#include <linux/kprobes.h> /* __kprobes, ... */
#include <linux/mmiotrace.h> /* kmmio_handler, ... */
#include <linux/perf_event.h> /* perf_sw_event */
+ #include <linux/hugetlb.h> /* hstate_index_to_shift */
#include <asm/traps.h> /* dotraplinkage, ... */
#include <asm/pgalloc.h> /* pgd_*(), ... */
static void
force_sig_info_fault(int si_signo, int si_code, unsigned long address,
- struct task_struct *tsk)
+ struct task_struct *tsk, int fault)
{
+ unsigned lsb = 0;
siginfo_t info;
info.si_signo = si_signo;
info.si_errno = 0;
info.si_code = si_code;
info.si_addr = (void __user *)address;
- info.si_addr_lsb = si_code == BUS_MCEERR_AR ? PAGE_SHIFT : 0;
+ if (fault & VM_FAULT_HWPOISON_LARGE)
+ lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+ if (fault & VM_FAULT_HWPOISON)
+ lsb = PAGE_SHIFT;
+ info.si_addr_lsb = lsb;
force_sig_info(si_signo, &info, tsk);
}
spin_lock_irqsave(&pgd_lock, flags);
list_for_each_entry(page, &pgd_list, lru) {
- if (!vmalloc_sync_one(page_address(page), address))
+ spinlock_t *pgt_lock;
+ pmd_t *ret;
+
+ pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
+
+ spin_lock(pgt_lock);
+ ret = vmalloc_sync_one(page_address(page), address);
+ spin_unlock(pgt_lock);
+
+ if (!ret)
break;
}
spin_unlock_irqrestore(&pgd_lock, flags);
if (!(address >= VMALLOC_START && address < VMALLOC_END))
return -1;
+ WARN_ON_ONCE(in_nmi());
+
/*
* Synchronize this task's top level page-table
* with the 'reference' page table.
void vmalloc_sync_all(void)
{
- unsigned long address;
-
- for (address = VMALLOC_START & PGDIR_MASK; address <= VMALLOC_END;
- address += PGDIR_SIZE) {
-
- const pgd_t *pgd_ref = pgd_offset_k(address);
- unsigned long flags;
- struct page *page;
-
- if (pgd_none(*pgd_ref))
- continue;
-
- spin_lock_irqsave(&pgd_lock, flags);
- list_for_each_entry(page, &pgd_list, lru) {
- pgd_t *pgd;
- pgd = (pgd_t *)page_address(page) + pgd_index(address);
- if (pgd_none(*pgd))
- set_pgd(pgd, *pgd_ref);
- else
- BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
- }
- spin_unlock_irqrestore(&pgd_lock, flags);
- }
+ sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
}
/*
if (!(address >= VMALLOC_START && address < VMALLOC_END))
return -1;
+ WARN_ON_ONCE(in_nmi());
+
/*
* Copy kernel mappings over when needed. This can also
* happen within a race in page table update. In the later
tsk->thread.error_code = error_code | (address >= TASK_SIZE);
tsk->thread.trap_no = 14;
- force_sig_info_fault(SIGSEGV, si_code, address, tsk);
+ force_sig_info_fault(SIGSEGV, si_code, address, tsk, 0);
return;
}
tsk->thread.trap_no = 14;
#ifdef CONFIG_MEMORY_FAILURE
- if (fault & VM_FAULT_HWPOISON) {
+ if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
printk(KERN_ERR
"MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n",
tsk->comm, tsk->pid, address);
code = BUS_MCEERR_AR;
}
#endif
- force_sig_info_fault(SIGBUS, code, address, tsk);
+ force_sig_info_fault(SIGBUS, code, address, tsk, fault);
}
static noinline void
if (fault & VM_FAULT_OOM) {
out_of_memory(regs, error_code, address);
} else {
- if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON))
+ if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
+ VM_FAULT_HWPOISON_LARGE))
do_sigbus(regs, error_code, address, fault);
else
BUG();
if (pmd_large(*pmd))
return spurious_fault_check(error_code, (pte_t *) pmd);
+ /*
+ * Note: don't use pte_present() here, since it returns true
+ * if the _PAGE_PROTNONE bit is set. However, this aliases the
+ * _PAGE_GLOBAL bit, which for kernel pages give false positives
+ * when CONFIG_DEBUG_PAGEALLOC is used.
+ */
pte = pte_offset_kernel(pmd, address);
- if (!pte_present(*pte))
+ if (!(pte_flags(*pte) & _PAGE_PRESENT))
return 0;
ret = spurious_fault_check(error_code, pte);
* Free Software Foundation.
*
* High level machine check handler. Handles pages reported by the
- * hardware as being corrupted usually due to a 2bit ECC memory or cache
+ * hardware as being corrupted usually due to a multi-bit ECC memory or cache
* failure.
+ *
+ * In addition there is a "soft offline" entry point that allows stop using
+ * not-yet-corrupted-by-suspicious pages without killing anything.
*
* Handles page cache pages in various states. The tricky part
- * here is that we can access any page asynchronous to other VM
- * users, because memory failures could happen anytime and anywhere,
- * possibly violating some of their assumptions. This is why this code
- * has to be extremely careful. Generally it tries to use normal locking
- * rules, as in get the standard locks, even if that means the
- * error handling takes potentially a long time.
- *
- * The operation to map back from RMAP chains to processes has to walk
- * the complete process list and has non linear complexity with the number
- * mappings. In short it can be quite slow. But since memory corruptions
- * are rare we hope to get away with this.
+ * here is that we can access any page asynchronously in respect to
+ * other VM users, because memory failures could happen anytime and
+ * anywhere. This could violate some of their assumptions. This is why
+ * this code has to be extremely careful. Generally it tries to use
+ * normal locking rules, as in get the standard locks, even if that means
+ * the error handling takes potentially a long time.
+ *
+ * There are several operations here with exponential complexity because
+ * of unsuitable VM data structures. For example the operation to map back
+ * from RMAP chains to processes has to walk the complete process list and
+ * has non linear complexity with the number. But since memory corruptions
+ * are rare we hope to get away with this. This avoids impacting the core
+ * VM.
*/
/*
* - kcore/oldmem/vmcore/mem/kmem check for hwpoison pages
* - pass bad pages to kdump next kernel
*/
-#define DEBUG 1 /* remove me in 2.6.34 */
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/page-flags.h>
return 0;
/*
- * page_mapping() does not accept slab page
+ * page_mapping() does not accept slab pages.
*/
if (PageSlab(p))
return -EINVAL;
struct list_head nd;
struct task_struct *tsk;
unsigned long addr;
- unsigned addr_valid:1;
+ char addr_valid;
};
/*
* a SIGKILL because the error is not contained anymore.
*/
if (tk->addr == -EFAULT) {
- pr_debug("MCE: Unable to find user space address %lx in %s\n",
+ pr_info("MCE: Unable to find user space address %lx in %s\n",
page_to_pfn(p), tsk->comm);
tk->addr_valid = 0;
}
pfn, err);
} else if (page_has_private(p) &&
!try_to_release_page(p, GFP_NOIO)) {
- pr_debug("MCE %#lx: failed to release buffers\n", pfn);
+ pr_info("MCE %#lx: failed to release buffers\n", pfn);
} else {
ret = RECOVERED;
}
* Issues:
* - 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)
{
+ int res = 0;
struct page *hpage = compound_head(p);
/*
* We can safely recover from error on free or reserved (i.e.
* so there is no race between isolation and mapping/unmapping.
*/
if (!(page_mapping(hpage) || PageAnon(hpage))) {
- __isolate_hwpoisoned_huge_page(hpage);
- return RECOVERED;
+ res = dequeue_hwpoisoned_huge_page(hpage);
+ if (!res)
+ return RECOVERED;
}
return DELAYED;
}
return (result == RECOVERED || result == DELAYED) ? 0 : -EBUSY;
}
-#define N_UNMAP_TRIES 5
-
/*
* Do all that is necessary to remove user space mappings. Unmap
* the pages and send SIGBUS to the processes if the data was dirty.
struct address_space *mapping;
LIST_HEAD(tokill);
int ret;
- int i;
int kill = 1;
struct page *hpage = compound_head(p);
if (kill)
collect_procs(hpage, &tokill);
- /*
- * try_to_unmap can fail temporarily due to races.
