linux/drivers/xen/balloon.c

640 lines
16 KiB
C
Raw Normal View History

/******************************************************************************
* balloon.c
*
* Xen balloon driver - enables returning/claiming memory to/from Xen.
*
* Copyright (c) 2003, B Dragovic
* Copyright (c) 2003-2004, M Williamson, K Fraser
* Copyright (c) 2005 Dan M. Smith, IBM Corporation
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License version 2
* as published by the Free Software Foundation; or, when distributed
* separately from the Linux kernel or incorporated into other
* software packages, subject to the following license:
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this source file (the "Software"), to deal in the Software without
* restriction, including without limitation the rights to use, copy, modify,
* merge, publish, distribute, sublicense, and/or sell copies of the Software,
* and to permit persons to whom the Software is furnished to do so, subject to
* the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
* IN THE SOFTWARE.
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/bootmem.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/sysdev.h>
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>
2010-03-24 08:04:11 +00:00
#include <linux/gfp.h>
#include <asm/page.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
#include <asm/uaccess.h>
#include <asm/tlb.h>
#include <asm/e820.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
#include <xen/xen.h>
#include <xen/interface/xen.h>
#include <xen/interface/memory.h>
#include <xen/xenbus.h>
#include <xen/features.h>
#include <xen/page.h>
#define PAGES2KB(_p) ((_p)<<(PAGE_SHIFT-10))
#define BALLOON_CLASS_NAME "xen_memory"
/*
* balloon_process() state:
*
* BP_DONE: done or nothing to do,
* BP_EAGAIN: error, go to sleep,
* BP_ECANCELED: error, balloon operation canceled.
*/
enum bp_state {
BP_DONE,
BP_EAGAIN,
BP_ECANCELED
};
#define RETRY_UNLIMITED 0
struct balloon_stats {
/* We aim for 'current allocation' == 'target allocation'. */
unsigned long current_pages;
unsigned long target_pages;
/* Number of pages in high- and low-memory balloons. */
unsigned long balloon_low;
unsigned long balloon_high;
unsigned long schedule_delay;
unsigned long max_schedule_delay;
unsigned long retry_count;
unsigned long max_retry_count;
};
static DEFINE_MUTEX(balloon_mutex);
static struct sys_device balloon_sysdev;
static int register_balloon(struct sys_device *sysdev);
static struct balloon_stats balloon_stats;
/* We increase/decrease in batches which fit in a page */
static unsigned long frame_list[PAGE_SIZE / sizeof(unsigned long)];
#ifdef CONFIG_HIGHMEM
#define inc_totalhigh_pages() (totalhigh_pages++)
#define dec_totalhigh_pages() (totalhigh_pages--)
#else
#define inc_totalhigh_pages() do {} while(0)
#define dec_totalhigh_pages() do {} while(0)
#endif
/* List of ballooned pages, threaded through the mem_map array. */
static LIST_HEAD(ballooned_pages);
/* Main work function, always executed in process context. */
static void balloon_process(struct work_struct *work);
static DECLARE_DELAYED_WORK(balloon_worker, balloon_process);
/* When ballooning out (allocating memory to return to Xen) we don't really
want the kernel to try too hard since that can trigger the oom killer. */
#define GFP_BALLOON \
(GFP_HIGHUSER | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC)
static void scrub_page(struct page *page)
{
#ifdef CONFIG_XEN_SCRUB_PAGES
clear_highpage(page);
#endif
}
/* balloon_append: add the given page to the balloon. */
static void __balloon_append(struct page *page)
{
/* Lowmem is re-populated first, so highmem pages go at list tail. */
if (PageHighMem(page)) {
list_add_tail(&page->lru, &ballooned_pages);
balloon_stats.balloon_high++;
dec_totalhigh_pages();
} else {
list_add(&page->lru, &ballooned_pages);
balloon_stats.balloon_low++;
}
}
static void balloon_append(struct page *page)
{
__balloon_append(page);
totalram_pages--;
}
/* balloon_retrieve: rescue a page from the balloon, if it is not empty. */
static struct page *balloon_retrieve(void)
{
struct page *page;
if (list_empty(&ballooned_pages))
return NULL;
page = list_entry(ballooned_pages.next, struct page, lru);
