Merge tag 'x86-entry-2020-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 conversion to generic entry code from Thomas Gleixner:
 "The conversion of X86 syscall, interrupt and exception entry/exit
  handling to the generic code.

  Pretty much a straight-forward 1:1 conversion plus the consolidation
  of the KVM handling of pending work before entering guest mode"

* tag 'x86-entry-2020-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/kvm: Use __xfer_to_guest_mode_work_pending() in kvm_run_vcpu()
  x86/kvm: Use generic xfer to guest work function
  x86/entry: Cleanup idtentry_enter/exit
  x86/entry: Use generic interrupt entry/exit code
  x86/entry: Cleanup idtentry_entry/exit_user
  x86/entry: Use generic syscall exit functionality
  x86/entry: Use generic syscall entry function
  x86/ptrace: Provide pt_regs helper for entry/exit
  x86/entry: Move user return notifier out of loop
  x86/entry: Consolidate 32/64 bit syscall entry
  x86/entry: Consolidate check_user_regs()
  x86: Correct noinstr qualifiers
  x86/idtentry: Remove stale comment

arch/x86/Kconfig

@@ -115,6 +115,7 @@ config X86
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_EARLY_IOREMAP
+	select GENERIC_ENTRY
 	select GENERIC_FIND_FIRST_BIT
 	select GENERIC_IOMAP
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK	if SMP

arch/x86/entry/entry_32.S

@@ -846,7 +846,7 @@ SYM_CODE_START(ret_from_fork)
 2:
 	/* When we fork, we trace the syscall return in the child, too. */
 	movl    %esp, %eax
-	call    syscall_return_slowpath
+	call    syscall_exit_to_user_mode
 	jmp     .Lsyscall_32_done
 
 	/* kernel thread */

arch/x86/entry/entry_64.S

@@ -283,7 +283,7 @@ SYM_CODE_START(ret_from_fork)
 2:
 	UNWIND_HINT_REGS
 	movq	%rsp, %rdi
-	call	syscall_return_slowpath	/* returns with IRQs disabled */
+	call	syscall_exit_to_user_mode	/* returns with IRQs disabled */
 	jmp	swapgs_restore_regs_and_return_to_usermode
 
 1:

arch/x86/include/asm/entry-common.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_X86_ENTRY_COMMON_H
+#define _ASM_X86_ENTRY_COMMON_H
+
+#include <linux/user-return-notifier.h>
+
+#include <asm/nospec-branch.h>
+#include <asm/io_bitmap.h>
+#include <asm/fpu/api.h>
+
+/* Check that the stack and regs on entry from user mode are sane. */
+static __always_inline void arch_check_user_regs(struct pt_regs *regs)
+{
+	if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) {
+		/*
+		 * Make sure that the entry code gave us a sensible EFLAGS
+		 * register.  Native because we want to check the actual CPU
+		 * state, not the interrupt state as imagined by Xen.
+		 */
+		unsigned long flags = native_save_fl();
+		WARN_ON_ONCE(flags & (X86_EFLAGS_AC | X86_EFLAGS_DF |
+				      X86_EFLAGS_NT));
+
+		/* We think we came from user mode. Make sure pt_regs agrees. */
+		WARN_ON_ONCE(!user_mode(regs));
+
+		/*
+		 * All entries from user mode (except #DF) should be on the
+		 * normal thread stack and should have user pt_regs in the
+		 * correct location.
+		 */
+		WARN_ON_ONCE(!on_thread_stack());
+		WARN_ON_ONCE(regs != task_pt_regs(current));
+	}
+}
+#define arch_check_user_regs arch_check_user_regs
+
+#define ARCH_SYSCALL_EXIT_WORK		(_TIF_SINGLESTEP)
+
+static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
+						  unsigned long ti_work)
+{
+	if (ti_work & _TIF_USER_RETURN_NOTIFY)
+		fire_user_return_notifiers();
+
+	if (unlikely(ti_work & _TIF_IO_BITMAP))
+		tss_update_io_bitmap();
+
+	fpregs_assert_state_consistent();
+	if (unlikely(ti_work & _TIF_NEED_FPU_LOAD))
+		switch_fpu_return();
+
+#ifdef CONFIG_COMPAT
+	/*
+	 * Compat syscalls set TS_COMPAT.  Make sure we clear it before
+	 * returning to user mode.  We need to clear it *after* signal
+	 * handling, because syscall restart has a fixup for compat
+	 * syscalls.  The fixup is exercised by the ptrace_syscall_32
+	 * selftest.
+	 *
+	 * We also need to clear TS_REGS_POKED_I386: the 32-bit tracer
+	 * special case only applies after poking regs and before the
+	 * very next return to user mode.
+	 */
+	current_thread_info()->status &= ~(TS_COMPAT | TS_I386_REGS_POKED);
+#endif
+}
+#define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
+
+static __always_inline void arch_exit_to_user_mode(void)
+{
+	mds_user_clear_cpu_buffers();
+}
+#define arch_exit_to_user_mode arch_exit_to_user_mode
+
+#endif

