Merge branch 'for-6.15/io_uring-rx-zc' into for-6.15/io_uring-reg-vec

* for-6.15/io_uring-rx-zc: (80 commits)
  io_uring/zcrx: add selftest case for recvzc with read limit
  io_uring/zcrx: add a read limit to recvzc requests
  io_uring: add missing IORING_MAP_OFF_ZCRX_REGION in io_uring_mmap
  io_uring: Rename KConfig to Kconfig
  io_uring/zcrx: fix leaks on failed registration
  io_uring/zcrx: recheck ifq on shutdown
  io_uring/zcrx: add selftest
  net: add documentation for io_uring zcrx
  io_uring/zcrx: add copy fallback
  io_uring/zcrx: throttle receive requests
  io_uring/zcrx: set pp memory provider for an rx queue
  io_uring/zcrx: add io_recvzc request
  io_uring/zcrx: dma-map area for the device
  io_uring/zcrx: implement zerocopy receive pp memory provider
  io_uring/zcrx: grab a net device
  io_uring/zcrx: add io_zcrx_area
  io_uring/zcrx: add interface queue and refill queue
  net: add helpers for setting a memory provider on an rx queue
  net: page_pool: add memory provider helpers
  net: prepare for non devmem TCP memory providers
  ...

107 files changed, 3554 insertions, 3357 deletions

diff --git a/Documentation/arch/s390/driver-model.rst b/Documentation/arch/s390/driver-model.rst
index ad4bc2dbea43..ad18f129fb0b 100644
--- a/Documentation/arch/s390/driver-model.rst
+++ b/Documentation/arch/s390/driver-model.rst
@@ -244,7 +244,7 @@ information about the interrupt from the irb parameter.
 --------------------
 
 The ccwgroup mechanism is designed to handle devices consisting of multiple ccw
-devices, like lcs or ctc.
+devices, like qeth or ctc.
 
 The ccw driver provides a 'group' attribute. Piping bus ids of ccw devices to
 this attributes creates a ccwgroup device consisting of these ccw devices (if
diff --git a/Documentation/devicetree/bindings/net/faraday,ftgmac100.yaml b/Documentation/devicetree/bindings/net/faraday,ftgmac100.yaml
index 9bcbacb6640d..55d6a8379025 100644
--- a/Documentation/devicetree/bindings/net/faraday,ftgmac100.yaml
+++ b/Documentation/devicetree/bindings/net/faraday,ftgmac100.yaml
@@ -44,6 +44,9 @@ properties:
   phy-mode:
     enum:
       - rgmii
+      - rgmii-id
+      - rgmii-rxid
+      - rgmii-txid
       - rmii
 
   phy-handle: true
diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml
index 9660ffb1ed6a..44f2226160ca 100644
--- a/Documentation/netlink/genetlink-c.yaml
+++ b/Documentation/netlink/genetlink-c.yaml
@@ -14,9 +14,10 @@ $defs:
     pattern: ^[0-9A-Za-z_-]+( - 1)?$
     minimum: 0
   len-or-limit:
-    # literal int or limit based on fixed-width type e.g. u8-min, u16-max, etc.
+    # literal int, const name, or limit based on fixed-width type
+    # e.g. u8-min, u16-max, etc.
     type: [ string, integer ]
-    pattern: ^[su](8|16|32|64)-(min|max)$
+    pattern: ^[0-9A-Za-z_-]+$
     minimum: 0
 
 # Schema for specs
diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml
index 16380e12cabe..ed64acf1bef7 100644
--- a/Documentation/netlink/genetlink-legacy.yaml
+++ b/Documentation/netlink/genetlink-legacy.yaml
@@ -14,9 +14,10 @@ $defs:
     pattern: ^[0-9A-Za-z_-]+( - 1)?$
     minimum: 0
   len-or-limit:
-    # literal int or limit based on fixed-width type e.g. u8-min, u16-max, etc.
+    # literal int, const name, or limit based on fixed-width type
+    # e.g. u8-min, u16-max, etc.
     type: [ string, integer ]
-    pattern: ^[su](8|16|32|64)-(min|max)$
+    pattern: ^[0-9A-Za-z_-]+$
     minimum: 0
 
 # Schema for specs
diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml
index b036227b46f1..e43e50dba2e4 100644
--- a/Documentation/netlink/genetlink.yaml
+++ b/Documentation/netlink/genetlink.yaml
@@ -14,9 +14,10 @@ $defs:
     pattern: ^[0-9A-Za-z_-]+( - 1)?$
     minimum: 0
   len-or-limit:
-    # literal int or limit based on fixed-width type e.g. u8-min, u16-max, etc.
+    # literal int, const name, or limit based on fixed-width type
+    # e.g. u8-min, u16-max, etc.
     type: [ string, integer ]
-    pattern: ^[su](8|16|32|64)-(min|max)$
+    pattern: ^[0-9A-Za-z_-]+$
     minimum: 0
 
 # Schema for specs
diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index cbb544bd6c84..288923e965ae 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -115,6 +115,9 @@ attribute-sets:
         type: u64
         enum: xsk-flags
   -
+    name: io-uring-provider-info
+    attributes: []
+  -
     name: page-pool
     attributes:
       -
@@ -171,6 +174,11 @@ attribute-sets:
         name: dmabuf
         doc: ID of the dmabuf this page-pool is attached to.
         type: u32
+      -
+        name: io-uring
+        doc: io-uring memory provider information.
+        type: nest
+        nested-attributes: io-uring-provider-info
   -
     name: page-pool-info
     subset-of: page-pool
@@ -296,6 +304,11 @@ attribute-sets:
         name: dmabuf
         doc: ID of the dmabuf attached to this queue, if any.
         type: u32
+      -
+        name: io-uring
+        doc: io_uring memory provider information.
+        type: nest
+        nested-attributes: io-uring-provider-info
 
   -
     name: qstats
@@ -572,6 +585,7 @@ operations:
             - inflight-mem
             - detach-time
             - dmabuf
+            - io-uring
       dump:
         reply: *pp-reply
       config-cond: page-pool
@@ -637,6 +651,7 @@ operations:
             - napi-id
             - ifindex
             - dmabuf
+            - io-uring
       dump:
         request:
           attributes:
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index 058193ed2eeb..c64133d309bf 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -63,6 +63,7 @@ Contents:
    gtp
    ila
    ioam6-sysctl
+   iou-zcrx
    ip_dynaddr
    ipsec
    ip-sysctl
diff --git a/Documentation/networking/iou-zcrx.rst b/Documentation/networking/iou-zcrx.rst
new file mode 100644
index 000000000000..0127319b30bb
--- /dev/null
+++ b/Documentation/networking/iou-zcrx.rst
@@ -0,0 +1,202 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
+io_uring zero copy Rx
+=====================
+
+Introduction
+============
+
+io_uring zero copy Rx (ZC Rx) is a feature that removes kernel-to-user copy on
+the network receive path, allowing packet data to be received directly into
+userspace memory. This feature is different to TCP_ZEROCOPY_RECEIVE in that
+there are no strict alignment requirements and no need to mmap()/munmap().
+Compared to kernel bypass solutions such as e.g. DPDK, the packet headers are
+processed by the kernel TCP stack as normal.
+
+NIC HW Requirements
+===================
+
+Several NIC HW features are required for io_uring ZC Rx to work. For now the
+kernel API does not configure the NIC and it must be done by the user.
+
+Header/data split
+-----------------
+
+Required to split packets at the L4 boundary into a header and a payload.
+Headers are received into kernel memory as normal and processed by the TCP
+stack as normal. Payloads are received into userspace memory directly.
+
+Flow steering
+-------------
+
+Specific HW Rx queues are configured for this feature, but modern NICs
+typically distribute flows across all HW Rx queues. Flow steering is required
+to ensure that only desired flows are directed towards HW queues that are
+configured for io_uring ZC Rx.
+
+RSS
+---
+
+In addition to flow steering above, RSS is required to steer all other non-zero
+copy flows away from queues that are configured for io_uring ZC Rx.
+
+Usage
+=====
+
+Setup NIC
+---------
+
+Must be done out of band for now.
+
+Ensure there are at least two queues::
+
+  ethtool -L eth0 combined 2
+
+Enable header/data split::
+
+  ethtool -G eth0 tcp-data-split on
+
+Carve out half of the HW Rx queues for zero copy using RSS::
+
+  ethtool -X eth0 equal 1
+
+Set up flow steering, bearing in mind that queues are 0-indexed::
+
+  ethtool -N eth0 flow-type tcp6 ... action 1
+
+Setup io_uring
+--------------
+
+This section describes the low level io_uring kernel API. Please refer to
+liburing documentation for how to use the higher level API.
+
+Create an io_uring instance with the following required setup flags::
+
+  IORING_SETUP_SINGLE_ISSUER
+  IORING_SETUP_DEFER_TASKRUN
+  IORING_SETUP_CQE32
+
+Create memory area
+------------------
+
+Allocate userspace memory area for receiving zero copy data::
+
+  void *area_ptr = mmap(NULL, area_size,
+                        PROT_READ | PROT_WRITE,
+                        MAP_ANONYMOUS | MAP_PRIVATE,
+                        0, 0);
+
+Create refill ring
+------------------
+
+Allocate memory for a shared ringbuf used for returning consumed buffers::
+
+  void *ring_ptr = mmap(NULL, ring_size,
+                        PROT_READ | PROT_WRITE,
+                        MAP_ANONYMOUS | MAP_PRIVATE,
+                        0, 0);
+
+This refill ring consists of some space for the header, followed by an array of
+``struct io_uring_zcrx_rqe``::
+
+  size_t rq_entries = 4096;
+  size_t ring_size = rq_entries * sizeof(struct io_uring_zcrx_rqe) + PAGE_SIZE;
+  /* align to page size */
+  ring_size = (ring_size + (PAGE_SIZE - 1)) & ~(PAGE_SIZE - 1);
+
+Register ZC Rx
+--------------
+
+Fill in registration structs::
+
+  struct io_uring_zcrx_area_reg area_reg = {
+    .addr = (__u64)(unsigned long)area_ptr,
+    .len = area_size,
+    .flags = 0,
+  };
+
+  struct io_uring_region_desc region_reg = {
+    .user_addr = (__u64)(unsigned long)ring_ptr,
+    .size = ring_size,
+    .flags = IORING_MEM_REGION_TYPE_USER,
+  };
+
+  struct io_uring_zcrx_ifq_reg reg = {
+    .if_idx = if_nametoindex("eth0"),
+    /* this is the HW queue with desired flow steered into it */
+    .if_rxq = 1,
+    .rq_entries = rq_entries,
+    .area_ptr = (__u64)(unsigned long)&area_reg,
+    .region_ptr = (__u64)(unsigned long)&region_reg,
+  };
+
+Register with kernel::
+
+  io_uring_register_ifq(ring, &reg);
+
+Map refill ring
+---------------
+
+The kernel fills in fields for the refill ring in the registration ``struct
+io_uring_zcrx_ifq_reg``. Map it into userspace::
+
+  struct io_uring_zcrx_rq refill_ring;
+
+  refill_ring.khead = (unsigned *)((char *)ring_ptr + reg.offsets.head);
+  refill_ring.khead = (unsigned *)((char *)ring_ptr + reg.offsets.tail);
+  refill_ring.rqes =
+    (struct io_uring_zcrx_rqe *)((char *)ring_ptr + reg.offsets.rqes);
+  refill_ring.rq_tail = 0;
+  refill_ring.ring_ptr = ring_ptr;
+
+Receiving data
+--------------
+
+Prepare a zero copy recv request::
+
+  struct io_uring_sqe *sqe;
+
+  sqe = io_uring_get_sqe(ring);
+  io_uring_prep_rw(IORING_OP_RECV_ZC, sqe, fd, NULL, 0, 0);
+  sqe->ioprio |= IORING_RECV_MULTISHOT;
+
+Now, submit and wait::
+
+  io_uring_submit_and_wait(ring, 1);
+
+Finally, process completions::
+
+  struct io_uring_cqe *cqe;
+  unsigned int count = 0;
+  unsigned int head;
+
+  io_uring_for_each_cqe(ring, head, cqe) {
+    struct io_uring_zcrx_cqe *rcqe = (struct io_uring_zcrx_cqe *)(cqe + 1);
+
+    unsigned long mask = (1ULL << IORING_ZCRX_AREA_SHIFT) - 1;
+    unsigned char *data = area_ptr + (rcqe->off & mask);
+    /* do something with the data */
+
+    count++;
+  }
+  io_uring_cq_advance(ring, count);
+
+Recycling buffers
+-----------------
+
+Return buffers back to the kernel to be used again::
+
+  struct io_uring_zcrx_rqe *rqe;
+  unsigned mask = refill_ring.ring_entries - 1;
+  rqe = &refill_ring.rqes[refill_ring.rq_tail & mask];
+
+  unsigned long area_offset = rcqe->off & ~IORING_ZCRX_AREA_MASK;
+  rqe->off = area_offset | area_reg.rq_area_token;
+  rqe->len = cqe->res;
+  IO_URING_WRITE_ONCE(*refill_ring.ktail, ++refill_ring.rq_tail);
+
+Testing
+=======
+
+See ``tools/testing/selftests/drivers/net/hw/iou-zcrx.c``
diff --git a/Kconfig b/Kconfig
index 745bc773f567..307e581144de 100644
--- a/Kconfig
+++ b/Kconfig
@@ -30,3 +30,5 @@ source "lib/Kconfig"
 source "lib/Kconfig.debug"
 
 source "Documentation/Kconfig"
+
+source "io_uring/Kconfig"
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index d9e705f4a697..bde6a496df5f 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -54,7 +54,6 @@ enum interruption_class {
 	IRQIO_C70,
 	IRQIO_TAP,
 	IRQIO_VMR,
-	IRQIO_LCS,
 	IRQIO_CTC,
 	IRQIO_ADM,
 	IRQIO_CSC,
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index ef7be599e1f7..7ca157ffab30 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -84,7 +84,6 @@ static const struct irq_class irqclass_sub_desc[] = {
 	{.irq = IRQIO_C70,  .name = "C70", .desc = "[I/O] 3270"},
 	{.irq = IRQIO_TAP,  .name = "TAP", .desc = "[I/O] Tape"},
 	{.irq = IRQIO_VMR,  .name = "VMR", .desc = "[I/O] Unit Record Devices"},
-	{.irq = IRQIO_LCS,  .name = "LCS", .desc = "[I/O] LCS"},
 	{.irq = IRQIO_CTC,  .name = "CTC", .desc = "[I/O] CTC"},
 	{.irq = IRQIO_ADM,  .name = "ADM", .desc = "[I/O] EADM Subchannel"},
 	{.irq = IRQIO_CSC,  .name = "CSC", .desc = "[I/O] CHSC Subchannel"},
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index e45bba240cbc..f6d0628a36d9 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -432,9 +432,6 @@ static struct net_device *bond_ipsec_dev(struct xfrm_state *xs)
 	struct bonding *bond;
 	struct slave *slave;
 
-	if (!bond_dev)
-		return NULL;
-
 	bond = netdev_priv(bond_dev);
 	if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)
 		return NULL;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index f5901f8e3907..f6b990b7f5b4 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -226,7 +226,6 @@ struct __packed offload_info {
 	struct offload_port_info ports;
 	struct offload_ka_info kas;
 	struct offload_rr_info rrs;
-	u8 buf[];
 };
 
 struct __packed hw_atl_utils_fw_rpc {
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index 6b6cb73482d7..1753bb87dfbd 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -1433,22 +1433,6 @@ int octeon_wait_for_ddr_init(struct octeon_device *oct, u32 *timeout)
 }
 EXPORT_SYMBOL_GPL(octeon_wait_for_ddr_init);
 
-/* Get the octeon id assigned to the octeon device passed as argument.
- *  This function is exported to other modules.
- *  @param dev - octeon device pointer passed as a void *.
- *  @return octeon device id
- */
-int lio_get_device_id(void *dev)
-{
-	struct octeon_device *octeon_dev = (struct octeon_device *)dev;
-	u32 i;
-
-	for (i = 0; i < MAX_OCTEON_DEVICES; i++)
-		if (octeon_device[i] == octeon_dev)
-			return octeon_dev->octeon_id;
-	return -1;
-}
-
 void lio_enable_irq(struct octeon_droq *droq, struct octeon_instr_queue *iq)
 {
 	u64 instr_cnt;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
index d26364c2ac81..19344b21f8fb 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -705,13 +705,6 @@ octeon_get_dispatch(struct octeon_device *octeon_dev, u16 opcode,
  */
 struct octeon_device *lio_get_device(u32 octeon_id);
 
-/** Get the octeon id assigned to the octeon device passed as argument.
- *  This function is exported to other modules.
- *  @param dev - octeon device pointer passed as a void *.
- *  @return octeon device id
- */
-int lio_get_device_id(void *dev);
-
 /** Read windowed register.
  *  @param  oct   -  pointer to the Octeon device.
  *  @param  addr  -  Address of the register to read.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index c7c2c15a1815..95e6f015a6af 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -1211,9 +1211,6 @@ struct adapter {
 	struct timer_list flower_stats_timer;
 	struct work_struct flower_stats_work;
 
-	/* Ethtool Dump */
-	struct ethtool_dump eth_dump;
-
 	/* HMA */
 	struct hma_data hma;
 
@@ -1233,6 +1230,10 @@ struct adapter {
 
 	/* Ethtool n-tuple */
 	struct cxgb4_ethtool_filter *ethtool_filters;
+
+	/* Ethtool Dump */
+	/* Must be last - ends in a flex-array member. */
+	struct ethtool_dump eth_dump;
 };
 
 /* Support for "sched-class" command to allow a TX Scheduling Class to be
diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c
index b330020dc0d6..598df63518c5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c
@@ -526,28 +526,6 @@ out:
 	return res;
 }
 
-u32 mlx4_zone_free_entries(struct mlx4_zone_allocator *zones, u32 uid, u32 obj, u32 count)
-{
-	struct mlx4_zone_entry *zone;
-	int res = 0;
-
-	spin_lock(&zones->lock);
-
-	zone = __mlx4_find_zone_by_uid(zones, uid);
-
-	if (NULL == zone) {
-		res = -1;
-		goto out;
-	}
-
-	__mlx4_free_from_zone(zone, obj, count);
-
-out:
-	spin_unlock(&zones->lock);
-
-	return res;
-}
-
 u32 mlx4_zone_free_entries_unique(struct mlx4_zone_allocator *zones, u32 obj, u32 count)
 {
 	struct mlx4_zone_entry *zone;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index d7d856d1758a..b213094ea30f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1478,12 +1478,6 @@ void mlx4_zone_allocator_destroy(struct mlx4_zone_allocator *zone_alloc);
 u32 mlx4_zone_alloc_entries(struct mlx4_zone_allocator *zones, u32 uid, int count,
 			    int align, u32 skip_mask, u32 *puid);
 
-/* Free <count> objects, start from <obj> of the uid <uid> from zone_allocator
- * <zones>.
- */
-u32 mlx4_zone_free_entries(struct mlx4_zone_allocator *zones,
-			   u32 uid, u32 obj, u32 count);
-
 /* If <zones> was allocated with MLX4_ZONE_ALLOC_FLAGS_NO_OVERLAP, instead of
  * specifying the uid when freeing an object, zone allocator could figure it by
  * itself. Other parameters are similar to mlx4_zone_free.
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 4e43f4a7d246..e3d0b13c1610 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -147,26 +147,6 @@ static int mlx4_set_port_mac_table(struct mlx4_dev *dev, u8 port,
 	return err;
 }
 
-int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx)
-{
-	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
-	struct mlx4_mac_table *table = &info->mac_table;
-	int i;
-
-	for (i = 0; i < MLX4_MAX_MAC_NUM; i++) {
-		if (!table->refs[i])
-			continue;
-
-		if (mac == (MLX4_MAC_MASK & be64_to_cpu(table->entries[i]))) {
-			*idx = i;
-			return 0;
-		}
-	}
-
-	return -ENOENT;
-}
-EXPORT_SYMBOL_GPL(mlx4_find_cached_mac);
-
 static bool mlx4_need_mf_bond(struct mlx4_dev *dev)
 {
 	int i, num_eth_ports = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 5f6a0605e4ae..f62fbfb67a1b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -296,11 +296,16 @@ enum mlx5e_fec_supported_link_mode {
 	MLX5E_FEC_SUPPORTED_LINK_MODE_200G_2X,
 	MLX5E_FEC_SUPPORTED_LINK_MODE_400G_4X,
 	MLX5E_FEC_SUPPORTED_LINK_MODE_800G_8X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_200G_1X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_400G_2X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_800G_4X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_1600G_8X,
 	MLX5E_MAX_FEC_SUPPORTED_LINK_MODE,
 };
 
 #define MLX5E_FEC_FIRST_50G_PER_LANE_MODE MLX5E_FEC_SUPPORTED_LINK_MODE_50G_1X
 #define MLX5E_FEC_FIRST_100G_PER_LANE_MODE MLX5E_FEC_SUPPORTED_LINK_MODE_100G_1X
+#define MLX5E_FEC_FIRST_200G_PER_LANE_MODE MLX5E_FEC_SUPPORTED_LINK_MODE_200G_1X
 
 #define MLX5E_FEC_OVERRIDE_ADMIN_POLICY(buf, policy, write, link)			\
 	do {										\
@@ -320,8 +325,10 @@ static bool mlx5e_is_fec_supported_link_mode(struct mlx5_core_dev *dev,
 	return link_mode < MLX5E_FEC_FIRST_50G_PER_LANE_MODE ||
 	       (link_mode < MLX5E_FEC_FIRST_100G_PER_LANE_MODE &&
 		MLX5_CAP_PCAM_FEATURE(dev, fec_50G_per_lane_in_pplm)) ||
-	       (link_mode >= MLX5E_FEC_FIRST_100G_PER_LANE_MODE &&
-		MLX5_CAP_PCAM_FEATURE(dev, fec_100G_per_lane_in_pplm));
+	       (link_mode < MLX5E_FEC_FIRST_200G_PER_LANE_MODE &&
+		MLX5_CAP_PCAM_FEATURE(dev, fec_100G_per_lane_in_pplm)) ||
+	       (link_mode >= MLX5E_FEC_FIRST_200G_PER_LANE_MODE &&
+		MLX5_CAP_PCAM_FEATURE(dev, fec_200G_per_lane_in_pplm));
 }
 
 /* get/set FEC admin field for a given speed */
@@ -368,6 +375,18 @@ static int mlx5e_fec_admin_field(u32 *pplm, u16 *fec_policy, bool write,
 	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_8X:
 		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 800g_8x);
 		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_200G_1X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 200g_1x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_2X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 400g_2x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_4X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 800g_4x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_1600G_8X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 1600g_8x);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -421,6 +440,18 @@ static int mlx5e_get_fec_cap_field(u32 *pplm, u16 *fec_cap,
 	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_8X:
 		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 800g_8x);
 		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_200G_1X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 200g_1x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_2X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 400g_2x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_4X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 800g_4x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_1600G_8X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 1600g_8x);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -494,6 +525,26 @@ out:
 	return 0;
 }
 
+static u16 mlx5e_remap_fec_conf_mode(enum mlx5e_fec_supported_link_mode link_mode,
+				     u16 conf_fec)
+{
+	/* RS fec in ethtool is originally mapped to MLX5E_FEC_RS_528_514.
+	 * For link modes up to 25G per lane, the value is kept.
+	 * For 50G or 100G per lane, it's remapped to MLX5E_FEC_RS_544_514.
+	 * For 200G per lane, remapped to MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD.
+	 */
+	if (conf_fec != BIT(MLX5E_FEC_RS_528_514))
+		return conf_fec;
+
+	if (link_mode >= MLX5E_FEC_FIRST_200G_PER_LANE_MODE)
+		return BIT(MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD);
+
+	if (link_mode >= MLX5E_FEC_FIRST_50G_PER_LANE_MODE)
+		return BIT(MLX5E_FEC_RS_544_514);
+
+	return conf_fec;
+}
+
 int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy)
 {
 	bool fec_50g_per_lane = MLX5_CAP_PCAM_FEATURE(dev, fec_50G_per_lane_in_pplm);
@@ -530,14 +581,7 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy)
 		if (!mlx5e_is_fec_supported_link_mode(dev, i))
 			break;
 
-		/* RS fec in ethtool is mapped to MLX5E_FEC_RS_528_514
-		 * to link modes up to 25G per lane and to
-		 * MLX5E_FEC_RS_544_514 in the new link modes based on
-		 * 50G or 100G per lane
-		 */
-		if (conf_fec == (1 << MLX5E_FEC_RS_528_514) &&
-		    i >= MLX5E_FEC_FIRST_50G_PER_LANE_MODE)
-			conf_fec = (1 << MLX5E_FEC_RS_544_514);
+		conf_fec = mlx5e_remap_fec_conf_mode(i, conf_fec);
 
 		mlx5e_get_fec_cap_field(out, &fec_caps, i);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
index d1da225f35da..fa2283dd383b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
@@ -61,6 +61,7 @@ enum {
 	MLX5E_FEC_NOFEC,
 	MLX5E_FEC_FIRECODE,
 	MLX5E_FEC_RS_528_514,
+	MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD = 4,
 	MLX5E_FEC_RS_544_514 = 7,
 	MLX5E_FEC_LLRS_272_257_1 = 9,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index afd654583b6b..131ed97ca997 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -326,7 +326,7 @@ static int mlx5e_ptp_alloc_txqsq(struct mlx5e_ptp *c, int txq_ix,
 	int node;
 
 	sq->pdev      = c->pdev;
-	sq->clock     = &mdev->clock;
+	sq->clock     = mdev->clock;
 	sq->mkey_be   = c->mkey_be;
 	sq->netdev    = c->netdev;
 	sq->priv      = c->priv;
@@ -696,7 +696,7 @@ static int mlx5e_init_ptp_rq(struct mlx5e_ptp *c, struct mlx5e_params *params,
 	rq->pdev         = c->pdev;
 	rq->netdev       = priv->netdev;
 	rq->priv         = priv;
-	rq->clock        = &mdev->clock;
+	rq->clock        = mdev->clock;
 	rq->tstamp       = &priv->tstamp;
 	rq->mdev         = mdev;
 	rq->hw_mtu       = MLX5E_SW2HW_MTU(params, params->sw_mtu);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h
index d6c12d0ea55b..2e528b2c34d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h
@@ -73,11 +73,6 @@ struct mlx5e_tc_act {
 	bool is_terminating_action;
 };
 
-struct mlx5e_tc_flow_action {
-	unsigned int num_entries;
-	struct flow_action_entry **entries;
-};
-
 extern struct mlx5e_tc_act mlx5e_tc_act_drop;
 extern struct mlx5e_tc_act mlx5e_tc_act_trap;
 extern struct mlx5e_tc_act mlx5e_tc_act_accept;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
index 53ca16cb9c41..140606fcd23b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
@@ -46,7 +46,7 @@ static void mlx5e_init_trap_rq(struct mlx5e_trap *t, struct mlx5e_params *params
 	rq->pdev         = t->pdev;
 	rq->netdev       = priv->netdev;
 	rq->priv         = priv;
-	rq->clock        = &mdev->clock;
+	rq->clock        = mdev->clock;
 	rq->tstamp       = &priv->tstamp;
 	rq->mdev         = mdev;
 	rq->hw_mtu       = MLX5E_SW2HW_MTU(params, params->sw_mtu);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 94b291662087..3cc4d55613bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -289,9 +289,9 @@ static u64 mlx5e_xsk_fill_timestamp(void *_priv)
 	ts = get_cqe_ts(priv->cqe);
 
 	if (mlx5_is_real_time_rq(priv->cq->mdev) || mlx5_is_real_time_sq(priv->cq->mdev))
-		return mlx5_real_time_cyc2time(&priv->cq->mdev->clock, ts);
+		return mlx5_real_time_cyc2time(priv->cq->mdev->clock, ts);
 
-	return  mlx5_timecounter_cyc2time(&priv->cq->mdev->clock, ts);
+	return  mlx5_timecounter_cyc2time(priv->cq->mdev->clock, ts);
 }
 
 static void mlx5e_xsk_request_checksum(u16 csum_start, u16 csum_offset, void *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 9240cfe25d10..d743e823362a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -72,7 +72,7 @@ static int mlx5e_init_xsk_rq(struct mlx5e_channel *c,
 	rq->netdev       = c->netdev;
 	rq->priv         = c->priv;
 	rq->tstamp       = c->tstamp;
-	rq->clock        = &mdev->clock;
+	rq->clock        = mdev->clock;
 	rq->icosq        = &c->icosq;
 	rq->ix           = c->ix;
 	rq->channel      = c;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index cae39198b4db..f9113cb13a0c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -237,6 +237,27 @@ void mlx5e_build_ptys2ethtool_map(void)
 				       ETHTOOL_LINK_MODE_800000baseDR8_2_Full_BIT,
 				       ETHTOOL_LINK_MODE_800000baseSR8_Full_BIT,
 				       ETHTOOL_LINK_MODE_800000baseVR8_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_200GAUI_1_200GBASE_CR1_KR1, ext,
+				       ETHTOOL_LINK_MODE_200000baseCR_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseKR_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseDR_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseDR_2_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseSR_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseVR_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_400GAUI_2_400GBASE_CR2_KR2, ext,
+				       ETHTOOL_LINK_MODE_400000baseCR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseKR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseDR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseDR2_2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseSR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseVR2_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_800GAUI_4_800GBASE_CR4_KR4, ext,
+				       ETHTOOL_LINK_MODE_800000baseCR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseKR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseDR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseDR4_2_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseSR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseVR4_Full_BIT);
 }
 
 static void mlx5e_ethtool_get_speed_arr(struct mlx5_core_dev *mdev,
@@ -931,6 +952,7 @@ static const u32 pplm_fec_2_ethtool[] = {
 	[MLX5E_FEC_RS_528_514] = ETHTOOL_FEC_RS,
 	[MLX5E_FEC_RS_544_514] = ETHTOOL_FEC_RS,
 	[MLX5E_FEC_LLRS_272_257_1] = ETHTOOL_FEC_LLRS,
+	[MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD] = ETHTOOL_FEC_RS,
 };
 
 static u32 pplm2ethtool_fec(u_long fec_mode, unsigned long size)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a814b63ed97e..2fdc86432ac0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -737,7 +737,7 @@ static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param
 	rq->netdev       = c->netdev;
 	rq->priv         = c->priv;
 	rq->tstamp       = c->tstamp;
-	rq->clock        = &mdev->clock;
+	rq->clock        = mdev->clock;
 	rq->icosq        = &c->icosq;
 	rq->ix           = c->ix;
 	rq->channel      = c;
@@ -1614,7 +1614,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	int err;
 
 	sq->pdev      = c->pdev;
-	sq->clock     = &mdev->clock;
+	sq->clock     = mdev->clock;
 	sq->mkey_be   = c->mkey_be;
 	sq->netdev    = c->netdev;
 	sq->mdev      = c->mdev;
@@ -3816,8 +3816,11 @@ static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv,
 	/* MQPRIO is another toplevel qdisc that can't be attached
 	 * simultaneously with the offloaded HTB.
 	 */
-	if (WARN_ON(mlx5e_selq_is_htb_enabled(&priv->selq)))
-		return -EINVAL;
+	if (mlx5e_selq_is_htb_enabled(&priv->selq)) {
+		NL_SET_ERR_MSG_MOD(mqprio->extack,
+				   "MQPRIO cannot be configured when HTB offload is enabled.");
+		return -EOPNOTSUPP;
+	}
 
 	switch (mqprio->mode) {
 	case TC_MQPRIO_MODE_DCB:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
index bde79cac33a9..d832a12ffec0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
@@ -97,7 +97,7 @@ static int mlx5_lag_create_port_sel_table(struct mlx5_lag *ldev,
 						mlx5_del_flow_rules(lag_definer->rules[idx]);
 					}
 					j = ldev->buckets;
-				};
+				}
 				goto destroy_fg;
 			}
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index d61a1a9297c9..65a94e46edcf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -43,6 +43,8 @@
 #include <linux/cpufeature.h>
 #endif /* CONFIG_X86 */
 
+#define MLX5_RT_CLOCK_IDENTITY_SIZE MLX5_FLD_SZ_BYTES(mrtcq_reg, rt_clock_identity)
+
 enum {
 	MLX5_PIN_MODE_IN		= 0x0,
 	MLX5_PIN_MODE_OUT		= 0x1,
@@ -77,6 +79,56 @@ enum {
 	MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX = 200000,
 };
 
+struct mlx5_clock_dev_state {
+	struct mlx5_core_dev *mdev;
+	struct mlx5_devcom_comp_dev *compdev;
+	struct mlx5_nb pps_nb;
+	struct work_struct out_work;
+};
+
+struct mlx5_clock_priv {
+	struct mlx5_clock clock;
+	struct mlx5_core_dev *mdev;
+	struct mutex lock; /* protect mdev and used in PTP callbacks */
+	struct mlx5_core_dev *event_mdev;
+};
+
+static struct mlx5_clock_priv *clock_priv(struct mlx5_clock *clock)
+{
+	return container_of(clock, struct mlx5_clock_priv, clock);
+}
+
+static void mlx5_clock_lockdep_assert(struct mlx5_clock *clock)
+{
+	if (!clock->shared)
+		return;
+
+	lockdep_assert(lockdep_is_held(&clock_priv(clock)->lock));
+}
+
+static struct mlx5_core_dev *mlx5_clock_mdev_get(struct mlx5_clock *clock)
+{
+	mlx5_clock_lockdep_assert(clock);
+
+	return clock_priv(clock)->mdev;
+}
+
+static void mlx5_clock_lock(struct mlx5_clock *clock)
+{
+	if (!clock->shared)
+		return;
+
+	mutex_lock(&clock_priv(clock)->lock);
+}
+
+static void mlx5_clock_unlock(struct mlx5_clock *clock)
+{
+	if (!clock->shared)
+		return;
+
+	mutex_unlock(&clock_priv(clock)->lock);
+}
+
 static bool mlx5_real_time_mode(struct mlx5_core_dev *mdev)
 {
 	return (mlx5_is_real_time_rq(mdev) || mlx5_is_real_time_sq(mdev));
@@ -94,6 +146,22 @@ static bool mlx5_modify_mtutc_allowed(struct mlx5_core_dev *mdev)
 	return MLX5_CAP_MCAM_FEATURE(mdev, ptpcyc2realtime_modify);
 }
 
+static int mlx5_clock_identity_get(struct mlx5_core_dev *mdev,
+				   u8 identify[MLX5_RT_CLOCK_IDENTITY_SIZE])
+{
+	u32 out[MLX5_ST_SZ_DW(mrtcq_reg)] = {};
+	u32 in[MLX5_ST_SZ_DW(mrtcq_reg)] = {};
+	int err;
+
+	err = mlx5_core_access_reg(mdev, in, sizeof(in),
+				   out, sizeof(out), MLX5_REG_MRTCQ, 0, 0);
+	if (!err)
+		memcpy(identify, MLX5_ADDR_OF(mrtcq_reg, out, rt_clock_identity),
+		       MLX5_RT_CLOCK_IDENTITY_SIZE);
+
+	return err;
+}
+
 static u32 mlx5_ptp_shift_constant(u32 dev_freq_khz)
 {
 	/* Optimal shift constant leads to corrections above just 1 scaled ppm.
@@ -119,21 +187,30 @@ static u32 mlx5_ptp_shift_constant(u32 dev_freq_khz)
 		   ilog2((U32_MAX / NSEC_PER_MSEC) * dev_freq_khz));
 }
 
+static s32 mlx5_clock_getmaxphase(struct mlx5_core_dev *mdev)
+{
+	return MLX5_CAP_MCAM_FEATURE(mdev, mtutc_time_adjustment_extended_range) ?
+		       MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX :
+			     MLX5_MTUTC_OPERATION_ADJUST_TIME_MAX;
+}
+
 static s32 mlx5_ptp_getmaxphase(struct ptp_clock_info *ptp)
 {
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct mlx5_core_dev *mdev;
+	s32 ret;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+	ret = mlx5_clock_getmaxphase(mdev);
+	mlx5_clock_unlock(clock);
 
-	return MLX5_CAP_MCAM_FEATURE(mdev, mtutc_time_adjustment_extended_range) ?
-		       MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX :
-			     MLX5_MTUTC_OPERATION_ADJUST_TIME_MAX;
+	return ret;
 }
 
 static bool mlx5_is_mtutc_time_adj_cap(struct mlx5_core_dev *mdev, s64 delta)
 {
-	s64 max = mlx5_ptp_getmaxphase(&mdev->clock.ptp_info);
+	s64 max = mlx5_clock_getmaxphase(mdev);
 
 	if (delta < -max || delta > max)
 		return false;
@@ -209,7 +286,7 @@ static int mlx5_mtctr_syncdevicetime(ktime_t *device_time,
 	if (real_time_mode)
 		*device_time = ns_to_ktime(REAL_TIME_TO_NS(device >> 32, device & U32_MAX));
 	else
-		*device_time = mlx5_timecounter_cyc2time(&mdev->clock, device);
+		*device_time = mlx5_timecounter_cyc2time(mdev->clock, device);
 
 	return 0;
 }
@@ -220,16 +297,23 @@ static int mlx5_ptp_getcrosststamp(struct ptp_clock_info *ptp,
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct system_time_snapshot history_begin = {0};
 	struct mlx5_core_dev *mdev;
+	int err;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
 
-	if (!mlx5_is_ptm_source_time_available(mdev))
-		return -EBUSY;
+	if (!mlx5_is_ptm_source_time_available(mdev)) {
+		err = -EBUSY;
+		goto unlock;
+	}
 
 	ktime_get_snapshot(&history_begin);
 
-	return get_device_system_crosststamp(mlx5_mtctr_syncdevicetime, mdev,
-					     &history_begin, cts);
+	err = get_device_system_crosststamp(mlx5_mtctr_syncdevicetime, mdev,
+					    &history_begin, cts);
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 #endif /* CONFIG_X86 */
 
@@ -263,8 +347,7 @@ static u64 read_internal_timer(const struct cyclecounter *cc)
 {
 	struct mlx5_timer *timer = container_of(cc, struct mlx5_timer, cycles);
 	struct mlx5_clock *clock = container_of(timer, struct mlx5_clock, timer);
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev,
-						  clock);
+	struct mlx5_core_dev *mdev = mlx5_clock_mdev_get(clock);
 
 	return mlx5_read_time(mdev, NULL, false) & cc->mask;
 }
@@ -272,7 +355,7 @@ static u64 read_internal_timer(const struct cyclecounter *cc)
 static void mlx5_update_clock_info_page(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_ib_clock_info *clock_info = mdev->clock_info;
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	struct mlx5_timer *timer;
 	u32 sign;
 
@@ -295,12 +378,10 @@ static void mlx5_update_clock_info_page(struct mlx5_core_dev *mdev)
 
 static void mlx5_pps_out(struct work_struct *work)
 {
-	struct mlx5_pps *pps_info = container_of(work, struct mlx5_pps,
-						 out_work);
-	struct mlx5_clock *clock = container_of(pps_info, struct mlx5_clock,
-						pps_info);
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev,
-						  clock);
+	struct mlx5_clock_dev_state *clock_state = container_of(work, struct mlx5_clock_dev_state,
+								out_work);
+	struct mlx5_core_dev *mdev = clock_state->mdev;
+	struct mlx5_clock *clock = mdev->clock;
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
 	unsigned long flags;
 	int i;
@@ -330,7 +411,8 @@ static long mlx5_timestamp_overflow(struct ptp_clock_info *ptp_info)
 	unsigned long flags;
 
 	clock = container_of(ptp_info, struct mlx5_clock, ptp_info);
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
 	timer = &clock->timer;
 
 	if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
@@ -342,6 +424,7 @@ static long mlx5_timestamp_overflow(struct ptp_clock_info *ptp_info)
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
 out:
+	mlx5_clock_unlock(clock);
 	return timer->overflow_period;
 }
 
@@ -361,15 +444,12 @@ static int mlx5_ptp_settime_real_time(struct mlx5_core_dev *mdev,
 	return mlx5_set_mtutc(mdev, in, sizeof(in));
 }
 
-static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts)
+static int mlx5_clock_settime(struct mlx5_core_dev *mdev, struct mlx5_clock *clock,
+			      const struct timespec64 *ts)
 {
-	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct mlx5_timer *timer = &clock->timer;
-	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
-
 	if (mlx5_modify_mtutc_allowed(mdev)) {
 		int err = mlx5_ptp_settime_real_time(mdev, ts);
 
@@ -385,6 +465,20 @@ static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64
 	return 0;
 }
 
+static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts)
+{
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
+	struct mlx5_core_dev *mdev;
+	int err;
+
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+	err = mlx5_clock_settime(mdev, clock, ts);
+	mlx5_clock_unlock(clock);
+
+	return err;
+}
+
 static
 struct timespec64 mlx5_ptp_gettimex_real_time(struct mlx5_core_dev *mdev,
 					      struct ptp_system_timestamp *sts)
@@ -404,7 +498,8 @@ static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
 	struct mlx5_core_dev *mdev;
 	u64 cycles, ns;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
 	if (mlx5_real_time_mode(mdev)) {
 		*ts = mlx5_ptp_gettimex_real_time(mdev, sts);
 		goto out;
@@ -414,6 +509,7 @@ static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
 	ns = mlx5_timecounter_cyc2time(clock, cycles);
 	*ts = ns_to_timespec64(ns);
 out:
+	mlx5_clock_unlock(clock);
 	return 0;
 }
 
@@ -444,14 +540,16 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	struct mlx5_timer *timer = &clock->timer;
 	struct mlx5_core_dev *mdev;
 	unsigned long flags;
+	int err = 0;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
 
 	if (mlx5_modify_mtutc_allowed(mdev)) {
-		int err = mlx5_ptp_adjtime_real_time(mdev, delta);
+		err = mlx5_ptp_adjtime_real_time(mdev, delta);
 
 		if (err)
-			return err;
+			goto unlock;
 	}
 
 	write_seqlock_irqsave(&clock->lock, flags);
@@ -459,17 +557,23 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	mlx5_update_clock_info_page(mdev);
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
-	return 0;
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 
 static int mlx5_ptp_adjphase(struct ptp_clock_info *ptp, s32 delta)
 {
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct mlx5_core_dev *mdev;
+	int err;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+	err = mlx5_ptp_adjtime_real_time(mdev, delta);
+	mlx5_clock_unlock(clock);
 
-	return mlx5_ptp_adjtime_real_time(mdev, delta);
+	return err;
 }
 
 static int mlx5_ptp_freq_adj_real_time(struct mlx5_core_dev *mdev, long scaled_ppm)
@@ -498,15 +602,17 @@ static int mlx5_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 	struct mlx5_timer *timer = &clock->timer;
 	struct mlx5_core_dev *mdev;
 	unsigned long flags;
+	int err = 0;
 	u32 mult;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
 
 	if (mlx5_modify_mtutc_allowed(mdev)) {
-		int err = mlx5_ptp_freq_adj_real_time(mdev, scaled_ppm);
+		err = mlx5_ptp_freq_adj_real_time(mdev, scaled_ppm);
 
 		if (err)
-			return err;
+			goto unlock;
 	}
 
 	mult = (u32)adjust_by_scaled_ppm(timer->nominal_c_mult, scaled_ppm);
@@ -518,7 +624,9 @@ static int mlx5_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 	write_sequnlock_irqrestore(&clock->lock, flags);
 	ptp_schedule_worker(clock->ptp, timer->overflow_period);
 
-	return 0;
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 
 static int mlx5_extts_configure(struct ptp_clock_info *ptp,
@@ -527,18 +635,14 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 {
 	struct mlx5_clock *clock =
 			container_of(ptp, struct mlx5_clock, ptp_info);
-	struct mlx5_core_dev *mdev =
-			container_of(clock, struct mlx5_core_dev, clock);
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
+	struct mlx5_core_dev *mdev;
 	u32 field_select = 0;
 	u8 pin_mode = 0;
 	u8 pattern = 0;
 	int pin = -1;
 	int err = 0;
 
-	if (!MLX5_PPS_CAP(mdev))
-		return -EOPNOTSUPP;
-
 	/* Reject requests with unsupported flags */
 	if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
 				PTP_RISING_EDGE |
@@ -569,6 +673,14 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 		field_select = MLX5_MTPPS_FS_ENABLE;
 	}
 
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+
+	if (!MLX5_PPS_CAP(mdev)) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
 	MLX5_SET(mtpps_reg, in, pin, pin);
 	MLX5_SET(mtpps_reg, in, pin_mode, pin_mode);
 	MLX5_SET(mtpps_reg, in, pattern, pattern);
@@ -577,15 +689,23 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 
 	err = mlx5_set_mtpps(mdev, in, sizeof(in));
 	if (err)
-		return err;
+		goto unlock;
+
+	err = mlx5_set_mtppse(mdev, pin, 0, MLX5_EVENT_MODE_REPETETIVE & on);
+	if (err)
+		goto unlock;
+
+	clock->pps_info.pin_armed[pin] = on;
+	clock_priv(clock)->event_mdev = mdev;
 
-	return mlx5_set_mtppse(mdev, pin, 0,
-			       MLX5_EVENT_MODE_REPETETIVE & on);
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 
 static u64 find_target_cycles(struct mlx5_core_dev *mdev, s64 target_ns)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	u64 cycles_now, cycles_delta;
 	u64 nsec_now, nsec_delta;
 	struct mlx5_timer *timer;
@@ -644,7 +764,7 @@ static int mlx5_perout_conf_out_pulse_duration(struct mlx5_core_dev *mdev,
 					       struct ptp_clock_request *rq,
 					       u32 *out_pulse_duration_ns)
 {
-	struct mlx5_pps *pps_info = &mdev->clock.pps_info;
+	struct mlx5_pps *pps_info = &mdev->clock->pps_info;
 	u32 out_pulse_duration;
 	struct timespec64 ts;
 
@@ -677,7 +797,7 @@ static int perout_conf_npps_real_time(struct mlx5_core_dev *mdev, struct ptp_clo
 				      u32 *field_select, u32 *out_pulse_duration_ns,
 				      u64 *period, u64 *time_stamp)
 {
-	struct mlx5_pps *pps_info = &mdev->clock.pps_info;
+	struct mlx5_pps *pps_info = &mdev->clock->pps_info;
 	struct ptp_clock_time *time = &rq->perout.start;
 	struct timespec64 ts;
 
@@ -712,26 +832,18 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 {
 	struct mlx5_clock *clock =
 			container_of(ptp, struct mlx5_clock, ptp_info);
-	struct mlx5_core_dev *mdev =
-			container_of(clock, struct mlx5_core_dev, clock);
-	bool rt_mode = mlx5_real_time_mode(mdev);
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
 	u32 out_pulse_duration_ns = 0;
+	struct mlx5_core_dev *mdev;
 	u32 field_select = 0;
 	u64 npps_period = 0;
 	u64 time_stamp = 0;
 	u8 pin_mode = 0;
 	u8 pattern = 0;
+	bool rt_mode;
 	int pin = -1;
 	int err = 0;
 
-	if (!MLX5_PPS_CAP(mdev))
-		return -EOPNOTSUPP;
-
-	/* Reject requests with unsupported flags */
-	if (mlx5_perout_verify_flags(mdev, rq->perout.flags))
-		return -EOPNOTSUPP;
-
 	if (rq->perout.index >= clock->ptp_info.n_pins)
 		return -EINVAL;
 
@@ -740,14 +852,29 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 	if (pin < 0)
 		return -EBUSY;
 
-	if (on) {
-		bool rt_mode = mlx5_real_time_mode(mdev);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+	rt_mode = mlx5_real_time_mode(mdev);
+
+	if (!MLX5_PPS_CAP(mdev)) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	/* Reject requests with unsupported flags */
+	if (mlx5_perout_verify_flags(mdev, rq->perout.flags)) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
 
+	if (on) {
 		pin_mode = MLX5_PIN_MODE_OUT;
 		pattern = MLX5_OUT_PATTERN_PERIODIC;
 
-		if (rt_mode &&  rq->perout.start.sec > U32_MAX)
-			return -EINVAL;
+		if (rt_mode &&  rq->perout.start.sec > U32_MAX) {
+			err = -EINVAL;
+			goto unlock;
+		}
 
 		field_select |= MLX5_MTPPS_FS_PIN_MODE |
 				MLX5_MTPPS_FS_PATTERN |
@@ -760,7 +887,7 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 		else
 			err = perout_conf_1pps(mdev, rq, &time_stamp, rt_mode);
 		if (err)
-			return err;
+			goto unlock;
 	}
 
 	MLX5_SET(mtpps_reg, in, pin, pin);
@@ -773,13 +900,16 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 	MLX5_SET(mtpps_reg, in, out_pulse_duration_ns, out_pulse_duration_ns);
 	err = mlx5_set_mtpps(mdev, in, sizeof(in));
 	if (err)
-		return err;
+		goto unlock;
 
 	if (rt_mode)
-		return 0;
+		goto unlock;
+
+	err = mlx5_set_mtppse(mdev, pin, 0, MLX5_EVENT_MODE_REPETETIVE & on);
 
-	return mlx5_set_mtppse(mdev, pin, 0,
-			       MLX5_EVENT_MODE_REPETETIVE & on);
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 
 static int mlx5_pps_configure(struct ptp_clock_info *ptp,
@@ -866,10 +996,8 @@ static int mlx5_query_mtpps_pin_mode(struct mlx5_core_dev *mdev, u8 pin,
 				    mtpps_size, MLX5_REG_MTPPS, 0, 0);
 }
 
-static int mlx5_get_pps_pin_mode(struct mlx5_clock *clock, u8 pin)
+static int mlx5_get_pps_pin_mode(struct mlx5_core_dev *mdev, u8 pin)
 {
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, clock);
-
 	u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {};
 	u8 mode;
 	int err;
@@ -888,8 +1016,9 @@ static int mlx5_get_pps_pin_mode(struct mlx5_clock *clock, u8 pin)
 	return PTP_PF_NONE;
 }
 
-static void mlx5_init_pin_config(struct mlx5_clock *clock)
+static void mlx5_init_pin_config(struct mlx5_core_dev *mdev)
 {
+	struct mlx5_clock *clock = mdev->clock;
 	int i;
 
 	if (!clock->ptp_info.n_pins)
@@ -910,15 +1039,15 @@ static void mlx5_init_pin_config(struct mlx5_clock *clock)
 			 sizeof(clock->ptp_info.pin_config[i].name),
 			 "mlx5_pps%d", i);
 		clock->ptp_info.pin_config[i].index = i;
-		clock->ptp_info.pin_config[i].func = mlx5_get_pps_pin_mode(clock, i);
+		clock->ptp_info.pin_config[i].func = mlx5_get_pps_pin_mode(mdev, i);
 		clock->ptp_info.pin_config[i].chan = 0;
 	}
 }
 
 static void mlx5_get_pps_caps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
 	u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
+	struct mlx5_clock *clock = mdev->clock;
 
 	mlx5_query_mtpps(mdev, out, sizeof(out));
 
@@ -968,16 +1097,16 @@ static u64 perout_conf_next_event_timer(struct mlx5_core_dev *mdev,
 static int mlx5_pps_event(struct notifier_block *nb,
 			  unsigned long type, void *data)
 {
-	struct mlx5_clock *clock = mlx5_nb_cof(nb, struct mlx5_clock, pps_nb);
+	struct mlx5_clock_dev_state *clock_state = mlx5_nb_cof(nb, struct mlx5_clock_dev_state,
+							       pps_nb);
+	struct mlx5_core_dev *mdev = clock_state->mdev;
+	struct mlx5_clock *clock = mdev->clock;
 	struct ptp_clock_event ptp_event;
 	struct mlx5_eqe *eqe = data;
 	int pin = eqe->data.pps.pin;
-	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 	u64 ns;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
-
 	switch (clock->ptp_info.pin_config[pin].func) {
 	case PTP_PF_EXTTS:
 		ptp_event.index = pin;
@@ -997,11 +1126,15 @@ static int mlx5_pps_event(struct notifier_block *nb,
 		ptp_clock_event(clock->ptp, &ptp_event);
 		break;
 	case PTP_PF_PEROUT:
+		if (clock->shared) {
+			mlx5_core_warn(mdev, " Received unexpected PPS out event\n");
+			break;
+		}
 		ns = perout_conf_next_event_timer(mdev, clock);
 		write_seqlock_irqsave(&clock->lock, flags);
 		clock->pps_info.start[pin] = ns;
 		write_sequnlock_irqrestore(&clock->lock, flags);
-		schedule_work(&clock->pps_info.out_work);
+		schedule_work(&clock_state->out_work);
 		break;
 	default:
 		mlx5_core_err(mdev, " Unhandled clock PPS event, func %d\n",
@@ -1013,7 +1146,7 @@ static int mlx5_pps_event(struct notifier_block *nb,
 
 static void mlx5_timecounter_init(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	struct mlx5_timer *timer = &clock->timer;
 	u32 dev_freq;
 
@@ -1029,10 +1162,10 @@ static void mlx5_timecounter_init(struct mlx5_core_dev *mdev)
 			 ktime_to_ns(ktime_get_real()));
 }
 
-static void mlx5_init_overflow_period(struct mlx5_clock *clock)
+static void mlx5_init_overflow_period(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, clock);
 	struct mlx5_ib_clock_info *clock_info = mdev->clock_info;
+	struct mlx5_clock *clock = mdev->clock;
 	struct mlx5_timer *timer = &clock->timer;
 	u64 overflow_cycles;
 	u64 frac = 0;
@@ -1065,7 +1198,7 @@ static void mlx5_init_overflow_period(struct mlx5_clock *clock)
 
 static void mlx5_init_clock_info(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	struct mlx5_ib_clock_info *info;
 	struct mlx5_timer *timer;
 
@@ -1088,7 +1221,7 @@ static void mlx5_init_clock_info(struct mlx5_core_dev *mdev)
 
 static void mlx5_init_timer_max_freq_adjustment(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	u32 out[MLX5_ST_SZ_DW(mtutc_reg)] = {};
 	u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {};
 	u8 log_max_freq_adjustment = 0;
@@ -1107,7 +1240,7 @@ static void mlx5_init_timer_max_freq_adjustment(struct mlx5_core_dev *mdev)
 
 static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 
 	/* Configure the PHC */
 	clock->ptp_info = mlx5_ptp_clock_info;
@@ -1123,38 +1256,30 @@ static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev)
 
 	mlx5_timecounter_init(mdev);
 	mlx5_init_clock_info(mdev);
-	mlx5_init_overflow_period(clock);
+	mlx5_init_overflow_period(mdev);
 
 	if (mlx5_real_time_mode(mdev)) {
 		struct timespec64 ts;
 
 		ktime_get_real_ts64(&ts);
-		mlx5_ptp_settime(&clock->ptp_info, &ts);
+		mlx5_clock_settime(mdev, clock, &ts);
 	}
 }
 
 static void mlx5_init_pps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
-
 	if (!MLX5_PPS_CAP(mdev))
 		return;
 
 	mlx5_get_pps_caps(mdev);
-	mlx5_init_pin_config(clock);
+	mlx5_init_pin_config(mdev);
 }
 
-void mlx5_init_clock(struct mlx5_core_dev *mdev)
+static void mlx5_init_clock_dev(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
-
-	if (!MLX5_CAP_GEN(mdev, device_frequency_khz)) {
-		mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n");
-		return;
-	}
+	struct mlx5_clock *clock = mdev->clock;
 
 	seqlock_init(&clock->lock);
-	INIT_WORK(&clock->pps_info.out_work, mlx5_pps_out);
 
 	/* Initialize the device clock */
 	mlx5_init_timer_clock(mdev);
@@ -1163,35 +1288,27 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 	mlx5_init_pps(mdev);
 
 	clock->ptp = ptp_clock_register(&clock->ptp_info,
-					&mdev->pdev->dev);
+					clock->shared ? NULL : &mdev->pdev->dev);
 	if (IS_ERR(clock->ptp)) {
-		mlx5_core_warn(mdev, "ptp_clock_register failed %ld\n",
+		mlx5_core_warn(mdev, "%sptp_clock_register failed %ld\n",
+			       clock->shared ? "shared clock " : "",
 			       PTR_ERR(clock->ptp));
 		clock->ptp = NULL;
 	}
 
-	MLX5_NB_INIT(&clock->pps_nb, mlx5_pps_event, PPS_EVENT);
-	mlx5_eq_notifier_register(mdev, &clock->pps_nb);
-
 	if (clock->ptp)
 		ptp_schedule_worker(clock->ptp, 0);
 }
 
-void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
+static void mlx5_destroy_clock_dev(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 
-	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
-		return;
-
-	mlx5_eq_notifier_unregister(mdev, &clock->pps_nb);
 	if (clock->ptp) {
 		ptp_clock_unregister(clock->ptp);
 		clock->ptp = NULL;
 	}
 
-	cancel_work_sync(&clock->pps_info.out_work);
-
 	if (mdev->clock_info) {
 		free_page((unsigned long)mdev->clock_info);
 		mdev->clock_info = NULL;
@@ -1199,3 +1316,248 @@ void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
 
 	kfree(clock->ptp_info.pin_config);
 }
+
+static void mlx5_clock_free(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_clock_priv *cpriv = clock_priv(mdev->clock);
+
+	mlx5_destroy_clock_dev(mdev);
+	mutex_destroy(&cpriv->lock);
+	kfree(cpriv);
+	mdev->clock = NULL;
+}
+
+static int mlx5_clock_alloc(struct mlx5_core_dev *mdev, bool shared)
+{
+	struct mlx5_clock_priv *cpriv;
+	struct mlx5_clock *clock;
+
+	cpriv = kzalloc(sizeof(*cpriv), GFP_KERNEL);
+	if (!cpriv)
+		return -ENOMEM;
+
+	mutex_init(&cpriv->lock);
+	cpriv->mdev = mdev;
+	clock = &cpriv->clock;
+	clock->shared = shared;
+	mdev->clock = clock;
+	mlx5_clock_lock(clock);
+	mlx5_init_clock_dev(mdev);
+	mlx5_clock_unlock(clock);
+
+	if (!clock->shared)
+		return 0;
+
+	if (!clock->ptp) {
+		mlx5_core_warn(mdev, "failed to create ptp dev shared by multiple functions");
+		mlx5_clock_free(mdev);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void mlx5_shared_clock_register(struct mlx5_core_dev *mdev, u64 key)
+{
+	struct mlx5_core_dev *peer_dev, *next = NULL;
+	struct mlx5_devcom_comp_dev *pos;
+
+	mdev->clock_state->compdev = mlx5_devcom_register_component(mdev->priv.devc,
+								    MLX5_DEVCOM_SHARED_CLOCK,
+								    key, NULL, mdev);
+	if (IS_ERR(mdev->clock_state->compdev))
+		return;
+
+	mlx5_devcom_comp_lock(mdev->clock_state->compdev);
+	mlx5_devcom_for_each_peer_entry(mdev->clock_state->compdev, peer_dev, pos) {
+		if (peer_dev->clock) {
+			next = peer_dev;
+			break;
+		}
+	}
+
+	if (next) {
+		mdev->clock = next->clock;
+		/* clock info is shared among all the functions using the same clock */
+		mdev->clock_info = next->clock_info;
+	} else {
+		mlx5_clock_alloc(mdev, true);
+	}
+	mlx5_devcom_comp_unlock(mdev->clock_state->compdev);
+
+	if (!mdev->clock) {
+		mlx5_devcom_unregister_component(mdev->clock_state->compdev);
+		mdev->clock_state->compdev = NULL;
+	}
+}
+
+static void mlx5_shared_clock_unregister(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_core_dev *peer_dev, *next = NULL;
+	struct mlx5_clock *clock = mdev->clock;
+	struct mlx5_devcom_comp_dev *pos;
+
+	mlx5_devcom_comp_lock(mdev->clock_state->compdev);
+	mlx5_devcom_for_each_peer_entry(mdev->clock_state->compdev, peer_dev, pos) {
+		if (peer_dev->clock && peer_dev != mdev) {
+			next = peer_dev;
+			break;
+		}
+	}
+
+	if (next) {
+		struct mlx5_clock_priv *cpriv = clock_priv(clock);
+
+		mlx5_clock_lock(clock);
+		if (mdev == cpriv->mdev)
+			cpriv->mdev = next;
+		mlx5_clock_unlock(clock);
+	} else {
+		mlx5_clock_free(mdev);
+	}
+
+	mdev->clock = NULL;
+	mdev->clock_info = NULL;
+	mlx5_devcom_comp_unlock(mdev->clock_state->compdev);
+
+	mlx5_devcom_unregister_component(mdev->clock_state->compdev);
+}
+
+static void mlx5_clock_arm_pps_in_event(struct mlx5_clock *clock,
+					struct mlx5_core_dev *new_mdev,
+					struct mlx5_core_dev *old_mdev)
+{
+	struct ptp_clock_info *ptp_info = &clock->ptp_info;
+	struct mlx5_clock_priv *cpriv = clock_priv(clock);
+	int i;
+
+	for (i = 0; i < ptp_info->n_pins; i++) {
+		if (ptp_info->pin_config[i].func != PTP_PF_EXTTS ||
+		    !clock->pps_info.pin_armed[i])
+			continue;
+
+		if (new_mdev) {
+			mlx5_set_mtppse(new_mdev, i, 0, MLX5_EVENT_MODE_REPETETIVE);
+			cpriv->event_mdev = new_mdev;
+		} else {
+			cpriv->event_mdev = NULL;
+		}
+
+		if (old_mdev)
+			mlx5_set_mtppse(old_mdev, i, 0, MLX5_EVENT_MODE_DISABLE);
+	}
+}
+
+void mlx5_clock_load(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_clock *clock = mdev->clock;
+	struct mlx5_clock_priv *cpriv;
+
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
+		return;
+
+	INIT_WORK(&mdev->clock_state->out_work, mlx5_pps_out);
+	MLX5_NB_INIT(&mdev->clock_state->pps_nb, mlx5_pps_event, PPS_EVENT);
+	mlx5_eq_notifier_register(mdev, &mdev->clock_state->pps_nb);
+
+	if (!clock->shared) {
+		mlx5_clock_arm_pps_in_event(clock, mdev, NULL);
+		return;
+	}
+
+	cpriv = clock_priv(clock);
+	mlx5_devcom_comp_lock(mdev->clock_state->compdev);
+	mlx5_clock_lock(clock);
+	if (mdev == cpriv->mdev && mdev != cpriv->event_mdev)
+		mlx5_clock_arm_pps_in_event(clock, mdev, cpriv->event_mdev);
+	mlx5_clock_unlock(clock);
+	mlx5_devcom_comp_unlock(mdev->clock_state->compdev);
+}
+
+void mlx5_clock_unload(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_core_dev *peer_dev, *next = NULL;
+	struct mlx5_clock *clock = mdev->clock;
+	struct mlx5_devcom_comp_dev *pos;
+
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
+		return;
+
+	if (!clock->shared) {
+		mlx5_clock_arm_pps_in_event(clock, NULL, mdev);
+		goto out;
+	}
+
+	mlx5_devcom_comp_lock(mdev->clock_state->compdev);
+	mlx5_devcom_for_each_peer_entry(mdev->clock_state->compdev, peer_dev, pos) {
+		if (peer_dev->clock && peer_dev != mdev) {
+			next = peer_dev;
+			break;
+		}
+	}
+
+	mlx5_clock_lock(clock);
+	if (mdev == clock_priv(clock)->event_mdev)
+		mlx5_clock_arm_pps_in_event(clock, next, mdev);
+	mlx5_clock_unlock(clock);
+	mlx5_devcom_comp_unlock(mdev->clock_state->compdev);
+
+out:
+	mlx5_eq_notifier_unregister(mdev, &mdev->clock_state->pps_nb);
+	cancel_work_sync(&mdev->clock_state->out_work);
+}
+
+static struct mlx5_clock null_clock;
+
+int mlx5_init_clock(struct mlx5_core_dev *mdev)
+{
+	u8 identity[MLX5_RT_CLOCK_IDENTITY_SIZE];
+	struct mlx5_clock_dev_state *clock_state;
+	u64 key;
+	int err;
+
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz)) {
+		mdev->clock = &null_clock;
+		mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n");
+		return 0;
+	}
+
+	clock_state = kzalloc(sizeof(*clock_state), GFP_KERNEL);
+	if (!clock_state)
+		return -ENOMEM;
+	clock_state->mdev = mdev;
+	mdev->clock_state = clock_state;
+
+	if (MLX5_CAP_MCAM_REG3(mdev, mrtcq) && mlx5_real_time_mode(mdev)) {
+		if (mlx5_clock_identity_get(mdev, identity)) {
+			mlx5_core_warn(mdev, "failed to get rt clock identity, create ptp dev per function\n");
+		} else {
+			memcpy(&key, &identity, sizeof(key));
+			mlx5_shared_clock_register(mdev, key);
+		}
+	}
+
+	if (!mdev->clock) {
+		err = mlx5_clock_alloc(mdev, false);
+		if (err) {
+			kfree(clock_state);
+			mdev->clock_state = NULL;
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
+{
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
+		return;
+
+	if (mdev->clock->shared)
+		mlx5_shared_clock_unregister(mdev);
+	else
+		mlx5_clock_free(mdev);
+	kfree(mdev->clock_state);
+	mdev->clock_state = NULL;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
index bd95b9f8d143..c18a652c0faa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
@@ -33,6 +33,35 @@
 #ifndef __LIB_CLOCK_H__
 #define __LIB_CLOCK_H__
 
+#include <linux/ptp_clock_kernel.h>
+
+#define MAX_PIN_NUM	8
+struct mlx5_pps {
+	u8                         pin_caps[MAX_PIN_NUM];
+	u64                        start[MAX_PIN_NUM];
+	u8                         enabled;
+	u64                        min_npps_period;
+	u64                        min_out_pulse_duration_ns;
+	bool                       pin_armed[MAX_PIN_NUM];
+};
+
+struct mlx5_timer {
+	struct cyclecounter        cycles;
+	struct timecounter         tc;
+	u32                        nominal_c_mult;
+	unsigned long              overflow_period;
+};
+
+struct mlx5_clock {
+	seqlock_t                  lock;
+	struct hwtstamp_config     hwtstamp_config;
+	struct ptp_clock          *ptp;
+	struct ptp_clock_info      ptp_info;
+	struct mlx5_pps            pps_info;
+	struct mlx5_timer          timer;
+	bool                       shared;
+};
+
 static inline bool mlx5_is_real_time_rq(struct mlx5_core_dev *mdev)
 {
 	u8 rq_ts_format_cap = MLX5_CAP_GEN(mdev, rq_ts_format);
@@ -54,12 +83,14 @@ static inline bool mlx5_is_real_time_sq(struct mlx5_core_dev *mdev)
 typedef ktime_t (*cqe_ts_to_ns)(struct mlx5_clock *, u64);
 
 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
-void mlx5_init_clock(struct mlx5_core_dev *mdev);
+int mlx5_init_clock(struct mlx5_core_dev *mdev);
 void mlx5_cleanup_clock(struct mlx5_core_dev *mdev);
+void mlx5_clock_load(struct mlx5_core_dev *mdev);
+void mlx5_clock_unload(struct mlx5_core_dev *mdev);
 
 static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
 {
-	return mdev->clock.ptp ? ptp_clock_index(mdev->clock.ptp) : -1;
+	return mdev->clock->ptp ? ptp_clock_index(mdev->clock->ptp) : -1;
 }
 
 static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
@@ -87,8 +118,10 @@ static inline ktime_t mlx5_real_time_cyc2time(struct mlx5_clock *clock,
 	return ns_to_ktime(time);
 }
 #else
-static inline void mlx5_init_clock(struct mlx5_core_dev *mdev) {}
+static inline int mlx5_init_clock(struct mlx5_core_dev *mdev) { return 0; }
 static inline void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_clock_load(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_clock_unload(struct mlx5_core_dev *mdev) {}
 static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
 {
 	return -1;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
index d58032dd0df7..c79699b94a02 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
@@ -11,6 +11,7 @@ enum mlx5_devcom_component {
 	MLX5_DEVCOM_MPV,
 	MLX5_DEVCOM_HCA_PORTS,
 	MLX5_DEVCOM_SD_GROUP,
+	MLX5_DEVCOM_SHARED_CLOCK,
 	MLX5_DEVCOM_NUM_COMPONENTS,
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index ec956c4bcebd..710633d5fdbe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1038,7 +1038,11 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 
 	mlx5_init_reserved_gids(dev);
 
-	mlx5_init_clock(dev);
+	err = mlx5_init_clock(dev);
+	if (err) {
+		mlx5_core_err(dev, "failed to initialize hardware clock\n");
+		goto err_tables_cleanup;
+	}
 
 	dev->vxlan = mlx5_vxlan_create(dev);
 	dev->geneve = mlx5_geneve_create(dev);
@@ -1046,7 +1050,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	err = mlx5_init_rl_table(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to init rate limiting\n");
-		goto err_tables_cleanup;
+		goto err_clock_cleanup;
 	}
 
 	err = mlx5_mpfs_init(dev);
@@ -1123,10 +1127,11 @@ err_mpfs_cleanup:
 	mlx5_mpfs_cleanup(dev);
 err_rl_cleanup:
 	mlx5_cleanup_rl_table(dev);
-err_tables_cleanup:
+err_clock_cleanup:
 	mlx5_geneve_destroy(dev->geneve);
 	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cleanup_clock(dev);
+err_tables_cleanup:
 	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cq_debugfs_cleanup(dev);
 	mlx5_fw_reset_cleanup(dev);
@@ -1359,6 +1364,8 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 		goto err_eq_table;
 	}
 
+	mlx5_clock_load(dev);
+
 	err = mlx5_fw_tracer_init(dev->tracer);
 	if (err) {
 		mlx5_core_err(dev, "Failed to init FW tracer %d\n", err);
@@ -1442,6 +1449,7 @@ err_fpga_start:
 	mlx5_hv_vhca_cleanup(dev->hv_vhca);
 	mlx5_fw_reset_events_stop(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
+	mlx5_clock_unload(dev);
 	mlx5_eq_table_destroy(dev);
 err_eq_table:
 	mlx5_irq_table_destroy(dev);
@@ -1468,6 +1476,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
 	mlx5_hv_vhca_cleanup(dev->hv_vhca);
 	mlx5_fw_reset_events_stop(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
+	mlx5_clock_unload(dev);
 	mlx5_eq_table_destroy(dev);
 	mlx5_irq_table_destroy(dev);
 	mlx5_pagealloc_stop(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 50931584132b..3995df064101 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -1105,6 +1105,9 @@ static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = {
 	[MLX5E_200GAUI_2_200GBASE_CR2_KR2] = 200000,
 	[MLX5E_400GAUI_4_400GBASE_CR4_KR4] = 400000,
 	[MLX5E_800GAUI_8_800GBASE_CR8_KR8] = 800000,
+	[MLX5E_200GAUI_1_200GBASE_CR1_KR1] = 200000,
+	[MLX5E_400GAUI_2_400GBASE_CR2_KR2] = 400000,
+	[MLX5E_800GAUI_4_800GBASE_CR4_KR4] = 800000,
 };
 
 int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c
index 60cb4527588a..65740bb68b09 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c
@@ -516,30 +516,6 @@ def_xa_destroy:
 	return NULL;
 }
 
-/* Assure synchronization of the device steering tables with updates made by SW
- * insertion.
- */
-int mlx5dr_domain_sync(struct mlx5dr_domain *dmn, u32 flags)
-{
-	int ret = 0;
-
-	if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_SW) {
-		mlx5dr_domain_lock(dmn);
-		ret = mlx5dr_send_ring_force_drain(dmn);
-		mlx5dr_domain_unlock(dmn);
-		if (ret) {
-			mlx5dr_err(dmn, "Force drain failed flags: %d, ret: %d\n",
-				   flags, ret);
-			return ret;
-		}
-	}
-
-	if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_HW)
-		ret = mlx5dr_cmd_sync_steering(dmn->mdev);
-
-	return ret;
-}
-
 int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn)
 {
 	if (WARN_ON_ONCE(refcount_read(&dmn->refcount) > 1))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c
index f57c84e5128b..4fd4e8483382 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c
@@ -1331,36 +1331,3 @@ void mlx5dr_send_ring_free(struct mlx5dr_domain *dmn,
 	kfree(send_ring->sync_buff);
 	kfree(send_ring);
 }
-
-int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn)
-{
-	struct mlx5dr_send_ring *send_ring = dmn->send_ring;
-	struct postsend_info send_info = {};
-	u8 data[DR_STE_SIZE];
-	int num_of_sends_req;
-	int ret;
-	int i;
-
-	/* Sending this amount of requests makes sure we will get drain */
-	num_of_sends_req = send_ring->signal_th * TH_NUMS_TO_DRAIN / 2;
-
-	/* Send fake requests forcing the last to be signaled */
-	send_info.write.addr = (uintptr_t)data;
-	send_info.write.length = DR_STE_SIZE;
-	send_info.write.lkey = 0;
-	/* Using the sync_mr in order to write/read */
-	send_info.remote_addr = (uintptr_t)send_ring->sync_mr->addr;
-	send_info.rkey = send_ring->sync_mr->mkey;
-
-	for (i = 0; i < num_of_sends_req; i++) {
-		ret = dr_postsend_icm_data(dmn, &send_info);
-		if (ret)
-			return ret;
-	}
-
-	spin_lock(&send_ring->lock);
-	ret = dr_handle_pending_wc(dmn, send_ring);
-	spin_unlock(&send_ring->lock);
-
-	return ret;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h
index 7618c6147f86..cc328292bf84 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h
@@ -1473,7 +1473,6 @@ struct mlx5dr_send_ring {
 int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn);
 void mlx5dr_send_ring_free(struct mlx5dr_domain *dmn,
 			   struct mlx5dr_send_ring *send_ring);
-int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn);
 int mlx5dr_send_postsend_ste(struct mlx5dr_domain *dmn,
 			     struct mlx5dr_ste *ste,
 			     u8 *data,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h
index 0bb3724c10c2..fc8a2169d1a1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h
@@ -45,8 +45,6 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type);
 
 int mlx5dr_domain_destroy(struct mlx5dr_domain *domain);
 
-int mlx5dr_domain_sync(struct mlx5dr_domain *domain, u32 flags);
-
 void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
 			    struct mlx5dr_domain *peer_dmn,
 			    u16 peer_vhca_id);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index b10f80fc651b..fa7082ee5183 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -754,9 +754,6 @@ void
 mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
 void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp,
 				 struct net_device *dev);
-bool mlxsw_sp_rif_exists(struct mlxsw_sp *mlxsw_sp,
-			 const struct net_device *dev);
-u16 mlxsw_sp_rif_vid(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev);
 u16 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp);
 int mlxsw_sp_router_nve_promote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id,
 				      enum mlxsw_sp_l3proto ul_proto,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 7d6d859cef3f..464821dd492d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -8184,41 +8184,6 @@ mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
 	return NULL;
 }
 
-bool mlxsw_sp_rif_exists(struct mlxsw_sp *mlxsw_sp,
-			 const struct net_device *dev)
-{
-	struct mlxsw_sp_rif *rif;
-
-	mutex_lock(&mlxsw_sp->router->lock);
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
-	mutex_unlock(&mlxsw_sp->router->lock);
-
-	return rif;
-}
-
-u16 mlxsw_sp_rif_vid(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev)
-{
-	struct mlxsw_sp_rif *rif;
-	u16 vid = 0;
-
-	mutex_lock(&mlxsw_sp->router->lock);
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
-	if (!rif)
-		goto out;
-
-	/* We only return the VID for VLAN RIFs. Otherwise we return an
-	 * invalid value (0).
-	 */
-	if (rif->ops->type != MLXSW_SP_RIF_TYPE_VLAN)
-		goto out;
-
-	vid = mlxsw_sp_fid_8021q_vid(rif->fid);
-
-out:
-	mutex_unlock(&mlxsw_sp->router->lock);
-	return vid;
-}
-
 static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif)
 {
 	char ritr_pl[MLXSW_REG_RITR_LEN];
@@ -8417,19 +8382,6 @@ u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
 	return lb_rif->common.rif_index;
 }
 
-u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
-{
-	struct net_device *dev = mlxsw_sp_rif_dev(&lb_rif->common);
-	u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(dev);
-	struct mlxsw_sp_vr *ul_vr;
-
-	ul_vr = mlxsw_sp_vr_get(lb_rif->common.mlxsw_sp, ul_tb_id, NULL);
-	if (WARN_ON(IS_ERR(ul_vr)))
-		return 0;
-
-	return ul_vr->id;
-}
-
 u16 mlxsw_sp_ipip_lb_ul_rif_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
 {
 	return lb_rif->ul_rif_id;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index 0432c7cc6b07..313efab5c324 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -90,7 +90,6 @@ struct mlxsw_sp_ipip_entry;
 struct mlxsw_sp_rif *mlxsw_sp_rif_by_index(const struct mlxsw_sp *mlxsw_sp,
 					   u16 rif_index);
 u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *rif);
-u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *rif);
 u16 mlxsw_sp_ipip_lb_ul_rif_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif);
 u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev);
 int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif);
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c b/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
index 59951b5abdb7..ac80981f67c0 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
@@ -10,6 +10,40 @@
 
 static struct dentry *fbnic_dbg_root;
 
+static void fbnic_dbg_desc_break(struct seq_file *s, int i)
+{
+	while (i--)
+		seq_putc(s, '-');
+
+	seq_putc(s, '\n');
+}
+
+static int fbnic_dbg_mac_addr_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+	char hdr[80];
+	int i;
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-17s %s\n",
+		 "Idx", "S", "TCAM Bitmap", "Addr/Mask");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < FBNIC_RPC_TCAM_MACDA_NUM_ENTRIES; i++) {
+		struct fbnic_mac_addr *mac_addr = &fbd->mac_addr[i];
+
+		seq_printf(s, "%02d  %d %64pb %pm\n",
+			   i, mac_addr->state, mac_addr->act_tcam,
+			   mac_addr->value.addr8);
+		seq_printf(s, "                        %pm\n",
+			   mac_addr->mask.addr8);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_mac_addr);
+
 static int fbnic_dbg_pcie_stats_show(struct seq_file *s, void *v)
 {
 	struct fbnic_dev *fbd = s->private;
@@ -48,6 +82,8 @@ void fbnic_dbg_fbd_init(struct fbnic_dev *fbd)
 	fbd->dbg_fbd = debugfs_create_dir(name, fbnic_dbg_root);
 	debugfs_create_file("pcie_stats", 0400, fbd->dbg_fbd, fbd,
 			    &fbnic_dbg_pcie_stats_fops);
+	debugfs_create_file("mac_addr", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_mac_addr_fops);
 }
 
 void fbnic_dbg_fbd_exit(struct fbnic_dev *fbd)
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index 7a96b6ee773f..1db57c42333e 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -628,6 +628,8 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd)
 	fbnic_rss_key_fill(fbn->rss_key);
 	fbnic_rss_init_en_mask(fbn);
 
+	netdev->priv_flags |= IFF_UNICAST_FLT;
+
 	netdev->features |=
 		NETIF_F_RXHASH |
 		NETIF_F_SG |
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index fa167b1aa019..5222a035fd19 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -3033,7 +3033,7 @@ static void qed_iov_vf_mbx_vport_update(struct qed_hwfn *p_hwfn,
 	u16 length;
 	int rc;
 
-	/* Valiate PF can send such a request */
+	/* Validate PF can send such a request */
 	if (!vf->vport_instance) {
 		DP_VERBOSE(p_hwfn,
 			   QED_MSG_IOV,
@@ -3312,7 +3312,7 @@ static void qed_iov_vf_mbx_ucast_filter(struct qed_hwfn *p_hwfn,
 		goto out;
 	}
 
-	/* Determine if the unicast filtering is acceptible by PF */
+	/* Determine if the unicast filtering is acceptable by PF */
 	if ((p_bulletin->valid_bitmap & BIT(VLAN_ADDR_FORCED)) &&
 	    (params.type == QED_FILTER_VLAN ||
 	     params.type == QED_FILTER_MAC_VLAN)) {
@@ -3729,7 +3729,7 @@ qed_iov_execute_vf_flr_cleanup(struct qed_hwfn *p_hwfn,
 
 		rc = qed_iov_enable_vf_access(p_hwfn, p_ptt, p_vf);
 		if (rc) {
-			DP_ERR(p_hwfn, "Failed to re-enable VF[%d] acces\n",
+			DP_ERR(p_hwfn, "Failed to re-enable VF[%d] access\n",
 			       vfid);
 			return rc;
 		}
@@ -4480,7 +4480,7 @@ int qed_sriov_disable(struct qed_dev *cdev, bool pci_enabled)
 		struct qed_ptt *ptt = qed_ptt_acquire(hwfn);
 
 		/* Failure to acquire the ptt in 100g creates an odd error
-		 * where the first engine has already relased IOV.
+		 * where the first engine has already released IOV.
 		 */
 		if (!ptt) {
 			DP_ERR(hwfn, "Failed to acquire ptt\n");
diff --git a/drivers/net/ethernet/realtek/Kconfig b/drivers/net/ethernet/realtek/Kconfig
index 8a8ea51c639e..fe136f61586f 100644
--- a/drivers/net/ethernet/realtek/Kconfig
+++ b/drivers/net/ethernet/realtek/Kconfig
@@ -114,7 +114,8 @@ config R8169
 	  will be called r8169.  This is recommended.
 
 config R8169_LEDS
-	def_bool R8169 && LEDS_TRIGGER_NETDEV
+	bool "Support for controlling the NIC LEDs"
+	depends on R8169 && LEDS_TRIGGER_NETDEV
 	depends on !(R8169=y && LEDS_CLASS=m)
 	help
 	  Optional support for controlling the NIC LED's with the netdev
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 5a5eba49c651..7306c8e323d7 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5222,6 +5222,7 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 	new_bus->priv = tp;
 	new_bus->parent = &pdev->dev;
 	new_bus->irq[0] = PHY_MAC_INTERRUPT;
+	new_bus->phy_mask = GENMASK(31, 1);
 	snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x-%x",
 		 pci_domain_nr(pdev->bus), pci_dev_id(pdev));
 
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 6bf3ec985f3d..f181f05cb429 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -13,7 +13,7 @@
  */
 const char *phy_speed_to_str(int speed)
 {
-	BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 103,
+	BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 121,
 		"Enum ethtool_link_mode_bit_indices and phylib are out of sync. "
 		"If a speed or mode has been added please update phy_speed_to_str "
 		"and the PHY settings array.\n");
@@ -169,6 +169,12 @@ static const struct phy_setting settings[] = {
 	PHY_SETTING( 800000, FULL, 800000baseDR8_2_Full		),
 	PHY_SETTING( 800000, FULL, 800000baseSR8_Full		),
 	PHY_SETTING( 800000, FULL, 800000baseVR8_Full		),
+	PHY_SETTING( 800000, FULL, 800000baseCR4_Full		),
+	PHY_SETTING( 800000, FULL, 800000baseKR4_Full		),
+	PHY_SETTING( 800000, FULL, 800000baseDR4_Full		),
+	PHY_SETTING( 800000, FULL, 800000baseDR4_2_Full		),
+	PHY_SETTING( 800000, FULL, 800000baseSR4_Full		),
+	PHY_SETTING( 800000, FULL, 800000baseVR4_Full		),
 	/* 400G */
 	PHY_SETTING( 400000, FULL, 400000baseCR8_Full		),
 	PHY_SETTING( 400000, FULL, 400000baseKR8_Full		),
@@ -180,6 +186,12 @@ static const struct phy_setting settings[] = {
 	PHY_SETTING( 400000, FULL, 400000baseLR4_ER4_FR4_Full	),
 	PHY_SETTING( 400000, FULL, 400000baseDR4_Full		),
 	PHY_SETTING( 400000, FULL, 400000baseSR4_Full		),
+	PHY_SETTING( 400000, FULL, 400000baseCR2_Full		),
+	PHY_SETTING( 400000, FULL, 400000baseKR2_Full		),
+	PHY_SETTING( 400000, FULL, 400000baseDR2_Full		),
+	PHY_SETTING( 400000, FULL, 400000baseDR2_2_Full		),
+	PHY_SETTING( 400000, FULL, 400000baseSR2_Full		),
+	PHY_SETTING( 400000, FULL, 400000baseVR2_Full		),
 	/* 200G */
 	PHY_SETTING( 200000, FULL, 200000baseCR4_Full		),
 	PHY_SETTING( 200000, FULL, 200000baseKR4_Full		),
@@ -191,6 +203,12 @@ static const struct phy_setting settings[] = {
 	PHY_SETTING( 200000, FULL, 200000baseLR2_ER2_FR2_Full	),
 	PHY_SETTING( 200000, FULL, 200000baseDR2_Full		),
 	PHY_SETTING( 200000, FULL, 200000baseSR2_Full		),
+	PHY_SETTING( 200000, FULL, 200000baseCR_Full		),
+	PHY_SETTING( 200000, FULL, 200000baseKR_Full		),
+	PHY_SETTING( 200000, FULL, 200000baseDR_Full		),
+	PHY_SETTING( 200000, FULL, 200000baseDR_2_Full		),
+	PHY_SETTING( 200000, FULL, 200000baseSR_Full		),
+	PHY_SETTING( 200000, FULL, 200000baseVR_Full		),
 	/* 100G */
 	PHY_SETTING( 100000, FULL, 100000baseCR4_Full		),
 	PHY_SETTING( 100000, FULL, 100000baseKR4_Full		),
diff --git a/drivers/net/phy/realtek/Kconfig b/drivers/net/phy/realtek/Kconfig
index 31935f147d87..b05c2a1e9024 100644
--- a/drivers/net/phy/realtek/Kconfig
+++ b/drivers/net/phy/realtek/Kconfig
@@ -4,8 +4,12 @@ config REALTEK_PHY
 	help
 	  Currently supports RTL821x/RTL822x and fast ethernet PHYs
 