list_del(&page->lru);
if (PageHighMem(page)) {
balloon_stats.balloon_high--;
inc_totalhigh_pages();
}
else
balloon_stats.balloon_low--;
totalram_pages++;
return page;
}
static struct page *balloon_first_page(void)
{
if (list_empty(&ballooned_pages))
return NULL;
return list_entry(ballooned_pages.next, struct page, lru);
}
static struct page *balloon_next_page(struct page *page)
{
struct list_head *next = page->lru.next;
if (next == &ballooned_pages)
return NULL;
return list_entry(next, struct page, lru);
}
static enum bp_state update_schedule(enum bp_state state)
{
if (state == BP_DONE) {
balloon_stats.schedule_delay = 1;
balloon_stats.retry_count = 1;
return BP_DONE;
}
pr_info("xen_balloon: Retry count: %lu/%lu\n", balloon_stats.retry_count,
balloon_stats.max_retry_count);
++balloon_stats.retry_count;
if (balloon_stats.max_retry_count != RETRY_UNLIMITED &&
balloon_stats.retry_count > balloon_stats.max_retry_count) {
pr_info("xen_balloon: Retry count limit exceeded\n"
"xen_balloon: Balloon operation canceled\n");
balloon_stats.schedule_delay = 1;
balloon_stats.retry_count = 1;
return BP_ECANCELED;
}
balloon_stats.schedule_delay <<= 1;
if (balloon_stats.schedule_delay > balloon_stats.max_schedule_delay)
balloon_stats.schedule_delay = balloon_stats.max_schedule_delay;
return BP_EAGAIN;
}
static unsigned long current_target(void)
{
unsigned long target = balloon_stats.target_pages;
target = min(target,
balloon_stats.current_pages +
balloon_stats.balloon_low +
balloon_stats.balloon_high);
return target;
}
static enum bp_state increase_reservation(unsigned long nr_pages)
{
int rc;
unsigned long pfn, i;
struct page *page;
struct xen_memory_reservation reservation = {
.address_bits = 0,
.extent_order = 0,
.domid = DOMID_SELF
};
if (nr_pages > ARRAY_SIZE(frame_list))
nr_pages = ARRAY_SIZE(frame_list);
page = balloon_first_page();
for (i = 0; i < nr_pages; i++) {
if (!page) {
nr_pages = i;
break;
}
frame_list[i] = page_to_pfn(page);
page = balloon_next_page(page);
}
set_xen_guest_handle(reservation.extent_start, frame_list);
reservation.nr_extents = nr_pages;
rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
if (rc <= 0) {
pr_info("xen_balloon: %s: Cannot allocate memory\n", __func__);
return BP_EAGAIN;
}
for (i = 0; i < rc; i++) {
page = balloon_retrieve();
BUG_ON(page == NULL);
pfn = page_to_pfn(page);
BUG_ON(!xen_feature(XENFEAT_auto_translated_physmap) &&
phys_to_machine_mapping_valid(pfn));
set_phys_to_machine(pfn, frame_list[i]);
/* Link back into the page tables if not highmem. */
if (pfn < max_low_pfn) {
int ret;
ret = HYPERVISOR_update_va_mapping(
(unsigned long)__va(pfn << PAGE_SHIFT),
mfn_pte(frame_list[i], PAGE_KERNEL),
0);
BUG_ON(ret);
}
/* Relinquish the page back to the allocator. */
ClearPageReserved(page);
init_page_count(page);
__free_page(page);
}
balloon_stats.current_pages += rc;
return BP_DONE;
}
static enum bp_state decrease_reservation(unsigned long nr_pages)
{
enum bp_state state = BP_DONE;
unsigned long pfn, i;
struct page *page;
int ret;
struct xen_memory_reservation reservation = {
.address_bits = 0,
.extent_order = 0,
.domid = DOMID_SELF
};
if (nr_pages > ARRAY_SIZE(frame_list))
nr_pages = ARRAY_SIZE(frame_list);
for (i = 0; i < nr_pages; i++) {
if ((page = alloc_page(GFP_BALLOON)) == NULL) {
pr_info("xen_balloon: %s: Cannot allocate memory\n", __func__);
nr_pages = i;
state = BP_EAGAIN;
break;
}
pfn = page_to_pfn(page);
frame_list[i] = pfn_to_mfn(pfn);
scrub_page(page);
if (!PageHighMem(page)) {
ret = HYPERVISOR_update_va_mapping(
(unsigned long)__va(pfn << PAGE_SHIFT),
__pte_ma(0), 0);
BUG_ON(ret);
}
}
/* Ensure that ballooned highmem pages don't have kmaps. */
kmap_flush_unused();
flush_tlb_all();
/* No more mappings: invalidate P2M and add to balloon. */
for (i = 0; i < nr_pages; i++) {
pfn = mfn_to_pfn(frame_list[i]);
set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
balloon_append(pfn_to_page(pfn));
}
set_xen_guest_handle(reservation.extent_start, frame_list);
reservation.nr_extents = nr_pages;
ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
BUG_ON(ret != nr_pages);
balloon_stats.current_pages -= nr_pages;
return state;
}
/*
* We avoid multiple worker processes conflicting via the balloon mutex.
