qemu/migration/postcopy-ram.c
Dr. David Alan Gilbert 5d214a92ac postcopy: Require RAMBlocks that are whole pages
It turns out that it's legal to create a VM with RAMBlocks that aren't
a multiple of the pagesize in use; e.g. a 1025M main memory using
2M host pages.  That breaks postcopy's atomic placement of pages,
so disallow it.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
2017-05-18 18:04:53 +02:00

815 lines
25 KiB
C

/*
* Postcopy migration for RAM
*
* Copyright 2013-2015 Red Hat, Inc. and/or its affiliates
*
* Authors:
* Dave Gilbert <dgilbert@redhat.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*
*/
/*
* Postcopy is a migration technique where the execution flips from the
* source to the destination before all the data has been copied.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "migration/migration.h"
#include "postcopy-ram.h"
#include "sysemu/sysemu.h"
#include "sysemu/balloon.h"
#include "qemu/error-report.h"
#include "trace.h"
/* Arbitrary limit on size of each discard command,
* keeps them around ~200 bytes
*/
#define MAX_DISCARDS_PER_COMMAND 12
struct PostcopyDiscardState {
const char *ramblock_name;
uint16_t cur_entry;
/*
* Start and length of a discard range (bytes)
*/
uint64_t start_list[MAX_DISCARDS_PER_COMMAND];
uint64_t length_list[MAX_DISCARDS_PER_COMMAND];
unsigned int nsentwords;
unsigned int nsentcmds;
};
/* Postcopy needs to detect accesses to pages that haven't yet been copied
* across, and efficiently map new pages in, the techniques for doing this
* are target OS specific.
*/
#if defined(__linux__)
#include <poll.h>
#include <sys/ioctl.h>
#include <sys/syscall.h>
#include <asm/types.h> /* for __u64 */
#endif
#if defined(__linux__) && defined(__NR_userfaultfd) && defined(CONFIG_EVENTFD)
#include <sys/eventfd.h>
#include <linux/userfaultfd.h>
static bool ufd_version_check(int ufd)
{
struct uffdio_api api_struct;
uint64_t ioctl_mask;
api_struct.api = UFFD_API;
api_struct.features = 0;
if (ioctl(ufd, UFFDIO_API, &api_struct)) {
error_report("postcopy_ram_supported_by_host: UFFDIO_API failed: %s",
strerror(errno));
return false;
}
ioctl_mask = (__u64)1 << _UFFDIO_REGISTER |
(__u64)1 << _UFFDIO_UNREGISTER;
if ((api_struct.ioctls & ioctl_mask) != ioctl_mask) {
error_report("Missing userfault features: %" PRIx64,
(uint64_t)(~api_struct.ioctls & ioctl_mask));
return false;
}
if (getpagesize() != ram_pagesize_summary()) {
bool have_hp = false;
/* We've got a huge page */
#ifdef UFFD_FEATURE_MISSING_HUGETLBFS
have_hp = api_struct.features & UFFD_FEATURE_MISSING_HUGETLBFS;
#endif
if (!have_hp) {
error_report("Userfault on this host does not support huge pages");
return false;
}
}
return true;
}
/* Callback from postcopy_ram_supported_by_host block iterator.
*/
static int test_ramblock_postcopiable(const char *block_name, void *host_addr,
ram_addr_t offset, ram_addr_t length, void *opaque)
{
RAMBlock *rb = qemu_ram_block_by_name(block_name);
size_t pagesize = qemu_ram_pagesize(rb);
if (qemu_ram_is_shared(rb)) {
error_report("Postcopy on shared RAM (%s) is not yet supported",
block_name);
return 1;
}
if (length % pagesize) {
error_report("Postcopy requires RAM blocks to be a page size multiple,"
" block %s is 0x" RAM_ADDR_FMT " bytes with a "
"page size of 0x%zx", block_name, length, pagesize);
return 1;
}
return 0;
}
/*
* Note: This has the side effect of munlock'ing all of RAM, that's
* normally fine since if the postcopy succeeds it gets turned back on at the
* end.
*/
bool postcopy_ram_supported_by_host(void)
{
long pagesize = getpagesize();
int ufd = -1;
bool ret = false; /* Error unless we change it */
void *testarea = NULL;
struct uffdio_register reg_struct;
struct uffdio_range range_struct;
uint64_t feature_mask;
if (qemu_target_page_size() > pagesize) {
error_report("Target page size bigger than host page size");
goto out;
}
ufd = syscall(__NR_userfaultfd, O_CLOEXEC);
if (ufd == -1) {
error_report("%s: userfaultfd not available: %s", __func__,
strerror(errno));
goto out;
}
/* Version and features check */
if (!ufd_version_check(ufd)) {
goto out;
}
/* We don't support postcopy with shared RAM yet */
if (qemu_ram_foreach_block(test_ramblock_postcopiable, NULL)) {
goto out;
}
/*
* userfault and mlock don't go together; we'll put it back later if
* it was enabled.
*/
if (munlockall()) {
error_report("%s: munlockall: %s", __func__, strerror(errno));
return -1;
}
/*
* We need to check that the ops we need are supported on anon memory
* To do that we need to register a chunk and see the flags that
* are returned.
*/
testarea = mmap(NULL, pagesize, PROT_READ | PROT_WRITE, MAP_PRIVATE |
MAP_ANONYMOUS, -1, 0);
if (testarea == MAP_FAILED) {
error_report("%s: Failed to map test area: %s", __func__,
strerror(errno));
goto out;
}
g_assert(((size_t)testarea & (pagesize-1)) == 0);
reg_struct.range.start = (uintptr_t)testarea;
reg_struct.range.len = pagesize;
reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING;
if (ioctl(ufd, UFFDIO_REGISTER, &reg_struct)) {
error_report("%s userfault register: %s", __func__, strerror(errno));
goto out;
}
range_struct.start = (uintptr_t)testarea;
range_struct.len = pagesize;
if (ioctl(ufd, UFFDIO_UNREGISTER, &range_struct)) {
error_report("%s userfault unregister: %s", __func__, strerror(errno));
goto out;
}
feature_mask = (__u64)1 << _UFFDIO_WAKE |
(__u64)1 << _UFFDIO_COPY |
(__u64)1 << _UFFDIO_ZEROPAGE;
if ((reg_struct.ioctls & feature_mask) != feature_mask) {
error_report("Missing userfault map features: %" PRIx64,
(uint64_t)(~reg_struct.ioctls & feature_mask));
goto out;
}
/* Success! */
ret = true;
out:
if (testarea) {
munmap(testarea, pagesize);
}
if (ufd != -1) {
close(ufd);
}
return ret;
}
/*
* Setup an area of RAM so that it *can* be used for postcopy later; this
* must be done right at the start prior to pre-copy.
* opaque should be the MIS.
*/
static int init_range(const char *block_name, void *host_addr,
ram_addr_t offset, ram_addr_t length, void *opaque)
{
trace_postcopy_init_range(block_name, host_addr, offset, length);
/*
* We need the whole of RAM to be truly empty for postcopy, so things
* like ROMs and any data tables built during init must be zero'd
* - we're going to get the copy from the source anyway.
* (Precopy will just overwrite this data, so doesn't need the discard)
*/
if (ram_discard_range(block_name, 0, length)) {
return -1;
}
return 0;
}
/*
* At the end of migration, undo the effects of init_range
* opaque should be the MIS.
*/
static int cleanup_range(const char *block_name, void *host_addr,
ram_addr_t offset, ram_addr_t length, void *opaque)
{
MigrationIncomingState *mis = opaque;
struct uffdio_range range_struct;
trace_postcopy_cleanup_range(block_name, host_addr, offset, length);
/*
* We turned off hugepage for the precopy stage with postcopy enabled
* we can turn it back on now.
*/
qemu_madvise(host_addr, length, QEMU_MADV_HUGEPAGE);
/*
* We can also turn off userfault now since we should have all the
* pages. It can be useful to leave it on to debug postcopy
* if you're not sure it's always getting every page.
