linux/arch/x86/ia32/ia32entry.S
Andy Lutomirski 653bc77af6 x86_64, entry: Fix out of bounds read on sysenter
Rusty noticed a Really Bad Bug (tm) in my NT fix.  The entry code
reads out of bounds, causing the NT fix to be unreliable.  But, and
this is much, much worse, if your stack is somehow just below the
top of the direct map (or a hole), you read out of bounds and crash.

Excerpt from the crash:

[    1.129513] RSP: 0018:ffff88001da4bf88  EFLAGS: 00010296

  2b:*    f7 84 24 90 00 00 00     testl  $0x4000,0x90(%rsp)

That read is deterministically above the top of the stack.  I
thought I even single-stepped through this code when I wrote it to
check the offset, but I clearly screwed it up.

Fixes: 8c7aa698ba ("x86_64, entry: Filter RFLAGS.NT on entry from userspace")
Reported-by: Rusty Russell <rusty@ozlabs.org>
Cc: stable@vger.kernel.org
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-31 18:47:09 -07:00

515 lines
14 KiB
ArmAsm

/*
* Compatibility mode system call entry point for x86-64.
*
* Copyright 2000-2002 Andi Kleen, SuSE Labs.
*/
#include <asm/dwarf2.h>
#include <asm/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>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
#include <linux/elf-em.h>
#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE)
#define __AUDIT_ARCH_LE 0x40000000
#ifndef CONFIG_AUDITSYSCALL
#define sysexit_audit ia32_ret_from_sys_call
#define sysretl_audit ia32_ret_from_sys_call
#endif
.section .entry.text, "ax"
.macro IA32_ARG_FIXUP noebp=0
movl %edi,%r8d
.if \noebp
.else
movl %ebp,%r9d
.endif
xchg %ecx,%esi
movl %ebx,%edi
movl %edx,%edx /* zero extension */
.endm
/* clobbers %eax */
.macro CLEAR_RREGS offset=0, _r9=rax
xorl %eax,%eax
movq %rax,\offset+R11(%rsp)
movq %rax,\offset+R10(%rsp)
movq %\_r9,\offset+R9(%rsp)
movq %rax,\offset+R8(%rsp)
.endm
/*
* Reload arg registers from stack in case ptrace changed them.
* We don't reload %eax because syscall_trace_enter() returned
* the %rax value we should see. Instead, we just truncate that
* value to 32 bits again as we did on entry from user mode.
* If it's a new value set by user_regset during entry tracing,
* this matches the normal truncation of the user-mode value.
* If it's -1 to make us punt the syscall, then (u32)-1 is still
* an appropriately invalid value.
*/
.macro LOAD_ARGS32 offset, _r9=0
.if \_r9
movl \offset+16(%rsp),%r9d
.endif
movl \offset+40(%rsp),%ecx
movl \offset+48(%rsp),%edx
movl \offset+56(%rsp),%esi
movl \offset+64(%rsp),%edi
movl %eax,%eax /* zero extension */
.endm
.macro CFI_STARTPROC32 simple
CFI_STARTPROC \simple
CFI_UNDEFINED r8
CFI_UNDEFINED r9
CFI_UNDEFINED r10
CFI_UNDEFINED r11
CFI_UNDEFINED r12
CFI_UNDEFINED r13
CFI_UNDEFINED r14
CFI_UNDEFINED r15
.endm
#ifdef CONFIG_PARAVIRT
ENTRY(native_usergs_sysret32)
swapgs
sysretl
ENDPROC(native_usergs_sysret32)
ENTRY(native_irq_enable_sysexit)
swapgs
sti
sysexit
ENDPROC(native_irq_enable_sysexit)
#endif
/*
* 32bit SYSENTER instruction entry.
*
* Arguments:
* %eax System call number.
* %ebx Arg1
* %ecx Arg2
* %edx Arg3
* %esi Arg4
* %edi Arg5
* %ebp user stack
* 0(%ebp) Arg6
*
* Interrupts off.
*
* This is purely a fast path. For anything complicated we use the int 0x80
