#include <linux/page-isolation.h>
#include <linux/suspend.h>
#include <linux/slab.h>
+#include <linux/swapops.h>
#include <linux/hugetlb.h>
#include "internal.h"
* signal.
*/
static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno,
- unsigned long pfn)
+ unsigned long pfn, struct page *page)
{
struct siginfo si;
int ret;
#ifdef __ARCH_SI_TRAPNO
si.si_trapno = trapno;
#endif
- si.si_addr_lsb = PAGE_SHIFT;
+ si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT;
/*
* Don't use force here, it's convenient if the signal
* can be temporarily blocked.
* wrong earlier.
*/
static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno,
- int fail, unsigned long pfn)
+ int fail, struct page *page, unsigned long pfn)
{
struct to_kill *tk, *next;
* process anyways.
*/
else if (kill_proc_ao(tk->tsk, tk->addr, trapno,
- pfn) < 0)
+ pfn, page) < 0)
printk(KERN_ERR
"MCE %#lx: Cannot send advisory machine check signal to %s:%d\n",
pfn, tk->tsk->comm, tk->tsk->pid);
/*
* Huge pages. Needs work.
* Issues:
- * No rmap support so we cannot find the original mapper. In theory could walk
- * all MMs and look for the mappings, but that would be non atomic and racy.
- * Need rmap for hugepages for this. Alternatively we could employ a heuristic,
- * like just walking the current process and hoping it has it mapped (that
- * should be usually true for the common "shared database cache" case)
- * Should handle free huge pages and dequeue them too, but this needs to
- * handle huge page accounting correctly.
+ * - Error on hugepage is contained in hugepage unit (not in raw page unit.)
+ * To narrow down kill region to one page, we need to break up pmd.
+ * - To support soft-offlining for hugepage, we need to support hugepage
+ * migration.
*/
static int me_huge_page(struct page *p, unsigned long pfn)
{
- return FAILED;
+ struct page *hpage = compound_head(p);
+ /*
+ * We can safely recover from error on free or reserved (i.e.
+ * not in-use) hugepage by dequeuing it from freelist.
+ * To check whether a hugepage is in-use or not, we can't use
+ * page->lru because it can be used in other hugepage operations,
+ * such as __unmap_hugepage_range() and gather_surplus_pages().
+ * So instead we use page_mapping() and PageAnon().
+ * We assume that this function is called with page lock held,
+ * so there is no race between isolation and mapping/unmapping.
+ */
+ if (!(page_mapping(hpage) || PageAnon(hpage))) {
+ __isolate_hwpoisoned_huge_page(hpage);
+ return RECOVERED;
+ }
+ return DELAYED;
}
/*
* any accesses to the poisoned memory.
*/
kill_procs_ao(&tokill, !!PageDirty(hpage), trapno,
- ret != SWAP_SUCCESS, pfn);
+ ret != SWAP_SUCCESS, p, pfn);
return ret;
}
/* keep elevated page count for bad page */
return ret;
}
+
+/*
+ * The caller must hold current->mm->mmap_sem in read mode.
+ */
+int is_hwpoison_address(unsigned long addr)
+{
+ pgd_t *pgdp;
+ pud_t pud, *pudp;
+ pmd_t pmd, *pmdp;
+ pte_t pte, *ptep;
+ swp_entry_t entry;
+
+ pgdp = pgd_offset(current->mm, addr);
+ if (!pgd_present(*pgdp))
+ return 0;
+ pudp = pud_offset(pgdp, addr);
+ pud = *pudp;
+ if (!pud_present(pud) || pud_large(pud))
+ return 0;
+ pmdp = pmd_offset(pudp, addr);
+ pmd = *pmdp;
+ if (!pmd_present(pmd) || pmd_large(pmd))
+ return 0;
+ ptep = pte_offset_map(pmdp, addr);
+ pte = *ptep;
+ pte_unmap(ptep);
+ if (!is_swap_pte(pte))
+ return 0;
+ entry = pte_to_swp_entry(pte);
+ return is_hwpoison_entry(entry);
+}
+EXPORT_SYMBOL_GPL(is_hwpoison_address);