log-dirty: refine common code to support PML

Using PML, it's possible there are dirty GPAs logged in vcpus' PML buffers
when userspace peek/clear dirty pages, therefore we need to flush them befor
reporting dirty pages to userspace. This applies to both video ram tracking and
paging_log_dirty_op.

This patch adds new p2m layer functions to enable/disable PML and flush PML
buffers. The new functions are named to be generic to cover potential futher
PML-like features for other platforms.

Signed-off-by: Kai Huang <kai.huang@linux.intel.com>
Acked-by: Tim Deegan <tim@xen.org>

xen/arch/x86/mm/hap/hap.c

@@ -121,7 +121,10 @@ int hap_track_dirty_vram(struct domain *d,
                 p2m_change_type_range(d, ostart, oend,
                                       p2m_ram_logdirty, p2m_ram_rw);
 
-            /* set l1e entries of range within P2M table to be read-only. */
+            /*
+             * Switch vram to log dirty mode, either by setting l1e entries of
+             * P2M table to be read-only, or via hardware-assisted log-dirty.
+             */
             p2m_change_type_range(d, begin_pfn, begin_pfn + nr,
                                   p2m_ram_rw, p2m_ram_logdirty);
 
@@ -135,6 +138,9 @@ int hap_track_dirty_vram(struct domain *d,
 
             domain_pause(d);
 
+            /* Flush dirty GFNs potentially cached by hardware. */
+            p2m_flush_hardware_cached_dirty(d);
+
             /* get the bitmap */
             paging_log_dirty_range(d, begin_pfn, nr, dirty_bitmap);
 
@@ -190,9 +196,15 @@ static int hap_enable_log_dirty(struct domain *d, bool_t log_global)
     d->arch.paging.mode |= PG_log_dirty;
     paging_unlock(d);
 
+    /* Enable hardware-assisted log-dirty if it is supported. */
+    p2m_enable_hardware_log_dirty(d);
+
     if ( log_global )
     {
-        /* set l1e entries of P2M table to be read-only. */
+        /*
+         * Switch to log dirty mode, either by setting l1e entries of P2M table
+         * to be read-only, or via hardware-assisted log-dirty.
+         */
         p2m_change_entry_type_global(d, p2m_ram_rw, p2m_ram_logdirty);
         flush_tlb_mask(d->domain_dirty_cpumask);
     }
@@ -205,14 +217,23 @@ static int hap_disable_log_dirty(struct domain *d)
     d->arch.paging.mode &= ~PG_log_dirty;
     paging_unlock(d);
 
-    /* set l1e entries of P2M table with normal mode */
+    /* Disable hardware-assisted log-dirty if it is supported. */
+    p2m_disable_hardware_log_dirty(d);
+
+    /*
+     * switch to normal mode, either by setting l1e entries of P2M table to
+     * normal mode, or via hardware-assisted log-dirty.
+     */
     p2m_change_entry_type_global(d, p2m_ram_logdirty, p2m_ram_rw);
     return 0;
 }
 
 static void hap_clean_dirty_bitmap(struct domain *d)
 {
-    /* set l1e entries of P2M table to be read-only. */
+    /*
+     * Switch to log-dirty mode, either by setting l1e entries of P2M table to
+     * be read-only, or via hardware-assisted log-dirty.
+     */
     p2m_change_entry_type_global(d, p2m_ram_rw, p2m_ram_logdirty);
     flush_tlb_mask(d->domain_dirty_cpumask);
 }

xen/arch/x86/mm/p2m.c

@@ -239,6 +239,42 @@ void p2m_memory_type_changed(struct domain *d)
     }
 }
 
+void p2m_enable_hardware_log_dirty(struct domain *d)
+{
+    struct p2m_domain *p2m = p2m_get_hostp2m(d);
+
+    if ( p2m->enable_hardware_log_dirty )
+    {
+        p2m_lock(p2m);
+        p2m->enable_hardware_log_dirty(p2m);
+        p2m_unlock(p2m);
+    }
+}
+
+void p2m_disable_hardware_log_dirty(struct domain *d)
+{
+    struct p2m_domain *p2m = p2m_get_hostp2m(d);
+
+    if ( p2m->disable_hardware_log_dirty )
+    {
+        p2m_lock(p2m);
+        p2m->disable_hardware_log_dirty(p2m);
+        p2m_unlock(p2m);
+    }
+}
+
+void p2m_flush_hardware_cached_dirty(struct domain *d)
+{
+    struct p2m_domain *p2m = p2m_get_hostp2m(d);
+
+    if ( p2m->flush_hardware_cached_dirty )
+    {
+        p2m_lock(p2m);
+        p2m->flush_hardware_cached_dirty(p2m);
+        p2m_unlock(p2m);
+    }
+}
+
 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)

xen/arch/x86/mm/paging.c

@@ -422,7 +422,17 @@ static int paging_log_dirty_op(struct domain *d,
     int i4, i3, i2;
 
     if ( !resuming )
+    {
         domain_pause(d);
+
+        /*
+         * Flush dirty GFNs potentially cached by hardware. Only need to flush
+         * when not resuming, as domain was paused in resuming case therefore
+         * it's not possible to have any new dirty pages.
+         */
+        p2m_flush_hardware_cached_dirty(d);
+    }
+
     paging_lock(d);
 
     if ( !d->arch.paging.preempt.dom )

xen/include/asm-x86/p2m.h

@@ -233,6 +233,9 @@ struct p2m_domain {
                                        p2m_access_t *p2ma,
                                        p2m_query_t q,
                                        unsigned int *page_order);
+    void               (*enable_hardware_log_dirty)(struct p2m_domain *p2m);
+    void               (*disable_hardware_log_dirty)(struct p2m_domain *p2m);
+    void               (*flush_hardware_cached_dirty)(struct p2m_domain *p2m);
     void               (*change_entry_type_global)(struct p2m_domain *p2m,
                                                    p2m_type_t ot,
                                                    p2m_type_t nt);
@@ -507,6 +510,14 @@ void guest_physmap_remove_page(struct domain *d,
 /* Set a p2m range as populate-on-demand */
 int guest_physmap_mark_populate_on_demand(struct domain *d, unsigned long gfn,
                                           unsigned int order);
+/* Enable hardware-assisted log-dirty. */
+void p2m_enable_hardware_log_dirty(struct domain *d);
+
+/* Disable hardware-assisted log-dirty */
+void p2m_disable_hardware_log_dirty(struct domain *d);
+
+/* Flush hardware cached dirty GFNs */
+void p2m_flush_hardware_cached_dirty(struct domain *d);
 
 /* Change types across all p2m entries in a domain */
 void p2m_change_entry_type_global(struct domain *d,