTEXT_TRACKING + call enter_from_user_mode +#endif + 1: /* * Save previous stack pointer, optionally switch to interrupt stack. @@ -580,14 +525,14 @@ END(irq_entries_start) * a little cheaper to use a separate counter in the PDA (short of * moving irq_enter into assembly, which would be too much work) */ - movq %rsp, %rsi + movq %rsp, %rdi incl PER_CPU_VAR(irq_count) cmovzq PER_CPU_VAR(irq_stack_ptr), %rsp - pushq %rsi + pushq %rdi /* We entered an interrupt context - irqs are off: */ TRACE_IRQS_OFF - call \func + call \func /* rdi points to pt_regs */ .endm /* @@ -606,34 +551,19 @@ ret_from_intr: decl PER_CPU_VAR(irq_count) /* Restore saved previous stack */ - popq %rsi - /* return code expects complete pt_regs - adjust rsp accordingly: */ - leaq -RBP(%rsi), %rsp + popq %rsp testb $3, CS(%rsp) jz retint_kernel - /* Interrupt came from user space */ -retint_user: - GET_THREAD_INFO(%rcx) - /* %rcx: thread info. Interrupts are off. */ -retint_with_reschedule: - movl $_TIF_WORK_MASK, %edi -retint_check: + /* Interrupt came from user space */ LOCKDEP_SYS_EXIT_IRQ - movl TI_flags(%rcx), %edx - andl %edi, %edx - jnz retint_careful - -retint_swapgs: /* return to user-space */ - /* - * The iretq could re-enable interrupts: - */ - DISABLE_INTERRUPTS(CLBR_ANY) +GLOBAL(retint_user) + mov %rsp,%rdi + call prepare_exit_to_usermode TRACE_IRQS_IRETQ - SWAPGS - jmp restore_c_regs_and_iret + jmp restore_regs_and_iret /* Returning to kernel space */ retint_kernel: @@ -657,6 +587,8 @@ retint_kernel: * At this label, code paths which return to kernel and to user, * which come from interrupts/exception and from syscalls, merge. */ +restore_regs_and_iret: + RESTORE_EXTRA_REGS restore_c_regs_and_iret: RESTORE_C_REGS REMOVE_PT_GPREGS_FROM_STACK 8 @@ -707,37 +639,6 @@ native_irq_return_ldt: popq %rax jmp native_irq_return_iret #endif - - /* edi: workmask, edx: work */ -retint_careful: - bt $TIF_NEED_RESCHED, %edx - jnc retint_signal - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - pushq %rdi - SCHEDULE_USER - popq %rdi - GET_THREAD_INFO(%rcx) - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - jmp retint_check - -retint_signal: - testl $_TIF_DO_NOTIFY_MASK, %edx - jz retint_swapgs - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - SAVE_EXTRA_REGS - movq $-1, ORIG_RAX(%rsp) - xorl %esi, %esi /* oldset */ - movq %rsp, %rdi /* &pt_regs */ - call do_notify_resume - RESTORE_EXTRA_REGS - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - GET_THREAD_INFO(%rcx) - jmp retint_with_reschedule - END(common_interrupt) /* @@ -1143,12 +1044,22 @@ ENTRY(error_entry) SAVE_EXTRA_REGS 8 xorl %ebx, %ebx testb $3, CS+8(%rsp) - jz error_kernelspace + jz .Lerror_kernelspace - /* We entered from user mode */ +.Lerror_entry_from_usermode_swapgs: + /* + * We entered from user mode or we're pretending to have entered + * from user mode due to an IRET fault. + */ SWAPGS -error_entry_done: +.Lerror_entry_from_usermode_after_swapgs: +#ifdef CONFIG_CONTEXT_TRACKING + call enter_from_user_mode +#endif + +.Lerror_entry_done: + TRACE_IRQS_OFF ret @@ -1158,31 +1069,30 @@ error_entry_done: * truncated RIP for IRET exceptions returning to compat mode. Check * for these here too. */ -error_kernelspace: +.Lerror_kernelspace: incl %ebx leaq native_irq_return_iret(%rip), %rcx cmpq %rcx, RIP+8(%rsp) - je error_bad_iret + je .Lerror_bad_iret movl %ecx, %eax /* zero extend */ cmpq %rax, RIP+8(%rsp) - je bstep_iret + je .Lbstep_iret cmpq $gs_change, RIP+8(%rsp) - jne error_entry_done + jne .Lerror_entry_done /* * hack: gs_change can fail with user gsbase. If this happens, fix up * gsbase and proceed. We'll fix up the exception and land in * gs_change's error handler with kernel gsbase. */ - SWAPGS - jmp error_entry_done + jmp .Lerror_entry_from_usermode_swapgs -bstep_iret: +.Lbstep_iret: /* Fix truncated RIP */ movq %rcx, RIP+8(%rsp) /* fall through */ -error_bad_iret: +.Lerror_bad_iret: /* * We came from an IRET to user mode, so we have user gsbase. * Switch to kernel gsbase: @@ -1198,7 +1108,7 @@ error_bad_iret: call fixup_bad_iret mov %rax, %rsp decl %ebx - jmp error_entry_done + jmp .Lerror_entry_from_usermode_after_swapgs END(error_entry) @@ -1209,7 +1119,6 @@ END(error_entry) */ ENTRY(error_exit) movl %ebx, %eax - RESTORE_EXTRA_REGS DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF testl %eax, %eax diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index a7e257d9cb90..a9360d40fb7f 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -22,8 +22,8 @@ #define __AUDIT_ARCH_LE 0x40000000 #ifndef CONFIG_AUDITSYSCALL -# define sysexit_audit ia32_ret_from_sys_call -# define sysretl_audit ia32_ret_from_sys_call +# define sysexit_audit ia32_ret_from_sys_call_irqs_off +# define sysretl_audit ia32_ret_from_sys_call_irqs_off #endif .section .entry.text, "ax" @@ -141,7 +141,8 @@ sysexit_from_sys_call: andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) movl RIP(%rsp), %ecx /* User %eip */ movq RAX(%rsp), %rax - RESTORE_RSI_RDI + movl RSI(%rsp), %esi + movl RDI(%rsp), %edi xorl %edx, %edx /* Do not leak kernel information */ xorq %r8, %r8 xorq %r9, %r9 @@ -209,10 +210,10 @@ sysexit_from_sys_call: .endm .macro auditsys_exit exit - testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz ia32_ret_from_sys_call TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) + testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jnz ia32_ret_from_sys_call movl %eax, %esi /* second arg, syscall return value */ cmpl $-MAX_ERRNO, %eax /* is it an error ? */ jbe 1f @@ -230,7 +231,7 @@ sysexit_from_sys_call: movq %rax, R10(%rsp) movq %rax, R9(%rsp) movq %rax, R8(%rsp) - jmp int_with_check + jmp int_ret_from_sys_call_irqs_off .endm sysenter_auditsys: @@ -365,7 +366,9 @@ cstar_dispatch: sysretl_from_sys_call: andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) - RESTORE_RSI_RDI_RDX + movl RDX(%rsp), %edx + movl RSI(%rsp), %esi + movl RDI(%rsp), %edi movl RIP(%rsp), %ecx movl EFLAGS(%rsp), %r11d movq RAX(%rsp), %rax @@ -430,8 +433,48 @@ cstar_tracesys: END(entry_SYSCALL_compat) ia32_badarg: - ASM_CLAC - movq $-EFAULT, RAX(%rsp) + /* + * So far, we've entered kernel mode, set AC, turned on IRQs, and + * saved C regs except r8-r11. We haven't done any of the other + * standard entry work, though. We want to bail, but we shouldn't + * treat this as a syscall entry since we don't even know what the + * args are. Instead, treat this as a non-syscall entry, finish + * the entry work, and immediately exit after setting AX = -EFAULT. + * + * We're really just being polite here. Killing the task outright + * would be a reasonable action, too. Given that the only valid + * way to have gotten here is through the vDSO, and we already know + * that the stack pointer is bad, the task isn't going to survive + * for long no matter what we do. + */ + + ASM_CLAC /* undo STAC */ + movq $-EFAULT, RAX(%rsp) /* return -EFAULT if possible */ + + /* Fill in the rest of pt_regs */ + xorl %eax, %eax + movq %rax, R11(%rsp) + movq %rax, R10(%rsp) + movq %rax, R9(%rsp) + movq %rax, R8(%rsp) + SAVE_EXTRA_REGS + + /* Turn IRQs back off. */ + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF + + /* Now finish entering normal kernel mode. */ +#ifdef CONFIG_CONTEXT_TRACKING + call enter_from_user_mode +#endif + + /* And exit again. */ + jmp retint_user + +ia32_ret_from_sys_call_irqs_off: + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + ia32_ret_from_sys_call: xorl %eax, %eax /* Do not leak kernel information */ movq %rax, R11(%rsp) diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index ef8187f9d28d..25e3cf1cd8fd 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -365,3 +365,18 @@ 356 i386 memfd_create sys_memfd_create 357 i386 bpf sys_bpf 358 i386 execveat sys_execveat stub32_execveat +359 i386 socket sys_socket +360 i386 socketpair sys_socketpair +361 i386 bind sys_bind +362 i386 connect sys_connect +363 i386 listen sys_listen +364 i386 accept4 sys_accept4 +365 i386 getsockopt sys_getsockopt compat_sys_getsockopt +366 i386 setsockopt sys_setsockopt compat_sys_setsockopt +367 i386 getsockname sys_getsockname +368 i386 getpeername sys_getpeername +369 i386 sendto sys_sendto +370 i386 sendmsg sys_sendmsg compat_sys_sendmsg +371 i386 recvfrom sys_recvfrom compat_sys_recvfrom +372 i386 recvmsg sys_recvmsg compat_sys_recvmsg +373 i386 shutdown sys_shutdown diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index e97032069f88..a3d0767a6b29 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -8,7 +8,7 @@ KASAN_SANITIZE := n VDSO64-$(CONFIG_X86_64) := y VDSOX32-$(CONFIG_X86_X32_ABI) := y VDSO32-$(CONFIG_X86_32) := y -VDSO32-$(CONFIG_COMPAT) := y +VDSO32-$(CONFIG_IA32_EMULATION) := y # files to link into the vdso vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o @@ -20,7 +20,7 @@ obj-y += vma.o vdso_img-$(VDSO64-y) += 64 vdso_img-$(VDSOX32-y) += x32 vdso_img-$(VDSO32-y) += 32-int80 -vdso_img-$(CONFIG_COMPAT) += 32-syscall +vdso_img-$(CONFIG_IA32_EMULATION) += 32-syscall vdso_img-$(VDSO32-y) += 32-sysenter obj-$(VDSO32-y) += vdso32-setup.o @@ -126,7 +126,7 @@ $(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE # Build multiple 32-bit vDSO images to choose from at boot time. # vdso32.so-$(VDSO32-y) += int80 -vdso32.so-$(CONFIG_COMPAT) += syscall +vdso32.so-$(CONFIG_IA32_EMULATION) += syscall vdso32.so-$(VDSO32-y) += sysenter vdso32-images = $(vdso32.so-y:%=vdso32-%.so) @@ -175,7 +175,7 @@ quiet_cmd_vdso = VDSO $@ -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' -VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \ +VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=both) \ $(call cc-ldoption, -Wl$(comma)--build-id) -Wl,-Bsymbolic $(LTO_CFLAGS) GCOV_PROFILE := n diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 9793322751e0..ca94fa649251 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -175,20 +175,8 @@ static notrace cycle_t vread_pvclock(int *mode) notrace static cycle_t vread_tsc(void) { - cycle_t ret; - u64 last; - - /* - * Empirically, a fence (of type that depends on the CPU) - * before rdtsc is enough to ensure that rdtsc is ordered - * with respect to loads. The various CPU manuals are unclear - * as to whether rdtsc can be reordered with later loads, - * but no one has ever seen it happen. - */ - rdtsc_barrier(); - ret = (cycle_t)__native_read_tsc(); - - last = gtod->cycle_last; + cycle_t ret = (cycle_t)rdtsc_ordered(); + u64 last = gtod->cycle_last; if (likely(ret >= last)) return ret; diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 1c9f750c3859..434543145d78 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -177,7 +177,7 @@ up_fail: return ret; } -#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT) +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) static int load_vdso32(void) { int ret; @@ -219,8 +219,11 @@ int compat_arch_setup_additional_pages(struct linux_binprm *bprm, return