mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-16 21:06:43 +07:00
f4ea6dcb08
Not all user space application is ready to handle wide addresses. It's known that at least some JIT compilers use higher bits in pointers to encode their information. It collides with valid pointers with 512TB addresses and leads to crashes. To mitigate this, we are not going to allocate virtual address space above 128TB by default. But userspace can ask for allocation from full address space by specifying hint address (with or without MAP_FIXED) above 128TB. If hint address set above 128TB, but MAP_FIXED is not specified, we try to look for unmapped area by specified address. If it's already occupied, we look for unmapped area in *full* address space, rather than from 128TB window. This approach helps to easily make application's memory allocator aware about large address space without manually tracking allocated virtual address space. This is going to be a per mmap decision. ie, we can have some mmaps with larger addresses and other that do not. A sample memory layout looks like: 10000000-10010000 r-xp 00000000 fc:00 9057045 /home/max_addr_512TB 10010000-10020000 r--p 00000000 fc:00 9057045 /home/max_addr_512TB 10020000-10030000 rw-p 00010000 fc:00 9057045 /home/max_addr_512TB 10029630000-10029660000 rw-p 00000000 00:00 0 [heap] 7fff834a0000-7fff834b0000 rw-p 00000000 00:00 0 7fff834b0000-7fff83670000 r-xp 00000000 fc:00 9177190 /lib/powerpc64le-linux-gnu/libc-2.23.so 7fff83670000-7fff83680000 r--p 001b0000 fc:00 9177190 /lib/powerpc64le-linux-gnu/libc-2.23.so 7fff83680000-7fff83690000 rw-p 001c0000 fc:00 9177190 /lib/powerpc64le-linux-gnu/libc-2.23.so 7fff83690000-7fff836a0000 rw-p 00000000 00:00 0 7fff836a0000-7fff836c0000 r-xp 00000000 00:00 0 [vdso] 7fff836c0000-7fff83700000 r-xp 00000000 fc:00 9177193 /lib/powerpc64le-linux-gnu/ld-2.23.so 7fff83700000-7fff83710000 r--p 00030000 fc:00 9177193 /lib/powerpc64le-linux-gnu/ld-2.23.so 7fff83710000-7fff83720000 rw-p 00040000 fc:00 9177193 /lib/powerpc64le-linux-gnu/ld-2.23.so 7fffdccf0000-7fffdcd20000 rw-p 00000000 00:00 0 [stack] 1000000000000-1000000010000 rw-p 00000000 00:00 0 1ffff83710000-1ffff83720000 rw-p 00000000 00:00 0 Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
90 lines
2.3 KiB
C
90 lines
2.3 KiB
C
#include <linux/mm.h>
|
|
#include <linux/hugetlb.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/machdep.h>
|
|
#include <asm/mman.h>
|
|
#include <asm/tlb.h>
|
|
|
|
void radix__flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
|
|
{
|
|
int psize;
|
|
struct hstate *hstate = hstate_file(vma->vm_file);
|
|
|
|
psize = hstate_get_psize(hstate);
|
|
radix__flush_tlb_page_psize(vma->vm_mm, vmaddr, psize);
|
|
}
|
|
|
|
void radix__local_flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
|
|
{
|
|
int psize;
|
|
struct hstate *hstate = hstate_file(vma->vm_file);
|
|
|
|
psize = hstate_get_psize(hstate);
|
|
radix__local_flush_tlb_page_psize(vma->vm_mm, vmaddr, psize);
|
|
}
|
|
|
|
void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long start,
|
|
unsigned long end)
|
|
{
|
|
int psize;
|
|
struct hstate *hstate = hstate_file(vma->vm_file);
|
|
|
|
psize = hstate_get_psize(hstate);
|
|
radix__flush_tlb_range_psize(vma->vm_mm, start, end, psize);
|
|
}
|
|
|
|
/*
|
|
* A vairant of hugetlb_get_unmapped_area doing topdown search
|
|
* FIXME!! should we do as x86 does or non hugetlb area does ?
|
|
* ie, use topdown or not based on mmap_is_legacy check ?
|
|
*/
|
|
unsigned long
|
|
radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
|
|
unsigned long len, unsigned long pgoff,
|
|
unsigned long flags)
|
|
{
|
|
struct mm_struct *mm = current->mm;
|
|
struct vm_area_struct *vma;
|
|
struct hstate *h = hstate_file(file);
|
|
struct vm_unmapped_area_info info;
|
|
|
|
if (unlikely(addr > mm->context.addr_limit && addr < TASK_SIZE))
|
|
mm->context.addr_limit = TASK_SIZE;
|
|
|
|
if (len & ~huge_page_mask(h))
|
|
return -EINVAL;
|
|
if (len > mm->context.addr_limit)
|
|
return -ENOMEM;
|
|
|
|
if (flags & MAP_FIXED) {
|
|
if (prepare_hugepage_range(file, addr, len))
|
|
return -EINVAL;
|
|
return addr;
|
|
}
|
|
|
|
if (addr) {
|
|
addr = ALIGN(addr, huge_page_size(h));
|
|
vma = find_vma(mm, addr);
|
|
if (mm->context.addr_limit - len >= addr &&
|
|
(!vma || addr + len <= vma->vm_start))
|
|
return addr;
|
|
}
|
|
/*
|
|
* We are always doing an topdown search here. Slice code
|
|
* does that too.
|
|
*/
|
|
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
|
|
info.length = len;
|
|
info.low_limit = PAGE_SIZE;
|
|
info.high_limit = current->mm->mmap_base;
|
|
info.align_mask = PAGE_MASK & ~huge_page_mask(h);
|
|
info.align_offset = 0;
|
|
|
|
if (addr > DEFAULT_MAP_WINDOW)
|
|
info.high_limit += mm->context.addr_limit - DEFAULT_MAP_WINDOW;
|
|
|
|
return vm_unmapped_area(&info);
|
|
}
|