From f34343cc11afc7bb1f881c3492bee3484016bf71 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Tue, 6 May 2025 08:59:39 -0700
Subject: [PATCH 01/16] fbnic: Fix initialization of mailbox descriptor rings

Address to issues with the FW mailbox descriptor initialization.

We need to reverse the order of accesses when we invalidate an entry versus
writing an entry. When writing an entry we write upper and then lower as
the lower 32b contain the valid bit that makes the entire address valid.
However for invalidation we should write it in the reverse order so that
the upper is marked invalid before we update it.

Without this change we may see FW attempt to access pages with the upper
32b of the address set to 0 which will likely result in DMAR faults due to
write access failures on mailbox shutdown.

Fixes: da3cde08209e ("eth: fbnic: Add FW communication mechanism")
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/174654717972.499179.8083789731819297034.stgit@ahduyck-xeon-server.home.arpa
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/meta/fbnic/fbnic_fw.c | 32 ++++++++++++++++------
 1 file changed, 23 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index 88db3dacb940..c4956f0a741e 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -17,11 +17,29 @@ static void __fbnic_mbx_wr_desc(struct fbnic_dev *fbd, int mbx_idx,
 {
 	u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
 
+	/* Write the upper 32b and then the lower 32b. Doing this the
+	 * FW can then read lower, upper, lower to verify that the state
+	 * of the descriptor wasn't changed mid-transaction.
+	 */
 	fw_wr32(fbd, desc_offset + 1, upper_32_bits(desc));
 	fw_wrfl(fbd);
 	fw_wr32(fbd, desc_offset, lower_32_bits(desc));
 }
 
+static void __fbnic_mbx_invalidate_desc(struct fbnic_dev *fbd, int mbx_idx,
+					int desc_idx, u32 desc)
+{
+	u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
+
+	/* For initialization we write the lower 32b of the descriptor first.
+	 * This way we can set the state to mark it invalid before we clear the
+	 * upper 32b.
+	 */
+	fw_wr32(fbd, desc_offset, desc);
+	fw_wrfl(fbd);
+	fw_wr32(fbd, desc_offset + 1, 0);
+}
+
 static u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx)
 {
 	u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
@@ -41,21 +59,17 @@ static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 	 * solid stop for the firmware to hit when it is done looping
 	 * through the ring.
 	 */
-	__fbnic_mbx_wr_desc(fbd, mbx_idx, 0, 0);
-
-	fw_wrfl(fbd);
+	__fbnic_mbx_invalidate_desc(fbd, mbx_idx, 0, 0);
 
 	/* We then fill the rest of the ring starting at the end and moving
 	 * back toward descriptor 0 with skip descriptors that have no
 	 * length nor address, and tell the firmware that they can skip
 	 * them and just move past them to the one we initialized to 0.
 	 */
-	for (desc_idx = FBNIC_IPC_MBX_DESC_LEN; --desc_idx;) {
-		__fbnic_mbx_wr_desc(fbd, mbx_idx, desc_idx,
-				    FBNIC_IPC_MBX_DESC_FW_CMPL |
-				    FBNIC_IPC_MBX_DESC_HOST_CMPL);
-		fw_wrfl(fbd);
-	}
+	for (desc_idx = FBNIC_IPC_MBX_DESC_LEN; --desc_idx;)
+		__fbnic_mbx_invalidate_desc(fbd, mbx_idx, desc_idx,
+					    FBNIC_IPC_MBX_DESC_FW_CMPL |
+					    FBNIC_IPC_MBX_DESC_HOST_CMPL);
 }
 
 void fbnic_mbx_init(struct fbnic_dev *fbd)
-- 
2.51.0


From 3b12f00ddd08e888273b2ac0488d396d90a836fc Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Tue, 6 May 2025 08:59:46 -0700
Subject: [PATCH 02/16] fbnic: Gate AXI read/write enabling on FW mailbox

In order to prevent the device from throwing spurious writes and/or reads
at us we need to gate the AXI fabric interface to the PCIe until such time
as we know the FW is in a known good state.

To accomplish this we use the mailbox as a mechanism for us to recognize
that the FW has acknowledged our presence and is no longer sending any
stale message data to us.

We start in fbnic_mbx_init by calling fbnic_mbx_reset_desc_ring function,
disabling the DMA in both directions, and then invalidating all the
descriptors in each ring.

We then poll the mailbox in fbnic_mbx_poll_tx_ready and when the interrupt
is set by the FW we pick it up and mark the mailboxes as ready, while also
enabling the DMA.

Once we have completed all the transactions and need to shut down we call
into fbnic_mbx_clean which will in turn call fbnic_mbx_reset_desc_ring for
each ring and shut down the DMA and once again invalidate the descriptors.

Fixes: 3646153161f1 ("eth: fbnic: Add register init to set PCIe/Ethernet device config")
Fixes: da3cde08209e ("eth: fbnic: Add FW communication mechanism")
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/174654718623.499179.7445197308109347982.stgit@ahduyck-xeon-server.home.arpa
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/meta/fbnic/fbnic_csr.h |  2 ++
 drivers/net/ethernet/meta/fbnic/fbnic_fw.c  | 38 +++++++++++++++++----
 drivers/net/ethernet/meta/fbnic/fbnic_mac.c |  6 ----
 3 files changed, 33 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
index 3b12a0ab5906..51bee8072420 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
@@ -796,8 +796,10 @@ enum {
 /* PUL User Registers */
 #define FBNIC_CSR_START_PUL_USER	0x31000	/* CSR section delimiter */
 #define FBNIC_PUL_OB_TLP_HDR_AW_CFG	0x3103d		/* 0xc40f4 */
+#define FBNIC_PUL_OB_TLP_HDR_AW_CFG_FLUSH	CSR_BIT(19)
 #define FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME		CSR_BIT(18)
 #define FBNIC_PUL_OB_TLP_HDR_AR_CFG	0x3103e		/* 0xc40f8 */
+#define FBNIC_PUL_OB_TLP_HDR_AR_CFG_FLUSH	CSR_BIT(19)
 #define FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME		CSR_BIT(18)
 #define FBNIC_PUL_USER_OB_RD_TLP_CNT_31_0 \
 					0x3106e		/* 0xc41b8 */
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index c4956f0a741e..f4749bfd840c 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -51,10 +51,26 @@ static u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx)
 	return desc;
 }
 
-static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
+static void fbnic_mbx_reset_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	int desc_idx;
 
+	/* Disable DMA transactions from the device,
+	 * and flush any transactions triggered during cleaning
+	 */
+	switch (mbx_idx) {
+	case FBNIC_IPC_MBX_RX_IDX:
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AW_CFG_FLUSH);
+		break;
+	case FBNIC_IPC_MBX_TX_IDX:
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AR_CFG_FLUSH);
+		break;
+	}
+
+	wrfl(fbd);
+
 	/* Initialize first descriptor to all 0s. Doing this gives us a
 	 * solid stop for the firmware to hit when it is done looping
 	 * through the ring.
@@ -90,7 +106,7 @@ void fbnic_mbx_init(struct fbnic_dev *fbd)
 	wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
 
 	for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
-		fbnic_mbx_init_desc_ring(fbd, i);
+		fbnic_mbx_reset_desc_ring(fbd, i);
 }
 
 static int fbnic_mbx_map_msg(struct fbnic_dev *fbd, int mbx_idx,
@@ -155,7 +171,7 @@ static void fbnic_mbx_clean_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	int i;
 
-	fbnic_mbx_init_desc_ring(fbd, mbx_idx);
+	fbnic_mbx_reset_desc_ring(fbd, mbx_idx);
 
 	for (i = FBNIC_IPC_MBX_DESC_LEN; i--;)
 		fbnic_mbx_unmap_and_free_msg(fbd, mbx_idx, i);
@@ -354,7 +370,7 @@ static int fbnic_fw_xmit_cap_msg(struct fbnic_dev *fbd)
 	return (err == -EOPNOTSUPP) ? 0 : err;
 }
 
-static void fbnic_mbx_postinit_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
+static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	struct fbnic_fw_mbx *mbx = &fbd->mbx[mbx_idx];
 
@@ -366,10 +382,18 @@ static void fbnic_mbx_postinit_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 
 	switch (mbx_idx) {
 	case FBNIC_IPC_MBX_RX_IDX:
+		/* Enable DMA writes from the device */
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME);
+
 		/* Make sure we have a page for the FW to write to */
 		fbnic_mbx_alloc_rx_msgs(fbd);
 		break;
 	case FBNIC_IPC_MBX_TX_IDX:
+		/* Enable DMA reads from the device */
+		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
+		     FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME);
+
 		/* Force version to 1 if we successfully requested an update
 		 * from the firmware. This should be overwritten once we get
 		 * the actual version from the firmware in the capabilities
@@ -386,7 +410,7 @@ static void fbnic_mbx_postinit(struct fbnic_dev *fbd)
 {
 	int i;
 
-	/* We only need to do this on the first interrupt following init.
+	/* We only need to do this on the first interrupt following reset.
 	 * this primes the mailbox so that we will have cleared all the
 	 * skip descriptors.
 	 */
@@ -396,7 +420,7 @@ static void fbnic_mbx_postinit(struct fbnic_dev *fbd)
 	wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
 
 	for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
-		fbnic_mbx_postinit_desc_ring(fbd, i);
+		fbnic_mbx_init_desc_ring(fbd, i);
 }
 
 /**
@@ -894,7 +918,7 @@ int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd)
 		 * avoid the mailbox getting stuck closed if the interrupt
 		 * is reset.
 		 */
-		fbnic_mbx_init_desc_ring(fbd, FBNIC_IPC_MBX_TX_IDX);
+		fbnic_mbx_reset_desc_ring(fbd, FBNIC_IPC_MBX_TX_IDX);
 
 		msleep(200);
 
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
index 14291401f463..dde4a37116e2 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
@@ -79,12 +79,6 @@ static void fbnic_mac_init_axi(struct fbnic_dev *fbd)
 	fbnic_init_readrq(fbd, FBNIC_QM_RNI_RBP_CTL, cls, readrq);
 	fbnic_init_mps(fbd, FBNIC_QM_RNI_RDE_CTL, cls, mps);
 	fbnic_init_mps(fbd, FBNIC_QM_RNI_RCM_CTL, cls, mps);
-
-	/* Enable XALI AR/AW outbound */
-	wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
-	     FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME);
-	wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
-	     FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME);
 }
 
 static void fbnic_mac_init_qm(struct fbnic_dev *fbd)
-- 
2.51.0


From 682a61281d1036962b68d651994cc407371daef5 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Tue, 6 May 2025 08:59:52 -0700
Subject: [PATCH 03/16] fbnic: Add additional handling of IRQs

We have two issues that need to be addressed in our IRQ handling.

One is the fact that we can end up double-freeing IRQs in the event of an
exception handling error such as a PCIe reset/recovery that fails. To
prevent that from becoming an issue we can use the msix_vector values to
indicate that we have successfully requested/freed the IRQ by only setting
or clearing them when we have completed the given action.

The other issue is that we have several potential races in our IRQ path due
to us manipulating the mask before the vector has been truly disabled. In
order to handle that in the case of the FW mailbox we need to not
auto-enable the IRQ and instead will be enabling/disabling it separately.
In the case of the PCS vector we can mitigate this by unmapping it and
synchronizing the IRQ before we clear the mask.

The general order of operations after this change is now to request the
interrupt, poll the FW mailbox to ready, and then enable the interrupt. For
the shutdown we do the reverse where we disable the interrupt, flush any
pending Tx, and then free the IRQ. I am renaming the enable/disable to
request/free to be equivilent with the IRQ calls being used. We may see
additions in the future to enable/disable the IRQs versus request/free them
for certain use cases.

Fixes: da3cde08209e ("eth: fbnic: Add FW communication mechanism")
Fixes: 69684376eed5 ("eth: fbnic: Add link detection")
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/174654719271.499179.3634535105127848325.stgit@ahduyck-xeon-server.home.arpa
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/meta/fbnic/fbnic.h       |   8 +-
 drivers/net/ethernet/meta/fbnic/fbnic_irq.c   | 142 ++++++++++++------
 .../net/ethernet/meta/fbnic/fbnic_netdev.c    |   5 +-
 drivers/net/ethernet/meta/fbnic/fbnic_pci.c   |  14 +-
 4 files changed, 110 insertions(+), 59 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h
index 4ca7b99ef131..de6b1a340f55 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic.h
@@ -154,14 +154,14 @@ struct fbnic_dev *fbnic_devlink_alloc(struct pci_dev *pdev);
 void fbnic_devlink_register(struct fbnic_dev *fbd);
 void fbnic_devlink_unregister(struct fbnic_dev *fbd);
 
-int fbnic_fw_enable_mbx(struct fbnic_dev *fbd);
-void fbnic_fw_disable_mbx(struct fbnic_dev *fbd);
+int fbnic_fw_request_mbx(struct fbnic_dev *fbd);
+void fbnic_fw_free_mbx(struct fbnic_dev *fbd);
 
 void fbnic_hwmon_register(struct fbnic_dev *fbd);
 void fbnic_hwmon_unregister(struct fbnic_dev *fbd);
 
-int fbnic_pcs_irq_enable(struct fbnic_dev *fbd);
-void fbnic_pcs_irq_disable(struct fbnic_dev *fbd);
+int fbnic_pcs_request_irq(struct fbnic_dev *fbd);
+void fbnic_pcs_free_irq(struct fbnic_dev *fbd);
 
 void fbnic_napi_name_irqs(struct fbnic_dev *fbd);
 int fbnic_napi_request_irq(struct fbnic_dev *fbd,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c
index 1bbc0e56f3a0..1c88a2bf3a7a 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c
@@ -19,69 +19,105 @@ static irqreturn_t fbnic_fw_msix_intr(int __always_unused irq, void *data)
 	return IRQ_HANDLED;
 }
 
+static int __fbnic_fw_enable_mbx(struct fbnic_dev *fbd, int vector)
+{
+	int err;
+
+	/* Initialize mailbox and attempt to poll it into ready state */
+	fbnic_mbx_init(fbd);
+	err = fbnic_mbx_poll_tx_ready(fbd);
+	if (err) {
+		dev_warn(fbd->dev, "FW mailbox did not enter ready state\n");
+		return err;
+	}
+
+	/* Enable interrupt and unmask the vector */
+	enable_irq(vector);
+	fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
+
+	return 0;
+}
+
 /**
- * fbnic_fw_enable_mbx - Configure and initialize Firmware Mailbox
+ * fbnic_fw_request_mbx - Configure and initialize Firmware Mailbox
  * @fbd: Pointer to device to initialize
  *
- * This function will initialize the firmware mailbox rings, enable the IRQ
- * and initialize the communication between the Firmware and the host. The
- * firmware is expected to respond to the initialization by sending an
- * interrupt essentially notifying the host that it has seen the
- * initialization and is now synced up.
+ * This function will allocate the IRQ and then reinitialize the mailbox
+ * starting communication between the host and firmware.
  *
  * Return: non-zero on failure.
  **/
-int fbnic_fw_enable_mbx(struct fbnic_dev *fbd)
+int fbnic_fw_request_mbx(struct fbnic_dev *fbd)
 {
-	u32 vector = fbd->fw_msix_vector;
-	int err;
+	struct pci_dev *pdev = to_pci_dev(fbd->dev);
+	int vector, err;
+
+	WARN_ON(fbd->fw_msix_vector);
+
+	vector = pci_irq_vector(pdev, FBNIC_FW_MSIX_ENTRY);
+	if (vector < 0)
+		return vector;
 
 	/* Request the IRQ for FW Mailbox vector. */
 	err = request_threaded_irq(vector, NULL, &fbnic_fw_msix_intr,
-				   IRQF_ONESHOT, dev_name(fbd->dev), fbd);
+				   IRQF_ONESHOT | IRQF_NO_AUTOEN,
+				   dev_name(fbd->dev), fbd);
 	if (err)
 		return err;
 
 	/* Initialize mailbox and attempt to poll it into ready state */
-	fbnic_mbx_init(fbd);
-	err = fbnic_mbx_poll_tx_ready(fbd);
-	if (err) {
-		dev_warn(fbd->dev, "FW mailbox did not enter ready state\n");
+	err = __fbnic_fw_enable_mbx(fbd, vector);
+	if (err)
 		free_irq(vector, fbd);
-		return err;
-	}
 
-	/* Enable interrupts */
-	fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
+	fbd->fw_msix_vector = vector;
 
-	return 0;
+	return err;
 }
 
 /**
- * fbnic_fw_disable_mbx - Disable mailbox and place it in standby state
- * @fbd: Pointer to device to disable
+ * fbnic_fw_disable_mbx - Temporarily place mailbox in standby state
+ * @fbd: Pointer to device
  *
- * This function will disable the mailbox interrupt, free any messages still
- * in the mailbox and place it into a standby state. The firmware is
- * expected to see the update and assume that the host is in the reset state.
+ * Shutdown the mailbox by notifying the firmware to stop sending us logs, mask
+ * and synchronize the IRQ, and then clean up the rings.
  **/
-void fbnic_fw_disable_mbx(struct fbnic_dev *fbd)
+static void fbnic_fw_disable_mbx(struct fbnic_dev *fbd)
 {
-	/* Disable interrupt and free vector */
-	fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_FW_MSIX_ENTRY);
+	/* Disable interrupt and synchronize the IRQ */
+	disable_irq(fbd->fw_msix_vector);
 
-	/* Free the vector */
-	free_irq(fbd->fw_msix_vector, fbd);
+	/* Mask the vector */
+	fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_FW_MSIX_ENTRY);
 
