diff options
Diffstat (limited to 'drivers/virtio/virtio_balloon.c')
| -rw-r--r-- | drivers/virtio/virtio_balloon.c | 557 |
1 files changed, 355 insertions, 202 deletions
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index fb12fe205f86..74fe59f5a78c 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -1,22 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * 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> @@ -27,37 +14,37 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/balloon_compaction.h> +#include <linux/oom.h> #include <linux/wait.h> #include <linux/mm.h> -#include <linux/mount.h> -#include <linux/magic.h> +#include <linux/page_reporting.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_PAGES_PER_PAGE (unsigned int)(PAGE_SIZE >> VIRTIO_BALLOON_PFN_SHIFT) #define VIRTIO_BALLOON_ARRAY_PFNS_MAX 256 -#define VIRTBALLOON_OOM_NOTIFY_PRIORITY 80 +/* Maximum number of (4k) pages to deflate on OOM notifications. */ +#define VIRTIO_BALLOON_OOM_NR_PAGES 256 +#define VIRTIO_BALLOON_OOM_NOTIFY_PRIORITY 80 #define VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG (__GFP_NORETRY | __GFP_NOWARN | \ __GFP_NOMEMALLOC) /* The order of free page blocks to report to host */ -#define VIRTIO_BALLOON_FREE_PAGE_ORDER (MAX_ORDER - 1) +#define VIRTIO_BALLOON_HINT_BLOCK_ORDER MAX_PAGE_ORDER /* The size of a free page block in bytes */ -#define VIRTIO_BALLOON_FREE_PAGE_SIZE \ - (1 << (VIRTIO_BALLOON_FREE_PAGE_ORDER + PAGE_SHIFT)) - -#ifdef CONFIG_BALLOON_COMPACTION -static struct vfsmount *balloon_mnt; -#endif +#define VIRTIO_BALLOON_HINT_BLOCK_BYTES \ + (1 << (VIRTIO_BALLOON_HINT_BLOCK_ORDER + PAGE_SHIFT)) +#define VIRTIO_BALLOON_HINT_BLOCK_PAGES (1 << VIRTIO_BALLOON_HINT_BLOCK_ORDER) enum virtio_balloon_vq { VIRTIO_BALLOON_VQ_INFLATE, VIRTIO_BALLOON_VQ_DEFLATE, VIRTIO_BALLOON_VQ_STATS, VIRTIO_BALLOON_VQ_FREE_PAGE, + VIRTIO_BALLOON_VQ_REPORTING, VIRTIO_BALLOON_VQ_MAX }; @@ -123,11 +110,26 @@ struct virtio_balloon { /* Memory statistics */ struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR]; - /* To register a shrinker to shrink memory upon memory pressure */ - struct shrinker shrinker; + /* Shrinker to return free pages - VIRTIO_BALLOON_F_FREE_PAGE_HINT */ + struct shrinker *shrinker; + + /* OOM notifier to deflate on OOM - VIRTIO_BALLOON_F_DEFLATE_ON_OOM */ + struct notifier_block oom_nb; + + /* Free page reporting device */ + struct virtqueue *reporting_vq; + struct page_reporting_dev_info pr_dev_info; + + /* State for keeping the wakeup_source active while adjusting the balloon */ + spinlock_t wakeup_lock; + bool processing_wakeup_event; + u32 wakeup_signal_mask; }; -static struct virtio_device_id id_table[] = { +#define VIRTIO_BALLOON_WAKEUP_SIGNAL_ADJUST (1 << 0) +#define VIRTIO_BALLOON_WAKEUP_SIGNAL_STATS (1 << 1) + +static const struct virtio_device_id id_table[] = { { VIRTIO_ID_BALLOON, VIRTIO_DEV_ANY_ID }, { 0 }, }; @@ -141,6 +143,36 @@ static u32 page_to_balloon_pfn(struct page *page) return pfn * VIRTIO_BALLOON_PAGES_PER_PAGE; } +static void start_wakeup_event(struct virtio_balloon *vb, u32 mask) +{ + unsigned long flags; + + spin_lock_irqsave(&vb->wakeup_lock, flags); + vb->wakeup_signal_mask |= mask; + if (!vb->processing_wakeup_event) { + vb->processing_wakeup_event = true; + pm_stay_awake(&vb->vdev->dev); + } + spin_unlock_irqrestore(&vb->wakeup_lock, flags); +} + +static void process_wakeup_event(struct virtio_balloon *vb, u32 mask) +{ + spin_lock_irq(&vb->wakeup_lock); + vb->wakeup_signal_mask &= ~mask; + spin_unlock_irq(&vb->wakeup_lock); +} + +static void finish_wakeup_event(struct virtio_balloon *vb) +{ + spin_lock_irq(&vb->wakeup_lock); + if (!vb->wakeup_signal_mask && vb->processing_wakeup_event) { + vb->processing_wakeup_event = false; + pm_relax(&vb->vdev->dev); + } + spin_unlock_irq(&vb->wakeup_lock); +} + static void balloon_ack(struct virtqueue *vq) { struct virtio_balloon *vb = vq->vdev->priv; @@ -164,11 +196,40 @@ static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq) } +static int virtballoon_free_page_report(struct page_reporting_dev_info *pr_dev_info, + struct scatterlist *sg, unsigned int nents) +{ + struct virtio_balloon *vb = + container_of(pr_dev_info, struct virtio_balloon, pr_dev_info); + struct virtqueue *vq = vb->reporting_vq; + unsigned int unused, err; + + /* We should always be able to add these buffers to an empty queue. */ + err = virtqueue_add_inbuf(vq, sg, nents, vb, GFP_NOWAIT); + + /* + * In the extremely unlikely case that something has occurred and we + * are able to trigger an error we will simply display a warning + * and exit without actually processing the pages. + */ + if (WARN_ON_ONCE(err)) + return err; + + virtqueue_kick(vq); + + /* When host has read buffer, this completes via balloon_ack */ + wait_event(vb->acked, virtqueue_get_buf(vq, &unused)); + + return 0; +} + static void set_page_pfns(struct virtio_balloon *vb, __virtio32 pfns[], struct page *page) { unsigned int i; + BUILD_BUG_ON(VIRTIO_BALLOON_PAGES_PER_PAGE > VIRTIO_BALLOON_ARRAY_PFNS_MAX); + /* * Set balloon pfns pointing at this page. * Note that the first pfn points at start of the page. @@ -178,10 +239,10 @@ static void set_page_pfns(struct virtio_balloon *vb, page_to_balloon_pfn(page) + i); } -static unsigned fill_balloon(struct virtio_balloon *vb, size_t num) +static unsigned int fill_balloon(struct virtio_balloon *vb, size_t num) { - unsigned num_allocated_pages; - unsigned num_pfns; + unsigned int num_allocated_pages; + unsigned int num_pfns; struct page *page; LIST_HEAD(pages); @@ -190,7 +251,7 @@ static unsigned fill_balloon(struct virtio_balloon *vb, size_t num) for (num_pfns = 0; num_pfns < num; num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) { - struct page *page = balloon_page_alloc(); + page = balloon_page_alloc(); if (!page) { dev_info_ratelimited(&vb->vdev->dev, @@ -242,9 +303,9 @@ static void release_pages_balloon(struct virtio_balloon *vb, } } -static unsigned leak_balloon(struct virtio_balloon *vb, size_t num) +static unsigned int leak_balloon(struct virtio_balloon *vb, size_t num) { - unsigned num_freed_pages; + unsigned int num_freed_pages; struct page *page; struct balloon_dev_info *vb_dev_info = &vb->vb_dev_info; LIST_HEAD(pages); @@ -288,34 +349,67 @@ static inline void update_stat(struct virtio_balloon *vb, int idx, #define pages_to_bytes(x) ((u64)(x) << PAGE_SHIFT) -static unsigned int update_balloon_stats(struct virtio_balloon *vb) +#ifdef CONFIG_VM_EVENT_COUNTERS +/* Return the number of entries filled by vm events */ +static inline unsigned int update_balloon_vm_stats(struct virtio_balloon *vb) { unsigned long events[NR_VM_EVENT_ITEMS]; - struct sysinfo i; unsigned int idx = 0; - long available; - unsigned long caches; + unsigned int zid; + unsigned long stall = 0; 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])); + pages_to_bytes(events[PSWPIN])); update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_OUT, - pages_to_bytes(events[PSWPOUT])); + 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]); + update_stat(vb, idx++, VIRTIO_BALLOON_S_OOM_KILL, events[OOM_KILL]); + + /* sum all the stall events */ + for (zid = 0; zid < MAX_NR_ZONES; zid++) + stall += events[ALLOCSTALL_NORMAL - ZONE_NORMAL + zid]; + + update_stat(vb, idx++, VIRTIO_BALLOON_S_ALLOC_STALL, stall); + + update_stat(vb, idx++, VIRTIO_BALLOON_S_ASYNC_SCAN, + pages_to_bytes(events[PGSCAN_KSWAPD])); + update_stat(vb, idx++, VIRTIO_BALLOON_S_DIRECT_SCAN, + pages_to_bytes(events[PGSCAN_DIRECT])); + update_stat(vb, idx++, VIRTIO_BALLOON_S_ASYNC_RECLAIM, + pages_to_bytes(events[PGSTEAL_KSWAPD])); + update_stat(vb, idx++, VIRTIO_BALLOON_S_DIRECT_RECLAIM, + pages_to_bytes(events[PGSTEAL_DIRECT])); + #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 +#endif /* CONFIG_HUGETLB_PAGE */ + + return idx; +} +#else /* CONFIG_VM_EVENT_COUNTERS */ +static inline unsigned int update_balloon_vm_stats(struct virtio_balloon *vb) +{ + return 0; +} +#endif /* CONFIG_VM_EVENT_COUNTERS */ + +static unsigned int update_balloon_stats(struct virtio_balloon *vb) +{ + struct sysinfo i; + unsigned int idx; + long available; + unsigned long caches; + + idx = update_balloon_vm_stats(vb); + + si_meminfo(&i); + available = si_mem_available(); + caches = global_node_page_state(NR_FILE_PAGES); update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMFREE, pages_to_bytes(i.freeram)); update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMTOT, @@ -342,8 +436,10 @@ static void stats_request(struct virtqueue *vq) struct virtio_balloon *vb = vq->vdev->priv; spin_lock(&vb->stop_update_lock); - if (!vb->stop_update) + if (!vb->stop_update) { + start_wakeup_event(vb, VIRTIO_BALLOON_WAKEUP_SIGNAL_STATS); queue_work(system_freezable_wq, &vb->update_balloon_stats_work); + } spin_unlock(&vb->stop_update_lock); } @@ -368,14 +464,15 @@ 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); + virtio_cread_le(vb->vdev, struct virtio_balloon_config, num_pages, + &num_pages); - target = num_pages; + /* + * Aligned up to guest page size to avoid inflating and deflating + * balloon endlessly. + */ + target = ALIGN(num_pages, VIRTIO_BALLOON_PAGES_PER_PAGE); return target - vb->num_pages; } @@ -391,8 +488,7 @@ static unsigned long return_free_pages_to_mm(struct virtio_balloon *vb, page = balloon_page_pop(&vb->free_page_list); if (!page) break; - free_pages((unsigned long)page_address(page), - VIRTIO_BALLOON_FREE_PAGE_ORDER); + __free_pages(page, VIRTIO_BALLOON_HINT_BLOCK_ORDER); } vb->num_free_page_blocks -= num_returned; spin_unlock_irq(&vb->free_page_list_lock); @@ -413,6 +509,12 @@ static void virtio_balloon_queue_free_page_work(struct virtio_balloon *vb) queue_work(vb->balloon_wq, &vb->report_free_page_work); } +static void start_update_balloon_size(struct virtio_balloon *vb) +{ + start_wakeup_event(vb, VIRTIO_BALLOON_WAKEUP_SIGNAL_ADJUST); + queue_work(system_freezable_wq, &vb->update_balloon_size_work); +} + static void virtballoon_changed(struct virtio_device *vdev) { struct virtio_balloon *vb = vdev->priv; @@ -420,8 +522,7 @@ static void virtballoon_changed(struct virtio_device *vdev) spin_lock_irqsave(&vb->stop_update_lock, flags); if (!vb->stop_update) { - queue_work(system_freezable_wq, - &vb->update_balloon_size_work); + start_update_balloon_size(vb); virtio_balloon_queue_free_page_work(vb); } spin_unlock_irqrestore(&vb->stop_update_lock, flags); @@ -432,11 +533,8 @@ 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); + virtio_cwrite_le(vb->vdev, struct virtio_balloon_config, actual, + &actual); } static void update_balloon_stats_func(struct work_struct *work) @@ -445,7 +543,10 @@ static void update_balloon_stats_func(struct work_struct *work) vb = container_of(work, struct virtio_balloon, update_balloon_stats_work); + + process_wakeup_event(vb, VIRTIO_BALLOON_WAKEUP_SIGNAL_STATS); stats_handle_request(vb); + finish_wakeup_event(vb); } static void update_balloon_size_func(struct work_struct *work) @@ -455,23 +556,29 @@ static void update_balloon_size_func(struct work_struct *work) vb = container_of(work, struct virtio_balloon, update_balloon_size_work); + + process_wakeup_event(vb, VIRTIO_BALLOON_WAKEUP_SIGNAL_ADJUST); + 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) { + if (diff > 0) + diff -= fill_balloon(vb, diff); + else + diff += leak_balloon(vb, -diff); + update_balloon_size(vb); + } if (diff) queue_work(system_freezable_wq, work); + else + finish_wakeup_event(vb); } static int init_vqs(struct virtio_balloon *vb) { + struct virtqueue_info vqs_info[VIRTIO_BALLOON_VQ_MAX] = {}; struct virtqueue *vqs[VIRTIO_BALLOON_VQ_MAX]; - vq_callback_t *callbacks[VIRTIO_BALLOON_VQ_MAX]; - const char *names[VIRTIO_BALLOON_VQ_MAX]; int err; /* @@ -479,25 +586,26 @@ static int init_vqs(struct virtio_balloon *vb) * will be NULL if the related feature is not enabled, which will * cause no allocation for the corresponding virtqueue in find_vqs. */ - callbacks[VIRTIO_BALLOON_VQ_INFLATE] = balloon_ack; - names[VIRTIO_BALLOON_VQ_INFLATE] = "inflate"; - callbacks[VIRTIO_BALLOON_VQ_DEFLATE] = balloon_ack; - names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate"; - names[VIRTIO_BALLOON_VQ_STATS] = NULL; - names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL; + vqs_info[VIRTIO_BALLOON_VQ_INFLATE].callback = balloon_ack; + vqs_info[VIRTIO_BALLOON_VQ_INFLATE].name = "inflate"; + vqs_info[VIRTIO_BALLOON_VQ_DEFLATE].callback = balloon_ack; + vqs_info[VIRTIO_BALLOON_VQ_DEFLATE].name = "deflate"; if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) { - names[VIRTIO_BALLOON_VQ_STATS] = "stats"; - callbacks[VIRTIO_BALLOON_VQ_STATS] = stats_request; + vqs_info[VIRTIO_BALLOON_VQ_STATS].name = "stats"; + vqs_info[VIRTIO_BALLOON_VQ_STATS].callback = stats_request; } - if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) { - names[VIRTIO_BALLOON_VQ_FREE_PAGE] = "free_page_vq"; - callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL; + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) + vqs_info[VIRTIO_BALLOON_VQ_FREE_PAGE].name = "free_page_vq"; + + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) { + vqs_info[VIRTIO_BALLOON_VQ_REPORTING].name = "reporting_vq"; + vqs_info[VIRTIO_BALLOON_VQ_REPORTING].callback = balloon_ack; } - err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX, - vqs, callbacks, names, NULL, NULL); + err = virtio_find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX, vqs, + vqs_info, NULL); if (err) return err; @@ -528,16 +636,21 @@ static int init_vqs(struct virtio_balloon *vb) if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) vb->free_page_vq = vqs[VIRTIO_BALLOON_VQ_FREE_PAGE]; + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) + vb->reporting_vq = vqs[VIRTIO_BALLOON_VQ_REPORTING]; + return 0; } static u32 virtio_balloon_cmd_id_received(struct virtio_balloon *vb) { if (test_and_clear_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID, - &vb->config_read_bitmap)) - virtio_cread(vb->vdev, struct virtio_balloon_config, - free_page_report_cmd_id, - &vb->cmd_id_received_cache); + &vb->config_read_bitmap)) { + /* Legacy balloon config space is LE, unlike all other devices. */ + virtio_cread_le(vb->vdev, struct virtio_balloon_config, + free_page_hint_cmd_id, + &vb->cmd_id_received_cache); + } return vb->cmd_id_received_cache; } @@ -552,7 +665,7 @@ static int send_cmd_id_start(struct virtio_balloon *vb) while (virtqueue_get_buf(vq, &unused)) ; - vb->cmd_id_active = virtio32_to_cpu(vb->vdev, + vb->cmd_id_active = cpu_to_virtio32(vb->vdev, virtio_balloon_cmd_id_received(vb)); sg_init_one(&sg, &vb->cmd_id_active, sizeof(vb->cmd_id_active)); err = virtqueue_add_outbuf(vq, &sg, 1, &vb->cmd_id_active, GFP_KERNEL); @@ -591,7 +704,7 @@ static int get_free_page_and_send(struct virtio_balloon *vb) ; page = alloc_pages(VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG, - VIRTIO_BALLOON_FREE_PAGE_ORDER); + VIRTIO_BALLOON_HINT_BLOCK_ORDER); /* * When the allocation returns