linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Jane Chu <jane.chu@oracle.com>
To: linmiaohe@huawei.com, nao.horiguchi@gmail.com,
	akpm@linux-foundation.org, osalvador@suse.de, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH v3 3/5] mm/memory-failure: improve memory failure action_result messages
Date: Tue, 21 May 2024 17:54:27 -0600	[thread overview]
Message-ID: <20240521235429.2368017-4-jane.chu@oracle.com> (raw)
In-Reply-To: <20240521235429.2368017-1-jane.chu@oracle.com>

Added two explicit MF_MSG messages describing failure in get_hwpoison_page.
Attemped to document the definition of various action names, and made a few
adjustment to the action_result() calls.

Signed-off-by: Jane Chu <jane.chu@oracle.com>
---
 include/linux/mm.h      |  2 ++
 include/ras/ras_event.h |  2 ++
 mm/memory-failure.c     | 38 +++++++++++++++++++++++++++++++++-----
 3 files changed, 37 insertions(+), 5 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9849dfda44d4..b4598c6a393a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -4111,6 +4111,7 @@ enum mf_action_page_type {
 	MF_MSG_DIFFERENT_COMPOUND,
 	MF_MSG_HUGE,
 	MF_MSG_FREE_HUGE,
+	MF_MSG_GET_HWPOISON,
 	MF_MSG_UNMAP_FAILED,
 	MF_MSG_DIRTY_SWAPCACHE,
 	MF_MSG_CLEAN_SWAPCACHE,
@@ -4124,6 +4125,7 @@ enum mf_action_page_type {
 	MF_MSG_BUDDY,
 	MF_MSG_DAX,
 	MF_MSG_UNSPLIT_THP,
+	MF_MSG_ALREADY_POISONED,
 	MF_MSG_UNKNOWN,
 };
 
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index c011ea236e9b..b3f6832a94fe 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -360,6 +360,7 @@ TRACE_EVENT(aer_event,
 	EM ( MF_MSG_DIFFERENT_COMPOUND, "different compound page after locking" ) \
 	EM ( MF_MSG_HUGE, "huge page" )					\
 	EM ( MF_MSG_FREE_HUGE, "free huge page" )			\
+	EM ( MF_MSG_GET_HWPOISON, "get hwpoison page" )			\
 	EM ( MF_MSG_UNMAP_FAILED, "unmapping failed page" )		\
 	EM ( MF_MSG_DIRTY_SWAPCACHE, "dirty swapcache page" )		\
 	EM ( MF_MSG_CLEAN_SWAPCACHE, "clean swapcache page" )		\
@@ -373,6 +374,7 @@ TRACE_EVENT(aer_event,
 	EM ( MF_MSG_BUDDY, "free buddy page" )				\
 	EM ( MF_MSG_DAX, "dax page" )					\
 	EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" )			\
+	EM ( MF_MSG_ALREADY_POISONED, "already poisoned" )		\
 	EMe ( MF_MSG_UNKNOWN, "unknown page" )
 
 /*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 739311e121af..1e22d73c9329 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -879,6 +879,28 @@ static int kill_accessing_process(struct task_struct *p, unsigned long pfn,
 	return ret > 0 ? -EHWPOISON : -EFAULT;
 }
 
+/*
+ * MF_IGNORED - The m-f() handler marks the page as PG_hwpoisoned'ed.
+ * But it could not do more to isolate the page from being accessed again,
+ * nor does it kill the process. This is extremely rare and one of the
+ * potential causes is that the page state has been changed due to
+ * underlying race condition. This is the most severe outcomes.
+ *
+ * MF_FAILED - The m-f() handler marks the page as PG_hwpoisoned'ed. It
+ * should have killed the process, but it can't isolate the page, due to
+ * conditions such as extra pin, unmap failure, etc. Accessing the page
+ * again will trigger another MCE and the process will be killed by the
+ * m-f() handler immediately.
+ *
+ * MF_DELAYED - The m-f() handler marks the page as PG_hwpoisoned'ed. The
+ * page is unmapped, but perhaps remains in LRU or file mapping. An attempt
+ * to access the page again will trigger page fault and the PF handler
+ * will kill the process.
+ *
+ * MF_RECOVERED - The m-f() handler marks the page as PG_hwpoisoned'ed.
+ * The page has been completely isolated, that is, unmapped, taken out of
+ * the buddy system, or hole-punnched out of the file mapping.
+ */
 static const char *action_name[] = {
 	[MF_IGNORED] = "Ignored",
 	[MF_FAILED] = "Failed",
@@ -893,6 +915,7 @@ static const char * const action_page_types[] = {
 	[MF_MSG_DIFFERENT_COMPOUND]	= "different compound page after locking",
 	[MF_MSG_HUGE]			= "huge page",
 	[MF_MSG_FREE_HUGE]		= "free huge page",
+	[MF_MSG_GET_HWPOISON]		= "get hwpoison page",
 	[MF_MSG_UNMAP_FAILED]		= "unmapping failed page",
 	[MF_MSG_DIRTY_SWAPCACHE]	= "dirty swapcache page",
 	[MF_MSG_CLEAN_SWAPCACHE]	= "clean swapcache page",
@@ -906,6 +929,7 @@ static const char * const action_page_types[] = {
 	[MF_MSG_BUDDY]			= "free buddy page",
 	[MF_MSG_DAX]			= "dax page",
 	[MF_MSG_UNSPLIT_THP]		= "unsplit thp",
+	[MF_MSG_ALREADY_POISONED]	= "already poisoned",
 	[MF_MSG_UNKNOWN]		= "unknown page",
 };
 