+if REALTEK_PHY
+
 config REALTEK_PHY_HWMON
-	def_bool REALTEK_PHY && HWMON
-	depends on !(REALTEK_PHY=y && HWMON=m)
+	bool "HWMON support for Realtek PHYs"
+	depends on HWMON && !(REALTEK_PHY=y && HWMON=m)
 	help
 	  Optional hwmon support for the temperature sensor
+
+endif # REALTEK_PHY
diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c
index 572a933636b0..210fefac44d4 100644
--- a/drivers/net/phy/realtek/realtek_main.c
+++ b/drivers/net/phy/realtek/realtek_main.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/clk.h>
+#include <linux/string_choices.h>
 
 #include "realtek.h"
 
@@ -422,11 +423,11 @@ static int rtl8211f_config_init(struct phy_device *phydev)
 	} else if (ret) {
 		dev_dbg(dev,
 			"%s 2ns TX delay (and changing the value from pin-strapping RXD1 or the bootloader)\n",
-			val_txdly ? "Enabling" : "Disabling");
+			str_enable_disable(val_txdly));
 	} else {
 		dev_dbg(dev,
 			"2ns TX delay was already %s (by pin-strapping RXD1 or bootloader configuration)\n",
-			val_txdly ? "enabled" : "disabled");
+			str_enabled_disabled(val_txdly));
 	}
 
 	ret = phy_modify_paged_changed(phydev, 0xd08, 0x15, RTL8211F_RX_DELAY,
@@ -437,11 +438,11 @@ static int rtl8211f_config_init(struct phy_device *phydev)
 	} else if (ret) {
 		dev_dbg(dev,
 			"%s 2ns RX delay (and changing the value from pin-strapping RXD0 or the bootloader)\n",
-			val_rxdly ? "Enabling" : "Disabling");
+			str_enable_disable(val_rxdly));
 	} else {
 		dev_dbg(dev,
 			"2ns RX delay was already %s (by pin-strapping RXD0 or bootloader configuration)\n",
-			val_rxdly ? "enabled" : "disabled");
+			str_enabled_disabled(val_rxdly));
 	}
 
 	if (priv->has_phycr2) {
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 92516189e792..03175419bf28 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -227,9 +227,9 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 			be32_to_cpu(fdb->vni)))
 		goto nla_put_failure;
 
-	ci.ndm_used	 = jiffies_to_clock_t(now - fdb->used);
+	ci.ndm_used	 = jiffies_to_clock_t(now - READ_ONCE(fdb->used));
 	ci.ndm_confirmed = 0;
-	ci.ndm_updated	 = jiffies_to_clock_t(now - fdb->updated);
+	ci.ndm_updated	 = jiffies_to_clock_t(now - READ_ONCE(fdb->updated));
 	ci.ndm_refcnt	 = 0;
 
 	if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci))
@@ -434,8 +434,12 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan,
 	struct vxlan_fdb *f;
 
 	f = __vxlan_find_mac(vxlan, mac, vni);
-	if (f && f->used != jiffies)
-		f->used = jiffies;
+	if (f) {
+		unsigned long now = jiffies;
+
+		if (READ_ONCE(f->used) != now)
+			WRITE_ONCE(f->used, now);
+	}
 
 	return f;
 }
@@ -1009,12 +1013,10 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
 	    !(f->flags & NTF_VXLAN_ADDED_BY_USER)) {
 		if (f->state != state) {
 			f->state = state;
-			f->updated = jiffies;
 			notify = 1;
 		}
 		if (f->flags != fdb_flags) {
 			f->flags = fdb_flags;
-			f->updated = jiffies;
 			notify = 1;
 		}
 	}
@@ -1048,12 +1050,13 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
 	}
 
 	if (ndm_flags & NTF_USE)
-		f->used = jiffies;
+		WRITE_ONCE(f->updated, jiffies);
 
 	if (notify) {
 		if (rd == NULL)
 			rd = first_remote_rtnl(f);
 
+		WRITE_ONCE(f->updated, jiffies);
 		err = vxlan_fdb_notify(vxlan, f, rd, RTM_NEWNEIGH,
 				       swdev_notify, extack);
 		if (err)
@@ -1292,7 +1295,7 @@ int __vxlan_fdb_delete(struct vxlan_dev *vxlan,
 	struct vxlan_fdb *f;
 	int err = -ENOENT;
 
-	f = vxlan_find_mac(vxlan, addr, src_vni);
+	f = __vxlan_find_mac(vxlan, addr, src_vni);
 	if (!f)
 		return err;
 
@@ -1459,9 +1462,13 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev,
 		ifindex = src_ifindex;
 #endif
 
-	f = vxlan_find_mac(vxlan, src_mac, vni);
+	f = __vxlan_find_mac(vxlan, src_mac, vni);
 	if (likely(f)) {
 		struct vxlan_rdst *rdst = first_remote_rcu(f);
+		unsigned long now = jiffies;
+
+		if (READ_ONCE(f->updated) != now)
+			WRITE_ONCE(f->updated, now);
 
 		if (likely(vxlan_addr_equal(&rdst->remote_ip, src_ip) &&
 			   rdst->remote_ifindex == ifindex))
@@ -1481,7 +1488,6 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev,
 				    src_mac, &rdst->remote_ip.sa, &src_ip->sa);
 
 		rdst->remote_ip = *src_ip;
-		f->updated = jiffies;
 		vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true, NULL);
 	} else {
 		u32 hash_index = fdb_head_index(vxlan, src_mac, vni);
@@ -2852,7 +2858,7 @@ static void vxlan_cleanup(struct timer_list *t)
 			if (f->flags & NTF_EXT_LEARNED)
 				continue;
 
-			timeout = f->used + vxlan->cfg.age_interval * HZ;
+			timeout = READ_ONCE(f->updated) + vxlan->cfg.age_interval * HZ;
 			if (time_before_eq(timeout, jiffies)) {
 				netdev_dbg(vxlan->dev,
 					   "garbage collect %pM\n",
@@ -4768,7 +4774,7 @@ vxlan_fdb_offloaded_set(struct net_device *dev,
 
 	spin_lock_bh(&vxlan->hash_lock[hash_index]);
 
-	f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni);
+	f = __vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni);
 	if (!f)
 		goto out;
 
@@ -4824,7 +4830,7 @@ vxlan_fdb_external_learn_del(struct net_device *dev,
 	hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni);
 	spin_lock_bh(&vxlan->hash_lock[hash_index]);
 
-	f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni);
+	f = __vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni);
 	if (!f)
 		err = -ENOENT;
 	else if (f->flags & NTF_EXT_LEARNED)
diff --git a/drivers/s390/net/Kconfig b/drivers/s390/net/Kconfig
index c61e6427384c..9eb9e3c49f81 100644
--- a/drivers/s390/net/Kconfig
+++ b/drivers/s390/net/Kconfig
@@ -2,15 +2,6 @@
 menu "S/390 network device drivers"
 	depends on NETDEVICES && S390
 
-config LCS
-	def_tristate m
-	prompt "Lan Channel Station Interface"
-	depends on CCW && NETDEVICES && ETHERNET
-	help
-	  Select this option if you want to use LCS networking on IBM System z.
-	  To compile as a module, choose M. The module name is lcs.
-	  If you do not use LCS, choose N.
-
 config CTCM
 	def_tristate m
 	prompt "CTC and MPC SNA device support"
@@ -98,7 +89,7 @@ config QETH_OSX
 
 config CCWGROUP
 	tristate
-	default (LCS || CTCM || QETH || SMC)
+	default (CTCM || QETH || SMC)
 
