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

Pull x86 PTI and Spectre related fixes and updates from Ingo Molnar:
 "Here's the latest set of Spectre and PTI related fixes and updates:

  Spectre:
   - Add entry code register clearing to reduce the Spectre attack
     surface
   - Update the Spectre microcode blacklist
   - Inline the KVM Spectre helpers to get close to v4.14 performance
     again.
   - Fix indirect_branch_prediction_barrier()
   - Fix/improve Spectre related kernel messages
   - Fix array_index_nospec_mask() asm constraint
   - KVM: fix two MSR handling bugs

  PTI:
   - Fix a paranoid entry PTI CR3 handling bug
   - Fix comments

  objtool:
   - Fix paranoid_entry() frame pointer warning
   - Annotate WARN()-related UD2 as reachable
   - Various fixes
   - Add Add Peter Zijlstra as objtool co-maintainer

  Misc:
   - Various x86 entry code self-test fixes
   - Improve/simplify entry code stack frame generation and handling
     after recent heavy-handed PTI and Spectre changes. (There's two
     more WIP improvements expected here.)
   - Type fix for cache entries

  There's also some low risk non-fix changes I've included in this
  branch to reduce backporting conflicts:

   - rename a confusing x86_cpu field name
   - de-obfuscate the naming of single-TLB flushing primitives"

* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
  x86/entry/64: Fix CR3 restore in paranoid_exit()
  x86/cpu: Change type of x86_cache_size variable to unsigned int
  x86/spectre: Fix an error message
  x86/cpu: Rename cpu_data.x86_mask to cpu_data.x86_stepping
  selftests/x86/mpx: Fix incorrect bounds with old _sigfault
  x86/mm: Rename flush_tlb_single() and flush_tlb_one() to __flush_tlb_one_[user|kernel]()
  x86/speculation: Add <asm/msr-index.h> dependency
  nospec: Move array_index_nospec() parameter checking into separate macro
  x86/speculation: Fix up array_index_nospec_mask() asm constraint
  x86/debug: Use UD2 for WARN()
  x86/debug, objtool: Annotate WARN()-related UD2 as reachable
  objtool: Fix segfault in ignore_unreachable_insn()
  selftests/x86: Disable tests requiring 32-bit support on pure 64-bit systems
  selftests/x86: Do not rely on "int $0x80" in single_step_syscall.c
  selftests/x86: Do not rely on "int $0x80" in test_mremap_vdso.c
  selftests/x86: Fix build bug caused by the 5lvl test which has been moved to the VM directory
  selftests/x86/pkeys: Remove unused functions
  selftests/x86: Clean up and document sscanf() usage
  selftests/x86: Fix vDSO selftest segfault for vsyscall=none
  x86/entry/64: Remove the unused 'icebp' macro
  ...

3 files changed, 97 insertions, 132 deletions

diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 3f48f695d5e6..dce7092ab24a 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -97,80 +97,69 @@ For 32-bit we have the following conventions - kernel is built with
 
