linux/arch/x86/ia32/ia32entry.S

499 lines
13 KiB
ArmAsm
Raw Normal View History

/*
* 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>
Audit: push audit success and retcode into arch ptrace.h The audit system previously expected arches calling to audit_syscall_exit to supply as arguments if the syscall was a success and what the return code was. Audit also provides a helper AUDITSC_RESULT which was supposed to simplify things by converting from negative retcodes to an audit internal magic value stating success or failure. This helper was wrong and could indicate that a valid pointer returned to userspace was a failed syscall. The fix is to fix the layering foolishness. We now pass audit_syscall_exit a struct pt_reg and it in turns calls back into arch code to collect the return value and to determine if the syscall was a success or failure. We also define a generic is_syscall_success() macro which determines success/failure based on if the value is < -MAX_ERRNO. This works for arches like x86 which do not use a separate mechanism to indicate syscall failure. We make both the is_syscall_success() and regs_return_value() static inlines instead of macros. The reason is because the audit function must take a void* for the regs. (uml calls theirs struct uml_pt_regs instead of just struct pt_regs so audit_syscall_exit can't take a struct pt_regs). Since the audit function takes a void* we need to use static inlines to cast it back to the arch correct structure to dereference it. The other major change is that on some arches, like ia64, MIPS and ppc, we change regs_return_value() to give us the negative value on syscall failure. THE only other user of this macro, kretprobe_example.c, won't notice and it makes the value signed consistently for the audit functions across all archs. In arch/sh/kernel/ptrace_64.c I see that we were using regs[9] in the old audit code as the return value. But the ptrace_64.h code defined the macro regs_return_value() as regs[3]. I have no idea which one is correct, but this patch now uses the regs_return_value() function, so it now uses regs[3]. For powerpc we previously used regs->result but now use the regs_return_value() function which uses regs->gprs[3]. regs->gprs[3] is always positive so the regs_return_value(), much like ia64 makes it negative before calling the audit code when appropriate. Signed-off-by: Eric Paris <eparis@redhat.com> Acked-by: H. Peter Anvin <hpa@zytor.com> [for x86 portion] Acked-by: Tony Luck <tony.luck@intel.com> [for ia64] Acked-by: Richard Weinberger <richard@nod.at> [for uml] Acked-by: David S. Miller <davem@davemloft.net> [for sparc] Acked-by: Ralf Baechle <ralf@linux-mips.org> [for mips] Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> [for ppc]
2012-01-03 19:23:06 +00:00
#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
x86: Separate out entry text section Put x86 entry code into a separate link section: .entry.text. Separating the entry text section seems to have performance benefits - caused by more efficient instruction cache usage. Running hackbench with perf stat --repeat showed that the change compresses the icache footprint. The icache load miss rate went down by about 15%: before patch: 19417627 L1-icache-load-misses ( +- 0.147% ) after patch: 16490788 L1-icache-load-misses ( +- 0.180% ) The motivation of the patch was to fix a particular kprobes bug that relates to the entry text section, the performance advantage was discovered accidentally. Whole perf output follows: - results for current tip tree: Performance counter stats for './hackbench/hackbench 10' (500 runs): 19417627 L1-icache-load-misses ( +- 0.147% ) 2676914223 instructions # 0.497 IPC ( +- 0.079% ) 5389516026 cycles ( +- 0.144% ) 0.206267711 seconds time elapsed ( +- 0.138% ) - results for current tip tree with the patch applied: Performance counter stats for './hackbench/hackbench 10' (500 runs): 16490788 L1-icache-load-misses ( +- 0.180% ) 2717734941 instructions # 0.502 IPC ( +- 0.079% ) 5414756975 cycles ( +- 0.148% ) 0.206747566 seconds time elapsed ( +- 0.137% ) Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: masami.hiramatsu.pt@hitachi.com Cc: ananth@in.ibm.com Cc: davem@davemloft.net Cc: 2nddept-manager@sdl.hitachi.co.jp LKML-Reference: <20110307181039.GB15197@jolsa.redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-03-07 18:10:39 +00:00
.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
x86/paravirt: groundwork for 64-bit Xen support, fix Ingo Molnar wrote: > * Jeremy Fitzhardinge <jeremy@goop.org> wrote: > > >>> It quickly broke the build in testing: >>> >>> include/asm/pgalloc.h: In function ‘paravirt_pgd_free': >>> include/asm/pgalloc.h:14: error: parameter name omitted >>> arch/x86/kernel/entry_64.S: In file included from >>> arch/x86/kernel/traps_64.c:51:include/asm/pgalloc.h: In function >>> ‘paravirt_pgd_free': >>> include/asm/pgalloc.h:14: error: parameter name omitted >>> >>> >> No, looks like my fault. The non-PARAVIRT version of >> paravirt_pgd_free() is: >> >> static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *) {} >> >> but C doesn't like missing parameter names, even if unused. >> >> This should fix it: >> > > that fixed the build but now we've got a boot crash with this config: > > time.c: Detected 2010.304 MHz processor. > spurious 8259A interrupt: IRQ7. > BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 > IP: [<0000000000000000>] > PGD 0 > Thread overran stack, or stack corrupted > Oops: 0010 [1] SMP > CPU 0 > > with: > > http://redhat.com/~mingo/misc/config-Thu_Jun_26_12_46_46_CEST_2008.bad > Use SWAPGS_UNSAFE_STACK in ia32entry.S in the places where the active stack is the usermode stack. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: xen-devel <xen-devel@lists.xensource.com> Cc: Stephen Tweedie <sct@redhat.com> Cc: Eduardo Habkost <ehabkost@redhat.com> Cc: Mark McLoughlin <markmc@redhat.com> Cc: Vegard Nossum <vegard.nossum@gmail.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Yinghai Lu <yhlu.kernel@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-06-26 14:28:51 +00:00
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
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
#ifdef CONFIG_AUDITSYSCALL
.macro auditsys_entry_common
movl %esi,%r9d /* 6th arg: 4th syscall arg */
movl %edx,%r8d /* 5th arg: 3rd syscall arg */
/* (already in %ecx) 4th arg: 2nd syscall arg */
movl %ebx,%edx /* 3rd arg: 1st syscall arg */
movl %eax,%esi /* 2nd arg: syscall number */
movl $AUDIT_ARCH_I386,%edi /* 1st arg: audit arch */
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 */
Audit: push audit success and retcode into arch ptrace.h The audit system previously expected arches calling to audit_syscall_exit to supply as arguments if the syscall was a success and what the return code was. Audit also provides a helper AUDITSC_RESULT which was supposed to simplify things by converting from negative retcodes to an audit internal magic value stating success or failure. This helper was wrong and could indicate that a valid pointer returned to userspace was a failed syscall. The fix is to fix the layering foolishness. We now pass audit_syscall_exit a struct pt_reg and it in turns calls back into arch code to collect the return value and to determine if the syscall was a success or failure. We also define a generic is_syscall_success() macro which determines success/failure based on if the value is < -MAX_ERRNO. This works for arches like x86 which do not use a separate mechanism to indicate syscall failure. We make both the is_syscall_success() and regs_return_value() static inlines instead of macros. The reason is because the audit function must take a void* for the regs. (uml calls theirs struct uml_pt_regs instead of just struct pt_regs so audit_syscall_exit can't take a struct pt_regs). Since the audit function takes a void* we need to use static inlines to cast it back to the arch correct structure to dereference it. The other major change is that on some arches, like ia64, MIPS and ppc, we change regs_return_value() to give us the negative value on syscall failure. THE only other user of this macro, kretprobe_example.c, won't notice and it makes the value signed consistently for the audit functions across all archs. In arch/sh/kernel/ptrace_64.c I see that we were using regs[9] in the old audit code as the return value. But the ptrace_64.h code defined the macro regs_return_value() as regs[3]. I have no idea which one is correct, but this patch now uses the regs_return_value() function, so it now uses regs[3]. For powerpc we previously used regs->result but now use the regs_return_value() function which uses regs->gprs[3]. regs->gprs[3] is always positive so the regs_return_value(), much like ia64 makes it negative before calling the audit code when appropriate. Signed-off-by: Eric Paris <eparis@redhat.com> Acked-by: H. Peter Anvin <hpa@zytor.com> [for x86 portion] Acked-by: Tony Luck <tony.luck@intel.com> [for ia64] Acked-by: Richard Weinberger <richard@nod.at> [for uml] Acked-by: David S. Miller <davem@davemloft.net> [for sparc] Acked-by: Ralf Baechle <ralf@linux-mips.org> [for mips] Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> [for ppc]
2012-01-03 19:23:06 +00:00
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 */
