@@ -2669,6 +2669,7 @@ enum mf_action_page_type {
MF_MSG_TRUNCATED_LRU,
MF_MSG_BUDDY,
MF_MSG_BUDDY_2ND,
+ MF_MSG_DAX,
MF_MSG_UNKNOWN,
};
@@ -55,6 +55,7 @@
#include <linux/hugetlb.h>
#include <linux/memory_hotplug.h>
#include <linux/mm_inline.h>
+#include <linux/memremap.h>
#include <linux/kfifo.h>
#include <linux/ratelimit.h>
#include "internal.h"
@@ -531,6 +532,7 @@ static const char * const action_page_types[] = {
[MF_MSG_TRUNCATED_LRU] = "already truncated LRU page",
[MF_MSG_BUDDY] = "free buddy page",
[MF_MSG_BUDDY_2ND] = "free buddy page (2nd try)",
+ [MF_MSG_DAX] = "dax page",
[MF_MSG_UNKNOWN] = "unknown page",
};
@@ -1132,6 +1134,144 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
return res;
}
+static unsigned long dax_mapping_size(struct address_space *mapping,
+ struct page *page)
+{
+ pgoff_t pgoff = page_to_pgoff(page);
+ struct vm_area_struct *vma;
+ unsigned long size = 0;
+
+ i_mmap_lock_read(mapping);
+ xa_lock_irq(&mapping->i_pages);
+ /* validate that @page is still linked to @mapping */
+ if (page->mapping != mapping) {
+ xa_unlock_irq(&mapping->i_pages);
+ i_mmap_unlock_read(mapping);
+ return 0;
+ }
+ vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
+ unsigned long address = vma_address(page, vma);
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ pgd = pgd_offset(vma->vm_mm, address);
+ if (!pgd_present(*pgd))
+ continue;
+ p4d = p4d_offset(pgd, address);
+ if (!p4d_present(*p4d))
+ continue;
+ pud = pud_offset(p4d, address);
+ if (!pud_present(*pud))
+ continue;
+ if (pud_devmap(*pud)) {
+ size = PUD_SIZE;
+ break;
+ }
+ pmd = pmd_offset(pud, address);
+ if (!pmd_present(*pmd))
+ continue;
+ if (pmd_devmap(*pmd)) {
+ size = PMD_SIZE;
+ break;
+ }
+ pte = pte_offset_map(pmd, address);
+ if (!pte_present(*pte))
+ continue;
+ if (pte_devmap(*pte)) {
+ size = PAGE_SIZE;
+ break;
+ }
+ }
+ xa_unlock_irq(&mapping->i_pages);
+ i_mmap_unlock_read(mapping);
+
+ return size;
+}
+
+static int memory_failure_dev_pagemap(unsigned long pfn, int flags,
+ struct dev_pagemap *pgmap)
+{
+ struct page *page = pfn_to_page(pfn);
+ const bool unmap_success = true;
+ struct address_space *mapping;
+ unsigned long size;
+ LIST_HEAD(tokill);
+ int rc = -EBUSY;
+ loff_t start;
+
+ /*
+ * Prevent the inode from being freed while we are interrogating
+ * the address_space, typically this would be handled by
+ * lock_page(), but dax pages do not use the page lock.
+ */
+ rcu_read_lock();
+ mapping = page->mapping;
+ if (!mapping) {
+ rcu_read_unlock();
+ goto out;
+ }
+ if (!igrab(mapping->host)) {
+ mapping = NULL;
+ rcu_read_unlock();
+ goto out;
+ }
+ rcu_read_unlock();
+
+ if (hwpoison_filter(page)) {
+ rc = 0;
+ goto out;
+ }
+
+ switch (pgmap->type) {
+ case MEMORY_DEVICE_PRIVATE:
+ case MEMORY_DEVICE_PUBLIC:
+ /*
+ * TODO: Handle HMM pages which may need coordination
+ * with device-side memory.
+ */
+ goto out;
+ default:
+ break;
+ }
+
+ /*
+ * If the page is not mapped in userspace then report it as
+ * unhandled.
+ */
+ size = dax_mapping_size(mapping, page);
+ if (!size) {
+ pr_err("Memory failure: %#lx: failed to unmap page\n", pfn);
+ goto out;
+ }
+
+ SetPageHWPoison(page);
+
+ /*
+ * Unlike System-RAM there is no possibility to swap in a
+ * different physical page at a given virtual address, so all
+ * userspace consumption of ZONE_DEVICE memory necessitates
+ * SIGBUS (i.e. MF_MUST_KILL)
+ */
+ flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
+ collect_procs(mapping, page, &tokill, flags & MF_ACTION_REQUIRED);
+
+ start = (page->index << PAGE_SHIFT) & ~(size - 1);
+ unmap_mapping_range(page->mapping, start, start + size, 0);
+
+ kill_procs(&tokill, flags & MF_MUST_KILL, !unmap_success, ilog2(size),
+ mapping, page, flags);
+ rc = 0;
+out:
+ if (mapping)
+ iput(mapping->host);
+ put_dev_pagemap(pgmap);
+ action_result(pfn, MF_MSG_DAX, rc ? MF_FAILED : MF_RECOVERED);
+ return rc;
+}
+
/**
* memory_failure - Handle memory failure of a page.
* @pfn: Page Number of the corrupted page
@@ -1154,6 +1294,7 @@ int memory_failure(unsigned long pfn, int flags)
struct page *p;
struct page *hpage;
struct page *orig_head;
+ struct dev_pagemap *pgmap;
int res;
unsigned long page_flags;
@@ -1166,6 +1307,10 @@ int memory_failure(unsigned long pfn, int flags)
return -ENXIO;
}
+ pgmap = get_dev_pagemap(pfn, NULL);
+ if (pgmap)
+ return memory_failure_dev_pagemap(pfn, flags, pgmap);
+
p = pfn_to_page(pfn);
if (PageHuge(p))
return memory_failure_hugetlb(pfn, flags);
mce: Uncorrected hardware memory error in user-access at af34214200 {1}[Hardware Error]: It has been corrected by h/w and requires no further action mce: [Hardware Error]: Machine check events logged {1}[Hardware Error]: event severity: corrected Memory failure: 0xaf34214: reserved kernel page still referenced by 1 users [..] Memory failure: 0xaf34214: recovery action for reserved kernel page: Failed mce: Memory error not recovered In contrast to typical memory, dev_pagemap pages may be dax mapped. With dax there is no possibility to map in another page dynamically since dax establishes 1:1 physical address to file offset associations. Also dev_pagemap pages associated with NVDIMM / persistent memory devices can internal remap/repair addresses with poison. While memory_failure() assumes that it can discard typical poisoned pages and keep them unmapped indefinitely, dev_pagemap pages may be returned to service after the error is cleared. Teach memory_failure() to detect and handle MEMORY_DEVICE_HOST dev_pagemap pages that have poison consumed by userspace. Mark the memory as UC instead of unmapping it completely to allow ongoing access via the device driver (nd_pmem). Later, nd_pmem will grow support for marking the page back to WB when the error is cleared. Cc: Jan Kara <jack@suse.cz> Cc: Christoph Hellwig <hch@lst.de> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> --- include/linux/mm.h | 1 mm/memory-failure.c | 145 +++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 146 insertions(+)