NULL, it indicates that we have got all * the possible free pages, so return -EINTR to stop. @@ -600,13 +713,12 @@ static int get_free_page_and_send(struct virtio_balloon *vb) return -EINTR; p = page_address(page); - sg_init_one(&sg, p, VIRTIO_BALLOON_FREE_PAGE_SIZE); + sg_init_one(&sg, p, VIRTIO_BALLOON_HINT_BLOCK_BYTES); /* There is always 1 entry reserved for the cmd id to use. */ if (vq->num_free > 1) { err = virtqueue_add_inbuf(vq, &sg, 1, p, GFP_KERNEL); if (unlikely(err)) { - free_pages((unsigned long)p, - VIRTIO_BALLOON_FREE_PAGE_ORDER); + __free_pages(page, VIRTIO_BALLOON_HINT_BLOCK_ORDER); return err; } virtqueue_kick(vq); @@ -619,7 +731,7 @@ static int get_free_page_and_send(struct virtio_balloon *vb) * The vq has no available entry to add this page block, so * just free it. */ - free_pages((unsigned long)p, VIRTIO_BALLOON_FREE_PAGE_ORDER); + __free_pages(page, VIRTIO_BALLOON_HINT_BLOCK_ORDER); } return 0; @@ -694,7 +806,7 @@ static void report_free_page_func(struct work_struct *work) #ifdef CONFIG_BALLOON_COMPACTION /* * virtballoon_migratepage - perform the balloon page migration on behalf of - * a compation thread. (called under page lock) + * a compaction 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. @@ -708,7 +820,7 @@ static void report_free_page_func(struct work_struct *work) * 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 + * Called through movable_operations->migrate_page */ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info, struct page *newpage, struct page *page, enum migrate_mode mode) @@ -730,6 +842,17 @@ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info, 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); @@ -741,37 +864,17 @@ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info, 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); + balloon_page_finalize(page); 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); + return 0; } - -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 shrink_free_pages(struct virtio_balloon *vb, @@ -780,84 +883,66 @@ static unsigned long shrink_free_pages(struct virtio_balloon *vb, unsigned long blocks_to_free, blocks_freed; pages_to_free = round_up(pages_to_free, - 1 << VIRTIO_BALLOON_FREE_PAGE_ORDER); - blocks_to_free = pages_to_free >> VIRTIO_BALLOON_FREE_PAGE_ORDER; + VIRTIO_BALLOON_HINT_BLOCK_PAGES); + blocks_to_free = pages_to_free / VIRTIO_BALLOON_HINT_BLOCK_PAGES; blocks_freed = return_free_pages_to_mm(vb, blocks_to_free); - return blocks_freed << VIRTIO_BALLOON_FREE_PAGE_ORDER; -} - -static unsigned long shrink_balloon_pages(struct virtio_balloon *vb, - unsigned long pages_to_free) -{ - unsigned long pages_freed = 0; - - /* - * 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_freed += leak_balloon(vb, pages_to_free) / - VIRTIO_BALLOON_PAGES_PER_PAGE; - pages_to_free -= pages_freed; - } - update_balloon_size(vb); - - return pages_freed; + return blocks_freed * VIRTIO_BALLOON_HINT_BLOCK_PAGES; } 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; + struct virtio_balloon *vb = shrinker->private_data; - if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) - pages_freed = shrink_free_pages(vb, pages_to_free); - - if (pages_freed >= pages_to_free) - return pages_freed; - - pages_freed += shrink_balloon_pages(vb, pages_to_free - pages_freed); - - return pages_freed; + return shrink_free_pages(vb, sc->nr_to_scan); } 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); - unsigned long count; + struct virtio_balloon *vb = shrinker->private_data; - count = vb->num_pages / VIRTIO_BALLOON_PAGES_PER_PAGE; - count += vb->num_free_page_blocks >> VIRTIO_BALLOON_FREE_PAGE_ORDER; + return vb->num_free_page_blocks * VIRTIO_BALLOON_HINT_BLOCK_PAGES; +} - return