diff options
Diffstat (limited to 'arch/x86/kernel/entry_64.S')
| -rw-r--r-- | arch/x86/kernel/entry_64.S | 298 |
1 files changed, 253 insertions, 45 deletions
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index a20e1cb9dc8..cdc79b5cfcd 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -55,6 +55,7 @@ #include <asm/paravirt.h> #include <asm/ftrace.h> #include <asm/percpu.h> +#include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ #include <linux/elf-em.h> @@ -319,7 +320,7 @@ ENDPROC(native_usergs_sysret64) movq %rsp, %rsi leaq -RBP(%rsp),%rdi /* arg1 for handler */ - testl $3, CS(%rdi) + testl $3, CS-RBP(%rsi) je 1f SWAPGS /* @@ -329,11 +330,10 @@ ENDPROC(native_usergs_sysret64) * moving irq_enter into assembly, which would be too much work) */ 1: incl PER_CPU_VAR(irq_count) - jne 2f - mov PER_CPU_VAR(irq_stack_ptr),%rsp + cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp CFI_DEF_CFA_REGISTER rsi -2: /* Store previous stack value */ + /* Store previous stack value */ pushq %rsi CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \ 0x77 /* DW_OP_breg7 */, 0, \ @@ -481,7 +481,12 @@ GLOBAL(system_call_after_swapgs) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) jnz tracesys system_call_fastpath: +#if __SYSCALL_MASK == ~0 cmpq $__NR_syscall_max,%rax +#else + andl $__SYSCALL_MASK,%eax + cmpl $__NR_syscall_max,%eax +#endif ja badsys movq %r10,%rcx call *sys_call_table(,%rax,8) # XXX: rip relative @@ -548,7 +553,7 @@ badsys: #ifdef CONFIG_AUDITSYSCALL /* * Fast path for syscall audit without full syscall trace. - * We just call audit_syscall_entry() directly, and then + * We just call __audit_syscall_entry() directly, and then * jump back to the normal fast path. */ auditsys: @@ -558,22 +563,21 @@ auditsys: movq %rdi,%rdx /* 3rd arg: 1st syscall arg */ movq %rax,%rsi /* 2nd arg: syscall number */ movl $AUDIT_ARCH_X86_64,%edi /* 1st arg: audit arch */ - call audit_syscall_entry + call __audit_syscall_entry LOAD_ARGS 0 /* reload call-clobbered registers */ jmp system_call_fastpath /* - * Return fast path for syscall audit. Call audit_syscall_exit() + * Return fast path for syscall audit. Call __audit_syscall_exit() * directly and then jump back to the fast path with TIF_SYSCALL_AUDIT * masked off. */ sysret_audit: movq RAX-ARGOFFSET(%rsp),%rsi /* second arg, syscall return value */ - cmpq $0,%rsi /* is it < 0? */ - setl %al /* 1 if so, 0 if not */ + cmpq $-MAX_ERRNO,%rsi /* is it < -MAX_ERRNO? */ + setbe %al /* 1 if so, 0 if not */ movzbl %al,%edi /* zero-extend that into %edi */ - inc %edi /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */ - call audit_syscall_exit + call __audit_syscall_exit movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi jmp sysret_check #endif /* CONFIG_AUDITSYSCALL */ @@ -596,7 +600,12 @@ tracesys: */ LOAD_ARGS ARGOFFSET, 1 RESTORE_REST +#if __SYSCALL_MASK == ~0 cmpq $__NR_syscall_max,%rax +#else + andl $__SYSCALL_MASK,%eax + cmpl $__NR_syscall_max,%eax +#endif ja int_ret_from_sys_call /* RAX(%rsp) set to -ENOSYS above */ movq %r10,%rcx /* fixup for C */ call *sys_call_table(,%rax,8) @@ -736,6 +745,40 @@ ENTRY(stub_rt_sigreturn) CFI_ENDPROC END(stub_rt_sigreturn) +#ifdef CONFIG_X86_X32_ABI + PTREGSCALL stub_x32_sigaltstack, sys32_sigaltstack, %rdx + +ENTRY(stub_x32_rt_sigreturn) + CFI_STARTPROC + addq $8, %rsp + PARTIAL_FRAME 0 + SAVE_REST + movq %rsp,%rdi + FIXUP_TOP_OF_STACK %r11 + call sys32_x32_rt_sigreturn + movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer + RESTORE_REST + jmp int_ret_from_sys_call + CFI_ENDPROC +END(stub_x32_rt_sigreturn) + +ENTRY(stub_x32_execve) + CFI_STARTPROC + addq $8, %rsp + PARTIAL_FRAME 0 + SAVE_REST + FIXUP_TOP_OF_STACK %r11 + movq %rsp, %rcx + call sys32_execve + RESTORE_TOP_OF_STACK %r11 + movq %rax,RAX(%rsp) + RESTORE_REST + jmp int_ret_from_sys_call + CFI_ENDPROC +END(stub_x32_execve) + +#endif + /* * Build the entry stubs and