mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-15 15:36:56 +07:00
f2b375756c
Due to a blatant design error, SYSENTER doesn't clear TF (single-step).
As a result, if a user does SYSENTER with TF set, we will single-step
through the kernel until something clears TF. There is absolutely
nothing we can do to prevent this short of turning off SYSENTER [1].
Simplify the handling considerably with two changes:
1. We already sanitize EFLAGS in SYSENTER to clear NT and AC. We can
add TF to that list of flags to sanitize with no overhead whatsoever.
2. Teach do_debug() to ignore single-step traps in the SYSENTER prologue.
That's all we need to do.
Don't get too excited -- our handling is still buggy on 32-bit
kernels. There's nothing wrong with the SYSENTER code itself, but
the #DB prologue has a clever fixup for traps on the very first
instruction of entry_SYSENTER_32, and the fixup doesn't work quite
correctly. The next two patches will fix that.
[1] We could probably prevent it by forcing BTF on at all times and
making sure we clear TF before any branches in the SYSENTER
code. Needless to say, this is a bad idea.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/a30d2ea06fe4b621fe6a9ef911b02c0f38feb6f2.1457578375.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
328 lines
10 KiB
ArmAsm
328 lines
10 KiB
ArmAsm
/*
|
|
* Compatibility mode system call entry point for x86-64.
|
|
*
|
|
* Copyright 2000-2002 Andi Kleen, SuSE Labs.
|
|
*/
|
|
#include "calling.h"
|
|
#include <asm/asm-offsets.h>
|
|
#include <asm/current.h>
|
|
#include <asm/errno.h>
|
|
#include <asm/ia32_unistd.h>
|
|
#include <asm/thread_info.h>
|
|
#include <asm/segment.h>
|
|
#include <asm/irqflags.h>
|
|
#include <asm/asm.h>
|
|
#include <asm/smap.h>
|
|
#include <linux/linkage.h>
|
|
#include <linux/err.h>
|
|
|
|
.section .entry.text, "ax"
|
|
|
|
/*
|
|
* 32-bit SYSENTER instruction entry.
|
|
*
|
|
* SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs.
|
|
* IF and VM in rflags are cleared (IOW: interrupts are off).
|
|
* SYSENTER does not save anything on the stack,
|
|
* and does not save old rip (!!!) and rflags.
|
|
*
|
|
* Arguments:
|
|
* eax system call number
|
|
* ebx arg1
|
|
* ecx arg2
|
|
* edx arg3
|
|
* esi arg4
|
|
* edi arg5
|
|
* ebp user stack
|
|
* 0(%ebp) arg6
|
|
*
|
|
* This is purely a fast path. For anything complicated we use the int 0x80
|
|
* path below. We set up a complete hardware stack frame to share code
|
|
* with the int 0x80 path.
|
|
*/
|
|
ENTRY(entry_SYSENTER_compat)
|
|
/* Interrupts are off on entry. */
|
|
SWAPGS_UNSAFE_STACK
|
|
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
|
|
|
|
/*
|
|
* User tracing code (ptrace or signal handlers) might assume that
|
|
* the saved RAX contains a 32-bit number when we're invoking a 32-bit
|
|
* syscall. Just in case the high bits are nonzero, zero-extend
|
|
* the syscall number. (This could almost certainly be deleted
|
|
* with no ill effects.)
|
|
*/
|
|
movl %eax, %eax
|
|
|
|
/* Construct struct pt_regs on stack */
|
|
pushq $__USER32_DS /* pt_regs->ss */
|
|
pushq %rbp /* pt_regs->sp (stashed in bp) */
|
|
|
|
/*
|
|
* Push flags. This is nasty. First, interrupts are currently
|
|
* off, but we need pt_regs->flags to have IF set. Second, even
|
|
* if TF was set when SYSENTER started, it's clear by now. We fix
|
|
* that later using TIF_SINGLESTEP.
