[PATCH 0/4] net/bnxt: miscellaneous bug fixes

[PATCH 0/4] net/bnxt: miscellaneous bug fixes

[Mohammad Shuab Siddique]

From: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>

This series collects four independent bug fixes for the bnxt PMD:

 - Eliminate unnecessary long TX BDs when only checksum offload is needed
 - Pass QP1 resource count correctly when configuring backing store
 - Fix implicit integer sign-extension in the doorbell calculation
 - Prevent VFs from attempting global RSS configuration

All patches carry Fixes: tags and Cc: stable@dpdk.org.

Ajit Khaparde (2):
  net/bnxt: modify check for short Tx BDs
  net/bnxt: fix QP resource count in backing store config

Mohammad Shuab Siddique (1):
  net/bnxt: fix RSS hash mode configuration for VFs

Zoe Cheimets (1):
  net/bnxt: remove implicit integer sign-extension

 drivers/net/bnxt/bnxt_ethdev.c |  4 ++--
 drivers/net/bnxt/bnxt_hwrm.c   | 18 ++++++++++++++++--
 drivers/net/bnxt/bnxt_ring.c   |  7 ++++---
 drivers/net/bnxt/bnxt_txr.c    |  3 +--
 4 files changed, 23 insertions(+), 9 deletions(-)

-- 
2.47.3

[PATCH 1/4] net/bnxt: modify check for short Tx BDs

[Mohammad Shuab Siddique]

From: Ajit Khaparde <ajit.khaparde@broadcom.com>

There is no need to use the long BDs for transmits
where only checksum offload is needed.
Modify the check for long BD and use long BDs only in cases
where TSO and other offloads are requested.

Fixes: 527b10089cc5 ("net/bnxt: optimize Tx completion handling")
Cc: stable@dpdk.org

Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Signed-off-by: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>
---
 drivers/net/bnxt/bnxt_txr.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/bnxt/bnxt_txr.c b/drivers/net/bnxt/bnxt_txr.c
index 27758898b0..7ef5b15ae8 100644
--- a/drivers/net/bnxt/bnxt_txr.c
+++ b/drivers/net/bnxt/bnxt_txr.c
@@ -111,8 +111,7 @@ int bnxt_init_tx_ring_struct(struct bnxt_tx_queue *txq, unsigned int socket_id)
 static bool
 bnxt_xmit_need_long_bd(struct rte_mbuf *tx_pkt, struct bnxt_tx_queue *txq)
 {
-	if (tx_pkt->ol_flags & (RTE_MBUF_F_TX_TCP_SEG | RTE_MBUF_F_TX_TCP_CKSUM |
-				RTE_MBUF_F_TX_UDP_CKSUM | RTE_MBUF_F_TX_IP_CKSUM |
+	if (tx_pkt->ol_flags & (RTE_MBUF_F_TX_TCP_SEG |
 				RTE_MBUF_F_TX_VLAN | RTE_MBUF_F_TX_OUTER_IP_CKSUM |
 				RTE_MBUF_F_TX_TUNNEL_GRE | RTE_MBUF_F_TX_TUNNEL_VXLAN |
 				RTE_MBUF_F_TX_TUNNEL_GENEVE | RTE_MBUF_F_TX_IEEE1588_TMST |
-- 
2.47.3

Re: [PATCH 1/4] net/bnxt: modify check for short Tx BDs

[Kishore Padmanabha]

[-- Attachment #1.1: Type: text/plain, Size: 1718 bytes --]

On Wed, Jun 3, 2026 at 1:49 PM Mohammad Shuab Siddique <
mohammad-shuab.siddique@broadcom.com> wrote:

> From: Ajit Khaparde <ajit.khaparde@broadcom.com>
>
> There is no need to use the long BDs for transmits
> where only checksum offload is needed.
> Modify the check for long BD and use long BDs only in cases
> where TSO and other offloads are requested.
>
> Fixes: 527b10089cc5 ("net/bnxt: optimize Tx completion handling")
> Cc: stable@dpdk.org
>
> Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
> Signed-off-by: Mohammad Shuab Siddique <
> mohammad-shuab.siddique@broadcom.com>
>
Acked-by:  Kishore Padmanabha <kishore.padmanabha@broadcom.com>

