2005-04-17 06:20:36 +08:00
|
|
|
/*
|
2015-06-08 15:49:11 +08:00
|
|
|
* Copyright (C) 1991,1992 Linus Torvalds
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
2015-06-08 15:49:11 +08:00
|
|
|
* entry_32.S contains the system-call and low-level fault and trap handling routines.
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
2007-05-03 01:27:19 +08:00
|
|
|
* Stack layout in 'syscall_exit':
|
2015-06-08 15:49:11 +08:00
|
|
|
* ptrace needs to have all registers on the stack.
|
|
|
|
* If the order here is changed, it needs to be
|
|
|
|
* updated in fork.c:copy_process(), signal.c:do_signal(),
|
2005-04-17 06:20:36 +08:00
|
|
|
* ptrace.c and ptrace.h
|
|
|
|
*
|
|
|
|
* 0(%esp) - %ebx
|
|
|
|
* 4(%esp) - %ecx
|
|
|
|
* 8(%esp) - %edx
|
2015-06-09 04:35:33 +08:00
|
|
|
* C(%esp) - %esi
|
2005-04-17 06:20:36 +08:00
|
|
|
* 10(%esp) - %edi
|
|
|
|
* 14(%esp) - %ebp
|
|
|
|
* 18(%esp) - %eax
|
|
|
|
* 1C(%esp) - %ds
|
|
|
|
* 20(%esp) - %es
|
2007-02-13 20:26:20 +08:00
|
|
|
* 24(%esp) - %fs
|
2009-02-09 21:17:40 +08:00
|
|
|
* 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS
|
|
|
|
* 2C(%esp) - orig_eax
|
|
|
|
* 30(%esp) - %eip
|
|
|
|
* 34(%esp) - %cs
|
|
|
|
* 38(%esp) - %eflags
|
|
|
|
* 3C(%esp) - %oldesp
|
|
|
|
* 40(%esp) - %oldss
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/linkage.h>
|
2012-01-04 03:23:06 +08:00
|
|
|
#include <linux/err.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <asm/thread_info.h>
|
2006-07-03 15:24:43 +08:00
|
|
|
#include <asm/irqflags.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <asm/errno.h>
|
|
|
|
#include <asm/segment.h>
|
|
|
|
#include <asm/smp.h>
|
2009-02-14 03:14:01 +08:00
|
|
|
#include <asm/page_types.h>
|
2006-12-07 09:14:01 +08:00
|
|
|
#include <asm/percpu.h>
|
2008-03-26 03:16:32 +08:00
|
|
|
#include <asm/processor-flags.h>
|
2008-06-22 02:17:27 +08:00
|
|
|
#include <asm/ftrace.h>
|
2008-05-03 02:10:09 +08:00
|
|
|
#include <asm/irq_vectors.h>
|
2010-03-21 21:00:43 +08:00
|
|
|
#include <asm/cpufeature.h>
|
2011-08-26 04:10:33 +08:00
|
|
|
#include <asm/alternative-asm.h>
|
2012-04-21 03:19:50 +08:00
|
|
|
#include <asm/asm.h>
|
2012-09-22 04:58:10 +08:00
|
|
|
#include <asm/smap.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2011-03-08 02:10:39 +08:00
|
|
|
.section .entry.text, "ax"
|
|
|
|
|
2006-12-07 09:14:08 +08:00
|
|
|
/*
|
|
|
|
* We use macros for low-level operations which need to be overridden
|
|
|
|
* for paravirtualization. The following will never clobber any registers:
|
|
|
|
* INTERRUPT_RETURN (aka. "iret")
|
|
|
|
* GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
|
2008-06-25 12:19:26 +08:00
|
|
|
* ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
|
2006-12-07 09:14:08 +08:00
|
|
|
*
|
|
|
|
* For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
|
|
|
|
* specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
|
|
|
|
* Allowing a register to be clobbered can shrink the paravirt replacement
|
|
|
|
* enough to patch inline, increasing performance.
|
|
|
|
*/
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#ifdef CONFIG_PREEMPT
|
2015-06-08 15:49:11 +08:00
|
|
|
# define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
|
2005-04-17 06:20:36 +08:00
|
|
|
#else
|
2015-06-08 15:49:11 +08:00
|
|
|
# define preempt_stop(clobbers)
|
|
|
|
# define resume_kernel restore_all
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
2006-07-03 15:24:43 +08:00
|
|
|
.macro TRACE_IRQS_IRET
|
|
|
|
#ifdef CONFIG_TRACE_IRQFLAGS
|
2015-06-08 15:49:11 +08:00
|
|
|
testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off?
|
|
|
|
jz 1f
|
2006-07-03 15:24:43 +08:00
|
|
|
TRACE_IRQS_ON
|
|
|
|
1:
|
|
|
|
#endif
|
|
|
|
.endm
|
|
|
|
|
2009-02-09 21:17:40 +08:00
|
|
|
/*
|
|
|
|
* User gs save/restore
|
|
|
|
*
|
|
|
|
* %gs is used for userland TLS and kernel only uses it for stack
|
|
|
|
* canary which is required to be at %gs:20 by gcc. Read the comment
|
|
|
|
* at the top of stackprotector.h for more info.
|
|
|
|
*
|
|
|
|
* Local labels 98 and 99 are used.
|
|
|
|
*/
|
|
|
|
#ifdef CONFIG_X86_32_LAZY_GS
|
|
|
|
|
|
|
|
/* unfortunately push/pop can't be no-op */
|
|
|
|
.macro PUSH_GS
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $0
|
2009-02-09 21:17:40 +08:00
|
|
|
.endm
|
|
|
|
.macro POP_GS pop=0
|
2015-06-08 15:49:11 +08:00
|
|
|
addl $(4 + \pop), %esp
|
2009-02-09 21:17:40 +08:00
|
|
|
.endm
|
|
|
|
.macro POP_GS_EX
|
|
|
|
.endm
|
|
|
|
|
|
|
|
/* all the rest are no-op */
|
|
|
|
.macro PTGS_TO_GS
|
|
|
|
.endm
|
|
|
|
.macro PTGS_TO_GS_EX
|
|
|
|
.endm
|
|
|
|
.macro GS_TO_REG reg
|
|
|
|
.endm
|
|
|
|
.macro REG_TO_PTGS reg
|
|
|
|
.endm
|
|
|
|
.macro SET_KERNEL_GS reg
|
|
|
|
.endm
|
|
|
|
|
|
|
|
#else /* CONFIG_X86_32_LAZY_GS */
|
|
|
|
|
|
|
|
.macro PUSH_GS
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl %gs
|
2009-02-09 21:17:40 +08:00
|
|
|
.endm
|
|
|
|
|
|
|
|
.macro POP_GS pop=0
|
2015-06-08 15:49:11 +08:00
|
|
|
98: popl %gs
|
2009-02-09 21:17:40 +08:00
|
|
|
.if \pop <> 0
|
2015-06-09 04:35:33 +08:00
|
|
|
add $\pop, %esp
|
2009-02-09 21:17:40 +08:00
|
|
|
.endif
|
|
|
|
.endm
|
|
|
|
.macro POP_GS_EX
|
|
|
|
.pushsection .fixup, "ax"
|
2015-06-08 15:49:11 +08:00
|
|
|
99: movl $0, (%esp)
|
|
|
|
jmp 98b
|
2009-02-09 21:17:40 +08:00
|
|
|
.popsection
|
2015-06-08 15:49:11 +08:00
|
|
|
_ASM_EXTABLE(98b, 99b)
|
2009-02-09 21:17:40 +08:00
|
|
|
.endm
|
|
|
|
|
|
|
|
.macro PTGS_TO_GS
|
2015-06-08 15:49:11 +08:00
|
|
|
98: mov PT_GS(%esp), %gs
|
2009-02-09 21:17:40 +08:00
|
|
|
.endm
|
|
|
|
.macro PTGS_TO_GS_EX
|
|
|
|
.pushsection .fixup, "ax"
|
2015-06-08 15:49:11 +08:00
|
|
|
99: movl $0, PT_GS(%esp)
|
|
|
|
jmp 98b
|
2009-02-09 21:17:40 +08:00
|
|
|
.popsection
|
2015-06-08 15:49:11 +08:00
|
|
|
_ASM_EXTABLE(98b, 99b)
|
2009-02-09 21:17:40 +08:00
|
|
|
.endm
|
|
|
|
|
|
|
|
.macro GS_TO_REG reg
|
2015-06-08 15:49:11 +08:00
|
|
|
movl %gs, \reg
|
2009-02-09 21:17:40 +08:00
|
|
|
.endm
|
|
|
|
.macro REG_TO_PTGS reg
|
2015-06-08 15:49:11 +08:00
|
|
|
movl \reg, PT_GS(%esp)
|
2009-02-09 21:17:40 +08:00
|
|
|
.endm
|
|
|
|
.macro SET_KERNEL_GS reg
|
2015-06-08 15:49:11 +08:00
|
|
|
movl $(__KERNEL_STACK_CANARY), \reg
|
|
|
|
movl \reg, %gs
|
2009-02-09 21:17:40 +08:00
|
|
|
.endm
|
|
|
|
|
2015-06-08 15:49:11 +08:00
|
|
|
#endif /* CONFIG_X86_32_LAZY_GS */
|
2009-02-09 21:17:40 +08:00
|
|
|
|
2009-02-09 21:17:40 +08:00
|
|
|
.macro SAVE_ALL
|
|
|
|
cld
|
2009-02-09 21:17:40 +08:00
|
|
|
PUSH_GS
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl %fs
|
|
|
|
pushl %es
|
|
|
|
pushl %ds
|
|
|
|
pushl %eax
|
|
|
|
pushl %ebp
|
|
|
|
pushl %edi
|
|
|
|
pushl %esi
|
|
|
|
pushl %edx
|
|
|
|
pushl %ecx
|
|
|
|
pushl %ebx
|
|
|
|
movl $(__USER_DS), %edx
|
|
|
|
movl %edx, %ds
|
|
|
|
movl %edx, %es
|
|
|
|
movl $(__KERNEL_PERCPU), %edx
|
|
|
|
movl %edx, %fs
|
2009-02-09 21:17:40 +08:00
|
|
|
SET_KERNEL_GS %edx
|
2009-02-09 21:17:40 +08:00
|
|
|
.endm
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-02-09 21:17:40 +08:00
|
|
|
.macro RESTORE_INT_REGS
|
2015-06-08 15:49:11 +08:00
|
|
|
popl %ebx
|
|
|
|
popl %ecx
|
|
|
|
popl %edx
|
|
|
|
popl %esi
|
|
|
|
popl %edi
|
|
|
|
popl %ebp
|
|
|
|
popl %eax
|
2009-02-09 21:17:40 +08:00
|
|
|
.endm
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-02-09 21:17:40 +08:00
|
|
|
.macro RESTORE_REGS pop=0
|
2009-02-09 21:17:40 +08:00
|
|
|
RESTORE_INT_REGS
|
2015-06-08 15:49:11 +08:00
|
|
|
1: popl %ds
|
|
|
|
2: popl %es
|
|
|
|
3: popl %fs
|
2009-02-09 21:17:40 +08:00
|
|
|
POP_GS \pop
|
2009-02-09 21:17:40 +08:00
|
|
|
.pushsection .fixup, "ax"
|
2015-06-08 15:49:11 +08:00
|
|
|
4: movl $0, (%esp)
|
|
|
|
jmp 1b
|
|
|
|
5: movl $0, (%esp)
|
|
|
|
jmp 2b
|
|
|
|
6: movl $0, (%esp)
|
|
|
|
jmp 3b
|
[PATCH] i386: Use %gs as the PDA base-segment in the kernel
This patch is the meat of the PDA change. This patch makes several related
changes:
1: Most significantly, %gs is now used in the kernel. This means that on
entry, the old value of %gs is saved away, and it is reloaded with
__KERNEL_PDA.
2: entry.S constructs the stack in the shape of struct pt_regs, and this
is passed around the kernel so that the process's saved register
state can be accessed.
Unfortunately struct pt_regs doesn't currently have space for %gs
(or %fs). This patch extends pt_regs to add space for gs (no space
is allocated for %fs, since it won't be used, and it would just
complicate the code in entry.S to work around the space).
3: Because %gs is now saved on the stack like %ds, %es and the integer
registers, there are a number of places where it no longer needs to
be handled specially; namely context switch, and saving/restoring the
register state in a signal context.
4: And since kernel threads run in kernel space and call normal kernel
code, they need to be created with their %gs == __KERNEL_PDA.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: Chuck Ebbert <76306.1226@compuserve.com>
Cc: Zachary Amsden <zach@vmware.com>
Cc: Jan Beulich <jbeulich@novell.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
2006-12-07 09:14:02 +08:00
|
|
|
.popsection
|
2015-06-08 15:49:11 +08:00
|
|
|
_ASM_EXTABLE(1b, 4b)
|
|
|
|
_ASM_EXTABLE(2b, 5b)
|
|
|
|
_ASM_EXTABLE(3b, 6b)
|
2009-02-09 21:17:40 +08:00
|
|
|
POP_GS_EX
|
2009-02-09 21:17:40 +08:00
|
|
|
.endm
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
ENTRY(ret_from_fork)
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl %eax
|
|
|
|
call schedule_tail
|
2005-04-17 06:20:36 +08:00
|
|
|
GET_THREAD_INFO(%ebp)
|
2015-06-08 15:49:11 +08:00
|
|
|
popl %eax
|
|
|
|
pushl $0x0202 # Reset kernel eflags
|
x86/debug: Remove perpetually broken, unmaintainable dwarf annotations
So the dwarf2 annotations in low level assembly code have
become an increasing hindrance: unreadable, messy macros
mixed into some of the most security sensitive code paths
of the Linux kernel.
These debug info annotations don't even buy the upstream
kernel anything: dwarf driven stack unwinding has caused
problems in the past so it's out of tree, and the upstream
kernel only uses the much more robust framepointers based
stack unwinding method.
In addition to that there's a steady, slow bitrot going
on with these annotations, requiring frequent fixups.
There's no tooling and no functionality upstream that
keeps it correct.
So burn down the sick forest, allowing new, healthier growth:
27 files changed, 350 insertions(+), 1101 deletions(-)
Someone who has the willingness and time to do this
properly can attempt to reintroduce dwarf debuginfo in x86
assembly code plus dwarf unwinding from first principles,
with the following conditions:
- it should be maximally readable, and maximally low-key to
'ordinary' code reading and maintenance.
- find a build time method to insert dwarf annotations
automatically in the most common cases, for pop/push
instructions that manipulate the stack pointer. This could
be done for example via a preprocessing step that just
looks for common patterns - plus special annotations for
the few cases where we want to depart from the default.
We have hundreds of CFI annotations, so automating most of
that makes sense.
- it should come with build tooling checks that ensure that
CFI annotations are sensible. We've seen such efforts from
the framepointer side, and there's no reason it couldn't be
done on the dwarf side.
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: Frédéric Weisbecker <fweisbec@gmail.com
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jan Beulich <JBeulich@suse.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-28 18:21:47 +08:00
|
|
|
popfl
|
2015-06-08 15:49:11 +08:00
|
|
|
jmp syscall_exit
|
2007-02-13 20:26:24 +08:00
|
|
|
END(ret_from_fork)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2012-10-11 09:35:42 +08:00
|
|
|
ENTRY(ret_from_kernel_thread)
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl %eax
|
|
|
|
call schedule_tail
|
2012-08-03 03:05:11 +08:00
|
|
|
GET_THREAD_INFO(%ebp)
|
2015-06-08 15:49:11 +08:00
|
|
|
popl %eax
|
|
|
|
pushl $0x0202 # Reset kernel eflags
|
x86/debug: Remove perpetually broken, unmaintainable dwarf annotations
So the dwarf2 annotations in low level assembly code have
become an increasing hindrance: unreadable, messy macros
mixed into some of the most security sensitive code paths
of the Linux kernel.
These debug info annotations don't even buy the upstream
kernel anything: dwarf driven stack unwinding has caused
problems in the past so it's out of tree, and the upstream
kernel only uses the much more robust framepointers based
stack unwinding method.
In addition to that there's a steady, slow bitrot going
on with these annotations, requiring frequent fixups.
There's no tooling and no functionality upstream that
keeps it correct.
So burn down the sick forest, allowing new, healthier growth:
27 files changed, 350 insertions(+), 1101 deletions(-)
Someone who has the willingness and time to do this
properly can attempt to reintroduce dwarf debuginfo in x86
assembly code plus dwarf unwinding from first principles,
with the following conditions:
- it should be maximally readable, and maximally low-key to
'ordinary' code reading and maintenance.
- find a build time method to insert dwarf annotations
automatically in the most common cases, for pop/push
instructions that manipulate the stack pointer. This could
be done for example via a preprocessing step that just
looks for common patterns - plus special annotations for
the few cases where we want to depart from the default.
We have hundreds of CFI annotations, so automating most of
that makes sense.
- it should come with build tooling checks that ensure that
CFI annotations are sensible. We've seen such efforts from
the framepointer side, and there's no reason it couldn't be
done on the dwarf side.
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: Frédéric Weisbecker <fweisbec@gmail.com
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jan Beulich <JBeulich@suse.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-28 18:21:47 +08:00
|
|
|
popfl
|
2015-06-08 15:49:11 +08:00
|
|
|
movl PT_EBP(%esp), %eax
|
|
|
|
call *PT_EBX(%esp)
|
|
|
|
movl $0, PT_EAX(%esp)
|
|
|
|
jmp syscall_exit
|
2012-10-11 09:35:42 +08:00
|
|
|
ENDPROC(ret_from_kernel_thread)
|
2012-08-03 03:05:11 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Return to user mode is not as complex as all this looks,
|
|
|
|
* but we want the default path for a system call return to
|
|
|
|
* go as quickly as possible which is why some of this is
|
|
|
|
* less clear than it otherwise should be.
|
|
|
|
*/
|
|
|
|
|
|
|
|
# userspace resumption stub bypassing syscall exit tracing
|
|
|
|
ALIGN
|
|
|
|
ret_from_exception:
|
2006-12-07 09:14:08 +08:00
|
|
|
preempt_stop(CLBR_ANY)
|
2005-04-17 06:20:36 +08:00
|
|
|
ret_from_intr:
|
|
|
|
GET_THREAD_INFO(%ebp)
|
2012-03-23 04:39:25 +08:00
|
|
|
#ifdef CONFIG_VM86
|
2015-06-08 15:49:11 +08:00
|
|
|
movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS
|
|
|
|
movb PT_CS(%esp), %al
|
|
|
|
andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
|
2012-03-23 04:39:25 +08:00
|
|
|
#else
|
|
|
|
/*
|
2012-08-03 03:05:11 +08:00
|
|
|
* We can be coming here from child spawned by kernel_thread().
|
2012-03-23 04:39:25 +08:00
|
|
|
*/
|
2015-06-08 15:49:11 +08:00
|
|
|
movl PT_CS(%esp), %eax
|
|
|
|
andl $SEGMENT_RPL_MASK, %eax
|
2012-03-23 04:39:25 +08:00
|
|
|
#endif
|
2015-06-08 15:49:11 +08:00
|
|
|
cmpl $USER_RPL, %eax
|
|
|
|
jb resume_kernel # not returning to v8086 or userspace
|
[PATCH] i386: Use %gs as the PDA base-segment in the kernel
This patch is the meat of the PDA change. This patch makes several related
changes:
1: Most significantly, %gs is now used in the kernel. This means that on
entry, the old value of %gs is saved away, and it is reloaded with
__KERNEL_PDA.
2: entry.S constructs the stack in the shape of struct pt_regs, and this
is passed around the kernel so that the process's saved register
state can be accessed.
