472f948330
commit 63341ab03706e11a31e3dd8ccc0fbc9beaf723f0 upstream.
In case we have to migrate a ballon page to a newpage of another zone, the
managed page count of both zones is wrong. Paired with memory offlining
(which will adjust the managed page count), we can trigger kernel crashes
and all kinds of different symptoms.
One way to reproduce:
1. Start a QEMU guest with 4GB, no NUMA
2. Hotplug a 1GB DIMM and online the memory to ZONE_NORMAL
3. Inflate the balloon to 1GB
4. Unplug the DIMM (be quick, otherwise unmovable data ends up on it)
5. Observe /proc/zoneinfo
Node 0, zone Normal
pages free 16810
min 24848885473806
low 18471592959183339
high 36918337032892872
spanned 262144
present 262144
managed 18446744073709533486
6. Do anything that requires some memory (e.g., inflate the balloon some
more). The OOM goes crazy and the system crashes
[ 238.324946] Out of memory: Killed process 537 (login) total-vm:27584kB, anon-rss:860kB, file-rss:0kB, shmem-rss:00
[ 238.338585] systemd invoked oom-killer: gfp_mask=0x100cca(GFP_HIGHUSER_MOVABLE), order=0, oom_score_adj=0
[ 238.339420] CPU: 0 PID: 1 Comm: systemd Tainted: G D W 5.4.0-next-20191204+ #75
[ 238.340139] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu4
[ 238.341121] Call Trace:
[ 238.341337] dump_stack+0x8f/0xd0
[ 238.341630] dump_header+0x61/0x5ea
[ 238.341942] oom_kill_process.cold+0xb/0x10
[ 238.342299] out_of_memory+0x24d/0x5a0
[ 238.342625] __alloc_pages_slowpath+0xd12/0x1020
[ 238.343024] __alloc_pages_nodemask+0x391/0x410
[ 238.343407] pagecache_get_page+0xc3/0x3a0
[ 238.343757] filemap_fault+0x804/0xc30
[ 238.344083] ? ext4_filemap_fault+0x28/0x42
[ 238.344444] ext4_filemap_fault+0x30/0x42
[ 238.344789] __do_fault+0x37/0x1a0
[ 238.345087] __handle_mm_fault+0x104d/0x1ab0
[ 238.345450] handle_mm_fault+0x169/0x360
[ 238.345790] do_user_addr_fault+0x20d/0x490
[ 238.346154] do_page_fault+0x31/0x210
[ 238.346468] async_page_fault+0x43/0x50
[ 238.346797] RIP: 0033:0x7f47eba4197e
[ 238.347110] Code: Bad RIP value.
[ 238.347387] RSP: 002b:00007ffd7c0c1890 EFLAGS: 00010293
[ 238.347834] RAX: 0000000000000002 RBX: 000055d196a20a20 RCX: 00007f47eba4197e
[ 238.348437] RDX: 0000000000000033 RSI: 00007ffd7c0c18c0 RDI: 0000000000000004
[ 238.349047] RBP: 00007ffd7c0c1c20 R08: 0000000000000000 R09: 0000000000000033
[ 238.349660] R10: 00000000ffffffff R11: 0000000000000293 R12: 0000000000000001
[ 238.350261] R13: ffffffffffffffff R14: 0000000000000000 R15: 00007ffd7c0c18c0
[ 238.350878] Mem-Info:
[ 238.351085] active_anon:3121 inactive_anon:51 isolated_anon:0
[ 238.351085] active_file:12 inactive_file:7 isolated_file:0
[ 238.351085] unevictable:0 dirty:0 writeback:0 unstable:0
[ 238.351085] slab_reclaimable:5565 slab_unreclaimable:10170
[ 238.351085] mapped:3 shmem:111 pagetables:155 bounce:0
[ 238.351085] free:720717 free_pcp:2 free_cma:0
[ 238.353757] Node 0 active_anon:12484kB inactive_anon:204kB active_file:48kB inactive_file:28kB unevictable:0kB iss
[ 238.355979] Node 0 DMA free:11556kB min:36kB low:48kB high:60kB reserved_highatomic:0KB active_anon:152kB inactivB
[ 238.358345] lowmem_reserve[]: 0 2955 2884 2884 2884
[ 238.358761] Node 0 DMA32 free:2677864kB min:7004kB low:10028kB high:13052kB reserved_highatomic:0KB active_anon:0B
[ 238.361202] lowmem_reserve[]: 0 0 72057594037927865 72057594037927865 72057594037927865
[ 238.361888] Node 0 Normal free:193448kB min:99395541895224kB low:73886371836733356kB high:147673348131571488kB reB
[ 238.364765] lowmem_reserve[]: 0 0 0 0 0
[ 238.365101] Node 0 DMA: 7*4kB (U) 5*8kB (UE) 6*16kB (UME) 2*32kB (UM) 1*64kB (U) 2*128kB (UE) 3*256kB (UME) 2*512B
[ 238.366379] Node 0 DMA32: 0*4kB 1*8kB (U) 2*16kB (UM) 2*32kB (UM) 2*64kB (UM) 1*128kB (U) 1*256kB (U) 1*512kB (U)B
[ 238.367654] Node 0 Normal: 1985*4kB (UME) 1321*8kB (UME) 844*16kB (UME) 524*32kB (UME) 300*64kB (UME) 138*128kB (B
[ 238.369184] Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 hugepages_size=2048kB
[ 238.369915] 130 total pagecache pages
