x86: Make early_node_mem get mem > 4 GB if possible

So we could put pgdata for the node high, and later sparse
vmmap will get the section nr that need.

With this patch will make <4 GB ram not use a sparse vmmap.

before this patch, will get, before swiotlb try get bootmem
[    0.000000] nid=1 start=0 end=2080000 aligned=1
[    0.000000]   free [10 - 96]
[    0.000000]   free [b12 - 1000]
[    0.000000]   free [359f - 38a3]
[    0.000000]   free [38b5 - 3a00]
[    0.000000]   free [41e01 - 42000]
[    0.000000]   free [73dde - 73e00]
[    0.000000]   free [73fdd - 74000]
[    0.000000]   free [741dd - 74200]
[    0.000000]   free [743dd - 74400]
[    0.000000]   free [745dd - 74600]
[    0.000000]   free [747dd - 74800]
[    0.000000]   free [749dd - 74a00]
[    0.000000]   free [74bdd - 74c00]
[    0.000000]   free [74ddd - 74e00]
[    0.000000]   free [74fdd - 75000]
[    0.000000]   free [751dd - 75200]
[    0.000000]   free [753dd - 75400]
[    0.000000]   free [755dd - 75600]
[    0.000000]   free [757dd - 75800]
[    0.000000]   free [759dd - 75a00]
[    0.000000]   free [75bdd - 7bf5f]
[    0.000000]   free [7f730 - 7f750]
[    0.000000]   free [100000 - 2080000]
[    0.000000]   total free 1f87170
[   93.301474] Placing 64MB software IO TLB between ffff880075bdd000 - ffff880079bdd000
[   93.311814] software IO TLB at phys 0x75bdd000 - 0x79bdd000

with this patch will get: before swiotlb try get bootmem
[    0.000000] nid=1 start=0 end=2080000 aligned=1
[    0.000000]   free [a - 96]
[    0.000000]   free [702 - 1000]
[    0.000000]   free [359f - 3600]
[    0.000000]   free [37de - 3800]
[    0.000000]   free [39dd - 3a00]
[    0.000000]   free [3bdd - 3c00]
[    0.000000]   free [3ddd - 3e00]
[    0.000000]   free [3fdd - 4000]
[    0.000000]   free [41dd - 4200]
[    0.000000]   free [43dd - 4400]
[    0.000000]   free [45dd - 4600]
[    0.000000]   free [47dd - 4800]
[    0.000000]   free [49dd - 4a00]
[    0.000000]   free [4bdd - 4c00]
[    0.000000]   free [4ddd - 4e00]
[    0.000000]   free [4fdd - 5000]
[    0.000000]   free [51dd - 5200]
[    0.000000]   free [53dd - 5400]
[    0.000000]   free [55dd - 7bf5f]
[    0.000000]   free [7f730 - 7f750]
[    0.000000]   free [100428 - 100600]
[    0.000000]   free [13ea01 - 13ec00]
[    0.000000]   free [170800 - 2080000]
[    0.000000]   total free 1f87170

[   92.689485] PCI-DMA: Using software bounce buffering for IO (SWIOTLB)
[   92.699799] Placing 64MB software IO TLB between ffff8800055dd000 - ffff8800095dd000
[   92.710916] software IO TLB at phys 0x55dd000 - 0x95dd000

so will get enough space below 4G, aka pfn 0x100000

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <1265793639-15071-15-git-send-email-yinghai@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 3232148..02f13cb 100644 (file)
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -163,14 +163,27 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
                                    unsigned long end, unsigned long size,
                                    unsigned long align)
 {
-       unsigned long mem = find_e820_area(start, end, size, align);
+       unsigned long mem;
 
+       /*
+        * put it on high as possible
+        * something will go with NODE_DATA
+        */
+       if (start < (MAX_DMA_PFN<<PAGE_SHIFT))
+               start = MAX_DMA_PFN<<PAGE_SHIFT;
+       if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) &&
+           end > (MAX_DMA32_PFN<<PAGE_SHIFT))
+               start = MAX_DMA32_PFN<<PAGE_SHIFT;
+       mem = find_e820_area(start, end, size, align);
        if (mem != -1L)
                return __va(mem);
 
-
-       start = __pa(MAX_DMA_ADDRESS);
-       end = max_low_pfn_mapped << PAGE_SHIFT;
+       /* extend the search scope */
+       end = max_pfn_mapped << PAGE_SHIFT;
+       if (end > (MAX_DMA32_PFN<<PAGE_SHIFT))
+               start = MAX_DMA32_PFN<<PAGE_SHIFT;
+       else
+               start = MAX_DMA_PFN<<PAGE_SHIFT;
        mem = find_e820_area(start, end, size, align);
        if (mem != -1L)
                return __va(mem);