1 files changed, 65 insertions, 32 deletions

diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 0a67ce9f827e..9704f3f76e63 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -633,11 +633,54 @@ static void iommu_table_clear(struct iommu_table *tbl)
 #endif
 }
 
+static void iommu_table_reserve_pages(struct iommu_table *tbl,
+		unsigned long res_start, unsigned long res_end)
+{
+	int i;
+
+	WARN_ON_ONCE(res_end < res_start);
+	/*
+	 * Reserve page 0 so it will not be used for any mappings.
+	 * This avoids buggy drivers that consider page 0 to be invalid
+	 * to crash the machine or even lose data.
+	 */
+	if (tbl->it_offset == 0)
+		set_bit(0, tbl->it_map);
+
+	tbl->it_reserved_start = res_start;
+	tbl->it_reserved_end = res_end;
+
+	/* Check if res_start..res_end isn't empty and overlaps the table */
+	if (res_start && res_end &&
+			(tbl->it_offset + tbl->it_size < res_start ||
+			 res_end < tbl->it_offset))
+		return;
+
+	for (i = tbl->it_reserved_start; i < tbl->it_reserved_end; ++i)
+		set_bit(i - tbl->it_offset, tbl->it_map);
+}
+
+static void iommu_table_release_pages(struct iommu_table *tbl)
+{
+	int i;
+
+	/*
+	 * In case we have reserved the first bit, we should not emit
+	 * the warning below.
+	 */
+	if (tbl->it_offset == 0)
+		clear_bit(0, tbl->it_map);
+
+	for (i = tbl->it_reserved_start; i < tbl->it_reserved_end; ++i)
+		clear_bit(i - tbl->it_offset, tbl->it_map);
+}
+
 /*
  * Build a iommu_table structure.  This contains a bit map which
  * is used to manage allocation of the tce space.
  */
-struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
+struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid,
+		unsigned long res_start, unsigned long res_end)
 {
 	unsigned long sz;
 	static int welcomed = 0;
@@ -656,13 +699,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
 	tbl->it_map = page_address(page);
 	memset(tbl->it_map, 0, sz);
 
-	/*
-	 * Reserve page 0 so it will not be used for any mappings.
-	 * This avoids buggy drivers that consider page 0 to be invalid
-	 * to crash the machine or even lose data.
-	 */
-	if (tbl->it_offset == 0)
-		set_bit(0, tbl->it_map);
+	iommu_table_reserve_pages(tbl, res_start, res_end);
 
 	/* We only split the IOMMU table if we have 1GB or more of space */
 	if ((tbl->it_size << tbl->it_page_shift) >= (1UL * 1024 * 1024 * 1024))
@@ -714,12 +751,7 @@ static void iommu_table_free(struct kref *kref)
 		return;
 	}
 
-	/*
-	 * In case we have reserved the first bit, we should not emit
-	 * the warning below.
-	 */
-	if (tbl->it_offset == 0)
-		clear_bit(0, tbl->it_map);
+	iommu_table_release_pages(tbl);
 
 	/* verify that table contains no entries */
 	if (!bitmap_empty(tbl->it_map, tbl->it_size))
@@ -981,29 +1013,32 @@ int iommu_tce_check_gpa(unsigned long page_shift, unsigned long gpa)
 }
 EXPORT_SYMBOL_GPL(iommu_tce_check_gpa);
 
-long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl,
+extern long iommu_tce_xchg_no_kill(struct mm_struct *mm,
+		struct iommu_table *tbl,
 		unsigned long entry, unsigned long *hpa,
 		enum dma_data_direction *direction)
 {
 	long ret;
 	unsigned long size = 0;
 
-	ret = tbl->it_ops->exchange(tbl, entry, hpa, direction);
-
+	ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction, false);
 	if (!ret && ((*direction == DMA_FROM_DEVICE) ||
 			(*direction == DMA_BIDIRECTIONAL)) &&
 			!mm_iommu_is_devmem(mm, *hpa, tbl->it_page_shift,
 					&size))
 		SetPageDirty(pfn_to_page(*hpa >> PAGE_SHIFT));
 
-	/* if (unlikely(ret))
-		pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n",
-			__func__, hwaddr, entry << tbl->it_page_shift,
-				hwaddr, ret); */
-
 	return ret;
 }
-EXPORT_SYMBOL_GPL(iommu_tce_xchg);
+EXPORT_SYMBOL_GPL(iommu_tce_xchg_no_kill);
+
+void iommu_tce_kill(struct iommu_table *tbl,
+		unsigned long entry, unsigned long pages)
+{
+	if (tbl->it_ops->tce_kill)
+		tbl->it_ops->tce_kill(tbl, entry, pages, false);
+}
+EXPORT_SYMBOL_GPL(iommu_tce_kill);
 
 int iommu_take_ownership(struct iommu_table *tbl)
 {
@@ -1017,22 +1052,21 @@ int iommu_take_ownership(struct iommu_table *tbl)
 	 * requires exchange() callback defined so if it is not
 	 * implemented, we disallow taking ownership over the table.
 	 */
-	if (!tbl->it_ops->exchange)
+	if (!tbl->it_ops->xchg_no_kill)
 		return -EINVAL;
 
 	spin_lock_irqsave(&tbl->large_pool.lock, flags);
 	for (i = 0; i < tbl->nr_pools; i++)
 		spin_lock(&tbl->pools[i].lock);
 
-	if (tbl->it_offset == 0)
-		clear_bit(0, tbl->it_map);
+	iommu_table_release_pages(tbl);
 
 	if (!bitmap_empty(tbl->it_map, tbl->it_size)) {
 		pr_err("iommu_tce: it_map is not empty");
 		ret = -EBUSY;
-		/* Restore bit#0 set by iommu_init_table() */
-		if (tbl->it_offset == 0)
-			set_bit(0, tbl->it_map);
+		/* Undo iommu_table_release_pages, i.e. restore bit#0, etc */
+		iommu_table_reserve_pages(tbl, tbl->it_reserved_start,
+				tbl->it_reserved_end);
 	} else {
 		memset(tbl->it_map, 0xff, sz);
 	}
@@ -1055,9 +1089,8 @@ void iommu_release_ownership(struct iommu_table *tbl)
 
 	memset(tbl->it_map, 0, sz);
 
-	/* Restore bit#0 set by iommu_init_table() */
-	if (tbl->it_offset == 0)
-		set_bit(0, tbl->it_map);
+	iommu_table_reserve_pages(tbl, tbl->it_reserved_start,
+			tbl->it_reserved_end);
 
 	for (i = 0; i < tbl->nr_pools; i++)
 		spin_unlock(&tbl->pools[i].lock);