[ 238.370241] 0 pages in swap cache
[ 238.370533] Swap cache stats: add 0, delete 0, find 0/0
[ 238.370981] Free swap = 0kB
[ 238.371239] Total swap = 0kB
[ 238.371488] 1048445 pages RAM
[ 238.371756] 0 pages HighMem/MovableOnly
[ 238.372090] 306992 pages reserved
[ 238.372376] 0 pages cma reserved
[ 238.372661] 0 pages hwpoisoned
In another instance (older kernel), I was able to observe this
(negative page count :/):
[ 180.896971] Offlined Pages 32768
[ 182.667462] Offlined Pages 32768
[ 184.408117] Offlined Pages 32768
[ 186.026321] Offlined Pages 32768
[ 187.684861] Offlined Pages 32768
[ 189.227013] Offlined Pages 32768
[ 190.830303] Offlined Pages 32768
[ 190.833071] Built 1 zonelists, mobility grouping on. Total pages: -36920272750453009
In another instance (older kernel), I was no longer able to start any
process:
[root@vm ~]# [ 214.348068] Offlined Pages 32768
[ 215.973009] Offlined Pages 32768
cat /proc/meminfo
-bash: fork: Cannot allocate memory
[root@vm ~]# cat /proc/meminfo
-bash: fork: Cannot allocate memory
Fix it by properly adjusting the managed page count when migrating if
the zone changed. The managed page count of the zones now looks after
unplug of the DIMM (and after deflating the balloon) just like before
inflating the balloon (and plugging+onlining the DIMM).
We'll temporarily modify the totalram page count. If this ever becomes a
problem, we can fine tune by providing helpers that don't touch
the totalram pages (e.g., adjust_zone_managed_page_count()).
Please note that fixing up the managed page count is only necessary when
we adjusted the managed page count when inflating - only if we
don't have VIRTIO_BALLOON_F_DEFLATE_ON_OOM. With that feature, the
managed page count is not touched when inflating/deflating.
Reported-by: Yumei Huang <yuhuang@redhat.com>
Fixes: 3dcc0571cd
("mm: correctly update zone->managed_pages")
Cc: <stable@vger.kernel.org> # v3.11+
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: virtualization@lists.linux-foundation.org
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
738 lines
20 KiB
C
738 lines
20 KiB
C
/*
|
|
* Virtio balloon implementation, inspired by Dor Laor and Marcelo
|
|
* Tosatti's implementations.
|
|
*
|
|
* Copyright 2008 Rusty Russell IBM Corporation
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write to the Free Software
|
|
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
|
|
*/
|
|
|
|
#include <linux/virtio.h>
|
|
#include <linux/virtio_balloon.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/delay.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/module.h>
|
|
#include <linux/balloon_compaction.h>
|
|
#include <linux/wait.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/mount.h>
|
|
#include <linux/magic.h>
|
|
|
|
/*
|
|
* Balloon device works in 4K page units. So each page is pointed to by
|
|
* multiple balloon pages. All memory counters in this driver are in balloon
|
|
* page units.
|
|
*/
|
|
#define VIRTIO_BALLOON_PAGES_PER_PAGE (unsigned)(PAGE_SIZE >> VIRTIO_BALLOON_PFN_SHIFT)
|
|
#define VIRTIO_BALLOON_ARRAY_PFNS_MAX 256
|
|
#define VIRTBALLOON_OOM_NOTIFY_PRIORITY 80
|
|
|
|
#ifdef CONFIG_BALLOON_COMPACTION
|
|
static struct vfsmount *balloon_mnt;
|
|
#endif
|
|
|
|
struct virtio_balloon {
|
|
struct virtio_device *vdev;
|
|
struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
|
|
|
|
/* The balloon servicing is delegated to a freezable workqueue. */
|
|
struct work_struct update_balloon_stats_work;
|
|
struct work_struct update_balloon_size_work;
|
|
|
|
/* Prevent updating balloon when it is being canceled. */
|
|
spinlock_t stop_update_lock;
|
|
bool stop_update;
|
|
|
|
/* Waiting for host to ack the pages we released. */
|
|
wait_queue_head_t acked;
|
|
|
|
/* Number of balloon pages we've told the Host we're not using. */
|
|
unsigned int num_pages;
|
|
/*
|
|
* The pages we've told the Host we're not using are enqueued
|
|
* at vb_dev_info->pages list.
