[PATCH v2 0/3] x86_64: Tidy up vsyscall emulation and make it optional

[PATCH v2 0/3] x86_64: Tidy up vsyscall emulation and make it optional

[Andy Lutomirski]

Now that arch/x86/kernel/vsyscall_64.c contains only vsyscall
emulation code, clean it up and make it optional.

Patch 1 makes vsyscall=none work be a bit more self-consistent: it
actually removes the fake vsyscall page instead of just segfaulting
anyone who tries to use it.

Patch 2 is pure cosmetic cleanup.

Patch 3 is the meat: it lets vsyscall emulation be configured out.
The config option to disable it is hidden under CONFIG_EXPERT, since
it will break legacy code.

Note that, last I checked, current userspace is unlikely to work if
the vDSO *and* vsyscalls are off.  Take it up with the glibc
maintainers.

This applies on top of tip/x86/vdso.

Changes from v1:
 - Added Josh's Reviewed-by
 - Fixup up Xen bits in patch 3

Andy Lutomirski (3):
  x86_64,vsyscall: Turn vsyscalls all the way off when vsyscall=none
  x86_64,vsyscall: Rewrite comment and clean up headers in vsyscall code
  x86_64,vsyscall: Make vsyscall emulation configurable

 arch/x86/Kconfig                | 18 ++++++++++++
 arch/x86/include/asm/fixmap.h   |  2 ++
 arch/x86/include/asm/page_64.h  |  4 ++-
 arch/x86/include/asm/vsyscall.h |  8 +++++
 arch/x86/kernel/Makefile        |  3 +-
 arch/x86/kernel/setup.c         |  2 --
 arch/x86/kernel/vsyscall_64.c   | 65 +++++++++++++++++------------------------
 arch/x86/xen/mmu.c              |  6 ++--
 8 files changed, 63 insertions(+), 45 deletions(-)

-- 
1.9.3

[PATCH v2 1/3] x86_64,vsyscall: Turn vsyscalls all the way off when vsyscall=none

[Andy Lutomirski]

I see no point in having an unusable read-only page sitting at
0xffffffffff600000 when vsyscall=none.  Instead, skip mapping it and
remove it from /proc/PID/maps.

I kept the ratelimited warning when programs try to use a vsyscall
in this mode, since it may help admins avoid confusion.

Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
---
 arch/x86/kernel/vsyscall_64.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 419e83b58436..2d912629c96e 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -307,6 +307,8 @@ struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 	if (!mm || mm->context.ia32_compat)
 		return NULL;
 #endif
+	if (vsyscall_mode == NONE)
+		return NULL;
 	return &gate_vma;
 }
 
@@ -327,7 +329,7 @@ int in_gate_area(struct mm_struct *mm, unsigned long addr)
  */
 int in_gate_area_no_mm(unsigned long addr)
 {
-	return (addr & PAGE_MASK) == VSYSCALL_ADDR;
+	return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR;
 }
 
 void __init map_vsyscall(void)
@@ -335,10 +337,12 @@ void __init map_vsyscall(void)
 	extern char __vsyscall_page;
 	unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
 
-	__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
-		     vsyscall_mode == NATIVE
-		     ? PAGE_KERNEL_VSYSCALL
-		     : PAGE_KERNEL_VVAR);
+	if (vsyscall_mode != NONE)
+		__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
+			     vsyscall_mode == NATIVE
+			     ? PAGE_KERNEL_VSYSCALL
+			     : PAGE_KERNEL_VVAR);
+
 	BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
 		     (unsigned long)VSYSCALL_ADDR);
 }
-- 
1.9.3

[PATCH v2 2/3] x86_64,vsyscall: Rewrite comment and clean up headers in vsyscall code

[Andy Lutomirski]

vsyscall_64.c is just vsyscall emulation.  Tidy it up accordingly.

If my comment editing offends anyone, let me know and I can fix it.

Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
---
 arch/x86/kernel/vsyscall_64.c | 51 +++++++++++++++----------------------------
 1 file changed, 18 insertions(+), 33 deletions(-)

diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 2d912629c96e..ee622f8183f3 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -1,52 +1,37 @@
 /*
- *  Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
- *  Copyright 2003 Andi Kleen, SuSE Labs.
+ * Mostly copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>
  *
- *  [ NOTE: this mechanism is now deprecated in favor of the vDSO. ]
+ * This file implements vsyscall emulation.  vsyscalls are a legacy ABI:
+ * userspace can request certain kernel services by calling fixed
+ * addresses.  This concept is problematic:
  *
- *  Thanks to hpa@transmeta.com for some useful hint.
- *  Special thanks to Ingo Molnar for his early experience with
- *  a different vsyscall implementation for Linux/IA32 and for the name.
+ * - It interferes with ASLR.
+ * - It's awkward to write code that lives in kernel addresses but is
+ *   callable by userspace at fixed addresses.
+ * - The whole concept is impossible for 32-bit compat userspace.
+ * - UML cannot easily virtualize a vsyscall.
  *
- *  vsyscall 1 is located at -10Mbyte, vsyscall 2 is located
- *  at virtual address -10Mbyte+1024bytes etc... There are at max 4
- *  vsyscalls. One vsyscall can reserve more than 1 slot to avoid
- *  jumping out of line if necessary. We cannot add more with this
- *  mechanism because older kernels won't return -ENOSYS.
+ * As of mid-2014, I believe that there is no new userspace code that
+ * will use a vsyscall if the vDSO is present.  I hope that there will
+ * soon be no new userspace code that will ever use a vsyscall.
  *
- *  Note: the concept clashes with user mode linux.  UML users should
- *  use the vDSO.
+ * The code in this file emulates vsyscalls when notified of a page
+ * fault to a vsyscall address.
+ *
+ * The original version of this code is:
+ * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
+ * Copyright 2003 Andi Kleen, SuSE Labs.
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/time.h>
-#include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/timer.h>
-#include <linux/seqlock.h>
-#include <linux/jiffies.h>
-#include <linux/sysctl.h>
-#include <linux/topology.h>
-#include <linux/timekeeper_internal.h>
-#include <linux/getcpu.h>
-#include <linux/cpu.h>
-#include <linux/smp.h>
-#include <linux/notifier.h>
 #include <linux/syscalls.h>
 #include <linux/ratelimit.h>
 
 #include <asm/vsyscall.h>
-#include <asm/pgtable.h>
-#include <asm/compat.h>
-#include <asm/page.h>
 #include <asm/unistd.h>
 #include <asm/fixmap.h>
-#include <asm/errno.h>
-#include <asm/io.h>
-#include <asm/segment.h>
-#include <asm/desc.h>
-#include <asm/topology.h>
 #include <asm/traps.h>
 
 #define CREATE_TRACE_POINTS
-- 
1.9.3

[PATCH v2 3/3] x86_64,vsyscall: Make vsyscall emulation configurable

[Andy Lutomirski]

This adds CONFIG_X86_VSYSCALL_EMULATION, guarded by CONFIG_EXPERT.
Turning it off completely disables vsyscall emulation, saving ~3.5k
for vsyscall_64.c, 4k for vsyscall_emu_64.S (the fake vsyscall
page), some tiny amount of core mm code that supports a gate area,
and possibly 4k for a wasted pagetable.  The latter is because the
vsyscall addresses are misaligned and fit poorly in the fixmap.

Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
---
 arch/x86/Kconfig                | 18 ++++++++++++++++++
 arch/x86/include/asm/fixmap.h   |  2 ++
 arch/x86/include/asm/page_64.h  |  4 +++-
 arch/x86/include/asm/vsyscall.h |  8 ++++++++
 arch/x86/kernel/Makefile        |  3 +--
 arch/x86/kernel/setup.c         |  2 --
 arch/x86/xen/mmu.c              |  6 ++++--
 7 files changed, 36 insertions(+), 7 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f2327e88e07c..cd10436d7d1c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -984,6 +984,24 @@ config X86_ESPFIX64
 	def_bool y
 	depends on X86_16BIT && X86_64
 
+config X86_VSYSCALL_EMULATION
+       bool "Enable vsyscall emulation" if EXPERT
+       default y
+       depends on X86_64
+       ---help---
+	 This enables emulation of the legacy vsyscall page.  Disabling
+	 it is roughly equivalent to booting with vsyscall=none, except
+	 that it will also disable the helpful warning if a program
+	 tries to use a vsyscall.  With this option set to N, offending
+	 programs will just segfault, citing addresses of the form
+	 0xffffffffff600?00.
+
+	 This option is required by many programs built before 2013, and
+	 care should be used even with newer programs if set to N.
+
+	 Disabling this option saves about 7K of kernel size and
+	 possibly 4K of additional runtime pagetable memory.
+
 config TOSHIBA
 	tristate "Toshiba Laptop support"
 	depends on X86_32
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index ffb1733ac91f..d8d5bcb2a0b5 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -69,7 +69,9 @@ enum fixed_addresses {
 #ifdef CONFIG_X86_32
 	FIX_HOLE,
 #else
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 	VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT,
+#endif
 #ifdef CONFIG_PARAVIRT_CLOCK
 	PVCLOCK_FIXMAP_BEGIN,
 	PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1,
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index f408caf73430..b3bebf9e5746 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -39,6 +39,8 @@ void copy_page(void *to, void *from);
 
 #endif	/* !__ASSEMBLY__ */
 
-#define __HAVE_ARCH_GATE_AREA 1
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
+# define __HAVE_ARCH_GATE_AREA 1
+#endif
 
 #endif /* _ASM_X86_PAGE_64_H */
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index 34f7d8857542..6ba66ee79710 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -4,6 +4,7 @@
 #include <linux/seqlock.h>
 #include <uapi/asm/vsyscall.h>
 
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 extern void map_vsyscall(void);
 
 /*
@@ -11,5 +12,12 @@ extern void map_vsyscall(void);
  * Returns true if handled.
  */
 extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address);
+#else
+static inline void map_vsyscall(void) {}
+static inline bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
+{
+	return false;
+}
+#endif
 
 #endif /* _ASM_X86_VSYSCALL_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 8f1e77440b2b..5d4502c8b983 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -28,8 +28,7 @@ obj-$(CONFIG_X86_32)	+= i386_ksyms_32.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-$(CONFIG_X86_64)	+= mcount_64.o
 obj-y			+= syscall_$(BITS).o vsyscall_gtod.o
-obj-$(CONFIG_X86_64)	+= vsyscall_64.o
-obj-$(CONFIG_X86_64)	+= vsyscall_emu_64.o
+obj-$(CONFIG_X86_VSYSCALL_EMULATION)	+= vsyscall_64.o vsyscall_emu_64.o
 obj-$(CONFIG_X86_ESPFIX64)	+= espfix_64.o
 obj-$(CONFIG_SYSFS)	+= ksysfs.o
 obj-y			+= bootflag.o e820.o
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 235cfd39e0d7..59a6f884fdad 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1190,9 +1190,7 @@ void __init setup_arch(char **cmdline_p)
 
 	tboot_probe();
 
-#ifdef CONFIG_X86_64
 	map_vsyscall();
-#endif
 
 	generic_apic_probe();
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index a8a1a3d08d4d..8906cf0e536f 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1457,8 +1457,10 @@ static int xen_pgd_alloc(struct mm_struct *mm)
 		page->private = (unsigned long)user_pgd;
 
 		if (user_pgd != NULL) {
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 			user_pgd[pgd_index(VSYSCALL_ADDR)] =
 				__pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
+#endif
 			ret = 0;
 		}
 
@@ -2021,7 +2023,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 # ifdef CONFIG_HIGHMEM
 	case FIX_KMAP_BEGIN ... FIX_KMAP_END:
 # endif
-#else
+#elif defined(CONFIG_X86_VSYSCALL_EMULATION)
 	case VSYSCALL_PAGE:
 #endif
 	case FIX_TEXT_POKE0:
@@ -2060,7 +2062,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 
 	__native_set_fixmap(idx, pte);
 
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 	/* Replicate changes to map the vsyscall page into the user
 	   pagetable vsyscall mapping. */
 	if (idx == VSYSCALL_PAGE) {
-- 
1.9.3

Re: [PATCH v2 2/3] x86_64,vsyscall: Rewrite comment and clean up headers in vsyscall code

[Thomas Gleixner]

On Wed, 29 Oct 2014, Andy Lutomirski wrote:

> vsyscall_64.c is just vsyscall emulation.  Tidy it up accordingly.
> 
> If my comment editing offends anyone, let me know and I can fix it.
> 
> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
> Signed-off-by: Andy Lutomirski <luto@amacapital.net>
> ---
>  arch/x86/kernel/vsyscall_64.c | 51 +++++++++++++++----------------------------
>  1 file changed, 18 insertions(+), 33 deletions(-)
> 
> diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
> index 2d912629c96e..ee622f8183f3 100644
> --- a/arch/x86/kernel/vsyscall_64.c
> +++ b/arch/x86/kernel/vsyscall_64.c
> @@ -1,52 +1,37 @@
>  /*
> - *  Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
> - *  Copyright 2003 Andi Kleen, SuSE Labs.
> + * Mostly copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>

We usualy leave the old copyright notices around even if the code
which is related to them has been removed more or less completely.

So I change this to:

/*
 * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>
 *
 * Based on the original implementation:
 *  Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
 *  Copyright 2003 Andi Kleen, SuSE Labs.

and apply the whole lot.

Thanks,

	tglx

Re: [PATCH v2 2/3] x86_64,vsyscall: Rewrite comment and clean up headers in vsyscall code

[Andy Lutomirski]

On Mon, Nov 3, 2014 at 12:31 PM, Thomas Gleixner <tglx@linutronix.de> wrote:
> On Wed, 29 Oct 2014, Andy Lutomirski wrote:
>
>> vsyscall_64.c is just vsyscall emulation.  Tidy it up accordingly.
>>
>> If my comment editing offends anyone, let me know and I can fix it.
>>
>> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
>> Signed-off-by: Andy Lutomirski <luto@amacapital.net>
>> ---
>>  arch/x86/kernel/vsyscall_64.c | 51 +++++++++++++++----------------------------
>>  1 file changed, 18 insertions(+), 33 deletions(-)
>>
>> diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
>> index 2d912629c96e..ee622f8183f3 100644
>> --- a/arch/x86/kernel/vsyscall_64.c
>> +++ b/arch/x86/kernel/vsyscall_64.c
>> @@ -1,52 +1,37 @@
>>  /*
>> - *  Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
>> - *  Copyright 2003 Andi Kleen, SuSE Labs.
>> + * Mostly copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>
>
> We usualy leave the old copyright notices around even if the code
> which is related to them has been removed more or less completely.
>
> So I change this to:
>
> /*
>  * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>
>  *
>  * Based on the original implementation:
>  *  Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
>  *  Copyright 2003 Andi Kleen, SuSE Labs.
>
> and apply the whole lot.

Would it make more sense to move those copyright notices to
arch/x86/vdso/vma.c?  That's where most of the code ended up.

