* NOTE: This code handles signal-recognition, which happens every time
* after an interrupt and after each system call.
*
- * Normal syscalls and interrupts don't save a full stack frame, this is
- * only done for syscall tracing, signals or fork/exec et.al.
- *
* A note on terminology:
* - top of stack: Architecture defined interrupt frame from SS to RIP
* at the top of the kernel process stack.
* Some macro usage:
* - CFI macros are used to generate dwarf2 unwind information for better
* backtraces. They don't change any code.
- * - SAVE_ALL/RESTORE_ALL - Save/restore all registers
- * - SAVE_ARGS/RESTORE_ARGS - Save/restore registers that C functions modify.
- * There are unfortunately lots of special cases where some registers
- * not touched. The macro is a big mess that should be cleaned up.
- * - SAVE_REST/RESTORE_REST - Handle the registers not saved by SAVE_ARGS.
- * Gives a full stack frame.
* - ENTRY/END Define functions in the symbol table.
* - FIXUP_TOP_OF_STACK/RESTORE_TOP_OF_STACK - Fix up the hardware stack
* frame that is otherwise undefined after a SYSCALL
#endif /* CONFIG_PARAVIRT */
-.macro TRACE_IRQS_IRETQ offset=ARGOFFSET
+.macro TRACE_IRQS_IRETQ
#ifdef CONFIG_TRACE_IRQFLAGS
- bt $9,EFLAGS-\offset(%rsp) /* interrupts off? */
+ bt $9,EFLAGS(%rsp) /* interrupts off? */
jnc 1f
TRACE_IRQS_ON
1:
call debug_stack_reset
.endm
-.macro TRACE_IRQS_IRETQ_DEBUG offset=ARGOFFSET
- bt $9,EFLAGS-\offset(%rsp) /* interrupts off? */
+.macro TRACE_IRQS_IRETQ_DEBUG
+ bt $9,EFLAGS(%rsp) /* interrupts off? */
jnc 1f
TRACE_IRQS_ON_DEBUG
1:
movq \tmp,RSP+\offset(%rsp)
movq $__USER_DS,SS+\offset(%rsp)
movq $__USER_CS,CS+\offset(%rsp)
- movq $-1,RCX+\offset(%rsp)
+ movq RIP+\offset(%rsp),\tmp /* get rip */
+ movq \tmp,RCX+\offset(%rsp) /* copy it to rcx as sysret would do */
movq R11+\offset(%rsp),\tmp /* get eflags */
movq \tmp,EFLAGS+\offset(%rsp)
.endm
movq \tmp,R11+\offset(%rsp)
.endm
- .macro FAKE_STACK_FRAME child_rip
- /* push in order ss, rsp, eflags, cs, rip */
- xorl %eax, %eax
- pushq_cfi $__KERNEL_DS /* ss */
- /*CFI_REL_OFFSET ss,0*/
- pushq_cfi %rax /* rsp */
- CFI_REL_OFFSET rsp,0
- pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) /* eflags - interrupts on */
- /*CFI_REL_OFFSET rflags,0*/
- pushq_cfi $__KERNEL_CS /* cs */
- /*CFI_REL_OFFSET cs,0*/
- pushq_cfi \child_rip /* rip */
- CFI_REL_OFFSET rip,0
- pushq_cfi %rax /* orig rax */
- .endm
-
- .macro UNFAKE_STACK_FRAME
- addq $8*6, %rsp
- CFI_ADJUST_CFA_OFFSET -(6*8)
- .endm
-
/*
- * initial frame state for interrupts (and exceptions without error code)
+ * empty frame
*/
.macro EMPTY_FRAME start=1 offset=0
.if \start
INTR_FRAME \start, RIP+\offset-ORIG_RAX
.endm
-/*
- * frame that enables calling into C.
- */
- .macro PARTIAL_FRAME start=1 offset=0
- XCPT_FRAME \start, ORIG_RAX+\offset-ARGOFFSET
- CFI_REL_OFFSET rdi, RDI+\offset-ARGOFFSET
- CFI_REL_OFFSET rsi, RSI+\offset-ARGOFFSET
- CFI_REL_OFFSET rdx, RDX+\offset-ARGOFFSET
- CFI_REL_OFFSET rcx, RCX+\offset-ARGOFFSET
- CFI_REL_OFFSET rax, RAX+\offset-ARGOFFSET
- CFI_REL_OFFSET r8, R8+\offset-ARGOFFSET
- CFI_REL_OFFSET r9, R9+\offset-ARGOFFSET
- CFI_REL_OFFSET r10, R10+\offset-ARGOFFSET
- CFI_REL_OFFSET r11, R11+\offset-ARGOFFSET
- .endm
-
/*
* frame that enables passing a complete pt_regs to a C function.
*/
.macro DEFAULT_FRAME start=1 offset=0
- PARTIAL_FRAME \start, R11+\offset-R15
+ XCPT_FRAME \start, ORIG_RAX+\offset
+ CFI_REL_OFFSET rdi, RDI+\offset
+ CFI_REL_OFFSET rsi, RSI+\offset
+ CFI_REL_OFFSET rdx, RDX+\offset
+ CFI_REL_OFFSET rcx, RCX+\offset
+ CFI_REL_OFFSET rax, RAX+\offset
+ CFI_REL_OFFSET r8, R8+\offset
+ CFI_REL_OFFSET r9, R9+\offset
+ CFI_REL_OFFSET r10, R10+\offset
+ CFI_REL_OFFSET r11, R11+\offset
CFI_REL_OFFSET rbx, RBX+\offset
CFI_REL_OFFSET rbp, RBP+\offset
CFI_REL_OFFSET r12, R12+\offset
CFI_REL_OFFSET r15, R15+\offset
.endm
-/* save partial stack frame */
- .macro SAVE_ARGS_IRQ
- cld
- /* start from rbp in pt_regs and jump over */
- movq_cfi rdi, (RDI-RBP)
- movq_cfi rsi, (RSI-RBP)
- movq_cfi rdx, (RDX-RBP)
- movq_cfi rcx, (RCX-RBP)
- movq_cfi rax, (RAX-RBP)
- movq_cfi r8, (R8-RBP)
- movq_cfi r9, (R9-RBP)
- movq_cfi r10, (R10-RBP)
- movq_cfi r11, (R11-RBP)
-
- /* Save rbp so that we can unwind from get_irq_regs() */
- movq_cfi rbp, 0
-
- /* Save previous stack value */
- movq %rsp, %rsi
-
- leaq -RBP(%rsp),%rdi /* arg1 for handler */
- testl $3, CS-RBP(%rsi)
- je 1f
- SWAPGS
- /*
- * irq_count is used to check if a CPU is already on an interrupt stack
- * or not. While this is essentially redundant with preempt_count it is
- * a little cheaper to use a separate counter in the PDA (short of
- * moving irq_enter into assembly, which would be too much work)
- */
-1: incl PER_CPU_VAR(irq_count)
- cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
- CFI_DEF_CFA_REGISTER rsi
-
- /* Store previous stack value */
- pushq %rsi
- CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \
- 0x77 /* DW_OP_breg7 */, 0, \
- 0x06 /* DW_OP_deref */, \
- 0x08 /* DW_OP_const1u */, SS+8-RBP, \
- 0x22 /* DW_OP_plus */
- /* We entered an interrupt context - irqs are off: */
- TRACE_IRQS_OFF
- .endm
-
ENTRY(save_paranoid)
XCPT_FRAME 1 RDI+8
cld
- movq %rdi, RDI+8(%rsp)
- movq %rsi, RSI+8(%rsp)
- movq_cfi rdx, RDX+8
- movq_cfi rcx, RCX+8
- movq_cfi rax, RAX+8
- movq %r8, R8+8(%rsp)
- movq %r9, R9+8(%rsp)
- movq %r10, R10+8(%rsp)
- movq %r11, R11+8(%rsp)
- movq_cfi rbx, RBX+8
- movq %rbp, RBP+8(%rsp)
- movq %r12, R12+8(%rsp)
- movq %r13, R13+8(%rsp)
- movq %r14, R14+8(%rsp)
- movq %r15, R15+8(%rsp)
+ SAVE_C_REGS 8
+ SAVE_EXTRA_REGS 8
movl $1,%ebx
movl $MSR_GS_BASE,%ecx
rdmsr
GET_THREAD_INFO(%rcx)
- RESTORE_REST
+ RESTORE_EXTRA_REGS
- testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread?
+ testl $3,CS(%rsp) # from kernel_thread?
jz 1f
testl $_TIF_IA32, TI_flags(%rcx) # 32-bit compat task needs IRET
jnz int_ret_from_sys_call
- RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET
+ RESTORE_TOP_OF_STACK %rdi
jmp ret_from_sys_call # go to the SYSRET fastpath
1:
- subq $REST_SKIP, %rsp # leave space for volatiles
- CFI_ADJUST_CFA_OFFSET REST_SKIP
movq %rbp, %rdi
call *%rbx
movl $0, RAX(%rsp)
- RESTORE_REST
+ RESTORE_EXTRA_REGS
jmp int_ret_from_sys_call
CFI_ENDPROC
END(ret_from_fork)
* and short:
*/
ENABLE_INTERRUPTS(CLBR_NONE)
- SAVE_ARGS 8, 0, rax_enosys=1
- movq_cfi rax,(ORIG_RAX-ARGOFFSET)
- movq %rcx,RIP-ARGOFFSET(%rsp)
- CFI_REL_OFFSET rip,RIP-ARGOFFSET
- testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+ ALLOC_PT_GPREGS_ON_STACK 8
+ SAVE_C_REGS_EXCEPT_RAX_RCX
+ movq $-ENOSYS,RAX(%rsp)
+ movq_cfi rax,ORIG_RAX
+ movq %rcx,RIP(%rsp)
+ CFI_REL_OFFSET rip,RIP
+ testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP)
jnz tracesys
system_call_fastpath:
#if __SYSCALL_MASK == ~0
ja ret_from_sys_call /* and return regs->ax */
movq %r10,%rcx
call *sys_call_table(,%rax,8) # XXX: rip relative
- movq %rax,RAX-ARGOFFSET(%rsp)
+ movq %rax,RAX(%rsp)
/*
* Syscall return path ending with SYSRET (fast path)
* Has incomplete stack frame and undefined top of stack.
*/
ret_from_sys_call:
- movl $_TIF_ALLWORK_MASK,%edi
- /* edi: flagmask */
-sysret_check:
+ testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP)
+ jnz int_ret_from_sys_call_fixup /* Go the the slow path */
+
LOCKDEP_SYS_EXIT
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- movl TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET),%edx
- andl %edi,%edx
- jnz sysret_careful
CFI_REMEMBER_STATE
/*
* sysretq will re-enable interrupts:
*/
TRACE_IRQS_ON
- movq RIP-ARGOFFSET(%rsp),%rcx
+ RESTORE_C_REGS_EXCEPT_RCX
+ movq RIP(%rsp),%rcx
CFI_REGISTER rip,rcx
- RESTORE_ARGS 1,-ARG_SKIP,0
/*CFI_REGISTER rflags,r11*/
movq PER_CPU_VAR(old_rsp), %rsp
USERGS_SYSRET64
CFI_RESTORE_STATE
- /* Handle reschedules */
- /* edx: work, edi: workmask */
-sysret_careful:
- bt $TIF_NEED_RESCHED,%edx
- jnc sysret_signal
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- pushq_cfi %rdi
- SCHEDULE_USER
- popq_cfi %rdi
- jmp sysret_check
- /* Handle a signal */
-sysret_signal:
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
-#ifdef CONFIG_AUDITSYSCALL
- bt $TIF_SYSCALL_AUDIT,%edx
- jc sysret_audit
-#endif
- /*
- * We have a signal, or exit tracing or single-step.
- * These all wind up with the iret return path anyway,
- * so just join that path right now.