map_vdso(&vdso_image_x32, true); } #endif - +#ifdef CONFIG_IA32_EMULATION return load_vdso32(); +#else + return 0; +#endif } #endif #else diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 2dcc6ff6fdcc..26a46f44e298 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -290,7 +290,7 @@ static struct vm_area_struct gate_vma = { struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { -#ifdef CONFIG_IA32_EMULATION +#ifdef CONFIG_COMPAT if (!mm || mm->context.ia32_compat) return NULL; #endif diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index ae3a29ae875b..a0a19b7ba22d 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -34,99 +34,6 @@ #include <asm/sys_ia32.h> #include <asm/smap.h> -int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) -{ - int err = 0; - bool ia32 = test_thread_flag(TIF_IA32); - - if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t))) - return -EFAULT; - - put_user_try { - /* If you change siginfo_t structure, please make sure that - this code is fixed accordingly. - It should never copy any pad contained in the structure - to avoid security leaks, but must copy the generic - 3 ints plus the relevant union member. */ - put_user_ex(from->si_signo, &to->si_signo); - put_user_ex(from->si_errno, &to->si_errno); - put_user_ex((short)from->si_code, &to->si_code); - - if (from->si_code < 0) { - put_user_ex(from->si_pid, &to->si_pid); - put_user_ex(from->si_uid, &to->si_uid); - put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr); - } else { - /* - * First 32bits of unions are always present: - * si_pid === si_band === si_tid === si_addr(LS half) - */ - put_user_ex(from->_sifields._pad[0], - &to->_sifields._pad[0]); - switch (from->si_code >> 16) { - case __SI_FAULT >> 16: - break; - case __SI_SYS >> 16: - put_user_ex(from->si_syscall, &to->si_syscall); - put_user_ex(from->si_arch, &to->si_arch); - break; - case __SI_CHLD >> 16: - if (ia32) { - put_user_ex(from->si_utime, &to->si_utime); - put_user_ex(from->si_stime, &to->si_stime); - } else { - put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime); - put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime); - } - put_user_ex(from->si_status, &to->si_status); - /* FALL THROUGH */ - default: - case __SI_KILL >> 16: - put_user_ex(from->si_uid, &to->si_uid); - break; - case __SI_POLL >> 16: - put_user_ex(from->si_fd, &to->si_fd); - break; - case __SI_TIMER >> 16: - put_user_ex(from->si_overrun, &to->si_overrun); - put_user_ex(ptr_to_compat(from->si_ptr), - &to->si_ptr); - break; - /* This is not generated by the kernel as of now. */ - case __SI_RT >> 16: - case __SI_MESGQ >> 16: - put_user_ex(from->si_uid, &to->si_uid); - put_user_ex(from->si_int, &to->si_int); - break; - } - } - } put_user_catch(err); - - return err; -} - -int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) -{ - int err = 0; - u32 ptr32; - - if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t))) - return -EFAULT; - - get_user_try { - get_user_ex(to->si_signo, &from->si_signo); - get_user_ex(to->si_errno, &from->si_errno); - get_user_ex(to->si_code, &from->si_code); - - get_user_ex(to->si_pid, &from->si_pid); - get_user_ex(to->si_uid, &from->si_uid); - get_user_ex(ptr32, &from->si_ptr); - to->si_ptr = compat_ptr(ptr32); - } get_user_catch(err); - - return err; -} - /* * Do a signal return; undo the signal stack. */ diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index e51a8f803f55..818cb8788225 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -91,15 +91,4 @@ do { \ #define smp_mb__before_atomic() barrier() #define smp_mb__after_atomic() barrier() -/* - * Stop RDTSC speculation. This is needed when you need to use RDTSC - * (or get_cycles or vread that possibly accesses the TSC) in a defined - * code region. - */ -static __always_inline void rdtsc_barrier(void) -{ - alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, - "lfence", X86_FEATURE_LFENCE_RDTSC); -} - #endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/context_tracking.h b/arch/x86/include/asm/context_tracking.h deleted file mode 100644 index 1fe49704b146..000000000000 --- a/arch/x86/include/asm/context_tracking.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef _ASM_X86_CONTEXT_TRACKING_H -#define _ASM_X86_CONTEXT_TRACKING_H - -#ifdef CONFIG_CONTEXT_TRACKING -# define SCHEDULE_USER call schedule_user -#else -# define SCHEDULE_USER call schedule -#endif - -#endif diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index f161c189c27b..141c561f4664 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -78,7 +78,7 @@ typedef struct user_fxsr_struct elf_fpxregset_t; #ifdef CONFIG_X86_64 extern unsigned int vdso64_enabled; #endif -#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT) +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) extern unsigned int vdso32_enabled; #endif @@ -187,8 +187,8 @@ static inline void elf_common_init(struct thread_struct *t, #define COMPAT_ELF_PLAT_INIT(regs, load_addr) \ elf_common_init(¤t->thread, regs, __USER_DS) -void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp); -#define compat_start_thread start_thread_ia32 +void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp); +#define compat_start_thread compat_start_thread void set_personality_ia32(bool); #define COMPAT_SET_PERSONALITY(ex) \ @@ -344,14 +344,9 @@ extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm, */ static inline int mmap_is_ia32(void) { -#ifdef CONFIG_X86_32 - return 1; -#endif -#ifdef CONFIG_IA32_EMULATION - if (test_thread_flag(TIF_ADDR32)) - return 1; -#endif - return 0; + return config_enabled(CONFIG_X86_32) || + (config_enabled(CONFIG_COMPAT) && + test_thread_flag(TIF_ADDR32)); } /* Do not change the values. See get_align_mask() */ diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index d0e8e0141041..28019765442e 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -22,15 +22,6 @@ struct ucontext_ia32 { compat_sigset_t uc_sigmask; /* mask last for extensibility */ }; -struct ucontext_x32 { - unsigned int uc_flags; - unsigned int uc_link; - compat_stack_t uc_stack; - unsigned int uc__pad0; /* needed for alignment */ - struct sigcontext uc_mcontext; /* the 64-bit sigcontext type */ - compat_sigset_t uc_sigmask; /* mask last for extensibility */ -}; - /* This matches struct stat64 in glibc2.2, hence the absolutely * insane amounts of padding around dev_t's. */ diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 4c2d2eb2060a..6ca9fd6234e1 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -117,16 +117,6 @@ #define FPU_IRQ 13 -#define FIRST_VM86_IRQ 3 -#define LAST_VM86_IRQ 15 - -#ifndef __ASSEMBLY__ -static inline int invalid_vm86_irq(int irq) -{ - return irq < FIRST_VM86_IRQ || irq > LAST_VM86_IRQ; -} -#endif - /* * Size the maximum number of interrupts. * 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 <asm/ptrace.h> -#include <asm/vm86.h> /* 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/mmu.h b/arch/x86/include/asm/mmu.h index 364d27481a52..55234d5e7160 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -9,7 +9,9 @@ * we put the segment information here. */ typedef struct { +#ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; +#endif #ifdef CONFIG_X86_64 /* True if mm supports a task running in 32 bit compatibility mode. */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 984abfe47edc..379cd3658799 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -33,6 +33,7 @@ static inline void load_mm_cr4(struct mm_struct *mm) static inline void load_mm_cr4(struct mm_struct *mm) {} #endif +#ifdef CONFIG_MODIFY_LDT_SYSCALL /* * ldt_structs can be allocated, used, and freed, but they are never * modified while live. @@ -48,8 +49,23 @@ struct ldt_struct { int size; }; +/* + * Used for LDT copy/destruction. + */ +int init_new_context(struct task_struct *tsk, struct mm_struct *mm); +void destroy_context(struct mm_struct *mm); +#else /* CONFIG_MODIFY_LDT_SYSCALL */ +static inline int init_new_context(struct task_struct *tsk, + struct mm_struct *mm) +{ + return 0; +} +static inline void destroy_context(struct mm_struct *mm) {} +#endif + static inline void load_mm_ldt(struct mm_struct *mm) { +#ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; /* lockless_dereference synchronizes with smp_store_release */ @@ -73,17 +89,13 @@ static inline void load_mm_ldt(struct mm_struct *mm) set_ldt(ldt->entries, ldt->size); else clear_LDT(); +#else + clear_LDT(); +#endif DEBUG_LOCKS_WARN_ON(preemptible()); } -/* - * Used for LDT copy/destruction. - */ -int init_new_context(struct task_struct *tsk, struct mm_struct *mm); -void destroy_context(struct mm_struct *mm); - - static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { #ifdef CONFIG_SMP @@ -114,6 +126,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, /* Load per-mm CR4 state */ load_mm_cr4(next); +#ifdef CONFIG_MODIFY_LDT_SYSCALL /* * Load the LDT, if the LDT is different. * @@ -128,6 +141,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, */ if (unlikely(prev->context.ldt != next->context.ldt)) load_mm_ldt(next); +#endif } #ifdef CONFIG_SMP else { diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index e6a707eb5081..131eec2ca137 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -47,14 +47,13 @@ static inline unsigned long long native_read_tscp(unsigned int *aux) * it means rax *or* rdx. */ #ifdef CONFIG_X86_64 -#define DECLARE_ARGS(val, low, high) unsigned low, high -#define EAX_EDX_VAL(val, low, high) ((low) | ((u64)(high) << 32)) -#define EAX_EDX_ARGS(val, low, high) "a" (low), "d" (high) +/* Using 64-bit values saves one instruction clearing the high half of low */ +#define DECLARE_ARGS(val, low, high) unsigned long low, high +#define EAX_EDX_VAL(val, low, high) ((low) | (high) << 32) #define EAX_EDX_RET(val, low, high) "=a" (low), "=d" (high) #else #define DECLARE_ARGS(val, low, high) unsigned long long val #define EAX_EDX_VAL(val, low, high) (val) -#define EAX_EDX_ARGS(val, low, high) "A" (val) #define EAX_EDX_RET(val, low, high) "=A" (val) #endif @@ -106,12 +105,19 @@ notrace static inline int native_write_msr_safe(unsigned int msr, return err; } -extern unsigned long long native_read_tsc(void); - extern int rdmsr_safe_regs(u32 regs[8]); extern int wrmsr_safe_regs(u32 regs[8]); -static __always_inline unsigned long long __native_read_tsc(void) +/** + * rdtsc() - returns the current TSC without ordering constraints + * + * rdtsc() returns the result of RDTSC as a 64-bit integer. The + * only ordering constraint it supplies is the ordering implied by + * "asm volatile": it will put the RDTSC in the place you expect. The + * CPU can and will speculatively execute that RDTSC, though, so the + * results can be non-monotonic if compared on different CPUs. + */ +static __always_inline unsigned long long rdtsc(void) { DECLARE_ARGS(val, low, high); @@ -120,6 +126,32 @@ static __always_inline unsigned long long __native_read_tsc(void) return