|
|
* Each page on this list adds VIRTIO_BALLOON_PAGES_PER_PAGE
|
|
* to num_pages above.
|
|
*/
|
|
struct balloon_dev_info vb_dev_info;
|
|
|
|
/* Synchronize access/update to this struct virtio_balloon elements */
|
|
struct mutex balloon_lock;
|
|
|
|
/* The array of pfns we tell the Host about. */
|
|
unsigned int num_pfns;
|
|
__virtio32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX];
|
|
|
|
/* Memory statistics */
|
|
struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
|
|
|
|
/* To register a shrinker to shrink memory upon memory pressure */
|
|
struct shrinker shrinker;
|
|
};
|
|
|
|
static struct virtio_device_id id_table[] = {
|
|
{ VIRTIO_ID_BALLOON, VIRTIO_DEV_ANY_ID },
|
|
{ 0 },
|
|
};
|
|
|
|
static u32 page_to_balloon_pfn(struct page *page)
|
|
{
|
|
unsigned long pfn = page_to_pfn(page);
|
|
|
|
BUILD_BUG_ON(PAGE_SHIFT < VIRTIO_BALLOON_PFN_SHIFT);
|
|
/* Convert pfn from Linux page size to balloon page size. */
|
|
return pfn * VIRTIO_BALLOON_PAGES_PER_PAGE;
|
|
}
|
|
|
|
static void balloon_ack(struct virtqueue *vq)
|
|
{
|
|
struct virtio_balloon *vb = vq->vdev->priv;
|
|
|
|
wake_up(&vb->acked);
|
|
}
|
|
|
|
static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq)
|
|
{
|
|
struct scatterlist sg;
|
|
unsigned int len;
|
|
|
|
sg_init_one(&sg, vb->pfns, sizeof(vb->pfns[0]) * vb->num_pfns);
|
|
|
|
/* We should always be able to add one buffer to an empty queue. */
|
|
virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
|
|
virtqueue_kick(vq);
|
|
|
|
/* When host has read buffer, this completes via balloon_ack */
|
|
wait_event(vb->acked, virtqueue_get_buf(vq, &len));
|
|
|
|
}
|
|
|
|
static void set_page_pfns(struct virtio_balloon *vb,
|
|
__virtio32 pfns[], struct page *page)
|
|
{
|
|
unsigned int i;
|
|
|
|
/*
|
|
* Set balloon pfns pointing at this page.
|
|
* Note that the first pfn points at start of the page.
|
|
*/
|
|
for (i = 0; i < VIRTIO_BALLOON_PAGES_PER_PAGE; i++)
|
|
pfns[i] = cpu_to_virtio32(vb->vdev,
|
|
page_to_balloon_pfn(page) + i);
|
|
}
|
|
|
|
static unsigned fill_balloon(struct virtio_balloon *vb, size_t num)
|
|
{
|
|
unsigned num_allocated_pages;
|
|
unsigned num_pfns;
|
|
struct page *page;
|
|
LIST_HEAD(pages);
|
|
|
|
/* We can only do one array worth at a time. */
|
|
num = min(num, ARRAY_SIZE(vb->pfns));
|
|
|
|
for (num_pfns = 0; num_pfns < num;
|
|
num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
|
|
struct page *page = balloon_page_alloc();
|
|
|
|
if (!page) {
|
|
dev_info_ratelimited(&vb->vdev->dev,
|
|
"Out of puff! Can't get %u pages\n",
|
|
VIRTIO_BALLOON_PAGES_PER_PAGE);
|
|
/* Sleep for at least 1/5 of a second before retry. */
|
|
msleep(200);
|
|
break;
|
|
}
|
|
|
|
balloon_page_push(&pages, page);
|
|
}
|
|
|
|
mutex_lock(&vb->balloon_lock);
|
|
|
|
vb->num_pfns = 0;
|
|
|
|
while ((page = balloon_page_pop(&pages))) {
|
|
balloon_page_enqueue(&vb->vb_dev_info, page);
|
|
|
|
set_page_pfns(vb, vb->pfns + vb->num_pfns, page);
|
|
vb->num_pages += VIRTIO_BALLOON_PAGES_PER_PAGE;
|
|
if (!virtio_has_feature(vb->vdev,
|
|
VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
|
|
adjust_managed_page_count(page, -1);
|
|
vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE;
|
|
}
|
|
|
|
num_allocated_pages = vb->num_pfns;
|
|
/* Did we get any? */
|
|
if (vb->num_pfns != 0)
|
|
tell_host(vb, vb->inflate_vq);
|
|
mutex_unlock(&vb->balloon_lock);
|
|
|
|
return num_allocated_pages;
|
|
}
|
|
|
|
static void release_pages_balloon(struct virtio_balloon *vb,
|
|
struct list_head *pages)
|
|
{
|
|
struct page *page, *next;
|
|
|
|
list_for_each_entry_safe(page, next, pages, lru) {
|
|
if (!virtio_has_feature(vb->vdev,
|
|
VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
|
|
adjust_managed_page_count(page, 1);
|
|
list_del(&page->lru);
|
|
put_page(page); /* balloon reference */
|
|
}
|
|
}
|
|
|
|
static unsigned leak_balloon(struct virtio_balloon *vb, size_t num)
|
|
{
|
|
unsigned num_freed_pages;
|
|
struct page *page;
|
|
struct balloon_dev_info *vb_dev_info = &vb->vb_dev_info;
|
|
LIST_HEAD(pages);
|
|
|
|
/* We can only do one array worth at a time. */
|
|
num = min(num, ARRAY_SIZE(vb->pfns));
|
|
|
|
mutex_lock(&vb->balloon_lock);
|
|
/* We can't release more pages than taken */
|
|
num = min(num, (size_t)vb->num_pages);
|
|
for (vb->num_pfns = 0; vb->num_pfns < num;
|
|
vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
|
|
page = balloon_page_dequeue(vb_dev_info);
|
|
if (!page)
|
|
break;
|
|
set_page_pfns(vb, vb->pfns + vb->num_pfns, page);
|
|
list_add(&page->lru, &pages);
|
|
vb->num_pages -= VIRTIO_BALLOON_PAGES_PER_PAGE;
|
|
}
|
|
|
|
num_freed_pages = vb->num_pfns;
|
|
/*
|
|
* Note that if
|
|
* virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
|
|
* is true, we *have* to do it in this order
|
|
*/
|
|
if (vb->num_pfns != 0)
|
|
tell_host(vb, vb->deflate_vq);
|
|
release_pages_balloon(vb, &pages);
|
|
mutex_unlock(&vb->balloon_lock);
|
|
return num_freed_pages;
|
|
}
|
|
|
|
static inline void update_stat(struct virtio_balloon *vb, int idx,
|
|
u16 tag, u64 val)
|
|
{
|
|
BUG_ON(idx >= VIRTIO_BALLOON_S_NR);
|
|
vb->stats[idx].tag = cpu_to_virtio16(vb->vdev, tag);
|
|
vb->stats[idx].val = cpu_to_virtio64(vb->vdev, val);
|
|
}
|
|
|
|
#define pages_to_bytes(x) ((u64)(x) << PAGE_SHIFT)
|
|
|
|
static unsigned int update_balloon_stats(struct virtio_balloon *vb)
|
|
{
|
|
unsigned long events[NR_VM_EVENT_ITEMS];
|
|
struct sysinfo i;
|
|
unsigned int idx = 0;
|
|
long available;
|
|
unsigned long caches;
|
|
|
|
all_vm_events(events);
|
|
si_meminfo(&i);
|
|
|
|
available = si_mem_available();
|
|
caches = global_node_page_state(NR_FILE_PAGES);
|
|
|
|
#ifdef CONFIG_VM_EVENT_COUNTERS
|
|
update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_IN,
|
|
pages_to_bytes(events[PSWPIN]));
|
|
update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_OUT,
|
|
pages_to_bytes(events[PSWPOUT]));
|
|
update_stat(vb, idx++, VIRTIO_BALLOON_S_MAJFLT, events[PGMAJFAULT]);
|
|
update_stat(vb, idx++, VIRTIO_BALLOON_S_MINFLT, events[PGFAULT]);
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
update_stat(vb, idx++, VIRTIO_BALLOON_S_HTLB_PGALLOC,
|
|
events[HTLB_BUDDY_PGALLOC]);
|
|
update_stat(vb, idx++, VIRTIO_BALLOON_S_HTLB_PGFAIL,
|
|
events[HTLB_BUDDY_PGALLOC_FAIL]);
|
|
#endif
|
|
#endif
|
|
update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMFREE,
|
|
pages_to_bytes(i.freeram));
|
|
update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMTOT,
|
|
pages_to_bytes(i.totalram));
|
|
update_stat(vb, idx++, VIRTIO_BALLOON_S_AVAIL,
|
|
pages_to_bytes(available));
|
|
update_stat(vb, idx++, VIRTIO_BALLOON_S_CACHES,
|
|
pages_to_bytes(caches));
|
|
|
|
return idx;
|
|
}
|
|
|
|
/*
|
|
* While most virtqueues communicate guest-initiated requests to the hypervisor,
|
|
* the stats queue operates in reverse. The driver initializes the virtqueue
|
|
* with a single buffer. From that point forward, all conversations consist of
|
|
* a hypervisor request (a call to this function) which directs us to refill
|
|
* the virtqueue with a fresh stats buffer. Since stats collection can sleep,
|
|
* we delegate the job to a freezable workqueue that will do the actual work via
|
|
* stats_handle_request().
