* [RFC PATCH] mm: introduce __GFP_TRACKLEAK to track in-kernel allocation
@ 2022-08-26 6:40 zhaoyang.huang
2022-08-26 11:49 ` Vlastimil Babka (SUSE)
0 siblings, 1 reply; 3+ messages in thread
From: zhaoyang.huang @ 2022-08-26 6:40 UTC (permalink / raw)
To: Andrew Morton, Catalin Marinas, Zhaoyang Huang, linux-mm,
linux-kernel, ke.wang
From: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
Kthread and drivers could fetch memory via alloc_pages directly which make them
hard to debug when leaking. Solve this by introducing __GFP_TRACELEAK and reuse
kmemleak mechanism which unified most of kernel cosuming pages into kmemleak.
Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
---
include/linux/gfp.h | 4 +++-
include/linux/page-flags.h | 3 +++
mm/kmemleak.c | 2 +-
mm/page_alloc.c | 6 ++++++
4 files changed, 13 insertions(+), 2 deletions(-)
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 2d2ccae..081ab54 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -68,6 +68,7 @@
#else
#define ___GFP_NOLOCKDEP 0
#endif
+#define ___GFP_TRACKLEAK 0x10000000u
/* If the above are modified, __GFP_BITS_SHIFT may need updating */
/*
@@ -259,12 +260,13 @@
#define __GFP_SKIP_ZERO ((__force gfp_t)___GFP_SKIP_ZERO)
#define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON)
#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON)
+#define __GFP_TRACKLEAK ((__force gfp_t)___GFP_TRACKLEAK)
/* Disable lockdep for GFP context tracking */
#define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
/* Room for N __GFP_FOO bits */
-#define __GFP_BITS_SHIFT (27 + IS_ENABLED(CONFIG_LOCKDEP))
+#define __GFP_BITS_SHIFT (28 + IS_ENABLED(CONFIG_LOCKDEP))
#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
/**
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index e66f7aa..ef0f814 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -942,6 +942,7 @@ static inline bool is_page_hwpoison(struct page *page)
#define PG_offline 0x00000100
#define PG_table 0x00000200
#define PG_guard 0x00000400
+#define PG_trackleak 0x00000800
#define PageType(page, flag) \
((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE)
@@ -1012,6 +1013,8 @@ static inline int page_has_type(struct page *page)
*/
PAGE_TYPE_OPS(Guard, guard)
+PAGE_TYPE_OPS(Trackleak, trackleak)
+
extern bool is_free_buddy_page(struct page *page);
PAGEFLAG(Isolated, isolated, PF_ANY);
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 422f28f..a182f5d 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1471,7 +1471,7 @@ static void kmemleak_scan(void)
if (page_zone(page) != zone)
continue;
/* only scan if page is in use */
- if (page_count(page) == 0 || PageReserved(page))
+ if (page_count(page) == 0)
continue;
scan_block(page, page + 1, NULL);
if (!(pfn & 63))
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e008a3d..d8995c6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1361,6 +1361,8 @@ static __always_inline bool free_pages_prepare(struct page *page,
page->mapping = NULL;
if (memcg_kmem_enabled() && PageMemcgKmem(page))
__memcg_kmem_uncharge_page(page, order);
+ if (PageTrackleak(page))
+ kmemleak_free(page);
if (check_free)
bad += check_free_page(page);
if (bad)
@@ -5444,6 +5446,10 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
__free_pages(page, order);
page = NULL;
}
+ if (gfp & __GFP_TRACKLEAK) {
+ kmemleak_alloc(page_address(page), PAGE_SIZE << order, 1, gfp & ~__GFP_TRACKLEAK);
+ __SetPageTrackleak(page);
+ }
trace_mm_page_alloc(page, order, alloc_gfp, ac.migratetype);
--
1.9.1
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [RFC PATCH] mm: introduce __GFP_TRACKLEAK to track in-kernel allocation
2022-08-26 6:40 [RFC PATCH] mm: introduce __GFP_TRACKLEAK to track in-kernel allocation zhaoyang.huang
@ 2022-08-26 11:49 ` Vlastimil Babka (SUSE)
2022-08-27 7:53 ` Zhaoyang Huang
0 siblings, 1 reply; 3+ messages in thread
From: Vlastimil Babka (SUSE) @ 2022-08-26 11:49 UTC (permalink / raw)
To: zhaoyang.huang, Andrew Morton, Catalin Marinas, Zhaoyang Huang,
linux-mm, linux-kernel, ke.wang
On 8/26/22 08:40, zhaoyang.huang wrote:
> From: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
>
> Kthread and drivers could fetch memory via alloc_pages directly which make them
> hard to debug when leaking. Solve this by introducing __GFP_TRACELEAK and reuse
> kmemleak mechanism which unified most of kernel cosuming pages into kmemleak.