Unfortunately struct pt_regs doesn't currently have space for %gs
(or %fs). This patch extends pt_regs to add space for gs (no space
is allocated for %fs, since it won't be used, and it would just
complicate the code in entry.S to work around the space).
3: Because %gs is now saved on the stack like %ds, %es and the integer
registers, there are a number of places where it no longer needs to
be handled specially; namely context switch, and saving/restoring the
register state in a signal context.
4: And since kernel threads run in kernel space and call normal kernel
code, they need to be created with their %gs == __KERNEL_PDA.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: Chuck Ebbert <76306.1226@compuserve.com>
Cc: Zachary Amsden <zach@vmware.com>
Cc: Jan Beulich <jbeulich@novell.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
2006-12-07 09:14:02 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
ENTRY(resume_userspace)
|
2015-08-01 05:41:09 +08:00
|
|
|
DISABLE_INTERRUPTS(CLBR_ANY)
|
2008-06-06 16:14:08 +08:00
|
|
|
TRACE_IRQS_OFF
|
2015-08-01 05:41:09 +08:00
|
|
|
movl %esp, %eax
|
|
|
|
call prepare_exit_to_usermode
|
2015-06-08 15:49:11 +08:00
|
|
|
jmp restore_all
|
2007-02-13 20:26:24 +08:00
|
|
|
END(ret_from_exception)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#ifdef CONFIG_PREEMPT
|
|
|
|
ENTRY(resume_kernel)
|
2006-12-07 09:14:08 +08:00
|
|
|
DISABLE_INTERRUPTS(CLBR_ANY)
|
2005-04-17 06:20:36 +08:00
|
|
|
need_resched:
|
2015-06-08 15:49:11 +08:00
|
|
|
cmpl $0, PER_CPU_VAR(__preempt_count)
|
|
|
|
jnz restore_all
|
|
|
|
testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ?
|
|
|
|
jz restore_all
|
|
|
|
call preempt_schedule_irq
|
|
|
|
jmp need_resched
|
2007-02-13 20:26:24 +08:00
|
|
|
END(resume_kernel)
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
2015-06-08 15:49:11 +08:00
|
|
|
/*
|
|
|
|
* SYSENTER_RETURN points to after the SYSENTER instruction
|
|
|
|
* in the vsyscall page. See vsyscall-sysentry.S, which defines
|
|
|
|
* the symbol.
|
|
|
|
*/
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2015-06-08 15:49:11 +08:00
|
|
|
# SYSENTER call handler stub
|
2015-06-08 14:33:56 +08:00
|
|
|
ENTRY(entry_SYSENTER_32)
|
2015-06-08 15:49:11 +08:00
|
|
|
movl TSS_sysenter_sp0(%esp), %esp
|
2005-04-17 06:20:36 +08:00
|
|
|
sysenter_past_esp:
|
2006-07-03 15:24:43 +08:00
|
|
|
/*
|
2008-03-25 07:43:21 +08:00
|
|
|
* Interrupts are disabled here, but we can't trace it until
|
|
|
|
* enough kernel state to call TRACE_IRQS_OFF can be called - but
|
|
|
|
* we immediately enable interrupts at that point anyway.
|
2006-07-03 15:24:43 +08:00
|
|
|
*/
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $__USER_DS
|
|
|
|
pushl %ebp
|
x86/debug: Remove perpetually broken, unmaintainable dwarf annotations
So the dwarf2 annotations in low level assembly code have
become an increasing hindrance: unreadable, messy macros
mixed into some of the most security sensitive code paths
of the Linux kernel.
These debug info annotations don't even buy the upstream
kernel anything: dwarf driven stack unwinding has caused
problems in the past so it's out of tree, and the upstream
kernel only uses the much more robust framepointers based
stack unwinding method.
In addition to that there's a steady, slow bitrot going
on with these annotations, requiring frequent fixups.
There's no tooling and no functionality upstream that
keeps it correct.
So burn down the sick forest, allowing new, healthier growth:
27 files changed, 350 insertions(+), 1101 deletions(-)
Someone who has the willingness and time to do this
properly can attempt to reintroduce dwarf debuginfo in x86
assembly code plus dwarf unwinding from first principles,
with the following conditions:
- it should be maximally readable, and maximally low-key to
'ordinary' code reading and maintenance.
- find a build time method to insert dwarf annotations
automatically in the most common cases, for pop/push
instructions that manipulate the stack pointer. This could
be done for example via a preprocessing step that just
looks for common patterns - plus special annotations for
the few cases where we want to depart from the default.
We have hundreds of CFI annotations, so automating most of
that makes sense.
- it should come with build tooling checks that ensure that
CFI annotations are sensible. We've seen such efforts from
the framepointer side, and there's no reason it couldn't be
done on the dwarf side.
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: Frédéric Weisbecker <fweisbec@gmail.com
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jan Beulich <JBeulich@suse.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-28 18:21:47 +08:00
|
|
|
pushfl
|
2015-06-08 15:49:11 +08:00
|
|
|
orl $X86_EFLAGS_IF, (%esp)
|
|
|
|
pushl $__USER_CS
|
[PATCH] vdso: randomize the i386 vDSO by moving it into a vma
Move the i386 VDSO down into a vma and thus randomize it.
Besides the security implications, this feature also helps debuggers, which
can COW a vma-backed VDSO just like a normal DSO and can thus do
single-stepping and other debugging features.
It's good for hypervisors (Xen, VMWare) too, which typically live in the same
high-mapped address space as the VDSO, hence whenever the VDSO is used, they
get lots of guest pagefaults and have to fix such guest accesses up - which
slows things down instead of speeding things up (the primary purpose of the
VDSO).
There's a new CONFIG_COMPAT_VDSO (default=y) option, which provides support
for older glibcs that still rely on a prelinked high-mapped VDSO. Newer
distributions (using glibc 2.3.3 or later) can turn this option off. Turning
it off is also recommended for security reasons: attackers cannot use the
predictable high-mapped VDSO page as syscall trampoline anymore.
There is a new vdso=[0|1] boot option as well, and a runtime
/proc/sys/vm/vdso_enabled sysctl switch, that allows the VDSO to be turned
on/off.
(This version of the VDSO-randomization patch also has working ELF
coredumping, the previous patch crashed in the coredumping code.)
This code is a combined work of the exec-shield VDSO randomization
code and Gerd Hoffmann's hypervisor-centric VDSO patch. Rusty Russell
started this patch and i completed it.
[akpm@osdl.org: cleanups]
[akpm@osdl.org: compile fix]
[akpm@osdl.org: compile fix 2]
[akpm@osdl.org: compile fix 3]
[akpm@osdl.org: revernt MAXMEM change]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Cc: Gerd Hoffmann <kraxel@suse.de>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Zachary Amsden <zach@vmware.com>
Cc: Andi Kleen <ak@muc.de>
Cc: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 17:53:50 +08:00
|
|
|
/*
|
|
|
|
* Push current_thread_info()->sysenter_return to the stack.
|
2015-04-03 03:41:44 +08:00
|
|
|
* A tiny bit of offset fixup is necessary: TI_sysenter_return
|
|
|
|
* is relative to thread_info, which is at the bottom of the
|
|
|
|
* kernel stack page. 4*4 means the 4 words pushed above;
|
|
|
|
* TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack;
|
|
|
|
* and THREAD_SIZE takes us to the bottom.
|
[PATCH] vdso: randomize the i386 vDSO by moving it into a vma
Move the i386 VDSO down into a vma and thus randomize it.
Besides the security implications, this feature also helps debuggers, which
can COW a vma-backed VDSO just like a normal DSO and can thus do
single-stepping and other debugging features.
It's good for hypervisors (Xen, VMWare) too, which typically live in the same
high-mapped address space as the VDSO, hence whenever the VDSO is used, they
get lots of guest pagefaults and have to fix such guest accesses up - which
slows things down instead of speeding things up (the primary purpose of the
VDSO).
There's a new CONFIG_COMPAT_VDSO (default=y) option, which provides support
for older glibcs that still rely on a prelinked high-mapped VDSO. Newer
distributions (using glibc 2.3.3 or later) can turn this option off. Turning
it off is also recommended for security reasons: attackers cannot use the
predictable high-mapped VDSO page as syscall trampoline anymore.
There is a new vdso=[0|1] boot option as well, and a runtime
/proc/sys/vm/vdso_enabled sysctl switch, that allows the VDSO to be turned
on/off.
(This version of the VDSO-randomization patch also has working ELF
coredumping, the previous patch crashed in the coredumping code.)
This code is a combined work of the exec-shield VDSO randomization
code and Gerd Hoffmann's hypervisor-centric VDSO patch. Rusty Russell
started this patch and i completed it.
[akpm@osdl.org: cleanups]
[akpm@osdl.org: compile fix]
[akpm@osdl.org: compile fix 2]
[akpm@osdl.org: compile fix 3]
[akpm@osdl.org: revernt MAXMEM change]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Cc: Gerd Hoffmann <kraxel@suse.de>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Zachary Amsden <zach@vmware.com>
Cc: Andi Kleen <ak@muc.de>
Cc: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-27 17:53:50 +08:00
|
|
|
*/
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl %eax
|
2008-03-25 07:43:21 +08:00
|
|
|
SAVE_ALL
|
|
|
|
ENABLE_INTERRUPTS(CLBR_NONE)
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Load the potential sixth argument from user stack.
|
|
|
|
* Careful about security.
|
|
|
|
*/
|
2015-06-08 15:49:11 +08:00
|
|
|
cmpl $__PAGE_OFFSET-3, %ebp
|
|
|
|
jae syscall_fault
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_STAC
|
2015-06-08 15:49:11 +08:00
|
|
|
1: movl (%ebp), %ebp
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
movl %ebp, PT_EBP(%esp)
|
|
|
|
_ASM_EXTABLE(1b, syscall_fault)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
GET_THREAD_INFO(%ebp)
|
|
|
|
|
2015-06-08 15:49:11 +08:00
|
|
|
testl $_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
|
2015-08-01 05:41:08 +08:00
|
|
|
jnz syscall_trace_entry
|
2008-06-24 19:16:52 +08:00
|
|
|
sysenter_do_call:
|
2015-06-08 15:49:11 +08:00
|
|
|
cmpl $(NR_syscalls), %eax
|
|
|
|
jae sysenter_badsys
|
|
|
|
call *sys_call_table(, %eax, 4)
|
2014-06-24 05:22:15 +08:00
|
|
|
sysenter_after_call:
|
2015-06-08 15:49:11 +08:00
|
|
|
movl %eax, PT_EAX(%esp)
|
2007-10-12 04:11:12 +08:00
|
|
|
LOCKDEP_SYS_EXIT
|
2007-05-03 01:27:14 +08:00
|
|
|
DISABLE_INTERRUPTS(CLBR_ANY)
|
2006-07-03 15:24:43 +08:00
|
|
|
TRACE_IRQS_OFF
|
2015-06-08 15:49:11 +08:00
|
|
|
movl TI_flags(%ebp), %ecx
|
|
|
|
testl $_TIF_ALLWORK_MASK, %ecx
|
2015-08-01 05:41:09 +08:00
|
|
|
jnz syscall_exit_work_irqs_off
|
2008-06-24 19:16:52 +08:00
|
|
|
sysenter_exit:
|
2005-04-17 06:20:36 +08:00
|
|
|
/* if something modifies registers it must also disable sysexit */
|
2015-06-08 15:49:11 +08:00
|
|
|
movl PT_EIP(%esp), %edx
|
|
|
|
movl PT_OLDESP(%esp), %ecx
|
|
|
|
xorl %ebp, %ebp
|
2006-07-03 15:24:43 +08:00
|
|
|
TRACE_IRQS_ON
|
2015-06-08 15:49:11 +08:00
|
|
|
1: mov PT_FS(%esp), %fs
|
2009-02-09 21:17:40 +08:00
|
|
|
PTGS_TO_GS
|
2008-06-25 12:19:26 +08:00
|
|
|
ENABLE_INTERRUPTS_SYSEXIT
|
2008-06-24 19:16:52 +08:00
|
|
|
|
2015-06-08 15:49:11 +08:00
|
|
|
.pushsection .fixup, "ax"
|
|
|
|
2: movl $0, PT_FS(%esp)
|
|
|
|
jmp 1b
|
[PATCH] i386: Use %gs as the PDA base-segment in the kernel
This patch is the meat of the PDA change. This patch makes several related
changes:
1: Most significantly, %gs is now used in the kernel. This means that on
entry, the old value of %gs is saved away, and it is reloaded with
__KERNEL_PDA.
2: entry.S constructs the stack in the shape of struct pt_regs, and this
is passed around the kernel so that the process's saved register
state can be accessed.
Unfortunately struct pt_regs doesn't currently have space for %gs
(or %fs). This patch extends pt_regs to add space for gs (no space
is allocated for %fs, since it won't be used, and it would just
complicate the code in entry.S to work around the space).
3: Because %gs is now saved on the stack like %ds, %es and the integer
registers, there are a number of places where it no longer needs to
be handled specially; namely context switch, and saving/restoring the
register state in a signal context.
4: And since kernel threads run in kernel space and call normal kernel
code, they need to be created with their %gs == __KERNEL_PDA.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: Chuck Ebbert <76306.1226@compuserve.com>
Cc: Zachary Amsden <zach@vmware.com>
Cc: Jan Beulich <jbeulich@novell.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
2006-12-07 09:14:02 +08:00
|
|
|
.popsection
|
2015-06-08 15:49:11 +08:00
|
|
|
_ASM_EXTABLE(1b, 2b)
|
2009-02-09 21:17:40 +08:00
|
|
|
PTGS_TO_GS_EX
|
2015-06-08 14:33:56 +08:00
|
|
|
ENDPROC(entry_SYSENTER_32)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
# system call handler stub
|
2015-06-08 14:42:03 +08:00
|
|
|
ENTRY(entry_INT80_32)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl %eax # save orig_eax
|
2005-04-17 06:20:36 +08:00
|
|
|
SAVE_ALL
|
|
|
|
GET_THREAD_INFO(%ebp)
|
2015-06-08 15:49:11 +08:00
|
|
|
# system call tracing in operation / emulation
|
|
|
|
testl $_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
|
|
|
|
jnz syscall_trace_entry
|
|
|
|
cmpl $(NR_syscalls), %eax
|
|
|
|
jae syscall_badsys
|
2005-04-17 06:20:36 +08:00
|
|
|
syscall_call:
|
2015-06-08 15:49:11 +08:00
|
|
|
call *sys_call_table(, %eax, 4)
|
x86_32, entry: Store badsys error code in %eax
Commit 554086d ("x86_32, entry: Do syscall exit work on badsys
(CVE-2014-4508)") introduced a regression in the x86_32 syscall entry
code, resulting in syscall() not returning proper errors for undefined
syscalls on CPUs supporting the sysenter feature.
The following code:
> int result = syscall(666);
> printf("result=%d errno=%d error=%s\n", result, errno, strerror(errno));
results in:
> result=666 errno=0 error=Success
Obviously, the syscall return value is the called syscall number, but it
should have been an ENOSYS error. When run under ptrace it behaves
correctly, which makes it hard to debug in the wild:
> result=-1 errno=38 error=Function not implemented
The %eax register is the return value register. For debugging via ptrace
the syscall entry code stores the complete register context on the
stack. The badsys handlers only store the ENOSYS error code in the
ptrace register set and do not set %eax like a regular syscall handler
would. The old resume_userspace call chain contains code that clobbers
%eax and it restores %eax from the ptrace registers afterwards. The same
goes for the ptrace-enabled call chain. When ptrace is not used, the
syscall return value is the passed-in syscall number from the untouched
%eax register.
Use %eax as the return value register in syscall_badsys and
sysenter_badsys, like a real syscall handler does, and have the caller
push the value onto the stack for ptrace access.
Signed-off-by: Sven Wegener <sven.wegener@stealer.net>
Link: http://lkml.kernel.org/r/alpine.LNX.2.11.1407221022380.31021@titan.int.lan.stealer.net
Reviewed-and-tested-by: Andy Lutomirski <luto@amacapital.net>
Cc: <stable@vger.kernel.org> # If 554086d is backported
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2014-07-22 16:26:06 +08:00
|
|
|
syscall_after_call:
|
2015-06-08 15:49:11 +08:00
|
|
|
movl %eax, PT_EAX(%esp) # store the return value
|
2005-04-17 06:20:36 +08:00
|
|
|
syscall_exit:
|
2015-08-01 05:41:09 +08:00
|
|
|
jmp syscall_exit_work
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
restore_all:
|
i386: fix return to 16-bit stack from NMI handler
Returning to a task with a 16-bit stack requires special care: the iret
instruction does not restore the high word of esp in that case. The
espfix code fixes this, but currently is not invoked on NMIs. This means
that a running task gets the upper word of esp clobbered due intervening
NMIs. To reproduce, compile and run the following program with the nmi
watchdog enabled (nmi_watchdog=2 on the command line). Using gdb you can
see that the high bits of esp contain garbage, while the low bits are
still correct.
This patch puts the espfix code back into the NMI code path.
The patch is slightly complicated due to the irqtrace infrastructure not
being NMI-safe. The NMI return path cannot call TRACE_IRQS_IRET.
Otherwise, the tail of the normal iret-code is correct for the nmi code
path too. To be able to share this code-path, the TRACE_IRQS_IRET was
move up a bit. The espfix code exists after the TRACE_IRQS_IRET, but
this code explicitly disables interrupts. This short interrupts-off
section is now not traced anymore. The return-to-kernel path now always
includes the preliminary test to decide if the espfix code should be
called. This is never the case, but doing it this way keeps the patch as
simple as possible and the few extra instructions should not affect
timing in any significant way.
#define _GNU_SOURCE
#include <stdio.h>
#include <sys/types.h>
#include <sys/mman.h>
#include <unistd.h>
#include <sys/syscall.h>
#include <asm/ldt.h>
int modify_ldt(int func, void *ptr, unsigned long bytecount)
{
return syscall(SYS_modify_ldt, func, ptr, bytecount);
}
/* this is assumed to be usable */
#define SEGBASEADDR 0x10000
#define SEGLIMIT 0x20000
/* 16-bit segment */
struct user_desc desc = {
.entry_number = 0,
.base_addr = SEGBASEADDR,
.limit = SEGLIMIT,
.seg_32bit = 0,
.contents = 0, /* ??? */
.read_exec_only = 0,
.limit_in_pages = 0,
.seg_not_present = 0,
.useable = 1
};
int main(void)
{
setvbuf(stdout, NULL, _IONBF, 0);
/* map a 64 kb segment */
char *pointer = mmap((void *)SEGBASEADDR, SEGLIMIT+1,
PROT_EXEC|PROT_READ|PROT_WRITE,
MAP_SHARED|MAP_ANONYMOUS, -1, 0);
if (pointer == NULL) {
printf("could not map space\n");
return 0;
}
/* write ldt, new mode */
int err = modify_ldt(0x11, &desc, sizeof(desc));
if (err) {
printf("error modifying ldt: %i\n", err);
return 0;
}
for (int i=0; i<1000; i++) {
asm volatile (
"pusha\n\t"
"mov %ss, %eax\n\t" /* preserve ss:esp */
"mov %esp, %ebp\n\t"
"push $7\n\t" /* index 0, ldt, user mode */
"push $65536-4096\n\t" /* esp */
"lss (%esp), %esp\n\t" /* switch to new stack */
"push %eax\n\t" /* save old ss:esp on new stack */
"push %ebp\n\t"
"add $17*65536, %esp\n\t" /* set high bits */
"mov %esp, %edx\n\t"
"mov $10000000, %ecx\n\t" /* wait... */
"1: loop 1b\n\t" /* ... a bit */
"cmp %esp, %edx\n\t"
"je 1f\n\t"
"ud2\n\t" /* esp changed inexplicably! */
"1:\n\t"
"sub $17*65536, %esp\n\t" /* restore high bits */
"lss (%esp), %esp\n\t" /* restore old ss:esp */
"popa\n\t");
printf("\rx%ix", i);
}
return 0;
}
Signed-off-by: Alexander van Heukelum <heukelum@fastmail.fm>
Acked-by: Stas Sergeev <stsp@aknet.ru>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-06-18 06:35:57 +08:00
|
|
|
TRACE_IRQS_IRET
|
|
|
|
restore_all_notrace:
|
2014-05-05 01:36:22 +08:00
|
|
|
#ifdef CONFIG_X86_ESPFIX32
|
2015-06-08 15:49:11 +08:00
|
|
|
movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS
|
|
|
|
/*
|
|
|
|
* Warning: PT_OLDSS(%esp) contains the wrong/random values if we
|
|
|
|
* are returning to the kernel.
|
|
|
|
* See comments in process.c:copy_thread() for details.
|
|
|
|
*/
|
|
|
|
movb PT_OLDSS(%esp), %ah
|
|
|
|
movb PT_CS(%esp), %al
|
|
|
|
andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
|
|
|
|
cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
|
|
|
|
je ldt_ss # returning to user-space with LDT SS
|
2014-05-05 01:36:22 +08:00
|
|
|
#endif
|
2005-04-17 06:20:36 +08:00
|
|
|
restore_nocheck:
|
2015-06-08 15:49:11 +08:00
|
|
|
RESTORE_REGS 4 # skip orig_eax/error_code
|
2008-02-14 05:29:53 +08:00
|
|
|
irq_return:
|
2008-02-10 06:24:08 +08:00
|
|
|
INTERRUPT_RETURN
|
2015-06-08 15:49:11 +08:00
|
|
|
.section .fixup, "ax"
|
|
|
|
ENTRY(iret_exc )
|
|
|
|
pushl $0 # no error code
|
|
|
|
pushl $do_iret_error
|
|
|
|
jmp error_code
|
2005-04-17 06:20:36 +08:00
|
|
|
.previous
|
2015-06-08 15:49:11 +08:00
|
|
|
_ASM_EXTABLE(irq_return, iret_exc)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2014-05-05 01:36:22 +08:00
|
|
|
#ifdef CONFIG_X86_ESPFIX32
|
2005-04-17 06:20:36 +08:00
|
|
|
ldt_ss:
|
2006-12-07 09:14:07 +08:00
|
|
|
#ifdef CONFIG_PARAVIRT
|
|
|
|
/*
|
|
|
|
* The kernel can't run on a non-flat stack if paravirt mode
|
|
|
|
* is active. Rather than try to fixup the high bits of
|
|
|
|
* ESP, bypass this code entirely. This may break DOSemu
|
|
|
|
* and/or Wine support in a paravirt VM, although the option
|
|
|
|
* is still available to implement the setting of the high
|
|
|
|
* 16-bits in the INTERRUPT_RETURN paravirt-op.
|
|
|
|
*/
|
2015-06-08 15:49:11 +08:00
|
|
|
cmpl $0, pv_info+PARAVIRT_enabled
|
|
|
|
jne restore_nocheck
|
2006-12-07 09:14:07 +08:00
|
|
|
#endif
|
|
|
|
|
i386: fix/simplify espfix stack switching, move it into assembly
The espfix code triggers if we have a protected mode userspace
application with a 16-bit stack. On returning to userspace, with iret,
the CPU doesn't restore the high word of the stack pointer. This is an
"official" bug, and the work-around used in the kernel is to temporarily
switch to a 32-bit stack segment/pointer pair where the high word of the
pointer is equal to the high word of the userspace stackpointer.
The current implementation uses THREAD_SIZE to determine the cut-off,
but there is no good reason not to use the more natural 64kb... However,
implementing this by simply substituting THREAD_SIZE with 65536 in
patch_espfix_desc crashed the test application. patch_espfix_desc tries
to do what is described above, but gets it subtly wrong if the userspace
stack pointer is just below a multiple of THREAD_SIZE: an overflow
occurs to bit 13... With a bit of luck, when the kernelspace
stackpointer is just below a 64kb-boundary, the overflow then ripples
trough to bit 16 and userspace will see its stack pointer changed by
65536.
This patch moves all espfix code into entry_32.S. Selecting a 16-bit
cut-off simplifies the code. The game with changing the limit dynamically
is removed too. It complicates matters and I see no value in it. Changing
only the top 16-bit word of ESP is one instruction and it also implies
that only two bytes of the ESPFIX GDT entry need to be changed and this
can be implemented in just a handful simple to understand instructions.
As a side effect, the operation to compute the original ESP from the
ESPFIX ESP and the GDT entry simplifies a bit too, and the remaining
three instructions have been expanded inline in entry_32.S.
impact: can now reliably run userspace with ESP=xxxxfffc on 16-bit
stack segment
Signed-off-by: Alexander van Heukelum <heukelum@fastmail.fm>
Acked-by: Stas Sergeev <stsp@aknet.ru>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-06-18 06:35:58 +08:00
|
|
|
/*
|
|
|
|
* Setup and switch to ESPFIX stack
|
|
|
|
*
|
|
|
|
* We're returning to userspace with a 16 bit stack. The CPU will not
|
|
|
|
* restore the high word of ESP for us on executing iret... This is an
|
|
|
|
* "official" bug of all the x86-compatible CPUs, which we can work
|
|
|
|
* around to make dosemu and wine happy. We do this by preloading the
|
|
|
|
* high word of ESP with the high word of the userspace ESP while
|
|
|
|
* compensating for the offset by changing to the ESPFIX segment with
|
|
|
|
* a base address that matches for the difference.
|
|
|
|
*/
|
2010-08-01 00:48:23 +08:00
|
|
|
#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
|
2015-06-08 15:49:11 +08:00
|
|
|
mov %esp, %edx /* load kernel esp */
|
|
|
|
mov PT_OLDESP(%esp), %eax /* load userspace esp */
|
|
|
|
mov %dx, %ax /* eax: new kernel esp */
|
2015-06-09 04:35:33 +08:00
|
|
|
sub %eax, %edx /* offset (low word is 0) */
|
|
|
|
shr $16, %edx
|
2015-06-08 15:49:11 +08:00
|
|
|
mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
|
|
|
|
mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
|
|
|
|
pushl $__ESPFIX_SS
|
|
|
|
pushl %eax /* new kernel esp */
|
|
|
|
/*
|
|
|
|
* Disable interrupts, but do not irqtrace this section: we
|
i386: fix return to 16-bit stack from NMI handler
Returning to a task with a 16-bit stack requires special care: the iret
instruction does not restore the high word of esp in that case. The
espfix code fixes this, but currently is not invoked on NMIs. This means
that a running task gets the upper word of esp clobbered due intervening
NMIs. To reproduce, compile and run the following program with the nmi
watchdog enabled (nmi_watchdog=2 on the command line). Using gdb you can
see that the high bits of esp contain garbage, while the low bits are
still correct.
This patch puts the espfix code back into the NMI code path.
The patch is slightly complicated due to the irqtrace infrastructure not
being NMI-safe. The NMI return path cannot call TRACE_IRQS_IRET.
Otherwise, the tail of the normal iret-code is correct for the nmi code
path too. To be able to share this code-path, the TRACE_IRQS_IRET was
move up a bit. The espfix code exists after the TRACE_IRQS_IRET, but
this code explicitly disables interrupts. This short interrupts-off
section is now not traced anymore. The return-to-kernel path now always
includes the preliminary test to decide if the espfix code should be
called. This is never the case, but doing it this way keeps the patch as
simple as possible and the few extra instructions should not affect
timing in any significant way.
#define _GNU_SOURCE
#include <stdio.h>
#include <sys/types.h>
#include <sys/mman.h>
#include <unistd.h>
#include <sys/syscall.h>
#include <asm/ldt.h>
int modify_ldt(int func, void *ptr, unsigned long bytecount)
{
return syscall(SYS_modify_ldt, func, ptr, bytecount);
}
/* this is assumed to be usable */
#define SEGBASEADDR 0x10000
#define SEGLIMIT 0x20000
/* 16-bit segment */
struct user_desc desc = {
.entry_number = 0,
.base_addr = SEGBASEADDR,
.limit = SEGLIMIT,
.seg_32bit = 0,
.contents = 0, /* ??? */
.read_exec_only = 0,
.limit_in_pages = 0,
.seg_not_present = 0,
.useable = 1
};
int main(void)
{
setvbuf(stdout, NULL, _IONBF, 0);
/* map a 64 kb segment */
char *pointer = mmap((void *)SEGBASEADDR, SEGLIMIT+1,
PROT_EXEC|PROT_READ|PROT_WRITE,
MAP_SHARED|MAP_ANONYMOUS, -1, 0);
if (pointer == NULL) {
printf("could not map space\n");
return 0;
}
/* write ldt, new mode */
int err = modify_ldt(0x11, &desc, sizeof(desc));
if (err) {
printf("error modifying ldt: %i\n", err);
return 0;
}
for (int i=0; i<1000; i++) {
asm volatile (
"pusha\n\t"
"mov %ss, %eax\n\t" /* preserve ss:esp */
"mov %esp, %ebp\n\t"
"push $7\n\t" /* index 0, ldt, user mode */
"push $65536-4096\n\t" /* esp */
"lss (%esp), %esp\n\t" /* switch to new stack */
"push %eax\n\t" /* save old ss:esp on new stack */
"push %ebp\n\t"
"add $17*65536, %esp\n\t" /* set high bits */
"mov %esp, %edx\n\t"
"mov $10000000, %ecx\n\t" /* wait... */
"1: loop 1b\n\t" /* ... a bit */
"cmp %esp, %edx\n\t"
"je 1f\n\t"
"ud2\n\t" /* esp changed inexplicably! */
"1:\n\t"
"sub $17*65536, %esp\n\t" /* restore high bits */
"lss (%esp), %esp\n\t" /* restore old ss:esp */
"popa\n\t");
printf("\rx%ix", i);
}
return 0;
}
Signed-off-by: Alexander van Heukelum <heukelum@fastmail.fm>
Acked-by: Stas Sergeev <stsp@aknet.ru>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-06-18 06:35:57 +08:00
|
|
|
* will soon execute iret and the tracer was already set to
|
2015-06-08 15:49:11 +08:00
|
|
|
* the irqstate after the IRET:
|
|
|
|
*/
|
2006-12-07 09:14:08 +08:00
|
|
|
DISABLE_INTERRUPTS(CLBR_EAX)
|
2015-06-08 15:49:11 +08:00
|
|
|
lss (%esp), %esp /* switch to espfix segment */
|
|
|
|
jmp restore_nocheck
|
2014-05-05 01:36:22 +08:00
|
|
|
#endif
|
2015-06-08 14:42:03 +08:00
|
|
|
ENDPROC(entry_INT80_32)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
# perform syscall exit tracing
|
|
|
|
ALIGN
|
|
|
|
syscall_trace_entry:
|
2015-06-08 15:49:11 +08:00
|
|
|
movl $-ENOSYS, PT_EAX(%esp)
|
|
|
|
movl %esp, %eax
|
|
|
|
call syscall_trace_enter
|
2008-07-09 17:38:07 +08:00
|
|
|
/* What it returned is what we'll actually use. */
|
2015-06-08 15:49:11 +08:00
|
|
|
cmpl $(NR_syscalls), %eax
|
|
|
|
jnae syscall_call
|
|
|
|
jmp syscall_exit
|
2007-02-13 20:26:24 +08:00
|
|
|
END(syscall_trace_entry)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
# perform syscall exit tracing
|
|
|
|
ALIGN
|
2015-08-01 05:41:09 +08:00
|
|
|
syscall_exit_work_irqs_off:
|
2006-07-03 15:24:43 +08:00
|
|
|
TRACE_IRQS_ON
|
2015-08-01 05:41:09 +08:00
|
|
|
ENABLE_INTERRUPTS(CLBR_ANY)
|
|
|
|
|
|
|
|
syscall_exit_work:
|
2015-06-08 15:49:11 +08:00
|
|
|
movl %esp, %eax
|
2015-08-01 05:41:09 +08:00
|
|
|
call syscall_return_slowpath
|
|
|
|
jmp restore_all
|
2007-02-13 20:26:24 +08:00
|
|
|
END(syscall_exit_work)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
syscall_fault:
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2005-04-17 06:20:36 +08:00
|
|
|
GET_THREAD_INFO(%ebp)
|
2015-06-08 15:49:11 +08:00
|
|
|
movl $-EFAULT, PT_EAX(%esp)
|
|
|
|
jmp resume_userspace
|
2007-02-13 20:26:24 +08:00
|
|
|
END(syscall_fault)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
syscall_badsys:
|
2015-06-08 15:49:11 +08:00
|
|
|
movl $-ENOSYS, %eax
|
|
|
|
jmp syscall_after_call
|
2014-06-24 05:22:15 +08:00
|
|
|
END(syscall_badsys)
|
|
|
|
|
|
|
|
sysenter_badsys:
|
2015-06-08 15:49:11 +08:00
|
|
|
movl $-ENOSYS, %eax
|
|
|
|
jmp sysenter_after_call
|
2014-08-15 16:57:46 +08:00
|
|
|
END(sysenter_badsys)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-02-09 21:17:40 +08:00
|
|
|
.macro FIXUP_ESPFIX_STACK
|
i386: fix/simplify espfix stack switching, move it into assembly
The espfix code triggers if we have a protected mode userspace
application with a 16-bit stack. On returning to userspace, with iret,
the CPU doesn't restore the high word of the stack pointer. This is an
"official" bug, and the work-around used in the kernel is to temporarily
switch to a 32-bit stack segment/pointer pair where the high word of the
pointer is equal to the high word of the userspace stackpointer.
The current implementation uses THREAD_SIZE to determine the cut-off,
but there is no good reason not to use the more natural 64kb... However,
implementing this by simply substituting THREAD_SIZE with 65536 in
patch_espfix_desc crashed the test application. patch_espfix_desc tries
to do what is described above, but gets it subtly wrong if the userspace
stack pointer is just below a multiple of THREAD_SIZE: an overflow
occurs to bit 13... With a bit of luck, when the kernelspace
stackpointer is just below a 64kb-boundary, the overflow then ripples
trough to bit 16 and userspace will see its stack pointer changed by
65536.
This patch moves all espfix code into entry_32.S. Selecting a 16-bit
cut-off simplifies the code. The game with changing the limit dynamically
is removed too. It complicates matters and I see no value in it. Changing
only the top 16-bit word of ESP is one instruction and it also implies
that only two bytes of the ESPFIX GDT entry need to be changed and this
can be implemented in just a handful simple to understand instructions.
As a side effect, the operation to compute the original ESP from the
ESPFIX ESP and the GDT entry simplifies a bit too, and the remaining
three instructions have been expanded inline in entry_32.S.
impact: can now reliably run userspace with ESP=xxxxfffc on 16-bit
stack segment
Signed-off-by: Alexander van Heukelum <heukelum@fastmail.fm>
Acked-by: Stas Sergeev <stsp@aknet.ru>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-06-18 06:35:58 +08:00
|
|
|
/*
|
|
|
|
* Switch back for ESPFIX stack to the normal zerobased stack
|
|
|
|
*
|
|
|
|
* We can't call C functions using the ESPFIX stack. This code reads
|
|
|
|
* the high word of the segment base from the GDT and swiches to the
|
|
|
|
* normal stack and adjusts ESP with the matching offset.
|
|
|
|
*/
|
2014-05-05 01:36:22 +08:00
|
|
|
#ifdef CONFIG_X86_ESPFIX32
|
i386: fix/simplify espfix stack switching, move it into assembly
The espfix code triggers if we have a protected mode userspace
application with a 16-bit stack. On returning to userspace, with iret,
the CPU doesn't restore the high word of the stack pointer. This is an
"official" bug, and the work-around used in the kernel is to temporarily
switch to a 32-bit stack segment/pointer pair where the high word of the
pointer is equal to the high word of the userspace stackpointer.
The current implementation uses THREAD_SIZE to determine the cut-off,
but there is no good reason not to use the more natural 64kb... However,
implementing this by simply substituting THREAD_SIZE with 65536 in
patch_espfix_desc crashed the test application. patch_espfix_desc tries
to do what is described above, but gets it subtly wrong if the userspace
stack pointer is just below a multiple of THREAD_SIZE: an overflow
occurs to bit 13... With a bit of luck, when the kernelspace
stackpointer is just below a 64kb-boundary, the overflow then ripples
trough to bit 16 and userspace will see its stack pointer changed by
65536.
This patch moves all espfix code into entry_32.S. Selecting a 16-bit
cut-off simplifies the code. The game with changing the limit dynamically
is removed too. It complicates matters and I see no value in it. Changing
only the top 16-bit word of ESP is one instruction and it also implies
that only two bytes of the ESPFIX GDT entry need to be changed and this
can be implemented in just a handful simple to understand instructions.
As a side effect, the operation to compute the original ESP from the
ESPFIX ESP and the GDT entry simplifies a bit too, and the remaining
three instructions have been expanded inline in entry_32.S.
impact: can now reliably run userspace with ESP=xxxxfffc on 16-bit
stack segment
Signed-off-by: Alexander van Heukelum <heukelum@fastmail.fm>
Acked-by: Stas Sergeev <stsp@aknet.ru>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-06-18 06:35:58 +08:00
|
|
|
/* fixup the stack */
|
2015-06-08 15:49:11 +08:00
|
|
|
mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
|
|
|
|
mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
|
2015-06-09 04:35:33 +08:00
|
|
|
shl $16, %eax
|
2015-06-08 15:49:11 +08:00
|
|
|
addl %esp, %eax /* the adjusted stack pointer */
|
|
|
|
pushl $__KERNEL_DS
|
|
|
|
pushl %eax
|
|
|
|
lss (%esp), %esp /* switch to the normal stack segment */
|
2014-05-05 01:36:22 +08:00
|
|
|
#endif
|
2009-02-09 21:17:40 +08:00
|
|
|
.endm
|
|
|
|
.macro UNWIND_ESPFIX_STACK
|
2014-05-05 01:36:22 +08:00
|
|
|
#ifdef CONFIG_X86_ESPFIX32
|
2015-06-08 15:49:11 +08:00
|
|
|
movl %ss, %eax
|
2009-02-09 21:17:40 +08:00
|
|
|
/* see if on espfix stack */
|
2015-06-08 15:49:11 +08:00
|
|
|
cmpw $__ESPFIX_SS, %ax
|
|
|
|
jne 27f
|
|
|
|
movl $__KERNEL_DS, %eax
|
|
|
|
movl %eax, %ds
|
|
|
|
movl %eax, %es
|
2009-02-09 21:17:40 +08:00
|
|
|
/* switch to normal stack */
|
|
|
|
FIXUP_ESPFIX_STACK
|
|
|
|
27:
|
2014-05-05 01:36:22 +08:00
|
|
|
#endif
|
2009-02-09 21:17:40 +08:00
|
|
|
.endm
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
2015-04-04 03:49:13 +08:00
|
|
|
* Build the entry stubs with some assembler magic.
|
|
|
|
* We pack 1 stub into every 8-byte block.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2015-04-04 03:49:13 +08:00
|
|
|
.align 8
|
2005-04-17 06:20:36 +08:00
|
|
|
ENTRY(irq_entries_start)
|
2015-04-04 03:49:13 +08:00
|
|
|
vector=FIRST_EXTERNAL_VECTOR
|
|
|
|
.rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $(~vector+0x80) /* Note: always in signed byte range */
|
2015-04-04 03:49:13 +08:00
|
|
|
vector=vector+1
|
|
|
|
jmp common_interrupt
|
|
|
|
.align 8
|
|
|
|
.endr
|
2007-02-13 20:26:24 +08:00
|
|
|
END(irq_entries_start)
|
|
|
|
|
2006-07-03 15:24:43 +08:00
|
|
|
/*
|
|
|
|
* the CPU automatically disables interrupts when executing an IRQ vector,
|
|
|
|
* so IRQ-flags tracing has to follow that:
|
|
|
|
*/
|
2008-11-12 05:24:58 +08:00
|
|
|
.p2align CONFIG_X86_L1_CACHE_SHIFT
|
2005-04-17 06:20:36 +08:00
|
|
|
common_interrupt:
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
addl $-0x80, (%esp) /* Adjust vector into the [-256, -1] range */
|
2005-04-17 06:20:36 +08:00
|
|
|
SAVE_ALL
|
2006-07-03 15:24:43 +08:00
|
|
|
TRACE_IRQS_OFF
|
2015-06-08 15:49:11 +08:00
|
|
|
movl %esp, %eax
|
|
|
|
call do_IRQ
|
|
|
|
jmp ret_from_intr
|
2007-02-13 20:26:24 +08:00
|
|
|
ENDPROC(common_interrupt)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-01-21 16:26:06 +08:00
|
|
|
#define BUILD_INTERRUPT3(name, nr, fn) \
|
2005-04-17 06:20:36 +08:00
|
|
|
ENTRY(name) \
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC; \
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $~(nr); \
|
2006-06-26 19:57:44 +08:00
|
|
|
SAVE_ALL; \
|
2006-07-03 15:24:43 +08:00
|
|
|
TRACE_IRQS_OFF \
|
2015-06-08 15:49:11 +08:00
|
|
|
movl %esp, %eax; \
|
|
|
|
call fn; \
|
|
|
|
jmp ret_from_intr; \
|
2007-02-13 20:26:24 +08:00
|
|
|
ENDPROC(name)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
x86, trace: Add irq vector tracepoints
[Purpose of this patch]
As Vaibhav explained in the thread below, tracepoints for irq vectors
are useful.
http://www.spinics.net/lists/mm-commits/msg85707.html
<snip>
The current interrupt traces from irq_handler_entry and irq_handler_exit
provide when an interrupt is handled. They provide good data about when
the system has switched to kernel space and how it affects the currently
running processes.
There are some IRQ vectors which trigger the system into kernel space,
which are not handled in generic IRQ handlers. Tracing such events gives
us the information about IRQ interaction with other system events.
The trace also tells where the system is spending its time. We want to
know which cores are handling interrupts and how they are affecting other
processes in the system. Also, the trace provides information about when
the cores are idle and which interrupts are changing that state.
<snip>
On the other hand, my usecase is tracing just local timer event and
getting a value of instruction pointer.
I suggested to add an argument local timer event to get instruction pointer before.
But there is another way to get it with external module like systemtap.
So, I don't need to add any argument to irq vector tracepoints now.
[Patch Description]
Vaibhav's patch shared a trace point ,irq_vector_entry/irq_vector_exit, in all events.
But there is an above use case to trace specific irq_vector rather than tracing all events.
In this case, we are concerned about overhead due to unwanted events.
So, add following tracepoints instead of introducing irq_vector_entry/exit.
so that we can enable them independently.
- local_timer_vector
- reschedule_vector
- call_function_vector
- call_function_single_vector
- irq_work_entry_vector
- error_apic_vector
- thermal_apic_vector
- threshold_apic_vector
- spurious_apic_vector
- x86_platform_ipi_vector
Also, introduce a logic switching IDT at enabling/disabling time so that a time penalty
makes a zero when tracepoints are disabled. Detailed explanations are as follows.
- Create trace irq handlers with entering_irq()/exiting_irq().
- Create a new IDT, trace_idt_table, at boot time by adding a logic to
_set_gate(). It is just a copy of original idt table.
- Register the new handlers for tracpoints to the new IDT by introducing
macros to alloc_intr_gate() called at registering time of irq_vector handlers.
- Add checking, whether irq vector tracing is on/off, into load_current_idt().
This has to be done below debug checking for these reasons.
- Switching to debug IDT may be kicked while tracing is enabled.
- On the other hands, switching to trace IDT is kicked only when debugging
is disabled.
In addition, the new IDT is created only when CONFIG_TRACING is enabled to avoid being
used for other purposes.
Signed-off-by: Seiji Aguchi <seiji.aguchi@hds.com>
Link: http://lkml.kernel.org/r/51C323ED.5050708@hds.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
2013-06-20 23:46:53 +08:00
|
|
|
|
|
|
|
#ifdef CONFIG_TRACING
|
2015-06-08 15:49:11 +08:00
|
|
|
# define TRACE_BUILD_INTERRUPT(name, nr) BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name)
|
x86, trace: Add irq vector tracepoints
[Purpose of this patch]
As Vaibhav explained in the thread below, tracepoints for irq vectors
are useful.
http://www.spinics.net/lists/mm-commits/msg85707.html
<snip>
The current interrupt traces from irq_handler_entry and irq_handler_exit
provide when an interrupt is handled. They provide good data about when
the system has switched to kernel space and how it affects the currently
running processes.
There are some IRQ vectors which trigger the system into kernel space,
which are not handled in generic IRQ handlers. Tracing such events gives
us the information about IRQ interaction with other system events.
The trace also tells where the system is spending its time. We want to
know which cores are handling interrupts and how they are affecting other
processes in the system. Also, the trace provides information about when
the cores are idle and which interrupts are changing that state.
<snip>
On the other hand, my usecase is tracing just local timer event and
getting a value of instruction pointer.
I suggested to add an argument local timer event to get instruction pointer before.
But there is another way to get it with external module like systemtap.
So, I don't need to add any argument to irq vector tracepoints now.
[Patch Description]
Vaibhav's patch shared a trace point ,irq_vector_entry/irq_vector_exit, in all events.
But there is an above use case to trace specific irq_vector rather than tracing all events.
In this case, we are concerned about overhead due to unwanted events.
So, add following tracepoints instead of introducing irq_vector_entry/exit.
so that we can enable them independently.
- local_timer_vector
- reschedule_vector
- call_function_vector
- call_function_single_vector
- irq_work_entry_vector
- error_apic_vector
- thermal_apic_vector
- threshold_apic_vector
- spurious_apic_vector
- x86_platform_ipi_vector
Also, introduce a logic switching IDT at enabling/disabling time so that a time penalty
makes a zero when tracepoints are disabled. Detailed explanations are as follows.
- Create trace irq handlers with entering_irq()/exiting_irq().
- Create a new IDT, trace_idt_table, at boot time by adding a logic to
_set_gate(). It is just a copy of original idt table.
- Register the new handlers for tracpoints to the new IDT by introducing
macros to alloc_intr_gate() called at registering time of irq_vector handlers.
- Add checking, whether irq vector tracing is on/off, into load_current_idt().
This has to be done below debug checking for these reasons.
- Switching to debug IDT may be kicked while tracing is enabled.
- On the other hands, switching to trace IDT is kicked only when debugging
is disabled.
In addition, the new IDT is created only when CONFIG_TRACING is enabled to avoid being
used for other purposes.
Signed-off-by: Seiji Aguchi <seiji.aguchi@hds.com>
Link: http://lkml.kernel.org/r/51C323ED.5050708@hds.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
2013-06-20 23:46:53 +08:00
|
|
|
#else
|
2015-06-08 15:49:11 +08:00
|
|
|
# define TRACE_BUILD_INTERRUPT(name, nr)
|
x86, trace: Add irq vector tracepoints
[Purpose of this patch]
As Vaibhav explained in the thread below, tracepoints for irq vectors
are useful.
http://www.spinics.net/lists/mm-commits/msg85707.html
<snip>
The current interrupt traces from irq_handler_entry and irq_handler_exit
provide when an interrupt is handled. They provide good data about when
the system has switched to kernel space and how it affects the currently
running processes.
There are some IRQ vectors which trigger the system into kernel space,
which are not handled in generic IRQ handlers. Tracing such events gives
us the information about IRQ interaction with other system events.
The trace also tells where the system is spending its time. We want to
know which cores are handling interrupts and how they are affecting other
processes in the system. Also, the trace provides information about when
the cores are idle and which interrupts are changing that state.
<snip>
On the other hand, my usecase is tracing just local timer event and
getting a value of instruction pointer.
I suggested to add an argument local timer event to get instruction pointer before.
But there is another way to get it with external module like systemtap.
So, I don't need to add any argument to irq vector tracepoints now.
[Patch Description]
Vaibhav's patch shared a trace point ,irq_vector_entry/irq_vector_exit, in all events.
But there is an above use case to trace specific irq_vector rather than tracing all events.
In this case, we are concerned about overhead due to unwanted events.
So, add following tracepoints instead of introducing irq_vector_entry/exit.
so that we can enable them independently.
- local_timer_vector
- reschedule_vector
- call_function_vector
- call_function_single_vector
- irq_work_entry_vector
- error_apic_vector
- thermal_apic_vector
- threshold_apic_vector
- spurious_apic_vector
- x86_platform_ipi_vector
Also, introduce a logic switching IDT at enabling/disabling time so that a time penalty
makes a zero when tracepoints are disabled. Detailed explanations are as follows.
- Create trace irq handlers with entering_irq()/exiting_irq().
- Create a new IDT, trace_idt_table, at boot time by adding a logic to
_set_gate(). It is just a copy of original idt table.
- Register the new handlers for tracpoints to the new IDT by introducing
macros to alloc_intr_gate() called at registering time of irq_vector handlers.
- Add checking, whether irq vector tracing is on/off, into load_current_idt().
This has to be done below debug checking for these reasons.
- Switching to debug IDT may be kicked while tracing is enabled.
- On the other hands, switching to trace IDT is kicked only when debugging
is disabled.
In addition, the new IDT is created only when CONFIG_TRACING is enabled to avoid being
used for other purposes.
Signed-off-by: Seiji Aguchi <seiji.aguchi@hds.com>
Link: http://lkml.kernel.org/r/51C323ED.5050708@hds.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
2013-06-20 23:46:53 +08:00
|
|
|
#endif
|
|
|
|
|
2015-06-08 15:49:11 +08:00
|
|
|
#define BUILD_INTERRUPT(name, nr) \
|
|
|
|
BUILD_INTERRUPT3(name, nr, smp_##name); \
|
x86, trace: Add irq vector tracepoints
[Purpose of this patch]
As Vaibhav explained in the thread below, tracepoints for irq vectors
are useful.
http://www.spinics.net/lists/mm-commits/msg85707.html
<snip>
The current interrupt traces from irq_handler_entry and irq_handler_exit
provide when an interrupt is handled. They provide good data about when
the system has switched to kernel space and how it affects the currently
running processes.
There are some IRQ vectors which trigger the system into kernel space,
which are not handled in generic IRQ handlers. Tracing such events gives
us the information about IRQ interaction with other system events.
The trace also tells where the system is spending its time. We want to
know which cores are handling interrupts and how they are affecting other
processes in the system. Also, the trace provides information about when
the cores are idle and which interrupts are changing that state.
<snip>
On the other hand, my usecase is tracing just local timer event and
getting a value of instruction pointer.
I suggested to add an argument local timer event to get instruction pointer before.
But there is another way to get it with external module like systemtap.
So, I don't need to add any argument to irq vector tracepoints now.
[Patch Description]
Vaibhav's patch shared a trace point ,irq_vector_entry/irq_vector_exit, in all events.
But there is an above use case to trace specific irq_vector rather than tracing all events.
In this case, we are concerned about overhead due to unwanted events.
So, add following tracepoints instead of introducing irq_vector_entry/exit.
so that we can enable them independently.
- local_timer_vector
- reschedule_vector
- call_function_vector
- call_function_single_vector
- irq_work_entry_vector
- error_apic_vector
- thermal_apic_vector
- threshold_apic_vector
- spurious_apic_vector
- x86_platform_ipi_vector
Also, introduce a logic switching IDT at enabling/disabling time so that a time penalty
makes a zero when tracepoints are disabled. Detailed explanations are as follows.
- Create trace irq handlers with entering_irq()/exiting_irq().
- Create a new IDT, trace_idt_table, at boot time by adding a logic to
_set_gate(). It is just a copy of original idt table.
- Register the new handlers for tracpoints to the new IDT by introducing
macros to alloc_intr_gate() called at registering time of irq_vector handlers.
- Add checking, whether irq vector tracing is on/off, into load_current_idt().
This has to be done below debug checking for these reasons.
- Switching to debug IDT may be kicked while tracing is enabled.
- On the other hands, switching to trace IDT is kicked only when debugging
is disabled.
In addition, the new IDT is created only when CONFIG_TRACING is enabled to avoid being
used for other purposes.
Signed-off-by: Seiji Aguchi <seiji.aguchi@hds.com>
Link: http://lkml.kernel.org/r/51C323ED.5050708@hds.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
2013-06-20 23:46:53 +08:00
|
|
|
TRACE_BUILD_INTERRUPT(name, nr)
|
2009-01-21 16:26:06 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/* The include is where all of the SMP etc. interrupts come from */
|
2009-01-29 02:34:09 +08:00
|
|
|
#include <asm/entry_arch.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
ENTRY(coprocessor_error)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $0
|
|
|
|
pushl $do_coprocessor_error
|
|
|
|
jmp error_code
|
2007-02-13 20:26:24 +08:00
|
|
|
END(coprocessor_error)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
ENTRY(simd_coprocessor_error)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $0
|
2010-03-21 21:00:43 +08:00
|
|
|
#ifdef CONFIG_X86_INVD_BUG
|
|
|
|
/* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
|
2015-06-08 15:49:11 +08:00
|
|
|
ALTERNATIVE "pushl $do_general_protection", \
|
|
|
|
"pushl $do_simd_coprocessor_error", \
|
2015-01-18 19:35:55 +08:00
|
|
|
X86_FEATURE_XMM
|
2010-03-21 21:00:43 +08:00
|
|
|
#else
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $do_simd_coprocessor_error
|
2010-03-21 21:00:43 +08:00
|
|
|
#endif
|
2015-06-08 15:49:11 +08:00
|
|
|
jmp error_code
|
2007-02-13 20:26:24 +08:00
|
|
|
END(simd_coprocessor_error)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
ENTRY(device_not_available)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $-1 # mark this as an int
|
|
|
|
pushl $do_device_not_available
|
|
|
|
jmp error_code
|
2007-02-13 20:26:24 +08:00
|
|
|
END(device_not_available)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-12-07 09:14:07 +08:00
|
|
|
#ifdef CONFIG_PARAVIRT
|
|
|
|
ENTRY(native_iret)
|
2008-02-10 06:24:08 +08:00
|
|
|
iret
|
2012-04-21 03:19:50 +08:00
|
|
|
_ASM_EXTABLE(native_iret, iret_exc)
|
2007-02-13 20:26:24 +08:00
|
|
|
END(native_iret)
|
2006-12-07 09:14:07 +08:00
|
|
|
|
2008-06-25 12:19:26 +08:00
|
|
|
ENTRY(native_irq_enable_sysexit)
|
2006-12-07 09:14:07 +08:00
|
|
|
sti
|
|
|
|
sysexit
|
2008-06-25 12:19:26 +08:00
|
|
|
END(native_irq_enable_sysexit)
|
2006-12-07 09:14:07 +08:00
|
|
|
#endif
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
ENTRY(overflow)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $0
|
|
|
|
pushl $do_overflow
|
|
|
|
jmp error_code
|
2007-02-13 20:26:24 +08:00
|
|
|
END(overflow)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
ENTRY(bounds)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $0
|
|
|
|
pushl $do_bounds
|
|
|
|
jmp error_code
|
2007-02-13 20:26:24 +08:00
|
|
|
END(bounds)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
ENTRY(invalid_op)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $0
|
|
|
|
pushl $do_invalid_op
|
|
|
|
jmp error_code
|
2007-02-13 20:26:24 +08:00
|
|
|
END(invalid_op)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
ENTRY(coprocessor_segment_overrun)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $0
|
|
|
|
pushl $do_coprocessor_segment_overrun
|
|
|
|
jmp error_code
|
2007-02-13 20:26:24 +08:00
|
|
|
END(coprocessor_segment_overrun)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
ENTRY(invalid_TSS)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $do_invalid_TSS
|
|
|
|
jmp error_code
|
2007-02-13 20:26:24 +08:00
|
|
|
END(invalid_TSS)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
ENTRY(segment_not_present)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $do_segment_not_present
|
|
|
|
jmp error_code
|
2007-02-13 20:26:24 +08:00
|
|
|
END(segment_not_present)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
ENTRY(stack_segment)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $do_stack_segment
|
|
|
|
jmp error_code
|
2007-02-13 20:26:24 +08:00
|
|
|
END(stack_segment)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
ENTRY(alignment_check)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $do_alignment_check
|
|
|
|
jmp error_code
|
2007-02-13 20:26:24 +08:00
|
|
|
END(alignment_check)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
[PATCH] x86: error_code is not safe for kprobes
This patch moves the entry.S:error_entry to .kprobes.text section,
since code marked unsafe for kprobes jumps directly to entry.S::error_entry,
that must be marked unsafe as well.
This patch also moves all the ".previous.text" asm directives to ".previous"
for kprobes section.
AK: Following a similar i386 patch from Chuck Ebbert
AK: Also merged Jeremy's fix in.
+From: Jeremy Fitzhardinge <jeremy@goop.org>
KPROBE_ENTRY does a .section .kprobes.text, and expects its users to
do a .previous at the end of the function.
Unfortunately, if any code within the function switches sections, for
example .fixup, then the .previous ends up putting all subsequent code
into .fixup. Worse, any subsequent .fixup code gets intermingled with
the code its supposed to be fixing (which is also in .fixup). It's
surprising this didn't cause more havok.
The fix is to use .pushsection/.popsection, so this stuff nests
properly. A further cleanup would be to get rid of all
.section/.previous pairs, since they're inherently fragile.
+From: Chuck Ebbert <76306.1226@compuserve.com>
Because code marked unsafe for kprobes jumps directly to
entry.S::error_code, that must be marked unsafe as well.
The easiest way to do that is to move the page fault entry
point to just before error_code and let it inherit the same
section.
Also moved all the ".previous" asm directives for kprobes
sections to column 1 and removed ".text" from them.
Signed-off-by: Chuck Ebbert <76306.1226@compuserve.com>
Signed-off-by: Andi Kleen <ak@suse.de>
2006-09-26 16:52:34 +08:00
|
|
|
ENTRY(divide_error)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $0 # no error code
|
|
|
|
pushl $do_divide_error
|
|
|
|
jmp error_code
|
2007-02-13 20:26:24 +08:00
|
|
|
END(divide_error)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#ifdef CONFIG_X86_MCE
|
|
|
|
ENTRY(machine_check)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $0
|
|
|
|
pushl machine_check_vector
|
|
|
|
jmp error_code
|
2007-02-13 20:26:24 +08:00
|
|
|
END(machine_check)
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
|
|
|
ENTRY(spurious_interrupt_bug)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $0
|
|
|
|
pushl $do_spurious_interrupt_bug
|
|
|
|
jmp error_code
|
2007-02-13 20:26:24 +08:00
|
|
|
END(spurious_interrupt_bug)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
xen: Core Xen implementation
This patch is a rollup of all the core pieces of the Xen
implementation, including:
- booting and setup
- pagetable setup
- privileged instructions
- segmentation
- interrupt flags
- upcalls
- multicall batching
BOOTING AND SETUP
The vmlinux image is decorated with ELF notes which tell the Xen
domain builder what the kernel's requirements are; the domain builder
then constructs the address space accordingly and starts the kernel.
