Revision ec3937107ab43f3e8b2bc9dad95710043c462ff7 authored by Baoquan He on 04 April 2019, 02:03:13 UTC, committed by Borislav Petkov on 18 April 2019, 08:42:58 UTC
kernel_randomize_memory() uses __PHYSICAL_MASK_SHIFT to calculate the maximum amount of system RAM supported. The size of the direct mapping section is obtained from the smaller one of the below two values: (actual system RAM size + padding size) vs (max system RAM size supported) This calculation is wrong since commit b83ce5ee9147 ("x86/mm/64: Make __PHYSICAL_MASK_SHIFT always 52"). In it, __PHYSICAL_MASK_SHIFT was changed to be 52, regardless of whether the kernel is using 4-level or 5-level page tables. Thus, it will always use 4 PB as the maximum amount of system RAM, even in 4-level paging mode where it should actually be 64 TB. Thus, the size of the direct mapping section will always be the sum of the actual system RAM size plus the padding size. Even when the amount of system RAM is 64 TB, the following layout will still be used. Obviously KALSR will be weakened significantly. |____|_______actual RAM_______|_padding_|______the rest_______| 0 64TB ~120TB Instead, it should be like this: |____|_______actual RAM_______|_________the rest______________| 0 64TB ~120TB The size of padding region is controlled by CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING, which is 10 TB by default. The above issue only exists when CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING is set to a non-zero value, which is the case when CONFIG_MEMORY_HOTPLUG is enabled. Otherwise, using __PHYSICAL_MASK_SHIFT doesn't affect KASLR. Fix it by replacing __PHYSICAL_MASK_SHIFT with MAX_PHYSMEM_BITS. [ bp: Massage commit message. ] Fixes: b83ce5ee9147 ("x86/mm/64: Make __PHYSICAL_MASK_SHIFT always 52") Signed-off-by: Baoquan He <bhe@redhat.com> Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Thomas Garnier <thgarnie@google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: frank.ramsay@hpe.com Cc: herbert@gondor.apana.org.au Cc: kirill@shutemov.name Cc: mike.travis@hpe.com Cc: thgarnie@google.com Cc: x86-ml <x86@kernel.org> Cc: yamada.masahiro@socionext.com Link: https://lkml.kernel.org/r/20190417083536.GE7065@MiWiFi-R3L-srv
1 parent a943245
msync.c
// SPDX-License-Identifier: GPL-2.0
/*
* linux/mm/msync.c
*
* Copyright (C) 1994-1999 Linus Torvalds
*/
/*
* The msync() system call.
*/
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/file.h>
#include <linux/syscalls.h>
#include <linux/sched.h>
/*
* MS_SYNC syncs the entire file - including mappings.
*
* MS_ASYNC does not start I/O (it used to, up to 2.5.67).
* Nor does it marks the relevant pages dirty (it used to up to 2.6.17).
* Now it doesn't do anything, since dirty pages are properly tracked.
*
* The application may now run fsync() to
* write out the dirty pages and wait on the writeout and check the result.
* Or the application may run fadvise(FADV_DONTNEED) against the fd to start
* async writeout immediately.
* So by _not_ starting I/O in MS_ASYNC we provide complete flexibility to
* applications.
*/
SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
{
unsigned long end;
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
int unmapped_error = 0;
int error = -EINVAL;
if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
goto out;
if (offset_in_page(start))
goto out;
if ((flags & MS_ASYNC) && (flags & MS_SYNC))
goto out;
error = -ENOMEM;
len = (len + ~PAGE_MASK) & PAGE_MASK;
end = start + len;
if (end < start)
goto out;
error = 0;
if (end == start)
goto out;
/*
* If the interval [start,end) covers some unmapped address ranges,
* just ignore them, but return -ENOMEM at the end.
*/
down_read(&mm->mmap_sem);
vma = find_vma(mm, start);
for (;;) {
struct file *file;
loff_t fstart, fend;
/* Still start < end. */
error = -ENOMEM;
if (!vma)
goto out_unlock;
/* Here start < vma->vm_end. */
if (start < vma->vm_start) {
start = vma->vm_start;
if (start >= end)
goto out_unlock;
unmapped_error = -ENOMEM;
}
/* Here vma->vm_start <= start < vma->vm_end. */
if ((flags & MS_INVALIDATE) &&
(vma->vm_flags & VM_LOCKED)) {
error = -EBUSY;
goto out_unlock;
}
file = vma->vm_file;
fstart = (start - vma->vm_start) +
((loff_t)vma->vm_pgoff << PAGE_SHIFT);
fend = fstart + (min(end, vma->vm_end) - start) - 1;
start = vma->vm_end;
if ((flags & MS_SYNC) && file &&
(vma->vm_flags & VM_SHARED)) {
get_file(file);
up_read(&mm->mmap_sem);
error = vfs_fsync_range(file, fstart, fend, 1);
fput(file);
if (error || start >= end)
goto out;
down_read(&mm->mmap_sem);
vma = find_vma(mm, start);
} else {
if (start >= end) {
error = 0;
goto out_unlock;
}
vma = vma->vm_next;
}
}
out_unlock:
up_read(&mm->mmap_sem);
out:
return error ? : unmapped_error;
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...