> ---
>  drivers/net/bnxt/bnxt_txr.c | 3 +--
>  1 file changed, 1 insertion(+), 2 deletions(-)
>
> diff --git a/drivers/net/bnxt/bnxt_txr.c b/drivers/net/bnxt/bnxt_txr.c
> index 27758898b0..7ef5b15ae8 100644
> --- a/drivers/net/bnxt/bnxt_txr.c
> +++ b/drivers/net/bnxt/bnxt_txr.c
> @@ -111,8 +111,7 @@ int bnxt_init_tx_ring_struct(struct bnxt_tx_queue
> *txq, unsigned int socket_id)
>  static bool
>  bnxt_xmit_need_long_bd(struct rte_mbuf *tx_pkt, struct bnxt_tx_queue *txq)
>  {
> -       if (tx_pkt->ol_flags & (RTE_MBUF_F_TX_TCP_SEG |
> RTE_MBUF_F_TX_TCP_CKSUM |
> -                               RTE_MBUF_F_TX_UDP_CKSUM |
> RTE_MBUF_F_TX_IP_CKSUM |
> +       if (tx_pkt->ol_flags & (RTE_MBUF_F_TX_TCP_SEG |
>                                 RTE_MBUF_F_TX_VLAN |
> RTE_MBUF_F_TX_OUTER_IP_CKSUM |
>                                 RTE_MBUF_F_TX_TUNNEL_GRE |
> RTE_MBUF_F_TX_TUNNEL_VXLAN |
>                                 RTE_MBUF_F_TX_TUNNEL_GENEVE |
> RTE_MBUF_F_TX_IEEE1588_TMST |
> --
> 2.47.3
>
>

[-- Attachment #1.2: Type: text/html, Size: 3023 bytes --]

[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 5493 bytes --]

[PATCH 2/4] net/bnxt: fix QP resource count in backing store config

[Mohammad Shuab Siddique]

From: Ajit Khaparde <ajit.khaparde@broadcom.com>

The driver is not passing the QP1 count while
configuring backing store for QP type.
This can result in a smaller set of entries allocated by the
driver with the firmware.

The number of entries is provided by the firmware as a
part of backing store qcaps v2 HWRM command.

Fixes: 5b5d398434f9 ("net/bnxt: add support for backing store v2")
Cc: stable@dpdk.org
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Signed-off-by: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>
---
 drivers/net/bnxt/bnxt_ethdev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bnxt/bnxt_ethdev.c b/drivers/net/bnxt/bnxt_ethdev.c
index b677f9491d..7d70d0f3ec 100644
--- a/drivers/net/bnxt/bnxt_ethdev.c
+++ b/drivers/net/bnxt/bnxt_ethdev.c
@@ -5404,11 +5404,11 @@ int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp)
 			if (ctxm->type == HWRM_FUNC_BACKING_STORE_CFG_V2_INPUT_TYPE_CQ)
 				entries = ctxm->cq_l2_entries;
 			else if (ctxm->type == HWRM_FUNC_BACKING_STORE_CFG_V2_INPUT_TYPE_QP)
-				entries = ctxm->qp_l2_entries;
+				entries = ctxm->qp_l2_entries + ctxm->qp_qp1_entries;
 			else if (ctxm->type == HWRM_FUNC_BACKING_STORE_CFG_V2_INPUT_TYPE_MRAV)
 				entries = ctxm->mrav_av_entries;
 			else if (ctxm->type == HWRM_FUNC_BACKING_STORE_CFG_V2_INPUT_TYPE_TIM)
-				entries = ctx2->qp_l2_entries;
+				entries = ctx2->qp_l2_entries + ctx2->qp_qp1_entries;
 			entries = clamp_t(uint32_t, entries, ctxm->min_entries,
 					  ctxm->max_entries);
 			ctx_pg[i].entries = entries;
-- 
2.47.3

Re: [PATCH 2/4] net/bnxt: fix QP resource count in backing store config

[Kishore Padmanabha]

[-- Attachment #1.1: Type: text/plain, Size: 2220 bytes --]

On Wed, Jun 3, 2026 at 1:49 PM Mohammad Shuab Siddique <
mohammad-shuab.siddique@broadcom.com> wrote:

> From: Ajit Khaparde <ajit.khaparde@broadcom.com>
>
> The driver is not passing the QP1 count while
> configuring backing store for QP type.
> This can result in a smaller set of entries allocated by the
> driver with the firmware.
>
> The number of entries is provided by the firmware as a
> part of backing store qcaps v2 HWRM command.
>
> Fixes: 5b5d398434f9 ("net/bnxt: add support for backing store v2")
> Cc: stable@dpdk.org
> Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
> Signed-off-by: Mohammad Shuab Siddique <
> mohammad-shuab.siddique@broadcom.com>
>
Acked-by:  Kishore Padmanabha <kishore.padmanabha@broadcom.com>