*/
range_struct.start = (uintptr_t)host_addr;
range_struct.len = length;
if (ioctl(mis->userfault_fd, UFFDIO_UNREGISTER, &range_struct)) {
error_report("%s: userfault unregister %s", __func__, strerror(errno));
return -1;
}
return 0;
}
/*
* Initialise postcopy-ram, setting the RAM to a state where we can go into
* postcopy later; must be called prior to any precopy.
* called from arch_init's similarly named ram_postcopy_incoming_init
*/
int postcopy_ram_incoming_init(MigrationIncomingState *mis, size_t ram_pages)
{
if (qemu_ram_foreach_block(init_range, NULL)) {
return -1;
}
return 0;
}
/*
* At the end of a migration where postcopy_ram_incoming_init was called.
*/
int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
{
trace_postcopy_ram_incoming_cleanup_entry();
if (mis->have_fault_thread) {
uint64_t tmp64;
if (qemu_ram_foreach_block(cleanup_range, mis)) {
return -1;
}
/*
* Tell the fault_thread to exit, it's an eventfd that should
* currently be at 0, we're going to increment it to 1
*/
tmp64 = 1;
if (write(mis->userfault_quit_fd, &tmp64, 8) == 8) {
trace_postcopy_ram_incoming_cleanup_join();
qemu_thread_join(&mis->fault_thread);
} else {
/* Not much we can do here, but may as well report it */
error_report("%s: incrementing userfault_quit_fd: %s", __func__,
strerror(errno));
}
trace_postcopy_ram_incoming_cleanup_closeuf();
close(mis->userfault_fd);
close(mis->userfault_quit_fd);
mis->have_fault_thread = false;
}
qemu_balloon_inhibit(false);
if (enable_mlock) {
if (os_mlock() < 0) {
error_report("mlock: %s", strerror(errno));
/*
* It doesn't feel right to fail at this point, we have a valid
* VM state.
*/
}
}
postcopy_state_set(POSTCOPY_INCOMING_END);
migrate_send_rp_shut(mis, qemu_file_get_error(mis->from_src_file) != 0);
if (mis->postcopy_tmp_page) {
munmap(mis->postcopy_tmp_page, mis->largest_page_size);
mis->postcopy_tmp_page = NULL;
}
if (mis->postcopy_tmp_zero_page) {
munmap(mis->postcopy_tmp_zero_page, mis->largest_page_size);
mis->postcopy_tmp_zero_page = NULL;
}
trace_postcopy_ram_incoming_cleanup_exit();
return 0;
}
/*
* Disable huge pages on an area
*/
static int nhp_range(const char *block_name, void *host_addr,
ram_addr_t offset, ram_addr_t length, void *opaque)
{
trace_postcopy_nhp_range(block_name, host_addr, offset, length);
/*
* Before we do discards we need to ensure those discards really
* do delete areas of the page, even if THP thinks a hugepage would
* be a good idea, so force hugepages off.
*/
qemu_madvise(host_addr, length, QEMU_MADV_NOHUGEPAGE);
return 0;
}
/*
* Userfault requires us to mark RAM as NOHUGEPAGE prior to discard
* however leaving it until after precopy means that most of the precopy
* data is still THPd
*/
int postcopy_ram_prepare_discard(MigrationIncomingState *mis)
{
if (qemu_ram_foreach_block(nhp_range, mis)) {
return -1;
}
postcopy_state_set(POSTCOPY_INCOMING_DISCARD);
return 0;
}
/*
* Mark the given area of RAM as requiring notification to unwritten areas
* Used as a callback on qemu_ram_foreach_block.
* host_addr: Base of area to mark
* offset: Offset in the whole ram arena
* length: Length of the section
* opaque: MigrationIncomingState pointer
* Returns 0 on success
*/
static int ram_block_enable_notify(const char *block_name, void *host_addr,
ram_addr_t offset, ram_addr_t length,
void *opaque)
{
MigrationIncomingState *mis = opaque;
struct uffdio_register reg_struct;
reg_struct.range.start = (uintptr_t)host_addr;
reg_struct.range.len = length;
reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING;
/* Now tell our userfault_fd that it's responsible for this area */
if (ioctl(mis->userfault_fd, UFFDIO_REGISTER, &reg_struct)) {
error_report("%s userfault register: %s", __func__, strerror(errno));
return -1;
}
if (!(reg_struct.ioctls & ((__u64)1 << _UFFDIO_COPY))) {
error_report("%s userfault: Region doesn't support COPY", __func__);
return -1;
}
return 0;
}
/*
* Handle faults detected by the USERFAULT markings
*/
static void *postcopy_ram_fault_thread(void *opaque)
{
MigrationIncomingState *mis = opaque;
struct uffd_msg msg;
int ret;
RAMBlock *rb = NULL;
RAMBlock *last_rb = NULL; /* last RAMBlock we sent part of */
trace_postcopy_ram_fault_thread_entry();
qemu_sem_post(&mis->fault_thread_sem);
while (true) {
ram_addr_t rb_offset;
struct pollfd pfd[2];
/*
* We're mainly waiting for the kernel to give us a faulting HVA,
* however we can be told to quit via userfault_quit_fd which is
* an eventfd
*/
pfd[0].fd = mis->userfault_fd;
pfd[0].events = POLLIN;
pfd[0].revents = 0;
pfd[1].fd = mis->userfault_quit_fd;
pfd[1].events = POLLIN; /* Waiting for eventfd to go positive */
pfd[1].revents = 0;
if (poll(pfd, 2, -1 /* Wait forever */) == -1) {
error_report("%s: userfault poll: %s", __func__, strerror(errno));
break;
}
if (pfd[1].revents) {
trace_postcopy_ram_fault_thread_quit();
break;
}
ret = read(mis->userfault_fd, &msg, sizeof(msg));
if (ret != sizeof(msg)) {
if (errno == EAGAIN) {
/*
* if a wake up happens on the other thread just after
* the poll, there is nothing to read.
*/
continue;
}
if (ret < 0) {
error_report("%s: Failed to read full userfault message: %s",
__func__, strerror(errno));
break;
} else {
error_report("%s: Read %d bytes from userfaultfd expected %zd",
__func__, ret, sizeof(msg));
break; /* Lost alignment, don't know what we'd read next */
}
}
if (msg.event != UFFD_EVENT_PAGEFAULT) {
error_report("%s: Read unexpected event %ud from userfaultfd",
__func__, msg.event);
continue; /* It's not a page fault, shouldn't happen */
}
rb = qemu_ram_block_from_host(
(void *)(uintptr_t)msg.arg.pagefault.address,
true, &rb_offset);
if (!rb) {
error_report("postcopy_ram_fault_thread: Fault outside guest: %"
PRIx64, (uint64_t)msg.arg.pagefault.address);
break;
}
rb_offset &= ~(qemu_ram_pagesize(rb) - 1);
trace_postcopy_ram_fault_thread_request(msg.arg.pagefault.address,
qemu_ram_get_idstr(rb),
rb_offset);
/*
* Send the request to the source - we want to request one
* of our host page sizes (which is >= TPS)
*/
if (rb != last_rb) {
last_rb = rb;
migrate_send_rp_req_pages(mis, qemu_ram_get_idstr(rb),
rb_offset, qemu_ram_pagesize(rb));
} else {
/* Save some space */
migrate_send_rp_req_pages(mis, NULL,
rb_offset, qemu_ram_pagesize(rb));
}
}
trace_postcopy_ram_fault_thread_exit();
return NULL;
}
int postcopy_ram_enable_notify(MigrationIncomingState *mis)
{
/* Open the fd for the kernel to give us userfaults */
mis->userfault_fd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
if (mis->userfault_fd == -1) {
error_report("%s: Failed to open userfault fd: %s", __func__,
strerror(errno));
return -1;
}
/*
* Although the host check already tested the API, we need to
* do the check again as an ABI handshake on the new fd.