arch/x86/include/asm/idtentry.h

@@ -6,20 +6,11 @@
 #include <asm/trapnr.h>
 
 #ifndef __ASSEMBLY__
+#include <linux/entry-common.h>
 #include <linux/hardirq.h>
 
 #include <asm/irq_stack.h>
 
-void idtentry_enter_user(struct pt_regs *regs);
-void idtentry_exit_user(struct pt_regs *regs);
-
-typedef struct idtentry_state {
-	bool exit_rcu;
-} idtentry_state_t;
-
-idtentry_state_t idtentry_enter(struct pt_regs *regs);
-void idtentry_exit(struct pt_regs *regs, idtentry_state_t state);
-
 bool idtentry_enter_nmi(struct pt_regs *regs);
 void idtentry_exit_nmi(struct pt_regs *regs, bool irq_state);
 
@@ -52,8 +43,8 @@ void idtentry_exit_nmi(struct pt_regs *regs, bool irq_state);
  * The macro is written so it acts as function definition. Append the
  * body with a pair of curly brackets.
  *
- * idtentry_enter() contains common code which has to be invoked before
- * arbitrary code in the body. idtentry_exit() contains common code
+ * irqentry_enter() contains common code which has to be invoked before
+ * arbitrary code in the body. irqentry_exit() contains common code
  * which has to run before returning to the low level assembly code.
  */
 #define DEFINE_IDTENTRY(func)						\
@@ -61,12 +52,12 @@ static __always_inline void __##func(struct pt_regs *regs);		\
 									\
 __visible noinstr void func(struct pt_regs *regs)			\
 {									\
-	idtentry_state_t state = idtentry_enter(regs);			\
+	irqentry_state_t state = irqentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
 	__##func (regs);						\
 	instrumentation_end();						\
-	idtentry_exit(regs, state);					\
+	irqentry_exit(regs, state);					\
 }									\
 									\
 static __always_inline void __##func(struct pt_regs *regs)
@@ -108,12 +99,12 @@ static __always_inline void __##func(struct pt_regs *regs,		\
 __visible noinstr void func(struct pt_regs *regs,			\
 			    unsigned long error_code)			\
 {									\
-	idtentry_state_t state = idtentry_enter(regs);			\
+	irqentry_state_t state = irqentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
 	__##func (regs, error_code);					\
 	instrumentation_end();						\
-	idtentry_exit(regs, state);					\
+	irqentry_exit(regs, state);					\
 }									\
 									\
 static __always_inline void __##func(struct pt_regs *regs,		\
@@ -168,7 +159,7 @@ __visible noinstr void func(struct pt_regs *regs)
  * body with a pair of curly brackets.
  *
  * Contrary to DEFINE_IDTENTRY_ERRORCODE() this does not invoke the
- * idtentry_enter/exit() helpers before and after the body invocation. This
+ * irqentry_enter/exit() helpers before and after the body invocation. This
  * needs to be done in the body itself if applicable. Use if extra work
  * is required before the enter/exit() helpers are invoked.
  */
@@ -194,11 +185,9 @@ __visible noinstr void func(struct pt_regs *regs, unsigned long error_code)
  * to the function as error_code argument which needs to be truncated
  * to an u8 because the push is sign extending.
  *
- * On 64-bit idtentry_enter/exit() are invoked in the ASM entry code before
- * and after switching to the interrupt stack. On 32-bit this happens in C.
- *
  * irq_enter/exit_rcu() are invoked before the function body and the
- * KVM L1D flush request is set.
+ * KVM L1D flush request is set. Stack switching to the interrupt stack
+ * has to be done in the function body if necessary.
  */
 #define DEFINE_IDTENTRY_IRQ(func)					\
