diff mbox series

[v4,net-next,10/10] net: mscc: ocelot: configure watermarks using devlink-sb

Message ID 20210111174316.3515736-11-olteanv@gmail.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series Configuring congestion watermarks on ocelot switch using devlink-sb | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count success Link
netdev/tree_selection success Clearly marked for net-next
netdev/subject_prefix success Link
netdev/cc_maintainers warning 1 maintainers not CCed: vladimir.oltean@nxp.com
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch fail ERROR: spaces required around that '=' (ctx:VxW) WARNING: line length of 81 exceeds 80 columns WARNING: line length of 82 exceeds 80 columns WARNING: line length of 84 exceeds 80 columns WARNING: line length of 85 exceeds 80 columns WARNING: line length of 86 exceeds 80 columns WARNING: line length of 90 exceeds 80 columns
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/header_inline success Link
netdev/stable success Stable not CCed

Commit Message

Vladimir Oltean Jan. 11, 2021, 5:43 p.m. UTC
From: Vladimir Oltean <vladimir.oltean@nxp.com>

Using devlink-sb, we can configure 12/16 (the important 75%) of the
switch's controlling watermarks for congestion drops, and we can monitor
50% of the watermark occupancies (we can monitor the reservation
watermarks, but not the sharing watermarks, which are exposed as pool
sizes).

The following definitions can be made:

SB_BUF=0 # The devlink-sb for frame buffers
SB_REF=1 # The devlink-sb for frame references
POOL_ING=0 # The pool for ingress traffic. Both devlink-sb instances
           # have one of these.
POOL_EGR=1 # The pool for egress traffic. Both devlink-sb instances
           # have one of these.

Editing the hardware watermarks is done in the following way:
BUF_xxxx_I is accessed when sb=$SB_BUF and pool=$POOL_ING
REF_xxxx_I is accessed when sb=$SB_REF and pool=$POOL_ING
BUF_xxxx_E is accessed when sb=$SB_BUF and pool=$POOL_EGR
REF_xxxx_E is accessed when sb=$SB_REF and pool=$POOL_EGR

Configuring the sharing watermarks for COL_SHR(dp=0) is done implicitly
by modifying the corresponding pool size. By default, the pool size has
maximum size, so this can be skipped.

devlink sb pool set pci/0000:00:00.5 sb $SB_BUF pool $POOL_ING \
	size 129840 thtype static

Since by default there is no buffer reservation, the above command has
maxed out BUF_COL_SHR_I(dp=0).

Configuring the per-port reservation watermark (P_RSRV) is done in the
following way:

devlink sb port pool set pci/0000:00:00.5/0 sb $SB_BUF \
	pool $POOL_ING th 1000

The above command sets BUF_P_RSRV_I(port 0) to 1000 bytes. After this
command, the sharing watermarks are internally reconfigured with 1000
bytes less, i.e. from 129840 bytes to 128840 bytes.

Configuring the per-port-tc reservation watermarks (Q_RSRV) is done in
the following way:

for tc in {0..7}; do
	devlink sb tc bind set pci/0000:00:00.5/0 sb 0 tc $tc \
		type ingress pool $POOL_ING \
		th 3000
done

The above command sets BUF_Q_RSRV_I(port 0, tc 0..7) to 3000 bytes.
The sharing watermarks are again reconfigured with 24000 bytes less.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
---
Changes in v4:
Created some helper functions: devlink_to_ocelot, devlink_port_to_ocelot
and devlink_port_to_port.

Changes in v3:
None.

Changes in v2:
- Calling ocelot_watermark_init from ocelot_devlink_sb_register, since
  there was a bug in v1 where ocelot_watermark_init would use an
  uninitialized value from ocelot->pool_size, so we need to ensure that
  ocelot_watermark_init is called after ocelot_devlink_sb_register
  actually initializes the pool sizes.
- Deleted the "detected N bytes and M frame references" message since
  that information is now available through devlink-sb.

 drivers/net/dsa/ocelot/felix.c             | 118 ++++++
 drivers/net/ethernet/mscc/ocelot.c         |   5 -
 drivers/net/ethernet/mscc/ocelot.h         |   1 -
 drivers/net/ethernet/mscc/ocelot_devlink.c | 453 ++++++++++++++++++++-
 drivers/net/ethernet/mscc/ocelot_net.c     | 164 +++++++-
 include/soc/mscc/ocelot.h                  |  47 +++
 6 files changed, 773 insertions(+), 15 deletions(-)
diff mbox series

Patch

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index ac7a617cc5d2..52029a666a78 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -456,6 +456,7 @@  static int felix_init_structs(struct felix *felix, int num_phys_ports)
 	ocelot->ops		= felix->info->ops;
 	ocelot->inj_prefix	= OCELOT_TAG_PREFIX_SHORT;
 	ocelot->xtr_prefix	= OCELOT_TAG_PREFIX_SHORT;
+	ocelot->devlink		= felix->ds->devlink;
 
 	port_phy_modes = kcalloc(num_phys_ports, sizeof(phy_interface_t),
 				 GFP_KERNEL);
@@ -617,6 +618,10 @@  static int felix_setup(struct dsa_switch *ds)
 		felix_port_qos_map_init(ocelot, port);
 	}
 
+	err = ocelot_devlink_sb_register(ocelot);
+	if (err)
+		return err;
+
 	/* Include the CPU port module in the forwarding mask for unknown
 	 * unicast - the hardware default value for ANA_FLOODING_FLD_UNICAST
 	 * excludes BIT(ocelot->num_phys_ports), and so does ocelot_init, since
@@ -639,6 +644,7 @@  static void felix_teardown(struct dsa_switch *ds)
 	struct felix *felix = ocelot_to_felix(ocelot);
 	int port;
 
