1 files changed, 105 insertions, 66 deletions

diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index ce1d7534fa53..6e6c0a740837 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>
  *
@@ -36,17 +37,18 @@
 #include <asm/unistd.h>
 #include <asm/fixmap.h>
 #include <asm/traps.h>
+#include <asm/paravirt.h>
 
 #define CREATE_TRACE_POINTS
 #include "vsyscall_trace.h"
 
-static enum { EMULATE, NATIVE, NONE } vsyscall_mode =
-#if defined(CONFIG_LEGACY_VSYSCALL_NATIVE)
-	NATIVE;
-#elif defined(CONFIG_LEGACY_VSYSCALL_NONE)
+static enum { EMULATE, XONLY, NONE } vsyscall_mode __ro_after_init =
+#ifdef CONFIG_LEGACY_VSYSCALL_NONE
 	NONE;
+#elif defined(CONFIG_LEGACY_VSYSCALL_XONLY)
+	XONLY;
 #else
-	EMULATE;
+	#error VSYSCALL config is broken
 #endif
 
 static int __init vsyscall_setup(char *str)
@@ -54,8 +56,8 @@ 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("xonly", str))
+			vsyscall_mode = XONLY;
 		else if (!strcmp("none", str))
 			vsyscall_mode = NONE;
 		else
@@ -74,7 +76,7 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
 	if (!show_unhandled_signals)
 		return;
 
-	printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
+	printk_ratelimited("%s%s[%d] %s ip:%lx cs:%x 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);
@@ -96,47 +98,62 @@ static int addr_to_vsyscall_nr(unsigned long addr)
 
 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_err, this could go away.
-	 */
-
-	if (!access_ok(VERIFY_WRITE, (void __user *)ptr, size)) {
-		siginfo_t info;
+	if (!access_ok((void __user *)ptr, size)) {
 		struct thread_struct *thread = &current->thread;
 
-		thread->error_code	= 6;  /* user fault, no page, write */
+		thread->error_code	= X86_PF_USER | X86_PF_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);
+		force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)ptr);
 		return false;
 	} else {
 		return true;
 	}
 }
 
-bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
+bool emulate_vsyscall(unsigned long error_code,
+		      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_err;
 	long ret;
+	unsigned long orig_dx;
+
+	/* Write faults or kernel-privilege faults never get fixed up. */
+	if ((error_code & (X86_PF_WRITE | X86_PF_USER)) != X86_PF_USER)
+		return false;
+
+	/*
+	 * Assume that faults at regs->ip are because of an
+	 * instruction fetch. Return early and avoid
+	 * emulation for faults during data accesses:
+	 */
+	if (address != regs->ip) {
+		/* Failed vsyscall read */
+		if (vsyscall_mode == EMULATE)
+			return false;
+
+		/*
+		 * User code tried and failed to read the vsyscall page.
+		 */
+		warn_bad_vsyscall(KERN_INFO, regs, "vsyscall read attempt denied -- look up the vsyscall kernel parameter if you need a workaround");
+		return false;
+	}
+
+	/*
+	 * X86_PF_INSTR is only set when NX is supported.  When
+	 * available, use it to double-check that the emulation code
+	 * is only being used for instruction fetches:
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_NX))
+		WARN_ON_ONCE(!(error_code & X86_PF_INSTR));
 
 	/*
 	 * 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");
@@ -159,8 +176,6 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 		goto sigsegv;
 	}
 
-	tsk = current;
-
 	/*
 	 * Check for access_ok violations and find the syscall nr.
 	 *
@@ -171,7 +186,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 	 */
 	switch (vsyscall_nr) {
 	case 0:
-		if (!write_ok_or_segv(regs->di, sizeof(struct timeval)) ||
+		if (!write_ok_or_segv(regs->di, sizeof(struct __kernel_old_timeval)) ||
 		    !write_ok_or_segv(regs->si, sizeof(struct timezone))) {
 			ret = -EFAULT;
 			goto check_fault;
@@ -181,7 +196,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 		break;
 
 	case 1:
-		if (!write_ok_or_segv(regs->di, sizeof(time_t))) {
+		if (!write_ok_or_segv(regs->di, sizeof(__kernel_old_time_t))) {
 			ret = -EFAULT;
 			goto check_fault;
 		}
@@ -202,66 +217,55 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 
 	/*
 	 * Handle seccomp.  regs->ip must be the original value.
-	 * See seccomp_send_sigsys and Documentation/prctl/seccomp_filter.txt.
+	 * See seccomp_send_sigsys and Documentation/userspace-api/seccomp_filter.rst.
 	 *
 	 * We could optimize the seccomp disabled case, but performance
 	 * here doesn't matter.
 	 */
 	regs->orig_ax = syscall_nr;
 	regs->ax = -ENOSYS;
-	tmp = secure_computing(NULL);
+	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);
+		force_exit_sig(SIGSYS);
+		return true;
 	}
 	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.
+	 * With a real vsyscall, page faults cause SIGSEGV.
 	 */
-	prev_sig_on_uaccess_err = current->thread.sig_on_uaccess_err;
-	current->thread.sig_on_uaccess_err = 1;
-
 	ret = -EFAULT;
 	switch (vsyscall_nr) {
 	case 0:
-		ret = sys_gettimeofday(
-			(struct timeval __user *)regs->di,
-			(struct timezone __user *)regs->si);
+		/* this decodes regs->di and regs->si on its own */
+		ret = __x64_sys_gettimeofday(regs);
 		break;
 
