Merge tag 'mlx5-updates-2022-11-29' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2022-11-29

Misc update for mlx5 driver

1) Various trivial cleanups

2) Maor Dickman, Adds support for trap offload with additional actions

3) From Tariq, UMR (device memory registrations) cleanups,
   UMR WQE must be aligned to 64B per device spec, (not a bug fix).

* tag 'mlx5-updates-2022-11-29' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  net/mlx5e: Support devlink reload of IPsec core
  net/mlx5e: TC, Add offload support for trap with additional actions
  net/mlx5e: Do early return when setup vports dests for slow path flow
  net/mlx5: Remove redundant check
  net/mlx5e: Delete always true DMA check
  net/mlx5e: Don't access directly DMA device pointer
  net/mlx5e: Don't use termination table when redundant
  net/mlx5: Fix orthography errors in documentation
  net/mlx5: Use generic definition for UMR KLM alignment
  net/mlx5: Generalize name of UMR alignment definition
  net/mlx5: Remove unused UMR MTT definitions
  net/mlx5e: Add padding when needed in UMR WQEs
  net/mlx5: Remove unused ctx variables
  net/mlx5e: Replace zero-length arrays with DECLARE_FLEX_ARRAY() helper
  net/mlx5e: Remove unneeded io-mapping.h #include
====================

Link: https://lore.kernel.org/r/20221130051152.479480-1-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

22 files changed, 153 insertions, 135 deletions

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
index 5edf50d7dbd5..e8fa7ac9e6b1 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
@@ -25,7 +25,7 @@ Enabling the driver and kconfig options
 | at build time via kernel Kconfig flags.
 | Basic features, ethernet net device rx/tx offloads and XDP, are available with the most basic flags
 | CONFIG_MLX5_CORE=y/m and CONFIG_MLX5_CORE_EN=y.
-| For the list of advanced features please see below.
+| For the list of advanced features, please see below.
 
 **CONFIG_MLX5_CORE=(y/m/n)** (module mlx5_core.ko)
 
@@ -89,11 +89,11 @@ Enabling the driver and kconfig options
 
 **CONFIG_MLX5_EN_IPSEC=(y/n)**
 
-|    Enables `IPSec XFRM cryptography-offload accelaration <http://www.mellanox.com/related-docs/prod_software/Mellanox_Innova_IPsec_Ethernet_Adapter_Card_User_Manual.pdf>`_.
+|    Enables `IPSec XFRM cryptography-offload acceleration <http://www.mellanox.com/related-docs/prod_software/Mellanox_Innova_IPsec_Ethernet_Adapter_Card_User_Manual.pdf>`_.
 
 **CONFIG_MLX5_EN_TLS=(y/n)**
 
-|   TLS cryptography-offload accelaration.
+|   TLS cryptography-offload acceleration.
 
 
 **CONFIG_MLX5_INFINIBAND=(y/n/m)** (module mlx5_ib.ko)
@@ -139,14 +139,14 @@ flow_steering_mode: Device flow steering mode
 The flow steering mode parameter controls the flow steering mode of the driver.
 Two modes are supported:
 1. 'dmfs' - Device managed flow steering.
-2. 'smfs  - Software/Driver managed flow steering.
+2. 'smfs' - Software/Driver managed flow steering.
 
 In DMFS mode, the HW steering entities are created and managed through the
 Firmware.
 In SMFS mode, the HW steering entities are created and managed though by
-the driver directly into Hardware without firmware intervention.
+the driver directly into hardware without firmware intervention.
 
-SMFS mode is faster and provides better rule inserstion rate compared to default DMFS mode.
+SMFS mode is faster and provides better rule insertion rate compared to default DMFS mode.
 
 User command examples:
 
@@ -165,9 +165,9 @@ User command examples:
 enable_roce: RoCE enablement state
 ----------------------------------
 RoCE enablement state controls driver support for RoCE traffic.
-When RoCE is disabled, there is no gid table, only raw ethernet QPs are supported and traffic on the well known UDP RoCE port is handled as raw ethernet traffic.
+When RoCE is disabled, there is no gid table, only raw ethernet QPs are supported and traffic on the well-known UDP RoCE port is handled as raw ethernet traffic.
 
-To change RoCE enablement state a user must change the driverinit cmode value and run devlink reload.
+To change RoCE enablement state, a user must change the driverinit cmode value and run devlink reload.
 
 User command examples:
 
@@ -186,7 +186,7 @@ User command examples:
 
 esw_port_metadata: Eswitch port metadata state
 ----------------------------------------------
-When applicable, disabling Eswitch metadata can increase packet rate
+When applicable, disabling eswitch metadata can increase packet rate
 up to 20% depending on the use case and packet sizes.
 
 Eswitch port metadata state controls whether to internally tag packets with
@@ -253,26 +253,26 @@ mlx5 subfunction
 ================
 mlx5 supports subfunction management using devlink port (see :ref:`Documentation/networking/devlink/devlink-port.rst <devlink_port>`) interface.
 
-A Subfunction has its own function capabilities and its own resources. This
+A subfunction has its own function capabilities and its own resources. This
 means a subfunction has its own dedicated queues (txq, rxq, cq, eq). These
 queues are neither shared nor stolen from the parent PCI function.
 
-When a subfunction is RDMA capable, it has its own QP1, GID table and rdma
+When a subfunction is RDMA capable, it has its own QP1, GID table, and RDMA
 resources neither shared nor stolen from the parent PCI function.
 