* We may of course race updates of the target counts (which are protected
* by the balloon lock), or with changes to the Xen hard limit, but we will
* recover from these in time.
*/
static void balloon_process(struct work_struct *work)
{
enum bp_state state = BP_DONE;
long credit;
mutex_lock(&balloon_mutex);
do {
credit = current_target() - balloon_stats.current_pages;
if (credit > 0)
state = increase_reservation(credit);
if (credit < 0)
state = decrease_reservation(-credit);
state = update_schedule(state);
#ifndef CONFIG_PREEMPT
if (need_resched())
schedule();
#endif
} while (credit && state == BP_DONE);
/* Schedule more work if there is some still to be done. */
if (state == BP_EAGAIN)
schedule_delayed_work(&balloon_worker, balloon_stats.schedule_delay * HZ);
mutex_unlock(&balloon_mutex);
}
/* Resets the Xen limit, sets new target, and kicks off processing. */
static void balloon_set_new_target(unsigned long target)
{
/* No need for lock. Not read-modify-write updates. */
balloon_stats.target_pages = target;
schedule_delayed_work(&balloon_worker, 0);
}
static struct xenbus_watch target_watch =
{
.node = "memory/target"
};
/* React to a change in the target key */
static void watch_target(struct xenbus_watch *watch,
const char **vec, unsigned int len)
{
unsigned long long new_target;
int err;
err = xenbus_scanf(XBT_NIL, "memory", "target", "%llu", &new_target);
if (err != 1) {
/* This is ok (for domain0 at least) - so just return */
return;
}
/* The given memory/target value is in KiB, so it needs converting to
* pages. PAGE_SHIFT converts bytes to pages, hence PAGE_SHIFT - 10.
*/
balloon_set_new_target(new_target >> (PAGE_SHIFT - 10));
}
static int balloon_init_watcher(struct notifier_block *notifier,
unsigned long event,
void *data)
{
int err;
err = register_xenbus_watch(&target_watch);
if (err)
printk(KERN_ERR "Failed to set balloon watcher\n");
return NOTIFY_DONE;
}
static struct notifier_block xenstore_notifier;
static int __init balloon_init(void)
{
unsigned long pfn, extra_pfn_end;
struct page *page;
if (!xen_pv_domain())
return -ENODEV;
pr_info("xen_balloon: Initialising balloon driver.\n");
balloon_stats.current_pages = min(xen_start_info->nr_pages, max_pfn);
balloon_stats.target_pages = balloon_stats.current_pages;
balloon_stats.balloon_low = 0;
balloon_stats.balloon_high = 0;
balloon_stats.schedule_delay = 1;
balloon_stats.max_schedule_delay = 32;
balloon_stats.retry_count = 1;
balloon_stats.max_retry_count = 16;
register_balloon(&balloon_sysdev);
/*
* Initialise the balloon with excess memory space. We need
* to make sure we don't add memory which doesn't exist or
* logically exist. The E820 map can be trimmed to be smaller
* than the amount of physical memory due to the mem= command
* line parameter. And if this is a 32-bit non-HIGHMEM kernel
* on a system with memory which requires highmem to access,
* don't try to use it.
