xen/arm: p2m: Clean cache PT when the IOMMU doesn't support coherent walk

Some IOMMU don't suppport coherent PT walk. When the p2m is shared with
the CPU, Xen has to make sure the PT changes have reached the memory.

Introduce new IOMMU function that will check if the IOMMU feature is enabled
for a specified domain.

On ARM, the platform can contain multiple IOMMUs. Each of them may not
have the same set of feature. The domain parameter will be used to get the
set of features for IOMMUs used by this domain.
Signed-off-by: Julien Grall <julien.grall@linaro.org>
Acked-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>

xen/arch/arm/mm.c

@@ -1235,6 +1235,16 @@ int is_iomem_page(unsigned long mfn)
         return 1;
     return 0;
 }
+
+void clear_and_clean_page(struct page_info *page)
+{
+    void *p = __map_domain_page(page);
+
+    clear_page(p);
+    clean_xen_dcache_va_range(p, PAGE_SIZE);
+    unmap_domain_page(p);
+}
+
 /*
  * Local variables:
  * mode: C

xen/arch/arm/p2m.c

@@ -253,9 +253,15 @@ static lpae_t mfn_to_p2m_entry(unsigned long mfn, unsigned int mattr,
     return e;
 }
 
+static inline void p2m_write_pte(lpae_t *p, lpae_t pte, bool_t flush_cache)
+{
+    write_pte(p, pte);
+    if ( flush_cache )
+        clean_xen_dcache(*p);
+}
+
 /* Allocate a new page table page and hook it in via the given entry */
-static int p2m_create_table(struct domain *d,
-                            lpae_t *entry)
+static int p2m_create_table(struct domain *d, lpae_t *entry, bool_t flush_cache)
 {
     struct p2m_domain *p2m = &d->arch.p2m;
     struct page_info *page;
@@ -272,11 +278,13 @@ static int p2m_create_table(struct domain *d,
 
     p = __map_domain_page(page);
     clear_page(p);
+    if ( flush_cache )
+        clean_xen_dcache_va_range(p, PAGE_SIZE);
     unmap_domain_page(p);
 
     pte = mfn_to_p2m_entry(page_to_mfn(page), MATTR_MEM, p2m_invalid);
 
-    write_pte(entry, pte);
+    p2m_write_pte(entry, pte, flush_cache);
 
     return 0;
 }
@@ -308,6 +316,13 @@ static int apply_p2m_changes(struct domain *d,
     unsigned int flush = 0;
     bool_t populate = (op == INSERT || op == ALLOCATE);
     lpae_t pte;
+    bool_t flush_pt;
+
+    /* Some IOMMU don't support coherent PT walk. When the p2m is
+     * shared with the CPU, Xen has to make sure that the PT changes have
+     * reached the memory
+     */
+    flush_pt = iommu_enabled && !iommu_has_feature(d, IOMMU_FEAT_COHERENT_WALK);
 
     spin_lock(&p2m->lock);
 
@@ -334,7 +349,8 @@ static int apply_p2m_changes(struct domain *d,
                 continue;
             }
 
-            rc = p2m_create_table(d, &first[first_table_offset(addr)]);
+            rc = p2m_create_table(d, &first[first_table_offset(addr)],
+                                  flush_pt);
             if ( rc < 0 )
             {
                 printk("p2m_populate_ram: L1 failed\n");
@@ -360,7 +376,8 @@ static int apply_p2m_changes(struct domain *d,
                 continue;
             }
 
-            rc = p2m_create_table(d, &second[second_table_offset(addr)]);
+            rc = p2m_create_table(d, &second[second_table_offset(addr)],
+                                  flush_pt);
             if ( rc < 0 ) {
                 printk("p2m_populate_ram: L2 failed\n");
                 goto out;
@@ -411,13 +428,15 @@ static int apply_p2m_changes(struct domain *d,
 
                     pte = mfn_to_p2m_entry(page_to_mfn(page), mattr, t);
 