 A subfunction has a dedicated window in PCI BAR space that is not shared
-with ther other subfunctions or the parent PCI function. This ensures that all
-devices (netdev, rdma, vdpa etc.) of the subfunction accesses only assigned
+with the other subfunctions or the parent PCI function. This ensures that all
+devices (netdev, rdma, vdpa, etc.) of the subfunction accesses only assigned
 PCI BAR space.
 
-A Subfunction supports eswitch representation through which it supports tc
+A subfunction supports eswitch representation through which it supports tc
 offloads. The user configures eswitch to send/receive packets from/to
 the subfunction port.
 
 Subfunctions share PCI level resources such as PCI MSI-X IRQs with
 other subfunctions and/or with its parent PCI function.
 
-Example mlx5 software, system and device view::
+Example mlx5 software, system, and device view::
 
        _______
       | admin |
@@ -310,7 +310,7 @@ Example mlx5 software, system and device view::
            |                                      (device add/del)
       _____|____                                    ____|________
      |          |                                  | subfunction |
-     |  PCI NIC |---- activate/deactive events---->| host driver |
+     |  PCI NIC |--- activate/deactivate events--->| host driver |
      |__________|                                  | (mlx5_core) |
                                                    |_____________|
 
@@ -320,7 +320,7 @@ Subfunction is created using devlink port interface.
 
     $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev
 
-- Add a devlink port of subfunction flaovur::
+- Add a devlink port of subfunction flavour::
 
     $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88
     pci/0000:06:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false
@@ -379,18 +379,18 @@ device created for the PCI VF/SF.
       function:
         hw_addr 00:00:00:00:00:00
 
-- Set the MAC address of the VF identified by its unique devlink port index::
+- Set the MAC address of the SF identified by its unique devlink port index::
 
     $ devlink port function set pci/0000:06:00.0/32768 hw_addr 00:00:00:00:88:88
 
     $ devlink port show pci/0000:06:00.0/32768
-    pci/0000:06:00.0/32768: type eth netdev enp6s0pf0sf88 flavour pcivf pfnum 0 sfnum 88
+    pci/0000:06:00.0/32768: type eth netdev enp6s0pf0sf88 flavour pcisf pfnum 0 sfnum 88
       function:
         hw_addr 00:00:00:00:88:88
 
 SF state setup
 --------------
-To use the SF, the user must active the SF using the SF function state
+To use the SF, the user must activate the SF using the SF function state
 attribute.
 
 - Get the state of the SF identified by its unique devlink port index::
@@ -447,7 +447,7 @@ for it.
 
 Additionally, the SF port also gets the event when the driver attaches to the
 auxiliary device of the subfunction. This results in changing the operational
-state of the function. This provides visiblity to the user to decide when is it
+state of the function. This provides visibility to the user to decide when is it
 safe to delete the SF port for graceful termination of the subfunction.
 
 - Show the SF port operational state::
@@ -464,14 +464,14 @@ tx reporter
 -----------
 The tx reporter is responsible for reporting and recovering of the following two error scenarios:
 
-- TX timeout
+- tx timeout
     Report on kernel tx timeout detection.
     Recover by searching lost interrupts.
-- TX error completion
+- tx error completion
     Report on error tx completion.
-    Recover by flushing the TX queue and reset it.
+    Recover by flushing the tx queue and reset it.
 
-TX reporter also support on demand diagnose callback, on which it provides
+tx reporter also support on demand diagnose callback, on which it provides
 real time information of its send queues status.
 
 User commands examples:
@@ -491,32 +491,32 @@ rx reporter
 -----------
 The rx reporter is responsible for reporting and recovering of the following two error scenarios:
 
-- RX queues initialization (population) timeout
-    RX queues descriptors population on ring initialization is done in
-    napi context via triggering an irq, in case of a failure to get
-    the minimum amount of descriptors, a timeout would occur and it
-    could be recoverable by polling the EQ (Event Queue).
-- RX completions with errors (reported by HW on interrupt context)
+- rx queues' initialization (population) timeout
+    Population of rx queues' descriptors on ring initialization is done
+    in napi context via triggering an irq. In case of a failure to get
+    the minimum amount of descriptors, a timeout would occur, and
+    descriptors could be recovered by polling the EQ (Event Queue).
+- rx completions with errors (reported by HW on interrupt context)
     Report on rx completion error.
     Recover (if needed) by flushing the related queue and reset it.
 
-RX reporter also supports on demand diagnose callback, on which it
-provides real time information of its receive queues status.
+rx reporter also supports on demand diagnose callback, on which it
+provides real time information of its receive queues' status.
 
-- Diagnose rx queues status, and corresponding completion queue::
+- Diagnose rx queues' status and corresponding completion queue::
 
     $ devlink health diagnose pci/0000:82:00.0 reporter rx
 
-NOTE: This command has valid output only when interface is up, otherwise the command has empty output.
+NOTE: This command has valid output only when interface is up. Otherwise, the command has empty output.
 