> ---
>  drivers/net/bnxt/bnxt_ethdev.c | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/net/bnxt/bnxt_ethdev.c
> b/drivers/net/bnxt/bnxt_ethdev.c
> index b677f9491d..7d70d0f3ec 100644
> --- a/drivers/net/bnxt/bnxt_ethdev.c
> +++ b/drivers/net/bnxt/bnxt_ethdev.c
> @@ -5404,11 +5404,11 @@ int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp)
>                         if (ctxm->type ==
> HWRM_FUNC_BACKING_STORE_CFG_V2_INPUT_TYPE_CQ)
>                                 entries = ctxm->cq_l2_entries;
>                         else if (ctxm->type ==
> HWRM_FUNC_BACKING_STORE_CFG_V2_INPUT_TYPE_QP)
> -                               entries = ctxm->qp_l2_entries;
> +                               entries = ctxm->qp_l2_entries +
> ctxm->qp_qp1_entries;
>                         else if (ctxm->type ==
> HWRM_FUNC_BACKING_STORE_CFG_V2_INPUT_TYPE_MRAV)
>                                 entries = ctxm->mrav_av_entries;
>                         else if (ctxm->type ==
> HWRM_FUNC_BACKING_STORE_CFG_V2_INPUT_TYPE_TIM)
> -                               entries = ctx2->qp_l2_entries;
> +                               entries = ctx2->qp_l2_entries +
> ctx2->qp_qp1_entries;
>                         entries = clamp_t(uint32_t, entries,
> ctxm->min_entries,
>                                           ctxm->max_entries);
>                         ctx_pg[i].entries = entries;
> --
> 2.47.3
>
>

[-- Attachment #1.2: Type: text/html, Size: 3673 bytes --]

[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 5493 bytes --]

[PATCH 3/4] net/bnxt: remove implicit integer sign-extension

[Mohammad Shuab Siddique]

From: Zoe Cheimets <zoe.cheimets@broadcom.com>

In bnxt_ring.c, the result on line 389 was auto-sign extended by
the compiler because the arithmetic result is an int, but the
dpi_offset is uint64_t. Fix by casting the result to uint64_t
before the multiplication forces extension. To ensure that a
negative integer is not being cast to uint64_t, add a check in
the if-statement.

Fixes: 7a1f9c782b50 ("net/bnxt: add multi-doorbell support")
Cc: stable@dpdk.org
Signed-off-by: Zoe Cheimets <zoe.cheimets@broadcom.com>
Signed-off-by: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>
---
 drivers/net/bnxt/bnxt_ring.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/bnxt/bnxt_ring.c b/drivers/net/bnxt/bnxt_ring.c
index ccca779b97..579b73d2ce 100644
--- a/drivers/net/bnxt/bnxt_ring.c
+++ b/drivers/net/bnxt/bnxt_ring.c
@@ -385,9 +385,10 @@ void bnxt_set_db(struct bnxt *bp,
 		db->doorbell = (char *)bp->doorbell_base + db_offset;
 
 		if (bp->fw_cap & BNXT_FW_CAP_MULTI_DB &&
-				dpi != BNXT_PRIVILEGED_DPI) {
-			dpi_offset = (dpi - bp->nq_dpi_start) *
-					bp->db_page_size;
+		    dpi != BNXT_PRIVILEGED_DPI &&
+		    dpi >= bp->nq_dpi_start) {
+			dpi_offset = (uint64_t)(dpi - bp->nq_dpi_start) *
+							bp->db_page_size;
 			db->doorbell = (char *)db->doorbell + dpi_offset;
 		}
 		db->db_key64 |= (uint64_t)fid << DBR_XID_SFT;
-- 
2.47.3

Re: [PATCH 3/4] net/bnxt: remove implicit integer sign-extension

[Kishore Padmanabha]

[-- Attachment #1.1: Type: text/plain, Size: 1941 bytes --]

On Wed, Jun 3, 2026 at 1:50 PM Mohammad Shuab Siddique <
mohammad-shuab.siddique@broadcom.com> wrote:

> From: Zoe Cheimets <zoe.cheimets@broadcom.com>
>
> In bnxt_ring.c, the result on line 389 was auto-sign extended by
> the compiler because the arithmetic result is an int, but the
> dpi_offset is uint64_t. Fix by casting the result to uint64_t
> before the multiplication forces extension. To ensure that a
> negative integer is not being cast to uint64_t, add a check in
> the if-statement.
>
> Fixes: 7a1f9c782b50 ("net/bnxt: add multi-doorbell support")
> Cc: stable@dpdk.org
> Signed-off-by: Zoe Cheimets <zoe.cheimets@broadcom.com>
> Signed-off-by: Mohammad Shuab Siddique <
> mohammad-shuab.siddique@broadcom.com>
>
Acked-by:  Kishore Padmanabha <kishore.padmanabha@broadcom.com>

> ---
>  drivers/net/bnxt/bnxt_ring.c | 7 ++++---
>  1 file changed, 4 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/net/bnxt/bnxt_ring.c b/drivers/net/bnxt/bnxt_ring.c
> index ccca779b97..579b73d2ce 100644
> --- a/drivers/net/bnxt/bnxt_ring.c
> +++ b/drivers/net/bnxt/bnxt_ring.c
> @@ -385,9 +385,10 @@ void bnxt_set_db(struct bnxt *bp,
>                 db->doorbell = (char *)bp->doorbell_base + db_offset;
>
>                 if (bp->fw_cap & BNXT_FW_CAP_MULTI_DB &&
> -                               dpi != BNXT_PRIVILEGED_DPI) {
> -                       dpi_offset = (dpi - bp->nq_dpi_start) *
> -                                       bp->db_page_size;
> +                   dpi != BNXT_PRIVILEGED_DPI &&
> +                   dpi >= bp->nq_dpi_start) {
> +                       dpi_offset = (uint64_t)(dpi - bp->nq_dpi_start) *
> +                                                       bp->db_page_size;
>                         db->doorbell = (char *)db->doorbell + dpi_offset;
>                 }
>                 db->db_key64 |= (uint64_t)fid << DBR_XID_SFT;
> --
> 2.47.3
>
>

