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

Pull x86 fixes from Thomas Gleixner:
 "A set of x86 specific fixes and updates:

   - The CR2 corruption fixes which store CR2 early in the entry code
     and hand the stored address to the fault handlers.

   - Revert a forgotten leftover of the dropped FSGSBASE series.

   - Plug a memory leak in the boot code.

   - Make the Hyper-V assist functionality robust by zeroing the shadow
     page.

   - Remove a useless check for dead processes with LDT

   - Update paravirt and VMware maintainers entries.

   - A few cleanup patches addressing various compiler warnings"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/entry/64: Prevent clobbering of saved CR2 value
  x86/hyper-v: Zero out the VP ASSIST PAGE on allocation
  x86, boot: Remove multiple copy of static function sanitize_boot_params()
  x86/boot/compressed/64: Remove unused variable
  x86/boot/efi: Remove unused variables
  x86/mm, tracing: Fix CR2 corruption
  x86/entry/64: Update comments and sanity tests for create_gap
  x86/entry/64: Simplify idtentry a little
  x86/entry/32: Simplify common_exception
  x86/paravirt: Make read_cr2() CALLEE_SAVE
  MAINTAINERS: Update PARAVIRT_OPS_INTERFACE and VMWARE_HYPERVISOR_INTERFACE
  x86/process: Delete useless check for dead process with LDT
  x86: math-emu: Hide clang warnings for 16-bit overflow
  x86/e820: Use proper booleans instead of 0/1
  x86/apic: Silence -Wtype-limits compiler warnings
  x86/mm: Free sme_early_buffer after init
  x86/boot: Fix memory leak in default_get_smp_config()
  Revert "x86/ptrace: Prevent ptrace from clearing the FS/GS selector" and fix the test

3 files changed, 123 insertions, 99 deletions

diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 9f1f9e3b8230..830bd984182b 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -343,3 +343,9 @@ For 32-bit we have the following conventions - kernel is built with
 .Lafter_call_\@:
 #endif
 .endm
+
+#ifdef CONFIG_PARAVIRT_XXL
+#define GET_CR2_INTO(reg) GET_CR2_INTO_AX ; _ASM_MOV %_ASM_AX, reg
+#else
+#define GET_CR2_INTO(reg) _ASM_MOV %cr2, reg
+#endif
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 90b473297299..2bb986f305ac 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -294,9 +294,11 @@
 .Lfinished_frame_\@:
 .endm
 
-.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0
+.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 skip_gs=0
 	cld
+.if \skip_gs == 0
 	PUSH_GS
+.endif
 	FIXUP_FRAME
 	pushl	%fs
 	pushl	%es
@@ -313,13 +315,13 @@
 	movl	%edx, %es
 	movl	$(__KERNEL_PERCPU), %edx
 	movl	%edx, %fs
+.if \skip_gs == 0
 	SET_KERNEL_GS %edx
-
+.endif
 	/* Switch to kernel stack if necessary */
 .if \switch_stacks > 0
 	SWITCH_TO_KERNEL_STACK
 .endif
-
 .endm
 
 .macro SAVE_ALL_NMI cr3_reg:req
@@ -1441,39 +1443,46 @@ BUILD_INTERRUPT3(hv_stimer0_callback_vector, HYPERV_STIMER0_VECTOR,
 
 ENTRY(page_fault)
 	ASM_CLAC
-	pushl	$do_page_fault
-	ALIGN
-	jmp common_exception
+	pushl	$0; /* %gs's slot on the stack */
+
+	SAVE_ALL switch_stacks=1 skip_gs=1
+
+	ENCODE_FRAME_POINTER
+	UNWIND_ESPFIX_STACK
+
+	/* fixup %gs */
+	GS_TO_REG %ecx
+	REG_TO_PTGS %ecx
+	SET_KERNEL_GS %ecx
+
+	GET_CR2_INTO(%ecx)			# might clobber %eax
+
+	/* fixup orig %eax */
+	movl	PT_ORIG_EAX(%esp), %edx		# get the error code
+	movl	$-1, PT_ORIG_EAX(%esp)		# no syscall to restart
+
+	TRACE_IRQS_OFF
+	movl	%esp, %eax			# pt_regs pointer
+	call	do_page_fault
+	jmp	ret_from_exception
 END(page_fault)
 
