a937f8e857
virtio_blk_dma_restart_cb() is tricky because the BH must deal with
virtio_blk_data_plane_start()/virtio_blk_data_plane_stop() being called.
There are two issues with the code:
1. virtio_blk_realize() should use qdev_add_vm_change_state_handler()
instead of qemu_add_vm_change_state_handler(). This ensures the
ordering with virtio_init()'s vm change state handler that calls
virtio_blk_data_plane_start()/virtio_blk_data_plane_stop() is
well-defined. Then blk's AioContext is guaranteed to be up-to-date in
virtio_blk_dma_restart_cb() and it's no longer necessary to have a
special case for virtio_blk_data_plane_start().
2. Only blk_drain() waits for virtio_blk_dma_restart_cb()'s
blk_inc_in_flight() to be decremented. The bdrv_drain() family of
functions do not wait for BlockBackend's in_flight counter to reach
zero. virtio_blk_data_plane_stop() relies on blk_set_aio_context()'s
implicit drain, but that's a bdrv_drain() and not a blk_drain().
Note that virtio_blk_reset() already correctly relies on blk_drain().
If virtio_blk_data_plane_stop() switches to blk_drain() then we can
properly wait for pending virtio_blk_dma_restart_bh() calls.
Once these issues are taken care of the code becomes simpler. This
change is in preparation for multiple IOThreads in virtio-blk where we
need to clean up the multi-threading behavior.
I ran the reproducer from commit 49b44549ac ("virtio-blk: On restart,
process queued requests in the proper context") to check that there is
no regression.
Cc: Sergio Lopez <slp@redhat.com>
Cc: Kevin Wolf <kwolf@redhat.com>
Cc: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
Message-id: 20221102182337.252202-1-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
97 lines
2.2 KiB
C
97 lines
2.2 KiB
C
/*
|
|
* Virtio Block Device
|
|
*
|
|
* Copyright IBM, Corp. 2007
|
|
*
|
|
* 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.
|
|
*
|
|
*/
|
|
|
|
#ifndef QEMU_VIRTIO_BLK_H
|
|
#define QEMU_VIRTIO_BLK_H
|
|
|
|
#include "standard-headers/linux/virtio_blk.h"
|
|
#include "hw/virtio/virtio.h"
|
|
#include "hw/block/block.h"
|
|
#include "sysemu/iothread.h"
|
|
#include "sysemu/block-backend.h"
|
|
#include "sysemu/block-ram-registrar.h"
|
|
#include "qom/object.h"
|
|
|
|
#define TYPE_VIRTIO_BLK "virtio-blk-device"
|
|
OBJECT_DECLARE_SIMPLE_TYPE(VirtIOBlock, VIRTIO_BLK)
|
|
|
|
/* This is the last element of the write scatter-gather list */
|
|
struct virtio_blk_inhdr
|
|
{
|
|
unsigned char status;
|
|
};
|
|
|
|
#define VIRTIO_BLK_AUTO_NUM_QUEUES UINT16_MAX
|
|
|
|
struct VirtIOBlkConf
|
|
{
|
|
BlockConf conf;
|
|
IOThread *iothread;
|
|
char *serial;
|
|
uint32_t request_merging;
|
|
uint16_t num_queues;
|
|
uint16_t queue_size;
|
|
bool seg_max_adjust;
|
|
bool report_discard_granularity;
|
|
uint32_t max_discard_sectors;
|
|
uint32_t max_write_zeroes_sectors;
|
|
bool x_enable_wce_if_config_wce;
|
|
};
|
|
|
|
struct VirtIOBlockDataPlane;
|
|
|
|
struct VirtIOBlockReq;
|
|
struct VirtIOBlock {
|
|
VirtIODevice parent_obj;
|
|
BlockBackend *blk;
|
|
void *rq;
|
|
VirtIOBlkConf conf;
|
|
unsigned short sector_mask;
|
|
bool original_wce;
|
|
VMChangeStateEntry *change;
|
|
bool dataplane_disabled;
|
|
bool dataplane_started;
|
|
struct VirtIOBlockDataPlane *dataplane;
|
|
uint64_t host_features;
|
|
size_t config_size;
|
|
BlockRAMRegistrar blk_ram_registrar;
|
|
};
|
|
|
|
typedef struct VirtIOBlockReq {
|
|
VirtQueueElement elem;
|
|
int64_t sector_num;
|
|
VirtIOBlock *dev;
|
|
VirtQueue *vq;
|
|
IOVDiscardUndo inhdr_undo;
|
|
IOVDiscardUndo outhdr_undo;
|
|
struct virtio_blk_inhdr *in;
|
|
struct virtio_blk_outhdr out;
|
|
QEMUIOVector qiov;
|
|
size_t in_len;
|
|
struct VirtIOBlockReq *next;
|
|
struct VirtIOBlockReq *mr_next;
|
|
BlockAcctCookie acct;
|
|
} VirtIOBlockReq;
|
|
|
|
#define VIRTIO_BLK_MAX_MERGE_REQS 32
|
|
|
|
typedef struct MultiReqBuffer {
|
|
VirtIOBlockReq *reqs[VIRTIO_BLK_MAX_MERGE_REQS];
|
|
unsigned int num_reqs;
|
|
bool is_write;
|
|
} MultiReqBuffer;
|
|
|
|
void virtio_blk_handle_vq(VirtIOBlock *s, VirtQueue *vq);
|
|
|
|
#endif
|