Merge branch 'master' into net-next

include/linux/devlink.h

@@ -33,6 +33,30 @@ enum devlink_command {
 	DEVLINK_CMD_PORT_SPLIT,
 	DEVLINK_CMD_PORT_UNSPLIT,
 
+	DEVLINK_CMD_SB_GET,		/* can dump */
+	DEVLINK_CMD_SB_SET,
+	DEVLINK_CMD_SB_NEW,
+	DEVLINK_CMD_SB_DEL,
+
+	DEVLINK_CMD_SB_POOL_GET,	/* can dump */
+	DEVLINK_CMD_SB_POOL_SET,
+	DEVLINK_CMD_SB_POOL_NEW,
+	DEVLINK_CMD_SB_POOL_DEL,
+
+	DEVLINK_CMD_SB_PORT_POOL_GET,	/* can dump */
+	DEVLINK_CMD_SB_PORT_POOL_SET,
+	DEVLINK_CMD_SB_PORT_POOL_NEW,
+	DEVLINK_CMD_SB_PORT_POOL_DEL,
+
+	DEVLINK_CMD_SB_TC_POOL_BIND_GET,	/* can dump */
+	DEVLINK_CMD_SB_TC_POOL_BIND_SET,
+	DEVLINK_CMD_SB_TC_POOL_BIND_NEW,
+	DEVLINK_CMD_SB_TC_POOL_BIND_DEL,
+
+	/* Shared buffer occupancy monitoring commands */
+	DEVLINK_CMD_SB_OCC_SNAPSHOT,
+	DEVLINK_CMD_SB_OCC_MAX_CLEAR,
+
 	/* add new commands above here */
 
 	__DEVLINK_CMD_MAX,
@@ -46,6 +70,31 @@ enum devlink_port_type {
 	DEVLINK_PORT_TYPE_IB,
 };
 
+enum devlink_sb_pool_type {
+	DEVLINK_SB_POOL_TYPE_INGRESS,
+	DEVLINK_SB_POOL_TYPE_EGRESS,
+};
+
+/* static threshold - limiting the maximum number of bytes.
+ * dynamic threshold - limiting the maximum number of bytes
+ *   based on the currently available free space in the shared buffer pool.
+ *   In this mode, the maximum quota is calculated based
+ *   on the following formula:
+ *     max_quota = alpha / (1 + alpha) * Free_Buffer
+ *   While Free_Buffer is the amount of none-occupied buffer associated to
+ *   the relevant pool.
+ *   The value range which can be passed is 0-20 and serves
+ *   for computation of alpha by following formula:
+ *     alpha = 2 ^ (passed_value - 10)
+ */
+
+enum devlink_sb_threshold_type {
+	DEVLINK_SB_THRESHOLD_TYPE_STATIC,
+	DEVLINK_SB_THRESHOLD_TYPE_DYNAMIC,
+};
+
+#define DEVLINK_SB_THRESHOLD_TO_ALPHA_MAX 20
+
 enum devlink_attr {
 	/* don't change the order or add anything between, this is ABI! */
 	DEVLINK_ATTR_UNSPEC,
@@ -62,6 +111,20 @@ enum devlink_attr {
 	DEVLINK_ATTR_PORT_IBDEV_NAME,		/* string */
 	DEVLINK_ATTR_PORT_SPLIT_COUNT,		/* u32 */
 	DEVLINK_ATTR_PORT_SPLIT_GROUP,		/* u32 */
+	DEVLINK_ATTR_SB_INDEX,			/* u32 */
+	DEVLINK_ATTR_SB_SIZE,			/* u32 */
+	DEVLINK_ATTR_SB_INGRESS_POOL_COUNT,	/* u16 */
+	DEVLINK_ATTR_SB_EGRESS_POOL_COUNT,	/* u16 */
+	DEVLINK_ATTR_SB_INGRESS_TC_COUNT,	/* u16 */
+	DEVLINK_ATTR_SB_EGRESS_TC_COUNT,	/* u16 */
+	DEVLINK_ATTR_SB_POOL_INDEX,		/* u16 */
+	DEVLINK_ATTR_SB_POOL_TYPE,		/* u8 */
+	DEVLINK_ATTR_SB_POOL_SIZE,		/* u32 */
+	DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE,	/* u8 */
+	DEVLINK_ATTR_SB_THRESHOLD,		/* u32 */
+	DEVLINK_ATTR_SB_TC_INDEX,		/* u16 */
+	DEVLINK_ATTR_SB_OCC_CUR,		/* u32 */
+	DEVLINK_ATTR_SB_OCC_MAX,		/* u32 */
 