 	/* Make sure disabling logs message is sent, must be done here to
 	 * avoid risk of completing without a running interrupt.
 	 */
 	fbnic_mbx_flush_tx(fbd);
-
-	/* Reset the mailboxes to the initialized state */
 	fbnic_mbx_clean(fbd);
 }
 
+/**
+ * fbnic_fw_free_mbx - Disable mailbox and place it in standby state
+ * @fbd: Pointer to device to disable
+ *
+ * This function will disable the mailbox interrupt, free any messages still
+ * in the mailbox and place it into a disabled state. The firmware is
+ * expected to see the update and assume that the host is in the reset state.
+ **/
+void fbnic_fw_free_mbx(struct fbnic_dev *fbd)
+{
+	/* Vector has already been freed */
+	if (!fbd->fw_msix_vector)
+		return;
+
+	fbnic_fw_disable_mbx(fbd);
+
+	/* Free the vector */
+	free_irq(fbd->fw_msix_vector, fbd);
+	fbd->fw_msix_vector = 0;
+}
+
 static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data)
 {
 	struct fbnic_dev *fbd = data;
@@ -101,7 +137,7 @@ static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data)
 }
 
 /**
- * fbnic_pcs_irq_enable - Configure the MAC to enable it to advertise link
+ * fbnic_pcs_request_irq - Configure the PCS to enable it to advertise link
  * @fbd: Pointer to device to initialize
  *
  * This function provides basic bringup for the MAC/PCS IRQ. For now the IRQ
@@ -109,41 +145,61 @@ static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data)
  *
  * Return: non-zero on failure.
  **/
-int fbnic_pcs_irq_enable(struct fbnic_dev *fbd)
+int fbnic_pcs_request_irq(struct fbnic_dev *fbd)
 {
-	u32 vector = fbd->pcs_msix_vector;
-	int err;
+	struct pci_dev *pdev = to_pci_dev(fbd->dev);
+	int vector, err;
 
-	/* Request the IRQ for MAC link vector.
-	 * Map MAC cause to it, and unmask it
+	WARN_ON(fbd->pcs_msix_vector);
+
+	vector = pci_irq_vector(pdev, FBNIC_PCS_MSIX_ENTRY);
+	if (vector < 0)
+		return vector;
+
+	/* Request the IRQ for PCS link vector.
+	 * Map PCS cause to it, and unmask it
 	 */
 	err = request_irq(vector, &fbnic_pcs_msix_intr, 0,
 			  fbd->netdev->name, fbd);
 	if (err)
 		return err;
 
+	/* Map and enable interrupt, unmask vector after link is configured */
 	fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_PCS_IDX),
 		   FBNIC_PCS_MSIX_ENTRY | FBNIC_INTR_MSIX_CTRL_ENABLE);
 
+	fbd->pcs_msix_vector = vector;
+
 	return 0;
 }
 
 /**
- * fbnic_pcs_irq_disable - Teardown the MAC IRQ to prepare for stopping
+ * fbnic_pcs_free_irq - Teardown the PCS IRQ to prepare for stopping
  * @fbd: Pointer to device that is stopping
  *
- * This function undoes the work done in fbnic_pcs_irq_enable and prepares
+ * This function undoes the work done in fbnic_pcs_request_irq and prepares
  * the device to no longer receive traffic on the host interface.
  **/
-void fbnic_pcs_irq_disable(struct fbnic_dev *fbd)
+void fbnic_pcs_free_irq(struct fbnic_dev *fbd)
 {
+	/* Vector has already been freed */
+	if (!fbd->pcs_msix_vector)
+		return;
+
 	/* Disable interrupt */
 	fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_PCS_IDX),
 		   FBNIC_PCS_MSIX_ENTRY);
+	fbnic_wrfl(fbd);
+
+	/* Synchronize IRQ to prevent race that would unmask vector */
+	synchronize_irq(fbd->pcs_msix_vector);
+
+	/* Mask the vector */
 	fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_PCS_MSIX_ENTRY);
 
 	/* Free the vector */
 	free_irq(fbd->pcs_msix_vector, fbd);
+	fbd->pcs_msix_vector = 0;
 }
 
 void fbnic_synchronize_irq(struct fbnic_dev *fbd, int nr)
@@ -226,9 +282,6 @@ void fbnic_free_irqs(struct fbnic_dev *fbd)
 {
 	struct pci_dev *pdev = to_pci_dev(fbd->dev);
 
-	fbd->pcs_msix_vector = 0;
-	fbd->fw_msix_vector = 0;
-
 	fbd->num_irqs = 0;
 
 	pci_free_irq_vectors(pdev);
@@ -254,8 +307,5 @@ int fbnic_alloc_irqs(struct fbnic_dev *fbd)
 
 	fbd->num_irqs = num_irqs;
 
-	fbd->pcs_msix_vector = pci_irq_vector(pdev, FBNIC_PCS_MSIX_ENTRY);
-	fbd->fw_msix_vector = pci_irq_vector(pdev, FBNIC_FW_MSIX_ENTRY);
-
 	return 0;
 }
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index 79a01fdd1dd1..2524d9b88d59 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -44,9 +44,10 @@ int __fbnic_open(struct fbnic_net *fbn)
 	if (err)
 		goto time_stop;
 
-	err = fbnic_pcs_irq_enable(fbd);
+	err = fbnic_pcs_request_irq(fbd);
 	if (err)
 		goto time_stop;
+
 	/* Pull the BMC config and initialize the RPC */
 	fbnic_bmc_rpc_init(fbd);
 	fbnic_rss_reinit(fbd, fbn);
@@ -82,7 +83,7 @@ static int fbnic_stop(struct net_device *netdev)
 	struct fbnic_net *fbn = netdev_priv(netdev);
 
 	fbnic_down(fbn);
-	fbnic_pcs_irq_disable(fbn->fbd);
+	fbnic_pcs_free_irq(fbn->fbd);
 
 	fbnic_time_stop(fbn);
 	fbnic_fw_xmit_ownership_msg(fbn->fbd, false);
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
index 6cbbc2ee3e1f..4e8595239c0f 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
@@ -283,7 +283,7 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto free_irqs;
 	}
 
-	err = fbnic_fw_enable_mbx(fbd);
+	err = fbnic_fw_request_mbx(fbd);
 	if (err) {
 		dev_err(&pdev->dev,
 			"Firmware mailbox initialization failure\n");
@@ -363,7 +363,7 @@ static void fbnic_remove(struct pci_dev *pdev)
 	fbnic_hwmon_unregister(fbd);
 	fbnic_dbg_fbd_exit(fbd);
 	fbnic_devlink_unregister(fbd);
-	fbnic_fw_disable_mbx(fbd);
+	fbnic_fw_free_mbx(fbd);
 	fbnic_free_irqs(fbd);
 
 	fbnic_devlink_free(fbd);
@@ -387,7 +387,7 @@ static int fbnic_pm_suspend(struct device *dev)
 	rtnl_unlock();
 
 null_uc_addr:
-	fbnic_fw_disable_mbx(fbd);
+	fbnic_fw_free_mbx(fbd);
 
 	/* Free the IRQs so they aren't trying to occupy sleeping CPUs */
 	fbnic_free_irqs(fbd);
@@ -420,7 +420,7 @@ static int __fbnic_pm_resume(struct device *dev)
 	fbd->mac->init_regs(fbd);
 
 	/* Re-enable mailbox */
-	err = fbnic_fw_enable_mbx(fbd);
+	err = fbnic_fw_request_mbx(fbd);
 	if (err)
 		goto err_free_irqs;
 
@@ -438,15 +438,15 @@ static int __fbnic_pm_resume(struct device *dev)
 	if (netif_running(netdev)) {
 		err = __fbnic_open(fbn);
 		if (err)
-			goto err_disable_mbx;
+			goto err_free_mbx;
 	}
 
 	rtnl_unlock();
 
 	return 0;
-err_disable_mbx:
+err_free_mbx:
 	rtnl_unlock();
-	fbnic_fw_disable_mbx(fbd);
+	fbnic_fw_free_mbx(fbd);
 err_free_irqs:
 	fbnic_free_irqs(fbd);
 err_invalidate_uc_addr:
-- 
2.51.0


From 0f9a959a0addd9bbc47e5d16c36b3a7f97981915 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Tue, 6 May 2025 08:59:59 -0700
Subject: [PATCH 04/16] fbnic: Actually flush_tx instead of stalling out

The fbnic_mbx_flush_tx function had a number of issues.

First, we were waiting 200ms for the firmware to process the packets. We
can drop this to 20ms and in almost all cases this should be more than
enough time. So by changing this we can significantly reduce shutdown time.

Second, we were not making sure that the Tx path was actually shut off. As
such we could still have packets added while we were flushing the mailbox.
To prevent that we can now clear the ready flag for the Tx side and it
should stay down since the interrupt is disabled.

Third, we kept re-reading the tail due to the second issue. The tail should
not move after we have started the flush so we can just read it once while
we are holding the mailbox Tx lock. By doing that we are guaranteed that
the value should be consistent.

Fourth, we were keeping a count of descriptors cleaned due to the second
and third issues called out. That count is not a valid reason to be exiting
the cleanup, and with the tail only being read once we shouldn't see any
cases where the tail moves after the disable so the tracking of count can
be dropped.

Fifth, we were using attempts * sleep time to determine how long we would
wait in our polling loop to flush out the Tx. This can be very imprecise.
In order to tighten up the timing we are shifting over to using a jiffies
value of jiffies + 10 * HZ + 1 to determine the jiffies value we should
stop polling at as this should be accurate within once sleep cycle for the
total amount of time spent polling.

Fixes: da3cde08209e ("eth: fbnic: Add FW communication mechanism")
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/174654719929.499179.16406653096197423749.stgit@ahduyck-xeon-server.home.arpa
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/meta/fbnic/fbnic_fw.c | 31 +++++++++++-----------
 1 file changed, 16 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index f4749bfd840c..d019191d6ae9 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -930,35 +930,36 @@ int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd)
 
 void fbnic_mbx_flush_tx(struct fbnic_dev *fbd)
 {
+	unsigned long timeout = jiffies + 10 * HZ + 1;
 	struct fbnic_fw_mbx *tx_mbx;
-	int attempts = 50;
-	u8 count = 0;
-
-	/* Nothing to do if there is no mailbox */
-	if (!fbnic_fw_present(fbd))
-		return;
+	u8 tail;
 
 	/* Record current Rx stats */
 	tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
 
-	/* Nothing to do if mailbox never got to ready */
-	if (!tx_mbx->ready)
-		return;
+	spin_lock_irq(&fbd->fw_tx_lock);
+
+	/* Clear ready to prevent any further attempts to transmit */
+	tx_mbx->ready = false;
+
+	/* Read tail to determine the last tail state for the ring */
+	tail = tx_mbx->tail;
+
+	spin_unlock_irq(&fbd->fw_tx_lock);
 
 	/* Give firmware time to process packet,
-	 * we will wait up to 10 seconds which is 50 waits of 200ms.
+	 * we will wait up to 10 seconds which is 500 waits of 20ms.
 	 */
 	do {
 		u8 head = tx_mbx->head;
 
-		if (head == tx_mbx->tail)
+		/* Tx ring is empty once head == tail */
+		if (head == tail)
 			break;
 
-		msleep(200);
+		msleep(20);
 		fbnic_mbx_process_tx_msgs(fbd);
-
-		count += (tx_mbx->head - head) % FBNIC_IPC_MBX_DESC_LEN;
-	} while (count < FBNIC_IPC_MBX_DESC_LEN && --attempts);
+	} while (time_is_after_jiffies(timeout));
 }
 
 void fbnic_get_fw_ver_commit_str(struct fbnic_dev *fbd, char *fw_version,
-- 
2.51.0


From cdbb2dc3996a60ed3d7431c1239a8ca98c778e04 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Tue, 6 May 2025 09:00:05 -0700
Subject: [PATCH 05/16] fbnic: Cleanup handling of completions

There was an issue in that if we were to shutdown we could be left with
a completion in flight as the mailbox went away. To address that I have
added an fbnic_mbx_evict_all_cmpl function that is meant to essentially
create a "broken pipe" type response so that all callers will receive an
error indicating that the connection has been broken as a result of us
shutting down the mailbox.

Fixes: 378e5cc1c6c6 ("eth: fbnic: hwmon: Add completion infrastructure for firmware requests")
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/174654720578.499179.380252598204530873.stgit@ahduyck-xeon-server.home.arpa
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/meta/fbnic/fbnic_fw.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index d019191d6ae9..732875aae46c 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -928,6 +928,20 @@ int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd)
 	return attempts ? 0 : -ETIMEDOUT;
 }
 
+static void __fbnic_fw_evict_cmpl(struct fbnic_fw_completion *cmpl_data)
+{
+	cmpl_data->result = -EPIPE;
+	complete(&cmpl_data->done);
+}
+
+static void fbnic_mbx_evict_all_cmpl(struct fbnic_dev *fbd)
+{
+	if (fbd->cmpl_data) {
+		__fbnic_fw_evict_cmpl(fbd->cmpl_data);
+		fbd->cmpl_data = NULL;
+	}
+}
+
 void fbnic_mbx_flush_tx(struct fbnic_dev *fbd)
 {
 	unsigned long timeout = jiffies + 10 * HZ + 1;
@@ -945,6 +959,9 @@ void fbnic_mbx_flush_tx(struct fbnic_dev *fbd)
 	/* Read tail to determine the last tail state for the ring */
 	tail = tx_mbx->tail;
 
+	/* Flush any completions as we are no longer processing Rx */
+	fbnic_mbx_evict_all_cmpl(fbd);
+
 	spin_unlock_irq(&fbd->fw_tx_lock);
 
 	/* Give firmware time to process packet,
-- 
2.51.0


From ab064f6005973d456f95ae99cd9ea0d8ab676cce Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Tue, 6 May 2025 09:00:12 -0700
Subject: [PATCH 06/16] fbnic: Improve responsiveness of
 fbnic_mbx_poll_tx_ready

There were a couple different issues found in fbnic_mbx_poll_tx_ready.
Among them were the fact that we were sleeping much longer than we actually
needed to as the actual FW could respond in under 20ms. The other issue was
that we would just keep polling the mailbox even if the device itself had
gone away.

To address the responsiveness issues we can decrease the sleeps to 20ms and
use a jiffies based timeout value rather than just counting the number of
times we slept and then polled.

To address the hardware going away we can move the check for the firmware
BAR being present from where it was and place it inside the loop after the
mailbox descriptor ring is initialized and before we sleep so that we just
abort and return an error if the device went away during initialization.

With these two changes we see a significant improvement in boot times for
the driver.

Fixes: da3cde08209e ("eth: fbnic: Add FW communication mechanism")
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/174654721224.499179.2698616208976624755.stgit@ahduyck-xeon-server.home.arpa
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/meta/fbnic/fbnic_fw.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index 732875aae46c..d344b454f28b 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -905,27 +905,30 @@ void fbnic_mbx_poll(struct fbnic_dev *fbd)
 
 int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd)
 {
+	unsigned long timeout = jiffies + 10 * HZ + 1;
 	struct fbnic_fw_mbx *tx_mbx;
-	int attempts = 50;
-
-	/* Immediate fail if BAR4 isn't there */
-	if (!fbnic_fw_present(fbd))
-		return -ENODEV;
 
 	tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
-	while (!tx_mbx->ready && --attempts) {
+	while (!tx_mbx->ready) {
+		if (!time_is_after_jiffies(timeout))
+			return -ETIMEDOUT;
+
 		/* Force the firmware to trigger an interrupt response to
 		 * avoid the mailbox getting stuck closed if the interrupt
 		 * is reset.
 		 */
 		fbnic_mbx_reset_desc_ring(fbd, FBNIC_IPC_MBX_TX_IDX);
 
-		msleep(200);
+		/* Immediate fail if BAR4 went away */
+		if (!fbnic_fw_present(fbd))
+			return -ENODEV;
+
+		msleep(20);
 
 		fbnic_mbx_poll(fbd);
 	}
 
-	return attempts ? 0 : -ETIMEDOUT;
+	return 0;
 }
 
 static void __fbnic_fw_evict_cmpl(struct fbnic_fw_completion *cmpl_data)
-- 
2.51.0


From 1b34d1c1dc8384884febd83140c9afbc7c4b9eb8 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Tue, 6 May 2025 09:00:18 -0700
Subject: [PATCH 07/16] fbnic: Pull fbnic_fw_xmit_cap_msg use out of interrupt
 context

This change pulls the call to fbnic_fw_xmit_cap_msg out of
fbnic_mbx_init_desc_ring and instead places it in the polling function for
getting the Tx ready. Doing that we can avoid the potential issue with an
interrupt coming in later from the firmware that causes it to get fired in
interrupt context.

Fixes: 20d2e88cc746 ("eth: fbnic: Add initial messaging to notify FW of our presence")
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/174654721876.499179.9839651602256668493.stgit@ahduyck-xeon-server.home.arpa
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/meta/fbnic/fbnic_fw.c | 43 ++++++++--------------
 1 file changed, 16 insertions(+), 27 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index d344b454f28b..90a45c701543 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -352,24 +352,6 @@ static int fbnic_fw_xmit_simple_msg(struct fbnic_dev *fbd, u32 msg_type)
 	return err;
 }
 
-/**
- * fbnic_fw_xmit_cap_msg - Allocate and populate a FW capabilities message
- * @fbd: FBNIC device structure
- *
- * Return: NULL on failure to allocate, error pointer on error, or pointer
- * to new TLV test message.
- *
- * Sends a single TLV header indicating the host wants the firmware to
- * confirm the capabilities and version.
- **/
-static int fbnic_fw_xmit_cap_msg(struct fbnic_dev *fbd)
-{
-	int err = fbnic_fw_xmit_simple_msg(fbd, FBNIC_TLV_MSG_ID_HOST_CAP_REQ);
-
-	/* Return 0 if we are not calling this on ASIC */
-	return (err == -EOPNOTSUPP) ? 0 : err;
-}
-
 static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	struct fbnic_fw_mbx *mbx = &fbd->mbx[mbx_idx];
@@ -393,15 +375,6 @@ static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 		/* Enable DMA reads from the device */
 		wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
 		     FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME);
-
-		/* Force version to 1 if we successfully requested an update
-		 * from the firmware. This should be overwritten once we get
-		 * the actual version from the firmware in the capabilities
-		 * request message.
-		 */
-		if (!fbnic_fw_xmit_cap_msg(fbd) &&
-		    !fbd->fw_cap.running.mgmt.version)
-			fbd->fw_cap.running.mgmt.version = 1;
 		break;
 	}
 }
@@ -907,6 +880,7 @@ int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd)
 {
 	unsigned long timeout = jiffies + 10 * HZ + 1;
 	struct fbnic_fw_mbx *tx_mbx;
+	int err;
 
 	tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
 	while (!tx_mbx->ready) {
@@ -928,7 +902,22 @@ int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd)
 		fbnic_mbx_poll(fbd);
 	}
 
+	/* Request an update from the firmware. This should overwrite
+	 * mgmt.version once we get the actual version from the firmware
+	 * in the capabilities request message.
+	 */
+	err = fbnic_fw_xmit_simple_msg(fbd, FBNIC_TLV_MSG_ID_HOST_CAP_REQ);
+	if (err)
+		goto clean_mbx;
+
+	/* Use "1" to indicate we entered the state waiting for a response */
+	fbd->fw_cap.running.mgmt.version = 1;
+
 	return 0;
+clean_mbx:
+	/* Cleanup Rx buffers and disable mailbox */
+	fbnic_mbx_clean(fbd);
+	return err;
 }
 
 static void __fbnic_fw_evict_cmpl(struct fbnic_fw_completion *cmpl_data)
-- 
2.51.0


From ce2fa1dba204c761582674cf2eb9cbe0b949b5c7 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Tue, 6 May 2025 09:00:25 -0700
Subject: [PATCH 08/16] fbnic: Do not allow mailbox to toggle to ready outside
 fbnic_mbx_poll_tx_ready

We had originally thought to have the mailbox go to ready in the background
while we were doing other things. One issue with this though is that we
can't disable it by clearing the ready state without also blocking
interrupts or calls to mbx_poll as it will just pop back to life during an
interrupt.

In order to prevent that from happening we can pull the code for toggling
to ready out of the interrupt path and instead place it in the
fbnic_mbx_poll_tx_ready path so that it becomes the only spot where the
Rx/Tx can toggle to the ready state. By doing this we can prevent races
where we disable the DMA and/or free buffers only to have an interrupt fire
and undo what we have done.

Fixes: da3cde08209e ("eth: fbnic: Add FW communication mechanism")
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/174654722518.499179.11612865740376848478.stgit@ahduyck-xeon-server.home.arpa
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/meta/fbnic/fbnic_fw.c | 27 ++++++++--------------
 1 file changed, 10 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index 90a45c701543..3d9636a6c968 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -356,10 +356,6 @@ static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 {
 	struct fbnic_fw_mbx *mbx = &fbd->mbx[mbx_idx];
 
-	/* This is a one time init, so just exit if it is completed */
-	if (mbx->ready)
-		return;
-
 	mbx->ready = true;
 
 	switch (mbx_idx) {
@@ -379,21 +375,18 @@ static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
 	}
 }
 
-static void fbnic_mbx_postinit(struct fbnic_dev *fbd)
+static bool fbnic_mbx_event(struct fbnic_dev *fbd)
 {
-	int i;
-
 	/* We only need to do this on the first interrupt following reset.
 	 * this primes the mailbox so that we will have cleared all the
 	 * skip descriptors.
 	 */
 	if (!(rd32(fbd, FBNIC_INTR_STATUS(0)) & (1u << FBNIC_FW_MSIX_ENTRY)))
-		return;
+		return false;
 
 	wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
 
-	for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
-		fbnic_mbx_init_desc_ring(fbd, i);
+	return true;
 }
 
 /**
@@ -870,7 +863,7 @@ next_page:
 
 void fbnic_mbx_poll(struct fbnic_dev *fbd)
 {
-	fbnic_mbx_postinit(fbd);
+	fbnic_mbx_event(fbd);
 
 	fbnic_mbx_process_tx_msgs(fbd);
 	fbnic_mbx_process_rx_msgs(fbd);
@@ -879,11 +872,9 @@ void fbnic_mbx_poll(struct fbnic_dev *fbd)
 int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd)
 {
 	unsigned long timeout = jiffies + 10 * HZ + 1;
-	struct fbnic_fw_mbx *tx_mbx;
-	int err;
+	int err, i;
 
-	tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
-	while (!tx_mbx->ready) {
+	do {
 		if (!time_is_after_jiffies(timeout))
 			return -ETIMEDOUT;
 
@@ -898,9 +889,11 @@ int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd)
 			return -ENODEV;
 
 		msleep(20);
+	} while (!fbnic_mbx_event(fbd));
 
-		fbnic_mbx_poll(fbd);
-	}
+	/* FW has shown signs of life. Enable DMA and start Tx/Rx */
+	for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
+		fbnic_mbx_init_desc_ring(fbd, i);
 
 	/* Request an update from the firmware. This should overwrite
 	 * mgmt.version once we get the actual version from the firmware
-- 
2.51.0


From 23fa6a23d97182d36ca3c71e43c804fa91e46a03 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 6 May 2025 17:32:20 -0700
Subject: [PATCH 09/16] net: export a helper for adding up queue stats

Older drivers and drivers with lower queue counts often have a static
array of queues, rather than allocating structs for each queue on demand.
Add a helper for adding up qstats from a queue range. Expectation is
that driver will pass a queue range [netdev->real_num_*x_queues, MAX).
It was tempting to always use num_*x_queues as the end, but virtio
seems to clamp its queue count after allocating the netdev. And this
way we can trivaly reuse the helper for [0, real_..).

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250507003221.823267-2-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/netdev_queues.h |  6 ++++
 net/core/netdev-genl.c      | 69 +++++++++++++++++++++++++++----------
 2 files changed, 56 insertions(+), 19 deletions(-)

diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index 825141d675e5..d01c82983b4d 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -103,6 +103,12 @@ struct netdev_stat_ops {
 			       struct netdev_queue_stats_tx *tx);
 };
 
+void netdev_stat_queue_sum(struct net_device *netdev,
+			   int rx_start, int rx_end,
+			   struct netdev_queue_stats_rx *rx_sum,
+			   int tx_start, int tx_end,
+			   struct netdev_queue_stats_tx *tx_sum);
+
 /**
  * struct netdev_queue_mgmt_ops - netdev ops for queue management
  *
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 230743bdbb14..dae9f0d432fb 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -708,25 +708,66 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp,
 	return 0;
 }
 
+/**
+ * netdev_stat_queue_sum() - add up queue stats from range of queues
+ * @netdev:	net_device
+ * @rx_start:	index of the first Rx queue to query
+ * @rx_end:	index after the last Rx queue (first *not* to query)
+ * @rx_sum:	output Rx stats, should be already initialized
+ * @tx_start:	index of the first Tx queue to query
+ * @tx_end:	index after the last Tx queue (first *not* to query)
+ * @tx_sum:	output Tx stats, should be already initialized
+ *
+ * Add stats from [start, end) range of queue IDs to *x_sum structs.
+ * The sum structs must be already initialized. Usually this
+ * helper is invoked from the .get_base_stats callbacks of drivers
+ * to account for stats of disabled queues. In that case the ranges
+ * are usually [netdev->real_num_*x_queues, netdev->num_*x_queues).
+ */
+void netdev_stat_queue_sum(struct net_device *netdev,
+			   int rx_start, int rx_end,
+			   struct netdev_queue_stats_rx *rx_sum,
+			   int tx_start, int tx_end,
+			   struct netdev_queue_stats_tx *tx_sum)
+{
+	const struct netdev_stat_ops *ops;
+	struct netdev_queue_stats_rx rx;
+	struct netdev_queue_stats_tx tx;
+	int i;
+
+	ops = netdev->stat_ops;
+
+	for (i = rx_start; i < rx_end; i++) {
+		memset(&rx, 0xff, sizeof(rx));
+		if (ops->get_queue_stats_rx)
+			ops->get_queue_stats_rx(netdev, i, &rx);
+		netdev_nl_stats_add(rx_sum, &rx, sizeof(rx));
+	}
+	for (i = tx_start; i < tx_end; i++) {
+		memset(&tx, 0xff, sizeof(tx));
+		if (ops->get_queue_stats_tx)
+			ops->get_queue_stats_tx(netdev, i, &tx);
+		netdev_nl_stats_add(tx_sum, &tx, sizeof(tx));
+	}
+}
+EXPORT_SYMBOL(netdev_stat_queue_sum);
+
 static int
 netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp,
 			  const struct genl_info *info)
 {
-	struct netdev_queue_stats_rx rx_sum, rx;
-	struct netdev_queue_stats_tx tx_sum, tx;
-	const struct netdev_stat_ops *ops;
+	struct netdev_queue_stats_rx rx_sum;
+	struct netdev_queue_stats_tx tx_sum;
 	void *hdr;
-	int i;
 
-	ops = netdev->stat_ops;
 	/* Netdev can't guarantee any complete counters */
-	if (!ops->get_base_stats)
+	if (!netdev->stat_ops->get_base_stats)
 		return 0;
 
 	memset(&rx_sum, 0xff, sizeof(rx_sum));
 	memset(&tx_sum, 0xff, sizeof(tx_sum));
 
-	ops->get_base_stats(netdev, &rx_sum, &tx_sum);
+	netdev->stat_ops->get_base_stats(netdev, &rx_sum, &tx_sum);
 
 	/* The op was there, but nothing reported, don't bother */
 	if (!memchr_inv(&rx_sum, 0xff, sizeof(rx_sum)) &&
@@ -739,18 +780,8 @@ netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp,
 	if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex))
 		goto nla_put_failure;
 
-	for (i = 0; i < netdev->real_num_rx_queues; i++) {
-		memset(&rx, 0xff, sizeof(rx));
-		if (ops->get_queue_stats_rx)
-			ops->get_queue_stats_rx(netdev, i, &rx);
-		netdev_nl_stats_add(&rx_sum, &rx, sizeof(rx));
-	}
-	for (i = 0; i < netdev->real_num_tx_queues; i++) {
-		memset(&tx, 0xff, sizeof(tx));
-		if (ops->get_queue_stats_tx)
-			ops->get_queue_stats_tx(netdev, i, &tx);
-		netdev_nl_stats_add(&tx_sum, &tx, sizeof(tx));
-	}
+	netdev_stat_queue_sum(netdev, 0, netdev->real_num_rx_queues, &rx_sum,
+			      0, netdev->real_num_tx_queues, &tx_sum);
 
 	if (netdev_nl_stats_write_rx(rsp, &rx_sum) ||
 	    netdev_nl_stats_write_tx(rsp, &tx_sum))
-- 
2.51.0


From 001160ec8c59115efc39e197d40829bdafd4d7f5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 6 May 2025 17:32:21 -0700
Subject: [PATCH 10/16] virtio-net: fix total qstat values

NIPA tests report that the interface statistics reported
via qstat are lower than those reported via ip link.
Looks like this is because some tests flip the queue
count up and down, and we end up with some of the traffic
accounted on disabled queues.

Add up counters from disabled queues.

Fixes: d888f04c09bb ("virtio-net: support queue stat")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250507003221.823267-3-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/virtio_net.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index f9e3e628ec4d..e53ba600605a 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -5678,6 +5678,10 @@ static void virtnet_get_base_stats(struct net_device *dev,
 
 	if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_SPEED)
 		tx->hw_drop_ratelimits = 0;
+
+	netdev_stat_queue_sum(dev,
+			      dev->real_num_rx_queues, vi->max_queue_pairs, rx,
+			      dev->real_num_tx_queues, vi->max_queue_pairs, tx);
 }
 
 static const struct netdev_stat_ops virtnet_stat_ops = {
-- 
2.51.0


From 1f389a648a3be07400819c431ee30b74129a8a6e Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 7 May 2025 09:49:55 +0200
Subject: [PATCH 11/16] selftests: netfilter: fix conntrack stress test
 failures on debug kernels

Jakub reports test failures on debug kernel:
FAIL: proc inconsistency after uniq filter for ...

This is because entries are expiring while validation is happening.

Increase the timeout of ctnetlink injected entries and the
icmp (ping) timeout to 1h to avoid this.

To reduce run-time, add less entries via ctnetlink when KSFT_MACHINE_SLOW
is set.

also log of a failed run had:
 PASS: dump in netns had same entry count (-C 0, -L 0, -p 0, /proc 0)

... i.e. all entries already expired: add a check and set failure if
this happens.

While at it, include a diff when there were duplicate entries and add
netns name to error messages (it tells if icmp or ctnetlink failed).

Fixes: d33f889fd80c ("selftests: netfilter: add conntrack stress test")
Reported-by: Jakub Kicinski <kuba@kernel.org>
Closes: https://lore.kernel.org/netdev/20250506061125.1a244d12@kernel.org/
Signed-off-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20250507075000.5819-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/netfilter/conntrack_resize.sh         | 63 ++++++++++++-------
 1 file changed, 42 insertions(+), 21 deletions(-)

diff --git a/tools/testing/selftests/net/netfilter/conntrack_resize.sh b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
index aabc7c51181e..9e033e80219e 100755
--- a/tools/testing/selftests/net/netfilter/conntrack_resize.sh
+++ b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
@@ -9,8 +9,13 @@ checktool "nft --version" "run test without nft tool"
 init_net_max=0
 ct_buckets=0
 tmpfile=""
+tmpfile_proc=""
+tmpfile_uniq=""
 ret=0
 
+insert_count=2000
+[ "$KSFT_MACHINE_SLOW" = "yes" ] && insert_count=400
+
 modprobe -q nf_conntrack
 if ! sysctl -q net.netfilter.nf_conntrack_max >/dev/null;then
 	echo "SKIP: conntrack sysctls not available"
@@ -23,7 +28,7 @@ ct_buckets=$(sysctl -n net.netfilter.nf_conntrack_buckets) || exit 1
 cleanup() {
 	cleanup_all_ns
 
-	rm -f "$tmpfile"
+	rm -f "$tmpfile" "$tmpfile_proc" "$tmpfile_uniq"
 
 	# restore original sysctl setting
 	sysctl -q net.netfilter.nf_conntrack_max=$init_net_max
@@ -54,7 +59,7 @@ insert_ctnetlink() {
 		ip netns exec "$ns" bash -c "for i in \$(seq 1 $bulk); do \
 			if ! conntrack -I -s \$((\$RANDOM%256)).\$((\$RANDOM%256)).\$((\$RANDOM%256)).\$((\$RANDOM%255+1)) \
 					  -d \$((\$RANDOM%256)).\$((\$RANDOM%256)).\$((\$RANDOM%256)).\$((\$RANDOM%255+1)) \
-					  --protonum 17 --timeout 120 --status ASSURED,SEEN_REPLY --sport \$RANDOM --dport 53; then \
+					  --protonum 17 --timeout 3600 --status ASSURED,SEEN_REPLY --sport \$RANDOM --dport 53; then \
 					  return;\
 			fi & \
 		done ; wait" 2>/dev/null
@@ -191,7 +196,7 @@ insert_flood()
 	local n="$1"
 	local r=0
 
-	r=$((RANDOM%2000))
+	r=$((RANDOM%$insert_count))
 
 	ctflood "$n" "$timeout" "floodresize" &
 	insert_ctnetlink "$n" "$r" &
@@ -232,49 +237,61 @@ check_dump()
 	local proto=0
 	local proc=0
 	local unique=""
-
-	c=$(ip netns exec "$ns" conntrack -C)
+	local lret=0
 
 	# NOTE: assumes timeouts are large enough to not have
 	# expirations in all following tests.
-	l=$(ip netns exec "$ns" conntrack -L 2>/dev/null | tee "$tmpfile" | wc -l)
+	l=$(ip netns exec "$ns" conntrack -L 2>/dev/null | sort | tee "$tmpfile" | wc -l)
+	c=$(ip netns exec "$ns" conntrack -C)
+
+	if [ "$c" -eq 0 ]; then
+		echo "FAIL: conntrack count for $ns is 0"
+		lret=1
+	fi
 
 	if [ "$c" -ne "$l" ]; then
-		echo "FAIL: count inconsistency for $ns: $c != $l"
-		ret=1
+		echo "FAIL: conntrack count inconsistency for $ns -L: $c != $l"
+		lret=1
 	fi
 
 	# check the dump we retrieved is free of duplicated entries.
-	unique=$(sort "$tmpfile" | uniq | wc -l)
+	unique=$(uniq "$tmpfile" | tee "$tmpfile_uniq" | wc -l)
 	if [ "$l" -ne "$unique" ]; then
-		echo "FAIL: count identical but listing contained redundant entries: $l != $unique"
-		ret=1
+		echo "FAIL: listing contained redundant entries for $ns: $l != $unique"
+		diff -u "$tmpfile" "$tmpfile_uniq"
+		lret=1
 	fi
 
