Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
From: David Hildenbrand <david@redhat.com>
To: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org, linux-arm-kernel@lists.infradead.org,
	linux-ia64@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
	linux-s390@vger.kernel.org, linux-sh@vger.kernel.org,
	x86@kernel.org, David Hildenbrand <david@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Oscar Salvador <osalvador@suse.de>,
	Michal Hocko <mhocko@suse.com>,
	Pavel Tatashin <pasha.tatashin@soleen.com>,
	Dan Williams <dan.j.williams@intel.com>,
	Wei Yang <richardw.yang@linux.intel.com>,
	"Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>
Subject: [PATCH v6 03/10] mm/memory_hotplug: Don't access uninitialized memmaps in shrink_pgdat_span()
Date: Sun,  6 Oct 2019 10:56:39 +0200
Message-ID: <20191006085646.5768-4-david@redhat.com> (raw)
In-Reply-To: <20191006085646.5768-1-david@redhat.com>

We might use the nid of memmaps that were never initialized. For
example, if the memmap was poisoned, we will crash the kernel in
pfn_to_nid() right now. Let's use the calculated boundaries of the separate
zones instead. This now also avoids having to iterate over a whole bunch of
subsections again, after shrinking one zone.

Before commit d0dc12e86b31 ("mm/memory_hotplug: optimize memory
hotplug"), the memmap was initialized to 0 and the node was set to the
right value. After that commit, the node might be garbage.

We'll have to fix shrink_zone_span() next.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: David Hildenbrand <david@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Fixes: d0dc12e86b31 ("mm/memory_hotplug: optimize memory hotplug")
Reported-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 mm/memory_hotplug.c | 72 ++++++++++-----------------------------------
 1 file changed, 15 insertions(+), 57 deletions(-)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 680b4b3e57d9..86b4dc18e831 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -436,67 +436,25 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
 	zone_span_writeunlock(zone);
 }
 
-static void shrink_pgdat_span(struct pglist_data *pgdat,
-			      unsigned long start_pfn, unsigned long end_pfn)
+static void update_pgdat_span(struct pglist_data *pgdat)
 {
-	unsigned long pgdat_start_pfn = pgdat->node_start_pfn;
-	unsigned long p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */
-	unsigned long pgdat_end_pfn = p;
-	unsigned long pfn;
-	int nid = pgdat->node_id;
-
-	if (pgdat_start_pfn == start_pfn) {
-		/*
-		 * If the section is smallest section in the pgdat, it need
-		 * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages.
-		 * In this case, we find second smallest valid mem_section
-		 * for shrinking zone.
-		 */
-		pfn = find_smallest_section_pfn(nid, NULL, end_pfn,
-						pgdat_end_pfn);
-		if (pfn) {
-			pgdat->node_start_pfn = pfn;
-			pgdat->node_spanned_pages = pgdat_end_pfn - pfn;
-		}
-	} else if (pgdat_end_pfn == end_pfn) {
-		/*
-		 * If the section is biggest section in the pgdat, it need
-		 * shrink pgdat->node_spanned_pages.
-		 * In this case, we find second biggest valid mem_section for
-		 * shrinking zone.
-		 */
-		pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn,
-					       start_pfn);
-		if (pfn)
-			pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1;
-	}
-
-	/*
-	 * If the section is not biggest or smallest mem_section in the pgdat,
-	 * it only creates a hole in the pgdat. So in this case, we need not
-	 * change the pgdat.
-	 * But perhaps, the pgdat has only hole data. Thus it check the pgdat
-	 * has only hole or not.
-	 */
-	pfn = pgdat_start_pfn;
-	for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SUBSECTION) {
-		if (unlikely(!pfn_valid(pfn)))
-			continue;
-
-		if (pfn_to_nid(pfn) != nid)
-			continue;
+	unsigned long node_start_pfn = 0, node_end_pfn = 0;
+	struct zone *zone;
 
-		/* Skip range to be removed */
-		if (pfn >= start_pfn && pfn < end_pfn)
-			continue;
+	for (zone = pgdat->node_zones;
+	     zone < pgdat->node_zones + MAX_NR_ZONES; zone++) {
+		unsigned long zone_end_pfn = zone->zone_start_pfn +
+					     zone->spanned_pages;
 
