tgupdate: merge t/DO-NOT-MERGE-mptcp-enabled-by-default into t/upstream base

Author: matttbe

Documentation/networking/netconsole.rst

@@ -17,6 +17,8 @@ Release prepend support by Breno Leitao <[email protected]>, Jul 7 2023
 
 Userdata append support by Matthew Wood <[email protected]>, Jan 22 2024
 
+Sysdata append support by Breno Leitao <[email protected]>, Jan 15 2025
+
 Please send bug reports to Matt Mackall <[email protected]>
 Satyam Sharma <[email protected]>, and Cong Wang <[email protected]>
 
@@ -238,6 +240,49 @@ Delete `userdata` entries with `rmdir`::
 
    It is recommended to not write user data values with newlines.
 
+CPU number auto population in userdata
+--------------------------------------
+
+Inside the netconsole configfs hierarchy, there is a file called
+`cpu_nr` under the `userdata` directory. This file is used to enable or disable
+the automatic CPU number population feature. This feature automatically
+populates the CPU number that is sending the message.
+
+To enable the CPU number auto-population::
+
+  echo 1 > /sys/kernel/config/netconsole/target1/userdata/cpu_nr
+
+When this option is enabled, the netconsole messages will include an additional
+line in the userdata field with the format `cpu=<cpu_number>`. This allows the
+receiver of the netconsole messages to easily differentiate and demultiplex
+messages originating from different CPUs, which is particularly useful when
+dealing with parallel log output.
+
+Example::
+
+  echo "This is a message" > /dev/kmsg
+  12,607,22085407756,-;This is a message
+   cpu=42
+
+In this example, the message was sent by CPU 42.
+
+.. note::
+
+   If the user has set a conflicting `cpu` key in the userdata dictionary,
+   both keys will be reported, with the kernel-populated entry appearing after
+   the user one. For example::
+
+     # User-defined CPU entry
+     mkdir -p /sys/kernel/config/netconsole/target1/userdata/cpu
+     echo "1" > /sys/kernel/config/netconsole/target1/userdata/cpu/value
+
+   Output might look like::
+
+     12,607,22085407756,-;This is a message
+      cpu=1
+      cpu=42    # kernel-populated value
+
+
 Extended console:
 =================
 

MAINTAINERS

@@ -24152,7 +24152,7 @@ W:	http://vtun.sourceforge.net/tun
 F:	Documentation/networking/tuntap.rst
 F:	arch/um/os-Linux/drivers/
 F:	drivers/net/tap.c
-F:	drivers/net/tun.c
+F:	drivers/net/tun*
 
 TURBOCHANNEL SUBSYSTEM
 M:	"Maciej W. Rozycki" <[email protected]>

drivers/net/ethernet/intel/i40e/i40e_xsk.c

@@ -2,6 +2,7 @@
 /* Copyright(c) 2018 Intel Corporation. */
 
 #include <linux/bpf_trace.h>
+#include <linux/unroll.h>
 #include <net/xdp_sock_drv.h>
 #include "i40e_txrx_common.h"
 #include "i40e_xsk.h"
@@ -529,7 +530,8 @@ static void i40e_xmit_pkt_batch(struct i40e_ring *xdp_ring, struct xdp_desc *des
 	dma_addr_t dma;
 	u32 i;
 
-	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
+	unrolled_count(PKTS_PER_BATCH)
+	for (i = 0; i < PKTS_PER_BATCH; i++) {
 		u32 cmd = I40E_TX_DESC_CMD_ICRC | xsk_is_eop_desc(&desc[i]);
 
 		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc[i].addr);

drivers/net/ethernet/intel/i40e/i40e_xsk.h

@@ -6,22 +6,14 @@
 
 #include <linux/types.h>
 
-/* This value should match the pragma in the loop_unrolled_for
+/* This value should match the pragma in the unrolled_count()
  * macro. Why 4? It is strictly empirical. It seems to be a good
  * compromise between the advantage of having simultaneous outstanding
  * reads to the DMA array that can hide each others latency and the
  * disadvantage of having a larger code path.
  */
 #define PKTS_PER_BATCH 4
 
-#ifdef __clang__
-#define loop_unrolled_for _Pragma("clang loop unroll_count(4)") for
-#elif __GNUC__ >= 8
-#define loop_unrolled_for _Pragma("GCC unroll 4") for
-#else
-#define loop_unrolled_for for
-#endif
-
 struct i40e_ring;
 struct i40e_vsi;
 struct net_device;

drivers/net/ethernet/intel/ice/ice_xsk.c

@@ -2,6 +2,7 @@
 /* Copyright (c) 2019, Intel Corporation. */
 
 #include <linux/bpf_trace.h>
+#include <linux/unroll.h>
 #include <net/xdp_sock_drv.h>
 #include <net/xdp.h>
 #include "ice.h"
@@ -989,7 +990,8 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring,
 	struct ice_tx_desc *tx_desc;
 	u32 i;
 
-	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
+	unrolled_count(PKTS_PER_BATCH)
+	for (i = 0; i < PKTS_PER_BATCH; i++) {
 		dma_addr_t dma;
 
 		dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr);

drivers/net/ethernet/intel/ice/ice_xsk.h

@@ -7,14 +7,6 @@
 
 #define PKTS_PER_BATCH 8
 
-#ifdef __clang__
-#define loop_unrolled_for _Pragma("clang loop unroll_count(8)") for
-#elif __GNUC__ >= 8
-#define loop_unrolled_for _Pragma("GCC unroll 8") for
-#else
-#define loop_unrolled_for for
-#endif
-
 struct ice_vsi;
 
 #ifdef CONFIG_XDP_SOCKETS

drivers/net/ethernet/mellanox/mlxsw/pci.c

@@ -2214,6 +2214,8 @@ static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb,
 	for (i++; i < MLXSW_PCI_WQE_SG_ENTRIES; i++)
 		mlxsw_pci_wqe_byte_count_set(wqe, i, 0);
 
+	mlxsw_pci_wqe_ipcs_set(wqe, skb->ip_summed == CHECKSUM_PARTIAL);
+
 	/* Everything is set up, ring producer doorbell to get HW going */
 	q->producer_counter++;
 	mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q);

drivers/net/ethernet/mellanox/mlxsw/pci_hw.h

@@ -90,6 +90,11 @@ MLXSW_ITEM32(pci, wqe, lp, 0x00, 30, 1);
  */
 MLXSW_ITEM32(pci, wqe, type, 0x00, 23, 4);
 
+/* pci_wqe_ipcs
+ * Calculate IPv4 and TCP / UDP checksums.
+ */
+MLXSW_ITEM32(pci, wqe, ipcs, 0x00, 14, 1);
+
 /* pci_wqe_byte_count
  * Size of i-th scatter/gather entry, 0 if entry is unused.
  */

drivers/net/ethernet/mellanox/mlxsw/spectrum.c

@@ -1574,8 +1574,10 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port,
 	netif_carrier_off(dev);
 
 	dev->features |= NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_FILTER |
-			 NETIF_F_HW_TC;
-	dev->hw_features |= NETIF_F_HW_TC | NETIF_F_LOOPBACK;
+			 NETIF_F_HW_TC | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	dev->hw_features |= NETIF_F_HW_TC | NETIF_F_LOOPBACK |
+			    NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	dev->vlan_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 	dev->lltx = true;
 	dev->netns_local = true;
 

drivers/net/ethernet/meta/fbnic/fbnic.h

@@ -60,6 +60,12 @@ struct fbnic_dev {
 	u8 mac_addr_boundary;
 	u8 tce_tcam_last;
 
+	/* IP TCAM */
+	struct fbnic_ip_addr ip_src[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+	struct fbnic_ip_addr ip_dst[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+	struct fbnic_ip_addr ipo_src[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+	struct fbnic_ip_addr ipo_dst[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+
 	/* Number of TCQs/RCQs available on hardware */
 	u16 max_num_queues;