 - Show number of rx errors indicated, number of recover flows ended successfully,
-  is autorecover enabled and graceful period from last recover::
+  is autorecover enabled, and graceful period from last recover::
 
     $ devlink health show pci/0000:82:00.0 reporter rx
 
 fw reporter
 -----------
-The fw reporter implements diagnose and dump callbacks.
+The fw reporter implements `diagnose` and `dump` callbacks.
 It follows symptoms of fw error such as fw syndrome by triggering
 fw core dump and storing it into the dump buffer.
 The fw reporter diagnose command can be triggered any time by the user to check
@@ -537,7 +537,7 @@ running it on other PF or any VF will return "Operation not permitted".
 
 fw fatal reporter
 -----------------
-The fw fatal reporter implements dump and recover callbacks.
+The fw fatal reporter implements `dump` and `recover` callbacks.
 It follows fatal errors indications by CR-space dump and recover flow.
 The CR-space dump uses vsc interface which is valid even if the FW command
 interface is not functional, which is the case in most FW fatal errors.
@@ -552,7 +552,7 @@ User commands examples:
 
     $ devlink health recover pci/0000:82:00.0 reporter fw_fatal
 
-- Read FW CR-space dump if already strored or trigger new one::
+- Read FW CR-space dump if already stored or trigger new one::
 
     $ devlink health dump show pci/0000:82:00.1 reporter fw_fatal
 
@@ -561,10 +561,10 @@ NOTE: This command can run only on PF.
 mlx5 tracepoints
 ================
 
-mlx5 driver provides internal trace points for tracking and debugging using
+mlx5 driver provides internal tracepoints for tracking and debugging using
 kernel tracepoints interfaces (refer to Documentation/trace/ftrace.rst).
 
-For the list of support mlx5 events check /sys/kernel/debug/tracing/events/mlx5/
+For the list of support mlx5 events, check `/sys/kernel/debug/tracing/events/mlx5/`.
 
 tc and eswitch offloads tracepoints:
 
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index bc97958818bb..e6e021af6aa9 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -230,8 +230,7 @@ static bool mlx5_ib_invalidate_range(struct mmu_interval_notifier *mni,
 	struct ib_umem_odp *umem_odp =
 		container_of(mni, struct ib_umem_odp, notifier);
 	struct mlx5_ib_mr *mr;
-	const u64 umr_block_mask = (MLX5_UMR_MTT_ALIGNMENT /
-				    sizeof(struct mlx5_mtt)) - 1;
+	const u64 umr_block_mask = MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT - 1;
 	u64 idx = 0, blk_start_idx = 0;
 	u64 invalidations = 0;
 	unsigned long start;
diff --git a/drivers/infiniband/hw/mlx5/umr.c b/drivers/infiniband/hw/mlx5/umr.c
index d5105b5c9979..029e9536ec28 100644
--- a/drivers/infiniband/hw/mlx5/umr.c
+++ b/drivers/infiniband/hw/mlx5/umr.c
@@ -418,7 +418,7 @@ int mlx5r_umr_rereg_pd_access(struct mlx5_ib_mr *mr, struct ib_pd *pd,
 }
 
 #define MLX5_MAX_UMR_CHUNK                                                     \
-	((1 << (MLX5_MAX_UMR_SHIFT + 4)) - MLX5_UMR_MTT_ALIGNMENT)
+	((1 << (MLX5_MAX_UMR_SHIFT + 4)) - MLX5_UMR_FLEX_ALIGNMENT)
 #define MLX5_SPARE_UMR_CHUNK 0x10000
 
 /*
@@ -428,11 +428,11 @@ int mlx5r_umr_rereg_pd_access(struct mlx5_ib_mr *mr, struct ib_pd *pd,
  */
 static void *mlx5r_umr_alloc_xlt(size_t *nents, size_t ent_size, gfp_t gfp_mask)
 {
-	const size_t xlt_chunk_align = MLX5_UMR_MTT_ALIGNMENT / ent_size;
+	const size_t xlt_chunk_align = MLX5_UMR_FLEX_ALIGNMENT / ent_size;
 	size_t size;
 	void *res = NULL;
 
-	static_assert(PAGE_SIZE % MLX5_UMR_MTT_ALIGNMENT == 0);
+	static_assert(PAGE_SIZE % MLX5_UMR_FLEX_ALIGNMENT == 0);
 
 	/*
 	 * MLX5_IB_UPD_XLT_ATOMIC doesn't signal an atomic context just that the
@@ -666,7 +666,7 @@ int mlx5r_umr_update_mr_pas(struct mlx5_ib_mr *mr, unsigned int flags)
 	}
 
 	final_size = (void *)cur_mtt - (void *)mtt;
-	sg.length = ALIGN(final_size, MLX5_UMR_MTT_ALIGNMENT);
+	sg.length = ALIGN(final_size, MLX5_UMR_FLEX_ALIGNMENT);
 	memset(cur_mtt, 0, sg.length - final_size);
 	mlx5r_umr_final_update_xlt(dev, &wqe, mr, &sg, flags);
 
@@ -690,7 +690,7 @@ int mlx5r_umr_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages,
 	int desc_size = (flags & MLX5_IB_UPD_XLT_INDIRECT)
 			       ? sizeof(struct mlx5_klm)
 			       : sizeof(struct mlx5_mtt);
-	const int page_align = MLX5_UMR_MTT_ALIGNMENT / desc_size;
+	const int page_align = MLX5_UMR_FLEX_ALIGNMENT / desc_size;
 	struct mlx5_ib_dev *dev = mr_to_mdev(mr);
 	struct device *ddev = &dev->mdev->pdev->dev;
 	const int page_mask = page_align - 1;
@@ -711,7 +711,7 @@ int mlx5r_umr_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages,
 	if (WARN_ON(!mr->umem->is_odp))
 		return -EINVAL;
 
