qemu/hw/virtio-balloon.c

275 lines
7.6 KiB
C
Raw Normal View History

/*
* Virtio Balloon Device
*
* Copyright IBM, Corp. 2008
* Copyright (C) 2011 Red Hat, Inc.
* Copyright (C) 2011 Amit Shah <amit.shah@redhat.com>
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
*/
#include "iov.h"
#include "qemu-common.h"
#include "virtio.h"
#include "pc.h"
#include "cpu.h"
#include "balloon.h"
#include "virtio-balloon.h"
#include "kvm.h"
#include "exec-memory.h"
#if defined(__linux__)
#include <sys/mman.h>
#endif
typedef struct VirtIOBalloon
{
VirtIODevice vdev;
VirtQueue *ivq, *dvq, *svq;
uint32_t num_pages;
uint32_t actual;
uint64_t stats[VIRTIO_BALLOON_S_NR];
VirtQueueElement stats_vq_elem;
size_t stats_vq_offset;
DeviceState *qdev;
} VirtIOBalloon;
static VirtIOBalloon *to_virtio_balloon(VirtIODevice *vdev)
{
return (VirtIOBalloon *)vdev;
}
static void balloon_page(void *addr, int deflate)
{
#if defined(__linux__)
if (!kvm_enabled() || kvm_has_sync_mmu())
Introduce qemu_madvise() vl.c has a Sun-specific hack to supply a prototype for madvise(), but the call site has apparently moved to arch_init.c. Haiku doesn't implement madvise() in favor of posix_madvise(). OpenBSD and Solaris 10 don't implement posix_madvise() but madvise(). MinGW implements neither. Check for madvise() and posix_madvise() in configure and supply qemu_madvise() as wrapper. Prefer madvise() over posix_madvise() due to flag availability. Convert all callers to use qemu_madvise() and QEMU_MADV_*. Note that on Solaris the warning is fixed by moving the madvise() prototype, not by qemu_madvise() itself. It helps with porting though, and it simplifies most call sites. v7 -> v8: * Some versions of MinGW have no sys/mman.h header. Reported by Blue Swirl. v6 -> v7: * Adopt madvise() rather than posix_madvise() semantics for returning errors. * Use EINVAL in place of ENOTSUP. v5 -> v6: * Replace two leftover instances of POSIX_MADV_NORMAL with QEMU_MADV_INVALID. Spotted by Blue Swirl. v4 -> v5: * Introduce QEMU_MADV_INVALID, suggested by Alexander Graf. Note that this relies on -1 not being a valid advice value. v3 -> v4: * Eliminate #ifdefs at qemu_advise() call sites. Requested by Blue Swirl. This will currently break the check in kvm-all.c by calling madvise() with a supported flag, which will not fail. Ideas/patches welcome. v2 -> v3: * Reuse the *_MADV_* defines for QEMU_MADV_*. Suggested by Alexander Graf. * Add configure check for madvise(), too. Add defines to Makefile, not QEMU_CFLAGS. Convert all callers, untested. Suggested by Blue Swirl. * Keep Solaris' madvise() prototype around. Pointed out by Alexander Graf. * Display configure check results. v1 -> v2: * Don't rely on posix_madvise() availability, add qemu_madvise(). Suggested by Blue Swirl. Signed-off-by: Andreas Färber <afaerber@opensolaris.org> Cc: Blue Swirl <blauwirbel@gmail.com> Cc: Alexander Graf <agraf@suse.de> Cc: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
2010-09-25 15:26:05 +04:00
qemu_madvise(addr, TARGET_PAGE_SIZE,
deflate ? QEMU_MADV_WILLNEED : QEMU_MADV_DONTNEED);
#endif
}
/*
* reset_stats - Mark all items in the stats array as unset
*
* This function needs to be called at device intialization and before
* before updating to a set of newly-generated stats. This will ensure that no
* stale values stick around in case the guest reports a subset of the supported
* statistics.
