[pull request][net-next 00/13] mlx5 updates 2020-07-28

[pull request][net-next 00/13] mlx5 updates 2020-07-28

[Saeed Mahameed]

Hi Dave, Jakub,

This series contains small misc updates to mlx5 driver.

Note that the pci relaxed ordering patch is now much smaller and 
without the driver private knob by following the discussion conclusions 
on the previous patch to only use the pcie_relaxed_ordering_enabled()
kernel helper, and setpci to disable it as a chicken bit.

For more information please see tag log below.

Please pull and let me know if there is any problem.

Thanks,
Saeed.

---
The following changes since commit 5e619d73e6797ed9f2554a1bf996d52d8c91ca50:

  net/mlx4: Use fallthrough pseudo-keyword (2020-07-27 13:14:10 -0700)

are available in the Git repository at:

  git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux.git tags/mlx5-updates-2020-07-28

for you to fetch changes up to 22f9d2f4ee810e6442185ba7ecab37e24de1b413:

  net/mlx5: drop unnecessary list_empty (2020-07-28 02:37:57 -0700)

----------------------------------------------------------------
mlx5-updates-2020-07-28

Misc and small update to mlx5 driver:

1) Aya adds PCIe relaxed ordering support for mlx5 netdev queues.
2) Eran Refactors pages data base to be per vf/function to speedup
   unload time.
3) Parav changes eswitch steering initialization to account for
   tota_vports rather than for only active vports and
   Link non uplink representors to PCI device, for uniform naming scheme.

4) Tariq, trivial RX code improvements and missing inidirect calls
   wrappers.

5) Small cleanup patches

----------------------------------------------------------------
Alex Vesker (1):
      net/mlx5: DR, Reduce print level for matcher print

Avihu Hagag (1):
      net/mlx5: Add function ID to reclaim pages debug log

Aya Levin (1):
      net/mlx5e: Add support for PCI relaxed ordering

Eran Ben Elisha (1):
      net/mlx5: Hold pages RB tree per VF

Gustavo A. R. Silva (1):
      net/mlx5: Use fallthrough pseudo-keyword

Julia Lawall (1):
      net/mlx5: drop unnecessary list_empty

Parav Pandit (4):
      net/mlx5: E-switch, Consider maximum vf vports for steering init
      net/mlx5: E-switch, Reuse total_vports and avoid duplicate nvports
      net/mlx5: E-switch, Use eswitch total_vports
      net/mlx5e: Link non uplink representors to PCI device

Tariq Toukan (3):
      net/mlx5e: RX, Re-work initializaiton of RX function pointers
      net/mlx5e: Move exposure of datapath function to txrx header
      net/mlx5e: Use indirect call wrappers for RX post WQEs functions

 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  55 ++------
 drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h  |  30 ++++-
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c   |   5 +-
 .../net/ethernet/mellanox/mlx5/core/en/xsk/setup.c |   1 +
 .../net/ethernet/mellanox/mlx5/core/en/xsk/tx.c    |   1 -
 .../mellanox/mlx5/core/en_accel/ipsec_rxtx.h       |   1 -
 .../ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c |   2 +-
 .../net/ethernet/mellanox/mlx5/core/en_common.c    |  12 +-
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  55 +-------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   |   9 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.h   |   6 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    | 109 +++++++++++++---
 drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c  |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |   1 -
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c |  35 ++---
 .../net/ethernet/mellanox/mlx5/core/fpga/conn.c    |   4 +-
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c  |   3 +-
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h  |   2 +-
 .../ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c |   3 +-
 drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c   |   8 +-
 .../net/ethernet/mellanox/mlx5/core/pagealloc.c    | 145 +++++++++++++++------
 .../mellanox/mlx5/core/steering/dr_matcher.c       |  15 +--
 .../ethernet/mellanox/mlx5/core/steering/dr_rule.c |   5 +-
 drivers/net/ethernet/mellanox/mlx5/core/vport.c    |   2 +-
 include/linux/mlx5/driver.h                        |   2 +-
 26 files changed, 302 insertions(+), 213 deletions(-)

[net-next 01/13] net/mlx5: Hold pages RB tree per VF

[Saeed Mahameed]

From: Eran Ben Elisha <eranbe@mellanox.com>

Per page request event, FW request to allocated or release pages for a
single function. Driver maintains FW pages object per function, so there
is no need to hold one global page data-base. Instead, have a page
data-base per function, which will improve performance release flow in all
cases, especially for "release all pages".

As the range of function IDs is large and not sequential, use xarray to
store a per function ID page data-base, where the function ID is the key.

Upon first allocation of a page to a function ID, create the page
data-base per function. This data-base will be released only at pagealloc
mechanism cleanup.

NIC: ConnectX-4 Lx
CPU: Intel(R) Xeon(R) CPU E5-2650 v2 @ 2.60GHz
Test case: 32 VFs, measure release pages on one VF as part of FLR
Before: 0.021 Sec
After:  0.014 Sec

The improvement depends on amount of VFs and memory utilization
by them. Time measurements above were taken from idle system.

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/pagealloc.c   | 142 +++++++++++++-----
 include/linux/mlx5/driver.h                   |   2 +-
 2 files changed, 105 insertions(+), 39 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 5ddd18639a1ee..1b20e3397ddef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -35,6 +35,7 @@
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/mlx5/driver.h>
+#include <linux/xarray.h>
 #include "mlx5_core.h"
 #include "lib/eq.h"
 
@@ -73,15 +74,45 @@ enum {
 	MLX5_NUM_4K_IN_PAGE		= PAGE_SIZE / MLX5_ADAPTER_PAGE_SIZE,
 };
 
+static struct rb_root *page_root_per_func_id(struct mlx5_core_dev *dev, u16 func_id)
+{
+	struct rb_root *root;
+	int err;
+
+	root = xa_load(&dev->priv.page_root_xa, func_id);
+	if (root)
+		return root;
+
+	root = kzalloc(sizeof(*root), GFP_KERNEL);
+	if (!root)
+		return ERR_PTR(-ENOMEM);
+
+	err = xa_insert(&dev->priv.page_root_xa, func_id, root, GFP_KERNEL);
+	if (err) {
+		kfree(root);
+		return ERR_PTR(err);
+	}
+
+	*root = RB_ROOT;
+
+	return root;
+}
+
 static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u16 func_id)
 {
-	struct rb_root *root = &dev->priv.page_root;
-	struct rb_node **new = &root->rb_node;
 	struct rb_node *parent = NULL;
+	struct rb_root *root;
+	struct rb_node **new;
 	struct fw_page *nfp;
 	struct fw_page *tfp;
 	int i;
 
+	root = page_root_per_func_id(dev, func_id);
+	if (IS_ERR(root))
+		return PTR_ERR(root);
+
+	new = &root->rb_node;
+
 	while (*new) {
 		parent = *new;
 		tfp = rb_entry(parent, struct fw_page, rb_node);
@@ -111,13 +142,20 @@ static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u
 	return 0;
 }
 
-static struct fw_page *find_fw_page(struct mlx5_core_dev *dev, u64 addr)
+static struct fw_page *find_fw_page(struct mlx5_core_dev *dev, u64 addr,
+				    u32 func_id)
 {
-	struct rb_root *root = &dev->priv.page_root;
-	struct rb_node *tmp = root->rb_node;
 	struct fw_page *result = NULL;
+	struct rb_root *root;
+	struct rb_node *tmp;
 	struct fw_page *tfp;
 
