10 files changed, 61 insertions, 27 deletions

diff --git a/Documentation/ABI/stable/sysfs-devices-system-xen_memory b/Documentation/ABI/stable/sysfs-devices-system-xen_memory
index caa311d59ac1..6d83f95a8a8e 100644
--- a/Documentation/ABI/stable/sysfs-devices-system-xen_memory
+++ b/Documentation/ABI/stable/sysfs-devices-system-xen_memory
@@ -75,3 +75,12 @@ Contact:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
 Description:
                 Amount (in KiB) of low (or normal) memory in the
                 balloon.
+
+What:           /sys/devices/system/xen_memory/xen_memory0/scrub_pages
+Date:           September 2018
+KernelVersion:  4.20
+Contact:        xen-devel@lists.xenproject.org
+Description:
+                Control scrubbing pages before returning them to Xen for others domains
+                use. Can be set with xen_scrub_pages cmdline
+                parameter. Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 64a3bf54b974..92eb1f42240d 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5000,6 +5000,12 @@
                         Disables the PV optimizations forcing the HVM guest to
                         run as generic HVM guest with no PV drivers.
 
+        xen_scrub_pages=        [XEN]
+                        Boolean option to control scrubbing pages before giving them back
+                        to Xen, for use by other domains. Can be also changed at runtime
+                        with /sys/devices/system/xen_memory/xen_memory0/scrub_pages.
+                        Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT.
+
         xirc2ps_cs=     [NET,PCMCIA]
                         Format:
                         <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index b459edfacff3..90d387b50ab7 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -79,15 +79,19 @@ config XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
           This value is used to allocate enough space in internal
           tables needed for physical memory administration.
 
-config XEN_SCRUB_PAGES
-        bool "Scrub pages before returning them to system"
+config XEN_SCRUB_PAGES_DEFAULT
+        bool "Scrub pages before returning them to system by default"
         depends on XEN_BALLOON
         default y
         help
           Scrub pages before returning them to the system for reuse by
           other domains.  This makes sure that any confidential data
           is not accidentally visible to other domains.  Is it more
-          secure, but slightly less efficient.
+          secure, but slightly less efficient. This can be controlled with
+          xen_scrub_pages=0 parameter and
+          /sys/devices/system/xen_memory/xen_memory0/scrub_pages.
+          This option only sets the default value.
+
           If in doubt, say yes.
 
 config XEN_DEV_EVTCHN
diff --git a/drivers/xen/cpu_hotplug.c b/drivers/xen/cpu_hotplug.c
index d4265c8ebb22..b1357aa4bc55 100644
--- a/drivers/xen/cpu_hotplug.c
+++ b/drivers/xen/cpu_hotplug.c
@@ -19,15 +19,16 @@ static void enable_hotplug_cpu(int cpu)
 
 static void disable_hotplug_cpu(int cpu)
 {
-        if (cpu_online(cpu)) {
-                lock_device_hotplug();
+        if (!cpu_is_hotpluggable(cpu))
+                return;
+        lock_device_hotplug();
+        if (cpu_online(cpu))
                 device_offline(get_cpu_device(cpu));
-                unlock_device_hotplug();
-        }
-        if (cpu_present(cpu))
+        if (!cpu_online(cpu) && cpu_present(cpu)) {
                 xen_arch_unregister_cpu(cpu);
-
-        set_cpu_present(cpu, false);
+                set_cpu_present(cpu, false);
+        }
+        unlock_device_hotplug();
 }
 
 static int vcpu_online(unsigned int cpu)
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 08e4af04d6f2..e6c1934734b7 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -138,7 +138,7 @@ static int set_evtchn_to_irq(unsigned evtchn, unsigned irq)
                 clear_evtchn_to_irq_row(row);
         }
 
-        evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)] = irq;
+        evtchn_to_irq[row][col] = irq;
         return 0;
 }
 
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 57390c7666e5..b0b02a501167 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -492,12 +492,19 @@ static bool in_range(struct gntdev_grant_map *map,
         return true;
 }
 
-static void unmap_if_in_range(struct gntdev_grant_map *map,
-                              unsigned long start, unsigned long end)
+static int unmap_if_in_range(struct gntdev_grant_map *map,
+                              unsigned long start, unsigned long end,
+                              bool blockable)
 {
         unsigned long mstart, mend;
         int err;
 
+        if (!in_range(map, start, end))
+                return 0;
+
+        if (!blockable)
+                return -EAGAIN;
+
         mstart = max(start, map->vma->vm_start);
         mend   = min(end,   map->vma->vm_end);
         pr_debug("map %d+%d (%lx %lx), range %lx %lx, mrange %lx %lx\n",
@@ -508,6 +515,8 @@ static void unmap_if_in_range(struct gntdev_grant_map *map,
                                 (mstart - map->vma->vm_start) >> PAGE_SHIFT,
                                 (mend - mstart) >> PAGE_SHIFT);
         WARN_ON(err);
+
+        return 0;
 }
 
 static int mn_invl_range_start(struct mmu_notifier *mn,
@@ -519,25 +528,20 @@ static int mn_invl_range_start(struct mmu_notifier *mn,
         struct gntdev_grant_map *map;
         int ret = 0;
 
