1
0
Files
Greg Kroah-Hartman d0ed7f061d Merge 4.9.207 into android-4.9-q
Changes in 4.9.207
	arm64: tegra: Fix 'active-low' warning for Jetson TX1 regulator
	usb: gadget: u_serial: add missing port entry locking
	tty: serial: fsl_lpuart: use the sg count from dma_map_sg
	tty: serial: msm_serial: Fix flow control
	serial: pl011: Fix DMA ->flush_buffer()
	serial: serial_core: Perform NULL checks for break_ctl ops
	serial: ifx6x60: add missed pm_runtime_disable
	autofs: fix a leak in autofs_expire_indirect()
	RDMA/hns: Correct the value of HNS_ROCE_HEM_CHUNK_LEN
	exportfs_decode_fh(): negative pinned may become positive without the parent locked
	audit_get_nd(): don't unlock parent too early
	NFC: nxp-nci: Fix NULL pointer dereference after I2C communication error
	Input: cyttsp4_core - fix use after free bug
	ALSA: pcm: Fix stream lock usage in snd_pcm_period_elapsed()
	rsxx: add missed destroy_workqueue calls in remove
	net: ep93xx_eth: fix mismatch of request_mem_region in remove
	serial: core: Allow processing sysrq at port unlock time
	cxgb4vf: fix memleak in mac_hlist initialization
	iwlwifi: mvm: Send non offchannel traffic via AP sta
	ARM: 8813/1: Make aligned 2-byte getuser()/putuser() atomic on ARMv6+
	net/mlx5: Release resource on error flow
	extcon: max8997: Fix lack of path setting in USB device mode
	clk: rockchip: fix rk3188 sclk_smc gate data
	clk: rockchip: fix rk3188 sclk_mac_lbtest parameter ordering
	ARM: dts: rockchip: Fix rk3288-rock2 vcc_flash name
	dlm: fix missing idr_destroy for recover_idr
	MIPS: SiByte: Enable ZONE_DMA32 for LittleSur
	scsi: zfcp: drop default switch case which might paper over missing case
	pinctrl: qcom: ssbi-gpio: fix gpio-hog related boot issues
	Staging: iio: adt7316: Fix i2c data reading, set the data field
	regulator: Fix return value of _set_load() stub
	MIPS: OCTEON: octeon-platform: fix typing
	math-emu/soft-fp.h: (_FP_ROUND_ZERO) cast 0 to void to fix warning
	rtc: max8997: Fix the returned value in case of error in 'max8997_rtc_read_alarm()'
	rtc: dt-binding: abx80x: fix resistance scale
	ARM: dts: exynos: Use Samsung SoC specific compatible for DWC2 module
	media: pulse8-cec: return 0 when invalidating the logical address
	dmaengine: coh901318: Fix a double-lock bug
	dmaengine: coh901318: Remove unused variable
	usb: dwc3: don't log probe deferrals; but do log other error codes
	ACPI: fix acpi_find_child_device() invocation in acpi_preset_companion()
	dma-mapping: fix return type of dma_set_max_seg_size()
	altera-stapl: check for a null key before strcasecmp'ing it
	serial: imx: fix error handling in console_setup
	i2c: imx: don't print error message on probe defer
	dlm: NULL check before kmem_cache_destroy is not needed
	ARM: debug: enable UART1 for socfpga Cyclone5
	nfsd: fix a warning in __cld_pipe_upcall()
	ARM: OMAP1/2: fix SoC name printing
	net/x25: fix called/calling length calculation in x25_parse_address_block
	net/x25: fix null_x25_address handling
	ARM: dts: mmp2: fix the gpio interrupt cell number
	ARM: dts: realview-pbx: Fix duplicate regulator nodes
	tcp: fix off-by-one bug on aborting window-probing socket
	tcp: fix SNMP TCP timeout under-estimation
	modpost: skip ELF local symbols during section mismatch check
	kbuild: fix single target build for external module
	mtd: fix mtd_oobavail() incoherent returned value
	ARM: dts: pxa: clean up USB controller nodes
	clk: sunxi-ng: h3/h5: Fix CSI_MCLK parent
	ARM: dts: realview: Fix some more duplicate regulator nodes
	dlm: fix invalid cluster name warning
	net/mlx4_core: Fix return codes of unsupported operations
	powerpc/math-emu: Update macros from GCC
	MIPS: OCTEON: cvmx_pko_mem_debug8: use oldest forward compatible definition
	nfsd: Return EPERM, not EACCES, in some SETATTR cases
	tty: Don't block on IO when ldisc change is pending
	media: stkwebcam: Bugfix for wrong return values
	mlx4: Use snprintf instead of complicated strcpy
	ARM: dts: sunxi: Fix PMU compatible strings
	sched/fair: Scale bandwidth quota and period without losing quota/period ratio precision
	fuse: verify nlink
	fuse: verify attributes
	ALSA: pcm: oss: Avoid potential buffer overflows
	Input: goodix - add upside-down quirk for Teclast X89 tablet
	coresight: etm4x: Fix input validation for sysfs.
