qemu/migration/multifd.h

345 lines
9.8 KiB
C
Raw Normal View History

/*
* Multifd common functions
*
* Copyright (c) 2019-2020 Red Hat Inc
*
* Authors:
* Juan Quintela <quintela@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.
*/
#ifndef QEMU_MIGRATION_MULTIFD_H
#define QEMU_MIGRATION_MULTIFD_H
#include "exec/target_page.h"
#include "ram.h"
typedef struct MultiFDRecvData MultiFDRecvData;
typedef struct MultiFDSendData MultiFDSendData;
bool multifd_send_setup(void);
void multifd_send_shutdown(void);
void multifd_send_channel_created(void);
int multifd_recv_setup(Error **errp);
void multifd_recv_cleanup(void);
void multifd_recv_shutdown(void);
bool multifd_recv_all_channels_created(void);
2022-12-20 21:44:18 +03:00
void multifd_recv_new_channel(QIOChannel *ioc, Error **errp);
void multifd_recv_sync_main(void);
int multifd_send_sync_main(void);
bool multifd_queue_page(RAMBlock *block, ram_addr_t offset);
bool multifd_recv(void);
MultiFDRecvData *multifd_get_recv_data(void);
/* Multifd Compression flags */
#define MULTIFD_FLAG_SYNC (1 << 0)
/* We reserve 5 bits for compression methods */
#define MULTIFD_FLAG_COMPRESSION_MASK (0x1f << 1)
/* we need to be compatible. Before compression value was 0 */
#define MULTIFD_FLAG_NOCOMP (0 << 1)
#define MULTIFD_FLAG_ZLIB (1 << 1)
#define MULTIFD_FLAG_ZSTD (2 << 1)
#define MULTIFD_FLAG_QPL (4 << 1)
#define MULTIFD_FLAG_UADK (8 << 1)
#define MULTIFD_FLAG_QATZIP (16 << 1)
/* This value needs to be a multiple of qemu_target_page_size() */
#define MULTIFD_PACKET_SIZE (512 * 1024)
typedef struct {
uint32_t magic;
uint32_t version;
uint32_t flags;
/* maximum number of allocated pages */
uint32_t pages_alloc;
/* non zero pages */
uint32_t normal_pages;
/* size of the next packet that contains pages */
uint32_t next_packet_size;
uint64_t packet_num;
/* zero pages */
uint32_t zero_pages;
uint32_t unused32[1]; /* Reserved for future use */
uint64_t unused64[3]; /* Reserved for future use */
char ramblock[256];
/*
* This array contains the pointers to:
* - normal pages (initial normal_pages entries)
* - zero pages (following zero_pages entries)
*/
uint64_t offset[];
} __attribute__((packed)) MultiFDPacket_t;
typedef struct {
/* number of used pages */
uint32_t num;
/* number of normal pages */
uint32_t normal_num;
RAMBlock *block;
/* offset of each page */
ram_addr_t offset[];
} MultiFDPages_t;
struct MultiFDRecvData {
void *opaque;
size_t size;
/* for preadv */
off_t file_offset;
};
typedef enum {
MULTIFD_PAYLOAD_NONE,
MULTIFD_PAYLOAD_RAM,
} MultiFDPayloadType;
typedef union MultiFDPayload {
MultiFDPages_t ram;
} MultiFDPayload;
struct MultiFDSendData {
MultiFDPayloadType type;
MultiFDPayload u;
};
static inline bool multifd_payload_empty(MultiFDSendData *data)
{
return data->type == MULTIFD_PAYLOAD_NONE;
}
static inline void multifd_set_payload_type(MultiFDSendData *data,
MultiFDPayloadType type)
{
data->type = type;
}
typedef struct {
/* Fields are only written at creating/deletion time */
/* No lock required for them, they are read only */
/* channel number */
uint8_t id;
/* channel thread name */
char *name;
/* channel thread id */
QemuThread thread;
migration/multifd: Remove p->running We currently only need p->running to avoid calling qemu_thread_join() on a non existent thread if the thread has never been created. However, there are at least two bugs in this logic: 1) On the sending side, p->running is set too early and qemu_thread_create() can be skipped due to an error during TLS handshake, leaving the flag set and leading to a crash when multifd_send_cleanup() calls qemu_thread_join(). 