 #define SIZEOF_PTREGS	21*8
 
-	.macro ALLOC_PT_GPREGS_ON_STACK
-	addq	$-(15*8), %rsp
-	.endm
+.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax
+	/*
+	 * Push registers and sanitize registers of values that a
+	 * speculation attack might otherwise want to exploit. The
+	 * lower registers are likely clobbered well before they
+	 * could be put to use in a speculative execution gadget.
+	 * Interleave XOR with PUSH for better uop scheduling:
+	 */
+	pushq   %rdi		/* pt_regs->di */
+	pushq   %rsi		/* pt_regs->si */
+	pushq	\rdx		/* pt_regs->dx */
+	pushq   %rcx		/* pt_regs->cx */
+	pushq   \rax		/* pt_regs->ax */
+	pushq   %r8		/* pt_regs->r8 */
+	xorq    %r8, %r8	/* nospec   r8 */
+	pushq   %r9		/* pt_regs->r9 */
+	xorq    %r9, %r9	/* nospec   r9 */
+	pushq   %r10		/* pt_regs->r10 */
+	xorq    %r10, %r10	/* nospec   r10 */
+	pushq   %r11		/* pt_regs->r11 */
+	xorq    %r11, %r11	/* nospec   r11*/
+	pushq	%rbx		/* pt_regs->rbx */
+	xorl    %ebx, %ebx	/* nospec   rbx*/
+	pushq	%rbp		/* pt_regs->rbp */
+	xorl    %ebp, %ebp	/* nospec   rbp*/
+	pushq	%r12		/* pt_regs->r12 */
+	xorq    %r12, %r12	/* nospec   r12*/
+	pushq	%r13		/* pt_regs->r13 */
+	xorq    %r13, %r13	/* nospec   r13*/
+	pushq	%r14		/* pt_regs->r14 */
+	xorq    %r14, %r14	/* nospec   r14*/
+	pushq	%r15		/* pt_regs->r15 */
+	xorq    %r15, %r15	/* nospec   r15*/
+	UNWIND_HINT_REGS
+.endm
 
-	.macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1
-	.if \r11
-	movq %r11, 6*8+\offset(%rsp)
-	.endif
-	.if \r8910
-	movq %r10, 7*8+\offset(%rsp)
-	movq %r9,  8*8+\offset(%rsp)
-	movq %r8,  9*8+\offset(%rsp)
-	.endif
-	.if \rax
-	movq %rax, 10*8+\offset(%rsp)
-	.endif
-	.if \rcx
-	movq %rcx, 11*8+\offset(%rsp)
-	.endif
-	movq %rdx, 12*8+\offset(%rsp)
-	movq %rsi, 13*8+\offset(%rsp)
-	movq %rdi, 14*8+\offset(%rsp)
-	UNWIND_HINT_REGS offset=\offset extra=0
-	.endm
-	.macro SAVE_C_REGS offset=0
-	SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1
-	.endm
-	.macro SAVE_C_REGS_EXCEPT_RAX_RCX offset=0
-	SAVE_C_REGS_HELPER \offset, 0, 0, 1, 1
-	.endm
-	.macro SAVE_C_REGS_EXCEPT_R891011
-	SAVE_C_REGS_HELPER 0, 1, 1, 0, 0
-	.endm
-	.macro SAVE_C_REGS_EXCEPT_RCX_R891011
-	SAVE_C_REGS_HELPER 0, 1, 0, 0, 0
-	.endm
-	.macro SAVE_C_REGS_EXCEPT_RAX_RCX_R11
-	SAVE_C_REGS_HELPER 0, 0, 0, 1, 0
-	.endm
-
-	.macro SAVE_EXTRA_REGS offset=0
-	movq %r15, 0*8+\offset(%rsp)
-	movq %r14, 1*8+\offset(%rsp)
-	movq %r13, 2*8+\offset(%rsp)
-	movq %r12, 3*8+\offset(%rsp)
-	movq %rbp, 4*8+\offset(%rsp)
-	movq %rbx, 5*8+\offset(%rsp)
-	UNWIND_HINT_REGS offset=\offset
-	.endm
-
-	.macro POP_EXTRA_REGS
+.macro POP_REGS pop_rdi=1 skip_r11rcx=0
 	popq %r15
 	popq %r14
 	popq %r13
 	popq %r12
 	popq %rbp
 	popq %rbx
-	.endm
-
-	.macro POP_C_REGS
+	.if \skip_r11rcx
+	popq %rsi
+	.else
 	popq %r11
+	.endif
 	popq %r10
 	popq %r9
 	popq %r8
 	popq %rax
+	.if \skip_r11rcx
+	popq %rsi
+	.else
 	popq %rcx
+	.endif
 	popq %rdx
 	popq %rsi
+	.if \pop_rdi
 	popq %rdi
-	.endm
-
-	.macro icebp
-	.byte 0xf1
-	.endm
+	.endif
+.endm
 