*/
static inline void reset_stats(VirtIOBalloon *dev)
{
int i;
for (i = 0; i < VIRTIO_BALLOON_S_NR; dev->stats[i++] = -1);
}
static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIOBalloon *s = to_virtio_balloon(vdev);
VirtQueueElement elem;
MemoryRegionSection section;
while (virtqueue_pop(vq, &elem)) {
size_t offset = 0;
uint32_t pfn;
while (iov_to_buf(elem.out_sg, elem.out_num, offset, &pfn, 4) == 4) {
ram_addr_t pa;
ram_addr_t addr;
pa = (ram_addr_t)ldl_p(&pfn) << VIRTIO_BALLOON_PFN_SHIFT;
offset += 4;
/* FIXME: remove get_system_memory(), but how? */
section = memory_region_find(get_system_memory(), pa, 1);
if (!section.size || !memory_region_is_ram(section.mr))
continue;
/* Using memory_region_get_ram_ptr is bending the rules a bit, but
should be OK because we only want a single page. */
addr = section.offset_within_region;
balloon_page(memory_region_get_ram_ptr(section.mr) + addr,
!!(vq == s->dvq));
}
virtqueue_push(vq, &elem, offset);
virtio_notify(vdev, vq);
}
}
static void virtio_balloon_receive_stats(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIOBalloon *s = DO_UPCAST(VirtIOBalloon, vdev, vdev);
VirtQueueElement *elem = &s->stats_vq_elem;
VirtIOBalloonStat stat;
size_t offset = 0;
if (!virtqueue_pop(vq, elem)) {
return;
}
/* Initialize the stats to get rid of any stale values. This is only
* needed to handle the case where a guest supports fewer stats than it
* used to (ie. it has booted into an old kernel).
*/
reset_stats(s);
while (iov_to_buf(elem->out_sg, elem->out_num, offset, &stat, sizeof(stat))
== sizeof(stat)) {
uint16_t tag = tswap16(stat.tag);
uint64_t val = tswap64(stat.val);
offset += sizeof(stat);
if (tag < VIRTIO_BALLOON_S_NR)
s->stats[tag] = val;
}
s->stats_vq_offset = offset;
}
static void virtio_balloon_get_config(VirtIODevice *vdev, uint8_t *config_data)
{
VirtIOBalloon *dev = to_virtio_balloon(vdev);
struct virtio_balloon_config config;
config.num_pages = cpu_to_le32(dev->num_pages);
config.actual = cpu_to_le32(dev->actual);
memcpy(config_data, &config, 8);
}
static void virtio_balloon_set_config(VirtIODevice *vdev,
const uint8_t *config_data)
{
VirtIOBalloon *dev = to_virtio_balloon(vdev);
struct virtio_balloon_config config;
uint32_t oldactual = dev->actual;
memcpy(&config, config_data, 8);
dev->actual = le32_to_cpu(config.actual);
if (dev->actual != oldactual) {
qemu_balloon_changed(ram_size -
(dev->actual << VIRTIO_BALLOON_PFN_SHIFT));
}
}
static uint32_t virtio_balloon_get_features(VirtIODevice *vdev, uint32_t f)
{
f |= (1 << VIRTIO_BALLOON_F_STATS_VQ);
return f;
}
static void virtio_balloon_stat(void *opaque, BalloonInfo *info)
{
VirtIOBalloon *dev = opaque;
#if 0
/* Disable guest-provided stats for now. For more details please check:
* https://bugzilla.redhat.com/show_bug.cgi?id=623903
*
* If you do enable it (which is probably not going to happen as we
* need a new command for it), remember that you also need to fill the
* appropriate members of the BalloonInfo structure so that the stats
* are returned to the client.
*/
if (dev->vdev.guest_features & (1 << VIRTIO_BALLOON_F_STATS_VQ)) {
virtqueue_push(dev->svq, &dev->stats_vq_elem, dev->stats_vq_offset);
virtio_notify(&dev->vdev, dev->svq);
return;
}
#endif
/* Stats are not supported. Clear out any stale values that might
* have been set by a more featureful guest kernel.