--Andy

Re: [PATCH v2 2/3] x86_64,vsyscall: Rewrite comment and clean up headers in vsyscall code

[Thomas Gleixner]

On Mon, 3 Nov 2014, Andy Lutomirski wrote:
> On Mon, Nov 3, 2014 at 12:31 PM, Thomas Gleixner <tglx@linutronix.de> wrote:
> > On Wed, 29 Oct 2014, Andy Lutomirski wrote:
> >
> >> vsyscall_64.c is just vsyscall emulation.  Tidy it up accordingly.
> >>
> >> If my comment editing offends anyone, let me know and I can fix it.
> >>
> >> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
> >> Signed-off-by: Andy Lutomirski <luto@amacapital.net>
> >> ---
> >>  arch/x86/kernel/vsyscall_64.c | 51 +++++++++++++++----------------------------
> >>  1 file changed, 18 insertions(+), 33 deletions(-)
> >>
> >> diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
> >> index 2d912629c96e..ee622f8183f3 100644
> >> --- a/arch/x86/kernel/vsyscall_64.c
> >> +++ b/arch/x86/kernel/vsyscall_64.c
> >> @@ -1,52 +1,37 @@
> >>  /*
> >> - *  Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
> >> - *  Copyright 2003 Andi Kleen, SuSE Labs.
> >> + * Mostly copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>
> >
> > We usualy leave the old copyright notices around even if the code
> > which is related to them has been removed more or less completely.
> >
> > So I change this to:
> >
> > /*
> >  * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>
> >  *
> >  * Based on the original implementation:
> >  *  Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
> >  *  Copyright 2003 Andi Kleen, SuSE Labs.
> >
> > and apply the whole lot.
> 
> Would it make more sense to move those copyright notices to
> arch/x86/vdso/vma.c?  That's where most of the code ended up.

That has already a notice from Andi and I cant figure out what parts
of that have been written by Andrea. We'll worry about that when we
remove vsyscall_64.c. Until then the git history will be our friend.

Thanks,

	tglx

Re: [PATCH v2 2/3] x86_64,vsyscall: Rewrite comment and clean up headers in vsyscall code

[Andy Lutomirski]

On Mon, Nov 3, 2014 at 12:41 PM, Thomas Gleixner <tglx@linutronix.de> wrote:
> On Mon, 3 Nov 2014, Andy Lutomirski wrote:
>> On Mon, Nov 3, 2014 at 12:31 PM, Thomas Gleixner <tglx@linutronix.de> wrote:
>> > On Wed, 29 Oct 2014, Andy Lutomirski wrote:
>> >
>> >> vsyscall_64.c is just vsyscall emulation.  Tidy it up accordingly.
>> >>
>> >> If my comment editing offends anyone, let me know and I can fix it.
>> >>
>> >> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
>> >> Signed-off-by: Andy Lutomirski <luto@amacapital.net>
>> >> ---
>> >>  arch/x86/kernel/vsyscall_64.c | 51 +++++++++++++++----------------------------
>> >>  1 file changed, 18 insertions(+), 33 deletions(-)
>> >>
>> >> diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
>> >> index 2d912629c96e..ee622f8183f3 100644
>> >> --- a/arch/x86/kernel/vsyscall_64.c
>> >> +++ b/arch/x86/kernel/vsyscall_64.c
>> >> @@ -1,52 +1,37 @@
>> >>  /*
>> >> - *  Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
>> >> - *  Copyright 2003 Andi Kleen, SuSE Labs.
>> >> + * Mostly copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>
>> >
>> > We usualy leave the old copyright notices around even if the code
>> > which is related to them has been removed more or less completely.
>> >
>> > So I change this to:
>> >
>> > /*
>> >  * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>
>> >  *
>> >  * Based on the original implementation:
>> >  *  Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
>> >  *  Copyright 2003 Andi Kleen, SuSE Labs.
>> >
>> > and apply the whole lot.
>>
>> Would it make more sense to move those copyright notices to
>> arch/x86/vdso/vma.c?  That's where most of the code ended up.
>
> That has already a notice from Andi and I cant figure out what parts
> of that have been written by Andrea. We'll worry about that when we
> remove vsyscall_64.c. Until then the git history will be our friend.

Works for me.

