* Re: [PATCH 3/3] x86-64: Rework vsyscall emulation and add vsyscall= parameter
2011-08-10 15:15 ` [PATCH 3/3] x86-64: Rework vsyscall emulation and add vsyscall= parameter Andy Lutomirski
@ 2011-08-10 17:21 ` H. Peter Anvin
2011-08-10 17:47 ` Andrew Lutomirski
2011-08-11 0:02 ` [tip:x86/vdso] " tip-bot for Andy Lutomirski
2011-08-11 0:31 ` tip-bot for Andy Lutomirski
2 siblings, 1 reply; 15+ messages in thread
From: H. Peter Anvin @ 2011-08-10 17:21 UTC (permalink / raw)
To: Andy Lutomirski
Cc: x86, Andi Kleen, linux-kernel, torvalds, lueckintel, kimwooyoung,
Ingo Molnar, Borislav Petkov
On 08/10/2011 10:15 AM, Andy Lutomirski wrote:
> There are three choices:
>
> vsyscall=native: Vsyscalls are native code that issues the
> corresponding syscalls.
>
> vsyscall=emulate (default): Vsyscalls are emulated by instruction
> fault traps, tested in the bad_area path. The actual contents of
> the vsyscall page is the same as the vsyscall=native case except
> that it's marked NX. This way programs that make assumptions about
> what the code in the page does will not be confused when they read
> that code.
>
> vsyscall=none: Trying to execute a vsyscall will segfault.
>
> Signed-off-by: Andy Lutomirski <luto@mit.edu>
Hi Andy,
This patch doesn't apply. What is your baseline for this patch?
-hpa
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH 3/3] x86-64: Rework vsyscall emulation and add vsyscall= parameter
2011-08-10 17:21 ` H. Peter Anvin
@ 2011-08-10 17:47 ` Andrew Lutomirski
2011-08-10 21:14 ` H. Peter Anvin
0 siblings, 1 reply; 15+ messages in thread
From: Andrew Lutomirski @ 2011-08-10 17:47 UTC (permalink / raw)
To: H. Peter Anvin
Cc: x86, Andi Kleen, linux-kernel, torvalds, lueckintel, kimwooyoung,
Ingo Molnar, Borislav Petkov
On Wed, Aug 10, 2011 at 1:21 PM, H. Peter Anvin <hpa@zytor.com> wrote:
> On 08/10/2011 10:15 AM, Andy Lutomirski wrote:
>> There are three choices:
>>
>> vsyscall=native: Vsyscalls are native code that issues the
>> corresponding syscalls.
>>
>> vsyscall=emulate (default): Vsyscalls are emulated by instruction
>> fault traps, tested in the bad_area path. The actual contents of
>> the vsyscall page is the same as the vsyscall=native case except
>> that it's marked NX. This way programs that make assumptions about
>> what the code in the page does will not be confused when they read
>> that code.
>>
>> vsyscall=none: Trying to execute a vsyscall will segfault.
>>
>> Signed-off-by: Andy Lutomirski <luto@mit.edu>
>
> Hi Andy,
>
> This patch doesn't apply. What is your baseline for this patch?
My baseline was a commit that probably only lives in my tree, but the
patches should apply cleanly on top of
c149a665ac488e0dac22a42287f45ad1bda06ff1, which is the current
tip/x86/vdso.
--Andy
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH 3/3] x86-64: Rework vsyscall emulation and add vsyscall= parameter
2011-08-10 17:47 ` Andrew Lutomirski
@ 2011-08-10 21:14 ` H. Peter Anvin
2011-08-10 21:18 ` Andrew Lutomirski
0 siblings, 1 reply; 15+ messages in thread
From: H. Peter Anvin @ 2011-08-10 21:14 UTC (permalink / raw)
To: Andrew Lutomirski
Cc: x86, Andi Kleen, linux-kernel, torvalds, lueckintel, kimwooyoung,
Ingo Molnar, Borislav Petkov
Andrew Lutomirski <luto@mit.edu> wrote:
>On Wed, Aug 10, 2011 at 1:21 PM, H. Peter Anvin <hpa@zytor.com> wrote:
>> On 08/10/2011 10:15 AM, Andy Lutomirski wrote:
>>> There are three choices:
>>>
>>> vsyscall=native: Vsyscalls are native code that issues the
>>> corresponding syscalls.
>>>
>>> vsyscall=emulate (default): Vsyscalls are emulated by instruction
>>> fault traps, tested in the bad_area path. The actual contents of
>>> the vsyscall page is the same as the vsyscall=native case except
>>> that it's marked NX. This way programs that make assumptions about
>>> what the code in the page does will not be confused when they read
>>> that code.
>>>
>>> vsyscall=none: Trying to execute a vsyscall will segfault.
>>>
>>> Signed-off-by: Andy Lutomirski <luto@mit.edu>
>>
>> Hi Andy,
>>
>> This patch doesn't apply. What is your baseline for this patch?
>
>My baseline was a commit that probably only lives in my tree, but the
>patches should apply cleanly on top of
>c149a665ac488e0dac22a42287f45ad1bda06ff1, which is the current
>tip/x86/vdso.
>
>--Andy
Please rebase your patch on the current -linus since it appears to have changed since x86/vdso was merged.
-hpa
--
Sent from my mobile phone. Please excuse my brevity and lack of formatting.
