From 956f8b445061667c3545baa24778f890d1d522f4 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 6 Apr 2020 20:07:16 -0700 Subject: [PATCH] drivers/base/memory: rename MMOP_ONLINE_KEEP to MMOP_ONLINE Patch series "mm/memory_hotplug: allow to specify a default online_type", v3. Distributions nowadays use udev rules ([1] [2]) to specify if and how to online hotplugged memory. The rules seem to get more complex with many special cases. Due to the various special cases, CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE cannot be used. All memory hotplug is handled via udev rules. Every time we hotplug memory, the udev rule will come to the same conclusion. Especially Hyper-V (but also soon virtio-mem) add a lot of memory in separate memory blocks and wait for memory to get onlined by user space before continuing to add more memory blocks (to not add memory faster than it is getting onlined). This of course slows down the whole memory hotplug process. To make the job of distributions easier and to avoid udev rules that get more and more complicated, let's extend the mechanism provided by - /sys/devices/system/memory/auto_online_blocks - "memhp_default_state=" on the kernel cmdline to be able to specify also "online_movable" as well as "online_kernel" === Example /usr/libexec/config-memhotplug === #!/bin/bash VIRT=`systemd-detect-virt --vm` ARCH=`uname -p` sense_virtio_mem() { if [ -d "/sys/bus/virtio/drivers/virtio_mem/" ]; then DEVICES=`find /sys/bus/virtio/drivers/virtio_mem/ -maxdepth 1 -type l | wc -l` if [ $DEVICES != "0" ]; then return 0 fi fi return 1 } if [ ! -e "/sys/devices/system/memory/auto_online_blocks" ]; then echo "Memory hotplug configuration support missing in the kernel" exit 1 fi if grep "memhp_default_state=" /proc/cmdline > /dev/null; then echo "Memory hotplug configuration overridden in kernel cmdline (memhp_default_state=)" exit 1 fi if [ $VIRT == "microsoft" ]; then echo "Detected Hyper-V on $ARCH" # Hyper-V wants all memory in ZONE_NORMAL ONLINE_TYPE="online_kernel" elif sense_virtio_mem; then echo "Detected virtio-mem on $ARCH" # virtio-mem wants all memory in ZONE_NORMAL ONLINE_TYPE="online_kernel" elif [ $ARCH == "s390x" ] || [ $ARCH == "s390" ]; then echo "Detected $ARCH" # standby memory should not be onlined automatically ONLINE_TYPE="offline" elif [ $ARCH == "ppc64" ] || [ $ARCH == "ppc64le" ]; then echo "Detected" $ARCH # PPC64 onlines all hotplugged memory right from the kernel ONLINE_TYPE="offline" elif [ $VIRT == "none" ]; then echo "Detected bare-metal on $ARCH" # Bare metal users expect hotplugged memory to be unpluggable. We assume # that ZONE imbalances on such enterpise servers cannot happen and is # properly documented ONLINE_TYPE="online_movable" else # TODO: Hypervisors that want to unplug DIMMs and can guarantee that ZONE # imbalances won't happen echo "Detected $VIRT on $ARCH" # Usually, ballooning is used in virtual environments, so memory should go to # ZONE_NORMAL. However, sometimes "movable_node" is relevant. ONLINE_TYPE="online" fi echo "Selected online_type:" $ONLINE_TYPE # Configure what to do with memory that will be hotplugged in the future echo $ONLINE_TYPE 2>/dev/null > /sys/devices/system/memory/auto_online_blocks if [ $? != "0" ]; then echo "Memory hotplug cannot be configured (e.g., old kernel or missing permissions)" # A backup udev rule should handle old kernels if necessary exit 1 fi # Process all already pluggedd blocks (e.g., DIMMs, but also Hyper-V or virtio-mem) if [ $ONLINE_TYPE != "offline" ]; then for MEMORY in /sys/devices/system/memory/memory*; do STATE=`cat $MEMORY/state` if [ $STATE == "offline" ]; then echo $ONLINE_TYPE > $MEMORY/state fi done fi === Example /usr/lib/systemd/system/config-memhotplug.service === [Unit] Description=Configure memory hotplug behavior DefaultDependencies=no Conflicts=shutdown.target Before=sysinit.target shutdown.target After=systemd-modules-load.service ConditionPathExists=|/sys/devices/system/memory/auto_online_blocks [Service] ExecStart=/usr/libexec/config-memhotplug Type=oneshot TimeoutSec=0 RemainAfterExit=yes [Install] WantedBy=sysinit.target === Example modification to the 40-redhat.rules [2] === : diff --git a/40-redhat.rules b/40-redhat.rules-new : index 2c690e5..168fd03 100644 : --- a/40-redhat.rules : +++ b/40-redhat.rules-new : @@ -6,6 +6,9 @@ SUBSYSTEM=="cpu", ACTION=="add", TEST=="online", ATTR{online}=="0", ATTR{online} : # Memory hotadd request : SUBSYSTEM!