Merge tag 'x86-entry-2020-06-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 entry updates from Thomas Gleixner:
 "The x86 entry, exception and interrupt code rework

  This all started about 6 month ago with the attempt to move the Posix
  CPU timer heavy lifting out of the timer interrupt code and just have
  lockless quick checks in that code path. Trivial 5 patches.

  This unearthed an inconsistency in the KVM handling of task work and
  the review requested to move all of this into generic code so other
  architectures can share.

  Valid request and solved with another 25 patches but those unearthed
  inconsistencies vs. RCU and instrumentation.

  Digging into this made it obvious that there are quite some
  inconsistencies vs. instrumentation in general. The int3 text poke
  handling in particular was completely unprotected and with the batched
  update of trace events even more likely to expose to endless int3
  recursion.

  In parallel the RCU implications of instrumenting fragile entry code
  came up in several discussions.

  The conclusion of the x86 maintainer team was to go all the way and
  make the protection against any form of instrumentation of fragile and
  dangerous code pathes enforcable and verifiable by tooling.

  A first batch of preparatory work hit mainline with commit
  d5f744f9a2ac ("Pull x86 entry code updates from Thomas Gleixner")

  That (almost) full solution introduced a new code section
  '.noinstr.text' into which all code which needs to be protected from
  instrumentation of all sorts goes into. Any call into instrumentable
  code out of this section has to be annotated. objtool has support to
  validate this.

  Kprobes now excludes this section fully which also prevents BPF from
  fiddling with it and all 'noinstr' annotated functions also keep
  ftrace off. The section, kprobes and objtool changes are already
  merged.

  The major changes coming with this are:

    - Preparatory cleanups

    - Annotating of relevant functions to move them into the
      noinstr.text section or enforcing inlining by marking them
      __always_inline so the compiler cannot misplace or instrument
      them.

    - Splitting and simplifying the idtentry macro maze so that it is
      now clearly separated into simple exception entries and the more
      interesting ones which use interrupt stacks and have the paranoid
      handling vs. CR3 and GS.

    - Move quite some of the low level ASM functionality into C code:

       - enter_from and exit to user space handling. The ASM code now
         calls into C after doing the really necessary ASM handling and
         the return path goes back out without bells and whistels in
         ASM.

       - exception entry/exit got the equivivalent treatment

       - move all IRQ tracepoints from ASM to C so they can be placed as
         appropriate which is especially important for the int3
         recursion issue.

    - Consolidate the declaration and definition of entry points between
      32 and 64 bit. They share a common header and macros now.

    - Remove the extra device interrupt entry maze and just use the
      regular exception entry code.

    - All ASM entry points except NMI are now generated from the shared
      header file and the corresponding macros in the 32 and 64 bit
      entry ASM.

    - The C code entry points are consolidated as well with the help of
      DEFINE_IDTENTRY*() macros. This allows to ensure at one central
      point that all corresponding entry points share the same
      semantics. The actual function body for most entry points is in an
      instrumentable and sane state.

      There are special macros for the more sensitive entry points, e.g.
      INT3 and of course the nasty paranoid #NMI, #MCE, #DB and #DF.
      They allow to put the whole entry instrumentation and RCU handling
      into safe places instead of the previous pray that it is correct
      approach.

    - The INT3 text poke handling is now completely isolated and the
      recursion issue banned. Aside of the entry rework this required
      other isolation work, e.g. the ability to force inline bsearch.

    - Prevent #DB on fragile entry code, entry relevant memory and
      disable it on NMI, #MC entry, which allowed to get rid of the
      nested #DB IST stack shifting hackery.

    - A few other cleanups and enhancements which have been made
      possible through this and already merged changes, e.g.
      consolidating and further restricting the IDT code so the IDT
      table becomes RO after init which removes yet another popular
      attack vector

    - About 680 lines of ASM maze are gone.

  There are a few open issues:

   - An escape out of the noinstr section in the MCE handler which needs
     some more thought but under the aspect that MCE is a complete
     trainwreck by design and the propability to survive it is low, this
     was not high on the priority list.

   - Paravirtualization

     When PV is enabled then objtool complains about a bunch of indirect
     calls out of the noinstr section. There are a few straight forward
     ways to fix this, but the other issues vs. general correctness were
     more pressing than parawitz.

   - KVM

     KVM is inconsistent as well. Patches have been posted, but they
     have not yet been commented on or picked up by the KVM folks.

   - IDLE

     Pretty much the same problems can be found in the low level idle
     code especially the parts where RCU stopped watching. This was
     beyond the scope of the more obvious and exposable problems and is
     on the todo list.

  The lesson learned from this brain melting exercise to morph the
  evolved code base into something which can be validated and understood
  is that once again the violation of the most important engineering
  principle "correctness first" has caused quite a few people to spend
  valuable time on problems which could have been avoided in the first
  place. The "features first" tinkering mindset really has to stop.

  With that I want to say thanks to everyone involved in contributing to
  this effort. Special thanks go to the following people (alphabetical
  order): Alexandre Chartre, Andy Lutomirski, Borislav Petkov, Brian
  Gerst, Frederic Weisbecker, Josh Poimboeuf, Juergen Gross, Lai
  Jiangshan, Macro Elver, Paolo Bonzin,i Paul McKenney, Peter Zijlstra,
  Vitaly Kuznetsov, and Will Deacon"

* tag 'x86-entry-2020-06-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (142 commits)
  x86/entry: Force rcu_irq_enter() when in idle task
  x86/entry: Make NMI use IDTENTRY_RAW
  x86/entry: Treat BUG/WARN as NMI-like entries
  x86/entry: Unbreak __irqentry_text_start/end magic
  x86/entry: __always_inline CR2 for noinstr
  lockdep: __always_inline more for noinstr
  x86/entry: Re-order #DB handler to avoid *SAN instrumentation
  x86/entry: __always_inline arch_atomic_* for noinstr
  x86/entry: __always_inline irqflags for noinstr
  x86/entry: __always_inline debugreg for noinstr
  x86/idt: Consolidate idt functionality
  x86/idt: Cleanup trap_init()
  x86/idt: Use proper constants for table size
  x86/idt: Add comments about early #PF handling
  x86/idt: Mark init only functions __init
  x86/entry: Rename trace_hardirqs_off_prepare()
  x86/entry: Clarify irq_{enter,exit}_rcu()
  x86/entry: Remove DBn stacks
  x86/entry: Remove debug IDT frobbing
  x86/entry: Optimize local_db_save() for virt
  ...

7 files changed, 761 insertions, 1106 deletions

diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index 85eb381259c2..b7a5790d8d63 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -3,7 +3,13 @@
 # Makefile for the x86 low level entry code
 #
 
-OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y
+KASAN_SANITIZE := n
+UBSAN_SANITIZE := n
+KCOV_INSTRUMENT := n
+
+CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_syscall_32.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_syscall_64.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong
 
 CFLAGS_syscall_64.o		+= $(call cc-option,-Wno-override-init,)
 CFLAGS_syscall_32.o		+= $(call cc-option,-Wno-override-init,)
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 1c7f13bb6728..4208c1e3f601 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -341,30 +341,13 @@ For 32-bit we have the following conventions - kernel is built with
 #endif
 .endm
 
-#endif /* CONFIG_X86_64 */
+#else /* CONFIG_X86_64 */
+# undef		UNWIND_HINT_IRET_REGS
+# define	UNWIND_HINT_IRET_REGS
+#endif /* !CONFIG_X86_64 */
 
 .macro STACKLEAK_ERASE
 #ifdef CONFIG_GCC_PLUGIN_STACKLEAK
 	call stackleak_erase
 #endif
 .endm
-
-/*
- * This does 'call enter_from_user_mode' unless we can avoid it based on
- * kernel config or using the static jump infrastructure.
- */
-.macro CALL_enter_from_user_mode
-#ifdef CONFIG_CONTEXT_TRACKING
-#ifdef CONFIG_JUMP_LABEL
-	STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_key, def=0
-#endif
-	call enter_from_user_mode
-.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/common.c b/arch/x86/entry/common.c
index 76735ec813e6..bd3f14175193 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -27,6 +27,11 @@
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
 
+#ifdef CONFIG_XEN_PV
+#include <xen/xen-ops.h>
+#include <xen/events.h>
+#endif
+
 #include <asm/desc.h>
 #include <asm/traps.h>
 #include <asm/vdso.h>
@@ -35,21 +40,67 @@
 #include <asm/nospec-branch.h>
 #include <asm/io_bitmap.h>
 #include <asm/syscall.h>
+#include <asm/irq_stack.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
 #ifdef CONFIG_CONTEXT_TRACKING
-/* Called on entry from user mode with IRQs off. */
-__visible inline void enter_from_user_mode(void)
+/**
+ * enter_from_user_mode - Establish state when coming from user mode
+ *
+ * Syscall entry disables interrupts, but user mode is traced as interrupts
+ * enabled. Also with NO_HZ_FULL RCU might be idle.
+ *
+ * 1) Tell lockdep that interrupts are disabled
+ * 2) Invoke context tracking if enabled to reactivate RCU
+ * 3) Trace interrupts off state
+ */
+static noinstr void enter_from_user_mode(void)
 {
-	CT_WARN_ON(ct_state() != CONTEXT_USER);
+	enum ctx_state state = ct_state();
+
+	lockdep_hardirqs_off(CALLER_ADDR0);
 	user_exit_irqoff();
+
+	instrumentation_begin();
+	CT_WARN_ON(state != CONTEXT_USER);
+	trace_hardirqs_off_finish();
+	instrumentation_end();
 }
 #else
-static inline void enter_from_user_mode(void) {}
+static __always_inline void enter_from_user_mode(void)
+{
+	lockdep_hardirqs_off(CALLER_ADDR0);
+	instrumentation_begin();
+	trace_hardirqs_off_finish();
+	instrumentation_end();
+}
 #endif
 
+/**
+ * exit_to_user_mode - Fixup state when exiting to user mode
+ *
+ * Syscall exit enables interrupts, but the kernel state is interrupts
+ * disabled when this is invoked. Also tell RCU about it.
+ *
+ * 1) Trace interrupts on state
+ * 2) Invoke context tracking if enabled to adjust RCU state
+ * 3) Clear CPU buffers if CPU is affected by MDS and the migitation is on.
+ * 4) Tell lockdep that interrupts are enabled
+ */
+static __always_inline void exit_to_user_mode(void)
+{
+	instrumentation_begin();
+	trace_hardirqs_on_prepare();
+	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+	instrumentation_end();
+
+	user_enter_irqoff();
+	mds_user_clear_cpu_buffers();
+	lockdep_hardirqs_on(CALLER_ADDR0);
+}
+
 static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
 {
 #ifdef CONFIG_X86_64
@@ -179,8 +230,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 	}
 }
 
-/* Called with IRQs disabled. */
-__visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
+static void __prepare_exit_to_usermode(struct pt_regs *regs)
 {
 	struct thread_info *ti = current_thread_info();
 	u32 cached_flags;
@@ -219,10 +269,14 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 	 */
 	ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED);
 #endif
+}
 
-	user_enter_irqoff();
-
-	mds_user_clear_cpu_buffers();
+__visible noinstr void prepare_exit_to_usermode(struct pt_regs *regs)
+{
+	instrumentation_begin();
+	__prepare_exit_to_usermode(regs);
+	instrumentation_end();
+	exit_to_user_mode();
 }
 
 #define SYSCALL_EXIT_WORK_FLAGS				\
@@ -251,11 +305,7 @@ static void syscall_slow_exit_work(struct pt_regs *regs, u32 cached_flags)
 		tracehook_report_syscall_exit(regs, step);
 }
 