Can you expand how exactly this is expected to be used? So you first have to
suspect some concrete allocation and add __GFP_TRACKLEAK to it?
> Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
> ---
> include/linux/gfp.h | 4 +++-
> include/linux/page-flags.h | 3 +++
> mm/kmemleak.c | 2 +-
> mm/page_alloc.c | 6 ++++++
> 4 files changed, 13 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/gfp.h b/include/linux/gfp.h
> index 2d2ccae..081ab54 100644
> --- a/include/linux/gfp.h
> +++ b/include/linux/gfp.h
> @@ -68,6 +68,7 @@
> #else
> #define ___GFP_NOLOCKDEP 0
> #endif
> +#define ___GFP_TRACKLEAK 0x10000000u
> /* If the above are modified, __GFP_BITS_SHIFT may need updating */
>
> /*
> @@ -259,12 +260,13 @@
> #define __GFP_SKIP_ZERO ((__force gfp_t)___GFP_SKIP_ZERO)
> #define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON)
> #define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON)
> +#define __GFP_TRACKLEAK ((__force gfp_t)___GFP_TRACKLEAK)
>
> /* Disable lockdep for GFP context tracking */
> #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
>
> /* Room for N __GFP_FOO bits */
> -#define __GFP_BITS_SHIFT (27 + IS_ENABLED(CONFIG_LOCKDEP))
> +#define __GFP_BITS_SHIFT (28 + IS_ENABLED(CONFIG_LOCKDEP))
> #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
>
> /**
> diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
> index e66f7aa..ef0f814 100644
> --- a/include/linux/page-flags.h
> +++ b/include/linux/page-flags.h
> @@ -942,6 +942,7 @@ static inline bool is_page_hwpoison(struct page *page)
> #define PG_offline 0x00000100
> #define PG_table 0x00000200
> #define PG_guard 0x00000400
> +#define PG_trackleak 0x00000800
>
> #define PageType(page, flag) \
> ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE)
> @@ -1012,6 +1013,8 @@ static inline int page_has_type(struct page *page)
> */
> PAGE_TYPE_OPS(Guard, guard)
>
> +PAGE_TYPE_OPS(Trackleak, trackleak)
> +
> extern bool is_free_buddy_page(struct page *page);
>
> PAGEFLAG(Isolated, isolated, PF_ANY);
> diff --git a/mm/kmemleak.c b/mm/kmemleak.c
> index 422f28f..a182f5d 100644
> --- a/mm/kmemleak.c
> +++ b/mm/kmemleak.c
> @@ -1471,7 +1471,7 @@ static void kmemleak_scan(void)
> if (page_zone(page) != zone)
> continue;
> /* only scan if page is in use */
> - if (page_count(page) == 0 || PageReserved(page))
> + if (page_count(page) == 0)
> continue;
> scan_block(page, page + 1, NULL);
> if (!(pfn & 63))
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index e008a3d..d8995c6 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -1361,6 +1361,8 @@ static __always_inline bool free_pages_prepare(struct page *page,
> page->mapping = NULL;
> if (memcg_kmem_enabled() && PageMemcgKmem(page))
> __memcg_kmem_uncharge_page(page, order);
> + if (PageTrackleak(page))
> + kmemleak_free(page);
> if (check_free)
> bad += check_free_page(page);
> if (bad)
> @@ -5444,6 +5446,10 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
> __free_pages(page, order);
> page = NULL;
> }
> + if (gfp & __GFP_TRACKLEAK) {
> + kmemleak_alloc(page_address(page), PAGE_SIZE << order, 1, gfp & ~__GFP_TRACKLEAK);
> + __SetPageTrackleak(page);
> + }
>
> trace_mm_page_alloc(page, order, alloc_gfp, ac.migratetype);
>
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [RFC PATCH] mm: introduce __GFP_TRACKLEAK to track in-kernel allocation
2022-08-26 11:49 ` Vlastimil Babka (SUSE)
@ 2022-08-27 7:53 ` Zhaoyang Huang
0 siblings, 0 replies; 3+ messages in thread
From: Zhaoyang Huang @ 2022-08-27 7:53 UTC (permalink / raw)
To: Vlastimil Babka (SUSE)
Cc: zhaoyang.huang, Andrew Morton, Catalin Marinas,
open list:MEMORY MANAGEMENT, LKML, Ke Wang
On Fri, Aug 26, 2022 at 7:49 PM Vlastimil Babka (SUSE)
<vbabka@kernel.org> wrote:
>
> On 8/26/22 08:40, zhaoyang.huang wrote:
> > From: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
> >
> > Kthread and drivers could fetch memory via alloc_pages directly which make them
> > hard to debug when leaking. Solve this by introducing __GFP_TRACELEAK and reuse
> > kmemleak mechanism which unified most of kernel cosuming pages into kmemleak.
