From: Michael Chan <michael.chan@broadcom.com>
To: davem@davemloft.net
Cc: netdev@vger.kernel.org, edumazet@google.com, kuba@kernel.org,
pabeni@redhat.com, andrew+netdev@lunn.ch,
pavan.chebbi@broadcom.com, andrew.gospodarek@broadcom.com,
michal.swiatkowski@linux.intel.com, helgaas@kernel.org,
horms@kernel.org, Manoj Panicker <manoj.panicker2@amd.com>,
Somnath Kotur <somnath.kotur@broadcom.com>,
Wei Huang <wei.huang2@amd.com>,
Ajit Khaparde <ajit.khaparde@broadcom.com>
Subject: [PATCH net-next v3 10/10] bnxt_en: Add TPH support in BNXT driver
Date: Mon, 3 Feb 2025 16:46:09 -0800 [thread overview]
Message-ID: <20250204004609.1107078-11-michael.chan@broadcom.com> (raw)
In-Reply-To: <20250204004609.1107078-1-michael.chan@broadcom.com>
From: Manoj Panicker <manoj.panicker2@amd.com>
Add TPH support to the Broadcom BNXT device driver. This allows the
driver to utilize TPH functions for retrieving and configuring Steering
Tags when changing interrupt affinity. With compatible NIC firmware,
network traffic will be tagged correctly with Steering Tags, resulting
in significant memory bandwidth savings and other advantages as
demonstrated by real network benchmarks on TPH-capable platforms.
Co-developed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Co-developed-by: Wei Huang <wei.huang2@amd.com>
Signed-off-by: Wei Huang <wei.huang2@amd.com>
Signed-off-by: Manoj Panicker <manoj.panicker2@amd.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
Cc: Bjorn Helgaas <helgaas@kernel.org>
v3:
Add MODULE_IMPORT_NS("NETDEV_INTERNAL")
Previous driver series fixing rtnl_lock and empty release function:
https://lore.kernel.org/netdev/20241115200412.1340286-1-wei.huang2@amd.com/
v5 of the PCI series using netdev_rx_queue_restart():
https://lore.kernel.org/netdev/20240916205103.3882081-5-wei.huang2@amd.com/
v1 of the PCI series using open/close:
https://lore.kernel.org/netdev/20240509162741.1937586-9-wei.huang2@amd.com/
---
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 106 ++++++++++++++++++++++
drivers/net/ethernet/broadcom/bnxt/bnxt.h | 5 +
2 files changed, 111 insertions(+)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index fee9baff9e5a..2b7df91840fd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -55,6 +55,8 @@
#include <net/page_pool/helpers.h>
#include <linux/align.h>
#include <net/netdev_queues.h>
+#include <net/netdev_rx_queue.h>
+#include <linux/pci-tph.h>
#include "bnxt_hsi.h"
#include "bnxt.h"
@@ -76,6 +78,7 @@
#define BNXT_DEF_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_HW | \
NETIF_MSG_TX_ERR)
+MODULE_IMPORT_NS("NETDEV_INTERNAL");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Broadcom NetXtreme network driver");
@@ -11359,6 +11362,83 @@ static int bnxt_tx_queue_start(struct bnxt *bp, int idx)
return 0;
}
+static void bnxt_irq_affinity_notify(struct irq_affinity_notify *notify,
+ const cpumask_t *mask)
+{
+ struct bnxt_irq *irq;
+ u16 tag;
+ int err;
+
+ irq = container_of(notify, struct bnxt_irq, affinity_notify);
+
+ if (!irq->bp->tph_mode)
+ return;
+
+ cpumask_copy(irq->cpu_mask, mask);
+
+ if (irq->ring_nr >= irq->bp->rx_nr_rings)
+ return;
+
+ if (pcie_tph_get_cpu_st(irq->bp->pdev, TPH_MEM_TYPE_VM,
+ cpumask_first(irq->cpu_mask), &tag))
+ return;
+
+ if (pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, tag))
+ return;
+
+ rtnl_lock();
+ if (netif_running(irq->bp->dev)) {
+ err = netdev_rx_queue_restart(irq->bp->dev, irq->ring_nr);
+ if (err)
+ netdev_err(irq->bp->dev,
+ "RX queue restart failed: err=%d\n", err);
+ }
+ rtnl_unlock();
+}
+
+static void bnxt_irq_affinity_release(struct kref *ref)
+{
+ struct irq_affinity_notify *notify =
+ container_of(ref, struct irq_affinity_notify, kref);
+ struct bnxt_irq *irq;
+
+ irq = container_of(notify, struct bnxt_irq, affinity_notify);
+
+ if (!irq->bp->tph_mode)
+ return;
+
+ if (pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, 0)) {
+ netdev_err(irq->bp->dev,
+ "Setting ST=0 for MSIX entry %d failed\n",
+ irq->msix_nr);
+ return;
+ }
+}
+
+static void bnxt_release_irq_notifier(struct bnxt_irq *irq)
+{
+ irq_set_affinity_notifier(irq->vector, NULL);
+}
+
+static void bnxt_register_irq_notifier(struct bnxt *bp, struct bnxt_irq *irq)
+{
+ struct irq_affinity_notify *notify;
+
+ irq->bp = bp;
+