- * Try a few times (RED-PEN better strategy?)
- */
- for (i = 0; i < N_UNMAP_TRIES; i++) {
- ret = try_to_unmap(hpage, ttu);
- if (ret == SWAP_SUCCESS)
- break;
- pr_debug("MCE %#lx: try_to_unmap retry needed %d\n", pfn, ret);
- }
-
+ ret = try_to_unmap(hpage, ttu);
if (ret != SWAP_SUCCESS)
printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n",
pfn, page_mapcount(hpage));
* We need/can do nothing about count=0 pages.
* 1) it's a free page, and therefore in safe hand:
* prep_new_page() will be the gate keeper.
- * 2) it's part of a non-compound high order page.
+ * 2) it's a free hugepage, which is also safe:
+ * an affected hugepage will be dequeued from hugepage freelist,
+ * so there's no concern about reusing it ever after.
+ * 3) it's part of a non-compound high order page.
* Implies some kernel user: cannot stop them from
* R/W the page; let's pray that the page has been
* used and will be freed some time later.
if (is_free_buddy_page(p)) {
action_result(pfn, "free buddy", DELAYED);
return 0;
+ } else if (PageHuge(hpage)) {
+ /*
+ * Check "just unpoisoned", "filter hit", and
+ * "race with other subpage."
+ */
+ lock_page_nosync(hpage);
+ if (!PageHWPoison(hpage)
+ || (hwpoison_filter(p) && TestClearPageHWPoison(p))
+ || (p != hpage && TestSetPageHWPoison(hpage))) {
+ atomic_long_sub(nr_pages, &mce_bad_pages);
+ return 0;
+ }
+ set_page_hwpoison_huge_page(hpage);
+ res = dequeue_hwpoisoned_huge_page(hpage);
+ action_result(pfn, "free huge",
+ res ? IGNORED : DELAYED);
+ unlock_page(hpage);
+ return res;
} else {
action_result(pfn, "high order kernel", IGNORED);
return -EBUSY;
page = compound_head(p);
if (!PageHWPoison(p)) {
- pr_debug("MCE: Page was already unpoisoned %#lx\n", pfn);
+ pr_info("MCE: Page was already unpoisoned %#lx\n", pfn);
return 0;
}
nr_pages = 1 << compound_order(page);
if (!get_page_unless_zero(page)) {
+ /*
+ * Since HWPoisoned hugepage should have non-zero refcount,
+ * race between memory failure and unpoison seems to happen.
+ * In such case unpoison fails and memory failure runs
+ * to the end.
+ */
+ if (PageHuge(page)) {
+ pr_debug("MCE: Memory failure is now running on free hugepage %#lx\n", pfn);
+ return 0;
+ }
if (TestClearPageHWPoison(p))
atomic_long_sub(nr_pages, &mce_bad_pages);
- pr_debug("MCE: Software-unpoisoned free page %#lx\n", pfn);
+ pr_info("MCE: Software-unpoisoned free page %#lx\n", pfn);
return 0;
}
* the free buddy page pool.
*/
if (TestClearPageHWPoison(page)) {
- pr_debug("MCE: Software-unpoisoned page %#lx\n", pfn);
+ pr_info("MCE: Software-unpoisoned page %#lx\n", pfn);
atomic_long_sub(nr_pages, &mce_bad_pages);
freeit = 1;
+ if (PageHuge(page))
+ clear_page_hwpoison_huge_page(page);
}
- if (PageHuge(p))
- clear_page_hwpoison_huge_page(page);
unlock_page(page);
put_page(page);
static struct page *new_page(struct page *p, unsigned long private, int **x)
{
int nid = page_to_nid(p);
- return alloc_pages_exact_node(nid, GFP_HIGHUSER_MOVABLE, 0);
+ if (PageHuge(p))
+ return alloc_huge_page_node(page_hstate(compound_head(p)),
+ nid);
+ else
+ return alloc_pages_exact_node(nid, GFP_HIGHUSER_MOVABLE, 0);
}
/*
* was free.
