aboutsummaryrefslogtreecommitdiff
path: root/mm/memory-failure.c
diff options
context:
space:
mode:
authorIngo Molnar <mingo@elte.hu>2012-01-26 11:40:13 +0100
committerIngo Molnar <mingo@elte.hu>2012-01-26 11:40:13 +0100
commit4e9f44ba29f20484615a461244bfd3a419391490 (patch)
tree490dd38bb8d14765327cee0be2f9731254e9c402 /mm/memory-failure.c
parent87f71ae2dd7471c1b4c94100be1f218e91dc64c3 (diff)
parent5f7b88d51e89771f64c15903b96b5933dd0bc6d8 (diff)
Merge tag 'mce-recovery-for-tip' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras into x86/mce
Implement MCE recovery for the data load error path and assorted cleanups. Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'mm/memory-failure.c')
-rw-r--r--mm/memory-failure.c96
1 files changed, 50 insertions, 46 deletions
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 56080ea3614..0f6033b01ff 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -187,33 +187,40 @@ int hwpoison_filter(struct page *p)
EXPORT_SYMBOL_GPL(hwpoison_filter);
/*
- * Send all the processes who have the page mapped an ``action optional''
- * signal.
+ * Send all the processes who have the page mapped a signal.
+ * ``action optional'' if they are not immediately affected by the error
+ * ``action required'' if error happened in current execution context
*/
-static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno,
- unsigned long pfn, struct page *page)
+static int kill_proc(struct task_struct *t, unsigned long addr, int trapno,
+ unsigned long pfn, struct page *page, int flags)
{
struct siginfo si;
int ret;
printk(KERN_ERR
- "MCE %#lx: Killing %s:%d early due to hardware memory corruption\n",
+ "MCE %#lx: Killing %s:%d due to hardware memory corruption\n",
pfn, t->comm, t->pid);
si.si_signo = SIGBUS;
si.si_errno = 0;
- si.si_code = BUS_MCEERR_AO;
si.si_addr = (void *)addr;
#ifdef __ARCH_SI_TRAPNO
si.si_trapno = trapno;
#endif
si.si_addr_lsb = compound_trans_order(compound_head(page)) + PAGE_SHIFT;
- /*
- * Don't use force here, it's convenient if the signal
- * can be temporarily blocked.
- * This could cause a loop when the user sets SIGBUS
- * to SIG_IGN, but hopefully no one will do that?
- */
- ret = send_sig_info(SIGBUS, &si, t); /* synchronous? */
+
+ if ((flags & MF_ACTION_REQUIRED) && t == current) {
+ si.si_code = BUS_MCEERR_AR;
+ ret = force_sig_info(SIGBUS, &si, t);
+ } else {
+ /*
+ * Don't use force here, it's convenient if the signal
+ * can be temporarily blocked.
+ * This could cause a loop when the user sets SIGBUS
+ * to SIG_IGN, but hopefully no one will do that?
+ */
+ si.si_code = BUS_MCEERR_AO;
+ ret = send_sig_info(SIGBUS, &si, t); /* synchronous? */
+ }
if (ret < 0)
printk(KERN_INFO "MCE: Error sending signal to %s:%d: %d\n",
t->comm, t->pid, ret);
@@ -338,8 +345,9 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
* Also when FAIL is set do a force kill because something went
* wrong earlier.
*/
-static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno,
- int fail, struct page *page, unsigned long pfn)
+static void kill_procs(struct list_head *to_kill, int doit, int trapno,
+ int fail, struct page *page, unsigned long pfn,
+ int flags)
{
struct to_kill *tk, *next;
@@ -363,8 +371,8 @@ static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno,
* check for that, but we need to tell the
* process anyways.