-	/* UMR copies MTTs in units of MLX5_UMR_MTT_ALIGNMENT bytes,
+	/* UMR copies MTTs in units of MLX5_UMR_FLEX_ALIGNMENT bytes,
 	 * so we need to align the offset and length accordingly
 	 */
 	if (idx & page_mask) {
@@ -748,7 +748,7 @@ int mlx5r_umr_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages,
 		mlx5_odp_populate_xlt(xlt, idx, npages, mr, flags);
 		dma_sync_single_for_device(ddev, sg.addr, sg.length,
 					   DMA_TO_DEVICE);
-		sg.length = ALIGN(size_to_map, MLX5_UMR_MTT_ALIGNMENT);
+		sg.length = ALIGN(size_to_map, MLX5_UMR_FLEX_ALIGNMENT);
 
 		if (pages_mapped + pages_iter >= pages_to_map)
 			mlx5r_umr_final_update_xlt(dev, &wqe, mr, &sg, flags);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index e7a894ba5c3e..d3ca745d107d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -37,7 +37,6 @@
 #include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/random.h>
-#include <linux/io-mapping.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/eq.h>
 #include <linux/debugfs.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index ff5b302531d5..65790ff58a74 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -103,11 +103,11 @@ struct page_pool;
  * size actually used at runtime, but it's not a problem when calculating static
  * array sizes.
  */
-#define MLX5_UMR_MAX_MTT_SPACE \
+#define MLX5_UMR_MAX_FLEX_SPACE \
 	(ALIGN_DOWN(MLX5_SEND_WQE_MAX_SIZE - sizeof(struct mlx5e_umr_wqe), \
-		    MLX5_UMR_MTT_ALIGNMENT))
+		    MLX5_UMR_FLEX_ALIGNMENT))
 #define MLX5_MPWRQ_MAX_PAGES_PER_WQE \
-	rounddown_pow_of_two(MLX5_UMR_MAX_MTT_SPACE / sizeof(struct mlx5_mtt))
+	rounddown_pow_of_two(MLX5_UMR_MAX_FLEX_SPACE / sizeof(struct mlx5_mtt))
 
 #define MLX5E_MAX_RQ_NUM_MTTS	\
 	(ALIGN_DOWN(U16_MAX, 4) * 2) /* Fits into u16 and aligned by WQEBB. */
@@ -160,7 +160,7 @@ struct page_pool;
 	(((wqe_size) - sizeof(struct mlx5e_umr_wqe)) / sizeof(struct mlx5_klm))
 
 #define MLX5E_KLM_ENTRIES_PER_WQE(wqe_size)\
-	ALIGN_DOWN(MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size), MLX5_UMR_KLM_ALIGNMENT)
+	ALIGN_DOWN(MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size), MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT)
 
 #define MLX5E_MAX_KLM_PER_WQE(mdev) \
 	MLX5E_KLM_ENTRIES_PER_WQE(MLX5_SEND_WQE_BB * mlx5e_get_max_sq_aligned_wqebbs(mdev))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 9ec9662d1d0b..585bdc8383ee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -107,7 +107,7 @@ u8 mlx5e_mpwrq_log_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift,
 	/* Keep in sync with MLX5_MPWRQ_MAX_PAGES_PER_WQE. */
 	max_wqe_size = mlx5e_get_max_sq_aligned_wqebbs(mdev) * MLX5_SEND_WQE_BB;
 	max_pages_per_wqe = ALIGN_DOWN(max_wqe_size - sizeof(struct mlx5e_umr_wqe),
-				       MLX5_UMR_MTT_ALIGNMENT) / umr_entry_size;
+				       MLX5_UMR_FLEX_ALIGNMENT) / umr_entry_size;
 	max_log_mpwqe_size = ilog2(max_pages_per_wqe) + page_shift;
 
 	WARN_ON_ONCE(max_log_mpwqe_size < MLX5E_ORDER2_MAX_PACKET_MTU);
@@ -146,7 +146,7 @@ u16 mlx5e_mpwrq_umr_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift,
 	u16 umr_wqe_sz;
 
 	umr_wqe_sz = sizeof(struct mlx5e_umr_wqe) +
-		ALIGN(pages_per_wqe * umr_entry_size, MLX5_UMR_MTT_ALIGNMENT);
+		ALIGN(pages_per_wqe * umr_entry_size, MLX5_UMR_FLEX_ALIGNMENT);
 
 	WARN_ON_ONCE(DIV_ROUND_UP(umr_wqe_sz, MLX5_SEND_WQE_DS) > MLX5_WQE_CTRL_DS_MASK);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c
index 53b270f652b9..915ce201aeb2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c
@@ -3,6 +3,7 @@
 
 #include "act.h"
 #include "en/tc_priv.h"
+#include "eswitch.h"
 
 static bool
 tc_act_can_offload_trap(struct mlx5e_tc_act_parse_state *parse_state,
@@ -10,13 +11,6 @@ tc_act_can_offload_trap(struct mlx5e_tc_act_parse_state *parse_state,
 			int act_index,
 			struct mlx5_flow_attr *attr)
 {
-	struct netlink_ext_ack *extack = parse_state->extack;
-
-	if (parse_state->flow_action->num_entries != 1) {
-		NL_SET_ERR_MSG_MOD(extack, "action trap is supported as a sole action only");
-		return false;
-	}
-
 	return true;
 }
 
@@ -27,7 +21,7 @@ tc_act_parse_trap(struct mlx5e_tc_act_parse_state *parse_state,
 		  struct mlx5_flow_attr *attr)
 {
 	attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-	attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH;
+	attr->dest_ft = mlx5_eswitch_get_slow_fdb(priv->mdev->priv.eswitch);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index a715601865d3..1b03ab03fc5a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -345,29 +345,27 @@ static void mlx5e_xfrm_free_state(struct xfrm_state *x)
 	kfree(sa_entry);
 }
 