 common_exception:
 	/* the function address is in %gs's slot on the stack */
-	FIXUP_FRAME
-	pushl	%fs
-	pushl	%es
-	pushl	%ds
-	pushl	%eax
-	movl	$(__USER_DS), %eax
-	movl	%eax, %ds
-	movl	%eax, %es
-	movl	$(__KERNEL_PERCPU), %eax
-	movl	%eax, %fs
-	pushl	%ebp
-	pushl	%edi
-	pushl	%esi
-	pushl	%edx
-	pushl	%ecx
-	pushl	%ebx
-	SWITCH_TO_KERNEL_STACK
+	SAVE_ALL switch_stacks=1 skip_gs=1
 	ENCODE_FRAME_POINTER
-	cld
 	UNWIND_ESPFIX_STACK
+
+	/* fixup %gs */
 	GS_TO_REG %ecx
 	movl	PT_GS(%esp), %edi		# get the function address
-	movl	PT_ORIG_EAX(%esp), %edx		# get the error code
-	movl	$-1, PT_ORIG_EAX(%esp)		# no syscall to restart
 	REG_TO_PTGS %ecx
 	SET_KERNEL_GS %ecx
+
+	/* fixup orig %eax */
+	movl	PT_ORIG_EAX(%esp), %edx		# get the error code
+	movl	$-1, PT_ORIG_EAX(%esp)		# no syscall to restart
+
 	TRACE_IRQS_OFF
 	movl	%esp, %eax			# pt_regs pointer
 	CALL_NOSPEC %edi
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 35a66fcfcb91..3f5a978a02a7 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -864,18 +864,84 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
  */
 #define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + (x) * 8)
 
+.macro idtentry_part do_sym, has_error_code:req, read_cr2:req, paranoid:req, shift_ist=-1, ist_offset=0
+
+	.if \paranoid
+	call	paranoid_entry
+	/* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */
+	.else
+	call	error_entry
+	.endif
+	UNWIND_HINT_REGS
+
+	.if \read_cr2
+	/*
+	 * Store CR2 early so subsequent faults cannot clobber it. Use R12 as
+	 * intermediate storage as RDX can be clobbered in enter_from_user_mode().
+	 * GET_CR2_INTO can clobber RAX.
+	 */
+	GET_CR2_INTO(%r12);
+	.endif
+
+	.if \shift_ist != -1
+	TRACE_IRQS_OFF_DEBUG			/* reload IDT in case of recursion */
+	.else
+	TRACE_IRQS_OFF
+	.endif
+
+	.if \paranoid == 0
+	testb	$3, CS(%rsp)
+	jz	.Lfrom_kernel_no_context_tracking_\@
+	CALL_enter_from_user_mode
+.Lfrom_kernel_no_context_tracking_\@:
+	.endif
+
+	movq	%rsp, %rdi			/* pt_regs pointer */
+
+	.if \has_error_code
+	movq	ORIG_RAX(%rsp), %rsi		/* get error code */
+	movq	$-1, ORIG_RAX(%rsp)		/* no syscall to restart */
+	.else
+	xorl	%esi, %esi			/* no error code */
+	.endif
+
+	.if \shift_ist != -1
+	subq	$\ist_offset, CPU_TSS_IST(\shift_ist)
+	.endif
+
+	.if \read_cr2
+	movq	%r12, %rdx			/* Move CR2 into 3rd argument */
+	.endif
+
+	call	\do_sym
+
+	.if \shift_ist != -1
+	addq	$\ist_offset, CPU_TSS_IST(\shift_ist)
+	.endif
+
+	.if \paranoid
+	/* this procedure expect "no swapgs" flag in ebx */
+	jmp	paranoid_exit
+	.else
+	jmp	error_exit
+	.endif
+
+.endm
+
 /**
  * idtentry - Generate an IDT entry stub
  * @sym:		Name of the generated entry point
- * @do_sym: 		C function to be called
- * @has_error_code: 	True if this IDT vector has an error code on the stack
- * @paranoid: 		non-zero means that this vector may be invoked from
+ * @do_sym:		C function to be called
+ * @has_error_code:	True if this IDT vector has an error code on the stack
+ * @paranoid:		non-zero means that this vector may be invoked from
  *			kernel mode with user GSBASE and/or user CR3.
  *			2 is special -- see below.
  * @shift_ist:		Set to an IST index if entries from kernel mode should
- *             		decrement the IST stack so that nested entries get a
+ *			decrement the IST stack so that nested entries get a
  *			fresh stack.  (This is for #DB, which has a nasty habit
- *             		of recursing.)
+ *			of recursing.)
+ * @create_gap:		create a 6-word stack gap when coming from kernel mode.
+ * @read_cr2:		load CR2 into the 3rd argument; done before calling any C code
  *
  * idtentry generates an IDT stub that sets up a usable kernel context,
  * creates struct pt_regs, and calls @do_sym.  The stub has the following
@@ -900,15 +966,19 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
  * @paranoid == 2 is special: the stub will never switch stacks.  This is for
  * #DF: if the thread stack is somehow unusable, we'll still get a useful OOPS.
  */
-.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0 create_gap=0
+.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0 create_gap=0 read_cr2=0
 ENTRY(\sym)
 	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
 