-		/* If we find valid section, we have nothing to do */
-		return;
+		/* No need to lock the zones, they can't change. */
+		if (zone_end_pfn > node_end_pfn)
+			node_end_pfn = zone_end_pfn;
+		if (zone->zone_start_pfn < node_start_pfn)
+			node_start_pfn = zone->zone_start_pfn;
 	}
 
-	/* The pgdat has no valid section */
-	pgdat->node_start_pfn = 0;
-	pgdat->node_spanned_pages = 0;
+	pgdat->node_start_pfn = node_start_pfn;
+	pgdat->node_spanned_pages = node_end_pfn - node_start_pfn;
 }
 
 static void __remove_zone(struct zone *zone, unsigned long start_pfn,
@@ -507,7 +465,7 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn,
 
 	pgdat_resize_lock(zone->zone_pgdat, &flags);
 	shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
-	shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages);
+	update_pgdat_span(pgdat);
 	pgdat_resize_unlock(zone->zone_pgdat, &flags);
 }
 
-- 
2.21.0



  parent reply index

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-06  8:56 [PATCH v6 00/10] mm/memory_hotplug: Shrink zones before removing memory David Hildenbrand
2019-10-06  8:56 ` [PATCH v6 01/10] mm/memunmap: Don't access uninitialized memmap in memunmap_pages() David Hildenbrand
2019-10-06 19:58   ` Damian Tometzki
2019-10-06 20:13     ` David Hildenbrand
2019-10-14  9:05   ` David Hildenbrand
2019-10-06  8:56 ` [PATCH v6 02/10] mm/memmap_init: Update variable name in memmap_init_zone David Hildenbrand
2019-10-06  8:56 ` David Hildenbrand [this message]
2019-10-14  9:31   ` [PATCH v6 03/10] mm/memory_hotplug: Don't access uninitialized memmaps in shrink_pgdat_span() David Hildenbrand
2019-10-06  8:56 ` [PATCH v6 04/10] mm/memory_hotplug: Don't access uninitialized memmaps in shrink_zone_span() David Hildenbrand
2019-10-14  9:32   ` David Hildenbrand
2019-10-14 19:17     ` Andrew Morton
2019-11-19 14:16       ` David Hildenbrand
2019-11-19 20:44         ` Andrew Morton
2019-10-06  8:56 ` [PATCH v6 05/10] mm/memory_hotplug: Shrink zones when offlining memory David Hildenbrand
2019-10-14  9:39   ` David Hildenbrand
2019-10-14 19:16     ` Andrew Morton
2019-10-27 22:45   ` David Hildenbrand
2019-11-30 23:21     ` Andrew Morton
2019-11-30 23:43       ` David Hildenbrand
2019-12-18 17:08       ` David Hildenbrand
2019-12-18 20:16         ` Andrew Morton
2019-12-03 15:10   ` Oscar Salvador
2019-12-03 15:27     ` David Hildenbrand
2019-10-06  8:56 ` [PATCH v6 06/10] mm/memory_hotplug: Poison memmap in remove_pfn_range_from_zone() David Hildenbrand
2019-10-16 14:01   ` David Hildenbrand
2019-10-06  8:56 ` [PATCH v6 07/10] mm/memory_hotplug: We always have a zone in find_(smallest|biggest)_section_pfn David Hildenbrand
2019-10-06  8:56 ` [PATCH v6 08/10] mm/memory_hotplug: Don't check for "all holes" in shrink_zone_span() David Hildenbrand
2019-10-06  8:56 ` [PATCH v6 09/10] mm/memory_hotplug: Drop local variables " David Hildenbrand
2019-10-06  8:56 ` [PATCH v6 10/10] mm/memory_hotplug: Cleanup __remove_pages() David Hildenbrand
2019-12-02  9:09 ` [PATCH v6 00/10] mm/memory_hotplug: Shrink zones before removing memory David Hildenbrand
2019-12-03 13:36   ` Oscar Salvador

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191006085646.5768-4-david@redhat.com \
    --to=david@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@linux.ibm.com \
    --cc=dan.j.williams@intel.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-ia64@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=linux-sh@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=mhocko@suse.com \
    --cc=osalvador@suse.de \
    --cc=pasha.tatashin@soleen.com \
    --cc=richardw.yang@linux.intel.com \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org
	public-inbox-index linux-mm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git