 config ISM
 	tristate "Support for ISM vPCI Adapter"
diff --git a/drivers/s390/net/Makefile b/drivers/s390/net/Makefile
index bc55ec316adb..b5aaba290127 100644
--- a/drivers/s390/net/Makefile
+++ b/drivers/s390/net/Makefile
@@ -8,7 +8,6 @@ obj-$(CONFIG_CTCM) += ctcm.o fsm.o
 obj-$(CONFIG_NETIUCV) += netiucv.o fsm.o
 obj-$(CONFIG_SMSGIUCV) += smsgiucv.o
 obj-$(CONFIG_SMSGIUCV_EVENT) += smsgiucv_app.o
-obj-$(CONFIG_LCS) += lcs.o
 qeth-y += qeth_core_sys.o qeth_core_main.o qeth_core_mpc.o qeth_ethtool.o
 obj-$(CONFIG_QETH) += qeth.o
 qeth_l2-y += qeth_l2_main.o qeth_l2_sys.o
diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c
deleted file mode 100644
index 88db8378325a..000000000000
--- a/drivers/s390/net/lcs.c
+++ /dev/null
@@ -1,2385 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*
- *  Linux for S/390 LAN channel station device driver
- *
- *  Copyright IBM Corp. 1999, 2009
- *  Author(s): Original Code written by
- *			DJ Barrow <djbarrow@de.ibm.com,barrow_dj@yahoo.com>
- *	       Rewritten by
- *			Frank Pavlic <fpavlic@de.ibm.com> and
- *			Martin Schwidefsky <schwidefsky@de.ibm.com>
- */
-
-#define KMSG_COMPONENT		"lcs"
-#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
-
-#include <linux/module.h>
-#include <linux/if.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/inetdevice.h>
-#include <linux/in.h>
-#include <linux/igmp.h>
-#include <linux/delay.h>
-#include <linux/kthread.h>
-#include <linux/slab.h>
-#include <net/arp.h>
-#include <net/ip.h>
-
-#include <asm/debug.h>
-#include <asm/idals.h>
-#include <asm/timex.h>
-#include <linux/device.h>
-#include <asm/ccwgroup.h>
-
-#include "lcs.h"
-
-
-/*
- * initialization string for output
- */
-
-static char version[] __initdata = "LCS driver";
-
-/*
-  * the root device for lcs group devices
-  */
-static struct device *lcs_root_dev;
-
-/*
- * Some prototypes.
- */
-static void lcs_tasklet(unsigned long);
-static void lcs_start_kernel_thread(struct work_struct *);
-static void lcs_get_frames_cb(struct lcs_channel *, struct lcs_buffer *);
-#ifdef CONFIG_IP_MULTICAST
-static int lcs_send_delipm(struct lcs_card *, struct lcs_ipm_list *);
-#endif /* CONFIG_IP_MULTICAST */
-static int lcs_recovery(void *ptr);
-
-/*
- * Debug Facility Stuff
- */
-static char debug_buffer[255];
-static debug_info_t *lcs_dbf_setup;
-static debug_info_t *lcs_dbf_trace;
-
-/*
- *  LCS Debug Facility functions
- */
-static void
-lcs_unregister_debug_facility(void)
-{
-	debug_unregister(lcs_dbf_setup);
-	debug_unregister(lcs_dbf_trace);
-}
-
-static int
-lcs_register_debug_facility(void)
-{
-	lcs_dbf_setup = debug_register("lcs_setup", 2, 1, 8);
-	lcs_dbf_trace = debug_register("lcs_trace", 4, 1, 8);
-	if (lcs_dbf_setup == NULL || lcs_dbf_trace == NULL) {
-		pr_err("Not enough memory for debug facility.\n");
-		lcs_unregister_debug_facility();
-		return -ENOMEM;
-	}
-	debug_register_view(lcs_dbf_setup, &debug_hex_ascii_view);
-	debug_set_level(lcs_dbf_setup, 2);
-	debug_register_view(lcs_dbf_trace, &debug_hex_ascii_view);
-	debug_set_level(lcs_dbf_trace, 2);
-	return 0;
-}
-
-/*
- * Allocate io buffers.
- */
-static int
-lcs_alloc_channel(struct lcs_channel *channel)
-{
-	int cnt;
-
-	LCS_DBF_TEXT(2, setup, "ichalloc");
-	for (cnt = 0; cnt < LCS_NUM_BUFFS; cnt++) {
-		/* alloc memory fo iobuffer */
-		channel->iob[cnt].data =
-			kzalloc(LCS_IOBUFFERSIZE, GFP_DMA | GFP_KERNEL);
-		if (channel->iob[cnt].data == NULL)
-			break;
-		channel->iob[cnt].state = LCS_BUF_STATE_EMPTY;
-	}
-	if (cnt < LCS_NUM_BUFFS) {
-		/* Not all io buffers could be allocated. */
-		LCS_DBF_TEXT(2, setup, "echalloc");
-		while (cnt-- > 0)
-			kfree(channel->iob[cnt].data);
-		return -ENOMEM;
-	}
-	return 0;
-}
-
-/*
- * Free io buffers.
- */
-static void
-lcs_free_channel(struct lcs_channel *channel)
-{
-	int cnt;
-
-	LCS_DBF_TEXT(2, setup, "ichfree");
-	for (cnt = 0; cnt < LCS_NUM_BUFFS; cnt++) {
-		kfree(channel->iob[cnt].data);
-		channel->iob[cnt].data = NULL;
-	}
-}
-
-/*
- * Cleanup channel.
- */
-static void
-lcs_cleanup_channel(struct lcs_channel *channel)
-{
-	LCS_DBF_TEXT(3, setup, "cleanch");
-	/* Kill write channel tasklets. */
-	tasklet_kill(&channel->irq_tasklet);
-	/* Free channel buffers. */
-	lcs_free_channel(channel);
-}
-
-/*
- * LCS free memory for card and channels.
- */
-static void
-lcs_free_card(struct lcs_card *card)
-{
-	LCS_DBF_TEXT(2, setup, "remcard");
-	LCS_DBF_HEX(2, setup, &card, sizeof(void*));
-	kfree(card);
-}
-
-/*
- * LCS alloc memory for card and channels
- */
-static struct lcs_card *
-lcs_alloc_card(void)
-{
-	struct lcs_card *card;
-	int rc;
-
-	LCS_DBF_TEXT(2, setup, "alloclcs");
-
-	card = kzalloc(sizeof(struct lcs_card), GFP_KERNEL | GFP_DMA);
-	if (card == NULL)
-		return NULL;
-	card->lan_type = LCS_FRAME_TYPE_AUTO;
-	card->pkt_seq = 0;
-	card->lancmd_timeout = LCS_LANCMD_TIMEOUT_DEFAULT;
-	/* Allocate io buffers for the read channel. */
-	rc = lcs_alloc_channel(&card->read);
-	if (rc){
-		LCS_DBF_TEXT(2, setup, "iccwerr");
-		lcs_free_card(card);
-		return NULL;
-	}
-	/* Allocate io buffers for the write channel. */
-	rc = lcs_alloc_channel(&card->write);
-	if (rc) {
-		LCS_DBF_TEXT(2, setup, "iccwerr");
-		lcs_cleanup_channel(&card->read);
-		lcs_free_card(card);
-		return NULL;
-	}
-
-#ifdef CONFIG_IP_MULTICAST
-	INIT_LIST_HEAD(&card->ipm_list);
-#endif
-	LCS_DBF_HEX(2, setup, &card, sizeof(void*));
-	return card;
-}
-
-/*
- * Setup read channel.
- */
-static void
-lcs_setup_read_ccws(struct lcs_card *card)
-{
-	int cnt;
-
-	LCS_DBF_TEXT(2, setup, "ireadccw");
-	/* Setup read ccws. */
-	memset(card->read.ccws, 0, sizeof (struct ccw1) * (LCS_NUM_BUFFS + 1));
-	for (cnt = 0; cnt < LCS_NUM_BUFFS; cnt++) {
-		card->read.ccws[cnt].cmd_code = LCS_CCW_READ;
-		card->read.ccws[cnt].count = LCS_IOBUFFERSIZE;
-		card->read.ccws[cnt].flags =
-			CCW_FLAG_CC | CCW_FLAG_SLI | CCW_FLAG_PCI;
-		/*
-		 * Note: we have allocated the buffer with GFP_DMA, so
-		 * we do not need to do set_normalized_cda.
-		 */
-		card->read.ccws[cnt].cda =
-			virt_to_dma32(card->read.iob[cnt].data);
-		((struct lcs_header *)
-		 card->read.iob[cnt].data)->offset = LCS_ILLEGAL_OFFSET;
-		card->read.iob[cnt].callback = lcs_get_frames_cb;
-		card->read.iob[cnt].state = LCS_BUF_STATE_READY;
-		card->read.iob[cnt].count = LCS_IOBUFFERSIZE;
-	}
-	card->read.ccws[0].flags &= ~CCW_FLAG_PCI;
-	card->read.ccws[LCS_NUM_BUFFS - 1].flags &= ~CCW_FLAG_PCI;
-	card->read.ccws[LCS_NUM_BUFFS - 1].flags |= CCW_FLAG_SUSPEND;
-	/* Last ccw is a tic (transfer in channel). */
-	card->read.ccws[LCS_NUM_BUFFS].cmd_code = LCS_CCW_TRANSFER;
-	card->read.ccws[LCS_NUM_BUFFS].cda = virt_to_dma32(card->read.ccws);
-	/* Setg initial state of the read channel. */
-	card->read.state = LCS_CH_STATE_INIT;
-
-	card->read.io_idx = 0;
-	card->read.buf_idx = 0;
-}
-
-static void
-lcs_setup_read(struct lcs_card *card)
-{
-	LCS_DBF_TEXT(3, setup, "initread");
-
-	lcs_setup_read_ccws(card);
-	/* Initialize read channel tasklet. */
-	card->read.irq_tasklet.data = (unsigned long) &card->read;
-	card->read.irq_tasklet.func = lcs_tasklet;
-	/* Initialize waitqueue. */
-	init_waitqueue_head(&card->read.wait_q);
-}
-
-/*
- * Setup write channel.
- */
-static void
-lcs_setup_write_ccws(struct lcs_card *card)
-{
-	int cnt;
-
-	LCS_DBF_TEXT(3, setup, "iwritccw");
-	/* Setup write ccws. */
-	memset(card->write.ccws, 0, sizeof(struct ccw1) * (LCS_NUM_BUFFS + 1));
-	for (cnt = 0; cnt < LCS_NUM_BUFFS; cnt++) {
-		card->write.ccws[cnt].cmd_code = LCS_CCW_WRITE;
-		card->write.ccws[cnt].count = 0;
-		card->write.ccws[cnt].flags =
-			CCW_FLAG_SUSPEND | CCW_FLAG_CC | CCW_FLAG_SLI;
-		/*
-		 * Note: we have allocated the buffer with GFP_DMA, so
-		 * we do not need to do set_normalized_cda.
-		 */
-		card->write.ccws[cnt].cda =
-			virt_to_dma32(card->write.iob[cnt].data);
-	}
-	/* Last ccw is a tic (transfer in channel). */
-	card->write.ccws[LCS_NUM_BUFFS].cmd_code = LCS_CCW_TRANSFER;
-	card->write.ccws[LCS_NUM_BUFFS].cda = virt_to_dma32(card->write.ccws);
-	/* Set initial state of the write channel. */
-	card->read.state = LCS_CH_STATE_INIT;
-
-	card->write.io_idx = 0;
-	card->write.buf_idx = 0;
-}
-
-static void
-lcs_setup_write(struct lcs_card *card)
-{
-	LCS_DBF_TEXT(3, setup, "initwrit");
-
-	lcs_setup_write_ccws(card);
-	/* Initialize write channel tasklet. */
-	card->write.irq_tasklet.data = (unsigned long) &card->write;
-	card->write.irq_tasklet.func = lcs_tasklet;
-	/* Initialize waitqueue. */
-	init_waitqueue_head(&card->write.wait_q);
-}
-
-static void
-lcs_set_allowed_threads(struct lcs_card *card, unsigned long threads)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&card->mask_lock, flags);
-	card->thread_allowed_mask = threads;
-	spin_unlock_irqrestore(&card->mask_lock, flags);
-	wake_up(&card->wait_q);
-}
-static int lcs_threads_running(struct lcs_card *card, unsigned long threads)
-{
-        unsigned long flags;
-        int rc = 0;
-
-	spin_lock_irqsave(&card->mask_lock, flags);
-        rc = (card->thread_running_mask & threads);
-	spin_unlock_irqrestore(&card->mask_lock, flags);
-        return rc;
-}
-
-static int
-lcs_wait_for_threads(struct lcs_card *card, unsigned long threads)
-{
-        return wait_event_interruptible(card->wait_q,
-                        lcs_threads_running(card, threads) == 0);
-}
-
-static int lcs_set_thread_start_bit(struct lcs_card *card, unsigned long thread)
-{
-        unsigned long flags;
-
-	spin_lock_irqsave(&card->mask_lock, flags);
-        if ( !(card->thread_allowed_mask & thread) ||
-              (card->thread_start_mask & thread) ) {
-                spin_unlock_irqrestore(&card->mask_lock, flags);
-                return -EPERM;
-        }
-        card->thread_start_mask |= thread;
-	spin_unlock_irqrestore(&card->mask_lock, flags);
-        return 0;
-}
-
-static void
-lcs_clear_thread_running_bit(struct lcs_card *card, unsigned long thread)
-{
-        unsigned long flags;
-
-	spin_lock_irqsave(&card->mask_lock, flags);
-        card->thread_running_mask &= ~thread;
-	spin_unlock_irqrestore(&card->mask_lock, flags);
-        wake_up(&card->wait_q);
-}
-
-static int __lcs_do_run_thread(struct lcs_card *card, unsigned long thread)
-{
-        unsigned long flags;
-        int rc = 0;
-
-	spin_lock_irqsave(&card->mask_lock, flags);
-        if (card->thread_start_mask & thread){
-                if ((card->thread_allowed_mask & thread) &&
-                    !(card->thread_running_mask & thread)){
-                        rc = 1;
-                        card->thread_start_mask &= ~thread;
-                        card->thread_running_mask |= thread;
-                } else
-                        rc = -EPERM;
-        }
-	spin_unlock_irqrestore(&card->mask_lock, flags);
-        return rc;
-}
-
-static int
-lcs_do_run_thread(struct lcs_card *card, unsigned long thread)
-{
-        int rc = 0;
-        wait_event(card->wait_q,
-                   (rc = __lcs_do_run_thread(card, thread)) >= 0);
-        return rc;
-}
-
-static int
-lcs_do_start_thread(struct lcs_card *card, unsigned long thread)
-{
-        unsigned long flags;
-        int rc = 0;
-
-	spin_lock_irqsave(&card->mask_lock, flags);
-        LCS_DBF_TEXT_(4, trace, "  %02x%02x%02x",
-                        (u8) card->thread_start_mask,
-                        (u8) card->thread_allowed_mask,
-                        (u8) card->thread_running_mask);
-        rc = (card->thread_start_mask & thread);
-	spin_unlock_irqrestore(&card->mask_lock, flags);
-        return rc;
-}
-
-/*
- * Initialize channels,card and state machines.
- */
-static void
-lcs_setup_card(struct lcs_card *card)
-{
-	LCS_DBF_TEXT(2, setup, "initcard");
-	LCS_DBF_HEX(2, setup, &card, sizeof(void*));
-
-	lcs_setup_read(card);
-	lcs_setup_write(card);
-	/* Set cards initial state. */
-	card->state = DEV_STATE_DOWN;
-	card->tx_buffer = NULL;
-	card->tx_emitted = 0;
-
-	init_waitqueue_head(&card->wait_q);
-	spin_lock_init(&card->lock);
-	spin_lock_init(&card->ipm_lock);
-	spin_lock_init(&card->mask_lock);
-#ifdef CONFIG_IP_MULTICAST
-	INIT_LIST_HEAD(&card->ipm_list);
-#endif
-	INIT_LIST_HEAD(&card->lancmd_waiters);
-}
-
-static void lcs_clear_multicast_list(struct lcs_card *card)
-{
-#ifdef	CONFIG_IP_MULTICAST
-	struct lcs_ipm_list *ipm;
-	unsigned long flags;
-
-	/* Free multicast list. */
-	LCS_DBF_TEXT(3, setup, "clmclist");
-	spin_lock_irqsave(&card->ipm_lock, flags);
-	while (!list_empty(&card->ipm_list)){
-		ipm = list_entry(card->ipm_list.next,
-				 struct lcs_ipm_list, list);
-		list_del(&ipm->list);
-		if (ipm->ipm_state != LCS_IPM_STATE_SET_REQUIRED){
-			spin_unlock_irqrestore(&card->ipm_lock, flags);
-			lcs_send_delipm(card, ipm);
-			spin_lock_irqsave(&card->ipm_lock, flags);
-		}
-		kfree(ipm);
-	}
-	spin_unlock_irqrestore(&card->ipm_lock, flags);
-#endif
-}
-
-/*
- * Cleanup channels,card and state machines.
- */
-static void
-lcs_cleanup_card(struct lcs_card *card)
-{
-
-	LCS_DBF_TEXT(3, setup, "cleancrd");
-	LCS_DBF_HEX(2,setup,&card,sizeof(void*));
-
-	if (card->dev != NULL)
-		free_netdev(card->dev);
-	/* Cleanup channels. */
-	lcs_cleanup_channel(&card->write);
-	lcs_cleanup_channel(&card->read);
-}
-
-/*
- * Start channel.
- */
-static int
-lcs_start_channel(struct lcs_channel *channel)
-{
-	unsigned long flags;
-	int rc;
-
-	LCS_DBF_TEXT_(4, trace,"ssch%s", dev_name(&channel->ccwdev->dev));
-	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	rc = ccw_device_start(channel->ccwdev,
-			      channel->ccws + channel->io_idx, 0, 0,
-			      DOIO_DENY_PREFETCH | DOIO_ALLOW_SUSPEND);
-	if (rc == 0)
-		channel->state = LCS_CH_STATE_RUNNING;
-	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
-	if (rc) {
-		LCS_DBF_TEXT_(4,trace,"essh%s",
-			      dev_name(&channel->ccwdev->dev));
-		dev_err(&channel->ccwdev->dev,
-			"Starting an LCS device resulted in an error,"
-			" rc=%d!\n", rc);
-	}
-	return rc;
-}
-
-static int
-lcs_clear_channel(struct lcs_channel *channel)
-{
-	unsigned long flags;
-	int rc;
-
-	LCS_DBF_TEXT(4,trace,"clearch");
-	LCS_DBF_TEXT_(4, trace, "%s", dev_name(&channel->ccwdev->dev));
-	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	rc = ccw_device_clear(channel->ccwdev, 0);
-	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
-	if (rc) {
-		LCS_DBF_TEXT_(4, trace, "ecsc%s",
-			      dev_name(&channel->ccwdev->dev));
-		return rc;
-	}
-	wait_event(channel->wait_q, (channel->state == LCS_CH_STATE_CLEARED));
-	channel->state = LCS_CH_STATE_STOPPED;
-	return rc;
-}
-
-
-/*
- * Stop channel.
- */
-static int
-lcs_stop_channel(struct lcs_channel *channel)
-{
-	unsigned long flags;
-	int rc;
-
-	if (channel->state == LCS_CH_STATE_STOPPED)
-		return 0;
-	LCS_DBF_TEXT(4,trace,"haltsch");
-	LCS_DBF_TEXT_(4, trace, "%s", dev_name(&channel->ccwdev->dev));
-	channel->state = LCS_CH_STATE_INIT;
-	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	rc = ccw_device_halt(channel->ccwdev, 0);
-	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
-	if (rc) {
-		LCS_DBF_TEXT_(4, trace, "ehsc%s",
-			      dev_name(&channel->ccwdev->dev));
-		return rc;
-	}
-	/* Asynchronous halt initialted. Wait for its completion. */
-	wait_event(channel->wait_q, (channel->state == LCS_CH_STATE_HALTED));
-	lcs_clear_channel(channel);
-	return 0;
-}
-
-/*
- * start read and write channel
- */
-static int
-lcs_start_channels(struct lcs_card *card)
-{
-	int rc;
-
-	LCS_DBF_TEXT(2, trace, "chstart");
-	/* start read channel */
-	rc = lcs_start_channel(&card->read);
-	if (rc)
-		return rc;
-	/* start write channel */
-	rc = lcs_start_channel(&card->write);
-	if (rc)
-		lcs_stop_channel(&card->read);
-	return rc;
-}
-
-/*
- * stop read and write channel
- */
-static int
-lcs_stop_channels(struct lcs_card *card)
-{
-	LCS_DBF_TEXT(2, trace, "chhalt");
-	lcs_stop_channel(&card->read);
-	lcs_stop_channel(&card->write);
-	return 0;
-}
-
-/*
- * Get empty buffer.
- */
-static struct lcs_buffer *
-__lcs_get_buffer(struct lcs_channel *channel)
-{
-	int index;
-
-	LCS_DBF_TEXT(5, trace, "_getbuff");
-	index = channel->io_idx;
-	do {
-		if (channel->iob[index].state == LCS_BUF_STATE_EMPTY) {
-			channel->iob[index].state = LCS_BUF_STATE_LOCKED;
-			return channel->iob + index;
-		}
-		index = (index + 1) & (LCS_NUM_BUFFS - 1);
-	} while (index != channel->io_idx);
-	return NULL;
-}
-
-static struct lcs_buffer *
-lcs_get_buffer(struct lcs_channel *channel)
-{
-	struct lcs_buffer *buffer;
-	unsigned long flags;
-
-	LCS_DBF_TEXT(5, trace, "getbuff");
-	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	buffer = __lcs_get_buffer(channel);
-	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
-	return buffer;
-}
-
-/*
- * Resume channel program if the channel is suspended.
- */
-static int
-__lcs_resume_channel(struct lcs_channel *channel)
-{
-	int rc;
-
-	if (channel->state != LCS_CH_STATE_SUSPENDED)
-		return 0;
-	if (channel->ccws[channel->io_idx].flags & CCW_FLAG_SUSPEND)
-		return 0;
-	LCS_DBF_TEXT_(5, trace, "rsch%s", dev_name(&channel->ccwdev->dev));
-	rc = ccw_device_resume(channel->ccwdev);
-	if (rc) {
-		LCS_DBF_TEXT_(4, trace, "ersc%s",
-			      dev_name(&channel->ccwdev->dev));
-		dev_err(&channel->ccwdev->dev,
-			"Sending data from the LCS device to the LAN failed"
-			" with rc=%d\n",rc);
-	} else
-		channel->state = LCS_CH_STATE_RUNNING;
-	return rc;
-
-}
-
-/*
- * Make a buffer ready for processing.
- */
-static void __lcs_ready_buffer_bits(struct lcs_channel *channel, int index)
-{
-	int prev, next;
-
-	LCS_DBF_TEXT(5, trace, "rdybits");
-	prev = (index - 1) & (LCS_NUM_BUFFS - 1);
-	next = (index + 1) & (LCS_NUM_BUFFS - 1);
-	/* Check if we may clear the suspend bit of this buffer. */
-	if (channel->ccws[next].flags & CCW_FLAG_SUSPEND) {
-		/* Check if we have to set the PCI bit. */
-		if (!(channel->ccws[prev].flags & CCW_FLAG_SUSPEND))
-			/* Suspend bit of the previous buffer is not set. */
-			channel->ccws[index].flags |= CCW_FLAG_PCI;
-		/* Suspend bit of the next buffer is set. */
-		channel->ccws[index].flags &= ~CCW_FLAG_SUSPEND;
-	}
-}
-
-static int
-lcs_ready_buffer(struct lcs_channel *channel, struct lcs_buffer *buffer)
-{
-	unsigned long flags;
-	int index, rc;
-
-	LCS_DBF_TEXT(5, trace, "rdybuff");
-	BUG_ON(buffer->state != LCS_BUF_STATE_LOCKED &&
-	       buffer->state != LCS_BUF_STATE_PROCESSED);
-	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	buffer->state = LCS_BUF_STATE_READY;
-	index = buffer - channel->iob;
-	/* Set length. */
-	channel->ccws[index].count = buffer->count;
-	/* Check relevant PCI/suspend bits. */
-	__lcs_ready_buffer_bits(channel, index);
-	rc = __lcs_resume_channel(channel);
-	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
-	return rc;
-}
-
-/*
- * Mark the buffer as processed. Take care of the suspend bit
- * of the previous buffer. This function is called from
- * interrupt context, so the lock must not be taken.
- */
-static int
-__lcs_processed_buffer(struct lcs_channel *channel, struct lcs_buffer *buffer)
-{
-	int index, prev, next;
-
-	LCS_DBF_TEXT(5, trace, "prcsbuff");
-	BUG_ON(buffer->state != LCS_BUF_STATE_READY);
-	buffer->state = LCS_BUF_STATE_PROCESSED;
-	index = buffer - channel->iob;
-	prev = (index - 1) & (LCS_NUM_BUFFS - 1);
-	next = (index + 1) & (LCS_NUM_BUFFS - 1);
-	/* Set the suspend bit and clear the PCI bit of this buffer. */
-	channel->ccws[index].flags |= CCW_FLAG_SUSPEND;
-	channel->ccws[index].flags &= ~CCW_FLAG_PCI;
-	/* Check the suspend bit of the previous buffer. */
-	if (channel->iob[prev].state == LCS_BUF_STATE_READY) {
-		/*
-		 * Previous buffer is in state ready. It might have
-		 * happened in lcs_ready_buffer that the suspend bit
-		 * has not been cleared to avoid an endless loop.
-		 * Do it now.
-		 */
-		__lcs_ready_buffer_bits(channel, prev);
-	}
-	/* Clear PCI bit of next buffer. */
-	channel->ccws[next].flags &= ~CCW_FLAG_PCI;
-	return __lcs_resume_channel(channel);
-}
-
-/*
- * Put a processed buffer back to state empty.
- */
-static void
-lcs_release_buffer(struct lcs_channel *channel, struct lcs_buffer *buffer)
-{
-	unsigned long flags;
-
-	LCS_DBF_TEXT(5, trace, "relbuff");
-	BUG_ON(buffer->state != LCS_BUF_STATE_LOCKED &&
-	       buffer->state != LCS_BUF_STATE_PROCESSED);
-	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	buffer->state = LCS_BUF_STATE_EMPTY;
-	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
-}
-
-/*
- * Get buffer for a lan command.
- */
-static struct lcs_buffer *
-lcs_get_lancmd(struct lcs_card *card, int count)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-
-	LCS_DBF_TEXT(4, trace, "getlncmd");
-	/* Get buffer and wait if none is available. */
-	wait_event(card->write.wait_q,
-		   ((buffer = lcs_get_buffer(&card->write)) != NULL));
-	count += sizeof(struct lcs_header);
-	*(__u16 *)(buffer->data + count) = 0;
-	buffer->count = count + sizeof(__u16);
-	buffer->callback = lcs_release_buffer;
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->offset = count;
-	cmd->type = LCS_FRAME_TYPE_CONTROL;
-	cmd->slot = 0;
-	return buffer;
-}
-
-
-static void
-lcs_get_reply(struct lcs_reply *reply)
-{
-	refcount_inc(&reply->refcnt);
-}
-
-static void
-lcs_put_reply(struct lcs_reply *reply)
-{
-	if (refcount_dec_and_test(&reply->refcnt))
-		kfree(reply);
-}
-
-static struct lcs_reply *
-lcs_alloc_reply(struct lcs_cmd *cmd)
-{
-	struct lcs_reply *reply;
-
-	LCS_DBF_TEXT(4, trace, "getreply");
-
-	reply = kzalloc(sizeof(struct lcs_reply), GFP_ATOMIC);
-	if (!reply)
-		return NULL;
-	refcount_set(&reply->refcnt, 1);
-	reply->sequence_no = cmd->sequence_no;
-	reply->received = 0;
-	reply->rc = 0;
-	init_waitqueue_head(&reply->wait_q);
-
-	return reply;
-}
-
-/*
- * Notifier function for lancmd replies. Called from read irq.
- */
-static void
-lcs_notify_lancmd_waiters(struct lcs_card *card, struct lcs_cmd *cmd)
-{
-	struct list_head *l, *n;
-	struct lcs_reply *reply;
-
-	LCS_DBF_TEXT(4, trace, "notiwait");
-	spin_lock(&card->lock);
-	list_for_each_safe(l, n, &card->lancmd_waiters) {
-		reply = list_entry(l, struct lcs_reply, list);
-		if (reply->sequence_no == cmd->sequence_no) {
-			lcs_get_reply(reply);
-			list_del_init(&reply->list);
-			if (reply->callback != NULL)
-				reply->callback(card, cmd);
-			reply->received = 1;
-			reply->rc = cmd->return_code;
-			wake_up(&reply->wait_q);
-			lcs_put_reply(reply);
-			break;
-		}
-	}
-	spin_unlock(&card->lock);
-}
-
-/*
- * Emit buffer of a lan command.
- */
-static void
-lcs_lancmd_timeout(struct timer_list *t)
-{
-	struct lcs_reply *reply = from_timer(reply, t, timer);
-	struct lcs_reply *list_reply, *r;
-	unsigned long flags;
-
-	LCS_DBF_TEXT(4, trace, "timeout");
-	spin_lock_irqsave(&reply->card->lock, flags);
-	list_for_each_entry_safe(list_reply, r,
-				 &reply->card->lancmd_waiters,list) {
-		if (reply == list_reply) {
-			lcs_get_reply(reply);
-			list_del_init(&reply->list);
-			spin_unlock_irqrestore(&reply->card->lock, flags);
-			reply->received = 1;
-			reply->rc = -ETIME;
-			wake_up(&reply->wait_q);
-			lcs_put_reply(reply);
-			return;
-		}
-	}
-	spin_unlock_irqrestore(&reply->card->lock, flags);
-}
-
-static int
-lcs_send_lancmd(struct lcs_card *card, struct lcs_buffer *buffer,
-		void (*reply_callback)(struct lcs_card *, struct lcs_cmd *))
-{
-	struct lcs_reply *reply;
-	struct lcs_cmd *cmd;
-	unsigned long flags;
-	int rc;
-
-	LCS_DBF_TEXT(4, trace, "sendcmd");
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->return_code = 0;
-	cmd->sequence_no = card->sequence_no++;
-	reply = lcs_alloc_reply(cmd);
-	if (!reply)
-		return -ENOMEM;
-	reply->callback = reply_callback;
-	reply->card = card;
-	spin_lock_irqsave(&card->lock, flags);
-	list_add_tail(&reply->list, &card->lancmd_waiters);
-	spin_unlock_irqrestore(&card->lock, flags);
-
-	buffer->callback = lcs_release_buffer;
-	rc = lcs_ready_buffer(&card->write, buffer);
-	if (rc)
-		return rc;
-	timer_setup(&reply->timer, lcs_lancmd_timeout, 0);
-	mod_timer(&reply->timer, jiffies + HZ * card->lancmd_timeout);
-	wait_event(reply->wait_q, reply->received);
-	del_timer_sync(&reply->timer);
-	LCS_DBF_TEXT_(4, trace, "rc:%d",reply->rc);
-	rc = reply->rc;
-	lcs_put_reply(reply);
-	return rc ? -EIO : 0;
-}
-
-/*
- * LCS startup command
- */
-static int
-lcs_send_startup(struct lcs_card *card, __u8 initiator)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-
-	LCS_DBF_TEXT(2, trace, "startup");
-	buffer = lcs_get_lancmd(card, LCS_STD_CMD_SIZE);
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->cmd_code = LCS_CMD_STARTUP;
-	cmd->initiator = initiator;
-	cmd->cmd.lcs_startup.buff_size = LCS_IOBUFFERSIZE;
-	return lcs_send_lancmd(card, buffer, NULL);
-}
-
-/*
- * LCS shutdown command
- */
-static int
-lcs_send_shutdown(struct lcs_card *card)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-
-	LCS_DBF_TEXT(2, trace, "shutdown");
-	buffer = lcs_get_lancmd(card, LCS_STD_CMD_SIZE);
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->cmd_code = LCS_CMD_SHUTDOWN;
-	cmd->initiator = LCS_INITIATOR_TCPIP;
-	return lcs_send_lancmd(card, buffer, NULL);
-}
-
-/*
- * LCS lanstat command
- */
-static void
-__lcs_lanstat_cb(struct lcs_card *card, struct lcs_cmd *cmd)
-{
-	LCS_DBF_TEXT(2, trace, "statcb");
-	memcpy(card->mac, cmd->cmd.lcs_lanstat_cmd.mac_addr, LCS_MAC_LENGTH);
-}
-
-static int
-lcs_send_lanstat(struct lcs_card *card)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-
-	LCS_DBF_TEXT(2,trace, "cmdstat");
-	buffer = lcs_get_lancmd(card, LCS_STD_CMD_SIZE);
-	cmd = (struct lcs_cmd *) buffer->data;
-	/* Setup lanstat command. */
-	cmd->cmd_code = LCS_CMD_LANSTAT;
-	cmd->initiator = LCS_INITIATOR_TCPIP;
-	cmd->cmd.lcs_std_cmd.lan_type = card->lan_type;
-	cmd->cmd.lcs_std_cmd.portno = card->portno;
-	return lcs_send_lancmd(card, buffer, __lcs_lanstat_cb);
-}
-
-/*
- * send stoplan command
- */
-static int
-lcs_send_stoplan(struct lcs_card *card, __u8 initiator)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-
-	LCS_DBF_TEXT(2, trace, "cmdstpln");
-	buffer = lcs_get_lancmd(card, LCS_STD_CMD_SIZE);
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->cmd_code = LCS_CMD_STOPLAN;
-	cmd->initiator = initiator;
-	cmd->cmd.lcs_std_cmd.lan_type = card->lan_type;
-	cmd->cmd.lcs_std_cmd.portno = card->portno;
-	return lcs_send_lancmd(card, buffer, NULL);
-}
-
-/*
- * send startlan command
- */
-static void
-__lcs_send_startlan_cb(struct lcs_card *card, struct lcs_cmd *cmd)
-{
-	LCS_DBF_TEXT(2, trace, "srtlancb");
-	card->lan_type = cmd->cmd.lcs_std_cmd.lan_type;
-	card->portno = cmd->cmd.lcs_std_cmd.portno;
-}
-
-static int
-lcs_send_startlan(struct lcs_card *card, __u8 initiator)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-
-	LCS_DBF_TEXT(2, trace, "cmdstaln");
-	buffer = lcs_get_lancmd(card, LCS_STD_CMD_SIZE);
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->cmd_code = LCS_CMD_STARTLAN;
-	cmd->initiator = initiator;
-	cmd->cmd.lcs_std_cmd.lan_type = card->lan_type;
-	cmd->cmd.lcs_std_cmd.portno = card->portno;
-	return lcs_send_lancmd(card, buffer, __lcs_send_startlan_cb);
-}
-
-#ifdef CONFIG_IP_MULTICAST
-/*
- * send setipm command (Multicast)
- */
-static int
-lcs_send_setipm(struct lcs_card *card,struct lcs_ipm_list *ipm_list)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-
-	LCS_DBF_TEXT(2, trace, "cmdsetim");
-	buffer = lcs_get_lancmd(card, LCS_MULTICAST_CMD_SIZE);
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->cmd_code = LCS_CMD_SETIPM;
-	cmd->initiator = LCS_INITIATOR_TCPIP;
-	cmd->cmd.lcs_qipassist.lan_type = card->lan_type;
-	cmd->cmd.lcs_qipassist.portno = card->portno;
-	cmd->cmd.lcs_qipassist.version = 4;
-	cmd->cmd.lcs_qipassist.num_ip_pairs = 1;
-	memcpy(cmd->cmd.lcs_qipassist.lcs_ipass_ctlmsg.ip_mac_pair,
-	       &ipm_list->ipm, sizeof (struct lcs_ip_mac_pair));
-	LCS_DBF_TEXT_(2, trace, "%x",ipm_list->ipm.ip_addr);
-	return lcs_send_lancmd(card, buffer, NULL);
-}
-
-/*
- * send delipm command (Multicast)
- */
-static int
-lcs_send_delipm(struct lcs_card *card,struct lcs_ipm_list *ipm_list)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-
-	LCS_DBF_TEXT(2, trace, "cmddelim");
-	buffer = lcs_get_lancmd(card, LCS_MULTICAST_CMD_SIZE);
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->cmd_code = LCS_CMD_DELIPM;
-	cmd->initiator = LCS_INITIATOR_TCPIP;
-	cmd->cmd.lcs_qipassist.lan_type = card->lan_type;
-	cmd->cmd.lcs_qipassist.portno = card->portno;
-	cmd->cmd.lcs_qipassist.version = 4;
-	cmd->cmd.lcs_qipassist.num_ip_pairs = 1;
-	memcpy(cmd->cmd.lcs_qipassist.lcs_ipass_ctlmsg.ip_mac_pair,
-	       &ipm_list->ipm, sizeof (struct lcs_ip_mac_pair));
-	LCS_DBF_TEXT_(2, trace, "%x",ipm_list->ipm.ip_addr);
-	return lcs_send_lancmd(card, buffer, NULL);
-}
-
-/*
- * check if multicast is supported by LCS
- */
-static void
-__lcs_check_multicast_cb(struct lcs_card *card, struct lcs_cmd *cmd)
-{
-	LCS_DBF_TEXT(2, trace, "chkmccb");
-	card->ip_assists_supported =
-		cmd->cmd.lcs_qipassist.ip_assists_supported;
-	card->ip_assists_enabled =
-		cmd->cmd.lcs_qipassist.ip_assists_enabled;
-}
-
-static int
-lcs_check_multicast_support(struct lcs_card *card)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-	int rc;
-
-	LCS_DBF_TEXT(2, trace, "cmdqipa");
-	/* Send query ipassist. */
-	buffer = lcs_get_lancmd(card, LCS_STD_CMD_SIZE);
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->cmd_code = LCS_CMD_QIPASSIST;
-	cmd->initiator = LCS_INITIATOR_TCPIP;
-	cmd->cmd.lcs_qipassist.lan_type = card->lan_type;
-	cmd->cmd.lcs_qipassist.portno = card->portno;
-	cmd->cmd.lcs_qipassist.version = 4;
-	cmd->cmd.lcs_qipassist.num_ip_pairs = 1;
-	rc = lcs_send_lancmd(card, buffer, __lcs_check_multicast_cb);
-	if (rc != 0) {
-		pr_err("Query IPAssist failed. Assuming unsupported!\n");
-		return -EOPNOTSUPP;
-	}
-	if (card->ip_assists_supported & LCS_IPASS_MULTICAST_SUPPORT)
-		return 0;
-	return -EOPNOTSUPP;
-}
-
-/*
- * set or del multicast address on LCS card
- */
-static void
-lcs_fix_multicast_list(struct lcs_card *card)
-{
-	struct list_head failed_list;
-	struct lcs_ipm_list *ipm, *tmp;
-	unsigned long flags;
-	int rc;
-
-	LCS_DBF_TEXT(4,trace, "fixipm");
-	INIT_LIST_HEAD(&failed_list);
-	spin_lock_irqsave(&card->ipm_lock, flags);
-list_modified:
-	list_for_each_entry_safe(ipm, tmp, &card->ipm_list, list){
-		switch (ipm->ipm_state) {
-		case LCS_IPM_STATE_SET_REQUIRED:
-			/* del from ipm_list so no one else can tamper with
-			 * this entry */
-			list_del_init(&ipm->list);
-			spin_unlock_irqrestore(&card->ipm_lock, flags);
-			rc = lcs_send_setipm(card, ipm);
-			spin_lock_irqsave(&card->ipm_lock, flags);
-			if (rc) {
-				pr_info("Adding multicast address failed."
-					" Table possibly full!\n");
-				/* store ipm in failed list -> will be added
-				 * to ipm_list again, so a retry will be done
-				 * during the next call of this function */
-				list_add_tail(&ipm->list, &failed_list);
-			} else {
-				ipm->ipm_state = LCS_IPM_STATE_ON_CARD;
-				/* re-insert into ipm_list */
-				list_add_tail(&ipm->list, &card->ipm_list);
-			}
-			goto list_modified;
-		case LCS_IPM_STATE_DEL_REQUIRED:
-			list_del(&ipm->list);
-			spin_unlock_irqrestore(&card->ipm_lock, flags);
-			lcs_send_delipm(card, ipm);
-			spin_lock_irqsave(&card->ipm_lock, flags);
-			kfree(ipm);
-			goto list_modified;
-		case LCS_IPM_STATE_ON_CARD:
-			break;
-		}
-	}
-	/* re-insert all entries from the failed_list into ipm_list */
-	list_for_each_entry_safe(ipm, tmp, &failed_list, list)
-		list_move_tail(&ipm->list, &card->ipm_list);
-
-	spin_unlock_irqrestore(&card->ipm_lock, flags);
-}
-
-/*
- * get mac address for the relevant Multicast address
- */
-static void
-lcs_get_mac_for_ipm(__be32 ipm, char *mac, struct net_device *dev)
-{
-	LCS_DBF_TEXT(4,trace, "getmac");
-	ip_eth_mc_map(ipm, mac);
-}
-
-/*
- * function called by net device to handle multicast address relevant things
- */
-static void lcs_remove_mc_addresses(struct lcs_card *card,
-				    struct in_device *in4_dev)
-{
-	struct ip_mc_list *im4;
-	struct list_head *l;
-	struct lcs_ipm_list *ipm;
-	unsigned long flags;
-	char buf[MAX_ADDR_LEN];
-
-	LCS_DBF_TEXT(4, trace, "remmclst");
-	spin_lock_irqsave(&card->ipm_lock, flags);
-	list_for_each(l, &card->ipm_list) {
-		ipm = list_entry(l, struct lcs_ipm_list, list);
-		for (im4 = rcu_dereference(in4_dev->mc_list);
-		     im4 != NULL; im4 = rcu_dereference(im4->next_rcu)) {
-			lcs_get_mac_for_ipm(im4->multiaddr, buf, card->dev);
-			if ( (ipm->ipm.ip_addr == im4->multiaddr) &&
-			     (memcmp(buf, &ipm->ipm.mac_addr,
-				     LCS_MAC_LENGTH) == 0) )
-				break;
-		}
-		if (im4 == NULL)
-			ipm->ipm_state = LCS_IPM_STATE_DEL_REQUIRED;
-	}
-	spin_unlock_irqrestore(&card->ipm_lock, flags);
-}
-
-static struct lcs_ipm_list *lcs_check_addr_entry(struct lcs_card *card,
-						 struct ip_mc_list *im4,
-						 char *buf)
-{
-	struct lcs_ipm_list *tmp, *ipm = NULL;
-	struct list_head *l;
-	unsigned long flags;
-
-	LCS_DBF_TEXT(4, trace, "chkmcent");
-	spin_lock_irqsave(&card->ipm_lock, flags);
-	list_for_each(l, &card->ipm_list) {
-		tmp = list_entry(l, struct lcs_ipm_list, list);
-		if ( (tmp->ipm.ip_addr == im4->multiaddr) &&
-		     (memcmp(buf, &tmp->ipm.mac_addr,
-			     LCS_MAC_LENGTH) == 0) ) {
-			ipm = tmp;
-			break;
-		}
-	}
-	spin_unlock_irqrestore(&card->ipm_lock, flags);
-	return ipm;
-}
-
-static void lcs_set_mc_addresses(struct lcs_card *card,
-				 struct in_device *in4_dev)
-{
-
-	struct ip_mc_list *im4;
-	struct lcs_ipm_list *ipm;
-	char buf[MAX_ADDR_LEN];
-	unsigned long flags;
-
-	LCS_DBF_TEXT(4, trace, "setmclst");
-	for (im4 = rcu_dereference(in4_dev->mc_list); im4 != NULL;
-	     im4 = rcu_dereference(im4->next_rcu)) {
-		lcs_get_mac_for_ipm(im4->multiaddr, buf, card->dev);
-		ipm = lcs_check_addr_entry(card, im4, buf);
-		if (ipm != NULL)
-			continue;	/* Address already in list. */
-		ipm = kzalloc(sizeof(struct lcs_ipm_list), GFP_ATOMIC);
-		if (ipm == NULL) {
-			pr_info("Not enough memory to add"
-				" new multicast entry!\n");
-			break;
-		}
-		memcpy(&ipm->ipm.mac_addr, buf, LCS_MAC_LENGTH);
-		ipm->ipm.ip_addr = im4->multiaddr;
-		ipm->ipm_state = LCS_IPM_STATE_SET_REQUIRED;
-		spin_lock_irqsave(&card->ipm_lock, flags);
-		LCS_DBF_HEX(2,trace,&ipm->ipm.ip_addr,4);
-		list_add(&ipm->list, &card->ipm_list);
-		spin_unlock_irqrestore(&card->ipm_lock, flags);
-	}
-}
-
-static int
-lcs_register_mc_addresses(void *data)
-{
-	struct lcs_card *card;
-	struct in_device *in4_dev;
-
-	card = (struct lcs_card *) data;
-
-	if (!lcs_do_run_thread(card, LCS_SET_MC_THREAD))
-		return 0;
-	LCS_DBF_TEXT(4, trace, "regmulti");
-
-	in4_dev = in_dev_get(card->dev);
-	if (in4_dev == NULL)
-		goto out;
-	rcu_read_lock();
-	lcs_remove_mc_addresses(card,in4_dev);
-	lcs_set_mc_addresses(card, in4_dev);
-	rcu_read_unlock();
-	in_dev_put(in4_dev);
-
-	netif_carrier_off(card->dev);
-	netif_tx_disable(card->dev);
-	wait_event(card->write.wait_q,
-			(card->write.state != LCS_CH_STATE_RUNNING));
-	lcs_fix_multicast_list(card);
-	if (card->state == DEV_STATE_UP) {
-		netif_carrier_on(card->dev);
-		netif_wake_queue(card->dev);
-	}
-out:
-	lcs_clear_thread_running_bit(card, LCS_SET_MC_THREAD);
-	return 0;
-}
-#endif /* CONFIG_IP_MULTICAST */
-
-/*
- * function called by net device to
- * handle multicast address relevant things
- */
-static void
-lcs_set_multicast_list(struct net_device *dev)
-{
-#ifdef CONFIG_IP_MULTICAST
-        struct lcs_card *card;
-
-        LCS_DBF_TEXT(4, trace, "setmulti");
-        card = (struct lcs_card *) dev->ml_priv;
-
-        if (!lcs_set_thread_start_bit(card, LCS_SET_MC_THREAD))
-		schedule_work(&card->kernel_thread_starter);
-#endif /* CONFIG_IP_MULTICAST */
-}
-
-static long
-lcs_check_irb_error(struct ccw_device *cdev, struct irb *irb)
-{
-	if (!IS_ERR(irb))
-		return 0;
-
-	switch (PTR_ERR(irb)) {
-	case -EIO:
-		dev_warn(&cdev->dev,
-			"An I/O-error occurred on the LCS device\n");
-		LCS_DBF_TEXT(2, trace, "ckirberr");
-		LCS_DBF_TEXT_(2, trace, "  rc%d", -EIO);
-		break;
-	case -ETIMEDOUT:
-		dev_warn(&cdev->dev,
-			"A command timed out on the LCS device\n");
-		LCS_DBF_TEXT(2, trace, "ckirberr");
-		LCS_DBF_TEXT_(2, trace, "  rc%d", -ETIMEDOUT);
-		break;
-	default:
-		dev_warn(&cdev->dev,
-			"An error occurred on the LCS device, rc=%ld\n",
-			PTR_ERR(irb));
-		LCS_DBF_TEXT(2, trace, "ckirberr");
-		LCS_DBF_TEXT(2, trace, "  rc???");
-	}
-	return PTR_ERR(irb);
-}
-
-static int
-lcs_get_problem(struct ccw_device *cdev, struct irb *irb)
-{
-	int dstat, cstat;
-	char *sense;
-
-	sense = (char *) irb->ecw;
-	cstat = irb->scsw.cmd.cstat;
-	dstat = irb->scsw.cmd.dstat;
-
-	if (cstat & (SCHN_STAT_CHN_CTRL_CHK | SCHN_STAT_INTF_CTRL_CHK |
-		     SCHN_STAT_CHN_DATA_CHK | SCHN_STAT_CHAIN_CHECK |
-		     SCHN_STAT_PROT_CHECK   | SCHN_STAT_PROG_CHECK)) {
-		LCS_DBF_TEXT(2, trace, "CGENCHK");
-		return 1;
-	}
-	if (dstat & DEV_STAT_UNIT_CHECK) {
-		if (sense[LCS_SENSE_BYTE_1] &
-		    LCS_SENSE_RESETTING_EVENT) {
-			LCS_DBF_TEXT(2, trace, "REVIND");
-			return 1;
-		}
-		if (sense[LCS_SENSE_BYTE_0] &
-		    LCS_SENSE_CMD_REJECT) {
-			LCS_DBF_TEXT(2, trace, "CMDREJ");
-			return 0;
-		}
-		if ((!sense[LCS_SENSE_BYTE_0]) &&
-		    (!sense[LCS_SENSE_BYTE_1]) &&
-		    (!sense[LCS_SENSE_BYTE_2]) &&
-		    (!sense[LCS_SENSE_BYTE_3])) {
-			LCS_DBF_TEXT(2, trace, "ZEROSEN");
-			return 0;
-		}
-		LCS_DBF_TEXT(2, trace, "DGENCHK");
-		return 1;
-	}
-	return 0;
-}
-
-static void
-lcs_schedule_recovery(struct lcs_card *card)
-{
-	LCS_DBF_TEXT(2, trace, "startrec");
-	if (!lcs_set_thread_start_bit(card, LCS_RECOVERY_THREAD))
-		schedule_work(&card->kernel_thread_starter);
-}
-
-/*
- * IRQ Handler for LCS channels
- */
-static void
-lcs_irq(struct ccw_device *cdev, unsigned long intparm, struct irb *irb)
-{
-	struct lcs_card *card;
-	struct lcs_channel *channel;
-	int rc, index;
-	int cstat, dstat;
-
-	if (lcs_check_irb_error(cdev, irb))
-		return;
-
-	card = CARD_FROM_DEV(cdev);
-	if (card->read.ccwdev == cdev)
-		channel = &card->read;
-	else
-		channel = &card->write;
-
-	cstat = irb->scsw.cmd.cstat;
-	dstat = irb->scsw.cmd.dstat;
-	LCS_DBF_TEXT_(5, trace, "Rint%s", dev_name(&cdev->dev));
-	LCS_DBF_TEXT_(5, trace, "%4x%4x", irb->scsw.cmd.cstat,
-		      irb->scsw.cmd.dstat);
-	LCS_DBF_TEXT_(5, trace, "%4x%4x", irb->scsw.cmd.fctl,
-		      irb->scsw.cmd.actl);
-
-	/* Check for channel and device errors presented */
-	rc = lcs_get_problem(cdev, irb);
-	if (rc || (dstat & DEV_STAT_UNIT_EXCEP)) {
-		dev_warn(&cdev->dev,
-			"The LCS device stopped because of an error,"
-			" dstat=0x%X, cstat=0x%X \n",
-			    dstat, cstat);
-		if (rc) {
-			channel->state = LCS_CH_STATE_ERROR;
-		}
-	}
-	if (channel->state == LCS_CH_STATE_ERROR) {
-		lcs_schedule_recovery(card);
-		wake_up(&card->wait_q);
-		return;
-	}
-	/* How far in the ccw chain have we processed? */
-	if ((channel->state != LCS_CH_STATE_INIT) &&
-	    (irb->scsw.cmd.fctl & SCSW_FCTL_START_FUNC) &&
-	    (irb->scsw.cmd.cpa != 0)) {
-		index = (struct ccw1 *)dma32_to_virt(irb->scsw.cmd.cpa)
-			- channel->ccws;
-		if ((irb->scsw.cmd.actl & SCSW_ACTL_SUSPENDED) ||
-		    (irb->scsw.cmd.cstat & SCHN_STAT_PCI))
-			/* Bloody io subsystem tells us lies about cpa... */
-			index = (index - 1) & (LCS_NUM_BUFFS - 1);
-		while (channel->io_idx != index) {
-			__lcs_processed_buffer(channel,
-					       channel->iob + channel->io_idx);
-			channel->io_idx =
-				(channel->io_idx + 1) & (LCS_NUM_BUFFS - 1);
-		}
-	}
-
-	if ((irb->scsw.cmd.dstat & DEV_STAT_DEV_END) ||
-	    (irb->scsw.cmd.dstat & DEV_STAT_CHN_END) ||
-	    (irb->scsw.cmd.dstat & DEV_STAT_UNIT_CHECK))
-		/* Mark channel as stopped. */
-		channel->state = LCS_CH_STATE_STOPPED;
-	else if (irb->scsw.cmd.actl & SCSW_ACTL_SUSPENDED)
-		/* CCW execution stopped on a suspend bit. */
-		channel->state = LCS_CH_STATE_SUSPENDED;
-	if (irb->scsw.cmd.fctl & SCSW_FCTL_HALT_FUNC) {
-		if (irb->scsw.cmd.cc != 0) {
-			ccw_device_halt(channel->ccwdev, 0);
-			return;
-		}
-		/* The channel has been stopped by halt_IO. */
-		channel->state = LCS_CH_STATE_HALTED;
-	}
-	if (irb->scsw.cmd.fctl & SCSW_FCTL_CLEAR_FUNC)
-		channel->state = LCS_CH_STATE_CLEARED;
-	/* Do the rest in the tasklet. */
-	tasklet_schedule(&channel->irq_tasklet);
-}
-
-/*
- * Tasklet for IRQ handler
- */
-static void
-lcs_tasklet(unsigned long data)
-{
-	unsigned long flags;
-	struct lcs_channel *channel;
-	struct lcs_buffer *iob;
-	int buf_idx;
-
-	channel = (struct lcs_channel *) data;
-	LCS_DBF_TEXT_(5, trace, "tlet%s", dev_name(&channel->ccwdev->dev));
-
-	/* Check for processed buffers. */
-	iob = channel->iob;
-	buf_idx = channel->buf_idx;
-	while (iob[buf_idx].state == LCS_BUF_STATE_PROCESSED) {
-		/* Do the callback thing. */
-		if (iob[buf_idx].callback != NULL)
-			iob[buf_idx].callback(channel, iob + buf_idx);
-		buf_idx = (buf_idx + 1) & (LCS_NUM_BUFFS - 1);
-	}
-	channel->buf_idx = buf_idx;
-
-	if (channel->state == LCS_CH_STATE_STOPPED)
-		lcs_start_channel(channel);
-	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	if (channel->state == LCS_CH_STATE_SUSPENDED &&
-	    channel->iob[channel->io_idx].state == LCS_BUF_STATE_READY)
-		__lcs_resume_channel(channel);
-	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
-
-	/* Something happened on the channel. Wake up waiters. */
-	wake_up(&channel->wait_q);
-}
-
-/*
- * Finish current tx buffer and make it ready for transmit.
- */
-static void
-__lcs_emit_txbuffer(struct lcs_card *card)
-{
-	LCS_DBF_TEXT(5, trace, "emittx");
-	*(__u16 *)(card->tx_buffer->data + card->tx_buffer->count) = 0;
-	card->tx_buffer->count += 2;
-	lcs_ready_buffer(&card->write, card->tx_buffer);
-	card->tx_buffer = NULL;
-	card->tx_emitted++;
-}
-
-/*
- * Callback for finished tx buffers.
- */
-static void
-lcs_txbuffer_cb(struct lcs_channel *channel, struct lcs_buffer *buffer)
-{
-	struct lcs_card *card;
-
-	LCS_DBF_TEXT(5, trace, "txbuffcb");
-	/* Put buffer back to pool. */
-	lcs_release_buffer(channel, buffer);
-	card = container_of(channel, struct lcs_card, write);
-	if (netif_queue_stopped(card->dev) && netif_carrier_ok(card->dev))
-		netif_wake_queue(card->dev);
-	spin_lock(&card->lock);
-	card->tx_emitted--;
-	if (card->tx_emitted <= 0 && card->tx_buffer != NULL)
-		/*
-		 * Last running tx buffer has finished. Submit partially
-		 * filled current buffer.
-		 */
-		__lcs_emit_txbuffer(card);
-	spin_unlock(&card->lock);
-}
-
-/*
- * Packet transmit function called by network stack
- */
-static netdev_tx_t __lcs_start_xmit(struct lcs_card *card, struct sk_buff *skb,
-				    struct net_device *dev)
-{
-	struct lcs_header *header;
-	int rc = NETDEV_TX_OK;
-
-	LCS_DBF_TEXT(5, trace, "hardxmit");
-	if (skb == NULL) {
-		card->stats.tx_dropped++;
-		card->stats.tx_errors++;
-		return NETDEV_TX_OK;
-	}
-	if (card->state != DEV_STATE_UP) {
-		dev_kfree_skb(skb);
-		card->stats.tx_dropped++;
-		card->stats.tx_errors++;
-		card->stats.tx_carrier_errors++;
-		return NETDEV_TX_OK;
-	}
-	if (skb->protocol == htons(ETH_P_IPV6)) {
-		dev_kfree_skb(skb);
-		return NETDEV_TX_OK;
-	}
-	netif_stop_queue(card->dev);
-	spin_lock(&card->lock);
-	if (card->tx_buffer != NULL &&
-	    card->tx_buffer->count + sizeof(struct lcs_header) +
-	    skb->len + sizeof(u16) > LCS_IOBUFFERSIZE)
-		/* skb too big for current tx buffer. */
-		__lcs_emit_txbuffer(card);
-	if (card->tx_buffer == NULL) {
-		/* Get new tx buffer */
-		card->tx_buffer = lcs_get_buffer(&card->write);
-		if (card->tx_buffer == NULL) {
-			card->stats.tx_dropped++;
-			rc = NETDEV_TX_BUSY;
-			goto out;
-		}
-		card->tx_buffer->callback = lcs_txbuffer_cb;
-		card->tx_buffer->count = 0;
-	}
-	header = (struct lcs_header *)
-		(card->tx_buffer->data + card->tx_buffer->count);
-	card->tx_buffer->count += skb->len + sizeof(struct lcs_header);
-	header->offset = card->tx_buffer->count;
-	header->type = card->lan_type;
-	header->slot = card->portno;
-	skb_copy_from_linear_data(skb, header + 1, skb->len);
-	spin_unlock(&card->lock);
-	card->stats.tx_bytes += skb->len;
-	card->stats.tx_packets++;
-	dev_kfree_skb(skb);
-	netif_wake_queue(card->dev);
-	spin_lock(&card->lock);
-	if (card->tx_emitted <= 0 && card->tx_buffer != NULL)
-		/* If this is the first tx buffer emit it immediately. */
-		__lcs_emit_txbuffer(card);
-out:
-	spin_unlock(&card->lock);
-	return rc;
-}
-
-static netdev_tx_t lcs_start_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	struct lcs_card *card;
-	int rc;
-
-	LCS_DBF_TEXT(5, trace, "pktxmit");
-	card = (struct lcs_card *) dev->ml_priv;
-	rc = __lcs_start_xmit(card, skb, dev);
-	return rc;
-}
-
-/*
- * send startlan and lanstat command to make LCS device ready
- */
-static int
-lcs_startlan_auto(struct lcs_card *card)
-{
-	int rc;
-
-	LCS_DBF_TEXT(2, trace, "strtauto");
-	card->lan_type = LCS_FRAME_TYPE_ENET;
-	rc = lcs_send_startlan(card, LCS_INITIATOR_TCPIP);
-	if (rc == 0)
-		return 0;
-
-	return -EIO;
-}
-
-static int
-lcs_startlan(struct lcs_card *card)
-{
-	int rc, i;
-
-	LCS_DBF_TEXT(2, trace, "startlan");
-	rc = 0;
-	if (card->portno != LCS_INVALID_PORT_NO) {
-		if (card->lan_type == LCS_FRAME_TYPE_AUTO)
-			rc = lcs_startlan_auto(card);
-		else
-			rc = lcs_send_startlan(card, LCS_INITIATOR_TCPIP);
-	} else {
-                for (i = 0; i <= 16; i++) {
-                        card->portno = i;
-                        if (card->lan_type != LCS_FRAME_TYPE_AUTO)
-                                rc = lcs_send_startlan(card,
-                                                       LCS_INITIATOR_TCPIP);
-                        else
-                                /* autodetecting lan type */
-                                rc = lcs_startlan_auto(card);
-                        if (rc == 0)
-                                break;
-                }
-        }
-	if (rc == 0)
-		return lcs_send_lanstat(card);
-	return rc;
-}
-
-/*
- * LCS detect function
- * setup channels and make them I/O ready
- */
-static int
-lcs_detect(struct lcs_card *card)
-{
-	int rc = 0;
-
-	LCS_DBF_TEXT(2, setup, "lcsdetct");
-	/* start/reset card */
-	if (card->dev)
-		netif_stop_queue(card->dev);
-	rc = lcs_stop_channels(card);
-	if (rc == 0) {
-		rc = lcs_start_channels(card);
-		if (rc == 0) {
-			rc = lcs_send_startup(card, LCS_INITIATOR_TCPIP);
-			if (rc == 0)
-				rc = lcs_startlan(card);
-		}
-	}
-	if (rc == 0) {
-		card->state = DEV_STATE_UP;
-	} else {
-		card->state = DEV_STATE_DOWN;
-		card->write.state = LCS_CH_STATE_INIT;
-		card->read.state =  LCS_CH_STATE_INIT;
-	}
-	return rc;
-}
-
-/*
- * LCS Stop card
- */
-static int
-lcs_stopcard(struct lcs_card *card)
-{
-	int rc;
-
-	LCS_DBF_TEXT(3, setup, "stopcard");
-
-	if (card->read.state != LCS_CH_STATE_STOPPED &&
-	    card->write.state != LCS_CH_STATE_STOPPED &&
-	    card->read.state != LCS_CH_STATE_ERROR &&
-	    card->write.state != LCS_CH_STATE_ERROR &&
-	    card->state == DEV_STATE_UP) {
-		lcs_clear_multicast_list(card);
-		rc = lcs_send_stoplan(card,LCS_INITIATOR_TCPIP);
-		rc = lcs_send_shutdown(card);
-	}
-	rc = lcs_stop_channels(card);
-	card->state = DEV_STATE_DOWN;
-
-	return rc;
-}
-
-/*
- * Kernel Thread helper functions for LGW initiated commands
- */
-static void
-lcs_start_kernel_thread(struct work_struct *work)
-{
-	struct lcs_card *card = container_of(work, struct lcs_card, kernel_thread_starter);
-	LCS_DBF_TEXT(5, trace, "krnthrd");
-	if (lcs_do_start_thread(card, LCS_RECOVERY_THREAD))
-		kthread_run(lcs_recovery, card, "lcs_recover");
-#ifdef CONFIG_IP_MULTICAST
-	if (lcs_do_start_thread(card, LCS_SET_MC_THREAD))
-		kthread_run(lcs_register_mc_addresses, card, "regipm");
-#endif
-}
-
-/*
- * Process control frames.
- */
-static void
-lcs_get_control(struct lcs_card *card, struct lcs_cmd *cmd)
-{
-	LCS_DBF_TEXT(5, trace, "getctrl");
-	if (cmd->initiator == LCS_INITIATOR_LGW) {
-		switch(cmd->cmd_code) {
-		case LCS_CMD_STARTUP:
-		case LCS_CMD_STARTLAN:
-			lcs_schedule_recovery(card);
-			break;
-		case LCS_CMD_STOPLAN:
-			if (card->dev) {
-				pr_warn("Stoplan for %s initiated by LGW\n",
-					card->dev->name);
-				netif_carrier_off(card->dev);
-			}
-			break;
-		default:
-			LCS_DBF_TEXT(5, trace, "noLGWcmd");
-			break;
-		}
-	} else
-		lcs_notify_lancmd_waiters(card, cmd);
-}
-
-/*
- * Unpack network packet.
- */
-static void
-lcs_get_skb(struct lcs_card *card, char *skb_data, unsigned int skb_len)
-{
-	struct sk_buff *skb;
-
-	LCS_DBF_TEXT(5, trace, "getskb");
-	if (card->dev == NULL ||
-	    card->state != DEV_STATE_UP)
-		/* The card isn't up. Ignore the packet. */
-		return;
-
-	skb = dev_alloc_skb(skb_len);
-	if (skb == NULL) {
-		dev_err(&card->dev->dev,
-			" Allocating a socket buffer to interface %s failed\n",
-			  card->dev->name);
-		card->stats.rx_dropped++;
-		return;
-	}
-	skb_put_data(skb, skb_data, skb_len);
-	skb->protocol =	card->lan_type_trans(skb, card->dev);
-	card->stats.rx_bytes += skb_len;
-	card->stats.rx_packets++;
-	if (skb->protocol == htons(ETH_P_802_2))
-		*((__u32 *)skb->cb) = ++card->pkt_seq;
-	netif_rx(skb);
-}
-
-/*
- * LCS main routine to get packets and lancmd replies from the buffers
- */
-static void
-lcs_get_frames_cb(struct lcs_channel *channel, struct lcs_buffer *buffer)
-{
-	struct lcs_card *card;
-	struct lcs_header *lcs_hdr;
-	__u16 offset;
-
-	LCS_DBF_TEXT(5, trace, "lcsgtpkt");
-	lcs_hdr = (struct lcs_header *) buffer->data;
-	if (lcs_hdr->offset == LCS_ILLEGAL_OFFSET) {
-		LCS_DBF_TEXT(4, trace, "-eiogpkt");
-		return;
-	}
-	card = container_of(channel, struct lcs_card, read);
-	offset = 0;
-	while (lcs_hdr->offset != 0) {
-		if (lcs_hdr->offset <= 0 ||
-		    lcs_hdr->offset > LCS_IOBUFFERSIZE ||
-		    lcs_hdr->offset < offset) {
-			/* Offset invalid. */
-			card->stats.rx_length_errors++;
-			card->stats.rx_errors++;
-			return;
-		}
-		if (lcs_hdr->type == LCS_FRAME_TYPE_CONTROL)
-			lcs_get_control(card, (struct lcs_cmd *) lcs_hdr);
-		else if (lcs_hdr->type == LCS_FRAME_TYPE_ENET)
-			lcs_get_skb(card, (char *)(lcs_hdr + 1),
-				    lcs_hdr->offset - offset -
-				    sizeof(struct lcs_header));
-		else
-			dev_info_once(&card->dev->dev,
-				      "Unknown frame type %d\n",
-				      lcs_hdr->type);
-		offset = lcs_hdr->offset;
-		lcs_hdr->offset = LCS_ILLEGAL_OFFSET;
-		lcs_hdr = (struct lcs_header *) (buffer->data + offset);
-	}
-	/* The buffer is now empty. Make it ready again. */
-	lcs_ready_buffer(&card->read, buffer);
-}
-
-/*
- * get network statistics for ifconfig and other user programs
- */
-static struct net_device_stats *
-lcs_getstats(struct net_device *dev)
-{
-	struct lcs_card *card;
-
-	LCS_DBF_TEXT(4, trace, "netstats");
-	card = (struct lcs_card *) dev->ml_priv;
-	return &card->stats;
-}
-
-/*
- * stop lcs device
- * This function will be called by user doing ifconfig xxx down
- */
-static int
-lcs_stop_device(struct net_device *dev)
-{
-	struct lcs_card *card;
-	int rc;
-
-	LCS_DBF_TEXT(2, trace, "stopdev");
-	card   = (struct lcs_card *) dev->ml_priv;
-	netif_carrier_off(dev);
-	netif_tx_disable(dev);
-	dev->flags &= ~IFF_UP;
-	wait_event(card->write.wait_q,
-		(card->write.state != LCS_CH_STATE_RUNNING));
-	rc = lcs_stopcard(card);
-	if (rc)
-		dev_err(&card->dev->dev,
-			" Shutting down the LCS device failed\n");
-	return rc;
-}
-
-/*
- * start lcs device and make it runnable
- * This function will be called by user doing ifconfig xxx up
- */
-static int
-lcs_open_device(struct net_device *dev)
-{
-	struct lcs_card *card;
-	int rc;
-
-	LCS_DBF_TEXT(2, trace, "opendev");
-	card = (struct lcs_card *) dev->ml_priv;
-	/* initialize statistics */
-	rc = lcs_detect(card);
-	if (rc) {
-		pr_err("Error in opening device!\n");
-
-	} else {
-		dev->flags |= IFF_UP;
-		netif_carrier_on(dev);
-		netif_wake_queue(dev);
-		card->state = DEV_STATE_UP;
-	}
-	return rc;
-}
-
-/*
- * show function for portno called by cat or similar things
- */
-static ssize_t
-lcs_portno_show (struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct lcs_card *card;
-
-	card = dev_get_drvdata(dev);
-
-	if (!card)
-		return 0;
-
-	return sysfs_emit(buf, "%d\n", card->portno);
-}
-
-/*
- * store the value which is piped to file portno
- */
-static ssize_t
-lcs_portno_store (struct device *dev, struct device_attribute *attr, const char *buf, size_t count)
-{
-        struct lcs_card *card;
-	int rc;
-	s16 value;
-
-	card = dev_get_drvdata(dev);
-
-        if (!card)
-                return 0;
-
-	rc = kstrtos16(buf, 0, &value);
-	if (rc)
-		return -EINVAL;
-        /* TODO: sanity checks */
-        card->portno = value;
-	if (card->dev)
-		card->dev->dev_port = card->portno;
-
-        return count;
-
-}
-
-static DEVICE_ATTR(portno, 0644, lcs_portno_show, lcs_portno_store);
-
-static const char *lcs_type[] = {
-	"not a channel",
-	"2216 parallel",
-	"2216 channel",
-	"OSA LCS card",
-	"unknown channel type",
-	"unsupported channel type",
-};
-
-static ssize_t
-lcs_type_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct ccwgroup_device *cgdev;
-
-	cgdev = to_ccwgroupdev(dev);
-	if (!cgdev)
-		return -ENODEV;
-
-	return sysfs_emit(buf, "%s\n",
-			  lcs_type[cgdev->cdev[0]->id.driver_info]);
-}
-
-static DEVICE_ATTR(type, 0444, lcs_type_show, NULL);
-
-static ssize_t
-lcs_timeout_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct lcs_card *card;
-
-	card = dev_get_drvdata(dev);
-
-	return card ? sysfs_emit(buf, "%u\n", card->lancmd_timeout) : 0;
-}
-
-static ssize_t
-lcs_timeout_store (struct device *dev, struct device_attribute *attr, const char *buf, size_t count)
-{
-        struct lcs_card *card;
-	unsigned int value;
-	int rc;
-
-	card = dev_get_drvdata(dev);
-
-        if (!card)
-                return 0;
-
-	rc = kstrtouint(buf, 0, &value);
-	if (rc)
-		return -EINVAL;
-        /* TODO: sanity checks */
-        card->lancmd_timeout = value;
-
-        return count;
-
-}
-
-static DEVICE_ATTR(lancmd_timeout, 0644, lcs_timeout_show, lcs_timeout_store);
-
-static ssize_t
-lcs_dev_recover_store(struct device *dev, struct device_attribute *attr,
-		      const char *buf, size_t count)
-{
-	struct lcs_card *card = dev_get_drvdata(dev);
-	char *tmp;
-	int i;
-
-	if (!card)
-		return -EINVAL;
-	if (card->state != DEV_STATE_UP)
-		return -EPERM;
-	i = simple_strtoul(buf, &tmp, 16);
-	if (i == 1)
-		lcs_schedule_recovery(card);
-	return count;
-}
-
-static DEVICE_ATTR(recover, 0200, NULL, lcs_dev_recover_store);
-
-static struct attribute * lcs_attrs[] = {
-	&dev_attr_portno.attr,
-	&dev_attr_type.attr,
-	&dev_attr_lancmd_timeout.attr,
-	&dev_attr_recover.attr,
-	NULL,
-};
-static struct attribute_group lcs_attr_group = {
-	.attrs = lcs_attrs,
-};
-static const struct attribute_group *lcs_attr_groups[] = {
-	&lcs_attr_group,
-	NULL,
-};
-static const struct device_type lcs_devtype = {
-	.name = "lcs",
-	.groups = lcs_attr_groups,
-};
-
-/*
- * lcs_probe_device is called on establishing a new ccwgroup_device.
- */
-static int
-lcs_probe_device(struct ccwgroup_device *ccwgdev)
-{
-	struct lcs_card *card;
-
-	if (!get_device(&ccwgdev->dev))
-		return -ENODEV;
-
-	LCS_DBF_TEXT(2, setup, "add_dev");
-        card = lcs_alloc_card();
-        if (!card) {
-		LCS_DBF_TEXT_(2, setup, "  rc%d", -ENOMEM);
-		put_device(&ccwgdev->dev);
-                return -ENOMEM;
-        }
-	dev_set_drvdata(&ccwgdev->dev, card);
-	ccwgdev->cdev[0]->handler = lcs_irq;
-	ccwgdev->cdev[1]->handler = lcs_irq;
-	card->gdev = ccwgdev;
-	INIT_WORK(&card->kernel_thread_starter, lcs_start_kernel_thread);
-	card->thread_start_mask = 0;
-	card->thread_allowed_mask = 0;
-	card->thread_running_mask = 0;
-	ccwgdev->dev.type = &lcs_devtype;
-
-	return 0;
-}
-
-static int
-lcs_register_netdev(struct ccwgroup_device *ccwgdev)
-{
-	struct lcs_card *card;
-
-	LCS_DBF_TEXT(2, setup, "regnetdv");
-	card = dev_get_drvdata(&ccwgdev->dev);
-	if (card->dev->reg_state != NETREG_UNINITIALIZED)
-		return 0;
-	SET_NETDEV_DEV(card->dev, &ccwgdev->dev);
-	return register_netdev(card->dev);
-}
-
-/*
- * lcs_new_device will be called by setting the group device online.
- */
-static const struct net_device_ops lcs_netdev_ops = {
-	.ndo_open		= lcs_open_device,
-	.ndo_stop		= lcs_stop_device,
-	.ndo_get_stats		= lcs_getstats,
-	.ndo_start_xmit		= lcs_start_xmit,
-};
-
-static const struct net_device_ops lcs_mc_netdev_ops = {
-	.ndo_open		= lcs_open_device,
-	.ndo_stop		= lcs_stop_device,
-	.ndo_get_stats		= lcs_getstats,
-	.ndo_start_xmit		= lcs_start_xmit,
-	.ndo_set_rx_mode	= lcs_set_multicast_list,
-};
-
-static int
-lcs_new_device(struct ccwgroup_device *ccwgdev)
-{
-	struct  lcs_card *card;
-	struct net_device *dev=NULL;
-	enum lcs_dev_states recover_state;
-	int rc;
-
-	card = dev_get_drvdata(&ccwgdev->dev);
-	if (!card)
-		return -ENODEV;
-
-	LCS_DBF_TEXT(2, setup, "newdev");
-	LCS_DBF_HEX(3, setup, &card, sizeof(void*));
-	card->read.ccwdev  = ccwgdev->cdev[0];
-	card->write.ccwdev = ccwgdev->cdev[1];
-
-	recover_state = card->state;
-	rc = ccw_device_set_online(card->read.ccwdev);
-	if (rc)
-		goto out_err;
-	rc = ccw_device_set_online(card->write.ccwdev);
-	if (rc)
-		goto out_werr;
-
-	LCS_DBF_TEXT(3, setup, "lcsnewdv");
-
-	lcs_setup_card(card);
-	rc = lcs_detect(card);
-	if (rc) {
-		LCS_DBF_TEXT(2, setup, "dtctfail");
-		dev_err(&ccwgdev->dev,
-			"Detecting a network adapter for LCS devices"
-			" failed with rc=%d (0x%x)\n", rc, rc);
-		lcs_stopcard(card);
-		goto out;
-	}
-	if (card->dev) {
-		LCS_DBF_TEXT(2, setup, "samedev");
-		LCS_DBF_HEX(3, setup, &card, sizeof(void*));
-		goto netdev_out;
-	}
-	switch (card->lan_type) {
-	case LCS_FRAME_TYPE_ENET:
-		card->lan_type_trans = eth_type_trans;
-		dev = alloc_etherdev(0);
-		break;
-	default:
-		LCS_DBF_TEXT(3, setup, "errinit");
-		pr_err(" Initialization failed\n");
-		goto out;
-	}
-	if (!dev)
-		goto out;
-	card->dev = dev;
-	card->dev->ml_priv = card;
-	card->dev->netdev_ops = &lcs_netdev_ops;
-	card->dev->dev_port = card->portno;
-	eth_hw_addr_set(card->dev, card->mac);
-#ifdef CONFIG_IP_MULTICAST
-	if (!lcs_check_multicast_support(card))
-		card->dev->netdev_ops = &lcs_mc_netdev_ops;
-#endif
-netdev_out:
-	lcs_set_allowed_threads(card,0xffffffff);
-	if (recover_state == DEV_STATE_RECOVER) {
-		lcs_set_multicast_list(card->dev);
-		card->dev->flags |= IFF_UP;
-		netif_carrier_on(card->dev);
-		netif_wake_queue(card->dev);
-		card->state = DEV_STATE_UP;
-	} else {
-		lcs_stopcard(card);
-	}
-
-	if (lcs_register_netdev(ccwgdev) != 0)
-		goto out;
-
-	/* Print out supported assists: IPv6 */
-	pr_info("LCS device %s %s IPv6 support\n", card->dev->name,
-		(card->ip_assists_supported & LCS_IPASS_IPV6_SUPPORT) ?
-		"with" : "without");
-	/* Print out supported assist: Multicast */
-	pr_info("LCS device %s %s Multicast support\n", card->dev->name,
-		(card->ip_assists_supported & LCS_IPASS_MULTICAST_SUPPORT) ?
-		"with" : "without");
-	return 0;
-out:
-
-	ccw_device_set_offline(card->write.ccwdev);
-out_werr:
-	ccw_device_set_offline(card->read.ccwdev);
-out_err:
-	return -ENODEV;
-}
-
-/*
- * lcs_shutdown_device, called when setting the group device offline.
- */
-static int
-__lcs_shutdown_device(struct ccwgroup_device *ccwgdev, int recovery_mode)
-{
-	struct lcs_card *card;
-	enum lcs_dev_states recover_state;
-	int ret = 0, ret2 = 0, ret3 = 0;
-
-	LCS_DBF_TEXT(3, setup, "shtdndev");
-	card = dev_get_drvdata(&ccwgdev->dev);
-	if (!card)
-		return -ENODEV;
-	if (recovery_mode == 0) {
-		lcs_set_allowed_threads(card, 0);
-		if (lcs_wait_for_threads(card, LCS_SET_MC_THREAD))
-			return -ERESTARTSYS;
-	}
-	LCS_DBF_HEX(3, setup, &card, sizeof(void*));
-	recover_state = card->state;
-
-	ret = lcs_stop_device(card->dev);
-	ret2 = ccw_device_set_offline(card->read.ccwdev);
-	ret3 = ccw_device_set_offline(card->write.ccwdev);
-	if (!ret)
-		ret = (ret2) ? ret2 : ret3;
-	if (ret)
-		LCS_DBF_TEXT_(3, setup, "1err:%d", ret);
-	if (recover_state == DEV_STATE_UP) {
-		card->state = DEV_STATE_RECOVER;
-	}
-	return 0;
-}
-
-static int
-lcs_shutdown_device(struct ccwgroup_device *ccwgdev)
-{
-	return __lcs_shutdown_device(ccwgdev, 0);
-}
-
-/*
- * drive lcs recovery after startup and startlan initiated by Lan Gateway
- */
-static int
-lcs_recovery(void *ptr)
-{
-	struct lcs_card *card;
-	struct ccwgroup_device *gdev;
-        int rc;
-
-	card = (struct lcs_card *) ptr;
-
-	LCS_DBF_TEXT(4, trace, "recover1");
-	if (!lcs_do_run_thread(card, LCS_RECOVERY_THREAD))
-		return 0;
-	LCS_DBF_TEXT(4, trace, "recover2");
-	gdev = card->gdev;
-	dev_warn(&gdev->dev,
-		"A recovery process has been started for the LCS device\n");
-	rc = __lcs_shutdown_device(gdev, 1);
-	rc = lcs_new_device(gdev);
-	if (!rc)
-		pr_info("Device %s successfully recovered!\n",
-			card->dev->name);
-	else
-		pr_info("Device %s could not be recovered!\n",
-			card->dev->name);
-	lcs_clear_thread_running_bit(card, LCS_RECOVERY_THREAD);
-	return 0;
-}
-
-/*
- * lcs_remove_device, free buffers and card
- */
-static void
-lcs_remove_device(struct ccwgroup_device *ccwgdev)
-{
-	struct lcs_card *card;
-
-	card = dev_get_drvdata(&ccwgdev->dev);
-	if (!card)
-		return;
-
-	LCS_DBF_TEXT(3, setup, "remdev");
-	LCS_DBF_HEX(3, setup, &card, sizeof(void*));
-	if (ccwgdev->state == CCWGROUP_ONLINE) {
-		lcs_shutdown_device(ccwgdev);
-	}
-	if (card->dev)
-		unregister_netdev(card->dev);
-	lcs_cleanup_card(card);
-	lcs_free_card(card);
-	dev_set_drvdata(&ccwgdev->dev, NULL);
-	put_device(&ccwgdev->dev);
-}
-
-static struct ccw_device_id lcs_ids[] = {
-	{CCW_DEVICE(0x3088, 0x08), .driver_info = lcs_channel_type_parallel},
-	{CCW_DEVICE(0x3088, 0x1f), .driver_info = lcs_channel_type_2216},
-	{CCW_DEVICE(0x3088, 0x60), .driver_info = lcs_channel_type_osa2},
-	{},
-};
-MODULE_DEVICE_TABLE(ccw, lcs_ids);
-
-static struct ccw_driver lcs_ccw_driver = {
-	.driver = {
-		.owner	= THIS_MODULE,
-		.name	= "lcs",
-	},
-	.ids	= lcs_ids,
-	.probe	= ccwgroup_probe_ccwdev,
-	.remove	= ccwgroup_remove_ccwdev,
-	.int_class = IRQIO_LCS,
-};
-
-/*
- * LCS ccwgroup driver registration
- */
-static struct ccwgroup_driver lcs_group_driver = {
-	.driver = {
-		.owner	= THIS_MODULE,
-		.name	= "lcs",
-	},
-	.ccw_driver  = &lcs_ccw_driver,
-	.setup	     = lcs_probe_device,
-	.remove      = lcs_remove_device,
-	.set_online  = lcs_new_device,
-	.set_offline = lcs_shutdown_device,
-};
-
-static ssize_t group_store(struct device_driver *ddrv, const char *buf,
-			   size_t count)
-{
-	int err;
-	err = ccwgroup_create_dev(lcs_root_dev, &lcs_group_driver, 2, buf);
-	return err ? err : count;
-}
-static DRIVER_ATTR_WO(group);
-
-static struct attribute *lcs_drv_attrs[] = {
-	&driver_attr_group.attr,
-	NULL,
-};
-static struct attribute_group lcs_drv_attr_group = {
-	.attrs = lcs_drv_attrs,
-};
-static const struct attribute_group *lcs_drv_attr_groups[] = {
-	&lcs_drv_attr_group,
-	NULL,
-};
-
-/*
- *  LCS Module/Kernel initialization function
- */
-static int
-__init lcs_init_module(void)
-{
-	int rc;
-
-	pr_info("Loading %s\n", version);
-	rc = lcs_register_debug_facility();
-	LCS_DBF_TEXT(0, setup, "lcsinit");
-	if (rc)
-		goto out_err;
-	lcs_root_dev = root_device_register("lcs");
-	rc = PTR_ERR_OR_ZERO(lcs_root_dev);
-	if (rc)
-		goto register_err;
-	rc = ccw_driver_register(&lcs_ccw_driver);
-	if (rc)
-		goto ccw_err;
-	lcs_group_driver.driver.groups = lcs_drv_attr_groups;
-	rc = ccwgroup_driver_register(&lcs_group_driver);
-	if (rc)
-		goto ccwgroup_err;
-	return 0;
-
-ccwgroup_err:
-	ccw_driver_unregister(&lcs_ccw_driver);
-ccw_err:
-	root_device_unregister(lcs_root_dev);
-register_err:
-	lcs_unregister_debug_facility();
-out_err:
-	pr_err("Initializing the lcs device driver failed\n");
-	return rc;
-}
-
-
-/*
- *  LCS module cleanup function
- */
-static void
-__exit lcs_cleanup_module(void)
-{
-	pr_info("Terminating lcs module.\n");
-	LCS_DBF_TEXT(0, trace, "cleanup");
-	ccwgroup_driver_unregister(&lcs_group_driver);
-	ccw_driver_unregister(&lcs_ccw_driver);
-	root_device_unregister(lcs_root_dev);
-	lcs_unregister_debug_facility();
-}
-
-module_init(lcs_init_module);
-module_exit(lcs_cleanup_module);
-
-MODULE_AUTHOR("Frank Pavlic <fpavlic@de.ibm.com>");
-MODULE_DESCRIPTION("S/390 LAN channel station device driver");
-MODULE_LICENSE("GPL");
-
diff --git a/drivers/s390/net/lcs.h b/drivers/s390/net/lcs.h
deleted file mode 100644
index a2699b70b050..000000000000
--- a/drivers/s390/net/lcs.h
+++ /dev/null
@@ -1,342 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*lcs.h*/
-
-#include <linux/interrupt.h>
-#include <linux/netdevice.h>
-#include <linux/skbuff.h>
-#include <linux/workqueue.h>
-#include <linux/refcount.h>
-#include <asm/ccwdev.h>
-
-#define LCS_DBF_TEXT(level, name, text) \
-	do { \
-		debug_text_event(lcs_dbf_##name, level, text); \
-	} while (0)
-
-#define LCS_DBF_HEX(level,name,addr,len) \
-do { \
-	debug_event(lcs_dbf_##name,level,(void*)(addr),len); \
-} while (0)
-
-#define LCS_DBF_TEXT_(level,name,text...) \
-	do { \
-		if (debug_level_enabled(lcs_dbf_##name, level)) { \
-			scnprintf(debug_buffer, sizeof(debug_buffer), text); \
-			debug_text_event(lcs_dbf_##name, level, debug_buffer); \
-		} \
-	} while (0)
-
-/**
- *	sysfs related stuff
- */
-#define CARD_FROM_DEV(cdev) \
-	(struct lcs_card *) dev_get_drvdata( \
-		&((struct ccwgroup_device *)dev_get_drvdata(&cdev->dev))->dev);
-
-/**
- * Enum for classifying detected devices.
- */
-enum lcs_channel_types {
-	/* Device is not a channel  */
-	lcs_channel_type_none,
-
-	/* Device is a 2216 channel */
-	lcs_channel_type_parallel,
-
-	/* Device is a 2216 channel */
-	lcs_channel_type_2216,
-
-	/* Device is a OSA2 card */
-	lcs_channel_type_osa2
-};
-
-/**
- * CCW commands used in this driver
- */
-#define LCS_CCW_WRITE		0x01
-#define LCS_CCW_READ		0x02
-#define LCS_CCW_TRANSFER	0x08
-
-/**
- * LCS device status primitives
- */
-#define LCS_CMD_STARTLAN	0x01
-#define LCS_CMD_STOPLAN		0x02
-#define LCS_CMD_LANSTAT		0x04
-#define LCS_CMD_STARTUP		0x07
-#define LCS_CMD_SHUTDOWN	0x08
-#define LCS_CMD_QIPASSIST	0xb2
-#define LCS_CMD_SETIPM		0xb4
-#define LCS_CMD_DELIPM		0xb5
-
-#define LCS_INITIATOR_TCPIP	0x00
-#define LCS_INITIATOR_LGW	0x01
-#define LCS_STD_CMD_SIZE	16
-#define LCS_MULTICAST_CMD_SIZE	404
-
-/**
- * LCS IPASSIST MASKS,only used when multicast is switched on
- */
-/* Not supported by LCS */
-#define LCS_IPASS_ARP_PROCESSING	0x0001
-#define LCS_IPASS_IN_CHECKSUM_SUPPORT	0x0002
-#define LCS_IPASS_OUT_CHECKSUM_SUPPORT	0x0004
-#define LCS_IPASS_IP_FRAG_REASSEMBLY	0x0008
-#define LCS_IPASS_IP_FILTERING		0x0010
-/* Supported by lcs 3172 */
-#define LCS_IPASS_IPV6_SUPPORT		0x0020
-#define LCS_IPASS_MULTICAST_SUPPORT	0x0040
-
-/**
- * LCS sense byte definitions
- */
-#define LCS_SENSE_BYTE_0 		0
-#define LCS_SENSE_BYTE_1 		1
-#define LCS_SENSE_BYTE_2 		2
-#define LCS_SENSE_BYTE_3 		3
-#define LCS_SENSE_INTERFACE_DISCONNECT	0x01
-#define LCS_SENSE_EQUIPMENT_CHECK	0x10
-#define LCS_SENSE_BUS_OUT_CHECK		0x20
-#define LCS_SENSE_INTERVENTION_REQUIRED 0x40
-#define LCS_SENSE_CMD_REJECT		0x80
-#define LCS_SENSE_RESETTING_EVENT	0x80
-#define LCS_SENSE_DEVICE_ONLINE		0x20
-
-/**
- * LCS packet type definitions
- */
-#define LCS_FRAME_TYPE_CONTROL		0
-#define LCS_FRAME_TYPE_ENET		1
-#define LCS_FRAME_TYPE_TR		2
-#define LCS_FRAME_TYPE_FDDI		7
-#define LCS_FRAME_TYPE_AUTO		-1
-
-/**
- * some more definitions,we will sort them later
- */
-#define LCS_ILLEGAL_OFFSET		0xffff
-#define LCS_IOBUFFERSIZE		0x5000
-#define LCS_NUM_BUFFS			32	/* needs to be power of 2 */
-#define LCS_MAC_LENGTH			6
-#define LCS_INVALID_PORT_NO		-1
-#define LCS_LANCMD_TIMEOUT_DEFAULT      5
-
-/**
- * Multicast state
- */
-#define	 LCS_IPM_STATE_SET_REQUIRED	0
-#define	 LCS_IPM_STATE_DEL_REQUIRED	1
-#define	 LCS_IPM_STATE_ON_CARD		2
-
-/**
- * LCS IP Assist declarations
- * seems to be only used for multicast
- */
-#define	 LCS_IPASS_ARP_PROCESSING	0x0001
-#define	 LCS_IPASS_INBOUND_CSUM_SUPP	0x0002
-#define	 LCS_IPASS_OUTBOUND_CSUM_SUPP	0x0004
-#define	 LCS_IPASS_IP_FRAG_REASSEMBLY	0x0008
-#define	 LCS_IPASS_IP_FILTERING		0x0010
-#define	 LCS_IPASS_IPV6_SUPPORT		0x0020
-#define	 LCS_IPASS_MULTICAST_SUPPORT	0x0040
-
-/**
- * LCS Buffer states
- */
-enum lcs_buffer_states {
-	LCS_BUF_STATE_EMPTY,	/* buffer is empty */
-	LCS_BUF_STATE_LOCKED,	/* buffer is locked, don't touch */
-	LCS_BUF_STATE_READY,	/* buffer is ready for read/write */
-	LCS_BUF_STATE_PROCESSED,
-};
-
-/**
- * LCS Channel State Machine declarations
- */
-enum lcs_channel_states {
-	LCS_CH_STATE_INIT,
-	LCS_CH_STATE_HALTED,
-	LCS_CH_STATE_STOPPED,
-	LCS_CH_STATE_RUNNING,
-	LCS_CH_STATE_SUSPENDED,
-	LCS_CH_STATE_CLEARED,
-	LCS_CH_STATE_ERROR,
-};
-
-/**
- * LCS device state machine
- */
-enum lcs_dev_states {
-	DEV_STATE_DOWN,
-	DEV_STATE_UP,
-	DEV_STATE_RECOVER,
-};
-
-enum lcs_threads {
-	LCS_SET_MC_THREAD 	= 1,
-	LCS_RECOVERY_THREAD 	= 2,
-};
-
-/**
- * LCS struct declarations
- */
-struct lcs_header {
-	__u16  offset;
-	__u8   type;
-	__u8   slot;
-}  __attribute__ ((packed));
-
-struct lcs_ip_mac_pair {
-	__be32  ip_addr;
-	__u8   mac_addr[LCS_MAC_LENGTH];
-	__u8   reserved[2];
-}  __attribute__ ((packed));
-
-struct lcs_ipm_list {
-	struct list_head list;
-	struct lcs_ip_mac_pair ipm;
-	__u8 ipm_state;
-};
-
-struct lcs_cmd {
-	__u16  offset;
-	__u8   type;
-	__u8   slot;
-	__u8   cmd_code;
-	__u8   initiator;
-	__u16  sequence_no;
-	__u16  return_code;
-	union {
-		struct {
-			__u8   lan_type;
-			__u8   portno;
-			__u16  parameter_count;
-			__u8   operator_flags[3];
-			__u8   reserved[3];
-		} lcs_std_cmd;
-		struct {
-			__u16  unused1;
-			__u16  buff_size;
-			__u8   unused2[6];
-		} lcs_startup;
-		struct {
-			__u8   lan_type;
-			__u8   portno;
-			__u8   unused[10];
-			__u8   mac_addr[LCS_MAC_LENGTH];
-			__u32  num_packets_deblocked;
-			__u32  num_packets_blocked;
-			__u32  num_packets_tx_on_lan;
-			__u32  num_tx_errors_detected;
-			__u32  num_tx_packets_disgarded;
-			__u32  num_packets_rx_from_lan;
-			__u32  num_rx_errors_detected;
-			__u32  num_rx_discarded_nobuffs_avail;
-			__u32  num_rx_packets_too_large;
-		} lcs_lanstat_cmd;
-#ifdef CONFIG_IP_MULTICAST
-		struct {
-			__u8   lan_type;
-			__u8   portno;
-			__u16  num_ip_pairs;
-			__u16  ip_assists_supported;
-			__u16  ip_assists_enabled;
-			__u16  version;
-			struct {
-				struct lcs_ip_mac_pair
-				ip_mac_pair[32];
-				__u32	  response_data;
-			} lcs_ipass_ctlmsg __attribute ((packed));
-		} lcs_qipassist __attribute__ ((packed));
-#endif /*CONFIG_IP_MULTICAST */
-	} cmd __attribute__ ((packed));
-}  __attribute__ ((packed));
-
-/**
- * Forward declarations.
- */
-struct lcs_card;
-struct lcs_channel;
-
-/**
- * Definition of an lcs buffer.
- */
-struct lcs_buffer {
-	enum lcs_buffer_states state;
-	void *data;
-	int count;
-	/* Callback for completion notification. */
-	void (*callback)(struct lcs_channel *, struct lcs_buffer *);
-};
-
-struct lcs_reply {
-	struct list_head list;
-	__u16 sequence_no;
-	refcount_t refcnt;
-	/* Callback for completion notification. */
-	void (*callback)(struct lcs_card *, struct lcs_cmd *);
-	wait_queue_head_t wait_q;
-	struct lcs_card *card;
-	struct timer_list timer;
-	int received;
-	int rc;
-};
-
-/**
- * Definition of an lcs channel
- */
-struct lcs_channel {
-	enum lcs_channel_states state;
-	struct ccw_device *ccwdev;
-	struct ccw1 ccws[LCS_NUM_BUFFS + 1];
-	wait_queue_head_t wait_q;
-	struct tasklet_struct irq_tasklet;
-	struct lcs_buffer iob[LCS_NUM_BUFFS];
-	int io_idx;
-	int buf_idx;
-};
-
-
-/**
- * definition of the lcs card
- */
-struct lcs_card {
-	spinlock_t lock;
-	spinlock_t ipm_lock;
-	enum lcs_dev_states state;
-	struct net_device *dev;
-	struct net_device_stats stats;
-	__be16 (*lan_type_trans)(struct sk_buff *skb,
-					 struct net_device *dev);
-	struct ccwgroup_device *gdev;
-	struct lcs_channel read;
-	struct lcs_channel write;
-	struct lcs_buffer *tx_buffer;
-	int tx_emitted;
-	struct list_head lancmd_waiters;
-	int lancmd_timeout;
-
-	struct work_struct kernel_thread_starter;
-	spinlock_t mask_lock;
-	unsigned long thread_start_mask;
-	unsigned long thread_running_mask;
-	unsigned long thread_allowed_mask;
-	wait_queue_head_t wait_q;
-
-#ifdef CONFIG_IP_MULTICAST
-	struct list_head ipm_list;
-#endif
-	__u8 mac[LCS_MAC_LENGTH];
-	__u16 ip_assists_supported;
-	__u16 ip_assists_enabled;
-	__s8 lan_type;
-	__u32 pkt_seq;
-	__u16 sequence_no;
-	__s16 portno;
-	/* Some info copied from probeinfo */
-	u8 device_forced;
-	u8 max_port_no;
-	u8 hint_port_no;
-	s16 port_protocol_no;
-}  __attribute__ ((aligned(8)));
-
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 72aac84dca93..35fc241c4672 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -40,6 +40,8 @@ enum io_uring_cmd_flags {
 	IO_URING_F_TASK_DEAD		= (1 << 13),
 };
 
