From: SeongJae Park sjpark@amazon.de
mainline inclusion from mainline-5.15-rc1 commit 1c676e0d9b1a59b98885b24a0e16a81fe4cc8301 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4GVMK CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
------------------------------------------------- PG_idle and PG_young allow the two PTE Accessed bit users, Idle Page Tracking and the reclaim logic concurrently work while not interfering with each other. That is, when they need to clear the Accessed bit, they set PG_young to represent the previous state of the bit, respectively. And when they need to read the bit, if the bit is cleared, they further read the PG_young to know whether the other has cleared the bit meanwhile or not.
For yet another user of the PTE Accessed bit, we could add another page flag, or extend the mechanism to use the flags. For the DAMON usecase, however, we don't need to do that just yet. IDLE_PAGE_TRACKING and DAMON are mutually exclusive, so there's only ever going to be one user of the current set of flags.
In this commit, we split out the CONFIG options to allow for the use of PG_young and PG_idle outside of idle page tracking.
In the next commit, DAMON's reference implementation of the virtual memory address space monitoring primitives will use it.
[sjpark@amazon.de: set PAGE_EXTENSION for non-64BIT] Link: https://lkml.kernel.org/r/20210806095153.6444-1-sj38.park@gmail.com [akpm@linux-foundation.org: tweak Kconfig text] [sjpark@amazon.de: hide PAGE_IDLE_FLAG from users] Link: https://lkml.kernel.org/r/20210813081238.34705-1-sj38.park@gmail.com
Link: https://lkml.kernel.org/r/20210716081449.22187-5-sj38.park@gmail.com Signed-off-by: SeongJae Park sjpark@amazon.de Reviewed-by: Shakeel Butt shakeelb@google.com Reviewed-by: Fernand Sieber sieberf@amazon.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Amit Shah amit@kernel.org Cc: Benjamin Herrenschmidt benh@kernel.crashing.org Cc: Brendan Higgins brendanhiggins@google.com Cc: David Hildenbrand david@redhat.com Cc: David Rientjes rientjes@google.com Cc: David Woodhouse dwmw@amazon.com Cc: Fan Du fan.du@intel.com Cc: Greg Kroah-Hartman greg@kroah.com Cc: Greg Thelen gthelen@google.com Cc: Ingo Molnar mingo@redhat.com Cc: Joe Perches joe@perches.com Cc: Jonathan Cameron Jonathan.Cameron@huawei.com Cc: Jonathan Corbet corbet@lwn.net Cc: Leonard Foerster foersleo@amazon.de Cc: Marco Elver elver@google.com Cc: Markus Boehme markubo@amazon.de Cc: Maximilian Heyne mheyne@amazon.de Cc: Mel Gorman mgorman@suse.de Cc: Minchan Kim minchan@kernel.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Rik van Riel riel@surriel.com Cc: Shuah Khan shuah@kernel.org Cc: Steven Rostedt (VMware) rostedt@goodmis.org Cc: Vladimir Davydov vdavydov.dev@gmail.com Cc: Vlastimil Babka vbabka@suse.cz Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org (cherry picked from commit 1c676e0d9b1a59b98885b24a0e16a81fe4cc8301) Signed-off-by: Yue Zou zouyue3@huawei.com Reviewed-by: Kefeng Wang wangkefeng.wang@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- include/linux/page-flags.h | 4 ++-- include/linux/page_ext.h | 2 +- include/linux/page_idle.h | 6 +++--- include/trace/events/mmflags.h | 2 +- mm/Kconfig | 10 +++++++++- mm/page_ext.c | 12 +++++++++++- mm/page_idle.c | 10 ---------- 7 files changed, 27 insertions(+), 19 deletions(-)
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 5fed83d29ea8..56d9a03119a3 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -132,7 +132,7 @@ enum pageflags { #ifdef CONFIG_MEMORY_FAILURE PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif -#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) +#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) PG_young, PG_idle, #endif @@ -438,7 +438,7 @@ PAGEFLAG_FALSE(HWPoison) #define __PG_HWPOISON 0 #endif
