https://github.com/torvalds/linux
Revision 9cc3a5bd40067b9a0fbd49199d0780463fc2140f authored by Naoya Horiguchi on 17 April 2013, 22:58:30 UTC, committed by Linus Torvalds on 17 April 2013, 23:10:44 UTC
With applying the previous patch "hugetlbfs: stop setting VM_DONTDUMP in initializing vma(VM_HUGETLB)" to reenable hugepage coredump, if a memory error happens on a hugepage and the affected processes try to access the error hugepage, we hit VM_BUG_ON(atomic_read(&page->_count) <= 0) in get_page(). The reason for this bug is that coredump-related code doesn't recognise "hugepage hwpoison entry" with which a pmd entry is replaced when a memory error occurs on a hugepage. In other words, physical address information is stored in different bit layout between hugepage hwpoison entry and pmd entry, so follow_hugetlb_page() which is called in get_dump_page() returns a wrong page from a given address. The expected behavior is like this: absent is_swap_pte FOLL_DUMP Expected behavior ------------------------------------------------------------------- true false false hugetlb_fault false true false hugetlb_fault false false false return page true false true skip page (to avoid allocation) false true true hugetlb_fault false false true return page With this patch, we can call hugetlb_fault() and take proper actions (we wait for migration entries, fail with VM_FAULT_HWPOISON_LARGE for hwpoisoned entries,) and as the result we can dump all hugepages except for hwpoisoned ones. Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Rik van Riel <riel@redhat.com> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: David Rientjes <rientjes@google.com> Cc: <stable@vger.kernel.org> [2.6.34+?] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 23d9e48
Tip revision: 9cc3a5bd40067b9a0fbd49199d0780463fc2140f authored by Naoya Horiguchi on 17 April 2013, 22:58:30 UTC
hugetlbfs: add swap entry check in follow_hugetlb_page()
hugetlbfs: add swap entry check in follow_hugetlb_page()
Tip revision: 9cc3a5b
maccess.c
/*
* Access kernel memory without faulting.
*/
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/uaccess.h>
/**
* probe_kernel_read(): safely attempt to read from a location
* @dst: pointer to the buffer that shall take the data
* @src: address to read from
* @size: size of the data chunk
*
* Safely read from address @src to the buffer at @dst. If a kernel fault
* happens, handle that and return -EFAULT.
*/
long __weak probe_kernel_read(void *dst, const void *src, size_t size)
__attribute__((alias("__probe_kernel_read")));
long __probe_kernel_read(void *dst, const void *src, size_t size)
{
long ret;
mm_segment_t old_fs = get_fs();
set_fs(KERNEL_DS);
pagefault_disable();
ret = __copy_from_user_inatomic(dst,
(__force const void __user *)src, size);
pagefault_enable();
set_fs(old_fs);
return ret ? -EFAULT : 0;
}
EXPORT_SYMBOL_GPL(probe_kernel_read);
/**
* probe_kernel_write(): safely attempt to write to a location
* @dst: address to write to
* @src: pointer to the data that shall be written
* @size: size of the data chunk
*
* Safely write to address @dst from the buffer at @src. If a kernel fault
* happens, handle that and return -EFAULT.
*/
long __weak probe_kernel_write(void *dst, const void *src, size_t size)
__attribute__((alias("__probe_kernel_write")));
long __probe_kernel_write(void *dst, const void *src, size_t size)
{
long ret;
mm_segment_t old_fs = get_fs();
set_fs(KERNEL_DS);
pagefault_disable();
ret = __copy_to_user_inatomic((__force void __user *)dst, src, size);
pagefault_enable();
set_fs(old_fs);
return ret ? -EFAULT : 0;
}
EXPORT_SYMBOL_GPL(probe_kernel_write);
Computing file changes ...
