From: Scott Moser <smoser@redhat.com>
Subject: [RHEL5.1 PATCH] bz239569 [PPC] DMA 4GB boundary protection 
Date: Wed, 6 Jun 2007 14:36:37 -0400 (EDT)
Bugzilla: 239569
Message-Id: <Pine.LNX.4.64.0705291606070.5134@squad5-lp1.lab.boston.redhat.com>
Changelog: [PPC64] DMA 4GB boundary protection 


RHBZ#: 239569
------
https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=239569

Description:
------------
  [POWERPC] DMA 4GB boundary protection

  There are many adapters which cannot handle DMAing across any 4 GB
  boundary.  For instance, the latest Emulex adapters.

  This normally is not an issue as firmware gives dma-windows under
  4gigs.  However, some of the new System-P boxes have dma-windows above
  4gigs, and this present a problem.

  During initialization of the IOMMU tables, the last entry at each 4GB
  boundary is marked as used.  Thus no mappings can cross the boundary.
  If a table ends at a 4GB boundary, the entry is not marked as used.

  A boot option to remove this 4GB protection is given w/ protect4gb=off.
  This exposes the potential issue for driver and hardware development
  purposes.

  Signed-off-by: Jake Moilanen <moilanen@austin.ibm.com>
  Acked-by: Olof Johansson <olof@lixom.net>
  Signed-off-by: Paul Mackerras <paulus@samba.org>

RHEL Version Found:
-------------------
bug against 5.0

Upstream Status:
----------------
This code is upstream in 2.6.22 [1]

Test Status:
------------
These patches have been built against 2.6.18-19.el5, and successfully
built in brew task 794835 [2].

This patch has been tested by Jake Moilanen and Manoj Iyler of IBM.  The
JS21 was failing after ~10 minutes without this code.  With the patch
applied it stayed up for more than 2 hours (before being taken down for
non-releated reasons)

Proposed Patch:
----------------
Please review and ACK for RHEL5.1

--
[1] http://git.kernel.org/gitweb.cgi?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=569975591c5530fdc9c7a3c45122e5e46f075a74
[2] http://brewweb.devel.redhat.com/brew/taskinfo?taskID=794835

---
 arch/powerpc/kernel/iommu.c |   33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

Index: b/arch/powerpc/kernel/iommu.c
===================================================================
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -58,6 +58,18 @@ static inline unsigned long iommu_num_pa
 	return npages;
 }
 
+static int protect4gb = 1;
+
+static int __init setup_protect4gb(char *str)
+{
+	if (strcmp(str, "on") == 0)
+		protect4gb = 1;
+	else if (strcmp(str, "off") == 0)
+		protect4gb = 0;
+
+	return 1;
+}
+
 static int __init setup_iommu(char *str)
 {
 	if (!strcmp(str, "novmerge"))
@@ -67,6 +79,7 @@ static int __init setup_iommu(char *str)
 	return 1;
 }
 
+__setup("protect4gb=", setup_protect4gb);
 __setup("iommu=", setup_iommu);
 
 static unsigned long iommu_range_alloc(struct iommu_table *tbl,
@@ -429,6 +442,9 @@ void iommu_unmap_sg(struct iommu_table *
 struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
 {
 	unsigned long sz;
+	unsigned long start_index, end_index;
+	unsigned long entries_per_4g;
+	unsigned long index;
 	static int welcomed = 0;
 	struct page *page;
 
@@ -480,6 +496,23 @@ struct iommu_table *iommu_init_table(str
 	ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size);
 #endif
 
+	/*
+	 * DMA cannot cross 4 GB boundary.  Mark last entry of each 4
+	 * GB chunk as reserved.
+	 */
+	if (protect4gb) {
+		entries_per_4g = 0x100000000l >> PAGE_SHIFT;
+
+		/* Mark the last bit before a 4GB boundary as used */
+		start_index = tbl->it_offset | (entries_per_4g - 1);
+		start_index -= tbl->it_offset;
+
+		end_index = tbl->it_size;
+
+		for (index = start_index; index < end_index - 1; index += entries_per_4g)
+			__set_bit(index, tbl->it_map);
+	}
+
 	if (!welcomed) {
 		printk(KERN_INFO "IOMMU table initialized, virtual merging %s\n",
 		       novmerge ? "disabled" : "enabled");