-#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) +#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) TESTPAGEFLAG(Young, young, PF_ANY) SETPAGEFLAG(Young, young, PF_ANY) TESTCLEARFLAG(Young, young, PF_ANY) diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index aff81ba31bd8..fabb2e1e087f 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -19,7 +19,7 @@ struct page_ext_operations { enum page_ext_flags { PAGE_EXT_OWNER, PAGE_EXT_OWNER_ALLOCATED, -#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT) +#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) PAGE_EXT_YOUNG, PAGE_EXT_IDLE, #endif diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h index 1e894d34bdce..d8a6aecf99cb 100644 --- a/include/linux/page_idle.h +++ b/include/linux/page_idle.h @@ -6,7 +6,7 @@ #include <linux/page-flags.h> #include <linux/page_ext.h>
-#ifdef CONFIG_IDLE_PAGE_TRACKING +#ifdef CONFIG_PAGE_IDLE_FLAG
#ifdef CONFIG_64BIT static inline bool page_is_young(struct page *page) @@ -106,7 +106,7 @@ static inline void clear_page_idle(struct page *page) } #endif /* CONFIG_64BIT */
-#else /* !CONFIG_IDLE_PAGE_TRACKING */ +#else /* !CONFIG_PAGE_IDLE_FLAG */
static inline bool page_is_young(struct page *page) { @@ -135,6 +135,6 @@ static inline void clear_page_idle(struct page *page) { }
-#endif /* CONFIG_IDLE_PAGE_TRACKING */ +#endif /* CONFIG_PAGE_IDLE_FLAG */
#endif /* _LINUX_MM_PAGE_IDLE_H */ diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 673c6f590800..792e0a2fa775 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -73,7 +73,7 @@ #define IF_HAVE_PG_HWPOISON(flag,string) #endif
-#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) +#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) #define IF_HAVE_PG_IDLE(flag,string) ,{1UL << flag, string} #else #define IF_HAVE_PG_IDLE(flag,string) diff --git a/mm/Kconfig b/mm/Kconfig index c002358860c8..59fdace319fd 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -788,10 +788,18 @@ config DEFERRED_STRUCT_PAGE_INIT lifetime of the system until these kthreads finish the initialisation.
+config PAGE_IDLE_FLAG + bool + select PAGE_EXTENSION if !64BIT + help + This adds PG_idle and PG_young flags to 'struct page'. PTE Accessed + bit writers can set the state of the bit in the flags so that PTE + Accessed bit readers may avoid disturbance. + config IDLE_PAGE_TRACKING bool "Enable idle page tracking" depends on SYSFS && MMU - select PAGE_EXTENSION if !64BIT + select PAGE_IDLE_FLAG help This feature allows to estimate the amount of user pages that have not been touched during a given period of time. This information can diff --git a/mm/page_ext.c b/mm/page_ext.c index df6f74aac8e1..8e59da0f4367 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -58,11 +58,21 @@ * can utilize this callback to initialize the state of it correctly. */
+#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) +static bool need_page_idle(void) +{ + return true; +} +struct page_ext_operations page_idle_ops = { + .need = need_page_idle, +}; +#endif + static struct page_ext_operations *page_ext_ops[] = { #ifdef CONFIG_PAGE_OWNER &page_owner_ops, #endif -#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT) +#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) &page_idle_ops, #endif }; diff --git a/mm/page_idle.c b/mm/page_idle.c index 64e5344a992c..edead6a8a5f9 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -207,16 +207,6 @@ static const struct attribute_group page_idle_attr_group = { .name = "page_idle", };
-#ifndef CONFIG_64BIT -static bool need_page_idle(void) -{ - return true; -} -struct page_ext_operations page_idle_ops = { - .need = need_page_idle, -}; -#endif - static int __init page_idle_init(void) { int err;