+	ocelot_devlink_sb_unregister(ocelot);
 	ocelot_deinit_timestamp(ocelot);
 	ocelot_deinit(ocelot);
 
@@ -780,6 +786,108 @@  static int felix_port_setup_tc(struct dsa_switch *ds, int port,
 		return -EOPNOTSUPP;
 }
 
+static int felix_sb_pool_get(struct dsa_switch *ds, unsigned int sb_index,
+			     u16 pool_index,
+			     struct devlink_sb_pool_info *pool_info)
+{
+	struct ocelot *ocelot = ds->priv;
+
+	return ocelot_sb_pool_get(ocelot, sb_index, pool_index, pool_info);
+}
+
+static int felix_sb_pool_set(struct dsa_switch *ds, unsigned int sb_index,
+			     u16 pool_index, u32 size,
+			     enum devlink_sb_threshold_type threshold_type,
+			     struct netlink_ext_ack *extack)
+{
+	struct ocelot *ocelot = ds->priv;
+
+	return ocelot_sb_pool_set(ocelot, sb_index, pool_index, size,
+				  threshold_type, extack);
+}
+
+static int felix_sb_port_pool_get(struct dsa_switch *ds, int port,
+				  unsigned int sb_index, u16 pool_index,
+				  u32 *p_threshold)
+{
+	struct ocelot *ocelot = ds->priv;
+
+	return ocelot_sb_port_pool_get(ocelot, port, sb_index, pool_index,
+				       p_threshold);
+}
+
+static int felix_sb_port_pool_set(struct dsa_switch *ds, int port,
+				  unsigned int sb_index, u16 pool_index,
+				  u32 threshold, struct netlink_ext_ack *extack)
+{
+	struct ocelot *ocelot = ds->priv;
+
+	return ocelot_sb_port_pool_set(ocelot, port, sb_index, pool_index,
+				       threshold, extack);
+}
+
+static int felix_sb_tc_pool_bind_get(struct dsa_switch *ds, int port,
+				     unsigned int sb_index, u16 tc_index,
+				     enum devlink_sb_pool_type pool_type,
+				     u16 *p_pool_index, u32 *p_threshold)
+{
+	struct ocelot *ocelot = ds->priv;
+
+	return ocelot_sb_tc_pool_bind_get(ocelot, port, sb_index, tc_index,
+					  pool_type, p_pool_index,
+					  p_threshold);
+}
+
+static int felix_sb_tc_pool_bind_set(struct dsa_switch *ds, int port,
+				     unsigned int sb_index, u16 tc_index,
+				     enum devlink_sb_pool_type pool_type,
+				     u16 pool_index, u32 threshold,
+				     struct netlink_ext_ack *extack)
+{
+	struct ocelot *ocelot = ds->priv;
+
+	return ocelot_sb_tc_pool_bind_set(ocelot, port, sb_index, tc_index,
+					  pool_type, pool_index, threshold,
+					  extack);
+}
+
+static int felix_sb_occ_snapshot(struct dsa_switch *ds,
+				 unsigned int sb_index)
+{
+	struct ocelot *ocelot = ds->priv;
+
+	return ocelot_sb_occ_snapshot(ocelot, sb_index);
+}
+
+static int felix_sb_occ_max_clear(struct dsa_switch *ds,
+				  unsigned int sb_index)
+{
+	struct ocelot *ocelot = ds->priv;
+
+	return ocelot_sb_occ_max_clear(ocelot, sb_index);
+}
+
+static int felix_sb_occ_port_pool_get(struct dsa_switch *ds, int port,
+				      unsigned int sb_index, u16 pool_index,
+				      u32 *p_cur, u32 *p_max)
+{
+	struct ocelot *ocelot = ds->priv;
+
+	return ocelot_sb_occ_port_pool_get(ocelot, port, sb_index, pool_index,
+					   p_cur, p_max);
+}
+
+static int felix_sb_occ_tc_port_bind_get(struct dsa_switch *ds, int port,
+					 unsigned int sb_index, u16 tc_index,
+					 enum devlink_sb_pool_type pool_type,
+					 u32 *p_cur, u32 *p_max)
+{
+	struct ocelot *ocelot = ds->priv;
+
+	return ocelot_sb_occ_tc_port_bind_get(ocelot, port, sb_index, tc_index,
+					      pool_type, p_cur, p_max);
+}
+
 const struct dsa_switch_ops felix_switch_ops = {
 	.get_tag_protocol		= felix_get_tag_protocol,
 	.setup				= felix_setup,
@@ -820,6 +928,16 @@  const struct dsa_switch_ops felix_switch_ops = {
 	.cls_flower_del			= felix_cls_flower_del,
 	.cls_flower_stats		= felix_cls_flower_stats,
 	.port_setup_tc			= felix_port_setup_tc,
+	.devlink_sb_pool_get		= felix_sb_pool_get,
+	.devlink_sb_pool_set		= felix_sb_pool_set,
+	.devlink_sb_port_pool_get	= felix_sb_port_pool_get,
+	.devlink_sb_port_pool_set	= felix_sb_port_pool_set,
+	.devlink_sb_tc_pool_bind_get	= felix_sb_tc_pool_bind_get,
+	.devlink_sb_tc_pool_bind_set	= felix_sb_tc_pool_bind_set,
+	.devlink_sb_occ_snapshot	= felix_sb_occ_snapshot,
+	.devlink_sb_occ_max_clear	= felix_sb_occ_max_clear,
+	.devlink_sb_occ_port_pool_get	= felix_sb_occ_port_pool_get,
+	.devlink_sb_occ_tc_port_bind_get= felix_sb_occ_tc_port_bind_get,
 };
 
