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>

3 files changed, 24 insertions, 44 deletions

diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index af9b788823ac..8bff94b5474c 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -1434,8 +1434,7 @@ static int fcoe_rcv(struct sk_buff *skb, struct net_device *netdev,
 
 	return NET_RX_SUCCESS;
 err:
-	per_cpu_ptr(lport->stats, get_cpu())->ErrorFrames++;
-	put_cpu();
+	this_cpu_inc(lport->stats->ErrorFrames);
 err2:
 	kfree_skb(skb);
 	return NET_RX_DROP;
@@ -1475,7 +1474,6 @@ static int fcoe_xmit(struct fc_lport *lport, struct fc_frame *fp)
 	struct ethhdr *eh;
 	struct fcoe_crc_eof *cp;
 	struct sk_buff *skb;
-	struct fc_stats *stats;
 	struct fc_frame_header *fh;
 	unsigned int hlen;		/* header length implies the version */
 	unsigned int tlen;		/* trailer length */
@@ -1586,10 +1584,8 @@ static int fcoe_xmit(struct fc_lport *lport, struct fc_frame *fp)
 		skb_shinfo(skb)->gso_size = 0;
 	}
 	/* update tx stats: regardless if LLD fails */
-	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;
@@ -1611,7 +1607,6 @@ static inline int fcoe_filter_frames(struct fc_lport *lport,
 	struct fcoe_interface *fcoe;
 	struct fc_frame_header *fh;
 	struct sk_buff *skb = (struct sk_buff *)fp;
-	struct fc_stats *stats;
 
 	/*
 	 * We only check CRC if no offload is available and if it is
@@ -1641,11 +1636,8 @@ static inline int fcoe_filter_frames(struct fc_lport *lport,
 		return 0;
 	}
 
-	stats = per_cpu_ptr(lport->stats, get_cpu());
-	stats->InvalidCRCCount++;
-	if (stats->InvalidCRCCount < 5)
+	if (this_cpu_inc_return(lport->stats->InvalidCRCCount) < 5)
 		printk(KERN_WARNING "fcoe: dropping frame with CRC error\n");
-	put_cpu();
 	return -EINVAL;
 }
 
@@ -1658,7 +1650,6 @@ static void fcoe_recv_frame(struct sk_buff *skb)
 	u32 fr_len;
 	struct fc_lport *lport;
 	struct fcoe_rcv_info *fr;
-	struct fc_stats *stats;
 	struct fcoe_crc_eof crc_eof;
 	struct fc_frame *fp;
 	struct fcoe_hdr *hp;
@@ -1686,9 +1677,11 @@ static void fcoe_recv_frame(struct sk_buff *skb)
 	 */
 	hp = (struct fcoe_hdr *) skb_network_header(skb);
 
-	stats = per_cpu_ptr(lport->stats, get_cpu());
 	if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) {
-		if (stats->ErrorFrames < 5)
+		struct fc_stats *stats;
+
+		stats = per_cpu_ptr(lport->stats, raw_smp_processor_id());
+		if (READ_ONCE(stats->ErrorFrames) < 5)
 			printk(KERN_WARNING "fcoe: FCoE version "
 			       "mismatch: The frame has "
 			       "version %x, but the "
@@ -1701,8 +1694,8 @@ static void fcoe_recv_frame(struct sk_buff *skb)
 	skb_pull(skb, sizeof(struct fcoe_hdr));
 	fr_len = skb->len - sizeof(struct fcoe_crc_eof);
 
-	stats->RxFrames++;
-	stats->RxWords += fr_len / FCOE_WORD_TO_BYTE;
+	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);
@@ -1718,13 +1711,11 @@ static void fcoe_recv_frame(struct sk_buff *skb)
 		goto drop;
 
 	if (!fcoe_filter_frames(lport, fp)) {
-		put_cpu();
 		fc_exch_recv(lport, fp);
 		return;
 	}
 drop:
-	stats->ErrorFrames++;
-	put_cpu();
+	this_cpu_inc(lport->stats->ErrorFrames);
 	kfree_skb(skb);
 }
 
@@ -1848,7 +1839,6 @@ static int fcoe_device_notification(struct notifier_block *notifier,
 	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
 	struct fcoe_ctlr *ctlr;
 	struct fcoe_interface *fcoe;
-	struct fc_stats *stats;
 	u32 link_possible = 1;
 	u32 mfs;
 	int rc = NOTIFY_OK;
@@ -1922,9 +1912,7 @@ static int fcoe_device_notification(struct notifier_block *notifier,
 			break;
 		case FCOE_CTLR_ENABLED:
 		case FCOE_CTLR_UNUSED:
-			stats = per_cpu_ptr(lport->stats, get_cpu());
-			stats->LinkFailureCount++;
-			put_cpu();
+			this_cpu_inc(lport->stats->LinkFailureCount);
 			fcoe_clean_pending_queue(lport);
 		}
 	}
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index 1756a0ac6f08..8bf70659950d 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -824,22 +824,21 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip)
 	unsigned long deadline;
 	unsigned long sel_time = 0;
 	struct list_head del_list;
-	struct fc_stats *stats;
 