	x86/PCI: Avoid AMD FCH XHCI USB PME# from D0 defect
	CIFS: Fix NULL-pointer dereference in smb2_push_mandatory_locks
	CIFS: Fix SMB2 oplock break processing
	tty: vt: keyboard: reject invalid keycodes
	can: slcan: Fix use-after-free Read in slcan_open
	jbd2: Fix possible overflow in jbd2_log_space_left()
	drm/i810: Prevent underflow in ioctl
	KVM: x86: do not modify masked bits of shared MSRs
	KVM: x86: fix presentation of TSX feature in ARCH_CAPABILITIES
	crypto: crypto4xx - fix double-free in crypto4xx_destroy_sdr
	crypto: ccp - fix uninitialized list head
	crypto: ecdh - fix big endian bug in ECC library
	crypto: user - fix memory leak in crypto_report
	spi: atmel: Fix CS high support
	RDMA/qib: Validate ->show()/store() callbacks before calling them
	thermal: Fix deadlock in thermal thermal_zone_device_check
	KVM: x86: fix out-of-bounds write in KVM_GET_EMULATED_CPUID (CVE-2019-19332)
	appletalk: Fix potential NULL pointer dereference in unregister_snap_client
	appletalk: Set error code if register_snap_client failed
	usb: gadget: configfs: Fix missing spin_lock_init()
	USB: uas: honor flag to avoid CAPACITY16
	USB: uas: heed CAPACITY_HEURISTICS
	usb: Allow USB device to be warm reset in suspended state
	staging: rtl8188eu: fix interface sanity check
	staging: rtl8712: fix interface sanity check
	staging: gigaset: fix general protection fault on probe
	staging: gigaset: fix illegal free on probe errors
	staging: gigaset: add endpoint-type sanity check
	xhci: Increase STS_HALT timeout in xhci_suspend()
	ARM: dts: pandora-common: define wl1251 as child node of mmc3
	iio: humidity: hdc100x: fix IIO_HUMIDITYRELATIVE channel reporting
	USB: atm: ueagle-atm: add missing endpoint check
	USB: idmouse: fix interface sanity checks
	USB: serial: io_edgeport: fix epic endpoint lookup
	USB: adutux: fix interface sanity check
	usb: core: urb: fix URB structure initialization function
	usb: mon: Fix a deadlock in usbmon between mmap and read
	mtd: spear_smi: Fix Write Burst mode
	virtio-balloon: fix managed page counts when migrating pages between zones
	btrfs: check page->mapping when loading free space cache
	btrfs: Remove btrfs_bio::flags member
	Btrfs: send, skip backreference walking for extents with many references
	btrfs: record all roots for rename exchange on a subvol
	rtlwifi: rtl8192de: Fix missing code to retrieve RX buffer address
	rtlwifi: rtl8192de: Fix missing callback that tests for hw release of buffer
	rtlwifi: rtl8192de: Fix missing enable interrupt flag
	lib: raid6: fix awk build warnings
	ALSA: hda - Fix pending unsol events at shutdown
	workqueue: Fix spurious sanity check failures in destroy_workqueue()
	workqueue: Fix pwq ref leak in rescuer_thread()
	ASoC: Jack: Fix NULL pointer dereference in snd_soc_jack_report
	blk-mq: avoid sysfs buffer overflow with too many CPU cores
	cgroup: pids: use atomic64_t for pids->limit