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH 3/3] x86-64: Rework vsyscall emulation and add vsyscall= parameter
2011-08-10 21:14 ` H. Peter Anvin
@ 2011-08-10 21:18 ` Andrew Lutomirski
2011-08-10 22:20 ` H. Peter Anvin
0 siblings, 1 reply; 15+ messages in thread
From: Andrew Lutomirski @ 2011-08-10 21:18 UTC (permalink / raw)
To: H. Peter Anvin
Cc: x86, Andi Kleen, linux-kernel, torvalds, lueckintel, kimwooyoung,
Ingo Molnar, Borislav Petkov
On Wed, Aug 10, 2011 at 5:14 PM, H. Peter Anvin <hpa@zytor.com> wrote:
> Andrew Lutomirski <luto@mit.edu> wrote:
>
>>On Wed, Aug 10, 2011 at 1:21 PM, H. Peter Anvin <hpa@zytor.com> wrote:
>>> On 08/10/2011 10:15 AM, Andy Lutomirski wrote:
>>>> There are three choices:
>>>>
>>>> vsyscall=native: Vsyscalls are native code that issues the
>>>> corresponding syscalls.
>>>>
>>>> vsyscall=emulate (default): Vsyscalls are emulated by instruction
>>>> fault traps, tested in the bad_area path. The actual contents of
>>>> the vsyscall page is the same as the vsyscall=native case except
>>>> that it's marked NX. This way programs that make assumptions about
>>>> what the code in the page does will not be confused when they read
>>>> that code.
>>>>
>>>> vsyscall=none: Trying to execute a vsyscall will segfault.
>>>>
>>>> Signed-off-by: Andy Lutomirski <luto@mit.edu>
>>>
>>> Hi Andy,
>>>
>>> This patch doesn't apply. What is your baseline for this patch?
>>
>>My baseline was a commit that probably only lives in my tree, but the
>>patches should apply cleanly on top of
>>c149a665ac488e0dac22a42287f45ad1bda06ff1, which is the current
>>tip/x86/vdso.
>>
>>--Andy
>
> Please rebase your patch on the current -linus since it appears to have changed since x86/vdso was merged.
>
Can you double-check? I think it's the other way around: x86/vdso has
fixes that should be pushed to Linus.
$ git log tip/x86/vdso ^origin/master --oneline
c149a66 x86-64: Add vsyscall:emulate_vsyscall trace event
318f5a2 x86-64: Add user_64bit_mode paravirt op
5d5791a x86-64, xen: Enable the vvar mapping
f670bb7 x86-64: Work around gold bug 13023
9c40818 x86-64: Move the "user" vsyscall segment out of the data segment.
1bdfac1 x86-64: Pad vDSO to a page boundary
17b0436 Merge commit 'v3.0' into x86/vdso
--Andy
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH 3/3] x86-64: Rework vsyscall emulation and add vsyscall= parameter
2011-08-10 21:18 ` Andrew Lutomirski
@ 2011-08-10 22:20 ` H. Peter Anvin
2011-08-10 22:56 ` Andrew Lutomirski
0 siblings, 1 reply; 15+ messages in thread
From: H. Peter Anvin @ 2011-08-10 22:20 UTC (permalink / raw)
To: Andrew Lutomirski
Cc: x86, Andi Kleen, linux-kernel, torvalds, lueckintel, kimwooyoung,
Ingo Molnar, Borislav Petkov
Andrew Lutomirski <luto@mit.edu> wrote:
>On Wed, Aug 10, 2011 at 5:14 PM, H. Peter Anvin <hpa@zytor.com> wrote:
>> Andrew Lutomirski <luto@mit.edu> wrote:
>>
>>>On Wed, Aug 10, 2011 at 1:21 PM, H. Peter Anvin <hpa@zytor.com>
>wrote:
>>>> On 08/10/2011 10:15 AM, Andy Lutomirski wrote:
>>>>> There are three choices:
>>>>>
>>>>> vsyscall=native: Vsyscalls are native code that issues the
>>>>> corresponding syscalls.
>>>>>
>>>>> vsyscall=emulate (default): Vsyscalls are emulated by instruction
>>>>> fault traps, tested in the bad_area path. The actual contents of
>>>>> the vsyscall page is the same as the vsyscall=native case except
>>>>> that it's marked NX. This way programs that make assumptions
>about
>>>>> what the code in the page does will not be confused when they read
>>>>> that code.
>>>>>
>>>>> vsyscall=none: Trying to execute a vsyscall will segfault.
>>>>>
>>>>> Signed-off-by: Andy Lutomirski <luto@mit.edu>
>>>>
>>>> Hi Andy,
>>>>
>>>> This patch doesn't apply. What is your baseline for this patch?
>>>
>>>My baseline was a commit that probably only lives in my tree, but the
>>>patches should apply cleanly on top of
>>>c149a665ac488e0dac22a42287f45ad1bda06ff1, which is the current
>>>tip/x86/vdso.
>>>
>>>--Andy
>>
>> Please rebase your patch on the current -linus since it appears to
>have changed since x86/vdso was merged.
>>
>
>Can you double-check? I think it's the other way around: x86/vdso has
>fixes that should be pushed to Linus.
>
>$ git log tip/x86/vdso ^origin/master --oneline
>c149a66 x86-64: Add vsyscall:emulate_vsyscall trace event
>318f5a2 x86-64: Add user_64bit_mode paravirt op
>5d5791a x86-64, xen: Enable the vvar mapping
>f670bb7 x86-64: Work around gold bug 13023
>9c40818 x86-64: Move the "user" vsyscall segment out of the data
>segment.
>1bdfac1 x86-64: Pad vDSO to a page boundary
>17b0436 Merge commit 'v3.0' into x86/vdso
>
>--Andy
You're right, although coupling it makes the testing harder.
--
Sent from my mobile phone. Please excuse my brevity and lack of formatting.
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH 3/3] x86-64: Rework vsyscall emulation and add vsyscall= parameter
2011-08-10 22:20 ` H. Peter Anvin
@ 2011-08-10 22:56 ` Andrew Lutomirski
0 siblings, 0 replies; 15+ messages in thread
From: Andrew Lutomirski @ 2011-08-10 22:56 UTC (permalink / raw)
To: H. Peter Anvin
Cc: x86, Andi Kleen, linux-kernel, torvalds, lueckintel, kimwooyoung,
Ingo Molnar, Borislav Petkov
On Wed, Aug 10, 2011 at 6:20 PM, H. Peter Anvin <hpa@zytor.com> wrote:
> Andrew Lutomirski <luto@mit.edu> wrote:
>
>>On Wed, Aug 10, 2011 at 5:14 PM, H. Peter Anvin <hpa@zytor.com> wrote:
>>>
>>> Please rebase your patch on the current -linus since it appears to
>>have changed since x86/vdso was merged.
>>>
>>
>>Can you double-check? I think it's the other way around: x86/vdso has
>>fixes that should be pushed to Linus.
>>
>>$ git log tip/x86/vdso ^origin/master --oneline
>>c149a66 x86-64: Add vsyscall:emulate_vsyscall trace event
>>318f5a2 x86-64: Add user_64bit_mode paravirt op
>>5d5791a x86-64, xen: Enable the vvar mapping
>>f670bb7 x86-64: Work around gold bug 13023
>>9c40818 x86-64: Move the "user" vsyscall segment out of the data
>>segment.
>>1bdfac1 x86-64: Pad vDSO to a page boundary
>>17b0436 Merge commit 'v3.0' into x86/vdso
>>
>>--Andy
>
> You're right, although coupling it makes the testing harder.
If it helps, I can probably generate a new series that merges 9c40818
with the latest patch and makes the result independent of the rest
(except for the trace event). I'm not sure it's worth it, though.
--Andy
^ permalink raw reply [flat|nested] 15+ messages in thread
* [tip:x86/vdso] x86-64: Rework vsyscall emulation and add vsyscall= parameter
2011-08-10 15:15 ` [PATCH 3/3] x86-64: Rework vsyscall emulation and add vsyscall= parameter Andy Lutomirski
2011-08-10 17:21 ` H. Peter Anvin
@ 2011-08-11 0:02 ` tip-bot for Andy Lutomirski
2011-08-11 0:31 ` tip-bot for Andy Lutomirski
2 siblings, 0 replies; 15+ messages in thread
From: tip-bot for Andy Lutomirski @ 2011-08-11 0:02 UTC (permalink / raw)
To: linux-tip-commits; +Cc: linux-kernel, hpa, mingo, luto, tglx, hpa
Commit-ID: 721eb1343cdb53aa1c3b6b35f40976b7328faab0
Gitweb: http://git.kernel.org/tip/721eb1343cdb53aa1c3b6b35f40976b7328faab0
Author: Andy Lutomirski <luto@mit.edu>
AuthorDate: Wed, 10 Aug 2011 11:15:32 -0400
Committer: H. Peter Anvin <hpa@linux.intel.com>
CommitDate: Wed, 10 Aug 2011 18:56:01 -0500
x86-64: Rework vsyscall emulation and add vsyscall= parameter
There are three choices:
vsyscall=native: Vsyscalls are native code that issues the
corresponding syscalls.
vsyscall=emulate (default): Vsyscalls are emulated by instruction
fault traps, tested in the bad_area path. The actual contents of
the vsyscall page is the same as the vsyscall=native case except
that it's marked NX. This way programs that make assumptions about
what the code in the page does will not be confused when they read
that code.
vsyscall=none: Trying to execute a vsyscall will segfault.
Signed-off-by: Andy Lutomirski <luto@mit.edu>
Link: http://lkml.kernel.org/r/8449fb3abf89851fd6b2260972666a6f82542284.1312988155.git.luto@mit.edu
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: <stable@kernel.org> v3.0
---
Documentation/kernel-parameters.txt | 21 +++++++++
arch/x86/include/asm/irq_vectors.h | 4 --
arch/x86/include/asm/traps.h | 2 -
arch/x86/include/asm/vsyscall.h | 6 +++
arch/x86/kernel/entry_64.S | 1 -
arch/x86/kernel/traps.c | 6 ---
arch/x86/kernel/vmlinux.lds.S | 33 --------------
arch/x86/kernel/vsyscall_64.c | 79 +++++++++++++++++++++-------------
arch/x86/kernel/vsyscall_emu_64.S | 36 ++++++++++------
arch/x86/mm/fault.c | 12 +++++
10 files changed, 111 insertions(+), 89 deletions(-)
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index aa47be7..9cfd6bb 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2657,6 +2657,27 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
vmpoff= [KNL,S390] Perform z/VM CP command after power off.
Format: <command>
+ vsyscall= [X86-64]
+ Controls the behavior of vsyscalls (i.e. calls to
+ fixed addresses of 0xffffffffff600x00 from legacy
+ code). Most statically-linked binaries and older
+ versions of glibc use these calls. Because these
+ functions are at fixed addresses, they make nice
+ targets for exploits that can control RIP.
+
+ emulate [default] Vsyscalls turn into traps and are
+ emulated reasonably safely.
+
+ native Vsyscalls are native syscall instructions.
+ This is a little bit faster than trapping
+ and makes a few dynamic recompilers work
+ better than they would in emulation mode.
+ It also makes exploits much easier to write.
+
+ none Vsyscalls don't work at all. This makes
+ them quite hard to use for exploits but
+ might break your system.
+
vt.cur_default= [VT] Default cursor shape.
Format: 0xCCBBAA, where AA, BB, and CC are the same as
the parameters of the <Esc>[?A;B;Cc escape sequence;
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index a563c50..2c224e1 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -17,7 +17,6 @@
* Vectors 0 ... 31 : system traps and exceptions - hardcoded events
* Vectors 32 ... 127 : device interrupts
* Vector 128 : legacy int80 syscall interface
- * Vector 204 : legacy x86_64 vsyscall emulation
* Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 except 204 : device interrupts
* Vectors INVALIDATE_TLB_VECTOR_START ... 255 : special interrupts
*
@@ -51,9 +50,6 @@
#ifdef CONFIG_X86_32
# define SYSCALL_VECTOR 0x80
#endif
-#ifdef CONFIG_X86_64
-# define VSYSCALL_EMU_VECTOR 0xcc
-#endif
/*
* Vectors 0x30-0x3f are used for ISA interrupts.
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 2bae0a5..0012d09 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -40,7 +40,6 @@ asmlinkage void alignment_check(void);
asmlinkage void machine_check(void);
#endif /* CONFIG_X86_MCE */
asmlinkage void simd_coprocessor_error(void);
-asmlinkage void emulate_vsyscall(void);
dotraplinkage void do_divide_error(struct pt_regs *, long);
dotraplinkage void do_debug(struct pt_regs *, long);
@@ -67,7 +66,6 @@ dotraplinkage void do_alignment_check(struct pt_regs *, long);
dotraplinkage void do_machine_check(struct pt_regs *, long);
#endif
dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long);
-dotraplinkage void do_emulate_vsyscall(struct pt_regs *, long);
#ifdef CONFIG_X86_32
dotraplinkage void do_iret_error(struct pt_regs *, long);
#endif
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index 6010707..eaea1d3 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -27,6 +27,12 @@ extern struct timezone sys_tz;
extern void map_vsyscall(void);
+/*
+ * Called on instruction fetch fault in vsyscall page.
+ * Returns true if handled.
+ */
+extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address);
+
#endif /* __KERNEL__ */
#endif /* _ASM_X86_VSYSCALL_H */
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e949793..46792d9 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1123,7 +1123,6 @@ zeroentry spurious_interrupt_bug do_spurious_interrupt_bug
zeroentry coprocessor_error do_coprocessor_error
errorentry alignment_check do_alignment_check
zeroentry simd_coprocessor_error do_simd_coprocessor_error
-zeroentry emulate_vsyscall do_emulate_vsyscall
/* Reload gs selector with exception handling */
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index fbc097a..b9b6716 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -872,12 +872,6 @@ void __init trap_init(void)
set_bit(SYSCALL_VECTOR, used_vectors);
#endif
-#ifdef CONFIG_X86_64
- BUG_ON(test_bit(VSYSCALL_EMU_VECTOR, used_vectors));
- set_system_intr_gate(VSYSCALL_EMU_VECTOR, &emulate_vsyscall);
- set_bit(VSYSCALL_EMU_VECTOR, used_vectors);
-#endif
-
/*
* Should be a barrier for any external CPU state:
*/
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 8f3a265..0f703f1 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -71,7 +71,6 @@ PHDRS {
text PT_LOAD FLAGS(5); /* R_E */
data PT_LOAD FLAGS(6); /* RW_ */
#ifdef CONFIG_X86_64
- user PT_LOAD FLAGS(5); /* R_E */
#ifdef CONFIG_SMP
percpu PT_LOAD FLAGS(6); /* RW_ */
#endif
@@ -174,38 +173,6 @@ SECTIONS
. = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE);
-#define VSYSCALL_ADDR (-10*1024*1024)
-
-#define VLOAD_OFFSET (VSYSCALL_ADDR - __vsyscall_0 + LOAD_OFFSET)
-#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
-
-#define VVIRT_OFFSET (VSYSCALL_ADDR - __vsyscall_0)
-#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
-
- __vsyscall_0 = .;
-
- . = VSYSCALL_ADDR;
- .vsyscall : AT(VLOAD(.vsyscall)) {
- /* work around gold bug 13023 */
- __vsyscall_beginning_hack = .;
- *(.vsyscall_0)
-
- . = __vsyscall_beginning_hack + 1024;
- *(.vsyscall_1)
-
- . = __vsyscall_beginning_hack + 2048;
- *(.vsyscall_2)
-
- . = __vsyscall_beginning_hack + 4096; /* Pad the whole page. */
- } :user =0xcc
- . = ALIGN(__vsyscall_0 + PAGE_SIZE, PAGE_SIZE);
-
-#undef VSYSCALL_ADDR
-#undef VLOAD_OFFSET
-#undef VLOAD
-#undef VVIRT_OFFSET
-#undef VVIRT
-
#endif /* CONFIG_X86_64 */
/* Init code and data - will be freed after init */
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index bf8e9ff..18ae83d 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -56,6 +56,27 @@ DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) =
.lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock),
};
+static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE;
+
+static int __init vsyscall_setup(char *str)
+{
+ if (str) {
+ if (!strcmp("emulate", str))
+ vsyscall_mode = EMULATE;
+ else if (!strcmp("native", str))
+ vsyscall_mode = NATIVE;
+ else if (!strcmp("none", str))
+ vsyscall_mode = NONE;
+ else
+ return -EINVAL;
+
+ return 0;
+ }
+
+ return -EINVAL;
+}
+early_param("vsyscall", vsyscall_setup);
+
void update_vsyscall_tz(void)
{
unsigned long flags;
@@ -100,7 +121,7 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
printk("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
level, tsk->comm, task_pid_nr(tsk),
- message, regs->ip - 2, regs->cs,
+ message, regs->ip, regs->cs,
regs->sp, regs->ax, regs->si, regs->di);
}
@@ -118,45 +139,39 @@ static int addr_to_vsyscall_nr(unsigned long addr)
return nr;
}
-void dotraplinkage do_emulate_vsyscall(struct pt_regs *regs, long error_code)
+bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
{
struct task_struct *tsk;
unsigned long caller;
int vsyscall_nr;
long ret;
- local_irq_enable();
+ /*
+ * No point in checking CS -- the only way to get here is a user mode
+ * trap to a high address, which means that we're in 64-bit user code.
+ */
- if (!user_64bit_mode(regs)) {
- /*
- * If we trapped from kernel mode, we might as well OOPS now
- * instead of returning to some random address and OOPSing
- * then.
- */
- BUG_ON(!user_mode(regs));
+ WARN_ON_ONCE(address != regs->ip);
- /* Compat mode and non-compat 32-bit CS should both segfault. */
- warn_bad_vsyscall(KERN_WARNING, regs,
- "illegal int 0xcc from 32-bit mode");
- goto sigsegv;
+ if (vsyscall_mode == NONE) {
+ warn_bad_vsyscall(KERN_INFO, regs,
+ "vsyscall attempted with vsyscall=none");
+ return false;
}
- /*
- * x86-ism here: regs->ip points to the instruction after the int 0xcc,
- * and int 0xcc is two bytes long.
- */
- vsyscall_nr = addr_to_vsyscall_nr(regs->ip - 2);
+ vsyscall_nr = addr_to_vsyscall_nr(address);
trace_emulate_vsyscall(vsyscall_nr);
if (vsyscall_nr < 0) {
warn_bad_vsyscall(KERN_WARNING, regs,
- "illegal int 0xcc (exploit attempt?)");
+ "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround");
goto sigsegv;
}
if (get_user(caller, (unsigned long __user *)regs->sp) != 0) {
- warn_bad_vsyscall(KERN_WARNING, regs, "int 0xcc with bad stack (exploit attempt?)");
+ warn_bad_vsyscall(KERN_WARNING, regs,
+ "vsyscall with bad stack (exploit attempt?)");
goto sigsegv;
}
@@ -201,13 +216,11 @@ void dotraplinkage do_emulate_vsyscall(struct pt_regs *regs, long error_code)
regs->ip = caller;
regs->sp += 8;
- local_irq_disable();
- return;
+ return true;
sigsegv:
- regs->ip -= 2; /* The faulting instruction should be the int 0xcc. */
force_sig(SIGSEGV, current);
- local_irq_disable();
+ return true;
}
/*
@@ -255,15 +268,21 @@ cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg)
void __init map_vsyscall(void)
{
- extern char __vsyscall_0;
- unsigned long physaddr_page0 = __pa_symbol(&__vsyscall_0);
+ extern char __vsyscall_page;
+ unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
extern char __vvar_page;
unsigned long physaddr_vvar_page = __pa_symbol(&__vvar_page);
- /* Note that VSYSCALL_MAPPED_PAGES must agree with the code below. */
- __set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_page0, PAGE_KERNEL_VSYSCALL);
+ __set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_vsyscall,
+ vsyscall_mode == NATIVE
+ ? PAGE_KERNEL_VSYSCALL
+ : PAGE_KERNEL_VVAR);
+ BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_FIRST_PAGE) !=
+ (unsigned long)VSYSCALL_START);
+
__set_fixmap(VVAR_PAGE, physaddr_vvar_page, PAGE_KERNEL_VVAR);
- BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) != (unsigned long)VVAR_ADDRESS);
+ BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) !=
+ (unsigned long)VVAR_ADDRESS);
}
static int __init vsyscall_init(void)
diff --git a/arch/x86/kernel/vsyscall_emu_64.S b/arch/x86/kernel/vsyscall_emu_64.S
index ffa845e..c9596a9 100644
--- a/arch/x86/kernel/vsyscall_emu_64.S
+++ b/arch/x86/kernel/vsyscall_emu_64.S
@@ -7,21 +7,31 @@
*/
#include <linux/linkage.h>
+
#include <asm/irq_vectors.h>
+#include <asm/page_types.h>
+#include <asm/unistd_64.h>
+
+__PAGE_ALIGNED_DATA
+ .globl __vsyscall_page
+ .balign PAGE_SIZE, 0xcc
+ .type __vsyscall_page, @object
+__vsyscall_page:
+
+ mov $__NR_gettimeofday, %rax
+ syscall
+ ret
-/* The unused parts of the page are filled with 0xcc by the linker script. */
+ .balign 1024, 0xcc
+ mov $__NR_time, %rax
+ syscall
+ ret
-.section .vsyscall_0, "a"
-ENTRY(vsyscall_0)
- int $VSYSCALL_EMU_VECTOR
-END(vsyscall_0)
+ .balign 1024, 0xcc
+ mov $__NR_getcpu, %rax
+ syscall
+ ret
-.section .vsyscall_1, "a"
-ENTRY(vsyscall_1)
- int $VSYSCALL_EMU_VECTOR
-END(vsyscall_1)
+ .balign 4096, 0xcc
-.section .vsyscall_2, "a"
-ENTRY(vsyscall_2)
- int $VSYSCALL_EMU_VECTOR
-END(vsyscall_2)
+ .size __vsyscall_page, 4096
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index c1d0182..e58935c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -720,6 +720,18 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
if (is_errata100(regs, address))
return;
+#ifdef CONFIG_X86_64
+ /*
+ * Instruction fetch faults in the vsyscall page might need
+ * emulation.