2) During exit, the multifd thread clears the flag while holding the channel lock. The counterpart at multifd_send_cleanup() reads the flag outside of the lock and might free the mutex while the multifd thread still has it locked. Fix the first issue by setting the flag right before creating the thread. Rename it from p->running to p->thread_created to clarify its usage. Fix the second issue by not clearing the flag at the multifd thread exit. We don't have any use for that. Note that these bugs are straight-forward logic issues and not race conditions. There is still a gap for races to affect this code due to multifd_send_cleanup() being allowed to run concurrently with the thread creation loop. This issue is solved in the next patches. Cc: qemu-stable <qemu-stable@nongnu.org> Fixes: 29647140157a ("migration/tls: add support for multifd tls-handshake") Reported-by: Avihai Horon <avihaih@nvidia.com> Reported-by: chenyuhui5@huawei.com Reviewed-by: Peter Xu <peterx@redhat.com> Signed-off-by: Fabiano Rosas <farosas@suse.de> Link: https://lore.kernel.org/r/20240206215118.6171-3-farosas@suse.de Signed-off-by: Peter Xu <peterx@redhat.com>
2024-02-07 00:51:14 +03:00
bool thread_created;
QemuThread tls_thread;
bool tls_thread_created;
/* communication channel */
QIOChannel *c;
/* packet allocated len */
uint32_t packet_len;
/* multifd flags for sending ram */
int write_flags;
/* sem where to wait for more work */
QemuSemaphore sem;
/* syncs main thread and channels */
QemuSemaphore sem_sync;
/* multifd flags for each packet */
uint32_t flags;
migration/multifd: Separate SYNC request with normal jobs Multifd provide a threaded model for processing jobs. On sender side, there can be two kinds of job: (1) a list of pages to send, or (2) a sync request. The sync request is a very special kind of job. It never contains a page array, but only a multifd packet telling the dest side to synchronize with sent pages. Before this patch, both requests use the pending_job field, no matter what the request is, it will boost pending_job, while multifd sender thread will decrement it after it finishes one job. However this should be racy, because SYNC is special in that it needs to set p->flags with MULTIFD_FLAG_SYNC, showing that this is a sync request. Consider a sequence of operations where: - migration thread enqueue a job to send some pages, pending_job++ (0->1) - [...before the selected multifd sender thread wakes up...] - migration thread enqueue another job to sync, pending_job++ (1->2), setup p->flags=MULTIFD_FLAG_SYNC - multifd sender thread wakes up, found pending_job==2 - send the 1st packet with MULTIFD_FLAG_SYNC and list of pages - send the 2nd packet with flags==0 and no pages This is not expected, because MULTIFD_FLAG_SYNC should hopefully be done after all the pages are received. Meanwhile, the 2nd packet will be completely useless, which contains zero information. I didn't verify above, but I think this issue is still benign in that at least on the recv side we always receive pages before handling MULTIFD_FLAG_SYNC. However that's not always guaranteed and just tricky. One other reason I want to separate it is using p->flags to communicate between the two threads is also not clearly defined, it's very hard to read and understand why accessing p->flags is always safe; see the current impl of multifd_send_thread() where we tried to cache only p->flags. It doesn't need to be that complicated. This patch introduces pending_sync, a separate flag just to show that the requester needs a sync. Alongside, we remove the tricky caching of p->flags now because after this patch p->flags should only be used by multifd sender thread now, which will be crystal clear. So it is always thread safe to access p->flags. With that, we can also safely convert the pending_job into a boolean, because we don't support >1 pending jobs anyway. Always use atomic ops to access both flags to make sure no cache effect. When at it, drop the initial setting of "pending_job = 0" because it's always allocated using g_new0(). Reviewed-by: Fabiano Rosas <farosas@suse.de> Link: https://lore.kernel.org/r/20240202102857.110210-7-peterx@redhat.com Signed-off-by: Peter Xu <peterx@redhat.com>
2024-02-02 13:28:40 +03:00
/*
* The sender thread has work to do if either of below boolean is set.
