On 19.10.20 05:48, Wei Yang wrote:
> On Mon, Oct 12, 2020 at 02:53:22PM +0200, David Hildenbrand wrote:
>> Let's try to unplug completely offline big blocks first. Then, (if
>> enabled via unplug_offline) try to offline and remove whole big blocks.
>>
>> No locking necessary - we can deal with concurrent onlining/offlining
>> just fine.
>>
>> Note1: This is sub-optimal and might be dangerous in some environments: we
>> could end up in an infinite loop when offlining (e.g., long-term pinnings),
>> similar as with DIMMs. We'll introduce safe memory hotunplug via
>> fake-offlining next, and use this basic mode only when explicitly enabled.
>>
>> Note2: Without ZONE_MOVABLE, memory unplug will be extremely unreliable
>> with bigger block sizes.
>>
>> Cc: "Michael S. Tsirkin" <mst@xxxxxxxxxx>
>> Cc: Jason Wang <jasowang@xxxxxxxxxx>
>> Cc: Pankaj Gupta <pankaj.gupta.linux@xxxxxxxxx>
>> Cc: Michal Hocko <mhocko@xxxxxxxxxx>
>> Cc: Oscar Salvador <osalvador@xxxxxxx>
>> Cc: Wei Yang <richard.weiyang@xxxxxxxxxxxxxxxxx>
>> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
>> Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
>> ---
>> drivers/virtio/virtio_mem.c | 156 +++++++++++++++++++++++++++++++++++-
>> 1 file changed, 155 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
>> index 94cf44b15cbf..6bcd0acbff32 100644
>> --- a/drivers/virtio/virtio_mem.c
>> +++ b/drivers/virtio/virtio_mem.c
>> @@ -388,6 +388,12 @@ static int virtio_mem_bbm_bb_states_prepare_next_bb(struct virtio_mem *vm)
>> _bb_id++) \
>> if (virtio_mem_bbm_get_bb_state(_vm, _bb_id) == _state)
>>
>> +#define virtio_mem_bbm_for_each_bb_rev(_vm, _bb_id, _state) \
>> + for (_bb_id = vm->bbm.next_bb_id - 1; \
>> + _bb_id >= vm->bbm.first_bb_id && _vm->bbm.bb_count[_state]; \
>> + _bb_id--) \
>> + if (virtio_mem_bbm_get_bb_state(_vm, _bb_id) == _state)
>> +
>> /*
>> * Set the state of a memory block, taking care of the state counter.
>> */
>> @@ -685,6 +691,18 @@ static int virtio_mem_sbm_remove_mb(struct virtio_mem *vm, unsigned long mb_id)
>> return virtio_mem_remove_memory(vm, addr, size);
>> }
>>
>> +/*
>> + * See virtio_mem_remove_memory(): Try to remove all Linux memory blocks covered
>> + * by the big block.
>> + */
>> +static int virtio_mem_bbm_remove_bb(struct virtio_mem *vm, unsigned long bb_id)
>> +{
>> + const uint64_t addr = virtio_mem_bb_id_to_phys(vm, bb_id);
>> + const uint64_t size = vm->bbm.bb_size;
>> +
>> + return virtio_mem_remove_memory(vm, addr, size);
>> +}
>> +
>> /*
>> * Try offlining and removing memory from Linux.
>> *
>> @@ -731,6 +749,19 @@ static int virtio_mem_sbm_offline_and_remove_mb(struct virtio_mem *vm,
>> return virtio_mem_offline_and_remove_memory(vm, addr, size);
>> }
>>
>> +/*
>> + * See virtio_mem_offline_and_remove_memory(): Try to offline and remove a
>> + * all Linux memory blocks covered by the big block.
>> + */
>> +static int virtio_mem_bbm_offline_and_remove_bb(struct virtio_mem *vm,
>> + unsigned long bb_id)
>> +{
>> + const uint64_t addr = virtio_mem_bb_id_to_phys(vm, bb_id);
>> + const uint64_t size = vm->bbm.bb_size;
>> +
>> + return virtio_mem_offline_and_remove_memory(vm, addr, size);
>> +}
>> +
>> /*
>> * Trigger the workqueue so the device can perform its magic.
>> */
>> @@ -1928,6 +1959,129 @@ static int virtio_mem_sbm_unplug_request(struct virtio_mem *vm, uint64_t diff)
>> return rc;
>> }
>>
>> +/*
>> + * Try to offline and remove a big block from Linux and unplug it. Will fail
>> + * with -EBUSY if some memory is busy and cannot get unplugged.
>> + *
>> + * Will modify the state of the memory block. Might temporarily drop the
>> + * hotplug_mutex.
>> + */
>> +static int virtio_mem_bbm_offline_remove_and_unplug_bb(struct virtio_mem *vm,
>> + unsigned long bb_id)
>> +{
>> + int rc;
>> +
>> + if (WARN_ON_ONCE(virtio_mem_bbm_get_bb_state(vm, bb_id) !=
>> + VIRTIO_MEM_BBM_BB_ADDED))
>> + return -EINVAL;
>> +
>> + rc = virtio_mem_bbm_offline_and_remove_bb(vm, bb_id);
>> + if (rc)
>> + return rc;
>> +
>> + rc = virtio_mem_bbm_unplug_bb(vm, bb_id);
>> + if (rc)
>> + virtio_mem_bbm_set_bb_state(vm, bb_id,
>> + VIRTIO_MEM_BBM_BB_PLUGGED);
>> + else
>> + virtio_mem_bbm_set_bb_state(vm, bb_id,
>> + VIRTIO_MEM_BBM_BB_UNUSED);
>> + return rc;
>> +}
>> +
>> +/*
>> + * Try to remove a big block from Linux and unplug it. Will fail with
>> + * -EBUSY if some memory is online.
>> + *
>> + * Will modify the state of the memory block.
>> + */
>> +static int virtio_mem_bbm_remove_and_unplug_bb(struct virtio_mem *vm,
>> + unsigned long bb_id)
>> +{
>> + int rc;
>> +
>> + if (WARN_ON_ONCE(virtio_mem_bbm_get_bb_state(vm, bb_id) !=
>> + VIRTIO_MEM_BBM_BB_ADDED))
>> + return -EINVAL;
>> +
>> + rc = virtio_mem_bbm_remove_bb(vm, bb_id);
>> + if (rc)
>> + return -EBUSY;
>> +
>> + rc = virtio_mem_bbm_unplug_bb(vm, bb_id);
>> + if (rc)
>> + virtio_mem_bbm_set_bb_state(vm, bb_id,
>> + VIRTIO_MEM_BBM_BB_PLUGGED);
>> + else
>> + virtio_mem_bbm_set_bb_state(vm, bb_id,
>> + VIRTIO_MEM_BBM_BB_UNUSED);
>> + return rc;
>> +}
>> +
>> +/*
>> + * Test if a big block is completely offline.
>> + */
>> +static bool virtio_mem_bbm_bb_is_offline(struct virtio_mem *vm,
>> + unsigned long bb_id)
>> +{
>> + const unsigned long start_pfn = PFN_DOWN(virtio_mem_bb_id_to_phys(vm, bb_id));
>> + const unsigned long nr_pages = PFN_DOWN(vm->bbm.bb_size);
>> + unsigned long pfn;
>> +
>> + for (pfn = start_pfn; pfn < start_pfn + nr_pages;
>> + pfn += PAGES_PER_SECTION) {
>
> Can we do the check with memory block granularity?
I had that initially, but the code turned out nicer this way (e.g.,
PAGES_PER_SECTION).
--
Thanks,
David / dhildenb
