IB/hfi1: Use a common pad buffer for 9B and 16B packets

There is no reason for a different pad buffer for the two
packet types.

Expand the current buffer allocation to allow for both
packet types.

Fixes: f8195f3b ("IB/hfi1: Eliminate allocation while atomic")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Kaike Wan <kaike.wan@intel.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Link: https://lore.kernel.org/r/20191004204934.26838.13099.stgit@awfm-01.aw.intel.comSigned-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/hw/hfi1/sdma.c

@@ -65,6 +65,7 @@
 #define SDMA_DESCQ_CNT 2048
 #define SDMA_DESC_INTR 64
 #define INVALID_TAIL 0xffff
+#define SDMA_PAD max_t(size_t, MAX_16B_PADDING, sizeof(u32))
 
 static uint sdma_descq_cnt = SDMA_DESCQ_CNT;
 module_param(sdma_descq_cnt, uint, S_IRUGO);
@@ -1296,7 +1297,7 @@ void sdma_clean(struct hfi1_devdata *dd, size_t num_engines)
 	struct sdma_engine *sde;
 
 	if (dd->sdma_pad_dma) {
-		dma_free_coherent(&dd->pcidev->dev, 4,
+		dma_free_coherent(&dd->pcidev->dev, SDMA_PAD,
 				  (void *)dd->sdma_pad_dma,
 				  dd->sdma_pad_phys);
 		dd->sdma_pad_dma = NULL;
@@ -1491,7 +1492,7 @@ int sdma_init(struct hfi1_devdata *dd, u8 port)
 	}
 
 	/* Allocate memory for pad */
-	dd->sdma_pad_dma = dma_alloc_coherent(&dd->pcidev->dev, sizeof(u32),
+	dd->sdma_pad_dma = dma_alloc_coherent(&dd->pcidev->dev, SDMA_PAD,
 					      &dd->sdma_pad_phys, GFP_KERNEL);
 	if (!dd->sdma_pad_dma) {
 		dd_dev_err(dd, "failed to allocate SendDMA pad memory\n");

drivers/infiniband/hw/hfi1/verbs.c

@@ -147,9 +147,6 @@ static int pio_wait(struct rvt_qp *qp,
 /* Length of buffer to create verbs txreq cache name */
 #define TXREQ_NAME_LEN 24
 
-/* 16B trailing buffer */
-static const u8 trail_buf[MAX_16B_PADDING];
-
 static uint wss_threshold = 80;
 module_param(wss_threshold, uint, S_IRUGO);
 MODULE_PARM_DESC(wss_threshold, "Percentage (1-100) of LLC to use as a threshold for a cacheless copy");
@@ -820,8 +817,8 @@ static int build_verbs_tx_desc(
 
 	/* add icrc, lt byte, and padding to flit */
 	if (extra_bytes)
-		ret = sdma_txadd_kvaddr(sde->dd, &tx->txreq,
-					(void *)trail_buf, extra_bytes);
+		ret = sdma_txadd_daddr(sde->dd, &tx->txreq,
+				       sde->dd->sdma_pad_phys, extra_bytes);
 
 bail_txadd:
 	return ret;
@@ -1089,7 +1086,8 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 		}
 		/* add icrc, lt byte, and padding to flit */
 		if (extra_bytes)
-			seg_pio_copy_mid(pbuf, trail_buf, extra_bytes);
+			seg_pio_copy_mid(pbuf, ppd->dd->sdma_pad_dma,
+					 extra_bytes);
 
 		seg_pio_copy_end(pbuf);
 	}