xen/balloon: add runtime control for scrubbing ballooned out pages

Scrubbing pages on initial balloon down can take some time, especially
in nested virtualization case (nested EPT is slow). When HVM/PVH guest is
started with memory= significantly lower than maxmem=, all the extra
pages will be scrubbed before returning to Xen. But since most of them
weren't used at all at that point, Xen needs to populate them first
(from populate-on-demand pool). In nested virt case (Xen inside KVM)
this slows down the guest boot by 15-30s with just 1.5GB needed to be
returned to Xen.

Add runtime parameter to enable/disable it, to allow initially disabling
scrubbing, then enable it back during boot (for example in initramfs).
Such usage relies on assumption that a) most pages ballooned out during
initial boot weren't used at all, and b) even if they were, very few
secrets are in the guest at that time (before any serious userspace
kicks in).
Convert CONFIG_XEN_SCRUB_PAGES to CONFIG_XEN_SCRUB_PAGES_DEFAULT (also
enabled by default), controlling default value for the new runtime
switch.

Signed-off-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>

diff --git a/Documentation/ABI/stable/sysfs-devices-system-xen_memory b/Documentation/ABI/stable/sysfs-devices-system-xen_memory
index caa311d59ac1d24c92643f37b396407a1ab654f0..6d83f95a8a8e131c9a2f0454cd39128ffd3d7723 100644 (file)
--- 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 64a3bf54b97492e3b2b25508a7785d1f1e9e4186..92eb1f42240d7168354dc7129898e2500ef95c1a 100644 (file)
--- 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 b459edfacff35e0526fdc912cd0179ef8126ea74..90d387b50ab747f505597e87b439f1dcfe5f489f 100644 (file)
--- 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/mem-reservation.c b/drivers/xen/mem-reservation.c
index 084799c6180e6e6cb281eb882637b42999a1e683..3782cf070338e3fa5f830184a784dd9e2d0c666a 100644 (file)
--- 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 294f35ce9e46bc063a7e01061462cf3e298b4364..63c1494a8d73bf2f53f0f0a1887290f338ae454a 100644 (file)
--- 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 80b52b4945e965d96ce068fe3d729e9364cc9868..a2ab516fcd2caf33167f3e64a76c2e77b726d6df 100644 (file)
--- 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