 	# we either inserted icmp or only udp, hence, --proto should return same entry count as without filter.
-	proto=$(ip netns exec "$ns" conntrack -L --proto $protoname 2>/dev/null | wc -l)
+	proto=$(ip netns exec "$ns" conntrack -L --proto $protoname 2>/dev/null | sort | uniq | tee "$tmpfile_uniq" | wc -l)
 	if [ "$l" -ne "$proto" ]; then
-		echo "FAIL: dump inconsistency for $ns: $l != $proto"
-		ret=1
+		echo "FAIL: dump inconsistency for $ns -L --proto $protoname: $l != $proto"
+		diff -u "$tmpfile" "$tmpfile_uniq"
+		lret=1
 	fi
 
 	if [ -r /proc/self/net/nf_conntrack ] ; then
-		proc=$(ip netns exec "$ns" bash -c "wc -l < /proc/self/net/nf_conntrack")
+		proc=$(ip netns exec "$ns" bash -c "sort < /proc/self/net/nf_conntrack | tee \"$tmpfile_proc\" | wc -l")
 
 		if [ "$l" -ne "$proc" ]; then
 			echo "FAIL: proc inconsistency for $ns: $l != $proc"
-			ret=1
+			lret=1
 		fi
 
-		proc=$(ip netns exec "$ns" bash -c "sort < /proc/self/net/nf_conntrack | uniq | wc -l")
-
+		proc=$(uniq "$tmpfile_proc" | tee "$tmpfile_uniq" | wc -l)
 		if [ "$l" -ne "$proc" ]; then
 			echo "FAIL: proc inconsistency after uniq filter for $ns: $l != $proc"
-			ret=1
+			diff -u "$tmpfile_proc" "$tmpfile_uniq"
+			lret=1
 		fi
 	fi
 
-	echo "PASS: dump in netns had same entry count (-C $c, -L $l, -p $proto, /proc $proc)"
+	if [ $lret -eq 0 ];then
+		echo "PASS: dump in netns $ns had same entry count (-C $c, -L $l, -p $proto, /proc $proc)"
+	else
+		echo "FAIL: dump in netns $ns had different entry count (-C $c, -L $l, -p $proto, /proc $proc)"
+		ret=1
+	fi
 }
 
 test_dump_all()
@@ -287,8 +304,10 @@ test_dump_all()
 	ct_flush_once "$nsclient1"
 	ct_flush_once "$nsclient2"
 
+	ip netns exec "$nsclient1" sysctl -q net.netfilter.nf_conntrack_icmp_timeout=3600
+
 	ctflood "$nsclient1" $timeout "dumpall" &
-	insert_ctnetlink "$nsclient2" 2000
+	insert_ctnetlink "$nsclient2" $insert_count
 
 	wait
 
@@ -398,6 +417,8 @@ EOF
 done
 
 tmpfile=$(mktemp)
+tmpfile_proc=$(mktemp)
+tmpfile_uniq=$(mktemp)
 test_conntrack_max_limit
 test_dump_all
 test_floodresize_all
-- 
2.51.0


From d97e2634fbdcd238a51bc363267df0139c17f4da Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 7 May 2025 07:01:07 -0700
Subject: [PATCH 12/16] selftests: net-drv: remove the nic_performance and
 nic_link_layer tests

Revert fbbf93556f0c ("selftests: nic_performance: Add selftest for performance of NIC driver")
Revert c087dc54394b ("selftests: nic_link_layer: Add selftest case for speed and duplex states")
Revert 6116075e18f7 ("selftests: nic_link_layer: Add link layer selftest for NIC driver")

These tests don't clean up after themselves, don't use the disruptive
annotations, don't get included in make install etc. etc. The tests
were added before we have any "HW" runner, so the issues were missed.
Our CI doesn't have any way of excluding broken tests, remove these
for now to stop the random pollution of results due to broken env.
We can always add them back once / if fixed.

Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20250507140109.929801-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/drivers/net/hw/Makefile |   2 -
 .../drivers/net/hw/lib/py/__init__.py         |   1 -
 .../drivers/net/hw/lib/py/linkconfig.py       | 222 ------------------
 .../drivers/net/hw/nic_link_layer.py          | 113 ---------
 .../drivers/net/hw/nic_performance.py         | 137 -----------
 .../selftests/drivers/net/lib/py/load.py      |  20 +-
 6 files changed, 1 insertion(+), 494 deletions(-)
 delete mode 100644 tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py
 delete mode 100644 tools/testing/selftests/drivers/net/hw/nic_link_layer.py
 delete mode 100644 tools/testing/selftests/drivers/net/hw/nic_performance.py

diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index 5447785c286e..df2c047ffa90 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -15,8 +15,6 @@ TEST_PROGS = \
 	iou-zcrx.py \
 	irq.py \
 	loopback.sh \
-	nic_link_layer.py \
-	nic_performance.py \
 	pp_alloc_fail.py \
 	rss_ctx.py \
 	rss_input_xfrm.py \
diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
index 399789a9676a..b582885786f5 100644
--- a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
+++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
@@ -9,7 +9,6 @@ try:
     sys.path.append(KSFT_DIR.as_posix())
     from net.lib.py import *
     from drivers.net.lib.py import *
-    from .linkconfig import LinkConfig
 except ModuleNotFoundError as e:
     ksft_pr("Failed importing `net` library from kernel sources")
     ksft_pr(str(e))
diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py b/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py
deleted file mode 100644
index 79fde603cbbc..000000000000
--- a/tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py
+++ /dev/null
@@ -1,222 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-
-from lib.py import cmd, ethtool, ip
-from lib.py import ksft_pr, ksft_eq, KsftSkipEx
-from typing import Optional
-import re
-import time
-import json
-
-#The LinkConfig class is implemented to handle the link layer configurations.
-#Required minimum ethtool version is 6.10
-
-class LinkConfig:
-    """Class for handling the link layer configurations"""
-    def __init__(self, cfg: object) -> None:
-        self.cfg = cfg
-        self.partner_netif = self.get_partner_netif_name()
-
-        """Get the initial link configuration of local interface"""
-        self.common_link_modes = self.get_common_link_modes()
-
-    def get_partner_netif_name(self) -> Optional[str]:
-        partner_netif = None
-        try:
-            if not self.verify_link_up():
-                return None
-            """Get partner interface name"""
-            partner_json_output = ip("addr show", json=True, host=self.cfg.remote)
-            for interface in partner_json_output:
-                for addr in interface.get('addr_info', []):
-                    if addr.get('local') == self.cfg.remote_addr:
-                        partner_netif = interface['ifname']
-                        ksft_pr(f"Partner Interface name: {partner_netif}")
-            if partner_netif is None:
-                ksft_pr("Unable to get the partner interface name")
-        except Exception as e:
-            print(f"Unexpected error occurred while getting partner interface name: {e}")
-        self.partner_netif = partner_netif
-        return partner_netif
-
-    def verify_link_up(self) -> bool:
-        """Verify whether the local interface link is up"""
-        with open(f"/sys/class/net/{self.cfg.ifname}/operstate", "r") as fp:
-            link_state = fp.read().strip()
-
-        if link_state == "down":
-            ksft_pr(f"Link state of interface {self.cfg.ifname} is DOWN")
-            return False
-        else:
-            return True
-
-    def reset_interface(self, local: bool = True, remote: bool = True) -> bool:
-        ksft_pr("Resetting interfaces in local and remote")
-        if remote:
-            if self.verify_link_up():
-                if self.partner_netif is not None:
-                    ifname = self.partner_netif
-                    link_up_cmd = f"ip link set up {ifname}"
-                    link_down_cmd = f"ip link set down {ifname}"
-                    reset_cmd = f"{link_down_cmd} && sleep 5 && {link_up_cmd}"
-                    try:
-                        cmd(reset_cmd, host=self.cfg.remote)
-                    except Exception as e:
-                        ksft_pr(f"Unexpected error occurred while resetting remote: {e}")
-                else:
-                    ksft_pr("Partner interface not available")
-        if local:
-            ifname = self.cfg.ifname
-            link_up_cmd = f"ip link set up {ifname}"
-            link_down_cmd = f"ip link set down {ifname}"
-            reset_cmd = f"{link_down_cmd} && sleep 5 && {link_up_cmd}"
-            try:
-                cmd(reset_cmd)
-            except Exception as e:
-                ksft_pr(f"Unexpected error occurred while resetting local: {e}")
-        time.sleep(10)
-        if self.verify_link_up() and self.get_ethtool_field("link-detected"):
-            ksft_pr("Local and remote interfaces reset to original state")
-            return True
-        else:
-            ksft_pr("Error occurred after resetting interfaces. Link is DOWN.")
-            return False
-
-    def set_speed_and_duplex(self, speed: str, duplex: str, autoneg: bool = True) -> bool:
-        """Set the speed and duplex state for the interface"""
-        autoneg_state = "on" if autoneg is True else "off"
-        process = None
-        try:
-            process = ethtool(f"--change {self.cfg.ifname} speed {speed} duplex {duplex} autoneg {autoneg_state}")
-        except Exception as e:
-            ksft_pr(f"Unexpected error occurred while setting speed/duplex: {e}")
-        if process is None or process.ret != 0:
-            return False
-        else:
-            ksft_pr(f"Speed: {speed} Mbps, Duplex: {duplex} set for Interface: {self.cfg.ifname}")
-            return True
-
-    def verify_speed_and_duplex(self, expected_speed: str, expected_duplex: str) -> bool:
-        if not self.verify_link_up():
-            return False
-        """Verifying the speed and duplex state for the interface"""
-        with open(f"/sys/class/net/{self.cfg.ifname}/speed", "r") as fp:
-            actual_speed = fp.read().strip()
-        with open(f"/sys/class/net/{self.cfg.ifname}/duplex", "r") as fp:
-            actual_duplex = fp.read().strip()
-
-        ksft_eq(actual_speed, expected_speed)
-        ksft_eq(actual_duplex, expected_duplex)
-        return True
-
-    def set_autonegotiation_state(self, state: str, remote: bool = False) -> bool:
-        common_link_modes = self.common_link_modes
-        speeds, duplex_modes = self.get_speed_duplex_values(self.common_link_modes)
-        speed = speeds[0]
-        duplex = duplex_modes[0]
-        if not speed or not duplex:
-            ksft_pr("No speed or duplex modes found")
-            return False
-
-        speed_duplex_cmd = f"speed {speed} duplex {duplex}" if state == "off" else ""
-        if remote:
-            if not self.verify_link_up():
-                return False
-            """Set the autonegotiation state for the partner"""
-            command = f"-s {self.partner_netif} {speed_duplex_cmd} autoneg {state}"
-            partner_autoneg_change = None
-            """Set autonegotiation state for interface in remote pc"""
-            try:
-                partner_autoneg_change = ethtool(command, host=self.cfg.remote)
-            except Exception as e:
-                ksft_pr(f"Unexpected error occurred while changing auto-neg in remote: {e}")
-            if partner_autoneg_change is None or partner_autoneg_change.ret != 0:
-                ksft_pr(f"Not able to set autoneg parameter for interface {self.partner_netif}.")
-                return False
-            ksft_pr(f"Autoneg set as {state} for {self.partner_netif}")
-        else:
-            """Set the autonegotiation state for the interface"""
-            try:
-                process = ethtool(f"-s {self.cfg.ifname} {speed_duplex_cmd} autoneg {state}")
-                if process.ret != 0:
-                    ksft_pr(f"Not able to set autoneg parameter for interface {self.cfg.ifname}")
-                    return False
-            except Exception as e:
-                ksft_pr(f"Unexpected error occurred while changing auto-neg in local: {e}")
-                return False
-            ksft_pr(f"Autoneg set as {state} for {self.cfg.ifname}")
-        return True
-
-    def check_autoneg_supported(self, remote: bool = False) -> bool:
-        if not remote:
-            local_autoneg = self.get_ethtool_field("supports-auto-negotiation")
-            if local_autoneg is None:
-                ksft_pr(f"Unable to fetch auto-negotiation status for interface {self.cfg.ifname}")
-            """Return autoneg status of the local interface"""
-            return local_autoneg
-        else:
-            if not self.verify_link_up():
-                raise KsftSkipEx("Link is DOWN")
-            """Check remote auto-negotiation support status"""
-            partner_autoneg = False
-            if self.partner_netif is not None:
-                partner_autoneg = self.get_ethtool_field("supports-auto-negotiation", remote=True)
-                if partner_autoneg is None:
-                    ksft_pr(f"Unable to fetch auto-negotiation status for interface {self.partner_netif}")
-            return partner_autoneg
-
-    def get_common_link_modes(self) -> set[str]:
-        common_link_modes = []
-        """Populate common link modes"""
-        link_modes = self.get_ethtool_field("supported-link-modes")
-        partner_link_modes = self.get_ethtool_field("link-partner-advertised-link-modes")
-        if link_modes is None:
-            raise KsftSkipEx(f"Link modes not available for {self.cfg.ifname}")
-        if partner_link_modes is None:
-            raise KsftSkipEx(f"Partner link modes not available for {self.cfg.ifname}")
-        common_link_modes = set(link_modes) and set(partner_link_modes)
-        return common_link_modes
-
-    def get_speed_duplex_values(self, link_modes: list[str]) -> tuple[list[str], list[str]]:
-        speed = []
-        duplex = []
-        """Check the link modes"""
-        for data in link_modes:
-            parts = data.split('/')
-            speed_value = re.match(r'\d+', parts[0])
-            if speed_value:
-                speed.append(speed_value.group())
-            else:
-                ksft_pr(f"No speed value found for interface {self.ifname}")
-                return None, None
-            duplex.append(parts[1].lower())
-        return speed, duplex
-
-    def get_ethtool_field(self, field: str, remote: bool = False) -> Optional[str]:
-        process = None
-        if not remote:
-            """Get the ethtool field value for the local interface"""
-            try:
-                process = ethtool(self.cfg.ifname, json=True)
-            except Exception as e:
-                ksft_pr("Required minimum ethtool version is 6.10")
-                ksft_pr(f"Unexpected error occurred while getting ethtool field in local: {e}")
-                return None
-        else:
-            if not self.verify_link_up():
-                return None
-            """Get the ethtool field value for the remote interface"""
-            self.cfg.require_cmd("ethtool", remote=True)
-            if self.partner_netif is None:
-                ksft_pr(f"Partner interface name is unavailable.")
-                return None
-            try:
-                process = ethtool(self.partner_netif, json=True, host=self.cfg.remote)
-            except Exception as e:
-                ksft_pr("Required minimum ethtool version is 6.10")
-                ksft_pr(f"Unexpected error occurred while getting ethtool field in remote: {e}")
-                return None
-        json_data = process[0]
-        """Check if the field exist in the json data"""
-        if field not in json_data:
-            raise KsftSkipEx(f'Field {field} does not exist in the output of interface {json_data["ifname"]}')
-        return json_data[field]
diff --git a/tools/testing/selftests/drivers/net/hw/nic_link_layer.py b/tools/testing/selftests/drivers/net/hw/nic_link_layer.py
deleted file mode 100644
index efd921180532..000000000000
--- a/tools/testing/selftests/drivers/net/hw/nic_link_layer.py
+++ /dev/null
@@ -1,113 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-License-Identifier: GPL-2.0
-
-#Introduction:
-#This file has basic link layer tests for generic NIC drivers.
-#The test comprises of auto-negotiation, speed and duplex checks.
-#
-#Setup:
-#Connect the DUT PC with NIC card to partner pc back via ethernet medium of your choice(RJ45, T1)
-#
-#        DUT PC                                              Partner PC
-#┌───────────────────────┐                         ┌──────────────────────────┐
-#│                       │                         │                          │
-#│                       │                         │                          │
-#│           ┌───────────┐                         │                          │
-#│           │DUT NIC    │         Eth             │                          │
-#│           │Interface ─┼─────────────────────────┼─    any eth Interface    │
-#│           └───────────┘                         │                          │
-#│                       │                         │                          │
-#│                       │                         │                          │
-#└───────────────────────┘                         └──────────────────────────┘
-#
-#Configurations:
-#Required minimum ethtool version is 6.10 (supports json)
-#Default values:
-#time_delay = 8 #time taken to wait for transitions to happen, in seconds.
-
-import time
-import argparse
-from lib.py import ksft_run, ksft_exit, ksft_pr, ksft_eq
-from lib.py import KsftFailEx, KsftSkipEx
-from lib.py import NetDrvEpEnv
-from lib.py import LinkConfig
-
-def _pre_test_checks(cfg: object, link_config: LinkConfig) -> None:
-    if link_config.partner_netif is None:
-        KsftSkipEx("Partner interface is not available")
-    if not link_config.check_autoneg_supported() or not link_config.check_autoneg_supported(remote=True):
-        KsftSkipEx(f"Auto-negotiation not supported for interface {cfg.ifname} or {link_config.partner_netif}")
-    if not link_config.verify_link_up():
-        raise KsftSkipEx(f"Link state of interface {cfg.ifname} is DOWN")
-
-def verify_autonegotiation(cfg: object, expected_state: str, link_config: LinkConfig) -> None:
-    if not link_config.verify_link_up():
-        raise KsftSkipEx(f"Link state of interface {cfg.ifname} is DOWN")
-    """Verifying the autonegotiation state in partner"""
-    partner_autoneg_output = link_config.get_ethtool_field("auto-negotiation", remote=True)
-    if partner_autoneg_output is None:
-        KsftSkipEx(f"Auto-negotiation state not available for interface {link_config.partner_netif}")
-    partner_autoneg_state = "on" if partner_autoneg_output is True else "off"
-
-    ksft_eq(partner_autoneg_state, expected_state)
-
-    """Verifying the autonegotiation state of local"""
-    autoneg_output = link_config.get_ethtool_field("auto-negotiation")
-    if autoneg_output is None:
-        KsftSkipEx(f"Auto-negotiation state not available for interface {cfg.ifname}")
-    actual_state = "on" if autoneg_output is True else "off"
-
-    ksft_eq(actual_state, expected_state)
-
-    """Verifying the link establishment"""
-    link_available = link_config.get_ethtool_field("link-detected")
-    if link_available is None:
-        KsftSkipEx(f"Link status not available for interface {cfg.ifname}")
-    if link_available != True:
-        raise KsftSkipEx("Link not established at interface {cfg.ifname} after changing auto-negotiation")
-
-def test_autonegotiation(cfg: object, link_config: LinkConfig, time_delay: int) -> None:
-    _pre_test_checks(cfg, link_config)
-    for state in ["off", "on"]:
-        if not link_config.set_autonegotiation_state(state, remote=True):
-            raise KsftSkipEx(f"Unable to set auto-negotiation state for interface {link_config.partner_netif}")
-        if not link_config.set_autonegotiation_state(state):
-            raise KsftSkipEx(f"Unable to set auto-negotiation state for interface {cfg.ifname}")
-        time.sleep(time_delay)
-        verify_autonegotiation(cfg, state, link_config)
-
-def test_network_speed(cfg: object, link_config: LinkConfig, time_delay: int) -> None:
-    _pre_test_checks(cfg, link_config)
-    common_link_modes = link_config.common_link_modes
-    if not common_link_modes:
-        KsftSkipEx("No common link modes exist")
-    speeds, duplex_modes = link_config.get_speed_duplex_values(common_link_modes)
-
-    if speeds and duplex_modes and len(speeds) == len(duplex_modes):
-        for idx in range(len(speeds)):
-            speed = speeds[idx]
-            duplex = duplex_modes[idx]
-            if not link_config.set_speed_and_duplex(speed, duplex):
-                raise KsftFailEx(f"Unable to set speed and duplex parameters for {cfg.ifname}")
-            time.sleep(time_delay)
-            if not link_config.verify_speed_and_duplex(speed, duplex):
-                raise KsftSkipEx(f"Error occurred while verifying speed and duplex states for interface {cfg.ifname}")
-    else:
-        if not speeds or not duplex_modes:
-            KsftSkipEx(f"No supported speeds or duplex modes found for interface {cfg.ifname}")
-        else:
-            KsftSkipEx("Mismatch in the number of speeds and duplex modes")
-
-def main() -> None:
-    parser = argparse.ArgumentParser(description="Run basic link layer tests for NIC driver")
-    parser.add_argument('--time-delay', type=int, default=8, help='Time taken to wait for transitions to happen(in seconds). Default is 8 seconds.')
-    args = parser.parse_args()
-    time_delay = args.time_delay
-    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
-        link_config = LinkConfig(cfg)
-        ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, link_config, time_delay,))
-        link_config.reset_interface()
-    ksft_exit()
-
-if __name__ == "__main__":
-    main()
diff --git a/tools/testing/selftests/drivers/net/hw/nic_performance.py b/tools/testing/selftests/drivers/net/hw/nic_performance.py
deleted file mode 100644
index 201403b76ea3..000000000000
--- a/tools/testing/selftests/drivers/net/hw/nic_performance.py
+++ /dev/null
@@ -1,137 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-License-Identifier: GPL-2.0
-
-#Introduction:
-#This file has basic performance test for generic NIC drivers.
-#The test comprises of throughput check for TCP and UDP streams.
-#
-#Setup:
-#Connect the DUT PC with NIC card to partner pc back via ethernet medium of your choice(RJ45, T1)
-#
-#        DUT PC                                              Partner PC
-#┌───────────────────────┐                         ┌──────────────────────────┐
-#│                       │                         │                          │
-#│                       │                         │                          │
-#│           ┌───────────┐                         │                          │
-#│           │DUT NIC    │         Eth             │                          │
-#│           │Interface ─┼─────────────────────────┼─    any eth Interface    │
-#│           └───────────┘                         │                          │
-#│                       │                         │                          │
-#│                       │                         │                          │
-#└───────────────────────┘                         └──────────────────────────┘
-#
-#Configurations:
-#To prevent interruptions, Add ethtool, ip to the sudoers list in remote PC and get the ssh key from remote.
-#Required minimum ethtool version is 6.10
-#Change the below configuration based on your hw needs.
-# """Default values"""
-#time_delay = 8 #time taken to wait for transitions to happen, in seconds.
-#test_duration = 10  #performance test duration for the throughput check, in seconds.
-#send_throughput_threshold = 80 #percentage of send throughput required to pass the check
-#receive_throughput_threshold = 50 #percentage of receive throughput required to pass the check
-
-import time
-import json
-import argparse
-from lib.py import ksft_run, ksft_exit, ksft_pr, ksft_true
-from lib.py import KsftFailEx, KsftSkipEx, GenerateTraffic
-from lib.py import NetDrvEpEnv, bkg, wait_port_listen
-from lib.py import cmd
-from lib.py import LinkConfig
-
-class TestConfig:
-    def __init__(self, time_delay: int, test_duration: int, send_throughput_threshold: int, receive_throughput_threshold: int) -> None:
-        self.time_delay = time_delay
-        self.test_duration = test_duration
-        self.send_throughput_threshold = send_throughput_threshold
-        self.receive_throughput_threshold = receive_throughput_threshold
-
-def _pre_test_checks(cfg: object, link_config: LinkConfig) -> None:
-    if not link_config.verify_link_up():
-        KsftSkipEx(f"Link state of interface {cfg.ifname} is DOWN")
-    common_link_modes = link_config.common_link_modes
-    if common_link_modes is None:
-        KsftSkipEx("No common link modes found")
-    if link_config.partner_netif == None:
-        KsftSkipEx("Partner interface is not available")
-    if link_config.check_autoneg_supported():
-        KsftSkipEx("Auto-negotiation not supported by local")
-    if link_config.check_autoneg_supported(remote=True):
-        KsftSkipEx("Auto-negotiation not supported by remote")
-    cfg.require_cmd("iperf3", remote=True)
-
-def check_throughput(cfg: object, link_config: LinkConfig, test_config: TestConfig, protocol: str, traffic: GenerateTraffic) -> None:
-    common_link_modes = link_config.common_link_modes
-    speeds, duplex_modes = link_config.get_speed_duplex_values(common_link_modes)
-    """Test duration in seconds"""
-    duration = test_config.test_duration
-
-    ksft_pr(f"{protocol} test")
-    test_type = "-u" if protocol == "UDP" else ""
-
-    send_throughput = []
-    receive_throughput = []
-    for idx in range(0, len(speeds)):
-        if link_config.set_speed_and_duplex(speeds[idx], duplex_modes[idx]) == False:
-            raise KsftFailEx(f"Not able to set speed and duplex parameters for {cfg.ifname}")
-        time.sleep(test_config.time_delay)
-        if not link_config.verify_link_up():
-            raise KsftSkipEx(f"Link state of interface {cfg.ifname} is DOWN")
-
-        send_command=f"{test_type} -b 0 -t {duration} --json"
-        receive_command=f"{test_type} -b 0 -t {duration} --reverse --json"
-
-        send_result = traffic.run_remote_test(cfg, command=send_command)
-        if send_result.ret != 0:
-            raise KsftSkipEx("Error occurred during data transmit: {send_result.stdout}")
-
-        send_output = send_result.stdout
-        send_data = json.loads(send_output)
-
-        """Convert throughput to Mbps"""
-        send_throughput.append(round(send_data['end']['sum_sent']['bits_per_second'] / 1e6, 2))
-        ksft_pr(f"{protocol}: Send throughput: {send_throughput[idx]} Mbps")
-
-        receive_result = traffic.run_remote_test(cfg, command=receive_command)
-        if receive_result.ret != 0:
-            raise KsftSkipEx("Error occurred during data receive: {receive_result.stdout}")
-
-        receive_output = receive_result.stdout
-        receive_data = json.loads(receive_output)
-
-        """Convert throughput to Mbps"""
-        receive_throughput.append(round(receive_data['end']['sum_received']['bits_per_second'] / 1e6, 2))
-        ksft_pr(f"{protocol}: Receive throughput: {receive_throughput[idx]} Mbps")
-
-    """Check whether throughput is not below the threshold (default values set at start)"""
-    for idx in range(0, len(speeds)):
-        send_threshold = float(speeds[idx]) * float(test_config.send_throughput_threshold / 100)
-        receive_threshold = float(speeds[idx]) * float(test_config.receive_throughput_threshold / 100)
-        ksft_true(send_throughput[idx] >= send_threshold, f"{protocol}: Send throughput is below threshold for {speeds[idx]} Mbps in {duplex_modes[idx]} duplex")
-        ksft_true(receive_throughput[idx] >= receive_threshold, f"{protocol}: Receive throughput is below threshold for {speeds[idx]} Mbps in {duplex_modes[idx]} duplex")
-
-def test_tcp_throughput(cfg: object, link_config: LinkConfig, test_config: TestConfig, traffic: GenerateTraffic) -> None:
-    _pre_test_checks(cfg, link_config)
-    check_throughput(cfg, link_config, test_config, 'TCP', traffic)
-
-def test_udp_throughput(cfg: object, link_config: LinkConfig, test_config: TestConfig, traffic: GenerateTraffic) -> None:
-    _pre_test_checks(cfg, link_config)
-    check_throughput(cfg, link_config, test_config, 'UDP', traffic)
-
-def main() -> None:
-    parser = argparse.ArgumentParser(description="Run basic performance test for NIC driver")
-    parser.add_argument('--time-delay', type=int, default=8, help='Time taken to wait for transitions to happen(in seconds). Default is 8 seconds.')
-    parser.add_argument('--test-duration', type=int, default=10, help='Performance test duration for the throughput check, in seconds. Default is 10 seconds.')
-    parser.add_argument('--stt', type=int, default=80, help='Send throughput Threshold: Percentage of send throughput upon actual throughput required to pass the throughput check (in percentage). Default is 80.')
-    parser.add_argument('--rtt', type=int, default=50, help='Receive throughput Threshold: Percentage of receive throughput upon actual throughput required to pass the throughput check (in percentage). Default is 50.')
-    args=parser.parse_args()
-    test_config = TestConfig(args.time_delay, args.test_duration, args.stt, args.rtt)
-    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
-        traffic = GenerateTraffic(cfg)
-        link_config = LinkConfig(cfg)
-        ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, link_config, test_config, traffic,  ))
-        link_config.reset_interface()
-    ksft_exit()
-
-if __name__ == "__main__":
-    main()
diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py
index da5af2c680fa..d9c10613ae67 100644
--- a/tools/testing/selftests/drivers/net/lib/py/load.py
+++ b/tools/testing/selftests/drivers/net/lib/py/load.py
@@ -2,7 +2,7 @@
 
 import time
 
-from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen, bkg
+from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen
 
 class GenerateTraffic:
     def __init__(self, env, port=None):
@@ -23,24 +23,6 @@ class GenerateTraffic:
             self.stop(verbose=True)
             raise Exception("iperf3 traffic did not ramp up")
 
-    def run_remote_test(self, env: object, port=None, command=None):
-        if port is None:
-            port = rand_port()
-        try:
-            server_cmd = f"iperf3 -s 1 -p {port} --one-off"
-            with bkg(server_cmd, host=env.remote):
-                #iperf3 opens TCP connection as default in server
-                #-u to be specified in client command for UDP
-                wait_port_listen(port, host=env.remote)
-        except Exception as e:
-            raise Exception(f"Unexpected error occurred while running server command: {e}")
-        try:
-            client_cmd = f"iperf3 -c {env.remote_addr} -p {port} {command}"
-            proc = cmd(client_cmd)
-            return proc
-        except Exception as e:
-            raise Exception(f"Unexpected error occurred while running client command: {e}")
-
     def _wait_pkts(self, pkt_cnt=None, pps=None):
         """
         Wait until we've seen pkt_cnt or until traffic ramps up to pps.
-- 
2.51.0


From 4701073c3debd16d7f534f3eb808bd9b50601c0c Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Tue, 6 May 2025 16:07:22 +0800
Subject: [PATCH 13/16] net: enetc: add initial netc-lib driver to support NTMP

Some NETC functionality is controlled using control messages sent to the
hardware using BD ring interface with 32B descriptor similar to transmit
BD ring used on ENETC. This BD ring interface is referred to as command
BD ring. It is used to configure functionality where the underlying
resources may be shared between different entities or being too large to
configure using direct registers. Therefore, a messaging protocol called
NETC Table Management Protocol (NTMP) is provided for exchanging
configuration and management information between the software and the
hardware using the command BD ring interface.

For the management protocol of LS1028A has been retroactively named NTMP
1.0, and its implementation is in enetc_cbdr.c and enetc_qos.c. However,
NTMP of i.MX95 has been upgraded to version 2.0, which is incompatible
with LS1028A, because the message formats have been changed. Therefore,
add the netc-lib driver to support NTMP 2.0 to operate various tables.
Note that, only MAC address filter table and RSS table are supported at
the moment. More tables will be supported in subsequent patches.

It is worth mentioning that the purpose of the netc-lib driver is to
provide some NTMP-based generic interfaces for ENETC and NETC Switch
drivers. Currently, it only supports the configurations of some tables.
Interfaces such as tc flower and debugfs will be added in the future.

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250506080735.3444381-2-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS                                   |   1 +
 drivers/net/ethernet/freescale/enetc/Kconfig  |   8 +
 drivers/net/ethernet/freescale/enetc/Makefile |   3 +
 drivers/net/ethernet/freescale/enetc/ntmp.c   | 462 ++++++++++++++++++
 .../ethernet/freescale/enetc/ntmp_private.h   | 103 ++++
 include/linux/fsl/ntmp.h                      | 121 +++++
 6 files changed, 698 insertions(+)
 create mode 100644 drivers/net/ethernet/freescale/enetc/ntmp.c
 create mode 100644 drivers/net/ethernet/freescale/enetc/ntmp_private.h
 create mode 100644 include/linux/fsl/ntmp.h

diff --git a/MAINTAINERS b/MAINTAINERS
index c1bfbe48c5a2..890699d937b6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9378,6 +9378,7 @@ F:	Documentation/devicetree/bindings/net/nxp,netc-blk-ctrl.yaml
 F:	drivers/net/ethernet/freescale/enetc/
 F:	include/linux/fsl/enetc_mdio.h
 F:	include/linux/fsl/netc_global.h
+F:	include/linux/fsl/ntmp.h
 
 FREESCALE eTSEC ETHERNET DRIVER (GIANFAR)
 M:	Claudiu Manoil <claudiu.manoil@nxp.com>
diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig
index 7250d3bbf6bb..616ea22ceabc 100644
--- a/drivers/net/ethernet/freescale/enetc/Kconfig
+++ b/drivers/net/ethernet/freescale/enetc/Kconfig
@@ -15,6 +15,13 @@ config NXP_ENETC_PF_COMMON
 
 	  If compiled as module (M), the module name is nxp-enetc-pf-common.
 
+config NXP_NETC_LIB
+	tristate
+	help
+	  This module provides common functionalities for both ENETC and NETC
+	  Switch, such as NETC Table Management Protocol (NTMP) 2.0, common tc
+	  flower and debugfs interfaces and so on.
+
 config FSL_ENETC
 	tristate "ENETC PF driver"
 	depends on PCI_MSI
@@ -40,6 +47,7 @@ config NXP_ENETC4
 	select FSL_ENETC_CORE
 	select FSL_ENETC_MDIO
 	select NXP_ENETC_PF_COMMON
+	select NXP_NETC_LIB
 	select PHYLINK
 	select DIMLIB
 	help
diff --git a/drivers/net/ethernet/freescale/enetc/Makefile b/drivers/net/ethernet/freescale/enetc/Makefile
index 6fd27ee4fcd1..707a68e26971 100644
--- a/drivers/net/ethernet/freescale/enetc/Makefile
+++ b/drivers/net/ethernet/freescale/enetc/Makefile
@@ -6,6 +6,9 @@ fsl-enetc-core-y := enetc.o enetc_cbdr.o enetc_ethtool.o
 obj-$(CONFIG_NXP_ENETC_PF_COMMON) += nxp-enetc-pf-common.o
 nxp-enetc-pf-common-y := enetc_pf_common.o
 
+obj-$(CONFIG_NXP_NETC_LIB) += nxp-netc-lib.o
+nxp-netc-lib-y := ntmp.o
+
 obj-$(CONFIG_FSL_ENETC) += fsl-enetc.o
 fsl-enetc-y := enetc_pf.o
 fsl-enetc-$(CONFIG_PCI_IOV) += enetc_msg.o
diff --git a/drivers/net/ethernet/freescale/enetc/ntmp.c b/drivers/net/ethernet/freescale/enetc/ntmp.c
new file mode 100644
index 000000000000..ba32c1bbd9e1
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/ntmp.c
@@ -0,0 +1,462 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/*
+ * NETC NTMP (NETC Table Management Protocol) 2.0 Library
+ * Copyright 2025 NXP
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/fsl/netc_global.h>
+#include <linux/iopoll.h>
+
+#include "ntmp_private.h"
+
+#define NETC_CBDR_TIMEOUT		1000 /* us */
+#define NETC_CBDR_DELAY_US		10
+#define NETC_CBDR_MR_EN			BIT(31)
+
+#define NTMP_BASE_ADDR_ALIGN		128
+#define NTMP_DATA_ADDR_ALIGN		32
+
+/* Define NTMP Table ID */
+#define NTMP_MAFT_ID			1
+#define NTMP_RSST_ID			3
+
+/* Generic Update Actions for most tables */
+#define NTMP_GEN_UA_CFGEU		BIT(0)
+#define NTMP_GEN_UA_STSEU		BIT(1)
+
+#define NTMP_ENTRY_ID_SIZE		4
+#define RSST_ENTRY_NUM			64
+#define RSST_STSE_DATA_SIZE(n)		((n) * 8)
+#define RSST_CFGE_DATA_SIZE(n)		(n)
+
+int ntmp_init_cbdr(struct netc_cbdr *cbdr, struct device *dev,
+		   const struct netc_cbdr_regs *regs)
+{
+	int cbd_num = NETC_CBDR_BD_NUM;
+	size_t size;
+
+	size = cbd_num * sizeof(union netc_cbd) + NTMP_BASE_ADDR_ALIGN;
+	cbdr->addr_base = dma_alloc_coherent(dev, size, &cbdr->dma_base,
+					     GFP_KERNEL);
+	if (!cbdr->addr_base)
+		return -ENOMEM;
+
+	cbdr->dma_size = size;
+	cbdr->bd_num = cbd_num;
+	cbdr->regs = *regs;
+	cbdr->dev = dev;
+
+	/* The base address of the Control BD Ring must be 128 bytes aligned */
+	cbdr->dma_base_align =  ALIGN(cbdr->dma_base,  NTMP_BASE_ADDR_ALIGN);
+	cbdr->addr_base_align = PTR_ALIGN(cbdr->addr_base,
+					  NTMP_BASE_ADDR_ALIGN);
+
+	cbdr->next_to_clean = 0;
+	cbdr->next_to_use = 0;
+	spin_lock_init(&cbdr->ring_lock);
+
+	/* Step 1: Configure the base address of the Control BD Ring */
+	netc_write(cbdr->regs.bar0, lower_32_bits(cbdr->dma_base_align));
+	netc_write(cbdr->regs.bar1, upper_32_bits(cbdr->dma_base_align));
+
+	/* Step 2: Configure the producer index register */
+	netc_write(cbdr->regs.pir, cbdr->next_to_clean);
+
+	/* Step 3: Configure the consumer index register */
+	netc_write(cbdr->regs.cir, cbdr->next_to_use);
+
+	/* Step4: Configure the number of BDs of the Control BD Ring */
+	netc_write(cbdr->regs.lenr, cbdr->bd_num);
+
+	/* Step 5: Enable the Control BD Ring */
+	netc_write(cbdr->regs.mr, NETC_CBDR_MR_EN);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ntmp_init_cbdr);
+
+void ntmp_free_cbdr(struct netc_cbdr *cbdr)
+{
+	/* Disable the Control BD Ring */
+	netc_write(cbdr->regs.mr, 0);
+	dma_free_coherent(cbdr->dev, cbdr->dma_size, cbdr->addr_base,
+			  cbdr->dma_base);
+	memset(cbdr, 0, sizeof(*cbdr));
+}
+EXPORT_SYMBOL_GPL(ntmp_free_cbdr);
+
+static int ntmp_get_free_cbd_num(struct netc_cbdr *cbdr)
+{
+	return (cbdr->next_to_clean - cbdr->next_to_use - 1 +
+		cbdr->bd_num) % cbdr->bd_num;
+}
+
+static union netc_cbd *ntmp_get_cbd(struct netc_cbdr *cbdr, int index)
+{
+	return &((union netc_cbd *)(cbdr->addr_base_align))[index];
+}
+
+static void ntmp_clean_cbdr(struct netc_cbdr *cbdr)
+{
+	union netc_cbd *cbd;
+	int i;
+
+	i = cbdr->next_to_clean;
+	while (netc_read(cbdr->regs.cir) != i) {
+		cbd = ntmp_get_cbd(cbdr, i);
+		memset(cbd, 0, sizeof(*cbd));
+		i = (i + 1) % cbdr->bd_num;
+	}
+
+	cbdr->next_to_clean = i;
+}
+
+static int netc_xmit_ntmp_cmd(struct ntmp_user *user, union netc_cbd *cbd)
+{
+	union netc_cbd *cur_cbd;
+	struct netc_cbdr *cbdr;
+	int i, err;
+	u16 status;
+	u32 val;
+
+	/* Currently only i.MX95 ENETC is supported, and it only has one
+	 * command BD ring
+	 */
+	cbdr = &user->ring[0];
+
+	spin_lock_bh(&cbdr->ring_lock);
+
+	if (unlikely(!ntmp_get_free_cbd_num(cbdr)))
+		ntmp_clean_cbdr(cbdr);
+
+	i = cbdr->next_to_use;
+	cur_cbd = ntmp_get_cbd(cbdr, i);
+	*cur_cbd = *cbd;
+	dma_wmb();
+
+	/* Update producer index of both software and hardware */
+	i = (i + 1) % cbdr->bd_num;
+	cbdr->next_to_use = i;
+	netc_write(cbdr->regs.pir, i);
+
+	err = read_poll_timeout_atomic(netc_read, val, val == i,
+				       NETC_CBDR_DELAY_US, NETC_CBDR_TIMEOUT,
+				       true, cbdr->regs.cir);
+	if (unlikely(err))
+		goto cbdr_unlock;
+
+	dma_rmb();
+	/* Get the writeback command BD, because the caller may need
+	 * to check some other fields of the response header.
+	 */
+	*cbd = *cur_cbd;
+
+	/* Check the writeback error status */
+	status = le16_to_cpu(cbd->resp_hdr.error_rr) & NTMP_RESP_ERROR;
+	if (unlikely(status)) {
+		err = -EIO;
+		dev_err(user->dev, "Command BD error: 0x%04x\n", status);
+	}
+
+	ntmp_clean_cbdr(cbdr);
+	dma_wmb();
+
+cbdr_unlock:
+	spin_unlock_bh(&cbdr->ring_lock);
+
+	return err;
+}
+
+static int ntmp_alloc_data_mem(struct ntmp_dma_buf *data, void **buf_align)
+{
+	void *buf;
+
+	buf = dma_alloc_coherent(data->dev, data->size + NTMP_DATA_ADDR_ALIGN,
+				 &data->dma, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	data->buf = buf;
+	*buf_align = PTR_ALIGN(buf, NTMP_DATA_ADDR_ALIGN);
+
+	return 0;
+}
+
+static void ntmp_free_data_mem(struct ntmp_dma_buf *data)
+{
+	dma_free_coherent(data->dev, data->size + NTMP_DATA_ADDR_ALIGN,
+			  data->buf, data->dma);
+}
+
+static void ntmp_fill_request_hdr(union netc_cbd *cbd, dma_addr_t dma,
+				  int len, int table_id, int cmd,
+				  int access_method)
+{
+	dma_addr_t dma_align;
+
+	memset(cbd, 0, sizeof(*cbd));
+	dma_align = ALIGN(dma, NTMP_DATA_ADDR_ALIGN);
+	cbd->req_hdr.addr = cpu_to_le64(dma_align);
+	cbd->req_hdr.len = cpu_to_le32(len);
+	cbd->req_hdr.cmd = cmd;
+	cbd->req_hdr.access_method = FIELD_PREP(NTMP_ACCESS_METHOD,
+						access_method);
+	cbd->req_hdr.table_id = table_id;
+	cbd->req_hdr.ver_cci_rr = FIELD_PREP(NTMP_HDR_VERSION,
+					     NTMP_HDR_VER2);
+	/* For NTMP version 2.0 or later version */
+	cbd->req_hdr.npf = cpu_to_le32(NTMP_NPF);
+}
+
+static void ntmp_fill_crd(struct ntmp_cmn_req_data *crd, u8 tblv,
+			  u8 qa, u16 ua)
+{
+	crd->update_act = cpu_to_le16(ua);
+	crd->tblv_qact = NTMP_TBLV_QACT(tblv, qa);
+}
+
+static void ntmp_fill_crd_eid(struct ntmp_req_by_eid *rbe, u8 tblv,
+			      u8 qa, u16 ua, u32 entry_id)
+{
+	ntmp_fill_crd(&rbe->crd, tblv, qa, ua);
+	rbe->entry_id = cpu_to_le32(entry_id);
+}
+
+static const char *ntmp_table_name(int tbl_id)
+{
+	switch (tbl_id) {
+	case NTMP_MAFT_ID:
+		return "MAC Address Filter Table";
+	case NTMP_RSST_ID:
+		return "RSS Table";
+	default:
+		return "Unknown Table";
+	};
+}
+
+static int ntmp_delete_entry_by_id(struct ntmp_user *user, int tbl_id,
+				   u8 tbl_ver, u32 entry_id, u32 req_len,
+				   u32 resp_len)
+{
+	struct ntmp_dma_buf data = {
+		.dev = user->dev,
+		.size = max(req_len, resp_len),
+	};
+	struct ntmp_req_by_eid *req;
+	union netc_cbd cbd;
+	int err;
+
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	ntmp_fill_crd_eid(req, tbl_ver, 0, 0, entry_id);
+	ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(req_len, resp_len),
+			      tbl_id, NTMP_CMD_DELETE, NTMP_AM_ENTRY_ID);
+
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err)
+		dev_err(user->dev,
+			"Failed to delete entry 0x%x of %s, err: %pe",
+			entry_id, ntmp_table_name(tbl_id), ERR_PTR(err));
+
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+
+static int ntmp_query_entry_by_id(struct ntmp_user *user, int tbl_id,
+				  u32 len, struct ntmp_req_by_eid *req,
+				  dma_addr_t dma, bool compare_eid)
+{
+	struct ntmp_cmn_resp_query *resp;
+	int cmd = NTMP_CMD_QUERY;
+	union netc_cbd cbd;
+	u32 entry_id;
+	int err;
+
+	entry_id = le32_to_cpu(req->entry_id);
+	if (le16_to_cpu(req->crd.update_act))
+		cmd = NTMP_CMD_QU;
+
+	/* Request header */
+	ntmp_fill_request_hdr(&cbd, dma, len, tbl_id, cmd, NTMP_AM_ENTRY_ID);
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err) {
+		dev_err(user->dev,
+			"Failed to query entry 0x%x of %s, err: %pe\n",
+			entry_id, ntmp_table_name(tbl_id), ERR_PTR(err));
+		return err;
+	}
+
+	/* For a few tables, the first field of their response data is not
+	 * entry_id, so directly return success.
+	 */
+	if (!compare_eid)
+		return 0;
+
+	resp = (struct ntmp_cmn_resp_query *)req;
+	if (unlikely(le32_to_cpu(resp->entry_id) != entry_id)) {
+		dev_err(user->dev,
+			"%s: query EID 0x%x doesn't match response EID 0x%x\n",
+			ntmp_table_name(tbl_id), entry_id, le32_to_cpu(resp->entry_id));
+		return -EIO;
+	}
+
+	return 0;
+}
+
+int ntmp_maft_add_entry(struct ntmp_user *user, u32 entry_id,
+			struct maft_entry_data *maft)
+{
+	struct ntmp_dma_buf data = {
+		.dev = user->dev,
+		.size = sizeof(struct maft_req_add),
+	};
+	struct maft_req_add *req;
+	union netc_cbd cbd;
+	int err;
+
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	/* Set mac address filter table request data buffer */
+	ntmp_fill_crd_eid(&req->rbe, user->tbl.maft_ver, 0, 0, entry_id);
+	req->keye = maft->keye;
+	req->cfge = maft->cfge;
+
+	ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(data.size, 0),
+			      NTMP_MAFT_ID, NTMP_CMD_ADD, NTMP_AM_ENTRY_ID);
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err)
+		dev_err(user->dev, "Failed to add MAFT entry 0x%x, err: %pe\n",
+			entry_id, ERR_PTR(err));
+
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ntmp_maft_add_entry);
+
+int ntmp_maft_query_entry(struct ntmp_user *user, u32 entry_id,
+			  struct maft_entry_data *maft)
+{
+	struct ntmp_dma_buf data = {
+		.dev = user->dev,
+		.size = sizeof(struct maft_resp_query),
+	};
+	struct maft_resp_query *resp;
+	struct ntmp_req_by_eid *req;
+	int err;
+
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	ntmp_fill_crd_eid(req, user->tbl.maft_ver, 0, 0, entry_id);
+	err = ntmp_query_entry_by_id(user, NTMP_MAFT_ID,
+				     NTMP_LEN(sizeof(*req), data.size),
+				     req, data.dma, true);
+	if (err)
+		goto end;
+
+	resp = (struct maft_resp_query *)req;
+	maft->keye = resp->keye;
+	maft->cfge = resp->cfge;
+
+end:
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ntmp_maft_query_entry);
+
+int ntmp_maft_delete_entry(struct ntmp_user *user, u32 entry_id)
+{
+	return ntmp_delete_entry_by_id(user, NTMP_MAFT_ID, user->tbl.maft_ver,
+				       entry_id, NTMP_EID_REQ_LEN, 0);
+}
+EXPORT_SYMBOL_GPL(ntmp_maft_delete_entry);
+
+int ntmp_rsst_update_entry(struct ntmp_user *user, const u32 *table,
+			   int count)
+{
+	struct ntmp_dma_buf data = {.dev = user->dev};
+	struct rsst_req_update *req;
+	union netc_cbd cbd;
+	int err, i;
+
+	if (count != RSST_ENTRY_NUM)
+		/* HW only takes in a full 64 entry table */
+		return -EINVAL;
+
+	data.size = struct_size(req, groups, count);
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	/* Set the request data buffer */
+	ntmp_fill_crd_eid(&req->rbe, user->tbl.rsst_ver, 0,
+			  NTMP_GEN_UA_CFGEU | NTMP_GEN_UA_STSEU, 0);
+	for (i = 0; i < count; i++)
+		req->groups[i] = (u8)(table[i]);
+
+	ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(data.size, 0),
+			      NTMP_RSST_ID, NTMP_CMD_UPDATE, NTMP_AM_ENTRY_ID);
+
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err)
+		dev_err(user->dev, "Failed to update RSST entry, err: %pe\n",
+			ERR_PTR(err));
+
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ntmp_rsst_update_entry);
+
+int ntmp_rsst_query_entry(struct ntmp_user *user, u32 *table, int count)
+{
+	struct ntmp_dma_buf data = {.dev = user->dev};
+	struct ntmp_req_by_eid *req;
+	union netc_cbd cbd;
+	int err, i;
+	u8 *group;
+
+	if (count != RSST_ENTRY_NUM)
+		/* HW only takes in a full 64 entry table */
+		return -EINVAL;
+
+	data.size = NTMP_ENTRY_ID_SIZE + RSST_STSE_DATA_SIZE(count) +
+		    RSST_CFGE_DATA_SIZE(count);
+	err = ntmp_alloc_data_mem(&data, (void **)&req);
+	if (err)
+		return err;
+
+	/* Set the request data buffer */
+	ntmp_fill_crd_eid(req, user->tbl.rsst_ver, 0, 0, 0);
+	ntmp_fill_request_hdr(&cbd, data.dma, NTMP_LEN(sizeof(*req), data.size),
+			      NTMP_RSST_ID, NTMP_CMD_QUERY, NTMP_AM_ENTRY_ID);
+	err = netc_xmit_ntmp_cmd(user, &cbd);
+	if (err) {
+		dev_err(user->dev, "Failed to query RSST entry, err: %pe\n",
+			ERR_PTR(err));
+		goto end;
+	}
+
+	group = (u8 *)req;
+	group += NTMP_ENTRY_ID_SIZE + RSST_STSE_DATA_SIZE(count);
+	for (i = 0; i < count; i++)
+		table[i] = group[i];
+
+end:
+	ntmp_free_data_mem(&data);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(ntmp_rsst_query_entry);
+
+MODULE_DESCRIPTION("NXP NETC Library");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/ethernet/freescale/enetc/ntmp_private.h b/drivers/net/ethernet/freescale/enetc/ntmp_private.h
new file mode 100644
index 000000000000..685b388e7ddf
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/ntmp_private.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/*
+ * NTMP table request and response data buffer formats
+ * Copyright 2025 NXP
+ */
+
+#ifndef __NTMP_PRIVATE_H
+#define __NTMP_PRIVATE_H
+
+#include <linux/fsl/ntmp.h>
+
+#define NTMP_EID_REQ_LEN	8
+#define NETC_CBDR_BD_NUM	256
+
+union netc_cbd {
+	struct {
+		__le64 addr;
+		__le32 len;
+#define NTMP_RESP_LEN		GENMASK(19, 0)
+#define NTMP_REQ_LEN		GENMASK(31, 20)
+#define NTMP_LEN(req, resp)	(FIELD_PREP(NTMP_REQ_LEN, (req)) | \
+				((resp) & NTMP_RESP_LEN))
+		u8 cmd;
+#define NTMP_CMD_DELETE		BIT(0)
+#define NTMP_CMD_UPDATE		BIT(1)
+#define NTMP_CMD_QUERY		BIT(2)
+#define NTMP_CMD_ADD		BIT(3)
+#define NTMP_CMD_QU		(NTMP_CMD_QUERY | NTMP_CMD_UPDATE)
+		u8 access_method;
+#define NTMP_ACCESS_METHOD	GENMASK(7, 4)
+#define NTMP_AM_ENTRY_ID	0
+#define NTMP_AM_EXACT_KEY	1
+#define NTMP_AM_SEARCH		2
+#define NTMP_AM_TERNARY_KEY	3
+		u8 table_id;
+		u8 ver_cci_rr;
+#define NTMP_HDR_VERSION	GENMASK(5, 0)
+#define NTMP_HDR_VER2		2
+#define NTMP_CCI		BIT(6)
+#define NTMP_RR			BIT(7)
+		__le32 resv[3];
+		__le32 npf;
+#define NTMP_NPF		BIT(15)
+	} req_hdr;	/* NTMP Request Message Header Format */
+
+	struct {
+		__le32 resv0[3];
+		__le16 num_matched;
+		__le16 error_rr;
+#define NTMP_RESP_ERROR		GENMASK(11, 0)
+#define NTMP_RESP_RR		BIT(15)
+		__le32 resv1[4];
+	} resp_hdr; /* NTMP Response Message Header Format */
+};
+
+struct ntmp_dma_buf {
+	struct device *dev;
+	size_t size;
+	void *buf;
+	dma_addr_t dma;
+};
+
+struct ntmp_cmn_req_data {
+	__le16 update_act;
+	u8 dbg_opt;
+	u8 tblv_qact;
+#define NTMP_QUERY_ACT		GENMASK(3, 0)
+#define NTMP_TBL_VER		GENMASK(7, 4)
+#define NTMP_TBLV_QACT(v, a)	(FIELD_PREP(NTMP_TBL_VER, (v)) | \
+				 ((a) & NTMP_QUERY_ACT))
+};
+
+struct ntmp_cmn_resp_query {
+	__le32 entry_id;
+};
+
+/* Generic structure for request data by entry ID  */
+struct ntmp_req_by_eid {
+	struct ntmp_cmn_req_data crd;
+	__le32 entry_id;
+};
+
+/* MAC Address Filter Table Request Data Buffer Format of Add action */
+struct maft_req_add {
+	struct ntmp_req_by_eid rbe;
+	struct maft_keye_data keye;
+	struct maft_cfge_data cfge;
+};
+
+/* MAC Address Filter Table Response Data Buffer Format of Query action */
+struct maft_resp_query {
+	__le32 entry_id;
+	struct maft_keye_data keye;
+	struct maft_cfge_data cfge;
+};
+
+/* RSS Table Request Data Buffer Format of Update action */
+struct rsst_req_update {
+	struct ntmp_req_by_eid rbe;
+	u8 groups[];
+};
+
+#endif
diff --git a/include/linux/fsl/ntmp.h b/include/linux/fsl/ntmp.h
new file mode 100644
index 000000000000..916dc4fe7de3
--- /dev/null
+++ b/include/linux/fsl/ntmp.h
@@ -0,0 +1,121 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2025 NXP */
+#ifndef __NETC_NTMP_H
+#define __NETC_NTMP_H
+
+#include <linux/bitops.h>
+#include <linux/if_ether.h>
+
+struct maft_keye_data {
+	u8 mac_addr[ETH_ALEN];
+	__le16 resv;
+};
+
+struct maft_cfge_data {
+	__le16 si_bitmap;
+	__le16 resv;
+};
+
+struct netc_cbdr_regs {
+	void __iomem *pir;
+	void __iomem *cir;
+	void __iomem *mr;
+
+	void __iomem *bar0;
+	void __iomem *bar1;
+	void __iomem *lenr;
+};
+
+struct netc_tbl_vers {
+	u8 maft_ver;
+	u8 rsst_ver;
+};
+
+struct netc_cbdr {
+	struct device *dev;
+	struct netc_cbdr_regs regs;
+
+	int bd_num;
+	int next_to_use;
+	int next_to_clean;
+
+	int dma_size;
+	void *addr_base;
+	void *addr_base_align;
+	dma_addr_t dma_base;
+	dma_addr_t dma_base_align;
+
+	/* Serialize the order of command BD ring */
+	spinlock_t ring_lock;
+};
+
+struct ntmp_user {
+	int cbdr_num;	/* number of control BD ring */
+	struct device *dev;
+	struct netc_cbdr *ring;
+	struct netc_tbl_vers tbl;
+};
+
+struct maft_entry_data {
+	struct maft_keye_data keye;
+	struct maft_cfge_data cfge;
+};
+
+#if IS_ENABLED(CONFIG_NXP_NETC_LIB)
+int ntmp_init_cbdr(struct netc_cbdr *cbdr, struct device *dev,
+		   const struct netc_cbdr_regs *regs);
+void ntmp_free_cbdr(struct netc_cbdr *cbdr);
+
+/* NTMP APIs */
+int ntmp_maft_add_entry(struct ntmp_user *user, u32 entry_id,
+			struct maft_entry_data *maft);
+int ntmp_maft_query_entry(struct ntmp_user *user, u32 entry_id,
+			  struct maft_entry_data *maft);
+int ntmp_maft_delete_entry(struct ntmp_user *user, u32 entry_id);
+int ntmp_rsst_update_entry(struct ntmp_user *user, const u32 *table,
+			   int count);
+int ntmp_rsst_query_entry(struct ntmp_user *user,
+			  u32 *table, int count);
+#else
+static inline int ntmp_init_cbdr(struct netc_cbdr *cbdr, struct device *dev,
+				 const struct netc_cbdr_regs *regs)
+{
+	return 0;
+}
+
+static inline void ntmp_free_cbdr(struct netc_cbdr *cbdr)
+{
+}
+
+static inline int ntmp_maft_add_entry(struct ntmp_user *user, u32 entry_id,
+				      struct maft_entry_data *maft)
+{
+	return 0;
+}
+
+static inline int ntmp_maft_query_entry(struct ntmp_user *user, u32 entry_id,
+					struct maft_entry_data *maft)
+{
+	return 0;
+}
+
+static inline int ntmp_maft_delete_entry(struct ntmp_user *user, u32 entry_id)
+{
+	return 0;
+}
+
+static inline int ntmp_rsst_update_entry(struct ntmp_user *user,
+					 const u32 *table, int count)
+{
+	return 0;
+}
+
+static inline int ntmp_rsst_query_entry(struct ntmp_user *user,
+					u32 *table, int count)
+{
+	return 0;
+}
+
+#endif
+
+#endif
-- 
2.51.0


