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

Pull x86 pti updates from Thomas Gleixner:
 "This contains:

   - a PTI bugfix to avoid setting reserved CR3 bits when PCID is
     disabled. This seems to cause issues on a virtual machine at least
     and is incorrect according to the AMD manual.

   - a PTI bugfix which disables the perf BTS facility if PTI is
     enabled. The BTS AUX buffer is not globally visible and causes the
     CPU to fault when the mapping disappears on switching CR3 to user
     space. A full fix which restores BTS on PTI is non trivial and will
     be worked on.

   - PTI bugfixes for EFI and trusted boot which make sure that the user
     space visible page table entries have the NX bit cleared

   - removal of dead code in the PTI pagetable setup functions

   - add PTI documentation

   - add a selftest for vsyscall to verify that the kernel actually
     implements what it advertises.

   - a sysfs interface to expose vulnerability and mitigation
     information so there is a coherent way for users to retrieve the
     status.

   - the initial spectre_v2 mitigations, aka retpoline:

      + The necessary ASM thunk and compiler support

      + The ASM variants of retpoline and the conversion of affected ASM
        code

      + Make LFENCE serializing on AMD so it can be used as speculation
        trap

      + The RSB fill after vmexit

   - initial objtool support for retpoline

  As I said in the status mail this is the most of the set of patches
  which should go into 4.15 except two straight forward patches still on
  hold:

   - the retpoline add on of LFENCE which waits for ACKs

   - the RSB fill after context switch

  Both should be ready to go early next week and with that we'll have
  covered the major holes of spectre_v2 and go back to normality"

* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (28 commits)
  x86,perf: Disable intel_bts when PTI
  security/Kconfig: Correct the Documentation reference for PTI
  x86/pti: Fix !PCID and sanitize defines
  selftests/x86: Add test_vsyscall
  x86/retpoline: Fill return stack buffer on vmexit
  x86/retpoline/irq32: Convert assembler indirect jumps
  x86/retpoline/checksum32: Convert assembler indirect jumps
  x86/retpoline/xen: Convert Xen hypercall indirect jumps
  x86/retpoline/hyperv: Convert assembler indirect jumps
  x86/retpoline/ftrace: Convert ftrace assembler indirect jumps
  x86/retpoline/entry: Convert entry assembler indirect jumps
  x86/retpoline/crypto: Convert crypto assembler indirect jumps
  x86/spectre: Add boot time option to select Spectre v2 mitigation
  x86/retpoline: Add initial retpoline support
  objtool: Allow alternatives to be ignored
  objtool: Detect jumps to retpoline thunks
  x86/pti: Make unpoison of pgd for trusted boot work for real
  x86/alternatives: Fix optimize_nops() checking
  sysfs/cpu: Fix typos in vulnerability documentation
  x86/cpu/AMD: Use LFENCE_RDTSC in preference to MFENCE_RDTSC
  ...

3 files changed, 31 insertions, 22 deletions

diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 45a63e00a6af..3f48f695d5e6 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -198,8 +198,11 @@ For 32-bit we have the following conventions - kernel is built with
  * PAGE_TABLE_ISOLATION PGDs are 8k.  Flip bit 12 to switch between the two
  * halves:
  */
-#define PTI_SWITCH_PGTABLES_MASK	(1<<PAGE_SHIFT)
-#define PTI_SWITCH_MASK		(PTI_SWITCH_PGTABLES_MASK|(1<<X86_CR3_PTI_SWITCH_BIT))
+#define PTI_USER_PGTABLE_BIT		PAGE_SHIFT
+#define PTI_USER_PGTABLE_MASK		(1 << PTI_USER_PGTABLE_BIT)
+#define PTI_USER_PCID_BIT		X86_CR3_PTI_PCID_USER_BIT
+#define PTI_USER_PCID_MASK		(1 << PTI_USER_PCID_BIT)
+#define PTI_USER_PGTABLE_AND_PCID_MASK  (PTI_USER_PCID_MASK | PTI_USER_PGTABLE_MASK)
 
 .macro SET_NOFLUSH_BIT	reg:req
 	bts	$X86_CR3_PCID_NOFLUSH_BIT, \reg
@@ -208,7 +211,7 @@ For 32-bit we have the following conventions - kernel is built with
 .macro ADJUST_KERNEL_CR3 reg:req
 	ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID
 	/* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
-	andq    $(~PTI_SWITCH_MASK), \reg
+	andq    $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg
 .endm
 
 .macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
@@ -239,15 +242,19 @@ For 32-bit we have the following conventions - kernel is built with
 	/* Flush needed, clear the bit */
 	btr	\scratch_reg, THIS_CPU_user_pcid_flush_mask
 	movq	\scratch_reg2, \scratch_reg
-	jmp	.Lwrcr3_\@
+	jmp	.Lwrcr3_pcid_\@
 
