datapath-windows: STT - Add support for TCP Segmentation Offload

Create and initialize the background thread and buffer that
assists in defragmenting and completing a TSO packet.

Signed-off-by: Sairam Venugopal <vsairam@vmware.com>
Acked-by: Nithin Raju <nithin@vmware.com>
Signed-off-by: Gurucharan Shetty <gshetty@nicira.com>

3 files changed, 162 insertions, 6 deletions

diff --git a/datapath-windows/ovsext/Stt.c b/datapath-windows/ovsext/Stt.c
index 4a5a4a687..b78ef952c 100644
--- a/datapath-windows/ovsext/Stt.c
+++ b/datapath-windows/ovsext/Stt.c
@@ -35,6 +35,11 @@
 #define OVS_DBG_MOD OVS_DBG_STT
 #include "Debug.h"
 
+KSTART_ROUTINE OvsSttDefragCleaner;
+static PLIST_ENTRY OvsSttPktFragHash;
+static NDIS_SPIN_LOCK OvsSttSpinLock;
+static OVS_STT_THREAD_CTX sttDefragThreadCtx;
+
 static NDIS_STATUS
 OvsDoEncapStt(POVS_VPORT_ENTRY vport, PNET_BUFFER_LIST curNbl,
               const OvsIPv4TunnelKey *tunKey,
@@ -349,7 +354,7 @@ OvsCalculateTCPChecksum(PNET_BUFFER_LIST curNbl, PNET_BUFFER curNb)
     if (csumInfo.Receive.TcpChecksumSucceeded) {
         return NDIS_STATUS_SUCCESS;
     }
-        
+
     EthHdr *eth = (EthHdr *)NdisGetDataBuffer(curNb, sizeof(EthHdr),
                                               NULL, 1, 0);
 
@@ -379,6 +384,123 @@ OvsCalculateTCPChecksum(PNET_BUFFER_LIST curNbl, PNET_BUFFER curNb)
 }
 