+ */
+ if (unlikely((error_code & PF_INSTR) &&
+ ((address & ~0xfff) == VSYSCALL_START))) {
+ if (emulate_vsyscall(regs, address))
+ return;
+ }
+#endif
+
if (unlikely(show_unhandled_signals))
show_signal_msg(regs, error_code, address, tsk);
^ permalink raw reply related [flat|nested] 15+ messages in thread
* [tip:x86/vdso] x86-64: Rework vsyscall emulation and add vsyscall= parameter
2011-08-10 15:15 ` [PATCH 3/3] x86-64: Rework vsyscall emulation and add vsyscall= parameter Andy Lutomirski
2011-08-10 17:21 ` H. Peter Anvin
2011-08-11 0:02 ` [tip:x86/vdso] " tip-bot for Andy Lutomirski
@ 2011-08-11 0:31 ` tip-bot for Andy Lutomirski
2 siblings, 0 replies; 15+ messages in thread
From: tip-bot for Andy Lutomirski @ 2011-08-11 0:31 UTC (permalink / raw)
To: linux-tip-commits; +Cc: linux-kernel, hpa, mingo, luto, tglx, hpa
Commit-ID: 3ae36655b97a03fa1decf72f04078ef945647c1a
Gitweb: http://git.kernel.org/tip/3ae36655b97a03fa1decf72f04078ef945647c1a
Author: Andy Lutomirski <luto@mit.edu>
AuthorDate: Wed, 10 Aug 2011 11:15:32 -0400
Committer: H. Peter Anvin <hpa@linux.intel.com>
CommitDate: Wed, 10 Aug 2011 19:26:46 -0500
x86-64: Rework vsyscall emulation and add vsyscall= parameter
There are three choices:
vsyscall=native: Vsyscalls are native code that issues the
corresponding syscalls.
vsyscall=emulate (default): Vsyscalls are emulated by instruction
fault traps, tested in the bad_area path. The actual contents of
the vsyscall page is the same as the vsyscall=native case except
that it's marked NX. This way programs that make assumptions about
what the code in the page does will not be confused when they read
that code.
vsyscall=none: Trying to execute a vsyscall will segfault.
Signed-off-by: Andy Lutomirski <luto@mit.edu>
Link: http://lkml.kernel.org/r/8449fb3abf89851fd6b2260972666a6f82542284.1312988155.git.luto@mit.edu
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
Documentation/kernel-parameters.txt | 21 +++++++++
arch/x86/include/asm/irq_vectors.h | 4 --
arch/x86/include/asm/traps.h | 2 -
arch/x86/include/asm/vsyscall.h | 6 +++
arch/x86/kernel/entry_64.S | 1 -
arch/x86/kernel/traps.c | 6 ---
arch/x86/kernel/vmlinux.lds.S | 33 --------------
arch/x86/kernel/vsyscall_64.c | 79 +++++++++++++++++++++-------------
arch/x86/kernel/vsyscall_emu_64.S | 36 ++++++++++------
arch/x86/mm/fault.c | 12 +++++
10 files changed, 111 insertions(+), 89 deletions(-)
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index aa47be7..9cfd6bb 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2657,6 +2657,27 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
vmpoff= [KNL,S390] Perform z/VM CP command after power off.
Format: <command>
+ vsyscall= [X86-64]
+ Controls the behavior of vsyscalls (i.e. calls to
+ fixed addresses of 0xffffffffff600x00 from legacy
+ code). Most statically-linked binaries and older
+ versions of glibc use these calls. Because these
+ functions are at fixed addresses, they make nice
+ targets for exploits that can control RIP.
+
+ emulate [default] Vsyscalls turn into traps and are
+ emulated reasonably safely.
+
+ native Vsyscalls are native syscall instructions.
+ This is a little bit faster than trapping
+ and makes a few dynamic recompilers work
+ better than they would in emulation mode.
+ It also makes exploits much easier to write.
+
+ none Vsyscalls don't work at all. This makes
+ them quite hard to use for exploits but
+ might break your system.
+
vt.cur_default= [VT] Default cursor shape.
Format: 0xCCBBAA, where AA, BB, and CC are the same as
the parameters of the <Esc>[?A;B;Cc escape sequence;
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index a563c50..2c224e1 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -17,7 +17,6 @@
* Vectors 0 ... 31 : system traps and exceptions - hardcoded events
* Vectors 32 ... 127 : device interrupts
* Vector 128 : legacy int80 syscall interface
- * Vector 204 : legacy x86_64 vsyscall emulation
* Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 except 204 : device interrupts
* Vectors INVALIDATE_TLB_VECTOR_START ... 255 : special interrupts
*
@@ -51,9 +50,6 @@
#ifdef CONFIG_X86_32
# define SYSCALL_VECTOR 0x80
#endif
-#ifdef CONFIG_X86_64
-# define VSYSCALL_EMU_VECTOR 0xcc
-#endif
/*
* Vectors 0x30-0x3f are used for ISA interrupts.
