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

Pull x86 fixes from Thomas Gleixner:
 "Yet another pile of melted spectrum related changes:

   - sanitize the array_index_nospec protection mechanism: Remove the
     overengineered array_index_nospec_mask_check() magic and allow
     const-qualified types as index to avoid temporary storage in a
     non-const local variable.

   - make the microcode loader more robust by properly propagating error
     codes. Provide information about new feature bits after micro code
     was updated so administrators can act upon.

   - optimizations of the entry ASM code which reduce code footprint and
     make the code simpler and faster.

   - fix the {pmd,pud}_{set,clear}_flags() implementations to work
     properly on paravirt kernels by removing the address translation
     operations.

   - revert the harmful vmexit_fill_RSB() optimization

   - use IBRS around firmware calls

   - teach objtool about retpolines and add annotations for indirect
     jumps and calls.

   - explicitly disable jumplabel patching in __init code and handle
     patching failures properly instead of silently ignoring them.

   - remove indirect paravirt calls for writing the speculation control
     MSR as these calls are obviously proving the same attack vector
     which is tried to be mitigated.

   - a few small fixes which address build issues with recent compiler
     and assembler versions"

* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (38 commits)
  KVM/VMX: Optimize vmx_vcpu_run() and svm_vcpu_run() by marking the RDMSR path as unlikely()
  KVM/x86: Remove indirect MSR op calls from SPEC_CTRL
  objtool, retpolines: Integrate objtool with retpoline support more closely
  x86/entry/64: Simplify ENCODE_FRAME_POINTER
  extable: Make init_kernel_text() global
  jump_label: Warn on failed jump_label patching attempt
  jump_label: Explicitly disable jump labels in __init code
  x86/entry/64: Open-code switch_to_thread_stack()
  x86/entry/64: Move ASM_CLAC to interrupt_entry()
  x86/entry/64: Remove 'interrupt' macro
  x86/entry/64: Move the switch_to_thread_stack() call to interrupt_entry()
  x86/entry/64: Move ENTER_IRQ_STACK from interrupt macro to interrupt_entry
  x86/entry/64: Move PUSH_AND_CLEAR_REGS from interrupt macro to helper function
  x86/speculation: Move firmware_restrict_branch_speculation_*() from C to CPP
  objtool: Add module specific retpoline rules
  objtool: Add retpoline validation
  objtool: Use existing global variables for options
  x86/mm/sme, objtool: Annotate indirect call in sme_encrypt_execute()
  x86/boot, objtool: Annotate indirect jump in secondary_startup_64()
  x86/paravirt, objtool: Annotate indirect calls
  ...

1 files changed, 42 insertions, 29 deletions

diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index fd65e016e413..e811dd9c5e99 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -85,25 +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 */
+	xorl	%r8d, %r8d		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
-	xorq	%r9, %r9		/* nospec   r9 */
+	xorl	%r9d, %r9d		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
-	xorq	%r10, %r10		/* nospec   r10 */
+	xorl	%r10d, %r10d		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
-	xorq	%r11, %r11		/* nospec   r11 */
+	xorl	%r11d, %r11d		/* 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 */
+	xorl	%r12d, %r12d		/* nospec   r12 */
 	pushq   $0			/* pt_regs->r13 = 0 */
-	xorq	%r13, %r13		/* nospec   r13 */
+	xorl	%r13d, %r13d		/* nospec   r13 */
 	pushq   $0			/* pt_regs->r14 = 0 */
-	xorq	%r14, %r14		/* nospec   r14 */
+	xorl	%r14d, %r14d		/* nospec   r14 */
 	pushq   $0			/* pt_regs->r15 = 0 */
-	xorq	%r15, %r15		/* nospec   r15 */
+	xorl	%r15d, %r15d		/* nospec   r15 */
 	cld
 
 	/*
@@ -224,25 +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 */
+	xorl	%r8d, %r8d		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
-	xorq	%r9, %r9		/* nospec   r9 */
+	xorl	%r9d, %r9d		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
-	xorq	%r10, %r10		/* nospec   r10 */
+	xorl	%r10d, %r10d		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
-	xorq	%r11, %r11		/* nospec   r11 */
+	xorl	%r11d, %r11d		/* 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 */
+	xorl	%r12d, %r12d		/* nospec   r12 */
 	pushq   $0			/* pt_regs->r13 = 0 */
-	xorq	%r13, %r13		/* nospec   r13 */
+	xorl	%r13d, %r13d		/* nospec   r13 */
 	pushq   $0			/* pt_regs->r14 = 0 */
-	xorq	%r14, %r14		/* nospec   r14 */
+	xorl	%r14d, %r14d		/* nospec   r14 */
 	pushq   $0			/* pt_regs->r15 = 0 */
-	xorq	%r15, %r15		/* nospec   r15 */
+	xorl	%r15d, %r15d		/* nospec   r15 */
 
 	/*
 	 * User mode is traced as though IRQs are on, and SYSENTER
@@ -298,9 +298,9 @@ sysret32_from_system_call:
 	 */
 	SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9
 
-	xorq	%r8, %r8
-	xorq	%r9, %r9
-	xorq	%r10, %r10
+	xorl	%r8d, %r8d
+	xorl	%r9d, %r9d
+	xorl	%r10d, %r10d
 	swapgs
 	sysretl
 END(entry_SYSCALL_compat)
@@ -347,10 +347,23 @@ ENTRY(entry_INT80_compat)
 	 */
 	movl	%eax, %eax
 
+	/* switch to thread stack expects orig_ax and rdi to be pushed */
 	pushq	%rax			/* pt_regs->orig_ax */
+	pushq	%rdi			/* pt_regs->di */
+
+	/* Need to switch before accessing the thread stack. */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+
+	pushq	6*8(%rdi)		/* regs->ss */
+	pushq	5*8(%rdi)		/* regs->rsp */
+	pushq	4*8(%rdi)		/* regs->eflags */
+	pushq	3*8(%rdi)		/* regs->cs */
+	pushq	2*8(%rdi)		/* regs->ip */
+	pushq	1*8(%rdi)		/* regs->orig_ax */
 
-	/* switch to thread stack expects orig_ax to be pushed */
-	call	switch_to_thread_stack
+	movq	(%rdi), %rdi		/* restore %rdi */
 
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
@@ -358,25 +371,25 @@ 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 */
+	xorl	%r8d, %r8d		/* nospec   r8 */
 	pushq   $0			/* pt_regs->r9  = 0 */
-	xorq	%r9, %r9		/* nospec   r9 */
+	xorl	%r9d, %r9d		/* nospec   r9 */
 	pushq   $0			/* pt_regs->r10 = 0 */
-	xorq	%r10, %r10		/* nospec   r10 */
+	xorl	%r10d, %r10d		/* nospec   r10 */
 	pushq   $0			/* pt_regs->r11 = 0 */
-	xorq	%r11, %r11		/* nospec   r11 */
+	xorl	%r11d, %r11d		/* 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 */
+	xorl	%r12d, %r12d		/* nospec   r12 */
 	pushq   %r13                    /* pt_regs->r13 */
-	xorq	%r13, %r13		/* nospec   r13 */
+	xorl	%r13d, %r13d		/* nospec   r13 */
 	pushq   %r14                    /* pt_regs->r14 */
-	xorq	%r14, %r14		/* nospec   r14 */
+	xorl	%r14d, %r14d		/* nospec   r14 */
 	pushq   %r15                    /* pt_regs->r15 */
-	xorq	%r15, %r15		/* nospec   r15 */
+	xorl	%r15d, %r15d		/* nospec   r15 */
 	cld
 
 	/*