EAX_EDX_VAL(val, low, high); } +/** + * rdtsc_ordered() - read the current TSC in program order + * + * rdtsc_ordered() returns the result of RDTSC as a 64-bit integer. + * It is ordered like a load to a global in-memory counter. It should + * be impossible to observe non-monotonic rdtsc_unordered() behavior + * across multiple CPUs as long as the TSC is synced. + */ +static __always_inline unsigned long long rdtsc_ordered(void) +{ + /* + * The RDTSC instruction is not ordered relative to memory + * access. The Intel SDM and the AMD APM are both vague on this + * point, but empirically an RDTSC instruction can be + * speculatively executed before prior loads. An RDTSC + * immediately after an appropriate barrier appears to be + * ordered as a normal load, that is, it provides the same + * ordering guarantees as reading from a global memory location + * that some other imaginary CPU is updating continuously with a + * time stamp. + */ + alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, + "lfence", X86_FEATURE_LFENCE_RDTSC); + return rdtsc(); +} + static inline unsigned long long native_read_pmc(int counter) { DECLARE_ARGS(val, low, high); @@ -180,12 +212,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) return err; } -#define rdtscl(low) \ - ((low) = (u32)__native_read_tsc()) - -#define rdtscll(val) \ - ((val) = __native_read_tsc()) - #define rdpmc(counter, low, high) \ do { \ u64 _l = native_read_pmc((counter)); \ @@ -195,15 +221,6 @@ do { \ #define rdpmcl(counter, val) ((val) = native_read_pmc(counter)) -#define rdtscp(low, high, aux) \ -do { \ - unsigned long long _val = native_read_tscp(&(aux)); \ - (low) = (u32)_val; \ - (high) = (u32)(_val >> 32); \ -} while (0) - -#define rdtscpll(val, aux) (val) = native_read_tscp(&(aux)) - #endif /* !CONFIG_PARAVIRT */ /* diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index d143bfad45d7..c2be0375bcad 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -174,19 +174,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) return err; } -static inline u64 paravirt_read_tsc(void) -{ - return PVOP_CALL0(u64, pv_cpu_ops.read_tsc); -} - -#define rdtscl(low) \ -do { \ - u64 _l = paravirt_read_tsc(); \ - low = (int)_l; \ -} while (0) - -#define rdtscll(val) (val = paravirt_read_tsc()) - static inline unsigned long long paravirt_sched_clock(void) { return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock); @@ -215,27 +202,6 @@ do { \ #define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter)) -static inline unsigned long long paravirt_rdtscp(unsigned int *aux) -{ - return PVOP_CALL1(u64, pv_cpu_ops.read_tscp, aux); -} - -#define rdtscp(low, high, aux) \ -do { \ - int __aux; \ - unsigned long __val = paravirt_rdtscp(&__aux); \ - (low) = (u32)__val; \ - (high) = (u32)(__val >> 32); \ - (aux) = __aux; \ -} while (0) - -#define rdtscpll(val, aux) \ -do { \ - unsigned long __aux; \ - val = paravirt_rdtscp(&__aux); \ - (aux) = __aux; \ -} while (0) - static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries) { PVOP_VCALL2(pv_cpu_ops.alloc_ldt, ldt, entries); diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index a6b8f9fadb06..ce029e4fa7c6 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -156,9 +156,7 @@ struct pv_cpu_ops { u64 (*read_msr)(unsigned int msr, int *err); int (*write_msr)(unsigned int msr, unsigned low, unsigned high); - u64 (*read_tsc)(void); u64 (*read_pmc)(int counter); - unsigned long long (*read_tscp)(unsigned int *aux); #ifdef CONFIG_X86_32 /* diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 944f1785ed0d..9615a4e2645e 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -6,8 +6,8 @@ /* Forward declaration, a strange C thing */ struct task_struct; struct mm_struct; +struct vm86; -#include <asm/vm86.h> #include <asm/math_emu.h> #include <asm/segment.h> #include <asm/types.h> @@ -400,15 +400,9 @@ struct thread_struct { unsigned long cr2; unsigned long trap_nr; unsigned long error_code; -#ifdef CONFIG_X86_32 +#ifdef CONFIG_VM86 /* Virtual 86 mode info */ - struct vm86_struct __user *vm86_info; - unsigned long screen_bitmap; - unsigned long v86flags; - unsigned long v86mask; - unsigned long saved_sp0; - unsigned int saved_fs; - unsigned int saved_gs; + struct vm86 *vm86; #endif /* IO permissions: */ unsigned long *io_bitmap_ptr; @@ -720,7 +714,6 @@ static inline void spin_lock_prefetch(const void *x) #define INIT_THREAD { \ .sp0 = TOP_OF_INIT_STACK, \ - .vm86_info = NULL, \ .sysenter_cs = __KERNEL_CS, \ .io_bitmap_ptr = NULL, \ } diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 5fabf1362942..6271281f947d 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -88,7 +88,6 @@ extern long syscall_trace_enter_phase2(struct pt_regs *, u32 arch, unsigned long phase1_result); extern long syscall_trace_enter(struct pt_regs *); -extern void syscall_trace_leave(struct pt_regs *); static inline unsigned long regs_return_value(struct pt_regs *regs) { diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 628954ceede1..7a6bed5c08bc 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -62,7 +62,7 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) static __always_inline u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src) { - u64 delta = __native_read_tsc() - src->tsc_timestamp; + u64 delta = rdtsc_ordered() - src->tsc_timestamp; return pvclock_scale_delta(delta, src->tsc_to_system_mul, src->tsc_shift); } @@ -76,13 +76,7 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, u8 ret_flags; version = src->version; - /* Note: emulated platforms which do not advertise SSE2 support - * result in kvmclock not using the necessary RDTSC barriers. - * Without barriers, it is possible that RDTSC instruction reads from - * the time stamp counter outside rdtsc_barrier protected section - * below, resulting in violation of monotonicity. - */ - rdtsc_barrier(); + offset = pvclock_get_nsec_offset(src); ret = src->system_time + offset; ret_flags = src->flags; diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h index 7c7c27c97daa..1f3175bb994e 100644 --- a/arch/x86/include/asm/sigframe.h +++ b/arch/x86/include/asm/sigframe.h @@ -4,6 +4,7 @@ #include <asm/sigcontext.h> #include <asm/siginfo.h> #include <asm/ucontext.h> +#include <linux/compat.h> #ifdef CONFIG_X86_32 #define sigframe_ia32 sigframe @@ -69,6 +70,15 @@ struct rt_sigframe { #ifdef CONFIG_X86_X32_ABI +struct ucontext_x32 { + unsigned int uc_flags; + unsigned int uc_link; + compat_stack_t uc_stack; + unsigned int uc__pad0; /* needed for alignment */ + struct sigcontext uc_mcontext; /* the 64-bit sigcontext type */ + compat_sigset_t uc_sigmask; /* mask last for extensibility */ +}; + struct rt_sigframe_x32 { u64 pretcode; struct ucontext_x32 uc; diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 31eab867e6d3..c481be78fcf1 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -30,7 +30,7 @@ typedef sigset_t compat_sigset_t; #endif /* __ASSEMBLY__ */ #include <uapi/asm/signal.h> #ifndef __ASSEMBLY__ -extern void do_notify_resume(struct pt_regs *, void *, __u32); +extern void do_signal(struct pt_regs *regs); #define __ARCH_HAS_SA_RESTORER diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index c2e00bb2a136..58505f01962f 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -72,7 +72,7 @@ static __always_inline void boot_init_stack_canary(void) * on during the bootup the random pool has true entropy too. */ get_random_bytes(&canary, sizeof(canary)); - tsc = __native_read_tsc(); + tsc = rdtsc(); canary += tsc + (tsc << 32UL); current->stack_canary = canary; 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/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 225ee545e1a0..8afdc3e44247 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 @@ -140,27 +143,11 @@ struct thread_info { _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT | \ _TIF_NOHZ) -/* work to do in syscall_trace_leave() */ -#define _TIF_WORK_SYSCALL_EXIT \ - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP | \ - _TIF_SYSCALL_TRACEPOINT | _TIF_NOHZ) - -/* work to do on interrupt/exception return */ -#define _TIF_WORK_MASK \ - (0x0000FFFF & \ - ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT| \ - _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU)) - /* work to do on any return to user space */ #define _TIF_ALLWORK_MASK \ ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT | \ _TIF_NOHZ) -/* Only used for 64 bit */ -#define _TIF_DO_NOTIFY_MASK \ - (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | \ - _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE) - /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ (_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP) diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index c5380bea2a36..c3496619740a 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -112,8 +112,8 @@ asmlinkage void smp_threshold_interrupt(void); asmlinkage void smp_deferred_error_interrupt(void); #endif -extern enum ctx_state ist_enter(struct pt_regs *regs); -extern void ist_exit(struct pt_regs *regs, enum ctx_state prev_state); +extern void ist_enter(struct pt_regs *regs); +extern void ist_exit(struct pt_regs *regs); extern void ist_begin_non_atomic(struct pt_regs *regs); extern void ist_end_non_atomic(void); diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 94605c0e9cee..3df7675debcf 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -21,28 +21,12 @@ extern void disable_TSC(void); static inline cycles_t get_cycles(void) { - unsigned long long ret = 0; - #ifndef CONFIG_X86_TSC if (!cpu_has_tsc) return 0; #endif - rdtscll(ret); - - return ret; -} -static __always_inline cycles_t vget_cycles(void) -{ - /* - * We only do VDSOs on TSC capable CPUs, so this shouldn't - * access boot_cpu_data (which is not VDSO-safe): - */ -#ifndef CONFIG_X86_TSC - if (!cpu_has_tsc) - return 0; -#endif - return (cycles_t)__native_read_tsc(); + return rdtsc(); } extern void tsc_init(void); diff --git a/arch/x86/include/asm/vm86.h b/arch/x86/include/asm/vm86.h index 1d8de3f3feca..1e491f3af317 100644 --- a/arch/x86/include/asm/vm86.h +++ b/arch/x86/include/asm/vm86.h @@ -1,7 +1,6 @@ #ifndef _ASM_X86_VM86_H #define _ASM_X86_VM86_H - #include <asm/ptrace.h> #include <uapi/asm/vm86.h> @@ -28,43 +27,49 @@ struct kernel_vm86_regs { unsigned short gs, __gsh; }; -struct kernel_vm86_struct { - struct kernel_vm86_regs regs; -/* - * the below part remains on the kernel stack while we are in VM86 mode. - * 'tss.esp0' then contains the address of VM86_TSS_ESP0 below, and when we - * get forced back from VM86, the CPU and "SAVE_ALL" will restore the above - * 'struct kernel_vm86_regs' with the then actual values. - * Therefore, pt_regs in fact points to a complete 'kernel_vm86_struct' - * in kernelspace, hence we need not reget the data from userspace. - */ -#define VM86_TSS_ESP0 flags +struct vm86 { + struct vm86plus_struct __user *user_vm86; + struct