[-- Attachment #1.2: Type: text/html, Size: 3397 bytes --]

[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 5493 bytes --]

[PATCH 4/4] net/bnxt: fix RSS hash mode configuration for VFs

[Mohammad Shuab Siddique]

From: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>

Fixed VFs attempting global RSS configuration which is not
permitted by firmware. VFs (including trusted VFs) must use
per-VNIC RSS configuration with actual vnic_id and rss_ctx_idx
values.

Cc: stable@dpdk.org
Signed-off-by: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>
---
 drivers/net/bnxt/bnxt_hwrm.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bnxt/bnxt_hwrm.c b/drivers/net/bnxt/bnxt_hwrm.c
index 0c82935de9..afc948ac29 100644
--- a/drivers/net/bnxt/bnxt_hwrm.c
+++ b/drivers/net/bnxt/bnxt_hwrm.c
@@ -2970,8 +2970,22 @@ bnxt_hwrm_vnic_rss_cfg_hash_mode_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic
 		req.hash_mode_flags = BNXT_HASH_MODE_INNERMOST;
 	else
 		req.hash_mode_flags = vnic->hash_mode;
-	req.vnic_id = rte_cpu_to_le_16(BNXT_DFLT_VNIC_ID_INVALID);
-	req.rss_ctx_idx = rte_cpu_to_le_16(BNXT_RSS_CTX_IDX_INVALID);
+
+	/* VFs must use actual vnic_id for per-VNIC configuration.
+	 * PFs can use INVALID vnic_id for global configuration.
+	 * This is because VFs don't have permission to configure
+	 * global hash mode, even if they're trusted.
+	 */
+	if (BNXT_VF(bp)) {
+		req.vnic_id = rte_cpu_to_le_16(vnic->fw_vnic_id);
+		req.rss_ctx_idx = rte_cpu_to_le_16(vnic->fw_grp_ids[0]);
+		PMD_DRV_LOG_LINE(DEBUG, "VF using per-VNIC RSS config (vnic_id=%u)",
+				vnic->fw_vnic_id);
+	} else {
+		req.vnic_id = rte_cpu_to_le_16(BNXT_DFLT_VNIC_ID_INVALID);
+		req.rss_ctx_idx = rte_cpu_to_le_16(BNXT_RSS_CTX_IDX_INVALID);
+		PMD_DRV_LOG_LINE(DEBUG, "PF using global RSS config");
+	}
 
 	PMD_DRV_LOG_LINE(DEBUG, "RSS CFG: Hash level %d", req.hash_mode_flags);
 	rc = bnxt_hwrm_send_message(bp, &req, sizeof(req),
-- 
2.47.3

Re: [PATCH 4/4] net/bnxt: fix RSS hash mode configuration for VFs

[Kishore Padmanabha]

[-- Attachment #1.1: Type: text/plain, Size: 2317 bytes --]

On Wed, Jun 3, 2026 at 1:50 PM Mohammad Shuab Siddique <
mohammad-shuab.siddique@broadcom.com> wrote:

> From: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>
>
> Fixed VFs attempting global RSS configuration which is not
> permitted by firmware. VFs (including trusted VFs) must use
> per-VNIC RSS configuration with actual vnic_id and rss_ctx_idx
> values.
>
> Cc: stable@dpdk.org
> Signed-off-by: Mohammad Shuab Siddique <
> mohammad-shuab.siddique@broadcom.com>
>
Acked-by:  Kishore Padmanabha <kishore.padmanabha@broadcom.com>