+	root = xa_load(&dev->priv.page_root_xa, func_id);
+	if (WARN_ON_ONCE(!root))
+		return NULL;
+
+	tmp = root->rb_node;
+
 	while (tmp) {
 		tfp = rb_entry(tmp, struct fw_page, rb_node);
 		if (tfp->addr < addr) {
@@ -191,7 +229,13 @@ static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr, u16 func_id)
 static void free_fwp(struct mlx5_core_dev *dev, struct fw_page *fwp,
 		     bool in_free_list)
 {
-	rb_erase(&fwp->rb_node, &dev->priv.page_root);
+	struct rb_root *root;
+
+	root = xa_load(&dev->priv.page_root_xa, fwp->func_id);
+	if (WARN_ON_ONCE(!root))
+		return;
+
+	rb_erase(&fwp->rb_node, root);
 	if (in_free_list)
 		list_del(&fwp->list);
 	dma_unmap_page(dev->device, fwp->addr & MLX5_U64_4K_PAGE_MASK,
@@ -200,12 +244,12 @@ static void free_fwp(struct mlx5_core_dev *dev, struct fw_page *fwp,
 	kfree(fwp);
 }
 
-static void free_4k(struct mlx5_core_dev *dev, u64 addr)
+static void free_4k(struct mlx5_core_dev *dev, u64 addr, u32 func_id)
 {
 	struct fw_page *fwp;
 	int n;
 
-	fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK);
+	fwp = find_fw_page(dev, addr & MLX5_U64_4K_PAGE_MASK, func_id);
 	if (!fwp) {
 		mlx5_core_warn_rl(dev, "page not found\n");
 		return;
@@ -340,7 +384,7 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
 
 out_4k:
 	for (i--; i >= 0; i--)
-		free_4k(dev, MLX5_GET64(manage_pages_in, in, pas[i]));
+		free_4k(dev, MLX5_GET64(manage_pages_in, in, pas[i]), func_id);
 out_free:
 	kvfree(in);
 	if (notify_fail)
@@ -351,16 +395,19 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
 static void release_all_pages(struct mlx5_core_dev *dev, u32 func_id,
 			      bool ec_function)
 {
+	struct rb_root *root;
 	struct rb_node *p;
 	int npages = 0;
 
-	p = rb_first(&dev->priv.page_root);
+	root = xa_load(&dev->priv.page_root_xa, func_id);
+	if (WARN_ON_ONCE(!root))
+		return;
+
+	p = rb_first(root);
 	while (p) {
 		struct fw_page *fwp = rb_entry(p, struct fw_page, rb_node);
 
 		p = rb_next(p);
-		if (fwp->func_id != func_id)
-			continue;
 		npages += (MLX5_NUM_4K_IN_PAGE - fwp->free_count);
 		free_fwp(dev, fwp, fwp->free_count);
 	}
@@ -378,6 +425,7 @@ static void release_all_pages(struct mlx5_core_dev *dev, u32 func_id,
 static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
 			     u32 *in, int in_size, u32 *out, int out_size)
 {
+	struct rb_root *root;
 	struct fw_page *fwp;
 	struct rb_node *p;
 	u32 func_id;
@@ -391,12 +439,14 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
 	npages = MLX5_GET(manage_pages_in, in, input_num_entries);
 	func_id = MLX5_GET(manage_pages_in, in, function_id);
 
-	p = rb_first(&dev->priv.page_root);
+	root = xa_load(&dev->priv.page_root_xa, func_id);
+	if (WARN_ON_ONCE(!root))
+		return -EEXIST;
+
+	p = rb_first(root);
 	while (p && i < npages) {
 		fwp = rb_entry(p, struct fw_page, rb_node);
 		p = rb_next(p);
-		if (fwp->func_id != func_id)
-			continue;
 
 		MLX5_ARRAY_SET64(manage_pages_out, out, pas, i, fwp->addr);
 		i++;
@@ -446,7 +496,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	}
 
 	for (i = 0; i < num_claimed; i++)
-		free_4k(dev, MLX5_GET64(manage_pages_out, out, pas[i]));
+		free_4k(dev, MLX5_GET64(manage_pages_out, out, pas[i]), func_id);
 
 	if (nclaimed)
 		*nclaimed = num_claimed;
@@ -560,35 +610,49 @@ static int optimal_reclaimed_pages(void)
 	return ret;
 }
 
-int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
+static int mlx5_reclaim_root_pages(struct mlx5_core_dev *dev,
+				   struct rb_root *root, u16 func_id)
 {
 	unsigned long end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS);
-	struct fw_page *fwp;
-	struct rb_node *p;
-	int nclaimed = 0;
-	int err = 0;
 
-	do {
-		p = rb_first(&dev->priv.page_root);
-		if (p) {
-			fwp = rb_entry(p, struct fw_page, rb_node);
-			err = reclaim_pages(dev, fwp->func_id,
-					    optimal_reclaimed_pages(),
-					    &nclaimed, mlx5_core_is_ecpf(dev));
-
-			if (err) {
-				mlx5_core_warn(dev, "failed reclaiming pages (%d)\n",
-					       err);
-				return err;
-			}
-			if (nclaimed)
-				end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS);
+	while (!RB_EMPTY_ROOT(root)) {
+		int nclaimed;
+		int err;
+
+		err = reclaim_pages(dev, func_id, optimal_reclaimed_pages(),
+				    &nclaimed, mlx5_core_is_ecpf(dev));
+		if (err) {
+			mlx5_core_warn(dev, "failed reclaiming pages (%d) for func id 0x%x\n",
+				       err, func_id);
+			return err;
 		}
+
+		if (nclaimed)
+			end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS);
+
 		if (time_after(jiffies, end)) {
 			mlx5_core_warn(dev, "FW did not return all pages. giving up...\n");
 			break;
 		}
-	} while (p);
+	}
+
+	return 0;
+}
+
+int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
+{
+	struct rb_root *root;
+	unsigned long id;
+	void *entry;
+
+	xa_for_each(&dev->priv.page_root_xa, id, entry) {
+		root = entry;
+		mlx5_reclaim_root_pages(dev, root, id);
+		xa_erase(&dev->priv.page_root_xa, id);
+		kfree(root);
+	}
+
+	WARN_ON(!xa_empty(&dev->priv.page_root_xa));
 
 	WARN(dev->priv.fw_pages,
 	     "FW pages counter is %d after reclaiming all pages\n",
@@ -605,17 +669,19 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 
 int mlx5_pagealloc_init(struct mlx5_core_dev *dev)
 {
-	dev->priv.page_root = RB_ROOT;
 	INIT_LIST_HEAD(&dev->priv.free_list);
 	dev->priv.pg_wq = create_singlethread_workqueue("mlx5_page_allocator");
 	if (!dev->priv.pg_wq)
 		return -ENOMEM;
 
+	xa_init(&dev->priv.page_root_xa);
+
 	return 0;
 }
 
 void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev)
 {
+	xa_destroy(&dev->priv.page_root_xa);
 	destroy_workqueue(dev->priv.pg_wq);
 }
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 6a97ad601991e..a0fcc4d13e93a 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -541,7 +541,7 @@ struct mlx5_priv {
 	/* pages stuff */
 	struct mlx5_nb          pg_nb;
 	struct workqueue_struct *pg_wq;
-	struct rb_root		page_root;
+	struct xarray           page_root_xa;
 	int			fw_pages;
 	atomic_t		reg_pages;
 	struct list_head	free_list;
-- 
2.26.2

[net-next 02/13] net/mlx5: Add function ID to reclaim pages debug log

[Saeed Mahameed]

From: Avihu Hagag <avihuh@mellanox.com>

Add function ID to reclaim pages debug log for better user visibility.

Signed-off-by: Avihu Hagag <avihuh@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 1b20e3397ddef..a4a23a27c3682 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -480,7 +480,8 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	MLX5_SET(manage_pages_in, in, input_num_entries, npages);
 	MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
 
-	mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen);
+	mlx5_core_dbg(dev, "func 0x%x, npages %d, outlen %d\n",
+		      func_id, npages, outlen);
 	err = reclaim_pages_cmd(dev, in, sizeof(in), out, outlen);
 	if (err) {
 		mlx5_core_err(dev, "failed reclaiming pages: err %d\n", err);
-- 
2.26.2

[net-next 03/13] net/mlx5: E-switch, Consider maximum vf vports for steering init

[Saeed Mahameed]

From: Parav Pandit <parav@mellanox.com>

When eswitch is enabled, VFs might not be enabled. Hence, consider
maximum number of VFs.
This further closes the gap between handling VF vports between ECPF and
PF.

Fixes: ea2128fd632c ("net/mlx5: E-switch, Reduce dependency on num_vfs during mode set")
Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/eswitch_offloads.c    | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index db856d70c4f8f..a21b00d6a37d0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1986,15 +1986,9 @@ static void esw_destroy_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
 
 static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
 {
-	int num_vfs = esw->esw_funcs.num_vfs;
-	int total_vports;
+	int total_vports = esw->total_vports;
 	int err;
 
-	if (mlx5_core_is_ecpf_esw_manager(esw->dev))
-		total_vports = esw->total_vports;
-	else
-		total_vports = num_vfs + MLX5_SPECIAL_VPORTS(esw->dev);
-
 	memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb));
 	mutex_init(&esw->fdb_table.offloads.vports.lock);
 	hash_init(esw->fdb_table.offloads.vports.table);
-- 
2.26.2

[net-next 04/13] net/mlx5: E-switch, Reuse total_vports and avoid duplicate nvports

[Saeed Mahameed]

From: Parav Pandit <parav@mellanox.com>

Total e-switch vports are already stored in mlx5_eswitch total_vports.
Avoid copy of it in nvports and reuse existing total_vports calculation.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h   |  1 -
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c  | 13 ++++++-------
 2 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index b68e02ad65e26..1f52b329e9152 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -271,7 +271,6 @@ struct mlx5_eswitch {
 
 	struct mlx5_esw_offload offloads;
 	int                     mode;
-	int                     nvports;
 	u16                     manager_vport;
 	u16                     first_host_vport;
 	struct mlx5_esw_functions esw_funcs;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index a21b00d6a37d0..6097f9aac938f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1132,7 +1132,7 @@ static void esw_set_flow_group_source_port(struct mlx5_eswitch *esw,
 	}
 }
 
-static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
+static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_flow_table_attr ft_attr = {};
@@ -1165,7 +1165,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 		goto ns_err;
 	}
 
-	table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ +
+	table_size = esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ +
 		MLX5_ESW_MISS_FLOWS + esw->total_vports;
 
 	/* create the slow path fdb with encap set, so further table instances
@@ -1202,7 +1202,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 	MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_sqn);
 	MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_port);
 
-	ix = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ;
+	ix = esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ;
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix - 1);
 
@@ -1270,7 +1270,6 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 	if (err)
 		goto miss_rule_err;
 
-	esw->nvports = nvports;
 	kvfree(flow_group_in);
 	return 0;
 
@@ -2005,7 +2004,7 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
 	if (err)
 		goto create_restore_err;
 
-	err = esw_create_offloads_fdb_tables(esw, total_vports);
+	err = esw_create_offloads_fdb_tables(esw);
 	if (err)
 		goto create_fdb_err;
 
@@ -2459,13 +2458,13 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink,
 
 	esw->offloads.encap = encap;
 
-	err = esw_create_offloads_fdb_tables(esw, esw->nvports);
+	err = esw_create_offloads_fdb_tables(esw);
 
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Failed re-creating fast FDB table");
 		esw->offloads.encap = !encap;
-		(void)esw_create_offloads_fdb_tables(esw, esw->nvports);
+		(void)esw_create_offloads_fdb_tables(esw);
 	}
 
 unlock:
-- 
2.26.2

[net-next 05/13] net/mlx5: E-switch, Use eswitch total_vports

[Saeed Mahameed]

From: Parav Pandit <parav@mellanox.com>

Currently steering table and rx group initialization helper
routines works on the total_vports passed as input parameter.

Both eswitch helpers work on the mlx5_eswitch and thereby have access
to esw->total_vports. Hence use it directly instead of passing it
via function input arguments.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Bodong Wang <bodong@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 6097f9aac938f..54de53daf1c02 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1310,7 +1310,7 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 				     MLX5_FLOW_STEERING_MODE_DMFS);
 }
 
-static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports)
+static int esw_create_offloads_table(struct mlx5_eswitch *esw)
 {
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_core_dev *dev = esw->dev;
@@ -1324,7 +1324,7 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports)
 		return -EOPNOTSUPP;
 	}
 
-	ft_attr.max_fte = nvports + MLX5_ESW_MISS_FLOWS;
+	ft_attr.max_fte = esw->total_vports + MLX5_ESW_MISS_FLOWS;
 	ft_attr.prio = 1;
 
 	ft_offloads = mlx5_create_flow_table(ns, &ft_attr);
@@ -1345,14 +1345,15 @@ static void esw_destroy_offloads_table(struct mlx5_eswitch *esw)
 	mlx5_destroy_flow_table(offloads->ft_offloads);
 }
 
-static int esw_create_vport_rx_group(struct mlx5_eswitch *esw, int nvports)
+static int esw_create_vport_rx_group(struct mlx5_eswitch *esw)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_flow_group *g;
 	u32 *flow_group_in;
+	int nvports;
 	int err = 0;
 
-	nvports = nvports + MLX5_ESW_MISS_FLOWS;
+	nvports = esw->total_vports + MLX5_ESW_MISS_FLOWS;
 	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
 	if (!flow_group_in)
 		return -ENOMEM;
@@ -1985,7 +1986,6 @@ static void esw_destroy_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
 
 static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
 {
-	int total_vports = esw->total_vports;
 	int err;
 
 	memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb));
@@ -1996,7 +1996,7 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
 	if (err)
 		goto create_acl_err;
 
-	err = esw_create_offloads_table(esw, total_vports);
+	err = esw_create_offloads_table(esw);
 	if (err)
 		goto create_offloads_err;
 
@@ -2008,7 +2008,7 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
 	if (err)
 		goto create_fdb_err;
 
-	err = esw_create_vport_rx_group(esw, total_vports);
+	err = esw_create_vport_rx_group(esw);
 	if (err)
 		goto create_fg_err;
 
-- 
2.26.2

[net-next 06/13] net/mlx5e: Link non uplink representors to PCI device

[Saeed Mahameed]

From: Parav Pandit <parav@mellanox.com>

Currently PF and VF representors are exposed as virtual device.
They are not linked to its parent PCI device like how uplink
representor is linked.
Due to this, PF and VF representors cannot benefit of the
systemd defined naming scheme. This requires special handling
by the users.

Hence, link the PF and VF representors to their parent PCI device
similar to existing uplink representor netdevice.

Example:
udevadm output before linking to PCI device:
$ udevadm test-builtin net_id  /sys/class/net/eth6
Load module index
Network interface NamePolicy= disabled on kernel command line, ignoring.
Parsed configuration file /usr/lib/systemd/network/99-default.link
Created link configuration context.
Using default interface naming scheme 'v243'.
ID_NET_NAMING_SCHEME=v243
Unload module index
Unloaded link configuration context.

udevadm output after linking to PCI device:
$ udevadm test-builtin net_id /sys/class/net/eth6
Load module index
Network interface NamePolicy= disabled on kernel command line, ignoring.
Parsed configuration file /usr/lib/systemd/network/99-default.link
Created link configuration context.
Using default interface naming scheme 'v243'.
ID_NET_NAMING_SCHEME=v243
ID_NET_NAME_PATH=enp0s8f0npf0vf0
Unload module index
Unloaded link configuration context.

In past there was little concern over seeing 10,000 lines output
showing up at thread [1] is not applicable as ndo ops for VF
handling is not exposed for all the 100 repesentors for mlx5 devices.

Additionally alternative device naming [2] to overcome shorter device
naming is also part of the latest systemd release v245.

