qed: Read/write support

This patch implements the read/write state machine.  Operations are
fully asynchronous and multiple operations may be active at any time.

Allocating writes lock tables to ensure metadata updates do not
interfere with each other.  If two allocating writes need to update the
same L2 table they will run sequentially.  If two allocating writes need
to update different L2 tables they will run in parallel.

Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

Makefile.objs

@@ -21,6 +21,7 @@ block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
 block-nested-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
 block-nested-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o
 block-nested-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
+block-nested-y += qed-check.o
 block-nested-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o
 block-nested-$(CONFIG_WIN32) += raw-win32.o
 block-nested-$(CONFIG_POSIX) += raw-posix.o

block/qed.h

@@ -116,6 +116,29 @@ typedef struct QEDRequest {
     CachedL2Table *l2_table;
 } QEDRequest;
 
+typedef struct QEDAIOCB {
+    BlockDriverAIOCB common;
+    QEMUBH *bh;
+    int bh_ret;                     /* final return status for completion bh */
+    QSIMPLEQ_ENTRY(QEDAIOCB) next;  /* next request */
+    bool is_write;                  /* false - read, true - write */
+    bool *finished;                 /* signal for cancel completion */
+    uint64_t end_pos;               /* request end on block device, in bytes */
+
+    /* User scatter-gather list */
+    QEMUIOVector *qiov;
+    size_t qiov_offset;             /* byte count already processed */
+
+    /* Current cluster scatter-gather list */
+    QEMUIOVector cur_qiov;
+    uint64_t cur_pos;               /* position on block device, in bytes */
+    uint64_t cur_cluster;           /* cluster offset in image file */
+    unsigned int cur_nclusters;     /* number of clusters being accessed */
+    int find_cluster_ret;           /* used for L1/L2 update */
+
+    QEDRequest request;
+} QEDAIOCB;
+
 typedef struct {
     BlockDriverState *bs;           /* device */
     uint64_t file_size;             /* length of image file, in bytes */
@@ -127,6 +150,9 @@ typedef struct {
     uint32_t l1_shift;
     uint32_t l2_shift;
     uint32_t l2_mask;
+
+    /* Allocating write request queue */
+    QSIMPLEQ_HEAD(, QEDAIOCB) allocating_write_reqs;
 } BDRVQEDState;
 
 enum {

trace-events

@@ -203,3 +203,13 @@ disable qed_read_table(void *s, uint64_t offset, void *table) "s %p offset %"PRI
 disable qed_read_table_cb(void *s, void *table, int ret) "s %p table %p ret %d"
 disable qed_write_table(void *s, uint64_t offset, void *table, unsigned int index, unsigned int n) "s %p offset %"PRIu64" table %p index %u n %u"
 disable qed_write_table_cb(void *s, void *table, int flush, int ret) "s %p table %p flush %d ret %d"
+
+# block/qed.c
+disable qed_aio_complete(void *s, void *acb, int ret) "s %p acb %p ret %d"
+disable qed_aio_setup(void *s, void *acb, int64_t sector_num, int nb_sectors, void *opaque, int is_write) "s %p acb %p sector_num %"PRId64" nb_sectors %d opaque %p is_write %d"
+disable qed_aio_next_io(void *s, void *acb, int ret, uint64_t cur_pos) "s %p acb %p ret %d cur_pos %"PRIu64""
+disable qed_aio_read_data(void *s, void *acb, int ret, uint64_t offset, size_t len) "s %p acb %p ret %d offset %"PRIu64" len %zu"
+disable qed_aio_write_data(void *s, void *acb, int ret, uint64_t offset, size_t len) "s %p acb %p ret %d offset %"PRIu64" len %zu"
+disable qed_aio_write_prefill(void *s, void *acb, uint64_t start, size_t len, uint64_t offset) "s %p acb %p start %"PRIu64" len %zu offset %"PRIu64""
+disable qed_aio_write_postfill(void *s, void *acb, uint64_t start, size_t len, uint64_t offset) "s %p acb %p start %"PRIu64" len %zu offset %"PRIu64""
+disable qed_aio_write_main(void *s, void *acb, int ret, uint64_t offset, size_t len) "s %p acb %p ret %d offset %"PRIu64" len %zu"