Merge branch 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 PTI preparatory patches from Thomas Gleixner:
 "Todays Advent calendar window contains twentyfour easy to digest
  patches. The original plan was to have twenty three matching the date,
  but a late fixup made that moot.

   - Move the cpu_entry_area mapping out of the fixmap into a separate
     address space. That's necessary because the fixmap becomes too big
     with NRCPUS=8192 and this caused already subtle and hard to
     diagnose failures.

     The top most patch is fresh from today and cures a brain slip of
     that tall grumpy german greybeard, who ignored the intricacies of
     32bit wraparounds.

   - Limit the number of CPUs on 32bit to 64. That's insane big already,
     but at least it's small enough to prevent address space issues with
     the cpu_entry_area map, which have been observed and debugged with
     the fixmap code

   - A few TLB flush fixes in various places plus documentation which of
     the TLB functions should be used for what.

   - Rename the SYSENTER stack to CPU_ENTRY_AREA stack as it is used for
     more than sysenter now and keeping the name makes backtraces
     confusing.

   - Prevent LDT inheritance on exec() by moving it to arch_dup_mmap(),
     which is only invoked on fork().

   - Make vysycall more robust.

   - A few fixes and cleanups of the debug_pagetables code. Check
     PAGE_PRESENT instead of checking the PTE for 0 and a cleanup of the
     C89 initialization of the address hint array which already was out
     of sync with the index enums.

   - Move the ESPFIX init to a different place to prepare for PTI.

   - Several code moves with no functional change to make PTI
     integration simpler and header files less convoluted.

   - Documentation fixes and clarifications"

* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  x86/cpu_entry_area: Prevent wraparound in setup_cpu_entry_area_ptes() on 32bit
  init: Invoke init_espfix_bsp() from mm_init()
  x86/cpu_entry_area: Move it out of the fixmap
  x86/cpu_entry_area: Move it to a separate unit
  x86/mm: Create asm/invpcid.h
  x86/mm: Put MMU to hardware ASID translation in one place
  x86/mm: Remove hard-coded ASID limit checks
  x86/mm: Move the CR3 construction functions to tlbflush.h
  x86/mm: Add comments to clarify which TLB-flush functions are supposed to flush what
  x86/mm: Remove superfluous barriers
  x86/mm: Use __flush_tlb_one() for kernel memory
  x86/microcode: Dont abuse the TLB-flush interface
  x86/uv: Use the right TLB-flush API
  x86/entry: Rename SYSENTER_stack to CPU_ENTRY_AREA_entry_stack
  x86/doc: Remove obvious weirdnesses from the x86 MM layout documentation
  x86/mm/64: Improve the memory map documentation
  x86/ldt: Prevent LDT inheritance on exec
  x86/ldt: Rework locking
  arch, mm: Allow arch_dup_mmap() to fail
  x86/vsyscall/64: Warn and fail vsyscall emulation in NATIVE mode
  ...

3 files changed, 45 insertions, 9 deletions

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index bd8b57a5c874..ace8f321a5a1 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -942,9 +942,9 @@ ENTRY(debug)
 
 	/* Are we currently on the SYSENTER stack? */
 	movl	PER_CPU_VAR(cpu_entry_area), %ecx
-	addl	$CPU_ENTRY_AREA_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx
-	subl	%eax, %ecx	/* ecx = (end of SYSENTER_stack) - esp */
-	cmpl	$SIZEOF_SYSENTER_stack, %ecx
+	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+	subl	%eax, %ecx	/* ecx = (end of entry_stack) - esp */
+	cmpl	$SIZEOF_entry_stack, %ecx
 	jb	.Ldebug_from_sysenter_stack
 
 	TRACE_IRQS_OFF
@@ -986,9 +986,9 @@ ENTRY(nmi)
 
 	/* Are we currently on the SYSENTER stack? */
 	movl	PER_CPU_VAR(cpu_entry_area), %ecx
-	addl	$CPU_ENTRY_AREA_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx
-	subl	%eax, %ecx	/* ecx = (end of SYSENTER_stack) - esp */
-	cmpl	$SIZEOF_SYSENTER_stack, %ecx
+	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+	subl	%eax, %ecx	/* ecx = (end of entry_stack) - esp */
+	cmpl	$SIZEOF_entry_stack, %ecx
 	jb	.Lnmi_from_sysenter_stack
 
 	/* Not on SYSENTER stack. */
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 423885bee398..3d19c830e1b1 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -158,8 +158,8 @@ END(native_usergs_sysret64)
 	_entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip)
 
 /* The top word of the SYSENTER stack is hot and is usable as scratch space. */
-#define RSP_SCRATCH	CPU_ENTRY_AREA_SYSENTER_stack + \
-			SIZEOF_SYSENTER_stack - 8 + CPU_ENTRY_AREA
+#define RSP_SCRATCH	CPU_ENTRY_AREA_entry_stack + \
+			SIZEOF_entry_stack - 8 + CPU_ENTRY_AREA
 
 ENTRY(entry_SYSCALL_64_trampoline)
 	UNWIND_HINT_EMPTY
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index f279ba2643dc..1faf40f2dda9 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -37,6 +37,7 @@
 #include <asm/unistd.h>
 #include <asm/fixmap.h>
 #include <asm/traps.h>
+#include <asm/paravirt.h>
 
 #define CREATE_TRACE_POINTS
 #include "vsyscall_trace.h"
@@ -138,6 +139,10 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 
 	WARN_ON_ONCE(address != regs->ip);
 
+	/* This should be unreachable in NATIVE mode. */
+	if (WARN_ON(vsyscall_mode == NATIVE))
+		return false;
+
 	if (vsyscall_mode == NONE) {
 		warn_bad_vsyscall(KERN_INFO, regs,
 				  "vsyscall attempted with vsyscall=none");
@@ -329,16 +334,47 @@ 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.
+ */
+static void __init set_vsyscall_pgtable_user_bits(void)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset_k(VSYSCALL_ADDR);
+	set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
+	p4d = p4d_offset(pgd, VSYSCALL_ADDR);
+#if CONFIG_PGTABLE_LEVELS >= 5
+	p4d->p4d |= _PAGE_USER;
+#endif
+	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)
+	if (vsyscall_mode != NONE) {
 		__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
 			     vsyscall_mode == NATIVE
 			     ? PAGE_KERNEL_VSYSCALL
 			     : PAGE_KERNEL_VVAR);
+		set_vsyscall_pgtable_user_bits();
+	}
 
 	BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
 		     (unsigned long)VSYSCALL_ADDR);