4 files changed, 107 insertions, 44 deletions

diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index b5f776f60b1b..02d752460371 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1187,7 +1187,7 @@ static void drop_other_mm_ref(void *info)
 
         active_mm = percpu_read(cpu_tlbstate.active_mm);
 
-        if (active_mm == mm)
+        if (active_mm == mm && percpu_read(cpu_tlbstate.state) != TLBSTATE_OK)
                 leave_mm(smp_processor_id());
 
         /* If this cpu still has a stale cr3 reference, then make sure
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index c851397e657c..58efeb9d5440 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -522,11 +522,20 @@ static bool __init __early_alloc_p2m(unsigned long pfn)
         /* Boundary cross-over for the edges: */
         if (idx) {
                 unsigned long *p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);
+                unsigned long *mid_mfn_p;
 
                 p2m_init(p2m);
 
                 p2m_top[topidx][mididx] = p2m;
 
+                /* For save/restore we need to MFN of the P2M saved */
+                
+                mid_mfn_p = p2m_top_mfn_p[topidx];
+                WARN(mid_mfn_p[mididx] != virt_to_mfn(p2m_missing),
+                        "P2M_TOP_P[%d][%d] != MFN of p2m_missing!\n",
+                        topidx, mididx);
+                mid_mfn_p[mididx] = virt_to_mfn(p2m);
+
         }
         return idx != 0;
 }
@@ -549,12 +558,29 @@ unsigned long __init set_phys_range_identity(unsigned long pfn_s,
                 pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE)
         {
                 unsigned topidx = p2m_top_index(pfn);
-                if (p2m_top[topidx] == p2m_mid_missing) {
-                        unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
+                unsigned long *mid_mfn_p;
+                unsigned long **mid;
+
+                mid = p2m_top[topidx];
+                mid_mfn_p = p2m_top_mfn_p[topidx];
+                if (mid == p2m_mid_missing) {
+                        mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
 
                         p2m_mid_init(mid);
 
                         p2m_top[topidx] = mid;
+
+                        BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
+                }
+                /* And the save/restore P2M tables.. */
+                if (mid_mfn_p == p2m_mid_missing_mfn) {
+                        mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
+                        p2m_mid_mfn_init(mid_mfn_p);
+
+                        p2m_top_mfn_p[topidx] = mid_mfn_p;
+                        p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
+                        /* Note: we don't set mid_mfn_p[midix] here,
+                         * look in __early_alloc_p2m */
                 }
         }
 
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index d3663df2f967..be1a464f6d66 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -166,7 +166,7 @@ static unsigned long __init xen_set_identity(const struct e820entry *list,
                 if (last > end)
                         continue;
 
-                if (entry->type == E820_RAM) {
+                if ((entry->type == E820_RAM) || (entry->type == E820_UNUSABLE)) {
                         if (start > start_pci)
                                 identity += set_phys_range_identity(
                                                 PFN_UP(start_pci), PFN_DOWN(start));
@@ -227,7 +227,11 @@ char * __init xen_memory_setup(void)
 
         memcpy(map_raw, map, sizeof(map));
         e820.nr_map = 0;
+#ifdef CONFIG_X86_32
+        xen_extra_mem_start = mem_end;
+#else
         xen_extra_mem_start = max((1ULL << 32), mem_end);
+#endif
         for (i = 0; i < memmap.nr_entries; i++) {
                 unsigned long long end;
 
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 35e02a10110b..3ff822b48145 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -119,6 +119,8 @@ static DEFINE_PER_CPU(unsigned long [NR_EVENT_CHANNELS/BITS_PER_LONG],
 static struct irq_chip xen_dynamic_chip;
 static struct irq_chip xen_percpu_chip;
 static struct irq_chip xen_pirq_chip;
+static void enable_dynirq(struct irq_data *data);
+static void disable_dynirq(struct irq_data *data);
 
 /* Get info for IRQ */
 static struct irq_info *info_for_irq(unsigned irq)
@@ -476,16 +478,6 @@ static void xen_free_irq(unsigned irq)
         irq_free_desc(irq);
 }
 
-static void pirq_unmask_notify(int irq)
-{
-        struct physdev_eoi eoi = { .irq = pirq_from_irq(irq) };
-
-        if (unlikely(pirq_needs_eoi(irq))) {
-                int rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
-                WARN_ON(rc);
-        }
-}
-
 static void pirq_query_unmask(int irq)
 {
         struct physdev_irq_status_query irq_status;
@@ -509,6 +501,29 @@ static bool probing_irq(int irq)
         return desc && desc->action == NULL;
 }
 
+static void eoi_pirq(struct irq_data *data)
+{
+        int evtchn = evtchn_from_irq(data->irq);
+        struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) };
+        int rc = 0;
+
+        irq_move_irq(data);
+
+        if (VALID_EVTCHN(evtchn))
+                clear_evtchn(evtchn);
+
+        if (pirq_needs_eoi(data->irq)) {
+                rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
+                WARN_ON(rc);
+        }
+}
+
+static void mask_ack_pirq(struct irq_data *data)
+{
+        disable_dynirq(data);
+        eoi_pirq(data);
+}
+
 static unsigned int __startup_pirq(unsigned int irq)
 {
         struct evtchn_bind_pirq bind_pirq;
@@ -542,7 +557,7 @@ static unsigned int __startup_pirq(unsigned int irq)
 
 out:
         unmask_evtchn(evtchn);
-        pirq_unmask_notify(irq);
+        eoi_pirq(irq_get_irq_data(irq));
 
         return 0;
 }
@@ -582,18 +597,7 @@ static void enable_pirq(struct irq_data *data)
 
 static void disable_pirq(struct irq_data *data)
 {
-}
-
-static void ack_pirq(struct irq_data *data)
-{
-        int evtchn = evtchn_from_irq(data->irq);
-
-        irq_move_irq(data);
-
-        if (VALID_EVTCHN(evtchn)) {
-                mask_evtchn(evtchn);
-                clear_evtchn(evtchn);
-        }
+        disable_dynirq(data);
 }
 
 static int find_irq_by_gsi(unsigned gsi)
@@ -642,9 +646,6 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
         if (irq < 0)
                 goto out;
 