count; +static int virtio_balloon_oom_notify(struct notifier_block *nb, + unsigned long dummy, void *parm) +{ + struct virtio_balloon *vb = container_of(nb, + struct virtio_balloon, oom_nb); + unsigned long *freed = parm; + + *freed += leak_balloon(vb, VIRTIO_BALLOON_OOM_NR_PAGES) / + VIRTIO_BALLOON_PAGES_PER_PAGE; + update_balloon_size(vb); + + return NOTIFY_OK; } static void virtio_balloon_unregister_shrinker(struct virtio_balloon *vb) { - unregister_shrinker(&vb->shrinker); + shrinker_free(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; + vb->shrinker = shrinker_alloc(0, "virtio-balloon"); + if (!vb->shrinker) + return -ENOMEM; + + vb->shrinker->scan_objects = virtio_balloon_shrinker_scan; + vb->shrinker->count_objects = virtio_balloon_shrinker_count; + vb->shrinker->private_data = vb; + + shrinker_register(vb->shrinker); - return register_shrinker(&vb->shrinker); + return 0; } static int virtballoon_probe(struct virtio_device *vdev) { struct virtio_balloon *vb; - __u32 poison_val; int err; if (!vdev->config->get) { @@ -886,20 +971,7 @@ static int virtballoon_probe(struct virtio_device *vdev) 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 if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) { /* @@ -911,7 +983,8 @@ static int virtballoon_probe(struct virtio_device *vdev) goto out_del_vqs; } vb->balloon_wq = alloc_workqueue("balloon-wq", - WQ_FREEZABLE | WQ_CPU_INTENSIVE, 0); + WQ_FREEZABLE | WQ_CPU_INTENSIVE | WQ_PERCPU, + 0); if (!vb->balloon_wq) { err = -ENOMEM; goto out_del_vqs; @@ -922,30 +995,100 @@ static int virtballoon_probe(struct virtio_device *vdev) VIRTIO_BALLOON_CMD_ID_STOP); vb->cmd_id_stop = cpu_to_virtio32(vb->vdev, VIRTIO_BALLOON_CMD_ID_STOP); - vb->num_free_page_blocks = 0; spin_lock_init(&vb->free_page_list_lock); INIT_LIST_HEAD(&vb->free_page_list); - if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) { + /* + * We're allowed to reuse any free pages, even if they are + * still to be processed by the host. + */ + err = virtio_balloon_register_shrinker(vb); + if (err) + goto out_del_balloon_wq; + } + + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) { + vb->oom_nb.notifier_call = virtio_balloon_oom_notify; + vb->oom_nb.priority = VIRTIO_BALLOON_OOM_NOTIFY_PRIORITY; + err = register_oom_notifier(&vb->oom_nb); + if (err < 0) + goto out_unregister_shrinker; + } + + if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) { + /* Start with poison val of 0 representing general init */ + __u32 poison_val = 0; + + /* + * Let the hypervisor know that we are expecting a + * specific value to be written back in balloon pages. + * + * If the PAGE_POISON value was larger than a byte we would + * need to byte swap poison_val here to guarantee it is + * little-endian. However for now it is a single byte so we + * can pass it as-is. + */ + if (!want_init_on_free()) memset(&poison_val, PAGE_POISON, sizeof(poison_val)); - virtio_cwrite(vb->vdev, struct virtio_balloon_config, - poison_val, &poison_val); + + virtio_cwrite_le(vb->vdev, struct virtio_balloon_config, + poison_val, &poison_val); + } + + vb->pr_dev_info.report = virtballoon_free_page_report; + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) { + unsigned int capacity; + + capacity = virtqueue_get_vring_size(vb->reporting_vq); + if (capacity < PAGE_REPORTING_CAPACITY) { + err = -ENOSPC; + goto out_unregister_oom; } + + /* + * The default page reporting order is @pageblock_order, which + * corresponds to 512MB in size on ARM64 when 64KB base page + * size is used. The page reporting won't be triggered if the + * freeing page can't come up with a free area like that huge. + * So we specify the page reporting order to 5, corresponding + * to 2MB. It helps to avoid THP