- */
- FIXUP_TOP_OF_STACK %r11, -ARGOFFSET
- jmp int_check_syscall_exit_work
-
-#ifdef CONFIG_AUDITSYSCALL
- /*
- * 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 $-MAX_ERRNO,%rsi /* is it < -MAX_ERRNO? */
- setbe %al /* 1 if so, 0 if not */
- movzbl %al,%edi /* zero-extend that into %edi */
- call __audit_syscall_exit
- movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
- jmp sysret_check
-#endif /* CONFIG_AUDITSYSCALL */
+int_ret_from_sys_call_fixup:
+ FIXUP_TOP_OF_STACK %r11
+ jmp int_ret_from_sys_call
/* Do syscall tracing */
tracesys:
- leaq -REST_SKIP(%rsp), %rdi
+ movq %rsp, %rdi
movq $AUDIT_ARCH_X86_64, %rsi
call syscall_trace_enter_phase1
test %rax, %rax
jnz tracesys_phase2 /* if needed, run the slow path */
- LOAD_ARGS 0 /* else restore clobbered regs */
+ RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */
+ movq ORIG_RAX(%rsp), %rax
jmp system_call_fastpath /* and return to the fast path */
tracesys_phase2:
- SAVE_REST
+ SAVE_EXTRA_REGS
FIXUP_TOP_OF_STACK %rdi
movq %rsp, %rdi
movq $AUDIT_ARCH_X86_64, %rsi
call syscall_trace_enter_phase2
/*
- * Reload arg registers from stack in case ptrace changed them.
+ * Reload registers from stack in case ptrace changed them.
* We don't reload %rax because syscall_trace_entry_phase2() returned
* the value it wants us to use in the table lookup.
*/
- LOAD_ARGS ARGOFFSET, 1
- RESTORE_REST
+ RESTORE_C_REGS_EXCEPT_RAX
+ RESTORE_EXTRA_REGS
#if __SYSCALL_MASK == ~0
cmpq $__NR_syscall_max,%rax
#else
ja int_ret_from_sys_call /* RAX(%rsp) is already set */
movq %r10,%rcx /* fixup for C */
call *sys_call_table(,%rax,8)
- movq %rax,RAX-ARGOFFSET(%rsp)
+ movq %rax,RAX(%rsp)
/* Use IRET because user could have changed frame */
/*
int_very_careful:
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
-int_check_syscall_exit_work:
- SAVE_REST
+ SAVE_EXTRA_REGS
/* Check for syscall exit trace */
testl $_TIF_WORK_SYSCALL_EXIT,%edx
jz int_signal
call do_notify_resume
1: movl $_TIF_WORK_MASK,%edi
int_restore_rest:
- RESTORE_REST
+ RESTORE_EXTRA_REGS
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
jmp int_with_check
.macro FORK_LIKE func
ENTRY(stub_\func)
CFI_STARTPROC
- popq %r11 /* save return address */
- PARTIAL_FRAME 0
- SAVE_REST
- pushq %r11 /* put it back on stack */
+ DEFAULT_FRAME 0, 8 /* offset 8: return address */
+ SAVE_EXTRA_REGS 8
FIXUP_TOP_OF_STACK %r11, 8
- DEFAULT_FRAME 0 8 /* offset 8: return address */
call sys_\func
RESTORE_TOP_OF_STACK %r11, 8
- ret $REST_SKIP /* pop extended registers */
+ ret
CFI_ENDPROC
END(stub_\func)
.endm
.macro FIXED_FRAME label,func
ENTRY(\label)
CFI_STARTPROC
- PARTIAL_FRAME 0 8 /* offset 8: return address */
- FIXUP_TOP_OF_STACK %r11, 8-ARGOFFSET
