From: Nitesh Narayan Lal <nitesh@redhat.com>
To: linux-kernel@vger.kernel.org, linux-scsi@vger.kernel.org,
intel-wired-lan@lists.osuosl.org, netdev@vger.kernel.org,
linux-api@vger.kernel.org, linux-pci@vger.kernel.org,
tglx@linutronix.de, jesse.brandeburg@intel.com,
robin.murphy@arm.com, mtosatti@redhat.com, mingo@kernel.org,
jbrandeb@kernel.org, frederic@kernel.org, juri.lelli@redhat.com,
abelits@marvell.com, bhelgaas@google.com, rostedt@goodmis.org,
peterz@infradead.org, davem@davemloft.net,
akpm@linux-foundation.org, sfr@canb.auug.org.au,
stephen@networkplumber.org, rppt@linux.vnet.ibm.com,
chris.friesen@windriver.com, maz@kernel.org,
nhorman@tuxdriver.com, pjwaskiewicz@gmail.com,
sassmann@redhat.com, thenzl@redhat.com,
kashyap.desai@broadcom.com, sumit.saxena@broadcom.com,
shivasharan.srikanteshwara@broadcom.com,
sathya.prakash@broadcom.com, sreekanth.reddy@broadcom.com,
suganath-prabu.subramani@broadcom.com, james.smart@broadcom.com,
dick.kennedy@broadcom.com, jkc@redhat.com,
faisal.latif@intel.com, shiraz.saleem@intel.com,
tariqt@nvidia.com, ahleihel@redhat.com, kheib@redhat.com,
borisp@nvidia.com, saeedm@nvidia.com, benve@cisco.com,
govind@gmx.com, jassisinghbrar@gmail.com,
ajit.khaparde@broadcom.com, sriharsha.basavapatna@broadcom.com,
somnath.kotur@broadcom.com, nilal@redhat.com,
tatyana.e.nikolova@intel.com, mustafa.ismail@intel.com,
ahs3@redhat.com, leonro@nvidia.com,
chandrakanth.patil@broadcom.com
Subject: [PATCH v3 05/14] scsi: mpt3sas: Use irq_set_affinity_and_hint
Date: Tue, 13 Jul 2021 17:14:53 -0400 [thread overview]
Message-ID: <20210713211502.464259-6-nitesh@redhat.com> (raw)
In-Reply-To: <20210713211502.464259-1-nitesh@redhat.com>
The driver uses irq_set_affinity_hint() specifically for the high IOPS
queue interrupts for two purposes:
- To set the affinity_hint which is consumed by the userspace for
distributing the interrupts
- To apply an affinity that it provides
The driver enforces its own affinity to bind the high IOPS queue interrupts
to the local NUMA node. However, irq_set_affinity_hint() applying the
provided cpumask as an affinity (if not NULL) for the interrupt is an
undocumented side effect.
To remove this side effect irq_set_affinity_hint() has been marked
as deprecated and new interfaces have been introduced. Hence, replace the
irq_set_affinity_hint() with the new interface irq_set_affinity_and_hint()
where the provided mask needs to be applied as the affinity and
affinity_hint pointer needs to be set and replace with
irq_update_affinity_hint() where only affinity_hint needs to be updated.
Signed-off-by: Nitesh Narayan Lal <nitesh@redhat.com>
---
drivers/scsi/mpt3sas/mpt3sas_base.c | 21 ++++++++++-----------
1 file changed, 10 insertions(+), 11 deletions(-)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index c39955239d1c..c1a11962f227 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -2991,6 +2991,7 @@ _base_check_enable_msix(struct MPT3SAS_ADAPTER *ioc)
static void
_base_free_irq(struct MPT3SAS_ADAPTER *ioc)
{
+ unsigned int irq;
struct adapter_reply_queue *reply_q, *next;
if (list_empty(&ioc->reply_queue_list))
@@ -2998,9 +2999,10 @@ _base_free_irq(struct MPT3SAS_ADAPTER *ioc)
list_for_each_entry_safe(reply_q, next, &ioc->reply_queue_list, list) {
list_del(&reply_q->list);
- if (ioc->smp_affinity_enable)
- irq_set_affinity_hint(pci_irq_vector(ioc->pdev,
- reply_q->msix_index), NULL);
+ if (ioc->smp_affinity_enable) {
+ irq = pci_irq_vector(ioc->pdev, reply_q->msix_index);
+ irq_update_affinity_hint(irq, NULL);
+ }
free_irq(pci_irq_vector(ioc->pdev, reply_q->msix_index),
reply_q);
kfree(reply_q);
@@ -3056,16 +3058,13 @@ _base_request_irq(struct MPT3SAS_ADAPTER *ioc, u8 index)
* @ioc: per adapter object
*
* The enduser would need to set the affinity via /proc/irq/#/smp_affinity
- *
- * It would nice if we could call irq_set_affinity, however it is not
- * an exported symbol
*/
static void
_base_assign_reply_queues(struct MPT3SAS_ADAPTER *ioc)
{
- unsigned int cpu, nr_cpus, nr_msix, index = 0;
+ unsigned int cpu, nr_cpus, nr_msix, index = 0, irq;
struct adapter_reply_queue *reply_q;
- int local_numa_node;
+ const struct cpumask *mask;
if (!_base_is_controller_msix_enabled(ioc))
return;
@@ -3088,11 +3087,11 @@ _base_assign_reply_queues(struct MPT3SAS_ADAPTER *ioc)
* corresponding to high iops queues.