splitting if 4KB base page + * size is used by host. + * + * Ideally, the page reporting order is selected based on the + * host's base page size. However, it needs more work to report + * that value. The hard-coded order would be fine currently. + */ +#if defined(CONFIG_ARM64) && defined(CONFIG_ARM64_64K_PAGES) + vb->pr_dev_info.order = 5; +#endif + + err = page_reporting_register(&vb->pr_dev_info); + if (err) + goto out_unregister_oom; } + + spin_lock_init(&vb->wakeup_lock); + /* - * We continue to use VIRTIO_BALLOON_F_DEFLATE_ON_OOM to decide if a - * shrinker needs to be registered to relieve memory pressure. + * The virtio balloon itself can't wake up the device, but it is + * responsible for processing wakeup events passed up from the transport + * layer. Wakeup sources don't support nesting/chaining calls, so we use + * our own wakeup source to ensure wakeup events are properly handled + * without trampling on the transport layer's wakeup source. */ - if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) { - err = virtio_balloon_register_shrinker(vb); - if (err) - goto out_del_balloon_wq; - } + device_set_wakeup_capable(&vb->vdev->dev, true); + virtio_device_ready(vdev); if (towards_target(vb)) virtballoon_changed(vdev); return 0; +out_unregister_oom: + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) + unregister_oom_notifier(&vb->oom_nb); +out_unregister_shrinker: + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) + virtio_balloon_unregister_shrinker(vb); out_del_balloon_wq: if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) destroy_workqueue(vb->balloon_wq); @@ -964,8 +1107,12 @@ static void remove_common(struct virtio_balloon *vb) leak_balloon(vb, vb->num_pages); update_balloon_size(vb); + /* There might be free pages that are being reported: release them. */ + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) + return_free_pages_to_mm(vb, ULONG_MAX); + /* Now we reset the device so we can clean up the queues. */ - vb->vdev->config->reset(vb->vdev); + virtio_reset_device(vb->vdev); vb->vdev->config->del_vqs(vb->vdev); } @@ -974,7 +1121,11 @@ static void virtballoon_remove(struct virtio_device *vdev) { struct virtio_balloon *vb = vdev->priv; + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) + page_reporting_unregister(&vb->pr_dev_info); if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) + unregister_oom_notifier(&vb->oom_nb); + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) virtio_balloon_unregister_shrinker(vb); spin_lock_irq(&vb->stop_update_lock); vb->stop_update = true; @@ -988,12 +1139,6 @@ static void virtballoon_remove(struct virtio_device *vdev) } 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); } @@ -1030,10 +1175,18 @@ static int virtballoon_restore(struct virtio_device *vdev) static int virtballoon_validate(struct virtio_device *vdev) { - if (!page_poisoning_enabled()) + /* + * Inform the hypervisor that our pages are poisoned or + * initialized. If we cannot do that then we should disable + * page reporting as it could potentially change the contents + * of our free pages. + */ + if (!want_init_on_free() && !page_poisoning_enabled_static()) __virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON); + else if (!virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) + __virtio_clear_bit(vdev, VIRTIO_BALLOON_F_REPORTING); - __virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM); + __virtio_clear_bit(vdev, VIRTIO_F_ACCESS_PLATFORM); return 0; } @@ -1043,13 +1196,13 @@ static unsigned int features[] = { VIRTIO_BALLOON_F_DEFLATE_ON_OOM, VIRTIO_BALLOON_F_FREE_PAGE_HINT, VIRTIO_BALLOON_F_PAGE_POISON, + VIRTIO_BALLOON_F_REPORTING, }; 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, |