+struct io_zcrx_ifq;
+
 struct io_wq_work_node {
 	struct io_wq_work_node *next;
 };
@@ -384,6 +386,8 @@ struct io_ring_ctx {
 	struct wait_queue_head		poll_wq;
 	struct io_restriction		restrictions;
 
+	struct io_zcrx_ifq		*ifq;
+
 	u32			pers_next;
 	struct xarray		personalities;
 
@@ -436,6 +440,8 @@ struct io_ring_ctx {
 	struct io_mapped_region		ring_region;
 	/* used for optimised request parameter and wait argument passing  */
 	struct io_mapped_region		param_region;
+	/* just one zcrx per ring for now, will move to io_zcrx_ifq eventually */
+	struct io_mapped_region		zcrx_region;
 };
 
 /*
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 27f42f713c89..87edb7a8173b 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1415,7 +1415,6 @@ int mlx4_get_is_vlan_offload_disabled(struct mlx4_dev *dev, u8 port,
 				      bool *vlan_offload_disabled);
 void mlx4_handle_eth_header_mcast_prio(struct mlx4_net_trans_rule_hw_ctrl *ctrl,
 				       struct _rule_hw *eth_header);
-int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx);
 int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
 int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
 void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index af86097641b0..46bd7550adf8 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -54,7 +54,6 @@
 #include <linux/mlx5/doorbell.h>
 #include <linux/mlx5/eq.h>
 #include <linux/timecounter.h>
-#include <linux/ptp_clock_kernel.h>
 #include <net/devlink.h>
 
 #define MLX5_ADEV_NAME "mlx5_core"
@@ -679,33 +678,8 @@ struct mlx5_rsvd_gids {
 	struct ida ida;
 };
 
-#define MAX_PIN_NUM	8
-struct mlx5_pps {
-	u8                         pin_caps[MAX_PIN_NUM];
-	struct work_struct         out_work;
-	u64                        start[MAX_PIN_NUM];
-	u8                         enabled;
-	u64                        min_npps_period;
-	u64                        min_out_pulse_duration_ns;
-};
-
-struct mlx5_timer {
-	struct cyclecounter        cycles;
-	struct timecounter         tc;
-	u32                        nominal_c_mult;
-	unsigned long              overflow_period;
-};
-
-struct mlx5_clock {
-	struct mlx5_nb             pps_nb;
-	seqlock_t                  lock;
-	struct hwtstamp_config     hwtstamp_config;
-	struct ptp_clock          *ptp;
-	struct ptp_clock_info      ptp_info;
-	struct mlx5_pps            pps_info;
-	struct mlx5_timer          timer;
-};
-
+struct mlx5_clock;
+struct mlx5_clock_dev_state;
 struct mlx5_dm;
 struct mlx5_fw_tracer;
 struct mlx5_vxlan;
@@ -789,7 +763,8 @@ struct mlx5_core_dev {
 #ifdef CONFIG_MLX5_FPGA
 	struct mlx5_fpga_device *fpga;
 #endif
-	struct mlx5_clock        clock;
+	struct mlx5_clock       *clock;
+	struct mlx5_clock_dev_state *clock_state;
 	struct mlx5_ib_clock_info  *clock_info;
 	struct mlx5_fw_tracer   *tracer;
 	struct mlx5_rsc_dump    *rsc_dump;
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index e68d42b8ce65..fd625e0dd869 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -115,9 +115,12 @@ enum mlx5e_ext_link_mode {
 	MLX5E_100GAUI_1_100GBASE_CR_KR		= 11,
 	MLX5E_200GAUI_4_200GBASE_CR4_KR4	= 12,
 	MLX5E_200GAUI_2_200GBASE_CR2_KR2	= 13,
+	MLX5E_200GAUI_1_200GBASE_CR1_KR1	= 14,
 	MLX5E_400GAUI_8_400GBASE_CR8		= 15,
 	MLX5E_400GAUI_4_400GBASE_CR4_KR4	= 16,
+	MLX5E_400GAUI_2_400GBASE_CR2_KR2	= 17,
 	MLX5E_800GAUI_8_800GBASE_CR8_KR8	= 19,
+	MLX5E_800GAUI_4_800GBASE_CR4_KR4	= 20,
 	MLX5E_EXT_LINK_MODES_NUMBER,
 };
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ab550a89b9bf..9a387d456592 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -658,6 +658,7 @@ struct netdev_queue {
 	struct Qdisc __rcu	*qdisc_sleeping;
 #ifdef CONFIG_SYSFS
 	struct kobject		kobj;
+	const struct attribute_group	**groups;
 #endif
 	unsigned long		tx_maxrate;
 	/*
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 4bc2ee0b10b0..ccaaf4c7d5f6 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -43,6 +43,7 @@ extern void rtnl_lock(void);
 extern void rtnl_unlock(void);
 extern int rtnl_trylock(void);
 extern int rtnl_is_locked(void);
+extern int rtnl_lock_interruptible(void);
 extern int rtnl_lock_killable(void);
 extern bool refcount_dec_and_rtnl_lock(refcount_t *r);
 
diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
index 596836abf7bf..af40842f229d 100644
--- a/include/net/netdev_rx_queue.h
+++ b/include/net/netdev_rx_queue.h
@@ -16,6 +16,7 @@ struct netdev_rx_queue {
 	struct rps_dev_flow_table __rcu	*rps_flow_table;
 #endif
 	struct kobject			kobj;
+	const struct attribute_group	**groups;
 	struct net_device		*dev;
 	netdevice_tracker		dev_tracker;
 
diff --git a/include/net/netmem.h b/include/net/netmem.h
index 1b58faa4f20f..c61d5b21e7b4 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -24,11 +24,20 @@ struct net_iov {
 	unsigned long __unused_padding;
 	unsigned long pp_magic;
 	struct page_pool *pp;
-	struct dmabuf_genpool_chunk_owner *owner;
+	struct net_iov_area *owner;
 	unsigned long dma_addr;
 	atomic_long_t pp_ref_count;
 };
 
+struct net_iov_area {
+	/* Array of net_iovs for this area. */
+	struct net_iov *niovs;
+	size_t num_niovs;
+
+	/* Offset into the dma-buf where this chunk starts.  */
+	unsigned long base_virtual;
+};
+
 /* These fields in struct page are used by the page_pool and net stack:
  *
  *        struct {
@@ -54,6 +63,16 @@ NET_IOV_ASSERT_OFFSET(dma_addr, dma_addr);
 NET_IOV_ASSERT_OFFSET(pp_ref_count, pp_ref_count);
 #undef NET_IOV_ASSERT_OFFSET
 
+static inline struct net_iov_area *net_iov_owner(const struct net_iov *niov)
+{
+	return niov->owner;
+}
+
+static inline unsigned int net_iov_idx(const struct net_iov *niov)
+{
+	return niov - net_iov_owner(niov)->niovs;
+}
+
 /* netmem */
 
 /**
diff --git a/include/net/page_pool/memory_provider.h b/include/net/page_pool/memory_provider.h
new file mode 100644
index 000000000000..b3e665897767
--- /dev/null
+++ b/include/net/page_pool/memory_provider.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NET_PAGE_POOL_MEMORY_PROVIDER_H
+#define _NET_PAGE_POOL_MEMORY_PROVIDER_H
+
+#include <net/netmem.h>
+#include <net/page_pool/types.h>
+
+struct netdev_rx_queue;
+struct sk_buff;
+
+struct memory_provider_ops {
+	netmem_ref (*alloc_netmems)(struct page_pool *pool, gfp_t gfp);
+	bool (*release_netmem)(struct page_pool *pool, netmem_ref netmem);
+	int (*init)(struct page_pool *pool);
+	void (*destroy)(struct page_pool *pool);
+	int (*nl_fill)(void *mp_priv, struct sk_buff *rsp,
+		       struct netdev_rx_queue *rxq);
+	void (*uninstall)(void *mp_priv, struct netdev_rx_queue *rxq);
+};
+
+bool net_mp_niov_set_dma_addr(struct net_iov *niov, dma_addr_t addr);
+void net_mp_niov_set_page_pool(struct page_pool *pool, struct net_iov *niov);
+void net_mp_niov_clear_page_pool(struct net_iov *niov);
+
+int net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx,
+		    struct pp_memory_provider_params *p);
+void net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx,
+		      struct pp_memory_provider_params *old_p);
+
+/**
+  * net_mp_netmem_place_in_cache() - give a netmem to a page pool
+  * @pool:      the page pool to place the netmem into
+  * @netmem:    netmem to give
+  *
+  * Push an accounted netmem into the page pool's allocation cache. The caller
+  * must ensure that there is space in the cache. It should only be called off
+  * the mp_ops->alloc_netmems() path.
+  */
+static inline void net_mp_netmem_place_in_cache(struct page_pool *pool,
+						netmem_ref netmem)
+{
+	pool->alloc.cache[pool->alloc.count++] = netmem;
+}
+
+#endif
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 7f405672b089..36eb57d73abc 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -152,8 +152,11 @@ struct page_pool_stats {
  */
 #define PAGE_POOL_FRAG_GROUP_ALIGN	(4 * sizeof(long))
 
+struct memory_provider_ops;
+
 struct pp_memory_provider_params {
 	void *mp_priv;
+	const struct memory_provider_ops *mp_ops;
 };
 
 struct page_pool {
@@ -216,6 +219,7 @@ struct page_pool {
 	struct ptr_ring ring;
 
 	void *mp_priv;
+	const struct memory_provider_ops *mp_ops;
 
 #ifdef CONFIG_PAGE_POOL_STATS
 	/* recycle stats are per-cpu to avoid locking */
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 9b18c4cfe56f..2feba0929a8a 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -2059,6 +2059,24 @@ enum ethtool_link_mode_bit_indices {
 	ETHTOOL_LINK_MODE_10baseT1S_Half_BIT		 = 100,
 	ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT	 = 101,
 	ETHTOOL_LINK_MODE_10baseT1BRR_Full_BIT		 = 102,
+	ETHTOOL_LINK_MODE_200000baseCR_Full_BIT		 = 103,
+	ETHTOOL_LINK_MODE_200000baseKR_Full_BIT		 = 104,
+	ETHTOOL_LINK_MODE_200000baseDR_Full_BIT		 = 105,
+	ETHTOOL_LINK_MODE_200000baseDR_2_Full_BIT	 = 106,
+	ETHTOOL_LINK_MODE_200000baseSR_Full_BIT		 = 107,
+	ETHTOOL_LINK_MODE_200000baseVR_Full_BIT		 = 108,
+	ETHTOOL_LINK_MODE_400000baseCR2_Full_BIT	 = 109,
+	ETHTOOL_LINK_MODE_400000baseKR2_Full_BIT	 = 110,
+	ETHTOOL_LINK_MODE_400000baseDR2_Full_BIT	 = 111,
+	ETHTOOL_LINK_MODE_400000baseDR2_2_Full_BIT	 = 112,
+	ETHTOOL_LINK_MODE_400000baseSR2_Full_BIT	 = 113,
+	ETHTOOL_LINK_MODE_400000baseVR2_Full_BIT	 = 114,
+	ETHTOOL_LINK_MODE_800000baseCR4_Full_BIT	 = 115,
+	ETHTOOL_LINK_MODE_800000baseKR4_Full_BIT	 = 116,
+	ETHTOOL_LINK_MODE_800000baseDR4_Full_BIT	 = 117,
+	ETHTOOL_LINK_MODE_800000baseDR4_2_Full_BIT	 = 118,
+	ETHTOOL_LINK_MODE_800000baseSR4_Full_BIT	 = 119,
+	ETHTOOL_LINK_MODE_800000baseVR4_Full_BIT	 = 120,
 
 	/* must be last entry */
 	__ETHTOOL_LINK_MODE_MASK_NBITS
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 050fa8eb2e8f..1e02e94bc26d 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -87,6 +87,7 @@ struct io_uring_sqe {
 	union {
 		__s32	splice_fd_in;
 		__u32	file_index;
+		__u32	zcrx_ifq_idx;
 		__u32	optlen;
 		struct {
 			__u16	addr_len;
@@ -278,6 +279,7 @@ enum io_uring_op {
 	IORING_OP_FTRUNCATE,
 	IORING_OP_BIND,
 	IORING_OP_LISTEN,
+	IORING_OP_RECV_ZC,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -639,7 +641,8 @@ enum io_uring_register_op {
 	/* send MSG_RING without having a ring */
 	IORING_REGISTER_SEND_MSG_RING		= 31,
 
-	/* 32 reserved for zc rx */
+	/* register a netdev hw rx queue for zerocopy */
+	IORING_REGISTER_ZCRX_IFQ		= 32,
 
 	/* resize CQ ring */
 	IORING_REGISTER_RESIZE_RINGS		= 33,
@@ -956,6 +959,55 @@ enum io_uring_socket_op {
 	SOCKET_URING_OP_SETSOCKOPT,
 };
 
+/* Zero copy receive refill queue entry */
+struct io_uring_zcrx_rqe {
+	__u64	off;
+	__u32	len;
+	__u32	__pad;
+};
+
+struct io_uring_zcrx_cqe {
+	__u64	off;
+	__u64	__pad;
+};
+
+/* The bit from which area id is encoded into offsets */
+#define IORING_ZCRX_AREA_SHIFT	48
+#define IORING_ZCRX_AREA_MASK	(~(((__u64)1 << IORING_ZCRX_AREA_SHIFT) - 1))
+
+struct io_uring_zcrx_offsets {
+	__u32	head;
+	__u32	tail;
+	__u32	rqes;
+	__u32	__resv2;
+	__u64	__resv[2];
+};
+
+struct io_uring_zcrx_area_reg {
+	__u64	addr;
+	__u64	len;
+	__u64	rq_area_token;
+	__u32	flags;
+	__u32	__resv1;
+	__u64	__resv2[2];
+};
+
+/*
+ * Argument for IORING_REGISTER_ZCRX_IFQ
+ */
+struct io_uring_zcrx_ifq_reg {
+	__u32	if_idx;
+	__u32	if_rxq;
+	__u32	rq_entries;
+	__u32	flags;
+
+	__u64	area_ptr; /* pointer to struct io_uring_zcrx_area_reg */
+	__u64	region_ptr; /* struct io_uring_region_desc * */
+
+	struct io_uring_zcrx_offsets offsets;
+	__u64	__resv[4];
+};
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index e4be227d3ad6..6c6ee183802d 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -87,6 +87,11 @@ enum {
 };
 
 enum {
+	__NETDEV_A_IO_URING_PROVIDER_INFO_MAX,
+	NETDEV_A_IO_URING_PROVIDER_INFO_MAX = (__NETDEV_A_IO_URING_PROVIDER_INFO_MAX - 1)
+};
+
+enum {
 	NETDEV_A_PAGE_POOL_ID = 1,
 	NETDEV_A_PAGE_POOL_IFINDEX,
 	NETDEV_A_PAGE_POOL_NAPI_ID,
@@ -94,6 +99,7 @@ enum {
 	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
 	NETDEV_A_PAGE_POOL_DETACH_TIME,
 	NETDEV_A_PAGE_POOL_DMABUF,
+	NETDEV_A_PAGE_POOL_IO_URING,
 
 	__NETDEV_A_PAGE_POOL_MAX,
 	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
@@ -136,6 +142,7 @@ enum {
 	NETDEV_A_QUEUE_TYPE,
 	NETDEV_A_QUEUE_NAPI_ID,
 	NETDEV_A_QUEUE_DMABUF,
+	NETDEV_A_QUEUE_IO_URING,
 
 	__NETDEV_A_QUEUE_MAX,
 	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
diff --git a/io_uring/Kconfig b/io_uring/Kconfig
new file mode 100644
index 000000000000..9e2a4beba1ef
--- /dev/null
+++ b/io_uring/Kconfig
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# io_uring configuration
+#
+
+config IO_URING_ZCRX
+	def_bool y
+	depends on PAGE_POOL
+	depends on INET
+	depends on NET_RX_BUSY_POLL
diff --git a/io_uring/Makefile b/io_uring/Makefile
index d695b60dba4f..98e48339d84d 100644
--- a/io_uring/Makefile
+++ b/io_uring/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_IO_URING)		+= io_uring.o opdef.o kbuf.o rsrc.o notif.o \
 					epoll.o statx.o timeout.o fdinfo.o \
 					cancel.o waitid.o register.o \
 					truncate.o memmap.o alloc_cache.o
+obj-$(CONFIG_IO_URING_ZCRX)	+= zcrx.o
 obj-$(CONFIG_IO_WQ)		+= io-wq.o
 obj-$(CONFIG_FUTEX)		+= futex.o
 obj-$(CONFIG_NET_RX_BUSY_POLL) += napi.o
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 58003fa6b327..fa342be39158 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -97,6 +97,7 @@
 #include "uring_cmd.h"
 #include "msg_ring.h"
 #include "memmap.h"
+#include "zcrx.h"
 
 #include "timeout.h"
 #include "poll.h"
@@ -2729,6 +2730,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
 	mutex_lock(&ctx->uring_lock);
 	io_sqe_buffers_unregister(ctx);
 	io_sqe_files_unregister(ctx);
+	io_unregister_zcrx_ifqs(ctx);
 	io_cqring_overflow_kill(ctx);
 	io_eventfd_unregister(ctx);
 	io_free_alloc_caches(ctx);
@@ -2888,6 +2890,11 @@ static __cold void io_ring_exit_work(struct work_struct *work)
 			io_cqring_overflow_kill(ctx);
 			mutex_unlock(&ctx->uring_lock);
 		}
+		if (ctx->ifq) {
+			mutex_lock(&ctx->uring_lock);
+			io_shutdown_zcrx_ifqs(ctx);
+			mutex_unlock(&ctx->uring_lock);
+		}
 
 		if (ctx->flags & IORING_SETUP_DEFER_TASKRUN)
 			io_move_task_work_from_local(ctx);
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index d5c9b7a6911d..daf0e3b740ee 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -190,6 +190,16 @@ static inline bool io_get_cqe(struct io_ring_ctx *ctx, struct io_uring_cqe **ret
 	return io_get_cqe_overflow(ctx, ret, false);
 }
 
+static inline bool io_defer_get_uncommited_cqe(struct io_ring_ctx *ctx,
+					       struct io_uring_cqe **cqe_ret)
+{
+	io_lockdep_assert_cq_locked(ctx);
+
+	ctx->cq_extra++;
+	ctx->submit_state.cq_flush = true;
+	return io_get_cqe(ctx, cqe_ret);
+}
+
 static __always_inline bool io_fill_cqe_req(struct io_ring_ctx *ctx,
 					    struct io_kiocb *req)
 {
diff --git a/io_uring/memmap.c b/io_uring/memmap.c
index 361134544427..76fcc79656b0 100644
--- a/io_uring/memmap.c
+++ b/io_uring/memmap.c
@@ -271,6 +271,8 @@ static struct io_mapped_region *io_mmap_get_region(struct io_ring_ctx *ctx,
 		return io_pbuf_get_region(ctx, bgid);
 	case IORING_MAP_OFF_PARAM_REGION:
 		return &ctx->param_region;
+	case IORING_MAP_OFF_ZCRX_REGION:
+		return &ctx->zcrx_region;
 	}
 	return NULL;
 }
diff --git a/io_uring/memmap.h b/io_uring/memmap.h
index c898dcba2b4e..dad0aa5b1b45 100644
--- a/io_uring/memmap.h
+++ b/io_uring/memmap.h
@@ -2,6 +2,7 @@
 #define IO_URING_MEMMAP_H
 
 #define IORING_MAP_OFF_PARAM_REGION		0x20000000ULL
+#define IORING_MAP_OFF_ZCRX_REGION		0x30000000ULL
 
 struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages);
 
diff --git a/io_uring/net.c b/io_uring/net.c
index 6d13d378358b..905d1ee01201 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -16,6 +16,7 @@
 #include "net.h"
 #include "notif.h"
 #include "rsrc.h"
+#include "zcrx.h"
 
 #if defined(CONFIG_NET)
 struct io_shutdown {
@@ -88,6 +89,14 @@ struct io_sr_msg {
  */
 #define MULTISHOT_MAX_RETRY	32
 
+struct io_recvzc {
+	struct file			*file;
+	unsigned			msg_flags;
+	u16				flags;
+	u32				len;
+	struct io_zcrx_ifq		*ifq;
+};
+
 int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_shutdown *shutdown = io_kiocb_to_cmd(req, struct io_shutdown);
@@ -1200,6 +1209,81 @@ out_free:
 	return ret;
 }
 
