scsi: fcoe: Use per-CPU API to update per-CPU statistics

The per-CPU statistics (struct fc_stats) is updated by getting a stable
per-CPU pointer via get_cpu() + per_cpu_ptr() and then performing the
increment. This can be optimized by using this_cpu_*() which will do
whatever is needed on the architecture to perform the update safe and
efficient.  The read out of the individual value (fc_get_host_stats())
should be done by using READ_ONCE() instead of a plain-C access. The
difference is that READ_ONCE() will always perform a single access while
the plain-C access can be split by the compiler into two loads if it
appears beneficial.  The usage of u64 has the side-effect that it is also
64bit wide on 32bit architectures and the read is always split into two
loads. The can lead to strange values if the read happens during an update
which alters both 32bit parts of the 64bit value. This can be circumvented
by either using a 32bit variables on 32bit architecures or extending the
statistics with a sequence counter.

Use this_cpu_*() API to update the statistics and READ_ONCE() to read it.

Link: https://lore.kernel.org/r/20220506105758.283887-3-bigeasy@linutronix.de
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

2 files changed, 11 insertions, 24 deletions

diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index d295867a9b46..05ddbb9bb7d8 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -273,7 +273,6 @@ static int bnx2fc_xmit(struct fc_lport *lport, struct fc_frame *fp)
 	struct fcoe_port	*port;
 	struct fcoe_hdr		*hp;
 	struct bnx2fc_rport	*tgt;
-	struct fc_stats		*stats;
 	u8			sof, eof;
 	u32			crc;
 	unsigned int		hlen, tlen, elen;
@@ -399,10 +398,8 @@ static int bnx2fc_xmit(struct fc_lport *lport, struct fc_frame *fp)
 	}
 
 	/*update tx stats */
-	stats = per_cpu_ptr(lport->stats, get_cpu());
-	stats->TxFrames++;
-	stats->TxWords += wlen;
-	put_cpu();
+	this_cpu_inc(lport->stats->TxFrames);
+	this_cpu_add(lport->stats->TxWords, wlen);
 
 	/* send down to lld */
 	fr_dev(fp) = lport;
@@ -512,7 +509,6 @@ static void bnx2fc_recv_frame(struct sk_buff *skb)
 	u32 fr_len, fr_crc;
 	struct fc_lport *lport;
 	struct fcoe_rcv_info *fr;
-	struct fc_stats *stats;
 	struct fc_frame_header *fh;
 	struct fcoe_crc_eof crc_eof;
 	struct fc_frame *fp;
@@ -543,10 +539,8 @@ static void bnx2fc_recv_frame(struct sk_buff *skb)
 	skb_pull(skb, sizeof(struct fcoe_hdr));
 	fr_len = skb->len - sizeof(struct fcoe_crc_eof);
 
-	stats = per_cpu_ptr(lport->stats, get_cpu());
-	stats->RxFrames++;
-	stats->RxWords += fr_len / FCOE_WORD_TO_BYTE;
-	put_cpu();
+	this_cpu_inc(lport->stats->RxFrames);
+	this_cpu_add(lport->stats->RxWords, fr_len / FCOE_WORD_TO_BYTE);
 
 	fp = (struct fc_frame *)skb;
 	fc_frame_init(fp);
@@ -633,9 +627,7 @@ static void bnx2fc_recv_frame(struct sk_buff *skb)
 	fr_crc = le32_to_cpu(fr_crc(fp));
 
 	if (unlikely(fr_crc != ~crc32(~0, skb->data, fr_len))) {
-		stats = per_cpu_ptr(lport->stats, get_cpu());
-		crc_err = (stats->InvalidCRCCount++);
-		put_cpu();
+		crc_err = this_cpu_inc_return(lport->stats->InvalidCRCCount);
 		if (crc_err < 5)
 			printk(KERN_WARNING PFX "dropping frame with "
 			       "CRC error\n");
@@ -964,9 +956,7 @@ static void bnx2fc_indicate_netevent(void *context, unsigned long event,
 				mutex_unlock(&lport->lp_mutex);
 				fc_host_port_type(lport->host) =
 					FC_PORTTYPE_UNKNOWN;
-				per_cpu_ptr(lport->stats,
-					    get_cpu())->LinkFailureCount++;
-				put_cpu();
+				this_cpu_inc(lport->stats->LinkFailureCount);
 				fcoe_clean_pending_queue(lport);
 				wait_for_upload = 1;
 			}
diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c
index 962454f2e2b1..6a1fc35b832a 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_io.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_io.c
@@ -2032,7 +2032,6 @@ int bnx2fc_post_io_req(struct bnx2fc_rport *tgt,
 	struct bnx2fc_interface *interface = port->priv;
 	struct bnx2fc_hba *hba = interface->hba;
 	struct fc_lport *lport = port->lport;
-	struct fc_stats *stats;
 	int task_idx, index;
 	u16 xid;
 
@@ -2045,20 +2044,18 @@ int bnx2fc_post_io_req(struct bnx2fc_rport *tgt,
 	io_req->data_xfer_len = scsi_bufflen(sc_cmd);
 	bnx2fc_priv(sc_cmd)->io_req = io_req;
 
-	stats = per_cpu_ptr(lport->stats, get_cpu());
 	if (sc_cmd->sc_data_direction == DMA_FROM_DEVICE) {
 		io_req->io_req_flags = BNX2FC_READ;
-		stats->InputRequests++;
-		stats->InputBytes += io_req->data_xfer_len;
+		this_cpu_inc(lport->stats->InputRequests);
+		this_cpu_add(lport->stats->InputBytes, io_req->data_xfer_len);
 	} else if (sc_cmd->sc_data_direction == DMA_TO_DEVICE) {
 		io_req->io_req_flags = BNX2FC_WRITE;
-		stats->OutputRequests++;
-		stats->OutputBytes += io_req->data_xfer_len;
+		this_cpu_inc(lport->stats->OutputRequests);
+		this_cpu_add(lport->stats->OutputBytes, io_req->data_xfer_len);
 	} else {
 		io_req->io_req_flags = 0;
-		stats->ControlRequests++;
+		this_cpu_inc(lport->stats->ControlRequests);
 	}
-	put_cpu();
 
 	xid = io_req->xid;