|
|
*/
|
|
pushfq /* pt_regs->flags (except IF = 0) */
|
|
orl $X86_EFLAGS_IF, (%rsp) /* Fix saved flags */
|
|
pushq $__USER32_CS /* pt_regs->cs */
|
|
xorq %r8,%r8
|
|
pushq %r8 /* pt_regs->ip = 0 (placeholder) */
|
|
pushq %rax /* pt_regs->orig_ax */
|
|
pushq %rdi /* pt_regs->di */
|
|
pushq %rsi /* pt_regs->si */
|
|
pushq %rdx /* pt_regs->dx */
|
|
pushq %rcx /* pt_regs->cx */
|
|
pushq $-ENOSYS /* pt_regs->ax */
|
|
pushq %r8 /* pt_regs->r8 = 0 */
|
|
pushq %r8 /* pt_regs->r9 = 0 */
|
|
pushq %r8 /* pt_regs->r10 = 0 */
|
|
pushq %r8 /* pt_regs->r11 = 0 */
|
|
pushq %rbx /* pt_regs->rbx */
|
|
pushq %rbp /* pt_regs->rbp (will be overwritten) */
|
|
pushq %r8 /* pt_regs->r12 = 0 */
|
|
pushq %r8 /* pt_regs->r13 = 0 */
|
|
pushq %r8 /* pt_regs->r14 = 0 */
|
|
pushq %r8 /* pt_regs->r15 = 0 */
|
|
cld
|
|
|
|
/*
|
|
* SYSENTER doesn't filter flags, so we need to clear NT and AC
|
|
* ourselves. To save a few cycles, we can check whether
|
|
* either was set instead of doing an unconditional popfq.
|
|
* This needs to happen before enabling interrupts so that
|
|
* we don't get preempted with NT set.
|
|
*
|
|
* If TF is set, we will single-step all the way to here -- do_debug
|
|
* will ignore all the traps. (Yes, this is slow, but so is
|
|
* single-stepping in general. This allows us to avoid having
|
|
* a more complicated code to handle the case where a user program
|
|
* forces us to single-step through the SYSENTER entry code.)
|
|
*
|
|
* NB.: .Lsysenter_fix_flags is a label with the code under it moved
|
|
* out-of-line as an optimization: NT is unlikely to be set in the
|
|
* majority of the cases and instead of polluting the I$ unnecessarily,
|
|
* we're keeping that code behind a branch which will predict as
|
|
* not-taken and therefore its instructions won't be fetched.
|
|
*/
|
|
testl $X86_EFLAGS_NT|X86_EFLAGS_AC|X86_EFLAGS_TF, EFLAGS(%rsp)
|
|
jnz .Lsysenter_fix_flags
|
|
.Lsysenter_flags_fixed:
|
|
|
|
/*
|
|
* User mode is traced as though IRQs are on, and SYSENTER
|
|
* turned them off.
|
|
*/
|
|
TRACE_IRQS_OFF
|
|
|
|
movq %rsp, %rdi
|
|
call do_fast_syscall_32
|
|
/* XEN PV guests always use IRET path */
|
|
ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
|
|
"jmp .Lsyscall_32_done", X86_FEATURE_XENPV
|
|
jmp sysret32_from_system_call
|
|
|
|
.Lsysenter_fix_flags:
|
|
pushq $X86_EFLAGS_FIXED
|
|
popfq
|
|
jmp .Lsysenter_flags_fixed
|
|
GLOBAL(__end_entry_SYSENTER_compat)
|
|
ENDPROC(entry_SYSENTER_compat)
|
|
|
|
/*
|
|
* 32-bit SYSCALL instruction entry.
|
|
*
|
|
* 32-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
|
|
* then loads new ss, cs, and rip from previously programmed MSRs.
|
|
* rflags gets masked by a value from another MSR (so CLD and CLAC
|
|
* are not needed). SYSCALL does not save anything on the stack
|
|
* and does not change rsp.
|
|
*
|
|
* Note: rflags saving+masking-with-MSR happens only in Long mode
|
|
* (in legacy 32-bit mode, IF, RF and VM bits are cleared and that's it).
|
|
* Don't get confused: rflags saving+masking depends on Long Mode Active bit
|
|
* (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes
|
|
* or target CS descriptor's L bit (SYSCALL does not read segment descriptors).