*
* @pending_job: a job is pending
* @pending_sync: a sync request is pending
*
* For both of these fields, they're only set by the requesters, and
* cleared by the multifd sender threads.
*/
bool pending_job;
bool pending_sync;
MultiFDSendData *data;
/* thread local variables. No locking required */
/* pointer to the packet */
MultiFDPacket_t *packet;
/* size of the next packet that contains pages */
uint32_t next_packet_size;
/* packets sent through this channel */
uint64_t packets_sent;
/* buffers to send */
struct iovec *iov;
/* number of iovs used */
uint32_t iovs_num;
/* used for compression methods */
void *compress_data;
} MultiFDSendParams;
typedef struct {
/* Fields are only written at creating/deletion time */
/* No lock required for them, they are read only */
/* channel number */
uint8_t id;
/* channel thread name */
char *name;
/* channel thread id */
QemuThread thread;
migration/multifd: Remove p->running We currently only need p->running to avoid calling qemu_thread_join() on a non existent thread if the thread has never been created. However, there are at least two bugs in this logic: 1) On the sending side, p->running is set too early and qemu_thread_create() can be skipped due to an error during TLS handshake, leaving the flag set and leading to a crash when multifd_send_cleanup() calls qemu_thread_join(). 2) During exit, the multifd thread clears the flag while holding the channel lock. The counterpart at multifd_send_cleanup() reads the flag outside of the lock and might free the mutex while the multifd thread still has it locked. Fix the first issue by setting the flag right before creating the thread. Rename it from p->running to p->thread_created to clarify its usage. Fix the second issue by not clearing the flag at the multifd thread exit. We don't have any use for that. Note that these bugs are straight-forward logic issues and not race conditions. There is still a gap for races to affect this code due to multifd_send_cleanup() being allowed to run concurrently with the thread creation loop. This issue is solved in the next patches. Cc: qemu-stable <qemu-stable@nongnu.org> Fixes: 29647140157a ("migration/tls: add support for multifd tls-handshake") Reported-by: Avihai Horon <avihaih@nvidia.com> Reported-by: chenyuhui5@huawei.com Reviewed-by: Peter Xu <peterx@redhat.com> Signed-off-by: Fabiano Rosas <farosas@suse.de> Link: https://lore.kernel.org/r/20240206215118.6171-3-farosas@suse.de Signed-off-by: Peter Xu <peterx@redhat.com>
2024-02-07 00:51:14 +03:00
bool thread_created;
/* communication channel */
QIOChannel *c;
/* packet allocated len */
uint32_t packet_len;
/* syncs main thread and channels */
QemuSemaphore sem_sync;
/* sem where to wait for more work */
QemuSemaphore sem;
/* this mutex protects the following parameters */
QemuMutex mutex;
/* should this thread finish */
bool quit;
/* multifd flags for each packet */
uint32_t flags;
/* global number of generated multifd packets */
uint64_t packet_num;
int pending_job;
MultiFDRecvData *data;
/* thread local variables. No locking required */
/* pointer to the packet */
MultiFDPacket_t *packet;
/* size of the next packet that contains pages */
uint32_t next_packet_size;
/* packets received through this channel */
uint64_t packets_recved;
/* ramblock */
RAMBlock *block;
/* ramblock host address */
uint8_t *host;
/* buffers to recv */
struct iovec *iov;
/* Pages that are not zero */
ram_addr_t *normal;
/* num of non zero pages */
uint32_t normal_num;
/* Pages that are zero */
ram_addr_t *zero;
/* num of zero pages */
uint32_t zero_num;
/* used for de-compression methods */
void *compress_data;
} MultiFDRecvParams;
typedef struct {
/*
* The send_setup, send_cleanup, send_prepare are only called on
* the QEMU instance at the migration source.