-/*
- * Called with IRQs on and fully valid regs.  Returns with IRQs off in a
- * state such that we can immediately switch to user mode.
- */
-__visible inline void syscall_return_slowpath(struct pt_regs *regs)
+static void __syscall_return_slowpath(struct pt_regs *regs)
 {
 	struct thread_info *ti = current_thread_info();
 	u32 cached_flags = READ_ONCE(ti->flags);
@@ -276,15 +326,29 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs)
 		syscall_slow_exit_work(regs, cached_flags);
 
 	local_irq_disable();
-	prepare_exit_to_usermode(regs);
+	__prepare_exit_to_usermode(regs);
+}
+
+/*
+ * Called with IRQs on and fully valid regs.  Returns with IRQs off in a
+ * state such that we can immediately switch to user mode.
+ */
+__visible noinstr void syscall_return_slowpath(struct pt_regs *regs)
+{
+	instrumentation_begin();
+	__syscall_return_slowpath(regs);
+	instrumentation_end();
+	exit_to_user_mode();
 }
 
 #ifdef CONFIG_X86_64
-__visible void do_syscall_64(unsigned long nr, struct pt_regs *regs)
+__visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs)
 {
 	struct thread_info *ti;
 
 	enter_from_user_mode();
+	instrumentation_begin();
+
 	local_irq_enable();
 	ti = current_thread_info();
 	if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY)
@@ -301,8 +365,10 @@ __visible void do_syscall_64(unsigned long nr, struct pt_regs *regs)
 		regs->ax = x32_sys_call_table[nr](regs);
 #endif
 	}
+	__syscall_return_slowpath(regs);
 
-	syscall_return_slowpath(regs);
+	instrumentation_end();
+	exit_to_user_mode();
 }
 #endif
 
@@ -313,7 +379,7 @@ __visible void do_syscall_64(unsigned long nr, struct pt_regs *regs)
  * extremely hot in workloads that use it, and it's usually called from
  * do_fast_syscall_32, so forcibly inline it to improve performance.
  */
-static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
+static void do_syscall_32_irqs_on(struct pt_regs *regs)
 {
 	struct thread_info *ti = current_thread_info();
 	unsigned int nr = (unsigned int)regs->orig_ax;
@@ -337,27 +403,62 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
 		regs->ax = ia32_sys_call_table[nr](regs);
 	}
 
-	syscall_return_slowpath(regs);
+	__syscall_return_slowpath(regs);
 }
 
 /* Handles int $0x80 */
-__visible void do_int80_syscall_32(struct pt_regs *regs)
+__visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 {
 	enter_from_user_mode();
+	instrumentation_begin();
+
 	local_irq_enable();
 	do_syscall_32_irqs_on(regs);
+
+	instrumentation_end();
+	exit_to_user_mode();
+}
+
+static bool __do_fast_syscall_32(struct pt_regs *regs)
+{
+	int res;
+
+	/* Fetch EBP from where the vDSO stashed it. */
+	if (IS_ENABLED(CONFIG_X86_64)) {
+		/*
+		 * Micro-optimization: the pointer we're following is
+		 * explicitly 32 bits, so it can't be out of range.
+		 */
+		res = __get_user(*(u32 *)&regs->bp,
+			 (u32 __user __force *)(unsigned long)(u32)regs->sp);
+	} else {
+		res = get_user(*(u32 *)&regs->bp,
+		       (u32 __user __force *)(unsigned long)(u32)regs->sp);
+	}
+
+	if (res) {
+		/* User code screwed up. */
+		regs->ax = -EFAULT;
+		local_irq_disable();
+		__prepare_exit_to_usermode(regs);
+		return false;
+	}
+
+	/* Now this is just like a normal syscall. */
+	do_syscall_32_irqs_on(regs);
+	return true;
 }
 
 /* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
-__visible long do_fast_syscall_32(struct pt_regs *regs)
+__visible noinstr long do_fast_syscall_32(struct pt_regs *regs)
 {
 	/*
 	 * Called using the internal vDSO SYSENTER/SYSCALL32 calling
 	 * convention.  Adjust regs so it looks like we entered using int80.
 	 */
-
 	unsigned long landing_pad = (unsigned long)current->mm->context.vdso +
-		vdso_image_32.sym_int80_landing_pad;
+					vdso_image_32.sym_int80_landing_pad;
+	bool success;
 
 	/*
 	 * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
@@ -367,33 +468,17 @@ __visible long do_fast_syscall_32(struct pt_regs *regs)
 	regs->ip = landing_pad;
 
 	enter_from_user_mode();
+	instrumentation_begin();
 
 	local_irq_enable();
+	success = __do_fast_syscall_32(regs);
 
-	/* Fetch EBP from where the vDSO stashed it. */
-	if (
-#ifdef CONFIG_X86_64
-		/*
-		 * Micro-optimization: the pointer we're following is explicitly
-		 * 32 bits, so it can't be out of range.
-		 */
-		__get_user(*(u32 *)&regs->bp,
-			    (u32 __user __force *)(unsigned long)(u32)regs->sp)
-#else
-		get_user(*(u32 *)&regs->bp,
-			 (u32 __user __force *)(unsigned long)(u32)regs->sp)
-#endif
-		) {
-
-		/* User code screwed up. */
-		local_irq_disable();
-		regs->ax = -EFAULT;
-		prepare_exit_to_usermode(regs);
-		return 0;	/* Keep it simple: use IRET. */
-	}
+	instrumentation_end();
+	exit_to_user_mode();
 
-	/* Now this is just like a normal syscall. */
-	do_syscall_32_irqs_on(regs);
+	/* If it failed, keep it simple: use IRET. */
+	if (!success)
+		return 0;
 
 #ifdef CONFIG_X86_64
 	/*
@@ -431,3 +516,266 @@ SYSCALL_DEFINE0(ni_syscall)
 {
 	return -ENOSYS;
 }
+
+/**
+ * idtentry_enter_cond_rcu - Handle state tracking on idtentry with conditional
+ *			     RCU handling
+ * @regs:	Pointer to pt_regs of interrupted context
+ *
+ * Invokes:
+ *  - lockdep irqflag state tracking as low level ASM entry disabled
+ *    interrupts.
+ *
+ *  - Context tracking if the exception hit user mode.
+ *
+ *  - The hardirq tracer to keep the state consistent as low level ASM
+ *    entry disabled interrupts.
+ *
+ * For kernel mode entries RCU handling is done conditional. If RCU is
+ * watching then the only RCU requirement is to check whether the tick has
+ * to be restarted. If RCU is not watching then rcu_irq_enter() has to be
+ * invoked on entry and rcu_irq_exit() on exit.
+ *
+ * Avoiding the rcu_irq_enter/exit() calls is an optimization but also
+ * solves the problem of kernel mode pagefaults which can schedule, which
+ * is not possible after invoking rcu_irq_enter() without undoing it.
+ *
+ * For user mode entries enter_from_user_mode() must be invoked to
+ * establish the proper context for NOHZ_FULL. Otherwise scheduling on exit
+ * would not be possible.
+ *
+ * Returns: True if RCU has been adjusted on a kernel entry
+ *	    False otherwise
+ *
+ * The return value must be fed into the rcu_exit argument of
+ * idtentry_exit_cond_rcu().
+ */
+bool noinstr idtentry_enter_cond_rcu(struct pt_regs *regs)
+{
+	if (user_mode(regs)) {
+		enter_from_user_mode();
+		return false;
+	}
+
+	/*
+	 * If this entry hit the idle task invoke rcu_irq_enter() whether
+	 * RCU is watching or not.
+	 *
+	 * Interupts can nest when the first interrupt invokes softirq
+	 * processing on return which enables interrupts.
+	 *
+	 * Scheduler ticks in the idle task can mark quiescent state and
+	 * terminate a grace period, if and only if the timer interrupt is
+	 * not nested into another interrupt.
+	 *
+	 * Checking for __rcu_is_watching() here would prevent the nesting
+	 * interrupt to invoke rcu_irq_enter(). If that nested interrupt is
+	 * the tick then rcu_flavor_sched_clock_irq() would wrongfully
+	 * assume that it is the first interupt and eventually claim
+	 * quiescient state and end grace periods prematurely.
+	 *
+	 * Unconditionally invoke rcu_irq_enter() so RCU state stays
+	 * consistent.
+	 *
+	 * TINY_RCU does not support EQS, so let the compiler eliminate
+	 * this part when enabled.
+	 */
+	if (!IS_ENABLED(CONFIG_TINY_RCU) && is_idle_task(current)) {
+		/*
+		 * If RCU is not watching then the same careful
+		 * sequence vs. lockdep and tracing is required
+		 * as in enter_from_user_mode().
+		 */
+		lockdep_hardirqs_off(CALLER_ADDR0);
+		rcu_irq_enter();
+		instrumentation_begin();
+		trace_hardirqs_off_finish();
+		instrumentation_end();
+
+		return true;
+	}
+
+	/*
+	 * If RCU is watching then RCU only wants to check whether it needs
+	 * to restart the tick in NOHZ mode. rcu_irq_enter_check_tick()
+	 * already contains a warning when RCU is not watching, so no point
+	 * in having another one here.
+	 */
+	instrumentation_begin();
+	rcu_irq_enter_check_tick();
+	/* Use the combo lockdep/tracing function */
+	trace_hardirqs_off();
+	instrumentation_end();
+
+	return false;
+}
+
+static void idtentry_exit_cond_resched(struct pt_regs *regs, bool may_sched)
+{
+	if (may_sched && !preempt_count()) {
+		/* Sanity check RCU and thread stack */
+		rcu_irq_exit_check_preempt();
+		if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
+			WARN_ON_ONCE(!on_thread_stack());
+		if (need_resched())
+			preempt_schedule_irq();
+	}
+	/* Covers both tracing and lockdep */
+	trace_hardirqs_on();
+}
+
+/**
+ * idtentry_exit_cond_rcu - Handle return from exception with conditional RCU
+ *			    handling
+ * @regs:	Pointer to pt_regs (exception entry regs)
+ * @rcu_exit:	Invoke rcu_irq_exit() if true
+ *
+ * Depending on the return target (kernel/user) this runs the necessary
+ * preemption and work checks if possible and reguired and returns to
+ * the caller with interrupts disabled and no further work pending.
+ *
+ * This is the last action before returning to the low level ASM code which
+ * just needs to return to the appropriate context.
+ *
+ * Counterpart to idtentry_enter_cond_rcu(). The return value of the entry
+ * function must be fed into the @rcu_exit argument.
+ */
+void noinstr idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit)
+{
+	lockdep_assert_irqs_disabled();
+
+	/* Check whether this returns to user mode */
+	if (user_mode(regs)) {
+		prepare_exit_to_usermode(regs);
+	} else if (regs->flags & X86_EFLAGS_IF) {
+		/*
+		 * If RCU was not watching on entry this needs to be done
+		 * carefully and needs the same ordering of lockdep/tracing
+		 * and RCU as the return to user mode path.
+		 */
+		if (rcu_exit) {
+			instrumentation_begin();
+			/* Tell the tracer that IRET will enable interrupts */
+			trace_hardirqs_on_prepare();
+			lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+			instrumentation_end();
+			rcu_irq_exit();
+			lockdep_hardirqs_on(CALLER_ADDR0);
+			return;
+		}
+
+		instrumentation_begin();
+		idtentry_exit_cond_resched(regs, IS_ENABLED(CONFIG_PREEMPTION));
+		instrumentation_end();
+	} else {
+		/*
+		 * IRQ flags state is correct already. Just tell RCU if it
+		 * was not watching on entry.
+		 */
+		if (rcu_exit)
+			rcu_irq_exit();
+	}
+}
+
+/**
+ * idtentry_enter_user - Handle state tracking on idtentry from user mode
+ * @regs:	Pointer to pt_regs of interrupted context
+ *
+ * Invokes enter_from_user_mode() to establish the proper context for
+ * NOHZ_FULL. Otherwise scheduling on exit would not be possible.
+ */
+void noinstr idtentry_enter_user(struct pt_regs *regs)
+{
+	enter_from_user_mode();
+}
+
+/**
+ * idtentry_exit_user - Handle return from exception to user mode
+ * @regs:	Pointer to pt_regs (exception entry regs)
+ *
+ * Runs the necessary preemption and work checks and returns to the caller
+ * with interrupts disabled and no further work pending.
+ *
+ * This is the last action before returning to the low level ASM code which
+ * just needs to return to the appropriate context.
+ *
+ * Counterpart to idtentry_enter_user().
+ */
+void noinstr idtentry_exit_user(struct pt_regs *regs)
+{
+	lockdep_assert_irqs_disabled();
+
+	prepare_exit_to_usermode(regs);
+}
+
+#ifdef CONFIG_XEN_PV
+#ifndef CONFIG_PREEMPTION
+/*
+ * Some hypercalls issued by the toolstack can take many 10s of
+ * seconds. Allow tasks running hypercalls via the privcmd driver to
+ * be voluntarily preempted even if full kernel preemption is
+ * disabled.
+ *
+ * Such preemptible hypercalls are bracketed by
+ * xen_preemptible_hcall_begin() and xen_preemptible_hcall_end()
+ * calls.
+ */
+DEFINE_PER_CPU(bool, xen_in_preemptible_hcall);
+EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall);
+
+/*
+ * In case of scheduling the flag must be cleared and restored after
+ * returning from schedule as the task might move to a different CPU.
+ */
+static __always_inline bool get_and_clear_inhcall(void)
+{
+	bool inhcall = __this_cpu_read(xen_in_preemptible_hcall);
+
+	__this_cpu_write(xen_in_preemptible_hcall, false);
+	return inhcall;
+}
+
+static __always_inline void restore_inhcall(bool inhcall)
+{
+	__this_cpu_write(xen_in_preemptible_hcall, inhcall);
+}
+#else
+static __always_inline bool get_and_clear_inhcall(void) { return false; }
+static __always_inline void restore_inhcall(bool inhcall) { }
+#endif
+
+static void __xen_pv_evtchn_do_upcall(void)
+{
+	irq_enter_rcu();
+	inc_irq_stat(irq_hv_callback_count);
+
+	xen_hvm_evtchn_do_upcall();
+
+	irq_exit_rcu();
+}
+
+__visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs;
+	bool inhcall, rcu_exit;
+
+	rcu_exit = idtentry_enter_cond_rcu(regs);
+	old_regs = set_irq_regs(regs);
+
+	instrumentation_begin();
+	run_on_irqstack_cond(__xen_pv_evtchn_do_upcall, NULL, regs);
+	instrumentation_begin();
+
+	set_irq_regs(old_regs);
+
+	inhcall = get_and_clear_inhcall();
+	if (inhcall && !WARN_ON_ONCE(rcu_exit)) {
+		instrumentation_begin();
+		idtentry_exit_cond_resched(regs, true);
+		instrumentation_end();
+		restore_inhcall(inhcall);
+	} else {
+		idtentry_exit_cond_rcu(regs, rcu_exit);
+	}
+}
+#endif /* CONFIG_XEN_PV */
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index a5eed844e948..024d7d276cd4 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -44,40 +44,13 @@
 #include <asm/asm.h>
 #include <asm/smap.h>
 #include <asm/frame.h>
+#include <asm/trapnr.h>
 #include <asm/nospec-branch.h>
 