+int io_recvzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_recvzc *zc = io_kiocb_to_cmd(req, struct io_recvzc);
+	unsigned ifq_idx;
+
+	if (unlikely(sqe->file_index || sqe->addr2 || sqe->addr ||
+		     sqe->addr3))
+		return -EINVAL;
+
+	ifq_idx = READ_ONCE(sqe->zcrx_ifq_idx);
+	if (ifq_idx != 0)
+		return -EINVAL;
+	zc->ifq = req->ctx->ifq;
+	if (!zc->ifq)
+		return -EINVAL;
+	zc->len = READ_ONCE(sqe->len);
+	zc->flags = READ_ONCE(sqe->ioprio);
+	zc->msg_flags = READ_ONCE(sqe->msg_flags);
+	if (zc->msg_flags)
+		return -EINVAL;
+	if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST | IORING_RECV_MULTISHOT))
+		return -EINVAL;
+	/* multishot required */
+	if (!(zc->flags & IORING_RECV_MULTISHOT))
+		return -EINVAL;
+	/* All data completions are posted as aux CQEs. */
+	req->flags |= REQ_F_APOLL_MULTISHOT;
+
+	return 0;
+}
+
+int io_recvzc(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_recvzc *zc = io_kiocb_to_cmd(req, struct io_recvzc);
+	struct socket *sock;
+	unsigned int len;
+	int ret;
+
+	if (!(req->flags & REQ_F_POLLED) &&
+	    (zc->flags & IORING_RECVSEND_POLL_FIRST))
+		return -EAGAIN;
+
+	sock = sock_from_file(req->file);
+	if (unlikely(!sock))
+		return -ENOTSOCK;
+
+	len = zc->len;
+	ret = io_zcrx_recv(req, zc->ifq, sock, zc->msg_flags | MSG_DONTWAIT,
+			   issue_flags, &zc->len);
+	if (len && zc->len == 0) {
+		io_req_set_res(req, 0, 0);
+
+		if (issue_flags & IO_URING_F_MULTISHOT)
+			return IOU_STOP_MULTISHOT;
+		return IOU_OK;
+	}
+	if (unlikely(ret <= 0) && ret != -EAGAIN) {
+		if (ret == -ERESTARTSYS)
+			ret = -EINTR;
+		if (ret == IOU_REQUEUE)
+			return IOU_REQUEUE;
+
+		req_set_fail(req);
+		io_req_set_res(req, ret, 0);
+
+		if (issue_flags & IO_URING_F_MULTISHOT)
+			return IOU_STOP_MULTISHOT;
+		return IOU_OK;
+	}
+
+	if (issue_flags & IO_URING_F_MULTISHOT)
+		return IOU_ISSUE_SKIP_COMPLETE;
+	return -EAGAIN;
+}
+
 void io_send_zc_cleanup(struct io_kiocb *req)
 {
 	struct io_sr_msg *zc = io_kiocb_to_cmd(req, struct io_sr_msg);
diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index 306fd9c48b44..9511262c513e 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -37,6 +37,7 @@
 #include "waitid.h"
 #include "futex.h"
 #include "truncate.h"
+#include "zcrx.h"
 
 static int io_no_issue(struct io_kiocb *req, unsigned int issue_flags)
 {
@@ -516,6 +517,18 @@ const struct io_issue_def io_issue_defs[] = {
 		.prep			= io_eopnotsupp_prep,
 #endif
 	},
+	[IORING_OP_RECV_ZC] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollin			= 1,
+		.ioprio			= 1,
+#if defined(CONFIG_NET)
+		.prep			= io_recvzc_prep,
+		.issue			= io_recvzc,
+#else
+		.prep			= io_eopnotsupp_prep,
+#endif
+	},
 };
 
 const struct io_cold_def io_cold_defs[] = {
@@ -745,6 +758,9 @@ const struct io_cold_def io_cold_defs[] = {
 	[IORING_OP_LISTEN] = {
 		.name			= "LISTEN",
 	},
+	[IORING_OP_RECV_ZC] = {
+		.name			= "RECV_ZC",
+	},
 };
 
 const char *io_uring_get_opcode(u8 opcode)
diff --git a/io_uring/register.c b/io_uring/register.c
index 9a4d2fbce4ae..cc23a4c205cd 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -30,6 +30,7 @@
 #include "eventfd.h"
 #include "msg_ring.h"
 #include "memmap.h"
+#include "zcrx.h"
 
 #define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
 				 IORING_REGISTER_LAST + IORING_OP_LAST)
@@ -813,6 +814,12 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_register_clone_buffers(ctx, arg);
 		break;
+	case IORING_REGISTER_ZCRX_IFQ:
+		ret = -EINVAL;
+		if (!arg || nr_args != 1)
+			break;
+		ret = io_register_zcrx_ifq(ctx, arg);
+		break;
 	case IORING_REGISTER_RESIZE_RINGS:
 		ret = -EINVAL;
 		if (!arg || nr_args != 1)
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 5dd1e0827559..28783f1dde00 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -80,7 +80,7 @@ static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages)
 	return 0;
 }
 
-static int io_buffer_validate(struct iovec *iov)
+int io_buffer_validate(struct iovec *iov)
 {
 	unsigned long tmp, acct_len = iov->iov_len + (PAGE_SIZE - 1);
 
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index f10a1252b3e9..284e300e63fb 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -76,6 +76,7 @@ int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
 			    unsigned size, unsigned type);
 int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
 			unsigned int size, unsigned int type);
+int io_buffer_validate(struct iovec *iov);
 
 bool io_check_coalesce_buffer(struct page **page_array, int nr_pages,
 			      struct io_imu_folio_data *data);
diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
new file mode 100644
index 000000000000..9c95b5b6ec4e
--- /dev/null
+++ b/io_uring/zcrx.c
@@ -0,0 +1,960 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/dma-map-ops.h>
+#include <linux/mm.h>
+#include <linux/nospec.h>
+#include <linux/io_uring.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/skbuff_ref.h>
+
+#include <net/page_pool/helpers.h>
+#include <net/page_pool/memory_provider.h>
+#include <net/netlink.h>
+#include <net/netdev_rx_queue.h>
+#include <net/tcp.h>
+#include <net/rps.h>
+
+#include <trace/events/page_pool.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "kbuf.h"
+#include "memmap.h"
+#include "zcrx.h"
+#include "rsrc.h"
+
+#define IO_DMA_ATTR (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
+static void __io_zcrx_unmap_area(struct io_zcrx_ifq *ifq,
+				 struct io_zcrx_area *area, int nr_mapped)
+{
+	int i;
+
+	for (i = 0; i < nr_mapped; i++) {
+		struct net_iov *niov = &area->nia.niovs[i];
+		dma_addr_t dma;
+
+		dma = page_pool_get_dma_addr_netmem(net_iov_to_netmem(niov));
+		dma_unmap_page_attrs(ifq->dev, dma, PAGE_SIZE,
+				     DMA_FROM_DEVICE, IO_DMA_ATTR);
+		net_mp_niov_set_dma_addr(niov, 0);
+	}
+}
+
+static void io_zcrx_unmap_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area)
+{
+	if (area->is_mapped)
+		__io_zcrx_unmap_area(ifq, area, area->nia.num_niovs);
+}
+
+static int io_zcrx_map_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area)
+{
+	int i;
+
+	for (i = 0; i < area->nia.num_niovs; i++) {
+		struct net_iov *niov = &area->nia.niovs[i];
+		dma_addr_t dma;
+
+		dma = dma_map_page_attrs(ifq->dev, area->pages[i], 0, PAGE_SIZE,
+					 DMA_FROM_DEVICE, IO_DMA_ATTR);
+		if (dma_mapping_error(ifq->dev, dma))
+			break;
+		if (net_mp_niov_set_dma_addr(niov, dma)) {
+			dma_unmap_page_attrs(ifq->dev, dma, PAGE_SIZE,
+					     DMA_FROM_DEVICE, IO_DMA_ATTR);
+			break;
+		}
+	}
+
+	if (i != area->nia.num_niovs) {
+		__io_zcrx_unmap_area(ifq, area, i);
+		return -EINVAL;
+	}
+
+	area->is_mapped = true;
+	return 0;
+}
+
+static void io_zcrx_sync_for_device(const struct page_pool *pool,
+				    struct net_iov *niov)
+{
+#if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC)
+	dma_addr_t dma_addr;
+
+	if (!dma_dev_need_sync(pool->p.dev))
+		return;
+
+	dma_addr = page_pool_get_dma_addr_netmem(net_iov_to_netmem(niov));
+	__dma_sync_single_for_device(pool->p.dev, dma_addr + pool->p.offset,
+				     PAGE_SIZE, pool->p.dma_dir);
+#endif
+}
+
+#define IO_RQ_MAX_ENTRIES		32768
+
+#define IO_SKBS_PER_CALL_LIMIT	20
+
+struct io_zcrx_args {
+	struct io_kiocb		*req;
+	struct io_zcrx_ifq	*ifq;
+	struct socket		*sock;
+	unsigned		nr_skbs;
+};
+
+static const struct memory_provider_ops io_uring_pp_zc_ops;
+
+static inline struct io_zcrx_area *io_zcrx_iov_to_area(const struct net_iov *niov)
+{
+	struct net_iov_area *owner = net_iov_owner(niov);
+
+	return container_of(owner, struct io_zcrx_area, nia);
+}
+
+static inline atomic_t *io_get_user_counter(struct net_iov *niov)
+{
+	struct io_zcrx_area *area = io_zcrx_iov_to_area(niov);
+
+	return &area->user_refs[net_iov_idx(niov)];
+}
+
+static bool io_zcrx_put_niov_uref(struct net_iov *niov)
+{
+	atomic_t *uref = io_get_user_counter(niov);
+
+	if (unlikely(!atomic_read(uref)))
+		return false;
+	atomic_dec(uref);
+	return true;
+}
+
+static void io_zcrx_get_niov_uref(struct net_iov *niov)
+{
+	atomic_inc(io_get_user_counter(niov));
+}
+
+static inline struct page *io_zcrx_iov_page(const struct net_iov *niov)
+{
+	struct io_zcrx_area *area = io_zcrx_iov_to_area(niov);
+
+	return area->pages[net_iov_idx(niov)];
+}
+
+static int io_allocate_rbuf_ring(struct io_zcrx_ifq *ifq,
+				 struct io_uring_zcrx_ifq_reg *reg,
+				 struct io_uring_region_desc *rd)
+{
+	size_t off, size;
+	void *ptr;
+	int ret;
+
+	off = sizeof(struct io_uring);
+	size = off + sizeof(struct io_uring_zcrx_rqe) * reg->rq_entries;
+	if (size > rd->size)
+		return -EINVAL;
+
+	ret = io_create_region_mmap_safe(ifq->ctx, &ifq->ctx->zcrx_region, rd,
+					 IORING_MAP_OFF_ZCRX_REGION);
+	if (ret < 0)
+		return ret;
+
+	ptr = io_region_get_ptr(&ifq->ctx->zcrx_region);
+	ifq->rq_ring = (struct io_uring *)ptr;
+	ifq->rqes = (struct io_uring_zcrx_rqe *)(ptr + off);
+	return 0;
+}
+
+static void io_free_rbuf_ring(struct io_zcrx_ifq *ifq)
+{
+	io_free_region(ifq->ctx, &ifq->ctx->zcrx_region);
+	ifq->rq_ring = NULL;
+	ifq->rqes = NULL;
+}
+
+static void io_zcrx_free_area(struct io_zcrx_area *area)
+{
+	io_zcrx_unmap_area(area->ifq, area);
+
+	kvfree(area->freelist);
+	kvfree(area->nia.niovs);
+	kvfree(area->user_refs);
+	if (area->pages) {
+		unpin_user_pages(area->pages, area->nia.num_niovs);
+		kvfree(area->pages);
+	}
+	kfree(area);
+}
+
+static int io_zcrx_create_area(struct io_zcrx_ifq *ifq,
+			       struct io_zcrx_area **res,
+			       struct io_uring_zcrx_area_reg *area_reg)
+{
+	struct io_zcrx_area *area;
+	int i, ret, nr_pages;
+	struct iovec iov;
+
+	if (area_reg->flags || area_reg->rq_area_token)
+		return -EINVAL;
+	if (area_reg->__resv1 || area_reg->__resv2[0] || area_reg->__resv2[1])
+		return -EINVAL;
+	if (area_reg->addr & ~PAGE_MASK || area_reg->len & ~PAGE_MASK)
+		return -EINVAL;
+
+	iov.iov_base = u64_to_user_ptr(area_reg->addr);
+	iov.iov_len = area_reg->len;
+	ret = io_buffer_validate(&iov);
+	if (ret)
+		return ret;
+
+	ret = -ENOMEM;
+	area = kzalloc(sizeof(*area), GFP_KERNEL);
+	if (!area)
+		goto err;
+
+	area->pages = io_pin_pages((unsigned long)area_reg->addr, area_reg->len,
+				   &nr_pages);
+	if (IS_ERR(area->pages)) {
+		ret = PTR_ERR(area->pages);
+		area->pages = NULL;
+		goto err;
+	}
+	area->nia.num_niovs = nr_pages;
+
+	area->nia.niovs = kvmalloc_array(nr_pages, sizeof(area->nia.niovs[0]),
+					 GFP_KERNEL | __GFP_ZERO);
+	if (!area->nia.niovs)
+		goto err;
+
+	area->freelist = kvmalloc_array(nr_pages, sizeof(area->freelist[0]),
+					GFP_KERNEL | __GFP_ZERO);
+	if (!area->freelist)
+		goto err;
+
+	for (i = 0; i < nr_pages; i++)
+		area->freelist[i] = i;
+
+	area->user_refs = kvmalloc_array(nr_pages, sizeof(area->user_refs[0]),
+					GFP_KERNEL | __GFP_ZERO);
+	if (!area->user_refs)
+		goto err;
+
+	for (i = 0; i < nr_pages; i++) {
+		struct net_iov *niov = &area->nia.niovs[i];
+
+		niov->owner = &area->nia;
+		area->freelist[i] = i;
+		atomic_set(&area->user_refs[i], 0);
+	}
+
+	area->free_count = nr_pages;
+	area->ifq = ifq;
+	/* we're only supporting one area per ifq for now */
+	area->area_id = 0;
+	area_reg->rq_area_token = (u64)area->area_id << IORING_ZCRX_AREA_SHIFT;
+	spin_lock_init(&area->freelist_lock);
+	*res = area;
+	return 0;
+err:
+	if (area)
+		io_zcrx_free_area(area);
+	return ret;
+}
+
+static struct io_zcrx_ifq *io_zcrx_ifq_alloc(struct io_ring_ctx *ctx)
+{
+	struct io_zcrx_ifq *ifq;
+
+	ifq = kzalloc(sizeof(*ifq), GFP_KERNEL);
+	if (!ifq)
+		return NULL;
+
+	ifq->if_rxq = -1;
+	ifq->ctx = ctx;
+	spin_lock_init(&ifq->lock);
+	spin_lock_init(&ifq->rq_lock);
+	return ifq;
+}
+
+static void io_zcrx_drop_netdev(struct io_zcrx_ifq *ifq)
+{
+	spin_lock(&ifq->lock);
+	if (ifq->netdev) {
+		netdev_put(ifq->netdev, &ifq->netdev_tracker);
+		ifq->netdev = NULL;
+	}
+	spin_unlock(&ifq->lock);
+}
+
+static void io_close_queue(struct io_zcrx_ifq *ifq)
+{
+	struct net_device *netdev;
+	netdevice_tracker netdev_tracker;
+	struct pp_memory_provider_params p = {
+		.mp_ops = &io_uring_pp_zc_ops,
+		.mp_priv = ifq,
+	};
+
+	if (ifq->if_rxq == -1)
+		return;
+
+	spin_lock(&ifq->lock);
+	netdev = ifq->netdev;
+	netdev_tracker = ifq->netdev_tracker;
+	ifq->netdev = NULL;
+	spin_unlock(&ifq->lock);
+
+	if (netdev) {
+		net_mp_close_rxq(netdev, ifq->if_rxq, &p);
+		netdev_put(netdev, &netdev_tracker);
+	}
+	ifq->if_rxq = -1;
+}
+
+static void io_zcrx_ifq_free(struct io_zcrx_ifq *ifq)
+{
+	io_close_queue(ifq);
+	io_zcrx_drop_netdev(ifq);
+
+	if (ifq->area)
+		io_zcrx_free_area(ifq->area);
+	if (ifq->dev)
+		put_device(ifq->dev);
+
+	io_free_rbuf_ring(ifq);
+	kfree(ifq);
+}
+
+int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
+			  struct io_uring_zcrx_ifq_reg __user *arg)
+{
+	struct pp_memory_provider_params mp_param = {};
+	struct io_uring_zcrx_area_reg area;
+	struct io_uring_zcrx_ifq_reg reg;
+	struct io_uring_region_desc rd;
+	struct io_zcrx_ifq *ifq;
+	int ret;
+
+	/*
+	 * 1. Interface queue allocation.
+	 * 2. It can observe data destined for sockets of other tasks.
+	 */
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	/* mandatory io_uring features for zc rx */
+	if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN &&
+	      ctx->flags & IORING_SETUP_CQE32))
+		return -EINVAL;
+	if (ctx->ifq)
+		return -EBUSY;
+	if (copy_from_user(&reg, arg, sizeof(reg)))
+		return -EFAULT;
+	if (copy_from_user(&rd, u64_to_user_ptr(reg.region_ptr), sizeof(rd)))
+		return -EFAULT;
+	if (memchr_inv(&reg.__resv, 0, sizeof(reg.__resv)))
+		return -EINVAL;
+	if (reg.if_rxq == -1 || !reg.rq_entries || reg.flags)
+		return -EINVAL;
+	if (reg.rq_entries > IO_RQ_MAX_ENTRIES) {
+		if (!(ctx->flags & IORING_SETUP_CLAMP))
+			return -EINVAL;
+		reg.rq_entries = IO_RQ_MAX_ENTRIES;
+	}
+	reg.rq_entries = roundup_pow_of_two(reg.rq_entries);
+
+	if (copy_from_user(&area, u64_to_user_ptr(reg.area_ptr), sizeof(area)))
+		return -EFAULT;
+
+	ifq = io_zcrx_ifq_alloc(ctx);
+	if (!ifq)
+		return -ENOMEM;
+
+	ret = io_allocate_rbuf_ring(ifq, &reg, &rd);
+	if (ret)
+		goto err;
+
+	ret = io_zcrx_create_area(ifq, &ifq->area, &area);
+	if (ret)
+		goto err;
+
+	ifq->rq_entries = reg.rq_entries;
+
+	ret = -ENODEV;
+	ifq->netdev = netdev_get_by_index(current->nsproxy->net_ns, reg.if_idx,
+					  &ifq->netdev_tracker, GFP_KERNEL);
+	if (!ifq->netdev)
+		goto err;
+
+	ifq->dev = ifq->netdev->dev.parent;
+	ret = -EOPNOTSUPP;
+	if (!ifq->dev)
+		goto err;
+	get_device(ifq->dev);
+
+	ret = io_zcrx_map_area(ifq, ifq->area);
+	if (ret)
+		goto err;
+
+	mp_param.mp_ops = &io_uring_pp_zc_ops;
+	mp_param.mp_priv = ifq;
+	ret = net_mp_open_rxq(ifq->netdev, reg.if_rxq, &mp_param);
+	if (ret)
+		goto err;
+	ifq->if_rxq = reg.if_rxq;
+
+	reg.offsets.rqes = sizeof(struct io_uring);
+	reg.offsets.head = offsetof(struct io_uring, head);
+	reg.offsets.tail = offsetof(struct io_uring, tail);
+
+	if (copy_to_user(arg, &reg, sizeof(reg)) ||
+	    copy_to_user(u64_to_user_ptr(reg.region_ptr), &rd, sizeof(rd)) ||
+	    copy_to_user(u64_to_user_ptr(reg.area_ptr), &area, sizeof(area))) {
+		ret = -EFAULT;
+		goto err;
+	}
+	ctx->ifq = ifq;
+	return 0;
+err:
+	io_zcrx_ifq_free(ifq);
+	return ret;
+}
+
+void io_unregister_zcrx_ifqs(struct io_ring_ctx *ctx)
+{
+	struct io_zcrx_ifq *ifq = ctx->ifq;
+
+	lockdep_assert_held(&ctx->uring_lock);
+
+	if (!ifq)
+		return;
+
+	ctx->ifq = NULL;
+	io_zcrx_ifq_free(ifq);
+}
+
+static struct net_iov *__io_zcrx_get_free_niov(struct io_zcrx_area *area)
+{
+	unsigned niov_idx;
+
+	lockdep_assert_held(&area->freelist_lock);
+
+	niov_idx = area->freelist[--area->free_count];
+	return &area->nia.niovs[niov_idx];
+}
+
+static void io_zcrx_return_niov_freelist(struct net_iov *niov)
+{
+	struct io_zcrx_area *area = io_zcrx_iov_to_area(niov);
+
+	spin_lock_bh(&area->freelist_lock);
+	area->freelist[area->free_count++] = net_iov_idx(niov);
+	spin_unlock_bh(&area->freelist_lock);
+}
+
+static void io_zcrx_return_niov(struct net_iov *niov)
+{
+	netmem_ref netmem = net_iov_to_netmem(niov);
+
+	if (!niov->pp) {
+		/* copy fallback allocated niovs */
+		io_zcrx_return_niov_freelist(niov);
+		return;
+	}
+	page_pool_put_unrefed_netmem(niov->pp, netmem, -1, false);
+}
+
+static void io_zcrx_scrub(struct io_zcrx_ifq *ifq)
+{
+	struct io_zcrx_area *area = ifq->area;
+	int i;
+
+	if (!area)
+		return;
+
+	/* Reclaim back all buffers given to the user space. */
+	for (i = 0; i < area->nia.num_niovs; i++) {
+		struct net_iov *niov = &area->nia.niovs[i];
+		int nr;
+
+		if (!atomic_read(io_get_user_counter(niov)))
+			continue;
+		nr = atomic_xchg(io_get_user_counter(niov), 0);
+		if (nr && !page_pool_unref_netmem(net_iov_to_netmem(niov), nr))
+			io_zcrx_return_niov(niov);
+	}
+}
+
+void io_shutdown_zcrx_ifqs(struct io_ring_ctx *ctx)
+{
+	lockdep_assert_held(&ctx->uring_lock);
+
+	if (!ctx->ifq)
+		return;
+	io_zcrx_scrub(ctx->ifq);
+	io_close_queue(ctx->ifq);
+}
+
+static inline u32 io_zcrx_rqring_entries(struct io_zcrx_ifq *ifq)
+{
+	u32 entries;
+
+	entries = smp_load_acquire(&ifq->rq_ring->tail) - ifq->cached_rq_head;
+	return min(entries, ifq->rq_entries);
+}
+
+static struct io_uring_zcrx_rqe *io_zcrx_get_rqe(struct io_zcrx_ifq *ifq,
+						 unsigned mask)
+{
+	unsigned int idx = ifq->cached_rq_head++ & mask;
+
+	return &ifq->rqes[idx];
+}
+
+static void io_zcrx_ring_refill(struct page_pool *pp,
+				struct io_zcrx_ifq *ifq)
+{
+	unsigned int mask = ifq->rq_entries - 1;
+	unsigned int entries;
+	netmem_ref netmem;
+
+	spin_lock_bh(&ifq->rq_lock);
+
+	entries = io_zcrx_rqring_entries(ifq);
+	entries = min_t(unsigned, entries, PP_ALLOC_CACHE_REFILL - pp->alloc.count);
+	if (unlikely(!entries)) {
+		spin_unlock_bh(&ifq->rq_lock);
+		return;
+	}
+
+	do {
+		struct io_uring_zcrx_rqe *rqe = io_zcrx_get_rqe(ifq, mask);
+		struct io_zcrx_area *area;
+		struct net_iov *niov;
+		unsigned niov_idx, area_idx;
+
+		area_idx = rqe->off >> IORING_ZCRX_AREA_SHIFT;
+		niov_idx = (rqe->off & ~IORING_ZCRX_AREA_MASK) >> PAGE_SHIFT;
+
+		if (unlikely(rqe->__pad || area_idx))
+			continue;
+		area = ifq->area;
+
+		if (unlikely(niov_idx >= area->nia.num_niovs))
+			continue;
+		niov_idx = array_index_nospec(niov_idx, area->nia.num_niovs);
+
+		niov = &area->nia.niovs[niov_idx];
+		if (!io_zcrx_put_niov_uref(niov))
+			continue;
+
+		netmem = net_iov_to_netmem(niov);
+		if (page_pool_unref_netmem(netmem, 1) != 0)
+			continue;
+
+		if (unlikely(niov->pp != pp)) {
+			io_zcrx_return_niov(niov);
+			continue;
+		}
+
+		io_zcrx_sync_for_device(pp, niov);
+		net_mp_netmem_place_in_cache(pp, netmem);
+	} while (--entries);
+
+	smp_store_release(&ifq->rq_ring->head, ifq->cached_rq_head);
+	spin_unlock_bh(&ifq->rq_lock);
+}
+
+static void io_zcrx_refill_slow(struct page_pool *pp, struct io_zcrx_ifq *ifq)
+{
+	struct io_zcrx_area *area = ifq->area;
+
+	spin_lock_bh(&area->freelist_lock);
+	while (area->free_count && pp->alloc.count < PP_ALLOC_CACHE_REFILL) {
+		struct net_iov *niov = __io_zcrx_get_free_niov(area);
+		netmem_ref netmem = net_iov_to_netmem(niov);
+
+		net_mp_niov_set_page_pool(pp, niov);
+		io_zcrx_sync_for_device(pp, niov);
+		net_mp_netmem_place_in_cache(pp, netmem);
+	}
+	spin_unlock_bh(&area->freelist_lock);
+}
+
+static netmem_ref io_pp_zc_alloc_netmems(struct page_pool *pp, gfp_t gfp)
+{
+	struct io_zcrx_ifq *ifq = pp->mp_priv;
+
+	/* pp should already be ensuring that */
+	if (unlikely(pp->alloc.count))
+		goto out_return;
+
+	io_zcrx_ring_refill(pp, ifq);
+	if (likely(pp->alloc.count))
+		goto out_return;
+
+	io_zcrx_refill_slow(pp, ifq);
+	if (!pp->alloc.count)
+		return 0;
+out_return:
+	return pp->alloc.cache[--pp->alloc.count];
+}
+
+static bool io_pp_zc_release_netmem(struct page_pool *pp, netmem_ref netmem)
+{
+	struct net_iov *niov;
+
+	if (WARN_ON_ONCE(!netmem_is_net_iov(netmem)))
+		return false;
+
+	niov = netmem_to_net_iov(netmem);
+	net_mp_niov_clear_page_pool(niov);
+	io_zcrx_return_niov_freelist(niov);
+	return false;
+}
+
+static int io_pp_zc_init(struct page_pool *pp)
+{
+	struct io_zcrx_ifq *ifq = pp->mp_priv;
+
+	if (WARN_ON_ONCE(!ifq))
+		return -EINVAL;
+	if (WARN_ON_ONCE(ifq->dev != pp->p.dev))
+		return -EINVAL;
+	if (WARN_ON_ONCE(!pp->dma_map))
+		return -EOPNOTSUPP;
+	if (pp->p.order != 0)
+		return -EOPNOTSUPP;
+	if (pp->p.dma_dir != DMA_FROM_DEVICE)
+		return -EOPNOTSUPP;
+
+	percpu_ref_get(&ifq->ctx->refs);
+	return 0;
+}
+
+static void io_pp_zc_destroy(struct page_pool *pp)
+{
+	struct io_zcrx_ifq *ifq = pp->mp_priv;
+	struct io_zcrx_area *area = ifq->area;
+
+	if (WARN_ON_ONCE(area->free_count != area->nia.num_niovs))
+		return;
+	percpu_ref_put(&ifq->ctx->refs);
+}
+
+static int io_pp_nl_fill(void *mp_priv, struct sk_buff *rsp,
+			 struct netdev_rx_queue *rxq)
+{
+	struct nlattr *nest;
+	int type;
+
+	type = rxq ? NETDEV_A_QUEUE_IO_URING : NETDEV_A_PAGE_POOL_IO_URING;
+	nest = nla_nest_start(rsp, type);
+	if (!nest)
+		return -EMSGSIZE;
+	nla_nest_end(rsp, nest);
+
+	return 0;
+}
+
+static void io_pp_uninstall(void *mp_priv, struct netdev_rx_queue *rxq)
+{
+	struct pp_memory_provider_params *p = &rxq->mp_params;
+	struct io_zcrx_ifq *ifq = mp_priv;
+
+	io_zcrx_drop_netdev(ifq);
+	p->mp_ops = NULL;
+	p->mp_priv = NULL;
+}
+
+static const struct memory_provider_ops io_uring_pp_zc_ops = {
+	.alloc_netmems		= io_pp_zc_alloc_netmems,
+	.release_netmem		= io_pp_zc_release_netmem,
+	.init			= io_pp_zc_init,
+	.destroy		= io_pp_zc_destroy,
+	.nl_fill		= io_pp_nl_fill,
+	.uninstall		= io_pp_uninstall,
+};
+
+static bool io_zcrx_queue_cqe(struct io_kiocb *req, struct net_iov *niov,
+			      struct io_zcrx_ifq *ifq, int off, int len)
+{
+	struct io_uring_zcrx_cqe *rcqe;
+	struct io_zcrx_area *area;
+	struct io_uring_cqe *cqe;
+	u64 offset;
+
+	if (!io_defer_get_uncommited_cqe(req->ctx, &cqe))
+		return false;
+
+	cqe->user_data = req->cqe.user_data;
+	cqe->res = len;
+	cqe->flags = IORING_CQE_F_MORE;
+
+	area = io_zcrx_iov_to_area(niov);
+	offset = off + (net_iov_idx(niov) << PAGE_SHIFT);
+	rcqe = (struct io_uring_zcrx_cqe *)(cqe + 1);
+	rcqe->off = offset + ((u64)area->area_id << IORING_ZCRX_AREA_SHIFT);
+	rcqe->__pad = 0;
+	return true;
+}
+
+static struct net_iov *io_zcrx_alloc_fallback(struct io_zcrx_area *area)
+{
+	struct net_iov *niov = NULL;
+
+	spin_lock_bh(&area->freelist_lock);
+	if (area->free_count)
+		niov = __io_zcrx_get_free_niov(area);
+	spin_unlock_bh(&area->freelist_lock);
+
+	if (niov)
+		page_pool_fragment_netmem(net_iov_to_netmem(niov), 1);
+	return niov;
+}
+
+static ssize_t io_zcrx_copy_chunk(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+				  void *src_base, struct page *src_page,
+				  unsigned int src_offset, size_t len)
+{
+	struct io_zcrx_area *area = ifq->area;
+	size_t copied = 0;
+	int ret = 0;
+
+	while (len) {
+		size_t copy_size = min_t(size_t, PAGE_SIZE, len);
+		const int dst_off = 0;
+		struct net_iov *niov;
+		struct page *dst_page;
+		void *dst_addr;
+
+		niov = io_zcrx_alloc_fallback(area);
+		if (!niov) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		dst_page = io_zcrx_iov_page(niov);
+		dst_addr = kmap_local_page(dst_page);
+		if (src_page)
+			src_base = kmap_local_page(src_page);
+
+		memcpy(dst_addr, src_base + src_offset, copy_size);
+
+		if (src_page)
+			kunmap_local(src_base);
+		kunmap_local(dst_addr);
+
+		if (!io_zcrx_queue_cqe(req, niov, ifq, dst_off, copy_size)) {
+			io_zcrx_return_niov(niov);
+			ret = -ENOSPC;
+			break;
+		}
+
+		io_zcrx_get_niov_uref(niov);
+		src_offset += copy_size;
+		len -= copy_size;
+		copied += copy_size;
+	}
+
+	return copied ? copied : ret;
+}
+
+static int io_zcrx_copy_frag(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+			     const skb_frag_t *frag, int off, int len)
+{
+	struct page *page = skb_frag_page(frag);
+	u32 p_off, p_len, t, copied = 0;
+	int ret = 0;
+
+	off += skb_frag_off(frag);
+
+	skb_frag_foreach_page(frag, off, len,
+			      page, p_off, p_len, t) {
+		ret = io_zcrx_copy_chunk(req, ifq, NULL, page, p_off, p_len);
+		if (ret < 0)
+			return copied ? copied : ret;
+		copied += ret;
+	}
+	return copied;
+}
+
+static int io_zcrx_recv_frag(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+			     const skb_frag_t *frag, int off, int len)
+{
+	struct net_iov *niov;
+
+	if (unlikely(!skb_frag_is_net_iov(frag)))
+		return io_zcrx_copy_frag(req, ifq, frag, off, len);
+
+	niov = netmem_to_net_iov(frag->netmem);
+	if (niov->pp->mp_ops != &io_uring_pp_zc_ops ||
+	    niov->pp->mp_priv != ifq)
+		return -EFAULT;
+
+	if (!io_zcrx_queue_cqe(req, niov, ifq, off + skb_frag_off(frag), len))
+		return -ENOSPC;
+
+	/*
+	 * Prevent it from being recycled while user is accessing it.
+	 * It has to be done before grabbing a user reference.
+	 */
+	page_pool_ref_netmem(net_iov_to_netmem(niov));
+	io_zcrx_get_niov_uref(niov);
+	return len;
+}
+
+static int
+io_zcrx_recv_skb(read_descriptor_t *desc, struct sk_buff *skb,
+		 unsigned int offset, size_t len)
+{
+	struct io_zcrx_args *args = desc->arg.data;
+	struct io_zcrx_ifq *ifq = args->ifq;
+	struct io_kiocb *req = args->req;
+	struct sk_buff *frag_iter;
+	unsigned start, start_off = offset;
+	int i, copy, end, off;
+	int ret = 0;
+
+	len = min_t(size_t, len, desc->count);
+	if (unlikely(args->nr_skbs++ > IO_SKBS_PER_CALL_LIMIT))
+		return -EAGAIN;
+
+	if (unlikely(offset < skb_headlen(skb))) {
+		ssize_t copied;
+		size_t to_copy;
+
+		to_copy = min_t(size_t, skb_headlen(skb) - offset, len);
+		copied = io_zcrx_copy_chunk(req, ifq, skb->data, NULL,
+					    offset, to_copy);
+		if (copied < 0) {
+			ret = copied;
+			goto out;
+		}
+		offset += copied;
+		len -= copied;
+		if (!len)
+			goto out;
+		if (offset != skb_headlen(skb))
+			goto out;
+	}
+
+	start = skb_headlen(skb);
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		const skb_frag_t *frag;
+
+		if (WARN_ON(start > offset + len))
+			return -EFAULT;
+
+		frag = &skb_shinfo(skb)->frags[i];
+		end = start + skb_frag_size(frag);
+
+		if (offset < end) {
+			copy = end - offset;
+			if (copy > len)
+				copy = len;
+
+			off = offset - start;
+			ret = io_zcrx_recv_frag(req, ifq, frag, off, copy);
+			if (ret < 0)
+				goto out;
+
+			offset += ret;
+			len -= ret;
+			if (len == 0 || ret != copy)
+				goto out;
+		}
+		start = end;
+	}
+
+	skb_walk_frags(skb, frag_iter) {
+		if (WARN_ON(start > offset + len))
+			return -EFAULT;
+
+		end = start + frag_iter->len;
+		if (offset < end) {
+			copy = end - offset;
+			if (copy > len)
+				copy = len;
+
+			off = offset - start;
+			ret = io_zcrx_recv_skb(desc, frag_iter, off, copy);
+			if (ret < 0)
+				goto out;
+
+			offset += ret;
+			len -= ret;
+			if (len == 0 || ret != copy)
+				goto out;
+		}
+		start = end;
+	}
+
+out:
+	if (offset == start_off)
+		return ret;
+	desc->count -= (offset - start_off);
+	return offset - start_off;
+}
+
+static int io_zcrx_tcp_recvmsg(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+				struct sock *sk, int flags,
+				unsigned issue_flags, unsigned int *outlen)
+{
+	unsigned int len = *outlen;
+	struct io_zcrx_args args = {
+		.req = req,
+		.ifq = ifq,
+		.sock = sk->sk_socket,
+	};
+	read_descriptor_t rd_desc = {
+		.count = len ? len : UINT_MAX,
+		.arg.data = &args,
+	};
+	int ret;
+
+	lock_sock(sk);
+	ret = tcp_read_sock(sk, &rd_desc, io_zcrx_recv_skb);
+	if (len && ret > 0)
+		*outlen = len - ret;
+	if (ret <= 0) {
+		if (ret < 0 || sock_flag(sk, SOCK_DONE))
+			goto out;
+		if (sk->sk_err)
+			ret = sock_error(sk);
+		else if (sk->sk_shutdown & RCV_SHUTDOWN)
+			goto out;
+		else if (sk->sk_state == TCP_CLOSE)
+			ret = -ENOTCONN;
+		else
+			ret = -EAGAIN;
+	} else if (unlikely(args.nr_skbs > IO_SKBS_PER_CALL_LIMIT) &&
+		   (issue_flags & IO_URING_F_MULTISHOT)) {
+		ret = IOU_REQUEUE;
+	} else if (sock_flag(sk, SOCK_DONE)) {
+		/* Make it to retry until it finally gets 0. */
+		if (issue_flags & IO_URING_F_MULTISHOT)
+			ret = IOU_REQUEUE;
+		else
+			ret = -EAGAIN;
+	}
+out:
+	release_sock(sk);
+	return ret;
+}
+
+int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+		 struct socket *sock, unsigned int flags,
+		 unsigned issue_flags, unsigned int *len)
+{
+	struct sock *sk = sock->sk;
+	const struct proto *prot = READ_ONCE(sk->sk_prot);
+
+	if (prot->recvmsg != tcp_recvmsg)
+		return -EPROTONOSUPPORT;
+
+	sock_rps_record_flow(sk);
+	return io_zcrx_tcp_recvmsg(req, ifq, sk, flags, issue_flags, len);
+}
diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h
new file mode 100644
index 000000000000..706cc7300780
--- /dev/null
+++ b/io_uring/zcrx.h
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_ZC_RX_H
+#define IOU_ZC_RX_H
+
+#include <linux/io_uring_types.h>
+#include <linux/socket.h>
+#include <net/page_pool/types.h>
+#include <net/net_trackers.h>
+
+struct io_zcrx_area {
+	struct net_iov_area	nia;
+	struct io_zcrx_ifq	*ifq;
+	atomic_t		*user_refs;
+
+	bool			is_mapped;
+	u16			area_id;
+	struct page		**pages;
+
+	/* freelist */
+	spinlock_t		freelist_lock ____cacheline_aligned_in_smp;
+	u32			free_count;
+	u32			*freelist;
+};
+
+struct io_zcrx_ifq {
+	struct io_ring_ctx		*ctx;
+	struct io_zcrx_area		*area;
+
+	struct io_uring			*rq_ring;
+	struct io_uring_zcrx_rqe	*rqes;
+	u32				rq_entries;
+	u32				cached_rq_head;
+	spinlock_t			rq_lock;
+
+	u32				if_rxq;
+	struct device			*dev;
+	struct net_device		*netdev;
+	netdevice_tracker		netdev_tracker;
+	spinlock_t			lock;
+};
+
+#if defined(CONFIG_IO_URING_ZCRX)
+int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
+			 struct io_uring_zcrx_ifq_reg __user *arg);
+void io_unregister_zcrx_ifqs(struct io_ring_ctx *ctx);
+void io_shutdown_zcrx_ifqs(struct io_ring_ctx *ctx);
+int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+		 struct socket *sock, unsigned int flags,
+		 unsigned issue_flags, unsigned int *len);
+#else
+static inline int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
+					struct io_uring_zcrx_ifq_reg __user *arg)
+{
+	return -EOPNOTSUPP;
+}
+static inline void io_unregister_zcrx_ifqs(struct io_ring_ctx *ctx)
+{
+}
+static inline void io_shutdown_zcrx_ifqs(struct io_ring_ctx *ctx)
+{
+}
+static inline int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+			       struct socket *sock, unsigned int flags,
+			       unsigned issue_flags, unsigned int *len)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+int io_recvzc(struct io_kiocb *req, unsigned int issue_flags);
+int io_recvzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+
+#endif
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 1a52a0bca086..7e1ad229e133 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -1040,7 +1040,7 @@ static int br_mdb_add_group(const struct br_mdb_config *cfg,
 
 	/* host join */
 	if (!port) {
-		if (mp->host_joined) {
+		if (mp->host_joined && !(cfg->nlflags & NLM_F_REPLACE)) {
 			NL_SET_ERR_MSG_MOD(extack, "Group is already joined by host");
 			return -EEXIST;
 		}
diff --git a/net/core/dev.c b/net/core/dev.c
index 30da277c5a6f..4349aeef0a4a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -159,6 +159,7 @@
 #include <net/netdev_rx_queue.h>
 #include <net/page_pool/types.h>
 #include <net/page_pool/helpers.h>
+#include <net/page_pool/memory_provider.h>
 #include <net/rps.h>
 #include <linux/phy_link_topology.h>
 
@@ -6184,16 +6185,18 @@ EXPORT_SYMBOL(netif_receive_skb_list);
 static void flush_backlog(struct work_struct *work)
 {
 	struct sk_buff *skb, *tmp;
+	struct sk_buff_head list;
 	struct softnet_data *sd;
 
+	__skb_queue_head_init(&list);
 	local_bh_disable();
 	sd = this_cpu_ptr(&softnet_data);
 
 	backlog_lock_irq_disable(sd);
 	skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
-		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
+		if (READ_ONCE(skb->dev->reg_state) == NETREG_UNREGISTERING) {
 			__skb_unlink(skb, &sd->input_pkt_queue);
-			dev_kfree_skb_irq(skb);
+			__skb_queue_tail(&list, skb);
 			rps_input_queue_head_incr(sd);
 		}
 	}
@@ -6201,14 +6204,16 @@ static void flush_backlog(struct work_struct *work)
 
 	local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
 	skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
-		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
+		if (READ_ONCE(skb->dev->reg_state) == NETREG_UNREGISTERING) {
 			__skb_unlink(skb, &sd->process_queue);
-			kfree_skb(skb);
+			__skb_queue_tail(&list, skb);
 			rps_input_queue_head_incr(sd);
 		}
 	}
 	local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
 	local_bh_enable();
+
+	__skb_queue_purge_reason(&list, SKB_DROP_REASON_DEV_READY);
 }
 
 static bool flush_required(int cpu)
@@ -7153,6 +7158,9 @@ void __netif_napi_del_locked(struct napi_struct *napi)
 	if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state))
 		return;
 
+	/* Make sure NAPI is disabled (or was never enabled). */
+	WARN_ON(!test_bit(NAPI_STATE_SCHED, &napi->state));
+
 	if (napi->config) {
 		napi->index = -1;
 		napi->config = NULL;
@@ -11820,6 +11828,19 @@ void unregister_netdevice_queue(struct net_device *dev, struct list_head *head)
 }
 EXPORT_SYMBOL(unregister_netdevice_queue);
 
+static void dev_memory_provider_uninstall(struct net_device *dev)
+{
+	unsigned int i;
+
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		struct netdev_rx_queue *rxq = &dev->_rx[i];
+		struct pp_memory_provider_params *p = &rxq->mp_params;
+
+		if (p->mp_ops && p->mp_ops->uninstall)
+			p->mp_ops->uninstall(rxq->mp_params.mp_priv, rxq);
+	}
+}
+
 void unregister_netdevice_many_notify(struct list_head *head,
 				      u32 portid, const struct nlmsghdr *nlh)
 {
@@ -11874,7 +11895,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		dev_tcx_uninstall(dev);
 		dev_xdp_uninstall(dev);
 		bpf_dev_bound_netdev_unregister(dev);
-		dev_dmabuf_uninstall(dev);
+		dev_memory_provider_uninstall(dev);
 
 		netdev_offload_xstats_disable_all(dev);
 
diff --git a/net/core/devmem.c b/net/core/devmem.c
index 3bba3f018df0..7c6e0b5b6acb 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -16,6 +16,7 @@
 #include <net/netdev_queues.h>
 #include <net/netdev_rx_queue.h>
 #include <net/page_pool/helpers.h>
+#include <net/page_pool/memory_provider.h>
 #include <trace/events/page_pool.h>
 
 #include "devmem.h"
@@ -27,20 +28,28 @@
 /* Protected by rtnl_lock() */
 static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1);
 