 	/* add new attributes above here, update the policy in devlink.c */
 

include/list.h

@@ -33,6 +33,11 @@ static inline void list_add(struct list_head *new, struct list_head *head)
 	__list_add(new, head, head->next);
 }
 
+static inline void list_add_tail(struct list_head *new, struct list_head *head)
+{
+	__list_add(new, head->prev, head);
+}
+
 static inline void __list_del(struct list_head *prev, struct list_head *next)
 {
 	next->prev = prev;
@@ -50,9 +55,15 @@ static inline void list_del(struct list_head *entry)
 #define list_first_entry(ptr, type, member) \
 	list_entry((ptr)->next, type, member)
 
+#define list_last_entry(ptr, type, member) \
+	list_entry((ptr)->prev, type, member)
+
 #define list_next_entry(pos, member) \
 	list_entry((pos)->member.next, typeof(*(pos)), member)
 
+#define list_prev_entry(pos, member) \
+	list_entry((pos)->member.prev, typeof(*(pos)), member)
+
 #define list_for_each_entry(pos, head, member)				\
 	for (pos = list_first_entry(head, typeof(*pos), member);	\
 	     &pos->member != (head);					\
@@ -64,6 +75,11 @@ static inline void list_del(struct list_head *entry)
 	     &pos->member != (head);					\
 	     pos = n, n = list_next_entry(n, member))
 
+#define list_for_each_entry_reverse(pos, head, member)			\
+	for (pos = list_last_entry(head, typeof(*pos), member);		\
+	     &pos->member != (head);					\
+	     pos = list_prev_entry(pos, member))
+
 struct hlist_head {
 	struct hlist_node *first;
 };

ip/ipneigh.c

@@ -430,6 +430,8 @@ static int do_show_or_flush(int argc, char **argv, int flush)
 		addattr32(&req.n, sizeof(req), NDA_IFINDEX, filter.index);
 	}
 
+	req.ndm.ndm_family = filter.family;
+
 	if (flush) {
 		int round = 0;
 		char flushb[4096-512];
@@ -440,7 +442,7 @@ static int do_show_or_flush(int argc, char **argv, int flush)
 		filter.state &= ~NUD_FAILED;
 
 		while (round < MAX_ROUNDS) {
-			if (rtnl_wilddump_request(&rth, filter.family, RTM_GETNEIGH) < 0) {
+			if (rtnl_dump_request_n(&rth, &req.n) < 0) {
 				perror("Cannot send dump request");
 				exit(1);
 			}
@@ -472,8 +474,6 @@ static int do_show_or_flush(int argc, char **argv, int flush)
 		return 1;
 	}
 
-	req.ndm.ndm_family = filter.family;
-
 	if (rtnl_dump_request_n(&rth, &req.n) < 0) {
 		perror("Cannot send dump request");
 		exit(1);

man/man8/devlink-dev.8

@@ -16,6 +16,7 @@ devlink-dev \- devlink device configuration
 .ti -8
 .IR OPTIONS " := { "
 \fB\-V\fR[\fIersion\fR] |
+\fB\-n\fR[\fIno-nice-names\fR] }
 