+ DEFAULT_FRAME 0, 8 /* offset 8: return address */
+ FIXUP_TOP_OF_STACK %r11, 8
call \func
- RESTORE_TOP_OF_STACK %r11, 8-ARGOFFSET
+ RESTORE_TOP_OF_STACK %r11, 8
ret
CFI_ENDPROC
END(\label)
FORK_LIKE vfork
FIXED_FRAME stub_iopl, sys_iopl
-ENTRY(ptregscall_common)
- DEFAULT_FRAME 1 8 /* offset 8: return address */
- RESTORE_TOP_OF_STACK %r11, 8
- movq_cfi_restore R15+8, r15
- movq_cfi_restore R14+8, r14
- movq_cfi_restore R13+8, r13
- movq_cfi_restore R12+8, r12
- movq_cfi_restore RBP+8, rbp
- movq_cfi_restore RBX+8, rbx
- ret $REST_SKIP /* pop extended registers */
- CFI_ENDPROC
-END(ptregscall_common)
-
ENTRY(stub_execve)
CFI_STARTPROC
addq $8, %rsp
- PARTIAL_FRAME 0
- SAVE_REST
+ DEFAULT_FRAME 0
+ SAVE_EXTRA_REGS
FIXUP_TOP_OF_STACK %r11
call sys_execve
movq %rax,RAX(%rsp)
- RESTORE_REST
+ RESTORE_EXTRA_REGS
jmp int_ret_from_sys_call
CFI_ENDPROC
END(stub_execve)
ENTRY(stub_execveat)
CFI_STARTPROC
addq $8, %rsp
- PARTIAL_FRAME 0
- SAVE_REST
+ DEFAULT_FRAME 0
+ SAVE_EXTRA_REGS
FIXUP_TOP_OF_STACK %r11
call sys_execveat
RESTORE_TOP_OF_STACK %r11
movq %rax,RAX(%rsp)
- RESTORE_REST
+ RESTORE_EXTRA_REGS
jmp int_ret_from_sys_call
CFI_ENDPROC
END(stub_execveat)
ENTRY(stub_rt_sigreturn)
CFI_STARTPROC
addq $8, %rsp
- PARTIAL_FRAME 0
- SAVE_REST
+ DEFAULT_FRAME 0
+ SAVE_EXTRA_REGS
FIXUP_TOP_OF_STACK %r11
call sys_rt_sigreturn
movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer
- RESTORE_REST
+ RESTORE_EXTRA_REGS
jmp int_ret_from_sys_call
CFI_ENDPROC
END(stub_rt_sigreturn)
ENTRY(stub_x32_rt_sigreturn)
CFI_STARTPROC
addq $8, %rsp
- PARTIAL_FRAME 0
- SAVE_REST
+ DEFAULT_FRAME 0
+ SAVE_EXTRA_REGS
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
+ RESTORE_EXTRA_REGS
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
+ DEFAULT_FRAME 0
+ SAVE_EXTRA_REGS
FIXUP_TOP_OF_STACK %r11
call compat_sys_execve
RESTORE_TOP_OF_STACK %r11
movq %rax,RAX(%rsp)
- RESTORE_REST
+ RESTORE_EXTRA_REGS
jmp int_ret_from_sys_call
CFI_ENDPROC
END(stub_x32_execve)
ENTRY(stub_x32_execveat)
CFI_STARTPROC
addq $8, %rsp
- PARTIAL_FRAME 0
- SAVE_REST
+ DEFAULT_FRAME 0
+ SAVE_EXTRA_REGS
FIXUP_TOP_OF_STACK %r11
call compat_sys_execveat
RESTORE_TOP_OF_STACK %r11
movq %rax,RAX(%rsp)
- RESTORE_REST
+ RESTORE_EXTRA_REGS
jmp int_ret_from_sys_call
CFI_ENDPROC
END(stub_x32_execveat)
/* 0(%rsp): ~(interrupt number) */
.macro interrupt func
- /* reserve pt_regs for scratch regs and rbp */
- subq $ORIG_RAX-RBP, %rsp
- CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP
- SAVE_ARGS_IRQ
+ 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) */
+
+ testl $3, CS-RBP(%rsp)
+ je 1f
+ SWAPGS
+1:
+ /*
+ * Save previous stack pointer, optionally switch to interrupt stack.
