x86/xen: allow privcmd hypercalls to be preempted

Hypercalls submitted by user space tools via the privcmd driver can
take a long time (potentially many 10s of seconds) if the hypercall
has many sub-operations.

A fully preemptible kernel may deschedule such as task in any upcall
called from a hypercall continuation.

However, in a kernel with voluntary or no preemption, hypercall
continuations in Xen allow event handlers to be run but the task
issuing the hypercall will not be descheduled until the hypercall is
complete and the ioctl returns to user space.  These long running
tasks may also trigger the kernel's soft lockup detection.

Add xen_preemptible_hcall_begin() and xen_preemptible_hcall_end() to
bracket hypercalls that may be preempted.  Use these in the privcmd
driver.

When returning from an upcall, call xen_maybe_preempt_hcall() which
adds a schedule point if if the current task was within a preemptible
hypercall.

Since _cond_resched() can move the task to a different CPU, clear and
set xen_in_preemptible_hcall around the call.

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>

6 files changed, 79 insertions, 1 deletions

diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 000d4199b03e..31e2d5bf3e38 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -982,6 +982,9 @@ ENTRY(xen_hypervisor_callback)
 ENTRY(xen_do_upcall)
 1:      mov %esp, %eax
         call xen_evtchn_do_upcall
+#ifndef CONFIG_PREEMPT
+        call xen_maybe_preempt_hcall
+#endif
         jmp  ret_from_intr
         CFI_ENDPROC
 ENDPROC(xen_hypervisor_callback)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index db13655c3a2a..10074ad9ebf8 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1208,6 +1208,9 @@ ENTRY(xen_do_hypervisor_callback)   # do_hypervisor_callback(struct *pt_regs)
         popq %rsp
         CFI_DEF_CFA_REGISTER rsp
         decl PER_CPU_VAR(irq_count)
+#ifndef CONFIG_PREEMPT
+        call xen_maybe_preempt_hcall
+#endif
         jmp  error_exit
         CFI_ENDPROC
 END(xen_do_hypervisor_callback)
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 2140398a2a8c..2ccd3592d41f 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -2,7 +2,7 @@ ifeq ($(filter y, $(CONFIG_ARM) $(CONFIG_ARM64)),)
 obj-$(CONFIG_HOTPLUG_CPU)               += cpu_hotplug.o
 endif
 obj-$(CONFIG_X86)                       += fallback.o
-obj-y   += grant-table.o features.o balloon.o manage.o
+obj-y   += grant-table.o features.o balloon.o manage.o preempt.o
 obj-y   += events/
 obj-y   += xenbus/
 
diff --git a/drivers/xen/preempt.c b/drivers/xen/preempt.c
new file mode 100644
index 000000000000..a1800c150839
--- /dev/null
+++ b/drivers/xen/preempt.c
@@ -0,0 +1,44 @@
+/*
+ * Preemptible hypercalls
+ *
+ * Copyright (C) 2014 Citrix Systems R&D ltd.
+ *
+ * This source code is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ */
+
+#include <linux/sched.h>
+#include <xen/xen-ops.h>
+
+#ifndef CONFIG_PREEMPT
+
+/*
+ * 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);
+
+asmlinkage __visible void xen_maybe_preempt_hcall(void)
+{
+        if (unlikely(__this_cpu_read(xen_in_preemptible_hcall)
+                     && should_resched())) {
+                /*
+                 * Clear flag as we may be rescheduled on a different
+                 * cpu.
+                 */
+                __this_cpu_write(xen_in_preemptible_hcall, false);
+                _cond_resched();
+                __this_cpu_write(xen_in_preemptible_hcall, true);
+        }
+}
+#endif /* CONFIG_PREEMPT */
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 569a13b9e856..59ac71c4a043 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -56,10 +56,12 @@ static long privcmd_ioctl_hypercall(void __user *udata)
         if (copy_from_user(&hypercall, udata, sizeof(hypercall)))
                 return -EFAULT;
 
+        xen_preemptible_hcall_begin();
         ret = privcmd_call(hypercall.op,
                            hypercall.arg[0], hypercall.arg[1],
                            hypercall.arg[2], hypercall.arg[3],
                            hypercall.arg[4]);
+        xen_preemptible_hcall_end();
 
         return ret;
 }
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 7491ee5d8164..83338210ee04 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -46,4 +46,30 @@ static inline efi_system_table_t __init *xen_efi_probe(void)
 }
 #endif
 
+#ifdef CONFIG_PREEMPT
+
+static inline void xen_preemptible_hcall_begin(void)
+{
+}
+
+static inline void xen_preemptible_hcall_end(void)
+{
+}
+
+#else
+
+DECLARE_PER_CPU(bool, xen_in_preemptible_hcall);
+
+static inline void xen_preemptible_hcall_begin(void)
+{
+        __this_cpu_write(xen_in_preemptible_hcall, true);
+}
+
+static inline void xen_preemptible_hcall_end(void)
+{
+        __this_cpu_write(xen_in_preemptible_hcall, false);
+}
+
+#endif /* CONFIG_PREEMPT */
+
 #endif /* INCLUDE_XEN_OPS_H */