Xen has its own entrypoint for the kernel (contained in an ELF note).
The ELF notes are set up by xen-head.S, which is included into head.S.
In principle it could be linked separately, but it seems to provoke
lots of binutils bugs.
Because the domain builder starts the kernel in a fairly sane state
(32-bit protected mode, paging enabled, flat segments set up), there's
not a lot of setup needed before starting the kernel proper. The main
steps are:
1. Install the Xen paravirt_ops, which is simply a matter of a
structure assignment.
2. Set init_mm to use the Xen-supplied pagetables (analogous to the
head.S generated pagetables in a native boot).
3. Reserve address space for Xen, since it takes a chunk at the top
of the address space for its own use.
4. Call start_kernel()
PAGETABLE SETUP
Once we hit the main kernel boot sequence, it will end up calling back
via paravirt_ops to set up various pieces of Xen specific state. One
of the critical things which requires a bit of extra care is the
construction of the initial init_mm pagetable. Because Xen places
tight constraints on pagetables (an active pagetable must always be
valid, and must always be mapped read-only to the guest domain), we
need to be careful when constructing the new pagetable to keep these
constraints in mind. It turns out that the easiest way to do this is
use the initial Xen-provided pagetable as a template, and then just
insert new mappings for memory where a mapping doesn't already exist.
This means that during pagetable setup, it uses a special version of
xen_set_pte which ignores any attempt to remap a read-only page as
read-write (since Xen will map its own initial pagetable as RO), but
lets other changes to the ptes happen, so that things like NX are set
properly.
PRIVILEGED INSTRUCTIONS AND SEGMENTATION
When the kernel runs under Xen, it runs in ring 1 rather than ring 0.
This means that it is more privileged than user-mode in ring 3, but it
still can't run privileged instructions directly. Non-performance
critical instructions are dealt with by taking a privilege exception
and trapping into the hypervisor and emulating the instruction, but
more performance-critical instructions have their own specific
paravirt_ops. In many cases we can avoid having to do any hypercalls
for these instructions, or the Xen implementation is quite different
from the normal native version.
The privileged instructions fall into the broad classes of:
Segmentation: setting up the GDT and the GDT entries, LDT,
TLS and so on. Xen doesn't allow the GDT to be directly
modified; all GDT updates are done via hypercalls where the new
entries can be validated. This is important because Xen uses
segment limits to prevent the guest kernel from damaging the
hypervisor itself.
Traps and exceptions: Xen uses a special format for trap entrypoints,
so when the kernel wants to set an IDT entry, it needs to be
converted to the form Xen expects. Xen sets int 0x80 up specially
so that the trap goes straight from userspace into the guest kernel
without going via the hypervisor. sysenter isn't supported.
Kernel stack: The esp0 entry is extracted from the tss and provided to
Xen.
TLB operations: the various TLB calls are mapped into corresponding
Xen hypercalls.
Control registers: all the control registers are privileged. The most
important is cr3, which points to the base of the current pagetable,
and we handle it specially.
Another instruction we treat specially is CPUID, even though its not
privileged. We want to control what CPU features are visible to the
rest of the kernel, and so CPUID ends up going into a paravirt_op.
Xen implements this mainly to disable the ACPI and APIC subsystems.
INTERRUPT FLAGS
Xen maintains its own separate flag for masking events, which is
contained within the per-cpu vcpu_info structure. Because the guest
kernel runs in ring 1 and not 0, the IF flag in EFLAGS is completely
ignored (and must be, because even if a guest domain disables
interrupts for itself, it can't disable them overall).
(A note on terminology: "events" and interrupts are effectively
synonymous. However, rather than using an "enable flag", Xen uses a
"mask flag", which blocks event delivery when it is non-zero.)
There are paravirt_ops for each of cli/sti/save_fl/restore_fl, which
are implemented to manage the Xen event mask state. The only thing
worth noting is that when events are unmasked, we need to explicitly
see if there's a pending event and call into the hypervisor to make
sure it gets delivered.
UPCALLS
Xen needs a couple of upcall (or callback) functions to be implemented
by each guest. One is the event upcalls, which is how events
(interrupts, effectively) are delivered to the guests. The other is
the failsafe callback, which is used to report errors in either
reloading a segment register, or caused by iret. These are
implemented in i386/kernel/entry.S so they can jump into the normal
iret_exc path when necessary.
MULTICALL BATCHING
Xen provides a multicall mechanism, which allows multiple hypercalls
to be issued at once in order to mitigate the cost of trapping into
the hypervisor. This is particularly useful for context switches,
since the 4-5 hypercalls they would normally need (reload cr3, update
TLS, maybe update LDT) can be reduced to one. This patch implements a
generic batching mechanism for hypercalls, which gets used in many
places in the Xen code.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Cc: Ian Pratt <ian.pratt@xensource.com>
Cc: Christian Limpach <Christian.Limpach@cl.cam.ac.uk>
Cc: Adrian Bunk <bunk@stusta.de>
2007-07-18 09:37:04 +08:00
|
|
|
#ifdef CONFIG_XEN
|
2015-06-08 15:49:11 +08:00
|
|
|
/*
|
|
|
|
* Xen doesn't set %esp to be precisely what the normal SYSENTER
|
|
|
|
* entry point expects, so fix it up before using the normal path.
|
|
|
|
*/
|
2008-03-18 07:37:17 +08:00
|
|
|
ENTRY(xen_sysenter_target)
|
2015-06-08 15:49:11 +08:00
|
|
|
addl $5*4, %esp /* remove xen-provided frame */
|
|
|
|
jmp sysenter_past_esp
|
2008-03-18 07:37:17 +08:00
|
|
|
|
xen: Core Xen implementation
This patch is a rollup of all the core pieces of the Xen
implementation, including:
- booting and setup
- pagetable setup
- privileged instructions
- segmentation
- interrupt flags
- upcalls
- multicall batching
BOOTING AND SETUP
The vmlinux image is decorated with ELF notes which tell the Xen
domain builder what the kernel's requirements are; the domain builder
then constructs the address space accordingly and starts the kernel.
Xen has its own entrypoint for the kernel (contained in an ELF note).
The ELF notes are set up by xen-head.S, which is included into head.S.
In principle it could be linked separately, but it seems to provoke
lots of binutils bugs.
Because the domain builder starts the kernel in a fairly sane state
(32-bit protected mode, paging enabled, flat segments set up), there's
not a lot of setup needed before starting the kernel proper. The main
steps are:
1. Install the Xen paravirt_ops, which is simply a matter of a
structure assignment.
2. Set init_mm to use the Xen-supplied pagetables (analogous to the
head.S generated pagetables in a native boot).
3. Reserve address space for Xen, since it takes a chunk at the top
of the address space for its own use.
4. Call start_kernel()
PAGETABLE SETUP
Once we hit the main kernel boot sequence, it will end up calling back
via paravirt_ops to set up various pieces of Xen specific state. One
of the critical things which requires a bit of extra care is the
construction of the initial init_mm pagetable. Because Xen places
tight constraints on pagetables (an active pagetable must always be
valid, and must always be mapped read-only to the guest domain), we
need to be careful when constructing the new pagetable to keep these
constraints in mind. It turns out that the easiest way to do this is
use the initial Xen-provided pagetable as a template, and then just
insert new mappings for memory where a mapping doesn't already exist.
This means that during pagetable setup, it uses a special version of
xen_set_pte which ignores any attempt to remap a read-only page as
read-write (since Xen will map its own initial pagetable as RO), but
lets other changes to the ptes happen, so that things like NX are set
properly.
PRIVILEGED INSTRUCTIONS AND SEGMENTATION
When the kernel runs under Xen, it runs in ring 1 rather than ring 0.
This means that it is more privileged than user-mode in ring 3, but it
still can't run privileged instructions directly. Non-performance
critical instructions are dealt with by taking a privilege exception
and trapping into the hypervisor and emulating the instruction, but
more performance-critical instructions have their own specific
paravirt_ops. In many cases we can avoid having to do any hypercalls
for these instructions, or the Xen implementation is quite different
from the normal native version.
The privileged instructions fall into the broad classes of:
Segmentation: setting up the GDT and the GDT entries, LDT,
TLS and so on. Xen doesn't allow the GDT to be directly
modified; all GDT updates are done via hypercalls where the new
entries can be validated. This is important because Xen uses
segment limits to prevent the guest kernel from damaging the
hypervisor itself.
Traps and exceptions: Xen uses a special format for trap entrypoints,
so when the kernel wants to set an IDT entry, it needs to be
converted to the form Xen expects. Xen sets int 0x80 up specially
so that the trap goes straight from userspace into the guest kernel
without going via the hypervisor. sysenter isn't supported.
Kernel stack: The esp0 entry is extracted from the tss and provided to
Xen.
TLB operations: the various TLB calls are mapped into corresponding
Xen hypercalls.
Control registers: all the control registers are privileged. The most
important is cr3, which points to the base of the current pagetable,
and we handle it specially.
Another instruction we treat specially is CPUID, even though its not
privileged. We want to control what CPU features are visible to the
rest of the kernel, and so CPUID ends up going into a paravirt_op.
Xen implements this mainly to disable the ACPI and APIC subsystems.
INTERRUPT FLAGS
Xen maintains its own separate flag for masking events, which is
contained within the per-cpu vcpu_info structure. Because the guest
kernel runs in ring 1 and not 0, the IF flag in EFLAGS is completely
ignored (and must be, because even if a guest domain disables
interrupts for itself, it can't disable them overall).
(A note on terminology: "events" and interrupts are effectively
synonymous. However, rather than using an "enable flag", Xen uses a
"mask flag", which blocks event delivery when it is non-zero.)
There are paravirt_ops for each of cli/sti/save_fl/restore_fl, which
are implemented to manage the Xen event mask state. The only thing
worth noting is that when events are unmasked, we need to explicitly
see if there's a pending event and call into the hypervisor to make
sure it gets delivered.
UPCALLS
Xen needs a couple of upcall (or callback) functions to be implemented
by each guest. One is the event upcalls, which is how events
(interrupts, effectively) are delivered to the guests. The other is
the failsafe callback, which is used to report errors in either
reloading a segment register, or caused by iret. These are
implemented in i386/kernel/entry.S so they can jump into the normal
iret_exc path when necessary.
MULTICALL BATCHING
Xen provides a multicall mechanism, which allows multiple hypercalls
to be issued at once in order to mitigate the cost of trapping into
the hypervisor. This is particularly useful for context switches,
since the 4-5 hypercalls they would normally need (reload cr3, update
TLS, maybe update LDT) can be reduced to one. This patch implements a
generic batching mechanism for hypercalls, which gets used in many
places in the Xen code.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Cc: Ian Pratt <ian.pratt@xensource.com>
Cc: Christian Limpach <Christian.Limpach@cl.cam.ac.uk>
Cc: Adrian Bunk <bunk@stusta.de>
2007-07-18 09:37:04 +08:00
|
|
|
ENTRY(xen_hypervisor_callback)
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $-1 /* orig_ax = -1 => not a system call */
|
xen: Core Xen implementation
This patch is a rollup of all the core pieces of the Xen
implementation, including:
- booting and setup
- pagetable setup
- privileged instructions
- segmentation
- interrupt flags
- upcalls
- multicall batching
BOOTING AND SETUP
The vmlinux image is decorated with ELF notes which tell the Xen
domain builder what the kernel's requirements are; the domain builder
then constructs the address space accordingly and starts the kernel.
Xen has its own entrypoint for the kernel (contained in an ELF note).
The ELF notes are set up by xen-head.S, which is included into head.S.
In principle it could be linked separately, but it seems to provoke
lots of binutils bugs.
Because the domain builder starts the kernel in a fairly sane state
(32-bit protected mode, paging enabled, flat segments set up), there's
not a lot of setup needed before starting the kernel proper. The main
steps are:
1. Install the Xen paravirt_ops, which is simply a matter of a
structure assignment.
2. Set init_mm to use the Xen-supplied pagetables (analogous to the
head.S generated pagetables in a native boot).
3. Reserve address space for Xen, since it takes a chunk at the top
of the address space for its own use.
4. Call start_kernel()
PAGETABLE SETUP
Once we hit the main kernel boot sequence, it will end up calling back
via paravirt_ops to set up various pieces of Xen specific state. One
of the critical things which requires a bit of extra care is the
construction of the initial init_mm pagetable. Because Xen places
tight constraints on pagetables (an active pagetable must always be
valid, and must always be mapped read-only to the guest domain), we
need to be careful when constructing the new pagetable to keep these
constraints in mind. It turns out that the easiest way to do this is
use the initial Xen-provided pagetable as a template, and then just
insert new mappings for memory where a mapping doesn't already exist.
This means that during pagetable setup, it uses a special version of
xen_set_pte which ignores any attempt to remap a read-only page as
read-write (since Xen will map its own initial pagetable as RO), but
lets other changes to the ptes happen, so that things like NX are set
properly.
PRIVILEGED INSTRUCTIONS AND SEGMENTATION
When the kernel runs under Xen, it runs in ring 1 rather than ring 0.
This means that it is more privileged than user-mode in ring 3, but it
still can't run privileged instructions directly. Non-performance
critical instructions are dealt with by taking a privilege exception
and trapping into the hypervisor and emulating the instruction, but
more performance-critical instructions have their own specific
paravirt_ops. In many cases we can avoid having to do any hypercalls
for these instructions, or the Xen implementation is quite different
from the normal native version.
The privileged instructions fall into the broad classes of:
Segmentation: setting up the GDT and the GDT entries, LDT,
TLS and so on. Xen doesn't allow the GDT to be directly
modified; all GDT updates are done via hypercalls where the new
entries can be validated. This is important because Xen uses
segment limits to prevent the guest kernel from damaging the
hypervisor itself.
Traps and exceptions: Xen uses a special format for trap entrypoints,
so when the kernel wants to set an IDT entry, it needs to be
converted to the form Xen expects. Xen sets int 0x80 up specially
so that the trap goes straight from userspace into the guest kernel
without going via the hypervisor. sysenter isn't supported.
Kernel stack: The esp0 entry is extracted from the tss and provided to
Xen.
TLB operations: the various TLB calls are mapped into corresponding
Xen hypercalls.
Control registers: all the control registers are privileged. The most
important is cr3, which points to the base of the current pagetable,
and we handle it specially.
Another instruction we treat specially is CPUID, even though its not
privileged. We want to control what CPU features are visible to the
rest of the kernel, and so CPUID ends up going into a paravirt_op.
Xen implements this mainly to disable the ACPI and APIC subsystems.
INTERRUPT FLAGS
Xen maintains its own separate flag for masking events, which is
contained within the per-cpu vcpu_info structure. Because the guest
kernel runs in ring 1 and not 0, the IF flag in EFLAGS is completely
ignored (and must be, because even if a guest domain disables
interrupts for itself, it can't disable them overall).
(A note on terminology: "events" and interrupts are effectively
synonymous. However, rather than using an "enable flag", Xen uses a
"mask flag", which blocks event delivery when it is non-zero.)
There are paravirt_ops for each of cli/sti/save_fl/restore_fl, which
are implemented to manage the Xen event mask state. The only thing
worth noting is that when events are unmasked, we need to explicitly
see if there's a pending event and call into the hypervisor to make
sure it gets delivered.
UPCALLS
Xen needs a couple of upcall (or callback) functions to be implemented
by each guest. One is the event upcalls, which is how events
(interrupts, effectively) are delivered to the guests. The other is
the failsafe callback, which is used to report errors in either
reloading a segment register, or caused by iret. These are
implemented in i386/kernel/entry.S so they can jump into the normal
iret_exc path when necessary.
MULTICALL BATCHING
Xen provides a multicall mechanism, which allows multiple hypercalls
to be issued at once in order to mitigate the cost of trapping into
the hypervisor. This is particularly useful for context switches,
since the 4-5 hypercalls they would normally need (reload cr3, update
TLS, maybe update LDT) can be reduced to one. This patch implements a
generic batching mechanism for hypercalls, which gets used in many
places in the Xen code.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Cc: Ian Pratt <ian.pratt@xensource.com>
Cc: Christian Limpach <Christian.Limpach@cl.cam.ac.uk>
Cc: Adrian Bunk <bunk@stusta.de>
2007-07-18 09:37:04 +08:00
|
|
|
SAVE_ALL
|
|
|
|
TRACE_IRQS_OFF
|
xen: use iret directly when possible
Most of the time we can simply use the iret instruction to exit the
kernel, rather than having to use the iret hypercall - the only
exception is if we're returning into vm86 mode, or from delivering an
NMI (which we don't support yet).
When running native, iret has the behaviour of testing for a pending
interrupt atomically with re-enabling interrupts. Unfortunately
there's no way to do this with Xen, so there's a window in which we
could get a recursive exception after enabling events but before
actually returning to userspace.
This causes a problem: if the nested interrupt causes one of the
task's TIF_WORK_MASK flags to be set, they will not be checked again
before returning to userspace. This means that pending work may be
left pending indefinitely, until the process enters and leaves the
kernel again. The net effect is that a pending signal or reschedule
event could be delayed for an unbounded amount of time.
To deal with this, the xen event upcall handler checks to see if the
EIP is within the critical section of the iret code, after events
are (potentially) enabled up to the iret itself. If its within this
range, it calls the iret critical section fixup, which adjusts the
stack to deal with any unrestored registers, and then shifts the
stack frame up to replace the previous invocation.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
2007-07-18 09:37:07 +08:00
|
|
|
|
2015-06-08 15:49:11 +08:00
|
|
|
/*
|
|
|
|
* Check to see if we got the event in the critical
|
|
|
|
* region in xen_iret_direct, after we've reenabled
|
|
|
|
* events and checked for pending events. This simulates
|
|
|
|
* iret instruction's behaviour where it delivers a
|
|
|
|
* pending interrupt when enabling interrupts:
|
|
|
|
*/
|
|
|
|
movl PT_EIP(%esp), %eax
|
|
|
|
cmpl $xen_iret_start_crit, %eax
|
|
|
|
jb 1f
|
|
|
|
cmpl $xen_iret_end_crit, %eax
|
|
|
|
jae 1f
|
xen: use iret directly when possible
Most of the time we can simply use the iret instruction to exit the
kernel, rather than having to use the iret hypercall - the only
exception is if we're returning into vm86 mode, or from delivering an
NMI (which we don't support yet).
When running native, iret has the behaviour of testing for a pending
interrupt atomically with re-enabling interrupts. Unfortunately
there's no way to do this with Xen, so there's a window in which we
could get a recursive exception after enabling events but before
actually returning to userspace.
This causes a problem: if the nested interrupt causes one of the
task's TIF_WORK_MASK flags to be set, they will not be checked again
before returning to userspace. This means that pending work may be
left pending indefinitely, until the process enters and leaves the
kernel again. The net effect is that a pending signal or reschedule
event could be delayed for an unbounded amount of time.
