[PATCH 2/6] HWPOISON: Add code to handle "action required" errors.

From: Tony Luck
Date: Thu Dec 15 2011 - 16:17:59 EST


Add new flag bit "MF_ACTION_REQUIRED" to be used by machine check
code to force a signal with si_code = BUS_MCEERR_AR in the case
where the error occurs in processor execution context. Pass the
flags argument along call chain:
memory_failure()
hwpoison_user_mappings()
kill_procs()
kill_proc()

Drop the "_ao" suffix from kill_procs_ao() and kill_proc_ao() since
they can now handle "action required" as well as "action optional" errors.

Acked-by: Borislav Petkov <bp@xxxxxxxxx>
Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
---
include/linux/mm.h | 1 +
mm/memory-failure.c | 50 +++++++++++++++++++++++++++++---------------------
2 files changed, 30 insertions(+), 21 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index bcc5234..bf169ca 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1606,6 +1606,7 @@ void vmemmap_populate_print_last(void);

enum mf_flags {
MF_COUNT_INCREASED = 1 << 0,
+ MF_ACTION_REQUIRED = 1 << 1,
};
extern int memory_failure(unsigned long pfn, int trapno, int flags);
extern void memory_failure_queue(unsigned long pfn, int trapno, int flags);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index ab259bb..95fd307 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;
}
@@ -1148,7 +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;
--
1.7.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/