 #include "calling.h"
 
 	.section .entry.text, "ax"
 
-/*
- * We use macros for low-level operations which need to be overridden
- * for paravirtualization.  The following will never clobber any registers:
- *   INTERRUPT_RETURN (aka. "iret")
- *   GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
- *   ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
- *
- * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
- * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
- * Allowing a register to be clobbered can shrink the paravirt replacement
- * enough to patch inline, increasing performance.
- */
-
-#ifdef CONFIG_PREEMPTION
-# define preempt_stop(clobbers)	DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
-#else
-# define preempt_stop(clobbers)
-#endif
-
-.macro TRACE_IRQS_IRET
-#ifdef CONFIG_TRACE_IRQFLAGS
-	testl	$X86_EFLAGS_IF, PT_EFLAGS(%esp)     # interrupts off?
-	jz	1f
-	TRACE_IRQS_ON
-1:
-#endif
-.endm
-
 #define PTI_SWITCH_MASK         (1 << PAGE_SHIFT)
 
 /*
@@ -726,10 +699,68 @@
 
 .Lend_\@:
 .endm
+
+/**
+ * idtentry - Macro to generate entry stubs for simple IDT entries
+ * @vector:		Vector number
+ * @asmsym:		ASM symbol for the entry point
+ * @cfunc:		C function to be called
+ * @has_error_code:	Hardware pushed error code on stack
+ */
+.macro idtentry vector asmsym cfunc has_error_code:req
+SYM_CODE_START(\asmsym)
+	ASM_CLAC
+	cld
+
+	.if \has_error_code == 0
+		pushl	$0		/* Clear the error code */
+	.endif
+
+	/* Push the C-function address into the GS slot */
+	pushl	$\cfunc
+	/* Invoke the common exception entry */
+	jmp	handle_exception
+SYM_CODE_END(\asmsym)
+.endm
+
+.macro idtentry_irq vector cfunc
+	.p2align CONFIG_X86_L1_CACHE_SHIFT
+SYM_CODE_START_LOCAL(asm_\cfunc)
+	ASM_CLAC
+	SAVE_ALL switch_stacks=1
+	ENCODE_FRAME_POINTER
+	movl	%esp, %eax
+	movl	PT_ORIG_EAX(%esp), %edx		/* get the vector from stack */
+	movl	$-1, PT_ORIG_EAX(%esp)		/* no syscall to restart */
+	call	\cfunc
+	jmp	handle_exception_return
+SYM_CODE_END(asm_\cfunc)
+.endm
+
+.macro idtentry_sysvec vector cfunc
+	idtentry \vector asm_\cfunc \cfunc has_error_code=0
+.endm
+
+/*
+ * Include the defines which emit the idt entries which are shared
+ * shared between 32 and 64 bit and emit the __irqentry_text_* markers
+ * so the stacktrace boundary checks work.
+ */
+	.align 16
+	.globl __irqentry_text_start
+__irqentry_text_start:
+
+#include <asm/idtentry.h>
+
+	.align 16
+	.globl __irqentry_text_end
+__irqentry_text_end:
+
 /*
  * %eax: prev task
  * %edx: next task
  */
+.pushsection .text, "ax"
 SYM_CODE_START(__switch_to_asm)
 	/*
 	 * Save callee-saved registers
@@ -776,6 +807,7 @@ SYM_CODE_START(__switch_to_asm)
 
 	jmp	__switch_to
 SYM_CODE_END(__switch_to_asm)
+.popsection
 
 /*
  * The unwinder expects the last frame on the stack to always be at the same
@@ -784,6 +816,7 @@ SYM_CODE_END(__switch_to_asm)
  * asmlinkage function so its argument has to be pushed on the stack.  This
  * wrapper creates a proper "end of stack" frame header before the call.
  */
+.pushsection .text, "ax"
 SYM_FUNC_START(schedule_tail_wrapper)
 	FRAME_BEGIN
 
@@ -794,6 +827,8 @@ SYM_FUNC_START(schedule_tail_wrapper)
 	FRAME_END
 	ret
 SYM_FUNC_END(schedule_tail_wrapper)
+.popsection
+
 /*
  * A newly forked process directly context switches into this address.
  *
@@ -801,6 +836,7 @@ SYM_FUNC_END(schedule_tail_wrapper)
  * ebx: kernel thread func (NULL for user thread)
  * edi: kernel thread arg
  */
+.pushsection .text, "ax"
 SYM_CODE_START(ret_from_fork)
 	call	schedule_tail_wrapper
 
@@ -811,8 +847,7 @@ SYM_CODE_START(ret_from_fork)
 	/* When we fork, we trace the syscall return in the child, too. */
 	movl    %esp, %eax
 	call    syscall_return_slowpath
-	STACKLEAK_ERASE
-	jmp     restore_all
+	jmp     .Lsyscall_32_done
 
 	/* kernel thread */
 1:	movl	%edi, %eax
@@ -825,38 +860,7 @@ SYM_CODE_START(ret_from_fork)
 	movl	$0, PT_EAX(%esp)
 	jmp	2b
 SYM_CODE_END(ret_from_fork)
-
-/*
- * Return to user mode is not as complex as all this looks,
- * but we want the default path for a system call return to
- * go as quickly as possible which is why some of this is
- * less clear than it otherwise should be.
- */
-
-	# userspace resumption stub bypassing syscall exit tracing
-SYM_CODE_START_LOCAL(ret_from_exception)
-	preempt_stop(CLBR_ANY)
-ret_from_intr:
-#ifdef CONFIG_VM86
-	movl	PT_EFLAGS(%esp), %eax		# mix EFLAGS and CS
-	movb	PT_CS(%esp), %al
-	andl	$(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
-#else
-	/*
-	 * We can be coming here from child spawned by kernel_thread().
-	 */
-	movl	PT_CS(%esp), %eax
-	andl	$SEGMENT_RPL_MASK, %eax
-#endif
-	cmpl	$USER_RPL, %eax
-	jb	restore_all_kernel		# not returning to v8086 or userspace
-
-	DISABLE_INTERRUPTS(CLBR_ANY)
-	TRACE_IRQS_OFF
-	movl	%esp, %eax
-	call	prepare_exit_to_usermode
-	jmp	restore_all
-SYM_CODE_END(ret_from_exception)
+.popsection
 
 SYM_ENTRY(__begin_SYSENTER_singlestep_region, SYM_L_GLOBAL, SYM_A_NONE)
 /*
@@ -960,12 +964,6 @@ SYM_FUNC_START(entry_SYSENTER_32)
 	jnz	.Lsysenter_fix_flags
 .Lsysenter_flags_fixed:
 
-	/*
-	 * User mode is traced as though IRQs are on, and SYSENTER
-	 * turned them off.
-	 */
-	TRACE_IRQS_OFF
-
 	movl	%esp, %eax
 	call	do_fast_syscall_32
 	/* XEN PV guests always use IRET path */
@@ -974,8 +972,7 @@ SYM_FUNC_START(entry_SYSENTER_32)
 
 	STACKLEAK_ERASE
 
-/* Opportunistic SYSEXIT */
-	TRACE_IRQS_ON			/* User mode traces as IRQs on. */
+	/* Opportunistic SYSEXIT */
 
 	/*
 	 * Setup entry stack - we keep the pointer in %eax and do the
@@ -1075,20 +1072,12 @@ SYM_FUNC_START(entry_INT80_32)
 
 	SAVE_ALL pt_regs_ax=$-ENOSYS switch_stacks=1	/* save rest */
 
-	/*
-	 * User mode is traced as though IRQs are on, and the interrupt gate
-	 * turned them off.
-	 */
-	TRACE_IRQS_OFF
-
 	movl	%esp, %eax
 	call	do_int80_syscall_32
 .Lsyscall_32_done:
-
 	STACKLEAK_ERASE
 
-restore_all:
-	TRACE_IRQS_ON
+restore_all_switch_stack:
 	SWITCH_TO_ENTRY_STACK
 	CHECK_AND_APPLY_ESPFIX
 
@@ -1107,26 +1096,10 @@ restore_all:
 	 */
 	INTERRUPT_RETURN
 
-restore_all_kernel:
-#ifdef CONFIG_PREEMPTION
-	DISABLE_INTERRUPTS(CLBR_ANY)
-	cmpl	$0, PER_CPU_VAR(__preempt_count)
-	jnz	.Lno_preempt
-	testl	$X86_EFLAGS_IF, PT_EFLAGS(%esp)	# interrupts off (exception path) ?
-	jz	.Lno_preempt
-	call	preempt_schedule_irq
-.Lno_preempt:
-#endif
-	TRACE_IRQS_IRET
-	PARANOID_EXIT_TO_KERNEL_MODE
-	BUG_IF_WRONG_CR3
-	RESTORE_REGS 4
-	jmp	.Lirq_return
-
 .section .fixup, "ax"
-SYM_CODE_START(iret_exc)
+SYM_CODE_START(asm_iret_error)
 	pushl	$0				# no error code
-	pushl	$do_iret_error
+	pushl	$iret_error
 
 #ifdef CONFIG_DEBUG_ENTRY
 	/*
@@ -1140,10 +1113,10 @@ SYM_CODE_START(iret_exc)
 	popl	%eax
 #endif
 