--Andy

[tip:x86/vdso] x86_64, vsyscall: Turn vsyscalls all the way off when vsyscall==none

[tip-bot for Andy Lutomirski]

Commit-ID:  87983c66bc02c9cd8e4a42e7924435145d52bb13
Gitweb:     http://git.kernel.org/tip/87983c66bc02c9cd8e4a42e7924435145d52bb13
Author:     Andy Lutomirski <luto@amacapital.net>
AuthorDate: Wed, 29 Oct 2014 14:33:45 -0700
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Mon, 3 Nov 2014 21:44:57 +0100

x86_64, vsyscall: Turn vsyscalls all the way off when vsyscall==none

I see no point in having an unusable read-only page sitting at
0xffffffffff600000 when vsyscall=none. Instead, skip mapping it and
remove it from /proc/PID/maps.

I kept the ratelimited warning when programs try to use a vsyscall
in this mode, since it may help admins avoid confusion.

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Link: http://lkml.kernel.org/r/0dddbadc1d4e3bfbaf887938ff42afc97a7cc1f2.1414618407.git.luto@amacapital.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/vsyscall_64.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 419e83b..2d91262 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -307,6 +307,8 @@ struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 	if (!mm || mm->context.ia32_compat)
 		return NULL;
 #endif
+	if (vsyscall_mode == NONE)
+		return NULL;
 	return &gate_vma;
 }
 
@@ -327,7 +329,7 @@ int in_gate_area(struct mm_struct *mm, unsigned long addr)
  */
 int in_gate_area_no_mm(unsigned long addr)
 {
-	return (addr & PAGE_MASK) == VSYSCALL_ADDR;
+	return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR;
 }
 
 void __init map_vsyscall(void)
@@ -335,10 +337,12 @@ void __init map_vsyscall(void)
 	extern char __vsyscall_page;
 	unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
 
-	__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
-		     vsyscall_mode == NATIVE
-		     ? PAGE_KERNEL_VSYSCALL
-		     : PAGE_KERNEL_VVAR);
+	if (vsyscall_mode != NONE)
+		__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
+			     vsyscall_mode == NATIVE
+			     ? PAGE_KERNEL_VSYSCALL
+			     : PAGE_KERNEL_VVAR);
+
 	BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
 		     (unsigned long)VSYSCALL_ADDR);
 }

[tip:x86/vdso] x86_64, vsyscall: Rewrite comment and clean up headers in vsyscall code

[tip-bot for Andy Lutomirski]

Commit-ID:  95c46b56922409ed8838b3b420b11cfebb8c6c88
Gitweb:     http://git.kernel.org/tip/95c46b56922409ed8838b3b420b11cfebb8c6c88
Author:     Andy Lutomirski <luto@amacapital.net>
AuthorDate: Wed, 29 Oct 2014 14:33:46 -0700
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Mon, 3 Nov 2014 21:44:57 +0100

x86_64, vsyscall: Rewrite comment and clean up headers in vsyscall code

vsyscall_64.c is just vsyscall emulation. Tidy it up accordingly.

[ tglx: Preserved the original copyright notices ]

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Link: http://lkml.kernel.org/r/9c448d5643d0fdb618f8cde9a54c21d2bcd486ce.1414618407.git.luto@amacapital.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/vsyscall_64.c | 50 ++++++++++++++++---------------------------
 1 file changed, 18 insertions(+), 32 deletions(-)

diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 2d91262..7d9eb4b 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -1,52 +1,38 @@
 /*
+ * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>
+ *
+ * Based on the original implementation which is:
  *  Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
  *  Copyright 2003 Andi Kleen, SuSE Labs.
  *
- *  [ NOTE: this mechanism is now deprecated in favor of the vDSO. ]
+ *  Parts of the original code have been moved to arch/x86/vdso/vma.c
+ *
+ * This file implements vsyscall emulation.  vsyscalls are a legacy ABI:
+ * Userspace can request certain kernel services by calling fixed
+ * addresses.  This concept is problematic:
  *
- *  Thanks to hpa@transmeta.com for some useful hint.
- *  Special thanks to Ingo Molnar for his early experience with
- *  a different vsyscall implementation for Linux/IA32 and for the name.
+ * - It interferes with ASLR.
+ * - It's awkward to write code that lives in kernel addresses but is
+ *   callable by userspace at fixed addresses.
+ * - The whole concept is impossible for 32-bit compat userspace.
+ * - UML cannot easily virtualize a vsyscall.
  *
- *  vsyscall 1 is located at -10Mbyte, vsyscall 2 is located
- *  at virtual address -10Mbyte+1024bytes etc... There are at max 4
- *  vsyscalls. One vsyscall can reserve more than 1 slot to avoid
- *  jumping out of line if necessary. We cannot add more with this
- *  mechanism because older kernels won't return -ENOSYS.
+ * As of mid-2014, I believe that there is no new userspace code that
+ * will use a vsyscall if the vDSO is present.  I hope that there will
+ * soon be no new userspace code that will ever use a vsyscall.
  *
- *  Note: the concept clashes with user mode linux.  UML users should
- *  use the vDSO.
+ * The code in this file emulates vsyscalls when notified of a page
+ * fault to a vsyscall address.
  */
 
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/time.h>
-#include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/timer.h>
-#include <linux/seqlock.h>
-#include <linux/jiffies.h>
-#include <linux/sysctl.h>
-#include <linux/topology.h>
-#include <linux/timekeeper_internal.h>
-#include <linux/getcpu.h>
-#include <linux/cpu.h>
-#include <linux/smp.h>
-#include <linux/notifier.h>
 #include <linux/syscalls.h>
 #include <linux/ratelimit.h>
 
 #include <asm/vsyscall.h>
-#include <asm/pgtable.h>
-#include <asm/compat.h>
-#include <asm/page.h>
 #include <asm/unistd.h>
 #include <asm/fixmap.h>
-#include <asm/errno.h>
-#include <asm/io.h>
-#include <asm/segment.h>
-#include <asm/desc.h>
-#include <asm/topology.h>
 #include <asm/traps.h>
 
 #define CREATE_TRACE_POINTS

[tip:x86/vdso] x86_64,vsyscall: Make vsyscall emulation configurable

[tip-bot for Andy Lutomirski]

Commit-ID:  1ad83c858c7d4ea210429142c99a1548e6715a35
Gitweb:     http://git.kernel.org/tip/1ad83c858c7d4ea210429142c99a1548e6715a35
Author:     Andy Lutomirski <luto@amacapital.net>
AuthorDate: Wed, 29 Oct 2014 14:33:47 -0700
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Mon, 3 Nov 2014 21:44:57 +0100

x86_64,vsyscall: Make vsyscall emulation configurable

This adds CONFIG_X86_VSYSCALL_EMULATION, guarded by CONFIG_EXPERT.
Turning it off completely disables vsyscall emulation, saving ~3.5k
for vsyscall_64.c, 4k for vsyscall_emu_64.S (the fake vsyscall
page), some tiny amount of core mm code that supports a gate area,
and possibly 4k for a wasted pagetable.  The latter is because the
vsyscall addresses are misaligned and fit poorly in the fixmap.

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Link: http://lkml.kernel.org/r/406db88b8dd5f0cbbf38216d11be34bbb43c7eae.1414618407.git.luto@amacapital.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/Kconfig                | 18 ++++++++++++++++++
 arch/x86/include/asm/fixmap.h   |  2 ++
 arch/x86/include/asm/page_64.h  |  4 +++-
 arch/x86/include/asm/vsyscall.h |  8 ++++++++
 arch/x86/kernel/Makefile        |  3 +--
 arch/x86/kernel/setup.c         |  2 --
 arch/x86/xen/mmu.c              |  6 ++++--
 7 files changed, 36 insertions(+), 7 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f2327e8..cd10436 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -984,6 +984,24 @@ config X86_ESPFIX64
 	def_bool y
 	depends on X86_16BIT && X86_64
 
