xen: enter/exit lazy_mmu_mode around m2p_override calls

This patch is a significant performance improvement for the
m2p_override: about 6% using the gntdev device.

Each m2p_add/remove_override call issues a MULTI_grant_table_op and a
__flush_tlb_single if kmap_op != NULL.  Batching all the calls together
is a great performance benefit because it means issuing one hypercall
total rather than two hypercall per page.
If paravirt_lazy_mode is set PARAVIRT_LAZY_MMU, all these calls are
going to be batched together, otherwise they are issued one at a time.

Adding arch_enter_lazy_mmu_mode/arch_leave_lazy_mmu_mode around the
m2p_add/remove_override calls forces paravirt_lazy_mode to
PARAVIRT_LAZY_MMU, therefore makes sure that they are always batched.

However it is not safe to call arch_enter_lazy_mmu_mode if we are in
interrupt context or if we are already in PARAVIRT_LAZY_MMU mode, so
check for both conditions before doing so.

Changes in v4:
- rebased on 3.4-rc4: all the m2p_override users call gnttab_unmap_refs
and gnttab_map_refs;
- check whether we are in interrupt context and the lazy_mode we are in
before calling arch_enter/leave_lazy_mmu_mode.

Changes in v3:
- do not call arch_enter/leave_lazy_mmu_mode in xen_blkbk_unmap, that
can be called in interrupt context.
Signed-off-by: NStefano Stabellini <stefano.stabellini@eu.citrix.com>
[v5: s/int lazy/bool lazy/]
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

drivers/xen/grant-table.c

@@ -38,6 +38,7 @@
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
+#include <linux/hardirq.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
@@ -827,6 +828,7 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 		    struct page **pages, unsigned int count)
 {
 	int i, ret;
+	bool lazy = false;
 	pte_t *pte;
 	unsigned long mfn;
 
@@ -837,6 +839,11 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return ret;
 
+	if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
+		arch_enter_lazy_mmu_mode();
+		lazy = true;
+	}
+
 	for (i = 0; i < count; i++) {
 		/* Do not add to override if the map failed. */
 		if (map_ops[i].status)
@@ -855,6 +862,9 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 			return ret;
 	}
 
+	if (lazy)
+		arch_leave_lazy_mmu_mode();
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(gnttab_map_refs);
@@ -863,6 +873,7 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 		      struct page **pages, unsigned int count, bool clear_pte)
 {
 	int i, ret;
+	bool lazy = false;
 
 	ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap_ops, count);
 	if (ret)
@@ -871,12 +882,20 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return ret;
 
+	if (!in_interrupt() && paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
+		arch_enter_lazy_mmu_mode();
+		lazy = true;
+	}
+
 	for (i = 0; i < count; i++) {
 		ret = m2p_remove_override(pages[i], clear_pte);
 		if (ret)
 			return ret;
 	}
 
+	if (lazy)
+		arch_leave_lazy_mmu_mode();
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(gnttab_unmap_refs);