Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   David Dai <zdai@linux.vnet.ibm.com>
To:     jhs@mojatatu.com, xiyou.wangcong@gmail.com, jiri@resnulli.us,
        netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Cc:     zdai@us.ibm.com, zdai@linux.vnet.ibm.com
Subject: [v1] iproute2: police: support 64bit rate and peakrate in tc utility
Date:   Wed, 28 Aug 2019 17:52:56 -0500
Message-Id: <1567032776-1118-1-git-send-email-zdai@linux.vnet.ibm.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

For high speed adapter like Mellanox CX-5 card, it can reach upto
100 Gbits per second bandwidth. Currently htb already supports 64bit rate
in tc utility. However police action rate and peakrate are still limited
to 32bit value (upto 32 Gbits per second). Taking advantage of the 2 new
attributes TCA_POLICE_RATE64 and TCA_POLICE_PEAKRATE64 from kernel,
tc can use them to break the 32bit limit, and still keep the backward 
binary compatibility.

Tested-by: David Dai <zdai@linux.vnet.ibm.com>
Signed-off-by: David Dai <zdai@linux.vnet.ibm.com>
---
 include/uapi/linux/pkt_cls.h |    2 +
 tc/m_police.c                |   64 +++++++++++++++++++++++++++--------------
 tc/tc_core.c                 |   29 +++++++++++++++++++
 tc/tc_core.h                 |    3 ++
 4 files changed, 76 insertions(+), 22 deletions(-)

diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index b057aee..eb4ea4d 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -159,6 +159,8 @@ enum {
 	TCA_POLICE_AVRATE,
 	TCA_POLICE_RESULT,
 	TCA_POLICE_TM,
+	TCA_POLICE_RATE64,
+	TCA_POLICE_PEAKRATE64,
 	TCA_POLICE_PAD,
 	__TCA_POLICE_MAX
 #define TCA_POLICE_RESULT TCA_POLICE_RESULT
diff --git a/tc/m_police.c b/tc/m_police.c
index 862a39f..abdbcce 100644
--- a/tc/m_police.c
+++ b/tc/m_police.c
@@ -71,6 +71,7 @@ static int act_parse_police(struct action_util *a, int *argc_p, char ***argv_p,
 	unsigned int linklayer = LINKLAYER_ETHERNET; /* Assume ethernet */
 	int Rcell_log =  -1, Pcell_log = -1;
 	struct rtattr *tail;
+	__u64 rate64 = 0, prate64 = 0;
 
 	if (a) /* new way of doing things */
 		NEXT_ARG();
@@ -121,11 +122,11 @@ static int act_parse_police(struct action_util *a, int *argc_p, char ***argv_p,
 			}
 		} else if (strcmp(*argv, "rate") == 0) {
 			NEXT_ARG();
-			if (p.rate.rate) {
+			if (rate64) {
 				fprintf(stderr, "Double \"rate\" spec\n");
 				return -1;
 			}
-			if (get_rate(&p.rate.rate, *argv)) {
+			if (get_rate64(&rate64, *argv)) {
 				explain1("rate");
 				return -1;
 			}
@@ -141,11 +142,11 @@ static int act_parse_police(struct action_util *a, int *argc_p, char ***argv_p,
 			}
 		} else if (matches(*argv, "peakrate") == 0) {
 			NEXT_ARG();
-			if (p.peakrate.rate) {
+			if (prate64) {
 				fprintf(stderr, "Double \"peakrate\" spec\n");
 				return -1;
 			}
-			if (get_rate(&p.peakrate.rate, *argv)) {
+			if (get_rate64(&prate64, *argv)) {
 				explain1("peakrate");
 				return -1;
 			}
@@ -189,23 +190,23 @@ action_ctrl_ok:
 	if (!ok)
 		return -1;
 
-	if (p.rate.rate && avrate)
+	if (rate64 && avrate)
 		return -1;
 
