xen/grant-table: add a mechanism to safely unmap pages that are in use

Introduce gnttab_unmap_refs_async() that can be used to safely unmap
pages that may be in use (ref count > 1).  If the pages are in use the
unmap is deferred and retried later.  This polling is not very clever
but it should be good enough if the cases where the delay is necessary
are rare.

The initial delay is 5 ms and is increased linearly on each subsequent
retry (to reduce load if the page is in use for a long time).

This is needed to allow block backends using grant mapping to safely
use network storage (block or filesystem based such as iSCSI or NFS).

The network storage driver may complete a block request whilst there
is a queued network packet retry (because the ack from the remote end
races with deciding to queue the retry).  The pages for the retried
packet would be grant unmapped and the network driver (or hardware)
would access the unmapped page.

Signed-off-by: Jennifer Herbert <jennifer.herbert@citrix.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>

1 files changed, 44 insertions, 0 deletions

diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 89dcca448bb6..17972fbacddc 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -42,6 +42,7 @@
 #include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/hardirq.h>
+#include <linux/workqueue.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
@@ -819,6 +820,49 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 }
 EXPORT_SYMBOL_GPL(gnttab_unmap_refs);
 
+#define GNTTAB_UNMAP_REFS_DELAY 5
+
+static void __gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item);
+
+static void gnttab_unmap_work(struct work_struct *work)
+{
+        struct gntab_unmap_queue_data
+                *unmap_data = container_of(work, 
+                                           struct gntab_unmap_queue_data,
+                                           gnttab_work.work);
+        if (unmap_data->age != UINT_MAX)
+                unmap_data->age++;
+        __gnttab_unmap_refs_async(unmap_data);
+}
+
+static void __gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item)
+{
+        int ret;
+        int pc;
+
+        for (pc = 0; pc < item->count; pc++) {
+                if (page_count(item->pages[pc]) > 1) {
+                        unsigned long delay = GNTTAB_UNMAP_REFS_DELAY * (item->age + 1);
+                        schedule_delayed_work(&item->gnttab_work,
+                                              msecs_to_jiffies(delay));
+                        return;
+                }
+        }
+
+        ret = gnttab_unmap_refs(item->unmap_ops, item->kunmap_ops,
+                                item->pages, item->count);
+        item->done(ret, item);
+}
+
+void gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item)
+{
+        INIT_DELAYED_WORK(&item->gnttab_work, gnttab_unmap_work);
+        item->age = 0;
+
+        __gnttab_unmap_refs_async(item);
+}
+EXPORT_SYMBOL_GPL(gnttab_unmap_refs_async);
+
 static int gnttab_map_frames_v1(xen_pfn_t *frames, unsigned int nr_gframes)
 {
         int rc;