> ---
>  drivers/net/bnxt/bnxt_hwrm.c | 18 ++++++++++++++++--
>  1 file changed, 16 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/net/bnxt/bnxt_hwrm.c b/drivers/net/bnxt/bnxt_hwrm.c
> index 0c82935de9..afc948ac29 100644
> --- a/drivers/net/bnxt/bnxt_hwrm.c
> +++ b/drivers/net/bnxt/bnxt_hwrm.c
> @@ -2970,8 +2970,22 @@ bnxt_hwrm_vnic_rss_cfg_hash_mode_p5(struct bnxt
> *bp, struct bnxt_vnic_info *vnic
>                 req.hash_mode_flags = BNXT_HASH_MODE_INNERMOST;
>         else
>                 req.hash_mode_flags = vnic->hash_mode;
> -       req.vnic_id = rte_cpu_to_le_16(BNXT_DFLT_VNIC_ID_INVALID);
> -       req.rss_ctx_idx = rte_cpu_to_le_16(BNXT_RSS_CTX_IDX_INVALID);
> +
> +       /* VFs must use actual vnic_id for per-VNIC configuration.
> +        * PFs can use INVALID vnic_id for global configuration.
> +        * This is because VFs don't have permission to configure
> +        * global hash mode, even if they're trusted.
> +        */
> +       if (BNXT_VF(bp)) {
> +               req.vnic_id = rte_cpu_to_le_16(vnic->fw_vnic_id);
> +               req.rss_ctx_idx = rte_cpu_to_le_16(vnic->fw_grp_ids[0]);
> +               PMD_DRV_LOG_LINE(DEBUG, "VF using per-VNIC RSS config
> (vnic_id=%u)",
> +                               vnic->fw_vnic_id);
> +       } else {
> +               req.vnic_id = rte_cpu_to_le_16(BNXT_DFLT_VNIC_ID_INVALID);
> +               req.rss_ctx_idx =
> rte_cpu_to_le_16(BNXT_RSS_CTX_IDX_INVALID);
> +               PMD_DRV_LOG_LINE(DEBUG, "PF using global RSS config");
> +       }
>
>         PMD_DRV_LOG_LINE(DEBUG, "RSS CFG: Hash level %d",
> req.hash_mode_flags);
>         rc = bnxt_hwrm_send_message(bp, &req, sizeof(req),
> --
> 2.47.3
>
>

[-- Attachment #1.2: Type: text/html, Size: 3679 bytes --]

[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 5493 bytes --]

[PATCH v2] net/bnxt: fix RSS hash mode configuration for VFs

[Mohammad Shuab Siddique]

From: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>

Fixed VFs attempting global RSS configuration which is not
permitted by firmware. VFs (including trusted VFs) must use
per-VNIC RSS configuration with actual vnic_id and rss_ctx_idx
values.

Fixes: 8b9adaf0da6b ("net/bnxt: support RSS on ESP and AH headers")
Cc: stable@dpdk.org
Signed-off-by: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>
---
 drivers/net/bnxt/bnxt_hwrm.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bnxt/bnxt_hwrm.c b/drivers/net/bnxt/bnxt_hwrm.c
index 0c82935de9..afc948ac29 100644
--- a/drivers/net/bnxt/bnxt_hwrm.c
+++ b/drivers/net/bnxt/bnxt_hwrm.c
@@ -2970,8 +2970,22 @@ bnxt_hwrm_vnic_rss_cfg_hash_mode_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic
 		req.hash_mode_flags = BNXT_HASH_MODE_INNERMOST;
 	else
 		req.hash_mode_flags = vnic->hash_mode;
-	req.vnic_id = rte_cpu_to_le_16(BNXT_DFLT_VNIC_ID_INVALID);
-	req.rss_ctx_idx = rte_cpu_to_le_16(BNXT_RSS_CTX_IDX_INVALID);
+
+	/* VFs must use actual vnic_id for per-VNIC configuration.
+	 * PFs can use INVALID vnic_id for global configuration.
+	 * This is because VFs don't have permission to configure
+	 * global hash mode, even if they're trusted.
+	 */
+	if (BNXT_VF(bp)) {
+		req.vnic_id = rte_cpu_to_le_16(vnic->fw_vnic_id);
+		req.rss_ctx_idx = rte_cpu_to_le_16(vnic->fw_grp_ids[0]);
+		PMD_DRV_LOG_LINE(DEBUG, "VF using per-VNIC RSS config (vnic_id=%u)",
+				 vnic->fw_vnic_id);
+	} else {
+		req.vnic_id = rte_cpu_to_le_16(BNXT_DFLT_VNIC_ID_INVALID);
+		req.rss_ctx_idx = rte_cpu_to_le_16(BNXT_RSS_CTX_IDX_INVALID);
+		PMD_DRV_LOG_LINE(DEBUG, "PF using global RSS config");
+	}
 
 	PMD_DRV_LOG_LINE(DEBUG, "RSS CFG: Hash level %d", req.hash_mode_flags);
 	rc = bnxt_hwrm_send_message(bp, &req, sizeof(req),
-- 
2.47.3

[PATCH v3 4/4] net/bnxt: fix RSS hash mode configuration for VFs

[Mohammad Shuab Siddique]

From: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>

Fixed VFs attempting global RSS configuration which is not
permitted by firmware. VFs (including trusted VFs) must use
per-VNIC RSS configuration with actual vnic_id and rss_ctx_idx
values.