-        irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_level_irq,
-                                      name);
-
         irq_op.irq = irq;
         irq_op.vector = 0;
 
@@ -661,6 +662,32 @@ int xen_bind_pirq_gsi_to_irq(unsigned gsi,
         xen_irq_info_pirq_init(irq, 0, pirq, gsi, irq_op.vector, DOMID_SELF,
                                shareable ? PIRQ_SHAREABLE : 0);
 
+        pirq_query_unmask(irq);
+        /* We try to use the handler with the appropriate semantic for the
+         * type of interrupt: if the interrupt doesn't need an eoi
+         * (pirq_needs_eoi returns false), we treat it like an edge
+         * triggered interrupt so we use handle_edge_irq.
+         * As a matter of fact this only happens when the corresponding
+         * physical interrupt is edge triggered or an msi.
+         *
+         * On the other hand if the interrupt needs an eoi (pirq_needs_eoi
+         * returns true) we treat it like a level triggered interrupt so we
+         * use handle_fasteoi_irq like the native code does for this kind of
+         * interrupts.
+         * Depending on the Xen version, pirq_needs_eoi might return true
+         * not only for level triggered interrupts but for edge triggered
+         * interrupts too. In any case Xen always honors the eoi mechanism,
+         * not injecting any more pirqs of the same kind if the first one
+         * hasn't received an eoi yet. Therefore using the fasteoi handler
+         * is the right choice either way.
+         */
+        if (pirq_needs_eoi(irq))
+                irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
+                                handle_fasteoi_irq, name);
+        else
+                irq_set_chip_and_handler_name(irq, &xen_pirq_chip,
+                                handle_edge_irq, name);
+
 out:
         spin_unlock(&irq_mapping_update_lock);
 
@@ -694,8 +721,8 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
         if (irq == -1)
                 goto out;
 
-        irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_level_irq,
-                                      name);
+        irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_edge_irq,
+                        name);
 
         xen_irq_info_pirq_init(irq, 0, pirq, 0, vector, domid, 0);
         ret = irq_set_msi_desc(irq, msidesc);
@@ -790,7 +817,7 @@ int bind_evtchn_to_irq(unsigned int evtchn)
                         goto out;
 
                 irq_set_chip_and_handler_name(irq, &xen_dynamic_chip,
-                                              handle_fasteoi_irq, "event");
+                                              handle_edge_irq, "event");
 
                 xen_irq_info_evtchn_init(irq, evtchn);
         }
@@ -1196,9 +1223,6 @@ static void __xen_evtchn_do_upcall(void)
                                 port = (word_idx * BITS_PER_LONG) + bit_idx;
                                 irq = evtchn_to_irq[port];
 
-                                mask_evtchn(port);
-                                clear_evtchn(port);
-
                                 if (irq != -1) {
                                         desc = irq_to_desc(irq);
                                         if (desc)
@@ -1354,10 +1378,16 @@ static void ack_dynirq(struct irq_data *data)
 {
         int evtchn = evtchn_from_irq(data->irq);
 
-        irq_move_masked_irq(data);
+        irq_move_irq(data);
 
         if (VALID_EVTCHN(evtchn))
-                unmask_evtchn(evtchn);
+                clear_evtchn(evtchn);
+}
+
+static void mask_ack_dynirq(struct irq_data *data)
+{
+        disable_dynirq(data);
+        ack_dynirq(data);
 }
 
 static int retrigger_dynirq(struct irq_data *data)
@@ -1564,7 +1594,9 @@ static struct irq_chip xen_dynamic_chip __read_mostly = {
         .irq_mask               = disable_dynirq,
         .irq_unmask             = enable_dynirq,
 
-        .irq_eoi                = ack_dynirq,
+        .irq_ack                = ack_dynirq,
+        .irq_mask_ack           = mask_ack_dynirq,
+
         .irq_set_affinity       = set_affinity_irq,
         .irq_retrigger          = retrigger_dynirq,
 };
@@ -1574,14 +1606,15 @@ static struct irq_chip xen_pirq_chip __read_mostly = {
 
         .irq_startup            = startup_pirq,
         .irq_shutdown           = shutdown_pirq,
-
         .irq_enable             = enable_pirq,
-        .irq_unmask             = enable_pirq,
-
         .irq_disable            = disable_pirq,
-        .irq_mask               = disable_pirq,
 
-        .irq_ack                = ack_pirq,
+        .irq_mask               = disable_dynirq,
+        .irq_unmask             = enable_dynirq,
+
+        .irq_ack                = eoi_pirq,
+        .irq_eoi                = eoi_pirq,
+        .irq_mask_ack           = mask_ack_pirq,
 
         .irq_set_affinity       = set_affinity_irq,