From e3f4a0a8ddb41962efa51c6353e869b90d183e68 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Tue, 6 May 2025 16:07:23 +0800
Subject: [PATCH 14/16] net: enetc: add command BD ring support for i.MX95
 ENETC

The command BD ring is used to configure functionality where the
underlying resources may be shared between different entities or being
too large to configure using direct registers (such as lookup tables).

Because the command BD and table formats of i.MX95 and LS1028A are very
different, the software processing logic is also different. So add
enetc4_setup_cbdr() and enetc4_teardown_cbdr() for ENETC v4 drivers.

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250506080735.3444381-3-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.h  |  9 ++++-
 .../net/ethernet/freescale/enetc/enetc4_pf.c  | 39 ++++++++++++++++++-
 .../net/ethernet/freescale/enetc/enetc_cbdr.c | 38 ++++++++++++++++++
 3 files changed, 84 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 4ad4eb5c5a74..384e0bded87f 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -8,6 +8,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/skbuff.h>
 #include <linux/ethtool.h>
+#include <linux/fsl/ntmp.h>
 #include <linux/if_vlan.h>
 #include <linux/phylink.h>
 #include <linux/dim.h>
@@ -274,7 +275,10 @@ struct enetc_si {
 
 	struct net_device *ndev; /* back ref. */
 
-	struct enetc_cbdr cbd_ring;
+	union {
+		struct enetc_cbdr cbd_ring; /* Only ENETC 1.0 */
+		struct ntmp_user ntmp_user; /* ENETC 4.1 and later */
+	};
 
 	int num_rx_rings; /* how many rings are available in the SI */
 	int num_tx_rings;
@@ -284,6 +288,7 @@ struct enetc_si {
 	u16 revision;
 	int hw_features;
 	const struct enetc_drvdata *drvdata;
+	const struct enetc_si_ops *ops;
 };
 
 #define ENETC_SI_ALIGN	32
@@ -493,6 +498,8 @@ void enetc_mm_commit_preemptible_tcs(struct enetc_ndev_priv *priv);
 int enetc_setup_cbdr(struct device *dev, struct enetc_hw *hw, int bd_count,
 		     struct enetc_cbdr *cbdr);
 void enetc_teardown_cbdr(struct enetc_cbdr *cbdr);
+int enetc4_setup_cbdr(struct enetc_si *si);
+void enetc4_teardown_cbdr(struct enetc_si *si);
 int enetc_set_mac_flt_entry(struct enetc_si *si, int index,
 			    char *mac_addr, int si_map);
 int enetc_clear_mac_flt_entry(struct enetc_si *si, int index);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index 73ac8c6afb3a..175eebadde76 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -260,6 +260,21 @@ static void enetc4_configure_port(struct enetc_pf *pf)
 	enetc4_enable_trx(pf);
 }
 
+static int enetc4_init_ntmp_user(struct enetc_si *si)
+{
+	struct ntmp_user *user = &si->ntmp_user;
+
+	/* For ENETC 4.1, all table versions are 0 */
+	memset(&user->tbl, 0, sizeof(user->tbl));
+
+	return enetc4_setup_cbdr(si);
+}
+
+static void enetc4_free_ntmp_user(struct enetc_si *si)
+{
+	enetc4_teardown_cbdr(si);
+}
+
 static int enetc4_pf_init(struct enetc_pf *pf)
 {
 	struct device *dev = &pf->si->pdev->dev;
@@ -272,11 +287,22 @@ static int enetc4_pf_init(struct enetc_pf *pf)
 		return err;
 	}
 
+	err = enetc4_init_ntmp_user(pf->si);
+	if (err) {
+		dev_err(dev, "Failed to init CBDR\n");
+		return err;
+	}
+
 	enetc4_configure_port(pf);
 
 	return 0;
 }
 
+static void enetc4_pf_free(struct enetc_pf *pf)
+{
+	enetc4_free_ntmp_user(pf->si);
+}
+
 static const struct net_device_ops enetc4_ndev_ops = {
 	.ndo_open		= enetc_open,
 	.ndo_stop		= enetc_close,
@@ -728,14 +754,25 @@ static int enetc4_pf_probe(struct pci_dev *pdev,
 
 	enetc_get_si_caps(si);
 
-	return enetc4_pf_netdev_create(si);
+	err = enetc4_pf_netdev_create(si);
+	if (err)
+		goto err_netdev_create;
+
+	return 0;
+
+err_netdev_create:
+	enetc4_pf_free(pf);
+
+	return err;
 }
 
 static void enetc4_pf_remove(struct pci_dev *pdev)
 {
 	struct enetc_si *si = pci_get_drvdata(pdev);
+	struct enetc_pf *pf = enetc_si_priv(si);
 
 	enetc4_pf_netdev_destroy(si);
+	enetc4_pf_free(pf);
 }
 
 static const struct pci_device_id enetc4_pf_id_table[] = {
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c
index 20bfdf7fb4b4..71e4da530028 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c
@@ -60,6 +60,44 @@ void enetc_teardown_cbdr(struct enetc_cbdr *cbdr)
 }
 EXPORT_SYMBOL_GPL(enetc_teardown_cbdr);
 
+int enetc4_setup_cbdr(struct enetc_si *si)
+{
+	struct ntmp_user *user = &si->ntmp_user;
+	struct device *dev = &si->pdev->dev;
+	struct enetc_hw *hw = &si->hw;
+	struct netc_cbdr_regs regs;
+
+	user->cbdr_num = 1;
+	user->dev = dev;
+	user->ring = devm_kcalloc(dev, user->cbdr_num,
+				  sizeof(struct netc_cbdr), GFP_KERNEL);
+	if (!user->ring)
+		return -ENOMEM;
+
+	/* set CBDR cache attributes */
+	enetc_wr(hw, ENETC_SICAR2,
+		 ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT);
+
+	regs.pir = hw->reg + ENETC_SICBDRPIR;
+	regs.cir = hw->reg + ENETC_SICBDRCIR;
+	regs.mr = hw->reg + ENETC_SICBDRMR;
+	regs.bar0 = hw->reg + ENETC_SICBDRBAR0;
+	regs.bar1 = hw->reg + ENETC_SICBDRBAR1;
+	regs.lenr = hw->reg + ENETC_SICBDRLENR;
+
+	return ntmp_init_cbdr(user->ring, dev, &regs);
+}
+EXPORT_SYMBOL_GPL(enetc4_setup_cbdr);
+
+void enetc4_teardown_cbdr(struct enetc_si *si)
+{
+	struct ntmp_user *user = &si->ntmp_user;
+
+	ntmp_free_cbdr(user->ring);
+	user->dev = NULL;
+}
+EXPORT_SYMBOL_GPL(enetc4_teardown_cbdr);
+
 static void enetc_clean_cbdr(struct enetc_cbdr *ring)
 {
 	struct enetc_cbd *dest_cbd;
-- 
2.51.0


From 401dbdd1c23c82e5eb57121bc837cd7731dbebe8 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Tue, 6 May 2025 16:07:24 +0800
Subject: [PATCH 15/16] net: enetc: move generic MAC filtering interfaces to
 enetc-core

Although only ENETC PF can access the MAC address filter table, the table
entries can specify MAC address filtering for one or more SIs based on
SI_BITMAP, which means that the table also supports MAC address filtering
for VFs.

Currently, only the ENETC v1 PF driver supports MAC address filtering. In
order to add the MAC address filtering support for the ENETC v4 PF driver
and VF driver in the future, the relevant generic interfaces are moved to
the enetc-core driver. This lays the basis for i.MX95 ENETC PF and VFs to
support MAC address filtering.

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250506080735.3444381-4-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c  | 36 +++++++++++++++++++
 drivers/net/ethernet/freescale/enetc/enetc.h  | 15 ++++++++
 .../net/ethernet/freescale/enetc/enetc_pf.c   | 34 ------------------
 .../net/ethernet/freescale/enetc/enetc_pf.h   | 11 ------
 4 files changed, 51 insertions(+), 45 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 3ee52f4b1166..5a7af44e4594 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -36,6 +36,42 @@ static void enetc_change_preemptible_tcs(struct enetc_ndev_priv *priv,
 	enetc_mm_commit_preemptible_tcs(priv);
 }
 
+static int enetc_mac_addr_hash_idx(const u8 *addr)
+{
+	u64 fold = __swab64(ether_addr_to_u64(addr)) >> 16;
+	u64 mask = 0;
+	int res = 0;
+	int i;
+
+	for (i = 0; i < 8; i++)
+		mask |= BIT_ULL(i * 6);
+
+	for (i = 0; i < 6; i++)
+		res |= (hweight64(fold & (mask << i)) & 0x1) << i;
+
+	return res;
+}
+
+void enetc_add_mac_addr_ht_filter(struct enetc_mac_filter *filter,
+				  const unsigned char *addr)
+{
+	int idx = enetc_mac_addr_hash_idx(addr);
+
+	/* add hash table entry */
+	__set_bit(idx, filter->mac_hash_table);
+	filter->mac_addr_cnt++;
+}
+EXPORT_SYMBOL_GPL(enetc_add_mac_addr_ht_filter);
+
+void enetc_reset_mac_addr_filter(struct enetc_mac_filter *filter)
+{
+	filter->mac_addr_cnt = 0;
+
+	bitmap_zero(filter->mac_hash_table,
+		    ENETC_MADDR_HASH_TBL_SZ);
+}
+EXPORT_SYMBOL_GPL(enetc_reset_mac_addr_filter);
+
 static int enetc_num_stack_tx_queues(struct enetc_ndev_priv *priv)
 {
 	int num_tx_rings = priv->num_tx_rings;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index 384e0bded87f..c3ebb32ce50c 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -23,6 +23,18 @@
 
 #define ENETC_CBD_DATA_MEM_ALIGN 64
 
+#define ENETC_MADDR_HASH_TBL_SZ	64
+
+enum enetc_mac_addr_type {UC, MC, MADDR_TYPE};
+
+struct enetc_mac_filter {
+	union {
+		char mac_addr[ETH_ALEN];
+		DECLARE_BITMAP(mac_hash_table, ENETC_MADDR_HASH_TBL_SZ);
+	};
+	int mac_addr_cnt;
+};
+
 struct enetc_tx_swbd {
 	union {
 		struct sk_buff *skb;
@@ -471,6 +483,9 @@ int enetc_alloc_si_resources(struct enetc_ndev_priv *priv);
 void enetc_free_si_resources(struct enetc_ndev_priv *priv);
 int enetc_configure_si(struct enetc_ndev_priv *priv);
 int enetc_get_driver_data(struct enetc_si *si);
+void enetc_add_mac_addr_ht_filter(struct enetc_mac_filter *filter,
+				  const unsigned char *addr);
+void enetc_reset_mac_addr_filter(struct enetc_mac_filter *filter);
 
 int enetc_open(struct net_device *ndev);
 int enetc_close(struct net_device *ndev);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 203862ec1114..f76403f7aee8 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -72,30 +72,6 @@ static void enetc_set_isol_vlan(struct enetc_hw *hw, int si, u16 vlan, u8 qos)
 	enetc_port_wr(hw, ENETC_PSIVLANR(si), val);
 }
 
-static int enetc_mac_addr_hash_idx(const u8 *addr)
-{
-	u64 fold = __swab64(ether_addr_to_u64(addr)) >> 16;
-	u64 mask = 0;
-	int res = 0;
-	int i;
-
-	for (i = 0; i < 8; i++)
-		mask |= BIT_ULL(i * 6);
-
-	for (i = 0; i < 6; i++)
-		res |= (hweight64(fold & (mask << i)) & 0x1) << i;
-
-	return res;
-}
-
-static void enetc_reset_mac_addr_filter(struct enetc_mac_filter *filter)
-{
-	filter->mac_addr_cnt = 0;
-
-	bitmap_zero(filter->mac_hash_table,
-		    ENETC_MADDR_HASH_TBL_SZ);
-}
-
 static void enetc_add_mac_addr_em_filter(struct enetc_mac_filter *filter,
 					 const unsigned char *addr)
 {
@@ -104,16 +80,6 @@ static void enetc_add_mac_addr_em_filter(struct enetc_mac_filter *filter,
 	filter->mac_addr_cnt++;
 }
 
-static void enetc_add_mac_addr_ht_filter(struct enetc_mac_filter *filter,
-					 const unsigned char *addr)
-{
-	int idx = enetc_mac_addr_hash_idx(addr);
-
-	/* add hash table entry */
-	__set_bit(idx, filter->mac_hash_table);
-	filter->mac_addr_cnt++;
-}
-
 static void enetc_clear_mac_ht_flt(struct enetc_si *si, int si_idx, int type)
 {
 	bool err = si->errata & ENETC_ERR_UCMCSWP;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.h b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
index a26a12863855..a8b3c8d14254 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
@@ -5,19 +5,8 @@
 #include <linux/phylink.h>
 
 #define ENETC_PF_NUM_RINGS	8
-
-enum enetc_mac_addr_type {UC, MC, MADDR_TYPE};
 #define ENETC_MAX_NUM_MAC_FLT	((ENETC_MAX_NUM_VFS + 1) * MADDR_TYPE)
 
-#define ENETC_MADDR_HASH_TBL_SZ	64
-struct enetc_mac_filter {
-	union {
-		char mac_addr[ETH_ALEN];
-		DECLARE_BITMAP(mac_hash_table, ENETC_MADDR_HASH_TBL_SZ);
-	};
-	int mac_addr_cnt;
-};
-
 #define ENETC_VLAN_HT_SIZE	64
 
 enum enetc_vf_flags {
-- 
2.51.0


From 6c5bafba347b0e080cae15a73fae67fa79975c97 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Tue, 6 May 2025 16:07:25 +0800
Subject: [PATCH 16/16] net: enetc: add MAC filtering for i.MX95 ENETC PF

The i.MX95 ENETC supports both MAC hash filter and MAC exact filter. MAC
hash filter is implenented through a 64-bit hash table to match against
the hashed addresses, PF and VFs each have two MAC hash tables, one is
for unicast and the other one is for multicast. But MAC exact filter is
shared between SIs (PF and VFs), each table entry contains a MAC address
that may be unicast or multicast and the entry also contains an SI bitmap
field that indicates for which SIs the entry is valid.