Fixes: 8b9adaf0da6b ("net/bnxt: support RSS on ESP and AH headers")
Cc: stable@dpdk.org
Signed-off-by: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>
---
 drivers/net/bnxt/bnxt_hwrm.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bnxt/bnxt_hwrm.c b/drivers/net/bnxt/bnxt_hwrm.c
index 0c82935de9..afc948ac29 100644
--- a/drivers/net/bnxt/bnxt_hwrm.c
+++ b/drivers/net/bnxt/bnxt_hwrm.c
@@ -2970,8 +2970,22 @@ bnxt_hwrm_vnic_rss_cfg_hash_mode_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic
 		req.hash_mode_flags = BNXT_HASH_MODE_INNERMOST;
 	else
 		req.hash_mode_flags = vnic->hash_mode;
-	req.vnic_id = rte_cpu_to_le_16(BNXT_DFLT_VNIC_ID_INVALID);
-	req.rss_ctx_idx = rte_cpu_to_le_16(BNXT_RSS_CTX_IDX_INVALID);
+
+	/* VFs must use actual vnic_id for per-VNIC configuration.
+	 * PFs can use INVALID vnic_id for global configuration.
+	 * This is because VFs don't have permission to configure
+	 * global hash mode, even if they're trusted.
+	 */
+	if (BNXT_VF(bp)) {
+		req.vnic_id = rte_cpu_to_le_16(vnic->fw_vnic_id);
+		req.rss_ctx_idx = rte_cpu_to_le_16(vnic->fw_grp_ids[0]);
+		PMD_DRV_LOG_LINE(DEBUG, "VF using per-VNIC RSS config (vnic_id=%u)",
+				 vnic->fw_vnic_id);
+	} else {
+		req.vnic_id = rte_cpu_to_le_16(BNXT_DFLT_VNIC_ID_INVALID);
+		req.rss_ctx_idx = rte_cpu_to_le_16(BNXT_RSS_CTX_IDX_INVALID);
+		PMD_DRV_LOG_LINE(DEBUG, "PF using global RSS config");
+	}
 
 	PMD_DRV_LOG_LINE(DEBUG, "RSS CFG: Hash level %d", req.hash_mode_flags);
 	rc = bnxt_hwrm_send_message(bp, &req, sizeof(req),
-- 
2.47.3

Re: [PATCH v3 4/4] net/bnxt: fix RSS hash mode configuration for VFs

[Stephen Hemminger]

On Wed,  3 Jun 2026 14:02:07 -0600
Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com> wrote:

> From: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>
> 
> Fixed VFs attempting global RSS configuration which is not
> permitted by firmware. VFs (including trusted VFs) must use
> per-VNIC RSS configuration with actual vnic_id and rss_ctx_idx
> values.
> 
> Fixes: 8b9adaf0da6b ("net/bnxt: support RSS on ESP and AH headers")
> Cc: stable@dpdk.org
> Signed-off-by: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>
> ---

If you need to update one patch in a series, you need to resend
the whole series. The CI system works in patch series.

[PATCH v2 0/4] net/bnxt: miscellaneous bug fixes

[Mohammad Shuab Siddique]

From: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>

This series collects four independent bug fixes for the bnxt PMD:

 - Eliminate unnecessary long TX BDs when only checksum offload is needed
 - Pass QP1 resource count correctly when configuring backing store
 - Fix implicit integer sign-extension in the doorbell calculation
 - Prevent VFs from attempting global RSS configuration

All patches carry Fixes: tags and Cc: stable@dpdk.org.

Changes in v2:
 - Patch 4/4: add missing Fixes: tag for RSS hash mode fix

Ajit Khaparde (2):
  net/bnxt: modify check for short Tx BDs
  net/bnxt: fix QP resource count in backing store config

Mohammad Shuab Siddique (1):
  net/bnxt: fix RSS hash mode configuration for VFs

Zoe Cheimets (1):
  net/bnxt: remove implicit integer sign-extension

 drivers/net/bnxt/bnxt_ethdev.c |  4 ++--
 drivers/net/bnxt/bnxt_hwrm.c   | 18 ++++++++++++++++--
 drivers/net/bnxt/bnxt_ring.c   |  7 ++++---
 drivers/net/bnxt/bnxt_txr.c    |  3 +--
 4 files changed, 23 insertions(+), 9 deletions(-)

-- 
2.47.3

[PATCH v2 1/4] net/bnxt: modify check for short Tx BDs

[Mohammad Shuab Siddique]

From: Ajit Khaparde <ajit.khaparde@broadcom.com>

There is no need to use the long BDs for transmits
where only checksum offload is needed.
Modify the check for long BD and use long BDs only in cases
where TSO and other offloads are requested.