pt_regs regs32; + unsigned long veflags; + unsigned long veflags_mask; + unsigned long saved_sp0; + unsigned long flags; unsigned long screen_bitmap; unsigned long cpu_type; struct revectored_struct int_revectored; struct revectored_struct int21_revectored; struct vm86plus_info_struct vm86plus; - struct pt_regs *regs32; /* here we save the pointer to the old regs */ -/* - * The below is not part of the structure, but the stack layout continues - * this way. In front of 'return-eip' may be some data, depending on - * compilation, so we don't rely on this and save the pointer to 'oldregs' - * in 'regs32' above. - * However, with GCC-2.7.2 and the current CFLAGS you see exactly this: - - long return-eip; from call to vm86() - struct pt_regs oldregs; user space registers as saved by syscall - */ }; #ifdef CONFIG_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; + +#define free_vm86(t) do { \ + struct thread_struct *__t = (t); \ + if (__t->vm86 != NULL) { \ + kfree(__t->vm86); \ + __t->vm86 = NULL; \ + } \ +} while (0) + +/* + * Support for VM86 programs to request interrupts for + * real mode hardware drivers: + */ +#define FIRST_VM86_IRQ 3 +#define LAST_VM86_IRQ 15 + +static inline int invalid_vm86_irq(int irq) +{ + return irq < FIRST_VM86_IRQ || irq > LAST_VM86_IRQ; +} + void release_vm86_irqs(struct task_struct *); #else @@ -77,6 +82,10 @@ 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 */ #endif /* _ASM_X86_VM86_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 0f15af41bd80..514064897d55 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -23,8 +23,10 @@ KASAN_SANITIZE_dumpstack_$(BITS).o := n CFLAGS_irq.o := -I$(src)/../include/asm/trace obj-y := process_$(BITS).o signal.o +obj-$(CONFIG_COMPAT) += signal_compat.o obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o -obj-y += time.o ioport.o ldt.o dumpstack.o nmi.o +obj-y += time.o ioport.o dumpstack.o nmi.o +obj-$(CONFIG_MODIFY_LDT_SYSCALL) += ldt.o obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-y += probe_roms.o diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index ede92c3364d3..222a57076039 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -263,7 +263,7 @@ static int apbt_clocksource_register(void) /* Verify whether apbt counter works */ t1 = dw_apb_clocksource_read(clocksource_apbt); - rdtscll(start); + start = rdtsc(); /* * We don't know the TSC frequency yet, but waiting for @@ -273,7 +273,7 @@ static int apbt_clocksource_register(void) */ do { rep_nop(); - rdtscll(now); + now = rdtsc(); } while ((now - start) < 200000UL); /* APBT is the only always on clocksource, it has to work! */ @@ -390,13 +390,13 @@ unsigned long apbt_quick_calibrate(void) old = dw_apb_clocksource_read(clocksource_apbt); old += loop; - t1 = __native_read_tsc(); + t1 = rdtsc(); do { new = dw_apb_clocksource_read(clocksource_apbt); } while (new < old); - t2 = __native_read_tsc(); + t2 = rdtsc(); shift = 5; if (unlikely(loop >> shift == 0)) { diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index dcb52850a28f..0d71cd9b4a50 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -457,7 +457,7 @@ static int lapic_next_deadline(unsigned long delta, { u64 tsc; - rdtscll(tsc); + tsc = rdtsc(); wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR)); return 0; } @@ -592,7 +592,7 @@ static void __init lapic_cal_handler(struct clock_event_device *dev) unsigned long pm = acpi_pm_read_early(); if (cpu_has_tsc) - rdtscll(tsc); + tsc = rdtsc(); switch (lapic_cal_loops++) { case 0: @@ -1209,7 +1209,7 @@ void setup_local_APIC(void) long long max_loops = cpu_khz ? cpu_khz : 1000000; if (cpu_has_tsc) - rdtscll(tsc); + tsc = rdtsc(); if (disable_apic) { disable_ioapic_support(); @@ -1293,7 +1293,7 @@ void setup_local_APIC(void) } if (queued) { if (cpu_has_tsc && cpu_khz) { - rdtscll(ntsc); + ntsc = rdtsc(); max_loops = (cpu_khz << 10) - (ntsc - tsc); } else max_loops--; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index dd3a4baffe50..51ad2af84a72 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -114,7 +114,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) const int K6_BUG_LOOP = 1000000; int n; void (*f_vide)(void); - unsigned long d, d2; + u64 d, d2; printk(KERN_INFO "AMD K6 stepping B detected - "); @@ -125,10 +125,10 @@ static void init_amd_k6(struct cpuinfo_x86 *c) n = K6_BUG_LOOP; f_vide = vide; - rdtscl(d); + d = rdtsc(); while (n--) f_vide(); - rdtscl(d2); + d2 = rdtsc(); d = d2-d; if (d > 20*K6_BUG_LOOP) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index df919ff103c3..99940d151e7d 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -125,7 +125,7 @@ void mce_setup(struct mce *m) { memset(m, 0, sizeof(struct mce)); m->cpu = m->extcpu = smp_processor_id(); - rdtscll(m->tsc); + m->tsc = rdtsc(); /* We hope get_seconds stays lockless */ m->time = get_seconds(); m->cpuvendor = boot_cpu_data.x86_vendor; @@ -1029,7 +1029,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) { struct mca_config *cfg = &mca_cfg; struct mce m, *final; - enum ctx_state prev_state; int i; int worst = 0; int severity; @@ -1055,7 +1054,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) int flags = MF_ACTION_REQUIRED; int lmce = 0; - prev_state = ist_enter(regs); + ist_enter(regs); this_cpu_inc(mce_exception_count); @@ -1227,7 +1226,7 @@ out: local_irq_disable(); ist_end_non_atomic(); done: - ist_exit(regs, prev_state); + ist_exit(regs); } EXPORT_SYMBOL_GPL(do_machine_check); @@ -1784,7 +1783,7 @@ static void collect_tscs(void *data) { unsigned long *cpu_tsc = (unsigned long *)data; - rdtscll(cpu_tsc[smp_processor_id()]); + cpu_tsc[smp_processor_id()] = rdtsc(); } static int mce_apei_read_done; diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c index 737b0ad4e61a..12402e10aeff 100644 --- a/arch/x86/kernel/cpu/mcheck/p5.c +++ b/arch/x86/kernel/cpu/mcheck/p5.c @@ -19,10 +19,9 @@ int mce_p5_enabled __read_mostly; /* Machine check handler for Pentium class Intel CPUs: */ static void pentium_machine_check(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; u32 loaddr, hi, lotype; - prev_state = ist_enter(regs); + ist_enter(regs); rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi); rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi); @@ -39,7 +38,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code) add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - ist_exit(regs, prev_state); + ist_exit(regs); } /* Set up machine check reporting for processors with Intel style MCE: */ diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c index 44f138296fbe..01dd8702880b 100644 --- a/arch/x86/kernel/cpu/mcheck/winchip.c +++ b/arch/x86/kernel/cpu/mcheck/winchip.c @@ -15,12 +15,12 @@ /* Machine check handler for WinChip C6: */ static void winchip_machine_check(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state = ist_enter(regs); + ist_enter(regs); printk(KERN_EMERG "CPU0: Machine Check Exception.\n"); add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - ist_exit(regs, prev_state); + ist_exit(regs); } /* Set up machine check reporting on the Winchip C6 series */ diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 9469dfa55607..cc25c8f3512d 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -2179,6 +2179,7 @@ static unsigned long get_segment_base(unsigned int segment) int idx = segment >> 3; if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) { +#ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; if (idx > LDT_ENTRIES) @@ -2190,6 +2191,9 @@ static unsigned long get_segment_base(unsigned int segment) return 0; desc = &ldt->entries[idx]; +#else + return 0; +#endif } else { if (idx > GDT_ENTRIES) return 0; @@ -2200,7 +2204,7 @@ static unsigned long get_segment_base(unsigned int segment) return get_desc_base(desc); } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_IA32_EMULATION #include <asm/compat.h> diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index ce95676abd60..4d38416e2a7f 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -110,7 +110,7 @@ static void init_espfix_random(void) */ if (!arch_get_random_long(&rand)) { /* The constant is an arbitrary large prime */ - rdtscll(rand); + rand = rdtsc(); rand *= 0xc345c6b72fd16123UL; } diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 10757d0a3fcf..f75c5908c7a6 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -735,7 +735,7 @@ static int hpet_clocksource_register(void) /* Verify whether hpet counter works */ t1 = hpet_readl(HPET_COUNTER); - rdtscll(start); + start = rdtsc(); /* * We don't know the TSC frequency yet, but waiting for @@ -745,7 +745,7 @@ static int hpet_clocksource_register(void) */ do { rep_nop(); - rdtscll(now); + now = rdtsc(); } while ((now - start) < 200000UL); if (t1 == hpet_readl(HPET_COUNTER)) { diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index c7dfe1be784e..d596eba9586e 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -216,8 +216,23 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) unsigned vector = ~regs->orig_ax; unsigned irq; + /* + * NB: Unlike exception entries, IRQ entries do not reliably + * handle context tracking in the low-level entry code. This is + * because syscall entries execute briefly with IRQs on before + * updating context tracking state, so we can take an IRQ from + * kernel mode with CONTEXT_USER. The low-level entry code only + * updates the context if we came from user mode, so we won't + * switch to CONTEXT_KERNEL. We'll fix that once the syscall + * code is cleaned up enough that we can cleanly defer enabling + * IRQs. + */ + entering_irq(); + /* entering_irq() tells RCU that we're not quiescent. Check it. */ + rcu_lockdep_assert(rcu_is_watching(), "IRQ failed to wake up RCU"); + irq = __this_cpu_read(vector_irq[vector]); if (!handle_irq(irq, regs)) { diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index d05bd2e2ee91..697f90db0e37 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -110,7 +110,7 @@ static void nmi_max_handler(struct irq_work *w) a->handler, whole_msecs, decimal_msecs); } -static int nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) +static int nmi_handle(unsigned int type, struct pt_regs *regs) { struct nmi_desc *desc = nmi_to_desc(type); struct nmiaction *a; @@ -213,7 +213,7 @@ static void pci_serr_error(unsigned char reason, struct pt_regs *regs) { /* check to see if anyone registered against these types of errors */ - if (nmi_handle(NMI_SERR, regs, false)) + if (nmi_handle(NMI_SERR, regs)) return; pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n", @@ -247,7 +247,7 @@ io_check_error(unsigned char reason, struct pt_regs *regs) unsigned long i; /* check to see if anyone registered against these types of errors */ - if (nmi_handle(NMI_IO_CHECK, regs, false)) + if (nmi_handle(NMI_IO_CHECK, regs)) return; pr_emerg( @@ -284,7 +284,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) * as only the first one is ever run (unless it can actually determine * if it caused the NMI) */ - handled = nmi_handle(NMI_UNKNOWN, regs, false); + handled = nmi_handle(NMI_UNKNOWN, regs); if (handled) { __this_cpu_add(nmi_stats.unknown, handled); return; @@ -332,7 +332,7 @@ static void default_do_nmi(struct pt_regs *regs) __this_cpu_write(last_nmi_rip, regs->ip); - handled = nmi_handle(NMI_LOCAL, regs, b2b); + handled = nmi_handle(NMI_LOCAL, regs); __this_cpu_add(nmi_stats.normal, handled); if (handled) { /* diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 58bcfb67c01f..f68e48f5f6c2 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -351,9 +351,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .wbinvd = native_wbinvd, .read_msr = native_read_msr_safe, .write_msr = native_write_msr_safe, - .