 /*
  * This is a sneaky trick to help the unwinder find pt_regs on the stack.  The
@@ -178,7 +167,7 @@ For 32-bit we have the following conventions - kernel is built with
  * is just setting the LSB, which makes it an invalid stack address and is also
  * a signal to the unwinder that it's a pt_regs pointer in disguise.
  *
- * NOTE: This macro must be used *after* SAVE_EXTRA_REGS because it corrupts
+ * NOTE: This macro must be used *after* PUSH_AND_CLEAR_REGS because it corrupts
  * the original rbp.
  */
 .macro ENCODE_FRAME_POINTER ptregs_offset=0
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 30c8c5344c4a..8971bd64d515 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -213,7 +213,7 @@ ENTRY(entry_SYSCALL_64)
 
 	swapgs
 	/*
-	 * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it
+	 * This path is only taken when PAGE_TABLE_ISOLATION is disabled so it
 	 * is not required to switch CR3.
 	 */
 	movq	%rsp, PER_CPU_VAR(rsp_scratch)
@@ -227,22 +227,8 @@ ENTRY(entry_SYSCALL_64)
 	pushq	%rcx				/* pt_regs->ip */
 GLOBAL(entry_SYSCALL_64_after_hwframe)
 	pushq	%rax				/* pt_regs->orig_ax */
-	pushq	%rdi				/* pt_regs->di */
-	pushq	%rsi				/* pt_regs->si */
-	pushq	%rdx				/* pt_regs->dx */
-	pushq	%rcx				/* pt_regs->cx */
-	pushq	$-ENOSYS			/* pt_regs->ax */
-	pushq	%r8				/* pt_regs->r8 */
-	pushq	%r9				/* pt_regs->r9 */
-	pushq	%r10				/* pt_regs->r10 */
-	pushq	%r11				/* pt_regs->r11 */
-	pushq	%rbx				/* pt_regs->rbx */
-	pushq	%rbp				/* pt_regs->rbp */
-	pushq	%r12				/* pt_regs->r12 */
-	pushq	%r13				/* pt_regs->r13 */
-	pushq	%r14				/* pt_regs->r14 */
-	pushq	%r15				/* pt_regs->r15 */
-	UNWIND_HINT_REGS
+
+	PUSH_AND_CLEAR_REGS rax=$-ENOSYS
 
 	TRACE_IRQS_OFF
 
@@ -321,15 +307,7 @@ GLOBAL(entry_SYSCALL_64_after_hwframe)
 syscall_return_via_sysret:
 	/* rcx and r11 are already restored (see code above) */
 	UNWIND_HINT_EMPTY
-	POP_EXTRA_REGS
-	popq	%rsi	/* skip r11 */
-	popq	%r10
-	popq	%r9
-	popq	%r8
-	popq	%rax
-	popq	%rsi	/* skip rcx */
-	popq	%rdx
-	popq	%rsi
+	POP_REGS pop_rdi=0 skip_r11rcx=1
 
 	/*
 	 * Now all regs are restored except RSP and RDI.
@@ -559,9 +537,7 @@ END(irq_entries_start)
 	call	switch_to_thread_stack
 1:
 
-	ALLOC_PT_GPREGS_ON_STACK
-	SAVE_C_REGS
-	SAVE_EXTRA_REGS
+	PUSH_AND_CLEAR_REGS
 	ENCODE_FRAME_POINTER
 
 	testb	$3, CS(%rsp)
@@ -622,15 +598,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode)
 	ud2
 1:
 #endif
-	POP_EXTRA_REGS
-	popq	%r11
-	popq	%r10
-	popq	%r9
-	popq	%r8
-	popq	%rax
-	popq	%rcx
-	popq	%rdx
-	popq	%rsi
+	POP_REGS pop_rdi=0
 