>
> Can you expand how exactly this is expected to be used? So you first have to
> suspect some concrete allocation and add __GFP_TRACKLEAK to it?
It could be used to investigate suspicious drivers or kthread which
may introduce in-kernel leak during debug phase by enabling kmemleak.
This can be done via page owner things now. I would like to unified it
together with slab leak into kmemleak.
>
> > Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
> > ---
> > include/linux/gfp.h | 4 +++-
> > include/linux/page-flags.h | 3 +++
> > mm/kmemleak.c | 2 +-
> > mm/page_alloc.c | 6 ++++++
> > 4 files changed, 13 insertions(+), 2 deletions(-)
> >
> > diff --git a/include/linux/gfp.h b/include/linux/gfp.h
> > index 2d2ccae..081ab54 100644
> > --- a/include/linux/gfp.h
> > +++ b/include/linux/gfp.h
> > @@ -68,6 +68,7 @@
> > #else
> > #define ___GFP_NOLOCKDEP 0
> > #endif
> > +#define ___GFP_TRACKLEAK 0x10000000u
> > /* If the above are modified, __GFP_BITS_SHIFT may need updating */
> >
> > /*
> > @@ -259,12 +260,13 @@
> > #define __GFP_SKIP_ZERO ((__force gfp_t)___GFP_SKIP_ZERO)
> > #define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON)
> > #define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON)
> > +#define __GFP_TRACKLEAK ((__force gfp_t)___GFP_TRACKLEAK)
> >
> > /* Disable lockdep for GFP context tracking */
> > #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
> >
> > /* Room for N __GFP_FOO bits */
> > -#define __GFP_BITS_SHIFT (27 + IS_ENABLED(CONFIG_LOCKDEP))
> > +#define __GFP_BITS_SHIFT (28 + IS_ENABLED(CONFIG_LOCKDEP))
> > #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
> >
> > /**
> > diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
> > index e66f7aa..ef0f814 100644
> > --- a/include/linux/page-flags.h
> > +++ b/include/linux/page-flags.h
> > @@ -942,6 +942,7 @@ static inline bool is_page_hwpoison(struct page *page)
> > #define PG_offline 0x00000100
> > #define PG_table 0x00000200
> > #define PG_guard 0x00000400
> > +#define PG_trackleak 0x00000800
> >
> > #define PageType(page, flag) \
> > ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE)
> > @@ -1012,6 +1013,8 @@ static inline int page_has_type(struct page *page)
> > */
> > PAGE_TYPE_OPS(Guard, guard)
> >
> > +PAGE_TYPE_OPS(Trackleak, trackleak)
> > +
> > extern bool is_free_buddy_page(struct page *page);
> >
> > PAGEFLAG(Isolated, isolated, PF_ANY);
> > diff --git a/mm/kmemleak.c b/mm/kmemleak.c
> > index 422f28f..a182f5d 100644
> > --- a/mm/kmemleak.c
> > +++ b/mm/kmemleak.c
> > @@ -1471,7 +1471,7 @@ static void kmemleak_scan(void)
> > if (page_zone(page) != zone)
> > continue;
> > /* only scan if page is in use */
> > - if (page_count(page) == 0 || PageReserved(page))
> > + if (page_count(page) == 0)
> > continue;
> > scan_block(page, page + 1, NULL);
> > if (!(pfn & 63))
> > diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> > index e008a3d..d8995c6 100644
> > --- a/mm/page_alloc.c
> > +++ b/mm/page_alloc.c
> > @@ -1361,6 +1361,8 @@ static __always_inline bool free_pages_prepare(struct page *page,
> > page->mapping = NULL;
> > if (memcg_kmem_enabled() && PageMemcgKmem(page))
> > __memcg_kmem_uncharge_page(page, order);
> > + if (PageTrackleak(page))
> > + kmemleak_free(page);
> > if (check_free)
> > bad += check_free_page(page);
> > if (bad)
> > @@ -5444,6 +5446,10 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
> > __free_pages(page, order);
> > page = NULL;
> > }
> > + if (gfp & __GFP_TRACKLEAK) {
> > + kmemleak_alloc(page_address(page), PAGE_SIZE << order, 1, gfp & ~__GFP_TRACKLEAK);
> > + __SetPageTrackleak(page);
> > + }
> >
> > trace_mm_page_alloc(page, order, alloc_gfp, ac.migratetype);
> >
>
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2022-08-27 7:54 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-08-26 6:40 [RFC PATCH] mm: introduce __GFP_TRACKLEAK to track in-kernel allocation zhaoyang.huang
2022-08-26 11:49 ` Vlastimil Babka (SUSE)
2022-08-27 7:53 ` Zhaoyang Huang
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).