@@ -1013,12 +1037,13 @@ static int me_kernel(struct page_state *ps, struct page *p)
 
 /*
  * Page in unknown state. Do nothing.
+ * This is a catch-all in case we fail to make sense of the page state.
  */
 static int me_unknown(struct page_state *ps, struct page *p)
 {
 	pr_err("%#lx: Unknown page state\n", page_to_pfn(p));
 	unlock_page(p);
-	return MF_FAILED;
+	return MF_IGNORED;
 }
 
 /*
@@ -2055,6 +2080,8 @@ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb
 		if (flags & MF_ACTION_REQUIRED) {
 			folio = page_folio(p);
 			res = kill_accessing_process(current, folio_pfn(folio), flags);
+			action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED);
+			return res;
 		}
 		return res;
 	} else if (res == -EBUSY) {
@@ -2062,7 +2089,7 @@ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb
 			flags |= MF_NO_RETRY;
 			goto retry;
 		}
-		return action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED);
+		return action_result(pfn, MF_MSG_GET_HWPOISON, MF_IGNORED);
 	}
 
 	folio = page_folio(p);
@@ -2097,7 +2124,7 @@ static int try_memory_failure_hugetlb(unsigned long pfn, int flags, int *hugetlb
 
 	if (!hwpoison_user_mappings(folio, p, pfn, flags)) {
 		folio_unlock(folio);
-		return action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
+		return action_result(pfn, MF_MSG_UNMAP_FAILED, MF_FAILED);
 	}
 
 	return identify_page_state(pfn, p, page_flags);
@@ -2231,6 +2258,7 @@ int memory_failure(unsigned long pfn, int flags)
 			res = kill_accessing_process(current, pfn, flags);
 		if (flags & MF_COUNT_INCREASED)
 			put_page(p);
+		action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED);
 		goto unlock_mutex;
 	}
 
@@ -2267,7 +2295,7 @@ int memory_failure(unsigned long pfn, int flags)
 			}
 			goto unlock_mutex;
 		} else if (res < 0) {
-			res = action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED);
+			res = action_result(pfn, MF_MSG_GET_HWPOISON, MF_IGNORED);
 			goto unlock_mutex;
 		}
 	}
@@ -2363,7 +2391,7 @@ int memory_failure(unsigned long pfn, int flags)
 	 * Abort on fail: __filemap_remove_folio() assumes unmapped page.
 	 */
 	if (!hwpoison_user_mappings(folio, p, pfn, flags)) {
-		res = action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
+		res = action_result(pfn, MF_MSG_UNMAP_FAILED, MF_FAILED);
 		goto unlock_page;
 	}
 
-- 
2.39.3



  parent reply	other threads:[~2024-05-21 23:55 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-05-21 23:54 [PATCH v3 0/5] Enhance soft hwpoison handling and injection Jane Chu
2024-05-21 23:54 ` [PATCH v3 1/5] mm/memory-failure: try to send SIGBUS even if unmap failed Jane Chu
2024-05-21 23:54 ` [PATCH v3 2/5] mm/madvise: Add MF_ACTION_REQUIRED to madvise(MADV_HWPOISON) Jane Chu
2024-05-23  1:54   ` Miaohe Lin
2024-05-21 23:54 ` Jane Chu [this message]
2024-05-22 20:37   ` [PATCH v3 3/5] mm/memory-failure: improve memory failure action_result messages Oscar Salvador
2024-05-23 17:38     ` Jane Chu
2024-05-23  2:31   ` Miaohe Lin
2024-05-23 19:58     ` Jane Chu
2024-05-21 23:54 ` [PATCH v3 4/5] mm/memory-failure: move hwpoison_filter() higher up Jane Chu
2024-05-22 20:50   ` Oscar Salvador
2024-05-23  2:37   ` Miaohe Lin
2024-05-21 23:54 ` [PATCH v3 5/5] mm/memory-failure: send SIGBUS in the event of thp split fail Jane Chu
2024-05-22 20:57   ` Oscar Salvador
2024-05-23  3:02   ` Miaohe Lin
2024-05-23 20:01     ` Jane Chu

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=20240521235429.2368017-4-jane.chu@oracle.com \
    --to=jane.chu@oracle.com \
    --cc=akpm@linux-foundation.org \
    --cc=linmiaohe@huawei.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=nao.horiguchi@gmail.com \
    --cc=osalvador@suse.de \
    /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