Fixes: 527b10089cc5 ("net/bnxt: optimize Tx completion handling")
Cc: stable@dpdk.org

Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Signed-off-by: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>
---
 drivers/net/bnxt/bnxt_txr.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/bnxt/bnxt_txr.c b/drivers/net/bnxt/bnxt_txr.c
index 27758898b0..7ef5b15ae8 100644
--- a/drivers/net/bnxt/bnxt_txr.c
+++ b/drivers/net/bnxt/bnxt_txr.c
@@ -111,8 +111,7 @@ int bnxt_init_tx_ring_struct(struct bnxt_tx_queue *txq, unsigned int socket_id)
 static bool
 bnxt_xmit_need_long_bd(struct rte_mbuf *tx_pkt, struct bnxt_tx_queue *txq)
 {
-	if (tx_pkt->ol_flags & (RTE_MBUF_F_TX_TCP_SEG | RTE_MBUF_F_TX_TCP_CKSUM |
-				RTE_MBUF_F_TX_UDP_CKSUM | RTE_MBUF_F_TX_IP_CKSUM |
+	if (tx_pkt->ol_flags & (RTE_MBUF_F_TX_TCP_SEG |
 				RTE_MBUF_F_TX_VLAN | RTE_MBUF_F_TX_OUTER_IP_CKSUM |
 				RTE_MBUF_F_TX_TUNNEL_GRE | RTE_MBUF_F_TX_TUNNEL_VXLAN |
 				RTE_MBUF_F_TX_TUNNEL_GENEVE | RTE_MBUF_F_TX_IEEE1588_TMST |
-- 
2.47.3

[PATCH v2 2/4] net/bnxt: fix QP resource count in backing store config

[Mohammad Shuab Siddique]

From: Ajit Khaparde <ajit.khaparde@broadcom.com>

The driver is not passing the QP1 count while
configuring backing store for QP type.
This can result in a smaller set of entries allocated by the
driver with the firmware.

The number of entries is provided by the firmware as a
part of backing store qcaps v2 HWRM command.

Fixes: 5b5d398434f9 ("net/bnxt: add support for backing store v2")
Cc: stable@dpdk.org
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Signed-off-by: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>
---
 drivers/net/bnxt/bnxt_ethdev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bnxt/bnxt_ethdev.c b/drivers/net/bnxt/bnxt_ethdev.c
index b677f9491d..7d70d0f3ec 100644
--- a/drivers/net/bnxt/bnxt_ethdev.c
+++ b/drivers/net/bnxt/bnxt_ethdev.c
@@ -5404,11 +5404,11 @@ int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp)
 			if (ctxm->type == HWRM_FUNC_BACKING_STORE_CFG_V2_INPUT_TYPE_CQ)
 				entries = ctxm->cq_l2_entries;
 			else if (ctxm->type == HWRM_FUNC_BACKING_STORE_CFG_V2_INPUT_TYPE_QP)
-				entries = ctxm->qp_l2_entries;
+				entries = ctxm->qp_l2_entries + ctxm->qp_qp1_entries;
 			else if (ctxm->type == HWRM_FUNC_BACKING_STORE_CFG_V2_INPUT_TYPE_MRAV)
 				entries = ctxm->mrav_av_entries;
 			else if (ctxm->type == HWRM_FUNC_BACKING_STORE_CFG_V2_INPUT_TYPE_TIM)
-				entries = ctx2->qp_l2_entries;
+				entries = ctx2->qp_l2_entries + ctx2->qp_qp1_entries;
 			entries = clamp_t(uint32_t, entries, ctxm->min_entries,
 					  ctxm->max_entries);
 			ctx_pg[i].entries = entries;
-- 
2.47.3

[PATCH v2 3/4] net/bnxt: remove implicit integer sign-extension

[Mohammad Shuab Siddique]

From: Zoe Cheimets <zoe.cheimets@broadcom.com>

In bnxt_ring.c, the result on line 389 was auto-sign extended by
the compiler because the arithmetic result is an int, but the
dpi_offset is uint64_t. Fix by casting the result to uint64_t
before the multiplication forces extension. To ensure that a
negative integer is not being cast to uint64_t, add a check in
the if-statement.

Fixes: 7a1f9c782b50 ("net/bnxt: add multi-doorbell support")
Cc: stable@dpdk.org
Signed-off-by: Zoe Cheimets <zoe.cheimets@broadcom.com>
Signed-off-by: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>
---
 drivers/net/bnxt/bnxt_ring.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/bnxt/bnxt_ring.c b/drivers/net/bnxt/bnxt_ring.c
index ccca779b97..579b73d2ce 100644
--- a/drivers/net/bnxt/bnxt_ring.c
+++ b/drivers/net/bnxt/bnxt_ring.c
@@ -385,9 +385,10 @@ void bnxt_set_db(struct bnxt *bp,
 		db->doorbell = (char *)bp->doorbell_base + db_offset;
 
 		if (bp->fw_cap & BNXT_FW_CAP_MULTI_DB &&
-				dpi != BNXT_PRIVILEGED_DPI) {
-			dpi_offset = (dpi - bp->nq_dpi_start) *
-					bp->db_page_size;
+		    dpi != BNXT_PRIVILEGED_DPI &&
+		    dpi >= bp->nq_dpi_start) {
+			dpi_offset = (uint64_t)(dpi - bp->nq_dpi_start) *
+							bp->db_page_size;
 			db->doorbell = (char *)db->doorbell + dpi_offset;
 		}
 		db->db_key64 |= (uint64_t)fid << DBR_XID_SFT;
-- 
2.47.3

[PATCH v2 4/4] net/bnxt: fix RSS hash mode configuration for VFs

[Mohammad Shuab Siddique]

From: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>

Fixed VFs attempting global RSS configuration which is not
permitted by firmware. VFs (including trusted VFs) must use
per-VNIC RSS configuration with actual vnic_id and rss_ctx_idx
values.