+ * irq_count is used to check if a CPU is already on an interrupt stack
+ * or not. While this is essentially redundant with preempt_count it is
+ * 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
+ incl PER_CPU_VAR(irq_count)
+ cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
+ CFI_DEF_CFA_REGISTER rsi
+ pushq %rsi
+ CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \
+ 0x77 /* DW_OP_breg7 */, 0, \
+ 0x06 /* DW_OP_deref */, \
+ 0x08 /* DW_OP_const1u */, SS+8-RBP, \
+ 0x22 /* DW_OP_plus */
+ /* We entered an interrupt context - irqs are off: */
+ TRACE_IRQS_OFF
+
call \func
.endm
ASM_CLAC
addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */
interrupt do_IRQ
- /* 0(%rsp): old_rsp-ARGOFFSET */
+ /* 0(%rsp): old_rsp */
ret_from_intr:
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
/* Restore saved previous stack */
popq %rsi
CFI_DEF_CFA rsi,SS+8-RBP /* reg/off reset after def_cfa_expr */
- leaq ARGOFFSET-RBP(%rsi), %rsp
+ /* return code expects complete pt_regs - adjust rsp accordingly: */
+ leaq -RBP(%rsi),%rsp
CFI_DEF_CFA_REGISTER rsp
- CFI_ADJUST_CFA_OFFSET RBP-ARGOFFSET
+ CFI_ADJUST_CFA_OFFSET RBP
exit_intr:
GET_THREAD_INFO(%rcx)
- testl $3,CS-ARGOFFSET(%rsp)
+ testl $3,CS(%rsp)
je retint_kernel
/* Interrupt came from user space */
/*
- * Has a correct top of stack, but a partial stack frame
+ * Has a correct top of stack.
* %rcx: thread info. Interrupts off.
*/
retint_with_reschedule:
*/
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_IRETQ
+
+ /*
+ * Try to use SYSRET instead of IRET if we're returning to
+ * a completely clean 64-bit userspace context.
+ */
+ movq RCX(%rsp),%rcx
+ cmpq %rcx,RIP(%rsp) /* RCX == RIP */
+ jne opportunistic_sysret_failed
+
+ /*
+ * On Intel CPUs, sysret with non-canonical RCX/RIP will #GP
+ * in kernel space. This essentially lets the user take over
+ * the kernel, since userspace controls RSP. It's not worth
+ * testing for canonicalness exactly -- this check detects any
+ * of the 17 high bits set, which is true for non-canonical
+ * or kernel addresses. (This will pessimize vsyscall=native.
+ * Big deal.)
+ *
+ * If virtual addresses ever become wider, this will need
+ * to be updated to remain correct on both old and new CPUs.
+ */
+ .ifne __VIRTUAL_MASK_SHIFT - 47
+ .error "virtual address width changed -- sysret checks need update"
+ .endif
+ shr $__VIRTUAL_MASK_SHIFT, %rcx
+ jnz opportunistic_sysret_failed
+
+ cmpq $__USER_CS,CS(%rsp) /* CS must match SYSRET */
+ jne opportunistic_sysret_failed
+
+ movq R11(%rsp),%r11
+ cmpq %r11,EFLAGS(%rsp) /* R11 == RFLAGS */
+ jne opportunistic_sysret_failed
+
+ testq $X86_EFLAGS_RF,%r11 /* sysret can't restore RF */
+ jnz opportunistic_sysret_failed
+
+ /* nothing to check for RSP */
+
+ cmpq $__USER_DS,SS(%rsp) /* SS must match SYSRET */
+ jne opportunistic_sysret_failed
+
+ /*
+ * We win! This label is here just for ease of understanding
+ * perf profiles. Nothing jumps here.
+ */
+irq_return_via_sysret:
+ CFI_REMEMBER_STATE
+ RESTORE_C_REGS
+ REMOVE_PT_GPREGS_FROM_STACK 8
+ movq (RSP-RIP)(%rsp),%rsp
+ USERGS_SYSRET64
+ CFI_RESTORE_STATE
+
+opportunistic_sysret_failed:
SWAPGS
jmp restore_args
*/
TRACE_IRQS_IRETQ
restore_args:
- RESTORE_ARGS 1,8,1
+ RESTORE_C_REGS
+ REMOVE_PT_GPREGS_FROM_STACK 8
irq_return:
INTERRUPT_RETURN
jz retint_swapgs
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
- SAVE_REST
+ SAVE_EXTRA_REGS
movq $-1,ORIG_RAX(%rsp)
xorl %esi,%esi # oldset
movq %rsp,%rdi # &pt_regs
call do_notify_resume
- RESTORE_REST
+ RESTORE_EXTRA_REGS
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
GET_THREAD_INFO(%rcx)
ENTRY(retint_kernel)
cmpl $0,PER_CPU_VAR(__preempt_count)
jnz retint_restore_args
- bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */
+ bt $9,EFLAGS(%rsp) /* interrupts off? */
jnc retint_restore_args
call preempt_schedule_irq
jmp exit_intr
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
.endif
- subq $ORIG_RAX-R15, %rsp
- CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
+ ALLOC_PT_GPREGS_ON_STACK
.if \paranoid
+ .if \paranoid == 1
+ CFI_REMEMBER_STATE
+ testl $3, CS(%rsp) /* If coming from userspace, switch */
+ jnz 1f /* stacks. */
+ .endif
call save_paranoid
.else
call error_entry
jmp error_exit /* %ebx: no swapgs flag */
.endif
+ .if \paranoid == 1
+ CFI_RESTORE_STATE
+ /*
+ * Paranoid entry from userspace. Switch stacks and treat it
+ * as a normal entry. This means that paranoid handlers
+ * run in real process context if user_mode(regs).
+ */
+1:
+ call error_entry
+
+ DEFAULT_FRAME 0
+
+ movq %rsp,%rdi /* pt_regs pointer */
+ call sync_regs
+ movq %rax,%rsp /* switch stack */
+
+ movq %rsp,%rdi /* pt_regs pointer */
+
+ .if \has_error_code
+ movq ORIG_RAX(%rsp),%rsi /* get error code */
+ movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */
+ .else
+ xorl %esi,%esi /* no error code */
+ .endif
+
+ call \do_sym
+
+ jmp error_exit /* %ebx: no swapgs flag */
+ .endif
+
CFI_ENDPROC
END(\sym)
.endm
idtentry bounds do_bounds has_error_code=0
idtentry invalid_op do_invalid_op has_error_code=0
idtentry device_not_available do_device_not_available has_error_code=0
-idtentry double_fault do_double_fault has_error_code=1 paranoid=1
+idtentry double_fault do_double_fault has_error_code=1 paranoid=2
idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0
idtentry invalid_TSS do_invalid_TSS has_error_code=1
idtentry segment_not_present do_segment_not_present has_error_code=1
popq %rsp
CFI_DEF_CFA_REGISTER rsp
decl PER_CPU_VAR(irq_count)
+#ifndef CONFIG_PREEMPT
+ call xen_maybe_preempt_hcall
+#endif
jmp error_exit
CFI_ENDPROC
END(xen_do_hypervisor_callback)
addq $0x30,%rsp
CFI_ADJUST_CFA_OFFSET -0x30
pushq_cfi $-1 /* orig_ax = -1 => not a system call */
- SAVE_ALL
+ ALLOC_PT_GPREGS_ON_STACK
+ SAVE_C_REGS
+ SAVE_EXTRA_REGS
jmp error_exit
CFI_ENDPROC
END(xen_failsafe_callback)
#endif
/*
- * "Paranoid" exit path from exception stack.
- * Paranoid because this is used by NMIs and cannot take
- * any kernel state for granted.
- * We don't do kernel preemption checks here, because only
- * NMI should be common and it does not enable IRQs and
- * cannot get reschedule ticks.
+ * "Paranoid" exit path from exception stack. This is invoked
+ * only on return from non-NMI IST interrupts that came
+ * from kernel space.