[1] https://marc.info/?l=linux-netdev&m=152657949117904&w=2
[2] https://lwn.net/Articles/814068/

Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index c300729fb498e..a7a74748c9484 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -699,8 +699,8 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct mlx5_core_dev *mdev = priv->mdev;
 
+	SET_NETDEV_DEV(netdev, mdev->device);
 	if (rep->vport == MLX5_VPORT_UPLINK) {
-		SET_NETDEV_DEV(netdev, mdev->device);
 		netdev->netdev_ops = &mlx5e_netdev_ops_uplink_rep;
 		/* we want a persistent mac for the uplink rep */
 		mlx5_query_mac_address(mdev, netdev->dev_addr);
-- 
2.26.2

[net-next 07/13] net/mlx5e: RX, Re-work initializaiton of RX function pointers

[Saeed Mahameed]

From: Tariq Toukan <tariqt@mellanox.com>

Instead of exposing the RQ datapath handlers (from en_rx.c) so that
they are set in the control path (in en_main.c), wrap this logic
in a single function in en_rx.c and expose it alone.

Every profile will now have a pointer to the new mlx5e_rx_handlers
structure, instead of directly pointing to the previously-exposed
RQ handlers.

This significantly improves locality and modularity of the driver,
and allows many functions in en_rx.c to become static.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h  |  31 ++----
 .../mellanox/mlx5/core/en_accel/ipsec_rxtx.h  |   1 -
 .../net/ethernet/mellanox/mlx5/core/en_main.c |  53 +--------
 .../net/ethernet/mellanox/mlx5/core/en_rep.c  |   6 +-
 .../net/ethernet/mellanox/mlx5/core/en_rep.h  |   6 +-
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   | 103 +++++++++++++++---
 .../ethernet/mellanox/mlx5/core/ipoib/ipoib.c |   3 +-
 .../ethernet/mellanox/mlx5/core/ipoib/ipoib.h |   2 +-
 .../mellanox/mlx5/core/ipoib/ipoib_vlan.c     |   3 +-
 9 files changed, 112 insertions(+), 96 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index c44669102626b..878714f949a55 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -530,6 +530,8 @@ typedef struct sk_buff *
 typedef bool (*mlx5e_fp_post_rx_wqes)(struct mlx5e_rq *rq);
 typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq*, u16);
 
+int mlx5e_rq_set_handlers(struct mlx5e_rq *rq, struct mlx5e_params *params, bool xsk);
+
 enum mlx5e_rq_flag {
 	MLX5E_RQ_FLAG_XDP_XMIT,
 	MLX5E_RQ_FLAG_XDP_REDIRECT,
@@ -812,6 +814,13 @@ struct mlx5e_priv {
 	struct mlx5e_scratchpad    scratchpad;
 };
 
+struct mlx5e_rx_handlers {
+	mlx5e_fp_handle_rx_cqe handle_rx_cqe;
+	mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe;
+};
+
+extern const struct mlx5e_rx_handlers mlx5e_rx_handlers_nic;
+
 struct mlx5e_profile {
 	int	(*init)(struct mlx5_core_dev *mdev,
 			struct net_device *netdev,
@@ -828,10 +837,7 @@ struct mlx5e_profile {
 	void	(*update_carrier)(struct mlx5e_priv *priv);
 	unsigned int (*stats_grps_num)(struct mlx5e_priv *priv);
 	mlx5e_stats_grp_t *stats_grps;
-	struct {
-		mlx5e_fp_handle_rx_cqe handle_rx_cqe;
-		mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe;
-	} rx_handlers;
+	const struct mlx5e_rx_handlers *rx_handlers;
 	int	max_tc;
 	u8	rq_groups;
 };
@@ -860,26 +866,9 @@ void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info);
 void mlx5e_page_release_dynamic(struct mlx5e_rq *rq,
 				struct mlx5e_dma_info *dma_info,
 				bool recycle);
-void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
-void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
 int mlx5e_poll_ico_cq(struct mlx5e_cq *cq);
 bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq);
-void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
-void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
-struct sk_buff *
-mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
-				u16 cqe_bcnt, u32 head_offset, u32 page_idx);
-struct sk_buff *
-mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
-				   u16 cqe_bcnt, u32 head_offset, u32 page_idx);
-struct sk_buff *
-mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
-			  struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt);
-struct sk_buff *
-mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
-			     struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt);
-
 void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
 void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
index 2a47673da5a4e..f96e786db158e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
@@ -47,7 +47,6 @@
 
 struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev,
 					  struct sk_buff *skb, u32 *cqe_bcnt);
-void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 
 void mlx5e_ipsec_inverse_table_init(void);
 bool mlx5e_ipsec_feature_check(struct sk_buff *skb, struct net_device *netdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 9d5d8b28bcd81..ac91504be8e8b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -45,7 +45,6 @@
 #include "en_tc.h"
 #include "en_rep.h"
 #include "en_accel/ipsec.h"
-#include "en_accel/ipsec_rxtx.h"
 #include "en_accel/en_accel.h"
 #include "en_accel/tls.h"
 #include "accel/ipsec.h"
@@ -65,7 +64,6 @@
 #include "en/hv_vhca_stats.h"
 #include "en/devlink.h"
 #include "lib/mlx5.h"
-#include "fpga/ipsec.h"
 
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 {
@@ -428,29 +426,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		pool_size = MLX5_MPWRQ_PAGES_PER_WQE <<
 			mlx5e_mpwqe_get_log_rq_size(params, xsk);
 
-		rq->post_wqes = mlx5e_post_rx_mpwqes;
-		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
-
-		rq->handle_rx_cqe = c->priv->profile->rx_handlers.handle_rx_cqe_mpwqe;
-#ifdef CONFIG_MLX5_EN_IPSEC
-		if (MLX5_IPSEC_DEV(mdev)) {
-			err = -EINVAL;
-			netdev_err(c->netdev, "MPWQE RQ with IPSec offload not supported\n");
-			goto err_rq_wq_destroy;
-		}
-#endif
-		if (!rq->handle_rx_cqe) {
-			err = -EINVAL;
-			netdev_err(c->netdev, "RX handler of MPWQE RQ is not set, err %d\n", err);
-			goto err_rq_wq_destroy;
-		}
-
-		rq->mpwqe.skb_from_cqe_mpwrq = xsk ?
-			mlx5e_xsk_skb_from_cqe_mpwrq_linear :
-			mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL) ?
-				mlx5e_skb_from_cqe_mpwrq_linear :
-				mlx5e_skb_from_cqe_mpwrq_nonlinear;
-
 		rq->mpwqe.log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk);
 		rq->mpwqe.num_strides =
 			BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk));
@@ -492,30 +467,13 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		if (err)
 			goto err_free;
 
-		rq->post_wqes = mlx5e_post_rx_wqes;
-		rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
-
-#ifdef CONFIG_MLX5_EN_IPSEC
-		if ((mlx5_fpga_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_DEVICE) &&
-		    c->priv->ipsec)
-			rq->handle_rx_cqe = mlx5e_ipsec_handle_rx_cqe;
-		else
-#endif
-			rq->handle_rx_cqe = c->priv->profile->rx_handlers.handle_rx_cqe;
-		if (!rq->handle_rx_cqe) {
-			err = -EINVAL;
-			netdev_err(c->netdev, "RX handler of RQ is not set, err %d\n", err);
-			goto err_free;
-		}
-
-		rq->wqe.skb_from_cqe = xsk ?
-			mlx5e_xsk_skb_from_cqe_linear :
-			mlx5e_rx_is_linear_skb(params, NULL) ?
-				mlx5e_skb_from_cqe_linear :
-				mlx5e_skb_from_cqe_nonlinear;
 		rq->mkey_be = c->mkey_be;
 	}
 
+	err = mlx5e_rq_set_handlers(rq, params, xsk);
+	if (err)
+		goto err_free;
+
 	if (xsk) {
 		err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
 						 MEM_TYPE_XSK_BUFF_POOL, NULL);
@@ -5288,8 +5246,7 @@ static const struct mlx5e_profile mlx5e_nic_profile = {
 	.update_rx	   = mlx5e_update_nic_rx,
 	.update_stats	   = mlx5e_update_ndo_stats,
 	.update_carrier	   = mlx5e_update_carrier,
-	.rx_handlers.handle_rx_cqe       = mlx5e_handle_rx_cqe,
-	.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
+	.rx_handlers       = &mlx5e_rx_handlers_nic,
 	.max_tc		   = MLX5E_MAX_NUM_TC,
 	.rq_groups	   = MLX5E_NUM_RQ_GROUPS(XSK),
 	.stats_grps	   = mlx5e_nic_stats_grps,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index a7a74748c9484..ea6b99b8bcd83 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1143,8 +1143,7 @@ static const struct mlx5e_profile mlx5e_rep_profile = {
 	.enable		        = mlx5e_rep_enable,
 	.update_rx		= mlx5e_update_rep_rx,
 	.update_stats           = mlx5e_update_ndo_stats,
-	.rx_handlers.handle_rx_cqe       = mlx5e_handle_rx_cqe_rep,
-	.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq_rep,
+	.rx_handlers            = &mlx5e_rx_handlers_rep,
 	.max_tc			= 1,
 	.rq_groups		= MLX5E_NUM_RQ_GROUPS(REGULAR),
 	.stats_grps		= mlx5e_rep_stats_grps,
@@ -1163,8 +1162,7 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
 	.update_rx		= mlx5e_update_rep_rx,
 	.update_stats           = mlx5e_update_ndo_stats,
 	.update_carrier	        = mlx5e_update_carrier,
-	.rx_handlers.handle_rx_cqe       = mlx5e_handle_rx_cqe_rep,
-	.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq_rep,
+	.rx_handlers            = &mlx5e_rx_handlers_rep,
 	.max_tc			= MLX5E_MAX_NUM_TC,
 	.rq_groups		= MLX5E_NUM_RQ_GROUPS(REGULAR),
 	.stats_grps		= mlx5e_ul_rep_stats_grps,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 1d56698014843..622c27ae4ac7d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -41,6 +41,8 @@
 #include "lib/port_tun.h"
 
 #ifdef CONFIG_MLX5_ESWITCH
+extern const struct mlx5e_rx_handlers mlx5e_rx_handlers_rep;
+
 struct mlx5e_neigh_update_table {
 	struct rhashtable       neigh_ht;
 	/* Save the neigh hash entries in a list in addition to the hash table
@@ -223,10 +225,6 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv);
 int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv);
 void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv);
 
-void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
-void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq,
-				   struct mlx5_cqe64 *cqe);
-
 void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv);
 
 bool mlx5e_eswitch_vf_rep(struct net_device *netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 74860f3827b1a..9c0ef6e5da881 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -44,12 +44,29 @@
 #include "en_rep.h"
 #include "en/rep/tc.h"
 #include "ipoib/ipoib.h"
+#include "accel/ipsec.h"
+#include "fpga/ipsec.h"
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/tls_rxtx.h"
 #include "lib/clock.h"
 #include "en/xdp.h"
 #include "en/xsk/rx.h"
 #include "en/health.h"
+#include "en/params.h"
+
+static struct sk_buff *
+mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+				u16 cqe_bcnt, u32 head_offset, u32 page_idx);
+static struct sk_buff *
+mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+				   u16 cqe_bcnt, u32 head_offset, u32 page_idx);
+static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
+static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
+
+const struct mlx5e_rx_handlers mlx5e_rx_handlers_nic = {
+	.handle_rx_cqe       = mlx5e_handle_rx_cqe,
+	.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
+};
 
 static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
 {
@@ -370,7 +387,7 @@ static inline void mlx5e_free_rx_wqe(struct mlx5e_rq *rq,
 		mlx5e_put_rx_frag(rq, wi, recycle);
 }
 
-void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
+static void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
 {
 	struct mlx5e_wqe_frag_info *wi = get_frag(rq, ix);
 
@@ -537,7 +554,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	return err;
 }
 
-void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
+static void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 {
 	struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
 	/* Don't recycle, this function is called on rq/netdev close */
@@ -1106,7 +1123,7 @@ static void mlx5e_fill_xdp_buff(struct mlx5e_rq *rq, void *va, u16 headroom,
 	xdp->frame_sz = rq->buff.frame0_sz;
 }
 
-struct sk_buff *
+static struct sk_buff *
 mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 			  struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt)
 {
@@ -1146,7 +1163,7 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	return skb;
 }
 
-struct sk_buff *
+static struct sk_buff *
 mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 			     struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt)
 {
@@ -1201,7 +1218,7 @@ static void trigger_report(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	}
 }
 
-void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 {
 	struct mlx5_wq_cyc *wq = &rq->wqe.wq;
 	struct mlx5e_wqe_frag_info *wi;
@@ -1244,7 +1261,7 @@ void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 }
 
 #ifdef CONFIG_MLX5_ESWITCH
-void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+static void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 {
 	struct net_device *netdev = rq->netdev;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -1299,8 +1316,7 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	mlx5_wq_cyc_pop(wq);
 }
 
-void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq,
-				   struct mlx5_cqe64 *cqe)
+static void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 {
 	u16 cstrides       = mpwrq_get_cqe_consumed_strides(cqe);
 	u16 wqe_id         = be16_to_cpu(cqe->wqe_id);
@@ -1358,9 +1374,14 @@ void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq,
 	mlx5e_free_rx_mpwqe(rq, wi, true);
 	mlx5_wq_ll_pop(wq, cqe->wqe_id, &wqe->next.next_wqe_index);
 }
+
+const struct mlx5e_rx_handlers mlx5e_rx_handlers_rep = {
+	.handle_rx_cqe       = mlx5e_handle_rx_cqe_rep,
+	.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq_rep,
+};
 #endif
 
-struct sk_buff *
+static struct sk_buff *
 mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 				   u16 cqe_bcnt, u32 head_offset, u32 page_idx)
 {
@@ -1406,7 +1427,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	return skb;
 }
 
-struct sk_buff *
+static struct sk_buff *
 mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 				u16 cqe_bcnt, u32 head_offset, u32 page_idx)
 {
@@ -1456,7 +1477,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 	return skb;
 }
 
-void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 {
 	u16 cstrides       = mpwrq_get_cqe_consumed_strides(cqe);
 	u16 wqe_id         = be16_to_cpu(cqe->wqe_id);
@@ -1652,7 +1673,7 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 	stats->bytes += cqe_bcnt;
 }
 
-void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+static void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 {
 	struct mlx5_wq_cyc *wq = &rq->wqe.wq;
 	struct mlx5e_wqe_frag_info *wi;
@@ -1688,11 +1709,15 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	mlx5_wq_cyc_pop(wq);
 }
 
+const struct mlx5e_rx_handlers mlx5i_rx_handlers = {
+	.handle_rx_cqe       = mlx5i_handle_rx_cqe,
+	.handle_rx_cqe_mpwqe = NULL, /* Not supported */
+};
 #endif /* CONFIG_MLX5_CORE_IPOIB */
 
 #ifdef CONFIG_MLX5_EN_IPSEC
 
-void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+static void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 {
 	struct mlx5_wq_cyc *wq = &rq->wqe.wq;
 	struct mlx5e_wqe_frag_info *wi;
@@ -1729,3 +1754,55 @@ void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 }
 
