diff options
Diffstat (limited to 'arch/x86/kernel/entry_64.S')
| -rw-r--r-- | arch/x86/kernel/entry_64.S | 286 |
1 files changed, 253 insertions, 33 deletions
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 556a8df522a7..8410e26f4183 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -51,16 +51,121 @@ #include <asm/page.h> #include <asm/irqflags.h> #include <asm/paravirt.h> +#include <asm/ftrace.h> .code64 +#ifdef CONFIG_FTRACE +#ifdef CONFIG_DYNAMIC_FTRACE +ENTRY(mcount) + + subq $0x38, %rsp + movq %rax, (%rsp) + movq %rcx, 8(%rsp) + movq %rdx, 16(%rsp) + movq %rsi, 24(%rsp) + movq %rdi, 32(%rsp) + movq %r8, 40(%rsp) + movq %r9, 48(%rsp) + + movq 0x38(%rsp), %rdi + subq $MCOUNT_INSN_SIZE, %rdi + +.globl mcount_call +mcount_call: + call ftrace_stub + + movq 48(%rsp), %r9 + movq 40(%rsp), %r8 + movq 32(%rsp), %rdi + movq 24(%rsp), %rsi + movq 16(%rsp), %rdx + movq 8(%rsp), %rcx + movq (%rsp), %rax + addq $0x38, %rsp + + retq +END(mcount) + +ENTRY(ftrace_caller) + + /* taken from glibc */ + subq $0x38, %rsp + movq %rax, (%rsp) + movq %rcx, 8(%rsp) + movq %rdx, 16(%rsp) + movq %rsi, 24(%rsp) + movq %rdi, 32(%rsp) + movq %r8, 40(%rsp) + movq %r9, 48(%rsp) + + movq 0x38(%rsp), %rdi + movq 8(%rbp), %rsi + subq $MCOUNT_INSN_SIZE, %rdi + +.globl ftrace_call +ftrace_call: + call ftrace_stub + + movq 48(%rsp), %r9 + movq 40(%rsp), %r8 + movq 32(%rsp), %rdi + movq 24(%rsp), %rsi + movq 16(%rsp), %rdx + movq 8(%rsp), %rcx + movq (%rsp), %rax + addq $0x38, %rsp + +.globl ftrace_stub +ftrace_stub: + retq +END(ftrace_caller) + +#else /* ! CONFIG_DYNAMIC_FTRACE */ +ENTRY(mcount) + cmpq $ftrace_stub, ftrace_trace_function + jnz trace +.globl ftrace_stub +ftrace_stub: + retq + +trace: + /* taken from glibc */ + subq $0x38, %rsp + movq %rax, (%rsp) + movq %rcx, 8(%rsp) + movq %rdx, 16(%rsp) + movq %rsi, 24(%rsp) + movq %rdi, 32(%rsp) + movq %r8, 40(%rsp) + movq %r9, 48(%rsp) + + movq 0x38(%rsp), %rdi + movq 8(%rbp), %rsi + subq $MCOUNT_INSN_SIZE, %rdi + + call *ftrace_trace_function + + movq 48(%rsp), %r9 + movq 40(%rsp), %r8 + movq 32(%rsp), %rdi + movq 24(%rsp), %rsi + movq 16(%rsp), %rdx + movq 8(%rsp), %rcx + movq (%rsp), %rax + addq $0x38, %rsp + + jmp ftrace_stub +END(mcount) +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_FTRACE */ + #ifndef CONFIG_PREEMPT #define retint_kernel retint_restore_args #endif #ifdef CONFIG_PARAVIRT -ENTRY(native_irq_enable_syscall_ret) - movq %gs:pda_oldrsp,%rsp +ENTRY(native_usergs_sysret64) swapgs sysretq #endif /* CONFIG_PARAVIRT */ @@ -104,7 +209,7 @@ ENTRY(native_irq_enable_syscall_ret) .macro FAKE_STACK_FRAME child_rip /* push in order ss, rsp, eflags, cs, rip */ xorl %eax, %eax - pushq %rax /* ss */ + pushq $__KERNEL_DS /* ss */ CFI_ADJUST_CFA_OFFSET 8 /*CFI_REL_OFFSET ss,0*/ pushq %rax /* rsp */ @@ -169,13 +274,13 @@ ENTRY(ret_from_fork) CFI_ADJUST_CFA_OFFSET -4 call schedule_tail GET_THREAD_INFO(%rcx) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),threadinfo_flags(%rcx) + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%rcx) jnz rff_trace rff_action: RESTORE_REST testl $3,CS-ARGOFFSET(%rsp) # from kernel_thread? je int_ret_from_sys_call - testl $_TIF_IA32,threadinfo_flags(%rcx) + testl $_TIF_IA32,TI_flags(%rcx) jnz int_ret_from_sys_call RESTORE_TOP_OF_STACK %rdi,ARGOFFSET jmp ret_from_sys_call @@ -244,7 +349,7 @@ ENTRY(system_call_after_swapgs) movq %rcx,RIP-ARGOFFSET(%rsp) CFI_REL_OFFSET rip,RIP-ARGOFFSET GET_THREAD_INFO(%rcx) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%rcx) + testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%rcx) jnz tracesys cmpq $__NR_syscall_max,%rax ja badsys @@ -263,7 +368,7 @@ sysret_check: GET_THREAD_INFO(%rcx) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - movl threadinfo_flags(%rcx),%edx + movl TI_flags(%rcx),%edx andl %edi,%edx jnz sysret_careful CFI_REMEMBER_STATE @@ -275,7 +380,8 @@ sysret_check: CFI_REGISTER rip,rcx RESTORE_ARGS 0,-ARG_SKIP,1 /*CFI_REGISTER rflags,r11*/ - ENABLE_INTERRUPTS_SYSCALL_RET + movq %gs:pda_oldrsp, %rsp + USERGS_SYSRET64 CFI_RESTORE_STATE /* Handle reschedules */ @@ -305,7 +411,7 @@ sysret_signal: leaq -ARGOFFSET(%rsp),%rdi # &pt_regs -> arg1 xorl %esi,%esi # oldset -> arg2 call ptregscall_common -1: movl $_TIF_NEED_RESCHED,%edi +1: movl $_TIF_WORK_MASK,%edi /* Use IRET because user could have changed frame. This works because ptregscall_common has called FIXUP_TOP_OF_STACK. */ DISABLE_INTERRUPTS(CLBR_NONE) @@ -323,7 +429,12 @@ tracesys: FIXUP_TOP_OF_STACK %rdi movq %rsp,%rdi call syscall_trace_enter - LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed it */ + /* + * Reload arg registers from stack in case ptrace changed them. + * We don't reload %rax because syscall_trace_enter() returned + * the value it wants us to use in the table lookup. + */ + LOAD_ARGS ARGOFFSET, 1 RESTORE_REST cmpq $__NR_syscall_max,%rax ja int_ret_from_sys_call /* RAX(%rsp) set to -ENOSYS above */ @@ -347,10 +458,10 @@ int_ret_from_sys_call: int_with_check: LOCKDEP_SYS_EXIT_IRQ GET_THREAD_INFO(%rcx) - movl threadinfo_flags(%rcx),%edx + movl TI_flags(%rcx),%edx andl %edi,%edx jnz int_careful - andl $~TS_COMPAT,threadinfo_status(%rcx) + andl $~TS_COMPAT,TI_status(%rcx) jmp retint_swapgs /* Either reschedule or signal or syscall exit tracking needed. */ @@ -376,7 +487,7 @@ int_very_careful: ENABLE_INTERRUPTS(CLBR_NONE) SAVE_REST /* Check for syscall exit trace */ - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP),%edx + testl $_TIF_WORK_SYSCALL_EXIT,%edx jz int_signal pushq %rdi CFI_ADJUST_CFA_OFFSET 8 @@ -384,7 +495,7 @@ int_very_careful: call syscall_trace_leave popq %rdi CFI_ADJUST_CFA_OFFSET -8 - andl $~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP),%edi + andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi jmp int_restore_rest int_signal: @@ -393,7 +504,7 @@ int_signal: movq %rsp,%rdi # &ptregs -> arg1 xorl %esi,%esi # oldset -> arg2 call do_notify_resume -1: movl $_TIF_NEED_RESCHED,%edi +1: movl $_TIF_WORK_MASK,%edi int_restore_rest: RESTORE_REST DISABLE_INTERRUPTS(CLBR_NONE) @@ -420,7 +531,6 @@ END(\label) PTREGSCALL stub_clone, sys_clone, %r8 PTREGSCALL stub_fork, sys_fork, %rdi PTREGSCALL stub_vfork, sys_vfork, %rdi - PTREGSCALL stub_rt_sigsuspend, sys_rt_sigsuspend, %rdx PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx PTREGSCALL stub_iopl, sys_iopl, %rsi @@ -559,7 +669,7 @@ retint_with_reschedule: movl $_TIF_WORK_MASK,%edi retint_check: LOCKDEP_SYS_EXIT_IRQ - movl threadinfo_flags(%rcx),%edx + movl TI_flags(%rcx),%edx andl %edi,%edx CFI_REMEMBER_STATE jnz retint_careful @@ -647,17 +757,16 @@ retint_signal: RESTORE_REST DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - movl $_TIF_NEED_RESCHED,%edi GET_THREAD_INFO(%rcx) - jmp retint_check + jmp retint_with_reschedule #ifdef CONFIG_PREEMPT /* Returning to kernel space. Check if we need preemption */ /* rcx: threadinfo. interrupts off. */ ENTRY(retint_kernel) - cmpl $0,threadinfo_preempt_count(%rcx) + cmpl $0,TI_preempt_count(%rcx) jnz retint_restore_args - bt $TIF_NEED_RESCHED,threadinfo_flags(%rcx) + bt $TIF_NEED_RESCHED,TI_flags(%rcx) jnc retint_restore_args bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */ jnc retint_restore_args @@ -711,6 +820,9 @@ END(invalidate_interrupt\num) ENTRY(call_function_interrupt) apicinterrupt CALL_FUNCTION_VECTOR,smp_call_function_interrupt END(call_function_interrupt) +ENTRY(call_function_single_interrupt) + apicinterrupt CALL_FUNCTION_SINGLE_VECTOR,smp_call_function_single_interrupt +END(call_function_single_interrupt) ENTRY(irq_move_cleanup_interrupt) apicinterrupt IRQ_MOVE_CLEANUP_VECTOR,smp_irq_move_cleanup_interrupt END(irq_move_cleanup_interrupt) @@ -720,6 +832,10 @@ ENTRY(apic_timer_interrupt) apicinterrupt LOCAL_TIMER_VECTOR,smp_apic_timer_interrupt END(apic_timer_interrupt) +ENTRY(uv_bau_message_intr1) + apicinterrupt 220,uv_bau_message_interrupt +END(uv_bau_message_intr1) + ENTRY(error_interrupt) apicinterrupt ERROR_APIC_VECTOR,smp_error_interrupt END(error_interrupt) @@ -733,6 +849,7 @@ END(spurious_interrupt) */ .macro zeroentry sym INTR_FRAME + PARAVIRT_ADJUST_EXCEPTION_FRAME pushq $0 /* push error code/oldrax */ CFI_ADJUST_CFA_OFFSET 8 pushq %rax /* push real oldrax to the rdi slot */ @@ -745,6 +862,7 @@ END(spurious_interrupt) .macro errorentry sym XCPT_FRAME + PARAVIRT_ADJUST_EXCEPTION_FRAME pushq %rax CFI_ADJUST_CFA_OFFSET 8 CFI_REL_OFFSET rax,0 @@ -814,7 +932,7 @@ paranoid_restore\trace: jmp irq_return paranoid_userspace\trace: GET_THREAD_INFO(%rcx) - movl threadinfo_flags(%rcx),%ebx + movl TI_flags(%rcx),%ebx andl $_TIF_WORK_MASK,%ebx jz paranoid_swapgs\trace movq %rsp,%rdi /* &pt_regs */ @@ -912,7 +1030,7 @@ error_exit: testl %eax,%eax jne retint_kernel LOCKDEP_SYS_EXIT_IRQ - movl threadinfo_flags(%rcx),%edx + movl TI_flags(%rcx),%edx movl $_TIF_WORK_MASK,%edi andl %edi,%edx jnz retint_careful @@ -926,11 +1044,11 @@ error_kernelspace: iret run with kernel gs again, so don't set the user space flag. B stepping K8s sometimes report an truncated RIP for IRET exceptions returning to compat mode. Check for these here too. */ - leaq irq_return(%rip),%rbp - cmpq %rbp,RIP(%rsp) + leaq irq_return(%rip),%rcx + cmpq %rcx,RIP(%rsp) je error_swapgs - movl %ebp,%ebp /* zero extend */ - cmpq %rbp,RIP(%rsp) + movl %ecx,%ecx /* zero extend */ + cmpq %rcx,RIP(%rsp) je error_swapgs cmpq $gs_change,RIP(%rsp) je error_swapgs @@ -939,7 +1057,7 @@ KPROBE_END(error_entry) /* Reload gs selector with exception handling */ /* edi: new selector */ -ENTRY(load_gs_index) +ENTRY(native_load_gs_index) CFI_STARTPROC pushf CFI_ADJUST_CFA_OFFSET 8 @@ -953,7 +1071,7 @@ gs_change: CFI_ADJUST_CFA_OFFSET -8 ret CFI_ENDPROC -ENDPROC(load_gs_index) +ENDPROC(native_load_gs_index) .section __ex_table,"a" .align 8 @@ -1075,6 +1193,7 @@ END(device_not_available) /* runs on exception stack */ KPROBE_ENTRY(debug) INTR_FRAME + PARAVIRT_ADJUST_EXCEPTION_FRAME pushq $0 CFI_ADJUST_CFA_OFFSET 8 paranoidentry do_debug, DEBUG_STACK @@ -1084,6 +1203,7 @@ KPROBE_END(debug) /* runs on exception stack */ KPROBE_ENTRY(nmi) INTR_FRAME + PARAVIRT_ADJUST_EXCEPTION_FRAME pushq $-1 CFI_ADJUST_CFA_OFFSET 8 paranoidentry do_nmi, 0, 0 @@ -1097,6 +1217,7 @@ KPROBE_END(nmi) KPROBE_ENTRY(int3) INTR_FRAME + PARAVIRT_ADJUST_EXCEPTION_FRAME pushq $0 CFI_ADJUST_CFA_OFFSET 8 paranoidentry do_int3, DEBUG_STACK @@ -1120,13 +1241,10 @@ ENTRY(coprocessor_segment_overrun) zeroentry do_coprocessor_segment_overrun END(coprocessor_segment_overrun) -ENTRY(reserved) - zeroentry do_reserved -END(reserved) - /* runs on exception stack */ ENTRY(double_fault) XCPT_FRAME + PARAVIRT_ADJUST_EXCEPTION_FRAME paranoidentry do_double_fault jmp paranoid_exit1 CFI_ENDPROC @@ -1143,6 +1261,7 @@ END(segment_not_present) /* runs on exception stack */ ENTRY(stack_segment) XCPT_FRAME + PARAVIRT_ADJUST_EXCEPTION_FRAME paranoidentry do_stack_segment jmp paranoid_exit1 CFI_ENDPROC @@ -1168,6 +1287,7 @@ END(spurious_interrupt_bug) /* runs on exception stack */ ENTRY(machine_check) INTR_FRAME + PARAVIRT_ADJUST_EXCEPTION_FRAME pushq $0 CFI_ADJUST_CFA_OFFSET 8 paranoidentry do_machine_check @@ -1202,3 +1322,103 @@ KPROBE_ENTRY(ignore_sysret) sysret CFI_ENDPROC ENDPROC(ignore_sysret) + +#ifdef CONFIG_XEN +ENTRY(xen_hypervisor_callback) + zeroentry xen_do_hypervisor_callback +END(xen_hypervisor_callback) + +/* +# A note on the "critical region" in our callback handler. +# We want to avoid stacking callback handlers due to events occurring +# during handling of the last event. To do this, we keep events disabled +# until we've done all processing. HOWEVER, we must enable events before +# popping the stack frame (can't be done atomically) and so it would still +# be possible to get enough handler activations to overflow the stack. +# Although unlikely, bugs of that kind are hard to track down, so we'd +# like to avoid the possibility. +# So, on entry to the handler we detect whether we interrupted an +# existing activation in its critical region -- if so, we pop the current +# activation and restart the handler using the previous one. +*/ +ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs) + CFI_STARTPROC +/* Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will + see the correct pointer to the pt_regs */ + movq %rdi, %rsp # we don't return, adjust the stack frame + CFI_ENDPROC + CFI_DEFAULT_STACK +11: incl %gs:pda_irqcount + movq %rsp,%rbp + CFI_DEF_CFA_REGISTER rbp + cmovzq %gs:pda_irqstackptr,%rsp + pushq %rbp # backlink for old unwinder + call xen_evtchn_do_upcall + popq %rsp + CFI_DEF_CFA_REGISTER rsp + decl %gs:pda_irqcount + jmp error_exit + CFI_ENDPROC +END(do_hypervisor_callback) + +/* +# Hypervisor uses this for application faults while it executes. +# We get here for two reasons: +# 1. Fault while reloading DS, ES, FS or GS +# 2. Fault while executing IRET +# Category 1 we do not need to fix up as Xen has already reloaded all segment +# registers that could be reloaded and zeroed the others. +# Category 2 we fix up by killing the current process. We cannot use the +# normal Linux return path in this case because if we use the IRET hypercall +# to pop the stack frame we end up in an infinite loop of failsafe callbacks. +# We distinguish between categories by comparing each saved segment register +# with its current contents: any discrepancy means we in category 1. +*/ +ENTRY(xen_failsafe_callback) + framesz = (RIP-0x30) /* workaround buggy gas */ + _frame framesz + CFI_REL_OFFSET rcx, 0 + CFI_REL_OFFSET r11, 8 + movw %ds,%cx + cmpw %cx,0x10(%rsp) + CFI_REMEMBER_STATE + jne 1f + movw %es,%cx + cmpw %cx,0x18(%rsp) + jne 1f + movw %fs,%cx + cmpw %cx,0x20(%rsp) + jne 1f + movw %gs,%cx + cmpw %cx,0x28(%rsp) + jne 1f + /* All segments match their saved values => Category 2 (Bad IRET). */ + movq (%rsp),%rcx + CFI_RESTORE rcx + movq 8(%rsp),%r11 + CFI_RESTORE r11 + addq $0x30,%rsp + CFI_ADJUST_CFA_OFFSET -0x30 + pushq $0 + CFI_ADJUST_CFA_OFFSET 8 + pushq %r11 + CFI_ADJUST_CFA_OFFSET 8 + pushq %rcx + CFI_ADJUST_CFA_OFFSET 8 + jmp general_protection + CFI_RESTORE_STATE +1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */ + movq (%rsp),%rcx + CFI_RESTORE rcx + movq 8(%rsp),%r11 + CFI_RESTORE r11 + addq $0x30,%rsp + CFI_ADJUST_CFA_OFFSET -0x30 + pushq $0 + CFI_ADJUST_CFA_OFFSET 8 + SAVE_ALL + jmp error_exit + CFI_ENDPROC +END(xen_failsafe_callback) + +#endif /* CONFIG_XEN */ |