[PATCH v2 08/18] IOMMU/x86: support freeing of pagetables

[Jan Beulich <jbeulich@xxxxxxxx>]

For vendor specific code to support superpages we need to be able to
deal with a superpage mapping replacing an intermediate page table (or
hierarchy thereof). Consequently an iommu_alloc_pgtable() counterpart is
needed to free individual page tables while a domain is still alive.
Since the freeing needs to be deferred until after a suitable IOTLB
flush was performed, released page tables get queued for processing by a
tasklet.

Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
---
I was considering whether to use a softirq-taklet instead. This would
have the benefit of avoiding extra scheduling operations, but come with
the risk of the freeing happening prematurely because of a
process_pending_softirqs() somewhere.

--- a/xen/drivers/passthrough/x86/iommu.c
+++ b/xen/drivers/passthrough/x86/iommu.c
@@ -12,6 +12,7 @@
  * this program; If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <xen/cpu.h>
 #include <xen/sched.h>
 #include <xen/iommu.h>
 #include <xen/paging.h>
@@ -463,6 +464,85 @@ struct page_info *iommu_alloc_pgtable(st
     return pg;
 }
 
+/*
+ * Intermediate page tables which get replaced by large pages may only be
+ * freed after a suitable IOTLB flush. Hence such pages get queued on a
+ * per-CPU list, with a per-CPU tasklet processing the list on the assumption
+ * that the necessary IOTLB flush will have occurred by the time tasklets get
+ * to run. (List and tasklet being per-CPU has the benefit of accesses not
+ * requiring any locking.)
+ */
+static DEFINE_PER_CPU(struct page_list_head, free_pgt_list);
+static DEFINE_PER_CPU(struct tasklet, free_pgt_tasklet);
+
+static void free_queued_pgtables(void *arg)
+{
+    struct page_list_head *list = arg;
+    struct page_info *pg;
+
+    while ( (pg = page_list_remove_head(list)) )
+        free_domheap_page(pg);
+}
+
+void iommu_queue_free_pgtable(struct domain *d, struct page_info *pg)
+{
+    struct domain_iommu *hd = dom_iommu(d);
+    unsigned int cpu = smp_processor_id();
+
+    spin_lock(&hd->arch.pgtables.lock);
+    page_list_del(pg, &hd->arch.pgtables.list);
+    spin_unlock(&hd->arch.pgtables.lock);
+
+    page_list_add_tail(pg, &per_cpu(free_pgt_list, cpu));
+
+    tasklet_schedule(&per_cpu(free_pgt_tasklet, cpu));
+}
+
+static int cpu_callback(
+    struct notifier_block *nfb, unsigned long action, void *hcpu)
+{
+    unsigned int cpu = (unsigned long)hcpu;
+    struct page_list_head *list = &per_cpu(free_pgt_list, cpu);
+    struct tasklet *tasklet = &per_cpu(free_pgt_tasklet, cpu);
+
+    switch ( action )
+    {
+    case CPU_DOWN_PREPARE:
+        tasklet_kill(tasklet);
+        break;
+
+    case CPU_DEAD:
+        page_list_splice(list, &this_cpu(free_pgt_list));
+        INIT_PAGE_LIST_HEAD(list);
+        tasklet_schedule(&this_cpu(free_pgt_tasklet));
+        break;
+
+    case CPU_UP_PREPARE:
+    case CPU_DOWN_FAILED:
+        tasklet_init(tasklet, free_queued_pgtables, list);
+        break;
+    }
+
+    return NOTIFY_DONE;
+}
+
+static struct notifier_block cpu_nfb = {
+    .notifier_call = cpu_callback,
+};
+
+static int __init bsp_init(void)
+{
+    if ( iommu_enabled )
+    {
+        cpu_callback(&cpu_nfb, CPU_UP_PREPARE,
+                     (void *)(unsigned long)smp_processor_id());
+        register_cpu_notifier(&cpu_nfb);
+    }
+
+    return 0;
+}
+presmp_initcall(bsp_init);
+
 bool arch_iommu_use_permitted(const struct domain *d)
 {
     /*
--- a/xen/include/asm-x86/iommu.h
+++ b/xen/include/asm-x86/iommu.h
@@ -143,6 +143,7 @@ int pi_update_irte(const struct pi_desc
 
 int __must_check iommu_free_pgtables(struct domain *d);
 struct page_info *__must_check iommu_alloc_pgtable(struct domain *d);
+void iommu_queue_free_pgtable(struct domain *d, struct page_info *pg);
 
 #endif /* !__ARCH_X86_IOMMU_H__ */
 /*