*/
- else if (kill_proc_ao(tk->tsk, tk->addr, trapno,
- pfn, page) < 0)
+ else if (kill_proc(tk->tsk, tk->addr, trapno,
+ pfn, page, flags) < 0)
printk(KERN_ERR
"MCE %#lx: Cannot send advisory machine check signal to %s:%d\n",
pfn, tk->tsk->comm, tk->tsk->pid);
@@ -844,7 +852,7 @@ static int page_action(struct page_state *ps, struct page *p,
* the pages and send SIGBUS to the processes if the data was dirty.
*/
static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
- int trapno)
+ int trapno, int flags)
{
enum ttu_flags ttu = TTU_UNMAP | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
struct address_space *mapping;
@@ -962,8 +970,8 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
* use a more force-full uncatchable kill to prevent
* any accesses to the poisoned memory.
*/
- kill_procs_ao(&tokill, !!PageDirty(ppage), trapno,
- ret != SWAP_SUCCESS, p, pfn);
+ kill_procs(&tokill, !!PageDirty(ppage), trapno,
+ ret != SWAP_SUCCESS, p, pfn, flags);
return ret;
}
@@ -984,7 +992,25 @@ static void clear_page_hwpoison_huge_page(struct page *hpage)
ClearPageHWPoison(hpage + i);
}
-int __memory_failure(unsigned long pfn, int trapno, int flags)
+/**
+ * memory_failure - Handle memory failure of a page.
+ * @pfn: Page Number of the corrupted page
+ * @trapno: Trap number reported in the signal to user space.
+ * @flags: fine tune action taken
+ *
+ * This function is called by the low level machine check code
+ * of an architecture when it detects hardware memory corruption
+ * of a page. It tries its best to recover, which includes
+ * dropping pages, killing processes etc.
+ *
+ * The function is primarily of use for corruptions that
+ * happen outside the current execution context (e.g. when
+ * detected by a background scrubber)
+ *
+ * Must run in process context (e.g. a work queue) with interrupts
+ * enabled and no spinlocks hold.
+ */
+int memory_failure(unsigned long pfn, int trapno, int flags)
{
struct page_state *ps;
struct page *p;
@@ -1130,7 +1156,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
* Now take care of user space mappings.
* Abort on fail: __delete_from_page_cache() assumes unmapped page.
*/
- if (hwpoison_user_mappings(p, pfn, trapno) != SWAP_SUCCESS) {
+ if (hwpoison_user_mappings(p, pfn, trapno, flags) != SWAP_SUCCESS) {
printk(KERN_ERR "MCE %#lx: cannot unmap page, give up\n", pfn);
res = -EBUSY;
goto out;
@@ -1156,29 +1182,7 @@ out:
unlock_page(hpage);
return res;
}
-EXPORT_SYMBOL_GPL(__memory_failure);
-
-/**
- * memory_failure - Handle memory failure of a page.
- * @pfn: Page Number of the corrupted page
- * @trapno: Trap number reported in the signal to user space.
- *
- * This function is called by the low level machine check code
- * of an architecture when it detects hardware memory corruption
- * of a page. It tries its best to recover, which includes
- * dropping pages, killing processes etc.
- *
- * The function is primarily of use for corruptions that
- * happen outside the current execution context (e.g. when
- * detected by a background scrubber)
- *
- * Must run in process context (e.g. a work queue) with interrupts
- * enabled and no spinlocks hold.
- */
-void memory_failure(unsigned long pfn, int trapno)
-{
- __memory_failure(pfn, trapno, 0);
-}
+EXPORT_SYMBOL_GPL(memory_failure);
#define MEMORY_FAILURE_FIFO_ORDER 4
#define MEMORY_FAILURE_FIFO_SIZE (1 << MEMORY_FAILURE_FIFO_ORDER)
@@ -1251,7 +1255,7 @@ static void memory_failure_work_func(struct work_struct *work)
spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
if (!gotten)
break;
- __memory_failure(entry.pfn, entry.trapno, entry.flags);
+ memory_failure(entry.pfn, entry.trapno, entry.flags);
}
}