 static __always_inline void __##func(struct pt_regs *regs, u8 vector);	\
@@ -206,7 +195,7 @@ static __always_inline void __##func(struct pt_regs *regs, u8 vector);	\
 __visible noinstr void func(struct pt_regs *regs,			\
 			    unsigned long error_code)			\
 {									\
-	idtentry_state_t state = idtentry_enter(regs);			\
+	irqentry_state_t state = irqentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
 	irq_enter_rcu();						\
@@ -214,7 +203,7 @@ __visible noinstr void func(struct pt_regs *regs,			\
 	__##func (regs, (u8)error_code);				\
 	irq_exit_rcu();							\
 	instrumentation_end();						\
-	idtentry_exit(regs, state);					\
+	irqentry_exit(regs, state);					\
 }									\
 									\
 static __always_inline void __##func(struct pt_regs *regs, u8 vector)
@@ -238,7 +227,7 @@ static __always_inline void __##func(struct pt_regs *regs, u8 vector)
  * DEFINE_IDTENTRY_SYSVEC - Emit code for system vector IDT entry points
  * @func:	Function name of the entry point
  *
- * idtentry_enter/exit() and irq_enter/exit_rcu() are invoked before the
+ * irqentry_enter/exit() and irq_enter/exit_rcu() are invoked before the
  * function body. KVM L1D flush request is set.
  *
  * Runs the function on the interrupt stack if the entry hit kernel mode
@@ -248,7 +237,7 @@ static void __##func(struct pt_regs *regs);				\
 									\
 __visible noinstr void func(struct pt_regs *regs)			\
 {									\
-	idtentry_state_t state = idtentry_enter(regs);			\
+	irqentry_state_t state = irqentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
 	irq_enter_rcu();						\
@@ -256,7 +245,7 @@ __visible noinstr void func(struct pt_regs *regs)			\
 	run_on_irqstack_cond(__##func, regs, regs);			\
 	irq_exit_rcu();							\
 	instrumentation_end();						\
-	idtentry_exit(regs, state);					\
+	irqentry_exit(regs, state);					\
 }									\
 									\
 static noinline void __##func(struct pt_regs *regs)
@@ -277,7 +266,7 @@ static __always_inline void __##func(struct pt_regs *regs);		\
 									\
 __visible noinstr void func(struct pt_regs *regs)			\
 {									\
-	idtentry_state_t state = idtentry_enter(regs);			\
+	irqentry_state_t state = irqentry_enter(regs);			\
 									\
 	instrumentation_begin();					\
 	__irq_enter_raw();						\
@@ -285,7 +274,7 @@ __visible noinstr void func(struct pt_regs *regs)			\
 	__##func (regs);						\
 	__irq_exit_raw();						\
 	instrumentation_end();						\
-	idtentry_exit(regs, state);					\
+	irqentry_exit(regs, state);					\
 }									\
 									\
 static __always_inline void __##func(struct pt_regs *regs)

arch/x86/include/asm/ptrace.h

@@ -209,6 +209,11 @@ static inline void user_stack_pointer_set(struct pt_regs *regs,
 	regs->sp = val;
 }
 
+static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
+{
+	return !(regs->flags & X86_EFLAGS_IF);
+}
+
 /* Query offset/name of register from its name/offset */
 extern int regs_query_register_offset(const char *name);
 extern const char *regs_query_register_name(unsigned int offset);

arch/x86/include/asm/signal.h

@@ -35,7 +35,6 @@ typedef sigset_t compat_sigset_t;
 #endif /* __ASSEMBLY__ */
 #include <uapi/asm/signal.h>
 #ifndef __ASSEMBLY__
-extern void do_signal(struct pt_regs *regs);
 
 #define __ARCH_HAS_SA_RESTORER
 

arch/x86/include/asm/thread_info.h

@@ -133,11 +133,6 @@ struct thread_info {
 #define _TIF_X32		(1 << TIF_X32)
 #define _TIF_FSCHECK		(1 << TIF_FSCHECK)
 
-/* Work to do before invoking the actual syscall. */
-#define _TIF_WORK_SYSCALL_ENTRY	\
-	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT |	\
-	 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT)
-
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW_BASE					\
 	(_TIF_NOCPUID | _TIF_NOTSC | _TIF_BLOCKSTEP |		\

arch/x86/kernel/alternative.c

@@ -1047,7 +1047,7 @@ static __always_inline int patch_cmp(const void *key, const void *elt)
 	return 0;
 }
 
-int noinstr poke_int3_handler(struct pt_regs *regs)
+noinstr int poke_int3_handler(struct pt_regs *regs)
 {
 	struct bp_patching_desc *desc;
 	struct text_poke_loc *tp;

arch/x86/kernel/cpu/mce/core.c

@@ -1215,7 +1215,7 @@ static void kill_me_maybe(struct callback_head *cb)
  * backing the user stack, tracing that reads the user stack will cause
  * potentially infinite recursion.
  */
-void noinstr do_machine_check(struct pt_regs *regs)
+noinstr void do_machine_check(struct pt_regs *regs)
 {
 	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
 	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
@@ -1930,11 +1930,11 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
 
 static __always_inline void exc_machine_check_user(struct pt_regs *regs)
 {
-	idtentry_enter_user(regs);
+	irqentry_enter_from_user_mode(regs);
 	instrumentation_begin();
 	machine_check_vector(regs);
 	instrumentation_end();
-	idtentry_exit_user(regs);
+	irqentry_exit_to_user_mode(regs);
 }
 
 #ifdef CONFIG_X86_64

arch/x86/kernel/kvm.c

@@ -233,7 +233,7 @@ EXPORT_SYMBOL_GPL(kvm_read_and_reset_apf_flags);
 noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
 {
 	u32 reason = kvm_read_and_reset_apf_flags();
-	idtentry_state_t state;
+	irqentry_state_t state;
 
 	switch (reason) {
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
@@ -243,7 +243,7 @@ noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
 		return false;
 	}
 
-	state = idtentry_enter(regs);
+	state = irqentry_enter(regs);
 	instrumentation_begin();
 
 	/*
@@ -264,7 +264,7 @@ noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token)
 	}
 
 	instrumentation_end();
-	idtentry_exit(regs, state);
+	irqentry_exit(regs, state);
 	return true;
 }
 

arch/x86/kernel/signal.c

@@ -25,6 +25,7 @@
 #include <linux/user-return-notifier.h>
 #include <linux/uprobes.h>
 #include <linux/context_tracking.h>
+#include <linux/entry-common.h>
 #include <linux/syscalls.h>
 
 #include <asm/processor.h>
@@ -803,7 +804,7 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
  * want to handle. Thus you cannot kill init even with a SIGKILL even by
  * mistake.
  */
-void do_signal(struct pt_regs *regs)
+void arch_do_signal(struct pt_regs *regs)
 {
 	struct ksignal ksig;
 

arch/x86/kernel/traps.c

@@ -245,7 +245,7 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 
 DEFINE_IDTENTRY_RAW(exc_invalid_op)
 {
-	idtentry_state_t state;
+	irqentry_state_t state;
 
 	/*
 	 * We use UD2 as a short encoding for 'CALL __WARN', as such
@@ -255,11 +255,11 @@ DEFINE_IDTENTRY_RAW(exc_invalid_op)
 	if (!user_mode(regs) && handle_bug(regs))
 		return;
 
-	state = idtentry_enter(regs);
+	state = irqentry_enter(regs);
 	instrumentation_begin();
 	handle_invalid_op(regs);
 	instrumentation_end();
-	idtentry_exit(regs, state);
+	irqentry_exit(regs, state);
 }
 
 DEFINE_IDTENTRY(exc_coproc_segment_overrun)
@@ -638,18 +638,18 @@ DEFINE_IDTENTRY_RAW(exc_int3)
 		return;
 