*/
set_migratetype_isolate(p);
+ /*
+ * When the target page is a free hugepage, just remove it
+ * from free hugepage list.
+ */
if (!get_page_unless_zero(compound_head(p))) {
- if (is_free_buddy_page(p)) {
+ if (PageHuge(p)) {
- pr_debug("get_any_page: %#lx free huge page\n", pfn);
++ pr_info("get_any_page: %#lx free huge page\n", pfn);
+ ret = dequeue_hwpoisoned_huge_page(compound_head(p));
+ } else if (is_free_buddy_page(p)) {
- pr_debug("get_any_page: %#lx free buddy page\n", pfn);
+ pr_info("get_any_page: %#lx free buddy page\n", pfn);
/* Set hwpoison bit while page is still isolated */
SetPageHWPoison(p);
ret = 0;
} else {
- pr_debug("get_any_page: %#lx: unknown zero refcount page type %lx\n",
+ pr_info("get_any_page: %#lx: unknown zero refcount page type %lx\n",
pfn, p->flags);
ret = -EIO;
}
return ret;
}
+ static int soft_offline_huge_page(struct page *page, int flags)
+ {
+ int ret;
+ unsigned long pfn = page_to_pfn(page);
+ struct page *hpage = compound_head(page);
+ LIST_HEAD(pagelist);
+
+ ret = get_any_page(page, pfn, flags);
+ if (ret < 0)
+ return ret;
+ if (ret == 0)
+ goto done;
+
+ if (PageHWPoison(hpage)) {
+ put_page(hpage);
+ pr_debug("soft offline: %#lx hugepage already poisoned\n", pfn);
+ return -EBUSY;
+ }
+
+ /* Keep page count to indicate a given hugepage is isolated. */
+
+ list_add(&hpage->lru, &pagelist);
+ ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0);
+ if (ret) {
+ pr_debug("soft offline: %#lx: migration failed %d, type %lx\n",
+ pfn, ret, page->flags);
+ if (ret > 0)
+ ret = -EIO;
+ return ret;
+ }
+ done:
+ if (!PageHWPoison(hpage))
+ atomic_long_add(1 << compound_order(hpage), &mce_bad_pages);
+ set_page_hwpoison_huge_page(hpage);
+ dequeue_hwpoisoned_huge_page(hpage);
+ /* keep elevated page count for bad page */
+ return ret;
+ }
+
/**
* soft_offline_page - Soft offline a page.
* @page: page to offline
int ret;
unsigned long pfn = page_to_pfn(page);
+ if (PageHuge(page))
+ return soft_offline_huge_page(page, flags);
+
ret = get_any_page(page, pfn, flags);
if (ret < 0)
return ret;
goto done;
}
if (!PageLRU(page)) {
- pr_debug("soft_offline: %#lx: unknown non LRU page type %lx\n",
+ pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n",
pfn, page->flags);
return -EIO;
}
if (PageHWPoison(page)) {
unlock_page(page);
put_page(page);
- pr_debug("soft offline: %#lx page already poisoned\n", pfn);
+ pr_info("soft offline: %#lx page already poisoned\n", pfn);
return -EBUSY;
}
put_page(page);
if (ret == 1) {
ret = 0;
- pr_debug("soft_offline: %#lx: invalidated\n", pfn);
+ pr_info("soft_offline: %#lx: invalidated\n", pfn);
goto done;
}
list_add(&page->lru, &pagelist);
ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0);
if (ret) {
- pr_debug("soft offline: %#lx: migration failed %d, type %lx\n",
+ pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
pfn, ret, page->flags);
if (ret > 0)
ret = -EIO;
}
} else {
- pr_debug("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n",
+ pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n",
pfn, ret, page_count(page), page->flags);
}
if (ret)
git.openpandora.org / pandora-kernel.git / commitdiff