-	jmp	common_exception
-SYM_CODE_END(iret_exc)
+	jmp	handle_exception
+SYM_CODE_END(asm_iret_error)
 .previous
-	_ASM_EXTABLE(.Lirq_return, iret_exc)
+	_ASM_EXTABLE(.Lirq_return, asm_iret_error)
 SYM_FUNC_END(entry_INT80_32)
 
 .macro FIXUP_ESPFIX_STACK
@@ -1193,192 +1166,21 @@ SYM_FUNC_END(entry_INT80_32)
 #endif
 .endm
 
-/*
- * Build the entry stubs with some assembler magic.
- * We pack 1 stub into every 8-byte block.
- */
-	.align 8
-SYM_CODE_START(irq_entries_start)
-    vector=FIRST_EXTERNAL_VECTOR
-    .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
-	pushl	$(~vector+0x80)			/* Note: always in signed byte range */
-    vector=vector+1
-	jmp	common_interrupt
-	.align	8
-    .endr
-SYM_CODE_END(irq_entries_start)
-
-#ifdef CONFIG_X86_LOCAL_APIC
-	.align 8
-SYM_CODE_START(spurious_entries_start)
-    vector=FIRST_SYSTEM_VECTOR
-    .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR)
-	pushl	$(~vector+0x80)			/* Note: always in signed byte range */
-    vector=vector+1
-	jmp	common_spurious
-	.align	8
-    .endr
-SYM_CODE_END(spurious_entries_start)
-
-SYM_CODE_START_LOCAL(common_spurious)
-	ASM_CLAC
-	addl	$-0x80, (%esp)			/* Adjust vector into the [-256, -1] range */
-	SAVE_ALL switch_stacks=1
-	ENCODE_FRAME_POINTER
-	TRACE_IRQS_OFF
-	movl	%esp, %eax
-	call	smp_spurious_interrupt
-	jmp	ret_from_intr
-SYM_CODE_END(common_spurious)
-#endif
-
-/*
- * the CPU automatically disables interrupts when executing an IRQ vector,
- * so IRQ-flags tracing has to follow that:
- */
-	.p2align CONFIG_X86_L1_CACHE_SHIFT
-SYM_CODE_START_LOCAL(common_interrupt)
-	ASM_CLAC
-	addl	$-0x80, (%esp)			/* Adjust vector into the [-256, -1] range */
-
-	SAVE_ALL switch_stacks=1
-	ENCODE_FRAME_POINTER
-	TRACE_IRQS_OFF
-	movl	%esp, %eax
-	call	do_IRQ
-	jmp	ret_from_intr
-SYM_CODE_END(common_interrupt)
-
-#define BUILD_INTERRUPT3(name, nr, fn)			\
-SYM_FUNC_START(name)					\
-	ASM_CLAC;					\
-	pushl	$~(nr);					\
-	SAVE_ALL switch_stacks=1;			\
-	ENCODE_FRAME_POINTER;				\
-	TRACE_IRQS_OFF					\
-	movl	%esp, %eax;				\
-	call	fn;					\
-	jmp	ret_from_intr;				\
-SYM_FUNC_END(name)
-
-#define BUILD_INTERRUPT(name, nr)		\
-	BUILD_INTERRUPT3(name, nr, smp_##name);	\
-
-/* The include is where all of the SMP etc. interrupts come from */
-#include <asm/entry_arch.h>
-
-SYM_CODE_START(coprocessor_error)
-	ASM_CLAC
-	pushl	$0
-	pushl	$do_coprocessor_error
-	jmp	common_exception
-SYM_CODE_END(coprocessor_error)
-
-SYM_CODE_START(simd_coprocessor_error)
-	ASM_CLAC
-	pushl	$0
-#ifdef CONFIG_X86_INVD_BUG
-	/* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
-	ALTERNATIVE "pushl	$do_general_protection",	\
-		    "pushl	$do_simd_coprocessor_error",	\
-		    X86_FEATURE_XMM
-#else
-	pushl	$do_simd_coprocessor_error
-#endif
-	jmp	common_exception
-SYM_CODE_END(simd_coprocessor_error)
-
-SYM_CODE_START(device_not_available)
-	ASM_CLAC
-	pushl	$0
-	pushl	$do_device_not_available
-	jmp	common_exception
-SYM_CODE_END(device_not_available)
-
 #ifdef CONFIG_PARAVIRT
 SYM_CODE_START(native_iret)
 	iret
-	_ASM_EXTABLE(native_iret, iret_exc)
+	_ASM_EXTABLE(native_iret, asm_iret_error)
 SYM_CODE_END(native_iret)
 #endif
 
-SYM_CODE_START(overflow)
-	ASM_CLAC
-	pushl	$0
-	pushl	$do_overflow
-	jmp	common_exception
-SYM_CODE_END(overflow)
-
-SYM_CODE_START(bounds)
-	ASM_CLAC
-	pushl	$0
-	pushl	$do_bounds
-	jmp	common_exception
-SYM_CODE_END(bounds)
-
-SYM_CODE_START(invalid_op)
-	ASM_CLAC
-	pushl	$0
-	pushl	$do_invalid_op
-	jmp	common_exception
-SYM_CODE_END(invalid_op)
-
-SYM_CODE_START(coprocessor_segment_overrun)
-	ASM_CLAC
-	pushl	$0
-	pushl	$do_coprocessor_segment_overrun
-	jmp	common_exception
-SYM_CODE_END(coprocessor_segment_overrun)
-
-SYM_CODE_START(invalid_TSS)
-	ASM_CLAC
-	pushl	$do_invalid_TSS
-	jmp	common_exception
-SYM_CODE_END(invalid_TSS)
-
-SYM_CODE_START(segment_not_present)
-	ASM_CLAC
-	pushl	$do_segment_not_present
-	jmp	common_exception
-SYM_CODE_END(segment_not_present)
-
-SYM_CODE_START(stack_segment)
-	ASM_CLAC
-	pushl	$do_stack_segment
-	jmp	common_exception
-SYM_CODE_END(stack_segment)
-
-SYM_CODE_START(alignment_check)
-	ASM_CLAC
-	pushl	$do_alignment_check
-	jmp	common_exception
-SYM_CODE_END(alignment_check)
-
-SYM_CODE_START(divide_error)
-	ASM_CLAC
-	pushl	$0				# no error code
-	pushl	$do_divide_error
-	jmp	common_exception
-SYM_CODE_END(divide_error)
-
-#ifdef CONFIG_X86_MCE
-SYM_CODE_START(machine_check)
-	ASM_CLAC
-	pushl	$0
-	pushl	$do_mce
-	jmp	common_exception
-SYM_CODE_END(machine_check)
-#endif
-
-SYM_CODE_START(spurious_interrupt_bug)
-	ASM_CLAC
-	pushl	$0
-	pushl	$do_spurious_interrupt_bug
-	jmp	common_exception
-SYM_CODE_END(spurious_interrupt_bug)
-
 #ifdef CONFIG_XEN_PV
-SYM_FUNC_START(xen_hypervisor_callback)
+/*
+ * See comment in entry_64.S for further explanation
+ *
+ * Note: This is not an actual IDT entry point. It's a XEN specific entry
+ * point and therefore named to match the 64-bit trampoline counterpart.
+ */
+SYM_FUNC_START(xen_asm_exc_xen_hypervisor_callback)
 	/*
 	 * Check to see if we got the event in the critical
 	 * region in xen_iret_direct, after we've reenabled
@@ -1395,14 +1197,11 @@ SYM_FUNC_START(xen_hypervisor_callback)
 	pushl	$-1				/* orig_ax = -1 => not a system call */
 	SAVE_ALL
 	ENCODE_FRAME_POINTER
-	TRACE_IRQS_OFF
+
 	mov	%esp, %eax
-	call	xen_evtchn_do_upcall
-#ifndef CONFIG_PREEMPTION
-	call	xen_maybe_preempt_hcall
-#endif
-	jmp	ret_from_intr
-SYM_FUNC_END(xen_hypervisor_callback)
+	call	xen_pv_evtchn_do_upcall
+	jmp	handle_exception_return
+SYM_FUNC_END(xen_asm_exc_xen_hypervisor_callback)
 
 /*
  * Hypervisor uses this for application faults while it executes.
@@ -1429,11 +1228,11 @@ SYM_FUNC_START(xen_failsafe_callback)
 	popl	%eax
 	lea	16(%esp), %esp
 	jz	5f
-	jmp	iret_exc
+	jmp	asm_iret_error
 5:	pushl	$-1				/* orig_ax = -1 => not a system call */
 	SAVE_ALL
 	ENCODE_FRAME_POINTER
-	jmp	ret_from_exception
+	jmp	handle_exception_return
 
 .section .fixup, "ax"
 6:	xorl	%eax, %eax
@@ -1456,56 +1255,7 @@ SYM_FUNC_START(xen_failsafe_callback)
 SYM_FUNC_END(xen_failsafe_callback)
 #endif /* CONFIG_XEN_PV */
 
-#ifdef CONFIG_XEN_PVHVM
-BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
-		 xen_evtchn_do_upcall)
-#endif
-
-
-#if IS_ENABLED(CONFIG_HYPERV)
-
-BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
-		 hyperv_vector_handler)
-
-BUILD_INTERRUPT3(hyperv_reenlightenment_vector, HYPERV_REENLIGHTENMENT_VECTOR,
-		 hyperv_reenlightenment_intr)
-
-BUILD_INTERRUPT3(hv_stimer0_callback_vector, HYPERV_STIMER0_VECTOR,
-		 hv_stimer0_vector_handler)
-
-#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)
+SYM_CODE_START_LOCAL_NOALIGN(handle_exception)
 	/* 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
@@ -1520,23 +1270,35 @@ SYM_CODE_START_LOCAL_NOALIGN(common_exception)
 	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)
 
-SYM_CODE_START(debug)
+handle_exception_return:
+#ifdef CONFIG_VM86
+	movl	PT_EFLAGS(%esp), %eax		# mix EFLAGS and CS
+	movb	PT_CS(%esp), %al
+	andl	$(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
+#else
 	/*
-	 * Entry from sysenter is now handled in common_exception
+	 * We can be coming here from child spawned by kernel_thread().
 	 */
-	ASM_CLAC
-	pushl	$0
-	pushl	$do_debug
-	jmp	common_exception
-SYM_CODE_END(debug)
+	movl	PT_CS(%esp), %eax
+	andl	$SEGMENT_RPL_MASK, %eax
+#endif
+	cmpl	$USER_RPL, %eax			# returning to v8086 or userspace ?
+	jnb	ret_to_user
 
-SYM_CODE_START(double_fault)
+	PARANOID_EXIT_TO_KERNEL_MODE
+	BUG_IF_WRONG_CR3
+	RESTORE_REGS 4
+	jmp	.Lirq_return
+
+ret_to_user:
+	movl	%esp, %eax
+	jmp	restore_all_switch_stack
+SYM_CODE_END(handle_exception)
+
+SYM_CODE_START(asm_exc_double_fault)
 1:
 	/*
 	 * This is a task gate handler, not an interrupt gate handler.
@@ -1574,7 +1336,7 @@ SYM_CODE_START(double_fault)
 1:
 	hlt
 	jmp 1b
-SYM_CODE_END(double_fault)
+SYM_CODE_END(asm_exc_double_fault)
 
 /*
  * NMI is doubly nasty.  It can happen on the first instruction of
@@ -1583,7 +1345,7 @@ SYM_CODE_END(double_fault)
  * switched stacks.  We handle both conditions by simply checking whether we
  * interrupted kernel code running on the SYSENTER stack.
  */
-SYM_CODE_START(nmi)
+SYM_CODE_START(asm_exc_nmi)
 	ASM_CLAC
 
 #ifdef CONFIG_X86_ESPFIX32
@@ -1612,7 +1374,7 @@ SYM_CODE_START(nmi)
 	jb	.Lnmi_from_sysenter_stack
 
 	/* Not on SYSENTER stack. */
-	call	do_nmi
+	call	exc_nmi
 	jmp	.Lnmi_return
 
 .Lnmi_from_sysenter_stack:
@@ -1622,7 +1384,7 @@ SYM_CODE_START(nmi)
 	 */
 	movl	%esp, %ebx
 	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esp
-	call	do_nmi
+	call	exc_nmi
 	movl	%ebx, %esp
 
 .Lnmi_return:
@@ -1676,21 +1438,9 @@ SYM_CODE_START(nmi)
 	lss	(1+5+6)*4(%esp), %esp			# back to espfix stack
 	jmp	.Lirq_return
 #endif
-SYM_CODE_END(nmi)
-
-SYM_CODE_START(int3)
-	ASM_CLAC
-	pushl	$0
-	pushl	$do_int3
-	jmp	common_exception
-SYM_CODE_END(int3)
-
-SYM_CODE_START(general_protection)
-	ASM_CLAC
-	pushl	$do_general_protection
-	jmp	common_exception
-SYM_CODE_END(general_protection)
+SYM_CODE_END(asm_exc_nmi)
 
+.pushsection .text, "ax"
 SYM_CODE_START(rewind_stack_do_exit)
 	/* Prevent any naive code from trying to unwind to our caller. */
 	xorl	%ebp, %ebp
@@ -1701,3 +1451,4 @@ SYM_CODE_START(rewind_stack_do_exit)
 	call	do_exit
 1:	jmp 1b
 SYM_CODE_END(rewind_stack_do_exit)
+.popsection
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index eead1e2bebd5..d2a00c97e53f 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -16,7 +16,6 @@
  *
  * Some macro usage:
  * - SYM_FUNC_START/END:Define functions in the symbol table.
- * - TRACE_IRQ_*:	Trace hardirq state for lock debugging.
  * - idtentry:		Define exception entry points.
  */
 #include <linux/linkage.h>
@@ -37,6 +36,7 @@
 #include <asm/pgtable_types.h>
 #include <asm/export.h>
 #include <asm/frame.h>
+#include <asm/trapnr.h>
 #include <asm/nospec-branch.h>
 #include <linux/err.h>
 
@@ -53,57 +53,6 @@ SYM_CODE_START(native_usergs_sysret64)
 SYM_CODE_END(native_usergs_sysret64)
 #endif /* CONFIG_PARAVIRT */
 
-.macro TRACE_IRQS_FLAGS flags:req
-#ifdef CONFIG_TRACE_IRQFLAGS
-	btl	$9, \flags		/* interrupts off? */
-	jnc	1f
-	TRACE_IRQS_ON
-1:
-#endif
-.endm
-
-.macro TRACE_IRQS_IRETQ
-	TRACE_IRQS_FLAGS EFLAGS(%rsp)
-.endm
-
-/*
- * When dynamic function tracer is enabled it will add a breakpoint
- * to all locations that it is about to modify, sync CPUs, update
- * all the code, sync CPUs, then remove the breakpoints. In this time
- * if lockdep is enabled, it might jump back into the debug handler
- * outside the updating of the IST protection. (TRACE_IRQS_ON/OFF).
- *
- * We need to change the IDT table before calling TRACE_IRQS_ON/OFF to
- * make sure the stack pointer does not get reset back to the top
- * of the debug stack, and instead just reuses the current stack.
- */
-#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS)
-
-.macro TRACE_IRQS_OFF_DEBUG
-	call	debug_stack_set_zero
-	TRACE_IRQS_OFF
-	call	debug_stack_reset
-.endm
-
-.macro TRACE_IRQS_ON_DEBUG
-	call	debug_stack_set_zero
-	TRACE_IRQS_ON
-	call	debug_stack_reset
-.endm
-
-.macro TRACE_IRQS_IRETQ_DEBUG
-	btl	$9, EFLAGS(%rsp)		/* interrupts off? */
-	jnc	1f
-	TRACE_IRQS_ON_DEBUG
-1:
-.endm
-
-#else
-# define TRACE_IRQS_OFF_DEBUG			TRACE_IRQS_OFF
-# define TRACE_IRQS_ON_DEBUG			TRACE_IRQS_ON
-# define TRACE_IRQS_IRETQ_DEBUG			TRACE_IRQS_IRETQ
-#endif
-
 /*
  * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers.
  *
@@ -144,11 +93,6 @@ SYM_CODE_END(native_usergs_sysret64)
 
 SYM_CODE_START(entry_SYSCALL_64)
 	UNWIND_HINT_EMPTY
-	/*
-	 * Interrupts are off on entry.
-	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
-	 * it is too small to ever cause noticeable irq latency.
-	 */
 
 	swapgs
 	/* tss.sp2 is scratch space. */
@@ -167,15 +111,11 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 
 	PUSH_AND_CLEAR_REGS rax=$-ENOSYS
 
-	TRACE_IRQS_OFF
-
 	/* IRQs are off. */
 	movq	%rax, %rdi
 	movq	%rsp, %rsi
 	call	do_syscall_64		/* returns with IRQs disabled */
 
-	TRACE_IRQS_ON			/* return enables interrupts */
-
 	/*
 	 * Try to use SYSRET instead of IRET if we're returning to
 	 * a completely clean 64-bit userspace context.  If we're not,
@@ -279,6 +219,7 @@ SYM_CODE_END(entry_SYSCALL_64)
  * %rdi: prev task
  * %rsi: next task
  */
+.pushsection .text, "ax"
 SYM_FUNC_START(__switch_to_asm)
 	/*
 	 * Save callee-saved registers
@@ -321,6 +262,7 @@ SYM_FUNC_START(__switch_to_asm)
 
 	jmp	__switch_to
 SYM_FUNC_END(__switch_to_asm)
+.popsection
 
 /*
  * A newly forked process directly context switches into this address.
@@ -329,6 +271,7 @@ SYM_FUNC_END(__switch_to_asm)
  * rbx: kernel thread func (NULL for user thread)
  * r12: kernel thread arg
  */
+.pushsection .text, "ax"
 SYM_CODE_START(ret_from_fork)
 	UNWIND_HINT_EMPTY
 	movq	%rax, %rdi
@@ -341,7 +284,6 @@ SYM_CODE_START(ret_from_fork)
 	UNWIND_HINT_REGS
 	movq	%rsp, %rdi
 	call	syscall_return_slowpath	/* returns with IRQs disabled */
-	TRACE_IRQS_ON			/* user mode is traced as IRQS on */
 	jmp	swapgs_restore_regs_and_return_to_usermode
 
 1:
@@ -357,34 +299,7 @@ SYM_CODE_START(ret_from_fork)
 	movq	$0, RAX(%rsp)
 	jmp	2b
 SYM_CODE_END(ret_from_fork)
-
-/*
- * Build the entry stubs with some assembler magic.
- * We pack 1 stub into every 8-byte block.
- */
-	.align 8
-SYM_CODE_START(irq_entries_start)
-    vector=FIRST_EXTERNAL_VECTOR
-    .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
-	UNWIND_HINT_IRET_REGS
-	pushq	$(~vector+0x80)			/* Note: always in signed byte range */
-	jmp	common_interrupt
-	.align	8
-	vector=vector+1
-    .endr
-SYM_CODE_END(irq_entries_start)
-
-	.align 8
-SYM_CODE_START(spurious_entries_start)
-    vector=FIRST_SYSTEM_VECTOR
-    .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR)
-	UNWIND_HINT_IRET_REGS
-	pushq	$(~vector+0x80)			/* Note: always in signed byte range */
-	jmp	common_spurious
-	.align	8
-	vector=vector+1
-    .endr
-SYM_CODE_END(spurious_entries_start)
+.popsection
 
 .macro DEBUG_ENTRY_ASSERT_IRQS_OFF
 #ifdef CONFIG_DEBUG_ENTRY
@@ -398,228 +313,185 @@ SYM_CODE_END(spurious_entries_start)
 #endif
 .endm
 
-/*
- * Enters the IRQ stack if we're not already using it.  NMI-safe.  Clobbers
- * flags and puts old RSP into old_rsp, and leaves all other GPRs alone.
- * Requires kernel GSBASE.
- *
- * The invariant is that, if irq_count != -1, then the IRQ stack is in use.
+/**
+ * idtentry_body - Macro to emit code calling the C function
+ * @cfunc:		C function to be called
+ * @has_error_code:	Hardware pushed error code on stack
  */
-.macro ENTER_IRQ_STACK regs=1 old_rsp save_ret=0
-	DEBUG_ENTRY_ASSERT_IRQS_OFF
+.macro idtentry_body cfunc has_error_code:req
 
-	.if \save_ret
-	/*
-	 * If save_ret is set, the original stack contains one additional
-	 * entry -- the return address. Therefore, move the address one
-	 * entry below %rsp to \old_rsp.
-	 */
-	leaq	8(%rsp), \old_rsp
-	.else
-	movq	%rsp, \old_rsp
-	.endif
-
-	.if \regs
-	UNWIND_HINT_REGS base=\old_rsp
-	.endif
+	call	error_entry
+	UNWIND_HINT_REGS
 
-	incl	PER_CPU_VAR(irq_count)
-	jnz	.Lirq_stack_push_old_rsp_\@
+	movq	%rsp, %rdi			/* pt_regs pointer into 1st argument*/
 
-	/*
-	 * Right now, if we just incremented irq_count to zero, we've
-	 * claimed the IRQ stack but we haven't switched to it yet.
-	 *
-	 * If anything is added that can interrupt us here without using IST,
-	 * it must be *extremely* careful to limit its stack usage.  This
-	 * could include kprobes and a hypothetical future IST-less #DB
-	 * handler.
-	 *
-	 * The OOPS unwinder relies on the word at the top of the IRQ
-	 * stack linking back to the previous RSP for the entire time we're
-	 * on the IRQ stack.  For this to work reliably, we need to write
-	 * it before we actually move ourselves to the IRQ stack.
-	 */
+	.if \has_error_code == 1
+		movq	ORIG_RAX(%rsp), %rsi	/* get error code into 2nd argument*/
+		movq	$-1, ORIG_RAX(%rsp)	/* no syscall to restart */
+	.endif
 
-	movq	\old_rsp, PER_CPU_VAR(irq_stack_backing_store + IRQ_STACK_SIZE - 8)
-	movq	PER_CPU_VAR(hardirq_stack_ptr), %rsp
+	call	\cfunc
 
-#ifdef CONFIG_DEBUG_ENTRY
-	/*
-	 * If the first movq above becomes wrong due to IRQ stack layout
-	 * changes, the only way we'll notice is if we try to unwind right
-	 * here.  Assert that we set up the stack right to catch this type
-	 * of bug quickly.
-	 */
-	cmpq	-8(%rsp), \old_rsp
-	je	.Lirq_stack_okay\@
-	ud2
-	.Lirq_stack_okay\@:
-#endif
+	jmp	error_return
+.endm
 
-.Lirq_stack_push_old_rsp_\@:
-	pushq	\old_rsp
+/**
+ * idtentry - Macro to generate entry stubs for simple IDT entries
+ * @vector:		Vector number
+ * @asmsym:		ASM symbol for the entry point
+ * @cfunc:		C function to be called
+ * @has_error_code:	Hardware pushed error code on stack
+ *
+ * The macro emits code to set up the kernel context for straight forward
+ * and simple IDT entries. No IST stack, no paranoid entry checks.
+ */
+.macro idtentry vector asmsym cfunc has_error_code:req
+SYM_CODE_START(\asmsym)
+	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
+	ASM_CLAC
 
-	.if \regs
-	UNWIND_HINT_REGS indirect=1
+	.if \has_error_code == 0
+		pushq	$-1			/* ORIG_RAX: no syscall to restart */
 	.endif
 
-	.if \save_ret
-	/*
-	 * Push the return address to the stack. This return address can
-	 * be found at the "real" original RSP, which was offset by 8 at
-	 * the beginning of this macro.
-	 */
-	pushq	-8(\old_rsp)
+	.if \vector == X86_TRAP_BP
+		/*
+		 * If coming from kernel space, create a 6-word gap to allow the
+		 * int3 handler to emulate a call instruction.
+		 */
+		testb	$3, CS-ORIG_RAX(%rsp)
+		jnz	.Lfrom_usermode_no_gap_\@
+		.rept	6
+		pushq	5*8(%rsp)
+		.endr
+		UNWIND_HINT_IRET_REGS offset=8
+.Lfrom_usermode_no_gap_\@:
 	.endif
+
+	idtentry_body \cfunc \has_error_code
+
+_ASM_NOKPROBE(\asmsym)
+SYM_CODE_END(\asmsym)
 .endm
 
