x86/entry: Switch page fault exception to IDTENTRY_RAW

Convert page fault exceptions to IDTENTRY_RAW:

  - Implement the C entry point with DEFINE_IDTENTRY_RAW
  - Add the CR2 read into the exception handler
  - Add the idtentry_enter/exit_cond_rcu() invocations in
    in the regular page fault handler and in the async PF
    part.
  - Emit the ASM stub with DECLARE_IDTENTRY_RAW
  - Remove the ASM idtentry in 64-bit
  - Remove the CR2 read from 64-bit
  - Remove the open coded ASM entry code in 32-bit
  - Fix up the XEN/PV code
  - Remove the old prototypes

No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/r/20200521202118.238455120@linutronix.de

arch/x86/entry/entry_32.S

@@ -1398,36 +1398,6 @@ BUILD_INTERRUPT3(hv_stimer0_callback_vector, HYPERV_STIMER0_VECTOR,
 
 #endif /* CONFIG_HYPERV */
 
-SYM_CODE_START(page_fault)
-	ASM_CLAC
-	pushl	$do_page_fault
-	jmp	common_exception_read_cr2
-SYM_CODE_END(page_fault)
-
-SYM_CODE_START_LOCAL_NOALIGN(common_exception_read_cr2)
-	/* the function address is in %gs's slot on the stack */
-	SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1
-
-	ENCODE_FRAME_POINTER
-
-	/* fixup %gs */
-	GS_TO_REG %ecx
-	movl	PT_GS(%esp), %edi
-	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_NOSPEC edi
-	jmp	ret_from_exception
-SYM_CODE_END(common_exception_read_cr2)
-
 SYM_CODE_START_LOCAL_NOALIGN(common_exception)
 	/* the function address is in %gs's slot on the stack */
 	SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1

arch/x86/entry/entry_64.S

@@ -506,15 +506,6 @@ SYM_CODE_END(spurious_entries_start)
 	call	error_entry
 	UNWIND_HINT_REGS
 
-	.if \vector == X86_TRAP_PF
-		/*
-		 * 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 \sane == 0
 	TRACE_IRQS_OFF
 
@@ -533,10 +524,6 @@ SYM_CODE_END(spurious_entries_start)
 		movq	$-1, ORIG_RAX(%rsp)	/* no syscall to restart */
 	.endif
 
-	.if \vector == X86_TRAP_PF
-		movq	%r12, %rdx		/* Move CR2 into 3rd argument */
-	.endif
-
 	call	\cfunc
 
 	.if \sane == 0
@@ -1059,12 +1046,6 @@ apicinterrupt SPURIOUS_APIC_VECTOR		spurious_interrupt		smp_spurious_interrupt
 apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
 #endif
 
-/*
- * Exception entry points.
- */
-
-idtentry	X86_TRAP_PF		page_fault		do_page_fault			has_error_code=1
-
 /*
  * Reload gs selector with exception handling
  * edi:  new selector

arch/x86/include/asm/idtentry.h

@@ -388,6 +388,7 @@ DECLARE_IDTENTRY_ERRORCODE(X86_TRAP_AC,	exc_alignment_check);
 
 /* Raw exception entries which need extra work */
 DECLARE_IDTENTRY_RAW(X86_TRAP_BP,		exc_int3);
+DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_PF,	exc_page_fault);
 
 #ifdef CONFIG_X86_MCE
 DECLARE_IDTENTRY_MCE(X86_TRAP_MC,	exc_machine_check);

arch/x86/include/asm/traps.h

@@ -9,17 +9,6 @@
 #include <asm/idtentry.h>
 #include <asm/siginfo.h>			/* TRAP_TRACE, ... */
 
-#define dotraplinkage __visible
-
-asmlinkage void page_fault(void);
-asmlinkage void async_page_fault(void);
-
-#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV)
-asmlinkage void xen_page_fault(void);
-#endif
-
-dotraplinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address);
-
 #ifdef CONFIG_X86_64
 asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs);
 asmlinkage __visible notrace

arch/x86/kernel/idt.c

@@ -62,7 +62,7 @@ static const __initconst struct idt_data early_idts[] = {
 	INTG(X86_TRAP_DB,		asm_exc_debug),
 	SYSG(X86_TRAP_BP,		asm_exc_int3),
 #ifdef CONFIG_X86_32
-	INTG(X86_TRAP_PF,		page_fault),
+	INTG(X86_TRAP_PF,		asm_exc_page_fault),
 #endif
 };
 
@@ -156,7 +156,7 @@ static const __initconst struct idt_data apic_idts[] = {
  * stacks work only after cpu_init().
  */
 static const __initconst struct idt_data early_pf_idts[] = {
-	INTG(X86_TRAP_PF,		page_fault),
+	INTG(X86_TRAP_PF,		asm_exc_page_fault),
 };
 
 /*

arch/x86/kernel/kvm.c

@@ -218,7 +218,7 @@ void kvm_async_pf_task_wake(u32 token)
 }
 EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake);
 
-u32 kvm_read_and_reset_apf_flags(void)
+noinstr u32 kvm_read_and_reset_apf_flags(void)
 {
 	u32 flags = 0;
 
@@ -230,11 +230,11 @@ u32 kvm_read_and_reset_apf_flags(void)
 	return flags;
 }
 EXPORT_SYMBOL_GPL(kvm_read_and_reset_apf_flags);
-NOKPROBE_SYMBOL(kvm_read_and_reset_apf_flags);
 
-bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
+noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
 {
 	u32 reason = kvm_read_and_reset_apf_flags();
+	bool rcu_exit;
 
 	switch (reason) {
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
@@ -244,6 +244,9 @@ bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
 		return false;
 	}
 
+	rcu_exit = idtentry_enter_cond_rcu(regs);
+	instrumentation_begin();
+
 	/*
 	 * If the host managed to inject an async #PF into an interrupt
 	 * disabled region, then die hard as this is not going to end well
@@ -258,13 +261,13 @@ bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
 		/* Page is swapped out by the host. */
 		kvm_async_pf_task_wait_schedule(token);
 	} else {
-		rcu_irq_enter();
 		kvm_async_pf_task_wake(token);
-		rcu_irq_exit();
 	}
+
+	instrumentation_end();
+	idtentry_exit_cond_rcu(regs, rcu_exit);
 	return true;
 }
-NOKPROBE_SYMBOL(__kvm_handle_async_pf);
 
 static void __init paravirt_ops_setup(void)
 {

arch/x86/mm/fault.c

@@ -1357,11 +1357,38 @@ trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code,
 		trace_page_fault_kernel(address, regs, error_code);
 }
 
-dotraplinkage void
-do_page_fault(struct pt_regs *regs, unsigned long hw_error_code,
+static __always_inline void
+handle_page_fault(struct pt_regs *regs, unsigned long error_code,
 			      unsigned long address)
 {
+	trace_page_fault_entries(regs, error_code, address);
+
+	if (unlikely(kmmio_fault(regs, address)))
+		return;
+
+	/* Was the fault on kernel-controlled part of the address space? */
+	if (unlikely(fault_in_kernel_space(address))) {
+		do_kern_addr_fault(regs, error_code, address);
+	} else {
+		do_user_addr_fault(regs, error_code, address);
+		/*
+		 * User address page fault handling might have reenabled
+		 * interrupts. Fixing up all potential exit points of
+		 * do_user_addr_fault() and its leaf functions is just not
+		 * doable w/o creating an unholy mess or turning the code
+		 * upside down.
+		 */
+		local_irq_disable();
+	}
+}
+
+DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
+{
+	unsigned long address = read_cr2();
+	bool rcu_exit;
+
 	prefetchw(&current->mm->mmap_lock);
+
 	/*
 	 * KVM has two types of events that are, logically, interrupts, but
 	 * are unfortunately delivered using the #PF vector.  These events are
@@ -1376,28 +1403,28 @@ do_page_fault(struct pt_regs *regs, unsigned long hw_error_code,
 	 * getting values from real and async page faults mixed up.
 	 *
 	 * Fingers crossed.
+	 *
+	 * The async #PF handling code takes care of idtentry handling
+	 * itself.
 	 */
 	if (kvm_handle_async_pf(regs, (u32)address))
 		return;
 
-	trace_page_fault_entries(regs, hw_error_code, address);
-
-	if (unlikely(kmmio_fault(regs, address)))
-		return;
-
-	/* Was the fault on kernel-controlled part of the address space? */
-	if (unlikely(fault_in_kernel_space(address))) {
-		do_kern_addr_fault(regs, hw_error_code, address);
-	} else {
-		do_user_addr_fault(regs, hw_error_code, address);
 	/*
-		 * User address page fault handling might have reenabled
-		 * interrupts. Fixing up all potential exit points of
-		 * do_user_addr_fault() and its leaf functions is just not
-		 * doable w/o creating an unholy mess or turning the code
-		 * upside down.
+	 * Entry handling for valid #PF from kernel mode is slightly
+	 * different: RCU is already watching and rcu_irq_enter() must not
+	 * be invoked because a kernel fault on a user space address might
+	 * sleep.
+	 *
+	 * In case the fault hit a RCU idle region the conditional entry
+	 * code reenabled RCU to avoid subsequent wreckage which helps
+	 * debugability.
 	 */
-		local_irq_disable();
-	}
+	rcu_exit = idtentry_enter_cond_rcu(regs);
+
+	instrumentation_begin();
+	handle_page_fault(regs, error_code, address);
+	instrumentation_end();
+
+	idtentry_exit_cond_rcu(regs, rcu_exit);
 }
-NOKPROBE_SYMBOL(do_page_fault);

arch/x86/xen/enlighten_pv.c

@@ -626,7 +626,7 @@ static struct trap_array_entry trap_array[] = {
 #ifdef CONFIG_IA32_EMULATION
 	{ entry_INT80_compat,          xen_entry_INT80_compat,          false },
 #endif
-	{ page_fault,                  xen_page_fault,                  false },
+	TRAP_ENTRY(exc_page_fault,			false ),
 	TRAP_ENTRY(exc_divide_error,			false ),
 	TRAP_ENTRY(exc_bounds,				false ),
 	TRAP_ENTRY(exc_invalid_op,			false ),

arch/x86/xen/xen-asm_64.S

@@ -43,7 +43,7 @@ xen_pv_trap asm_exc_invalid_tss
 xen_pv_trap asm_exc_segment_not_present
 xen_pv_trap asm_exc_stack_segment
 xen_pv_trap asm_exc_general_protection
-xen_pv_trap page_fault
+xen_pv_trap asm_exc_page_fault
 xen_pv_trap asm_exc_spurious_interrupt_bug
 xen_pv_trap asm_exc_coprocessor_error
 xen_pv_trap asm_exc_alignment_check