mm/page_ref: add tracepoint to track down page reference manipulation

CMA allocation should be guaranteed to succeed by definition, but,
unfortunately, it would be failed sometimes.  It is hard to track down
the problem, because it is related to page reference manipulation and we
don't have any facility to analyze it.

This patch adds tracepoints to track down page reference manipulation.
With it, we can find exact reason of failure and can fix the problem.
Following is an example of tracepoint output.  (note: this example is
stale version that printing flags as the number.  Recent version will
print it as human readable string.)

<...>-9018  [004]    92.678375: page_ref_set:         pfn=0x17ac9 flags=0x0 count=1 mapcount=0 mapping=(nil) mt=4 val=1
<...>-9018  [004]    92.678378: kernel_stack:
 => get_page_from_freelist (ffffffff81176659)
 => __alloc_pages_nodemask (ffffffff81176d22)
 => alloc_pages_vma (ffffffff811bf675)
 => handle_mm_fault (ffffffff8119e693)
 => __do_page_fault (ffffffff810631ea)
 => trace_do_page_fault (ffffffff81063543)
 => do_async_page_fault (ffffffff8105c40a)
 => async_page_fault (ffffffff817581d8)
[snip]
<...>-9018  [004]    92.678379: page_ref_mod:         pfn=0x17ac9 flags=0x40048 count=2 mapcount=1 mapping=0xffff880015a78dc1 mt=4 val=1
[snip]
...
...
<...>-9131  [001]    93.174468: test_pages_isolated:  start_pfn=0x17800 end_pfn=0x17c00 fin_pfn=0x17ac9 ret=fail
[snip]
<...>-9018  [004]    93.174843: page_ref_mod_and_test: pfn=0x17ac9 flags=0x40068 count=0 mapcount=0 mapping=0xffff880015a78dc1 mt=4 val=-1 ret=1
 => release_pages (ffffffff8117c9e4)
 => free_pages_and_swap_cache (ffffffff811b0697)
 => tlb_flush_mmu_free (ffffffff81199616)
 => tlb_finish_mmu (ffffffff8119a62c)
 => exit_mmap (ffffffff811a53f7)
 => mmput (ffffffff81073f47)
 => do_exit (ffffffff810794e9)
 => do_group_exit (ffffffff81079def)
 => SyS_exit_group (ffffffff81079e74)
 => entry_SYSCALL_64_fastpath (ffffffff817560b6)

This output shows that problem comes from exit path.  In exit path, to
improve performance, pages are not freed immediately.  They are gathered
and processed by batch.  During this process, migration cannot be
possible and CMA allocation is failed.  This problem is hard to find
without this page reference tracepoint facility.

Enabling this feature bloat kernel text 30 KB in my configuration.

   text    data     bss     dec     hex filename
12127327        2243616 1507328 15878271         f2487f vmlinux_disabled
12157208        2258880 1507328 15923416         f2f8d8 vmlinux_enabled

Note that, due to header file dependency problem between mm.h and
tracepoint.h, this feature has to open code the static key functions for
tracepoints.  Proposed by Steven Rostedt in following link.

https://lkml.org/lkml/2015/12/9/699

[arnd@arndb.de: crypto/async_pq: use __free_page() instead of put_page()]
[iamjoonsoo.kim@lge.com: fix build failure for xtensa]
[akpm@linux-foundation.org: tweak Kconfig text, per Vlastimil]
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Michal Nazarewicz <mina86@mina86.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
index c0748bbd4c083b47f78c662cdd7cb490590a2587..08b3ac68952b19fba6e4ab747744ca3317f0de9d 100644 (file)
--- a/crypto/async_tx/async_pq.c
+++ b/crypto/async_tx/async_pq.c
@@ -444,7 +444,7 @@ static int __init async_pq_init(void)
 
 static void __exit async_pq_exit(void)
 {
-       put_page(pq_scribble_page);
+       __free_page(pq_scribble_page);
 }
 
 module_init(async_pq_init);

diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h
index 30f5817f6b8ee0af2e6ca71eb594ad1cdae0844d..e596d5d9540e2b534d6ad1fb09a1e1d68274fdf4 100644 (file)
--- a/include/linux/page_ref.h
+++ b/include/linux/page_ref.h
@@ -4,6 +4,62 @@
 #include <linux/atomic.h>
 #include <linux/mm_types.h>
 #include <linux/page-flags.h>
+#include <linux/tracepoint-defs.h>
+
+extern struct tracepoint __tracepoint_page_ref_set;
+extern struct tracepoint __tracepoint_page_ref_mod;
+extern struct tracepoint __tracepoint_page_ref_mod_and_test;
+extern struct tracepoint __tracepoint_page_ref_mod_and_return;
+extern struct tracepoint __tracepoint_page_ref_mod_unless;
+extern struct tracepoint __tracepoint_page_ref_freeze;
+extern struct tracepoint __tracepoint_page_ref_unfreeze;
+
+#ifdef CONFIG_DEBUG_PAGE_REF
+
+/*
+ * Ideally we would want to use the trace_<tracepoint>_enabled() helper
+ * functions. But due to include header file issues, that is not
+ * feasible. Instead we have to open code the static key functions.
+ *
+ * See trace_##name##_enabled(void) in include/linux/tracepoint.h
+ */
+#define page_ref_tracepoint_active(t) static_key_false(&(t).key)
+
+extern void __page_ref_set(struct page *page, int v);
+extern void __page_ref_mod(struct page *page, int v);
+extern void __page_ref_mod_and_test(struct page *page, int v, int ret);
+extern void __page_ref_mod_and_return(struct page *page, int v, int ret);
+extern void __page_ref_mod_unless(struct page *page, int v, int u);
+extern void __page_ref_freeze(struct page *page, int v, int ret);
+extern void __page_ref_unfreeze(struct page *page, int v);
+
+#else
+
+#define page_ref_tracepoint_active(t) false
+
+static inline void __page_ref_set(struct page *page, int v)
+{
+}
+static inline void __page_ref_mod(struct page *page, int v)
+{
+}
+static inline void __page_ref_mod_and_test(struct page *page, int v, int ret)
+{
+}
+static inline void __page_ref_mod_and_return(struct page *page, int v, int ret)
+{
+}
+static inline void __page_ref_mod_unless(struct page *page, int v, int u)
+{
+}
+static inline void __page_ref_freeze(struct page *page, int v, int ret)
+{
+}
+static inline void __page_ref_unfreeze(struct page *page, int v)
+{
+}
+
+#endif
 
 static inline int page_ref_count(struct page *page)
 {
@@ -18,6 +74,8 @@ static inline int page_count(struct page *page)
 static inline void set_page_count(struct page *page, int v)
 {
        atomic_set(&page->_count, v);
+       if (page_ref_tracepoint_active(__tracepoint_page_ref_set))
+               __page_ref_set(page, v);
 }
 
 /*
@@ -32,46 +90,74 @@ static inline void init_page_count(struct page *page)
 static inline void page_ref_add(struct page *page, int nr)
 {
        atomic_add(nr, &page->_count);
+       if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+               __page_ref_mod(page, nr);
 }
 
 static inline void page_ref_sub(struct page *page, int nr)
 {
        atomic_sub(nr, &page->_count);
+       if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+               __page_ref_mod(page, -nr);
 }
 
 static inline void page_ref_inc(struct page *page)
 {
        atomic_inc(&page->_count);
+       if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+               __page_ref_mod(page, 1);
 }
 
 static inline void page_ref_dec(struct page *page)
 {
        atomic_dec(&page->_count);
+       if (page_ref_tracepoint_active(__tracepoint_page_ref_mod))
+               __page_ref_mod(page, -1);
 }
 
 static inline int page_ref_sub_and_test(struct page *page, int nr)
 {
-       return atomic_sub_and_test(nr, &page->_count);
+       int ret = atomic_sub_and_test(nr, &page->_count);
+
+       if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test))
+               __page_ref_mod_and_test(page, -nr, ret);
+       return ret;
 }
 
 static inline int page_ref_dec_and_test(struct page *page)
 {
-       return atomic_dec_and_test(&page->_count);
+       int ret = atomic_dec_and_test(&page->_count);
+
+       if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test))
+               __page_ref_mod_and_test(page, -1, ret);
+       return ret;
 }
 
 static inline int page_ref_dec_return(struct page *page)
 {
-       return atomic_dec_return(&page->_count);
+       int ret = atomic_dec_return(&page->_count);
+
+       if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return))
+               __page_ref_mod_and_return(page, -1, ret);
+       return ret;
 }
 
 static inline int page_ref_add_unless(struct page *page, int nr, int u)
 {
-       return atomic_add_unless(&page->_count, nr, u);
+       int ret = atomic_add_unless(&page->_count, nr, u);
+
+       if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_unless))
+               __page_ref_mod_unless(page, nr, ret);
+       return ret;
 }
 
 static inline int page_ref_freeze(struct page *page, int count)
 {
-       return likely(atomic_cmpxchg(&page->_count, count, 0) == count);
+       int ret = likely(atomic_cmpxchg(&page->_count, count, 0) == count);
+
+       if (page_ref_tracepoint_active(__tracepoint_page_ref_freeze))
+               __page_ref_freeze(page, count, ret);
+       return ret;
 }
 
 static inline void page_ref_unfreeze(struct page *page, int count)
@@ -80,6 +166,8 @@ static inline void page_ref_unfreeze(struct page *page, int count)
        VM_BUG_ON(count == 0);
 
        atomic_set(&page->_count, count);
+       if (page_ref_tracepoint_active(__tracepoint_page_ref_unfreeze))
+               __page_ref_unfreeze(page, count);
 }
 
 #endif

diff --git a/include/trace/events/page_ref.h b/include/trace/events/page_ref.h
new file mode 100644 (file)
index 0000000..81001f8
--- /dev/null
+++ b/include/trace/events/page_ref.h
@@ -0,0 +1,134 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM page_ref
+
+#if !defined(_TRACE_PAGE_REF_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PAGE_REF_H
+
+#include <linux/types.h>
+#include <linux/page_ref.h>
+#include <linux/tracepoint.h>
+#include <trace/events/mmflags.h>
+
+DECLARE_EVENT_CLASS(page_ref_mod_template,
+
+       TP_PROTO(struct page *page, int v),
+
+       TP_ARGS(page, v),
+
+       TP_STRUCT__entry(
+               __field(unsigned long, pfn)
+               __field(unsigned long, flags)
+               __field(int, count)
+               __field(int, mapcount)
+               __field(void *, mapping)
+               __field(int, mt)
+               __field(int, val)
+       ),
+
+       TP_fast_assign(
+               __entry->pfn = page_to_pfn(page);
+               __entry->flags = page->flags;
+               __entry->count = page_ref_count(page);
+               __entry->mapcount = page_mapcount(page);
+               __entry->mapping = page->mapping;
+               __entry->mt = get_pageblock_migratetype(page);
+               __entry->val = v;
+       ),
+
+       TP_printk("pfn=0x%lx flags=%s count=%d mapcount=%d mapping=%p mt=%d val=%d",
+               __entry->pfn,
+               show_page_flags(__entry->flags & ((1UL << NR_PAGEFLAGS) - 1)),
+               __entry->count,
+               __entry->mapcount, __entry->mapping, __entry->mt,
+               __entry->val)
+);
+
+DEFINE_EVENT(page_ref_mod_template, page_ref_set,
+
+       TP_PROTO(struct page *page, int v),
+
+       TP_ARGS(page, v)
+);
+
+DEFINE_EVENT(page_ref_mod_template, page_ref_mod,
+
+       TP_PROTO(struct page *page, int v),
+
+       TP_ARGS(page, v)
+);
+
+DECLARE_EVENT_CLASS(page_ref_mod_and_test_template,
+
+       TP_PROTO(struct page *page, int v, int ret),
+
+       TP_ARGS(page, v, ret),
+
+       TP_STRUCT__entry(
+               __field(unsigned long, pfn)
+               __field(unsigned long, flags)
+               __field(int, count)
+               __field(int, mapcount)
+               __field(void *, mapping)
+               __field(int, mt)
+               __field(int, val)
+               __field(int, ret)
+       ),
+
+       TP_fast_assign(
+               __entry->pfn = page_to_pfn(page);
+               __entry->flags = page->flags;
+               __entry->count = page_ref_count(page);
+               __entry->mapcount = page_mapcount(page);
+               __entry->mapping = page->mapping;
+               __entry->mt = get_pageblock_migratetype(page);
+               __entry->val = v;
+               __entry->ret = ret;
+       ),
+
+       TP_printk("pfn=0x%lx flags=%s count=%d mapcount=%d mapping=%p mt=%d val=%d ret=%d",
+               __entry->pfn,
+               show_page_flags(__entry->flags & ((1UL << NR_PAGEFLAGS) - 1)),
+               __entry->count,
+               __entry->mapcount, __entry->mapping, __entry->mt,
+               __entry->val, __entry->ret)
+);
+
+DEFINE_EVENT(page_ref_mod_and_test_template, page_ref_mod_and_test,
+
+       TP_PROTO(struct page *page, int v, int ret),
+
+       TP_ARGS(page, v, ret)
+);
+
+DEFINE_EVENT(page_ref_mod_and_test_template, page_ref_mod_and_return,
+
+       TP_PROTO(struct page *page, int v, int ret),
+
+       TP_ARGS(page, v, ret)
+);
+
+DEFINE_EVENT(page_ref_mod_and_test_template, page_ref_mod_unless,
+
+       TP_PROTO(struct page *page, int v, int ret),
+
+       TP_ARGS(page, v, ret)
+);
+
+DEFINE_EVENT(page_ref_mod_and_test_template, page_ref_freeze,
+
+       TP_PROTO(struct page *page, int v, int ret),
+
+       TP_ARGS(page, v, ret)
+);
+
+DEFINE_EVENT(page_ref_mod_template, page_ref_unfreeze,
+
+       TP_PROTO(struct page *page, int v),
+
+       TP_ARGS(page, v)
+);
+
+#endif /* _TRACE_PAGE_COUNT_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index 5c50b238b7705a5a4e2ce9a1845e11fc76ec4503..22f4cd96acb0d3a320c9a6440d63585f0dfd6057 100644 (file)
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -79,3 +79,16 @@ config PAGE_POISONING_ZERO
           Enabling page poisoning with this option will disable hibernation
 
           If unsure, say N
+       bool
+
+config DEBUG_PAGE_REF
+       bool "Enable tracepoint to track down page reference manipulation"
+       depends on DEBUG_KERNEL
+       depends on TRACEPOINTS
+       ---help---
+         This is a feature to add tracepoint for tracking down page reference
+         manipulation. This tracking is useful to diagnose functional failure
+         due to migration failures caused by page reference mismatches.  Be
+         careful when enabling this feature because it adds about 30 KB to the
+         kernel code.  However the runtime performance overhead is virtually
+         nil until the tracepoints are actually enabled.

diff --git a/mm/Makefile b/mm/Makefile
index cfdd481d27a5d7344b1eeb706174b0ec393acade..6da300a1414bb11eaccceed440b70b2202bb8c22 100644 (file)
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -81,3 +81,4 @@ obj-$(CONFIG_CMA_DEBUGFS) += cma_debug.o
 obj-$(CONFIG_USERFAULTFD) += userfaultfd.o
 obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o
 obj-$(CONFIG_FRAME_VECTOR) += frame_vector.o
+obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o

diff --git a/mm/debug_page_ref.c b/mm/debug_page_ref.c
new file mode 100644 (file)
index 0000000..1aef3d5
--- /dev/null
+++ b/mm/debug_page_ref.c
@@ -0,0 +1,54 @@
+#include <linux/mm_types.h>
+#include <linux/tracepoint.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/page_ref.h>
+
+void __page_ref_set(struct page *page, int v)
+{
+       trace_page_ref_set(page, v);
+}
+EXPORT_SYMBOL(__page_ref_set);
+EXPORT_TRACEPOINT_SYMBOL(page_ref_set);
+
+void __page_ref_mod(struct page *page, int v)
+{
+       trace_page_ref_mod(page, v);
+}
+EXPORT_SYMBOL(__page_ref_mod);
+EXPORT_TRACEPOINT_SYMBOL(page_ref_mod);
+
+void __page_ref_mod_and_test(struct page *page, int v, int ret)
+{
+       trace_page_ref_mod_and_test(page, v, ret);
+}
+EXPORT_SYMBOL(__page_ref_mod_and_test);
+EXPORT_TRACEPOINT_SYMBOL(page_ref_mod_and_test);
+
+void __page_ref_mod_and_return(struct page *page, int v, int ret)
+{
+       trace_page_ref_mod_and_return(page, v, ret);
+}
+EXPORT_SYMBOL(__page_ref_mod_and_return);
+EXPORT_TRACEPOINT_SYMBOL(page_ref_mod_and_return);
+
+void __page_ref_mod_unless(struct page *page, int v, int u)
+{
+       trace_page_ref_mod_unless(page, v, u);
+}
+EXPORT_SYMBOL(__page_ref_mod_unless);
+EXPORT_TRACEPOINT_SYMBOL(page_ref_mod_unless);
+
+void __page_ref_freeze(struct page *page, int v, int ret)
+{
+       trace_page_ref_freeze(page, v, ret);
+}
+EXPORT_SYMBOL(__page_ref_freeze);
+EXPORT_TRACEPOINT_SYMBOL(page_ref_freeze);
+
+void __page_ref_unfreeze(struct page *page, int v)
+{
+       trace_page_ref_unfreeze(page, v);
+}
+EXPORT_SYMBOL(__page_ref_unfreeze);
+EXPORT_TRACEPOINT_SYMBOL(page_ref_unfreeze);