 #endif /* CONFIG_MLX5_EN_IPSEC */
+
+int mlx5e_rq_set_handlers(struct mlx5e_rq *rq, struct mlx5e_params *params, bool xsk)
+{
+	struct mlx5_core_dev *mdev = rq->mdev;
+	struct mlx5e_channel *c = rq->channel;
+
+	switch (rq->wq_type) {
+	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		rq->mpwqe.skb_from_cqe_mpwrq = xsk ?
+			mlx5e_xsk_skb_from_cqe_mpwrq_linear :
+			mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL) ?
+				mlx5e_skb_from_cqe_mpwrq_linear :
+				mlx5e_skb_from_cqe_mpwrq_nonlinear;
+		rq->post_wqes = mlx5e_post_rx_mpwqes;
+		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
+
+		rq->handle_rx_cqe = c->priv->profile->rx_handlers->handle_rx_cqe_mpwqe;
+#ifdef CONFIG_MLX5_EN_IPSEC
+		if (MLX5_IPSEC_DEV(mdev)) {
+			netdev_err(c->netdev, "MPWQE RQ with IPSec offload not supported\n");
+			return -EINVAL;
+		}
+#endif
+		if (!rq->handle_rx_cqe) {
+			netdev_err(c->netdev, "RX handler of MPWQE RQ is not set\n");
+			return -EINVAL;
+		}
+		break;
+	default: /* MLX5_WQ_TYPE_CYCLIC */
+		rq->wqe.skb_from_cqe = xsk ?
+			mlx5e_xsk_skb_from_cqe_linear :
+			mlx5e_rx_is_linear_skb(params, NULL) ?
+				mlx5e_skb_from_cqe_linear :
+				mlx5e_skb_from_cqe_nonlinear;
+		rq->post_wqes = mlx5e_post_rx_wqes;
+		rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
+
+#ifdef CONFIG_MLX5_EN_IPSEC
+		if ((mlx5_fpga_ipsec_device_caps(mdev) & MLX5_ACCEL_IPSEC_CAP_DEVICE) &&
+		    c->priv->ipsec)
+			rq->handle_rx_cqe = mlx5e_ipsec_handle_rx_cqe;
+		else
+#endif
+			rq->handle_rx_cqe = c->priv->profile->rx_handlers->handle_rx_cqe;
+		if (!rq->handle_rx_cqe) {
+			netdev_err(c->netdev, "RX handler of RQ is not set\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 690b822c61524..5763965d5ef33 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -464,8 +464,7 @@ static const struct mlx5e_profile mlx5i_nic_profile = {
 	.update_rx	   = mlx5i_update_nic_rx,
 	.update_stats	   = NULL, /* mlx5i_update_stats */
 	.update_carrier    = NULL, /* no HW update in IB link */
-	.rx_handlers.handle_rx_cqe       = mlx5i_handle_rx_cqe,
-	.rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */
+	.rx_handlers       = &mlx5i_rx_handlers,
 	.max_tc		   = MLX5I_MAX_NUM_TC,
 	.rq_groups	   = MLX5E_NUM_RQ_GROUPS(REGULAR),
 	.stats_grps        = mlx5i_stats_grps,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
index 79071a15c4ca7..b79dc1e28c418 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
@@ -42,6 +42,7 @@
 
 extern const struct ethtool_ops mlx5i_ethtool_ops;
 extern const struct ethtool_ops mlx5i_pkey_ethtool_ops;
+extern const struct mlx5e_rx_handlers mlx5i_rx_handlers;
 
 #define MLX5_IB_GRH_BYTES       40
 #define MLX5_IPOIB_ENCAP_LEN    4
@@ -117,7 +118,6 @@ struct mlx5i_tx_wqe {
 
 void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		   struct mlx5_av *av, u32 dqpn, u32 dqkey, bool xmit_more);
-void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 void mlx5i_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
 
 #endif /* CONFIG_MLX5_CORE_IPOIB */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
index f70367018862f..7163d9f6c4a6f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
@@ -349,8 +349,7 @@ static const struct mlx5e_profile mlx5i_pkey_nic_profile = {
 	.disable	   = NULL,
 	.update_rx	   = mlx5i_update_nic_rx,
 	.update_stats	   = NULL,
-	.rx_handlers.handle_rx_cqe       = mlx5i_handle_rx_cqe,
-	.rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */
+	.rx_handlers       = &mlx5i_rx_handlers,
 	.max_tc		   = MLX5I_MAX_NUM_TC,
 	.rq_groups	   = MLX5E_NUM_RQ_GROUPS(REGULAR),
 };
-- 
2.26.2

[net-next 08/13] net/mlx5e: Move exposure of datapath function to txrx header

[Saeed Mahameed]

From: Tariq Toukan <tariqt@mellanox.com>

Move them from the generic header file "en.h", to the
datapath header file "txrx.h".

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h  | 23 ----------------
 .../net/ethernet/mellanox/mlx5/core/en/txrx.h | 27 +++++++++++++++++++
 .../mellanox/mlx5/core/en/xsk/setup.c         |  1 +
 .../net/ethernet/mellanox/mlx5/core/en_rep.c  |  1 +
 4 files changed, 29 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 878714f949a55..0fb30fe93207b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -844,31 +844,10 @@ struct mlx5e_profile {
 
 void mlx5e_build_ptys2ethtool_map(void);
 
-u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       struct net_device *sb_dev);
-netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
-void mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
-		   struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more);
-
-void mlx5e_trigger_irq(struct mlx5e_icosq *sq);
-void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe);
-void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
-int mlx5e_napi_poll(struct napi_struct *napi, int budget);
-bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
-int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
-void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq);
-
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev);
 bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev,
 				struct mlx5e_params *params);
 
-void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info);
-void mlx5e_page_release_dynamic(struct mlx5e_rq *rq,
-				struct mlx5e_dma_info *dma_info,
-				bool recycle);
-bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
-int mlx5e_poll_ico_cq(struct mlx5e_cq *cq);
-bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq);
 void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
 void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s);
 
@@ -971,8 +950,6 @@ void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state);
 void mlx5e_activate_rq(struct mlx5e_rq *rq);
 void mlx5e_deactivate_rq(struct mlx5e_rq *rq);
-void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
-void mlx5e_free_rx_in_progress_descs(struct mlx5e_rq *rq);
 void mlx5e_activate_icosq(struct mlx5e_icosq *icosq);
 void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index cf425a60cddcf..b25e4ec752281 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -18,6 +18,33 @@ enum mlx5e_icosq_wqe_type {
 #endif
 };
 
+/* General */
+void mlx5e_trigger_irq(struct mlx5e_icosq *sq);
+void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe);
+void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
+int mlx5e_napi_poll(struct napi_struct *napi, int budget);
+int mlx5e_poll_ico_cq(struct mlx5e_cq *cq);
+
+/* RX */
+void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info);
+void mlx5e_page_release_dynamic(struct mlx5e_rq *rq,
+				struct mlx5e_dma_info *dma_info,
+				bool recycle);
+bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
+bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq);
+int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
+void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
+void mlx5e_free_rx_in_progress_descs(struct mlx5e_rq *rq);
+
+/* TX */
+u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
+		       struct net_device *sb_dev);
+netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
+void mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
+		   struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more);
+bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
+void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq);
+
 static inline bool
 mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n)
 {
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 cc46414773b50..dd9df519d383b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -3,6 +3,7 @@
 
 #include "setup.h"
 #include "en/params.h"
+#include "en/txrx.h"
 
 /* It matches XDP_UMEM_MIN_CHUNK_SIZE, but as this constant is private and may
  * change unexpectedly, and mlx5e has a minimum valid stride size for striding
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index ea6b99b8bcd83..111477086f66e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -42,6 +42,7 @@
 #include "esw/chains.h"
 #include "en.h"
 #include "en_rep.h"
+#include "en/txrx.h"
 #include "en_tc.h"
 #include "en/rep/tc.h"
 #include "en/rep/neigh.h"
-- 
2.26.2

[net-next 09/13] net/mlx5e: Use indirect call wrappers for RX post WQEs functions

[Saeed Mahameed]

From: Tariq Toukan <tariqt@mellanox.com>

Use the indirect call wrapper API macros for declaration and scope
of the RX post WQEs functions.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h   | 5 +++--
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c    | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c     | 6 +++---
 drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c   | 2 +-
 5 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index b25e4ec752281..f7fd2ed322792 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -5,6 +5,7 @@
 #define __MLX5_EN_TXRX_H___
 
 #include "en.h"
+#include <linux/indirect_call_wrapper.h>
 
 #define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start))
 
