powerpc/powernv/ioda2: Create bigger default window with 64k IOMMU pages

At the moment we create a small window only for 32bit devices, the window
maps 0..2GB of the PCI space only. For other devices we either use
a sketchy bypass or hardware bypass but the former can only work if
the amount of RAM is no bigger than the device's DMA mask and the latter
requires devices to support at least 59bit DMA.

This extends the default DMA window to the maximum size possible to allow
a wider DMA mask than just 32bit. The default window size is now limited
by the the iommu_table::it_map allocation bitmap which is a contiguous
array, 1 bit per an IOMMU page.

This increases the default IOMMU page size from hard coded 4K to
the system page size to allow wider DMA masks.

This increases the level number to not exceed the max order allocation
limit per TCE level. By the same time, this keeps minimal levels number
as 2 in order to save memory.

As the extended window now overlaps the 32bit MMIO region, this adds
an area reservation to iommu_init_table().

After this change the default window size is 0x80000000000==1<<43 so
devices limited to DMA mask smaller than the amount of system RAM can
still use more than just 2GB of memory for DMA.

This is an optimization and not a bug fix for DMA API usage.

With the on-demand allocation of indirect TCE table levels enabled and
2 levels, the first TCE level size is just
1<<ceil((log2(0x7ffffffffff+1)-16)/2)=16384 TCEs or 2 system pages.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190718051139.74787-5-aik@ozlabs.ru

1 files changed, 52 insertions, 22 deletions

diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 0a67ce9f827e..e7a2b160d4c6 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))
@@ -1024,15 +1056,14 @@ int iommu_take_ownership(struct iommu_table *tbl)
 	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 +1086,8 @@ 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);