 	/* Must at least do late binding, use TB or ewma policing */
-	if (!p.rate.rate && !avrate && !p.index) {
+	if (!rate64 && !avrate && !p.index) {
 		fprintf(stderr, "\"rate\" or \"avrate\" MUST be specified.\n");
 		return -1;
 	}
 
 	/* When the TB policer is used, burst is required */
-	if (p.rate.rate && !buffer && !avrate) {
+	if (rate64 && !buffer && !avrate) {
 		fprintf(stderr, "\"burst\" requires \"rate\".\n");
 		return -1;
 	}
 
-	if (p.peakrate.rate) {
-		if (!p.rate.rate) {
+	if (prate64) {
+		if (!rate64) {
 			fprintf(stderr, "\"peakrate\" requires \"rate\".\n");
 			return -1;
 		}
@@ -215,22 +216,24 @@ action_ctrl_ok:
 		}
 	}
 
-	if (p.rate.rate) {
+	if (rate64) {
+		p.rate.rate = (rate64 >= (1ULL << 32)) ? ~0U : rate64;
 		p.rate.mpu = mpu;
 		p.rate.overhead = overhead;
-		if (tc_calc_rtable(&p.rate, rtab, Rcell_log, mtu,
-				   linklayer) < 0) {
+		if (tc_calc_rtable_64(&p.rate, rtab, Rcell_log, mtu,
+				   linklayer, rate64) < 0) {
 			fprintf(stderr, "POLICE: failed to calculate rate table.\n");
 			return -1;
 		}
-		p.burst = tc_calc_xmittime(p.rate.rate, buffer);
+		p.burst = tc_calc_xmittime(rate64, buffer);
 	}
 	p.mtu = mtu;
-	if (p.peakrate.rate) {
+	if (prate64) {
+		p.peakrate.rate = (prate64 >= (1ULL << 32)) ? ~0U : prate64;
 		p.peakrate.mpu = mpu;
 		p.peakrate.overhead = overhead;
-		if (tc_calc_rtable(&p.peakrate, ptab, Pcell_log, mtu,
-				   linklayer) < 0) {
+		if (tc_calc_rtable_64(&p.peakrate, ptab, Pcell_log, mtu,
+				   linklayer, prate64) < 0) {
 			fprintf(stderr, "POLICE: failed to calculate peak rate table.\n");
 			return -1;
 		}
@@ -238,10 +241,16 @@ action_ctrl_ok:
 
 	tail = addattr_nest(n, MAX_MSG, tca_id);
 	addattr_l(n, MAX_MSG, TCA_POLICE_TBF, &p, sizeof(p));
-	if (p.rate.rate)
+	if (rate64) {
 		addattr_l(n, MAX_MSG, TCA_POLICE_RATE, rtab, 1024);
-	if (p.peakrate.rate)
+		if (rate64 >= (1ULL << 32))
+			addattr64(n, MAX_MSG, TCA_POLICE_RATE64, rate64);
+	}
+	if (prate64) {
 		addattr_l(n, MAX_MSG, TCA_POLICE_PEAKRATE, ptab, 1024);
+		if (prate64 >= (1ULL << 32))
+			addattr64(n, MAX_MSG, TCA_POLICE_PEAKRATE64, prate64);
+	}
 	if (avrate)
 		addattr32(n, MAX_MSG, TCA_POLICE_AVRATE, avrate);
 	if (presult)
@@ -268,6 +277,7 @@ static int print_police(struct action_util *a, FILE *f, struct rtattr *arg)
 	struct rtattr *tb[TCA_POLICE_MAX+1];
 	unsigned int buffer;
 	unsigned int linklayer;
+	__u64 rate64, prate64;
 
 	if (arg == NULL)
 		return 0;
@@ -286,16 +296,26 @@ static int print_police(struct action_util *a, FILE *f, struct rtattr *arg)
 #endif
 	p = RTA_DATA(tb[TCA_POLICE_TBF]);
 