 /*
- * Undoes ENTER_IRQ_STACK.
+ * Interrupt entry/exit.
+ *
+ + The interrupt stubs push (vector) onto the stack, which is the error_code
+ * position of idtentry exceptions, and jump to one of the two idtentry points
+ * (common/spurious).
+ *
+ * common_interrupt is a hotpath, align it to a cache line
  */
-.macro LEAVE_IRQ_STACK regs=1
-	DEBUG_ENTRY_ASSERT_IRQS_OFF
-	/* We need to be off the IRQ stack before decrementing irq_count. */
-	popq	%rsp
-
-	.if \regs
-	UNWIND_HINT_REGS
-	.endif
-
-	/*
-	 * As in ENTER_IRQ_STACK, irq_count == 0, we are still claiming
-	 * the irq stack but we're not on it.
-	 */
-
-	decl	PER_CPU_VAR(irq_count)
+.macro idtentry_irq vector cfunc
+	.p2align CONFIG_X86_L1_CACHE_SHIFT
+	idtentry \vector asm_\cfunc \cfunc has_error_code=1
 .endm
 
 /*
- * Interrupt entry helper function.
+ * System vectors which invoke their handlers directly and are not
+ * going through the regular common device interrupt handling code.
+ */
+.macro idtentry_sysvec vector cfunc
+	idtentry \vector asm_\cfunc \cfunc has_error_code=0
+.endm
+
+/**
+ * idtentry_mce_db - Macro to generate entry stubs for #MC and #DB
+ * @vector:		Vector number
+ * @asmsym:		ASM symbol for the entry point
+ * @cfunc:		C function to be called
+ *
+ * The macro emits code to set up the kernel context for #MC and #DB
+ *
+ * If the entry comes from user space it uses the normal entry path
+ * including the return to user space work and preemption checks on
+ * exit.
  *
- * Entry runs with interrupts off. Stack layout at entry:
- * +----------------------------------------------------+
- * | regs->ss						|
- * | regs->rsp						|
- * | regs->eflags					|
- * | regs->cs						|
- * | regs->ip						|
- * +----------------------------------------------------+
- * | regs->orig_ax = ~(interrupt number)		|
- * +----------------------------------------------------+
- * | return address					|
- * +----------------------------------------------------+
+ * If hits in kernel mode then it needs to go through the paranoid
+ * entry as the exception can hit any random state. No preemption
+ * check on exit to keep the paranoid path simple.
  */
-SYM_CODE_START(interrupt_entry)
-	UNWIND_HINT_IRET_REGS offset=16
+.macro idtentry_mce_db vector asmsym cfunc
+SYM_CODE_START(\asmsym)
+	UNWIND_HINT_IRET_REGS
 	ASM_CLAC
-	cld
 
-	testb	$3, CS-ORIG_RAX+8(%rsp)
-	jz	1f
-	SWAPGS
-	FENCE_SWAPGS_USER_ENTRY
+	pushq	$-1			/* ORIG_RAX: no syscall to restart */
+
 	/*
-	 * Switch to the thread stack. The IRET frame and orig_ax are
-	 * on the stack, as well as the return address. RDI..R12 are
-	 * not (yet) on the stack and space has not (yet) been
-	 * allocated for them.
+	 * If the entry is from userspace, switch stacks and treat it as
+	 * a normal entry.
 	 */
-	pushq	%rdi
+	testb	$3, CS-ORIG_RAX(%rsp)
+	jnz	.Lfrom_usermode_switch_stack_\@
 
-	/* 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
+	/*
+	 * paranoid_entry returns SWAPGS flag for paranoid_exit in EBX.
+	 * EBX == 0 -> SWAPGS, EBX == 1 -> no SWAPGS
+	 */
+	call	paranoid_entry
 
-	 /*
-	  * We have RDI, return address, and orig_ax on the stack on
-	  * top of the IRET frame. That means offset=24
-	  */
-	UNWIND_HINT_IRET_REGS base=%rdi offset=24
-
-	pushq	7*8(%rdi)		/* regs->ss */
-	pushq	6*8(%rdi)		/* regs->rsp */
-	pushq	5*8(%rdi)		/* regs->eflags */
-	pushq	4*8(%rdi)		/* regs->cs */
-	pushq	3*8(%rdi)		/* regs->ip */
-	UNWIND_HINT_IRET_REGS
-	pushq	2*8(%rdi)		/* regs->orig_ax */
-	pushq	8(%rdi)			/* return address */
+	UNWIND_HINT_REGS
 
-	movq	(%rdi), %rdi
-	jmp	2f
-1:
-	FENCE_SWAPGS_KERNEL_ENTRY
-2:
-	PUSH_AND_CLEAR_REGS save_ret=1
-	ENCODE_FRAME_POINTER 8
+	movq	%rsp, %rdi		/* pt_regs pointer */
 
-	testb	$3, CS+8(%rsp)
-	jz	1f
+	call	\cfunc
 
-	/*
-	 * IRQ from user mode.
-	 *
-	 * 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).  Since TRACE_IRQS_OFF is idempotent,
-	 * the simplest way to handle it is to just call it twice if
-	 * we enter from user mode.  There's no reason to optimize this since
-	 * TRACE_IRQS_OFF is a no-op if lockdep is off.
-	 */
-	TRACE_IRQS_OFF
+	jmp	paranoid_exit
 
-	CALL_enter_from_user_mode
+	/* Switch to the regular task stack and use the noist entry point */
+.Lfrom_usermode_switch_stack_\@:
+	idtentry_body noist_\cfunc, has_error_code=0
 
-1:
-	ENTER_IRQ_STACK old_rsp=%rdi save_ret=1
-	/* We entered an interrupt context - irqs are off: */
-	TRACE_IRQS_OFF
+_ASM_NOKPROBE(\asmsym)
+SYM_CODE_END(\asmsym)
+.endm
 
-	ret
-SYM_CODE_END(interrupt_entry)
-_ASM_NOKPROBE(interrupt_entry)
+/*
+ * Double fault entry. Straight paranoid. No checks from which context
+ * this comes because for the espfix induced #DF this would do the wrong
+ * thing.
+ */
+.macro idtentry_df vector asmsym cfunc
+SYM_CODE_START(\asmsym)
+	UNWIND_HINT_IRET_REGS offset=8
+	ASM_CLAC
 
+	/*
+	 * paranoid_entry returns SWAPGS flag for paranoid_exit in EBX.
+	 * EBX == 0 -> SWAPGS, EBX == 1 -> no SWAPGS
+	 */
+	call	paranoid_entry
+	UNWIND_HINT_REGS
 
-/* Interrupt entry/exit. */
+	movq	%rsp, %rdi		/* pt_regs pointer into first argument */
+	movq	ORIG_RAX(%rsp), %rsi	/* get error code into 2nd argument*/
+	movq	$-1, ORIG_RAX(%rsp)	/* no syscall to restart */
+	call	\cfunc
+
+	jmp	paranoid_exit
+
+_ASM_NOKPROBE(\asmsym)
+SYM_CODE_END(\asmsym)
+.endm
 
 /*
- * The interrupt stubs push (~vector+0x80) onto the stack and
- * then jump to common_spurious/interrupt.
+ * Include the defines which emit the idt entries which are shared
+ * shared between 32 and 64 bit and emit the __irqentry_text_* markers
+ * so the stacktrace boundary checks work.
  */
-SYM_CODE_START_LOCAL(common_spurious)
-	addq	$-0x80, (%rsp)			/* Adjust vector to [-256, -1] range */
-	call	interrupt_entry
-	UNWIND_HINT_REGS indirect=1
-	call	smp_spurious_interrupt		/* rdi points to pt_regs */
-	jmp	ret_from_intr
-SYM_CODE_END(common_spurious)
-_ASM_NOKPROBE(common_spurious)
-
-/* common_interrupt is a hotpath. Align it */
-	.p2align CONFIG_X86_L1_CACHE_SHIFT
-SYM_CODE_START_LOCAL(common_interrupt)
-	addq	$-0x80, (%rsp)			/* Adjust vector to [-256, -1] range */
-	call	interrupt_entry
-	UNWIND_HINT_REGS indirect=1
-	call	do_IRQ	/* rdi points to pt_regs */
-	/* 0(%rsp): old RSP */
-ret_from_intr:
-	DISABLE_INTERRUPTS(CLBR_ANY)
-	TRACE_IRQS_OFF
-
-	LEAVE_IRQ_STACK
+	.align 16
+	.globl __irqentry_text_start
+__irqentry_text_start:
 
-	testb	$3, CS(%rsp)
-	jz	retint_kernel
+#include <asm/idtentry.h>
 
-	/* Interrupt came from user space */
-.Lretint_user:
-	mov	%rsp,%rdi
-	call	prepare_exit_to_usermode
-	TRACE_IRQS_ON
+	.align 16
+	.globl __irqentry_text_end
+__irqentry_text_end:
 
+SYM_CODE_START_LOCAL(common_interrupt_return)
 SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 #ifdef CONFIG_DEBUG_ENTRY
 	/* Assert that pt_regs indicates user mode. */
@@ -662,23 +534,6 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 	INTERRUPT_RETURN
 
 
-/* Returning to kernel space */
-retint_kernel:
-#ifdef CONFIG_PREEMPTION
-	/* Interrupts are off */
-	/* Check if we need preemption */
-	btl	$9, EFLAGS(%rsp)		/* were interrupts off? */
-	jnc	1f
-	cmpl	$0, PER_CPU_VAR(__preempt_count)
-	jnz	1f
-	call	preempt_schedule_irq
-1:
-#endif
-	/*
-	 * The iretq could re-enable interrupts:
-	 */
-	TRACE_IRQS_IRETQ
-
 SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL)
 #ifdef CONFIG_DEBUG_ENTRY
 	/* Assert that pt_regs indicates kernel mode. */
@@ -710,7 +565,7 @@ SYM_INNER_LABEL(native_irq_return_iret, SYM_L_GLOBAL)
 	/*
 	 * This may fault.  Non-paranoid faults on return to userspace are
 	 * handled by fixup_bad_iret.  These include #SS, #GP, and #NP.
-	 * Double-faults due to espfix64 are handled in do_double_fault.
+	 * Double-faults due to espfix64 are handled in exc_double_fault.
 	 * Other faults here are fatal.
 	 */
 	iretq
@@ -788,280 +643,32 @@ native_irq_return_ldt:
 	 */
 	jmp	native_irq_return_iret
 #endif
-SYM_CODE_END(common_interrupt)
-_ASM_NOKPROBE(common_interrupt)
-
-/*
- * APIC interrupts.
- */
-.macro apicinterrupt3 num sym do_sym
-SYM_CODE_START(\sym)
-	UNWIND_HINT_IRET_REGS
-	pushq	$~(\num)
-.Lcommon_\sym:
-	call	interrupt_entry
-	UNWIND_HINT_REGS indirect=1
-	call	\do_sym	/* rdi points to pt_regs */
-	jmp	ret_from_intr
-SYM_CODE_END(\sym)
-_ASM_NOKPROBE(\sym)
-.endm
-
-/* Make sure APIC interrupt handlers end up in the irqentry section: */
-#define PUSH_SECTION_IRQENTRY	.pushsection .irqentry.text, "ax"
-#define POP_SECTION_IRQENTRY	.popsection
-
-.macro apicinterrupt num sym do_sym
-PUSH_SECTION_IRQENTRY
-apicinterrupt3 \num \sym \do_sym
-POP_SECTION_IRQENTRY
-.endm
-
-#ifdef CONFIG_SMP
-apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR		irq_move_cleanup_interrupt	smp_irq_move_cleanup_interrupt
-apicinterrupt3 REBOOT_VECTOR			reboot_interrupt		smp_reboot_interrupt
-#endif
-
-#ifdef CONFIG_X86_UV
-apicinterrupt3 UV_BAU_MESSAGE			uv_bau_message_intr1		uv_bau_message_interrupt
-#endif
-
-apicinterrupt LOCAL_TIMER_VECTOR		apic_timer_interrupt		smp_apic_timer_interrupt
-apicinterrupt X86_PLATFORM_IPI_VECTOR		x86_platform_ipi		smp_x86_platform_ipi
-
-#ifdef CONFIG_HAVE_KVM
-apicinterrupt3 POSTED_INTR_VECTOR		kvm_posted_intr_ipi		smp_kvm_posted_intr_ipi
-apicinterrupt3 POSTED_INTR_WAKEUP_VECTOR	kvm_posted_intr_wakeup_ipi	smp_kvm_posted_intr_wakeup_ipi
-apicinterrupt3 POSTED_INTR_NESTED_VECTOR	kvm_posted_intr_nested_ipi	smp_kvm_posted_intr_nested_ipi
-#endif
-
-#ifdef CONFIG_X86_MCE_THRESHOLD
-apicinterrupt THRESHOLD_APIC_VECTOR		threshold_interrupt		smp_threshold_interrupt
-#endif
-
-#ifdef CONFIG_X86_MCE_AMD
-apicinterrupt DEFERRED_ERROR_VECTOR		deferred_error_interrupt	smp_deferred_error_interrupt
-#endif
-
-#ifdef CONFIG_X86_THERMAL_VECTOR
-apicinterrupt THERMAL_APIC_VECTOR		thermal_interrupt		smp_thermal_interrupt
-#endif
-
-#ifdef CONFIG_SMP
-apicinterrupt CALL_FUNCTION_SINGLE_VECTOR	call_function_single_interrupt	smp_call_function_single_interrupt
-apicinterrupt CALL_FUNCTION_VECTOR		call_function_interrupt		smp_call_function_interrupt
-apicinterrupt RESCHEDULE_VECTOR			reschedule_interrupt		smp_reschedule_interrupt
-#endif
-
-apicinterrupt ERROR_APIC_VECTOR			error_interrupt			smp_error_interrupt
-apicinterrupt SPURIOUS_APIC_VECTOR		spurious_interrupt		smp_spurious_interrupt
-
-#ifdef CONFIG_IRQ_WORK
-apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
-#endif
+SYM_CODE_END(common_interrupt_return)
+_ASM_NOKPROBE(common_interrupt_return)
 