Fixes: 8b9adaf0da6b ("net/bnxt: support RSS on ESP and AH headers")
Cc: stable@dpdk.org
Signed-off-by: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>
---
 drivers/net/bnxt/bnxt_hwrm.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bnxt/bnxt_hwrm.c b/drivers/net/bnxt/bnxt_hwrm.c
index 0c82935de9..afc948ac29 100644
--- a/drivers/net/bnxt/bnxt_hwrm.c
+++ b/drivers/net/bnxt/bnxt_hwrm.c
@@ -2970,8 +2970,22 @@ bnxt_hwrm_vnic_rss_cfg_hash_mode_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic
 		req.hash_mode_flags = BNXT_HASH_MODE_INNERMOST;
 	else
 		req.hash_mode_flags = vnic->hash_mode;
-	req.vnic_id = rte_cpu_to_le_16(BNXT_DFLT_VNIC_ID_INVALID);
-	req.rss_ctx_idx = rte_cpu_to_le_16(BNXT_RSS_CTX_IDX_INVALID);
+
+	/* VFs must use actual vnic_id for per-VNIC configuration.
+	 * PFs can use INVALID vnic_id for global configuration.
+	 * This is because VFs don't have permission to configure
+	 * global hash mode, even if they're trusted.
+	 */
+	if (BNXT_VF(bp)) {
+		req.vnic_id = rte_cpu_to_le_16(vnic->fw_vnic_id);
+		req.rss_ctx_idx = rte_cpu_to_le_16(vnic->fw_grp_ids[0]);
+		PMD_DRV_LOG_LINE(DEBUG, "VF using per-VNIC RSS config (vnic_id=%u)",
+				vnic->fw_vnic_id);
+	} else {
+		req.vnic_id = rte_cpu_to_le_16(BNXT_DFLT_VNIC_ID_INVALID);
+		req.rss_ctx_idx = rte_cpu_to_le_16(BNXT_RSS_CTX_IDX_INVALID);
+		PMD_DRV_LOG_LINE(DEBUG, "PF using global RSS config");
+	}
 
 	PMD_DRV_LOG_LINE(DEBUG, "RSS CFG: Hash level %d", req.hash_mode_flags);
 	rc = bnxt_hwrm_send_message(bp, &req, sizeof(req),
-- 
2.47.3

Re: [PATCH v2 0/4] net/bnxt: miscellaneous bug fixes

[Kishore Padmanabha]

[-- Attachment #1.1: Type: text/plain, Size: 1305 bytes --]

On Thu, Jun 4, 2026 at 6:54 PM Mohammad Shuab Siddique <
mohammad-shuab.siddique@broadcom.com> wrote:

> From: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>
>
> This series collects four independent bug fixes for the bnxt PMD:
>
>  - Eliminate unnecessary long TX BDs when only checksum offload is needed
>  - Pass QP1 resource count correctly when configuring backing store
>  - Fix implicit integer sign-extension in the doorbell calculation
>  - Prevent VFs from attempting global RSS configuration
>
> All patches carry Fixes: tags and Cc: stable@dpdk.org.
>
> Changes in v2:
>  - Patch 4/4: add missing Fixes: tag for RSS hash mode fix
>
> Ajit Khaparde (2):
>   net/bnxt: modify check for short Tx BDs
>   net/bnxt: fix QP resource count in backing store config
>
> Mohammad Shuab Siddique (1):
>   net/bnxt: fix RSS hash mode configuration for VFs
>
> Zoe Cheimets (1):
>   net/bnxt: remove implicit integer sign-extension
>
>  drivers/net/bnxt/bnxt_ethdev.c |  4 ++--
>  drivers/net/bnxt/bnxt_hwrm.c   | 18 ++++++++++++++++--
>  drivers/net/bnxt/bnxt_ring.c   |  7 ++++---
>  drivers/net/bnxt/bnxt_txr.c    |  3 +--
>  4 files changed, 23 insertions(+), 9 deletions(-)
>
> patches merged into dpdk-next-net-brcm
Thanks

> --
> 2.47.3
>
>

[-- Attachment #1.2: Type: text/html, Size: 2024 bytes --]

[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 5493 bytes --]