 	/*
-	 * idtentry_enter_user() uses static_branch_{,un}likely() and therefore
-	 * can trigger INT3, hence poke_int3_handler() must be done
-	 * before. If the entry came from kernel mode, then use nmi_enter()
-	 * because the INT3 could have been hit in any context including
-	 * NMI.
+	 * irqentry_enter_from_user_mode() uses static_branch_{,un}likely()
+	 * and therefore can trigger INT3, hence poke_int3_handler() must
+	 * be done before. If the entry came from kernel mode, then use
+	 * nmi_enter() because the INT3 could have been hit in any context
+	 * including NMI.
 	 */
 	if (user_mode(regs)) {
-		idtentry_enter_user(regs);
+		irqentry_enter_from_user_mode(regs);
 		instrumentation_begin();
 		do_int3_user(regs);
 		instrumentation_end();
-		idtentry_exit_user(regs);
+		irqentry_exit_to_user_mode(regs);
 	} else {
 		bool irq_state = idtentry_enter_nmi(regs);
 		instrumentation_begin();
@@ -895,13 +895,13 @@ static __always_inline void exc_debug_user(struct pt_regs *regs,
 	 */
 	WARN_ON_ONCE(!user_mode(regs));
 
-	idtentry_enter_user(regs);
+	irqentry_enter_from_user_mode(regs);
 	instrumentation_begin();
 
 	handle_debug(regs, dr6, true);
 
 	instrumentation_end();
-	idtentry_exit_user(regs);
+	irqentry_exit_to_user_mode(regs);
 }
 
 #ifdef CONFIG_X86_64

arch/x86/kvm/Kconfig

@@ -42,6 +42,7 @@ config KVM
 	select HAVE_KVM_MSI
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select HAVE_KVM_NO_POLL
+	select KVM_XFER_TO_GUEST_WORK
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_VFIO
 	select SRCU

arch/x86/kvm/vmx/vmx.c

@@ -27,6 +27,7 @@
 #include <linux/slab.h>
 #include <linux/tboot.h>
 #include <linux/trace_events.h>
+#include <linux/entry-kvm.h>
 
 #include <asm/apic.h>
 #include <asm/asm.h>
@@ -5373,14 +5374,12 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 		}
 
 		/*
-		 * Note, return 1 and not 0, vcpu_run() is responsible for
-		 * morphing the pending signal into the proper return code.
+		 * Note, return 1 and not 0, vcpu_run() will invoke
+		 * xfer_to_guest_mode() which will create a proper return
+		 * code.
 		 */
-		if (signal_pending(current))
+		if (__xfer_to_guest_mode_work_pending())
 			return 1;
-
-		if (need_resched())
-			schedule();
 	}
 
 	return 1;

arch/x86/kvm/x86.c

@@ -56,6 +56,7 @@
 #include <linux/sched/stat.h>
 #include <linux/sched/isolation.h>
 #include <linux/mem_encrypt.h>
+#include <linux/entry-kvm.h>
 
 #include <trace/events/kvm.h>
 
@@ -1587,7 +1588,7 @@ EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr);
 bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu)
 {
 	return vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) ||
-		need_resched() || signal_pending(current);
+		xfer_to_guest_mode_work_pending();
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_exit_request);
 
@@ -8681,15 +8682,11 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 			break;
 		}
 
-		if (signal_pending(current)) {
-			r = -EINTR;
-			vcpu->run->exit_reason = KVM_EXIT_INTR;
-			++vcpu->stat.signal_exits;
-			break;
-		}
-		if (need_resched()) {
+		if (__xfer_to_guest_mode_work_pending()) {
 			srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
-			cond_resched();
+			r = xfer_to_guest_mode_handle_work(vcpu);
+			if (r)
+				return r;
 			vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
 		}
 	}

arch/x86/mm/fault.c

@@ -1377,7 +1377,7 @@ handle_page_fault(struct pt_regs *regs, unsigned long error_code,
 DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
 {
 	unsigned long address = read_cr2();
-	idtentry_state_t state;
+	irqentry_state_t state;
 
 	prefetchw(&current->mm->mmap_lock);
 
@@ -1412,11 +1412,11 @@ DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
 	 * code reenabled RCU to avoid subsequent wreckage which helps
 	 * debugability.
 	 */
-	state = idtentry_enter(regs);
+	state = irqentry_enter(regs);
 
 	instrumentation_begin();
 	handle_page_fault(regs, error_code, address);
 	instrumentation_end();
 
-	idtentry_exit(regs, state);
+	irqentry_exit(regs, state);
 }