linux-sg2042/arch/powerpc/mm/hugetlbpage-radix.c

90 lines
2.3 KiB
C
Raw Normal View History

#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;
powerpc/mm: Enable mappings above 128TB 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>
2017-03-30 19:05:21 +08:00
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->task_size)
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->task_size - len >= addr &&
mm: larger stack guard gap, between vmas Stack guard page is a useful feature to reduce a risk of stack smashing into a different mapping. We have been using a single page gap which is sufficient to prevent having stack adjacent to a different mapping. But this seems to be insufficient in the light of the stack usage in userspace. E.g. glibc uses as large as 64kB alloca() in many commonly used functions. Others use constructs liks gid_t buffer[NGROUPS_MAX] which is 256kB or stack strings with MAX_ARG_STRLEN. This will become especially dangerous for suid binaries and the default no limit for the stack size limit because those applications can be tricked to consume a large portion of the stack and a single glibc call could jump over the guard page. These attacks are not theoretical, unfortunatelly. Make those attacks less probable by increasing the stack guard gap to 1MB (on systems with 4k pages; but make it depend on the page size because systems with larger base pages might cap stack allocations in the PAGE_SIZE units) which should cover larger alloca() and VLA stack allocations. It is obviously not a full fix because the problem is somehow inherent, but it should reduce attack space a lot. One could argue that the gap size should be configurable from userspace, but that can be done later when somebody finds that the new 1MB is wrong for some special case applications. For now, add a kernel command line option (stack_guard_gap) to specify the stack gap size (in page units). Implementation wise, first delete all the old code for stack guard page: because although we could get away with accounting one extra page in a stack vma, accounting a larger gap can break userspace - case in point, a program run with "ulimit -S -v 20000" failed when the 1MB gap was counted for RLIMIT_AS; similar problems could come with RLIMIT_MLOCK and strict non-overcommit mode. Instead of keeping gap inside the stack vma, maintain the stack guard gap as a gap between vmas: using vm_start_gap() in place of vm_start (or vm_end_gap() in place of vm_end if VM_GROWSUP) in just those few places which need to respect the gap - mainly arch_get_unmapped_area(), and and the vma tree's subtree_gap support for that. Original-patch-by: Oleg Nesterov <oleg@redhat.com> Original-patch-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Hugh Dickins <hughd@google.com> Acked-by: Michal Hocko <mhocko@suse.com> Tested-by: Helge Deller <deller@gmx.de> # parisc Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-06-19 19:03:24 +08:00
(!vma || addr + len <= vm_start_gap(vma)))
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;
powerpc/mm: Enable mappings above 128TB 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>
2017-03-30 19:05:21 +08:00
if (addr > DEFAULT_MAP_WINDOW)
info.high_limit += mm->context.addr_limit - DEFAULT_MAP_WINDOW;
return vm_unmapped_area(&info);
}