-int mlx5e_ipsec_init(struct mlx5e_priv *priv)
+void mlx5e_ipsec_init(struct mlx5e_priv *priv)
 {
 	struct mlx5e_ipsec *ipsec;
-	int ret;
+	int ret = -ENOMEM;
 
 	if (!mlx5_ipsec_device_caps(priv->mdev)) {
 		netdev_dbg(priv->netdev, "Not an IPSec offload device\n");
-		return 0;
+		return;
 	}
 
 	ipsec = kzalloc(sizeof(*ipsec), GFP_KERNEL);
 	if (!ipsec)
-		return -ENOMEM;
+		return;
 
 	hash_init(ipsec->sadb_rx);
 	spin_lock_init(&ipsec->sadb_rx_lock);
 	ipsec->mdev = priv->mdev;
 	ipsec->wq = alloc_ordered_workqueue("mlx5e_ipsec: %s", 0,
 					    priv->netdev->name);
-	if (!ipsec->wq) {
-		ret = -ENOMEM;
+	if (!ipsec->wq)
 		goto err_wq;
-	}
 
 	ret = mlx5e_accel_ipsec_fs_init(ipsec);
 	if (ret)
@@ -375,13 +373,14 @@ int mlx5e_ipsec_init(struct mlx5e_priv *priv)
 
 	priv->ipsec = ipsec;
 	netdev_dbg(priv->netdev, "IPSec attached to netdevice\n");
-	return 0;
+	return;
 
 err_fs_init:
 	destroy_workqueue(ipsec->wq);
 err_wq:
 	kfree(ipsec);
-	return (ret != -EOPNOTSUPP) ? ret : 0;
+	mlx5_core_err(priv->mdev, "IPSec initialization failed, %d\n", ret);
+	return;
 }
 
 void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 16bcceec16c4..4c47347d0ee2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -146,7 +146,7 @@ struct mlx5e_ipsec_sa_entry {
 	struct mlx5e_ipsec_modify_state_work modify_work;
 };
 
-int mlx5e_ipsec_init(struct mlx5e_priv *priv);
+void mlx5e_ipsec_init(struct mlx5e_priv *priv);
 void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv);
 void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv);
 
@@ -174,9 +174,8 @@ mlx5e_ipsec_sa2dev(struct mlx5e_ipsec_sa_entry *sa_entry)
 	return sa_entry->ipsec->mdev;
 }
 #else
-static inline int mlx5e_ipsec_init(struct mlx5e_priv *priv)
+static inline void mlx5e_ipsec_init(struct mlx5e_priv *priv)
 {
-	return 0;
 }
 
 static inline void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
index f900709639f6..9369a580743e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -186,7 +186,7 @@ static int mlx5e_macsec_aso_reg_mr(struct mlx5_core_dev *mdev, struct mlx5e_macs
 		return err;
 	}
 
-	dma_device = &mdev->pdev->dev;
+	dma_device = mlx5_core_dma_dev(mdev);
 	dma_addr = dma_map_single(dma_device, umr->ctx, sizeof(umr->ctx), DMA_BIDIRECTIONAL);
 	err = dma_mapping_error(dma_device, dma_addr);
 	if (err) {
@@ -1299,12 +1299,12 @@ static void macsec_aso_build_wqe_ctrl_seg(struct mlx5e_macsec_aso *macsec_aso,
 					  struct mlx5_wqe_aso_ctrl_seg *aso_ctrl,
 					  struct mlx5_aso_ctrl_param *param)
 {
+	struct mlx5e_macsec_umr *umr = macsec_aso->umr;
+
 	memset(aso_ctrl, 0, sizeof(*aso_ctrl));
-	if (macsec_aso->umr->dma_addr) {
-		aso_ctrl->va_l  = cpu_to_be32(macsec_aso->umr->dma_addr | ASO_CTRL_READ_EN);
-		aso_ctrl->va_h  = cpu_to_be32((u64)macsec_aso->umr->dma_addr >> 32);
-		aso_ctrl->l_key = cpu_to_be32(macsec_aso->umr->mkey);
-	}
+	aso_ctrl->va_l = cpu_to_be32(umr->dma_addr | ASO_CTRL_READ_EN);
+	aso_ctrl->va_h = cpu_to_be32((u64)umr->dma_addr >> 32);
+	aso_ctrl->l_key = cpu_to_be32(umr->mkey);
 
 	if (!param)
 		return;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 217c8a478977..8d36e2de53a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -208,7 +208,7 @@ static u16 mlx5e_mpwrq_umr_octowords(u32 entries, enum mlx5e_mpwrq_umr_mode umr_
 	u8 umr_entry_size = mlx5e_mpwrq_umr_entry_size(umr_mode);
 	u32 sz;
 
-	sz = ALIGN(entries * umr_entry_size, MLX5_UMR_MTT_ALIGNMENT);
+	sz = ALIGN(entries * umr_entry_size, MLX5_UMR_FLEX_ALIGNMENT);
 
 	return sz / MLX5_OCTWORD;
 }
@@ -5238,10 +5238,6 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 	}
 	priv->fs = fs;
 
-	err = mlx5e_ipsec_init(priv);
-	if (err)
-		mlx5_core_err(mdev, "IPSec initialization failed, %d\n", err);
-
 	err = mlx5e_ktls_init(priv);
 	if (err)
 		mlx5_core_err(mdev, "TLS initialization failed, %d\n", err);
@@ -5254,7 +5250,6 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 {
 	mlx5e_health_destroy_reporters(priv);
 	mlx5e_ktls_cleanup(priv);
-	mlx5e_ipsec_cleanup(priv);
 	mlx5e_fs_cleanup(priv->fs);
 }
 