*/
extra_pfn_end = min(min(max_pfn, e820_end_of_ram_pfn()),
(unsigned long)PFN_DOWN(xen_extra_mem_start + xen_extra_mem_size));
for (pfn = PFN_UP(xen_extra_mem_start);
pfn < extra_pfn_end;
pfn++) {
page = pfn_to_page(pfn);
/* totalram_pages doesn't include the boot-time
balloon extension, so don't subtract from it. */
__balloon_append(page);
}
target_watch.callback = watch_target;
xenstore_notifier.notifier_call = balloon_init_watcher;
register_xenstore_notifier(&xenstore_notifier);
return 0;
}
subsys_initcall(balloon_init);
static void balloon_exit(void)
{
/* XXX - release balloon here */
return;
}
module_exit(balloon_exit);
#define BALLOON_SHOW(name, format, args...) \
static ssize_t show_##name(struct sys_device *dev, \
struct sysdev_attribute *attr, \
char *buf) \
{ \
return sprintf(buf, format, ##args); \
} \
static SYSDEV_ATTR(name, S_IRUGO, show_##name, NULL)
BALLOON_SHOW(current_kb, "%lu\n", PAGES2KB(balloon_stats.current_pages));
BALLOON_SHOW(low_kb, "%lu\n", PAGES2KB(balloon_stats.balloon_low));
BALLOON_SHOW(high_kb, "%lu\n", PAGES2KB(balloon_stats.balloon_high));
static SYSDEV_ULONG_ATTR(schedule_delay, 0444, balloon_stats.schedule_delay);
static SYSDEV_ULONG_ATTR(max_schedule_delay, 0644, balloon_stats.max_schedule_delay);
static SYSDEV_ULONG_ATTR(retry_count, 0444, balloon_stats.retry_count);
static SYSDEV_ULONG_ATTR(max_retry_count, 0644, balloon_stats.max_retry_count);
static ssize_t show_target_kb(struct sys_device *dev, struct sysdev_attribute *attr,
char *buf)
{
return sprintf(buf, "%lu\n", PAGES2KB(balloon_stats.target_pages));
}
static ssize_t store_target_kb(struct sys_device *dev,
struct sysdev_attribute *attr,
const char *buf,
size_t count)
{
char *endchar;
unsigned long long target_bytes;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
target_bytes = simple_strtoull(buf, &endchar, 0) * 1024;
balloon_set_new_target(target_bytes >> PAGE_SHIFT);
return count;
}
static SYSDEV_ATTR(target_kb, S_IRUGO | S_IWUSR,
show_target_kb, store_target_kb);
static ssize_t show_target(struct sys_device *dev, struct sysdev_attribute *attr,
char *buf)
{
return sprintf(buf, "%llu\n",
(unsigned long long)balloon_stats.target_pages
<< PAGE_SHIFT);
}
static ssize_t store_target(struct sys_device *dev,
struct sysdev_attribute *attr,
const char *buf,
size_t count)
{
char *endchar;
unsigned long long target_bytes;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
target_bytes = memparse(buf, &endchar);
balloon_set_new_target(target_bytes >> PAGE_SHIFT);
return count;
}
static SYSDEV_ATTR(target, S_IRUGO | S_IWUSR,
show_target, store_target);
static struct sysdev_attribute *balloon_attrs[] = {
&attr_target_kb,
&attr_target,
&attr_schedule_delay.attr,
&attr_max_schedule_delay.attr,
&attr_retry_count.attr,
&attr_max_retry_count.attr
};
static struct attribute *balloon_info_attrs[] = {
&attr_current_kb.attr,
&attr_low_kb.attr,
&attr_high_kb.attr,
NULL
};
static struct attribute_group balloon_info_group = {
.name = "info",
.attrs = balloon_info_attrs,
};
static struct sysdev_class balloon_sysdev_class = {
.name = BALLOON_CLASS_NAME,
};
static int register_balloon(struct sys_device *sysdev)
{
int i, error;
error = sysdev_class_register(&balloon_sysdev_class);
if (error)
return error;
sysdev->id = 0;
sysdev->cls = &balloon_sysdev_class;
error = sysdev_register(sysdev);
if (error) {
sysdev_class_unregister(&balloon_sysdev_class);
return error;
}
for (i = 0; i < ARRAY_SIZE(balloon_attrs); i++) {
error = sysdev_create_file(sysdev, balloon_attrs[i]);
if (error)
goto fail;
}
error = sysfs_create_group(&sysdev->kobj, &balloon_info_group);
if (error)
goto fail;
return 0;
fail:
while (--i >= 0)
sysdev_remove_file(sysdev, balloon_attrs[i]);
sysdev_unregister(sysdev);
sysdev_class_unregister(&balloon_sysdev_class);
return error;
}
MODULE_LICENSE("GPL");