xen: implement save/restore

This patch implements Xen save/restore and migration.

Saving is triggered via xenbus, which is polled in
drivers/xen/manage.c.  When a suspend request comes in, the kernel
prepares itself for saving by:

1 - Freeze all processes.  This is primarily to prevent any
    partially-completed pagetable updates from confusing the suspend
    process.  If CONFIG_PREEMPT isn't defined, then this isn't necessary.

2 - Suspend xenbus and other devices

3 - Stop_machine, to make sure all the other vcpus are quiescent.  The
    Xen tools require the domain to run its save off vcpu0.

4 - Within the stop_machine state, it pins any unpinned pgds (under
    construction or destruction), performs canonicalizes various other
    pieces of state (mostly converting mfns to pfns), and finally

5 - Suspend the domain

Restore reverses the steps used to save the domain, ending when all
the frozen processes are thawed.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

7 files changed, 105 insertions, 5 deletions

diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 40b119b6b103..2ba2d1649131 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -1,4 +1,4 @@
 obj-y           := enlighten.o setup.o multicalls.o mmu.o \
-                        time.o xen-asm.o grant-table.o
+                        time.o xen-asm.o grant-table.o suspend.o
 
 obj-$(CONFIG_SMP)       += smp.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index ce67dc8f36af..b94f63ac228b 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -857,7 +857,7 @@ static __init void xen_pagetable_setup_start(pgd_t *base)
                           PFN_DOWN(__pa(xen_start_info->pt_base)));
 }
 
-static __init void setup_shared_info(void)
+void xen_setup_shared_info(void)
 {
         if (!xen_feature(XENFEAT_auto_translated_physmap)) {
                 unsigned long addr = fix_to_virt(FIX_PARAVIRT_BOOTMAP);
@@ -894,7 +894,7 @@ static __init void xen_pagetable_setup_done(pgd_t *base)
         pv_mmu_ops.release_pmd = xen_release_pmd;
         pv_mmu_ops.set_pte = xen_set_pte;
 
-        setup_shared_info();
+        xen_setup_shared_info();
 
         /* Actually pin the pagetable down, but we can't set PG_pinned
            yet because the page structures don't exist yet. */
@@ -902,7 +902,7 @@ static __init void xen_pagetable_setup_done(pgd_t *base)
 }
 
 /* This is called once we have the cpu_possible_map */
-void __init xen_setup_vcpu_info_placement(void)
+void xen_setup_vcpu_info_placement(void)
 {
         int cpu;
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 4740cda36563..e95955968ba3 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -560,6 +560,29 @@ void xen_pgd_pin(pgd_t *pgd)
         xen_mc_issue(0);
 }
 
+/*
+ * On save, we need to pin all pagetables to make sure they get their
+ * mfns turned into pfns.  Search the list for any unpinned pgds and pin
+ * them (unpinned pgds are not currently in use, probably because the
+ * process is under construction or destruction).
+ */
+void xen_mm_pin_all(void)
+{
+        unsigned long flags;
+        struct page *page;
+
+        spin_lock_irqsave(&pgd_lock, flags);
+
+        list_for_each_entry(page, &pgd_list, lru) {
+                if (!PagePinned(page)) {
+                        xen_pgd_pin((pgd_t *)page_address(page));
+                        SetPageSavePinned(page);
+                }
+        }
+
+        spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
 /* The init_mm pagetable is really pinned as soon as its created, but
    that's before we have page structures to store the bits.  So do all
    the book-keeping now. */
@@ -617,6 +640,29 @@ static void xen_pgd_unpin(pgd_t *pgd)
         xen_mc_issue(0);
 }
 