 struct net_device *felix_port_to_netdev(struct ocelot *ocelot, int port)
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index f547728c6718..02fa86c72eb5 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1492,10 +1492,6 @@  static void ocelot_detect_features(struct ocelot *ocelot)
 
 	eq_ctrl = ocelot_read(ocelot, QSYS_EQ_CTRL);
 	ocelot->num_frame_refs = QSYS_MMGT_EQ_CTRL_FP_FREE_CNT(eq_ctrl);
-
-	dev_info(ocelot->dev,
-		 "Detected %d bytes of packet buffer and %d frame references\n",
-		 ocelot->packet_buffer_size, ocelot->num_frame_refs);
 }
 
 int ocelot_init(struct ocelot *ocelot)
@@ -1636,7 +1632,6 @@  int ocelot_init(struct ocelot *ocelot)
 	INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats_work);
 	queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
 			   OCELOT_STATS_CHECK_DELAY);
-	ocelot_watermark_init(ocelot);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index c9aefefc83ca..de4dd62ef39e 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -126,7 +126,6 @@  void ocelot_devlink_teardown(struct ocelot *ocelot);
 int ocelot_port_devlink_init(struct ocelot *ocelot, int port,
 			     enum devlink_port_flavour flavour);
 void ocelot_port_devlink_teardown(struct ocelot *ocelot, int port);
-void ocelot_watermark_init(struct ocelot *ocelot);
 
 extern struct notifier_block ocelot_netdevice_nb;
 extern struct notifier_block ocelot_switchdev_nb;
diff --git a/drivers/net/ethernet/mscc/ocelot_devlink.c b/drivers/net/ethernet/mscc/ocelot_devlink.c
index c96309cde82d..d441ab8dcfb8 100644
--- a/drivers/net/ethernet/mscc/ocelot_devlink.c
+++ b/drivers/net/ethernet/mscc/ocelot_devlink.c
@@ -232,6 +232,14 @@  static void ocelot_wm_write(struct ocelot *ocelot, int index, u32 val)
 	ocelot_write_gix(ocelot, wm, QSYS_RES_CFG, index);
 }
 
+static void ocelot_wm_status(struct ocelot *ocelot, int index, u32 *inuse,
+			     u32 *maxuse)
+{
+	int res_stat = ocelot_read_gix(ocelot, QSYS_RES_STAT, index);
+
+	return ocelot->ops->wm_stat(res_stat, inuse, maxuse);
+}
+
 /* The hardware comes out of reset with strange defaults: the sum of all
  * reservations for frame memory is larger than the total buffer size.
  * One has to wonder how can the reservation watermarks still guarantee
@@ -348,10 +356,14 @@  static void ocelot_setup_sharing_watermarks(struct ocelot *ocelot)
 	ocelot_get_buf_rsrv(ocelot, &buf_rsrv_i, &buf_rsrv_e);
 	ocelot_get_ref_rsrv(ocelot, &ref_rsrv_i, &ref_rsrv_e);
 
-	buf_shr_i = ocelot->packet_buffer_size - buf_rsrv_i;
-	buf_shr_e = ocelot->packet_buffer_size - buf_rsrv_e;
-	ref_shr_i = ocelot->num_frame_refs - ref_rsrv_i;
-	ref_shr_e = ocelot->num_frame_refs - ref_rsrv_e;
+	buf_shr_i = ocelot->pool_size[OCELOT_SB_BUF][OCELOT_SB_POOL_ING] -
+		    buf_rsrv_i;
+	buf_shr_e = ocelot->pool_size[OCELOT_SB_BUF][OCELOT_SB_POOL_EGR] -
+		    buf_rsrv_e;
+	ref_shr_i = ocelot->pool_size[OCELOT_SB_REF][OCELOT_SB_POOL_ING] -
+		    ref_rsrv_i;
+	ref_shr_e = ocelot->pool_size[OCELOT_SB_REF][OCELOT_SB_POOL_EGR] -
+		    ref_rsrv_e;
 
 	buf_shr_i /= OCELOT_BUFFER_CELL_SZ;
 	buf_shr_e /= OCELOT_BUFFER_CELL_SZ;
@@ -366,6 +378,40 @@  static void ocelot_setup_sharing_watermarks(struct ocelot *ocelot)
 	ocelot_wm_write(ocelot, REF_COL_SHR_I(1), 0);
 }
 