+	rate64 = p->rate.rate;
+	if (tb[TCA_POLICE_RATE64] &&
+	    RTA_PAYLOAD(tb[TCA_POLICE_RATE64]) >= sizeof(rate64))
+		rate64 = rta_getattr_u64(tb[TCA_POLICE_RATE64]);
+
 	fprintf(f, " police 0x%x ", p->index);
-	fprintf(f, "rate %s ", sprint_rate(p->rate.rate, b1));
-	buffer = tc_calc_xmitsize(p->rate.rate, p->burst);
+	fprintf(f, "rate %s ", sprint_rate(rate64, b1));
+	buffer = tc_calc_xmitsize(rate64, p->burst);
 	fprintf(f, "burst %s ", sprint_size(buffer, b1));
 	fprintf(f, "mtu %s ", sprint_size(p->mtu, b1));
 	if (show_raw)
 		fprintf(f, "[%08x] ", p->burst);
 
-	if (p->peakrate.rate)
-		fprintf(f, "peakrate %s ", sprint_rate(p->peakrate.rate, b1));
+	prate64 = p->peakrate.rate;
+	if (tb[TCA_POLICE_PEAKRATE64] &&
+	    RTA_PAYLOAD(tb[TCA_POLICE_PEAKRATE64]) >= sizeof(prate64))
+		prate64 = rta_getattr_u64(tb[TCA_POLICE_PEAKRATE64]);
+
+	if (prate64)
+		fprintf(f, "peakrate %s ", sprint_rate(prate64, b1));
 
 	if (tb[TCA_POLICE_AVRATE])
 		fprintf(f, "avrate %s ",
diff --git a/tc/tc_core.c b/tc/tc_core.c
index 8eb1122..498d35d 100644
--- a/tc/tc_core.c
+++ b/tc/tc_core.c
@@ -152,6 +152,35 @@ int tc_calc_rtable(struct tc_ratespec *r, __u32 *rtab,
 	return cell_log;
 }
 
+int tc_calc_rtable_64(struct tc_ratespec *r, __u32 *rtab,
+		   int cell_log, unsigned int mtu,
+		   enum link_layer linklayer, __u64 rate)
+{
+	int i;
+	unsigned int sz;
+	__u64 bps = rate;
+	unsigned int mpu = r->mpu;
+
+	if (mtu == 0)
+		mtu = 2047;
+
+	if (cell_log < 0) {
+		cell_log = 0;
+		while ((mtu >> cell_log) > 255)
+			cell_log++;
+	}
+
+	for (i = 0; i < 256; i++) {
+		sz = tc_adjust_size((i + 1) << cell_log, mpu, linklayer);
+		rtab[i] = tc_calc_xmittime(bps, sz);
+	}
+
+	r->cell_align =  -1;
+	r->cell_log = cell_log;
+	r->linklayer = (linklayer & TC_LINKLAYER_MASK);
+	return cell_log;
+}
+
 /*
    stab[pkt_len>>cell_log] = pkt_xmit_size>>size_log
  */
diff --git a/tc/tc_core.h b/tc/tc_core.h
index bd4a99f..40520e7 100644
--- a/tc/tc_core.h
+++ b/tc/tc_core.h
@@ -21,6 +21,9 @@ unsigned tc_calc_xmittime(__u64 rate, unsigned size);
 unsigned tc_calc_xmitsize(__u64 rate, unsigned ticks);
 int tc_calc_rtable(struct tc_ratespec *r, __u32 *rtab,
 		   int cell_log, unsigned mtu, enum link_layer link_layer);
+int tc_calc_rtable_64(struct tc_ratespec *r, __u32 *rtab,
+			int cell_log, unsigned mtu, enum link_layer link_layer,
+			__u64 rate);
 int tc_calc_size_table(struct tc_sizespec *s, __u16 **stab);
 
 int tc_setup_estimator(unsigned A, unsigned time_const, struct tc_estimator *est);
-- 
1.7.1