|
|
*/
|
|
static void stats_request(struct virtqueue *vq)
|
|
{
|
|
struct virtio_balloon *vb = vq->vdev->priv;
|
|
|
|
spin_lock(&vb->stop_update_lock);
|
|
if (!vb->stop_update)
|
|
queue_work(system_freezable_wq, &vb->update_balloon_stats_work);
|
|
spin_unlock(&vb->stop_update_lock);
|
|
}
|
|
|
|
static void stats_handle_request(struct virtio_balloon *vb)
|
|
{
|
|
struct virtqueue *vq;
|
|
struct scatterlist sg;
|
|
unsigned int len, num_stats;
|
|
|
|
num_stats = update_balloon_stats(vb);
|
|
|
|
vq = vb->stats_vq;
|
|
if (!virtqueue_get_buf(vq, &len))
|
|
return;
|
|
sg_init_one(&sg, vb->stats, sizeof(vb->stats[0]) * num_stats);
|
|
virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
|
|
virtqueue_kick(vq);
|
|
}
|
|
|
|
static void virtballoon_changed(struct virtio_device *vdev)
|
|
{
|
|
struct virtio_balloon *vb = vdev->priv;
|
|
unsigned long flags;
|
|
|
|
spin_lock_irqsave(&vb->stop_update_lock, flags);
|
|
if (!vb->stop_update)
|
|
queue_work(system_freezable_wq, &vb->update_balloon_size_work);
|
|
spin_unlock_irqrestore(&vb->stop_update_lock, flags);
|
|
}
|
|
|
|
static inline s64 towards_target(struct virtio_balloon *vb)
|
|
{
|
|
s64 target;
|
|
u32 num_pages;
|
|
|
|
virtio_cread(vb->vdev, struct virtio_balloon_config, num_pages,
|
|
&num_pages);
|
|
|
|
/* Legacy balloon config space is LE, unlike all other devices. */
|
|
if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1))
|
|
num_pages = le32_to_cpu((__force __le32)num_pages);
|
|
|
|
target = num_pages;
|
|
return target - vb->num_pages;
|
|
}
|
|
|
|
static void update_balloon_size(struct virtio_balloon *vb)
|
|
{
|
|
u32 actual = vb->num_pages;
|
|
|
|
/* Legacy balloon config space is LE, unlike all other devices. */
|
|
if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1))
|
|
actual = (__force u32)cpu_to_le32(actual);
|
|
|
|
virtio_cwrite(vb->vdev, struct virtio_balloon_config, actual,
|
|
&actual);
|
|
}
|
|
|
|
static void update_balloon_stats_func(struct work_struct *work)
|
|
{
|
|
struct virtio_balloon *vb;
|
|
|
|
vb = container_of(work, struct virtio_balloon,
|
|
update_balloon_stats_work);
|
|
stats_handle_request(vb);
|
|
}
|
|
|
|
static void update_balloon_size_func(struct work_struct *work)
|
|
{
|
|
struct virtio_balloon *vb;
|
|
s64 diff;
|
|
|
|
vb = container_of(work, struct virtio_balloon,
|
|
update_balloon_size_work);
|
|
diff = towards_target(vb);
|
|
|
|
if (diff > 0)
|
|
diff -= fill_balloon(vb, diff);
|
|
else if (diff < 0)
|
|
diff += leak_balloon(vb, -diff);
|
|
update_balloon_size(vb);
|
|
|
|
if (diff)
|
|
queue_work(system_freezable_wq, work);
|
|
}
|
|
|
|
static int init_vqs(struct virtio_balloon *vb)
|
|
{
|
|
struct virtqueue *vqs[3];
|
|
vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
|
|
static const char * const names[] = { "inflate", "deflate", "stats" };
|
|
int err, nvqs;
|
|
|
|
/*
|
|
* We expect two virtqueues: inflate and deflate, and
|
|
* optionally stat.
|
|
*/
|
|
nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
|
|
err = virtio_find_vqs(vb->vdev, nvqs, vqs, callbacks, names, NULL);
|
|
if (err)
|
|
return err;
|
|
|
|
vb->inflate_vq = vqs[0];
|
|
vb->deflate_vq = vqs[1];
|
|
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
|
|
struct scatterlist sg;
|
|
unsigned int num_stats;
|
|
vb->stats_vq = vqs[2];
|
|
|
|
/*
|
|
* Prime this virtqueue with one buffer so the hypervisor can
|
|
* use it to signal us later (it can't be broken yet!).
|
|
*/
|
|
num_stats = update_balloon_stats(vb);
|
|
|
|
sg_init_one(&sg, vb->stats, sizeof(vb->stats[0]) * num_stats);
|
|
err = virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb,
|
|
GFP_KERNEL);
|
|
if (err) {
|
|
dev_warn(&vb->vdev->dev, "%s: add stat_vq failed\n",
|
|
__func__);
|
|
return err;
|
|
}
|
|
virtqueue_kick(vb->stats_vq);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
#ifdef CONFIG_BALLOON_COMPACTION
|
|
/*
|
|
* virtballoon_migratepage - perform the balloon page migration on behalf of
|
|
* a compation thread. (called under page lock)
|
|
* @vb_dev_info: the balloon device
|
|
* @newpage: page that will replace the isolated page after migration finishes.
|
|
* @page : the isolated (old) page that is about to be migrated to newpage.
|
|
* @mode : compaction mode -- not used for balloon page migration.
|
|
*
|
|
* After a ballooned page gets isolated by compaction procedures, this is the
|
|
* function that performs the page migration on behalf of a compaction thread
|
|
* The page migration for virtio balloon is done in a simple swap fashion which
|
|
* follows these two macro steps:
|
|
* 1) insert newpage into vb->pages list and update the host about it;
|
|
* 2) update the host about the old page removed from vb->pages list;
|
|
*
|
|
* This function preforms the balloon page migration task.
|
|
* Called through balloon_mapping->a_ops->migratepage
|
|
*/
|
|
static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info,
|
|
struct page *newpage, struct page *page, enum migrate_mode mode)
|
|
{
|
|
struct virtio_balloon *vb = container_of(vb_dev_info,
|
|
struct virtio_balloon, vb_dev_info);
|
|
unsigned long flags;
|
|
|
|
/*
|
|
* In order to avoid lock contention while migrating pages concurrently
|
|
* to leak_balloon() or fill_balloon() we just give up the balloon_lock
|
|
* this turn, as it is easier to retry the page migration later.
|
|
* This also prevents fill_balloon() getting stuck into a mutex
|
|
* recursion in the case it ends up triggering memory compaction
|
|
* while it is attempting to inflate the ballon.
|
|
*/
|
|
if (!mutex_trylock(&vb->balloon_lock))
|
|
return -EAGAIN;
|
|
|
|
get_page(newpage); /* balloon reference */
|
|
|
|
/*
|
|
* When we migrate a page to a different zone and adjusted the
|
|
* managed page count when inflating, we have to fixup the count of
|
|
* both involved zones.