+/* Ensure that all reservations can be enforced */
+static int ocelot_watermark_validate(struct ocelot *ocelot,
+				     struct netlink_ext_ack *extack)
+{
+	u32 buf_rsrv_i, buf_rsrv_e;
+	u32 ref_rsrv_i, ref_rsrv_e;
+
+	ocelot_get_buf_rsrv(ocelot, &buf_rsrv_i, &buf_rsrv_e);
+	ocelot_get_ref_rsrv(ocelot, &ref_rsrv_i, &ref_rsrv_e);
+
+	if (buf_rsrv_i > ocelot->pool_size[OCELOT_SB_BUF][OCELOT_SB_POOL_ING]) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Ingress frame reservations exceed pool size");
+		return -ERANGE;
+	}
+	if (buf_rsrv_e > ocelot->pool_size[OCELOT_SB_BUF][OCELOT_SB_POOL_EGR]) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Egress frame reservations exceed pool size");
+		return -ERANGE;
+	}
+	if (ref_rsrv_i > ocelot->pool_size[OCELOT_SB_REF][OCELOT_SB_POOL_ING]) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Ingress reference reservations exceed pool size");
+		return -ERANGE;
+	}
+	if (ref_rsrv_e > ocelot->pool_size[OCELOT_SB_REF][OCELOT_SB_POOL_EGR]) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Egress reference reservations exceed pool size");
+		return -ERANGE;
+	}
+
+	return 0;
+}
+
 /* The hardware works like this:
  *
  *                         Frame forwarding decision taken
@@ -427,7 +473,7 @@  static void ocelot_setup_sharing_watermarks(struct ocelot *ocelot)
  * reservations by default, let sharing use all resources) and disables the
  * unused watermarks.
  */
-void ocelot_watermark_init(struct ocelot *ocelot)
+static void ocelot_watermark_init(struct ocelot *ocelot)
 {
 	int all_tcs = GENMASK(OCELOT_NUM_TC - 1, 0);
 	int port;
@@ -440,3 +486,400 @@  void ocelot_watermark_init(struct ocelot *ocelot)
 	ocelot_disable_tc_sharing_watermarks(ocelot);
 	ocelot_setup_sharing_watermarks(ocelot);
 }
+
+/* Pool size and type are fixed up at runtime. Keeping this structure to
+ * look up the cell size multipliers.
+ */
+static const struct devlink_sb_pool_info ocelot_sb_pool[] = {
+	[OCELOT_SB_BUF] = {
+		.cell_size = OCELOT_BUFFER_CELL_SZ,
+		.threshold_type = DEVLINK_SB_THRESHOLD_TYPE_STATIC,
+	},
+	[OCELOT_SB_REF] = {
+		.cell_size = 1,
+		.threshold_type = DEVLINK_SB_THRESHOLD_TYPE_STATIC,
+	},
+};
+
+/* Returns the pool size configured through ocelot_sb_pool_set */
+int ocelot_sb_pool_get(struct ocelot *ocelot, unsigned int sb_index,
+		       u16 pool_index,
+		       struct devlink_sb_pool_info *pool_info)
+{
+	if (sb_index >= OCELOT_SB_NUM)
+		return -ENODEV;
+	if (pool_index >= OCELOT_SB_POOL_NUM)
+		return -ENODEV;
+
+	*pool_info = ocelot_sb_pool[sb_index];
+	pool_info->size = ocelot->pool_size[sb_index][pool_index];
+	if (pool_index)
+		pool_info->pool_type = DEVLINK_SB_POOL_TYPE_INGRESS;
+	else
+		pool_info->pool_type = DEVLINK_SB_POOL_TYPE_EGRESS;
+
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_sb_pool_get);
+
+/* The pool size received here configures the total amount of resources used on
+ * ingress (or on egress, depending upon the pool index). The pool size, minus
+ * the values for the port and port-tc reservations, is written into the
+ * COL_SHR(dp=0) sharing watermark.
+ */
+int ocelot_sb_pool_set(struct ocelot *ocelot, unsigned int sb_index,
+		       u16 pool_index, u32 size,
+		       enum devlink_sb_threshold_type threshold_type,
+		       struct netlink_ext_ack *extack)
+{
+	u32 old_pool_size;
+	int err;
+
+	if (sb_index >= OCELOT_SB_NUM) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Invalid sb, use 0 for buffers and 1 for frame references");
+		return -ENODEV;
+	}
+	if (pool_index >= OCELOT_SB_POOL_NUM) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Invalid pool, use 0 for ingress and 1 for egress");
+		return -ENODEV;
+	}
+	if (threshold_type != DEVLINK_SB_THRESHOLD_TYPE_STATIC) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Only static threshold supported");
+		return -EOPNOTSUPP;
+	}
+
+	old_pool_size = ocelot->pool_size[sb_index][pool_index];
+	ocelot->pool_size[sb_index][pool_index] = size;
+
+	err = ocelot_watermark_validate(ocelot, extack);
+	if (err) {
+		ocelot->pool_size[sb_index][pool_index] = old_pool_size;
+		return err;
+	}
+
+	ocelot_setup_sharing_watermarks(ocelot);
+
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_sb_pool_set);
+
+/* This retrieves the configuration made with ocelot_sb_port_pool_set */
+int ocelot_sb_port_pool_get(struct ocelot *ocelot, int port,
+			    unsigned int sb_index, u16 pool_index,
+			    u32 *p_threshold)
+{
+	int wm_index;
+
+	switch (sb_index) {
+	case OCELOT_SB_BUF:
+		if (pool_index == OCELOT_SB_POOL_ING)
+			wm_index = BUF_P_RSRV_I(port);
+		else
+			wm_index = BUF_P_RSRV_E(port);
+		break;
+	case OCELOT_SB_REF:
+		if (pool_index == OCELOT_SB_POOL_ING)
+			wm_index = REF_P_RSRV_I(port);
+		else
+			wm_index = REF_P_RSRV_E(port);
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	*p_threshold = ocelot_wm_read(ocelot, wm_index);
+	*p_threshold *= ocelot_sb_pool[sb_index].cell_size;
+
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_sb_port_pool_get);
+
+/* This configures the P_RSRV per-port reserved resource watermark */
+int ocelot_sb_port_pool_set(struct ocelot *ocelot, int port,
+			    unsigned int sb_index, u16 pool_index,
+			    u32 threshold, struct netlink_ext_ack *extack)
+{
+	int wm_index, err;
+	u32 old_thr;
+
+	switch (sb_index) {
+	case OCELOT_SB_BUF:
+		if (pool_index == OCELOT_SB_POOL_ING)
+			wm_index = BUF_P_RSRV_I(port);
+		else
+			wm_index = BUF_P_RSRV_E(port);
+		break;
+	case OCELOT_SB_REF:
+		if (pool_index == OCELOT_SB_POOL_ING)
+			wm_index = REF_P_RSRV_I(port);
+		else
+			wm_index = REF_P_RSRV_E(port);
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack, "Invalid shared buffer");
+		return -ENODEV;
+	}
+
+	threshold /= ocelot_sb_pool[sb_index].cell_size;
+
+	old_thr = ocelot_wm_read(ocelot, wm_index);
+	ocelot_wm_write(ocelot, wm_index, threshold);
+
+	err = ocelot_watermark_validate(ocelot, extack);
+	if (err) {
+		ocelot_wm_write(ocelot, wm_index, old_thr);
+		return err;
+	}
+
+	ocelot_setup_sharing_watermarks(ocelot);
+
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_sb_port_pool_set);
+
+/* This retrieves the configuration done by ocelot_sb_tc_pool_bind_set */
+int ocelot_sb_tc_pool_bind_get(struct ocelot *ocelot, int port,
+			       unsigned int sb_index, u16 tc_index,
+			       enum devlink_sb_pool_type pool_type,
+			       u16 *p_pool_index, u32 *p_threshold)
+{
+	int wm_index;
+
+	switch (sb_index) {
+	case OCELOT_SB_BUF:
+		if (pool_type == DEVLINK_SB_POOL_TYPE_INGRESS)
+			wm_index = BUF_Q_RSRV_I(port, tc_index);
+		else
+			wm_index = BUF_Q_RSRV_E(port, tc_index);
+		break;
+	case OCELOT_SB_REF:
+		if (pool_type == DEVLINK_SB_POOL_TYPE_INGRESS)
+			wm_index = REF_Q_RSRV_I(port, tc_index);
+		else
+			wm_index = REF_Q_RSRV_E(port, tc_index);
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	*p_threshold = ocelot_wm_read(ocelot, wm_index);
+	*p_threshold *= ocelot_sb_pool[sb_index].cell_size;
+
+	if (pool_type == DEVLINK_SB_POOL_TYPE_INGRESS)
+		*p_pool_index = 0;
+	else
+		*p_pool_index = 1;
+
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_sb_tc_pool_bind_get);
+
+/* This configures the Q_RSRV per-port-tc reserved resource watermark */
+int ocelot_sb_tc_pool_bind_set(struct ocelot *ocelot, int port,
+			       unsigned int sb_index, u16 tc_index,
+			       enum devlink_sb_pool_type pool_type,
+			       u16 pool_index, u32 threshold,
+			       struct netlink_ext_ack *extack)
+{
+	int wm_index, err;
+	u32 old_thr;
+
+	/* Paranoid check? */
+	if (pool_index == OCELOT_SB_POOL_ING &&
+	    pool_type != DEVLINK_SB_POOL_TYPE_INGRESS)
+		return -EINVAL;
+	if (pool_index == OCELOT_SB_POOL_EGR &&
+	    pool_type != DEVLINK_SB_POOL_TYPE_EGRESS)
+		return -EINVAL;
+
+	switch (sb_index) {
+	case OCELOT_SB_BUF:
+		if (pool_type == DEVLINK_SB_POOL_TYPE_INGRESS)
+			wm_index = BUF_Q_RSRV_I(port, tc_index);
+		else
+			wm_index = BUF_Q_RSRV_E(port, tc_index);
+		break;
+	case OCELOT_SB_REF:
+		if (pool_type == DEVLINK_SB_POOL_TYPE_INGRESS)
+			wm_index = REF_Q_RSRV_I(port, tc_index);
+		else
+			wm_index = REF_Q_RSRV_E(port, tc_index);
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack, "Invalid shared buffer");
+		return -ENODEV;
+	}
+
+	threshold /= ocelot_sb_pool[sb_index].cell_size;
+
+	old_thr = ocelot_wm_read(ocelot, wm_index);
+	ocelot_wm_write(ocelot, wm_index, threshold);
+	err = ocelot_watermark_validate(ocelot, extack);
+	if (err) {
+		ocelot_wm_write(ocelot, wm_index, old_thr);
+		return err;
+	}
+
+	ocelot_setup_sharing_watermarks(ocelot);
+
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_sb_tc_pool_bind_set);
+
+/* The hardware does not support atomic snapshots, we'll read out the
+ * occupancy registers individually and have this as just a stub.
+ */
+int ocelot_sb_occ_snapshot(struct ocelot *ocelot, unsigned int sb_index)
+{
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_sb_occ_snapshot);
+
+/* The watermark occupancy registers are cleared upon read,
+ * so let's read them.
+ */