@@ -30,8 +31,8 @@ void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info);
 void mlx5e_page_release_dynamic(struct mlx5e_rq *rq,
 				struct mlx5e_dma_info *dma_info,
 				bool recycle);
-bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
-bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq);
+INDIRECT_CALLABLE_DECLARE(bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq));
+INDIRECT_CALLABLE_DECLARE(bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq));
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
 void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
 void mlx5e_free_rx_in_progress_descs(struct mlx5e_rq *rq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index e0c1b010d41ab..90db221e31df3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -34,7 +34,6 @@
 #include <net/xdp_sock_drv.h>
 #include "en/xdp.h"
 #include "en/params.h"
-#include <linux/indirect_call_wrapper.h>
 
 int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
index 0dfbc96e952ab..4d892f6cecb3e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -6,7 +6,6 @@
 #include "en/xdp.h"
 #include "en/params.h"
 #include <net/xdp_sock_drv.h>
-#include <linux/indirect_call_wrapper.h>
 
 int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 9c0ef6e5da881..65828af120b7a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -34,11 +34,11 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/tcp.h>
-#include <linux/indirect_call_wrapper.h>
 #include <net/ip6_checksum.h>
 #include <net/page_pool.h>
 #include <net/inet_ecn.h>
 #include "en.h"
+#include "en/txrx.h"
 #include "en_tc.h"
 #include "eswitch.h"
 #include "en_rep.h"
@@ -561,7 +561,7 @@ static void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	mlx5e_free_rx_mpwqe(rq, wi, false);
 }
 
-bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
+INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
 {
 	struct mlx5_wq_cyc *wq = &rq->wqe.wq;
 	u8 wqe_bulk;
@@ -702,7 +702,7 @@ int mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
 	return i;
 }
 
-bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
+INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 {
 	struct mlx5e_icosq *sq = &rq->channel->icosq;
 	struct mlx5_wq_ll *wq = &rq->mpwqe.wq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index e3dbab2a294cf..de10b06bade53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -31,8 +31,8 @@
  */
 
 #include <linux/irq.h>
-#include <linux/indirect_call_wrapper.h>
 #include "en.h"
+#include "en/txrx.h"
 #include "en/xdp.h"
 #include "en/xsk/rx.h"
 #include "en/xsk/tx.h"
-- 
2.26.2

[net-next 10/13] net/mlx5e: Add support for PCI relaxed ordering

[Saeed Mahameed]

From: Aya Levin <ayal@mellanox.com>

The concept of Relaxed Ordering in the PCI Express environment allows
switches in the path between the Requester and Completer to reorder some
transactions just received before others that were previously enqueued.

In ETH driver, there is no question of write integrity since each memory
segment is written only once per cycle. In addition, the driver doesn't
access the memory shared with the hardware until the corresponding CQE
arrives indicating all PCI transactions are done.

Running TCP single stream over ConnectX-4 LX, ARM CPU on remote-numa has
300% improvement in the bandwidth.

With relaxed ordering turned off: BW:10 [GB/s]
With relaxed ordering turned on: BW:40 [GB/s]

The driver turns relaxed ordering with respect to the firmware
capabilities and the return value from pcie_relaxed_ordering_enabled().

Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h        |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 12 +++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c   |  2 +-
 3 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 0fb30fe93207b..f2fa1307e90cb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -974,6 +974,7 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev);
 void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
 int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb,
 		       bool enable_mc_lb);
+void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc);
 
 /* common netdev helpers */
 void mlx5e_create_q_counters(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 1e42c7ae621b9..a6cf008057b5f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -60,6 +60,16 @@ void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
 	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 }
 
+void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc)
+{
+	bool ro_pci_enable = pcie_relaxed_ordering_enabled(mdev->pdev);
+	bool ro_write = MLX5_CAP_GEN(mdev, relaxed_ordering_write);
+	bool ro_read = MLX5_CAP_GEN(mdev, relaxed_ordering_read);
+
+	MLX5_SET(mkc, mkc, relaxed_ordering_read, ro_pci_enable && ro_read);
+	MLX5_SET(mkc, mkc, relaxed_ordering_write, ro_pci_enable && ro_write);
+}
+
 static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
 			     struct mlx5_core_mkey *mkey)
 {
@@ -76,7 +86,7 @@ static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
 	MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_PA);
 	MLX5_SET(mkc, mkc, lw, 1);
 	MLX5_SET(mkc, mkc, lr, 1);
-
+	mlx5e_mkey_set_relaxed_ordering(mdev, mkc);
 	MLX5_SET(mkc, mkc, pd, pdn);
 	MLX5_SET(mkc, mkc, length64, 1);
 	MLX5_SET(mkc, mkc, qpn, 0xffffff);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index ac91504be8e8b..f374348fa8100 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -274,7 +274,7 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
 	MLX5_SET(mkc, mkc, lw, 1);
 	MLX5_SET(mkc, mkc, lr, 1);
 	MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_MTT);
-
+	mlx5e_mkey_set_relaxed_ordering(mdev, mkc);
 	MLX5_SET(mkc, mkc, qpn, 0xffffff);
 	MLX5_SET(mkc, mkc, pd, mdev->mlx5e_res.pdn);
 	MLX5_SET64(mkc, mkc, len, npages << page_shift);
-- 
2.26.2

[net-next 11/13] net/mlx5: DR, Reduce print level for matcher print

[Saeed Mahameed]

From: Alex Vesker <valex@mellanox.com>

There is no need to print on each unsuccessful matcher
ip_version combination since it probably will happen when
trying to create all the possible combinations.
On a real failure we have a print in the calling function.

Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
index 31abcbb95ca29..6960aedd33cb8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
@@ -395,7 +395,7 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
 	/* Check that all mask fields were consumed */
 	for (i = 0; i < sizeof(struct mlx5dr_match_param); i++) {
 		if (((u8 *)&mask)[i] != 0) {
-			mlx5dr_err(dmn, "Mask contains unsupported parameters\n");
+			mlx5dr_dbg(dmn, "Mask contains unsupported parameters\n");
 			return -EOPNOTSUPP;
 		}
 	}
-- 
2.26.2

[net-next 12/13] net/mlx5: Use fallthrough pseudo-keyword

[Saeed Mahameed]

From: "Gustavo A. R. Silva" <gustavoars@kernel.org>

Replace the existing /* fall through */ comments and its variants with
the new pseudo-keyword macro fallthrough[1]. Also, remove unnecessary
fall-through markings when it is the case.

[1] https://www.kernel.org/doc/html/v5.7/process/deprecated.html?highlight=fallthrough#implicit-switch-case-fall-through

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h         | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c          | 4 ++--
 .../net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c    | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c      | 2 +-
 .../net/ethernet/mellanox/mlx5/core/eswitch_offloads.c    | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c       | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c          | 8 ++++----
 drivers/net/ethernet/mellanox/mlx5/core/vport.c           | 2 +-
 8 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index f7fd2ed322792..9334c9c3e208b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -388,7 +388,7 @@ mlx5e_set_eseg_swp(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg,
 	switch (swp_spec->tun_l4_proto) {
 	case IPPROTO_UDP:
 		eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP;
-		/* fall through */
+		fallthrough;
 	case IPPROTO_TCP:
 		eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2;
 		break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 90db221e31df3..0e6946fc121f0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -152,11 +152,11 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		return true;
 	default:
 		bpf_warn_invalid_xdp_action(act);
-		/* fall through */
+		fallthrough;
 	case XDP_ABORTED:
 xdp_abort:
 		trace_xdp_exception(rq->netdev, prog, act);
-		/* fall through */
+		fallthrough;
 	case XDP_DROP:
 		rq->stats->xdp_drop++;
 		return true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 0e6698d1b4ca9..f4861545b236b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -470,7 +470,7 @@ bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *s
 			if (likely(!skb->decrypted))
 				goto out;
 			WARN_ON_ONCE(1);
-			/* fall-through */
+			fallthrough;
 		case MLX5E_KTLS_SYNC_FAIL:
 			goto err_out;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index af849bc83c306..08270987c5066 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -243,7 +243,7 @@ int mlx5e_ethtool_get_sset_count(struct mlx5e_priv *priv, int sset)
 		return MLX5E_NUM_PFLAGS;
 	case ETH_SS_TEST:
 		return mlx5e_self_test_num(priv);
-	/* fallthrough */
+		fallthrough;
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 54de53daf1c02..be610d40749a6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2346,7 +2346,7 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
 	case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
 		if (mode == DEVLINK_ESWITCH_INLINE_MODE_NONE)
 			goto out;
-		/* fall through */
+		fallthrough;
 	case MLX5_CAP_INLINE_MODE_L2:
 		NL_SET_ERR_MSG_MOD(extack, "Inline mode can't be set");
 		err = -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index 182d3ac3e73f2..831d2c39e1534 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -339,14 +339,14 @@ static void mlx5_fpga_conn_handle_cqe(struct mlx5_fpga_conn *conn,
 	switch (opcode) {
 	case MLX5_CQE_REQ_ERR:
 		status = ((struct mlx5_err_cqe *)cqe)->syndrome;
-		/* Fall through */
+		fallthrough;
 	case MLX5_CQE_REQ:
 		mlx5_fpga_conn_sq_cqe(conn, cqe, status);
 		break;
 