pointer table with some assembler magic. * We pack 7 stubs into a single 32-byte chunk, which will fit in a @@ -813,7 +856,7 @@ ret_from_intr: /* Restore saved previous stack */ popq %rsi - CFI_DEF_CFA_REGISTER rsi + CFI_DEF_CFA rsi,SS+8-RBP /* reg/off reset after def_cfa_expr */ leaq ARGOFFSET-RBP(%rsi), %rsp CFI_DEF_CFA_REGISTER rsp CFI_ADJUST_CFA_OFFSET RBP-ARGOFFSET @@ -1480,60 +1523,225 @@ ENTRY(error_exit) CFI_ENDPROC END(error_exit) +/* + * Test if a given stack is an NMI stack or not. + */ + .macro test_in_nmi reg stack nmi_ret normal_ret + cmpq %\reg, \stack + ja \normal_ret + subq $EXCEPTION_STKSZ, %\reg + cmpq %\reg, \stack + jb \normal_ret + jmp \nmi_ret + .endm /* runs on exception stack */ ENTRY(nmi) INTR_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq_cfi $-1 + /* + * We allow breakpoints in NMIs. If a breakpoint occurs, then + * the iretq it performs will take us out of NMI context. + * This means that we can have nested NMIs where the next + * NMI is using the top of the stack of the previous NMI. We + * can't let it execute because the nested NMI will corrupt the + * stack of the previous NMI. NMI handlers are not re-entrant + * anyway. + * + * To handle this case we do the following: + * Check the a special location on the stack that contains + * a variable that is set when NMIs are executing. + * The interrupted task's stack is also checked to see if it + * is an NMI stack. + * If the variable is not set and the stack is not the NMI + * stack then: + * o Set the special variable on the stack + * o Copy the interrupt frame into a "saved" location on the stack + * o Copy the interrupt frame into a "copy" location on the stack + * o Continue processing the NMI + * If the variable is set or the previous stack is the NMI stack: + * o Modify the "copy" location to jump to the repeate_nmi + * o return back to the first NMI + * + * Now on exit of the first NMI, we first clear the stack variable + * The NMI stack will tell any nested NMIs at that point that it is + * nested. Then we pop the stack normally with iret, and if there was + * a nested NMI that updated the copy interrupt stack frame, a + * jump will be made to the repeat_nmi code that will handle the second + * NMI. + */ + + /* Use %rdx as out temp variable throughout */ + pushq_cfi %rdx + CFI_REL_OFFSET rdx, 0 + + /* + * If %cs was not the kernel segment, then the NMI triggered in user + * space, which means it is definitely not nested. + */ + cmpl $__KERNEL_CS, 16(%rsp) + jne first_nmi + + /* + * Check the special variable on the stack to see if NMIs are + * executing. + */ + cmpl $1, -8(%rsp) + je nested_nmi + + /* + * Now test if the previous stack was an NMI stack. + * We need the double check. We check the NMI stack to satisfy the + * race when the first NMI clears the variable before returning. + * We check the variable because the first NMI could be in a + * breakpoint routine using a breakpoint stack. + */ + lea 6*8(%rsp), %rdx + test_in_nmi rdx, 4*8(%rsp), nested_nmi, first_nmi + CFI_REMEMBER_STATE + +nested_nmi: + /* + * Do nothing if we interrupted the fixup in repeat_nmi. + * It's about to repeat the NMI handler, so we are fine + * with ignoring this one. + */ + movq $repeat_nmi, %rdx + cmpq 8(%rsp), %rdx + ja 1f + movq $end_repeat_nmi, %rdx + cmpq 8(%rsp), %rdx + ja nested_nmi_out + +1: + /* Set up the interrupted NMIs stack to jump to repeat_nmi */ + leaq -6*8(%rsp), %rdx + movq %rdx, %rsp + CFI_ADJUST_CFA_OFFSET 6*8 + pushq_cfi $__KERNEL_DS + pushq_cfi %rdx + pushfq_cfi + pushq_cfi $__KERNEL_CS + pushq_cfi $repeat_nmi + + /* Put stack back */ + addq $(11*8), %rsp + CFI_ADJUST_CFA_OFFSET -11*8 + +nested_nmi_out: + popq_cfi %rdx + CFI_RESTORE rdx + + /* No need to check faults here */ + INTERRUPT_RETURN + + CFI_RESTORE_STATE +first_nmi: + /* + * Because nested NMIs will use the pushed location that we + * stored in rdx, we must keep that