+int ocelot_sb_occ_max_clear(struct ocelot *ocelot, unsigned int sb_index)
+{
+	u32 inuse, maxuse;
+	int port, prio;
+
+	switch (sb_index) {
+	case OCELOT_SB_BUF:
+		for (port = 0; port <= ocelot->num_phys_ports; port++) {
+			for (prio = 0; prio < OCELOT_NUM_TC; prio++) {
+				ocelot_wm_status(ocelot, BUF_Q_RSRV_I(port, prio),
+						 &inuse, &maxuse);
+				ocelot_wm_status(ocelot, BUF_Q_RSRV_E(port, prio),
+						 &inuse, &maxuse);
+			}
+			ocelot_wm_status(ocelot, BUF_P_RSRV_I(port),
+					 &inuse, &maxuse);
+			ocelot_wm_status(ocelot, BUF_P_RSRV_E(port),
+					 &inuse, &maxuse);
+		}
+		break;
+	case OCELOT_SB_REF:
+		for (port = 0; port <= ocelot->num_phys_ports; port++) {
+			for (prio = 0; prio < OCELOT_NUM_TC; prio++) {
+				ocelot_wm_status(ocelot, REF_Q_RSRV_I(port, prio),
+						 &inuse, &maxuse);
+				ocelot_wm_status(ocelot, REF_Q_RSRV_E(port, prio),
+						 &inuse, &maxuse);
+			}
+			ocelot_wm_status(ocelot, REF_P_RSRV_I(port),
+					 &inuse, &maxuse);
+			ocelot_wm_status(ocelot, REF_P_RSRV_E(port),
+					 &inuse, &maxuse);
+		}
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_sb_occ_max_clear);
+
+/* This retrieves the watermark occupancy for per-port P_RSRV watermarks */
+int ocelot_sb_occ_port_pool_get(struct ocelot *ocelot, int port,
+				unsigned int sb_index, u16 pool_index,
+				u32 *p_cur, u32 *p_max)
+{
+	int wm_index;
+
+	switch (sb_index) {
+	case OCELOT_SB_BUF:
+		if (pool_index == OCELOT_SB_POOL_ING)
+			wm_index = BUF_P_RSRV_I(port);
+		else
+			wm_index = BUF_P_RSRV_E(port);
+		break;
+	case OCELOT_SB_REF:
+		if (pool_index == OCELOT_SB_POOL_ING)
+			wm_index = REF_P_RSRV_I(port);
+		else
+			wm_index = REF_P_RSRV_E(port);
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	ocelot_wm_status(ocelot, wm_index, p_cur, p_max);
+	*p_cur *= ocelot_sb_pool[sb_index].cell_size;
+	*p_max *= ocelot_sb_pool[sb_index].cell_size;
+
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_sb_occ_port_pool_get);
+
+/* This retrieves the watermark occupancy for per-port-tc Q_RSRV watermarks */
+int ocelot_sb_occ_tc_port_bind_get(struct ocelot *ocelot, int port,
+				   unsigned int sb_index, u16 tc_index,
+				   enum devlink_sb_pool_type pool_type,
+				   u32 *p_cur, u32 *p_max)
+{
+	int wm_index;
+
+	switch (sb_index) {
+	case OCELOT_SB_BUF:
+		if (pool_type == DEVLINK_SB_POOL_TYPE_INGRESS)
+			wm_index = BUF_Q_RSRV_I(port, tc_index);
+		else
+			wm_index = BUF_Q_RSRV_E(port, tc_index);
+		break;
+	case OCELOT_SB_REF:
+		if (pool_type == DEVLINK_SB_POOL_TYPE_INGRESS)
+			wm_index = REF_Q_RSRV_I(port, tc_index);
+		else
+			wm_index = REF_Q_RSRV_E(port, tc_index);
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	ocelot_wm_status(ocelot, wm_index, p_cur, p_max);
+	*p_cur *= ocelot_sb_pool[sb_index].cell_size;
+	*p_max *= ocelot_sb_pool[sb_index].cell_size;
+
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_sb_occ_tc_port_bind_get);
+
+int ocelot_devlink_sb_register(struct ocelot *ocelot)
+{
+	int err;
+
+	err = devlink_sb_register(ocelot->devlink, OCELOT_SB_BUF,
+				  ocelot->packet_buffer_size, 1, 1,
+				  OCELOT_NUM_TC, OCELOT_NUM_TC);
+	if (err)
+		return err;
+
+	err = devlink_sb_register(ocelot->devlink, OCELOT_SB_REF,
+				  ocelot->num_frame_refs, 1, 1,
+				  OCELOT_NUM_TC, OCELOT_NUM_TC);
+	if (err) {
+		devlink_sb_unregister(ocelot->devlink, OCELOT_SB_BUF);
+		return err;
+	}
+
+	ocelot->pool_size[OCELOT_SB_BUF][OCELOT_SB_POOL_ING] = ocelot->packet_buffer_size;
+	ocelot->pool_size[OCELOT_SB_BUF][OCELOT_SB_POOL_EGR] = ocelot->packet_buffer_size;
+	ocelot->pool_size[OCELOT_SB_REF][OCELOT_SB_POOL_ING] = ocelot->num_frame_refs;
+	ocelot->pool_size[OCELOT_SB_REF][OCELOT_SB_POOL_EGR] = ocelot->num_frame_refs;
+
+	ocelot_watermark_init(ocelot);
+
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_devlink_sb_register);
+
+void ocelot_devlink_sb_unregister(struct ocelot *ocelot)
+{
+	devlink_sb_unregister(ocelot->devlink, OCELOT_SB_BUF);
+	devlink_sb_unregister(ocelot->devlink, OCELOT_SB_REF);
+}
+EXPORT_SYMBOL(ocelot_devlink_sb_unregister);
diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c
index 0935af063da1..ca54ce05086d 100644
--- a/drivers/net/ethernet/mscc/ocelot_net.c
+++ b/drivers/net/ethernet/mscc/ocelot_net.c
@@ -1,7 +1,11 @@ 
 // SPDX-License-Identifier: (GPL-2.0 OR MIT)
 /* Microsemi Ocelot Switch driver
+ *
+ * This contains glue logic between the switchdev driver operations and the
+ * mscc_ocelot_switch_lib.
  *
  * Copyright (c) 2017, 2019 Microsemi Corporation
+ * Copyright 2020 NXP Semiconductors
  */
 
 #include <linux/if_bridge.h>
@@ -12,7 +16,150 @@  struct ocelot_devlink_private {
 	struct ocelot *ocelot;
 };
 
+static struct ocelot *devlink_to_ocelot(struct devlink *dl)
+{
+	struct ocelot_devlink_private *dl_priv = devlink_priv(dl);
+
+	return dl_priv->ocelot;
+}
+
+static struct ocelot *devlink_port_to_ocelot(struct devlink_port *dlp)
+{
+	return devlink_to_ocelot(dlp->devlink);
+}
+
+static int devlink_port_to_port(struct devlink_port *dlp)
+{
+	struct ocelot *ocelot = devlink_port_to_ocelot(dlp);
+
+	return dlp - ocelot->devlink_ports;
+}
+
+static int ocelot_devlink_sb_pool_get(struct devlink *dl,
+				      unsigned int sb_index, u16 pool_index,
+				      struct devlink_sb_pool_info *pool_info)
+{
+	struct ocelot *ocelot = devlink_to_ocelot(dl);
+
+	return ocelot_sb_pool_get(ocelot, sb_index, pool_index, pool_info);
+}
+
+static int ocelot_devlink_sb_pool_set(struct devlink *dl, unsigned int sb_index,
+				      u16 pool_index, u32 size,
+				      enum devlink_sb_threshold_type threshold_type,
+				      struct netlink_ext_ack *extack)
+{
+	struct ocelot *ocelot = devlink_to_ocelot(dl);
+
+	return ocelot_sb_pool_set(ocelot, sb_index, pool_index, size,
+				  threshold_type, extack);
+}
+
+static int ocelot_devlink_sb_port_pool_get(struct devlink_port *dlp,
+					   unsigned int sb_index, u16 pool_index,
+					   u32 *p_threshold)
+{
+	struct ocelot *ocelot = devlink_port_to_ocelot(dlp);
+	int port = devlink_port_to_port(dlp);
+
+	return ocelot_sb_port_pool_get(ocelot, port, sb_index, pool_index,
+				       p_threshold);
+}
+
+static int ocelot_devlink_sb_port_pool_set(struct devlink_port *dlp,
+					   unsigned int sb_index, u16 pool_index,
+					   u32 threshold,
+					   struct netlink_ext_ack *extack)
+{
+	struct ocelot *ocelot = devlink_port_to_ocelot(dlp);
+	int port = devlink_port_to_port(dlp);
+
+	return ocelot_sb_port_pool_set(ocelot, port, sb_index, pool_index,
+				       threshold, extack);
+}
+
+static int
+ocelot_devlink_sb_tc_pool_bind_get(struct devlink_port *dlp,
+				   unsigned int sb_index, u16 tc_index,
+				   enum devlink_sb_pool_type pool_type,
+				   u16 *p_pool_index, u32 *p_threshold)
+{
+	struct ocelot *ocelot = devlink_port_to_ocelot(dlp);
+	int port = devlink_port_to_port(dlp);
+
+	return ocelot_sb_tc_pool_bind_get(ocelot, port, sb_index, tc_index,
+					  pool_type, p_pool_index,
+					  p_threshold);
+}
+
+static int
+ocelot_devlink_sb_tc_pool_bind_set(struct devlink_port *dlp,
+				   unsigned int sb_index, u16 tc_index,
+				   enum devlink_sb_pool_type pool_type,
+				   u16 pool_index, u32 threshold,
+				   struct netlink_ext_ack *extack)
+{
+	struct ocelot *ocelot = devlink_port_to_ocelot(dlp);
+	int port = devlink_port_to_port(dlp);
+
+	return ocelot_sb_tc_pool_bind_set(ocelot, port, sb_index, tc_index,
+					  pool_type, pool_index, threshold,
+					  extack);
+}
+
+static int ocelot_devlink_sb_occ_snapshot(struct devlink *dl,
+					  unsigned int sb_index)
+{
+	struct ocelot *ocelot = devlink_to_ocelot(dl);
+
+	return ocelot_sb_occ_snapshot(ocelot, sb_index);
+}
+
+static int ocelot_devlink_sb_occ_max_clear(struct devlink *dl,
+					   unsigned int sb_index)
+{
+	struct ocelot *ocelot = devlink_to_ocelot(dl);
+
+	return ocelot_sb_occ_max_clear(ocelot, sb_index);
+}
+
+static int ocelot_devlink_sb_occ_port_pool_get(struct devlink_port *dlp,
+					       unsigned int sb_index,
+					       u16 pool_index, u32 *p_cur,
+					       u32 *p_max)
+{
+	struct ocelot *ocelot = devlink_port_to_ocelot(dlp);
+	int port = devlink_port_to_port(dlp);
+
+	return ocelot_sb_occ_port_pool_get(ocelot, port, sb_index, pool_index,
+					   p_cur, p_max);
+}
+
+static int
+ocelot_devlink_sb_occ_tc_port_bind_get(struct devlink_port *dlp,
+				       unsigned int sb_index, u16 tc_index,
+				       enum devlink_sb_pool_type pool_type,
+				       u32 *p_cur, u32 *p_max)
+{
+	struct ocelot *ocelot = devlink_port_to_ocelot(dlp);
+	int port = devlink_port_to_port(dlp);
+
+	return ocelot_sb_occ_tc_port_bind_get(ocelot, port, sb_index,
+					      tc_index, pool_type,
+					      p_cur, p_max);
+}
+
 static const struct devlink_ops ocelot_devlink_ops = {
+	.sb_pool_get			= ocelot_devlink_sb_pool_get,
+	.sb_pool_set			= ocelot_devlink_sb_pool_set,
+	.sb_port_pool_get		= ocelot_devlink_sb_port_pool_get,
+	.sb_port_pool_set		= ocelot_devlink_sb_port_pool_set,
+	.sb_tc_pool_bind_get		= ocelot_devlink_sb_tc_pool_bind_get,
+	.sb_tc_pool_bind_set		= ocelot_devlink_sb_tc_pool_bind_set,
+	.sb_occ_snapshot		= ocelot_devlink_sb_occ_snapshot,
+	.sb_occ_max_clear		= ocelot_devlink_sb_occ_max_clear,
+	.sb_occ_port_pool_get		= ocelot_devlink_sb_occ_port_pool_get,
+	.sb_occ_tc_port_bind_get	= ocelot_devlink_sb_occ_tc_port_bind_get,
 };
 