+static const struct memory_provider_ops dmabuf_devmem_ops;
+
+bool net_is_devmem_iov(struct net_iov *niov)
+{
+	return niov->pp->mp_ops == &dmabuf_devmem_ops;
+}
+
 static void net_devmem_dmabuf_free_chunk_owner(struct gen_pool *genpool,
 					       struct gen_pool_chunk *chunk,
 					       void *not_used)
 {
 	struct dmabuf_genpool_chunk_owner *owner = chunk->owner;
 
-	kvfree(owner->niovs);
+	kvfree(owner->area.niovs);
 	kfree(owner);
 }
 
 static dma_addr_t net_devmem_get_dma_addr(const struct net_iov *niov)
 {
-	struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov);
+	struct dmabuf_genpool_chunk_owner *owner;
 
+	owner = net_devmem_iov_to_chunk_owner(niov);
 	return owner->base_dma_addr +
 	       ((dma_addr_t)net_iov_idx(niov) << PAGE_SHIFT);
 }
@@ -83,7 +92,7 @@ net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
 
 	offset = dma_addr - owner->base_dma_addr;
 	index = offset / PAGE_SIZE;
-	niov = &owner->niovs[index];
+	niov = &owner->area.niovs[index];
 
 	niov->pp_magic = 0;
 	niov->pp = NULL;
@@ -94,7 +103,7 @@ net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
 
 void net_devmem_free_dmabuf(struct net_iov *niov)
 {
-	struct net_devmem_dmabuf_binding *binding = net_iov_binding(niov);
+	struct net_devmem_dmabuf_binding *binding = net_devmem_iov_binding(niov);
 	unsigned long dma_addr = net_devmem_get_dma_addr(niov);
 
 	if (WARN_ON(!gen_pool_has_addr(binding->chunk_pool, dma_addr,
@@ -117,6 +126,7 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
 		WARN_ON(rxq->mp_params.mp_priv != binding);
 
 		rxq->mp_params.mp_priv = NULL;
+		rxq->mp_params.mp_ops = NULL;
 
 		rxq_idx = get_netdev_rx_queue_index(rxq);
 
@@ -152,7 +162,7 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 	}
 
 	rxq = __netif_get_rx_queue(dev, rxq_idx);
-	if (rxq->mp_params.mp_priv) {
+	if (rxq->mp_params.mp_ops) {
 		NL_SET_ERR_MSG(extack, "designated queue already memory provider bound");
 		return -EEXIST;
 	}
@@ -170,6 +180,7 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 		return err;
 
 	rxq->mp_params.mp_priv = binding;
+	rxq->mp_params.mp_ops = &dmabuf_devmem_ops;
 
 	err = netdev_rx_queue_restart(dev, rxq_idx);
 	if (err)
@@ -179,6 +190,7 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 
 err_xa_erase:
 	rxq->mp_params.mp_priv = NULL;
+	rxq->mp_params.mp_ops = NULL;
 	xa_erase(&binding->bound_rxqs, xa_idx);
 
 	return err;
@@ -261,9 +273,9 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
 			goto err_free_chunks;
 		}
 
-		owner->base_virtual = virtual;
+		owner->area.base_virtual = virtual;
 		owner->base_dma_addr = dma_addr;
-		owner->num_niovs = len / PAGE_SIZE;
+		owner->area.num_niovs = len / PAGE_SIZE;
 		owner->binding = binding;
 
 		err = gen_pool_add_owner(binding->chunk_pool, dma_addr,
@@ -275,17 +287,17 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
 			goto err_free_chunks;
 		}
 
-		owner->niovs = kvmalloc_array(owner->num_niovs,
-					      sizeof(*owner->niovs),
-					      GFP_KERNEL);
-		if (!owner->niovs) {
+		owner->area.niovs = kvmalloc_array(owner->area.num_niovs,
+						   sizeof(*owner->area.niovs),
+						   GFP_KERNEL);
+		if (!owner->area.niovs) {
 			err = -ENOMEM;
 			goto err_free_chunks;
 		}
 
-		for (i = 0; i < owner->num_niovs; i++) {
-			niov = &owner->niovs[i];
-			niov->owner = owner;
+		for (i = 0; i < owner->area.num_niovs; i++) {
+			niov = &owner->area.niovs[i];
+			niov->owner = &owner->area;
 			page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov),
 						      net_devmem_get_dma_addr(niov));
 		}
@@ -313,26 +325,6 @@ err_put_dmabuf:
 	return ERR_PTR(err);
 }
 
-void dev_dmabuf_uninstall(struct net_device *dev)
-{
-	struct net_devmem_dmabuf_binding *binding;
-	struct netdev_rx_queue *rxq;
-	unsigned long xa_idx;
-	unsigned int i;
-
-	for (i = 0; i < dev->real_num_rx_queues; i++) {
-		binding = dev->_rx[i].mp_params.mp_priv;
-		if (!binding)
-			continue;
-
-		xa_for_each(&binding->bound_rxqs, xa_idx, rxq)
-			if (rxq == &dev->_rx[i]) {
-				xa_erase(&binding->bound_rxqs, xa_idx);
-				break;
-			}
-	}
-}
-
 /*** "Dmabuf devmem memory provider" ***/
 
 int mp_dmabuf_devmem_init(struct page_pool *pool)
@@ -398,3 +390,36 @@ bool mp_dmabuf_devmem_release_page(struct page_pool *pool, netmem_ref netmem)
 	/* We don't want the page pool put_page()ing our net_iovs. */
 	return false;
 }
+
+static int mp_dmabuf_devmem_nl_fill(void *mp_priv, struct sk_buff *rsp,
+				    struct netdev_rx_queue *rxq)
+{
+	const struct net_devmem_dmabuf_binding *binding = mp_priv;
+	int type = rxq ? NETDEV_A_QUEUE_DMABUF : NETDEV_A_PAGE_POOL_DMABUF;
+
+	return nla_put_u32(rsp, type, binding->id);
+}
+
+static void mp_dmabuf_devmem_uninstall(void *mp_priv,
+				       struct netdev_rx_queue *rxq)
+{
+	struct net_devmem_dmabuf_binding *binding = mp_priv;
+	struct netdev_rx_queue *bound_rxq;
+	unsigned long xa_idx;
+
+	xa_for_each(&binding->bound_rxqs, xa_idx, bound_rxq) {
+		if (bound_rxq == rxq) {
+			xa_erase(&binding->bound_rxqs, xa_idx);
+			break;
+		}
+	}
+}
+
+static const struct memory_provider_ops dmabuf_devmem_ops = {
+	.init			= mp_dmabuf_devmem_init,
+	.destroy		= mp_dmabuf_devmem_destroy,
+	.alloc_netmems		= mp_dmabuf_devmem_alloc_netmems,
+	.release_netmem		= mp_dmabuf_devmem_release_page,
+	.nl_fill		= mp_dmabuf_devmem_nl_fill,
+	.uninstall		= mp_dmabuf_devmem_uninstall,
+};
diff --git a/net/core/devmem.h b/net/core/devmem.h
index 76099ef9c482..7fc158d52729 100644
--- a/net/core/devmem.h
+++ b/net/core/devmem.h
@@ -10,6 +10,8 @@
 #ifndef _NET_DEVMEM_H
 #define _NET_DEVMEM_H
 
+#include <net/netmem.h>
+
 struct netlink_ext_ack;
 
 struct net_devmem_dmabuf_binding {
@@ -51,17 +53,11 @@ struct net_devmem_dmabuf_binding {
  * allocations from this chunk.
  */
 struct dmabuf_genpool_chunk_owner {
-	/* Offset into the dma-buf where this chunk starts.  */
-	unsigned long base_virtual;
+	struct net_iov_area area;
+	struct net_devmem_dmabuf_binding *binding;
 
 	/* dma_addr of the start of the chunk.  */
 	dma_addr_t base_dma_addr;
-
-	/* Array of net_iovs for this chunk. */
-	struct net_iov *niovs;
-	size_t num_niovs;
-
-	struct net_devmem_dmabuf_binding *binding;
 };
 
 void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding);
@@ -72,38 +68,34 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding);
 int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 				    struct net_devmem_dmabuf_binding *binding,
 				    struct netlink_ext_ack *extack);
-void dev_dmabuf_uninstall(struct net_device *dev);
 
 static inline struct dmabuf_genpool_chunk_owner *
-net_iov_owner(const struct net_iov *niov)
+net_devmem_iov_to_chunk_owner(const struct net_iov *niov)
 {
-	return niov->owner;
+	struct net_iov_area *owner = net_iov_owner(niov);
+
+	return container_of(owner, struct dmabuf_genpool_chunk_owner, area);
 }
 
-static inline unsigned int net_iov_idx(const struct net_iov *niov)
+static inline struct net_devmem_dmabuf_binding *
+net_devmem_iov_binding(const struct net_iov *niov)
 {
-	return niov - net_iov_owner(niov)->niovs;
+	return net_devmem_iov_to_chunk_owner(niov)->binding;
 }
 
-static inline struct net_devmem_dmabuf_binding *
-net_iov_binding(const struct net_iov *niov)
+static inline u32 net_devmem_iov_binding_id(const struct net_iov *niov)
 {
-	return net_iov_owner(niov)->binding;
+	return net_devmem_iov_binding(niov)->id;
 }
 
 static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov)
 {
-	struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov);
+	struct net_iov_area *owner = net_iov_owner(niov);
 
 	return owner->base_virtual +
 	       ((unsigned long)net_iov_idx(niov) << PAGE_SHIFT);
 }
 
-static inline u32 net_iov_binding_id(const struct net_iov *niov)
-{
-	return net_iov_owner(niov)->binding->id;
-}
-
 static inline void
 net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding)
 {
@@ -123,6 +115,8 @@ struct net_iov *
 net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding);
 void net_devmem_free_dmabuf(struct net_iov *ppiov);
 
+bool net_is_devmem_iov(struct net_iov *niov);
+
 #else
 struct net_devmem_dmabuf_binding;
 
@@ -152,10 +146,6 @@ net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 	return -EOPNOTSUPP;
 }
 
-static inline void dev_dmabuf_uninstall(struct net_device *dev)
-{
-}
-
 static inline struct net_iov *
 net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
 {
@@ -171,10 +161,15 @@ static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov)
 	return 0;
 }
 
-static inline u32 net_iov_binding_id(const struct net_iov *niov)
+static inline u32 net_devmem_iov_binding_id(const struct net_iov *niov)
 {
 	return 0;
 }
+
+static inline bool net_is_devmem_iov(struct net_iov *niov)
+{
+	return false;
+}
 #endif
 
 #endif /* _NET_DEVMEM_H */
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index bd0251bd74a1..d8dd686b5287 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -832,12 +832,10 @@ static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
 	return -ENOENT;
 }
 
-static void neigh_parms_destroy(struct neigh_parms *parms);
-
 static inline void neigh_parms_put(struct neigh_parms *parms)
 {
 	if (refcount_dec_and_test(&parms->refcnt))
-		neigh_parms_destroy(parms);
+		kfree(parms);
 }
 
 /*
@@ -1713,11 +1711,6 @@ void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms)
 }
 EXPORT_SYMBOL(neigh_parms_release);
 
-static void neigh_parms_destroy(struct neigh_parms *parms)
-{
-	kfree(parms);
-}
-
 static struct lock_class_key neigh_table_proxy_queue_class;
 
 static struct neigh_table __rcu *neigh_tables[NEIGH_NR_TABLES] __read_mostly;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 07cb99b114bd..3fe2c521e574 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -42,6 +42,87 @@ static inline int dev_isalive(const struct net_device *dev)
 	return READ_ONCE(dev->reg_state) <= NETREG_REGISTERED;
 }
 
+/* There is a possible ABBA deadlock between rtnl_lock and kernfs_node->active,
+ * when unregistering a net device and accessing associated sysfs files. The
+ * potential deadlock is as follow:
+ *
+ *         CPU 0                                         CPU 1
+ *
+ *    rtnl_lock                                   vfs_read
+ *    unregister_netdevice_many                   kernfs_seq_start
+ *    device_del / kobject_put                      kernfs_get_active (kn->active++)
+ *    kernfs_drain                                sysfs_kf_seq_show
+ *    wait_event(                                 rtnl_lock
+ *       kn->active == KN_DEACTIVATED_BIAS)       -> waits on CPU 0 to release
+ *    -> waits on CPU 1 to decrease kn->active       the rtnl lock.
+ *
+ * The historical fix was to use rtnl_trylock with restart_syscall to bail out
+ * of sysfs operations when the lock couldn't be taken. This fixed the above
+ * issue as it allowed CPU 1 to bail out of the ABBA situation.
+ *
+ * But it came with performances issues, as syscalls are being restarted in
+ * loops when there was contention on the rtnl lock, with huge slow downs in
+ * specific scenarios (e.g. lots of virtual interfaces created and userspace
+ * daemons querying their attributes).
+ *
+ * The idea below is to bail out of the active kernfs_node protection
+ * (kn->active) while trying to take the rtnl lock.
+ *
+ * This replaces rtnl_lock() and still has to be used with rtnl_unlock(). The
+ * net device is guaranteed to be alive if this returns successfully.
+ */
+static int sysfs_rtnl_lock(struct kobject *kobj, struct attribute *attr,
+			   struct net_device *ndev)
+{
+	struct kernfs_node *kn;
+	int ret = 0;
+
+	/* First, we hold a reference to the net device as the unregistration
+	 * path might run in parallel. This will ensure the net device and the
+	 * associated sysfs objects won't be freed while we try to take the rtnl
+	 * lock.
+	 */
+	dev_hold(ndev);
+	/* sysfs_break_active_protection was introduced to allow self-removal of
+	 * devices and their associated sysfs files by bailing out of the
+	 * sysfs/kernfs protection. We do this here to allow the unregistration
+	 * path to complete in parallel. The following takes a reference on the
+	 * kobject and the kernfs_node being accessed.
+	 *
+	 * This works because we hold a reference onto the net device and the
+	 * unregistration path will wait for us eventually in netdev_run_todo
+	 * (outside an rtnl lock section).
+	 */
+	kn = sysfs_break_active_protection(kobj, attr);
+	/* We can now try to take the rtnl lock. This can't deadlock us as the
+	 * unregistration path is able to drain sysfs files (kernfs_node) thanks
+	 * to the above dance.
+	 */
+	if (rtnl_lock_interruptible()) {
+		ret = -ERESTARTSYS;
+		goto unbreak;
+	}
+	/* Check dismantle on the device hasn't started, otherwise deny the
+	 * operation.
+	 */
+	if (!dev_isalive(ndev)) {
+		rtnl_unlock();
+		ret = -ENODEV;
+		goto unbreak;
+	}
+	/* We are now sure the device dismantle hasn't started nor that it can
+	 * start before we exit the locking section as we hold the rtnl lock.
+	 * There's no need to keep unbreaking the sysfs protection nor to hold
+	 * a net device reference from that point; that was only needed to take
+	 * the rtnl lock.
+	 */
+unbreak:
+	sysfs_unbreak_active_protection(kn);
+	dev_put(ndev);
+
+	return ret;
+}
+
 /* use same locking rules as GIF* ioctl's */
 static ssize_t netdev_show(const struct device *dev,
 			   struct device_attribute *attr, char *buf,
@@ -95,14 +176,14 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		goto err;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+	if (ret)
+		goto err;
+
+	ret = (*set)(netdev, new);
+	if (ret == 0)
+		ret = len;
 
-	if (dev_isalive(netdev)) {
-		ret = (*set)(netdev, new);
-		if (ret == 0)
-			ret = len;
-	}
 	rtnl_unlock();
  err:
 	return ret;
@@ -220,7 +301,7 @@ static ssize_t carrier_store(struct device *dev, struct device_attribute *attr,
 	struct net_device *netdev = to_net_dev(dev);
 
 	/* The check is also done in change_carrier; this helps returning early
-	 * without hitting the trylock/restart in netdev_store.
+	 * without hitting the locking section in netdev_store.
 	 */
 	if (!netdev->netdev_ops->ndo_change_carrier)
 		return -EOPNOTSUPP;
@@ -234,8 +315,9 @@ static ssize_t carrier_show(struct device *dev,
 	struct net_device *netdev = to_net_dev(dev);
 	int ret = -EINVAL;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+	if (ret)
+		return ret;
 
 	if (netif_running(netdev)) {
 		/* Synchronize carrier state with link watch,
@@ -245,8 +327,8 @@ static ssize_t carrier_show(struct device *dev,
 
 		ret = sysfs_emit(buf, fmt_dec, !!netif_carrier_ok(netdev));
 	}
-	rtnl_unlock();
 
+	rtnl_unlock();
 	return ret;
 }
 static DEVICE_ATTR_RW(carrier);
@@ -258,13 +340,14 @@ static ssize_t speed_show(struct device *dev,
 	int ret = -EINVAL;
 
 	/* The check is also done in __ethtool_get_link_ksettings; this helps
-	 * returning early without hitting the trylock/restart below.
+	 * returning early without hitting the locking section below.
 	 */
 	if (!netdev->ethtool_ops->get_link_ksettings)
 		return ret;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+	if (ret)
+		return ret;
 
 	if (netif_running(netdev)) {
 		struct ethtool_link_ksettings cmd;
@@ -284,13 +367,14 @@ static ssize_t duplex_show(struct device *dev,
 	int ret = -EINVAL;
 
 	/* The check is also done in __ethtool_get_link_ksettings; this helps
-	 * returning early without hitting the trylock/restart below.
+	 * returning early without hitting the locking section below.
 	 */
 	if (!netdev->ethtool_ops->get_link_ksettings)
 		return ret;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+	if (ret)
+		return ret;
 
 	if (netif_running(netdev)) {
 		struct ethtool_link_ksettings cmd;
@@ -490,16 +574,15 @@ static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr,
 	if (len >  0 && buf[len - 1] == '\n')
 		--count;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+	if (ret)
+		return ret;
 
-	if (dev_isalive(netdev)) {
-		ret = dev_set_alias(netdev, buf, count);
-		if (ret < 0)
-			goto err;
-		ret = len;
-		netdev_state_change(netdev);
-	}
+	ret = dev_set_alias(netdev, buf, count);
+	if (ret < 0)
+		goto err;
+	ret = len;
+	netdev_state_change(netdev);
 err:
 	rtnl_unlock();
 
@@ -551,24 +634,23 @@ static ssize_t phys_port_id_show(struct device *dev,
 				 struct device_attribute *attr, char *buf)
 {
 	struct net_device *netdev = to_net_dev(dev);
+	struct netdev_phys_item_id ppid;
 	ssize_t ret = -EINVAL;
 
 	/* The check is also done in dev_get_phys_port_id; this helps returning
-	 * early without hitting the trylock/restart below.
+	 * early without hitting the locking section below.
 	 */
 	if (!netdev->netdev_ops->ndo_get_phys_port_id)
 		return -EOPNOTSUPP;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+	if (ret)
+		return ret;
 
-	if (dev_isalive(netdev)) {
-		struct netdev_phys_item_id ppid;
+	ret = dev_get_phys_port_id(netdev, &ppid);
+	if (!ret)
+		ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id);
 
-		ret = dev_get_phys_port_id(netdev, &ppid);
-		if (!ret)
-			ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id);
-	}
 	rtnl_unlock();
 
 	return ret;
@@ -580,24 +662,23 @@ static ssize_t phys_port_name_show(struct device *dev,
 {
 	struct net_device *netdev = to_net_dev(dev);
 	ssize_t ret = -EINVAL;
+	char name[IFNAMSIZ];
 
 	/* The checks are also done in dev_get_phys_port_name; this helps
-	 * returning early without hitting the trylock/restart below.
+	 * returning early without hitting the locking section below.
 	 */
 	if (!netdev->netdev_ops->ndo_get_phys_port_name &&
 	    !netdev->devlink_port)
 		return -EOPNOTSUPP;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+	if (ret)
+		return ret;
 
-	if (dev_isalive(netdev)) {
-		char name[IFNAMSIZ];
+	ret = dev_get_phys_port_name(netdev, name, sizeof(name));
+	if (!ret)
+		ret = sysfs_emit(buf, "%s\n", name);
 
-		ret = dev_get_phys_port_name(netdev, name, sizeof(name));
-		if (!ret)
-			ret = sysfs_emit(buf, "%s\n", name);
-	}
 	rtnl_unlock();
 
 	return ret;
@@ -608,26 +689,25 @@ static ssize_t phys_switch_id_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
 	struct net_device *netdev = to_net_dev(dev);
+	struct netdev_phys_item_id ppid = { };
 	ssize_t ret = -EINVAL;
 
 	/* The checks are also done in dev_get_phys_port_name; this helps
-	 * returning early without hitting the trylock/restart below. This works
+	 * returning early without hitting the locking section below. This works
 	 * because recurse is false when calling dev_get_port_parent_id.
 	 */
 	if (!netdev->netdev_ops->ndo_get_port_parent_id &&
 	    !netdev->devlink_port)
 		return -EOPNOTSUPP;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+	if (ret)
+		return ret;
 
-	if (dev_isalive(netdev)) {
-		struct netdev_phys_item_id ppid = { };
+	ret = dev_get_port_parent_id(netdev, &ppid, false);
+	if (!ret)
+		ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id);
 
-		ret = dev_get_port_parent_id(netdev, &ppid, false);
-		if (!ret)
-			ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id);
-	}
 	rtnl_unlock();
 
 	return ret;
@@ -1108,7 +1188,6 @@ static void rx_queue_get_ownership(const struct kobject *kobj,
 static const struct kobj_type rx_queue_ktype = {
 	.sysfs_ops = &rx_queue_sysfs_ops,
 	.release = rx_queue_release,
-	.default_groups = rx_queue_default_groups,
 	.namespace = rx_queue_namespace,
 	.get_ownership = rx_queue_get_ownership,
 };
@@ -1131,6 +1210,22 @@ static int rx_queue_add_kobject(struct net_device *dev, int index)
 	struct kobject *kobj = &queue->kobj;
 	int error = 0;
 
+	/* Rx queues are cleared in rx_queue_release to allow later
+	 * re-registration. This is triggered when their kobj refcount is
+	 * dropped.
+	 *
+	 * If a queue is removed while both a read (or write) operation and a
+	 * the re-addition of the same queue are pending (waiting on rntl_lock)
+	 * it might happen that the re-addition will execute before the read,
+	 * making the initial removal to never happen (queue's kobj refcount
+	 * won't drop enough because of the pending read). In such rare case,
+	 * return to allow the removal operation to complete.
+	 */
+	if (unlikely(kobj->state_initialized)) {
+		netdev_warn_once(dev, "Cannot re-add rx queues before their removal completed");
+		return -EAGAIN;
+	}
+
 	/* Kobject_put later will trigger rx_queue_release call which
 	 * decreases dev refcount: Take that reference here
 	 */
@@ -1142,20 +1237,27 @@ static int rx_queue_add_kobject(struct net_device *dev, int index)
 	if (error)
 		goto err;
 
+	queue->groups = rx_queue_default_groups;
+	error = sysfs_create_groups(kobj, queue->groups);
+	if (error)
+		goto err;
+
 	if (dev->sysfs_rx_queue_group) {
 		error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group);
 		if (error)
-			goto err;
+			goto err_default_groups;
 	}
 
 	error = rx_queue_default_mask(dev, queue);
 	if (error)
-		goto err;
+		goto err_default_groups;
 
 	kobject_uevent(kobj, KOBJ_ADD);
 
 	return error;
 
+err_default_groups:
+	sysfs_remove_groups(kobj, queue->groups);
 err:
 	kobject_put(kobj);
 	return error;
@@ -1200,12 +1302,14 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
 	}
 
 	while (--i >= new_num) {
-		struct kobject *kobj = &dev->_rx[i].kobj;
+		struct netdev_rx_queue *queue = &dev->_rx[i];
+		struct kobject *kobj = &queue->kobj;
 
 		if (!refcount_read(&dev_net(dev)->ns.count))
 			kobj->uevent_suppress = 1;
 		if (dev->sysfs_rx_queue_group)
 			sysfs_remove_group(kobj, dev->sysfs_rx_queue_group);
+		sysfs_remove_groups(kobj, queue->groups);
 		kobject_put(kobj);
 	}
 
@@ -1244,9 +1348,11 @@ static int net_rx_queue_change_owner(struct net_device *dev, int num,
  */
 struct netdev_queue_attribute {
 	struct attribute attr;
-	ssize_t (*show)(struct netdev_queue *queue, char *buf);
-	ssize_t (*store)(struct netdev_queue *queue,
-			 const char *buf, size_t len);
+	ssize_t (*show)(struct kobject *kobj, struct attribute *attr,
+			struct netdev_queue *queue, char *buf);
+	ssize_t (*store)(struct kobject *kobj, struct attribute *attr,
+			 struct netdev_queue *queue, const char *buf,
+			 size_t len);
 };
 #define to_netdev_queue_attr(_attr) \
 	container_of(_attr, struct netdev_queue_attribute, attr)
@@ -1263,7 +1369,7 @@ static ssize_t netdev_queue_attr_show(struct kobject *kobj,
 	if (!attribute->show)
 		return -EIO;
 
-	return attribute->show(queue, buf);
+	return attribute->show(kobj, attr, queue, buf);
 }
 
 static ssize_t netdev_queue_attr_store(struct kobject *kobj,
@@ -1277,7 +1383,7 @@ static ssize_t netdev_queue_attr_store(struct kobject *kobj,
 	if (!attribute->store)
 		return -EIO;
 
-	return attribute->store(queue, buf, count);
+	return attribute->store(kobj, attr, queue, buf, count);
 }
 
 static const struct sysfs_ops netdev_queue_sysfs_ops = {
@@ -1285,7 +1391,8 @@ static const struct sysfs_ops netdev_queue_sysfs_ops = {
 	.store = netdev_queue_attr_store,
 };
 
-static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf)
+static ssize_t tx_timeout_show(struct kobject *kobj, struct attribute *attr,
+			       struct netdev_queue *queue, char *buf)
 {
 	unsigned long trans_timeout = atomic_long_read(&queue->trans_timeout);
 
@@ -1303,18 +1410,18 @@ static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
 	return i;
 }
 
-static ssize_t traffic_class_show(struct netdev_queue *queue,
-				  char *buf)
+static ssize_t traffic_class_show(struct kobject *kobj, struct attribute *attr,
+				  struct netdev_queue *queue, char *buf)
 {
 	struct net_device *dev = queue->dev;
-	int num_tc, tc;
-	int index;
+	int num_tc, tc, index, ret;
 
 	if (!netif_is_multiqueue(dev))
 		return -ENOENT;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(kobj, attr, queue->dev);
+	if (ret)
+		return ret;
 
 	index = get_netdev_queue_index(queue);
 
@@ -1341,24 +1448,25 @@ static ssize_t traffic_class_show(struct netdev_queue *queue,
 }
 
 #ifdef CONFIG_XPS
-static ssize_t tx_maxrate_show(struct netdev_queue *queue,
-			       char *buf)
+static ssize_t tx_maxrate_show(struct kobject *kobj, struct attribute *attr,
+			       struct netdev_queue *queue, char *buf)
 {
 	return sysfs_emit(buf, "%lu\n", queue->tx_maxrate);
 }
 
-static ssize_t tx_maxrate_store(struct netdev_queue *queue,
-				const char *buf, size_t len)
+static ssize_t tx_maxrate_store(struct kobject *kobj, struct attribute *attr,
+				struct netdev_queue *queue, const char *buf,
+				size_t len)
 {
-	struct net_device *dev = queue->dev;
 	int err, index = get_netdev_queue_index(queue);
+	struct net_device *dev = queue->dev;
 	u32 rate = 0;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
 
 	/* The check is also done later; this helps returning early without
-	 * hitting the trylock/restart below.
+	 * hitting the locking section below.
 	 */
 	if (!dev->netdev_ops->ndo_set_tx_maxrate)
 		return -EOPNOTSUPP;
@@ -1367,18 +1475,21 @@ static ssize_t tx_maxrate_store(struct netdev_queue *queue,
 	if (err < 0)
 		return err;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	err = sysfs_rtnl_lock(kobj, attr, dev);
+	if (err)
+		return err;
 
 	err = -EOPNOTSUPP;
 	if (dev->netdev_ops->ndo_set_tx_maxrate)
 		err = dev->netdev_ops->ndo_set_tx_maxrate(dev, index, rate);
 
-	rtnl_unlock();
 	if (!err) {
 		queue->tx_maxrate = rate;
+		rtnl_unlock();
 		return len;
 	}
+
+	rtnl_unlock();
 	return err;
 }
 
@@ -1422,16 +1533,17 @@ static ssize_t bql_set(const char *buf, const size_t count,
 	return count;
 }
 
-static ssize_t bql_show_hold_time(struct netdev_queue *queue,
-				  char *buf)
+static ssize_t bql_show_hold_time(struct kobject *kobj, struct attribute *attr,
+				  struct netdev_queue *queue, char *buf)
 {
 	struct dql *dql = &queue->dql;
 
 	return sysfs_emit(buf, "%u\n", jiffies_to_msecs(dql->slack_hold_time));
 }
 
-static ssize_t bql_set_hold_time(struct netdev_queue *queue,
-				 const char *buf, size_t len)
+static ssize_t bql_set_hold_time(struct kobject *kobj, struct attribute *attr,
+				 struct netdev_queue *queue, const char *buf,
+				 size_t len)
 {
 	struct dql *dql = &queue->dql;
 	unsigned int value;
@@ -1450,15 +1562,17 @@ static struct netdev_queue_attribute bql_hold_time_attribute __ro_after_init
 	= __ATTR(hold_time, 0644,
 		 bql_show_hold_time, bql_set_hold_time);
 
-static ssize_t bql_show_stall_thrs(struct netdev_queue *queue, char *buf)
+static ssize_t bql_show_stall_thrs(struct kobject *kobj, struct attribute *attr,
+				   struct netdev_queue *queue, char *buf)
 {
 	struct dql *dql = &queue->dql;
 
 	return sysfs_emit(buf, "%u\n", jiffies_to_msecs(dql->stall_thrs));
 }
 
-static ssize_t bql_set_stall_thrs(struct netdev_queue *queue,
-				  const char *buf, size_t len)
+static ssize_t bql_set_stall_thrs(struct kobject *kobj, struct attribute *attr,
+				  struct netdev_queue *queue, const char *buf,
+				  size_t len)
 {
 	struct dql *dql = &queue->dql;
 	unsigned int value;
@@ -1484,13 +1598,15 @@ static ssize_t bql_set_stall_thrs(struct netdev_queue *queue,
 static struct netdev_queue_attribute bql_stall_thrs_attribute __ro_after_init =
 	__ATTR(stall_thrs, 0644, bql_show_stall_thrs, bql_set_stall_thrs);
 
-static ssize_t bql_show_stall_max(struct netdev_queue *queue, char *buf)
+static ssize_t bql_show_stall_max(struct kobject *kobj, struct attribute *attr,
+				  struct netdev_queue *queue, char *buf)
 {
 	return sysfs_emit(buf, "%u\n", READ_ONCE(queue->dql.stall_max));
 }
 
-static ssize_t bql_set_stall_max(struct netdev_queue *queue,
-				 const char *buf, size_t len)
+static ssize_t bql_set_stall_max(struct kobject *kobj, struct attribute *attr,
+				 struct netdev_queue *queue, const char *buf,
+				 size_t len)
 {
 	WRITE_ONCE(queue->dql.stall_max, 0);
 	return len;
@@ -1499,7 +1615,8 @@ static ssize_t bql_set_stall_max(struct netdev_queue *queue,
 static struct netdev_queue_attribute bql_stall_max_attribute __ro_after_init =
 	__ATTR(stall_max, 0644, bql_show_stall_max, bql_set_stall_max);
 
-static ssize_t bql_show_stall_cnt(struct netdev_queue *queue, char *buf)
+static ssize_t bql_show_stall_cnt(struct kobject *kobj, struct attribute *attr,
+				  struct netdev_queue *queue, char *buf)
 {
 	struct dql *dql = &queue->dql;
 
@@ -1509,8 +1626,8 @@ static ssize_t bql_show_stall_cnt(struct netdev_queue *queue, char *buf)
 static struct netdev_queue_attribute bql_stall_cnt_attribute __ro_after_init =
 	__ATTR(stall_cnt, 0444, bql_show_stall_cnt, NULL);
 
-static ssize_t bql_show_inflight(struct netdev_queue *queue,
-				 char *buf)
+static ssize_t bql_show_inflight(struct kobject *kobj, struct attribute *attr,
+				 struct netdev_queue *queue, char *buf)
 {
 	struct dql *dql = &queue->dql;
 
@@ -1521,13 +1638,16 @@ static struct netdev_queue_attribute bql_inflight_attribute __ro_after_init =
 	__ATTR(inflight, 0444, bql_show_inflight, NULL);
 
 #define BQL_ATTR(NAME, FIELD)						\
-static ssize_t bql_show_ ## NAME(struct netdev_queue *queue,		\
-				 char *buf)				\
+static ssize_t bql_show_ ## NAME(struct kobject *kobj,			\
+				 struct attribute *attr,		\
+				 struct netdev_queue *queue, char *buf)	\
 {									\
 	return bql_show(buf, queue->dql.FIELD);				\
 }									\
 									\
-static ssize_t bql_set_ ## NAME(struct netdev_queue *queue,		\
+static ssize_t bql_set_ ## NAME(struct kobject *kobj,			\
+				struct attribute *attr,			\
+				struct netdev_queue *queue,		\
 				const char *buf, size_t len)		\
 {									\
 	return bql_set(buf, len, &queue->dql.FIELD);			\
@@ -1613,19 +1733,21 @@ out_no_maps:
 	return len < PAGE_SIZE ? len : -EINVAL;
 }
 
-static ssize_t xps_cpus_show(struct netdev_queue *queue, char *buf)
+static ssize_t xps_cpus_show(struct kobject *kobj, struct attribute *attr,
+			     struct netdev_queue *queue, char *buf)
 {
 	struct net_device *dev = queue->dev;
 	unsigned int index;
-	int len, tc;
+	int len, tc, ret;
 
 	if (!netif_is_multiqueue(dev))
 		return -ENOENT;
 
 	index = get_netdev_queue_index(queue);
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(kobj, attr, queue->dev);
+	if (ret)
+		return ret;
 
 	/* If queue belongs to subordinate dev use its map */
 	dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
@@ -1636,18 +1758,21 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue, char *buf)
 		return -EINVAL;
 	}
 
-	/* Make sure the subordinate device can't be freed */
-	get_device(&dev->dev);
+	/* Increase the net device refcnt to make sure it won't be freed while
+	 * xps_queue_show is running.
+	 */
+	dev_hold(dev);
 	rtnl_unlock();
 
 	len = xps_queue_show(dev, index, tc, buf, XPS_CPUS);
 
-	put_device(&dev->dev);
+	dev_put(dev);
 	return len;
 }
 
-static ssize_t xps_cpus_store(struct netdev_queue *queue,
-			      const char *buf, size_t len)
+static ssize_t xps_cpus_store(struct kobject *kobj, struct attribute *attr,
+			      struct netdev_queue *queue, const char *buf,
+			      size_t len)
 {
 	struct net_device *dev = queue->dev;
 	unsigned int index;
@@ -1671,9 +1796,10 @@ static ssize_t xps_cpus_store(struct netdev_queue *queue,
 		return err;
 	}
 
-	if (!rtnl_trylock()) {
+	err = sysfs_rtnl_lock(kobj, attr, dev);
+	if (err) {
 		free_cpumask_var(mask);
-		return restart_syscall();
+		return err;
 	}
 
 	err = netif_set_xps_queue(dev, mask, index);
@@ -1687,26 +1813,34 @@ static ssize_t xps_cpus_store(struct netdev_queue *queue,
 static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init
 	= __ATTR_RW(xps_cpus);
 
-static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf)
+static ssize_t xps_rxqs_show(struct kobject *kobj, struct attribute *attr,
+			     struct netdev_queue *queue, char *buf)
 {
 	struct net_device *dev = queue->dev;
 	unsigned int index;
-	int tc;
+	int tc, ret;
 
 	index = get_netdev_queue_index(queue);
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(kobj, attr, dev);
+	if (ret)
+		return ret;
 
 	tc = netdev_txq_to_tc(dev, index);
+
+	/* Increase the net device refcnt to make sure it won't be freed while
+	 * xps_queue_show is running.
+	 */
+	dev_hold(dev);
 	rtnl_unlock();
-	if (tc < 0)
-		return -EINVAL;
 
-	return xps_queue_show(dev, index, tc, buf, XPS_RXQS);
+	ret = tc >= 0 ? xps_queue_show(dev, index, tc, buf, XPS_RXQS) : -EINVAL;
+	dev_put(dev);
+	return ret;
 }
 
-static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf,
+static ssize_t xps_rxqs_store(struct kobject *kobj, struct attribute *attr,
+			      struct netdev_queue *queue, const char *buf,
 			      size_t len)
 {
 	struct net_device *dev = queue->dev;
@@ -1730,9 +1864,10 @@ static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf,
 		return err;
 	}
 
-	if (!rtnl_trylock()) {
+	err = sysfs_rtnl_lock(kobj, attr, dev);
+	if (err) {
 		bitmap_free(mask);
-		return restart_syscall();
+		return err;
 	}
 
 	cpus_read_lock();
@@ -1792,7 +1927,6 @@ static void netdev_queue_get_ownership(const struct kobject *kobj,
 static const struct kobj_type netdev_queue_ktype = {
 	.sysfs_ops = &netdev_queue_sysfs_ops,
 	.release = netdev_queue_release,
-	.default_groups = netdev_queue_default_groups,
 	.namespace = netdev_queue_namespace,
 	.get_ownership = netdev_queue_get_ownership,
 };
@@ -1811,6 +1945,22 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
 	struct kobject *kobj = &queue->kobj;
 	int error = 0;
 
+	/* Tx queues are cleared in netdev_queue_release to allow later
+	 * re-registration. This is triggered when their kobj refcount is
+	 * dropped.
+	 *
+	 * If a queue is removed while both a read (or write) operation and a
+	 * the re-addition of the same queue are pending (waiting on rntl_lock)
+	 * it might happen that the re-addition will execute before the read,
+	 * making the initial removal to never happen (queue's kobj refcount
+	 * won't drop enough because of the pending read). In such rare case,
+	 * return to allow the removal operation to complete.
+	 */
+	if (unlikely(kobj->state_initialized)) {
+		netdev_warn_once(dev, "Cannot re-add tx queues before their removal completed");
+		return -EAGAIN;
+	}
+
 	/* Kobject_put later will trigger netdev_queue_release call
 	 * which decreases dev refcount: Take that reference here
 	 */
@@ -1822,15 +1972,22 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
 	if (error)
 		goto err;
 
+	queue->groups = netdev_queue_default_groups;
+	error = sysfs_create_groups(kobj, queue->groups);
+	if (error)
+		goto err;
+
 	if (netdev_uses_bql(dev)) {
 		error = sysfs_create_group(kobj, &dql_group);
 		if (error)
-			goto err;
+			goto err_default_groups;
 	}
 
 	kobject_uevent(kobj, KOBJ_ADD);
 	return 0;
 
+err_default_groups:
+	sysfs_remove_groups(kobj, queue->groups);
 err:
 	kobject_put(kobj);
 	return error;
@@ -1885,6 +2042,7 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
 		if (netdev_uses_bql(dev))
 			sysfs_remove_group(&queue->kobj, &dql_group);
 
+		sysfs_remove_groups(&queue->kobj, queue->groups);
 		kobject_put(&queue->kobj);
 	}
 
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 715f85c6b62e..5b459b4fef46 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -10,6 +10,7 @@
 #include <net/sock.h>
 #include <net/xdp.h>
 #include <net/xdp_sock.h>
+#include <net/page_pool/memory_provider.h>
 
 #include "dev.h"
 #include "devmem.h"
@@ -368,7 +369,7 @@ static int
 netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 			 u32 q_idx, u32 q_type, const struct genl_info *info)
 {
-	struct net_devmem_dmabuf_binding *binding;
+	struct pp_memory_provider_params *params;
 	struct netdev_rx_queue *rxq;
 	struct netdev_queue *txq;
 	void *hdr;
@@ -385,15 +386,15 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 	switch (q_type) {
 	case NETDEV_QUEUE_TYPE_RX:
 		rxq = __netif_get_rx_queue(netdev, q_idx);
+
 		if (rxq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID,
 					     rxq->napi->napi_id))
 			goto nla_put_failure;
 
-		binding = rxq->mp_params.mp_priv;
-		if (binding &&
-		    nla_put_u32(rsp, NETDEV_A_QUEUE_DMABUF, binding->id))
+		params = &rxq->mp_params;
+		if (params->mp_ops &&
+		    params->mp_ops->nl_fill(params->mp_priv, rsp, rxq))
 			goto nla_put_failure;
-
 		break;
 	case NETDEV_QUEUE_TYPE_TX:
 		txq = netdev_get_tx_queue(netdev, q_idx);
diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
index db82786fa0c4..db46880f37cc 100644
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -3,6 +3,7 @@
 #include <linux/netdevice.h>
 #include <net/netdev_queues.h>
 #include <net/netdev_rx_queue.h>
+#include <net/page_pool/memory_provider.h>
 
 #include "page_pool_priv.h"
 
@@ -80,3 +81,71 @@ err_free_new_mem:
 	return err;
 }
 EXPORT_SYMBOL_NS_GPL(netdev_rx_queue_restart, "NETDEV_INTERNAL");
+
+static int __net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx,
+			     struct pp_memory_provider_params *p)
+{
+	struct netdev_rx_queue *rxq;
+	int ret;
+
+	if (ifq_idx >= dev->real_num_rx_queues)
+		return -EINVAL;
+	ifq_idx = array_index_nospec(ifq_idx, dev->real_num_rx_queues);
+
+	rxq = __netif_get_rx_queue(dev, ifq_idx);
+	if (rxq->mp_params.mp_ops)
+		return -EEXIST;
+
+	rxq->mp_params = *p;
+	ret = netdev_rx_queue_restart(dev, ifq_idx);
+	if (ret) {
+		rxq->mp_params.mp_ops = NULL;
+		rxq->mp_params.mp_priv = NULL;
+	}
+	return ret;
+}
+
+int net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx,
+		    struct pp_memory_provider_params *p)
+{
+	int ret;
+
+	rtnl_lock();
+	ret = __net_mp_open_rxq(dev, ifq_idx, p);
+	rtnl_unlock();
+	return ret;
+}
+
+static void __net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx,
+			      struct pp_memory_provider_params *old_p)
+{
+	struct netdev_rx_queue *rxq;
+
+	if (WARN_ON_ONCE(ifq_idx >= dev->real_num_rx_queues))
+		return;
+
+	rxq = __netif_get_rx_queue(dev, ifq_idx);
+
+	/* Callers holding a netdev ref may get here after we already
+	 * went thru shutdown via dev_memory_provider_uninstall().
+	 */
+	if (dev->reg_state > NETREG_REGISTERED &&
+	    !rxq->mp_params.mp_ops)
+		return;
+
+	if (WARN_ON_ONCE(rxq->mp_params.mp_ops != old_p->mp_ops ||
+			 rxq->mp_params.mp_priv != old_p->mp_priv))
+		return;
+
+	rxq->mp_params.mp_ops = NULL;
+	rxq->mp_params.mp_priv = NULL;
+	WARN_ON(netdev_rx_queue_restart(dev, ifq_idx));
+}
+
+void net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx,
+		      struct pp_memory_provider_params *old_p)
+{
+	rtnl_lock();
+	__net_mp_close_rxq(dev, ifq_idx, old_p);
+	rtnl_unlock();
+}
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index f5e908c9e7ad..686bd4a117d9 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -13,6 +13,7 @@
 