@@ -5383,6 +5378,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	int err;
 
 	mlx5e_fs_init_l2_addr(priv->fs, netdev);
+	mlx5e_ipsec_init(priv);
 
 	err = mlx5e_macsec_init(priv);
 	if (err)
@@ -5446,6 +5442,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 	mlx5_lag_remove_netdev(mdev, priv->netdev);
 	mlx5_vxlan_reset_to_default(mdev->vxlan);
 	mlx5e_macsec_cleanup(priv);
+	mlx5e_ipsec_cleanup(priv);
 }
 
 int mlx5e_update_nic_rx(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 1b53e8852c86..623886462c10 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -751,7 +751,6 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev,
 			     struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	int err;
 
 	priv->fs = mlx5e_fs_init(priv->profile, mdev,
 				 !test_bit(MLX5E_STATE_DESTROYING, &priv->state));
@@ -760,10 +759,6 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev,
 		return -ENOMEM;
 	}
 
-	err = mlx5e_ipsec_init(priv);
-	if (err)
-		mlx5_core_err(mdev, "Uplink rep IPsec initialization failed, %d\n", err);
-
 	mlx5e_vxlan_set_netdev_info(priv);
 	mlx5e_build_rep_params(netdev);
 	mlx5e_timestamp_init(priv);
@@ -773,7 +768,6 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev,
 static void mlx5e_cleanup_rep(struct mlx5e_priv *priv)
 {
 	mlx5e_fs_cleanup(priv->fs);
-	mlx5e_ipsec_cleanup(priv);
 }
 
 static int mlx5e_create_rep_ttc_table(struct mlx5e_priv *priv)
@@ -1112,6 +1106,8 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u16 max_mtu;
 
+	mlx5e_ipsec_init(priv);
+
 	netdev->min_mtu = ETH_MIN_MTU;
 	mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1);
 	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
@@ -1158,6 +1154,8 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
 	mlx5e_rep_tc_disable(priv);
 	mlx5_lag_remove_netdev(mdev, priv->netdev);
 	mlx5_vxlan_reset_to_default(mdev->vxlan);
+
+	mlx5e_ipsec_cleanup(priv);
 }
 
 static MLX5E_DEFINE_STATS_GRP(sw_rep, 0);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index b1ea0b995d9c..c8820ab22169 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -593,8 +593,8 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
 	int headroom, i;
 
 	headroom = rq->buff.headroom;
-	new_entries = klm_entries - (shampo->pi & (MLX5_UMR_KLM_ALIGNMENT - 1));
-	entries = ALIGN(klm_entries, MLX5_UMR_KLM_ALIGNMENT);
+	new_entries = klm_entries - (shampo->pi & (MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT - 1));
+	entries = ALIGN(klm_entries, MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT);
 	wqe_bbs = MLX5E_KLM_UMR_WQEBBS(entries);
 	pi = mlx5e_icosq_get_next_pi(sq, wqe_bbs);
 	umr_wqe = mlx5_wq_cyc_get_wqe(&sq->wq, pi);
@@ -603,7 +603,7 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
 	for (i = 0; i < entries; i++, index++) {
 		dma_info = &shampo->info[index];
 		if (i >= klm_entries || (index < shampo->pi && shampo->pi - index <
-					 MLX5_UMR_KLM_ALIGNMENT))
+					 MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT))
 			goto update_klm;
 		header_offset = (index & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) <<
 			MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE;
@@ -668,8 +668,8 @@ static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq)
 	if (!klm_entries)
 		return 0;
 
-	klm_entries += (shampo->pi & (MLX5_UMR_KLM_ALIGNMENT - 1));
-	index = ALIGN_DOWN(shampo->pi, MLX5_UMR_KLM_ALIGNMENT);
+	klm_entries += (shampo->pi & (MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT - 1));
+	index = ALIGN_DOWN(shampo->pi, MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT);
 	entries_before = shampo->hd_per_wq - index;
 
 	if (unlikely(entries_before < klm_entries))
@@ -727,6 +727,17 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 		};
 	}
 
+	/* Pad if needed, in case the value set to ucseg->xlt_octowords
+	 * in mlx5e_build_umr_wqe() needed alignment.
+	 */
+	if (rq->mpwqe.pages_per_wqe & (MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT - 1)) {
+		int pad = ALIGN(rq->mpwqe.pages_per_wqe, MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT) -
+			rq->mpwqe.pages_per_wqe;
+
+		memset(&umr_wqe->inline_mtts[rq->mpwqe.pages_per_wqe], 0,
+		       sizeof(*umr_wqe->inline_mtts) * pad);
+	}
+
 	bitmap_zero(wi->xdp_xmit_bitmap, rq->mpwqe.pages_per_wqe);
 	wi->consumed_strides = 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 48241317a535..0db41fa4a9a6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -97,8 +97,8 @@ struct mlx5_flow_attr {
 	} lag;
 	/* keep this union last */
 	union {
-		struct mlx5_esw_flow_attr esw_attr[0];
-		struct mlx5_nic_flow_attr nic_attr[0];
+		DECLARE_FLEX_ARRAY(struct mlx5_esw_flow_attr, esw_attr);
+		DECLARE_FLEX_ARRAY(struct mlx5_nic_flow_attr, nic_attr);
 	};
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 3029bc1c0dd0..42d9df417e20 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -744,6 +744,11 @@ static inline int mlx5_eswitch_num_vfs(struct mlx5_eswitch *esw)
 	return 0;
 }
 