 	case 1:
-		ret = sys_time((time_t __user *)regs->di);
+		/* this decodes regs->di on its own */
+		ret = __x64_sys_time(regs);
 		break;
 
 	case 2:
-		ret = sys_getcpu((unsigned __user *)regs->di,
-				 (unsigned __user *)regs->si,
-				 NULL);
+		/* while we could clobber regs->dx, we didn't in the past... */
+		orig_dx = regs->dx;
+		regs->dx = 0;
+		/* this decodes regs->di, regs->si and regs->dx on its own */
+		ret = __x64_sys_getcpu(regs);
+		regs->dx = orig_dx;
 		break;
 	}
 
-	current->thread.sig_on_uaccess_err = prev_sig_on_uaccess_err;
-
 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. */
+		goto sigsegv;
 	}
 
 	regs->ax = ret;
@@ -273,7 +277,7 @@ do_ret:
 	return true;
 
 sigsegv:
-	force_sig(SIGSEGV, current);
+	force_sig(SIGSEGV);
 	return true;
 }
 
@@ -289,7 +293,7 @@ static const char *gate_vma_name(struct vm_area_struct *vma)
 static const struct vm_operations_struct gate_vma_ops = {
 	.name = gate_vma_name,
 };
-static struct vm_area_struct gate_vma = {
+static struct vm_area_struct gate_vma __ro_after_init = {
 	.vm_start	= VSYSCALL_ADDR,
 	.vm_end		= VSYSCALL_ADDR + PAGE_SIZE,
 	.vm_page_prot	= PAGE_READONLY_EXEC,
@@ -300,7 +304,7 @@ static struct vm_area_struct gate_vma = {
 struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 {
 #ifdef CONFIG_COMPAT
-	if (!mm || mm->context.ia32_compat)
+	if (!mm || !test_bit(MM_CONTEXT_HAS_VSYSCALL, &mm->context.flags))
 		return NULL;
 #endif
 	if (vsyscall_mode == NONE)
@@ -328,16 +332,51 @@ int in_gate_area_no_mm(unsigned long addr)
 	return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR;
 }
 
+/*
+ * The VSYSCALL page is the only user-accessible page in the kernel address
+ * range.  Normally, the kernel page tables can have _PAGE_USER clear, but
+ * the tables covering VSYSCALL_ADDR need _PAGE_USER set if vsyscalls
+ * are enabled.
+ *
+ * Some day we may create a "minimal" vsyscall mode in which we emulate
+ * vsyscalls but leave the page not present.  If so, we skip calling
+ * this.
+ */
+void __init set_vsyscall_pgtable_user_bits(pgd_t *root)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset_pgd(root, VSYSCALL_ADDR);
+	set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
+	p4d = p4d_offset(pgd, VSYSCALL_ADDR);
+	set_p4d(p4d, __p4d(p4d_val(*p4d) | _PAGE_USER));
+	pud = pud_offset(p4d, VSYSCALL_ADDR);
+	set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER));
+	pmd = pmd_offset(pud, VSYSCALL_ADDR);
+	set_pmd(pmd, __pmd(pmd_val(*pmd) | _PAGE_USER));
+}
+
 void __init map_vsyscall(void)
 {
 	extern char __vsyscall_page;
 	unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
 
-	if (vsyscall_mode != NONE)
+	/*
+	 * For full emulation, the page needs to exist for real.  In
+	 * execute-only mode, there is no PTE at all backing the vsyscall
+	 * page.
+	 */
+	if (vsyscall_mode == EMULATE) {
 		__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
-			     vsyscall_mode == NATIVE
-			     ? PAGE_KERNEL_VSYSCALL
-			     : PAGE_KERNEL_VVAR);
+			     PAGE_KERNEL_VVAR);
+		set_vsyscall_pgtable_user_bits(swapper_pg_dir);
+	}
+
+	if (vsyscall_mode == XONLY)
+		vm_flags_init(&gate_vma, VM_EXEC);
 
 	BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
 		     (unsigned long)VSYSCALL_ADDR);