="memory", GOTO="memory_hotplug_end" : ACTION!="add", GOTO="memory_hotplug_end" : +# memory hotplug behavior configured : +PROGRAM=="grep online /sys/devices/system/memory/auto_online_blocks", GOTO="memory_hotplug_end" : + : PROGRAM="/bin/uname -p", RESULT=="s390*", GOTO="memory_hotplug_end" : : ENV{.state}="online" === [1] https://github.com/lnykryn/systemd-rhel/pull/281 [2] https://github.com/lnykryn/systemd-rhel/blob/staging/rules/40-redhat.rules This patch (of 8): The name is misleading and it's not really clear what is "kept". Let's just name it like the online_type name we expose to user space ("online"). Add some documentation to the types. Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton Reviewed-by: Wei Yang Reviewed-by: Baoquan He Acked-by: Pankaj Gupta Cc: Greg Kroah-Hartman Cc: Michal Hocko Cc: Oscar Salvador Cc: "Rafael J. Wysocki" Cc: Wei Yang Cc: Vitaly Kuznetsov Cc: Yumei Huang Cc: Igor Mammedov Cc: Eduardo Habkost Cc: Benjamin Herrenschmidt Cc: Haiyang Zhang Cc: K. Y. Srinivasan Cc: Michael Ellerman (powerpc) Cc: Paul Mackerras Cc: Stephen Hemminger Cc: Wei Liu Link: http://lkml.kernel.org/r/20200319131221.14044-1-david@redhat.com Link: http://lkml.kernel.org/r/20200317104942.11178-2-david@redhat.com Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 9 +++++---- include/linux/memory_hotplug.h | 6 +++++- 2 files changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 96c80dfaac90..156b89b14fcc 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -208,7 +208,7 @@ static int memory_subsys_online(struct device *dev) * attribute and need to set the online_type. */ if (mem->online_type < 0) - mem->online_type = MMOP_ONLINE_KEEP; + mem->online_type = MMOP_ONLINE; ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE); @@ -243,7 +243,7 @@ static ssize_t state_store(struct device *dev, struct device_attribute *attr, else if (sysfs_streq(buf, "online_movable")) online_type = MMOP_ONLINE_MOVABLE; else if (sysfs_streq(buf, "online")) - online_type = MMOP_ONLINE_KEEP; + online_type = MMOP_ONLINE; else if (sysfs_streq(buf, "offline")) online_type = MMOP_OFFLINE; else { @@ -254,7 +254,7 @@ static ssize_t state_store(struct device *dev, struct device_attribute *attr, switch (online_type) { case MMOP_ONLINE_KERNEL: case MMOP_ONLINE_MOVABLE: - case MMOP_ONLINE_KEEP: + case MMOP_ONLINE: /* mem->online_type is protected by device_hotplug_lock */ mem->online_type = online_type; ret = device_online(&mem->dev); @@ -334,7 +334,8 @@ static ssize_t valid_zones_show(struct device *dev, } nid = mem->nid; - default_zone = zone_for_pfn_range(MMOP_ONLINE_KEEP, nid, start_pfn, nr_pages); + default_zone = zone_for_pfn_range(MMOP_ONLINE, nid, start_pfn, + nr_pages); strcat(buf, default_zone->name); print_allowed_zone(buf, nid, start_pfn, nr_pages, MMOP_ONLINE_KERNEL, diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index f4d59155f3d4..261dbf010d5d 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -47,9 +47,13 @@ enum { /* Types for control the zone type of onlined and offlined memory */ enum { + /* Offline the memory. */ MMOP_OFFLINE = -1, - MMOP_ONLINE_KEEP, + /* Online the memory. Zone depends, see default_zone_for_pfn(). */ + MMOP_ONLINE, + /* Online the memory to ZONE_NORMAL. */ MMOP_ONLINE_KERNEL, + /* Online the memory to ZONE_MOVABLE. */ MMOP_ONLINE_MOVABLE, };