This patch implemented parts of TODO left in commit id
a902c12ee45fc9389eb8fe54eeddaf267a555c58. 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 memflag to indicate
whether TLB-flush should be done in alloc_heap_pages or its caller
populate_physmap. Once this bit is set in memflag, alloc_heap_pages will
ignore TLB-flush.
Signed-off-by: Dongli Zhang
---
xen/common/memory.c | 26 ++
xen/common/page_alloc.c | 3 ++-
xen/include/xen/mm.h| 2 ++
3 files changed, 30 insertions(+), 1 deletion(-)
diff --git a/xen/common/memory.c b/xen/common/memory.c
index f34dd56..14ec5fa 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_t need_tlbflush = 0;
+ uint32_t tlbflush_timestamp = 0;
if ( !guest_handle_subrange_okay(a->extent_list, a->nr_done,
a->nr_extents-1) )
@@ -149,6 +151,8 @@ static void populate_physmap(struct memop_args *a)
if ( a->extent_order > (a->memflags & MEMF_populate_on_demand ? MAX_ORDER :
max_order(curr_d)) )
return;
+
+ a->memflags |= MEMF_no_tlbflush;
for ( i = a->nr_done; i < a->nr_extents; i++ )
{
@@ -213,6 +217,18 @@ static void populate_physmap(struct memop_args *a)
i, a->nr_extents);
goto out;
}
+
+ for ( j = 0; j < (1U << a->extent_order); j++ )
+ {
+ if ( page[j].u.free.need_tlbflush &&
+(page[j].tlbflush_timestamp <=
tlbflush_current_time()) &&
+(!need_tlbflush ||
+ (page[j].tlbflush_timestamp >
tlbflush_timestamp)) )
+ {
+ need_tlbflush = 1;
+ tlbflush_timestamp =
page[j].tlbflush_timestamp;
+ }
+ }
mfn = page_to_mfn(page);
}
@@ -232,6 +248,16 @@ static void populate_physmap(struct memop_args *a)
}
out:
+ if ( need_tlbflush )
+ {
+ cpumask_t mask = cpu_online_map;
+ tlbflush_filter(mask, tlbflush_timestamp);
+ if ( !cpumask_empty() )
+ {
+ perfc_incr(need_flush_tlb_flush);
+ flush_tlb_mask();
+ }
+ }
a->nr_done = i;
}
diff --git a/xen/common/page_alloc.c b/xen/common/page_alloc.c
index 18ff6cf..79f633b 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 ( pg[i].u.free.need_tlbflush &&
+if ( !(memflags & MEMF_no_tlbflush) &&
+pg[i].u.free.need_tlbflush &&
(pg[i].tlbflush_timestamp <= tlbflush_current_time()) &&
(!need_tlbflush ||
(pg[i].tlbflush_timestamp > tlbflush_timestamp)) )
diff --git a/xen/include/xen/mm.h b/xen/include/xen/mm.h
index 58bc0b8..880ca88 100644
--- a/xen/include/xen/mm.h
+++ b/xen/include/xen/mm.h
@@ -221,6 +221,8 @@ struct npfec {
#define MEMF_exact_node (1U<<_MEMF_exact_node)
#define _MEMF_no_owner5
#define MEMF_no_owner(1U<<_MEMF_no_owner)
+#define _MEMF_no_tlbflush 6
+#define MEMF_no_tlbflush (1U<<_MEMF_no_tlbflush)
#define _MEMF_node8
#define MEMF_node_mask ((1U << (8 * sizeof(nodeid_t))) - 1)
#define MEMF_node(n) n) + 1) & MEMF_node_mask) << _MEMF_node)
--
1.9.1
___
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel