A-Team_Digital_Solutions/android_kernel_motorola_sm6375
Watch
2
0
Fork
You've already forked android_kernel_motorola_sm6375
 0
mirror of https://github.com/BobTheBlinker/android_kernel_motorola_sm6375.git synced 2026-10-24 05:29:04 -04:00
Code Issues Projects Releases Packages Wiki Activity

[SPARC64]: Top-down address space allocation for 32-bit tasks.

Browse source 
Currently allocations are very constrained for 32-bit processes.
It grows down-up from 0x70000000 to 0xf0000000 which gives about
2GB of stack + dynamic mmap() space.

So support the top-down method, and we need to override the
generic helper function in order to deal with D-cache coloring.

With these changes I was able to squeeze out a mmap() just over
3.6GB in size in a 32-bit process.

Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller 2006-03-17 14:41:03 -08:00
commit a91690ddd0
4 changed files with 189 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

5
include/asm-sparc64/pgtable.h
View file

@ -752,8 +752,11 @@ extern int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
#include <asm-generic/pgtable.h>
/* We provide our own get_unmapped_area to cope with VA holes for userland */
/* We provide our own get_unmapped_area to cope with VA holes and
* SHM area cache aliasing for userland.
*/
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
/* We provide a special get_unmapped_area for framebuffer mmaps to try and use
* the largest alignment possible such that larget PTEs can be used.

2
include/asm-sparc64/processor.h
View file

@ -217,6 +217,8 @@ static inline void prefetchw(const void *x)
#define spin_lock_prefetch(x) prefetchw(x)
#define HAVE_ARCH_PICK_MMAP_LAYOUT
#endif /* !(__ASSEMBLY__) */
#endif /* !(__ASM_SPARC64_PROCESSOR_H) */