+/*
+ * On resume, undo any pinning done at save, so that the rest of the
+ * kernel doesn't see any unexpected pinned pagetables.
+ */
+void xen_mm_unpin_all(void)
+{
+        unsigned long flags;
+        struct page *page;
+
+        spin_lock_irqsave(&pgd_lock, flags);
+
+        list_for_each_entry(page, &pgd_list, lru) {
+                if (PageSavePinned(page)) {
+                        BUG_ON(!PagePinned(page));
+                        printk("unpinning pinned %p\n", page_address(page));
+                        xen_pgd_unpin((pgd_t *)page_address(page));
+                        ClearPageSavePinned(page);
+                }
+        }
+
+        spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
 void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next)
 {
         spin_lock(&next->page_table_lock);
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 74ab8968c525..d2e3c20127d7 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -35,7 +35,7 @@
 #include "xen-ops.h"
 #include "mmu.h"
 
-static cpumask_t xen_cpu_initialized_map;
+cpumask_t xen_cpu_initialized_map;
 static DEFINE_PER_CPU(int, resched_irq) = -1;
 static DEFINE_PER_CPU(int, callfunc_irq) = -1;
 static DEFINE_PER_CPU(int, debug_irq) = -1;
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
new file mode 100644
index 000000000000..7620a16fe535
--- /dev/null
+++ b/arch/x86/xen/suspend.c
@@ -0,0 +1,42 @@
+#include <linux/types.h>
+
+#include <xen/interface/xen.h>
+#include <xen/grant_table.h>
+#include <xen/events.h>
+
+#include <asm/xen/hypercall.h>
+#include <asm/xen/page.h>
+
+#include "xen-ops.h"
+#include "mmu.h"
+
+void xen_pre_suspend(void)
+{
+        xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn);
+        xen_start_info->console.domU.mfn =
+                mfn_to_pfn(xen_start_info->console.domU.mfn);
+
+        BUG_ON(!irqs_disabled());
+
+        HYPERVISOR_shared_info = &xen_dummy_shared_info;
+        if (HYPERVISOR_update_va_mapping(fix_to_virt(FIX_PARAVIRT_BOOTMAP),
+                                         __pte_ma(0), 0))
+                BUG();
+}
+
+void xen_post_suspend(int suspend_cancelled)
+{
+        if (suspend_cancelled) {
+                xen_start_info->store_mfn =
+                        pfn_to_mfn(xen_start_info->store_mfn);
+                xen_start_info->console.domU.mfn =
+                        pfn_to_mfn(xen_start_info->console.domU.mfn);
+        } else {
+#ifdef CONFIG_SMP
+                xen_cpu_initialized_map = cpu_online_map;
+#endif
+        }
+
+        xen_setup_shared_info();
+}
+
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index c39e1a5aa241..0bef256e5f2d 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -572,6 +572,14 @@ void xen_setup_cpu_clockevents(void)
         clockevents_register_device(&__get_cpu_var(xen_clock_events));
 }
 
+void xen_time_suspend(void)
+{
+}
+
+void xen_time_resume(void)
+{
+}
+
 __init void xen_time_init(void)
 {
         int cpu = smp_processor_id();
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index a1bc89a8f169..a0503acad664 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -9,6 +9,7 @@
 extern const char xen_hypervisor_callback[];
 extern const char xen_failsafe_callback[];
 
+struct trap_info;
 void xen_copy_trap_info(struct trap_info *traps);
 
 DECLARE_PER_CPU(unsigned long, xen_cr3);
@@ -19,6 +20,7 @@ extern struct shared_info xen_dummy_shared_info;
 extern struct shared_info *HYPERVISOR_shared_info;
 
 void xen_setup_mfn_list_list(void);
+void xen_setup_shared_info(void);
 
 char * __init xen_memory_setup(void);
 void __init xen_arch_setup(void);
@@ -59,6 +61,8 @@ int xen_smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 int xen_smp_call_function_mask(cpumask_t mask, void (*func)(void *),
                                void *info, int wait);
 
+extern cpumask_t xen_cpu_initialized_map;
+
 
 /* Declare an asm function, along with symbols needed to make it
    inlineable */