This patch implemented parts of TODO left in commit id
a902c12ee45fc9389eb8fe54eeddaf267a555c58 (More efficient TLB-flush
filtering in alloc_heap_pages()). It moved TLB-flush filtering out into
populate_physmap. Because of TLB-flush in alloc_heap_pages, it's very slow
to create a guest with memory size of more than 100GB on host with 100+
cpus.
This patch introduced a "MEMF_no_tlbflush" bit to memflags to indicate
whether TLB-flush should be done in alloc_heap_pages or its caller
populate_physmap. Once this bit is set in memflags, alloc_heap_pages will
ignore TLB-flush. To use this bit after vm is created might lead to
security issue, that is, this would make pages accessible to the guest B,
when guest A may still have a cached mapping to them.
Therefore, this patch also introduced a "creation_finished" field to struct
domain to indicate whether this domain has ever got unpaused by hypervisor.
MEMF_no_tlbflush can be set only during vm creation phase when
creation_finished is still false before this domain gets unpaused for the
first time.
Signed-off-by: Dongli Zhang
---
Changed since v4:
* Rename is_ever_unpaused to creation_finished.
* Change bool_t to bool.
* Polish comments.
Changed since v3:
* Set the flag to true in domain_unpause_by_systemcontroller when
unpausing the guest domain for the first time.
* Use true/false for all boot_t variables.
* Add unlikely to optimize "if statement".
* Correct comment style.
Changed since v2:
* Limit this optimization to domain creation time.
---
xen/common/domain.c | 8
xen/common/memory.c | 28
xen/common/page_alloc.c | 3 ++-
xen/include/xen/mm.h| 2 ++
xen/include/xen/sched.h | 6 ++
5 files changed, 46 insertions(+), 1 deletion(-)
diff --git a/xen/common/domain.c b/xen/common/domain.c
index a8804e4..c170c69 100644
--- a/xen/common/domain.c
+++ b/xen/common/domain.c
@@ -1004,6 +1004,14 @@ int domain_unpause_by_systemcontroller(struct domain *d)
{
int old, new, prev = d->controller_pause_count;
+/*
+ * We record this information here for populate_physmap to figure out
+ * that the domain has finished being created. In fact, we're only
+ * allowed to set the MEMF_no_tlbflush flag during VM creation.
+ */
+if ( unlikely(!d->creation_finished) )
+d->creation_finished = true;
+
do
{
old = prev;
diff --git a/xen/common/memory.c b/xen/common/memory.c
index cc0f69e..27d1f2a 100644
--- a/xen/common/memory.c
+++ b/xen/common/memory.c
@@ -141,6 +141,8 @@ static void populate_physmap(struct memop_args *a)
unsigned int i, j;
xen_pfn_t gpfn, mfn;
struct domain *d = a->domain, *curr_d = current->domain;
+bool need_tlbflush = false;
+uint32_t tlbflush_timestamp = 0;
if ( !guest_handle_subrange_okay(a->extent_list, a->nr_done,
a->nr_extents-1) )
@@ -150,6 +152,17 @@ static void populate_physmap(struct memop_args *a)
max_order(curr_d)) )
return;
+/*
+ * With MEMF_no_tlbflush set, alloc_heap_pages() will ignore
+ * TLB-flushes. After VM creation, this is a security issue (it can
+ * make pages accessible to guest B, when guest A may still have a
+ * cached mapping to them). So we only do this only during domain
+ * creation, when the domain itself has not yet been unpaused for the
+ * first time.
+ */
+if ( unlikely(!d->creation_finished) )
+a->memflags |= MEMF_no_tlbflush;
+
for ( i = a->nr_done; i < a->nr_extents; i++ )
{
if ( i != a->nr_done && hypercall_preempt_check() )
@@ -214,6 +227,19 @@ static void populate_physmap(struct memop_args *a)
goto out;
}
+if ( unlikely(a->memflags & MEMF_no_tlbflush) )
+{
+for ( j = 0; j < (1U << a->extent_order); j++ )
+{
+if ( accumulate_tlbflush(need_tlbflush, [j],
+ tlbflush_timestamp) )
+{
+need_tlbflush = true;
+tlbflush_timestamp = page[j].tlbflush_timestamp;
+}
+}
+}
+
mfn = page_to_mfn(page);
}
@@ -232,6 +258,8 @@ static void populate_physmap(struct memop_args *a)
}
out:
+if ( need_tlbflush )
+filtered_flush_tlb_mask(tlbflush_timestamp);
a->nr_done = i;
}
diff --git a/xen/common/page_alloc.c b/xen/common/page_alloc.c
index 173c10d..a67f49b 100644
--- a/xen/common/page_alloc.c
+++ b/xen/common/page_alloc.c
@@ -827,7 +827,8 @@ static struct page_info *alloc_heap_pages(
BUG_ON(pg[i].count_info != PGC_state_free);
pg[i].count_info = PGC_state_inuse;
-if ( accumulate_tlbflush(need_tlbflush, [i],
+