 	case MLX5_CQE_RESP_ERR:
 		status = ((struct mlx5_err_cqe *)cqe)->syndrome;
-		/* Fall through */
+		fallthrough;
 	case MLX5_CQE_RESP_SEND:
 		mlx5_fpga_conn_rq_cqe(conn, cqe, status);
 		break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
index e9089a793632b..9e68f5926ab6e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
@@ -198,13 +198,13 @@ static void mlx5_lag_fib_update(struct work_struct *work)
 	/* Protect internal structures from changes */
 	rtnl_lock();
 	switch (fib_work->event) {
-	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+	case FIB_EVENT_ENTRY_REPLACE:
 	case FIB_EVENT_ENTRY_DEL:
 		mlx5_lag_fib_route_event(ldev, fib_work->event,
 					 fib_work->fen_info.fi);
 		fib_info_put(fib_work->fen_info.fi);
 		break;
-	case FIB_EVENT_NH_ADD: /* fall through */
+	case FIB_EVENT_NH_ADD:
 	case FIB_EVENT_NH_DEL:
 		fib_nh = fib_work->fnh_info.fib_nh;
 		mlx5_lag_fib_nexthop_event(ldev,
@@ -255,7 +255,7 @@ static int mlx5_lag_fib_event(struct notifier_block *nb,
 		return NOTIFY_DONE;
 
 	switch (event) {
-	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+	case FIB_EVENT_ENTRY_REPLACE:
 	case FIB_EVENT_ENTRY_DEL:
 		fen_info = container_of(info, struct fib_entry_notifier_info,
 					info);
@@ -278,7 +278,7 @@ static int mlx5_lag_fib_event(struct notifier_block *nb,
 		 */
 		fib_info_hold(fib_work->fen_info.fi);
 		break;
-	case FIB_EVENT_NH_ADD: /* fall through */
+	case FIB_EVENT_NH_ADD:
 	case FIB_EVENT_NH_DEL:
 		fnh_info = container_of(info, struct fib_nh_notifier_info,
 					info);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 88cdb9bb4c4a4..bdafc85fd874d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -110,7 +110,7 @@ void mlx5_query_min_inline(struct mlx5_core_dev *mdev,
 	case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
 		if (!mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode))
 			break;
-		/* fall through */
+		fallthrough;
 	case MLX5_CAP_INLINE_MODE_L2:
 		*min_inline_mode = MLX5_INLINE_MODE_L2;
 		break;
-- 
2.26.2

[net-next 13/13] net/mlx5: drop unnecessary list_empty

[Saeed Mahameed]

From: Julia Lawall <Julia.Lawall@inria.fr>

list_for_each_entry is able to handle an empty list.
The only effect of avoiding the loop is not initializing the
index variable.
Drop list_empty tests in cases where these variables are not
used.

Note that list_for_each_entry is defined in terms of list_first_entry,
which indicates that it should not be used on an empty list.  But in
list_for_each_entry, the element obtained by list_first_entry is not
really accessed, only the address of its list_head field is compared
to the address of the list head, so the list_first_entry is safe.

The semantic patch that makes this change is as follows (with another
variant for the no brace case): (http://coccinelle.lip6.fr/)

<smpl>
@@
expression x,e;
iterator name list_for_each_entry;
statement S;
identifier i;
@@

-if (!(list_empty(x))) {
   list_for_each_entry(i,x,...) S
- }
 ... when != i
? i = e
</smpl>

Signed-off-by: Julia Lawall <Julia.Lawall@inria.fr>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../mellanox/mlx5/core/steering/dr_matcher.c        | 13 ++++++-------
 .../ethernet/mellanox/mlx5/core/steering/dr_rule.c  |  5 ++---
 2 files changed, 8 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
index 6960aedd33cb8..c63f727273d8f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
@@ -474,14 +474,13 @@ static int dr_matcher_add_to_tbl(struct mlx5dr_matcher *matcher)
 	int ret;
 
 	next_matcher = NULL;
-	if (!list_empty(&tbl->matcher_list))
-		list_for_each_entry(tmp_matcher, &tbl->matcher_list, matcher_list) {
-			if (tmp_matcher->prio >= matcher->prio) {
-				next_matcher = tmp_matcher;
-				break;
-			}
-			first = false;
+	list_for_each_entry(tmp_matcher, &tbl->matcher_list, matcher_list) {
+		if (tmp_matcher->prio >= matcher->prio) {
+			next_matcher = tmp_matcher;
+			break;
 		}
+		first = false;
+	}
 
 	prev_matcher = NULL;
 	if (next_matcher && !first)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
index cd708dcc2e3a3..6ec5106bc4724 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -574,9 +574,8 @@ void mlx5dr_rule_update_rule_member(struct mlx5dr_ste *ste,
 {
 	struct mlx5dr_rule_member *rule_mem;
 
-	if (!list_empty(&ste->rule_list))
-		list_for_each_entry(rule_mem, &ste->rule_list, use_ste_list)
-			rule_mem->ste = new_ste;
+	list_for_each_entry(rule_mem, &ste->rule_list, use_ste_list)
+		rule_mem->ste = new_ste;
 }
 
 static void dr_rule_clean_rule_members(struct mlx5dr_rule *rule,
-- 
2.26.2

Re: [pull request][net-next 00/13] mlx5 updates 2020-07-28

[David Miller]

From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 28 Jul 2020 02:43:58 -0700

> This series contains small misc updates to mlx5 driver.
> 
> Note that the pci relaxed ordering patch is now much smaller and 
> without the driver private knob by following the discussion conclusions 
> on the previous patch to only use the pcie_relaxed_ordering_enabled()
> kernel helper, and setpci to disable it as a chicken bit.
> 
> For more information please see tag log below.
> 
> Please pull and let me know if there is any problem.

Pulled, thank you.

Re: [net-next 06/13] net/mlx5e: Link non uplink representors to PCI device

[Jakub Kicinski]

On Tue, 28 Jul 2020 02:44:04 -0700 Saeed Mahameed wrote:
> In past there was little concern over seeing 10,000 lines output
> showing up at thread [1] is not applicable as ndo ops for VF
> handling is not exposed for all the 100 repesentors for mlx5 devices.

wasn't libvirt picking the netdev to run the vf ops on basically at
random, though?

Re: [pull request][net-next 00/13] mlx5 updates 2020-07-28

[Jakub Kicinski]

On Tue, 28 Jul 2020 02:43:58 -0700 Saeed Mahameed wrote:
> Hi Dave, Jakub,
> 
> This series contains small misc updates to mlx5 driver.
> 
> Note that the pci relaxed ordering patch is now much smaller and 
> without the driver private knob by following the discussion conclusions 
> on the previous patch to only use the pcie_relaxed_ordering_enabled()
> kernel helper, and setpci to disable it as a chicken bit.
> 
> For more information please see tag log below.
> 
> Please pull and let me know if there is any problem.

Reviewed-by: Jakub Kicinski <kuba@kernel.org>