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 2bae0a5..0012d09 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -40,7 +40,6 @@ asmlinkage void alignment_check(void);
asmlinkage void machine_check(void);
#endif /* CONFIG_X86_MCE */
asmlinkage void simd_coprocessor_error(void);
-asmlinkage void emulate_vsyscall(void);
dotraplinkage void do_divide_error(struct pt_regs *, long);
dotraplinkage void do_debug(struct pt_regs *, long);
@@ -67,7 +66,6 @@ dotraplinkage void do_alignment_check(struct pt_regs *, long);
dotraplinkage void do_machine_check(struct pt_regs *, long);
#endif
dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long);
-dotraplinkage void do_emulate_vsyscall(struct pt_regs *, long);
#ifdef CONFIG_X86_32
dotraplinkage void do_iret_error(struct pt_regs *, long);
#endif
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index 6010707..eaea1d3 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -27,6 +27,12 @@ extern struct timezone sys_tz;
extern void map_vsyscall(void);
+/*
+ * Called on instruction fetch fault in vsyscall page.
+ * Returns true if handled.
+ */
+extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address);
+
#endif /* __KERNEL__ */
#endif /* _ASM_X86_VSYSCALL_H */
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e949793..46792d9 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1123,7 +1123,6 @@ zeroentry spurious_interrupt_bug do_spurious_interrupt_bug
zeroentry coprocessor_error do_coprocessor_error
errorentry alignment_check do_alignment_check
zeroentry simd_coprocessor_error do_simd_coprocessor_error
-zeroentry emulate_vsyscall do_emulate_vsyscall
/* Reload gs selector with exception handling */
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index fbc097a..b9b6716 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -872,12 +872,6 @@ void __init trap_init(void)
set_bit(SYSCALL_VECTOR, used_vectors);
#endif
-#ifdef CONFIG_X86_64
- BUG_ON(test_bit(VSYSCALL_EMU_VECTOR, used_vectors));
- set_system_intr_gate(VSYSCALL_EMU_VECTOR, &emulate_vsyscall);
- set_bit(VSYSCALL_EMU_VECTOR, used_vectors);
-#endif
-
/*
* Should be a barrier for any external CPU state:
*/
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 8f3a265..0f703f1 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -71,7 +71,6 @@ PHDRS {
text PT_LOAD FLAGS(5); /* R_E */
data PT_LOAD FLAGS(6); /* RW_ */
#ifdef CONFIG_X86_64
- user PT_LOAD FLAGS(5); /* R_E */
#ifdef CONFIG_SMP
percpu PT_LOAD FLAGS(6); /* RW_ */
#endif
@@ -174,38 +173,6 @@ SECTIONS
. = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE);
-#define VSYSCALL_ADDR (-10*1024*1024)
-
-#define VLOAD_OFFSET (VSYSCALL_ADDR - __vsyscall_0 + LOAD_OFFSET)
-#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
-
-#define VVIRT_OFFSET (VSYSCALL_ADDR - __vsyscall_0)
-#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
-
- __vsyscall_0 = .;
-
- . = VSYSCALL_ADDR;
- .vsyscall : AT(VLOAD(.vsyscall)) {
- /* work around gold bug 13023 */
- __vsyscall_beginning_hack = .;
- *(.vsyscall_0)
-
- . = __vsyscall_beginning_hack + 1024;
- *(.vsyscall_1)
-
- . = __vsyscall_beginning_hack + 2048;
- *(.vsyscall_2)
-
- . = __vsyscall_beginning_hack + 4096; /* Pad the whole page. */
- } :user =0xcc
- . = ALIGN(__vsyscall_0 + PAGE_SIZE, PAGE_SIZE);
-
-#undef VSYSCALL_ADDR
-#undef VLOAD_OFFSET
-#undef VLOAD
-#undef VVIRT_OFFSET
-#undef VVIRT
-
#endif /* CONFIG_X86_64 */
/* Init code and data - will be freed after init */
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index bf8e9ff..18ae83d 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -56,6 +56,27 @@ DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) =
.lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock),
};
+static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE;
+
+static int __init vsyscall_setup(char *str)
+{
+ if (str) {
+ if (!strcmp("emulate", str))
+ vsyscall_mode = EMULATE;
+ else if (!strcmp("native", str))
+ vsyscall_mode = NATIVE;
+ else if (!strcmp("none", str))
+ vsyscall_mode = NONE;
+ else
+ return -EINVAL;
+
+ return 0;
+ }
+
+ return -EINVAL;
+}
+early_param("vsyscall", vsyscall_setup);
+
void update_vsyscall_tz(void)
{
unsigned long flags;
@@ -100,7 +121,7 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
printk("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
level, tsk->comm, task_pid_nr(tsk),
- message, regs->ip - 2, regs->cs,
+ message, regs->ip, regs->cs,
regs->sp, regs->ax, regs->si, regs->di);
}
@@ -118,45 +139,39 @@ static int addr_to_vsyscall_nr(unsigned long addr)
return nr;
}
-void dotraplinkage do_emulate_vsyscall(struct pt_regs *regs, long error_code)
+bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
{
struct task_struct *tsk;
unsigned long caller;
int vsyscall_nr;
long ret;
- local_irq_enable();
+ /*
+ * No point in checking CS -- the only way to get here is a user mode
+ * trap to a high address, which means that we're in 64-bit user code.