 #include <net/netdev_rx_queue.h>
 #include <net/page_pool/helpers.h>
+#include <net/page_pool/memory_provider.h>
 #include <net/xdp.h>
 
 #include <linux/dma-direction.h>
@@ -285,13 +286,19 @@ static int page_pool_init(struct page_pool *pool,
 		rxq = __netif_get_rx_queue(pool->slow.netdev,
 					   pool->slow.queue_idx);
 		pool->mp_priv = rxq->mp_params.mp_priv;
+		pool->mp_ops = rxq->mp_params.mp_ops;
 	}
 
-	if (pool->mp_priv) {
+	if (pool->mp_ops) {
 		if (!pool->dma_map || !pool->dma_sync)
 			return -EOPNOTSUPP;
 
-		err = mp_dmabuf_devmem_init(pool);
+		if (WARN_ON(!is_kernel_rodata((unsigned long)pool->mp_ops))) {
+			err = -EFAULT;
+			goto free_ptr_ring;
+		}
+
+		err = pool->mp_ops->init(pool);
 		if (err) {
 			pr_warn("%s() mem-provider init failed %d\n", __func__,
 				err);
@@ -587,8 +594,8 @@ netmem_ref page_pool_alloc_netmems(struct page_pool *pool, gfp_t gfp)
 		return netmem;
 
 	/* Slow-path: cache empty, do real allocation */
-	if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_priv)
-		netmem = mp_dmabuf_devmem_alloc_netmems(pool, gfp);
+	if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_ops)
+		netmem = pool->mp_ops->alloc_netmems(pool, gfp);
 	else
 		netmem = __page_pool_alloc_pages_slow(pool, gfp);
 	return netmem;
@@ -679,8 +686,8 @@ void page_pool_return_page(struct page_pool *pool, netmem_ref netmem)
 	bool put;
 
 	put = true;
-	if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_priv)
-		put = mp_dmabuf_devmem_release_page(pool, netmem);
+	if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_ops)
+		put = pool->mp_ops->release_netmem(pool, netmem);
 	else
 		__page_pool_release_page_dma(pool, netmem);
 
@@ -1048,8 +1055,8 @@ static void __page_pool_destroy(struct page_pool *pool)
 	page_pool_unlist(pool);
 	page_pool_uninit(pool);
 
-	if (pool->mp_priv) {
-		mp_dmabuf_devmem_destroy(pool);
+	if (pool->mp_ops) {
+		pool->mp_ops->destroy(pool);
 		static_branch_dec(&page_pool_mem_providers);
 	}
 
@@ -1190,3 +1197,31 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid)
 	}
 }
 EXPORT_SYMBOL(page_pool_update_nid);
+
+bool net_mp_niov_set_dma_addr(struct net_iov *niov, dma_addr_t addr)
+{
+	return page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov), addr);
+}
+
+/* Associate a niov with a page pool. Should follow with a matching
+ * net_mp_niov_clear_page_pool()
+ */
+void net_mp_niov_set_page_pool(struct page_pool *pool, struct net_iov *niov)
+{
+	netmem_ref netmem = net_iov_to_netmem(niov);
+
+	page_pool_set_pp_info(pool, netmem);
+
+	pool->pages_state_hold_cnt++;
+	trace_page_pool_state_hold(pool, netmem, pool->pages_state_hold_cnt);
+}
+
+/* Disassociate a niov from a page pool. Should only be used in the
+ * ->release_netmem() path.
+ */
+void net_mp_niov_clear_page_pool(struct net_iov *niov)
+{
+	netmem_ref netmem = net_iov_to_netmem(niov);
+
+	page_pool_clear_pp_info(netmem);
+}
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index 6677e0c2e256..9d8a3d8597fa 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -8,9 +8,9 @@
 #include <net/netdev_rx_queue.h>
 #include <net/page_pool/helpers.h>
 #include <net/page_pool/types.h>
+#include <net/page_pool/memory_provider.h>
 #include <net/sock.h>
 
-#include "devmem.h"
 #include "page_pool_priv.h"
 #include "netdev-genl-gen.h"
 
@@ -216,7 +216,6 @@ static int
 page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 		  const struct genl_info *info)
 {
-	struct net_devmem_dmabuf_binding *binding = pool->mp_priv;
 	size_t inflight, refsz;
 	unsigned int napi_id;
 	void *hdr;
@@ -249,7 +248,7 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 			 pool->user.detach_time))
 		goto err_cancel;
 
-	if (binding && nla_put_u32(rsp, NETDEV_A_PAGE_POOL_DMABUF, binding->id))
+	if (pool->mp_ops && pool->mp_ops->nl_fill(pool->mp_priv, rsp, NULL))
 		goto err_cancel;
 
 	genlmsg_end(rsp, hdr);
@@ -356,7 +355,7 @@ void page_pool_unlist(struct page_pool *pool)
 int page_pool_check_memory_provider(struct net_device *dev,
 				    struct netdev_rx_queue *rxq)
 {
-	struct net_devmem_dmabuf_binding *binding = rxq->mp_params.mp_priv;
+	void *binding = rxq->mp_params.mp_priv;
 	struct page_pool *pool;
 	struct hlist_node *n;
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d1e559fce918..abe1a461ea67 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -80,6 +80,11 @@ void rtnl_lock(void)
 }
 EXPORT_SYMBOL(rtnl_lock);
 
+int rtnl_lock_interruptible(void)
+{
+	return mutex_lock_interruptible(&rtnl_mutex);
+}
+
 int rtnl_lock_killable(void)
 {
 	return mutex_lock_killable(&rtnl_mutex);
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index b97374b508f6..ac8b6107863e 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -214,6 +214,24 @@ const char link_mode_names[][ETH_GSTRING_LEN] = {
 	__DEFINE_LINK_MODE_NAME(10, T1S, Half),
 	__DEFINE_LINK_MODE_NAME(10, T1S_P2MP, Half),
 	__DEFINE_LINK_MODE_NAME(10, T1BRR, Full),
+	__DEFINE_LINK_MODE_NAME(200000, CR, Full),
+	__DEFINE_LINK_MODE_NAME(200000, KR, Full),
+	__DEFINE_LINK_MODE_NAME(200000, DR, Full),
+	__DEFINE_LINK_MODE_NAME(200000, DR_2, Full),
+	__DEFINE_LINK_MODE_NAME(200000, SR, Full),
+	__DEFINE_LINK_MODE_NAME(200000, VR, Full),
+	__DEFINE_LINK_MODE_NAME(400000, CR2, Full),
+	__DEFINE_LINK_MODE_NAME(400000, KR2, Full),
+	__DEFINE_LINK_MODE_NAME(400000, DR2, Full),
+	__DEFINE_LINK_MODE_NAME(400000, DR2_2, Full),
+	__DEFINE_LINK_MODE_NAME(400000, SR2, Full),
+	__DEFINE_LINK_MODE_NAME(400000, VR2, Full),
+	__DEFINE_LINK_MODE_NAME(800000, CR4, Full),
+	__DEFINE_LINK_MODE_NAME(800000, KR4, Full),
+	__DEFINE_LINK_MODE_NAME(800000, DR4, Full),
+	__DEFINE_LINK_MODE_NAME(800000, DR4_2, Full),
+	__DEFINE_LINK_MODE_NAME(800000, SR4, Full),
+	__DEFINE_LINK_MODE_NAME(800000, VR4, Full),
 };
 static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS);
 
@@ -222,8 +240,11 @@ static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS);
 #define __LINK_MODE_LANES_CR4		4
 #define __LINK_MODE_LANES_CR8		8
 #define __LINK_MODE_LANES_DR		1
+#define __LINK_MODE_LANES_DR_2		1
 #define __LINK_MODE_LANES_DR2		2
+#define __LINK_MODE_LANES_DR2_2		2
 #define __LINK_MODE_LANES_DR4		4
+#define __LINK_MODE_LANES_DR4_2		4
 #define __LINK_MODE_LANES_DR8		8
 #define __LINK_MODE_LANES_KR		1
 #define __LINK_MODE_LANES_KR2		2
@@ -252,6 +273,9 @@ static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS);
 #define __LINK_MODE_LANES_T1L		1
 #define __LINK_MODE_LANES_T1S		1
 #define __LINK_MODE_LANES_T1S_P2MP	1
+#define __LINK_MODE_LANES_VR		1
+#define __LINK_MODE_LANES_VR2		2
+#define __LINK_MODE_LANES_VR4		4
 #define __LINK_MODE_LANES_VR8		8
 #define __LINK_MODE_LANES_DR8_2		8
 #define __LINK_MODE_LANES_T1BRR		1
@@ -379,6 +403,24 @@ const struct link_mode_info link_mode_params[] = {
 	__DEFINE_LINK_MODE_PARAMS(10, T1S, Half),
 	__DEFINE_LINK_MODE_PARAMS(10, T1S_P2MP, Half),
 	__DEFINE_LINK_MODE_PARAMS(10, T1BRR, Full),
+	__DEFINE_LINK_MODE_PARAMS(200000, CR, Full),
+	__DEFINE_LINK_MODE_PARAMS(200000, KR, Full),
+	__DEFINE_LINK_MODE_PARAMS(200000, DR, Full),
+	__DEFINE_LINK_MODE_PARAMS(200000, DR_2, Full),
+	__DEFINE_LINK_MODE_PARAMS(200000, SR, Full),
+	__DEFINE_LINK_MODE_PARAMS(200000, VR, Full),
+	__DEFINE_LINK_MODE_PARAMS(400000, CR2, Full),
+	__DEFINE_LINK_MODE_PARAMS(400000, KR2, Full),
+	__DEFINE_LINK_MODE_PARAMS(400000, DR2, Full),
+	__DEFINE_LINK_MODE_PARAMS(400000, DR2_2, Full),
+	__DEFINE_LINK_MODE_PARAMS(400000, SR2, Full),
+	__DEFINE_LINK_MODE_PARAMS(400000, VR2, Full),
+	__DEFINE_LINK_MODE_PARAMS(800000, CR4, Full),
+	__DEFINE_LINK_MODE_PARAMS(800000, KR4, Full),
+	__DEFINE_LINK_MODE_PARAMS(800000, DR4, Full),
+	__DEFINE_LINK_MODE_PARAMS(800000, DR4_2, Full),
+	__DEFINE_LINK_MODE_PARAMS(800000, SR4, Full),
+	__DEFINE_LINK_MODE_PARAMS(800000, VR4, Full),
 };
 static_assert(ARRAY_SIZE(link_mode_params) == __ETHTOOL_LINK_MODE_MASK_NBITS);
 
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index ed1b6b44faf8..c9f11a046c26 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -141,7 +141,6 @@ static int ipgre_err(struct sk_buff *skb, u32 info,
 	const struct iphdr *iph;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
-	unsigned int data_len = 0;
 	struct ip_tunnel *t;
 
 	if (tpi->proto == htons(ETH_P_TEB))
@@ -182,7 +181,6 @@ static int ipgre_err(struct sk_buff *skb, u32 info,
 	case ICMP_TIME_EXCEEDED:
 		if (code != ICMP_EXC_TTL)
 			return 0;
-		data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */
 		break;
 
 	case ICMP_REDIRECT:
@@ -190,10 +188,16 @@ static int ipgre_err(struct sk_buff *skb, u32 info,
 	}
 
 #if IS_ENABLED(CONFIG_IPV6)
-	if (tpi->proto == htons(ETH_P_IPV6) &&
-	    !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len,
-					type, data_len))
-		return 0;
+	if (tpi->proto == htons(ETH_P_IPV6)) {
+		unsigned int data_len = 0;
+
+		if (type == ICMP_TIME_EXCEEDED)
+			data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */
+
+		if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len,
+						type, data_len))
+			return 0;
+	}
 #endif
 
 	if (t->parms.iph.daddr == 0 ||
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 57df7c1d2faa..c2e24da633d4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2493,6 +2493,11 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb,
 			}
 
 			niov = skb_frag_net_iov(frag);
+			if (!net_is_devmem_iov(niov)) {
+				err = -ENODEV;
+				goto out;
+			}
+
 			end = start + skb_frag_size(frag);
 			copy = end - offset;
 
@@ -2511,7 +2516,7 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb,
 
 				/* Will perform the exchange later */
 				dmabuf_cmsg.frag_token = tcp_xa_pool.tokens[tcp_xa_pool.idx];
-				dmabuf_cmsg.dmabuf_id = net_iov_binding_id(niov);
+				dmabuf_cmsg.dmabuf_id = net_devmem_iov_binding_id(niov);
 
 				offset += copy;
 				remaining_len -= copy;
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index e4be227d3ad6..6c6ee183802d 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -87,6 +87,11 @@ enum {
 };
 
 enum {
+	__NETDEV_A_IO_URING_PROVIDER_INFO_MAX,
+	NETDEV_A_IO_URING_PROVIDER_INFO_MAX = (__NETDEV_A_IO_URING_PROVIDER_INFO_MAX - 1)
+};
+
+enum {
 	NETDEV_A_PAGE_POOL_ID = 1,
 	NETDEV_A_PAGE_POOL_IFINDEX,
 	NETDEV_A_PAGE_POOL_NAPI_ID,
@@ -94,6 +99,7 @@ enum {
 	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
 	NETDEV_A_PAGE_POOL_DETACH_TIME,
 	NETDEV_A_PAGE_POOL_DMABUF,
+	NETDEV_A_PAGE_POOL_IO_URING,
 
 	__NETDEV_A_PAGE_POOL_MAX,
 	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
@@ -136,6 +142,7 @@ enum {
 	NETDEV_A_QUEUE_TYPE,
 	NETDEV_A_QUEUE_NAPI_ID,
 	NETDEV_A_QUEUE_DMABUF,
+	NETDEV_A_QUEUE_IO_URING,
 
 	__NETDEV_A_QUEUE_MAX,
 	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps
index 0712b5e82eb7..d027a07c1e2c 100644
--- a/tools/net/ynl/Makefile.deps
+++ b/tools/net/ynl/Makefile.deps
@@ -17,9 +17,11 @@ get_hdr_inc=-D$(1) -include $(UAPI_PATH)/linux/$(2)
 CFLAGS_devlink:=$(call get_hdr_inc,_LINUX_DEVLINK_H_,devlink.h)
 CFLAGS_dpll:=$(call get_hdr_inc,_LINUX_DPLL_H,dpll.h)
 CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_H,ethtool.h) \
-		$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h)
+	$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) \
+	$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_GENERATED_H,ethtool_netlink_generated.h)
 CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h)
 CFLAGS_mptcp_pm:=$(call get_hdr_inc,_LINUX_MPTCP_PM_H,mptcp_pm.h)
+CFLAGS_net_shaper:=$(call get_hdr_inc,_LINUX_NET_SHAPER_H,net_shaper.h)
 CFLAGS_netdev:=$(call get_hdr_inc,_LINUX_NETDEV_H,netdev.h)
 CFLAGS_nlctrl:=$(call get_hdr_inc,__LINUX_GENERIC_NETLINK_H,genetlink.h)
 CFLAGS_nfsd:=$(call get_hdr_inc,_LINUX_NFSD_NETLINK_H,nfsd_netlink.h)
diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py
index c2eabc90dce8..b22082fd660e 100755
--- a/tools/net/ynl/pyynl/ynl_gen_c.py
+++ b/tools/net/ynl/pyynl/ynl_gen_c.py
@@ -100,7 +100,7 @@ class Type(SpecAttr):
         if isinstance(value, int):
             return value
         if value in self.family.consts:
-            raise Exception("Resolving family constants not implemented, yet")
+            return self.family.consts[value]["value"]
         return limit_to_number(value)
 
     def get_limit_str(self, limit, default=None, suffix=''):
@@ -110,6 +110,9 @@ class Type(SpecAttr):
         if isinstance(value, int):
             return str(value) + suffix
         if value in self.family.consts:
+            const = self.family.consts[value]
+            if const.get('header'):
+                return c_upper(value)
             return c_upper(f"{self.family['name']}-{value}")
         return c_upper(value)
 
@@ -2549,6 +2552,9 @@ def render_uapi(family, cw):
 
     defines = []
     for const in family['definitions']:
+        if const.get('header'):
+            continue
+
         if const['type'] != 'const':
             cw.writes_defines(defines)
             defines = []
diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile
index 137470bdee0c..c7f1c443f2af 100644
--- a/tools/testing/selftests/drivers/net/Makefile
+++ b/tools/testing/selftests/drivers/net/Makefile
@@ -7,6 +7,7 @@ TEST_INCLUDES := $(wildcard lib/py/*.py) \
 
 TEST_PROGS := \
 	netcons_basic.sh \
+	netcons_fragmented_msg.sh \
 	netcons_overflow.sh \
 	ping.py \
 	queues.py \
diff --git a/tools/testing/selftests/drivers/net/hw/.gitignore b/tools/testing/selftests/drivers/net/hw/.gitignore
index e9fe6ede681a..6942bf575497 100644
--- a/tools/testing/selftests/drivers/net/hw/.gitignore
+++ b/tools/testing/selftests/drivers/net/hw/.gitignore
@@ -1 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+iou-zcrx
 ncdevmem
diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index 21ba64ce1e34..7efc47c89463 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0+ OR MIT
 
+TEST_GEN_FILES = iou-zcrx
+
 TEST_PROGS = \
 	csum.py \
 	devlink_port_split.py \
@@ -10,6 +12,7 @@ TEST_PROGS = \
 	ethtool_rmon.sh \
 	hw_stats_l3.sh \
 	hw_stats_l3_gre.sh \
+	iou-zcrx.py \
 	loopback.sh \
 	nic_link_layer.py \
 	nic_performance.py \
@@ -38,3 +41,5 @@ include ../../../lib.mk
 # YNL build
 YNL_GENS := ethtool netdev
 include ../../../net/ynl.mk
+
+$(OUTPUT)/iou-zcrx: LDLIBS += -luring
diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.c b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c
new file mode 100644
index 000000000000..c26b4180eddd
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c
@@ -0,0 +1,457 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <assert.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <arpa/inet.h>
+#include <linux/errqueue.h>
+#include <linux/if_packet.h>
+#include <linux/ipv6.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/tcp.h>
+#include <netinet/udp.h>
+#include <sys/epoll.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/resource.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <sys/wait.h>
+
+#include <liburing.h>
+
+#define PAGE_SIZE (4096)
+#define AREA_SIZE (8192 * PAGE_SIZE)
+#define SEND_SIZE (512 * 4096)
+#define min(a, b) \
+	({ \
+		typeof(a) _a = (a); \
+		typeof(b) _b = (b); \
+		_a < _b ? _a : _b; \
+	})
+#define min_t(t, a, b) \
+	({ \
+		t _ta = (a); \
+		t _tb = (b); \
+		min(_ta, _tb); \
+	})
+
+#define ALIGN_UP(v, align) (((v) + (align) - 1) & ~((align) - 1))
+
+static int cfg_server;
+static int cfg_client;
+static int cfg_port = 8000;
+static int cfg_payload_len;
+static const char *cfg_ifname;
+static int cfg_queue_id = -1;
+static bool cfg_oneshot;
+static int cfg_oneshot_recvs;
+static int cfg_send_size = SEND_SIZE;
+static struct sockaddr_in6 cfg_addr;
+
+static char payload[SEND_SIZE] __attribute__((aligned(PAGE_SIZE)));
+static void *area_ptr;
+static void *ring_ptr;
+static size_t ring_size;
+static struct io_uring_zcrx_rq rq_ring;
+static unsigned long area_token;
+static int connfd;
+static bool stop;
+static size_t received;
+
+static unsigned long gettimeofday_ms(void)
+{
+	struct timeval tv;
+
+	gettimeofday(&tv, NULL);
+	return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
+{
+	int ret;
+
+	sin6->sin6_family = AF_INET6;
+	sin6->sin6_port = htons(port);
+
+	ret = inet_pton(sin6->sin6_family, str, &sin6->sin6_addr);
+	if (ret != 1) {
+		/* fallback to plain IPv4 */
+		ret = inet_pton(AF_INET, str, &sin6->sin6_addr.s6_addr32[3]);
+		if (ret != 1)
+			return -1;
+
+		/* add ::ffff prefix */
+		sin6->sin6_addr.s6_addr32[0] = 0;
+		sin6->sin6_addr.s6_addr32[1] = 0;
+		sin6->sin6_addr.s6_addr16[4] = 0;
+		sin6->sin6_addr.s6_addr16[5] = 0xffff;
+	}
+
+	return 0;
+}
+
+static inline size_t get_refill_ring_size(unsigned int rq_entries)
+{
+	size_t size;
+
+	ring_size = rq_entries * sizeof(struct io_uring_zcrx_rqe);
+	/* add space for the header (head/tail/etc.) */
+	ring_size += PAGE_SIZE;
+	return ALIGN_UP(ring_size, 4096);
+}
+
+static void setup_zcrx(struct io_uring *ring)
+{
+	unsigned int ifindex;
+	unsigned int rq_entries = 4096;
+	int ret;
+
+	ifindex = if_nametoindex(cfg_ifname);
+	if (!ifindex)
+		error(1, 0, "bad interface name: %s", cfg_ifname);
+
+	area_ptr = mmap(NULL,
+			AREA_SIZE,
+			PROT_READ | PROT_WRITE,
+			MAP_ANONYMOUS | MAP_PRIVATE,
+			0,
+			0);
+	if (area_ptr == MAP_FAILED)
+		error(1, 0, "mmap(): zero copy area");
+
+	ring_size = get_refill_ring_size(rq_entries);
+	ring_ptr = mmap(NULL,
+			ring_size,
+			PROT_READ | PROT_WRITE,
+			MAP_ANONYMOUS | MAP_PRIVATE,
+			0,
+			0);
+
+	struct io_uring_region_desc region_reg = {
+		.size = ring_size,
+		.user_addr = (__u64)(unsigned long)ring_ptr,
+		.flags = IORING_MEM_REGION_TYPE_USER,
+	};
+
+	struct io_uring_zcrx_area_reg area_reg = {
+		.addr = (__u64)(unsigned long)area_ptr,
+		.len = AREA_SIZE,
+		.flags = 0,
+	};
+
+	struct io_uring_zcrx_ifq_reg reg = {
+		.if_idx = ifindex,
+		.if_rxq = cfg_queue_id,
+		.rq_entries = rq_entries,
+		.area_ptr = (__u64)(unsigned long)&area_reg,
+		.region_ptr = (__u64)(unsigned long)&region_reg,
+	};
+
+	ret = io_uring_register_ifq(ring, &reg);
+	if (ret)
+		error(1, 0, "io_uring_register_ifq(): %d", ret);
+
+	rq_ring.khead = (unsigned int *)((char *)ring_ptr + reg.offsets.head);
+	rq_ring.ktail = (unsigned int *)((char *)ring_ptr + reg.offsets.tail);
+	rq_ring.rqes = (struct io_uring_zcrx_rqe *)((char *)ring_ptr + reg.offsets.rqes);
+	rq_ring.rq_tail = 0;
+	rq_ring.ring_entries = reg.rq_entries;
+
+	area_token = area_reg.rq_area_token;
+}
+
+static void add_accept(struct io_uring *ring, int sockfd)
+{
+	struct io_uring_sqe *sqe;
+
+	sqe = io_uring_get_sqe(ring);
+
+	io_uring_prep_accept(sqe, sockfd, NULL, NULL, 0);
+	sqe->user_data = 1;
+}
+
+static void add_recvzc(struct io_uring *ring, int sockfd)
+{
+	struct io_uring_sqe *sqe;
+
+	sqe = io_uring_get_sqe(ring);
+
+	io_uring_prep_rw(IORING_OP_RECV_ZC, sqe, sockfd, NULL, 0, 0);
+	sqe->ioprio |= IORING_RECV_MULTISHOT;
+	sqe->user_data = 2;
+}
+
+static void add_recvzc_oneshot(struct io_uring *ring, int sockfd, size_t len)
+{
+	struct io_uring_sqe *sqe;
+
+	sqe = io_uring_get_sqe(ring);
+
+	io_uring_prep_rw(IORING_OP_RECV_ZC, sqe, sockfd, NULL, len, 0);
+	sqe->ioprio |= IORING_RECV_MULTISHOT;
+	sqe->user_data = 2;
+}
+
+static void process_accept(struct io_uring *ring, struct io_uring_cqe *cqe)
+{
+	if (cqe->res < 0)
+		error(1, 0, "accept()");
+	if (connfd)
+		error(1, 0, "Unexpected second connection");
+
+	connfd = cqe->res;
+	if (cfg_oneshot)
+		add_recvzc_oneshot(ring, connfd, PAGE_SIZE);
+	else
+		add_recvzc(ring, connfd);
+}
+
+static void process_recvzc(struct io_uring *ring, struct io_uring_cqe *cqe)
+{
+	unsigned rq_mask = rq_ring.ring_entries - 1;
+	struct io_uring_zcrx_cqe *rcqe;
+	struct io_uring_zcrx_rqe *rqe;
+	struct io_uring_sqe *sqe;
+	uint64_t mask;
+	char *data;
+	ssize_t n;
+	int i;
+
+	if (cqe->res == 0 && cqe->flags == 0 && cfg_oneshot_recvs == 0) {
+		stop = true;
+		return;
+	}
+
+	if (cqe->res < 0)
+		error(1, 0, "recvzc(): %d", cqe->res);
+
+	if (cfg_oneshot) {
+		if (cqe->res == 0 && cqe->flags == 0 && cfg_oneshot_recvs) {
+			add_recvzc_oneshot(ring, connfd, PAGE_SIZE);
+			cfg_oneshot_recvs--;
+		}
+	} else if (!(cqe->flags & IORING_CQE_F_MORE)) {
+		add_recvzc(ring, connfd);
+	}
+
+	rcqe = (struct io_uring_zcrx_cqe *)(cqe + 1);
+
+	n = cqe->res;
+	mask = (1ULL << IORING_ZCRX_AREA_SHIFT) - 1;
+	data = (char *)area_ptr + (rcqe->off & mask);
+
+	for (i = 0; i < n; i++) {
+		if (*(data + i) != payload[(received + i)])
+			error(1, 0, "payload mismatch at ", i);
+	}
+	received += n;
+
+	rqe = &rq_ring.rqes[(rq_ring.rq_tail & rq_mask)];
+	rqe->off = (rcqe->off & ~IORING_ZCRX_AREA_MASK) | area_token;
+	rqe->len = cqe->res;
+	io_uring_smp_store_release(rq_ring.ktail, ++rq_ring.rq_tail);
+}
+
+static void server_loop(struct io_uring *ring)
+{
+	struct io_uring_cqe *cqe;
+	unsigned int count = 0;
+	unsigned int head;
+	int i, ret;
+
+	io_uring_submit_and_wait(ring, 1);
+
+	io_uring_for_each_cqe(ring, head, cqe) {
+		if (cqe->user_data == 1)
+			process_accept(ring, cqe);
+		else if (cqe->user_data == 2)
+			process_recvzc(ring, cqe);
+		else
+			error(1, 0, "unknown cqe");
+		count++;
+	}
+	io_uring_cq_advance(ring, count);
+}
+
+static void run_server(void)
+{
+	unsigned int flags = 0;
+	struct io_uring ring;
+	int fd, enable, ret;
+	uint64_t tstop;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd == -1)
+		error(1, 0, "socket()");
+
+	enable = 1;
+	ret = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &enable, sizeof(int));
+	if (ret < 0)
+		error(1, 0, "setsockopt(SO_REUSEADDR)");
+
+	ret = bind(fd, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr));
+	if (ret < 0)
+		error(1, 0, "bind()");
+
+	if (listen(fd, 1024) < 0)
+		error(1, 0, "listen()");
+
+	flags |= IORING_SETUP_COOP_TASKRUN;
+	flags |= IORING_SETUP_SINGLE_ISSUER;
+	flags |= IORING_SETUP_DEFER_TASKRUN;
+	flags |= IORING_SETUP_SUBMIT_ALL;
+	flags |= IORING_SETUP_CQE32;
+
+	io_uring_queue_init(512, &ring, flags);
+
+	setup_zcrx(&ring);
+
+	add_accept(&ring, fd);
+
+	tstop = gettimeofday_ms() + 5000;
+	while (!stop && gettimeofday_ms() < tstop)
+		server_loop(&ring);
+
+	if (!stop)
+		error(1, 0, "test failed\n");
+}
+
+static void run_client(void)
+{
+	ssize_t to_send = cfg_send_size;
+	ssize_t sent = 0;
+	ssize_t chunk, res;
+	int fd;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd == -1)
+		error(1, 0, "socket()");
+
+	if (connect(fd, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr)))
+		error(1, 0, "connect()");
+
+	while (to_send) {
+		void *src = &payload[sent];
+
+		chunk = min_t(ssize_t, cfg_payload_len, to_send);
+		res = send(fd, src, chunk, 0);
+		if (res < 0)
+			error(1, 0, "send(): %d", sent);
+		sent += res;
+		to_send -= res;
+	}
+
+	close(fd);
+}
+
+static void usage(const char *filepath)
+{
+	error(1, 0, "Usage: %s (-4|-6) (-s|-c) -h<server_ip> -p<port> "
+		    "-l<payload_size> -i<ifname> -q<rxq_id>", filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	const int max_payload_len = sizeof(payload) -
+				    sizeof(struct ipv6hdr) -
+				    sizeof(struct tcphdr) -
+				    40 /* max tcp options */;
+	struct sockaddr_in6 *addr6 = (void *) &cfg_addr;
+	char *addr = NULL;
+	int ret;
+	int c;
+
+	if (argc <= 1)
+		usage(argv[0]);
+	cfg_payload_len = max_payload_len;
+
+	while ((c = getopt(argc, argv, "sch:p:l:i:q:o:z:")) != -1) {
+		switch (c) {
+		case 's':
+			if (cfg_client)
+				error(1, 0, "Pass one of -s or -c");
+			cfg_server = 1;
+			break;
+		case 'c':
+			if (cfg_server)
+				error(1, 0, "Pass one of -s or -c");
+			cfg_client = 1;
+			break;
+		case 'h':
+			addr = optarg;
+			break;
+		case 'p':
+			cfg_port = strtoul(optarg, NULL, 0);
+			break;
+		case 'l':
+			cfg_payload_len = strtoul(optarg, NULL, 0);
+			break;
+		case 'i':
+			cfg_ifname = optarg;
+			break;
+		case 'q':
+			cfg_queue_id = strtoul(optarg, NULL, 0);
+			break;
+		case 'o': {
+			cfg_oneshot = true;
+			cfg_oneshot_recvs = strtoul(optarg, NULL, 0);
+			break;
+		}
+		case 'z':
+			cfg_send_size = strtoul(optarg, NULL, 0);
+			break;
+		}
+	}
+
+	if (cfg_server && addr)
+		error(1, 0, "Receiver cannot have -h specified");
+
+	memset(addr6, 0, sizeof(*addr6));
+	addr6->sin6_family = AF_INET6;
+	addr6->sin6_port = htons(cfg_port);
+	addr6->sin6_addr = in6addr_any;
+	if (addr) {
+		ret = parse_address(addr, cfg_port, addr6);
+		if (ret)
+			error(1, 0, "receiver address parse error: %s", addr);
+	}
+
+	if (cfg_payload_len > max_payload_len)
+		error(1, 0, "-l: payload exceeds max (%d)", max_payload_len);
+}
+
+int main(int argc, char **argv)
+{
+	const char *cfg_test = argv[argc - 1];
+	int i;
+
+	parse_opts(argc, argv);
+
+	for (i = 0; i < SEND_SIZE; i++)
+		payload[i] = 'a' + (i % 26);
+
+	if (cfg_server)
+		run_server();
+	else if (cfg_client)
+		run_client();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
new file mode 100755
index 000000000000..d301d9b356f7
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
@@ -0,0 +1,87 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import re
+from os import path
+from lib.py import ksft_run, ksft_exit
+from lib.py import NetDrvEpEnv
+from lib.py import bkg, cmd, ethtool, wait_port_listen
+
+
+def _get_rx_ring_entries(cfg):
+    output = ethtool(f"-g {cfg.ifname}", host=cfg.remote).stdout
+    values = re.findall(r'RX:\s+(\d+)', output)
+    return int(values[1])
+
+
+def _get_combined_channels(cfg):
+    output = ethtool(f"-l {cfg.ifname}", host=cfg.remote).stdout
+    values = re.findall(r'Combined:\s+(\d+)', output)
+    return int(values[1])
+
+
+def _set_flow_rule(cfg, chan):
+    output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port 9999 action {chan}", host=cfg.remote).stdout
+    values = re.search(r'ID (\d+)', output).group(1)
+    return int(values)
+
+
+def test_zcrx(cfg) -> None:
+    cfg.require_v6()
+
+    combined_chans = _get_combined_channels(cfg)
+    if combined_chans < 2:
+        raise KsftSkipEx('at least 2 combined channels required')
+    rx_ring = _get_rx_ring_entries(cfg)
+
+    try:
+        ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
+        ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
+        flow_rule_id = _set_flow_rule(cfg, combined_chans - 1)
+
+        rx_cmd = f"{cfg.bin_remote} -s -p 9999 -i {cfg.ifname} -q {combined_chans - 1}"
+        tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_v6} -p 9999 -l 12840"
+        with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
+            wait_port_listen(9999, proto="tcp", host=cfg.remote)
+            cmd(tx_cmd)
+    finally:
+        ethtool(f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
+        ethtool(f"-X {cfg.ifname} default", host=cfg.remote)
+        ethtool(f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
+
+
+def test_zcrx_oneshot(cfg) -> None:
+    cfg.require_v6()
+
+    combined_chans = _get_combined_channels(cfg)
+    if combined_chans < 2:
+        raise KsftSkipEx('at least 2 combined channels required')
+    rx_ring = _get_rx_ring_entries(cfg)
+
+    try:
+        ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
+        ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
+        flow_rule_id = _set_flow_rule(cfg, combined_chans - 1)
+
+        rx_cmd = f"{cfg.bin_remote} -s -p 9999 -i {cfg.ifname} -q {combined_chans - 1} -o 4"
+        tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_v6} -p 9999 -l 4096 -z 16384"
+        with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
+            wait_port_listen(9999, proto="tcp", host=cfg.remote)
+            cmd(tx_cmd)
+    finally:
+        ethtool(f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
+        ethtool(f"-X {cfg.ifname} default", host=cfg.remote)
+        ethtool(f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__) as cfg:
+        cfg.bin_local = path.abspath(path.dirname(__file__) + "/../../../drivers/net/hw/iou-zcrx")
+        cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
+
+        ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
index 3acaba41ac7b..0c262b123fdd 100644
--- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
+++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
@@ -110,6 +110,13 @@ function create_dynamic_target() {
 	echo 1 > "${NETCONS_PATH}"/enabled
 }
 
+# Do not append the release to the header of the message
+function disable_release_append() {
+	echo 0 > "${NETCONS_PATH}"/enabled
+	echo 0 > "${NETCONS_PATH}"/release
+	echo 1 > "${NETCONS_PATH}"/enabled
+}
+
 function cleanup() {
 	local NSIM_DEV_SYS_DEL="/sys/bus/netdevsim/del_device"
 
diff --git a/tools/testing/selftests/drivers/net/netcons_fragmented_msg.sh b/tools/testing/selftests/drivers/net/netcons_fragmented_msg.sh
new file mode 100755
index 000000000000..4a71e01a230c
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netcons_fragmented_msg.sh
@@ -0,0 +1,122 @@
+#!/usr/bin/env bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test netconsole's message fragmentation functionality.
+#
+# When a message exceeds the maximum packet size, netconsole splits it into
+# multiple fragments for transmission. This test verifies:
+#  - Correct fragmentation of large messages
+#  - Proper reassembly of fragments at the receiver
+#  - Preservation of userdata across fragments
+#  - Behavior with and without kernel release version appending
+#
+# Author: Breno Leitao <leitao@debian.org>
+
+set -euo pipefail
+
+SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")")
+
+source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh
+
+modprobe netdevsim 2> /dev/null || true
+modprobe netconsole 2> /dev/null || true
+
+# The content of kmsg will be save to the following file
+OUTPUT_FILE="/tmp/${TARGET}"
+
+# set userdata to a long value. In this case, it is "1-2-3-4...50-"
+USERDATA_VALUE=$(printf -- '%.2s-' {1..60})
+
+# Convert the header string in a regexp, so, we can remove
+# the second header as well.
+# A header looks like "13,468,514729715,-,ncfrag=0/1135;". If
+# release is appended, you might find something like:L
+# "6.13.0-04048-g4f561a87745a,13,468,514729715,-,ncfrag=0/1135;"
+function header_to_regex() {
+	# header is everything before ;
+	local HEADER="${1}"
+	REGEX=$(echo "${HEADER}" | cut -d'=' -f1)
+	echo "${REGEX}=[0-9]*\/[0-9]*;"
+}
+
+# We have two headers in the message. Remove both to get the full message,
+# and extract the full message.
+function extract_msg() {
+	local MSGFILE="${1}"
+	# Extract the header, which is the very first thing that arrives in the
+	# first list.
+	HEADER=$(sed -n '1p' "${MSGFILE}" | cut -d';' -f1)
+	HEADER_REGEX=$(header_to_regex "${HEADER}")
+
+	# Remove the two headers from the received message
+	# This will return the message without any header, similarly to what
+	# was sent.
+	sed "s/""${HEADER_REGEX}""//g" "${MSGFILE}"
+}
+
+# Validate the message, which has two messages glued together.
+# unwrap them to make sure all the characters were transmitted.
+# File will look like the following:
+#  13,468,514729715,-,ncfrag=0/1135;<message>
+#   key=<part of key>-13,468,514729715,-,ncfrag=967/1135;<rest of the key>
+function validate_fragmented_result() {
+	# Discard the netconsole headers, and assemble the full message
+	RCVMSG=$(extract_msg "${1}")
+
+	# check for the main message
+	if ! echo "${RCVMSG}" | grep -q "${MSG}"; then
+		echo "Message body doesn't match." >&2
+		echo "msg received=" "${RCVMSG}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	# check userdata
+	if ! echo "${RCVMSG}" | grep -q "${USERDATA_VALUE}"; then
+		echo "message userdata doesn't match" >&2
+		echo "msg received=" "${RCVMSG}" >&2
+		exit "${ksft_fail}"
+	fi
+	# test passed. hooray
+}
+
+# Check for basic system dependency and exit if not found
+check_for_dependencies
+# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5)
+echo "6 5" > /proc/sys/kernel/printk
+# Remove the namespace, interfaces and netconsole target on exit
+trap cleanup EXIT
+# Create one namespace and two interfaces
+set_network
+# Create a dynamic target for netconsole
+create_dynamic_target
+# Set userdata "key" with the "value" value
+set_user_data
+
+
+# TEST 1: Send message and userdata. They will fragment
+# =======
+MSG=$(printf -- 'MSG%.3s=' {1..150})
+
+# Listen for netconsole port inside the namespace and destination interface
+listen_port_and_save_to "${OUTPUT_FILE}" &
+# Wait for socat to start and listen to the port.
+wait_local_port_listen "${NAMESPACE}" "${PORT}" udp
+# Send the message
+echo "${MSG}: ${TARGET}" > /dev/kmsg
+# Wait until socat saves the file to disk
+busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}"
+# Check if the message was not corrupted
+validate_fragmented_result "${OUTPUT_FILE}"
+
+# TEST 2: Test with smaller message, and without release appended
+# =======
+MSG=$(printf -- 'FOOBAR%.3s=' {1..100})
+# Let's disable release and test again.
+disable_release_append
+
+listen_port_and_save_to "${OUTPUT_FILE}" &
+wait_local_port_listen "${NAMESPACE}" "${PORT}" udp
+echo "${MSG}: ${TARGET}" > /dev/kmsg
+busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}"
+validate_fragmented_result "${OUTPUT_FILE}"
+exit "${ksft_pass}"
diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
index d9d587454d20..8c1597ebc2d3 100755
--- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
@@ -149,7 +149,7 @@ cfg_test_host_common()
 	check_err $? "Failed to add $name host entry"
 
 	bridge mdb replace dev br0 port br0 grp $grp $state vid 10 &> /dev/null
-	check_fail $? "Managed to replace $name host entry"
+	check_err $? "Failed to replace $name host entry"
 
 	bridge mdb del dev br0 port br0 grp $grp $state vid 10
 	bridge mdb get dev br0 grp $grp vid 10 &> /dev/null
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index 3f9d50f1ef9e..180c5eca556f 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -740,6 +740,8 @@ test_learning()
 
 	vxlan_flood_test $mac $dst 0 10 0
 
+	# The entry should age out when it only forwards traffic
+	$MZ $h1 -c 50 -d 1sec -p 64 -b $mac -B $dst -t icmp -q &
 	sleep 60
 
 	bridge fdb show brport vx1 | grep $mac | grep -q self
diff --git a/tools/testing/selftests/net/ynl.mk b/tools/testing/selftests/net/ynl.mk
index 12e7cae251be..e907c2751956 100644
--- a/tools/testing/selftests/net/ynl.mk
+++ b/tools/testing/selftests/net/ynl.mk
@@ -27,7 +27,8 @@ $(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig:
 
 $(OUTPUT)/libynl.a: $(YNL_SPECS) $(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig
 	$(Q)rm -f $(top_srcdir)/tools/net/ynl/libynl.a
-	$(Q)$(MAKE) -C $(top_srcdir)/tools/net/ynl GENS="$(YNL_GENS)" libynl.a
+	$(Q)$(MAKE) -C $(top_srcdir)/tools/net/ynl \
+		GENS="$(YNL_GENS)" RSTS="" libynl.a
 	$(Q)cp $(top_srcdir)/tools/net/ynl/libynl.a $(OUTPUT)/libynl.a
 
 EXTRA_CLEAN += \