 int ocelot_port_devlink_init(struct ocelot *ocelot, int port,
@@ -53,16 +200,25 @@  int ocelot_devlink_init(struct ocelot *ocelot)
 	dl_priv->ocelot = ocelot;
 
 	err = devlink_register(ocelot->devlink, ocelot->dev);
-	if (err) {
-		devlink_free(ocelot->devlink);
-		return err;
-	}
+	if (err)
+		goto out_devlink_free;
+
+	err = ocelot_devlink_sb_register(ocelot);
+	if (err)
+		goto out_devlink_unregister;
 
 	return 0;
+
+out_devlink_unregister:
+	devlink_unregister(ocelot->devlink);
+out_devlink_free:
+	devlink_free(ocelot->devlink);
+	return err;
 }
 
 void ocelot_devlink_teardown(struct ocelot *ocelot)
 {
+	ocelot_devlink_sb_unregister(ocelot);
 	devlink_unregister(ocelot->devlink);
 	devlink_free(ocelot->devlink);
 }
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index dc3765e67c9d..4cce28b8ad86 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -579,6 +579,18 @@  struct ocelot_vlan {
 	u16 vid;
 };
 
+enum ocelot_sb {
+	OCELOT_SB_BUF,
+	OCELOT_SB_REF,
+	OCELOT_SB_NUM,
+};
+
+enum ocelot_sb_pool {
+	OCELOT_SB_POOL_ING,
+	OCELOT_SB_POOL_EGR,
+	OCELOT_SB_POOL_NUM,
+};
+
 struct ocelot_port {
 	struct ocelot			*ocelot;
 
@@ -612,6 +624,7 @@  struct ocelot {
 	const struct ocelot_stat_layout	*stats_layout;
 	unsigned int			num_stats;
 
+	u32				pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM];
 	int				packet_buffer_size;
 	int				num_frame_refs;
 	int				num_mact_rows;
@@ -784,4 +797,38 @@  int ocelot_port_mdb_add(struct ocelot *ocelot, int port,
 int ocelot_port_mdb_del(struct ocelot *ocelot, int port,
 			const struct switchdev_obj_port_mdb *mdb);
 
+int ocelot_devlink_sb_register(struct ocelot *ocelot);
+void ocelot_devlink_sb_unregister(struct ocelot *ocelot);
+int ocelot_sb_pool_get(struct ocelot *ocelot, unsigned int sb_index,
+		       u16 pool_index,
+		       struct devlink_sb_pool_info *pool_info);
+int ocelot_sb_pool_set(struct ocelot *ocelot, unsigned int sb_index,
+		       u16 pool_index, u32 size,
+		       enum devlink_sb_threshold_type threshold_type,
+		       struct netlink_ext_ack *extack);
+int ocelot_sb_port_pool_get(struct ocelot *ocelot, int port,
+			    unsigned int sb_index, u16 pool_index,
+			    u32 *p_threshold);
+int ocelot_sb_port_pool_set(struct ocelot *ocelot, int port,
+			    unsigned int sb_index, u16 pool_index,
+			    u32 threshold, struct netlink_ext_ack *extack);
+int ocelot_sb_tc_pool_bind_get(struct ocelot *ocelot, int port,
+			       unsigned int sb_index, u16 tc_index,
+			       enum devlink_sb_pool_type pool_type,
+			       u16 *p_pool_index, u32 *p_threshold);
+int ocelot_sb_tc_pool_bind_set(struct ocelot *ocelot, int port,
+			       unsigned int sb_index, u16 tc_index,
+			       enum devlink_sb_pool_type pool_type,
+			       u16 pool_index, u32 threshold,
+			       struct netlink_ext_ack *extack);
+int ocelot_sb_occ_snapshot(struct ocelot *ocelot, unsigned int sb_index);
+int ocelot_sb_occ_max_clear(struct ocelot *ocelot, unsigned int sb_index);
+int ocelot_sb_occ_port_pool_get(struct ocelot *ocelot, int port,
+				unsigned int sb_index, u16 pool_index,
+				u32 *p_cur, u32 *p_max);
+int ocelot_sb_occ_tc_port_bind_get(struct ocelot *ocelot, int port,
+				   unsigned int sb_index, u16 tc_index,
+				   enum devlink_sb_pool_type pool_type,
+				   u32 *p_cur, u32 *p_max);
+
 #endif