From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 20 Feb 2008 22:57:30 +0000 (+0100)
Subject: x86: fix vsyscall wreckage
X-Git-Tag: v2.6.25-rc4~159^2~8
X-Git-Url: http://git.samba.org/samba.git/?p=sfrench%2Fcifs-2.6.git;a=commitdiff_plain;h=ce28b9864b853803320c3f1d8de1b81aa4120b14;hp=d4afe414189b098d56bcd24280c018aa2ac9a990

x86: fix vsyscall wreckage

based on a report from Arne Georg Gleditsch about user-space apps
misbehaving after toggling /proc/sys/kernel/vsyscall64, a review
of the code revealed that the "NOP patching" done there is
fundamentally unsafe for a number of reasons:

1) the patching code runs without synchronizing other CPUs

2) it inserts NOPs even if there is no clock source which provides vread

3) when the clock source changes to one without vread we run in
   exactly the same problem as in #2

4) if nobody toggles the proc entry from 1 to 0 and to 1 again, then
   the syscall is not patched out

as a result it is possible to break user-space via this patching.
The only safe thing for now is to remove the patching.

This code was broken since v2.6.21.

Reported-by: Arne Georg Gleditsch <arne.gleditsch@dolphinics.no>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---

diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 3f8242774580..b6be812fac05 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -44,11 +44,6 @@
 
 #define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr)))
 #define __syscall_clobber "r11","cx","memory"
-#define __pa_vsymbol(x)			\
-	({unsigned long v;  		\
-	extern char __vsyscall_0; 	\
-	  asm("" : "=r" (v) : "0" (x)); \
-	  ((v - VSYSCALL_START) + __pa_symbol(&__vsyscall_0)); })
 
 /*
  * vsyscall_gtod_data contains data that is :
@@ -102,7 +97,7 @@ static __always_inline void do_get_tz(struct timezone * tz)
 static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz)
 {
 	int ret;
-	asm volatile("vsysc2: syscall"
+	asm volatile("syscall"
 		: "=a" (ret)
 		: "0" (__NR_gettimeofday),"D" (tv),"S" (tz)
 		: __syscall_clobber );
@@ -112,7 +107,7 @@ static __always_inline int gettimeofday(struct timeval *tv, struct timezone *tz)
 static __always_inline long time_syscall(long *t)
 {
 	long secs;
-	asm volatile("vsysc1: syscall"
+	asm volatile("syscall"
 		: "=a" (secs)
 		: "0" (__NR_time),"D" (t) : __syscall_clobber);
 	return secs;
@@ -227,50 +222,10 @@ long __vsyscall(3) venosys_1(void)
 }
 
 #ifdef CONFIG_SYSCTL
-
-#define SYSCALL 0x050f
-#define NOP2    0x9090
-
-/*
- * NOP out syscall in vsyscall page when not needed.
- */
-static int vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp,
-                        void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	extern u16 vsysc1, vsysc2;
-	u16 __iomem *map1;
-	u16 __iomem *map2;
-	int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
-	if (!write)
-		return ret;
-	/* gcc has some trouble with __va(__pa()), so just do it this
-	   way. */
-	map1 = ioremap(__pa_vsymbol(&vsysc1), 2);
-	if (!map1)
-		return -ENOMEM;
-	map2 = ioremap(__pa_vsymbol(&vsysc2), 2);
-	if (!map2) {
-		ret = -ENOMEM;
-		goto out;
-	}
-	if (!vsyscall_gtod_data.sysctl_enabled) {
-		writew(SYSCALL, map1);
-		writew(SYSCALL, map2);
-	} else {
-		writew(NOP2, map1);
-		writew(NOP2, map2);
-	}
-	iounmap(map2);
-out:
-	iounmap(map1);
-	return ret;
-}
-
 static ctl_table kernel_table2[] = {
 	{ .procname = "vsyscall64",
 	  .data = &vsyscall_gtod_data.sysctl_enabled, .maxlen = sizeof(int),
-	  .mode = 0644,
-	  .proc_handler = vsyscall_sysctl_change },
+	  .mode = 0644 },
 	{}
 };
 
@@ -279,7 +234,6 @@ static ctl_table kernel_root_table2[] = {
 	  .child = kernel_table2 },
 	{}
 };
-
 #endif
 
 /* Assume __initcall executes before all user space. Hopefully kmod