Merge tag 'rds-odp-for-5.5' into rdma.git for-next

From https://git.kernel.org/pub/scm/linux/kernel/git/leon/linux-rdma

Leon Romanovsky says:

====================
Use ODP MRs for kernel ULPs

The following series extends MR creation routines to allow creation of
user MRs through kernel ULPs as a proxy. The immediate use case is to
allow RDS to work over FS-DAX, which requires ODP (on-demand-paging)
MRs to be created and such MRs were not possible to create prior this
series.

The first part of this patchset extends RDMA to have special verb
ib_reg_user_mr(). The common use case that uses this function is a
userspace application that allocates memory for HCA access but the
responsibility to register the memory at the HCA is on an kernel ULP.
This ULP acts as an agent for the userspace application.

The second part provides advise MR functionality for ULPs. This is
integral part of ODP flows and used to trigger pagefaults in advance
to prepare memory before running working set.

The third part is actual user of those in-kernel APIs.
====================

* tag 'rds-odp-for-5.5':
  net/rds: Use prefetch for On-Demand-Paging MR
  net/rds: Handle ODP mr registration/unregistration
  net/rds: Detect need of On-Demand-Paging memory registration
  RDMA/mlx5: Fix handling of IOVA != user_va in ODP paths
  IB/mlx5: Mask out unsupported ODP capabilities for kernel QPs
  RDMA/mlx5: Don't fake udata for kernel path
  IB/mlx5: Add ODP WQE handlers for kernel QPs
  IB/core: Add interface to advise_mr for kernel users
  IB/core: Introduce ib_reg_user_mr
  IB: Allow calls to ib_umem_get from kernel ULPs

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

8 files changed, 28 insertions, 24 deletions

diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index f3f0c3f07391..1962c8330daa 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -358,7 +358,7 @@ static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port,
 		return -EINVAL;
 	}
 
-	ip_frag = be32_to_cpu(fs->m_ext.data[0]);
+	ip_frag = !!(be32_to_cpu(fs->h_ext.data[0]) & 1);
 
 	/* Locate the first rule available */
 	if (fs->location == RX_CLS_LOC_ANY)
@@ -569,7 +569,7 @@ static int bcm_sf2_cfp_rule_cmp(struct bcm_sf2_priv *priv, int port,
 
 		if (rule->fs.flow_type != fs->flow_type ||
 		    rule->fs.ring_cookie != fs->ring_cookie ||
-		    rule->fs.m_ext.data[0] != fs->m_ext.data[0])
+		    rule->fs.h_ext.data[0] != fs->h_ext.data[0])
 			continue;
 
 		switch (fs->flow_type & ~FLOW_EXT) {
@@ -621,7 +621,7 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port,
 		return -EINVAL;
 	}
 
-	ip_frag = be32_to_cpu(fs->m_ext.data[0]);
+	ip_frag = !!(be32_to_cpu(fs->h_ext.data[0]) & 1);
 
 	layout = &udf_tcpip6_layout;
 	slice_num = bcm_sf2_get_slice_number(layout, 0);
diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c
index 120a65d3e3ef..b016cc205f81 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.c
+++ b/drivers/net/dsa/mv88e6xxx/global1.c
@@ -360,6 +360,11 @@ int mv88e6390_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port)
 {
 	u16 ptr = MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST;
 
+	/* Use the default high priority for management frames sent to
+	 * the CPU.
+	 */
+	port |= MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST_MGMTPRI;
+
 	return mv88e6390_g1_monitor_write(chip, ptr, port);
 }
 
diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h
index bc5a6b2bb1e4..5324c6f4ae90 100644
--- a/drivers/net/dsa/mv88e6xxx/global1.h
+++ b/drivers/net/dsa/mv88e6xxx/global1.h
@@ -211,6 +211,7 @@
 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_INGRESS_DEST		0x2000
 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_EGRESS_DEST		0x2100
 #define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST		0x3000
+#define MV88E6390_G1_MONITOR_MGMT_CTL_PTR_CPU_DEST_MGMTPRI	0x00e0
 #define MV88E6390_G1_MONITOR_MGMT_CTL_DATA_MASK			0x00ff
 
 /* Offset 0x1C: Global Control 2 */
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index 7fe256c5739d..0b43c650e100 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -393,7 +393,7 @@ phy_interface_t mv88e6390x_port_max_speed_mode(int port)
 }
 
 static int mv88e6xxx_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
-				    phy_interface_t mode)
+				    phy_interface_t mode, bool force)
 {
 	u8 lane;
 	u16 cmode;
@@ -427,8 +427,8 @@ static int mv88e6xxx_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		cmode = 0;
 	}
 
-	/* cmode doesn't change, nothing to do for us */
-	if (cmode == chip->ports[port].cmode)
+	/* cmode doesn't change, nothing to do for us unless forced */
+	if (cmode == chip->ports[port].cmode && !force)
 		return 0;
 
 	lane = mv88e6xxx_serdes_get_lane(chip, port);
@@ -484,7 +484,7 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 	if (port != 9 && port != 10)
 		return -EOPNOTSUPP;
 
-	return mv88e6xxx_port_set_cmode(chip, port, mode);
+	return mv88e6xxx_port_set_cmode(chip, port, mode, false);
 }
 
 int mv88e6390_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
@@ -504,7 +504,7 @@ int mv88e6390_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		break;
 	}
 
-	return mv88e6xxx_port_set_cmode(chip, port, mode);
+	return mv88e6xxx_port_set_cmode(chip, port, mode, false);
 }
 
 static int mv88e6341_port_set_cmode_writable(struct mv88e6xxx_chip *chip,
@@ -555,7 +555,7 @@ int mv88e6341_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 	if (err)
 		return err;
 