 	INIT_LIST_HEAD(&del_list);
 
-	stats = per_cpu_ptr(fip->lp->stats, get_cpu());
-
 	list_for_each_entry_safe(fcf, next, &fip->fcfs, list) {
 		deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2;
 		if (fip->sel_fcf == fcf) {
 			if (time_after(jiffies, deadline)) {
-				stats->MissDiscAdvCount++;
+				u64 miss_cnt;
+
+				miss_cnt = this_cpu_inc_return(fip->lp->stats->MissDiscAdvCount);
 				printk(KERN_INFO "libfcoe: host%d: "
 				       "Missing Discovery Advertisement "
 				       "for fab %16.16llx count %lld\n",
 				       fip->lp->host->host_no, fcf->fabric_name,
-				       stats->MissDiscAdvCount);
+				       miss_cnt);
 			} else if (time_after(next_timer, deadline))
 				next_timer = deadline;
 		}
@@ -855,7 +854,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip)
 			 */
 			list_del(&fcf->list);
 			list_add(&fcf->list, &del_list);
-			stats->VLinkFailureCount++;
+			this_cpu_inc(fip->lp->stats->VLinkFailureCount);
 		} else {
 			if (time_after(next_timer, deadline))
 				next_timer = deadline;
@@ -864,7 +863,6 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip)
 				sel_time = fcf->time;
 		}
 	}
-	put_cpu();
 
 	list_for_each_entry_safe(fcf, next, &del_list, list) {
 		/* Removes fcf from current list */
@@ -1142,7 +1140,6 @@ static void fcoe_ctlr_recv_els(struct fcoe_ctlr *fip, struct sk_buff *skb)
 	struct fip_desc *desc;
 	struct fip_encaps *els;
 	struct fcoe_fcf *sel;
-	struct fc_stats *stats;
 	enum fip_desc_type els_dtype = 0;
 	u8 els_op;
 	u8 sub;
@@ -1286,10 +1283,8 @@ static void fcoe_ctlr_recv_els(struct fcoe_ctlr *fip, struct sk_buff *skb)
 	fr_dev(fp) = lport;
 	fr_encaps(fp) = els_dtype;
 
-	stats = per_cpu_ptr(lport->stats, get_cpu());
-	stats->RxFrames++;
-	stats->RxWords += skb->len / FIP_BPW;
-	put_cpu();
+	this_cpu_inc(lport->stats->RxFrames);
+	this_cpu_add(lport->stats->RxWords, skb->len / FIP_BPW);
 
 	fc_exch_recv(lport, fp);
 	return;
@@ -1427,9 +1422,7 @@ static void fcoe_ctlr_recv_clr_vlink(struct fcoe_ctlr *fip,
 						      ntoh24(vp->fd_fc_id));
 			if (vn_port && (vn_port == lport)) {
 				mutex_lock(&fip->ctlr_mutex);
-				per_cpu_ptr(lport->stats,
-					    get_cpu())->VLinkFailureCount++;
-				put_cpu();
+				this_cpu_inc(lport->stats->VLinkFailureCount);
 				fcoe_ctlr_reset(fip);
 				mutex_unlock(&fip->ctlr_mutex);
 			}
@@ -1457,8 +1450,7 @@ static void fcoe_ctlr_recv_clr_vlink(struct fcoe_ctlr *fip,
 		 * followed by physical port
 		 */
 		mutex_lock(&fip->ctlr_mutex);
-		per_cpu_ptr(lport->stats, get_cpu())->VLinkFailureCount++;
-		put_cpu();
+		this_cpu_inc(lport->stats->VLinkFailureCount);
 		fcoe_ctlr_reset(fip);
 		mutex_unlock(&fip->ctlr_mutex);
 
diff --git a/drivers/scsi/fcoe/fcoe_transport.c b/drivers/scsi/fcoe/fcoe_transport.c
index 4d0e19e7c84b..62341c6353a7 100644
--- a/drivers/scsi/fcoe/fcoe_transport.c
+++ b/drivers/scsi/fcoe/fcoe_transport.c
@@ -183,9 +183,9 @@ void __fcoe_get_lesb(struct fc_lport *lport,
 	memset(lesb, 0, sizeof(*lesb));
 	for_each_possible_cpu(cpu) {
 		stats = per_cpu_ptr(lport->stats, cpu);
-		lfc += stats->LinkFailureCount;
-		vlfc += stats->VLinkFailureCount;
-		mdac += stats->MissDiscAdvCount;
+		lfc += READ_ONCE(stats->LinkFailureCount);
+		vlfc += READ_ONCE(stats->VLinkFailureCount);
+		mdac += READ_ONCE(stats->MissDiscAdvCount);
 	}
 	lesb->lesb_link_fail = htonl(lfc);
 	lesb->lesb_vlink_fail = htonl(vlfc);