 /*
- * Exception entry points.
- */
-#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
- *			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
- *			fresh stack.  (This is for #DB, which has a nasty habit
- *			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
- * special behaviors:
- *
- * On an entry from user mode, the stub switches from the trampoline or
- * IST stack to the normal thread stack.  On an exit to user mode, the
- * normal exit-to-usermode path is invoked.
- *
- * On an exit to kernel mode, if @paranoid == 0, we check for preemption,
- * whereas we omit the preemption check if @paranoid != 0.  This is purely
- * because the implementation is simpler this way.  The kernel only needs
- * to check for asynchronous kernel preemption when IRQ handlers return.
- *
- * If @paranoid == 0, then the stub will handle IRET faults by pretending
- * that the fault came from user mode.  It will handle gs_change faults by
- * pretending that the fault happened with kernel GSBASE.  Since this handling
- * is omitted for @paranoid != 0, the #GP, #SS, and #NP stubs must have
- * @paranoid == 0.  This special handling will do the wrong thing for
- * espfix-induced #DF on IRET, so #DF must not use @paranoid == 0.
+ * Reload gs selector with exception handling
+ * edi:  new selector
  *
- * @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.
+ * Is in entry.text as it shouldn't be instrumented.
  */
-.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0 create_gap=0 read_cr2=0
-SYM_CODE_START(\sym)
-	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
-
-	/* Sanity check */
-	.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
-	pushq	$-1				/* ORIG_RAX: no syscall to restart */
-	.endif
-
-	.if \paranoid == 1
-	testb	$3, CS-ORIG_RAX(%rsp)		/* If coming from userspace, switch stacks */
-	jnz	.Lfrom_usermode_switch_stack_\@
-	.endif
-
-	.if \create_gap == 1
-	/*
-	 * If coming from kernel space, create a 6-word gap to allow the
-	 * int3 handler to emulate a call instruction.
-	 */
-	testb	$3, CS-ORIG_RAX(%rsp)
-	jnz	.Lfrom_usermode_no_gap_\@
-	.rept	6
-	pushq	5*8(%rsp)
-	.endr
-	UNWIND_HINT_IRET_REGS offset=8
-.Lfrom_usermode_no_gap_\@:
-	.endif
-
-	idtentry_part \do_sym, \has_error_code, \read_cr2, \paranoid, \shift_ist, \ist_offset
-
-	.if \paranoid == 1
-	/*
-	 * Entry from userspace.  Switch stacks and treat it
-	 * as a normal entry.  This means that paranoid handlers
-	 * run in real process context if user_mode(regs).
-	 */
-.Lfrom_usermode_switch_stack_\@:
-	idtentry_part \do_sym, \has_error_code, \read_cr2, paranoid=0
-	.endif
-
-_ASM_NOKPROBE(\sym)
-SYM_CODE_END(\sym)
-.endm
-
-idtentry divide_error			do_divide_error			has_error_code=0
-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 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
-idtentry spurious_interrupt_bug		do_spurious_interrupt_bug	has_error_code=0
-idtentry coprocessor_error		do_coprocessor_error		has_error_code=0
-idtentry alignment_check		do_alignment_check		has_error_code=1
-idtentry simd_coprocessor_error		do_simd_coprocessor_error	has_error_code=0
-
-
-	/*
-	 * Reload gs selector with exception handling
-	 * edi:  new selector
-	 */
-SYM_FUNC_START(native_load_gs_index)
+SYM_FUNC_START(asm_load_gs_index)
 	FRAME_BEGIN
-	pushfq
-	DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
-	TRACE_IRQS_OFF
-	SWAPGS
+	swapgs
 .Lgs_change:
 	movl	%edi, %gs
 2:	ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE
-	SWAPGS
-	TRACE_IRQS_FLAGS (%rsp)
-	popfq
+	swapgs
 	FRAME_END
 	ret
-SYM_FUNC_END(native_load_gs_index)
-EXPORT_SYMBOL(native_load_gs_index)
+SYM_FUNC_END(asm_load_gs_index)
+EXPORT_SYMBOL(asm_load_gs_index)
 
 	_ASM_EXTABLE(.Lgs_change, .Lbad_gs)
 	.section .fixup, "ax"
 	/* running with kernelgs */
 SYM_CODE_START_LOCAL_NOALIGN(.Lbad_gs)
-	SWAPGS					/* switch back to user gs */
+	swapgs					/* switch back to user gs */
 .macro ZAP_GS
 	/* This can't be a string because the preprocessor needs to see it. */
 	movl $__USER_DS, %eax
@@ -1074,20 +681,46 @@ SYM_CODE_START_LOCAL_NOALIGN(.Lbad_gs)
 SYM_CODE_END(.Lbad_gs)
 	.previous
 
-/* Call softirq on interrupt stack. Interrupts are off. */
-SYM_FUNC_START(do_softirq_own_stack)
-	pushq	%rbp
-	mov	%rsp, %rbp
-	ENTER_IRQ_STACK regs=0 old_rsp=%r11
-	call	__do_softirq
-	LEAVE_IRQ_STACK regs=0
+/*
+ * rdi: New stack pointer points to the top word of the stack
+ * rsi: Function pointer
+ * rdx: Function argument (can be NULL if none)
+ */
+SYM_FUNC_START(asm_call_on_stack)
+	/*
+	 * Save the frame pointer unconditionally. This allows the ORC
+	 * unwinder to handle the stack switch.
+	 */
+	pushq		%rbp
+	mov		%rsp, %rbp
+
+	/*
+	 * The unwinder relies on the word at the top of the new stack
+	 * page linking back to the previous RSP.
+	 */
+	mov		%rsp, (%rdi)
+	mov		%rdi, %rsp
+	/* Move the argument to the right place */
+	mov		%rdx, %rdi
+
+1:
+	.pushsection .discard.instr_begin
+	.long 1b - .
+	.popsection
+
+	CALL_NOSPEC	rsi
+
+2:
+	.pushsection .discard.instr_end
+	.long 2b - .
+	.popsection
+
+	/* Restore the previous stack pointer from RBP. */
 	leaveq
 	ret
-SYM_FUNC_END(do_softirq_own_stack)
+SYM_FUNC_END(asm_call_on_stack)
 
 #ifdef CONFIG_XEN_PV
-idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0
-
 /*
  * A note on the "critical region" in our callback handler.
  * We want to avoid stacking callback handlers due to events occurring
@@ -1100,9 +733,10 @@ idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0
  * So, on entry to the handler we detect whether we interrupted an
  * existing activation in its critical region -- if so, we pop the current
  * activation and restart the handler using the previous one.
+ *
+ * C calling convention: exc_xen_hypervisor_callback(struct *pt_regs)
  */
-/* do_hypervisor_callback(struct *pt_regs) */
-SYM_CODE_START_LOCAL(xen_do_hypervisor_callback)
+SYM_CODE_START_LOCAL(exc_xen_hypervisor_callback)
 
 /*
  * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
@@ -1112,15 +746,10 @@ SYM_CODE_START_LOCAL(xen_do_hypervisor_callback)
 	movq	%rdi, %rsp			/* we don't return, adjust the stack frame */
 	UNWIND_HINT_REGS
 
-	ENTER_IRQ_STACK old_rsp=%r10
-	call	xen_evtchn_do_upcall
-	LEAVE_IRQ_STACK
+	call	xen_pv_evtchn_do_upcall
 
-#ifndef CONFIG_PREEMPTION
-	call	xen_maybe_preempt_hcall
-#endif
-	jmp	error_exit
-SYM_CODE_END(xen_do_hypervisor_callback)
+	jmp	error_return
+SYM_CODE_END(exc_xen_hypervisor_callback)
 
 /*
  * Hypervisor uses this for application faults while it executes.
@@ -1155,7 +784,7 @@ SYM_CODE_START(xen_failsafe_callback)
 	addq	$0x30, %rsp
 	pushq	$0				/* RIP */
 	UNWIND_HINT_IRET_REGS offset=8
-	jmp	general_protection
+	jmp	asm_exc_general_protection
 1:	/* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
 	movq	(%rsp), %rcx
 	movq	8(%rsp), %r11
@@ -1164,48 +793,10 @@ SYM_CODE_START(xen_failsafe_callback)
 	pushq	$-1 /* orig_ax = -1 => not a system call */
 	PUSH_AND_CLEAR_REGS
 	ENCODE_FRAME_POINTER
-	jmp	error_exit
+	jmp	error_return
 SYM_CODE_END(xen_failsafe_callback)
 #endif /* CONFIG_XEN_PV */
 