+static inline struct mlx5_flow_table *
+mlx5_eswitch_get_slow_fdb(struct mlx5_eswitch *esw)
+{
+	return esw->fdb_table.offloads.slow_fdb;
+}
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 8c6c9bcb3dc3..9b6fbb19c22a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -248,7 +248,7 @@ esw_setup_slow_path_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_ac
 	if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level))
 		flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 	dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest[i].ft = esw->fdb_table.offloads.slow_fdb;
+	dest[i].ft = mlx5_eswitch_get_slow_fdb(esw);
 }
 
 static int
@@ -479,13 +479,15 @@ esw_setup_dests(struct mlx5_flow_destination *dest,
 	    esw_src_port_rewrite_supported(esw))
 		attr->flags |= MLX5_ATTR_FLAG_SRC_REWRITE;
 
-	if (attr->flags & MLX5_ATTR_FLAG_SAMPLE &&
-	    !(attr->flags & MLX5_ATTR_FLAG_SLOW_PATH)) {
-		esw_setup_sampler_dest(dest, flow_act, attr->sample_attr.sampler_id, *i);
-		(*i)++;
-	} else if (attr->flags & MLX5_ATTR_FLAG_SLOW_PATH) {
+	if (attr->flags & MLX5_ATTR_FLAG_SLOW_PATH) {
 		esw_setup_slow_path_dest(dest, flow_act, esw, *i);
 		(*i)++;
+		goto out;
+	}
+
+	if (attr->flags & MLX5_ATTR_FLAG_SAMPLE) {
+		esw_setup_sampler_dest(dest, flow_act, attr->sample_attr.sampler_id, *i);
+		(*i)++;
 	} else if (attr->flags & MLX5_ATTR_FLAG_ACCEPT) {
 		esw_setup_accept_dest(dest, flow_act, chains, *i);
 		(*i)++;
@@ -506,6 +508,7 @@ esw_setup_dests(struct mlx5_flow_destination *dest,
 		}
 	}
 
+out:
 	return err;
 }
 
@@ -1046,7 +1049,7 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw,
 	if (rep->vport == MLX5_VPORT_UPLINK)
 		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT;
 
-	flow_rule = mlx5_add_flow_rules(on_esw->fdb_table.offloads.slow_fdb,
+	flow_rule = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(on_esw),
 					spec, &flow_act, &dest, 1);
 	if (IS_ERR(flow_rule))
 		esw_warn(on_esw->dev, "FDB: Failed to add send to vport rule err %ld\n",
@@ -1095,7 +1098,7 @@ mlx5_eswitch_add_send_to_vport_meta_rule(struct mlx5_eswitch *esw, u16 vport_num
 		 mlx5_eswitch_get_vport_metadata_for_match(esw, vport_num));
 	dest.vport.num = vport_num;
 
-	flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+	flow_rule = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
 					spec, &flow_act, &dest, 1);
 	if (IS_ERR(flow_rule))
 		esw_warn(esw->dev, "FDB: Failed to add send to vport meta rule vport %d, err %ld\n",
@@ -1248,7 +1251,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 		esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch,
 						   spec, MLX5_VPORT_PF);
 
-		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+		flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
 					   spec, &flow_act, &dest, 1);
 		if (IS_ERR(flow)) {
 			err = PTR_ERR(flow);
@@ -1260,7 +1263,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	if (mlx5_ecpf_vport_exists(esw->dev)) {
 		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
 		MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_ECPF);
-		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+		flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
 					   spec, &flow_act, &dest, 1);
 		if (IS_ERR(flow)) {
 			err = PTR_ERR(flow);
@@ -1274,7 +1277,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 						   peer_dev->priv.eswitch,
 						   spec, vport->vport);
 
-		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+		flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
 					   spec, &flow_act, &dest, 1);
 		if (IS_ERR(flow)) {
 			err = PTR_ERR(flow);
@@ -1363,7 +1366,7 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
 	dest.vport.num = esw->manager_vport;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 
-	flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+	flow_rule = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
 					spec, &flow_act, &dest, 1);
 	if (IS_ERR(flow_rule)) {
 		err = PTR_ERR(flow_rule);
@@ -1378,7 +1381,7 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
 	dmac_v = MLX5_ADDR_OF(fte_match_param, headers_v,
 			      outer_headers.dmac_47_16);
 	dmac_v[0] = 0x01;
-	flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+	flow_rule = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw),
 					spec, &flow_act, &dest, 1);
 	if (IS_ERR(flow_rule)) {
 		err = PTR_ERR(flow_rule);
@@ -1927,7 +1930,7 @@ send_vport_err:
 fdb_chains_err:
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.tc_miss_table);
 tc_miss_table_err:
-	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
+	mlx5_destroy_flow_table(mlx5_eswitch_get_slow_fdb(esw));
 slow_fdb_err:
 	/* Holds true only as long as DMFS is the default */
 	mlx5_flow_namespace_set_mode(root_ns, MLX5_FLOW_STEERING_MODE_DMFS);
@@ -1938,7 +1941,7 @@ ns_err:
 
 static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 {
-	if (!esw->fdb_table.offloads.slow_fdb)
+	if (!mlx5_eswitch_get_slow_fdb(esw))
 		return;
 
 	esw_debug(esw->dev, "Destroy offloads FDB Tables\n");
@@ -1954,7 +1957,7 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	esw_chains_destroy(esw, esw_chains(esw));
 