|
|
*
|
|
* Arguments:
|
|
* eax system call number
|
|
* ecx return address
|
|
* ebx arg1
|
|
* ebp arg2 (note: not saved in the stack frame, should not be touched)
|
|
* edx arg3
|
|
* esi arg4
|
|
* edi arg5
|
|
* esp user stack
|
|
* 0(%esp) arg6
|
|
*/
|
|
ENTRY(entry_SYSCALL_compat)
|
|
/* Interrupts are off on entry. */
|
|
SWAPGS_UNSAFE_STACK
|
|
|
|
/* Stash user ESP and switch to the kernel stack. */
|
|
movl %esp, %r8d
|
|
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
|
|
|
|
/* Zero-extending 32-bit regs, do not remove */
|
|
movl %eax, %eax
|
|
|
|
/* Construct struct pt_regs on stack */
|
|
pushq $__USER32_DS /* pt_regs->ss */
|
|
pushq %r8 /* pt_regs->sp */
|
|
pushq %r11 /* pt_regs->flags */
|
|
pushq $__USER32_CS /* pt_regs->cs */
|
|
pushq %rcx /* pt_regs->ip */
|
|
pushq %rax /* pt_regs->orig_ax */
|
|
pushq %rdi /* pt_regs->di */
|
|
pushq %rsi /* pt_regs->si */
|
|
pushq %rdx /* pt_regs->dx */
|
|
pushq %rbp /* pt_regs->cx (stashed in bp) */
|
|
pushq $-ENOSYS /* pt_regs->ax */
|
|
xorq %r8,%r8
|
|
pushq %r8 /* pt_regs->r8 = 0 */
|
|
pushq %r8 /* pt_regs->r9 = 0 */
|
|
pushq %r8 /* pt_regs->r10 = 0 */
|
|
pushq %r8 /* pt_regs->r11 = 0 */
|
|
pushq %rbx /* pt_regs->rbx */
|
|
pushq %rbp /* pt_regs->rbp (will be overwritten) */
|
|
pushq %r8 /* pt_regs->r12 = 0 */
|
|
pushq %r8 /* pt_regs->r13 = 0 */
|
|
pushq %r8 /* pt_regs->r14 = 0 */
|
|
pushq %r8 /* pt_regs->r15 = 0 */
|
|
|
|
/*
|
|
* User mode is traced as though IRQs are on, and SYSENTER
|
|
* turned them off.
|
|
*/
|
|
TRACE_IRQS_OFF
|
|
|
|
movq %rsp, %rdi
|
|
call do_fast_syscall_32
|
|
/* XEN PV guests always use IRET path */
|
|
ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
|
|
"jmp .Lsyscall_32_done", X86_FEATURE_XENPV
|
|
|
|
/* Opportunistic SYSRET */
|
|
sysret32_from_system_call:
|
|
TRACE_IRQS_ON /* User mode traces as IRQs on. */
|
|
movq RBX(%rsp), %rbx /* pt_regs->rbx */
|
|
movq RBP(%rsp), %rbp /* pt_regs->rbp */
|
|
movq EFLAGS(%rsp), %r11 /* pt_regs->flags (in r11) */
|
|
movq RIP(%rsp), %rcx /* pt_regs->ip (in rcx) */
|
|
addq $RAX, %rsp /* Skip r8-r15 */
|
|
popq %rax /* pt_regs->rax */
|
|
popq %rdx /* Skip pt_regs->cx */
|
|
popq %rdx /* pt_regs->dx */
|
|
popq %rsi /* pt_regs->si */
|
|
popq %rdi /* pt_regs->di */
|
|
|
|
/*
|
|
* USERGS_SYSRET32 does:
|
|
* GSBASE = user's GS base
|
|
* EIP = ECX
|
|
* RFLAGS = R11
|
|
* CS = __USER32_CS
|
|
* SS = __USER_DS
|
|
*
|
|
* ECX will not match pt_regs->cx, but we're returning to a vDSO
|
|
* trampoline that will fix up RCX, so this is okay.