	ar5523: check NULL before memcpy() in ar5523_cmd()
	media: bdisp: fix memleak on release
	media: radio: wl1273: fix interrupt masking on release
	cpuidle: Do not unset the driver if it is there already
	PM / devfreq: Lock devfreq in trans_stat_show
	ACPI: OSL: only free map once in osl.c
	ACPI: bus: Fix NULL pointer check in acpi_bus_get_private_data()
	ACPI: PM: Avoid attaching ACPI PM domain to certain devices
	pinctrl: samsung: Fix device node refcount leaks in S3C24xx wakeup controller init
	pinctrl: samsung: Fix device node refcount leaks in init code
	mmc: host: omap_hsmmc: add code for special init of wl1251 to get rid of pandora_wl1251_init_card
	ppdev: fix PPGETTIME/PPSETTIME ioctls
	powerpc: Allow 64bit VDSO __kernel_sync_dicache to work across ranges >4GB
	video/hdmi: Fix AVI bar unpack
	quota: Check that quota is not dirty before release
	ext2: check err when partial != NULL
	quota: fix livelock in dquot_writeback_dquots
	scsi: zfcp: trace channel log even for FCP command responses
	usb: xhci: only set D3hot for pci device
	xhci: Fix memory leak in xhci_add_in_port()
	xhci: make sure interrupts are restored to correct state
	iio: adis16480: Add debugfs_reg_access entry
	Btrfs: fix negative subv_writers counter and data space leak after buffered write
	omap: pdata-quirks: remove openpandora quirks for mmc3 and wl1251
	scsi: lpfc: Cap NPIV vports to 256
	e100: Fix passing zero to 'PTR_ERR' warning in e100_load_ucode_wait
	x86/MCE/AMD: Turn off MC4_MISC thresholding on all family 0x15 models
	x86/MCE/AMD: Carve out the MC4_MISC thresholding quirk
	ath10k: fix fw crash by moving chip reset after napi disabled
	ARM: dts: omap3-tao3530: Fix incorrect MMC card detection GPIO polarity
	pinctrl: samsung: Fix device node refcount leaks in S3C64xx wakeup controller init
	scsi: qla2xxx: Fix DMA unmap leak
	scsi: qla2xxx: Fix session lookup in qlt_abort_work()
	scsi: qla2xxx: Fix qla24xx_process_bidir_cmd()
	scsi: qla2xxx: Always check the qla2x00_wait_for_hba_online() return value
	powerpc: Fix vDSO clock_getres()
	reiserfs: fix extended attributes on the root directory
	firmware: qcom: scm: Ensure 'a0' status code is treated as signed
	mm/shmem.c: cast the type of unmap_start to u64
	ext4: fix a bug in ext4_wait_for_tail_page_commit
	blk-mq: make sure that line break can be printed
	workqueue: Fix missing kfree(rescuer) in destroy_workqueue()
	sunrpc: fix crash when cache_head become valid before update
	net/mlx5e: Fix SFF 8472 eeprom length
	kernel/module.c: wakeup processes in module_wq on module unload
	nvme: host: core: fix precedence of ternary operator
	net: bridge: deny dev_set_mac_address() when unregistering
	net: ethernet: ti: cpsw: fix extra rx interrupt
	openvswitch: support asymmetric conntrack
	tcp: md5: fix potential overestimation of TCP option space
	tipc: fix ordering of tipc module init and exit routine
	inet: protect against too small mtu values.