 /*
+ *----------------------------------------------------------------------------
+ * OvsInitSttDefragmentation
+ *     Initialize the components used by the stt lso defragmentation
+ *----------------------------------------------------------------------------
+ */
+NTSTATUS
+OvsInitSttDefragmentation()
+{
+    NTSTATUS status;
+    HANDLE threadHandle = NULL;
+
+    /* Init the sync-lock */
+    NdisAllocateSpinLock(&OvsSttSpinLock);
+
+    /* Init the Hash Buffer */
+    OvsSttPktFragHash = (PLIST_ENTRY) OvsAllocateMemoryWithTag(
+                                                sizeof(LIST_ENTRY)
+                                                * STT_HASH_TABLE_SIZE,
+                                                OVS_STT_POOL_TAG);
+    if (OvsSttPktFragHash == NULL) {
+        NdisFreeSpinLock(&OvsSttSpinLock);
+        return STATUS_INSUFFICIENT_RESOURCES;
+    }
+
+    for (int i = 0; i < STT_HASH_TABLE_SIZE; i++) {
+        InitializeListHead(&OvsSttPktFragHash[i]);
+    }
+
+    /* Init Defrag Cleanup Thread */
+    KeInitializeEvent(&sttDefragThreadCtx.event, NotificationEvent, FALSE);
+    status = PsCreateSystemThread(&threadHandle, SYNCHRONIZE, NULL, NULL,
+                                  NULL, OvsSttDefragCleaner,
+                                  &sttDefragThreadCtx);
+
+    if (status != STATUS_SUCCESS) {
+        OvsCleanupSttDefragmentation();
+        return status;
+    }
+
+    ObReferenceObjectByHandle(threadHandle, SYNCHRONIZE, NULL, KernelMode,
+                              &sttDefragThreadCtx.threadObject, NULL);
+    ZwClose(threadHandle);
+    threadHandle = NULL;
+    return STATUS_SUCCESS;
+}
+
+/*
+ *----------------------------------------------------------------------------
+ * OvsCleanupSttDefragmentation
+ *     Cleanup memory and thread that were spawned for STT LSO defragmentation
+ *----------------------------------------------------------------------------
+ */
+VOID
+OvsCleanupSttDefragmentation(VOID)
+{
+    NdisAcquireSpinLock(&OvsSttSpinLock);
+    sttDefragThreadCtx.exit = 1;
+    KeSetEvent(&sttDefragThreadCtx.event, 0, FALSE);
+    NdisReleaseSpinLock(&OvsSttSpinLock);
+
+    KeWaitForSingleObject(sttDefragThreadCtx.threadObject, Executive,
+                          KernelMode, FALSE, NULL);
+    ObDereferenceObject(sttDefragThreadCtx.threadObject);
+
+    if (OvsSttPktFragHash) {
+        OvsFreeMemoryWithTag(OvsSttPktFragHash, OVS_STT_POOL_TAG);
+        OvsSttPktFragHash = NULL;
+    }
+
+    NdisFreeSpinLock(&OvsSttSpinLock);
+}
+
+/*
+ *----------------------------------------------------------------------------
+ * OvsSttDefragCleaner
+ *     Runs periodically and cleans up the buffer to remove expired segments
+ *----------------------------------------------------------------------------
+ */
+VOID
+OvsSttDefragCleaner(PVOID data)
+{
+    POVS_STT_THREAD_CTX context = (POVS_STT_THREAD_CTX)data;
+    PLIST_ENTRY link, next;
+    POVS_STT_PKT_ENTRY entry;
+    BOOLEAN success = TRUE;
+
+    while (success) {
+        NdisAcquireSpinLock(&OvsSttSpinLock);
+        if (context->exit) {
+            NdisReleaseSpinLock(&OvsSttSpinLock);
+            break;
+        }
+
+        /* Set the timeout for the thread and cleanup */
+        UINT64 currentTime, threadSleepTimeout;
+        NdisGetCurrentSystemTime((LARGE_INTEGER *)&currentTime);
+        threadSleepTimeout = currentTime + STT_CLEANUP_INTERVAL;
+
+        for (int i = 0; i < STT_HASH_TABLE_SIZE; i++) {
+            LIST_FORALL_SAFE(&OvsSttPktFragHash[i], link, next) {
+                entry = CONTAINING_RECORD(link, OVS_STT_PKT_ENTRY, link);
+                if (entry->timeout < currentTime) {
+                    RemoveEntryList(&entry->link);
+                    OvsFreeMemoryWithTag(entry, OVS_STT_POOL_TAG);
+                }
+            }
+        }
+
+        NdisReleaseSpinLock(&OvsSttSpinLock);
+        KeWaitForSingleObject(&context->event, Executive, KernelMode,
+                              FALSE, (LARGE_INTEGER *)&threadSleepTimeout);
+    }
+
+    PsTerminateSystemThread(STATUS_SUCCESS);
+}
+
+/*
  * --------------------------------------------------------------------------
  * OvsDecapStt --
  *     Decapsulates an STT packet.
@@ -416,7 +538,7 @@ OvsDecapStt(POVS_SWITCH_CONTEXT switchContext,
     if (csumInfo.Receive.TcpChecksumFailed) {
         return NDIS_STATUS_INVALID_PACKET;
     }
-    
+
     /* Calculate the TCP Checksum */
     status = OvsCalculateTCPChecksum(curNbl, curNb);
     if (status != NDIS_STATUS_SUCCESS) {
@@ -455,7 +577,7 @@ OvsDecapStt(POVS_SWITCH_CONTEXT switchContext,
     hdrLen = STT_HDR_LEN;
     NdisAdvanceNetBufferDataStart(curNb, hdrLen, FALSE, NULL);
     advanceCnt += hdrLen;
-    
+
     /* Verify checksum for inner packet if it's required */
     if (!(sttHdr->flags & STT_CSUM_VERIFIED)) {
         BOOLEAN innerChecksumPartial = sttHdr->flags & STT_CSUM_PARTIAL;
diff --git a/datapath-windows/ovsext/Stt.h b/datapath-windows/ovsext/Stt.h
index 38d721c49..9a453791f 100644
--- a/datapath-windows/ovsext/Stt.h
+++ b/datapath-windows/ovsext/Stt.h
@@ -34,6 +34,11 @@
 #define STT_PROTO_TCP       (1 << 3)
 #define STT_PROTO_TYPES     (STT_PROTO_IPV4 | STT_PROTO_TCP)
 
