linux-kernel - Re: [PATCH 18/19] sched, numa: Per task memory placement for big processes

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Wed, 08 Aug 2012 23:35:32 +0200
From:	Peter Zijlstra <a.p.zijlstra@...llo.nl>
To:	mingo@...nel.org
Cc:	riel@...hat.com, oleg@...hat.com, pjt@...gle.com,
	akpm@...ux-foundation.org, torvalds@...ux-foundation.org,
	tglx@...utronix.de, Lee.Schermerhorn@...com,
	linux-kernel@...r.kernel.org, Paul Mundt <lethal@...ux-sh.org>
Subject: Re: [PATCH 18/19] sched, numa: Per task memory placement for big
 processes

On Tue, 2012-07-31 at 21:12 +0200, Peter Zijlstra wrote:
> +#ifdef CONFIG_NUMA
> +       /*
> +        * XXX fold this into flags for 64bit or so...
> +        */
> +       int nid_last;
> +#endif 

Something like the below? I still ought to update all the various
comments about page flag layout etc..

Also, that #warning gives a very noisy build indeed, I guess we should
either make it silent or increase the page frame size for those
configs.. 32bit NUMA is quite rare for normal people (sorry Paul) :)

---
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -611,10 +611,19 @@ static inline pte_t maybe_mkwrite(pte_t 
 #define NODES_WIDTH		0
 #endif
 
+#if NODES_WIDTH && (SECTIONS_WIDTH+ZONES_WIDTH+2*NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS)
+#define LAST_NID_WIDTH	NODES_SHIFT
+#else
+#warning "faking page_xchg_last_nid"
+#define LAST_NID_NOT_IN_PAGE_FLAGS
+#define LAST_NID_WIDTH	0
+#endif
+
 /* Page flags: | [SECTION] | [NODE] | ZONE | ... | FLAGS | */
 #define SECTIONS_PGOFF		((sizeof(unsigned long)*8) - SECTIONS_WIDTH)
 #define NODES_PGOFF		(SECTIONS_PGOFF - NODES_WIDTH)
 #define ZONES_PGOFF		(NODES_PGOFF - ZONES_WIDTH)
+#define LAST_NID_PGOFF		(ZONES_PGOFF - LAST_NID_WIDTH)
 
 /*
  * We are going to use the flags for the page to node mapping if its in
@@ -632,6 +641,7 @@ static inline pte_t maybe_mkwrite(pte_t 
 #define SECTIONS_PGSHIFT	(SECTIONS_PGOFF * (SECTIONS_WIDTH != 0))
 #define NODES_PGSHIFT		(NODES_PGOFF * (NODES_WIDTH != 0))
 #define ZONES_PGSHIFT		(ZONES_PGOFF * (ZONES_WIDTH != 0))
+#define LAST_NID_PGSHIFT	(LAST_NID_PGOFF * (LAST_NID_WIDTH != 0))
 
 /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */
 #ifdef NODE_NOT_IN_PAGE_FLAGS
@@ -653,6 +663,7 @@ static inline pte_t maybe_mkwrite(pte_t 
 #define ZONES_MASK		((1UL << ZONES_WIDTH) - 1)
 #define NODES_MASK		((1UL << NODES_WIDTH) - 1)
 #define SECTIONS_MASK		((1UL << SECTIONS_WIDTH) - 1)
+#define LAST_NID_MASK		((1UL << LAST_NID_WIDTH) - 1)
 #define ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1)
 
 static inline enum zone_type page_zonenum(const struct page *page)
@@ -691,6 +702,39 @@ static inline int page_to_nid(const stru
 }
 #endif
 
+#ifdef LAST_NID_NOT_IN_PAGE_FLAGS
+static inline int page_xchg_last_nid(struct page *page, int nid)
+{
+	return nid; /* fakin' it */
+}
+
+static inline int page_last_nid(struct page *page)
+{
+	return page_to_nid(page);
+}	
+#else
+static inline int page_xchg_last_nid(struct page *page, int nid)
+{
+	unsigned long old_flags, flags;
+	int last_nid;
+
+       	old_flags = flags = page->flags;
+	last_nid = (flags >> LAST_NID_PGSHIFT) & LAST_NID_MASK;
+
+	flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT);
+	flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT;
+
+ 	(void)cmpxchg(&page->flags, old_flags, flags);
+
+	return last_nid;
+}
+
+static inline int page_last_nid(struct page *page)
+{
+	return (page->flags >> LAST_NID_PGSHIFT) & LAST_NID_MASK;
+}
+#endif /* LAST_NID_NOT_IN_PAGE_FLAGS */
+
 static inline struct zone *page_zone(const struct page *page)
 {
 	return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -176,12 +176,6 @@ struct page {
 	 */
 	void *shadow;
 #endif
-#ifdef CONFIG_NUMA
-	/*
-	 * XXX fold this into flags for 64bit or so...
-	 */
-	int nid_last;
-#endif
 }
 /*
  * The struct page can be forced to be double word aligned so that atomic ops
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1366,6 +1366,7 @@ static void __split_huge_page_refcount(s
 		page_tail->mapping = page->mapping;
 
 		page_tail->index = page->index + i;
+		page_xchg_last_nid(page, page_last_nid(tail_page));
 		page_tail->nid_last = page->nid_last;
 
 		BUG_ON(!PageAnon(page_tail));
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2265,10 +2265,9 @@ int mpol_misplaced(struct page *page, st
 	 * task_tick_numa().
 	 */
 	if (multi && (pol->flags & MPOL_F_HOME)) {
-		if (page->nid_last != polnid) {
-			page->nid_last = polnid;
+		int last_nid = page_xchg_last_nid(page, polnid);
+		if (last_nid != polnid)
 			goto out;
-		}
 	}
 
 	if (curnid != polnid)


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/