| 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
| ||
|
Message-ID: <20170530121806.GD7969@dhcp22.suse.cz>
Date: Tue, 30 May 2017 14:18:06 +0200
From: Michal Hocko <mhocko@...nel.org>
To: Heiko Carstens <heiko.carstens@...ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@...ibm.com>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org
Subject: Re: [-next] memory hotplug regression
On Fri 26-05-17 14:25:09, Heiko Carstens wrote:
[...]
> 1) With the new code I can generate overlapping zones for ZONE_DMA and
> ZONE_NORMAL:
>
> --- new code:
>
> DMA [mem 0x0000000000000000-0x000000007fffffff]
> Normal [mem 0x0000000080000000-0x000000017fffffff]
>
> # cat /sys/devices/system/memory/block_size_bytes
> 10000000
> # cat /sys/devices/system/memory/memory5/valid_zones
> DMA
> # echo 0 > /sys/devices/system/memory/memory5/online
> # cat /sys/devices/system/memory/memory5/valid_zones
> Normal
> # echo 1 > /sys/devices/system/memory/memory5/online
> Normal
>
> # cat /proc/zoneinfo
> Node 0, zone DMA
> spanned 524288 <-----
> present 458752
> managed 455078
> start_pfn: 0 <-----
>
> Node 0, zone Normal
> spanned 720896
> present 589824
> managed 571648
> start_pfn: 327680 <-----
>
> So ZONE_DMA ends within ZONE_NORMAL. This shouldn't be possible, unless
> this restriction is gone?
The patch below should help.
> --- old code:
>
> # echo 0 > /sys/devices/system/memory/memory5/online
> # cat /sys/devices/system/memory/memory5/valid_zones
> DMA
> # echo online_movable > /sys/devices/system/memory/memory5/state
> -bash: echo: write error: Invalid argument
> # echo online_kernel > /sys/devices/system/memory/memory5/state
> -bash: echo: write error: Invalid argument
this error doesn't make any sense. Because we we want to online kernel
memory and DMA is pretty much the kernel memory
> # echo online > /sys/devices/system/memory/memory5/state
> # cat /sys/devices/system/memory/memory5/valid_zones
> DMA
---
>From 91a432ceb6af9a8f3791d97b6731d2010cbd5b47 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@...e.com>
Date: Tue, 30 May 2017 13:56:23 +0200
Subject: [PATCH] mm, memory_hotplug: do not assume ZONE_NORMAL is default
kernel zone
Heiko Carstens has noticed that he can generate overlapping zones for
ZONE_DMA and ZONE_NORMAL:
DMA [mem 0x0000000000000000-0x000000007fffffff]
Normal [mem 0x0000000080000000-0x000000017fffffff]
$ cat /sys/devices/system/memory/block_size_bytes
10000000
$ cat /sys/devices/system/memory/memory5/valid_zones
DMA
$ echo 0 > /sys/devices/system/memory/memory5/online
$ cat /sys/devices/system/memory/memory5/valid_zones
Normal
$ echo 1 > /sys/devices/system/memory/memory5/online
Normal
$ cat /proc/zoneinfo
Node 0, zone DMA
spanned 524288 <-----
present 458752
managed 455078
start_pfn: 0 <-----
Node 0, zone Normal
spanned 720896
present 589824
managed 571648
start_pfn: 327680 <-----
The reason is that we assume that the default zone for kernel onlining
is ZONE_NORMAL. This was a simplification introduced by the memory
hotplug rework and it is easily fixable by checking the range overlap in
the zone order and considering the first matching zone as the default
one. If there is no such zone then assume ZONE_NORMAL as we have been
doing so far.
Fixes: "mm, memory_hotplug: do not associate hotadded memory to zones until online"
Reported-by: Heiko Carstens <heiko.carstens@...ibm.com>
Signed-off-by: Michal Hocko <mhocko@...e.com>
---
drivers/base/memory.c | 2 +-
include/linux/memory_hotplug.h | 2 ++
mm/memory_hotplug.c | 22 +++++++++++++++++++---
3 files changed, 22 insertions(+), 4 deletions(-)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index b86fda30ce62..c7c4e0325cdb 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -419,7 +419,7 @@ static ssize_t show_valid_zones(struct device *dev,
nid = pfn_to_nid(start_pfn);
if (allow_online_pfn_range(nid, start_pfn, nr_pages, MMOP_ONLINE_KERNEL)) {
- strcat(buf, NODE_DATA(nid)->node_zones[ZONE_NORMAL].name);
+ strcat(buf, default_zone_for_pfn(nid, start_pfn, nr_pages)->name);
append = true;
}
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 9e0249d0f5e4..ed167541e4fc 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -309,4 +309,6 @@ extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
unsigned long pnum);
extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
int online_type);
+extern struct zone *default_zone_for_pfn(int nid, unsigned long pfn,
+ unsigned long nr_pages);
#endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0a895df2397e..792c098e0e5f 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -858,7 +858,7 @@ bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
{
struct pglist_data *pgdat = NODE_DATA(nid);
struct zone *movable_zone = &pgdat->node_zones[ZONE_MOVABLE];
- struct zone *normal_zone = &pgdat->node_zones[ZONE_NORMAL];
+ struct zone *default_zone = default_zone_for_pfn(nid, pfn, nr_pages);
/*
* TODO there shouldn't be any inherent reason to have ZONE_NORMAL
@@ -872,7 +872,7 @@ bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
return true;
return movable_zone->zone_start_pfn >= pfn + nr_pages;
} else if (online_type == MMOP_ONLINE_MOVABLE) {
- return zone_end_pfn(normal_zone) <= pfn;
+ return zone_end_pfn(default_zone) <= pfn;
}
/* MMOP_ONLINE_KEEP will always succeed and inherits the current zone */
@@ -937,6 +937,22 @@ void __ref move_pfn_range_to_zone(struct zone *zone,
set_zone_contiguous(zone);
}
+struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn,
+ unsigned long nr_pages)
+{
+ struct pglist_data *pgdat = NODE_DATA(nid);
+ int zid;
+
+ for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+ struct zone *zone = &pgdat->node_zones[zid];
+
+ if (zone_intersects(zone, start_pfn, nr_pages))
+ return zone;
+ }
+
+ return &pgdat->node_zones[ZONE_NORMAL];
+}
+
/*
* Associates the given pfn range with the given node and the zone appropriate
* for the given online type.
@@ -945,7 +961,7 @@ static struct zone * __meminit move_pfn_range(int online_type, int nid,
unsigned long start_pfn, unsigned long nr_pages)
{
struct pglist_data *pgdat = NODE_DATA(nid);
- struct zone *zone = &pgdat->node_zones[ZONE_NORMAL];
+ struct zone *zone = default_zone_for_pfn(nid, start_pfn, nr_pages);
if (online_type == MMOP_ONLINE_KEEP) {
struct zone *movable_zone = &pgdat->node_zones[ZONE_MOVABLE];
--
2.11.0
--
Michal Hocko
SUSE Labs
Powered by blists - more mailing lists