diff options
Diffstat (limited to 'arch/x86/kernel/entry_32.S')
| -rw-r--r-- | arch/x86/kernel/entry_32.S | 319 |
1 files changed, 177 insertions, 142 deletions
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 623f2883747..0d0c9d4ab6d 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -57,6 +57,7 @@ #include <asm/cpufeature.h> #include <asm/alternative-asm.h> #include <asm/asm.h> +#include <asm/smap.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ #include <linux/elf-em.h> @@ -298,10 +299,21 @@ ENTRY(ret_from_fork) CFI_ENDPROC END(ret_from_fork) -/* - * Interrupt exit functions should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" +ENTRY(ret_from_kernel_thread) + CFI_STARTPROC + pushl_cfi %eax + call schedule_tail + GET_THREAD_INFO(%ebp) + popl_cfi %eax + pushl_cfi $0x0202 # Reset kernel eflags + popfl_cfi + movl PT_EBP(%esp),%eax + call *PT_EBX(%esp) + movl $0,PT_EAX(%esp) + jmp syscall_exit + CFI_ENDPROC +ENDPROC(ret_from_kernel_thread) + /* * Return to user mode is not as complex as all this looks, * but we want the default path for a system call return to @@ -322,8 +334,7 @@ ret_from_intr: andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax #else /* - * We can be coming here from a syscall done in the kernel space, - * e.g. a failed kernel_execve(). + * We can be coming here from child spawned by kernel_thread(). */ movl PT_CS(%esp), %eax andl $SEGMENT_RPL_MASK, %eax @@ -347,12 +358,9 @@ END(ret_from_exception) #ifdef CONFIG_PREEMPT ENTRY(resume_kernel) DISABLE_INTERRUPTS(CLBR_ANY) - cmpl $0,TI_preempt_count(%ebp) # non-zero preempt_count ? - jnz restore_all need_resched: - movl TI_flags(%ebp), %ecx # need_resched set ? - testb $_TIF_NEED_RESCHED, %cl - jz restore_all + cmpl $0,PER_CPU_VAR(__preempt_count) + jnz restore_all testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ? jz restore_all call preempt_schedule_irq @@ -360,10 +368,6 @@ need_resched: END(resume_kernel) #endif CFI_ENDPROC -/* - * End of kprobes section - */ - .popsection /* SYSENTER_RETURN points to after the "sysenter" instruction in the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */ @@ -407,7 +411,9 @@ sysenter_past_esp: */ cmpl $__PAGE_OFFSET-3,%ebp jae syscall_fault + ASM_STAC 1: movl (%ebp),%ebp + ASM_CLAC movl %ebp,PT_EBP(%esp) _ASM_EXTABLE(1b,syscall_fault) @@ -417,8 +423,9 @@ sysenter_past_esp: jnz sysenter_audit sysenter_do_call: cmpl $(NR_syscalls), %eax - jae syscall_badsys + jae sysenter_badsys call *sys_call_table(,%eax,4) +sysenter_after_call: movl %eax,PT_EAX(%esp) LOCKDEP_SYS_EXIT DISABLE_INTERRUPTS(CLBR_ANY) @@ -481,13 +488,10 @@ sysexit_audit: PTGS_TO_GS_EX ENDPROC(ia32_sysenter_target) -/* - * syscall stub including irq exit should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" # system call handler stub ENTRY(system_call) RING0_INT_FRAME # can't unwind into user space anyway + ASM_CLAC pushl_cfi %eax # save orig_eax SAVE_ALL GET_THREAD_INFO(%ebp) @@ -498,6 +502,7 @@ ENTRY(system_call) jae syscall_badsys syscall_call: call *sys_call_table(,%eax,4) +syscall_after_call: movl %eax,PT_EAX(%esp) # store the return value syscall_exit: LOCKDEP_SYS_EXIT @@ -512,6 +517,7 @@ syscall_exit: restore_all: TRACE_IRQS_IRET restore_all_notrace: +#ifdef CONFIG_X86_ESPFIX32 movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS # Warning: PT_OLDSS(%esp) contains the wrong/random values if we # are returning to the kernel. @@ -522,6 +528,7 @@ restore_all_notrace: cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax CFI_REMEMBER_STATE je ldt_ss # returning to user-space with LDT SS +#endif restore_nocheck: RESTORE_REGS 4 # skip orig_eax/error_code irq_return: @@ -534,13 +541,9 @@ ENTRY(iret_exc) .previous _ASM_EXTABLE(irq_return,iret_exc) +#ifdef CONFIG_X86_ESPFIX32 CFI_RESTORE_STATE ldt_ss: - larl PT_OLDSS(%esp), %eax - jnz restore_nocheck - testl $0x00400000, %eax # returning to 32bit stack? - jnz restore_nocheck # allright, normal return - #ifdef CONFIG_PARAVIRT /* * The kernel can't run on a non-flat stack if paravirt mode @@ -582,6 +585,7 @@ ldt_ss: lss (%esp), %esp /* switch to espfix segment */ CFI_ADJUST_CFA_OFFSET -8 jmp restore_nocheck +#endif CFI_ENDPROC ENDPROC(system_call) @@ -612,6 +616,10 @@ work_notifysig: # deal with pending signals and movl %esp, %eax jne 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 @@ -622,24 +630,15 @@ work_notifysig: # deal with pending signals and call do_notify_resume jmp resume_userspace +#ifdef CONFIG_VM86 ALIGN work_notifysig_v86: pushl_cfi %ecx # save ti_flags for do_notify_resume call save_v86_state # %eax contains pt_regs pointer popl_cfi %ecx movl %eax, %esp -#else - movl %esp, %eax + jmp 1b #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 END(work_pending) # perform syscall exit tracing @@ -670,85 +669,22 @@ END(syscall_exit_work) RING0_INT_FRAME # can't unwind into user space anyway syscall_fault: + ASM_CLAC GET_THREAD_INFO(%ebp) movl $-EFAULT,PT_EAX(%esp) jmp resume_userspace END(syscall_fault) syscall_badsys: - movl $-ENOSYS,PT_EAX(%esp) - jmp resume_userspace + movl $-ENOSYS,%eax + jmp syscall_after_call END(syscall_badsys) - CFI_ENDPROC -/* - * End of kprobes section - */ - .popsection -/* - * System calls that need a pt_regs pointer. - */ -#define PTREGSCALL0(name) \ -ENTRY(ptregs_##name) ; \ - leal 4(%esp),%eax; \ - jmp sys_##name; \ -ENDPROC(ptregs_##name) - -#define PTREGSCALL1(name) \ -ENTRY(ptregs_##name) ; \ - leal 4(%esp),%edx; \ - movl (PT_EBX+4)(%esp),%eax; \ - jmp sys_##name; \ -ENDPROC(ptregs_##name) - -#define PTREGSCALL2(name) \ -ENTRY(ptregs_##name) ; \ - leal 4(%esp),%ecx; \ - movl (PT_ECX+4)(%esp),%edx; \ - movl (PT_EBX+4)(%esp),%eax; \ - jmp sys_##name; \ -ENDPROC(ptregs_##name) - -#define PTREGSCALL3(name) \ -ENTRY(ptregs_##name) ; \ - CFI_STARTPROC; \ - leal 4(%esp),%eax; \ - pushl_cfi %eax; \ - movl PT_EDX(%eax),%ecx; \ - movl PT_ECX(%eax),%edx; \ - movl PT_EBX(%eax),%eax; \ - call sys_##name; \ - addl $4,%esp; \ - CFI_ADJUST_CFA_OFFSET -4; \ - ret; \ - CFI_ENDPROC; \ -ENDPROC(ptregs_##name) - -PTREGSCALL1(iopl) -PTREGSCALL0(fork) -PTREGSCALL0(vfork) -PTREGSCALL3(execve) -PTREGSCALL2(sigaltstack) -PTREGSCALL0(sigreturn) -PTREGSCALL0(rt_sigreturn) -PTREGSCALL2(vm86) -PTREGSCALL1(vm86old) - -/* Clone is an oddball. The 4th arg is in %edi */ -ENTRY(ptregs_clone) - CFI_STARTPROC - leal 4(%esp),%eax - pushl_cfi %eax - pushl_cfi PT_EDI(%eax) - movl PT_EDX(%eax),%ecx - movl PT_ECX(%eax),%edx - movl PT_EBX(%eax),%eax - call sys_clone - addl $8,%esp - CFI_ADJUST_CFA_OFFSET -8 - ret +sysenter_badsys: + movl $-ENOSYS,%eax + jmp sysenter_after_call +END(syscall_badsys) CFI_ENDPROC -ENDPROC(ptregs_clone) .macro FIXUP_ESPFIX_STACK /* @@ -758,6 +694,7 @@ ENDPROC(ptregs_clone) * the high word of the segment base from the GDT and swiches to the * normal stack and adjusts ESP with the matching offset. */ +#ifdef CONFIG_X86_ESPFIX32 /* fixup the stack */ mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ @@ -767,8 +704,10 @@ ENDPROC(ptregs_clone) pushl_cfi %eax lss (%esp), %esp /* switch to the normal stack segment */ CFI_ADJUST_CFA_OFFSET -8 +#endif .endm .macro UNWIND_ESPFIX_STACK +#ifdef CONFIG_X86_ESPFIX32 movl %ss, %eax /* see if on espfix stack */ cmpw $__ESPFIX_SS, %ax @@ -779,6 +718,7 @@ ENDPROC(ptregs_clone) /* switch to normal stack */ FIXUP_ESPFIX_STACK 27: +#endif .endm /* @@ -825,6 +765,7 @@ END(interrupt) */ .p2align CONFIG_X86_L1_CACHE_SHIFT common_interrupt: + ASM_CLAC addl $-0x80,(%esp) /* Adjust vector into the [-256,-1] range */ SAVE_ALL TRACE_IRQS_OFF @@ -834,13 +775,10 @@ common_interrupt: ENDPROC(common_interrupt) CFI_ENDPROC -/* - * Irq entries should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" #define BUILD_INTERRUPT3(name, nr, fn) \ ENTRY(name) \ RING0_INT_FRAME; \ + ASM_CLAC; \ pushl_cfi $~(nr); \ SAVE_ALL; \ TRACE_IRQS_OFF \ @@ -850,13 +788,24 @@ ENTRY(name) \ CFI_ENDPROC; \ ENDPROC(name) -#define BUILD_INTERRUPT(name, nr) BUILD_INTERRUPT3(name, nr, smp_##name) + +#ifdef CONFIG_TRACING +#define TRACE_BUILD_INTERRUPT(name, nr) \ + BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name) +#else +#define TRACE_BUILD_INTERRUPT(name, nr) +#endif + +#define BUILD_INTERRUPT(name, nr) \ + BUILD_INTERRUPT3(name, nr, smp_##name); \ + TRACE_BUILD_INTERRUPT(name, nr) /* The include is where all of the SMP etc. interrupts come from */ #include <asm/entry_arch.h> ENTRY(coprocessor_error) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_coprocessor_error jmp error_code @@ -865,6 +814,7 @@ END(coprocessor_error) ENTRY(simd_coprocessor_error) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 #ifdef CONFIG_X86_INVD_BUG /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */ @@ -886,6 +836,7 @@ END(simd_coprocessor_error) ENTRY(device_not_available) RING0_INT_FRAME + ASM_CLAC pushl_cfi $-1 # mark this as an int pushl_cfi $do_device_not_available jmp error_code @@ -906,6 +857,7 @@ END(native_irq_enable_sysexit) ENTRY(overflow) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_overflow jmp error_code @@ -914,6 +866,7 @@ END(overflow) ENTRY(bounds) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_bounds jmp error_code @@ -922,6 +875,7 @@ END(bounds) ENTRY(invalid_op) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_invalid_op jmp error_code @@ -930,6 +884,7 @@ END(invalid_op) ENTRY(coprocessor_segment_overrun) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_coprocessor_segment_overrun jmp error_code @@ -938,6 +893,7 @@ END(coprocessor_segment_overrun) ENTRY(invalid_TSS) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_invalid_TSS jmp error_code CFI_ENDPROC @@ -945,6 +901,7 @@ END(invalid_TSS) ENTRY(segment_not_present) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_segment_not_present jmp error_code CFI_ENDPROC @@ -952,6 +909,7 @@ END(segment_not_present) ENTRY(stack_segment) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_stack_segment jmp error_code CFI_ENDPROC @@ -959,6 +917,7 @@ END(stack_segment) ENTRY(alignment_check) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_alignment_check jmp error_code CFI_ENDPROC @@ -966,6 +925,7 @@ END(alignment_check) ENTRY(divide_error) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 # no error code pushl_cfi $do_divide_error jmp error_code @@ -975,6 +935,7 @@ END(divide_error) #ifdef CONFIG_X86_MCE ENTRY(machine_check) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi machine_check_vector jmp error_code @@ -984,25 +945,12 @@ END(machine_check) ENTRY(spurious_interrupt_bug) RING0_INT_FRAME + ASM_CLAC pushl_cfi $0 pushl_cfi $do_spurious_interrupt_bug jmp error_code CFI_ENDPROC END(spurious_interrupt_bug) -/* - * End of kprobes section - */ - .popsection - -ENTRY(kernel_thread_helper) - pushl $0 # fake return address for unwinder - CFI_STARTPROC - movl %edi,%eax - call *%esi - call do_exit - ud2 # padding for call trace - CFI_ENDPROC -ENDPROC(kernel_thread_helper) #ifdef CONFIG_XEN /* Xen doesn't set %esp to be precisely what the normal sysenter @@ -1016,7 +964,7 @@ ENTRY(xen_sysenter_target) ENTRY(xen_hypervisor_callback) CFI_STARTPROC - pushl_cfi $0 + pushl_cfi $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL TRACE_IRQS_OFF @@ -1058,14 +1006,15 @@ ENTRY(xen_failsafe_callback) 2: mov 8(%esp),%es 3: mov 12(%esp),%fs 4: mov 16(%esp),%gs + /* EAX == 0 => Category 1 (Bad segment) + EAX != 0 => Category 2 (Bad IRET) */ testl %eax,%eax popl_cfi %eax lea 16(%esp),%esp CFI_ADJUST_CFA_OFFSET -16 jz 5f - addl $16,%esp - jmp iret_exc # EAX != 0 => Category 2 (Bad IRET) -5: pushl_cfi $0 # EAX == 0 => Category 1 (Bad segment) + jmp iret_exc +5: pushl_cfi $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL jmp ret_from_exception CFI_ENDPROC @@ -1090,11 +1039,18 @@ ENTRY(xen_failsafe_callback) _ASM_EXTABLE(4b,9b) ENDPROC(xen_failsafe_callback) -BUILD_INTERRUPT3(xen_hvm_callback_vector, XEN_HVM_EVTCHN_CALLBACK, +BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR, xen_evtchn_do_upcall) #endif /* CONFIG_XEN */ +#if IS_ENABLED(CONFIG_HYPERV) + +BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR, + hyperv_vector_handler) + +#endif /* CONFIG_HYPERV */ + #ifdef CONFIG_FUNCTION_TRACER #ifdef CONFIG_DYNAMIC_FTRACE @@ -1109,17 +1065,21 @@ ENTRY(ftrace_caller) pushl %eax pushl %ecx pushl %edx - movl 0xc(%esp), %eax + pushl $0 /* Pass NULL as regs pointer */ + movl 4*4(%esp), %eax movl 0x4(%ebp), %edx + movl function_trace_op, %ecx subl $MCOUNT_INSN_SIZE, %eax .globl ftrace_call ftrace_call: call ftrace_stub + addl $4,%esp /* skip NULL pointer */ popl %edx popl %ecx popl %eax +ftrace_ret: #ifdef CONFIG_FUNCTION_GRAPH_TRACER .globl ftrace_graph_call ftrace_graph_call: @@ -1131,9 +1091,77 @@ ftrace_stub: ret END(ftrace_caller) +ENTRY(ftrace_regs_caller) + pushf /* push flags before compare (in cs location) */ + cmpl $0, function_trace_stop + jne ftrace_restore_flags + + /* + * i386 does not save SS and ESP when coming from kernel. + * Instead, to get sp, ®s->sp is used (see ptrace.h). + * Unfortunately, that means eflags must be at the same location + * as the current return ip is. We move the return ip into the + * ip location, and move flags into the return ip location. + */ + pushl 4(%esp) /* save return ip into ip slot */ + + pushl $0 /* Load 0 into orig_ax */ + pushl %gs + pushl %fs + pushl %es + pushl %ds + pushl %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx + + movl 13*4(%esp), %eax /* Get the saved flags */ + movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */ + /* clobbering return ip */ + movl $__KERNEL_CS,13*4(%esp) + + movl 12*4(%esp), %eax /* Load ip (1st parameter) */ + subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ + movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ + movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ + pushl %esp /* Save pt_regs as 4th parameter */ + +GLOBAL(ftrace_regs_call) + call ftrace_stub + + addl $4, %esp /* Skip pt_regs */ + movl 14*4(%esp), %eax /* Move flags back into cs */ + movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */ + movl 12*4(%esp), %eax /* Get return ip from regs->ip */ + movl %eax, 14*4(%esp) /* Put return ip back for ret */ + + popl %ebx + popl %ecx + popl %edx + popl %esi + popl %edi + popl %ebp + popl %eax + popl %ds + popl %es + popl %fs + popl %gs + addl $8, %esp /* Skip orig_ax and ip */ + popf /* Pop flags at end (no addl to corrupt flags) */ + jmp ftrace_ret + +ftrace_restore_flags: + popf + jmp ftrace_stub #else /* ! CONFIG_DYNAMIC_FTRACE */ ENTRY(mcount) + cmpl $__PAGE_OFFSET, %esp + jb ftrace_stub /* Paging not enabled yet? */ + cmpl $0, function_trace_stop jne ftrace_stub @@ -1171,9 +1199,6 @@ END(mcount) #ifdef CONFIG_FUNCTION_GRAPH_TRACER ENTRY(ftrace_graph_caller) - cmpl $0, function_trace_stop - jne ftrace_stub - pushl %eax pushl %ecx pushl %edx @@ -1200,13 +1225,19 @@ return_to_handler: jmp *%ecx #endif -/* - * Some functions should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" +#ifdef CONFIG_TRACING +ENTRY(trace_page_fault) + RING0_EC_FRAME + ASM_CLAC + pushl_cfi $trace_do_page_fault + jmp error_code + CFI_ENDPROC +END(trace_page_fault) +#endif ENTRY(page_fault) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_page_fault ALIGN error_code: @@ -1279,6 +1310,7 @@ END(page_fault) ENTRY(debug) RING0_INT_FRAME + ASM_CLAC cmpl $ia32_sysenter_target,(%esp) jne debug_stack_correct FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn @@ -1303,11 +1335,14 @@ END(debug) */ ENTRY(nmi) RING0_INT_FRAME + ASM_CLAC +#ifdef CONFIG_X86_ESPFIX32 pushl_cfi %eax movl %ss, %eax cmpw $__ESPFIX_SS, %ax popl_cfi %eax je nmi_espfix_stack +#endif cmpl $ia32_sysenter_target,(%esp) je nmi_stack_fixup pushl_cfi %eax @@ -1347,6 +1382,7 @@ nmi_debug_stack_check: FIX_STACK 24, nmi_stack_correct, 1 jmp nmi_stack_correct +#ifdef CONFIG_X86_ESPFIX32 nmi_espfix_stack: /* We have a RING0_INT_FRAME here. * @@ -1368,11 +1404,13 @@ nmi_espfix_stack: lss 12+4(%esp), %esp # back to espfix stack CFI_ADJUST_CFA_OFFSET -24 jmp irq_return +#endif CFI_ENDPROC END(nmi) ENTRY(int3) RING0_INT_FRAME + ASM_CLAC pushl_cfi $-1 # mark this as an int SAVE_ALL TRACE_IRQS_OFF @@ -1393,13 +1431,10 @@ END(general_protection) #ifdef CONFIG_KVM_GUEST ENTRY(async_page_fault) RING0_EC_FRAME + ASM_CLAC pushl_cfi $do_async_page_fault jmp error_code CFI_ENDPROC END(async_page_fault) #endif -/* - * End of kprobes section - */ - .popsection |
