linux/drivers/virtio/virtio_balloon.c
Tejun Heo 5a0e3ad6af include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files.  percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.

percpu.h -> slab.h dependency is about to be removed.  Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability.  As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.

  http://userweb.kernel.org/~tj/misc/slabh-sweep.py

The script does the followings.

* Scan files for gfp and slab usages and update includes such that
  only the necessary includes are there.  ie. if only gfp is used,
  gfp.h, if slab is used, slab.h.

* When the script inserts a new include, it looks at the include
  blocks and try to put the new include such that its order conforms
  to its surrounding.  It's put in the include block which contains
  core kernel includes, in the same order that the rest are ordered -
  alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
  doesn't seem to be any matching order.

* If the script can't find a place to put a new include (mostly
  because the file doesn't have fitting include block), it prints out
  an error message indicating which .h file needs to be added to the
  file.

The conversion was done in the following steps.

1. The initial automatic conversion of all .c files updated slightly
   over 4000 files, deleting around 700 includes and adding ~480 gfp.h
   and ~3000 slab.h inclusions.  The script emitted errors for ~400
   files.

2. Each error was manually checked.  Some didn't need the inclusion,
   some needed manual addition while adding it to implementation .h or
   embedding .c file was more appropriate for others.  This step added
   inclusions to around 150 files.

3. The script was run again and the output was compared to the edits
   from #2 to make sure no file was left behind.

4. Several build tests were done and a couple of problems were fixed.
   e.g. lib/decompress_*.c used malloc/free() wrappers around slab
   APIs requiring slab.h to be added manually.

5. The script was run on all .h files but without automatically
   editing them as sprinkling gfp.h and slab.h inclusions around .h
   files could easily lead to inclusion dependency hell.  Most gfp.h
   inclusion directives were ignored as stuff from gfp.h was usually
   wildly available and often used in preprocessor macros.  Each
   slab.h inclusion directive was examined and added manually as
   necessary.

6. percpu.h was updated not to include slab.h.

7. Build test were done on the following configurations and failures
   were fixed.  CONFIG_GCOV_KERNEL was turned off for all tests (as my
   distributed build env didn't work with gcov compiles) and a few
   more options had to be turned off depending on archs to make things
   build (like ipr on powerpc/64 which failed due to missing writeq).

   * x86 and x86_64 UP and SMP allmodconfig and a custom test config.
   * powerpc and powerpc64 SMP allmodconfig
   * sparc and sparc64 SMP allmodconfig
   * ia64 SMP allmodconfig
   * s390 SMP allmodconfig
   * alpha SMP allmodconfig
   * um on x86_64 SMP allmodconfig

8. percpu.h modifications were reverted so that it could be applied as
   a separate patch and serve as bisection point.

Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.

Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-30 22:02:32 +09:00

389 lines
9.8 KiB
C

/* Virtio balloon implementation, inspired by Dor Loar 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
*/
//#define DEBUG
#include <linux/virtio.h>
#include <linux/virtio_balloon.h>
#include <linux/swap.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/delay.h>
#include <linux/slab.h>
struct virtio_balloon
{
struct virtio_device *vdev;
struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
/* Where the ballooning thread waits for config to change. */
wait_queue_head_t config_change;
/* The thread servicing the balloon. */
struct task_struct *thread;
/* Waiting for host to ack the pages we released. */
struct completion acked;
/* Do we have to tell Host *before* we reuse pages? */
bool tell_host_first;
/* The pages we've told the Host we're not using. */
unsigned int num_pages;
struct list_head pages;
/* The array of pfns we tell the Host about. */
unsigned int num_pfns;
u32 pfns[256];
/* Memory statistics */
int need_stats_update;
struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
};
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 >> (PAGE_SHIFT - VIRTIO_BALLOON_PFN_SHIFT);
}
static void balloon_ack(struct virtqueue *vq)
{
struct virtio_balloon *vb;
unsigned int len;
vb = vq->vq_ops->get_buf(vq, &len);
if (vb)
complete(&vb->acked);
}
static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq)
{
struct scatterlist sg;
sg_init_one(&sg, vb->pfns, sizeof(vb->pfns[0]) * vb->num_pfns);
init_completion(&vb->acked);
/* We should always be able to add one buffer to an empty queue. */
if (vq->vq_ops->add_buf(vq, &sg, 1, 0, vb) < 0)
BUG();
vq->vq_ops->kick(vq);
/* When host has read buffer, this completes via balloon_ack */
wait_for_completion(&vb->acked);
}
static void fill_balloon(struct virtio_balloon *vb, size_t num)
{
/* We can only do one array worth at a time. */
num = min(num, ARRAY_SIZE(vb->pfns));
for (vb->num_pfns = 0; vb->num_pfns < num; vb->num_pfns++) {
struct page *page = alloc_page(GFP_HIGHUSER | __GFP_NORETRY);
if (!page) {
if (printk_ratelimit())
dev_printk(KERN_INFO, &vb->vdev->dev,
"Out of puff! Can't get %zu pages\n",
num);
/* Sleep for at least 1/5 of a second before retry. */
msleep(200);
break;
}
vb->pfns[vb->num_pfns] = page_to_balloon_pfn(page);
totalram_pages--;
vb->num_pages++;
list_add(&page->lru, &vb->pages);
}
/* Didn't get any? Oh well. */
if (vb->num_pfns == 0)
return;
tell_host(vb, vb->inflate_vq);
}
static void release_pages_by_pfn(const u32 pfns[], unsigned int num)
{
unsigned int i;
for (i = 0; i < num; i++) {
__free_page(pfn_to_page(pfns[i]));
totalram_pages++;
}
}
static void leak_balloon(struct virtio_balloon *vb, size_t num)
{
struct page *page;
/* We can only do one array worth at a time. */
num = min(num, ARRAY_SIZE(vb->pfns));
for (vb->num_pfns = 0; vb->num_pfns < num; vb->num_pfns++) {
page = list_first_entry(&vb->pages, struct page, lru);
list_del(&page->lru);
vb->pfns[vb->num_pfns] = page_to_balloon_pfn(page);
vb->num_pages--;
}
if (vb->tell_host_first) {
tell_host(vb, vb->deflate_vq);
release_pages_by_pfn(vb->pfns, vb->num_pfns);
} else {
release_pages_by_pfn(vb->pfns, vb->num_pfns);
tell_host(vb, vb->deflate_vq);
}
}
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 = tag;
vb->stats[idx].val = val;
}
#define pages_to_bytes(x) ((u64)(x) << PAGE_SHIFT)
static void update_balloon_stats(struct virtio_balloon *vb)
{
unsigned long events[NR_VM_EVENT_ITEMS];
struct sysinfo i;
int idx = 0;
all_vm_events(events);
si_meminfo(&i);
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]);
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));
}
/*
* 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 notify our kthread which does the actual work via stats_handle_request().
*/
static void stats_request(struct virtqueue *vq)
{
struct virtio_balloon *vb;
unsigned int len;
vb = vq->vq_ops->get_buf(vq, &len);
if (!vb)
return;
vb->need_stats_update = 1;
wake_up(&vb->config_change);
}
static void stats_handle_request(struct virtio_balloon *vb)
{
struct virtqueue *vq;
struct scatterlist sg;
vb->need_stats_update = 0;
update_balloon_stats(vb);
vq = vb->stats_vq;
sg_init_one(&sg, vb->stats, sizeof(vb->stats));
if (vq->vq_ops->add_buf(vq, &sg, 1, 0, vb) < 0)
BUG();
vq->vq_ops->kick(vq);
}
static void virtballoon_changed(struct virtio_device *vdev)
{
struct virtio_balloon *vb = vdev->priv;
wake_up(&vb->config_change);
}
static inline s64 towards_target(struct virtio_balloon *vb)
{
u32 v;
vb->vdev->config->get(vb->vdev,
offsetof(struct virtio_balloon_config, num_pages),
&v, sizeof(v));
return (s64)v - vb->num_pages;
}
static void update_balloon_size(struct virtio_balloon *vb)
{
__le32 actual = cpu_to_le32(vb->num_pages);
vb->vdev->config->set(vb->vdev,
offsetof(struct virtio_balloon_config, actual),
&actual, sizeof(actual));
}
static int balloon(void *_vballoon)
{
struct virtio_balloon *vb = _vballoon;
set_freezable();
while (!kthread_should_stop()) {
s64 diff;
try_to_freeze();
wait_event_interruptible(vb->config_change,
(diff = towards_target(vb)) != 0
|| vb->need_stats_update
|| kthread_should_stop()
|| freezing(current));
if (vb->need_stats_update)
stats_handle_request(vb);
if (diff > 0)
fill_balloon(vb, diff);
else if (diff < 0)
leak_balloon(vb, -diff);
update_balloon_size(vb);
}
return 0;
}
static int virtballoon_probe(struct virtio_device *vdev)
{
struct virtio_balloon *vb;
struct virtqueue *vqs[3];
vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
const char *names[] = { "inflate", "deflate", "stats" };
int err, nvqs;
vdev->priv = vb = kmalloc(sizeof(*vb), GFP_KERNEL);
if (!vb) {
err = -ENOMEM;
goto out;
}
INIT_LIST_HEAD(&vb->pages);
vb->num_pages = 0;
init_waitqueue_head(&vb->config_change);
vb->vdev = vdev;
vb->need_stats_update = 0;
/* We expect two virtqueues: inflate and deflate,
* and optionally stat. */
nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
err = vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names);
if (err)
goto out_free_vb;
vb->inflate_vq = vqs[0];
vb->deflate_vq = vqs[1];
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
struct scatterlist sg;
vb->stats_vq = vqs[2];
/*
* Prime this virtqueue with one buffer so the hypervisor can
* use it to signal us later.
*/
sg_init_one(&sg, vb->stats, sizeof vb->stats);
if (vb->stats_vq->vq_ops->add_buf(vb->stats_vq,
&sg, 1, 0, vb) < 0)
BUG();
vb->stats_vq->vq_ops->kick(vb->stats_vq);
}
vb->thread = kthread_run(balloon, vb, "vballoon");
if (IS_ERR(vb->thread)) {
err = PTR_ERR(vb->thread);
goto out_del_vqs;
}
vb->tell_host_first
= virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
return 0;
out_del_vqs:
vdev->config->del_vqs(vdev);
out_free_vb:
kfree(vb);
out:
return err;
}
static void __devexit virtballoon_remove(struct virtio_device *vdev)
{
struct virtio_balloon *vb = vdev->priv;
kthread_stop(vb->thread);
/* There might be pages left in the balloon: free them. */
while (vb->num_pages)
leak_balloon(vb, vb->num_pages);
/* Now we reset the device so we can clean up the queues. */
vdev->config->reset(vdev);
vdev->config->del_vqs(vdev);
kfree(vb);
}
static unsigned int features[] = {
VIRTIO_BALLOON_F_MUST_TELL_HOST,
VIRTIO_BALLOON_F_STATS_VQ,
};
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,
.probe = virtballoon_probe,
.remove = __devexit_p(virtballoon_remove),
.config_changed = virtballoon_changed,
};
static int __init init(void)
{
return register_virtio_driver(&virtio_balloon_driver);
}
static void __exit fini(void)
{
unregister_virtio_driver(&virtio_balloon_driver);
}
module_init(init);
module_exit(fini);
MODULE_DEVICE_TABLE(virtio, id_table);
MODULE_DESCRIPTION("Virtio balloon driver");
MODULE_LICENSE("GPL");