[PATCH v2 3/5] mm/memory-failure: improve memory failure action_result messages

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



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@xxxxxxxxxx>
---
 include/linux/mm.h      |  2 ++
 include/ras/ras_event.h |  2 ++
 mm/memory-failure.c     | 28 +++++++++++++++++++++++-----
 3 files changed, 27 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..62133c10fb51 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -879,6 +879,20 @@ static int kill_accessing_process(struct task_struct *p, unsigned long pfn,
 	return ret > 0 ? -EHWPOISON : -EFAULT;
 }
 
+/*
+ * MF_IGNORED - Either the m-f() handler did nothing to recover, or it did
+ *   something, then caught in a race condition which renders the effort sort
+ *   of moot. This is perhaps the most sever.
+ * MF_FAILED - The m-f() handler might have killed the process, but it can't
+ *   do much to the poisoned page other than marking it poisoned, due to
+ *   conditions such as extra pin, unmap failure, etc.
+ * MF_DELAYED - The poisoned page has been unmapped but not completely isolated,
+ *   such as page might remain in LRU. But an attempt by userspace process
+ *   to access the page again will hit page fault which will kill the process.
+ * MF_RECOVERED - The poisoned page has been completely isolated, via unmap,
+ *   taking the page out of the buddy system, or hole punching out of the
+ *   mapping.
+ */
 static const char *action_name[] = {
 	[MF_IGNORED] = "Ignored",
 	[MF_FAILED] = "Failed",
@@ -893,6 +907,7 @@ 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 +921,7 @@ 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",
 };
 
@@ -1018,7 +1034,7 @@ 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 +2071,7 @@ 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);
+			return action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED);
 		}
 		return res;
 	} else if (res == -EBUSY) {
@@ -2062,7 +2079,7 @@ 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 +2114,7 @@ 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 +2248,7 @@ 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 +2285,7 @@ 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 +2381,7 @@ 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





[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux OMAP]     [Linux MIPS]     [eCos]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux