[PATCH -mm] x86 calgary: fix handling of devces that aren't behind the Calgary

[FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>]

The calgary code can give drivers addresses above 4GB which is very
bad for hardware that is only 32bit DMA addressable:

http://lkml.org/lkml/2008/5/8/423

This patch tries to fix the problem by using per-device
dma_mapping_ops support. This fixes the calgary code to use swiotlb or
nommu properly for devices which are not behind the Calgary/CalIOC2.

With this patch, the calgary code sets the global dma_ops to swiotlb
or nommu, and the dma_ops of devices behind the Calgary/CalIOC2 to
calgary_dma_ops. So the calgary code can handle devices safely that
aren't behind the Calgary/CalIOC2.

I think that bus_register_notifier works nicely for hotplugging (the
calgary code can register a hook to set the device-per ops to
calgary_dma_ops) though I don't know the calgary code needs it.

This patch is against -mm (depends on the per-device dma_mapping_ops
patchset in -mm).

This is only compile tested.

Thanks,

==
From: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Subject: [PATCH] x86 calgary: fix handling of devces that aren't behind the Calgary

The calgary code can give drivers addresses above 4GB which is very
bad for hardware that is only 32bit DMA addressable.

With this patch, the calgary code sets the global dma_ops to swiotlb
or nommu properly, and the dma_ops of devices behind the
Calgary/CalIOC2 to calgary_dma_ops. So the calgary code can handle
devices safely that aren't behind the Calgary/CalIOC2.

Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
---
 arch/x86/kernel/pci-calgary_64.c |   63 +++++++++++---------------------------
 include/asm-x86/iommu.h          |    1 +
 2 files changed, 19 insertions(+), 45 deletions(-)

diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index dca9a82..1839968 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -36,6 +36,7 @@
 #include <linux/delay.h>
 #include <linux/scatterlist.h>
 #include <linux/iommu-helper.h>
+#include <asm/iommu.h>
 #include <asm/gart.h>
 #include <asm/calgary.h>
 #include <asm/tce.h>
@@ -410,22 +411,6 @@ static void calgary_unmap_sg(struct device *dev,
 	}
 }
 
-static int calgary_nontranslate_map_sg(struct device* dev,
-	struct scatterlist *sg, int nelems, int direction)
-{
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nelems, i) {
-		struct page *p = sg_page(s);
-
-		BUG_ON(!p);
-		s->dma_address = virt_to_bus(sg_virt(s));
-		s->dma_length = s->length;
-	}
-	return nelems;
-}
-
 static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 	int nelems, int direction)
 {
@@ -436,9 +421,6 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 	unsigned long entry;
 	int i;
 
-	if (!translation_enabled(tbl))
-		return calgary_nontranslate_map_sg(dev, sg, nelems, direction);
-
 	for_each_sg(sg, s, nelems, i) {
 		BUG_ON(!sg_page(s));
 
@@ -474,7 +456,6 @@ error:
 static dma_addr_t calgary_map_single(struct device *dev, phys_addr_t paddr,
 	size_t size, int direction)
 {
-	dma_addr_t dma_handle = bad_dma_address;
 	void *vaddr = phys_to_virt(paddr);
 	unsigned long uaddr;
 	unsigned int npages;
@@ -483,12 +464,7 @@ static dma_addr_t calgary_map_single(struct device *dev, phys_addr_t paddr,
 	uaddr = (unsigned long)vaddr;
 	npages = num_dma_pages(uaddr, size);
 
-	if (translation_enabled(tbl))
-		dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction);
-	else
-		dma_handle = virt_to_bus(vaddr);
-
-	return dma_handle;
+	return iommu_alloc(dev, tbl, vaddr, npages, direction);
 }
 
 static void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle,
@@ -497,9 +473,6 @@ static void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle,
 	struct iommu_table *tbl = find_iommu_table(dev);
 	unsigned int npages;
 
-	if (!translation_enabled(tbl))
-		return;
-
 	npages = num_dma_pages(dma_handle, size);
 	iommu_free(tbl, dma_handle, npages);
 }
@@ -522,18 +495,12 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size,
 		goto error;
 	memset(ret, 0, size);
 
-	if (translation_enabled(tbl)) {
-		/* set up tces to cover the allocated range */
-		mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL);
-		if (mapping == bad_dma_address)
-			goto free;
-
-		*dma_handle = mapping;
-	} else /* non translated slot */
-		*dma_handle = virt_to_bus(ret);
-
+	/* set up tces to cover the allocated range */
+	mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL);
+	if (mapping == bad_dma_address)
+		goto free;
+	*dma_handle = mapping;
 	return ret;
-
 free:
 	free_pages((unsigned long)ret, get_order(size));
 	ret = NULL;
@@ -1138,6 +1105,7 @@ static int __init calgary_init_one(struct pci_dev *dev)
 	tbl->chip_ops->handle_quirks(tbl, dev);
 
 	calgary_enable_translation(dev);
+	dev->dev.archdata.dma_ops = &calgary_dma_ops;
 
 	return 0;
 
@@ -1251,6 +1219,7 @@ error:
 		calgary_disable_translation(dev);
 		calgary_free_bus(dev);
 		pci_dev_put(dev); /* Undo calgary_init_one()'s pci_dev_get() */
+		dev->dev.archdata.dma_ops = NULL;
 	} while (1);
 
 	return ret;
@@ -1430,6 +1399,10 @@ void __init detect_calgary(void)
 		printk(KERN_INFO "PCI-DMA: Calgary TCE table spec is %d, "
 		       "CONFIG_IOMMU_DEBUG is %s.\n", specified_table_size,
 		       debugging ? "enabled" : "disabled");
+
+		/* swiotlb for devices that aren't behind the Calgary. */
+		if (end_pfn > MAX_DMA32_PFN)
+			swiotlb = 1;
 	}
 	return;
 
@@ -1446,7 +1419,7 @@ int __init calgary_iommu_init(void)
 {
 	int ret;
 
-	if (no_iommu || swiotlb)
+	if (no_iommu || (swiotlb && !calgary_detected))
 		return -ENODEV;
 
 	if (!calgary_detected)
@@ -1459,15 +1432,15 @@ int __init calgary_iommu_init(void)
 	if (ret) {
 		printk(KERN_ERR "PCI-DMA: Calgary init failed %d, "
 		       "falling back to no_iommu\n", ret);
-		if (end_pfn > MAX_DMA32_PFN)
-			printk(KERN_ERR "WARNING more than 4GB of memory, "
-					"32bit PCI may malfunction.\n");
 		return ret;
 	}
 
 	force_iommu = 1;
 	bad_dma_address = 0x0;
-	dma_ops = &calgary_dma_ops;
+
+	/* dma_ops is set to swiotlb or nommu */
+	if (!dma_ops)
+		dma_ops = &nommu_dma_ops;
 
 	return 0;
 }
diff --git a/include/asm-x86/iommu.h b/include/asm-x86/iommu.h
index 07862fd..1a5e7df 100644
--- a/include/asm-x86/iommu.h
+++ b/include/asm-x86/iommu.h
@@ -3,6 +3,7 @@
 
 extern void pci_iommu_shutdown(void);
 extern void no_iommu_init(void);
+extern struct dma_mapping_ops nommu_dma_ops;
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
 #ifdef CONFIG_IOMMU
-- 
1.5.4.2