*
- * "trace" is 0 for the NMI handler only, because irq-tracing
- * is fundamentally NMI-unsafe. (we cannot change the soft and
- * hard flags at once, atomically)
+ * We may be returning to very strange contexts (e.g. very early
+ * in syscall entry), so checking for preemption here would
+ * be complicated. Fortunately, we there's no good reason
+ * to try to handle preemption here.
*/
/* ebx: no swapgs flag */
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF_DEBUG
testl %ebx,%ebx /* swapgs needed? */
- jnz paranoid_restore
- testl $3,CS(%rsp)
- jnz paranoid_userspace
-paranoid_swapgs:
- TRACE_IRQS_IRETQ 0
+ jnz paranoid_exit_no_swapgs
+ TRACE_IRQS_IRETQ
SWAPGS_UNSAFE_STACK
- RESTORE_ALL 8
- jmp irq_return
-paranoid_restore:
- TRACE_IRQS_IRETQ_DEBUG 0
- RESTORE_ALL 8
- jmp irq_return
-paranoid_userspace:
- GET_THREAD_INFO(%rcx)
- movl TI_flags(%rcx),%ebx
- andl $_TIF_WORK_MASK,%ebx
- jz paranoid_swapgs
- movq %rsp,%rdi /* &pt_regs */
- call sync_regs
- movq %rax,%rsp /* switch stack for scheduling */
- testl $_TIF_NEED_RESCHED,%ebx
- jnz paranoid_schedule
- movl %ebx,%edx /* arg3: thread flags */
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- xorl %esi,%esi /* arg2: oldset */
- movq %rsp,%rdi /* arg1: &pt_regs */
- call do_notify_resume
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- jmp paranoid_userspace
-paranoid_schedule:
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_ANY)
- SCHEDULE_USER
- DISABLE_INTERRUPTS(CLBR_ANY)
- TRACE_IRQS_OFF
- jmp paranoid_userspace
+ jmp paranoid_exit_restore
+paranoid_exit_no_swapgs:
+ TRACE_IRQS_IRETQ_DEBUG
+paranoid_exit_restore:
+ RESTORE_EXTRA_REGS
+ RESTORE_C_REGS
+ REMOVE_PT_GPREGS_FROM_STACK 8
+ INTERRUPT_RETURN
CFI_ENDPROC
END(paranoid_exit)
CFI_ADJUST_CFA_OFFSET 15*8
/* oldrax contains error code */
cld
- movq %rdi, RDI+8(%rsp)
- movq %rsi, RSI+8(%rsp)
- movq %rdx, RDX+8(%rsp)
- movq %rcx, RCX+8(%rsp)
- movq %rax, RAX+8(%rsp)
- movq %r8, R8+8(%rsp)
- movq %r9, R9+8(%rsp)
- movq %r10, R10+8(%rsp)
- movq %r11, R11+8(%rsp)
- movq_cfi rbx, RBX+8
- movq %rbp, RBP+8(%rsp)
- movq %r12, R12+8(%rsp)
- movq %r13, R13+8(%rsp)
- movq %r14, R14+8(%rsp)
- movq %r15, R15+8(%rsp)
+ SAVE_C_REGS 8
+ SAVE_EXTRA_REGS 8
xorl %ebx,%ebx
testl $3,CS+8(%rsp)
je error_kernelspace
ENTRY(error_exit)
DEFAULT_FRAME
movl %ebx,%eax
- RESTORE_REST
+ RESTORE_EXTRA_REGS
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
GET_THREAD_INFO(%rcx)
* 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
+ ALLOC_PT_GPREGS_ON_STACK
+
/*
* Use save_paranoid to handle SWAPGS, but no need to use paranoid_exit
* as we should not be calling schedule in NMI context.
nmi_swapgs:
SWAPGS_UNSAFE_STACK
nmi_restore:
+ RESTORE_EXTRA_REGS
+ RESTORE_C_REGS
/* Pop the extra iret frame at once */
- RESTORE_ALL 6*8
+ REMOVE_PT_GPREGS_FROM_STACK 6*8
/* Clear the NMI executing stack variable */
movq $0, 5*8(%rsp)