|
|
*
|
|
* R12-R15 are callee-saved, so they contain whatever was in them
|
|
* when the system call started, which is already known to user
|
|
* code. We zero R8-R10 to avoid info leaks.
|
|
*/
|
|
xorq %r8, %r8
|
|
xorq %r9, %r9
|
|
xorq %r10, %r10
|
|
movq RSP-ORIG_RAX(%rsp), %rsp
|
|
swapgs
|
|
sysretl
|
|
END(entry_SYSCALL_compat)
|
|
|
|
/*
|
|
* Emulated IA32 system calls via int 0x80.
|
|
*
|
|
* Arguments:
|
|
* eax system call number
|
|
* ebx arg1
|
|
* ecx arg2
|
|
* edx arg3
|
|
* esi arg4
|
|
* edi arg5
|
|
* ebp arg6 (note: not saved in the stack frame, should not be touched)
|
|
*
|
|
* Notes:
|
|
* Uses the same stack frame as the x86-64 version.
|
|
* All registers except eax must be saved (but ptrace may violate that).
|
|
* Arguments are zero extended. For system calls that want sign extension and
|
|
* take long arguments a wrapper is needed. Most calls can just be called
|
|
* directly.
|
|
* Assumes it is only called from user space and entered with interrupts off.
|
|
*/
|
|
|
|
ENTRY(entry_INT80_compat)
|
|
/*
|
|
* Interrupts are off on entry.
|
|
*/
|
|
PARAVIRT_ADJUST_EXCEPTION_FRAME
|
|
ASM_CLAC /* Do this early to minimize exposure */
|
|
SWAPGS
|
|
|
|
/*
|
|
* User tracing code (ptrace or signal handlers) might assume that
|
|
* the saved RAX contains a 32-bit number when we're invoking a 32-bit
|
|
* syscall. Just in case the high bits are nonzero, zero-extend
|
|
* the syscall number. (This could almost certainly be deleted
|
|
* with no ill effects.)
|
|
*/
|
|
movl %eax, %eax
|
|
|
|
/* Construct struct pt_regs on stack (iret frame is already on stack) */
|
|
pushq %rax /* pt_regs->orig_ax */
|
|
pushq %rdi /* pt_regs->di */
|
|
pushq %rsi /* pt_regs->si */
|
|
pushq %rdx /* pt_regs->dx */
|
|
pushq %rcx /* pt_regs->cx */
|
|
pushq $-ENOSYS /* pt_regs->ax */
|
|
xorq %r8,%r8
|
|
pushq %r8 /* pt_regs->r8 = 0 */
|
|
pushq %r8 /* pt_regs->r9 = 0 */
|
|
pushq %r8 /* pt_regs->r10 = 0 */
|
|
pushq %r8 /* pt_regs->r11 = 0 */
|
|
pushq %rbx /* pt_regs->rbx */
|
|
pushq %rbp /* pt_regs->rbp */
|
|
pushq %r12 /* pt_regs->r12 */
|
|
pushq %r13 /* pt_regs->r13 */
|
|
pushq %r14 /* pt_regs->r14 */
|
|
pushq %r15 /* pt_regs->r15 */
|
|
cld
|
|
|
|
/*
|
|
* User mode is traced as though IRQs are on, and the interrupt
|
|
* gate turned them off.
|
|
*/
|
|
TRACE_IRQS_OFF
|
|
|
|
movq %rsp, %rdi
|
|
call do_syscall_32_irqs_off
|
|
.Lsyscall_32_done:
|
|
|
|
/* Go back to user mode. */
|
|
TRACE_IRQS_ON
|
|
SWAPGS
|
|
jmp restore_regs_and_iret
|
|
END(entry_INT80_compat)
|
|
|
|
ALIGN
|
|
GLOBAL(stub32_clone)
|
|
/*
|
|
* The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr).
|
|
* The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val).
|
|
*
|
|
* The native 64-bit kernel's sys_clone() implements the latter,
|
|
* so we need to swap arguments here before calling it:
|
|
*/
|
|
xchg %r8, %rcx
|
|
jmp sys_clone
|