For i.MX95 ENETC, MAC exact filter only has 4 entries. According to the
observation of the system default network configuration, the MAC filter
will be configured with multiple multicast addresses, so MAC exact filter
does not have enough entries to implement multicast filtering. Therefore,
the current MAC exact filter is only used for unicast filtering. If the
number of unicast addresses exceeds 4, then MAC hash filter is used.

Note that both MAC hash filter and MAC exact filter can only be accessed
by PF, VFs can notify PF to set its corresponding MAC filter through the
mailbox mechanism of ENETC. But currently MAC filter is only added for
i.MX95 ENETC PF. The MAC filter support of ENETC VFs will be supported in
subsequent patches.

Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250506080735.3444381-5-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.h  |   3 +
 .../net/ethernet/freescale/enetc/enetc4_hw.h  |   8 +
 .../net/ethernet/freescale/enetc/enetc4_pf.c  | 260 ++++++++++++++++++
 .../net/ethernet/freescale/enetc/enetc_pf.h   |   3 +
 4 files changed, 274 insertions(+)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index c3ebb32ce50c..1573ff06fcf4 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -301,6 +301,9 @@ struct enetc_si {
 	int hw_features;
 	const struct enetc_drvdata *drvdata;
 	const struct enetc_si_ops *ops;
+
+	struct workqueue_struct *workqueue;
+	struct work_struct rx_mode_task;
 };
 
 #define ENETC_SI_ALIGN	32
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
index 695cb07c74bc..826359004850 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
@@ -99,6 +99,14 @@
 #define ENETC4_PSICFGR2(a)		((a) * 0x80 + 0x2018)
 #define  PSICFGR2_NUM_MSIX		GENMASK(5, 0)
 
+/* Port station interface a unicast MAC hash filter register 0/1 */
+#define ENETC4_PSIUMHFR0(a)		((a) * 0x80 + 0x2050)
+#define ENETC4_PSIUMHFR1(a)		((a) * 0x80 + 0x2054)
+
+/* Port station interface a multicast MAC hash filter register 0/1 */
+#define ENETC4_PSIMMHFR0(a)		((a) * 0x80 + 0x2058)
+#define ENETC4_PSIMMHFR1(a)		((a) * 0x80 + 0x205c)
+
 #define ENETC4_PMCAPR			0x4004
 #define  PMCAPR_HD			BIT(8)
 #define  PMCAPR_FP			GENMASK(10, 9)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index 175eebadde76..7b801f6e9a31 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -11,6 +11,15 @@
 
 #define ENETC_SI_MAX_RING_NUM	8
 
+#define ENETC_MAC_FILTER_TYPE_UC	BIT(0)
+#define ENETC_MAC_FILTER_TYPE_MC	BIT(1)
+#define ENETC_MAC_FILTER_TYPE_ALL	(ENETC_MAC_FILTER_TYPE_UC | \
+					 ENETC_MAC_FILTER_TYPE_MC)
+
+struct enetc_mac_addr {
+	u8 addr[ETH_ALEN];
+};
+
 static void enetc4_get_port_caps(struct enetc_pf *pf)
 {
 	struct enetc_hw *hw = &pf->si->hw;
@@ -26,6 +35,9 @@ static void enetc4_get_port_caps(struct enetc_pf *pf)
 
 	val = enetc_port_rd(hw, ENETC4_PMCAPR);
 	pf->caps.half_duplex = (val & PMCAPR_HD) ? 1 : 0;
+
+	val = enetc_port_rd(hw, ENETC4_PSIMAFCAPR);
+	pf->caps.mac_filter_num = val & PSIMAFCAPR_NUM_MAC_AFTE;
 }
 
 static void enetc4_pf_set_si_primary_mac(struct enetc_hw *hw, int si,
@@ -56,6 +68,185 @@ static void enetc4_pf_get_si_primary_mac(struct enetc_hw *hw, int si,
 	put_unaligned_le16(lower, addr + 4);
 }
 
+static void enetc4_pf_set_si_mac_promisc(struct enetc_hw *hw, int si,
+					 bool uc_promisc, bool mc_promisc)
+{
+	u32 val = enetc_port_rd(hw, ENETC4_PSIPMMR);
+
+	if (uc_promisc)
+		val |= PSIPMMR_SI_MAC_UP(si);
+	else
+		val &= ~PSIPMMR_SI_MAC_UP(si);
+
+	if (mc_promisc)
+		val |= PSIPMMR_SI_MAC_MP(si);
+	else
+		val &= ~PSIPMMR_SI_MAC_MP(si);
+
+	enetc_port_wr(hw, ENETC4_PSIPMMR, val);
+}
+
+static void enetc4_pf_set_si_uc_hash_filter(struct enetc_hw *hw, int si,
+					    u64 hash)
+{
+	enetc_port_wr(hw, ENETC4_PSIUMHFR0(si), lower_32_bits(hash));
+	enetc_port_wr(hw, ENETC4_PSIUMHFR1(si), upper_32_bits(hash));
+}
+
+static void enetc4_pf_set_si_mc_hash_filter(struct enetc_hw *hw, int si,
+					    u64 hash)
+{
+	enetc_port_wr(hw, ENETC4_PSIMMHFR0(si), lower_32_bits(hash));
+	enetc_port_wr(hw, ENETC4_PSIMMHFR1(si), upper_32_bits(hash));
+}
+
+static void enetc4_pf_clear_maft_entries(struct enetc_pf *pf)
+{
+	int i;
+
+	for (i = 0; i < pf->num_mfe; i++)
+		ntmp_maft_delete_entry(&pf->si->ntmp_user, i);
+
+	pf->num_mfe = 0;
+}
+
+static int enetc4_pf_add_maft_entries(struct enetc_pf *pf,
+				      struct enetc_mac_addr *mac,
+				      int mac_cnt)
+{
+	struct maft_entry_data maft = {};
+	u16 si_bit = BIT(0);
+	int i, err;
+
+	maft.cfge.si_bitmap = cpu_to_le16(si_bit);
+	for (i = 0; i < mac_cnt; i++) {
+		ether_addr_copy(maft.keye.mac_addr, mac[i].addr);
+		err = ntmp_maft_add_entry(&pf->si->ntmp_user, i, &maft);
+		if (unlikely(err)) {
+			pf->num_mfe = i;
+			goto clear_maft_entries;
+		}
+	}
+
+	pf->num_mfe = mac_cnt;
+
+	return 0;
+
+clear_maft_entries:
+	enetc4_pf_clear_maft_entries(pf);
+
+	return  err;
+}
+
+static int enetc4_pf_set_uc_exact_filter(struct enetc_pf *pf)
+{
+	int max_num_mfe = pf->caps.mac_filter_num;
+	struct enetc_mac_filter mac_filter = {};
+	struct net_device *ndev = pf->si->ndev;
+	struct enetc_hw *hw = &pf->si->hw;
+	struct enetc_mac_addr *mac_tbl;
+	struct netdev_hw_addr *ha;
+	int i = 0, err;
+	int mac_cnt;
+
+	netif_addr_lock_bh(ndev);
+
+	mac_cnt = netdev_uc_count(ndev);
+	if (!mac_cnt) {
+		netif_addr_unlock_bh(ndev);
+		/* clear both MAC hash and exact filters */
+		enetc4_pf_set_si_uc_hash_filter(hw, 0, 0);
+		enetc4_pf_clear_maft_entries(pf);
+
+		return 0;
+	}
+
+	if (mac_cnt > max_num_mfe) {
+		err = -ENOSPC;
+		goto unlock_netif_addr;
+	}
+
+	mac_tbl = kcalloc(mac_cnt, sizeof(*mac_tbl), GFP_ATOMIC);
+	if (!mac_tbl) {
+		err = -ENOMEM;
+		goto unlock_netif_addr;
+	}
+
+	netdev_for_each_uc_addr(ha, ndev) {
+		enetc_add_mac_addr_ht_filter(&mac_filter, ha->addr);
+		ether_addr_copy(mac_tbl[i++].addr, ha->addr);
+	}
+
+	netif_addr_unlock_bh(ndev);
+
+	/* Set temporary unicast hash filters in case of Rx loss when
+	 * updating MAC address filter table
+	 */
+	enetc4_pf_set_si_uc_hash_filter(hw, 0, *mac_filter.mac_hash_table);
+	enetc4_pf_clear_maft_entries(pf);
+
+	if (!enetc4_pf_add_maft_entries(pf, mac_tbl, i))
+		enetc4_pf_set_si_uc_hash_filter(hw, 0, 0);
+
+	kfree(mac_tbl);
+
+	return 0;
+
+unlock_netif_addr:
+	netif_addr_unlock_bh(ndev);
+
+	return err;
+}
+
+static void enetc4_pf_set_mac_hash_filter(struct enetc_pf *pf, int type)
+{
+	struct net_device *ndev = pf->si->ndev;
+	struct enetc_mac_filter *mac_filter;
+	struct enetc_hw *hw = &pf->si->hw;
+	struct netdev_hw_addr *ha;
+
+	netif_addr_lock_bh(ndev);
+	if (type & ENETC_MAC_FILTER_TYPE_UC) {
+		mac_filter = &pf->mac_filter[UC];
+		enetc_reset_mac_addr_filter(mac_filter);
+		netdev_for_each_uc_addr(ha, ndev)
+			enetc_add_mac_addr_ht_filter(mac_filter, ha->addr);
+
+		enetc4_pf_set_si_uc_hash_filter(hw, 0,
+						*mac_filter->mac_hash_table);
+	}
+
+	if (type & ENETC_MAC_FILTER_TYPE_MC) {
+		mac_filter = &pf->mac_filter[MC];
+		enetc_reset_mac_addr_filter(mac_filter);
+		netdev_for_each_mc_addr(ha, ndev)
+			enetc_add_mac_addr_ht_filter(mac_filter, ha->addr);
+
+		enetc4_pf_set_si_mc_hash_filter(hw, 0,
+						*mac_filter->mac_hash_table);
+	}
+	netif_addr_unlock_bh(ndev);
+}
+
+static void enetc4_pf_set_mac_filter(struct enetc_pf *pf, int type)
+{
+	/* Currently, the MAC address filter table (MAFT) only has 4 entries,
+	 * and multiple multicast addresses for filtering will be configured
+	 * in the default network configuration, so MAFT is only suitable for
+	 * unicast filtering. If the number of unicast addresses exceeds the
+	 * table capacity, the MAC hash filter will be used.
+	 */
+	if (type & ENETC_MAC_FILTER_TYPE_UC && enetc4_pf_set_uc_exact_filter(pf)) {
+		/* Fall back to the MAC hash filter */
+		enetc4_pf_set_mac_hash_filter(pf, ENETC_MAC_FILTER_TYPE_UC);
+		/* Clear the old MAC exact filter */
+		enetc4_pf_clear_maft_entries(pf);
+	}
+
+	if (type & ENETC_MAC_FILTER_TYPE_MC)
+		enetc4_pf_set_mac_hash_filter(pf, ENETC_MAC_FILTER_TYPE_MC);
+}
+
 static const struct enetc_pf_ops enetc4_pf_ops = {
 	.set_si_primary_mac = enetc4_pf_set_si_primary_mac,
 	.get_si_primary_mac = enetc4_pf_get_si_primary_mac,
@@ -303,12 +494,59 @@ static void enetc4_pf_free(struct enetc_pf *pf)
 	enetc4_free_ntmp_user(pf->si);
 }
 
+static void enetc4_psi_do_set_rx_mode(struct work_struct *work)
+{
+	struct enetc_si *si = container_of(work, struct enetc_si, rx_mode_task);
+	struct enetc_pf *pf = enetc_si_priv(si);
+	struct net_device *ndev = si->ndev;
+	struct enetc_hw *hw = &si->hw;
+	bool uc_promisc = false;
+	bool mc_promisc = false;
+	int type = 0;
+
+	rtnl_lock();
+
+	if (ndev->flags & IFF_PROMISC) {
+		uc_promisc = true;
+		mc_promisc = true;
+	} else if (ndev->flags & IFF_ALLMULTI) {
+		mc_promisc = true;
+		type = ENETC_MAC_FILTER_TYPE_UC;
+	} else {
+		type = ENETC_MAC_FILTER_TYPE_ALL;
+	}
+
+	enetc4_pf_set_si_mac_promisc(hw, 0, uc_promisc, mc_promisc);
+
+	if (uc_promisc) {
+		enetc4_pf_set_si_uc_hash_filter(hw, 0, 0);
+		enetc4_pf_clear_maft_entries(pf);
+	}
+
+	if (mc_promisc)
+		enetc4_pf_set_si_mc_hash_filter(hw, 0, 0);
+
+	/* Set new MAC filter */
+	enetc4_pf_set_mac_filter(pf, type);
+
+	rtnl_unlock();
+}
+
+static void enetc4_pf_set_rx_mode(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_si *si = priv->si;
+
+	queue_work(si->workqueue, &si->rx_mode_task);
+}
+
 static const struct net_device_ops enetc4_ndev_ops = {
 	.ndo_open		= enetc_open,
 	.ndo_stop		= enetc_close,
 	.ndo_start_xmit		= enetc_xmit,
 	.ndo_get_stats		= enetc_get_stats,
 	.ndo_set_mac_address	= enetc_pf_set_mac_addr,
+	.ndo_set_rx_mode	= enetc4_pf_set_rx_mode,
 };
 
 static struct phylink_pcs *
@@ -643,6 +881,19 @@ static void enetc4_link_deinit(struct enetc_ndev_priv *priv)
 	enetc_mdiobus_destroy(pf);
 }
 
+static int enetc4_psi_wq_task_init(struct enetc_si *si)
+{
+	char wq_name[24];
+
+	INIT_WORK(&si->rx_mode_task, enetc4_psi_do_set_rx_mode);
+	snprintf(wq_name, sizeof(wq_name), "enetc-%s", pci_name(si->pdev));
+	si->workqueue = create_singlethread_workqueue(wq_name);
+	if (!si->workqueue)
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int enetc4_pf_netdev_create(struct enetc_si *si)
 {
 	struct device *dev = &si->pdev->dev;
@@ -683,6 +934,12 @@ static int enetc4_pf_netdev_create(struct enetc_si *si)
 	if (err)
 		goto err_link_init;
 
+	err = enetc4_psi_wq_task_init(si);
+	if (err) {
+		dev_err(dev, "Failed to init workqueue\n");
+		goto err_wq_init;
+	}
+
 	err = register_netdev(ndev);
 	if (err) {
 		dev_err(dev, "Failed to register netdev\n");
@@ -693,6 +950,7 @@ static int enetc4_pf_netdev_create(struct enetc_si *si)
 
 err_reg_netdev:
 	enetc4_link_deinit(priv);
+err_wq_init:
 err_link_init:
 	enetc_free_msix(priv);
 err_alloc_msix:
@@ -709,6 +967,8 @@ static void enetc4_pf_netdev_destroy(struct enetc_si *si)
 	struct net_device *ndev = si->ndev;
 
 	unregister_netdev(ndev);
+	cancel_work(&si->rx_mode_task);
+	destroy_workqueue(si->workqueue);
 	enetc4_link_deinit(priv);
 	enetc_free_msix(priv);
 	free_netdev(ndev);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.h b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
index a8b3c8d14254..ae407e9e9ee7 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
@@ -23,6 +23,7 @@ struct enetc_port_caps {
 	int num_msix;
 	int num_rx_bdr;
 	int num_tx_bdr;
+	int mac_filter_num;
 };
 
 struct enetc_pf;
@@ -60,6 +61,8 @@ struct enetc_pf {
 
 	struct enetc_port_caps caps;
 	const struct enetc_pf_ops *ops;
+
+	int num_mfe;	/* number of mac address filter table entries */
 };
 
 #define phylink_to_enetc_pf(config) \
-- 
2.51.0