To deal with this, the xen event upcall handler checks to see if the
EIP is within the critical section of the iret code, after events
are (potentially) enabled up to the iret itself. If its within this
range, it calls the iret critical section fixup, which adjusts the
stack to deal with any unrestored registers, and then shifts the
stack frame up to replace the previous invocation.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
2007-07-18 09:37:07 +08:00
|
|
|
|
2015-06-08 15:49:11 +08:00
|
|
|
jmp xen_iret_crit_fixup
|
2008-03-18 07:37:17 +08:00
|
|
|
|
|
|
|
ENTRY(xen_do_upcall)
|
2015-06-08 15:49:11 +08:00
|
|
|
1: mov %esp, %eax
|
|
|
|
call xen_evtchn_do_upcall
|
2015-02-19 23:23:17 +08:00
|
|
|
#ifndef CONFIG_PREEMPT
|
2015-06-08 15:49:11 +08:00
|
|
|
call xen_maybe_preempt_hcall
|
2015-02-19 23:23:17 +08:00
|
|
|
#endif
|
2015-06-08 15:49:11 +08:00
|
|
|
jmp ret_from_intr
|
xen: Core Xen implementation
This patch is a rollup of all the core pieces of the Xen
implementation, including:
- booting and setup
- pagetable setup
- privileged instructions
- segmentation
- interrupt flags
- upcalls
- multicall batching
BOOTING AND SETUP
The vmlinux image is decorated with ELF notes which tell the Xen
domain builder what the kernel's requirements are; the domain builder
then constructs the address space accordingly and starts the kernel.
Xen has its own entrypoint for the kernel (contained in an ELF note).
The ELF notes are set up by xen-head.S, which is included into head.S.
In principle it could be linked separately, but it seems to provoke
lots of binutils bugs.
Because the domain builder starts the kernel in a fairly sane state
(32-bit protected mode, paging enabled, flat segments set up), there's
not a lot of setup needed before starting the kernel proper. The main
steps are:
1. Install the Xen paravirt_ops, which is simply a matter of a
structure assignment.
2. Set init_mm to use the Xen-supplied pagetables (analogous to the
head.S generated pagetables in a native boot).
3. Reserve address space for Xen, since it takes a chunk at the top
of the address space for its own use.
4. Call start_kernel()
PAGETABLE SETUP
Once we hit the main kernel boot sequence, it will end up calling back
via paravirt_ops to set up various pieces of Xen specific state. One
of the critical things which requires a bit of extra care is the
construction of the initial init_mm pagetable. Because Xen places
tight constraints on pagetables (an active pagetable must always be
valid, and must always be mapped read-only to the guest domain), we
need to be careful when constructing the new pagetable to keep these
constraints in mind. It turns out that the easiest way to do this is
use the initial Xen-provided pagetable as a template, and then just
insert new mappings for memory where a mapping doesn't already exist.
This means that during pagetable setup, it uses a special version of
xen_set_pte which ignores any attempt to remap a read-only page as
read-write (since Xen will map its own initial pagetable as RO), but
lets other changes to the ptes happen, so that things like NX are set
properly.
PRIVILEGED INSTRUCTIONS AND SEGMENTATION
When the kernel runs under Xen, it runs in ring 1 rather than ring 0.
This means that it is more privileged than user-mode in ring 3, but it
still can't run privileged instructions directly. Non-performance
critical instructions are dealt with by taking a privilege exception
and trapping into the hypervisor and emulating the instruction, but
more performance-critical instructions have their own specific
paravirt_ops. In many cases we can avoid having to do any hypercalls
for these instructions, or the Xen implementation is quite different
from the normal native version.
The privileged instructions fall into the broad classes of:
Segmentation: setting up the GDT and the GDT entries, LDT,
TLS and so on. Xen doesn't allow the GDT to be directly
modified; all GDT updates are done via hypercalls where the new
entries can be validated. This is important because Xen uses
segment limits to prevent the guest kernel from damaging the
hypervisor itself.
Traps and exceptions: Xen uses a special format for trap entrypoints,
so when the kernel wants to set an IDT entry, it needs to be
converted to the form Xen expects. Xen sets int 0x80 up specially
so that the trap goes straight from userspace into the guest kernel
without going via the hypervisor. sysenter isn't supported.
Kernel stack: The esp0 entry is extracted from the tss and provided to
Xen.
TLB operations: the various TLB calls are mapped into corresponding
Xen hypercalls.
Control registers: all the control registers are privileged. The most
important is cr3, which points to the base of the current pagetable,
and we handle it specially.
Another instruction we treat specially is CPUID, even though its not
privileged. We want to control what CPU features are visible to the
rest of the kernel, and so CPUID ends up going into a paravirt_op.
Xen implements this mainly to disable the ACPI and APIC subsystems.
INTERRUPT FLAGS
Xen maintains its own separate flag for masking events, which is
contained within the per-cpu vcpu_info structure. Because the guest
kernel runs in ring 1 and not 0, the IF flag in EFLAGS is completely
ignored (and must be, because even if a guest domain disables
interrupts for itself, it can't disable them overall).
(A note on terminology: "events" and interrupts are effectively
synonymous. However, rather than using an "enable flag", Xen uses a
"mask flag", which blocks event delivery when it is non-zero.)
There are paravirt_ops for each of cli/sti/save_fl/restore_fl, which
are implemented to manage the Xen event mask state. The only thing
worth noting is that when events are unmasked, we need to explicitly
see if there's a pending event and call into the hypervisor to make
sure it gets delivered.
UPCALLS
Xen needs a couple of upcall (or callback) functions to be implemented
by each guest. One is the event upcalls, which is how events
(interrupts, effectively) are delivered to the guests. The other is
the failsafe callback, which is used to report errors in either
reloading a segment register, or caused by iret. These are
implemented in i386/kernel/entry.S so they can jump into the normal
iret_exc path when necessary.
MULTICALL BATCHING
Xen provides a multicall mechanism, which allows multiple hypercalls
to be issued at once in order to mitigate the cost of trapping into
the hypervisor. This is particularly useful for context switches,
since the 4-5 hypercalls they would normally need (reload cr3, update
TLS, maybe update LDT) can be reduced to one. This patch implements a
generic batching mechanism for hypercalls, which gets used in many
places in the Xen code.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Cc: Ian Pratt <ian.pratt@xensource.com>
Cc: Christian Limpach <Christian.Limpach@cl.cam.ac.uk>
Cc: Adrian Bunk <bunk@stusta.de>
2007-07-18 09:37:04 +08:00
|
|
|
ENDPROC(xen_hypervisor_callback)
|
|
|
|
|
2015-06-08 15:49:11 +08:00
|
|
|
/*
|
|
|
|
* Hypervisor uses this for application faults while it executes.
|
|
|
|
* We get here for two reasons:
|
|
|
|
* 1. Fault while reloading DS, ES, FS or GS
|
|
|
|
* 2. Fault while executing IRET
|
|
|
|
* Category 1 we fix up by reattempting the load, and zeroing the segment
|
|
|
|
* register if the load fails.
|
|
|
|
* Category 2 we fix up by jumping to do_iret_error. We cannot use the
|
|
|
|
* normal Linux return path in this case because if we use the IRET hypercall
|
|
|
|
* to pop the stack frame we end up in an infinite loop of failsafe callbacks.
|
|
|
|
* We distinguish between categories by maintaining a status value in EAX.
|
|
|
|
*/
|
xen: Core Xen implementation
This patch is a rollup of all the core pieces of the Xen
implementation, including:
- booting and setup
- pagetable setup
- privileged instructions
- segmentation
- interrupt flags
- upcalls
- multicall batching
BOOTING AND SETUP
The vmlinux image is decorated with ELF notes which tell the Xen
domain builder what the kernel's requirements are; the domain builder
then constructs the address space accordingly and starts the kernel.
Xen has its own entrypoint for the kernel (contained in an ELF note).
The ELF notes are set up by xen-head.S, which is included into head.S.
In principle it could be linked separately, but it seems to provoke
lots of binutils bugs.
Because the domain builder starts the kernel in a fairly sane state
(32-bit protected mode, paging enabled, flat segments set up), there's
not a lot of setup needed before starting the kernel proper. The main
steps are:
1. Install the Xen paravirt_ops, which is simply a matter of a
structure assignment.
2. Set init_mm to use the Xen-supplied pagetables (analogous to the
head.S generated pagetables in a native boot).
3. Reserve address space for Xen, since it takes a chunk at the top
of the address space for its own use.
4. Call start_kernel()
PAGETABLE SETUP
Once we hit the main kernel boot sequence, it will end up calling back
via paravirt_ops to set up various pieces of Xen specific state. One
of the critical things which requires a bit of extra care is the
construction of the initial init_mm pagetable. Because Xen places
tight constraints on pagetables (an active pagetable must always be
valid, and must always be mapped read-only to the guest domain), we
need to be careful when constructing the new pagetable to keep these
constraints in mind. It turns out that the easiest way to do this is
use the initial Xen-provided pagetable as a template, and then just
insert new mappings for memory where a mapping doesn't already exist.
This means that during pagetable setup, it uses a special version of
xen_set_pte which ignores any attempt to remap a read-only page as
read-write (since Xen will map its own initial pagetable as RO), but
lets other changes to the ptes happen, so that things like NX are set
properly.
PRIVILEGED INSTRUCTIONS AND SEGMENTATION
When the kernel runs under Xen, it runs in ring 1 rather than ring 0.
This means that it is more privileged than user-mode in ring 3, but it
still can't run privileged instructions directly. Non-performance
critical instructions are dealt with by taking a privilege exception
and trapping into the hypervisor and emulating the instruction, but
more performance-critical instructions have their own specific
paravirt_ops. In many cases we can avoid having to do any hypercalls
for these instructions, or the Xen implementation is quite different
from the normal native version.
The privileged instructions fall into the broad classes of:
Segmentation: setting up the GDT and the GDT entries, LDT,
TLS and so on. Xen doesn't allow the GDT to be directly
modified; all GDT updates are done via hypercalls where the new
entries can be validated. This is important because Xen uses
segment limits to prevent the guest kernel from damaging the
hypervisor itself.
Traps and exceptions: Xen uses a special format for trap entrypoints,
so when the kernel wants to set an IDT entry, it needs to be
converted to the form Xen expects. Xen sets int 0x80 up specially
so that the trap goes straight from userspace into the guest kernel
without going via the hypervisor. sysenter isn't supported.
Kernel stack: The esp0 entry is extracted from the tss and provided to
Xen.
TLB operations: the various TLB calls are mapped into corresponding
Xen hypercalls.
Control registers: all the control registers are privileged. The most
important is cr3, which points to the base of the current pagetable,
and we handle it specially.
Another instruction we treat specially is CPUID, even though its not
privileged. We want to control what CPU features are visible to the
rest of the kernel, and so CPUID ends up going into a paravirt_op.
Xen implements this mainly to disable the ACPI and APIC subsystems.
INTERRUPT FLAGS
Xen maintains its own separate flag for masking events, which is
contained within the per-cpu vcpu_info structure. Because the guest
kernel runs in ring 1 and not 0, the IF flag in EFLAGS is completely
ignored (and must be, because even if a guest domain disables
interrupts for itself, it can't disable them overall).
(A note on terminology: "events" and interrupts are effectively
synonymous. However, rather than using an "enable flag", Xen uses a
"mask flag", which blocks event delivery when it is non-zero.)
There are paravirt_ops for each of cli/sti/save_fl/restore_fl, which
are implemented to manage the Xen event mask state. The only thing
worth noting is that when events are unmasked, we need to explicitly
see if there's a pending event and call into the hypervisor to make
sure it gets delivered.
UPCALLS
Xen needs a couple of upcall (or callback) functions to be implemented
by each guest. One is the event upcalls, which is how events
(interrupts, effectively) are delivered to the guests. The other is
the failsafe callback, which is used to report errors in either
reloading a segment register, or caused by iret. These are
implemented in i386/kernel/entry.S so they can jump into the normal
iret_exc path when necessary.
MULTICALL BATCHING
Xen provides a multicall mechanism, which allows multiple hypercalls
to be issued at once in order to mitigate the cost of trapping into
the hypervisor. This is particularly useful for context switches,
since the 4-5 hypercalls they would normally need (reload cr3, update
TLS, maybe update LDT) can be reduced to one. This patch implements a
generic batching mechanism for hypercalls, which gets used in many
places in the Xen code.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Cc: Ian Pratt <ian.pratt@xensource.com>
Cc: Christian Limpach <Christian.Limpach@cl.cam.ac.uk>
Cc: Adrian Bunk <bunk@stusta.de>
2007-07-18 09:37:04 +08:00
|
|
|
ENTRY(xen_failsafe_callback)
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl %eax
|
|
|
|
movl $1, %eax
|
|
|
|
1: mov 4(%esp), %ds
|
|
|
|
2: mov 8(%esp), %es
|
|
|
|
3: mov 12(%esp), %fs
|
|
|
|
4: mov 16(%esp), %gs
|
2012-10-20 00:29:07 +08:00
|
|
|
/* EAX == 0 => Category 1 (Bad segment)
|
|
|
|
EAX != 0 => Category 2 (Bad IRET) */
|
2015-06-08 15:49:11 +08:00
|
|
|
testl %eax, %eax
|
|
|
|
popl %eax
|
|
|
|
lea 16(%esp), %esp
|
|
|
|
jz 5f
|
|
|
|
jmp iret_exc
|
|
|
|
5: pushl $-1 /* orig_ax = -1 => not a system call */
|
xen: Core Xen implementation
This patch is a rollup of all the core pieces of the Xen
implementation, including:
- booting and setup
- pagetable setup
- privileged instructions
- segmentation
- interrupt flags
- upcalls
- multicall batching
BOOTING AND SETUP
The vmlinux image is decorated with ELF notes which tell the Xen
domain builder what the kernel's requirements are; the domain builder
then constructs the address space accordingly and starts the kernel.
Xen has its own entrypoint for the kernel (contained in an ELF note).
The ELF notes are set up by xen-head.S, which is included into head.S.
In principle it could be linked separately, but it seems to provoke
lots of binutils bugs.
Because the domain builder starts the kernel in a fairly sane state
(32-bit protected mode, paging enabled, flat segments set up), there's
not a lot of setup needed before starting the kernel proper. The main
steps are:
1. Install the Xen paravirt_ops, which is simply a matter of a
structure assignment.
2. Set init_mm to use the Xen-supplied pagetables (analogous to the
head.S generated pagetables in a native boot).
3. Reserve address space for Xen, since it takes a chunk at the top
of the address space for its own use.
4. Call start_kernel()
PAGETABLE SETUP
Once we hit the main kernel boot sequence, it will end up calling back
via paravirt_ops to set up various pieces of Xen specific state. One
of the critical things which requires a bit of extra care is the
construction of the initial init_mm pagetable. Because Xen places
tight constraints on pagetables (an active pagetable must always be
valid, and must always be mapped read-only to the guest domain), we
need to be careful when constructing the new pagetable to keep these
constraints in mind. It turns out that the easiest way to do this is
use the initial Xen-provided pagetable as a template, and then just
insert new mappings for memory where a mapping doesn't already exist.
This means that during pagetable setup, it uses a special version of
xen_set_pte which ignores any attempt to remap a read-only page as
read-write (since Xen will map its own initial pagetable as RO), but
lets other changes to the ptes happen, so that things like NX are set
properly.
PRIVILEGED INSTRUCTIONS AND SEGMENTATION
When the kernel runs under Xen, it runs in ring 1 rather than ring 0.
This means that it is more privileged than user-mode in ring 3, but it
still can't run privileged instructions directly. Non-performance
critical instructions are dealt with by taking a privilege exception
and trapping into the hypervisor and emulating the instruction, but
more performance-critical instructions have their own specific
paravirt_ops. In many cases we can avoid having to do any hypercalls
for these instructions, or the Xen implementation is quite different
from the normal native version.
The privileged instructions fall into the broad classes of:
Segmentation: setting up the GDT and the GDT entries, LDT,
TLS and so on. Xen doesn't allow the GDT to be directly
modified; all GDT updates are done via hypercalls where the new
entries can be validated. This is important because Xen uses
segment limits to prevent the guest kernel from damaging the
hypervisor itself.
Traps and exceptions: Xen uses a special format for trap entrypoints,
so when the kernel wants to set an IDT entry, it needs to be
converted to the form Xen expects. Xen sets int 0x80 up specially
so that the trap goes straight from userspace into the guest kernel
without going via the hypervisor. sysenter isn't supported.
Kernel stack: The esp0 entry is extracted from the tss and provided to
Xen.
TLB operations: the various TLB calls are mapped into corresponding
Xen hypercalls.
Control registers: all the control registers are privileged. The most
important is cr3, which points to the base of the current pagetable,
and we handle it specially.
Another instruction we treat specially is CPUID, even though its not
privileged. We want to control what CPU features are visible to the
rest of the kernel, and so CPUID ends up going into a paravirt_op.
Xen implements this mainly to disable the ACPI and APIC subsystems.
INTERRUPT FLAGS
Xen maintains its own separate flag for masking events, which is
contained within the per-cpu vcpu_info structure. Because the guest
kernel runs in ring 1 and not 0, the IF flag in EFLAGS is completely
ignored (and must be, because even if a guest domain disables
interrupts for itself, it can't disable them overall).
(A note on terminology: "events" and interrupts are effectively
synonymous. However, rather than using an "enable flag", Xen uses a
"mask flag", which blocks event delivery when it is non-zero.)
There are paravirt_ops for each of cli/sti/save_fl/restore_fl, which
are implemented to manage the Xen event mask state. The only thing
worth noting is that when events are unmasked, we need to explicitly
see if there's a pending event and call into the hypervisor to make
sure it gets delivered.
UPCALLS
Xen needs a couple of upcall (or callback) functions to be implemented
by each guest. One is the event upcalls, which is how events
(interrupts, effectively) are delivered to the guests. The other is
the failsafe callback, which is used to report errors in either
reloading a segment register, or caused by iret. These are
implemented in i386/kernel/entry.S so they can jump into the normal
iret_exc path when necessary.
MULTICALL BATCHING
Xen provides a multicall mechanism, which allows multiple hypercalls
to be issued at once in order to mitigate the cost of trapping into
the hypervisor. This is particularly useful for context switches,
since the 4-5 hypercalls they would normally need (reload cr3, update
TLS, maybe update LDT) can be reduced to one. This patch implements a
generic batching mechanism for hypercalls, which gets used in many
places in the Xen code.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Cc: Ian Pratt <ian.pratt@xensource.com>
Cc: Christian Limpach <Christian.Limpach@cl.cam.ac.uk>
Cc: Adrian Bunk <bunk@stusta.de>
2007-07-18 09:37:04 +08:00
|
|
|
SAVE_ALL
|
2015-06-08 15:49:11 +08:00
|
|
|
jmp ret_from_exception
|
|
|
|
|
|
|
|
.section .fixup, "ax"
|
|
|
|
6: xorl %eax, %eax
|
|
|
|
movl %eax, 4(%esp)
|
|
|
|
jmp 1b
|
|
|
|
7: xorl %eax, %eax
|
|
|
|
movl %eax, 8(%esp)
|
|
|
|
jmp 2b
|
|
|
|
8: xorl %eax, %eax
|
|
|
|
movl %eax, 12(%esp)
|
|
|
|
jmp 3b
|
|
|
|
9: xorl %eax, %eax
|
|
|
|
movl %eax, 16(%esp)
|
|
|
|
jmp 4b
|
xen: Core Xen implementation
This patch is a rollup of all the core pieces of the Xen
implementation, including:
- booting and setup
- pagetable setup
- privileged instructions
- segmentation
- interrupt flags
- upcalls
- multicall batching
BOOTING AND SETUP
The vmlinux image is decorated with ELF notes which tell the Xen
domain builder what the kernel's requirements are; the domain builder
then constructs the address space accordingly and starts the kernel.