*/
reset_stats(dev);
info->actual = ram_size - ((uint64_t) dev->actual <<
VIRTIO_BALLOON_PFN_SHIFT);
}
balloon: Separate out stat and balloon handling Passing on '0' as ballooning target to indicate retrieval of stats is bad API. It also makes 'balloon 0' in the monitor cause a segfault. Have two different functions handle the different functionality instead. Detailed explanation from Markus's review: 1. do_info_balloon() is an info_async() method. It receives a callback with argument, to be called exactly once (callback frees the argument). It passes the callback via qemu_balloon_status() and indirectly through qemu_balloon_event to virtio_balloon_to_target(). virtio_balloon_to_target() executes its balloon stats half. It stores the callback in the device state. If it can't send a stats request, it resets stats and calls the callback right away. Else, it sends a stats request. The device model runs the callback when it receives the answer. Works. 2. do_balloon() is a cmd_async() method. It receives a callback with argument, to be called when the command completes. do_balloon() calls it right before it succeeds. Odd, but should work. Nevertheless, it passes the callback on via qemu_ballon() and indirectly through qemu_balloon_event to virtio_balloon_to_target(). a. If the argument is non-zero, virtio_balloon_to_target() executes its balloon half, which doesn't use the callback in any way. Odd, but works. b. If the argument is zero, virtio_balloon_to_target() executes its balloon stats half, just like in 1. It either calls the callback right away, or arranges for it to be called later. Thus, the callback runs twice: use after free and double free. Test case: start with -S -device virtio-balloon, execute "balloon 0" in human monitor. Runs the callback first from virtio_balloon_to_target(), then again from do_balloon(). Reported-by: Mike Cao <bcao@redhat.com> Signed-off-by: Amit Shah <amit.shah@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com>
2011-07-20 12:00:56 +04:00
static void virtio_balloon_to_target(void *opaque, ram_addr_t target)
{
VirtIOBalloon *dev = opaque;
if (target > ram_size) {
target = ram_size;
}
if (target) {
dev->num_pages = (ram_size - target) >> VIRTIO_BALLOON_PFN_SHIFT;
virtio_notify_config(&dev->vdev);
}
}
static void virtio_balloon_save(QEMUFile *f, void *opaque)
{
VirtIOBalloon *s = opaque;
virtio_save(&s->vdev, f);
qemu_put_be32(f, s->num_pages);
qemu_put_be32(f, s->actual);
}
static int virtio_balloon_load(QEMUFile *f, void *opaque, int version_id)
{
VirtIOBalloon *s = opaque;
int ret;
if (version_id != 1)
return -EINVAL;
ret = virtio_load(&s->vdev, f);
if (ret) {
return ret;
}
s->num_pages = qemu_get_be32(f);
s->actual = qemu_get_be32(f);
return 0;
}
VirtIODevice *virtio_balloon_init(DeviceState *dev)
{
VirtIOBalloon *s;
int ret;
s = (VirtIOBalloon *)virtio_common_init("virtio-balloon",
VIRTIO_ID_BALLOON,
8, sizeof(VirtIOBalloon));
s->vdev.get_config = virtio_balloon_get_config;
s->vdev.set_config = virtio_balloon_set_config;
s->vdev.get_features = virtio_balloon_get_features;
ret = qemu_add_balloon_handler(virtio_balloon_to_target,
virtio_balloon_stat, s);
if (ret < 0) {
virtio_cleanup(&s->vdev);
return NULL;
}
s->ivq = virtio_add_queue(&s->vdev, 128, virtio_balloon_handle_output);
s->dvq = virtio_add_queue(&s->vdev, 128, virtio_balloon_handle_output);
s->svq = virtio_add_queue(&s->vdev, 128, virtio_balloon_receive_stats);
reset_stats(s);
s->qdev = dev;
register_savevm(dev, "virtio-balloon", -1, 1,
virtio_balloon_save, virtio_balloon_load, s);
return &s->vdev;
}
void virtio_balloon_exit(VirtIODevice *vdev)
{
VirtIOBalloon *s = DO_UPCAST(VirtIOBalloon, vdev, vdev);
qemu_remove_balloon_handler(s);
unregister_savevm(s->qdev, "virtio-balloon", s);
virtio_cleanup(vdev);
}