 	/*
 	 * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS.
@@ -688,8 +656,7 @@ GLOBAL(restore_regs_and_return_to_kernel)
 	ud2
 1:
 #endif
-	POP_EXTRA_REGS
-	POP_C_REGS
+	POP_REGS
 	addq	$8, %rsp	/* skip regs->orig_ax */
 	/*
 	 * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
@@ -908,7 +875,9 @@ ENTRY(\sym)
 	pushq	$-1				/* ORIG_RAX: no syscall to restart */
 	.endif
 
-	ALLOC_PT_GPREGS_ON_STACK
+	/* Save all registers in pt_regs */
+	PUSH_AND_CLEAR_REGS
+	ENCODE_FRAME_POINTER
 
 	.if \paranoid < 2
 	testb	$3, CS(%rsp)			/* If coming from userspace, switch stacks */
@@ -1121,9 +1090,7 @@ ENTRY(xen_failsafe_callback)
 	addq	$0x30, %rsp
 	UNWIND_HINT_IRET_REGS
 	pushq	$-1 /* orig_ax = -1 => not a system call */
-	ALLOC_PT_GPREGS_ON_STACK
-	SAVE_C_REGS
-	SAVE_EXTRA_REGS
+	PUSH_AND_CLEAR_REGS
 	ENCODE_FRAME_POINTER
 	jmp	error_exit
 END(xen_failsafe_callback)
@@ -1163,16 +1130,13 @@ idtentry machine_check		do_mce			has_error_code=0	paranoid=1
 #endif
 
 /*
- * Save all registers in pt_regs, and switch gs if needed.
+ * Switch gs if needed.
  * Use slow, but surefire "are we in kernel?" check.
  * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
  */
 ENTRY(paranoid_entry)
 	UNWIND_HINT_FUNC
 	cld
-	SAVE_C_REGS 8
-	SAVE_EXTRA_REGS 8
-	ENCODE_FRAME_POINTER 8
 	movl	$1, %ebx
 	movl	$MSR_GS_BASE, %ecx
 	rdmsr
@@ -1211,21 +1175,18 @@ ENTRY(paranoid_exit)
 	jmp	.Lparanoid_exit_restore
 .Lparanoid_exit_no_swapgs:
 	TRACE_IRQS_IRETQ_DEBUG
+	RESTORE_CR3	scratch_reg=%rbx save_reg=%r14
 .Lparanoid_exit_restore:
 	jmp restore_regs_and_return_to_kernel
 END(paranoid_exit)
 
 /*
- * Save all registers in pt_regs, and switch gs if needed.
+ * Switch gs if needed.
  * Return: EBX=0: came from user mode; EBX=1: otherwise
  */
 ENTRY(error_entry)
-	UNWIND_HINT_FUNC
+	UNWIND_HINT_REGS offset=8
 	cld
-	SAVE_C_REGS 8
-	SAVE_EXTRA_REGS 8
-	ENCODE_FRAME_POINTER 8
-	xorl	%ebx, %ebx
 	testb	$3, CS+8(%rsp)
 	jz	.Lerror_kernelspace
 
@@ -1406,22 +1367,7 @@ ENTRY(nmi)
 	pushq	1*8(%rdx)	/* pt_regs->rip */
 	UNWIND_HINT_IRET_REGS
 	pushq   $-1		/* pt_regs->orig_ax */
-	pushq   %rdi		/* pt_regs->di */
-	pushq   %rsi		/* pt_regs->si */
-	pushq   (%rdx)		/* pt_regs->dx */
-	pushq   %rcx		/* pt_regs->cx */
-	pushq   %rax		/* pt_regs->ax */
-	pushq   %r8		/* pt_regs->r8 */
-	pushq   %r9		/* pt_regs->r9 */
-	pushq   %r10		/* pt_regs->r10 */
-	pushq   %r11		/* pt_regs->r11 */
-	pushq	%rbx		/* pt_regs->rbx */
-	pushq	%rbp		/* pt_regs->rbp */
-	pushq	%r12		/* pt_regs->r12 */
-	pushq	%r13		/* pt_regs->r13 */
-	pushq	%r14		/* pt_regs->r14 */
-	pushq	%r15		/* pt_regs->r15 */
-	UNWIND_HINT_REGS
+	PUSH_AND_CLEAR_REGS rdx=(%rdx)
 	ENCODE_FRAME_POINTER
 