 .Lnoflush_\@:
 	movq	\scratch_reg2, \scratch_reg
 	SET_NOFLUSH_BIT \scratch_reg
 
+.Lwrcr3_pcid_\@:
+	/* Flip the ASID to the user version */
+	orq	$(PTI_USER_PCID_MASK), \scratch_reg
+
 .Lwrcr3_\@:
-	/* Flip the PGD and ASID to the user version */
-	orq     $(PTI_SWITCH_MASK), \scratch_reg
+	/* Flip the PGD to the user version */
+	orq     $(PTI_USER_PGTABLE_MASK), \scratch_reg
 	mov	\scratch_reg, %cr3
 .Lend_\@:
 .endm
@@ -263,17 +270,12 @@ For 32-bit we have the following conventions - kernel is built with
 	movq	%cr3, \scratch_reg
 	movq	\scratch_reg, \save_reg
 	/*
-	 * Is the "switch mask" all zero?  That means that both of
-	 * these are zero:
-	 *
-	 *	1. The user/kernel PCID bit, and
-	 *	2. The user/kernel "bit" that points CR3 to the
-	 *	   bottom half of the 8k PGD
-	 *
-	 * That indicates a kernel CR3 value, not a user CR3.
+	 * Test the user pagetable bit. If set, then the user page tables
+	 * are active. If clear CR3 already has the kernel page table
+	 * active.
 	 */
-	testq	$(PTI_SWITCH_MASK), \scratch_reg
-	jz	.Ldone_\@
+	bt	$PTI_USER_PGTABLE_BIT, \scratch_reg
+	jnc	.Ldone_\@
 
 	ADJUST_KERNEL_CR3 \scratch_reg
 	movq	\scratch_reg, %cr3
@@ -290,7 +292,7 @@ For 32-bit we have the following conventions - kernel is built with
 	 * KERNEL pages can always resume with NOFLUSH as we do
 	 * explicit flushes.
 	 */
-	bt	$X86_CR3_PTI_SWITCH_BIT, \save_reg
+	bt	$PTI_USER_PGTABLE_BIT, \save_reg
 	jnc	.Lnoflush_\@
 
 	/*
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index ace8f321a5a1..a1f28a54f23a 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -44,6 +44,7 @@
 #include <asm/asm.h>
 #include <asm/smap.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>
 
 	.section .entry.text, "ax"
 
@@ -290,7 +291,7 @@ ENTRY(ret_from_fork)
 
 	/* kernel thread */
 1:	movl	%edi, %eax
-	call	*%ebx
+	CALL_NOSPEC %ebx
 	/*
 	 * A kernel thread is allowed to return here after successfully
 	 * calling do_execve().  Exit to userspace to complete the execve()
@@ -919,7 +920,7 @@ common_exception:
 	movl	%ecx, %es
 	TRACE_IRQS_OFF
 	movl	%esp, %eax			# pt_regs pointer
-	call	*%edi
+	CALL_NOSPEC %edi
 	jmp	ret_from_exception
 END(common_exception)
 
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f048e384ff54..4f8e1d35a97c 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -37,6 +37,7 @@
 #include <asm/pgtable_types.h>
 #include <asm/export.h>
 #include <asm/frame.h>
+#include <asm/nospec-branch.h>
 #include <linux/err.h>
 
 #include "calling.h"
@@ -191,7 +192,7 @@ ENTRY(entry_SYSCALL_64_trampoline)
 	 */
 	pushq	%rdi
 	movq	$entry_SYSCALL_64_stage2, %rdi
-	jmp	*%rdi
+	JMP_NOSPEC %rdi
 END(entry_SYSCALL_64_trampoline)
 
 	.popsection
@@ -270,7 +271,12 @@ entry_SYSCALL_64_fastpath:
 	 * It might end up jumping to the slow path.  If it jumps, RAX
 	 * and all argument registers are clobbered.
 	 */
+#ifdef CONFIG_RETPOLINE
+	movq	sys_call_table(, %rax, 8), %rax
+	call	__x86_indirect_thunk_rax
+#else
 	call	*sys_call_table(, %rax, 8)
+#endif
 .Lentry_SYSCALL_64_after_fastpath_call:
 
 	movq	%rax, RAX(%rsp)
@@ -442,7 +448,7 @@ ENTRY(stub_ptregs_64)
 	jmp	entry_SYSCALL64_slow_path
 
 1:
-	jmp	*%rax				/* Called from C */
+	JMP_NOSPEC %rax				/* Called from C */
 END(stub_ptregs_64)
 
 .macro ptregs_stub func
@@ -521,7 +527,7 @@ ENTRY(ret_from_fork)
 1:
 	/* kernel thread */
 	movq	%r12, %rdi
-	call	*%rbx
+	CALL_NOSPEC %rbx
 	/*
 	 * A kernel thread is allowed to return here after successfully
 	 * calling do_execve().  Exit to userspace to complete the execve()