-        /* TODO do we really need a mutex here? */
         if (blockable)
                 mutex_lock(&priv->lock);
         else if (!mutex_trylock(&priv->lock))
                 return -EAGAIN;
 
         list_for_each_entry(map, &priv->maps, next) {
-                if (in_range(map, start, end)) {
-                        ret = -EAGAIN;
+                ret = unmap_if_in_range(map, start, end, blockable);
+                if (ret)
                         goto out_unlock;
-                }
-                unmap_if_in_range(map, start, end);
         }
         list_for_each_entry(map, &priv->freeable_maps, next) {
-                if (in_range(map, start, end)) {
-                        ret = -EAGAIN;
+                ret = unmap_if_in_range(map, start, end, blockable);
+                if (ret)
                         goto out_unlock;
-                }
-                unmap_if_in_range(map, start, end);
         }
 
 out_unlock:
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index c93d8ef8df34..5bb01a62f214 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -280,9 +280,11 @@ static void sysrq_handler(struct xenbus_watch *watch, const char *path,
                 /*
                  * The Xenstore watch fires directly after registering it and
                  * after a suspend/resume cycle. So ENOENT is no error but
-                 * might happen in those cases.
+                 * might happen in those cases. ERANGE is observed when we get
+                 * an empty value (''), this happens when we acknowledge the
+                 * request by writing '\0' below.
                  */
-                if (err != -ENOENT)
+                if (err != -ENOENT && err != -ERANGE)
                         pr_err("Error %d reading sysrq code in control/sysrq\n",
                                err);
                 xenbus_transaction_end(xbt, 1);
diff --git a/drivers/xen/mem-reservation.c b/drivers/xen/mem-reservation.c
index 084799c6180e..3782cf070338 100644
--- a/drivers/xen/mem-reservation.c
+++ b/drivers/xen/mem-reservation.c
@@ -14,6 +14,10 @@
 
 #include <xen/interface/memory.h>
 #include <xen/mem-reservation.h>
+#include <linux/moduleparam.h>
+
+bool __read_mostly xen_scrub_pages = IS_ENABLED(CONFIG_XEN_SCRUB_PAGES_DEFAULT);
+core_param(xen_scrub_pages, xen_scrub_pages, bool, 0);
 
 /*
  * Use one extent per PAGE_SIZE to avoid to break down the page into
diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c
index 294f35ce9e46..63c1494a8d73 100644
--- a/drivers/xen/xen-balloon.c
+++ b/drivers/xen/xen-balloon.c
@@ -44,6 +44,7 @@
 #include <xen/xenbus.h>
 #include <xen/features.h>
 #include <xen/page.h>
+#include <xen/mem-reservation.h>
 
 #define PAGES2KB(_p) ((_p)<<(PAGE_SHIFT-10))
 
@@ -137,6 +138,7 @@ static DEVICE_ULONG_ATTR(schedule_delay, 0444, balloon_stats.schedule_delay);
 static DEVICE_ULONG_ATTR(max_schedule_delay, 0644, balloon_stats.max_schedule_delay);
 static DEVICE_ULONG_ATTR(retry_count, 0444, balloon_stats.retry_count);
 static DEVICE_ULONG_ATTR(max_retry_count, 0644, balloon_stats.max_retry_count);
+static DEVICE_BOOL_ATTR(scrub_pages, 0644, xen_scrub_pages);
 
 static ssize_t show_target_kb(struct device *dev, struct device_attribute *attr,
                               char *buf)
@@ -203,6 +205,7 @@ static struct attribute *balloon_attrs[] = {
         &dev_attr_max_schedule_delay.attr.attr,
         &dev_attr_retry_count.attr.attr,
         &dev_attr_max_retry_count.attr.attr,
+        &dev_attr_scrub_pages.attr.attr,
         NULL
 };
 
diff --git a/include/xen/mem-reservation.h b/include/xen/mem-reservation.h
index 80b52b4945e9..a2ab516fcd2c 100644
--- a/include/xen/mem-reservation.h
+++ b/include/xen/mem-reservation.h
@@ -17,11 +17,12 @@
 
 #include <xen/page.h>
 
+extern bool xen_scrub_pages;
+
 static inline void xenmem_reservation_scrub_page(struct page *page)
 {
-#ifdef CONFIG_XEN_SCRUB_PAGES
-        clear_highpage(page);
-#endif
+        if (xen_scrub_pages)
+                clear_highpage(page);
 }
 
 #ifdef CONFIG_XEN_HAVE_PVMMU