-	return mv88e6xxx_port_set_cmode(chip, port, mode);
+	return mv88e6xxx_port_set_cmode(chip, port, mode, true);
 }
 
 int mv88e6185_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode)
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index a51ac088c0bc..1da5ac111499 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -1569,8 +1569,8 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled)
 
 	if (enabled) {
 		/* Enable VLAN filtering. */
-		tpid  = ETH_P_8021AD;
-		tpid2 = ETH_P_8021Q;
+		tpid  = ETH_P_8021Q;
+		tpid2 = ETH_P_8021AD;
 	} else {
 		/* Disable VLAN filtering. */
 		tpid  = ETH_P_SJA1105;
@@ -1579,9 +1579,9 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled)
 
 	table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS];
 	general_params = table->entries;
-	/* EtherType used to identify outer tagged (S-tag) VLAN traffic */
-	general_params->tpid = tpid;
 	/* EtherType used to identify inner tagged (C-tag) VLAN traffic */
+	general_params->tpid = tpid;
+	/* EtherType used to identify outer tagged (S-tag) VLAN traffic */
 	general_params->tpid2 = tpid2;
 	/* When VLAN filtering is on, we need to at least be able to
 	 * decode management traffic through the "backup plan".
@@ -1855,7 +1855,7 @@ static netdev_tx_t sja1105_port_deferred_xmit(struct dsa_switch *ds, int port,
 	if (!clone)
 		goto out;
 
-	sja1105_ptp_txtstamp_skb(ds, slot, clone);
+	sja1105_ptp_txtstamp_skb(ds, port, clone);
 
 out:
 	mutex_unlock(&priv->mgmt_lock);
diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c
index 54258a25031d..43ab7589d0d0 100644
--- a/drivers/net/dsa/sja1105/sja1105_ptp.c
+++ b/drivers/net/dsa/sja1105/sja1105_ptp.c
@@ -234,7 +234,7 @@ int sja1105_ptp_commit(struct dsa_switch *ds, struct sja1105_ptp_cmd *cmd,
 	if (rw == SPI_WRITE)
 		priv->info->ptp_cmd_packing(buf, cmd, PACK);
 
-	rc = sja1105_xfer_buf(priv, SPI_WRITE, regs->ptp_control, buf,
+	rc = sja1105_xfer_buf(priv, rw, regs->ptp_control, buf,
 			      SJA1105_SIZE_PTP_CMD);
 
 	if (rw == SPI_READ)
@@ -659,7 +659,7 @@ void sja1105_ptp_clock_unregister(struct dsa_switch *ds)
 	ptp_data->clock = NULL;
 }
 
-void sja1105_ptp_txtstamp_skb(struct dsa_switch *ds, int slot,
+void sja1105_ptp_txtstamp_skb(struct dsa_switch *ds, int port,
 			      struct sk_buff *skb)
 {
 	struct sja1105_private *priv = ds->priv;
@@ -679,7 +679,7 @@ void sja1105_ptp_txtstamp_skb(struct dsa_switch *ds, int slot,
 		goto out;
 	}
 
-	rc = sja1105_ptpegr_ts_poll(ds, slot, &ts);
+	rc = sja1105_ptpegr_ts_poll(ds, port, &ts);
 	if (rc < 0) {
 		dev_err(ds->dev, "timed out polling for tstamp\n");
 		kfree_skb(skb);
diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c
index 0d03e13e9909..63d2311817c4 100644
--- a/drivers/net/dsa/sja1105/sja1105_static_config.c
+++ b/drivers/net/dsa/sja1105/sja1105_static_config.c
@@ -142,6 +142,9 @@ static size_t sja1105et_general_params_entry_packing(void *buf, void *entry_ptr,
 	return size;
 }
 
+/* TPID and TPID2 are intentionally reversed so that semantic
+ * compatibility with E/T is kept.
+ */
 static size_t
 sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr,
 					 enum packing_op op)
@@ -166,9 +169,9 @@ sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr,
 	sja1105_packing(buf, &entry->mirr_port,   141, 139, size, op);
 	sja1105_packing(buf, &entry->vlmarker,    138, 107, size, op);
 	sja1105_packing(buf, &entry->vlmask,      106,  75, size, op);
-	sja1105_packing(buf, &entry->tpid,         74,  59, size, op);
+	sja1105_packing(buf, &entry->tpid2,        74,  59, size, op);
 	sja1105_packing(buf, &entry->ignore2stf,   58,  58, size, op);
-	sja1105_packing(buf, &entry->tpid2,        57,  42, size, op);
+	sja1105_packing(buf, &entry->tpid,         57,  42, size, op);
 	sja1105_packing(buf, &entry->queue_ts,     41,  41, size, op);
 	sja1105_packing(buf, &entry->egrmirrvid,   40,  29, size, op);
 	sja1105_packing(buf, &entry->egrmirrpcp,   28,  26, size, op);
diff --git a/drivers/net/dsa/sja1105/sja1105_tas.c b/drivers/net/dsa/sja1105/sja1105_tas.c
index 26b925b5dace..fa6750d973d7 100644
--- a/drivers/net/dsa/sja1105/sja1105_tas.c
+++ b/drivers/net/dsa/sja1105/sja1105_tas.c
@@ -477,11 +477,6 @@ int sja1105_setup_tc_taprio(struct dsa_switch *ds, int port,
 	if (admin->cycle_time_extension)
 		return -ENOTSUPP;
 
-	if (!ns_to_sja1105_delta(admin->base_time)) {
-		dev_err(ds->dev, "A base time of zero is not hardware-allowed\n");
-		return -ERANGE;
-	}
-
 	for (i = 0; i < admin->num_entries; i++) {
 		s64 delta_ns = admin->entries[i].interval;
 		s64 delta_cycles = ns_to_sja1105_delta(delta_ns);