 .ti -8
 .B devlink dev show
@@ -51,6 +52,7 @@ Shows the state of specified devlink device.
 .SH SEE ALSO
 .BR devlink (8),
 .BR devlink-port (8),
+.BR devlink-sb (8),
 .BR devlink-monitor (8),
 .br
 

man/man8/devlink-monitor.8

@@ -29,6 +29,7 @@ opens Devlink Netlink socket, listens on it and dumps state changes.
 .SH SEE ALSO
 .BR devlink (8),
 .BR devlink-dev (8),
+.BR devlink-sb (8),
 .BR devlink-port (8),
 .br
 

man/man8/devlink-port.8

@@ -16,6 +16,7 @@ devlink-port \- devlink port configuration
 .ti -8
 .IR OPTIONS " := { "
 \fB\-V\fR[\fIersion\fR] |
+\fB\-n\fR[\fIno-nice-names\fR] }
 
 .ti -8
 .BR "devlink port set "
@@ -119,6 +120,7 @@ Unplit the specified previously split devlink port.
 .SH SEE ALSO
 .BR devlink (8),
 .BR devlink-dev (8),
+.BR devlink-sb (8),
 .BR devlink-monitor (8),
 .br
 

man/man8/devlink-sb.8

+.TH DEVLINK\-SB 8 "14 Apr 2016" "iproute2" "Linux"
+.SH NAME
+devlink-sb \- devlink shared buffer configuration
+.SH SYNOPSIS
+.sp
+.ad l
+.in +8
+.ti -8
+.B devlink
+.RI "[ " OPTIONS " ]"
+.B sb
+.RI  " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.IR OPTIONS " := { "
+\fB\-V\fR[\fIersion\fR] |
+\fB\-n\fR[\fIno-nice-names\fR] }
+
+.ti -8
+.BR "devlink sb show "
+.RI "[ " DEV " [ "
+.B sb
+.IR SB_INDEX " ] ]"
+
+.ti -8
+.BR "devlink sb pool show "
+.RI "[ " DEV " [ "
+.B sb
+.IR SB_INDEX " ] "
+.br
+.B pool
+.IR POOL_INDEX " ]"
+
+.ti -8
+.BI "devlink sb pool set " DEV "
+.RB "[ " sb
+.IR SB_INDEX " ] "
+.br
+.BI pool " POOL_INDEX "
+.br
+.BI size " POOL_SIZE "
+.br
+.BR thtype " { " static " | " dynamic " }"
+
+.ti -8
+.BR "devlink sb port pool show "
+.RI "[ " DEV/PORT_INDEX " [ "
+.B sb
+.IR SB_INDEX " ] "
+.br
+.B pool
+.IR POOL_INDEX " ]"
+
+.ti -8
+.BI "devlink sb port pool set " DEV/PORT_INDEX "
+.RB "[ " sb
+.IR SB_INDEX " ] "
+.br
+.BI pool " POOL_INDEX "
+.br
+.BI th " THRESHOLD "
+
+.ti -8
+.BR "devlink sb tc bind show "
+.RI "[ " DEV/PORT_INDEX " [ "
+.B sb
+.IR SB_INDEX " ] "
+.br
+.BI tc " TC_INDEX "
+.br
+.B type
+.RB "{ " ingress " | " egress " } ]"
+
+.ti -8
+.BI "devlink sb tc bind set " DEV/PORT_INDEX "
+.RB "[ " sb
+.IR SB_INDEX " ] "
+.br
+.BI tc " TC_INDEX "
+.br
+.BR type " { " ingress " | " egress " }"
+.br
+.BI pool " POOL_INDEX "
+.br
+.BI th " THRESHOLD "
+
+.ti -8
+.BR "devlink sb occupancy show "
+.RI "{ " DEV " | " DEV/PORT_INDEX " } [ "
+.B sb
+.IR SB_INDEX " ] "
+
+.ti -8
+.BR "devlink sb occupancy snapshot "
+.IR DEV " [ "
+.B sb
+.IR SB_INDEX " ]"
+
+.ti -8
+.BR "devlink sb occupancy clearmax "
+.IR DEV " [ "
+.B sb
+.IR SB_INDEX " ]"
+
+.ti -8
+.B devlink sb help
+
+.SH "DESCRIPTION"
+.SS devlink sb show - display available shared buffers and their attributes
+
+.PP
+.I "DEV"
+- specifies the devlink device to show shared buffers.
+If this argument is omitted all shared buffers of all devices are listed.
+
+.PP
+.I "SB_INDEX"
+- specifies the shared buffer.
+If this argument is omitted shared buffer with index 0 is selected.
+Behaviour of this argument it the same for every command.
+
+.SS devlink sb pool show - display available pools and their attributes
+
+.PP
+.I "DEV"
+- specifies the devlink device to show pools.
+If this argument is omitted all pools of all devices are listed.
+
+.SS devlink sb pool set - set attributes of pool
+
+.PP
+.I "DEV"
+- specifies the devlink device to set pool.
+
+.TP
+.BI size " POOL_SIZE"
+size of the pool in Bytes.
+
+.TP
+.BR thtype " { " static " | " dynamic " } "
+pool threshold type.
+
+.I static
+- Threshold values for the pool will be passed in Bytes.
+
+.I dynamic
+- Threshold values ("to_alpha") for the pool will be used to compute alpha parameter according to formula:
+.br
+.in +16
+alpha = 2 ^ (to_alpha - 10)
+.in -16
+
+.in +10
+The range of the passed value is between 0 to 20. The computed alpha is used to determine the maximum usage of the flow:
+.in -10
+.br
+.in +16
+max_usage = alpha / (1 + alpha) * Free_Buffer
+.in -16
+
+.SS devlink sb port pool show - display port-pool combinations and threshold for each
+.I "DEV/PORT_INDEX"
+- specifies the devlink port.
+
+.TP
+.BI pool " POOL_INDEX"
+pool index.
+
+.SS devlink sb port pool set - set port-pool threshold
+.I "DEV/PORT_INDEX"
+- specifies the devlink port.
+
+.TP
+.BI pool " POOL_INDEX"
+pool index.
+
+.TP
+.BI th " THRESHOLD"
+threshold value. Type of the value is either Bytes or "to_alpha", depends on
+.B thtype
+set for the pool.
+
+.SS devlink sb tc bind show - display port-TC to pool bindings and threshold for each
+
+.I "DEV/PORT_INDEX"
+- specifies the devlink port.
+
+.TP
+.BI tc " TC_INDEX"
+index of either ingress or egress TC, usually in range 0 to 8 (depends on device).
+
+.TP
+.BR type " { " ingress " | " egress " } "
+TC type.
+
+.SS devlink sb tc bind set - set port-TC to pool binding with specified threshold
+
+.I "DEV/PORT_INDEX"
+- specifies the devlink port.
+
+.TP
+.BI tc " TC_INDEX"
+index of either ingress or egress TC, usually in range 0 to 8 (depends on device).
+
+.TP
+.BR type " { " ingress " | " egress " } "
+TC type.
+
+.TP
+.BI pool " POOL_INDEX"
+index of pool to bind this to.
+
+.TP
+.BI th " THRESHOLD"
+threshold value. Type of the value is either Bytes or "to_alpha", depends on
+.B thtype
+set for the pool.
+
+.SS devlink sb occupancy show - display shared buffer occupancy values for device or port
+
+.PP
+This command is used to browse shared buffer occupancy values. Values are showed for every port-pool combination as well as for all port-TC combinations (with pool this port-TC is bound to). Format of value is:
+.br
+.in +16
+current_value/max_value
+.in -16
+Note that before showing values, one has to issue
+.b occupancy snapshot
+command first.
+
+.PP
+.I "DEV"
+- specifies the devlink device to show occupancy values for.
+
+.I "DEV/PORT_INDEX"
+- specifies the devlink port to show occupancy values for.
+
+.SS devlink sb occupancy snapshot - take occupancy snapshot of shared buffer for device
+This command is used to take a snapshot of shared buffer occupancy values. After that, the values can be showed using
+.B occupancy show
+command.
+
+.PP
+.I "DEV"
+- specifies the devlink device to take occupancy snapshot on.
+
+.SS devlink sb occupancy clearmax - clear occupancy watermarks of shared buffer for device
+This command is used to reset maximal occupancy values reached for whole device. Note that before browsing reset values, one has to issue
+.B occupancy snapshot
+command.
+
+.PP
+.I "DEV"
+- specifies the devlink device to clear occupancy watermarks on.
+
+.SH "EXAMPLES"
+.PP
+devlink sb show
+.RS 4
+List available share buffers.
+.RE
+.PP
+devlink sb pool show
+.RS 4
+List available pools and their config.
+.RE
+.PP
+devlink sb port pool show pci/0000:03:00.0/1 pool 0
+.RS 4
+Show port-pool setup for specified port and pool.
+.RE
+.PP
+sudo devlink sb port pool set pci/0000:03:00.0/1 pool 0 th 15
+.RS 4
+Change threshold for port specified port and pool.
+.RE
+.PP
+devlink sb tc bind show pci/0000:03:00.0/1 tc 0 type ingress
+.RS 4
+Show pool binding and threshold for specified port and TC.
+.RE
+.PP
+sudo devlink sb tc bind set pci/0000:03:00.0/1 tc 0 type ingress pool 0 th 9
+.RS 4
+Set pool binding and threshold for specified port and TC.
+.RE
+.PP
+sudo devlink sb occupancy snapshot pci/0000:03:00.0
+.RS 4
+Make a snapshot of occupancy of shared buffer for specified devlink device.
+.RE
+.PP
+devlink sb occupancy show pci/0000:03:00.0/1
+.RS 4
+Show occupancy for specified port from the snapshot.
+.RE
+.PP
+sudo devlink sb occupancy clearmax pci/0000:03:00.0
+.RS 4
+Clear watermarks for shared buffer of specified devlink device.
+
+
+.SH SEE ALSO
+.BR devlink (8),
+.BR devlink-dev (8),
+.BR devlink-port (8),
+.BR devlink-monitor (8),
+.br
+
+.SH AUTHOR
+Jiri Pirko <jiri@mellanox.com>

man/man8/devlink.8

@@ -19,6 +19,7 @@ devlink \- Devlink tool
 .ti -8
 .IR OPTIONS " := { "
 \fB\-V\fR[\fIersion\fR] |
+\fB\-n\fR[\fIno-nice-names\fR] }
 
 .SH OPTIONS
 
@@ -28,6 +29,10 @@ Print the version of the
 .B devlink
 utility and exit.
 
+.TP
+.BR "\-n" , " -no-nice-names"
+Turn off printing out nice names, for example netdevice ifnames instead of devlink port identification.
+
 .SS
 .I OBJECT
 

misc/ss.c

@@ -267,7 +267,7 @@ static void filter_default_dbs(struct filter *f)
 static void filter_states_set(struct filter *f, int states)
 {
 	if (states)
-		f->states = (f->states | states) & states;
+		f->states = states;
 }
 
 static void filter_merge_defaults(struct filter *f)
@@ -1556,9 +1556,10 @@ void *parse_hostcond(char *addr, bool is_port)
 
 out:
 	if (fam != AF_UNSPEC) {
+		int states = f->states;
 		f->families = 0;
 		filter_af_set(f, fam);
-		filter_states_set(f, 0);
+		filter_states_set(f, states);
 	}
 
 	res = malloc(sizeof(*res));
@@ -2018,7 +2019,8 @@ static void tcp_show_info(const struct nlmsghdr *nlh, struct inet_diag_msg *r,
 		s.segs_out = info->tcpi_segs_out;
 		s.segs_in = info->tcpi_segs_in;
 		s.not_sent = info->tcpi_notsent_bytes;
-		s.min_rtt = (double) info->tcpi_min_rtt / 1000;
+		if (info->tcpi_min_rtt && info->tcpi_min_rtt != ~0U)
+			s.min_rtt = (double) info->tcpi_min_rtt / 1000;
 		tcp_stats_print(&s);
 		free(s.dctcp);
 	}