x86/asm/entry: Move the vsyscall code to arch/x86/entry/vsyscall/

The vsyscall code is entry code too, so move it to arch/x86/entry/vsyscall/.

Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

5 files changed, 478 insertions, 0 deletions

diff --git a/arch/x86/entry/vsyscall/Makefile b/arch/x86/entry/vsyscall/Makefile
new file mode 100644
index 000000000000..a9f4856f622a
--- /dev/null
+++ b/arch/x86/entry/vsyscall/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the x86 low level vsyscall code
+#
+obj-y					:= vsyscall_gtod.o
+
+obj-$(CONFIG_X86_VSYSCALL_EMULATION)	+= vsyscall_64.o vsyscall_emu_64.o
+
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
new file mode 100644
index 000000000000..2dcc6ff6fdcc
--- /dev/null
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -0,0 +1,335 @@
+/*
+ * 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.
+ *
+ *  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:
+ *
+ * - 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.
+ *
+ * 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.
+ *
+ * The code in this file emulates vsyscalls when notified of a page
+ * fault to a vsyscall address.
+ */
+
+#include <linux/kernel.h>
+#include <linux/timer.h>
+#include <linux/syscalls.h>
+#include <linux/ratelimit.h>
+
+#include <asm/vsyscall.h>
+#include <asm/unistd.h>
+#include <asm/fixmap.h>
+#include <asm/traps.h>
+
+#define CREATE_TRACE_POINTS
+#include "vsyscall_trace.h"
+
+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);
+
+static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
+			      const char *message)
+{
+	if (!show_unhandled_signals)
+		return;
+
+	printk_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_ADDR)
+		return -EINVAL;
+
+	nr = (addr & 0xC00UL) >> 10;
+	if (nr >= 3)
+		return -EINVAL;
+
+	return nr;
+}
+
+static bool write_ok_or_segv(unsigned long ptr, size_t size)
+{
+	/*
+	 * XXX: if access_ok, get_user, and put_user handled
+	 * sig_on_uaccess_error, this could go away.
+	 */
+
+	if (!access_ok(VERIFY_WRITE, (void __user *)ptr, size)) {
+		siginfo_t info;
+		struct thread_struct *thread = &current->thread;
+
+		thread->error_code	= 6;  /* user fault, no page, write */
+		thread->cr2		= ptr;
+		thread->trap_nr		= X86_TRAP_PF;
+
+		memset(&info, 0, sizeof(info));
+		info.si_signo		= SIGSEGV;
+		info.si_errno		= 0;
+		info.si_code		= SEGV_MAPERR;
+		info.si_addr		= (void __user *)ptr;
+
+		force_sig_info(SIGSEGV, &info, current);
+		return false;
+	} else {
+		return true;
+	}
+}
+
+bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
+{
+	struct task_struct *tsk;
+	unsigned long caller;
+	int vsyscall_nr, syscall_nr, tmp;
+	int prev_sig_on_uaccess_error;
+	long ret;
+
+	/*
+	 * 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.
+	 */
+
+	WARN_ON_ONCE(address != regs->ip);
+
+	if (vsyscall_mode == NONE) {
+		warn_bad_vsyscall(KERN_INFO, regs,
+				  "vsyscall attempted with vsyscall=none");
+		return false;
+	}
+
+	vsyscall_nr = addr_to_vsyscall_nr(address);
+
+	trace_emulate_vsyscall(vsyscall_nr);
+
+	if (vsyscall_nr < 0) {
+		warn_bad_vsyscall(KERN_WARNING, regs,
+				  "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,
+				  "vsyscall with bad stack (exploit attempt?)");
+		goto sigsegv;
+	}
+
+	tsk = current;
+
+	/*
+	 * 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".
