xen64: add hypervisor callbacks for events, etc

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Stephen Tweedie <sct@redhat.com>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Cc: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index ae63e584c340cbafd342af95e18bce946b474525..7cc2de79614667bc2ccc3d6d399badbf1ab26daf 100644 (file)
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1312,3 +1312,101 @@ KPROBE_ENTRY(ignore_sysret)
        sysret
        CFI_ENDPROC
 ENDPROC(ignore_sysret)
+
+#ifdef CONFIG_XEN
+ENTRY(xen_hypervisor_callback)
+       zeroentry xen_do_hypervisor_callback
+END(xen_hypervisor_callback)
+
+/*
+# A note on the "critical region" in our callback handler.
+# We want to avoid stacking callback handlers due to events occurring
+# during handling of the last event. To do this, we keep events disabled
+# until we've done all processing. HOWEVER, we must enable events before
+# popping the stack frame (can't be done atomically) and so it would still
+# be possible to get enough handler activations to overflow the stack.
+# Although unlikely, bugs of that kind are hard to track down, so we'd
+# like to avoid the possibility.
+# 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.
+*/
+ENTRY(xen_do_hypervisor_callback)   # do_hypervisor_callback(struct *pt_regs)
+       CFI_STARTPROC
+/* Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
+   see the correct pointer to the pt_regs */
+       movq %rdi, %rsp            # we don't return, adjust the stack frame
+       CFI_ENDPROC
+       CFI_DEFAULT_STACK
+11:    incl %gs:pda_irqcount
+       movq %rsp,%rbp
+       CFI_DEF_CFA_REGISTER rbp
+       cmovzq %gs:pda_irqstackptr,%rsp
+       pushq %rbp                      # backlink for old unwinder
+       call xen_evtchn_do_upcall
+       popq %rsp
+       CFI_DEF_CFA_REGISTER rsp
+       decl %gs:pda_irqcount
+       jmp  error_exit
+       CFI_ENDPROC
+END(do_hypervisor_callback)
+
+/*
+# Hypervisor uses this for application faults while it executes.
+# We get here for two reasons:
+#  1. Fault while reloading DS, ES, FS or GS
+#  2. Fault while executing IRET
+# Category 1 we do not need to fix up as Xen has already reloaded all segment
+# registers that could be reloaded and zeroed the others.
+# Category 2 we fix up by killing the current process. We cannot use the
+# normal Linux return path in this case because if we use the IRET hypercall
+# to pop the stack frame we end up in an infinite loop of failsafe callbacks.
+# We distinguish between categories by comparing each saved segment register
+# with its current contents: any discrepancy means we in category 1.
+*/
+ENTRY(xen_failsafe_callback)
+#if 1
+       ud2a
+#else
+       _frame (RIP-0x30)
+       CFI_REL_OFFSET rcx, 0
+       CFI_REL_OFFSET r11, 8
+       movw %ds,%cx
+       cmpw %cx,0x10(%rsp)
+       CFI_REMEMBER_STATE
+       jne 1f
+       movw %es,%cx
+       cmpw %cx,0x18(%rsp)
+       jne 1f
+       movw %fs,%cx
+       cmpw %cx,0x20(%rsp)
+       jne 1f
+       movw %gs,%cx
+       cmpw %cx,0x28(%rsp)
+       jne 1f
+       /* All segments match their saved values => Category 2 (Bad IRET). */
+       movq (%rsp),%rcx
+       CFI_RESTORE rcx
+       movq 8(%rsp),%r11
+       CFI_RESTORE r11
+       addq $0x30,%rsp
+       CFI_ADJUST_CFA_OFFSET -0x30
+       movq $11,%rdi   /* SIGSEGV */
+       jmp do_exit
+       CFI_RESTORE_STATE
+1:     /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
+       movq (%rsp),%rcx
+       CFI_RESTORE rcx
+       movq 8(%rsp),%r11
+       CFI_RESTORE r11
+       addq $0x30,%rsp
+       CFI_ADJUST_CFA_OFFSET -0x30
+       pushq $0
+       CFI_ADJUST_CFA_OFFSET 8
+       SAVE_ALL
+       jmp error_exit
+       CFI_ENDPROC
+#endif
+END(xen_failsafe_callback)
+
+#endif /* CONFIG_XEN */