|
|
*/
|
|
if (!virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM) &&
|
|
page_zone(page) != page_zone(newpage)) {
|
|
adjust_managed_page_count(page, 1);
|
|
adjust_managed_page_count(newpage, -1);
|
|
}
|
|
|
|
/* balloon's page migration 1st step -- inflate "newpage" */
|
|
spin_lock_irqsave(&vb_dev_info->pages_lock, flags);
|
|
balloon_page_insert(vb_dev_info, newpage);
|
|
vb_dev_info->isolated_pages--;
|
|
__count_vm_event(BALLOON_MIGRATE);
|
|
spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags);
|
|
vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
|
|
set_page_pfns(vb, vb->pfns, newpage);
|
|
tell_host(vb, vb->inflate_vq);
|
|
|
|
/* balloon's page migration 2nd step -- deflate "page" */
|
|
spin_lock_irqsave(&vb_dev_info->pages_lock, flags);
|
|
balloon_page_delete(page);
|
|
spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags);
|
|
vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
|
|
set_page_pfns(vb, vb->pfns, page);
|
|
tell_host(vb, vb->deflate_vq);
|
|
|
|
mutex_unlock(&vb->balloon_lock);
|
|
|
|
put_page(page); /* balloon reference */
|
|
|
|
return MIGRATEPAGE_SUCCESS;
|
|
}
|
|
|
|
static struct dentry *balloon_mount(struct file_system_type *fs_type,
|
|
int flags, const char *dev_name, void *data)
|
|
{
|
|
static const struct dentry_operations ops = {
|
|
.d_dname = simple_dname,
|
|
};
|
|
|
|
return mount_pseudo(fs_type, "balloon-kvm:", NULL, &ops,
|
|
BALLOON_KVM_MAGIC);
|
|
}
|
|
|
|
static struct file_system_type balloon_fs = {
|
|
.name = "balloon-kvm",
|
|
.mount = balloon_mount,
|
|
.kill_sb = kill_anon_super,
|
|
};
|
|
|
|
#endif /* CONFIG_BALLOON_COMPACTION */
|
|
|
|
static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker,
|
|
struct shrink_control *sc)
|
|
{
|
|
unsigned long pages_to_free, pages_freed = 0;
|
|
struct virtio_balloon *vb = container_of(shrinker,
|
|
struct virtio_balloon, shrinker);
|
|
|
|
pages_to_free = sc->nr_to_scan * VIRTIO_BALLOON_PAGES_PER_PAGE;
|
|
|
|
/*
|
|
* One invocation of leak_balloon can deflate at most
|
|
* VIRTIO_BALLOON_ARRAY_PFNS_MAX balloon pages, so we call it
|
|
* multiple times to deflate pages till reaching pages_to_free.
|
|
*/
|
|
while (vb->num_pages && pages_to_free) {
|
|
pages_to_free -= pages_freed;
|
|
pages_freed += leak_balloon(vb, pages_to_free);
|
|
}
|
|
update_balloon_size(vb);
|
|
|
|
return pages_freed / VIRTIO_BALLOON_PAGES_PER_PAGE;
|
|
}
|
|
|
|
static unsigned long virtio_balloon_shrinker_count(struct shrinker *shrinker,
|
|
struct shrink_control *sc)
|
|
{
|
|
struct virtio_balloon *vb = container_of(shrinker,
|
|
struct virtio_balloon, shrinker);
|
|
|
|
return vb->num_pages / VIRTIO_BALLOON_PAGES_PER_PAGE;
|
|
}
|
|
|
|
static void virtio_balloon_unregister_shrinker(struct virtio_balloon *vb)
|
|
{
|
|
unregister_shrinker(&vb->shrinker);
|
|
}
|
|
|
|
static int virtio_balloon_register_shrinker(struct virtio_balloon *vb)
|
|
{
|
|
vb->shrinker.scan_objects = virtio_balloon_shrinker_scan;
|
|
vb->shrinker.count_objects = virtio_balloon_shrinker_count;
|
|
vb->shrinker.seeks = DEFAULT_SEEKS;
|
|
|
|
return register_shrinker(&vb->shrinker);
|
|
}
|
|
|
|
static int virtballoon_probe(struct virtio_device *vdev)
|
|
{
|
|
struct virtio_balloon *vb;
|
|
int err;
|
|
|
|
if (!vdev->config->get) {
|
|
dev_err(&vdev->dev, "%s failure: config access disabled\n",
|
|
__func__);
|
|
return -EINVAL;
|
|
}
|
|
|
|
vdev->priv = vb = kzalloc(sizeof(*vb), GFP_KERNEL);
|
|
if (!vb) {
|
|
err = -ENOMEM;
|
|
goto out;
|
|
}
|
|
|
|
INIT_WORK(&vb->update_balloon_stats_work, update_balloon_stats_func);
|
|
INIT_WORK(&vb->update_balloon_size_work, update_balloon_size_func);
|
|
spin_lock_init(&vb->stop_update_lock);
|
|
mutex_init(&vb->balloon_lock);
|
|
init_waitqueue_head(&vb->acked);
|
|
vb->vdev = vdev;
|
|
|
|
balloon_devinfo_init(&vb->vb_dev_info);
|
|
|
|
err = init_vqs(vb);
|
|
if (err)
|
|
goto out_free_vb;
|
|
|
|
#ifdef CONFIG_BALLOON_COMPACTION
|
|
balloon_mnt = kern_mount(&balloon_fs);
|
|
if (IS_ERR(balloon_mnt)) {
|
|
err = PTR_ERR(balloon_mnt);
|
|
goto out_del_vqs;
|
|
}
|
|
|
|
vb->vb_dev_info.migratepage = virtballoon_migratepage;
|
|
vb->vb_dev_info.inode = alloc_anon_inode(balloon_mnt->mnt_sb);
|
|
if (IS_ERR(vb->vb_dev_info.inode)) {
|
|
err = PTR_ERR(vb->vb_dev_info.inode);
|
|
kern_unmount(balloon_mnt);
|
|
goto out_del_vqs;
|
|
}
|
|
vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
|
|
#endif
|
|
/*
|
|
* We continue to use VIRTIO_BALLOON_F_DEFLATE_ON_OOM to decide if a
|
|
* shrinker needs to be registered to relieve memory pressure.