+	 */
+	switch (vsyscall_nr) {
+	case 0:
+		if (!write_ok_or_segv(regs->di, sizeof(struct timeval)) ||
+		    !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();
+	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);
+	}
+	regs->orig_ax = -1;
+	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:
+		ret = sys_time((time_t __user *)regs->di);
+		break;
+
+	case 2:
+		ret = sys_getcpu((unsigned __user *)regs->di,
+				 (unsigned __user *)regs->si,
+				 NULL);
+		break;
+	}
+
+	current_thread_info()->sig_on_uaccess_error = prev_sig_on_uaccess_error;
+
+check_fault:
+	if (ret == -EFAULT) {
+		/* Bad news -- userspace fed a bad pointer to a vsyscall. */
+		warn_bad_vsyscall(KERN_INFO, regs,
+				  "vsyscall fault (exploit attempt?)");
+
+		/*
+		 * If we failed to generate a signal for any reason,
+		 * generate one here.  (This should be impossible.)
+		 */
+		if (WARN_ON_ONCE(!sigismember(&tsk->pending.signal, SIGBUS) &&
+				 !sigismember(&tsk->pending.signal, SIGSEGV)))
+			goto sigsegv;
+
+		return true;  /* Don't emulate the ret. */
+	}
+
+	regs->ax = ret;
+
+do_ret:
+	/* Emulate a ret instruction. */
+	regs->ip = caller;
+	regs->sp += 8;
+	return true;
+
+sigsegv:
+	force_sig(SIGSEGV, current);
+	return true;
+}
+
+/*
+ * A pseudo VMA to allow ptrace access for the vsyscall page.  This only
+ * covers the 64bit vsyscall page now. 32bit has a real VMA now and does
+ * not need special handling anymore:
+ */
+static const char *gate_vma_name(struct vm_area_struct *vma)
+{
+	return "[vsyscall]";
+}
+static struct vm_operations_struct gate_vma_ops = {
+	.name = gate_vma_name,
+};
+static struct vm_area_struct gate_vma = {
+	.vm_start	= VSYSCALL_ADDR,
+	.vm_end		= VSYSCALL_ADDR + PAGE_SIZE,
+	.vm_page_prot	= PAGE_READONLY_EXEC,
+	.vm_flags	= VM_READ | VM_EXEC,
+	.vm_ops		= &gate_vma_ops,
+};
+
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
+{
+#ifdef CONFIG_IA32_EMULATION
+	if (!mm || mm->context.ia32_compat)
+		return NULL;
+#endif
+	if (vsyscall_mode == NONE)
+		return NULL;
+	return &gate_vma;
+}
+
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
+{
+	struct vm_area_struct *vma = get_gate_vma(mm);
+
+	if (!vma)
+		return 0;
+
+	return (addr >= vma->vm_start) && (addr < vma->vm_end);
+}
+
+/*
+ * Use this when you have no reliable mm, typically from interrupt
+ * context. It is less reliable than using a task's mm and may give
+ * false positives.
+ */
+int in_gate_area_no_mm(unsigned long addr)
+{
+	return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR;
+}
+
+void __init map_vsyscall(void)
+{
+	extern char __vsyscall_page;
+	unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
+
+	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);
+}
diff --git a/arch/x86/entry/vsyscall/vsyscall_emu_64.S b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
new file mode 100644
index 000000000000..c9596a9af159
--- /dev/null
+++ b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
@@ -0,0 +1,37 @@
+/*
+ * vsyscall_emu_64.S: Vsyscall emulation page
+ *
+ * Copyright (c) 2011 Andy Lutomirski
+ *
+ * Subject to the GNU General Public License, version 2
+ */
+
+#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
+
+	.balign 1024, 0xcc
+	mov $__NR_time, %rax
+	syscall
+	ret
+
+	.balign 1024, 0xcc
+	mov $__NR_getcpu, %rax
+	syscall
+	ret
+
+	.balign 4096, 0xcc
+
+	.size __vsyscall_page, 4096
diff --git a/arch/x86/entry/vsyscall/vsyscall_gtod.c b/arch/x86/entry/vsyscall/vsyscall_gtod.c
new file mode 100644
index 000000000000..51e330416995
--- /dev/null
+++ b/arch/x86/entry/vsyscall/vsyscall_gtod.c
@@ -0,0 +1,70 @@
+/*
+ *  Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
+ *  Copyright 2003 Andi Kleen, SuSE Labs.