-                    write_pte(&third[third_table_offset(addr)], pte);
+                    p2m_write_pte(&third[third_table_offset(addr)],
+                                  pte, flush_pt);
                 }
                 break;
             case INSERT:
                 {
                     pte = mfn_to_p2m_entry(maddr >> PAGE_SHIFT, mattr, t);
-                    write_pte(&third[third_table_offset(addr)], pte);
+                    p2m_write_pte(&third[third_table_offset(addr)],
+                                  pte, flush_pt);
                     maddr += PAGE_SIZE;
                 }
                 break;
@@ -433,7 +452,8 @@ static int apply_p2m_changes(struct domain *d,
                     count += 0x10;
 
                     memset(&pte, 0x00, sizeof(pte));
-                    write_pte(&third[third_table_offset(addr)], pte);
+                    p2m_write_pte(&third[third_table_offset(addr)],
+                                  pte, flush_pt);
                     count++;
                 }
                 break;
@@ -537,7 +557,6 @@ int p2m_alloc_table(struct domain *d)
 {
     struct p2m_domain *p2m = &d->arch.p2m;
     struct page_info *page;
-    void *p;
 
     page = alloc_domheap_pages(NULL, P2M_FIRST_ORDER, 0);
     if ( page == NULL )
@@ -546,13 +565,8 @@ int p2m_alloc_table(struct domain *d)
     spin_lock(&p2m->lock);
 
     /* Clear both first level pages */
-    p = __map_domain_page(page);
-    clear_page(p);
-    unmap_domain_page(p);
-
-    p = __map_domain_page(page + 1);
-    clear_page(p);
-    unmap_domain_page(p);
+    clear_and_clean_page(page);
+    clear_and_clean_page(page + 1);
 
     p2m->first_level = page;
 

xen/drivers/passthrough/iommu.c

@@ -344,6 +344,16 @@ void iommu_crash_shutdown(void)
     iommu_enabled = iommu_intremap = 0;
 }
 
+bool_t iommu_has_feature(struct domain *d, enum iommu_feature feature)
+{
+    const struct hvm_iommu *hd = domain_hvm_iommu(d);
+
+    if ( !iommu_enabled )
+        return 0;
+
+    return test_bit(feature, hd->features);
+}
+
 static void iommu_dump_p2m_table(unsigned char key)
 {
     struct domain *d;

xen/include/asm-arm/mm.h

@@ -5,6 +5,7 @@
 #include <xen/kernel.h>
 #include <asm/page.h>
 #include <public/xen.h>
+#include <xen/domain_page.h>
 
 /* Align Xen to a 2 MiB boundary. */
 #define XEN_PADDR_ALIGN (1 << 21)
@@ -341,6 +342,8 @@ static inline void put_page_and_type(struct page_info *page)
     put_page(page);
 }
 
+void clear_and_clean_page(struct page_info *page);
+
 #endif /*  __ARCH_ARM_MM__ */
 /*
  * Local variables:

xen/include/xen/hvm/iommu.h

@@ -34,6 +34,12 @@ struct hvm_iommu {
     /* List of DT devices assigned to this domain */
     struct list_head dt_devices;
 #endif
+
+    /* Features supported by the IOMMU */
+    DECLARE_BITMAP(features, IOMMU_FEAT_count);
 };
 
+#define iommu_set_feature(d, f)   set_bit((f), domain_hvm_iommu(d)->features)
+#define iommu_clear_feature(d, f) clear_bit((f), domain_hvm_iommu(d)->features)
+
 #endif /* __XEN_HVM_IOMMU_H__ */

xen/include/xen/iommu.h

@@ -67,6 +67,15 @@ int iommu_map_page(struct domain *d, unsigned long gfn, unsigned long mfn,
                    unsigned int flags);
 int iommu_unmap_page(struct domain *d, unsigned long gfn);
 
+enum iommu_feature
+{
+    IOMMU_FEAT_COHERENT_WALK,
+    IOMMU_FEAT_count
+};
+
+bool_t iommu_has_feature(struct domain *d, enum iommu_feature feature);
+
+
 #ifdef HAS_PCI
 void pt_pci_init(void);