 	/*
@@ -1631,7 +1577,8 @@ end_repeat_nmi:
 	 * frame to point back to repeat_nmi.
 	 */
 	pushq	$-1				/* ORIG_RAX: no syscall to restart */
-	ALLOC_PT_GPREGS_ON_STACK
+	PUSH_AND_CLEAR_REGS
+	ENCODE_FRAME_POINTER
 
 	/*
 	 * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit
@@ -1655,8 +1602,7 @@ end_repeat_nmi:
 nmi_swapgs:
 	SWAPGS_UNSAFE_STACK
 nmi_restore:
-	POP_EXTRA_REGS
-	POP_C_REGS
+	POP_REGS
 
 	/*
 	 * Skip orig_ax and the "outermost" frame to point RSP at the "iret"
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 98d5358e4041..fd65e016e413 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -85,15 +85,25 @@ ENTRY(entry_SYSENTER_compat)
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
+	xorq	%r8, %r8		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
+	xorq	%r9, %r9		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
+	xorq	%r10, %r10		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
+	xorq	%r11, %r11		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
+	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
+	xorl	%ebp, %ebp		/* nospec   rbp */
 	pushq   $0			/* pt_regs->r12 = 0 */
+	xorq	%r12, %r12		/* nospec   r12 */
 	pushq   $0			/* pt_regs->r13 = 0 */
+	xorq	%r13, %r13		/* nospec   r13 */
 	pushq   $0			/* pt_regs->r14 = 0 */
+	xorq	%r14, %r14		/* nospec   r14 */
 	pushq   $0			/* pt_regs->r15 = 0 */
+	xorq	%r15, %r15		/* nospec   r15 */
 	cld
 
 	/*
@@ -214,15 +224,25 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe)
 	pushq	%rbp			/* pt_regs->cx (stashed in bp) */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
+	xorq	%r8, %r8		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
+	xorq	%r9, %r9		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
+	xorq	%r10, %r10		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
+	xorq	%r11, %r11		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
+	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp (will be overwritten) */
+	xorl	%ebp, %ebp		/* nospec   rbp */
 	pushq   $0			/* pt_regs->r12 = 0 */
+	xorq	%r12, %r12		/* nospec   r12 */
 	pushq   $0			/* pt_regs->r13 = 0 */
+	xorq	%r13, %r13		/* nospec   r13 */
 	pushq   $0			/* pt_regs->r14 = 0 */
+	xorq	%r14, %r14		/* nospec   r14 */
 	pushq   $0			/* pt_regs->r15 = 0 */
+	xorq	%r15, %r15		/* nospec   r15 */
 
 	/*
 	 * User mode is traced as though IRQs are on, and SYSENTER
@@ -338,15 +358,25 @@ ENTRY(entry_INT80_compat)
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
 	pushq   $0			/* pt_regs->r8  = 0 */
+	xorq	%r8, %r8		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
+	xorq	%r9, %r9		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
+	xorq	%r10, %r10		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
+	xorq	%r11, %r11		/* nospec   r11 */
 	pushq   %rbx                    /* pt_regs->rbx */
+	xorl	%ebx, %ebx		/* nospec   rbx */
 	pushq   %rbp                    /* pt_regs->rbp */
+	xorl	%ebp, %ebp		/* nospec   rbp */
 	pushq   %r12                    /* pt_regs->r12 */
+	xorq	%r12, %r12		/* nospec   r12 */
 	pushq   %r13                    /* pt_regs->r13 */
+	xorq	%r13, %r13		/* nospec   r13 */
 	pushq   %r14                    /* pt_regs->r14 */
+	xorq	%r14, %r14		/* nospec   r14 */
 	pushq   %r15                    /* pt_regs->r15 */
+	xorq	%r15, %r15		/* nospec   r15 */
 	cld
 
 	/*