+ *
+ *  Modified for x86 32 bit architecture by
+ *  Stefani Seibold <stefani@seibold.net>
+ *  sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
+ *
+ *  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.
+ *
+ */
+
+#include <linux/timekeeper_internal.h>
+#include <asm/vgtod.h>
+#include <asm/vvar.h>
+
+DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
+
+void update_vsyscall_tz(void)
+{
+	vsyscall_gtod_data.tz_minuteswest = sys_tz.tz_minuteswest;
+	vsyscall_gtod_data.tz_dsttime = sys_tz.tz_dsttime;
+}
+
+void update_vsyscall(struct timekeeper *tk)
+{
+	struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
+
+	gtod_write_begin(vdata);
+
+	/* copy vsyscall data */
+	vdata->vclock_mode	= tk->tkr_mono.clock->archdata.vclock_mode;
+	vdata->cycle_last	= tk->tkr_mono.cycle_last;
+	vdata->mask		= tk->tkr_mono.mask;
+	vdata->mult		= tk->tkr_mono.mult;
+	vdata->shift		= tk->tkr_mono.shift;
+
+	vdata->wall_time_sec		= tk->xtime_sec;
+	vdata->wall_time_snsec		= tk->tkr_mono.xtime_nsec;
+
+	vdata->monotonic_time_sec	= tk->xtime_sec
+					+ tk->wall_to_monotonic.tv_sec;
+	vdata->monotonic_time_snsec	= tk->tkr_mono.xtime_nsec
+					+ ((u64)tk->wall_to_monotonic.tv_nsec
+						<< tk->tkr_mono.shift);
+	while (vdata->monotonic_time_snsec >=
+					(((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
+		vdata->monotonic_time_snsec -=
+					((u64)NSEC_PER_SEC) << tk->tkr_mono.shift;
+		vdata->monotonic_time_sec++;
+	}
+
+	vdata->wall_time_coarse_sec	= tk->xtime_sec;
+	vdata->wall_time_coarse_nsec	= (long)(tk->tkr_mono.xtime_nsec >>
+						 tk->tkr_mono.shift);
+
+	vdata->monotonic_time_coarse_sec =
+		vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec;
+	vdata->monotonic_time_coarse_nsec =
+		vdata->wall_time_coarse_nsec + tk->wall_to_monotonic.tv_nsec;
+
+	while (vdata->monotonic_time_coarse_nsec >= NSEC_PER_SEC) {
+		vdata->monotonic_time_coarse_nsec -= NSEC_PER_SEC;
+		vdata->monotonic_time_coarse_sec++;
+	}
+
+	gtod_write_end(vdata);
+}
diff --git a/arch/x86/entry/vsyscall/vsyscall_trace.h b/arch/x86/entry/vsyscall/vsyscall_trace.h
new file mode 100644
index 000000000000..9dd7359a38a8
--- /dev/null
+++ b/arch/x86/entry/vsyscall/vsyscall_trace.h
@@ -0,0 +1,29 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM vsyscall
+
+#if !defined(__VSYSCALL_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __VSYSCALL_TRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(emulate_vsyscall,
+
+	    TP_PROTO(int nr),
+
+	    TP_ARGS(nr),
+
+	    TP_STRUCT__entry(__field(int, nr)),
+
+	    TP_fast_assign(
+			   __entry->nr = nr;
+			   ),
+
+	    TP_printk("nr = %d", __entry->nr)
+);
+
+#endif
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../arch/x86/entry/vsyscall/
+#define TRACE_INCLUDE_FILE vsyscall_trace
+#include <trace/define_trace.h>