*/
if (!ufd_version_check(mis->userfault_fd)) {
return -1;
}
/* Now an eventfd we use to tell the fault-thread to quit */
mis->userfault_quit_fd = eventfd(0, EFD_CLOEXEC);
if (mis->userfault_quit_fd == -1) {
error_report("%s: Opening userfault_quit_fd: %s", __func__,
strerror(errno));
close(mis->userfault_fd);
return -1;
}
qemu_sem_init(&mis->fault_thread_sem, 0);
qemu_thread_create(&mis->fault_thread, "postcopy/fault",
postcopy_ram_fault_thread, mis, QEMU_THREAD_JOINABLE);
qemu_sem_wait(&mis->fault_thread_sem);
qemu_sem_destroy(&mis->fault_thread_sem);
mis->have_fault_thread = true;
/* Mark so that we get notified of accesses to unwritten areas */
if (qemu_ram_foreach_block(ram_block_enable_notify, mis)) {
return -1;
}
/*
* Ballooning can mark pages as absent while we're postcopying
* that would cause false userfaults.
*/
qemu_balloon_inhibit(true);
trace_postcopy_ram_enable_notify();
return 0;
}
/*
* Place a host page (from) at (host) atomically
* returns 0 on success
*/
int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from,
size_t pagesize)
{
struct uffdio_copy copy_struct;
copy_struct.dst = (uint64_t)(uintptr_t)host;
copy_struct.src = (uint64_t)(uintptr_t)from;
copy_struct.len = pagesize;
copy_struct.mode = 0;
/* copy also acks to the kernel waking the stalled thread up
* TODO: We can inhibit that ack and only do it if it was requested
* which would be slightly cheaper, but we'd have to be careful
* of the order of updating our page state.
*/
if (ioctl(mis->userfault_fd, UFFDIO_COPY, &copy_struct)) {
int e = errno;
error_report("%s: %s copy host: %p from: %p (size: %zd)",
__func__, strerror(e), host, from, pagesize);
return -e;
}
trace_postcopy_place_page(host);
return 0;
}
/*
* Place a zero page at (host) atomically
* returns 0 on success
*/
int postcopy_place_page_zero(MigrationIncomingState *mis, void *host,
size_t pagesize)
{
trace_postcopy_place_page_zero(host);
if (pagesize == getpagesize()) {
struct uffdio_zeropage zero_struct;
zero_struct.range.start = (uint64_t)(uintptr_t)host;
zero_struct.range.len = getpagesize();
zero_struct.mode = 0;
if (ioctl(mis->userfault_fd, UFFDIO_ZEROPAGE, &zero_struct)) {
int e = errno;
error_report("%s: %s zero host: %p",
__func__, strerror(e), host);
return -e;
}
} else {
/* The kernel can't use UFFDIO_ZEROPAGE for hugepages */
if (!mis->postcopy_tmp_zero_page) {
mis->postcopy_tmp_zero_page = mmap(NULL, mis->largest_page_size,
PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS,
-1, 0);
if (mis->postcopy_tmp_zero_page == MAP_FAILED) {
int e = errno;
mis->postcopy_tmp_zero_page = NULL;
error_report("%s: %s mapping large zero page",
__func__, strerror(e));
return -e;
}
memset(mis->postcopy_tmp_zero_page, '\0', mis->largest_page_size);
}
return postcopy_place_page(mis, host, mis->postcopy_tmp_zero_page,
pagesize);
}
return 0;
}
/*
* Returns a target page of memory that can be mapped at a later point in time
* using postcopy_place_page
* The same address is used repeatedly, postcopy_place_page just takes the
* backing page away.