+ /* Nothing to do if TPH is not enabled */
+ if (!bp->tph_mode)
+ return;
+
+ /* Register IRQ affinity notifier */
+ notify = &irq->affinity_notify;
+ notify->irq = irq->vector;
+ notify->notify = bnxt_irq_affinity_notify;
+ notify->release = bnxt_irq_affinity_release;
+
+ irq_set_affinity_notifier(irq->vector, notify);
+}
+
static void bnxt_free_irq(struct bnxt *bp)
{
struct bnxt_irq *irq;
@@ -11381,11 +11461,18 @@ static void bnxt_free_irq(struct bnxt *bp)
free_cpumask_var(irq->cpu_mask);
irq->have_cpumask = 0;
}
+
+ bnxt_release_irq_notifier(irq);
+
free_irq(irq->vector, bp->bnapi[i]);
}
irq->requested = 0;
}
+
+ /* Disable TPH support */
+ pcie_disable_tph(bp->pdev);
+ bp->tph_mode = 0;
}
static int bnxt_request_irq(struct bnxt *bp)
@@ -11405,6 +11492,12 @@ static int bnxt_request_irq(struct bnxt *bp)
#ifdef CONFIG_RFS_ACCEL
rmap = bp->dev->rx_cpu_rmap;
#endif
+
+ /* Enable TPH support as part of IRQ request */
+ rc = pcie_enable_tph(bp->pdev, PCI_TPH_ST_IV_MODE);
+ if (!rc)
+ bp->tph_mode = PCI_TPH_ST_IV_MODE;
+
for (i = 0, j = 0; i < bp->cp_nr_rings; i++) {
int map_idx = bnxt_cp_num_to_irq_num(bp, i);
struct bnxt_irq *irq = &bp->irq_tbl[map_idx];
@@ -11428,8 +11521,11 @@ static int bnxt_request_irq(struct bnxt *bp)
if (zalloc_cpumask_var(&irq->cpu_mask, GFP_KERNEL)) {
int numa_node = dev_to_node(&bp->pdev->dev);
+ u16 tag;
irq->have_cpumask = 1;
+ irq->msix_nr = map_idx;
+ irq->ring_nr = i;
cpumask_set_cpu(cpumask_local_spread(i, numa_node),
irq->cpu_mask);
rc = irq_update_affinity_hint(irq->vector, irq->cpu_mask);
@@ -11439,6 +11535,16 @@ static int bnxt_request_irq(struct bnxt *bp)
irq->vector);
break;
}
+
+ bnxt_register_irq_notifier(bp, irq);
+
+ /* Init ST table entry */
+ if (pcie_tph_get_cpu_st(irq->bp->pdev, TPH_MEM_TYPE_VM,
+ cpumask_first(irq->cpu_mask),
+ &tag))
+ continue;
+
+ pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, tag);
}
}
return rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 4e20878e7714..e85b5ce94f58 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1234,6 +1234,11 @@ struct bnxt_irq {
u8 have_cpumask:1;
char name[IFNAMSIZ + BNXT_IRQ_NAME_EXTRA];
cpumask_var_t cpu_mask;
+
+ struct bnxt *bp;
+ int msix_nr;
+ int ring_nr;
+ struct irq_affinity_notify affinity_notify;
};
#define HWRM_RING_ALLOC_TX 0x1
--
2.30.1
next prev parent reply other threads:[~2025-02-04 0:47 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-04 0:45 [PATCH net-next v3 00/10] bnxt_en: Add NPAR 1.2 and TPH support Michael Chan
2025-02-04 0:46 ` [PATCH net-next v3 01/10] bnxt_en: Set NAPR 1.2 support when registering with firmware Michael Chan
2025-02-04 0:46 ` [PATCH net-next v3 02/10] bnxt_en Refactor completion ring allocation logic for P5_PLUS chips Michael Chan
2025-02-04 0:46 ` [PATCH net-next v3 03/10] bnxt_en: Refactor TX ring allocation logic Michael Chan
2025-02-04 0:46 ` [PATCH net-next v3 04/10] bnxt_en: Refactor completion ring free routine Michael Chan
2025-02-04 0:46 ` [PATCH net-next v3 05/10] bnxt_en: Refactor bnxt_free_tx_rings() to free per TX ring Michael Chan
2025-02-04 0:46 ` [PATCH net-next v3 06/10] bnxt_en: Refactor RX/RX AGG ring parameters setup for P5_PLUS Michael Chan
2025-02-04 0:46 ` [PATCH net-next v3 07/10] bnxt_en: Pass NQ ID to the FW when allocating RX/RX AGG rings Michael Chan
2025-02-04 0:46 ` [PATCH net-next v3 08/10] bnxt_en: Reallocate RX completion ring for TPH support Michael Chan
2025-02-04 0:46 ` [PATCH net-next v3 09/10] bnxt_en: Extend queue stop/start for TX rings Michael Chan
2025-02-04 0:46 ` Michael Chan [this message]
2025-02-04 2:02 ` [PATCH net-next v3 00/10] bnxt_en: Add NPAR 1.2 and TPH support Bjorn Helgaas
2025-02-04 8:13 ` Michael Chan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250204004609.1107078-11-michael.chan@broadcom.com \
--to=michael.chan@broadcom.com \
--cc=ajit.khaparde@broadcom.com \
--cc=andrew+netdev@lunn.ch \
--cc=andrew.gospodarek@broadcom.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=helgaas@kernel.org \
--cc=horms@kernel.org \
--cc=kuba@kernel.org \
--cc=manoj.panicker2@amd.com \
--cc=michal.swiatkowski@linux.intel.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=pavan.chebbi@broadcom.com \
--cc=somnath.kotur@broadcom.com \
--cc=wei.huang2@amd.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox