[POWERPC] Use 4kB iommu pages even on 64kB-page systems

The 10Gigabit ethernet device drivers appear to be able to chew
up all 256MB of TCE mappings on pSeries systems, as evidenced by
numerous error messages:

 iommu_alloc failed, tbl c0000000010d5c48 vaddr c0000000d875eff0 npages 1

Some experimentation indicates that this is essentially because
one 1500 byte ethernet MTU gets mapped as a 64K DMA region when
the large 64K pages are enabled. Thus, it doesn't take much to
exhaust all of the available DMA mappings for a high-speed card.

This patch changes the iommu allocator to work with its own
unique, distinct page size. Although the patch is long, its
actually quite simple: it just #defines a distinct IOMMU_PAGE_SIZE
and then uses this in all the places that matter.

As a side effect, it also dramatically improves network performance
on platforms with H-calls on iommu translation inserts/removes (since
we no longer call it 16 times for a 1500 bytes packet when the iommu HW
is still 4k).

In the future, we might want to make the IOMMU_PAGE_SIZE a variable
in the iommu_table instance, thus allowing support for different HW
page sizes in the iommu itself.

Signed-off-by: Linas Vepstas <linas@austin.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Olof Johansson <olof@lixom.net>
Acked-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>

2 files changed, 22 insertions, 3 deletions

diff --git a/include/asm-powerpc/iommu.h b/include/asm-powerpc/iommu.h
index a5e98641a2ae..39fad685ffab 100644
--- a/include/asm-powerpc/iommu.h
+++ b/include/asm-powerpc/iommu.h
@@ -22,17 +22,35 @@
 #define _ASM_IOMMU_H
 #ifdef __KERNEL__
 
-#include <asm/types.h>
+#include <linux/compiler.h>
 #include <linux/spinlock.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
+#include <asm/types.h>
+#include <asm/bitops.h>
+
+#define IOMMU_PAGE_SHIFT      12
+#define IOMMU_PAGE_SIZE       (ASM_CONST(1) << IOMMU_PAGE_SHIFT)
+#define IOMMU_PAGE_MASK       (~((1 << IOMMU_PAGE_SHIFT) - 1))
+#define IOMMU_PAGE_ALIGN(addr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE)
+
+#ifndef __ASSEMBLY__
+
+/* Pure 2^n version of get_order */
+static __inline__ __attribute_const__ int get_iommu_order(unsigned long size)
+{
+        return __ilog2((size - 1) >> IOMMU_PAGE_SHIFT) + 1;
+}
+
+#endif   /* __ASSEMBLY__ */
+
 
 /*
  * IOMAP_MAX_ORDER defines the largest contiguous block
  * of dma space we can get.  IOMAP_MAX_ORDER = 13
  * allows up to 2**12 pages (4096 * 4096) = 16 MB
  */
-#define IOMAP_MAX_ORDER 13
+#define IOMAP_MAX_ORDER         13
 
 struct iommu_table {
         unsigned long  it_busno;     /* Bus number this table belongs to */
diff --git a/include/asm-powerpc/tce.h b/include/asm-powerpc/tce.h
index c9483adbf599..f663634cccc9 100644
--- a/include/asm-powerpc/tce.h
+++ b/include/asm-powerpc/tce.h
@@ -22,6 +22,8 @@
 #define _ASM_POWERPC_TCE_H
 #ifdef __KERNEL__
 
+#include <asm/iommu.h>
+
 /*
  * Tces come in two formats, one for the virtual bus and a different
  * format for PCI
@@ -33,7 +35,6 @@
 
 #define TCE_SHIFT       12
 #define TCE_PAGE_SIZE   (1 << TCE_SHIFT)
-#define TCE_PAGE_FACTOR (PAGE_SHIFT - TCE_SHIFT)
 
 #define TCE_ENTRY_SIZE          8               /* each TCE is 64 bits */