scsi: Optimize scsi_req_alloc

Zeroing sense buffer for each scsi request is not efficient, we can just
leave it uninitialized because sense_len is set to 0.

Move the implicitly zeroed fields to the end of the structure and use a
partial memset.

The explicitly initialized fields (by scsi_req_alloc or scsi_req_new)
are moved to the beginning of the structure, before sense buffer, to
skip the memset.

Also change g_malloc0 to g_slice_alloc.
Signed-off-by: NFam Zheng <famz@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

hw/scsi/scsi-bus.c

@@ -551,8 +551,11 @@ SCSIRequest *scsi_req_alloc(const SCSIReqOps *reqops, SCSIDevice *d,
     SCSIRequest *req;
     SCSIBus *bus = scsi_bus_from_device(d);
     BusState *qbus = BUS(bus);
+    const int memset_off = offsetof(SCSIRequest, sense)
+                           + sizeof(req->sense);
 
-    req = g_malloc0(reqops->size);
+    req = g_slice_alloc(reqops->size);
+    memset((uint8_t *)req + memset_off, 0, reqops->size - memset_off);
     req->refcount = 1;
     req->bus = bus;
     req->dev = d;
@@ -560,7 +563,6 @@ SCSIRequest *scsi_req_alloc(const SCSIReqOps *reqops, SCSIDevice *d,
     req->lun = lun;
     req->hba_private = hba_private;
     req->status = -1;
-    req->sense_len = 0;
     req->ops = reqops;
     object_ref(OBJECT(d));
     object_ref(OBJECT(qbus->parent));
@@ -1603,7 +1605,7 @@ void scsi_req_unref(SCSIRequest *req)
         }
         object_unref(OBJECT(req->dev));
         object_unref(OBJECT(qbus->parent));
-        g_free(req);
+        g_slice_free1(req->ops->size, req);
     }
 }
 

include/hw/scsi/scsi.h

@@ -50,17 +50,24 @@ struct SCSIRequest {
     uint32_t          tag;
     uint32_t          lun;
     uint32_t          status;
+    void              *hba_private;
     size_t            resid;
     SCSICommand       cmd;
+
+    /* Note:
+     * - fields before sense are initialized by scsi_req_alloc;
+     * - sense[] is uninitialized;
+     * - fields after sense are memset to 0 by scsi_req_alloc.
+     * */
+
+    uint8_t           sense[SCSI_SENSE_BUF_SIZE];
+    uint32_t          sense_len;
+    bool              enqueued;
+    bool              io_canceled;
+    bool              retry;
+    bool              dma_started;
     BlockDriverAIOCB  *aiocb;
     QEMUSGList        *sg;
-    bool              dma_started;
-    uint8_t sense[SCSI_SENSE_BUF_SIZE];
-    uint32_t sense_len;
-    bool enqueued;
-    bool io_canceled;
-    bool retry;
-    void *hba_private;
     QTAILQ_ENTRY(SCSIRequest) next;
 };