+#define STT_HASH_TABLE_SIZE ((UINT32)1 << 10)
+#define STT_HASH_TABLE_MASK (STT_HASH_TABLE_SIZE - 1)
+#define STT_ENTRY_TIMEOUT 300000000   // 30s
+#define STT_CLEANUP_INTERVAL 300000000 // 30s
+
 #define STT_ETH_PAD 2
 typedef struct SttHdr {
     UINT8    version;
@@ -58,14 +63,32 @@ typedef struct _OVS_STT_VPORT {
     UINT64 slowOutPkts;
 } OVS_STT_VPORT, *POVS_STT_VPORT;
 
+typedef struct _OVS_STT_PKT_KEY {
+    UINT32 sAddr;
+    UINT32 dAddr;
+    UINT32 ackSeq;
+} OVS_STT_PKT_KEY, *POVS_STT_PKT_KEY;
+
+typedef struct _OVS_STT_PKT_ENTRY {
+    OVS_STT_PKT_KEY     ovsPktKey;
+    UINT64              timeout;
+    UINT32              recvdLen;
+    SttHdr              sttHdr;
+    PCHAR               packetBuf;
+    LIST_ENTRY          link;
+} OVS_STT_PKT_ENTRY, *POVS_STT_PKT_ENTRY;
+
+typedef struct _OVS_STT_THREAD_CTX {
+    KEVENT      event;
+    PVOID       threadObject;
+    UINT32      exit;
+} OVS_STT_THREAD_CTX, *POVS_STT_THREAD_CTX;
+
 NTSTATUS OvsInitSttTunnel(POVS_VPORT_ENTRY vport,
                           UINT16 udpDestPort);
 
 VOID OvsCleanupSttTunnel(POVS_VPORT_ENTRY vport);
 
-
-void OvsCleanupSttTunnel(POVS_VPORT_ENTRY vport);
-
 NDIS_STATUS OvsEncapStt(POVS_VPORT_ENTRY vport,
                         PNET_BUFFER_LIST curNbl,
                         OvsIPv4TunnelKey *tunKey,
@@ -79,6 +102,10 @@ NDIS_STATUS OvsDecapStt(POVS_SWITCH_CONTEXT switchContext,
                         OvsIPv4TunnelKey *tunKey,
                         PNET_BUFFER_LIST *newNbl);
 
+NTSTATUS OvsInitSttDefragmentation();
+
+VOID OvsCleanupSttDefragmentation(VOID);
+
 static __inline UINT32
 OvsGetSttTunHdrSize(VOID)
 {
diff --git a/datapath-windows/ovsext/Switch.c b/datapath-windows/ovsext/Switch.c
index f176fa09f..2878e9192 100644
--- a/datapath-windows/ovsext/Switch.c
+++ b/datapath-windows/ovsext/Switch.c
@@ -212,6 +212,12 @@ OvsCreateSwitch(NDIS_HANDLE ndisFilterHandle,
         goto create_switch_done;
     }
 
+    status = OvsInitSttDefragmentation();
+    if (status != STATUS_SUCCESS) {
+        OVS_LOG_ERROR("Exit: Failed to initialize Stt Defragmentation");
+        goto create_switch_done;
+    }
+
     *switchContextOut = switchContext;
 
 create_switch_done:
@@ -242,6 +248,7 @@ OvsExtDetach(NDIS_HANDLE filterModuleContext)
     }
     OvsDeleteSwitch(switchContext);
     OvsCleanupIpHelper();
+    OvsCleanupSttDefragmentation();
     /* This completes the cleanup, and a new attach can be handled now. */
 
     OVS_LOG_TRACE("Exit: OvsDetach Successfully");