*/
/*
* Setup for sending side. Called once per channel during channel
* setup phase.
*
* Must allocate p->iov. If packets are in use (default), one
* extra iovec must be allocated for the packet header. Any memory
* allocated in this hook must be released at send_cleanup.
*
* p->write_flags may be used for passing flags to the QIOChannel.
*
* p->compression_data may be used by compression methods to store
* compression data.
*/
int (*send_setup)(MultiFDSendParams *p, Error **errp);
/*
* Cleanup for sending side. Called once per channel during
* channel cleanup phase.
*/
void (*send_cleanup)(MultiFDSendParams *p, Error **errp);
/*
* Prepare the send packet. Called as a result of multifd_send()
* on the client side, with p pointing to the MultiFDSendParams of
* a channel that is currently idle.
*
* Must populate p->iov with the data to be sent, increment
* p->iovs_num to match the amount of iovecs used and set
* p->next_packet_size with the amount of data currently present
* in p->iov.
*
* Must indicate whether this is a compression packet by setting
* p->flags.
*
* As a last step, if packets are in use (default), must prepare
* the packet by calling multifd_send_fill_packet().
*/
int (*send_prepare)(MultiFDSendParams *p, Error **errp);
/*
* The recv_setup, recv_cleanup, recv are only called on the QEMU
* instance at the migration destination.
*/
/*
* Setup for receiving side. Called once per channel during
* channel setup phase. May be empty.
*
* May allocate data structures for the receiving of data. May use
* p->iov. Compression methods may use p->compress_data.
*/
int (*recv_setup)(MultiFDRecvParams *p, Error **errp);
/*
* Cleanup for receiving side. Called once per channel during
* channel cleanup phase. May be empty.
*/
void (*recv_cleanup)(MultiFDRecvParams *p);
/*
* Data receive method. Called as a result of multifd_recv() on
* the client side, with p pointing to the MultiFDRecvParams of a
* channel that is currently idle. Only called if there is data
* available to receive.
*
* Must validate p->flags according to what was set at
* send_prepare.
*
* Must read the data from the QIOChannel p->c.
*/
int (*recv)(MultiFDRecvParams *p, Error **errp);
} MultiFDMethods;
void multifd_register_ops(int method, const MultiFDMethods *ops);
void multifd_send_fill_packet(MultiFDSendParams *p);
bool multifd_send_prepare_common(MultiFDSendParams *p);
void multifd_send_zero_page_detect(MultiFDSendParams *p);
void multifd_recv_zero_page_process(MultiFDRecvParams *p);
static inline void multifd_send_prepare_header(MultiFDSendParams *p)
{
p->iov[0].iov_len = p->packet_len;
p->iov[0].iov_base = p->packet;
p->iovs_num++;
}
void multifd_channel_connect(MultiFDSendParams *p, QIOChannel *ioc);
bool multifd_send(MultiFDSendData **send_data);
MultiFDSendData *multifd_send_data_alloc(void);
static inline uint32_t multifd_ram_page_size(void)
{
return qemu_target_page_size();
}
static inline uint32_t multifd_ram_page_count(void)
{
return MULTIFD_PACKET_SIZE / qemu_target_page_size();
}
void multifd_ram_save_setup(void);
void multifd_ram_save_cleanup(void);
int multifd_ram_flush_and_sync(void);
size_t multifd_ram_payload_size(void);
void multifd_ram_fill_packet(MultiFDSendParams *p);
int multifd_ram_unfill_packet(MultiFDRecvParams *p, Error **errp);
#endif