x86: Split swiotlb initialization into two stages

The commit f4780ca005404166cc40af77ef0e86132ab98a81 moves
swiotlb initialization before dma32_free_bootmem(). It's
supposed to fix a bug that the commit
75f1cdf1dda92cae037ec848ae63690d91913eac introduced, we
initialize SWIOTLB right after dma32_free_bootmem so we wrongly
steal memory area allocated for GART with broken BIOS earlier.

However, the above commit introduced another problem, which
likely breaks machines with huge amount of memory. Such a box
use the majority of DMA32_ZONE so there is no memory for
swiotlb.

With this patch, the x86 IOMMU initialization sequence are:

1. We set swiotlb to 1 in the case of (max_pfn > MAX_DMA32_PFN
   && !no_iommu). If swiotlb usage is forced by the boot option,
   we go to the step 3 and finish (we don't try to detect IOMMUs).

2. We call the detection functions of all the IOMMUs. The
   detection function sets x86_init.iommu.iommu_init to the IOMMU
   initialization function (so we can avoid calling the
   initialization functions of all the IOMMUs needlessly).

3. We initialize swiotlb (and set dma_ops to swiotlb_dma_ops) if
   swiotlb is set to 1.

4. If the IOMMU initialization function doesn't need swiotlb
   (e.g. the initialization is sucessful) then sets swiotlb to zero.

5. If we find that swiotlb is set to zero, we free swiotlb
   resource.

Reported-by: Yinghai Lu <yinghai@kernel.org>
Reported-by: Roland Dreier <rdreier@cisco.com>
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
LKML-Reference: <20091215204729A.fujita.tomonori@lab.ntt.co.jp>
Tested-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 17 insertions, 11 deletions

diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h
index 87ffcb12a1b8..8085277e1b8b 100644
--- a/arch/x86/include/asm/swiotlb.h
+++ b/arch/x86/include/asm/swiotlb.h
@@ -5,13 +5,17 @@
 
 #ifdef CONFIG_SWIOTLB
 extern int swiotlb;
-extern int pci_swiotlb_init(void);
+extern int __init pci_swiotlb_detect(void);
+extern void __init pci_swiotlb_init(void);
 #else
 #define swiotlb 0
-static inline int pci_swiotlb_init(void)
+static inline int pci_swiotlb_detect(void)
 {
 	return 0;
 }
+static inline void pci_swiotlb_init(void)
+{
+}
 #endif
 
 static inline void dma_mark_clean(void *addr, size_t size) {}
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index fcc2f2bfa39c..75e14e21f61a 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -120,15 +120,12 @@ static void __init dma32_free_bootmem(void)
 
 void __init pci_iommu_alloc(void)
 {
-	int use_swiotlb;
-
-	use_swiotlb = pci_swiotlb_init();
 #ifdef CONFIG_X86_64
 	/* free the range so iommu could get some range less than 4G */
 	dma32_free_bootmem();
 #endif
-	if (use_swiotlb)
-		return;
+	if (pci_swiotlb_detect())
+		goto out;
 
 	gart_iommu_hole_init();
 
@@ -138,6 +135,8 @@ void __init pci_iommu_alloc(void)
 
 	/* needs to be called after gart_iommu_hole_init */
 	amd_iommu_detect();
+out:
+	pci_swiotlb_init();
 }
 
 void *dma_generic_alloc_coherent(struct device *dev, size_t size,
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index e3c0a66b9e77..7d2829dde20e 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -43,12 +43,12 @@ static struct dma_map_ops swiotlb_dma_ops = {
 };
 
 /*
- * pci_swiotlb_init - initialize swiotlb if necessary
+ * pci_swiotlb_detect - set swiotlb to 1 if necessary
  *
  * This returns non-zero if we are forced to use swiotlb (by the boot
  * option).
  */
-int __init pci_swiotlb_init(void)
+int __init pci_swiotlb_detect(void)
 {
 	int use_swiotlb = swiotlb | swiotlb_force;
 
@@ -60,10 +60,13 @@ int __init pci_swiotlb_init(void)
 	if (swiotlb_force)
 		swiotlb = 1;
 
+	return use_swiotlb;
+}
+
+void __init pci_swiotlb_init(void)
+{
 	if (swiotlb) {
 		swiotlb_init(0);
 		dma_ops = &swiotlb_dma_ops;
 	}
-
-	return use_swiotlb;
 }