Xen has its own entrypoint for the kernel (contained in an ELF note).
The ELF notes are set up by xen-head.S, which is included into head.S.
In principle it could be linked separately, but it seems to provoke
lots of binutils bugs.
Because the domain builder starts the kernel in a fairly sane state
(32-bit protected mode, paging enabled, flat segments set up), there's
not a lot of setup needed before starting the kernel proper. The main
steps are:
1. Install the Xen paravirt_ops, which is simply a matter of a
structure assignment.
2. Set init_mm to use the Xen-supplied pagetables (analogous to the
head.S generated pagetables in a native boot).
3. Reserve address space for Xen, since it takes a chunk at the top
of the address space for its own use.
4. Call start_kernel()
PAGETABLE SETUP
Once we hit the main kernel boot sequence, it will end up calling back
via paravirt_ops to set up various pieces of Xen specific state. One
of the critical things which requires a bit of extra care is the
construction of the initial init_mm pagetable. Because Xen places
tight constraints on pagetables (an active pagetable must always be
valid, and must always be mapped read-only to the guest domain), we
need to be careful when constructing the new pagetable to keep these
constraints in mind. It turns out that the easiest way to do this is
use the initial Xen-provided pagetable as a template, and then just
insert new mappings for memory where a mapping doesn't already exist.
This means that during pagetable setup, it uses a special version of
xen_set_pte which ignores any attempt to remap a read-only page as
read-write (since Xen will map its own initial pagetable as RO), but
lets other changes to the ptes happen, so that things like NX are set
properly.
PRIVILEGED INSTRUCTIONS AND SEGMENTATION
When the kernel runs under Xen, it runs in ring 1 rather than ring 0.
This means that it is more privileged than user-mode in ring 3, but it
still can't run privileged instructions directly. Non-performance
critical instructions are dealt with by taking a privilege exception
and trapping into the hypervisor and emulating the instruction, but
more performance-critical instructions have their own specific
paravirt_ops. In many cases we can avoid having to do any hypercalls
for these instructions, or the Xen implementation is quite different
from the normal native version.
The privileged instructions fall into the broad classes of:
Segmentation: setting up the GDT and the GDT entries, LDT,
TLS and so on. Xen doesn't allow the GDT to be directly
modified; all GDT updates are done via hypercalls where the new
entries can be validated. This is important because Xen uses
segment limits to prevent the guest kernel from damaging the
hypervisor itself.
Traps and exceptions: Xen uses a special format for trap entrypoints,
so when the kernel wants to set an IDT entry, it needs to be
converted to the form Xen expects. Xen sets int 0x80 up specially
so that the trap goes straight from userspace into the guest kernel
without going via the hypervisor. sysenter isn't supported.
Kernel stack: The esp0 entry is extracted from the tss and provided to
Xen.
TLB operations: the various TLB calls are mapped into corresponding
Xen hypercalls.
Control registers: all the control registers are privileged. The most
important is cr3, which points to the base of the current pagetable,
and we handle it specially.
Another instruction we treat specially is CPUID, even though its not
privileged. We want to control what CPU features are visible to the
rest of the kernel, and so CPUID ends up going into a paravirt_op.
Xen implements this mainly to disable the ACPI and APIC subsystems.
INTERRUPT FLAGS
Xen maintains its own separate flag for masking events, which is
contained within the per-cpu vcpu_info structure. Because the guest
kernel runs in ring 1 and not 0, the IF flag in EFLAGS is completely
ignored (and must be, because even if a guest domain disables
interrupts for itself, it can't disable them overall).
(A note on terminology: "events" and interrupts are effectively
synonymous. However, rather than using an "enable flag", Xen uses a
"mask flag", which blocks event delivery when it is non-zero.)
There are paravirt_ops for each of cli/sti/save_fl/restore_fl, which
are implemented to manage the Xen event mask state. The only thing
worth noting is that when events are unmasked, we need to explicitly
see if there's a pending event and call into the hypervisor to make
sure it gets delivered.
UPCALLS
Xen needs a couple of upcall (or callback) functions to be implemented
by each guest. One is the event upcalls, which is how events
(interrupts, effectively) are delivered to the guests. The other is
the failsafe callback, which is used to report errors in either
reloading a segment register, or caused by iret. These are
implemented in i386/kernel/entry.S so they can jump into the normal
iret_exc path when necessary.
MULTICALL BATCHING
Xen provides a multicall mechanism, which allows multiple hypercalls
to be issued at once in order to mitigate the cost of trapping into
the hypervisor. This is particularly useful for context switches,
since the 4-5 hypercalls they would normally need (reload cr3, update
TLS, maybe update LDT) can be reduced to one. This patch implements a
generic batching mechanism for hypercalls, which gets used in many
places in the Xen code.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Cc: Ian Pratt <ian.pratt@xensource.com>
Cc: Christian Limpach <Christian.Limpach@cl.cam.ac.uk>
Cc: Adrian Bunk <bunk@stusta.de>
2007-07-18 09:37:04 +08:00
|
|
|
.previous
|
2015-06-08 15:49:11 +08:00
|
|
|
_ASM_EXTABLE(1b, 6b)
|
|
|
|
_ASM_EXTABLE(2b, 7b)
|
|
|
|
_ASM_EXTABLE(3b, 8b)
|
|
|
|
_ASM_EXTABLE(4b, 9b)
|
xen: Core Xen implementation
This patch is a rollup of all the core pieces of the Xen
implementation, including:
- booting and setup
- pagetable setup
- privileged instructions
- segmentation
- interrupt flags
- upcalls
- multicall batching
BOOTING AND SETUP
The vmlinux image is decorated with ELF notes which tell the Xen
domain builder what the kernel's requirements are; the domain builder
then constructs the address space accordingly and starts the kernel.
Xen has its own entrypoint for the kernel (contained in an ELF note).
The ELF notes are set up by xen-head.S, which is included into head.S.
In principle it could be linked separately, but it seems to provoke
lots of binutils bugs.
Because the domain builder starts the kernel in a fairly sane state
(32-bit protected mode, paging enabled, flat segments set up), there's
not a lot of setup needed before starting the kernel proper. The main
steps are:
1. Install the Xen paravirt_ops, which is simply a matter of a
structure assignment.
2. Set init_mm to use the Xen-supplied pagetables (analogous to the
head.S generated pagetables in a native boot).
3. Reserve address space for Xen, since it takes a chunk at the top
of the address space for its own use.
4. Call start_kernel()
PAGETABLE SETUP
Once we hit the main kernel boot sequence, it will end up calling back
via paravirt_ops to set up various pieces of Xen specific state. One
of the critical things which requires a bit of extra care is the
construction of the initial init_mm pagetable. Because Xen places
tight constraints on pagetables (an active pagetable must always be
valid, and must always be mapped read-only to the guest domain), we
need to be careful when constructing the new pagetable to keep these
constraints in mind. It turns out that the easiest way to do this is
use the initial Xen-provided pagetable as a template, and then just
insert new mappings for memory where a mapping doesn't already exist.
This means that during pagetable setup, it uses a special version of
xen_set_pte which ignores any attempt to remap a read-only page as
read-write (since Xen will map its own initial pagetable as RO), but
lets other changes to the ptes happen, so that things like NX are set
properly.
PRIVILEGED INSTRUCTIONS AND SEGMENTATION
When the kernel runs under Xen, it runs in ring 1 rather than ring 0.
This means that it is more privileged than user-mode in ring 3, but it
still can't run privileged instructions directly. Non-performance
critical instructions are dealt with by taking a privilege exception
and trapping into the hypervisor and emulating the instruction, but
more performance-critical instructions have their own specific
paravirt_ops. In many cases we can avoid having to do any hypercalls
for these instructions, or the Xen implementation is quite different
from the normal native version.
The privileged instructions fall into the broad classes of:
Segmentation: setting up the GDT and the GDT entries, LDT,
TLS and so on. Xen doesn't allow the GDT to be directly
modified; all GDT updates are done via hypercalls where the new
entries can be validated. This is important because Xen uses
segment limits to prevent the guest kernel from damaging the
hypervisor itself.
Traps and exceptions: Xen uses a special format for trap entrypoints,
so when the kernel wants to set an IDT entry, it needs to be
converted to the form Xen expects. Xen sets int 0x80 up specially
so that the trap goes straight from userspace into the guest kernel
without going via the hypervisor. sysenter isn't supported.
Kernel stack: The esp0 entry is extracted from the tss and provided to
Xen.
TLB operations: the various TLB calls are mapped into corresponding
Xen hypercalls.
Control registers: all the control registers are privileged. The most
important is cr3, which points to the base of the current pagetable,
and we handle it specially.
Another instruction we treat specially is CPUID, even though its not
privileged. We want to control what CPU features are visible to the
rest of the kernel, and so CPUID ends up going into a paravirt_op.
Xen implements this mainly to disable the ACPI and APIC subsystems.
INTERRUPT FLAGS
Xen maintains its own separate flag for masking events, which is
contained within the per-cpu vcpu_info structure. Because the guest
kernel runs in ring 1 and not 0, the IF flag in EFLAGS is completely
ignored (and must be, because even if a guest domain disables
interrupts for itself, it can't disable them overall).
(A note on terminology: "events" and interrupts are effectively
synonymous. However, rather than using an "enable flag", Xen uses a
"mask flag", which blocks event delivery when it is non-zero.)
There are paravirt_ops for each of cli/sti/save_fl/restore_fl, which
are implemented to manage the Xen event mask state. The only thing
worth noting is that when events are unmasked, we need to explicitly
see if there's a pending event and call into the hypervisor to make
sure it gets delivered.
UPCALLS
Xen needs a couple of upcall (or callback) functions to be implemented
by each guest. One is the event upcalls, which is how events
(interrupts, effectively) are delivered to the guests. The other is
the failsafe callback, which is used to report errors in either
reloading a segment register, or caused by iret. These are
implemented in i386/kernel/entry.S so they can jump into the normal
iret_exc path when necessary.
MULTICALL BATCHING
Xen provides a multicall mechanism, which allows multiple hypercalls
to be issued at once in order to mitigate the cost of trapping into
the hypervisor. This is particularly useful for context switches,
since the 4-5 hypercalls they would normally need (reload cr3, update
TLS, maybe update LDT) can be reduced to one. This patch implements a
generic batching mechanism for hypercalls, which gets used in many
places in the Xen code.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Cc: Ian Pratt <ian.pratt@xensource.com>
Cc: Christian Limpach <Christian.Limpach@cl.cam.ac.uk>
Cc: Adrian Bunk <bunk@stusta.de>
2007-07-18 09:37:04 +08:00
|
|
|
ENDPROC(xen_failsafe_callback)
|
|
|
|
|
2013-02-04 09:22:39 +08:00
|
|
|
BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
|
2010-05-14 19:40:51 +08:00
|
|
|
xen_evtchn_do_upcall)
|
|
|
|
|
2015-06-08 15:49:11 +08:00
|
|
|
#endif /* CONFIG_XEN */
|
2013-02-04 09:22:39 +08:00
|
|
|
|
|
|
|
#if IS_ENABLED(CONFIG_HYPERV)
|
|
|
|
|
|
|
|
BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
|
|
|
|
hyperv_vector_handler)
|
|
|
|
|
|
|
|
#endif /* CONFIG_HYPERV */
|
xen: Core Xen implementation
This patch is a rollup of all the core pieces of the Xen
implementation, including:
- booting and setup
- pagetable setup
- privileged instructions
- segmentation
- interrupt flags
- upcalls
- multicall batching
BOOTING AND SETUP
The vmlinux image is decorated with ELF notes which tell the Xen
domain builder what the kernel's requirements are; the domain builder
then constructs the address space accordingly and starts the kernel.
Xen has its own entrypoint for the kernel (contained in an ELF note).
The ELF notes are set up by xen-head.S, which is included into head.S.
In principle it could be linked separately, but it seems to provoke
lots of binutils bugs.
Because the domain builder starts the kernel in a fairly sane state
(32-bit protected mode, paging enabled, flat segments set up), there's
not a lot of setup needed before starting the kernel proper. The main
steps are:
1. Install the Xen paravirt_ops, which is simply a matter of a
structure assignment.
2. Set init_mm to use the Xen-supplied pagetables (analogous to the
head.S generated pagetables in a native boot).
3. Reserve address space for Xen, since it takes a chunk at the top
of the address space for its own use.
4. Call start_kernel()
PAGETABLE SETUP
Once we hit the main kernel boot sequence, it will end up calling back
via paravirt_ops to set up various pieces of Xen specific state. One
of the critical things which requires a bit of extra care is the
construction of the initial init_mm pagetable. Because Xen places
tight constraints on pagetables (an active pagetable must always be
valid, and must always be mapped read-only to the guest domain), we
need to be careful when constructing the new pagetable to keep these
constraints in mind. It turns out that the easiest way to do this is
use the initial Xen-provided pagetable as a template, and then just
insert new mappings for memory where a mapping doesn't already exist.
This means that during pagetable setup, it uses a special version of
xen_set_pte which ignores any attempt to remap a read-only page as
read-write (since Xen will map its own initial pagetable as RO), but
lets other changes to the ptes happen, so that things like NX are set
properly.
PRIVILEGED INSTRUCTIONS AND SEGMENTATION
When the kernel runs under Xen, it runs in ring 1 rather than ring 0.
This means that it is more privileged than user-mode in ring 3, but it
still can't run privileged instructions directly. Non-performance
critical instructions are dealt with by taking a privilege exception
and trapping into the hypervisor and emulating the instruction, but
more performance-critical instructions have their own specific
paravirt_ops. In many cases we can avoid having to do any hypercalls
for these instructions, or the Xen implementation is quite different
from the normal native version.
The privileged instructions fall into the broad classes of:
Segmentation: setting up the GDT and the GDT entries, LDT,
TLS and so on. Xen doesn't allow the GDT to be directly
modified; all GDT updates are done via hypercalls where the new
entries can be validated. This is important because Xen uses
segment limits to prevent the guest kernel from damaging the
hypervisor itself.
Traps and exceptions: Xen uses a special format for trap entrypoints,
so when the kernel wants to set an IDT entry, it needs to be
converted to the form Xen expects. Xen sets int 0x80 up specially
so that the trap goes straight from userspace into the guest kernel
without going via the hypervisor. sysenter isn't supported.
Kernel stack: The esp0 entry is extracted from the tss and provided to
Xen.
TLB operations: the various TLB calls are mapped into corresponding
Xen hypercalls.
Control registers: all the control registers are privileged. The most
important is cr3, which points to the base of the current pagetable,
and we handle it specially.
Another instruction we treat specially is CPUID, even though its not
privileged. We want to control what CPU features are visible to the
rest of the kernel, and so CPUID ends up going into a paravirt_op.
Xen implements this mainly to disable the ACPI and APIC subsystems.
INTERRUPT FLAGS
Xen maintains its own separate flag for masking events, which is
contained within the per-cpu vcpu_info structure. Because the guest
kernel runs in ring 1 and not 0, the IF flag in EFLAGS is completely
ignored (and must be, because even if a guest domain disables
interrupts for itself, it can't disable them overall).
(A note on terminology: "events" and interrupts are effectively
synonymous. However, rather than using an "enable flag", Xen uses a
"mask flag", which blocks event delivery when it is non-zero.)
There are paravirt_ops for each of cli/sti/save_fl/restore_fl, which
are implemented to manage the Xen event mask state. The only thing
worth noting is that when events are unmasked, we need to explicitly
see if there's a pending event and call into the hypervisor to make
sure it gets delivered.
UPCALLS
Xen needs a couple of upcall (or callback) functions to be implemented
by each guest. One is the event upcalls, which is how events
(interrupts, effectively) are delivered to the guests. The other is
the failsafe callback, which is used to report errors in either
reloading a segment register, or caused by iret. These are
implemented in i386/kernel/entry.S so they can jump into the normal
iret_exc path when necessary.
MULTICALL BATCHING
Xen provides a multicall mechanism, which allows multiple hypercalls
to be issued at once in order to mitigate the cost of trapping into
the hypervisor. This is particularly useful for context switches,
since the 4-5 hypercalls they would normally need (reload cr3, update
TLS, maybe update LDT) can be reduced to one. This patch implements a
generic batching mechanism for hypercalls, which gets used in many
places in the Xen code.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Cc: Ian Pratt <ian.pratt@xensource.com>
Cc: Christian Limpach <Christian.Limpach@cl.cam.ac.uk>
Cc: Adrian Bunk <bunk@stusta.de>
2007-07-18 09:37:04 +08:00
|
|
|
|
2008-10-07 07:06:12 +08:00
|
|
|
#ifdef CONFIG_FUNCTION_TRACER
|
2008-05-13 03:20:43 +08:00
|
|
|
#ifdef CONFIG_DYNAMIC_FTRACE
|
|
|
|
|
|
|
|
ENTRY(mcount)
|
|
|
|
ret
|
|
|
|
END(mcount)
|
|
|
|
|
|
|
|
ENTRY(ftrace_caller)
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl %eax
|
|
|
|
pushl %ecx
|
|
|
|
pushl %edx
|
|
|
|
pushl $0 /* Pass NULL as regs pointer */
|
|
|
|
movl 4*4(%esp), %eax
|
|
|
|
movl 0x4(%ebp), %edx
|
|
|
|
movl function_trace_op, %ecx
|
|
|
|
subl $MCOUNT_INSN_SIZE, %eax
|
2008-05-13 03:20:43 +08:00
|
|
|
|
|
|
|
.globl ftrace_call
|
|
|
|
ftrace_call:
|
2015-06-08 15:49:11 +08:00
|
|
|
call ftrace_stub
|
2008-05-13 03:20:43 +08:00
|
|
|
|
2015-06-08 15:49:11 +08:00
|
|
|
addl $4, %esp /* skip NULL pointer */
|
|
|
|
popl %edx
|
|
|
|
popl %ecx
|
|
|
|
popl %eax
|
2012-06-06 08:00:11 +08:00
|
|
|
ftrace_ret:
|
2008-11-26 13:16:24 +08:00
|
|
|
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
|
|
|
|
.globl ftrace_graph_call
|
|
|
|
ftrace_graph_call:
|
2015-06-08 15:49:11 +08:00
|
|
|
jmp ftrace_stub
|
2008-11-26 13:16:24 +08:00
|
|
|
#endif
|
2008-05-13 03:20:43 +08:00
|
|
|
|
|
|
|
.globl ftrace_stub
|
|
|
|
ftrace_stub:
|
|
|
|
ret
|
|
|
|
END(ftrace_caller)
|
|
|
|
|
2012-06-06 08:00:11 +08:00
|
|
|
ENTRY(ftrace_regs_caller)
|
|
|
|
pushf /* push flags before compare (in cs location) */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* i386 does not save SS and ESP when coming from kernel.
|
|
|
|
* Instead, to get sp, ®s->sp is used (see ptrace.h).
|
|
|
|
* Unfortunately, that means eflags must be at the same location
|
|
|
|
* as the current return ip is. We move the return ip into the
|
|
|
|
* ip location, and move flags into the return ip location.