Audit: push audit success and retcode into arch ptrace.h The audit system previously expected arches calling to audit_syscall_exit to supply as arguments if the syscall was a success and what the return code was. Audit also provides a helper AUDITSC_RESULT which was supposed to simplify things by converting from negative retcodes to an audit internal magic value stating success or failure. This helper was wrong and could indicate that a valid pointer returned to userspace was a failed syscall. The fix is to fix the layering foolishness. We now pass audit_syscall_exit a struct pt_reg and it in turns calls back into arch code to collect the return value and to determine if the syscall was a success or failure. We also define a generic is_syscall_success() macro which determines success/failure based on if the value is < -MAX_ERRNO. This works for arches like x86 which do not use a separate mechanism to indicate syscall failure. We make both the is_syscall_success() and regs_return_value() static inlines instead of macros. The reason is because the audit function must take a void* for the regs. (uml calls theirs struct uml_pt_regs instead of just struct pt_regs so audit_syscall_exit can't take a struct pt_regs). Since the audit function takes a void* we need to use static inlines to cast it back to the arch correct structure to dereference it. The other major change is that on some arches, like ia64, MIPS and ppc, we change regs_return_value() to give us the negative value on syscall failure. THE only other user of this macro, kretprobe_example.c, won't notice and it makes the value signed consistently for the audit functions across all archs. In arch/sh/kernel/ptrace_64.c I see that we were using regs[9] in the old audit code as the return value. But the ptrace_64.h code defined the macro regs_return_value() as regs[3]. I have no idea which one is correct, but this patch now uses the regs_return_value() function, so it now uses regs[3]. For powerpc we previously used regs->result but now use the regs_return_value() function which uses regs->gprs[3]. regs->gprs[3] is always positive so the regs_return_value(), much like ia64 makes it negative before calling the audit code when appropriate. Signed-off-by: Eric Paris <eparis@redhat.com> Acked-by: H. Peter Anvin <hpa@zytor.com> [for x86 portion] Acked-by: Tony Luck <tony.luck@intel.com> [for ia64] Acked-by: Richard Weinberger <richard@nod.at> [for uml] Acked-by: David S. Miller <davem@davemloft.net> [for sparc] Acked-by: Ralf Baechle <ralf@linux-mips.org> [for mips] Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> [for ppc]
2012-01-03 19:23:06 +00:00
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:
CFI_RESTORE_STATE
auditsys_entry_common
movl %ebp,%r9d /* reload 6th syscall arg */
jmp sysenter_dispatch
sysexit_audit:
auditsys_exit sysexit_from_sys_call
#endif
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*/
x86/paravirt: groundwork for 64-bit Xen support, fix Ingo Molnar wrote: > * Jeremy Fitzhardinge <jeremy@goop.org> wrote: > > >>> It quickly broke the build in testing: >>> >>> include/asm/pgalloc.h: In function ‘paravirt_pgd_free': >>> include/asm/pgalloc.h:14: error: parameter name omitted >>> arch/x86/kernel/entry_64.S: In file included from >>> arch/x86/kernel/traps_64.c:51:include/asm/pgalloc.h: In function >>> ‘paravirt_pgd_free': >>> include/asm/pgalloc.h:14: error: parameter name omitted >>> >>> >> No, looks like my fault. The non-PARAVIRT version of >> paravirt_pgd_free() is: >> >> static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *) {} >> >> but C doesn't like missing parameter names, even if unused. >> >> This should fix it: >> > > that fixed the build but now we've got a boot crash with this config: > > time.c: Detected 2010.304 MHz processor. > spurious 8259A interrupt: IRQ7. > BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 > IP: [<0000000000000000>] > PGD 0 > Thread overran stack, or stack corrupted > Oops: 0010 [1] SMP > CPU 0 > > with: > > http://redhat.com/~mingo/misc/config-Thu_Jun_26_12_46_46_CEST_2008.bad > Use SWAPGS_UNSAFE_STACK in ia32entry.S in the places where the active stack is the usermode stack. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: xen-devel <xen-devel@lists.xensource.com> Cc: Stephen Tweedie <sct@redhat.com> Cc: Eduardo Habkost <ehabkost@redhat.com> Cc: Mark McLoughlin <markmc@redhat.com> Cc: Vegard Nossum <vegard.nossum@gmail.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Yinghai Lu <yhlu.kernel@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-06-26 14:28:51 +00:00
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)