-#ifdef CONFIG_XEN_PVHVM
-apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
-	xen_hvm_callback_vector xen_evtchn_do_upcall
-#endif
-
-
-#if IS_ENABLED(CONFIG_HYPERV)
-apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
-	hyperv_callback_vector hyperv_vector_handler
-
-apicinterrupt3 HYPERV_REENLIGHTENMENT_VECTOR \
-	hyperv_reenlightenment_vector hyperv_reenlightenment_intr
-
-apicinterrupt3 HYPERV_STIMER0_VECTOR \
-	hv_stimer0_callback_vector hv_stimer0_vector_handler
-#endif /* CONFIG_HYPERV */
-
-#if IS_ENABLED(CONFIG_ACRN_GUEST)
-apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
-	acrn_hv_callback_vector acrn_hv_vector_handler
-#endif
-
-idtentry debug			do_debug		has_error_code=0	paranoid=1 shift_ist=IST_INDEX_DB ist_offset=DB_STACK_OFFSET
-idtentry int3			do_int3			has_error_code=0	create_gap=1
-idtentry stack_segment		do_stack_segment	has_error_code=1
-
-#ifdef CONFIG_XEN_PV
-idtentry xennmi			do_nmi			has_error_code=0
-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	read_cr2=1
-
-#ifdef CONFIG_X86_MCE
-idtentry machine_check		do_mce			has_error_code=0	paranoid=1
-#endif
-
 /*
  * Save all registers in pt_regs, and switch gs if needed.
  * Use slow, but surefire "are we in kernel?" check.
@@ -1261,17 +852,13 @@ SYM_CODE_END(paranoid_entry)
  */
 SYM_CODE_START_LOCAL(paranoid_exit)
 	UNWIND_HINT_REGS
-	DISABLE_INTERRUPTS(CLBR_ANY)
-	TRACE_IRQS_OFF_DEBUG
 	testl	%ebx, %ebx			/* swapgs needed? */
 	jnz	.Lparanoid_exit_no_swapgs
-	TRACE_IRQS_IRETQ
 	/* Always restore stashed CR3 value (see paranoid_entry) */
 	RESTORE_CR3	scratch_reg=%rbx save_reg=%r14
 	SWAPGS_UNSAFE_STACK
 	jmp	restore_regs_and_return_to_kernel
 .Lparanoid_exit_no_swapgs:
-	TRACE_IRQS_IRETQ_DEBUG
 	/* Always restore stashed CR3 value (see paranoid_entry) */
 	RESTORE_CR3	scratch_reg=%rbx save_reg=%r14
 	jmp restore_regs_and_return_to_kernel
@@ -1335,7 +922,6 @@ SYM_CODE_START_LOCAL(error_entry)
 	 */
 	SWAPGS
 	FENCE_SWAPGS_USER_ENTRY
-	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 	jmp .Lerror_entry_done
 
 .Lbstep_iret:
@@ -1362,14 +948,13 @@ SYM_CODE_START_LOCAL(error_entry)
 	jmp	.Lerror_entry_from_usermode_after_swapgs
 SYM_CODE_END(error_entry)
 
-SYM_CODE_START_LOCAL(error_exit)
+SYM_CODE_START_LOCAL(error_return)
 	UNWIND_HINT_REGS
-	DISABLE_INTERRUPTS(CLBR_ANY)
-	TRACE_IRQS_OFF
+	DEBUG_ENTRY_ASSERT_IRQS_OFF
 	testb	$3, CS(%rsp)
-	jz	retint_kernel
-	jmp	.Lretint_user
-SYM_CODE_END(error_exit)
+	jz	restore_regs_and_return_to_kernel
+	jmp	swapgs_restore_regs_and_return_to_usermode
+SYM_CODE_END(error_return)
 
 /*
  * Runs on exception stack.  Xen PV does not go through this path at all,
@@ -1379,7 +964,7 @@ SYM_CODE_END(error_exit)
  *	%r14: Used to save/restore the CR3 of the interrupted context
  *	      when PAGE_TABLE_ISOLATION is in use.  Do not clobber.
  */
-SYM_CODE_START(nmi)
+SYM_CODE_START(asm_exc_nmi)
 	UNWIND_HINT_IRET_REGS
 
 	/*
@@ -1464,7 +1049,7 @@ SYM_CODE_START(nmi)
 
 	movq	%rsp, %rdi
 	movq	$-1, %rsi
-	call	do_nmi
+	call	exc_nmi
 
 	/*
 	 * Return back to user mode.  We must *not* do the normal exit
@@ -1521,7 +1106,7 @@ SYM_CODE_START(nmi)
 	 * end_repeat_nmi, then we are a nested NMI.  We must not
 	 * modify the "iret" frame because it's being written by
 	 * the outer NMI.  That's okay; the outer NMI handler is
-	 * about to about to call do_nmi anyway, so we can just
+	 * about to about to call exc_nmi() anyway, so we can just
 	 * resume the outer NMI.
 	 */
 
@@ -1640,7 +1225,7 @@ repeat_nmi:
 	 * RSP is pointing to "outermost RIP".  gsbase is unknown, but, if
 	 * we're repeating an NMI, gsbase has the same value that it had on
 	 * the first iteration.  paranoid_entry will load the kernel
-	 * gsbase if needed before we call do_nmi.  "NMI executing"
+	 * gsbase if needed before we call exc_nmi().  "NMI executing"
 	 * is zero.
 	 */
 	movq	$1, 10*8(%rsp)		/* Set "NMI executing". */
@@ -1674,10 +1259,9 @@ end_repeat_nmi:
 	call	paranoid_entry
 	UNWIND_HINT_REGS
 
-	/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
 	movq	%rsp, %rdi
 	movq	$-1, %rsi
-	call	do_nmi
+	call	exc_nmi
 
 	/* Always restore stashed CR3 value (see paranoid_entry) */
 	RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
@@ -1714,7 +1298,7 @@ nmi_restore:
 	 * about espfix64 on the way back to kernel mode.
 	 */
 	iretq
-SYM_CODE_END(nmi)
+SYM_CODE_END(asm_exc_nmi)
 
 #ifndef CONFIG_IA32_EMULATION
 /*
@@ -1728,6 +1312,7 @@ SYM_CODE_START(ignore_sysret)
 SYM_CODE_END(ignore_sysret)
 #endif
 
+.pushsection .text, "ax"
 SYM_CODE_START(rewind_stack_do_exit)
 	UNWIND_HINT_FUNC
 	/* Prevent any naive code from trying to unwind to our caller. */
@@ -1739,3 +1324,4 @@ SYM_CODE_START(rewind_stack_do_exit)
 
 	call	do_exit
 SYM_CODE_END(rewind_stack_do_exit)
+.popsection
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index f1d3ccae5dd5..0f974ae01e62 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -46,12 +46,14 @@
  * ebp  user stack
  * 0(%ebp) arg6
  */
-SYM_FUNC_START(entry_SYSENTER_compat)
+SYM_CODE_START(entry_SYSENTER_compat)
+	UNWIND_HINT_EMPTY
 	/* Interrupts are off on entry. */
 	SWAPGS
 
-	/* We are about to clobber %rsp anyway, clobbering here is OK */
-	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+	pushq	%rax
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
+	popq	%rax
 
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
@@ -104,6 +106,9 @@ SYM_FUNC_START(entry_SYSENTER_compat)
 	xorl	%r14d, %r14d		/* nospec   r14 */
 	pushq   $0			/* pt_regs->r15 = 0 */
 	xorl	%r15d, %r15d		/* nospec   r15 */
+
+	UNWIND_HINT_REGS
+
 	cld
 
 	/*
@@ -129,17 +134,11 @@ SYM_FUNC_START(entry_SYSENTER_compat)
 	jnz	.Lsysenter_fix_flags
 .Lsysenter_flags_fixed:
 
-	/*
-	 * User mode is traced as though IRQs are on, and SYSENTER
-	 * turned them off.
-	 */
-	TRACE_IRQS_OFF
-
 	movq	%rsp, %rdi
 	call	do_fast_syscall_32
 	/* XEN PV guests always use IRET path */
-	ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
-		    "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
+	ALTERNATIVE "testl %eax, %eax; jz swapgs_restore_regs_and_return_to_usermode", \
+		    "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
 	jmp	sysret32_from_system_call
 
 .Lsysenter_fix_flags:
@@ -147,7 +146,7 @@ SYM_FUNC_START(entry_SYSENTER_compat)
 	popfq
 	jmp	.Lsysenter_flags_fixed
 SYM_INNER_LABEL(__end_entry_SYSENTER_compat, SYM_L_GLOBAL)
-SYM_FUNC_END(entry_SYSENTER_compat)
+SYM_CODE_END(entry_SYSENTER_compat)
 
 /*
  * 32-bit SYSCALL entry.
@@ -197,6 +196,7 @@ SYM_FUNC_END(entry_SYSENTER_compat)
  * 0(%esp) arg6
  */
 SYM_CODE_START(entry_SYSCALL_compat)
+	UNWIND_HINT_EMPTY
 	/* Interrupts are off on entry. */
 	swapgs
 
@@ -247,17 +247,13 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL)
 	pushq   $0			/* pt_regs->r15 = 0 */
 	xorl	%r15d, %r15d		/* nospec   r15 */
 
-	/*
-	 * User mode is traced as though IRQs are on, and SYSENTER
-	 * turned them off.
-	 */
-	TRACE_IRQS_OFF
+	UNWIND_HINT_REGS
 
 	movq	%rsp, %rdi
 	call	do_fast_syscall_32
 	/* XEN PV guests always use IRET path */
-	ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
-		    "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
+	ALTERNATIVE "testl %eax, %eax; jz swapgs_restore_regs_and_return_to_usermode", \
+		    "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
 
 	/* Opportunistic SYSRET */
 sysret32_from_system_call:
@@ -266,7 +262,7 @@ sysret32_from_system_call:
 	 * stack. So let's erase the thread stack right now.
 	 */
 	STACKLEAK_ERASE
-	TRACE_IRQS_ON			/* User mode traces as IRQs on. */
+
 	movq	RBX(%rsp), %rbx		/* pt_regs->rbx */
 	movq	RBP(%rsp), %rbp		/* pt_regs->rbp */
 	movq	EFLAGS(%rsp), %r11	/* pt_regs->flags (in r11) */
@@ -340,6 +336,7 @@ SYM_CODE_END(entry_SYSCALL_compat)
  * ebp  arg6
  */
 SYM_CODE_START(entry_INT80_compat)
+	UNWIND_HINT_EMPTY
 	/*
 	 * Interrupts are off on entry.
 	 */
@@ -361,8 +358,11 @@ SYM_CODE_START(entry_INT80_compat)
 
 	/* Need to switch before accessing the thread stack. */
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+
 	/* In the Xen PV case we already run on the thread stack. */
-	ALTERNATIVE "movq %rsp, %rdi", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV
+	ALTERNATIVE "", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV
+
+	movq	%rsp, %rdi
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	pushq	6*8(%rdi)		/* regs->ss */
@@ -401,19 +401,12 @@ SYM_CODE_START(entry_INT80_compat)
 	xorl	%r14d, %r14d		/* nospec   r14 */
 	pushq   %r15                    /* pt_regs->r15 */
 	xorl	%r15d, %r15d		/* nospec   r15 */
-	cld
 
-	/*
-	 * User mode is traced as though IRQs are on, and the interrupt
-	 * gate turned them off.
-	 */
-	TRACE_IRQS_OFF
+	UNWIND_HINT_REGS
+
+	cld
 
 	movq	%rsp, %rdi
 	call	do_int80_syscall_32
-.Lsyscall_32_done:
-
-	/* Go back to user mode. */
-	TRACE_IRQS_ON
 	jmp	swapgs_restore_regs_and_return_to_usermode
 SYM_CODE_END(entry_INT80_compat)
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index dbe4493b534e..ccd32877a3c4 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -3,7 +3,6 @@
  * Save registers before calling assembly functions. This avoids
  * disturbance of register allocation in some inline assembly constructs.
  * Copyright 2001,2002 by Andi Kleen, SuSE Labs.
- * Added trace_hardirqs callers - Copyright 2007 Steven Rostedt, Red Hat, Inc.
  */
 #include <linux/linkage.h>
 #include "calling.h"
@@ -37,15 +36,6 @@ SYM_FUNC_END(\name)
 	_ASM_NOKPROBE(\name)
 	.endm
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-	THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1
-	THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1
-#endif
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	THUNK lockdep_sys_exit_thunk,lockdep_sys_exit
-#endif
-
 #ifdef CONFIG_PREEMPTION
 	THUNK preempt_schedule_thunk, preempt_schedule
 	THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
@@ -53,9 +43,7 @@ SYM_FUNC_END(\name)
 	EXPORT_SYMBOL(preempt_schedule_notrace_thunk)
 #endif
 
-#if defined(CONFIG_TRACE_IRQFLAGS) \
- || defined(CONFIG_DEBUG_LOCK_ALLOC) \
- || defined(CONFIG_PREEMPTION)
+#ifdef CONFIG_PREEMPTION
 SYM_CODE_START_LOCAL_NOALIGN(.L_restore)
 	popq %r11
 	popq %r10