|
|
|
|
*/
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl 4(%esp) /* save return ip into ip slot */
|
|
|
|
|
|
|
|
pushl $0 /* Load 0 into orig_ax */
|
|
|
|
pushl %gs
|
|
|
|
pushl %fs
|
|
|
|
pushl %es
|
|
|
|
pushl %ds
|
|
|
|
pushl %eax
|
|
|
|
pushl %ebp
|
|
|
|
pushl %edi
|
|
|
|
pushl %esi
|
|
|
|
pushl %edx
|
|
|
|
pushl %ecx
|
|
|
|
pushl %ebx
|
|
|
|
|
|
|
|
movl 13*4(%esp), %eax /* Get the saved flags */
|
|
|
|
movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */
|
|
|
|
/* clobbering return ip */
|
|
|
|
movl $__KERNEL_CS, 13*4(%esp)
|
|
|
|
|
|
|
|
movl 12*4(%esp), %eax /* Load ip (1st parameter) */
|
|
|
|
subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */
|
|
|
|
movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */
|
|
|
|
movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
|
|
|
|
pushl %esp /* Save pt_regs as 4th parameter */
|
2012-06-06 08:00:11 +08:00
|
|
|
|
|
|
|
GLOBAL(ftrace_regs_call)
|
2015-06-08 15:49:11 +08:00
|
|
|
call ftrace_stub
|
|
|
|
|
|
|
|
addl $4, %esp /* Skip pt_regs */
|
|
|
|
movl 14*4(%esp), %eax /* Move flags back into cs */
|
|
|
|
movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */
|
|
|
|
movl 12*4(%esp), %eax /* Get return ip from regs->ip */
|
|
|
|
movl %eax, 14*4(%esp) /* Put return ip back for ret */
|
|
|
|
|
|
|
|
popl %ebx
|
|
|
|
popl %ecx
|
|
|
|
popl %edx
|
|
|
|
popl %esi
|
|
|
|
popl %edi
|
|
|
|
popl %ebp
|
|
|
|
popl %eax
|
|
|
|
popl %ds
|
|
|
|
popl %es
|
|
|
|
popl %fs
|
|
|
|
popl %gs
|
|
|
|
addl $8, %esp /* Skip orig_ax and ip */
|
|
|
|
popf /* Pop flags at end (no addl to corrupt flags) */
|
|
|
|
jmp ftrace_ret
|
2012-06-06 08:00:11 +08:00
|
|
|
|
|
|
|
popf
|
2015-06-08 15:49:11 +08:00
|
|
|
jmp ftrace_stub
|
2008-05-13 03:20:43 +08:00
|
|
|
#else /* ! CONFIG_DYNAMIC_FTRACE */
|
|
|
|
|
2008-05-13 03:20:42 +08:00
|
|
|
ENTRY(mcount)
|
2015-06-08 15:49:11 +08:00
|
|
|
cmpl $__PAGE_OFFSET, %esp
|
|
|
|
jb ftrace_stub /* Paging not enabled yet? */
|
2013-08-31 08:29:29 +08:00
|
|
|
|
2015-06-08 15:49:11 +08:00
|
|
|
cmpl $ftrace_stub, ftrace_trace_function
|
|
|
|
jnz trace
|
2008-11-26 04:07:04 +08:00
|
|
|
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
|
2015-06-08 15:49:11 +08:00
|
|
|
cmpl $ftrace_stub, ftrace_graph_return
|
|
|
|
jnz ftrace_graph_caller
|
2008-12-03 12:50:05 +08:00
|
|
|
|
2015-06-08 15:49:11 +08:00
|
|
|
cmpl $ftrace_graph_entry_stub, ftrace_graph_entry
|
|
|
|
jnz ftrace_graph_caller
|
2008-11-11 14:03:45 +08:00
|
|
|
#endif
|
2008-05-13 03:20:42 +08:00
|
|
|
.globl ftrace_stub
|
|
|
|
ftrace_stub:
|
|
|
|
ret
|
|
|
|
|
|
|
|
/* taken from glibc */
|
|
|
|
trace:
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl %eax
|
|
|
|
pushl %ecx
|
|
|
|
pushl %edx
|
|
|
|
movl 0xc(%esp), %eax
|
|
|
|
movl 0x4(%ebp), %edx
|
|
|
|
subl $MCOUNT_INSN_SIZE, %eax
|
|
|
|
|
|
|
|
call *ftrace_trace_function
|
|
|
|
|
|
|
|
popl %edx
|
|
|
|
popl %ecx
|
|
|
|
popl %eax
|
|
|
|
jmp ftrace_stub
|
2008-05-13 03:20:42 +08:00
|
|
|
END(mcount)
|
2008-05-13 03:20:43 +08:00
|
|
|
#endif /* CONFIG_DYNAMIC_FTRACE */
|
2008-10-07 07:06:12 +08:00
|
|
|
#endif /* CONFIG_FUNCTION_TRACER */
|
2008-05-13 03:20:42 +08:00
|
|
|
|
2008-11-26 04:07:04 +08:00
|
|
|
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
|
|
|
|
ENTRY(ftrace_graph_caller)
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl %eax
|
|
|
|
pushl %ecx
|
|
|
|
pushl %edx
|
|
|
|
movl 0xc(%esp), %eax
|
|
|
|
lea 0x4(%ebp), %edx
|
|
|
|
movl (%ebp), %ecx
|
|
|
|
subl $MCOUNT_INSN_SIZE, %eax
|
|
|
|
call prepare_ftrace_return
|
|
|
|
popl %edx
|
|
|
|
popl %ecx
|
|
|
|
popl %eax
|
2008-11-16 13:02:06 +08:00
|
|
|
ret
|
2008-11-26 04:07:04 +08:00
|
|
|
END(ftrace_graph_caller)
|
2008-11-11 14:03:45 +08:00
|
|
|
|
|
|
|
.globl return_to_handler
|
|
|
|
return_to_handler:
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl %eax
|
|
|
|
pushl %edx
|
|
|
|
movl %ebp, %eax
|
|
|
|
call ftrace_return_to_handler
|
|
|
|
movl %eax, %ecx
|
|
|
|
popl %edx
|
|
|
|
popl %eax
|
|
|
|
jmp *%ecx
|
2008-11-16 13:02:06 +08:00
|
|
|
#endif
|
2008-05-13 03:20:42 +08:00
|
|
|
|
2013-10-31 04:37:00 +08:00
|
|
|
#ifdef CONFIG_TRACING
|
|
|
|
ENTRY(trace_page_fault)
|
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $trace_do_page_fault
|
|
|
|
jmp error_code
|
2013-10-31 04:37:00 +08:00
|
|
|
END(trace_page_fault)
|
|
|
|
#endif
|
|
|
|
|
2008-11-24 22:38:45 +08:00
|
|
|
ENTRY(page_fault)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $do_page_fault
|
2008-11-24 22:38:45 +08:00
|
|
|
ALIGN
|
|
|
|
error_code:
|
2009-02-09 21:17:40 +08:00
|
|
|
/* the function address is in %gs's slot on the stack */
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl %fs
|
|
|
|
pushl %es
|
|
|
|
pushl %ds
|
|
|
|
pushl %eax
|
|
|
|
pushl %ebp
|
|
|
|
pushl %edi
|
|
|
|
pushl %esi
|
|
|
|
pushl %edx
|
|
|
|
pushl %ecx
|
|
|
|
pushl %ebx
|
2008-11-24 22:38:45 +08:00
|
|
|
cld
|
2015-06-08 15:49:11 +08:00
|
|
|
movl $(__KERNEL_PERCPU), %ecx
|
|
|
|
movl %ecx, %fs
|
2008-11-24 22:38:45 +08:00
|
|
|
UNWIND_ESPFIX_STACK
|
2009-02-09 21:17:40 +08:00
|
|
|
GS_TO_REG %ecx
|
2015-06-08 15:49:11 +08:00
|
|
|
movl PT_GS(%esp), %edi # get the function address
|
|
|
|
movl PT_ORIG_EAX(%esp), %edx # get the error code
|
|
|
|
movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart
|
2009-02-09 21:17:40 +08:00
|
|
|
REG_TO_PTGS %ecx
|
|
|
|
SET_KERNEL_GS %ecx
|
2015-06-08 15:49:11 +08:00
|
|
|
movl $(__USER_DS), %ecx
|
|
|
|
movl %ecx, %ds
|
|
|
|
movl %ecx, %es
|
2008-11-24 22:38:45 +08:00
|
|
|
TRACE_IRQS_OFF
|
2015-06-08 15:49:11 +08:00
|
|
|
movl %esp, %eax # pt_regs pointer
|
|
|
|
call *%edi
|
|
|
|
jmp ret_from_exception
|
2008-11-24 22:38:45 +08:00
|
|
|
END(page_fault)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Debug traps and NMI can happen at the one SYSENTER instruction
|
|
|
|
* that sets up the real kernel stack. Check here, since we can't
|
|
|
|
* allow the wrong stack to be used.
|
|
|
|
*
|
|
|
|
* "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
|
|
|
|
* already pushed 3 words if it hits on the sysenter instruction:
|
|
|
|
* eflags, cs and eip.
|
|
|
|
*
|
|
|
|
* We just load the right stack, and push the three (known) values
|
|
|
|
* by hand onto the new stack - while updating the return eip past
|
|
|
|
* the instruction that would have done it for sysenter.
|
|
|
|
*/
|
2009-02-09 21:17:40 +08:00
|
|
|
.macro FIX_STACK offset ok label
|
2015-06-08 15:49:11 +08:00
|
|
|
cmpw $__KERNEL_CS, 4(%esp)
|
|
|
|
jne \ok
|
2009-02-09 21:17:40 +08:00
|
|
|
\label:
|
2015-06-08 15:49:11 +08:00
|
|
|
movl TSS_sysenter_sp0 + \offset(%esp), %esp
|
x86/debug: Remove perpetually broken, unmaintainable dwarf annotations
So the dwarf2 annotations in low level assembly code have
become an increasing hindrance: unreadable, messy macros
mixed into some of the most security sensitive code paths
of the Linux kernel.
These debug info annotations don't even buy the upstream
kernel anything: dwarf driven stack unwinding has caused
problems in the past so it's out of tree, and the upstream
kernel only uses the much more robust framepointers based
stack unwinding method.
In addition to that there's a steady, slow bitrot going
on with these annotations, requiring frequent fixups.
There's no tooling and no functionality upstream that
keeps it correct.
So burn down the sick forest, allowing new, healthier growth:
27 files changed, 350 insertions(+), 1101 deletions(-)
Someone who has the willingness and time to do this
properly can attempt to reintroduce dwarf debuginfo in x86
assembly code plus dwarf unwinding from first principles,
with the following conditions:
- it should be maximally readable, and maximally low-key to
'ordinary' code reading and maintenance.
- find a build time method to insert dwarf annotations
automatically in the most common cases, for pop/push
instructions that manipulate the stack pointer. This could
be done for example via a preprocessing step that just
looks for common patterns - plus special annotations for
the few cases where we want to depart from the default.
We have hundreds of CFI annotations, so automating most of
that makes sense.
- it should come with build tooling checks that ensure that
CFI annotations are sensible. We've seen such efforts from
the framepointer side, and there's no reason it couldn't be
done on the dwarf side.
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: Frédéric Weisbecker <fweisbec@gmail.com
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jan Beulich <JBeulich@suse.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-28 18:21:47 +08:00
|
|
|
pushfl
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $__KERNEL_CS
|
|
|
|
pushl $sysenter_past_esp
|
2009-02-09 21:17:40 +08:00
|
|
|
.endm
|
2008-11-24 22:38:45 +08:00
|
|
|
|
|
|
|
ENTRY(debug)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
cmpl $entry_SYSENTER_32, (%esp)
|
|
|
|
jne debug_stack_correct
|
2009-02-09 21:17:40 +08:00
|
|
|
FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
|
2008-11-24 22:38:45 +08:00
|
|
|
debug_stack_correct:
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $-1 # mark this as an int
|
2008-11-24 22:38:45 +08:00
|
|
|
SAVE_ALL
|
|
|
|
TRACE_IRQS_OFF
|
2015-06-08 15:49:11 +08:00
|
|
|
xorl %edx, %edx # error code 0
|
|
|
|
movl %esp, %eax # pt_regs pointer
|
|
|
|
call do_debug
|
|
|
|
jmp ret_from_exception
|
2008-11-24 22:38:45 +08:00
|
|
|
END(debug)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* NMI is doubly nasty. It can happen _while_ we're handling
|
|
|
|
* a debug fault, and the debug fault hasn't yet been able to
|
|
|
|
* clear up the stack. So we first check whether we got an
|
|
|
|
* NMI on the sysenter entry path, but after that we need to
|
|
|
|
* check whether we got an NMI on the debug path where the debug
|
|
|
|
* fault happened on the sysenter path.
|
|
|
|
*/
|
|
|
|
ENTRY(nmi)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2014-05-05 01:36:22 +08:00
|
|
|
#ifdef CONFIG_X86_ESPFIX32
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl %eax
|
|
|
|
movl %ss, %eax
|
|
|
|
cmpw $__ESPFIX_SS, %ax
|
|
|
|
popl %eax
|
|
|
|
je nmi_espfix_stack
|
2014-05-05 01:36:22 +08:00
|
|
|
#endif
|
2015-06-08 15:49:11 +08:00
|
|
|
cmpl $entry_SYSENTER_32, (%esp)
|
|
|
|
je nmi_stack_fixup
|
|
|
|
pushl %eax
|
|
|
|
movl %esp, %eax
|
|
|
|
/*
|
|
|
|
* Do not access memory above the end of our stack page,
|
2008-11-24 22:38:45 +08:00
|
|
|
* it might not exist.
|
|
|
|
*/
|
2015-06-08 15:49:11 +08:00
|
|
|
andl $(THREAD_SIZE-1), %eax
|
|
|
|
cmpl $(THREAD_SIZE-20), %eax
|
|
|
|
popl %eax
|
|
|
|
jae nmi_stack_correct
|
|
|
|
cmpl $entry_SYSENTER_32, 12(%esp)
|
|
|
|
je nmi_debug_stack_check
|
2008-11-24 22:38:45 +08:00
|
|
|
nmi_stack_correct:
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl %eax
|
2008-11-24 22:38:45 +08:00
|
|
|
SAVE_ALL
|
2015-06-08 15:49:11 +08:00
|
|
|
xorl %edx, %edx # zero error code
|
|
|
|
movl %esp, %eax # pt_regs pointer
|
|
|
|
call do_nmi
|
|
|
|
jmp restore_all_notrace
|
2008-11-24 22:38:45 +08:00
|
|
|
|
|
|
|
nmi_stack_fixup:
|
2009-02-09 21:17:40 +08:00
|
|
|
FIX_STACK 12, nmi_stack_correct, 1
|
2015-06-08 15:49:11 +08:00
|
|
|
jmp nmi_stack_correct
|
2008-11-24 22:38:45 +08:00
|
|
|
|
|
|
|
nmi_debug_stack_check:
|
2015-06-08 15:49:11 +08:00
|
|
|
cmpw $__KERNEL_CS, 16(%esp)
|
|
|
|
jne nmi_stack_correct
|
|
|
|
cmpl $debug, (%esp)
|
|
|
|
jb nmi_stack_correct
|
|
|
|
cmpl $debug_esp_fix_insn, (%esp)
|
|
|
|
ja nmi_stack_correct
|
2009-02-09 21:17:40 +08:00
|
|
|
FIX_STACK 24, nmi_stack_correct, 1
|
2015-06-08 15:49:11 +08:00
|
|
|
jmp nmi_stack_correct
|
2008-11-24 22:38:45 +08:00
|
|
|
|
2014-05-05 01:36:22 +08:00
|
|
|
#ifdef CONFIG_X86_ESPFIX32
|
2008-11-24 22:38:45 +08:00
|
|
|
nmi_espfix_stack:
|
x86/debug: Remove perpetually broken, unmaintainable dwarf annotations
So the dwarf2 annotations in low level assembly code have
become an increasing hindrance: unreadable, messy macros
mixed into some of the most security sensitive code paths
of the Linux kernel.
These debug info annotations don't even buy the upstream
kernel anything: dwarf driven stack unwinding has caused
problems in the past so it's out of tree, and the upstream
kernel only uses the much more robust framepointers based
stack unwinding method.
In addition to that there's a steady, slow bitrot going
on with these annotations, requiring frequent fixups.
There's no tooling and no functionality upstream that
keeps it correct.
So burn down the sick forest, allowing new, healthier growth:
27 files changed, 350 insertions(+), 1101 deletions(-)
Someone who has the willingness and time to do this
properly can attempt to reintroduce dwarf debuginfo in x86
assembly code plus dwarf unwinding from first principles,
with the following conditions:
- it should be maximally readable, and maximally low-key to
'ordinary' code reading and maintenance.
- find a build time method to insert dwarf annotations
automatically in the most common cases, for pop/push
instructions that manipulate the stack pointer. This could
be done for example via a preprocessing step that just
looks for common patterns - plus special annotations for
the few cases where we want to depart from the default.
We have hundreds of CFI annotations, so automating most of
that makes sense.
- it should come with build tooling checks that ensure that
CFI annotations are sensible. We've seen such efforts from
the framepointer side, and there's no reason it couldn't be
done on the dwarf side.
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: Frédéric Weisbecker <fweisbec@gmail.com
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jan Beulich <JBeulich@suse.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-28 18:21:47 +08:00
|
|
|
/*
|
2008-11-24 22:38:45 +08:00
|
|
|
* create the pointer to lss back
|
|
|
|
*/
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl %ss
|
|
|
|
pushl %esp
|
|
|
|
addl $4, (%esp)
|
2008-11-24 22:38:45 +08:00
|
|
|
/* copy the iret frame of 12 bytes */
|
|
|
|
.rept 3
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl 16(%esp)
|
2008-11-24 22:38:45 +08:00
|
|
|
.endr
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl %eax
|
2008-11-24 22:38:45 +08:00
|
|
|
SAVE_ALL
|
2015-06-08 15:49:11 +08:00
|
|
|
FIXUP_ESPFIX_STACK # %eax == %esp
|
|
|
|
xorl %edx, %edx # zero error code
|
|
|
|
call do_nmi
|
2008-11-24 22:38:45 +08:00
|
|
|
RESTORE_REGS
|
2015-06-08 15:49:11 +08:00
|
|
|
lss 12+4(%esp), %esp # back to espfix stack
|
|
|
|
jmp irq_return
|
2014-05-05 01:36:22 +08:00
|
|
|
#endif
|
2008-11-24 22:38:45 +08:00
|
|
|
END(nmi)
|
|
|
|
|
|
|
|
ENTRY(int3)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $-1 # mark this as an int
|
2008-11-24 22:38:45 +08:00
|
|
|
SAVE_ALL
|
|
|
|
TRACE_IRQS_OFF
|
2015-06-08 15:49:11 +08:00
|
|
|
xorl %edx, %edx # zero error code
|
|
|
|
movl %esp, %eax # pt_regs pointer
|
|
|
|
call do_int3
|
|
|
|
jmp ret_from_exception
|
2008-11-24 22:38:45 +08:00
|
|
|
END(int3)
|
|
|
|
|
|
|
|
ENTRY(general_protection)
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $do_general_protection
|
|
|
|
jmp error_code
|
2008-11-24 22:38:45 +08:00
|
|
|
END(general_protection)
|
|
|
|
|
2010-10-14 17:22:52 +08:00
|
|
|
#ifdef CONFIG_KVM_GUEST
|
|
|
|
ENTRY(async_page_fault)
|
2012-09-22 04:58:10 +08:00
|
|
|
ASM_CLAC
|
2015-06-08 15:49:11 +08:00
|
|
|
pushl $do_async_page_fault
|
|
|
|
jmp error_code
|
2011-03-09 05:39:24 +08:00
|
|
|
END(async_page_fault)
|
2010-10-14 17:22:52 +08:00
|
|
|
#endif
|