mm, memory_failure: Teach memory_failure() about dev_pagemap pages

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 <willy@infradead.org>
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>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
This commit is contained in:
Dan Williams 2018-07-13 21:50:21 -07:00 committed by Dave Jiang
parent c2a7d2a115
commit 6100e34b25
2 changed files with 124 additions and 2 deletions

View file

@ -2725,6 +2725,7 @@ enum mf_action_page_type {
MF_MSG_TRUNCATED_LRU,
MF_MSG_BUDDY,
MF_MSG_BUDDY_2ND,
MF_MSG_DAX,
MF_MSG_UNKNOWN,
};

View file

@ -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"
@ -263,6 +264,40 @@ void shake_page(struct page *p, int access)
}
EXPORT_SYMBOL_GPL(shake_page);
static unsigned long dev_pagemap_mapping_shift(struct page *page,
struct vm_area_struct *vma)
{
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))
return 0;
p4d = p4d_offset(pgd, address);
if (!p4d_present(*p4d))
return 0;
pud = pud_offset(p4d, address);
if (!pud_present(*pud))
return 0;
if (pud_devmap(*pud))
return PUD_SHIFT;
pmd = pmd_offset(pud, address);
if (!pmd_present(*pmd))
return 0;
if (pmd_devmap(*pmd))
return PMD_SHIFT;
pte = pte_offset_map(pmd, address);
if (!pte_present(*pte))
return 0;
if (pte_devmap(*pte))
return PAGE_SHIFT;
return 0;
}
/*
* Failure handling: if we can't find or can't kill a process there's
* not much we can do. We just print a message and ignore otherwise.
@ -292,7 +327,10 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
}
tk->addr = page_address_in_vma(p, vma);
tk->addr_valid = 1;
tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT;
if (is_zone_device_page(p))
tk->size_shift = dev_pagemap_mapping_shift(p, vma);
else
tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT;
/*
* In theory we don't have to kill when the page was
@ -300,7 +338,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
* likely very rare kill anyways just out of paranoia, but use
* a SIGKILL because the error is not contained anymore.
*/
if (tk->addr == -EFAULT) {
if (tk->addr == -EFAULT || tk->size_shift == 0) {
pr_info("Memory failure: Unable to find user space address %lx in %s\n",
page_to_pfn(p), tsk->comm);
tk->addr_valid = 0;
@ -514,6 +552,7 @@ 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",
};
@ -1111,6 +1150,83 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
return res;
}
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;
unsigned long size = 0;
struct to_kill *tk;
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. This
* also prevents changes to the mapping of this pfn until
* poison signaling is complete.
*/
if (!dax_lock_mapping_entry(page))
goto out;
if (hwpoison_filter(page)) {
rc = 0;
goto unlock;
}
switch (pgmap->type) {
case MEMORY_DEVICE_PRIVATE:
case MEMORY_DEVICE_PUBLIC:
/*
* TODO: Handle HMM pages which may need coordination
* with device-side memory.
*/
goto unlock;
default:
break;
}
/*
* Use this flag as an indication that the dax page has been
* remapped UC to prevent speculative consumption of poison.
*/
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(page, &tokill, flags & MF_ACTION_REQUIRED);
list_for_each_entry(tk, &tokill, nd)
if (tk->size_shift)
size = max(size, 1UL << tk->size_shift);
if (size) {
/*
* Unmap the largest mapping to avoid breaking up
* device-dax mappings which are constant size. The
* actual size of the mapping being torn down is
* communicated in siginfo, see kill_proc()
*/
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, pfn, flags);
rc = 0;
unlock:
dax_unlock_mapping_entry(page);
out:
/* drop pgmap ref acquired in caller */
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
@ -1133,6 +1249,7 @@ 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;
@ -1145,6 +1262,10 @@ 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);