+config X86_VSYSCALL_EMULATION
+       bool "Enable vsyscall emulation" if EXPERT
+       default y
+       depends on X86_64
+       ---help---
+	 This enables emulation of the legacy vsyscall page.  Disabling
+	 it is roughly equivalent to booting with vsyscall=none, except
+	 that it will also disable the helpful warning if a program
+	 tries to use a vsyscall.  With this option set to N, offending
+	 programs will just segfault, citing addresses of the form
+	 0xffffffffff600?00.
+
+	 This option is required by many programs built before 2013, and
+	 care should be used even with newer programs if set to N.
+
+	 Disabling this option saves about 7K of kernel size and
+	 possibly 4K of additional runtime pagetable memory.
+
 config TOSHIBA
 	tristate "Toshiba Laptop support"
 	depends on X86_32
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index ffb1733..d8d5bcb 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -69,7 +69,9 @@ enum fixed_addresses {
 #ifdef CONFIG_X86_32
 	FIX_HOLE,
 #else
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 	VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT,
+#endif
 #ifdef CONFIG_PARAVIRT_CLOCK
 	PVCLOCK_FIXMAP_BEGIN,
 	PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1,
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index f408caf..b3bebf9 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -39,6 +39,8 @@ void copy_page(void *to, void *from);
 
 #endif	/* !__ASSEMBLY__ */
 
-#define __HAVE_ARCH_GATE_AREA 1
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
+# define __HAVE_ARCH_GATE_AREA 1
+#endif
 
 #endif /* _ASM_X86_PAGE_64_H */
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index 34f7d88..6ba66ee 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -4,6 +4,7 @@
 #include <linux/seqlock.h>
 #include <uapi/asm/vsyscall.h>
 
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 extern void map_vsyscall(void);
 
 /*
@@ -11,5 +12,12 @@ extern void map_vsyscall(void);
  * Returns true if handled.
  */
 extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address);
+#else
+static inline void map_vsyscall(void) {}
+static inline bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
+{
+	return false;
+}
+#endif
 
 #endif /* _ASM_X86_VSYSCALL_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 8f1e774..5d4502c 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -28,8 +28,7 @@ obj-$(CONFIG_X86_32)	+= i386_ksyms_32.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-$(CONFIG_X86_64)	+= mcount_64.o
 obj-y			+= syscall_$(BITS).o vsyscall_gtod.o
-obj-$(CONFIG_X86_64)	+= vsyscall_64.o
-obj-$(CONFIG_X86_64)	+= vsyscall_emu_64.o
+obj-$(CONFIG_X86_VSYSCALL_EMULATION)	+= vsyscall_64.o vsyscall_emu_64.o
 obj-$(CONFIG_X86_ESPFIX64)	+= espfix_64.o
 obj-$(CONFIG_SYSFS)	+= ksysfs.o
 obj-y			+= bootflag.o e820.o
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 235cfd3..59a6f884 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1190,9 +1190,7 @@ void __init setup_arch(char **cmdline_p)
 
 	tboot_probe();
 
-#ifdef CONFIG_X86_64
 	map_vsyscall();
-#endif
 
 	generic_apic_probe();
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index a8a1a3d..8906cf0 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1457,8 +1457,10 @@ static int xen_pgd_alloc(struct mm_struct *mm)
 		page->private = (unsigned long)user_pgd;
 
 		if (user_pgd != NULL) {
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 			user_pgd[pgd_index(VSYSCALL_ADDR)] =
 				__pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
+#endif
 			ret = 0;
 		}
 
@@ -2021,7 +2023,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 # ifdef CONFIG_HIGHMEM
 	case FIX_KMAP_BEGIN ... FIX_KMAP_END:
 # endif
-#else
+#elif defined(CONFIG_X86_VSYSCALL_EMULATION)
 	case VSYSCALL_PAGE:
 #endif
 	case FIX_TEXT_POKE0:
@@ -2060,7 +2062,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 
 	__native_set_fixmap(idx, pte);
 
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 	/* Replicate changes to map the vsyscall page into the user
 	   pagetable vsyscall mapping. */
 	if (idx == VSYSCALL_PAGE) {