mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Tony Luck <tony.luck@intel.com>
To: linux-kernel@vger.kernel.org
Cc: Ingo Molnar <mingo@elte.hu>, Borislav Petkov <bp@amd64.org>,
	Chen Gong <gong.chen@linux.intel.com>,
	"Huang, Ying" <ying.huang@intel.com>,
	Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Subject: [PATCH 2/6] HWPOISON: Add code to handle "action required" errors.
Date: Tue, 13 Dec 2011 09:27:58 -0800	[thread overview]
Message-ID: <f047b536da2126d7ca3d5670d2e67141ea4feeb2.1323979146.git.tony.luck@intel.com> (raw)
In-Reply-To: <cover.1323979146.git.tony.luck@intel.com>

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@amd64.org>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 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


  parent reply	other threads:[~2011-12-15 21:18 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-12-15 19:59 [PATCH 0/6] x86, mce: machine check recovery for applications [updated] Tony Luck
2011-12-08 22:49 ` [PATCH 6/6] x86, mce: Recognise machine check bank signature for data path error Tony Luck
2011-12-13 17:27 ` Tony Luck [this message]
2011-12-13 17:48 ` [PATCH 3/6] x86, mce: create helper function to save addr/misc when needed Tony Luck
2011-12-14 23:55 ` [PATCH 4/6] x86, mce: Add mechanism to safely save information in MCE handler Tony Luck
2011-12-16  0:13   ` Hidetoshi Seto
2011-12-16  8:14   ` Borislav Petkov
2011-12-15 18:48 ` [PATCH 1/6] HWPOISON: clean up memory_failure() vs. __memory_failure() Tony Luck
2011-12-16  8:17   ` Borislav Petkov
2011-12-15 19:02 ` [PATCH 5/6] x86, mce: handle "action required" errors Tony Luck
2011-12-16  0:14   ` Hidetoshi Seto
2011-12-16  0:29     ` Tony Luck
2011-12-16  0:22       ` [PATCH 5/6] x86, mce: handle "action required" errors (unjumbled version) Tony Luck
2011-12-16 16:35         ` Borislav Petkov
2011-12-17 19:25           ` Tony Luck
2011-12-16  0:51     ` [PATCH 5/6] x86, mce: handle "action required" errors Tony Luck
2011-12-16 23:36       ` [PATCH 5/6] x86, mce: handle "action required" errors (new version) Tony Luck
  -- strict thread matches above, loose matches on Subject: below --
2012-01-03 19:49 [PATCH 0/6] x86, mce: machine check recovery for applications Tony Luck
2011-12-13 17:27 ` [PATCH 2/6] HWPOISON: Add code to handle "action required" errors Tony Luck
2011-12-13 19:05 [PATCH 0/6] x86, mce: machine check recovery for applications Tony Luck
2011-12-13 17:27 ` [PATCH 2/6] HWPOISON: Add code to handle "action required" errors Tony Luck

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=f047b536da2126d7ca3d5670d2e67141ea4feeb2.1323979146.git.tony.luck@intel.com \
    --to=tony.luck@intel.com \
    --cc=bp@amd64.org \
    --cc=gong.chen@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=seto.hidetoshi@jp.fujitsu.com \
    --cc=ying.huang@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®