[PATCH][v2] powerpc/mm: using two zones for freescale 64 bit kernel

[Shaohui Xie]

PowerPC platform only supports ZONE_DMA zone for 64bit kernel, so all the
memory will be put into this zone. If the memory size is greater than
the device's DMA capability and device uses dma_alloc_coherent to allocate
memory, it will get an address which is over the device's DMA addressing,
the device will fail.

So we split the memory to two zones: zone ZONE_DMA32 & ZONE_NORMAL, since
we already allocate PCICSRBAR/PEXCSRBAR right below the 4G boundary (if the
lowest PCI address is above 4G), so we constrain the DMA zone ZONE_DMA32
to 2GB, also, we clear flag __GFP_DMA & __GFP_DMA32 and set __GFP_DMA32 only
if the device's dma_mask < total memory size. By doing this, devices which
cannot DMA all the memory will be limited to ZONE_DMA32, but devices which
can DMA all the memory will not be affected by this limitation.

Signed-off-by: Shaohui Xie <Shaohui.Xie at freescale.com>
Signed-off-by: Mingkai Hu <Mingkai.hu at freescale.com>
Signed-off-by: Chen Yuanquan <B41889 at freescale.com>
---
changes for v2:
1. use a config option for using two zones (ZONE_DMA32 & ZONE_NORMAL) in
freescale 64 bit kernel.

 arch/powerpc/Kconfig      |    3 +++
 arch/powerpc/kernel/dma.c |   15 +++++++++++++++
 arch/powerpc/mm/mem.c     |    4 ++++
 3 files changed, 22 insertions(+), 0 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 352f416..a96fbbb 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -629,6 +629,9 @@ config ZONE_DMA
 	bool
 	default y
 
+config ZONE_DMA32
+	def_bool (PPC64 && PPC_FSL_BOOK3E)
+
 config NEED_DMA_MAP_STATE
 	def_bool (PPC64 || NOT_COHERENT_CACHE)
 
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 355b9d8..cbf5ac1 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -41,9 +41,24 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 #else
 	struct page *page;
 	int node = dev_to_node(dev);
+#ifdef CONFIG_ZONE_DMA32
+	phys_addr_t top_ram_pfn = memblock_end_of_DRAM();
 
+	/*
+	 * check for crappy device which has dma_mask < ZONE_DMA, and
+	 * we are not going to support it, just warn and fail.
+	 */
+	if (*dev->dma_mask < DMA_BIT_MASK(31)) {
+		dev_err(dev, "Unsupported dma_mask 0x%llx\n", *dev->dma_mask);
+		return NULL;
+	}
 	/* ignore region specifiers */
+	flag  &= ~(__GFP_HIGHMEM | __GFP_DMA | __GFP_DMA32);
+	if (*dev->dma_mask < top_ram_pfn - 1)
+		flag |= __GFP_DMA32;
+#else
 	flag  &= ~(__GFP_HIGHMEM);
+#endif
 
 	page = alloc_pages_node(node, flag, get_order(size));
 	if (page == NULL)
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index baaafde..2a11e49 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -280,6 +280,10 @@ void __init paging_init(void)
 #ifdef CONFIG_HIGHMEM
 	max_zone_pfns[ZONE_DMA] = lowmem_end_addr >> PAGE_SHIFT;
 	max_zone_pfns[ZONE_HIGHMEM] = top_of_ram >> PAGE_SHIFT;
+#elif defined CONFIG_ZONE_DMA32
+	max_zone_pfns[ZONE_DMA32] = min_t(phys_addr_t, top_of_ram,
+					1ull << 31) >> PAGE_SHIFT;
+	max_zone_pfns[ZONE_NORMAL] = top_of_ram >> PAGE_SHIFT;
 #else
 	max_zone_pfns[ZONE_DMA] = top_of_ram >> PAGE_SHIFT;
 #endif
-- 
1.6.4