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.tc_miss_table);
-	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
+	mlx5_destroy_flow_table(mlx5_eswitch_get_slow_fdb(esw));
 	/* Holds true only as long as DMFS is the default */
 	mlx5_flow_namespace_set_mode(esw->fdb_table.offloads.ns,
 				     MLX5_FLOW_STEERING_MODE_DMFS);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
index edd910258314..3a9a6bb9158d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
@@ -210,6 +210,18 @@ static bool mlx5_eswitch_offload_is_uplink_port(const struct mlx5_eswitch *esw,
 	return (port_mask & port_value) == MLX5_VPORT_UPLINK;
 }
 
+static bool
+mlx5_eswitch_is_push_vlan_no_cap(struct mlx5_eswitch *esw,
+				 struct mlx5_flow_act *flow_act)
+{
+	if (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH &&
+	    !(mlx5_fs_get_capabilities(esw->dev, MLX5_FLOW_NAMESPACE_FDB) &
+	      MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX))
+		return true;
+
+	return false;
+}
+
 bool
 mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw,
 			      struct mlx5_flow_attr *attr,
@@ -225,10 +237,7 @@ mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw,
 	    (!mlx5_eswitch_offload_is_uplink_port(esw, spec) && !esw_attr->int_port))
 		return false;
 
-	/* push vlan on RX */
-	if (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH &&
-	    !(mlx5_fs_get_capabilities(esw->dev, MLX5_FLOW_NAMESPACE_FDB) &
-	      MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX))
+	if (mlx5_eswitch_is_push_vlan_no_cap(esw, flow_act))
 		return true;
 
 	/* hairpin */
@@ -252,19 +261,31 @@ mlx5_eswitch_add_termtbl_rule(struct mlx5_eswitch *esw,
 	struct mlx5_flow_act term_tbl_act = {};
 	struct mlx5_flow_handle *rule = NULL;
 	bool term_table_created = false;
+	bool is_push_vlan_on_rx;
 	int num_vport_dests = 0;
 	int i, curr_dest;
 
+	is_push_vlan_on_rx = mlx5_eswitch_is_push_vlan_no_cap(esw, flow_act);
 	mlx5_eswitch_termtbl_actions_move(flow_act, &term_tbl_act);
 	term_tbl_act.action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 
 	for (i = 0; i < num_dest; i++) {
 		struct mlx5_termtbl_handle *tt;
+		bool hairpin = false;
 
 		/* only vport destinations can be terminated */
 		if (dest[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT)
 			continue;
 
+		if (attr->dests[num_vport_dests].rep &&
+		    attr->dests[num_vport_dests].rep->vport == MLX5_VPORT_UPLINK)
+			hairpin = true;
+
+		if (!is_push_vlan_on_rx && !hairpin) {
+			num_vport_dests++;
+			continue;
+		}
+
 		if (attr->dests[num_vport_dests].flags & MLX5_ESW_DEST_ENCAP) {
 			term_tbl_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
 			term_tbl_act.pkt_reformat = attr->dests[num_vport_dests].pkt_reformat;
@@ -312,6 +333,9 @@ revert_changes:
 	for (curr_dest = 0; curr_dest < num_vport_dests; curr_dest++) {
 		struct mlx5_termtbl_handle *tt = attr->dests[curr_dest].termtbl;
 
+		if (!tt)
+			continue;
+
 		attr->dests[curr_dest].termtbl = NULL;
 
 		/* search for the destination associated with the
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
index c971ff04dd04..0f9e4f01c85a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
@@ -334,9 +334,6 @@ err_cq:
 
 void mlx5_aso_destroy(struct mlx5_aso *aso)
 {
-	if (IS_ERR_OR_NULL(aso))
-		return;
-
 	mlx5_aso_destroy_sq(aso);
 	mlx5_aso_destroy_cq(&aso->cq);
 	kfree(aso);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 70e8dc305bec..7f5db13e3550 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -37,7 +37,6 @@
 #include <linux/pci.h>
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
-#include <linux/io-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/mlx5/driver.h>
@@ -1604,8 +1603,6 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	int err;
 
 	memcpy(&dev->profile, &profile[profile_idx], sizeof(dev->profile));
-	INIT_LIST_HEAD(&priv->ctx_list);
-	spin_lock_init(&priv->ctx_lock);
 	lockdep_register_key(&dev->lock_key);
 	mutex_init(&dev->intf_state_mutex);
 	lockdep_set_class(&dev->intf_state_mutex, &dev->lock_key);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
index 8455e79bc44a..1513112ecec8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
@@ -31,7 +31,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/io-mapping.h>
 #include <linux/mlx5/driver.h>
 #include "mlx5_core.h"
 
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index eb3fac30488b..5fe5d198b57a 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -290,10 +290,9 @@ enum {
 	MLX5_UMR_INLINE			= (1 << 7),
 };
 
-#define MLX5_UMR_KLM_ALIGNMENT 4
-#define MLX5_UMR_MTT_ALIGNMENT 0x40
-#define MLX5_UMR_MTT_MASK      (MLX5_UMR_MTT_ALIGNMENT - 1)
-#define MLX5_UMR_MTT_MIN_CHUNK_SIZE MLX5_UMR_MTT_ALIGNMENT
+#define MLX5_UMR_FLEX_ALIGNMENT 0x40
+#define MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_mtt))
+#define MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_klm))
 
 #define MLX5_USER_INDEX_LEN (MLX5_FLD_SZ_BYTES(qpc, user_index) * 8)
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 06cbad166225..d476255c9a3f 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -606,8 +606,6 @@ struct mlx5_priv {
 	struct list_head        pgdir_list;
 	/* end: alloc staff */
 
-	struct list_head        ctx_list;
-	spinlock_t              ctx_lock;
 	struct mlx5_adev       **adev;
 	int			adev_idx;
 	int			sw_vhca_id;