+ */
- if (!user_64bit_mode(regs)) {
- /*
- * If we trapped from kernel mode, we might as well OOPS now
- * instead of returning to some random address and OOPSing
- * then.
- */
- BUG_ON(!user_mode(regs));
+ WARN_ON_ONCE(address != regs->ip);
- /* Compat mode and non-compat 32-bit CS should both segfault. */
- warn_bad_vsyscall(KERN_WARNING, regs,
- "illegal int 0xcc from 32-bit mode");
- goto sigsegv;
+ if (vsyscall_mode == NONE) {
+ warn_bad_vsyscall(KERN_INFO, regs,
+ "vsyscall attempted with vsyscall=none");
+ return false;
}
- /*
- * x86-ism here: regs->ip points to the instruction after the int 0xcc,
- * and int 0xcc is two bytes long.
- */
- vsyscall_nr = addr_to_vsyscall_nr(regs->ip - 2);
+ vsyscall_nr = addr_to_vsyscall_nr(address);
trace_emulate_vsyscall(vsyscall_nr);
if (vsyscall_nr < 0) {
warn_bad_vsyscall(KERN_WARNING, regs,
- "illegal int 0xcc (exploit attempt?)");
+ "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround");
goto sigsegv;
}
if (get_user(caller, (unsigned long __user *)regs->sp) != 0) {
- warn_bad_vsyscall(KERN_WARNING, regs, "int 0xcc with bad stack (exploit attempt?)");
+ warn_bad_vsyscall(KERN_WARNING, regs,
+ "vsyscall with bad stack (exploit attempt?)");
goto sigsegv;
}
@@ -201,13 +216,11 @@ void dotraplinkage do_emulate_vsyscall(struct pt_regs *regs, long error_code)
regs->ip = caller;
regs->sp += 8;
- local_irq_disable();
- return;
+ return true;
sigsegv:
- regs->ip -= 2; /* The faulting instruction should be the int 0xcc. */
force_sig(SIGSEGV, current);
- local_irq_disable();
+ return true;
}
/*
@@ -255,15 +268,21 @@ cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg)
void __init map_vsyscall(void)
{
- extern char __vsyscall_0;
- unsigned long physaddr_page0 = __pa_symbol(&__vsyscall_0);
+ extern char __vsyscall_page;
+ unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
extern char __vvar_page;
unsigned long physaddr_vvar_page = __pa_symbol(&__vvar_page);
- /* Note that VSYSCALL_MAPPED_PAGES must agree with the code below. */
- __set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_page0, PAGE_KERNEL_VSYSCALL);
+ __set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_vsyscall,
+ vsyscall_mode == NATIVE
+ ? PAGE_KERNEL_VSYSCALL
+ : PAGE_KERNEL_VVAR);
+ BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_FIRST_PAGE) !=
+ (unsigned long)VSYSCALL_START);
+
__set_fixmap(VVAR_PAGE, physaddr_vvar_page, PAGE_KERNEL_VVAR);
- BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) != (unsigned long)VVAR_ADDRESS);
+ BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) !=
+ (unsigned long)VVAR_ADDRESS);
}
static int __init vsyscall_init(void)
diff --git a/arch/x86/kernel/vsyscall_emu_64.S b/arch/x86/kernel/vsyscall_emu_64.S
index ffa845e..c9596a9 100644
--- a/arch/x86/kernel/vsyscall_emu_64.S
+++ b/arch/x86/kernel/vsyscall_emu_64.S
@@ -7,21 +7,31 @@
*/
#include <linux/linkage.h>
+
#include <asm/irq_vectors.h>
+#include <asm/page_types.h>
+#include <asm/unistd_64.h>
+
+__PAGE_ALIGNED_DATA
+ .globl __vsyscall_page
+ .balign PAGE_SIZE, 0xcc
+ .type __vsyscall_page, @object
+__vsyscall_page:
+
+ mov $__NR_gettimeofday, %rax
+ syscall
+ ret
-/* The unused parts of the page are filled with 0xcc by the linker script. */
+ .balign 1024, 0xcc
+ mov $__NR_time, %rax
+ syscall
+ ret
-.section .vsyscall_0, "a"
-ENTRY(vsyscall_0)
- int $VSYSCALL_EMU_VECTOR
-END(vsyscall_0)
+ .balign 1024, 0xcc
+ mov $__NR_getcpu, %rax
+ syscall
+ ret
-.section .vsyscall_1, "a"
-ENTRY(vsyscall_1)
- int $VSYSCALL_EMU_VECTOR
-END(vsyscall_1)
+ .balign 4096, 0xcc
-.section .vsyscall_2, "a"
-ENTRY(vsyscall_2)
- int $VSYSCALL_EMU_VECTOR
-END(vsyscall_2)
+ .size __vsyscall_page, 4096
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index c1d0182..e58935c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -720,6 +720,18 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
if (is_errata100(regs, address))
return;
+#ifdef CONFIG_X86_64
+ /*
+ * Instruction fetch faults in the vsyscall page might need
+ * emulation.
+ */
+ if (unlikely((error_code & PF_INSTR) &&
+ ((address & ~0xfff) == VSYSCALL_START))) {
+ if (emulate_vsyscall(regs, address))
+ return;
+ }
+#endif
+
if (unlikely(show_unhandled_signals))
show_signal_msg(regs, error_code, address, tsk);
^ permalink raw reply related [flat|nested] 15+ messages in thread