* Returns: Pointer to allocated page
*
*/
void *postcopy_get_tmp_page(MigrationIncomingState *mis)
{
if (!mis->postcopy_tmp_page) {
mis->postcopy_tmp_page = mmap(NULL, mis->largest_page_size,
PROT_READ | PROT_WRITE, MAP_PRIVATE |
MAP_ANONYMOUS, -1, 0);
if (mis->postcopy_tmp_page == MAP_FAILED) {
mis->postcopy_tmp_page = NULL;
error_report("%s: %s", __func__, strerror(errno));
return NULL;
}
}
return mis->postcopy_tmp_page;
}
#else
/* No target OS support, stubs just fail */
bool postcopy_ram_supported_by_host(void)
{
error_report("%s: No OS support", __func__);
return false;
}
int postcopy_ram_incoming_init(MigrationIncomingState *mis, size_t ram_pages)
{
error_report("postcopy_ram_incoming_init: No OS support");
return -1;
}
int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
{
assert(0);
return -1;
}
int postcopy_ram_prepare_discard(MigrationIncomingState *mis)
{
assert(0);
return -1;
}
int postcopy_ram_enable_notify(MigrationIncomingState *mis)
{
assert(0);
return -1;
}
int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from,
size_t pagesize)
{
assert(0);
return -1;
}
int postcopy_place_page_zero(MigrationIncomingState *mis, void *host,
size_t pagesize)
{
assert(0);
return -1;
}
void *postcopy_get_tmp_page(MigrationIncomingState *mis)
{
assert(0);
return NULL;
}
#endif
/* ------------------------------------------------------------------------- */
/**
* postcopy_discard_send_init: Called at the start of each RAMBlock before
* asking to discard individual ranges.
*
* @ms: The current migration state.
* @offset: the bitmap offset of the named RAMBlock in the migration
* bitmap.
* @name: RAMBlock that discards will operate on.
*
* returns: a new PDS.
*/
PostcopyDiscardState *postcopy_discard_send_init(MigrationState *ms,
const char *name)
{
PostcopyDiscardState *res = g_malloc0(sizeof(PostcopyDiscardState));
if (res) {
res->ramblock_name = name;
}
return res;
}
/**
* postcopy_discard_send_range: Called by the bitmap code for each chunk to
* discard. May send a discard message, may just leave it queued to
* be sent later.
*
* @ms: Current migration state.
* @pds: Structure initialised by postcopy_discard_send_init().
* @start,@length: a range of pages in the migration bitmap in the
* RAM block passed to postcopy_discard_send_init() (length=1 is one page)
*/
void postcopy_discard_send_range(MigrationState *ms, PostcopyDiscardState *pds,
unsigned long start, unsigned long length)
{
size_t tp_size = qemu_target_page_size();
/* Convert to byte offsets within the RAM block */
pds->start_list[pds->cur_entry] = start * tp_size;
pds->length_list[pds->cur_entry] = length * tp_size;
trace_postcopy_discard_send_range(pds->ramblock_name, start, length);
pds->cur_entry++;
pds->nsentwords++;
if (pds->cur_entry == MAX_DISCARDS_PER_COMMAND) {
/* Full set, ship it! */
qemu_savevm_send_postcopy_ram_discard(ms->to_dst_file,
pds->ramblock_name,
pds->cur_entry,
pds->start_list,
pds->length_list);
pds->nsentcmds++;
pds->cur_entry = 0;
}
}
/**
* postcopy_discard_send_finish: Called at the end of each RAMBlock by the
* bitmap code. Sends any outstanding discard messages, frees the PDS
*
* @ms: Current migration state.
* @pds: Structure initialised by postcopy_discard_send_init().
*/
void postcopy_discard_send_finish(MigrationState *ms, PostcopyDiscardState *pds)
{
/* Anything unsent? */
if (pds->cur_entry) {
qemu_savevm_send_postcopy_ram_discard(ms->to_dst_file,
pds->ramblock_name,
pds->cur_entry,
pds->start_list,
pds->length_list);
pds->nsentcmds++;
}
trace_postcopy_discard_send_finish(pds->ramblock_name, pds->nsentwords,
pds->nsentcmds);
g_free(pds);
}
/*
* Current state of incoming postcopy; note this is not part of
* MigrationIncomingState since it's state is used during cleanup
* at the end as MIS is being freed.
*/
static PostcopyState incoming_postcopy_state;
PostcopyState postcopy_state_get(void)
{
return atomic_mb_read(&incoming_postcopy_state);
}
/* Set the state and return the old state */
PostcopyState postcopy_state_set(PostcopyState new_state)
{
return atomic_xchg(&incoming_postcopy_state, new_state);
}