* path below. Set up a complete hardware stack frame to share code
* with the int 0x80 path.
*/
ENTRY(ia32_sysenter_target)
CFI_STARTPROC32 simple
CFI_SIGNAL_FRAME
CFI_DEF_CFA rsp,0
CFI_REGISTER rsp,rbp
SWAPGS_UNSAFE_STACK
movq PER_CPU_VAR(kernel_stack), %rsp
addq $(KERNEL_STACK_OFFSET),%rsp
/*
* No need to follow this irqs on/off section: the syscall
* disabled irqs, here we enable it straight after entry:
*/
ENABLE_INTERRUPTS(CLBR_NONE)
movl %ebp,%ebp /* zero extension */
pushq_cfi $__USER32_DS
/*CFI_REL_OFFSET ss,0*/
pushq_cfi %rbp
CFI_REL_OFFSET rsp,0
pushfq_cfi
/*CFI_REL_OFFSET rflags,0*/
movl TI_sysenter_return+THREAD_INFO(%rsp,3*8-KERNEL_STACK_OFFSET),%r10d
CFI_REGISTER rip,r10
pushq_cfi $__USER32_CS
/*CFI_REL_OFFSET cs,0*/
movl %eax, %eax
pushq_cfi %r10
CFI_REL_OFFSET rip,0
pushq_cfi %rax
cld
SAVE_ARGS 0,1,0
/* no need to do an access_ok check here because rbp has been
32bit zero extended */
ASM_STAC
1: movl (%rbp),%ebp
_ASM_EXTABLE(1b,ia32_badarg)
ASM_CLAC
/*
* Sysenter doesn't filter flags, so we need to clear NT
* ourselves. To save a few cycles, we can check whether
* NT was set instead of doing an unconditional popfq.
*/
testl $X86_EFLAGS_NT,EFLAGS-ARGOFFSET(%rsp)
jnz sysenter_fix_flags
sysenter_flags_fixed:
orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
CFI_REMEMBER_STATE
jnz sysenter_tracesys
cmpq $(IA32_NR_syscalls-1),%rax
ja ia32_badsys
sysenter_do_call:
IA32_ARG_FIXUP
sysenter_dispatch:
call *ia32_sys_call_table(,%rax,8)
movq %rax,RAX-ARGOFFSET(%rsp)
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
jnz sysexit_audit
sysexit_from_sys_call:
andl $~TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
/* clear IF, that popfq doesn't enable interrupts early */
andl $~0x200,EFLAGS-R11(%rsp)
movl RIP-R11(%rsp),%edx /* User %eip */
CFI_REGISTER rip,rdx
RESTORE_ARGS 0,24,0,0,0,0
xorq %r8,%r8
xorq %r9,%r9
xorq %r10,%r10
xorq %r11,%r11
popfq_cfi
/*CFI_RESTORE rflags*/
popq_cfi %rcx /* User %esp */
CFI_REGISTER rsp,rcx
TRACE_IRQS_ON
ENABLE_INTERRUPTS_SYSEXIT32
CFI_RESTORE_STATE
#ifdef CONFIG_AUDITSYSCALL
.macro auditsys_entry_common
movl %esi,%r8d /* 5th arg: 4th syscall arg */
movl %ecx,%r9d /*swap with edx*/
movl %edx,%ecx /* 4th arg: 3rd syscall arg */
movl %r9d,%edx /* 3rd arg: 2nd syscall arg */
movl %ebx,%esi /* 2nd arg: 1st syscall arg */
movl %eax,%edi /* 1st arg: syscall number */
call __audit_syscall_entry
movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall number */
cmpq $(IA32_NR_syscalls-1),%rax
ja ia32_badsys
movl %ebx,%edi /* reload 1st syscall arg */
movl RCX-ARGOFFSET(%rsp),%esi /* reload 2nd syscall arg */
movl RDX-ARGOFFSET(%rsp),%edx /* reload 3rd syscall arg */
movl RSI-ARGOFFSET(%rsp),%ecx /* reload 4th syscall arg */
movl RDI-ARGOFFSET(%rsp),%r8d /* reload 5th syscall arg */
.endm
.macro auditsys_exit exit
testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
jnz ia32_ret_from_sys_call
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
movl %eax,%esi /* second arg, syscall return value */
cmpl $-MAX_ERRNO,%eax /* is it an error ? */
jbe 1f
movslq %eax, %rsi /* if error sign extend to 64 bits */
1: setbe %al /* 1 if error, 0 if not */
