1 files changed, 78 insertions, 108 deletions

diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 08a18d0dcc5..ea5b5709aa7 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -18,6 +18,8 @@
  *  use the vDSO.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/time.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -26,7 +28,7 @@
 #include <linux/jiffies.h>
 #include <linux/sysctl.h>
 #include <linux/topology.h>
-#include <linux/clocksource.h>
+#include <linux/timekeeper_internal.h>
 #include <linux/getcpu.h>
 #include <linux/cpu.h>
 #include <linux/smp.h>
@@ -45,14 +47,12 @@
 #include <asm/segment.h>
 #include <asm/desc.h>
 #include <asm/topology.h>
-#include <asm/vgtod.h>
 #include <asm/traps.h>
 
 #define CREATE_TRACE_POINTS
 #include "vsyscall_trace.h"
 
 DEFINE_VVAR(int, vgetcpu_mode);
-DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
 
 static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE;
 
@@ -75,61 +75,23 @@ static int __init vsyscall_setup(char *str)
 }
 early_param("vsyscall", vsyscall_setup);
 
-void update_vsyscall_tz(void)
-{
-	vsyscall_gtod_data.sys_tz = sys_tz;
-}
-
-void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
-			struct clocksource *clock, u32 mult)
-{
-	struct timespec monotonic;
-
-	write_seqcount_begin(&vsyscall_gtod_data.seq);
-
-	/* copy vsyscall data */
-	vsyscall_gtod_data.clock.vclock_mode	= clock->archdata.vclock_mode;
-	vsyscall_gtod_data.clock.cycle_last	= clock->cycle_last;
-	vsyscall_gtod_data.clock.mask		= clock->mask;
-	vsyscall_gtod_data.clock.mult		= mult;
-	vsyscall_gtod_data.clock.shift		= clock->shift;
-
-	vsyscall_gtod_data.wall_time_sec	= wall_time->tv_sec;
-	vsyscall_gtod_data.wall_time_nsec	= wall_time->tv_nsec;
-
-	monotonic = timespec_add(*wall_time, *wtm);
-	vsyscall_gtod_data.monotonic_time_sec	= monotonic.tv_sec;
-	vsyscall_gtod_data.monotonic_time_nsec	= monotonic.tv_nsec;
-
-	vsyscall_gtod_data.wall_time_coarse	= __current_kernel_time();
-	vsyscall_gtod_data.monotonic_time_coarse =
-		timespec_add(vsyscall_gtod_data.wall_time_coarse, *wtm);
-
-	write_seqcount_end(&vsyscall_gtod_data.seq);
-}
-
 static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
 			      const char *message)
 {
-	static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST);
-	struct task_struct *tsk;
-
-	if (!show_unhandled_signals || !__ratelimit(&rs))
+	if (!show_unhandled_signals)
 		return;
 
-	tsk = current;
-
-	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, regs->cs,
-	       regs->sp, regs->ax, regs->si, regs->di);
+	pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
+			      level, current->comm, task_pid_nr(current),
+			      message, regs->ip, regs->cs,
+			      regs->sp, regs->ax, regs->si, regs->di);
 }
 
 static int addr_to_vsyscall_nr(unsigned long addr)
 {
 	int nr;
 
-	if ((addr & ~0xC00UL) != VSYSCALL_START)
+	if ((addr & ~0xC00UL) != VSYSCALL_ADDR)
 		return -EINVAL;
 
 	nr = (addr & 0xC00UL) >> 10;
@@ -139,15 +101,6 @@ static int addr_to_vsyscall_nr(unsigned long addr)
 	return nr;
 }
 
-static int vsyscall_seccomp(struct task_struct *tsk, int syscall_nr)
-{
-	if (!seccomp_mode(&tsk->seccomp))
-		return 0;
-	task_pt_regs(tsk)->orig_ax = syscall_nr;
-	task_pt_regs(tsk)->ax = syscall_nr;
-	return __secure_computing(syscall_nr);
-}
-
 static bool write_ok_or_segv(unsigned long ptr, size_t size)
 {
 	/*
@@ -180,10 +133,9 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 {
 	struct task_struct *tsk;
 	unsigned long caller;
-	int vsyscall_nr;
+	int vsyscall_nr, syscall_nr, tmp;
 	int prev_sig_on_uaccess_error;
 	long ret;
-	int skip;
 
 	/*
 	 * No point in checking CS -- the only way to get here is a user mode
@@ -215,56 +167,84 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 	}
 
 	tsk = current;
-	/*
-	 * With a real vsyscall, page faults cause SIGSEGV.  We want to
-	 * preserve that behavior to make writing exploits harder.
-	 */
-	prev_sig_on_uaccess_error = current_thread_info()->sig_on_uaccess_error;
-	current_thread_info()->sig_on_uaccess_error = 1;
 