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, - .read_tscp = native_read_tscp, .load_tr_desc = native_load_tr_desc, .set_ldt = native_set_ldt, .load_gdt = native_load_gdt, diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index e1b013696dde..c89f50a76e97 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -10,7 +10,6 @@ DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3"); DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax"); DEF_NATIVE(pv_cpu_ops, clts, "clts"); -DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc"); #if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)"); @@ -52,7 +51,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); PATCH_SITE(pv_cpu_ops, clts); - PATCH_SITE(pv_cpu_ops, read_tsc); #if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): if (pv_is_native_spin_unlock()) { diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 397688beed4b..2199d9b774c8 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -29,6 +29,7 @@ #include <asm/debugreg.h> #include <asm/nmi.h> #include <asm/tlbflush.h> +#include <asm/vm86.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -110,6 +111,8 @@ void exit_thread(void) kfree(bp); } + free_vm86(t); + fpu__drop(fpu); } 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 <asm/syscalls.h> #include <asm/debugreg.h> #include <asm/switch_to.h> +#include <asm/vm86.h> 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/process_64.c b/arch/x86/kernel/process_64.c index f6b916387590..3c1bbcf12924 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -121,6 +121,7 @@ void __show_regs(struct pt_regs *regs, int all) void release_thread(struct task_struct *dead_task) { if (dead_task->mm) { +#ifdef CONFIG_MODIFY_LDT_SYSCALL if (dead_task->mm->context.ldt) { pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n", dead_task->comm, @@ -128,6 +129,7 @@ void release_thread(struct task_struct *dead_task) dead_task->mm->context.ldt->size); BUG(); } +#endif } } @@ -248,8 +250,8 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) __USER_CS, __USER_DS, 0); } -#ifdef CONFIG_IA32_EMULATION -void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp) +#ifdef CONFIG_COMPAT +void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp) { start_thread_common(regs, new_ip, new_sp, test_thread_flag(TIF_X32) diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 9be72bc3613f..558f50edebca 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -37,12 +37,10 @@ #include <asm/proto.h> #include <asm/hw_breakpoint.h> #include <asm/traps.h> +#include <asm/syscall.h> #include "tls.h" -#define CREATE_TRACE_POINTS -#include <trace/events/syscalls.h> - enum x86_regset { REGSET_GENERAL, REGSET_FP, @@ -1123,6 +1121,73 @@ static int genregs32_set(struct task_struct *target, return ret; } +static long ia32_arch_ptrace(struct task_struct *child, compat_long_t request, + compat_ulong_t caddr, compat_ulong_t cdata) +{ + unsigned long addr = caddr; + unsigned long data = cdata; + void __user *datap = compat_ptr(data); + int ret; + __u32 val; + + switch (request) { + case PTRACE_PEEKUSR: + ret = getreg32(child, addr, &val); + if (ret == 0) + ret = put_user(val, (__u32 __user *)datap); + break; + + case PTRACE_POKEUSR: + ret = putreg32(child, addr, data); + break; + + case PTRACE_GETREGS: /* Get all gp regs from the child. */ + return copy_regset_to_user(child, &user_x86_32_view, + REGSET_GENERAL, + 0, sizeof(struct user_regs_struct32), + datap); + + case PTRACE_SETREGS: /* Set all gp regs in the child. */ + return copy_regset_from_user(child, &user_x86_32_view, + REGSET_GENERAL, 0, + sizeof(struct user_regs_struct32), + datap); + + case PTRACE_GETFPREGS: /* Get the child FPU state. */ + return copy_regset_to_user(child, &user_x86_32_view, + REGSET_FP, 0, + sizeof(struct user_i387_ia32_struct), + datap); + + case PTRACE_SETFPREGS: /* Set the child FPU state. */ + return copy_regset_from_user( + child, &user_x86_32_view, REGSET_FP, + 0, sizeof(struct user_i387_ia32_struct), datap); + + case PTRACE_GETFPXREGS: /* Get the child extended FPU state. */ + return copy_regset_to_user(child, &user_x86_32_view, + REGSET_XFP, 0, + sizeof(struct user32_fxsr_struct), + datap); + + case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */ + return copy_regset_from_user(child, &user_x86_32_view, + REGSET_XFP, 0, + sizeof(struct user32_fxsr_struct), + datap); + + case PTRACE_GET_THREAD_AREA: + case PTRACE_SET_THREAD_AREA: + return arch_ptrace(child, request, addr, data); + + default: + return compat_ptrace_request(child, request, addr, data); + } + + return ret; +} +#endif /* CONFIG_IA32_EMULATION */ + #ifdef CONFIG_X86_X32_ABI static long x32_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, @@ -1211,78 +1276,21 @@ static long x32_arch_ptrace(struct task_struct *child, } #endif +#ifdef CONFIG_COMPAT long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, compat_ulong_t cdata) { - unsigned long addr = caddr; - unsigned long data = cdata; - void __user *datap = compat_ptr(data); - int ret; - __u32 val; - #ifdef CONFIG_X86_X32_ABI if (!is_ia32_task()) return x32_arch_ptrace(child, request, caddr, cdata); #endif - - switch (request) { - case PTRACE_PEEKUSR: - ret = getreg32(child, addr, &val); - if (ret == 0) - ret = put_user(val, (__u32 __user *)datap); - break; - - case PTRACE_POKEUSR: - ret = putreg32(child, addr, data); - break; - - case PTRACE_GETREGS: /* Get all gp regs from the child. */ - return copy_regset_to_user(child, &user_x86_32_view, - REGSET_GENERAL, - 0, sizeof(struct user_regs_struct32), - datap); - - case PTRACE_SETREGS: /* Set all gp regs in the child. */ - return copy_regset_from_user(child, &user_x86_32_view, - REGSET_GENERAL, 0, - sizeof(struct user_regs_struct32), - datap); - - case PTRACE_GETFPREGS: /* Get the child FPU state. */ - return copy_regset_to_user(child, &user_x86_32_view, - REGSET_FP, 0, - sizeof(struct user_i387_ia32_struct), - datap); - - case PTRACE_SETFPREGS: /* Set the child FPU state. */ - return copy_regset_from_user( - child, &user_x86_32_view, REGSET_FP, - 0, sizeof(struct user_i387_ia32_struct), datap); - - case PTRACE_GETFPXREGS: /* Get the child extended FPU state. */ - return copy_regset_to_user(child, &user_x86_32_view, - REGSET_XFP, 0, - sizeof(struct user32_fxsr_struct), - datap); - - case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */ - return copy_regset_from_user(child, &user_x86_32_view, - REGSET_XFP, 0, - sizeof(struct user32_fxsr_struct), - datap); - - case PTRACE_GET_THREAD_AREA: - case PTRACE_SET_THREAD_AREA: - return arch_ptrace(child, request, addr, data); - - default: - return compat_ptrace_request(child, request, addr, data); - } - - return ret; +#ifdef CONFIG_IA32_EMULATION + return ia32_arch_ptrace(child, request, caddr, cdata); +#else + return 0; +#endif } - -#endif /* CONFIG_IA32_EMULATION */ +#endif /* CONFIG_COMPAT */ #ifdef CONFIG_X86_64 @@ -1434,201 +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 71820c42b6ce..da52e6bb5c7f 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -31,11 +31,11 @@ #include <asm/vdso.h> #include <asm/mce.h> #include <asm/sighandling.h> +#include <asm/vm86.h> #ifdef CONFIG_X86_64 #include <asm/proto.h> #include <asm/ia32_unistd.h> -#include <asm/sys_ia32.h> #endif /* CONFIG_X86_64 */ #include <asm/syscall.h> @@ -632,6 +632,9 @@ 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.. */ @@ -697,7 +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; @@ -732,32 +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; diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c new file mode 100644 index 000000000000..dc3c0b1c816f --- /dev/null +++ b/arch/x86/kernel/signal_compat.c @@ -0,0 +1,95 @@ +#include <linux/compat.h> +#include <linux/uaccess.h> + +int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) +{ + int err = 0; + bool ia32 = test_thread_flag(TIF_IA32); + + if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t))) + return -EFAULT; + + put_user_try { + /* If you change siginfo_t structure, please make sure that + this code is fixed accordingly. + It should never copy any pad contained in the structure + to avoid security leaks, but must copy the generic + 3 ints plus the relevant union member. */ + put_user_ex(from->si_signo, &to->si_signo); + put_user_ex(from->si_errno, &to->si_errno); + put_user_ex((short)from->si_code, &to->si_code); + + if (from->si_code < 0) { + put_user_ex(from->si_pid, &to->si_pid); + put_user_ex(from->si_uid, &to->si_uid); + put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr); + } else { + /* + * First 32bits of unions are always present: + * si_pid === si_band === si_tid === si_addr(LS half) + */ + put_user_ex(from->_sifields._pad[0], + &to->_sifields._pad[0]); + switch (from->si_code >> 16) { + case __SI_FAULT >> 16: + break; + case __SI_SYS >> 16: + put_user_ex(from->si_syscall, &to->si_syscall); + put_user_ex(from->si_arch, &to->si_arch); + break; + case __SI_CHLD >> 16: + if (ia32) { + put_user_ex(from->si_utime, &to->si_utime); + put_user_ex(from->si_stime, &to->si_stime); + } else { + put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime); + put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime); + } + put_user_ex(from->si_status, &to->si_status); + /* FALL THROUGH */ + default: + case __SI_KILL >> 16: + put_user_ex(from->si_uid, &to->si_uid); + break; + case __SI_POLL >> 16: + put_user_ex(from->si_fd, &to->si_fd); + break; + case __SI_TIMER >> 16: + put_user_ex(from->si_overrun, &to->si_overrun); + put_user_ex(ptr_to_compat(from->si_ptr), + &to->si_ptr); + break; + /* This is not generated by the kernel as of now. */ + case __SI_RT >> 16: + case __SI_MESGQ >> 16: + put_user_ex(from->si_uid, &to->si_uid); + put_user_ex(from->si_int, &to->si_int); + break; + } + } + } put_user_catch(err); + + return err; +} + +int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) +{ + int err = 0; + u32 ptr32; + + if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t))) + return -EFAULT; + + get_user_try { + get_user_ex(to->si_signo, &from->si_signo); + get_user_ex(to->si_errno, &from->si_errno); + get_user_ex(to->si_code, &from->si_code); + + get_user_ex(to->si_pid, &from->si_pid); + get_user_ex(to->si_uid, &from->si_uid); + get_user_ex(ptr32, &from->si_ptr); + to->si_ptr = compat_ptr(ptr32); + } get_user_catch(err); + + return err; +} diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 0ccb53a9fcd9..c9a073866ca7 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -18,6 +18,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re return addr; } +#ifdef CONFIG_MODIFY_LDT_SYSCALL /* * We'll assume that the code segments in the GDT * are all zero-based. That is largely true: the @@ -45,6 +46,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re } mutex_unlock(&child->mm->context.lock); } +#endif return addr; } diff --git a/arch/x86/kernel/trace_clock.c b/arch/x86/kernel/trace_clock.c index 25b993729f9b..80bb24d9b880 100644 --- a/arch/x86/kernel/trace_clock.c +++ b/arch/x86/kernel/trace_clock.c @@ -12,10 +12,5 @@ */ u64 notrace trace_clock_x86_tsc(void) { - u64 ret; - - rdtsc_barrier(); - rdtscll(ret); - - return ret; + return rdtsc_ordered(); } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index f5791927aa64..86a82eafb96f 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -62,6 +62,7 @@ #include <asm/fpu/xstate.h> #include <asm/trace/mpx.h> #include <asm/mpx.h> +#include <asm/vm86.