|
|
*/
|
|
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) {
|
|
err = virtio_balloon_register_shrinker(vb);
|
|
if (err)
|
|
goto out_del_vqs;
|
|
}
|
|
virtio_device_ready(vdev);
|
|
|
|
if (towards_target(vb))
|
|
virtballoon_changed(vdev);
|
|
return 0;
|
|
|
|
out_del_vqs:
|
|
vdev->config->del_vqs(vdev);
|
|
out_free_vb:
|
|
kfree(vb);
|
|
out:
|
|
return err;
|
|
}
|
|
|
|
static void remove_common(struct virtio_balloon *vb)
|
|
{
|
|
/* There might be pages left in the balloon: free them. */
|
|
while (vb->num_pages)
|
|
leak_balloon(vb, vb->num_pages);
|
|
update_balloon_size(vb);
|
|
|
|
/* Now we reset the device so we can clean up the queues. */
|
|
vb->vdev->config->reset(vb->vdev);
|
|
|
|
vb->vdev->config->del_vqs(vb->vdev);
|
|
}
|
|
|
|
static void virtballoon_remove(struct virtio_device *vdev)
|
|
{
|
|
struct virtio_balloon *vb = vdev->priv;
|
|
|
|
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
|
|
virtio_balloon_unregister_shrinker(vb);
|
|
spin_lock_irq(&vb->stop_update_lock);
|
|
vb->stop_update = true;
|
|
spin_unlock_irq(&vb->stop_update_lock);
|
|
cancel_work_sync(&vb->update_balloon_size_work);
|
|
cancel_work_sync(&vb->update_balloon_stats_work);
|
|
|
|
remove_common(vb);
|
|
#ifdef CONFIG_BALLOON_COMPACTION
|
|
if (vb->vb_dev_info.inode)
|
|
iput(vb->vb_dev_info.inode);
|
|
|
|
kern_unmount(balloon_mnt);
|
|
#endif
|
|
kfree(vb);
|
|
}
|
|
|
|
#ifdef CONFIG_PM_SLEEP
|
|
static int virtballoon_freeze(struct virtio_device *vdev)
|
|
{
|
|
struct virtio_balloon *vb = vdev->priv;
|
|
|
|
/*
|
|
* The workqueue is already frozen by the PM core before this
|
|
* function is called.
|
|
*/
|
|
remove_common(vb);
|
|
return 0;
|
|
}
|
|
|
|
static int virtballoon_restore(struct virtio_device *vdev)
|
|
{
|
|
struct virtio_balloon *vb = vdev->priv;
|
|
int ret;
|
|
|
|
ret = init_vqs(vdev->priv);
|
|
if (ret)
|
|
return ret;
|
|
|
|
virtio_device_ready(vdev);
|
|
|
|
if (towards_target(vb))
|
|
virtballoon_changed(vdev);
|
|
update_balloon_size(vb);
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
static int virtballoon_validate(struct virtio_device *vdev)
|
|
{
|
|
__virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM);
|
|
return 0;
|
|
}
|
|
|
|
static unsigned int features[] = {
|
|
VIRTIO_BALLOON_F_MUST_TELL_HOST,
|
|
VIRTIO_BALLOON_F_STATS_VQ,
|
|
VIRTIO_BALLOON_F_DEFLATE_ON_OOM,
|
|
};
|
|
|
|
static struct virtio_driver virtio_balloon_driver = {
|
|
.feature_table = features,
|
|
.feature_table_size = ARRAY_SIZE(features),
|
|
.driver.name = KBUILD_MODNAME,
|
|
.driver.owner = THIS_MODULE,
|
|
.id_table = id_table,
|
|
.validate = virtballoon_validate,
|
|
.probe = virtballoon_probe,
|
|
.remove = virtballoon_remove,
|
|
.config_changed = virtballoon_changed,
|
|
#ifdef CONFIG_PM_SLEEP
|
|
.freeze = virtballoon_freeze,
|
|
.restore = virtballoon_restore,
|
|
#endif
|
|
};
|
|
|
|
module_virtio_driver(virtio_balloon_driver);
|
|
MODULE_DEVICE_TABLE(virtio, id_table);
|
|
MODULE_DESCRIPTION("Virtio balloon driver");
|
|
MODULE_LICENSE("GPL");
|