space available. + * Here's what our stack frame will look like: + * +-------------------------+ + * | original SS | + * | original Return RSP | + * | original RFLAGS | + * | original CS | + * | original RIP | + * +-------------------------+ + * | temp storage for rdx | + * +-------------------------+ + * | NMI executing variable | + * +-------------------------+ + * | Saved SS | + * | Saved Return RSP | + * | Saved RFLAGS | + * | Saved CS | + * | Saved RIP | + * +-------------------------+ + * | copied SS | + * | copied Return RSP | + * | copied RFLAGS | + * | copied CS | + * | copied RIP | + * +-------------------------+ + * | pt_regs | + * +-------------------------+ + * + * The saved stack frame is used to fix up the copied stack frame + * that a nested NMI may change to make the interrupted NMI iret jump + * to the repeat_nmi. The original stack frame and the temp storage + * is also used by nested NMIs and can not be trusted on exit. + */ + /* Do not pop rdx, nested NMIs will corrupt that part of the stack */ + movq (%rsp), %rdx + CFI_RESTORE rdx + + /* Set the NMI executing variable on the stack. */ + pushq_cfi $1 + + /* Copy the stack frame to the Saved frame */ + .rept 5 + pushq_cfi 6*8(%rsp) + .endr + CFI_DEF_CFA_OFFSET SS+8-RIP + + /* Everything up to here is safe from nested NMIs */ + + /* + * If there was a nested NMI, the first NMI's iret will return + * here. But NMIs are still enabled and we can take another + * nested NMI. The nested NMI checks the interrupted RIP to see + * if it is between repeat_nmi and end_repeat_nmi, and if so + * it will just return, as we are about to repeat an NMI anyway. + * This makes it safe to copy to the stack frame that a nested + * NMI will update. + */ +repeat_nmi: + /* + * Update the stack variable to say we are still in NMI (the update + * is benign for the non-repeat case, where 1 was pushed just above + * to this very stack slot). + */ + movq $1, 5*8(%rsp) + + /* Make another copy, this one may be modified by nested NMIs */ + .rept 5 + pushq_cfi 4*8(%rsp) + .endr + CFI_DEF_CFA_OFFSET SS+8-RIP +end_repeat_nmi: + + /* + * Everything below this point can be preempted by a nested + * NMI if the first NMI took an exception and reset our iret stack + * so that we repeat another NMI. + */ + pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ subq $ORIG_RAX-R15, %rsp CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 + /* + * Use save_paranoid to handle SWAPGS, but no need to use paranoid_exit + * as we should not be calling schedule in NMI context. + * Even with normal interrupts enabled. An NMI should not be + * setting NEED_RESCHED or anything that normal interrupts and + * exceptions might do. + */ call save_paranoid DEFAULT_FRAME 0 /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ movq %rsp,%rdi movq $-1,%rsi call do_nmi -#ifdef CONFIG_TRACE_IRQFLAGS - /* paranoidexit; without TRACE_IRQS_OFF */ - /* ebx: no swapgs flag */ - DISABLE_INTERRUPTS(CLBR_NONE) testl %ebx,%ebx /* swapgs needed? */ jnz nmi_restore - testl $3,CS(%rsp) - jnz nmi_userspace nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: RESTORE_ALL 8 + /* Clear the NMI executing stack variable */ + movq $0, 10*8(%rsp) jmp irq_return -nmi_userspace: - GET_THREAD_INFO(%rcx) - movl TI_flags(%rcx),%ebx - andl $_TIF_WORK_MASK,%ebx - jz nmi_swapgs - movq %rsp,%rdi /* &pt_regs */ - call sync_regs - movq %rax,%rsp /* switch stack for scheduling */ - testl $_TIF_NEED_RESCHED,%ebx - jnz nmi_schedule - movl %ebx,%edx /* arg3: thread flags */ - ENABLE_INTERRUPTS(CLBR_NONE) - xorl %esi,%esi /* arg2: oldset */ - movq %rsp,%rdi /* arg1: &pt_regs */ - call do_notify_resume - DISABLE_INTERRUPTS(CLBR_NONE) - jmp nmi_userspace -nmi_schedule: - ENABLE_INTERRUPTS(CLBR_ANY) - call schedule - DISABLE_INTERRUPTS(CLBR_ANY) - jmp nmi_userspace CFI_ENDPROC -#else - jmp paranoid_exit - CFI_ENDPROC -#endif END(nmi) ENTRY(ignore_sysret) |