 	/*
+	 * Check for access_ok violations and find the syscall nr.
+	 *
 	 * NULL is a valid user pointer (in the access_ok sense) on 32-bit and
 	 * 64-bit, so we don't need to special-case it here.  For all the
 	 * vsyscalls, NULL means "don't write anything" not "write it at
 	 * address 0".
 	 */
-	ret = -EFAULT;
-	skip = 0;
 	switch (vsyscall_nr) {
 	case 0:
-		skip = vsyscall_seccomp(tsk, __NR_gettimeofday);
-		if (skip)
-			break;
-
 		if (!write_ok_or_segv(regs->di, sizeof(struct timeval)) ||
-		    !write_ok_or_segv(regs->si, sizeof(struct timezone)))
-			break;
+		    !write_ok_or_segv(regs->si, sizeof(struct timezone))) {
+			ret = -EFAULT;
+			goto check_fault;
+		}
+
+		syscall_nr = __NR_gettimeofday;
+		break;
+
+	case 1:
+		if (!write_ok_or_segv(regs->di, sizeof(time_t))) {
+			ret = -EFAULT;
+			goto check_fault;
+		}
+
+		syscall_nr = __NR_time;
+		break;
+
+	case 2:
+		if (!write_ok_or_segv(regs->di, sizeof(unsigned)) ||
+		    !write_ok_or_segv(regs->si, sizeof(unsigned))) {
+			ret = -EFAULT;
+			goto check_fault;
+		}
+
+		syscall_nr = __NR_getcpu;
+		break;
+	}
+
+	/*
+	 * Handle seccomp.  regs->ip must be the original value.
+	 * See seccomp_send_sigsys and Documentation/prctl/seccomp_filter.txt.
+	 *
+	 * We could optimize the seccomp disabled case, but performance
+	 * here doesn't matter.
+	 */
+	regs->orig_ax = syscall_nr;
+	regs->ax = -ENOSYS;
+	tmp = secure_computing(syscall_nr);
+	if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) {
+		warn_bad_vsyscall(KERN_DEBUG, regs,
+				  "seccomp tried to change syscall nr or ip");
+		do_exit(SIGSYS);
+	}
+	if (tmp)
+		goto do_ret;  /* skip requested */
+
+	/*
+	 * With a real vsyscall, page faults cause SIGSEGV.  We want to
+	 * preserve that behavior to make writing exploits harder.
+	 */
+	prev_sig_on_uaccess_error = current_thread_info()->sig_on_uaccess_error;
+	current_thread_info()->sig_on_uaccess_error = 1;
 
+	ret = -EFAULT;
+	switch (vsyscall_nr) {
+	case 0:
 		ret = sys_gettimeofday(
 			(struct timeval __user *)regs->di,
 			(struct timezone __user *)regs->si);
 		break;
 
 	case 1:
-		skip = vsyscall_seccomp(tsk, __NR_time);
-		if (skip)
-			break;
-
-		if (!write_ok_or_segv(regs->di, sizeof(time_t)))
-			break;
-
 		ret = sys_time((time_t __user *)regs->di);
 		break;
 
 	case 2:
-		skip = vsyscall_seccomp(tsk, __NR_getcpu);
-		if (skip)
-			break;
-
-		if (!write_ok_or_segv(regs->di, sizeof(unsigned)) ||
-		    !write_ok_or_segv(regs->si, sizeof(unsigned)))
-			break;
-
 		ret = sys_getcpu((unsigned __user *)regs->di,
 				 (unsigned __user *)regs->si,
 				 NULL);
@@ -273,12 +253,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 
 	current_thread_info()->sig_on_uaccess_error = prev_sig_on_uaccess_error;
 
-	if (skip) {
-		if ((long)regs->ax <= 0L) /* seccomp errno emulation */
-			goto do_ret;
-		goto done; /* seccomp trace/trap */
-	}
-
+check_fault:
 	if (ret == -EFAULT) {
 		/* Bad news -- userspace fed a bad pointer to a vsyscall. */
 		warn_bad_vsyscall(KERN_INFO, regs,
@@ -301,7 +276,6 @@ do_ret:
 	/* Emulate a ret instruction. */
 	regs->ip = caller;
 	regs->sp += 8;
-done:
 	return true;
 
 sigsegv:
@@ -313,7 +287,7 @@ sigsegv:
  * Assume __initcall executes before all user space. Hopefully kmod
  * doesn't violate that. We'll find out if it does.
  */
-static void __cpuinit vsyscall_set_cpu(int cpu)
+static void vsyscall_set_cpu(int cpu)
 {
 	unsigned long d;
 	unsigned long node = 0;
@@ -335,13 +309,13 @@ static void __cpuinit vsyscall_set_cpu(int cpu)
 	write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
 }
 
-static void __cpuinit cpu_vsyscall_init(void *arg)
+static void cpu_vsyscall_init(void *arg)
 {
 	/* preemption should be already off */
 	vsyscall_set_cpu(raw_smp_processor_id());
 }
 
-static int __cpuinit
+static int
 cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg)
 {
 	long cpu = (long)arg;
@@ -356,28 +330,24 @@ void __init map_vsyscall(void)
 {
 	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);
 
-	__set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_vsyscall,
+	__set_fixmap(VSYSCALL_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(VSYSCALL_PAGE) !=
+		     (unsigned long)VSYSCALL_ADDR);
 }
 
 static int __init vsyscall_init(void)
 {
-	BUG_ON(VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE));
+	cpu_notifier_register_begin();
 
 	on_each_cpu(cpu_vsyscall_init, NULL, 1);
 	/* notifier priority > KVM */
-	hotcpu_notifier(cpu_vsyscall_notifier, 30);
+	__hotcpu_notifier(cpu_vsyscall_notifier, 30);
+
+	cpu_notifier_register_done();
 
 	return 0;
 }