x86/entry: Switch XEN/PV hypercall entry to IDTENTRY

Convert the XEN/PV hypercall to IDTENTRY:

  - Emit the ASM stub with DECLARE_IDTENTRY
  - Remove the ASM idtentry in 64-bit
  - Remove the open coded ASM entry code in 32-bit
  - Remove the old prototypes

The handler stubs need to stay in ASM code as they need corner case handling
and adjustment of the stack pointer.

Provide a new C function which invokes the entry/exit handling and calls
into the XEN handler on the interrupt stack if required.

The exit code is slightly different from the regular idtentry_exit() on
non-preemptible kernels. If the hypercall is preemptible and need_resched()
is set then XEN provides a preempt hypercall scheduling function.

Move this functionality into the entry code so it can use the existing
idtentry functionality.

[ mingo: Build fixes. ]

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Juergen Gross <jgross@suse.com>
Tested-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/20200521202118.055270078@linutronix.de

3 files changed, 96 insertions, 22 deletions

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 066215a243b4..a0f8c3cb130a 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>
@@ -35,6 +40,7 @@
 #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>
@@ -680,3 +686,75 @@ void noinstr idtentry_exit_user(struct pt_regs *regs)
 
 	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 28d13f07b84d..3ab04dca9aab 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -1298,7 +1298,13 @@ SYM_CODE_END(native_iret)
 #endif
 
 #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
@@ -1315,14 +1321,11 @@ 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.
@@ -1464,6 +1467,7 @@ SYM_CODE_START_LOCAL_NOALIGN(handle_exception)
 	movl	%esp, %eax			# pt_regs pointer
 	CALL_NOSPEC edi
 
+handle_exception_return:
 #ifdef CONFIG_VM86
 	movl	PT_EFLAGS(%esp), %eax		# mix EFLAGS and CS
 	movb	PT_CS(%esp), %al
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 6b518be4da0a..dadb37d07266 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1067,10 +1067,6 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
 
 idtentry	X86_TRAP_PF		page_fault		do_page_fault			has_error_code=1
 
-#ifdef CONFIG_XEN_PV
-idtentry	512 /* dummy */		hypervisor_callback	xen_do_hypervisor_callback	has_error_code=0
-#endif
-
 /*
  * Reload gs selector with exception handling
  * edi:  new selector
@@ -1158,9 +1154,10 @@ SYM_FUNC_END(asm_call_on_stack)
  * 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
@@ -1170,15 +1167,10 @@ 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.