	tcp: fix rejected syncookies due to stale timestamps
	tcp: tighten acceptance of ACKs not matching a child socket
	tcp: Protect accesses to .ts_recent_stamp with {READ,WRITE}_ONCE()
	Revert "regulator: Defer init completion for a while after late_initcall"
	PCI: Fix Intel ACS quirk UPDCR register address
	PCI/MSI: Fix incorrect MSI-X masking on resume
	xtensa: fix TLB sanity checker
	CIFS: Respect O_SYNC and O_DIRECT flags during reconnect
	ARM: dts: s3c64xx: Fix init order of clock providers
	ARM: tegra: Fix FLOW_CTLR_HALT register clobbering by tegra_resume()
	vfio/pci: call irq_bypass_unregister_producer() before freeing irq
	dma-buf: Fix memory leak in sync_file_merge()
	dm btree: increase rebalance threshold in __rebalance2()
	scsi: iscsi: Fix a potential deadlock in the timeout handler
	drm/radeon: fix r1xx/r2xx register checker for POT textures
	xhci: fix USB3 device initiated resume race with roothub autosuspend
	net: stmmac: use correct DMA buffer size in the RX descriptor
	net: stmmac: don't stop NAPI processing when dropping a packet
	Linux 4.9.207

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
2019-12-24 17:28:43 +03:00

703 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/oom.h>
#include <linux/wait.h>
#include <linux/mm.h>
#include <linux/mount.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 OOM_VBALLOON_DEFAULT_PAGES 256
#define VIRTBALLOON_OOM_NOTIFY_PRIORITY 80
static int oom_pages = OOM_VBALLOON_DEFAULT_PAGES;
module_param(oom_pages, int, S_IRUSR | S_IWUSR);
MODULE_PARM_DESC(oom_pages, "pages to free on OOM");
#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 callback in oom notifier call chain */
struct notifier_block nb;
};
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 struct page *balloon_pfn_to_page(u32 pfn)
{
BUG_ON(pfn % VIRTIO_BALLOON_PAGES_PER_PAGE);
return pfn_to_page(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)
{
struct balloon_dev_info *vb_dev_info = &vb->vb_dev_info;
unsigned num_allocated_pages;
/* We can only do one array worth at a time. */
num = min(num, ARRAY_SIZE(vb->pfns));
mutex_lock(&vb->balloon_lock);
for (vb->num_pfns = 0; vb->num_pfns < num;
vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
struct page *page = balloon_page_enqueue(vb_dev_info);
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;
}
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);
}
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)
{
unsigned int i;
struct page *page;
/* Find pfns pointing at start of each page, get pages and free them. */
for (i = 0; i < vb->num_pfns; i += VIRTIO_BALLOON_PAGES_PER_PAGE) {
page = balloon_pfn_to_page(virtio32_to_cpu(vb->vdev,
vb->pfns[i]));
if (!virtio_has_feature(vb->vdev,
VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
adjust_managed_page_count(page, 1);
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;
/* 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);
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);
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;
all_vm_events(events);
si_meminfo(&i);
available = si_mem_available();
#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]);
#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));
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);
}
/*
* virtballoon_oom_notify - release pages when system is under severe
* memory pressure (called from out_of_memory())
* @self : notifier block struct
* @dummy: not used
* @parm : returned - number of freed pages
*
* The balancing of memory by use of the virtio balloon should not cause
* the termination of processes while there are pages in the balloon.
* If virtio balloon manages to release some memory, it will make the
* system return and retry the allocation that forced the OOM killer
* to run.
*/
static int virtballoon_oom_notify(struct notifier_block *self,
unsigned long dummy, void *parm)
{
struct virtio_balloon *vb;
unsigned long *freed;
unsigned num_freed_pages;
vb = container_of(self, struct virtio_balloon, nb);
if (!virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
return NOTIFY_OK;
freed = parm;
num_freed_pages = leak_balloon(vb, oom_pages);
update_balloon_size(vb);
*freed += num_freed_pages;
return NOTIFY_OK;
}
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 = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names);
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);
if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL)
< 0)
BUG();
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 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 = kmalloc(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);
vb->stop_update = false;
vb->num_pages = 0;
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;
vb->nb.notifier_call = virtballoon_oom_notify;
vb->nb.priority = VIRTBALLOON_OOM_NOTIFY_PRIORITY;
err = register_oom_notifier(&vb->nb);
if (err < 0)
goto out_del_vqs;
#ifdef CONFIG_BALLOON_COMPACTION
balloon_mnt = kern_mount(&balloon_fs);
if (IS_ERR(balloon_mnt)) {
err = PTR_ERR(balloon_mnt);
unregister_oom_notifier(&vb->nb);
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);
unregister_oom_notifier(&vb->nb);
vb->vb_dev_info.inode = NULL;
goto out_del_vqs;
}
vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
#endif
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;
unregister_oom_notifier(&vb->nb);
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 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,
.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");