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> @@ -108,13 +109,10 @@ static inline void preempt_conditional_cli(struct pt_regs *regs) preempt_count_dec(); } -enum ctx_state ist_enter(struct pt_regs *regs) +void ist_enter(struct pt_regs *regs) { - enum ctx_state prev_state; - if (user_mode(regs)) { - /* Other than that, we're just an exception. */ - prev_state = exception_enter(); + CT_WARN_ON(ct_state() != CONTEXT_KERNEL); } else { /* * We might have interrupted pretty much anything. In @@ -123,32 +121,25 @@ enum ctx_state ist_enter(struct pt_regs *regs) * but we need to notify RCU. */ rcu_nmi_enter(); - prev_state = CONTEXT_KERNEL; /* the value is irrelevant. */ } /* - * We are atomic because we're on the IST stack (or we're on x86_32, - * in which case we still shouldn't schedule). - * - * This must be after exception_enter(), because exception_enter() - * won't do anything if in_interrupt() returns true. + * We are atomic because we're on the IST stack; or we're on + * x86_32, in which case we still shouldn't schedule; or we're + * on x86_64 and entered from user mode, in which case we're + * still atomic unless ist_begin_non_atomic is called. */ preempt_count_add(HARDIRQ_OFFSET); /* This code is a bit fragile. Test it. */ rcu_lockdep_assert(rcu_is_watching(), "ist_enter didn't work"); - - return prev_state; } -void ist_exit(struct pt_regs *regs, enum ctx_state prev_state) +void ist_exit(struct pt_regs *regs) { - /* Must be before exception_exit. */ preempt_count_sub(HARDIRQ_OFFSET); - if (user_mode(regs)) - return exception_exit(prev_state); - else + if (!user_mode(regs)) rcu_nmi_exit(); } @@ -162,7 +153,7 @@ void ist_exit(struct pt_regs *regs, enum ctx_state prev_state) * a double fault, it can be safe to schedule. ist_begin_non_atomic() * begins a non-atomic section within an ist_enter()/ist_exit() region. * Callers are responsible for enabling interrupts themselves inside - * the non-atomic section, and callers must call is_end_non_atomic() + * the non-atomic section, and callers must call ist_end_non_atomic() * before ist_exit(). */ void ist_begin_non_atomic(struct pt_regs *regs) @@ -289,17 +280,16 @@ NOKPROBE_SYMBOL(do_trap); static void do_error_trap(struct pt_regs *regs, long error_code, char *str, unsigned long trapnr, int signr) { - enum ctx_state prev_state = exception_enter(); siginfo_t info; + CT_WARN_ON(ct_state() != CONTEXT_KERNEL); + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) != NOTIFY_STOP) { conditional_sti(regs); do_trap(trapnr, signr, str, regs, error_code, fill_trap_info(regs, signr, trapnr, &info)); } - - exception_exit(prev_state); } #define DO_ERROR(trapnr, signr, str, name) \ @@ -351,7 +341,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) } #endif - ist_enter(regs); /* Discard prev_state because we won't return. */ + ist_enter(regs); notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); tsk->thread.error_code = error_code; @@ -371,14 +361,13 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; const struct bndcsr *bndcsr; siginfo_t *info; - prev_state = exception_enter(); + CT_WARN_ON(ct_state() != CONTEXT_KERNEL); if (notify_die(DIE_TRAP, "bounds", regs, error_code, X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP) - goto exit; + return; conditional_sti(regs); if (!user_mode(regs)) @@ -435,9 +424,8 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) die("bounds", regs, error_code); } -exit: - exception_exit(prev_state); return; + exit_trap: /* * This path out is for all the cases where we could not @@ -447,35 +435,33 @@ exit_trap: * time.. */ do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, NULL); - exception_exit(prev_state); } dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code) { struct task_struct *tsk; - enum ctx_state prev_state; - prev_state = exception_enter(); + CT_WARN_ON(ct_state() != CONTEXT_KERNEL); conditional_sti(regs); if (v8086_mode(regs)) { local_irq_enable(); handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); - goto exit; + return; } tsk = current; if (!user_mode(regs)) { if (fixup_exception(regs)) - goto exit; + return; tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; if (notify_die(DIE_GPF, "general protection fault", regs, error_code, X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP) die("general protection fault", regs, error_code); - goto exit; + return; } tsk->thread.error_code = error_code; @@ -491,16 +477,12 @@ do_general_protection(struct pt_regs *regs, long error_code) } force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk); -exit: - exception_exit(prev_state); } NOKPROBE_SYMBOL(do_general_protection); /* May run on IST stack. */ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; - #ifdef CONFIG_DYNAMIC_FTRACE /* * ftrace must be first, everything else may cause a recursive crash. @@ -513,7 +495,8 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) if (poke_int3_handler(regs)) return; - prev_state = ist_enter(regs); + ist_enter(regs); + CT_WARN_ON(ct_state() != CONTEXT_KERNEL); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) @@ -539,7 +522,7 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) preempt_conditional_cli(regs); debug_stack_usage_dec(); exit: - ist_exit(regs, prev_state); + ist_exit(regs); } NOKPROBE_SYMBOL(do_int3); @@ -615,12 +598,11 @@ NOKPROBE_SYMBOL(fixup_bad_iret); dotraplinkage void do_debug(struct pt_regs *regs, long error_code) { struct task_struct *tsk = current; - enum ctx_state prev_state; int user_icebp = 0; unsigned long dr6; int si_code; - prev_state = ist_enter(regs); + ist_enter(regs); get_debugreg(dr6, 6); @@ -695,7 +677,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_dec(); exit: - ist_exit(regs, prev_state); + ist_exit(regs); } NOKPROBE_SYMBOL(do_debug); @@ -747,21 +729,15 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; - - prev_state = exception_enter(); + CT_WARN_ON(ct_state() != CONTEXT_KERNEL); math_error(regs, error_code, X86_TRAP_MF); - exception_exit(prev_state); } dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; - - prev_state = exception_enter(); + CT_WARN_ON(ct_state() != CONTEXT_KERNEL); math_error(regs, error_code, X86_TRAP_XF); - exception_exit(prev_state); } dotraplinkage void @@ -773,9 +749,7 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) dotraplinkage void do_device_not_available(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; - - prev_state = exception_enter(); + CT_WARN_ON(ct_state() != CONTEXT_KERNEL); BUG_ON(use_eager_fpu()); #ifdef CONFIG_MATH_EMULATION @@ -786,7 +760,6 @@ do_device_not_available(struct pt_regs *regs, long error_code) info.regs = regs; math_emulate(&info); - exception_exit(prev_state); return; } #endif @@ -794,7 +767,6 @@ do_device_not_available(struct pt_regs *regs, long error_code) #ifdef CONFIG_X86_32 conditional_sti(regs); #endif - exception_exit(prev_state); } NOKPROBE_SYMBOL(do_device_not_available); @@ -802,9 +774,8 @@ NOKPROBE_SYMBOL(do_device_not_available); dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) { siginfo_t info; - enum ctx_state prev_state; - prev_state = exception_enter(); + CT_WARN_ON(ct_state() != CONTEXT_KERNEL); local_irq_enable(); info.si_signo = SIGILL; @@ -816,7 +787,6 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, &info); } - exception_exit(prev_state); } #endif diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 7437b41f6a47..1bb8bab1b3cb 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -248,7 +248,7 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) data = cyc2ns_write_begin(cpu); - rdtscll(tsc_now); + tsc_now = rdtsc(); ns_now = cycles_2_ns(tsc_now); /* @@ -290,7 +290,7 @@ u64 native_sched_clock(void) } /* read the Time Stamp Counter: */ - rdtscll(tsc_now); + tsc_now = rdtsc(); /* return the value in ns */ return cycles_2_ns(tsc_now); @@ -308,12 +308,6 @@ unsigned long long sched_clock(void) __attribute__((alias("native_sched_clock"))); #endif -unsigned long long native_read_tsc(void) -{ - return __native_read_tsc(); -} -EXPORT_SYMBOL(native_read_tsc); - int check_tsc_unstable(void) { return tsc_unstable; @@ -976,7 +970,7 @@ static struct clocksource clocksource_tsc; */ static cycle_t read_tsc(struct clocksource *cs) { - return (cycle_t)get_cycles(); + return (cycle_t)rdtsc_ordered(); } /* diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index dd8d0791dfb5..78083bf23ed1 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -39,16 +39,15 @@ static cycles_t max_warp; static int nr_warps; /* - * TSC-warp measurement loop running on both CPUs: + * TSC-warp measurement loop running on both CPUs. This is not called + * if there is no TSC. */ static void check_tsc_warp(unsigned int timeout) { cycles_t start, now, prev, end; int i; - rdtsc_barrier(); - start = get_cycles(); - rdtsc_barrier(); + start = rdtsc_ordered(); /* * The measurement runs for 'timeout' msecs: */ @@ -63,9 +62,7 @@ static void check_tsc_warp(unsigned int timeout) */ arch_spin_lock(&sync_lock); prev = last_tsc; - rdtsc_barrier(); - now = get_cycles(); - rdtsc_barrier(); + now = rdtsc_ordered(); last_tsc = now; arch_spin_unlock(&sync_lock); @@ -126,7 +123,7 @@ void check_tsc_sync_source(int cpu) /* * No need to check if we already know that the TSC is not - * synchronized: + * synchronized or if we have no TSC. */ if (unsynchronized_tsc()) return; @@ -190,6 +187,7 @@ void check_tsc_sync_target(void) { int cpus = 2; + /* Also aborts if there is no TSC. */ if (unsynchronized_tsc() || tsc_clocksource_reliable) return; diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index fc9db6ef2a95..abd8b856bd2b 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -44,11 +44,14 @@ #include <linux/ptrace.h> #include <linux/audit.h> #include <linux/stddef.h> +#include <linux/slab.h> #include <asm/uaccess.h> #include <asm/io.h> #include <asm/tlbflush.h> #include <asm/irq.h> +#include <asm/traps.h> +#include <asm/vm86.h> /* * Known problems: @@ -66,10 +69,6 @@ */ -#define KVM86 ((struct kernel_vm86_struct *)regs) -#define VMPI KVM86->vm86plus - - /* * 8- and 16-bit register defines.. */ @@ -81,8 +80,8 @@ /* * virtual flags (16 and 32-bit versions) */ -#define VFLAGS (*(unsigned short *)&(current->thread.v86flags)) -#define VEFLAGS (current->thread.v86flags) +#define VFLAGS (*(unsigned short *)&(current->thread.vm86->veflags)) +#define VEFLAGS (current->thread.vm86->veflags) #define set_flags(X, new, mask) \ ((X) = ((X) & ~(mask)) | ((new) & (mask))) @@ -90,46 +89,13 @@ #define SAFE_MASK (0xDD5) #define RETURN_MASK (0xDFF) -/* convert kernel_vm86_regs to vm86_regs */ -static int copy_vm86_regs_to_user(struct vm86_regs __user *user, - const struct kernel_vm86_regs *regs) -{ - int ret = 0; - - /* - * kernel_vm86_regs is missing gs, so copy everything up to - * (but not including) orig_eax, and then rest including orig_eax. - */ - ret += copy_to_user(user, regs, offsetof(struct kernel_vm86_regs, pt.orig_ax)); - ret += copy_to_user(&user->orig_eax, ®s->pt.orig_ax, - sizeof(struct kernel_vm86_regs) - - offsetof(struct kernel_vm86_regs, pt.orig_ax)); - - return ret; -} - -/* convert vm86_regs to kernel_vm86_regs */ -static int copy_vm86_regs_from_user(struct kernel_vm86_regs *regs, - const struct vm86_regs __user *user, - unsigned extra) -{ - int ret = 0; - - /* copy ax-fs inclusive */ - ret += copy_from_user(regs, user, offsetof(struct kernel_vm86_regs, pt.orig_ax)); - /* copy orig_ax-__gsh+extra */ - ret += copy_from_user(®s->pt.orig_ax, &user->orig_eax, - sizeof(struct kernel_vm86_regs) - - offsetof(struct kernel_vm86_regs, pt.orig_ax) + - extra); - return ret; -} - -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; - unsigned long tmp; + struct task_struct *tsk = current; + struct vm86plus_struct __user *user; + struct vm86 *vm86 = current->thread.vm86; + long err = 0; /* * This gets called from entry.S with interrupts disabled, but @@ -138,31 +104,57 @@ struct pt_regs *save_v86_state(struct kernel_vm86_regs *regs) */ local_irq_enable(); - if (!current->thread.vm86_info) { - pr_alert("no vm86_info: BAD\n"); + if (!vm86 || !vm86->user_vm86) { + pr_alert("no user_vm86: BAD\n"); do_exit(SIGSEGV); } - set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | current->thread.v86mask); - tmp = copy_vm86_regs_to_user(¤t->thread.vm86_info->regs, regs); - tmp += put_user(current->thread.screen_bitmap, ¤t->thread.vm86_info->screen_bitmap); - if (tmp) { - pr_alert("could not access userspace vm86_info\n"); + set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | vm86->veflags_mask); + user = vm86->user_vm86; + + if (!access_ok(VERIFY_WRITE, user, vm86->vm86plus.is_vm86pus ? + sizeof(struct vm86plus_struct) : + sizeof(struct vm86_struct))) { + pr_alert("could not access userspace vm86 info\n"); + do_exit(SIGSEGV); + } + + put_user_try { + put_user_ex(regs->pt.bx, &user->regs.ebx); + put_user_ex(regs->pt.cx, &user->regs.ecx); + put_user_ex(regs->pt.dx, &user->regs.edx); + put_user_ex(regs->pt.si, &user->regs.esi); + put_user_ex(regs->pt.di, &user->regs.edi); + put_user_ex(regs->pt.bp, &user->regs.ebp); + put_user_ex(regs->pt.ax, &user->regs.eax); + put_user_ex(regs->pt.ip, &user->regs.eip); + put_user_ex(regs->pt.cs, &user->regs.cs); + put_user_ex(regs->pt.flags, &user->regs.eflags); + put_user_ex(regs->pt.sp, &user->regs.esp); + put_user_ex(regs->pt.ss, &user->regs.ss); + put_user_ex(regs->es, &user->regs.es); + put_user_ex(regs->ds, &user->regs.ds); + put_user_ex(regs->fs, &user->regs.fs); + put_user_ex(regs->gs, &user->regs.gs); + + put_user_ex(vm86->screen_bitmap, &user->screen_bitmap); + } put_user_catch(err); + if (err) { + pr_alert("could not access userspace vm86 info\n"); do_exit(SIGSEGV); } tss = &per_cpu(cpu_tss, get_cpu()); - current->thread.sp0 = current->thread.saved_sp0; - current->thread.sysenter_cs = __KERNEL_CS; - load_sp0(tss, ¤t->thread); - current->thread.saved_sp0 = 0; + tsk->thread.sp0 = vm86->saved_sp0; + tsk->thread.sysenter_cs = __KERNEL_CS; + load_sp0(tss, &tsk->thread); + vm86->saved_sp0 = 0; put_cpu(); - ret = KVM86->regs32; + memcpy(®s->pt, &vm86->regs32, sizeof(struct pt_regs)); - ret->fs = current->thread.saved_fs; - set_user_gs(ret, current->thread.saved_gs); + lazy_load_gs(vm86->regs32.gs); - return ret; + regs->pt.ax = retval; } static void mark_screen_rdonly(struct mm_struct *mm) @@ -200,45 +192,16 @@ out: static int do_vm86_irq_handling(int subfunction, int irqnumber); -static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk); +static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus); -SYSCALL_DEFINE1(vm86old, struct vm86_struct __user *, v86) +SYSCALL_DEFINE1(vm86old, struct vm86_struct __user *, user_vm86) { - struct kernel_vm86_struct info; /* declare this _on top_, - * this avoids wasting of stack space. - * This remains on the stack until we - * return to 32 bit user space. - */ - struct task_struct *tsk = current; - int tmp; - - if (tsk->thread.saved_sp0) - return -EPERM; - tmp = copy_vm86_regs_from_user(&info.regs, &v86->regs, - offsetof(struct kernel_vm86_struct, vm86plus) - - sizeof(info.regs)); - if (tmp) - return -EFAULT; - memset(&info.vm86plus, 0, (int)&info.regs32 - (int)&info.vm86plus); - info.regs32 = current_pt_regs(); - tsk->thread.vm86_info = v86; - do_sys_vm86(&info, tsk); - return 0; /* we never return here */ + return do_sys_vm86((struct vm86plus_struct __user *) user_vm86, false); } SYSCALL_DEFINE2(vm86, unsigned long, cmd, unsigned long, arg) { - struct kernel_vm86_struct info; /* declare this _on top_, - * this avoids wasting of stack space. - * This remains on the stack until we - * return to 32 bit user space. - */ - struct task_struct *tsk; - int tmp; - struct vm86plus_struct __user *v86; - - tsk = current; switch (cmd) { case VM86_REQUEST_IRQ: case VM86_FREE_IRQ: @@ -256,114 +219,133 @@ SYSCALL_DEFINE2(vm86, unsigned long, cmd, unsigned long, arg) } /* we come here only for functions VM86_ENTER, VM86_ENTER_NO_BYPASS */ - if (tsk->thread.saved_sp0) - return -EPERM; - v86 = (struct vm86plus_struct __user *)arg; - tmp = copy_vm86_regs_from_user(&info.regs, &v86->regs, - offsetof(struct kernel_vm86_struct, regs32) - - sizeof(info.regs)); - if (tmp) - return -EFAULT; - info.regs32 = current_pt_regs(); - info.vm86plus.is_vm86pus = 1; - tsk->thread.vm86_info = (struct vm86_struct __user *)v86; - do_sys_vm86(&info, tsk); - return 0; /* we never return here */ + return do_sys_vm86((struct vm86plus_struct __user *) arg, true); } -static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk) +static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) { struct tss_struct *tss; -/* - * make sure the vm86() system call doesn't try to do anything silly - */ - info->regs.pt.ds = 0; - info->regs.pt.es = 0; - info->regs.pt.fs = 0; -#ifndef CONFIG_X86_32_LAZY_GS - info->regs.pt.gs = 0; -#endif + struct task_struct *tsk = current; + struct vm86 *vm86 = tsk->thread.vm86; + struct kernel_vm86_regs vm86regs; + struct pt_regs *regs = current_pt_regs(); + unsigned long err = 0; + + if (!vm86) { + if (!(vm86 = kzalloc(sizeof(*vm86), GFP_KERNEL))) + return -ENOMEM; + tsk->thread.vm86 = vm86; + } + if (vm86->saved_sp0) + return -EPERM; + + if (!access_ok(VERIFY_READ, user_vm86, plus ? + sizeof(struct vm86_struct) : + sizeof(struct vm86plus_struct))) + return -EFAULT; + + memset(&vm86regs, 0, sizeof(vm86regs)); + get_user_try { + unsigned short seg; + get_user_ex(vm86regs.pt.bx, &user_vm86->regs.ebx); + get_user_ex(vm86regs.pt.cx, &user_vm86->regs.ecx); + get_user_ex(vm86regs.pt.dx, &user_vm86->regs.edx); + get_user_ex(vm86regs.pt.si, &user_vm86->regs.esi); + get_user_ex(vm86regs.pt.di, &user_vm86->regs.edi); + get_user_ex(vm86regs.pt.bp, &user_vm86->regs.ebp); + get_user_ex(vm86regs.pt.ax, &user_vm86->regs.eax); + get_user_ex(vm86regs.pt.ip, &user_vm86->regs.eip); + get_user_ex(seg, &user_vm86->regs.cs); + vm86regs.pt.cs = seg; + get_user_ex(vm86regs.pt.flags, &user_vm86->regs.eflags); + get_user_ex(vm86regs.pt.sp, &user_vm86->regs.esp); + get_user_ex(seg, &user_vm86->regs.ss); + vm86regs.pt.ss = seg; + get_user_ex(vm86regs.es, &user_vm86->regs.es); + get_user_ex(vm86regs.ds, &user_vm86->regs.ds); + get_user_ex(vm86regs.fs, &user_vm86->regs.fs); + get_user_ex(vm86regs.gs, &user_vm86->regs.gs); + + get_user_ex(vm86->flags, &user_vm86->flags); + get_user_ex(vm86->screen_bitmap, &user_vm86->screen_bitmap); + get_user_ex(vm86->cpu_type, &user_vm86->cpu_type); + } get_user_catch(err); + if (err) + return err; + + if (copy_from_user(&vm86->int_revectored, + &user_vm86->int_revectored, + sizeof(struct revectored_struct))) + return -EFAULT; + if (copy_from_user(&vm86->int21_revectored, + &user_vm86->int21_revectored, + sizeof(struct revectored_struct))) + return -EFAULT; + if (plus) { + if (copy_from_user(&vm86->vm86plus, &user_vm86->vm86plus, + sizeof(struct vm86plus_info_struct))) + return -EFAULT; + vm86->vm86plus.is_vm86pus = 1; + } else + memset(&vm86->vm86plus, 0, + sizeof(struct vm86plus_info_struct)); + + memcpy(&vm86->regs32, regs, sizeof(struct pt_regs)); + vm86->user_vm86 = user_vm86; /* * The flags register is also special: we cannot trust that the user * has set it up safely, so this makes sure interrupt etc flags are * inherited from protected mode. */ - VEFLAGS = info->regs.pt.flags; - info->regs.pt.flags &= SAFE_MASK; - info->regs.pt.flags |= info->regs32->flags & ~SAFE_MASK; - info->regs.pt.flags |= X86_VM_MASK; + VEFLAGS = vm86regs.pt.flags; + vm86regs.pt.flags &= SAFE_MASK; + vm86regs.pt.flags |= regs->flags & ~SAFE_MASK; + vm86regs.pt.flags |= X86_VM_MASK; + + vm86regs.pt.orig_ax = regs->orig_ax; - switch (info->cpu_type) { + switch (vm86->cpu_type) { case CPU_286: - tsk->thread.v86mask = 0; + vm86->veflags_mask = 0; break; case CPU_386: - tsk->thread.v86mask = X86_EFLAGS_NT | X86_EFLAGS_IOPL; + vm86->veflags_mask = X86_EFLAGS_NT | X86_EFLAGS_IOPL; break; case CPU_486: - tsk->thread.v86mask = X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL; + vm86->veflags_mask = X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL; break; default: - tsk->thread.v86mask = X86_EFLAGS_ID | X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL; + vm86->veflags_mask = X86_EFLAGS_ID | X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL; break; } /* - * Save old state, set default return value (%ax) to 0 (VM86_SIGNAL) + * Save old state */ - info->regs32->ax = VM86_SIGNAL; - tsk->thread.saved_sp0 = tsk->thread.sp0; - tsk->thread.saved_fs = info->regs32->fs; - tsk->thread.saved_gs = get_user_gs(info->regs32); + vm86->saved_sp0 = tsk->thread.sp0; + lazy_save_gs(vm86->regs32.gs); tss = &per_cpu(cpu_tss, get_cpu()); - tsk->thread.sp0 = (unsigned long) &info->VM86_TSS_ESP0; + /* make room for real-mode segments */ + tsk->thread.sp0 += 16; if (cpu_has_sep) tsk->thread.sysenter_cs = 0; load_sp0(tss, &tsk->thread); put_cpu(); - tsk->thread.screen_bitmap = info->screen_bitmap; - if (info->flags & VM86_SCREEN_BITMAP) + 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" (&info->regs), "r" (task_thread_info(tsk)), "r" (0)); - /* 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) @@ -395,7 +377,7 @@ static inline void clear_AC(struct kernel_vm86_regs *regs) static inline void set_vflags_long(unsigned long flags, struct kernel_vm86_regs *regs) { - set_flags(VEFLAGS, flags, current->thread.v86mask); + set_flags(VEFLAGS, flags, current->thread.vm86->veflags_mask); set_flags(regs->pt.flags, flags, SAFE_MASK); if (flags & X86_EFLAGS_IF) set_IF(regs); @@ -405,7 +387,7 @@ static inline void set_vflags_long(unsigned long flags, struct kernel_vm86_regs static inline void set_vflags_short(unsigned short flags, struct kernel_vm86_regs *regs) { - set_flags(VFLAGS, flags, current->thread.v86mask); + set_flags(VFLAGS, flags, current->thread.vm86->veflags_mask); set_flags(regs->pt.flags, flags, SAFE_MASK); if (flags & X86_EFLAGS_IF) set_IF(regs); @@ -420,7 +402,7 @@ static inline unsigned long get_vflags(struct kernel_vm86_regs *regs) if (VEFLAGS & X86_EFLAGS_VIF) flags |= X86_EFLAGS_IF; flags |= X86_EFLAGS_IOPL; - return flags | (VEFLAGS & current->thread.v86mask); + return flags | (VEFLAGS & current->thread.vm86->veflags_mask); } static inline int is_revectored(int nr, struct revectored_struct *bitmap) @@ -518,12 +500,13 @@ static void do_int(struct kernel_vm86_regs *regs, int i, { unsigned long __user *intr_ptr; unsigned long segoffs; + struct vm86 *vm86 = current->thread.vm86; if (regs->pt.cs == BIOSSEG) goto cannot_handle; - if (is_revectored(i, &KVM86->int_revectored)) + if (is_revectored(i, &vm86->int_revectored)) goto cannot_handle; - if (i == 0x21 && is_revectored(AH(regs), &KVM86->int21_revectored)) + if (i == 0x21 && is_revectored(AH(regs), &vm86->int21_revectored)) goto cannot_handle; intr_ptr = (unsigned long __user *) (i << 2); if (get_user(segoffs, intr_ptr)) @@ -542,18 +525,16 @@ 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) { - if (VMPI.is_vm86pus) { + struct vm86 *vm86 = current->thread.vm86; + + if (vm86->vm86plus.is_vm86pus) { if ((trapno == 3) || (trapno == 1)) { - KVM86->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 KVM86->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)); @@ -574,16 +555,11 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) unsigned char __user *ssp; unsigned short ip, sp, orig_flags; int data32, pref_done; + struct vm86plus_info_struct *vmpi = ¤t->thread.vm86->vm86plus; #define CHECK_IF_IN_TRAP \ - if (VMPI.vm86dbg_active && VMPI.vm86dbg_TFpendig) \ + 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; @@ -622,7 +598,7 @@ 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: @@ -642,16 +618,18 @@ 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 */ case 0xcd: { 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 (vmpi->vm86dbg_active) { + 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; @@ -682,14 +660,14 @@ 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 */ /* @@ -701,14 +679,29 @@ 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: /* FIXME: After a long discussion with Stas we finally * agreed, that this is wrong. Here we should @@ -720,7 +713,7 @@ 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 ----------------- */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 2a5ca97c263b..946f52c43b8f 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1172,7 +1172,7 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) tsc_deadline = apic->lapic_timer.expired_tscdeadline; apic->lapic_timer.expired_tscdeadline = 0; - guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc()); + guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, rdtsc()); trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline); /* __delay is delay_tsc whenever the hardware has TSC, thus always. */ @@ -1240,7 +1240,7 @@ static void start_apic_timer(struct kvm_lapic *apic) local_irq_save(flags); now = apic->lapic_timer.timer.base->get_time(); - guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc()); + guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, rdtsc()); if (likely(tscdeadline > guest_tsc)) { ns = (tscdeadline - guest_tsc) * 1000000ULL; do_div(ns, this_tsc_khz); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 8e0c0844c6b9..a4b8c8d57b96 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1139,7 +1139,7 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) { u64 tsc; - tsc = svm_scale_tsc(vcpu, native_read_tsc()); + tsc = svm_scale_tsc(vcpu, rdtsc()); return target_tsc - tsc; } @@ -3172,7 +3172,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr_info->index) { case MSR_IA32_TSC: { msr_info->data = svm->vmcb->control.tsc_offset + - svm_scale_tsc(vcpu, native_read_tsc()); + svm_scale_tsc(vcpu, rdtsc()); break; } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 83b7b5cd75d5..af30c265412c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2236,7 +2236,7 @@ static u64 guest_read_tsc(void) { u64 host_tsc, tsc_offset; - rdtscll(host_tsc); + host_tsc = rdtsc(); tsc_offset = vmcs_read64(TSC_OFFSET); return host_tsc + tsc_offset; } @@ -2317,7 +2317,7 @@ static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool ho static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) { - return target_tsc - native_read_tsc(); + return target_tsc - rdtsc(); } static bool guest_cpuid_has_vmx(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8f0f6eca69da..3a2b02906486 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1444,20 +1444,8 @@ EXPORT_SYMBOL_GPL(kvm_write_tsc); static cycle_t read_tsc(void) { - cycle_t ret; - u64 last; - - /* - * Empirically, a fence (of type that depends on the CPU) - * before rdtsc is enough to ensure that rdtsc is ordered - * with respect to loads. The various CPU manuals are unclear - * as to whether rdtsc can be reordered with later loads, - * but no one has ever seen it happen. - */ - rdtsc_barrier(); - ret = (cycle_t)vget_cycles(); - - last = pvclock_gtod_data.clock.cycle_last; + cycle_t ret = (cycle_t)rdtsc_ordered(); + u64 last = pvclock_gtod_data.clock.cycle_last; if (likely(ret >= last)) return ret; @@ -1646,7 +1634,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) return 1; } if (!use_master_clock) { - host_tsc = native_read_tsc(); + host_tsc = rdtsc(); kernel_ns = get_kernel_ns(); } @@ -2810,7 +2798,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) { s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 : - native_read_tsc() - vcpu->arch.last_host_tsc; + rdtsc() - vcpu->arch.last_host_tsc; if (tsc_delta < 0) mark_tsc_unstable("KVM discovered backwards TSC"); if (check_tsc_unstable()) { @@ -2838,7 +2826,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { kvm_x86_ops->vcpu_put(vcpu); kvm_put_guest_fpu(vcpu); - vcpu->arch.last_host_tsc = native_read_tsc(); + vcpu->arch.last_host_tsc = rdtsc(); } static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, @@ -6627,7 +6615,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) hw_breakpoint_restore(); vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, - native_read_tsc()); + rdtsc()); vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); @@ -7436,7 +7424,7 @@ int kvm_arch_hardware_enable(void) if (ret != 0) return ret; - local_tsc = native_read_tsc(); + local_tsc = rdtsc(); stable = !check_tsc_unstable(); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 39d6a3db0b96..4453d52a143d 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -49,16 +49,14 @@ static void delay_loop(unsigned long loops) /* TSC based delay: */ static void delay_tsc(unsigned long __loops) { - u32 bclock, now, loops = __loops; + u64 bclock, now, loops = __loops; int cpu; preempt_disable(); cpu = smp_processor_id(); - rdtsc_barrier(); - rdtscl(bclock); + bclock = rdtsc_ordered(); for (;;) { - rdtsc_barrier(); - rdtscl(now); + now = rdtsc_ordered(); if ((now - bclock) >= loops) break; @@ -79,8 +77,7 @@ static void delay_tsc(unsigned long __loops) if (unlikely(cpu != smp_processor_id())) { loops -= (now - bclock); cpu = smp_processor_id(); - rdtsc_barrier(); - rdtscl(bclock); + bclock = rdtsc_ordered(); } } preempt_enable(); @@ -100,7 +97,7 @@ void use_tsc_delay(void) int read_current_timer(unsigned long *timer_val) { if (delay_fn == delay_tsc) { - rdtscll(*timer_val); + *timer_val = rdtsc(); return 0; } return -1; diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c index 8300db71c2a6..8db26591d91a 100644 --- a/arch/x86/math-emu/get_address.c +++ b/arch/x86/math-emu/get_address.c @@ -20,6 +20,7 @@ #include <linux/stddef.h> #include <asm/uaccess.h> +#include <asm/vm86.h> #include "fpu_system.h" #include "exception.h" diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 9dc909841739..eef44d9a3f77 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -20,6 +20,7 @@ #include <asm/kmemcheck.h> /* kmemcheck_*(), ... */ #include <asm/fixmap.h> /* VSYSCALL_ADDR */ #include <asm/vsyscall.h> /* emulate_vsyscall */ +#include <asm/vm86.h> /* struct vm86 */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> @@ -301,14 +302,16 @@ static inline void check_v8086_mode(struct pt_regs *regs, unsigned long address, struct task_struct *tsk) { +#ifdef CONFIG_VM86 unsigned long bit; - if (!v8086_mode(regs)) + if (!v8086_mode(regs) || !tsk->thread.vm86) return; bit = (address - 0xA0000) >> PAGE_SHIFT; if (bit < 32) - tsk->thread.screen_bitmap |= 1 << bit; + tsk->thread.vm86->screen_bitmap |= 1 << bit; +#endif } static bool low_pfn(unsigned long pfn) diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h index b9531d343134..755481f14d90 100644 --- a/arch/x86/um/asm/barrier.h +++ b/arch/x86/um/asm/barrier.h @@ -45,17 +45,4 @@ #define read_barrier_depends() do { } while (0) #define smp_read_barrier_depends() do { } while (0) -/* - * Stop RDTSC speculation. This is needed when you need to use RDTSC - * (or get_cycles or vread that possibly accesses the TSC) in a defined - * code region. - * - * (Could use an alternative three way for this if there was one.) - */ -static inline void rdtsc_barrier(void) -{ - alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, - "lfence", X86_FEATURE_LFENCE_RDTSC); -} - #endif diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 11d6fb4e8483..d9cfa452da9d 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1215,11 +1215,8 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .read_msr = xen_read_msr_safe, .write_msr = xen_write_msr_safe, - .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, - .read_tscp = native_read_tscp, - .iret = xen_iret, #ifdef CONFIG_X86_64 .usergs_sysret32 = xen_sysret32, |