 	/* Sanity check */
-	.if \shift_ist != -1 && \paranoid == 0
+	.if \shift_ist != -1 && \paranoid != 1
 	.error "using shift_ist requires paranoid=1"
 	.endif
 
+	.if \create_gap && \paranoid
+	.error "using create_gap requires paranoid=0"
+	.endif
+
 	ASM_CLAC
 
 	.if \has_error_code == 0
@@ -934,47 +1004,7 @@ ENTRY(\sym)
 .Lfrom_usermode_no_gap_\@:
 	.endif
 
-	.if \paranoid
-	call	paranoid_entry
-	.else
-	call	error_entry
-	.endif
-	UNWIND_HINT_REGS
-	/* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */
-
-	.if \paranoid
-	.if \shift_ist != -1
-	TRACE_IRQS_OFF_DEBUG			/* reload IDT in case of recursion */
-	.else
-	TRACE_IRQS_OFF
-	.endif
-	.endif
-
-	movq	%rsp, %rdi			/* pt_regs pointer */
-
-	.if \has_error_code
-	movq	ORIG_RAX(%rsp), %rsi		/* get error code */
-	movq	$-1, ORIG_RAX(%rsp)		/* no syscall to restart */
-	.else
-	xorl	%esi, %esi			/* no error code */
-	.endif
-
-	.if \shift_ist != -1
-	subq	$\ist_offset, CPU_TSS_IST(\shift_ist)
-	.endif
-
-	call	\do_sym
-
-	.if \shift_ist != -1
-	addq	$\ist_offset, CPU_TSS_IST(\shift_ist)
-	.endif
-
-	/* these procedures expect "no swapgs" flag in ebx */
-	.if \paranoid
-	jmp	paranoid_exit
-	.else
-	jmp	error_exit
-	.endif
+	idtentry_part \do_sym, \has_error_code, \read_cr2, \paranoid, \shift_ist, \ist_offset
 
 	.if \paranoid == 1
 	/*
@@ -983,21 +1013,9 @@ ENTRY(\sym)
 	 * run in real process context if user_mode(regs).
 	 */
 .Lfrom_usermode_switch_stack_\@:
-	call	error_entry
-
-	movq	%rsp, %rdi			/* pt_regs pointer */
-
-	.if \has_error_code
-	movq	ORIG_RAX(%rsp), %rsi		/* get error code */
-	movq	$-1, ORIG_RAX(%rsp)		/* no syscall to restart */
-	.else
-	xorl	%esi, %esi			/* no error code */
+	idtentry_part \do_sym, \has_error_code, \read_cr2, paranoid=0
 	.endif
 
-	call	\do_sym
-
-	jmp	error_exit
-	.endif
 _ASM_NOKPROBE(\sym)
 END(\sym)
 .endm
@@ -1007,7 +1025,7 @@ idtentry overflow			do_overflow			has_error_code=0
 idtentry bounds				do_bounds			has_error_code=0
 idtentry invalid_op			do_invalid_op			has_error_code=0
 idtentry device_not_available		do_device_not_available		has_error_code=0
-idtentry double_fault			do_double_fault			has_error_code=1 paranoid=2
+idtentry double_fault			do_double_fault			has_error_code=1 paranoid=2 read_cr2=1
 idtentry coprocessor_segment_overrun	do_coprocessor_segment_overrun	has_error_code=0
 idtentry invalid_TSS			do_invalid_TSS			has_error_code=1
 idtentry segment_not_present		do_segment_not_present		has_error_code=1
@@ -1179,10 +1197,10 @@ idtentry xendebug		do_debug		has_error_code=0
 #endif
 
 idtentry general_protection	do_general_protection	has_error_code=1
-idtentry page_fault		do_page_fault		has_error_code=1
+idtentry page_fault		do_page_fault		has_error_code=1	read_cr2=1
 
 #ifdef CONFIG_KVM_GUEST
-idtentry async_page_fault	do_async_page_fault	has_error_code=1
+idtentry async_page_fault	do_async_page_fault	has_error_code=1	read_cr2=1
 #endif
 
 #ifdef CONFIG_X86_MCE
@@ -1281,18 +1299,9 @@ ENTRY(error_entry)
 	movq	%rax, %rsp			/* switch stack */
 	ENCODE_FRAME_POINTER
 	pushq	%r12
-
-	/*
-	 * We need to tell lockdep that IRQs are off.  We can't do this until
-	 * we fix gsbase, and we should do it before enter_from_user_mode
-	 * (which can take locks).
-	 */
-	TRACE_IRQS_OFF
-	CALL_enter_from_user_mode
 	ret
 
 .Lerror_entry_done:
-	TRACE_IRQS_OFF
 	ret
 
 	/*