movzbl %al,%edi /* zero-extend that into %edi */
call __audit_syscall_exit
movq RAX-ARGOFFSET(%rsp),%rax /* reload syscall return value */
movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
testl %edi,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
jz \exit
CLEAR_RREGS -ARGOFFSET
jmp int_with_check
.endm
sysenter_auditsys:
auditsys_entry_common
movl %ebp,%r9d /* reload 6th syscall arg */
jmp sysenter_dispatch
sysexit_audit:
auditsys_exit sysexit_from_sys_call
#endif
sysenter_fix_flags:
pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
popfq_cfi
jmp sysenter_flags_fixed
sysenter_tracesys:
#ifdef CONFIG_AUDITSYSCALL
testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
jz sysenter_auditsys
#endif
SAVE_REST
CLEAR_RREGS
movq $-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */
RESTORE_REST
cmpq $(IA32_NR_syscalls-1),%rax
ja int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */
jmp sysenter_do_call
CFI_ENDPROC
ENDPROC(ia32_sysenter_target)
/*
* 32bit SYSCALL instruction entry.
*
* Arguments:
* %eax System call number.
* %ebx Arg1
* %ecx return EIP
* %edx Arg3
* %esi Arg4
* %edi Arg5
* %ebp Arg2 [note: not saved in the stack frame, should not be touched]
* %esp user stack
* 0(%esp) Arg6
*
* Interrupts off.
*
* This is purely a fast path. For anything complicated we use the int 0x80
* path below. Set up a complete hardware stack frame to share code
* with the int 0x80 path.
*/
ENTRY(ia32_cstar_target)
CFI_STARTPROC32 simple
CFI_SIGNAL_FRAME
CFI_DEF_CFA rsp,KERNEL_STACK_OFFSET
CFI_REGISTER rip,rcx
/*CFI_REGISTER rflags,r11*/
SWAPGS_UNSAFE_STACK
movl %esp,%r8d
CFI_REGISTER rsp,r8
movq PER_CPU_VAR(kernel_stack),%rsp
/*
* No need to follow this irqs on/off section: the syscall
* disabled irqs and here we enable it straight after entry:
*/
ENABLE_INTERRUPTS(CLBR_NONE)
SAVE_ARGS 8,0,0
movl %eax,%eax /* zero extension */
movq %rax,ORIG_RAX-ARGOFFSET(%rsp)
movq %rcx,RIP-ARGOFFSET(%rsp)
CFI_REL_OFFSET rip,RIP-ARGOFFSET
movq %rbp,RCX-ARGOFFSET(%rsp) /* this lies slightly to ptrace */
movl %ebp,%ecx
movq $__USER32_CS,CS-ARGOFFSET(%rsp)
movq $__USER32_DS,SS-ARGOFFSET(%rsp)
movq %r11,EFLAGS-ARGOFFSET(%rsp)
/*CFI_REL_OFFSET rflags,EFLAGS-ARGOFFSET*/
movq %r8,RSP-ARGOFFSET(%rsp)
CFI_REL_OFFSET rsp,RSP-ARGOFFSET
/* no need to do an access_ok check here because r8 has been
32bit zero extended */
/* hardware stack frame is complete now */
ASM_STAC
1: movl (%r8),%r9d
_ASM_EXTABLE(1b,ia32_badarg)
ASM_CLAC
orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
CFI_REMEMBER_STATE
jnz cstar_tracesys
cmpq $IA32_NR_syscalls-1,%rax
ja ia32_badsys
cstar_do_call:
IA32_ARG_FIXUP 1
cstar_dispatch:
call *ia32_sys_call_table(,%rax,8)
movq %rax,RAX-ARGOFFSET(%rsp)
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
jnz sysretl_audit
sysretl_from_sys_call:
andl $~TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
RESTORE_ARGS 0,-ARG_SKIP,0,0,0
movl RIP-ARGOFFSET(%rsp),%ecx
CFI_REGISTER rip,rcx
movl EFLAGS-ARGOFFSET(%rsp),%r11d
/*CFI_REGISTER rflags,r11*/
xorq %r10,%r10
xorq %r9,%r9
xorq %r8,%r8
TRACE_IRQS_ON
movl RSP-ARGOFFSET(%rsp),%esp
CFI_RESTORE rsp
USERGS_SYSRET32
#ifdef CONFIG_AUDITSYSCALL
cstar_auditsys:
CFI_RESTORE_STATE
movl %r9d,R9-ARGOFFSET(%rsp) /* register to be clobbered by call */
auditsys_entry_common
movl R9-ARGOFFSET(%rsp),%r9d /* reload 6th syscall arg */
jmp cstar_dispatch
sysretl_audit:
auditsys_exit sysretl_from_sys_call
#endif
cstar_tracesys:
#ifdef CONFIG_AUDITSYSCALL
testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
jz cstar_auditsys
#endif
xchgl %r9d,%ebp
SAVE_REST
CLEAR_RREGS 0, r9
movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
LOAD_ARGS32 ARGOFFSET, 1 /* reload args from stack in case ptrace changed it */
RESTORE_REST
xchgl %ebp,%r9d
cmpq $(IA32_NR_syscalls-1),%rax
ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */
jmp cstar_do_call
END(ia32_cstar_target)
ia32_badarg:
ASM_CLAC
movq $-EFAULT,%rax
jmp ia32_sysret
CFI_ENDPROC
/*
* 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(ia32_syscall)
CFI_STARTPROC32 simple
CFI_SIGNAL_FRAME
CFI_DEF_CFA rsp,SS+8-RIP
/*CFI_REL_OFFSET ss,SS-RIP*/
CFI_REL_OFFSET rsp,RSP-RIP
/*CFI_REL_OFFSET rflags,EFLAGS-RIP*/
/*CFI_REL_OFFSET cs,CS-RIP*/
CFI_REL_OFFSET rip,RIP-RIP
PARAVIRT_ADJUST_EXCEPTION_FRAME
SWAPGS
/*
* No need to follow this irqs on/off section: the syscall
* disabled irqs and here we enable it straight after entry:
*/
ENABLE_INTERRUPTS(CLBR_NONE)
movl %eax,%eax
pushq_cfi %rax
cld
/* note the registers are not zero extended to the sf.
this could be a problem. */
SAVE_ARGS 0,1,0
orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
jnz ia32_tracesys
cmpq $(IA32_NR_syscalls-1),%rax
ja ia32_badsys
ia32_do_call:
IA32_ARG_FIXUP
call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
ia32_sysret:
movq %rax,RAX-ARGOFFSET(%rsp)
ia32_ret_from_sys_call:
CLEAR_RREGS -ARGOFFSET
jmp int_ret_from_sys_call
ia32_tracesys:
SAVE_REST
CLEAR_RREGS
movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
movq %rsp,%rdi /* &pt_regs -> arg1 */
call syscall_trace_enter
LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */
RESTORE_REST
cmpq $(IA32_NR_syscalls-1),%rax
ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */
jmp ia32_do_call
END(ia32_syscall)
ia32_badsys:
movq $0,ORIG_RAX-ARGOFFSET(%rsp)
movq $-ENOSYS,%rax
jmp ia32_sysret
CFI_ENDPROC
.macro PTREGSCALL label, func
ALIGN
GLOBAL(\label)
leaq \func(%rip),%rax
jmp ia32_ptregs_common
.endm
CFI_STARTPROC32
PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn
PTREGSCALL stub32_sigreturn, sys32_sigreturn
PTREGSCALL stub32_execve, compat_sys_execve
PTREGSCALL stub32_fork, sys_fork
PTREGSCALL stub32_vfork, sys_vfork
ALIGN
GLOBAL(stub32_clone)
leaq sys_clone(%rip),%rax
mov %r8, %rcx
jmp ia32_ptregs_common
ALIGN
ia32_ptregs_common:
popq %r11
CFI_ENDPROC
CFI_STARTPROC32 simple
CFI_SIGNAL_FRAME
CFI_DEF_CFA rsp,SS+8-ARGOFFSET
CFI_REL_OFFSET rax,RAX-ARGOFFSET
CFI_REL_OFFSET rcx,RCX-ARGOFFSET
CFI_REL_OFFSET rdx,RDX-ARGOFFSET
CFI_REL_OFFSET rsi,RSI-ARGOFFSET
CFI_REL_OFFSET rdi,RDI-ARGOFFSET
CFI_REL_OFFSET rip,RIP-ARGOFFSET
/* CFI_REL_OFFSET cs,CS-ARGOFFSET*/
/* CFI_REL_OFFSET rflags,EFLAGS-ARGOFFSET*/
CFI_REL_OFFSET rsp,RSP-ARGOFFSET
/* CFI_REL_OFFSET ss,SS-ARGOFFSET*/
SAVE_REST
call *%rax
RESTORE_REST
jmp ia32_sysret /* misbalances the return cache */
CFI_ENDPROC
END(ia32_ptregs_common)