@@ -263,14 +263,21 @@ declare_mm_lock(altp2mlist)
*/
declare_mm_rwlock(altp2m);
-#define p2m_lock(p) \
-{ \
- if ( p2m_is_altp2m(p) ) \
- mm_write_lock(altp2m, &(p)->lock); \
- else \
- mm_write_lock(p2m, &(p)->lock); \
-}
-#define p2m_unlock(p) mm_write_unlock(&(p)->lock);
+#define p2m_lock(p) \
+ do { \
+ if ( p2m_is_altp2m(p) ) \
+ mm_write_lock(altp2m, &(p)->lock); \
+ else \
+ mm_write_lock(p2m, &(p)->lock); \
+ (p)->defer_flush++; \
+ } while (0)
+#define p2m_unlock(p) \
+ do { \
+ if ( --(p)->defer_flush == 0 ) \
+ p2m_tlb_flush_and_unlock(p); \
+ else \
+ mm_write_unlock(&(p)->lock); \
+ } while (0)
#define gfn_lock(p,g,o) p2m_lock(p)
#define gfn_unlock(p,g,o) p2m_unlock(p)
#define p2m_read_lock(p) mm_read_lock(p2m, &(p)->lock)
@@ -843,7 +843,10 @@ out:
from the iommu tables, so as to avoid a potential
use-after-free. */
if ( is_epte_present(&old_entry) )
+ {
+ p2m_tlb_flush_sync(p2m);
ept_free_entry(p2m, &old_entry, target);
+ }
if ( rc == 0 && p2m_is_hostp2m(p2m) )
p2m_altp2m_propagate_change(d, _gfn(gfn), mfn, order, p2mt, p2ma);
@@ -1095,24 +1098,48 @@ static void __ept_sync_domain(void *info)
*/
}
-void ept_sync_domain(struct p2m_domain *p2m)
+static void ept_sync_domain_prepare(struct p2m_domain *p2m)
{
struct domain *d = p2m->domain;
struct ept_data *ept = &p2m->ept;
- /* Only if using EPT and this domain has some VCPUs to dirty. */
- if ( !paging_mode_hap(d) || !d->vcpu || !d->vcpu[0] )
- return;
-
- ASSERT(local_irq_is_enabled());
if ( nestedhvm_enabled(d) && !p2m_is_nestedp2m(p2m) )
p2m_flush_nestedp2m(d);
/* May need to invalidate on all PCPUs. */
cpumask_setall(ept->invalidate);
+}
+
+static void ept_sync_domain_mask(struct p2m_domain *p2m, const cpumask_t *mask)
+{
+ on_selected_cpus(mask, __ept_sync_domain, p2m, 1);
+}
- on_selected_cpus(d->domain_dirty_cpumask,
- __ept_sync_domain, p2m, 1);
+void ept_sync_domain(struct p2m_domain *p2m)
+{
+ struct domain *d = p2m->domain;
+
+ /* Only if using EPT and this domain has some VCPUs to dirty. */
+ if ( !paging_mode_hap(d) || !d->vcpu || !d->vcpu[0] )
+ return;
+
+ ept_sync_domain_prepare(p2m);
+
+ if ( p2m->defer_flush )
+ {
+ p2m->need_flush = 1;
+ return;
+ }
+
+ ept_sync_domain_mask(p2m, d->domain_dirty_cpumask);
+}
+
+static void ept_flush_and_unlock(struct p2m_domain *p2m, bool_t unlock)
+{
+ p2m->need_flush = 0;
+ if ( unlock )
+ mm_write_unlock(&p2m->lock);
+ ept_sync_domain_mask(p2m, p2m->domain->domain_dirty_cpumask);
}
static void ept_enable_pml(struct p2m_domain *p2m)
@@ -1163,6 +1190,7 @@ int ept_p2m_init(struct p2m_domain *p2m)
p2m->change_entry_type_range = ept_change_entry_type_range;
p2m->memory_type_changed = ept_memory_type_changed;
p2m->audit_p2m = NULL;
+ p2m->flush_and_unlock = ept_flush_and_unlock;
/* Set the memory type used when accessing EPT paging structures. */
ept->ept_mt = EPT_DEFAULT_MT;
@@ -886,6 +886,8 @@ p2m_pod_zero_check(struct p2m_domain *p2m, unsigned long *gfns, int count)
}
}
+ p2m_tlb_flush_sync(p2m);
+
/* Now check each page for real */
for ( i=0; i < count; i++ )
{
@@ -324,6 +324,20 @@ void p2m_flush_hardware_cached_dirty(struct domain *d)
}
}
+void p2m_tlb_flush_sync(struct p2m_domain *p2m)
+{
+ if ( p2m->need_flush )
+ p2m->flush_and_unlock(p2m, 0);
+}
+
+void p2m_tlb_flush_and_unlock(struct p2m_domain *p2m)
+{
+ if ( p2m->need_flush )
+ p2m->flush_and_unlock(p2m, 1);
+ else
+ mm_write_unlock(&p2m->lock);
+}
+
mfn_t __get_gfn_type_access(struct p2m_domain *p2m, unsigned long gfn,
p2m_type_t *t, p2m_access_t *a, p2m_query_t q,
unsigned int *page_order, bool_t locked)
@@ -261,6 +261,10 @@ struct p2m_domain {
unsigned long gfn, l1_pgentry_t *p,
l1_pgentry_t new, unsigned int level);
long (*audit_p2m)(struct p2m_domain *p2m);
+ void (*flush_and_unlock)(struct p2m_domain *p2m, bool_t unlock);
+
+ unsigned int defer_flush;
+ bool_t need_flush;
/* Default P2M access type for each page in the the domain: new pages,
* swapped in pages, cleared pages, and pages that are ambiguously
@@ -353,6 +357,12 @@ static inline bool_t p2m_is_altp2m(const struct p2m_domain *p2m)
#define p2m_get_pagetable(p2m) ((p2m)->phys_table)
+/*
+ * Ensure any deferred p2m TLB flush has been completed on all VCPUs.
+ */
+void p2m_tlb_flush_sync(struct p2m_domain *p2m);
+void p2m_tlb_flush_and_unlock(struct p2m_domain *p2m);
+
/**** p2m query accessors. They lock p2m_lock, and thus serialize
* lookups wrt modifications. They _do not_ release the lock on exit.
* After calling any of the variants below, caller needs to use
Holding the p2m lock while calling ept_sync_domain() is very expensive since it does a on_selected_cpus() call. IPIs on many socket machines can be very slows and on_selected_cpus() is serialized. It is safe to defer the invalidate until the p2m lock is released except for two cases: 1. When freeing a page table page (since partial translations may be cached). 2. When reclaiming a zero page as part of PoD. For these cases, add p2m_tlb_flush_sync() calls which will immediately perform the invalidate before the page is freed or reclaimed. Signed-off-by: David Vrabel <david.vrabel@citrix.com> --- v5: - add p2m_tlb_flush_sync() and call it before freeing pgae table pages and reclaiming zeroed pod pages. v2: - use per-p2m list for deferred pages. - update synced_mask while holding write lock. --- xen/arch/x86/mm/mm-locks.h | 23 +++++++++++++++-------- xen/arch/x86/mm/p2m-ept.c | 44 ++++++++++++++++++++++++++++++++++++-------- xen/arch/x86/mm/p2m-pod.c | 2 ++ xen/arch/x86/mm/p2m.c | 14 ++++++++++++++ xen/include/asm-x86/p2m.h | 10 ++++++++++ 5 files changed, 77 insertions(+), 16 deletions(-)