*/
if (ioc->high_iops_queues) {
- local_numa_node = dev_to_node(&ioc->pdev->dev);
+ mask = cpumask_of_node(dev_to_node(&ioc->pdev->dev));
for (index = 0; index < ioc->high_iops_queues;
index++) {
- irq_set_affinity_hint(pci_irq_vector(ioc->pdev,
- index), cpumask_of_node(local_numa_node));
+ irq = pci_irq_vector(ioc->pdev, index);
+ irq_set_affinity_and_hint(irq, mask);
}
}
--
2.27.0
WARNING: multiple messages have this Message-ID (diff)
From: Nitesh Narayan Lal <nitesh@redhat.com>
To: intel-wired-lan@osuosl.org
Subject: [Intel-wired-lan] [PATCH v3 05/14] scsi: mpt3sas: Use irq_set_affinity_and_hint
Date: Tue, 13 Jul 2021 17:14:53 -0400 [thread overview]
Message-ID: <20210713211502.464259-6-nitesh@redhat.com> (raw)
In-Reply-To: <20210713211502.464259-1-nitesh@redhat.com>
The driver uses irq_set_affinity_hint() specifically for the high IOPS
queue interrupts for two purposes:
- To set the affinity_hint which is consumed by the userspace for
distributing the interrupts
- To apply an affinity that it provides
The driver enforces its own affinity to bind the high IOPS queue interrupts
to the local NUMA node. However, irq_set_affinity_hint() applying the
provided cpumask as an affinity (if not NULL) for the interrupt is an
undocumented side effect.
To remove this side effect irq_set_affinity_hint() has been marked
as deprecated and new interfaces have been introduced. Hence, replace the
irq_set_affinity_hint() with the new interface irq_set_affinity_and_hint()
where the provided mask needs to be applied as the affinity and
affinity_hint pointer needs to be set and replace with
irq_update_affinity_hint() where only affinity_hint needs to be updated.
Signed-off-by: Nitesh Narayan Lal <nitesh@redhat.com>
---
drivers/scsi/mpt3sas/mpt3sas_base.c | 21 ++++++++++-----------
1 file changed, 10 insertions(+), 11 deletions(-)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index c39955239d1c..c1a11962f227 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -2991,6 +2991,7 @@ _base_check_enable_msix(struct MPT3SAS_ADAPTER *ioc)
static void
_base_free_irq(struct MPT3SAS_ADAPTER *ioc)
{
+ unsigned int irq;
struct adapter_reply_queue *reply_q, *next;
if (list_empty(&ioc->reply_queue_list))
@@ -2998,9 +2999,10 @@ _base_free_irq(struct MPT3SAS_ADAPTER *ioc)
list_for_each_entry_safe(reply_q, next, &ioc->reply_queue_list, list) {
list_del(&reply_q->list);
- if (ioc->smp_affinity_enable)
- irq_set_affinity_hint(pci_irq_vector(ioc->pdev,
- reply_q->msix_index), NULL);
+ if (ioc->smp_affinity_enable) {
+ irq = pci_irq_vector(ioc->pdev, reply_q->msix_index);
+ irq_update_affinity_hint(irq, NULL);
+ }
free_irq(pci_irq_vector(ioc->pdev, reply_q->msix_index),
reply_q);
kfree(reply_q);
@@ -3056,16 +3058,13 @@ _base_request_irq(struct MPT3SAS_ADAPTER *ioc, u8 index)
* @ioc: per adapter object
*
* The enduser would need to set the affinity via /proc/irq/#/smp_affinity
- *
- * It would nice if we could call irq_set_affinity, however it is not
- * an exported symbol
*/
static void
_base_assign_reply_queues(struct MPT3SAS_ADAPTER *ioc)
{
- unsigned int cpu, nr_cpus, nr_msix, index = 0;
+ unsigned int cpu, nr_cpus, nr_msix, index = 0, irq;
struct adapter_reply_queue *reply_q;
- int local_numa_node;
+ const struct cpumask *mask;
if (!_base_is_controller_msix_enabled(ioc))
return;
@@ -3088,11 +3087,11 @@ _base_assign_reply_queues(struct MPT3SAS_ADAPTER *ioc)
* corresponding to high iops queues.
*/
if (ioc->high_iops_queues) {
- local_numa_node = dev_to_node(&ioc->pdev->dev);
+ mask = cpumask_of_node(dev_to_node(&ioc->pdev->dev));
for (index = 0; index < ioc->high_iops_queues;
index++) {
- irq_set_affinity_hint(pci_irq_vector(ioc->pdev,
- index), cpumask_of_node(local_numa_node));
+ irq = pci_irq_vector(ioc->pdev, index);
+ irq_set_affinity_and_hint(irq, mask);
}
}
--
2.27.0
next prev parent reply other threads:[~2021-07-13 21:16 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-13 21:14 [PATCH v3 00/14] genirq: Cleanup the usage of irq_set_affinity_hint Nitesh Narayan Lal
2021-07-13 21:14 ` [Intel-wired-lan] " Nitesh Narayan Lal
2021-07-13 21:14 ` [PATCH v3 01/14] genirq: Provide new interfaces for affinity hints Nitesh Narayan Lal
2021-07-13 21:14 ` [Intel-wired-lan] " Nitesh Narayan Lal
2021-07-13 21:14 ` [PATCH v3 02/14] iavf: Use irq_update_affinity_hint Nitesh Narayan Lal
2021-07-13 21:14 ` [Intel-wired-lan] " Nitesh Narayan Lal
2021-07-13 21:51 ` Jesse Brandeburg
2021-07-13 21:51 ` [Intel-wired-lan] " Jesse Brandeburg
2021-07-13 21:14 ` [PATCH v3 03/14] i40e: " Nitesh Narayan Lal
2021-07-13 21:14 ` [Intel-wired-lan] " Nitesh Narayan Lal
2021-07-13 21:52 ` Jesse Brandeburg
2021-07-13 21:52 ` [Intel-wired-lan] " Jesse Brandeburg
2021-07-13 21:14 ` [PATCH v3 04/14] scsi: megaraid_sas: Use irq_set_affinity_and_hint Nitesh Narayan Lal
2021-07-13 21:14 ` [Intel-wired-lan] " Nitesh Narayan Lal
2021-07-13 21:14 ` Nitesh Narayan Lal [this message]
2021-07-13 21:14 ` [Intel-wired-lan] [PATCH v3 05/14] scsi: mpt3sas: " Nitesh Narayan Lal
2021-07-13 21:14 ` [PATCH v3 06/14] RDMA/irdma: " Nitesh Narayan Lal
2021-07-13 21:14 ` [Intel-wired-lan] " Nitesh Narayan Lal
2021-07-14 12:03 ` Leon Romanovsky
2021-07-14 12:03 ` [Intel-wired-lan] " Leon Romanovsky
2021-07-14 12:56 ` Nitesh Lal
2021-07-14 12:56 ` [Intel-wired-lan] " Nitesh Lal
2021-07-14 13:02 ` Leon Romanovsky
2021-07-14 13:02 ` [Intel-wired-lan] " Leon Romanovsky
2021-07-15 13:25 ` Nitesh Lal
2021-07-15 13:25 ` [Intel-wired-lan] " Nitesh Lal
2021-07-13 21:14 ` [PATCH v3 07/14] enic: Use irq_update_affinity_hint Nitesh Narayan Lal
2021-07-13 21:14 ` [Intel-wired-lan] " Nitesh Narayan Lal
2021-07-13 21:14 ` [PATCH v3 08/14] be2net: " Nitesh Narayan Lal
2021-07-13 21:14 ` [Intel-wired-lan] " Nitesh Narayan Lal
2021-07-13 21:14 ` [PATCH v3 09/14] ixgbe: " Nitesh Narayan Lal
2021-07-13 21:14 ` [Intel-wired-lan] " Nitesh Narayan Lal
2021-07-13 22:01 ` Jesse Brandeburg
2021-07-13 22:01 ` [Intel-wired-lan] " Jesse Brandeburg
2021-07-13 21:14 ` [PATCH v3 10/14] mailbox: " Nitesh Narayan Lal
2021-07-13 21:14 ` [Intel-wired-lan] " Nitesh Narayan Lal
2021-07-13 21:14 ` [PATCH v3 11/14] scsi: lpfc: Use irq_set_affinity Nitesh Narayan Lal
2021-07-13 21:14 ` [Intel-wired-lan] " Nitesh Narayan Lal
2021-07-13 21:15 ` [PATCH v3 12/14] hinic: Use irq_set_affinity_and_hint Nitesh Narayan Lal
2021-07-13 21:15 ` [Intel-wired-lan] " Nitesh Narayan Lal
2021-07-13 21:15 ` [PATCH v3 13/14] net/mlx5: " Nitesh Narayan Lal
2021-07-13 21:15 ` [Intel-wired-lan] " Nitesh Narayan Lal
2021-07-14 12:01 ` Leon Romanovsky
2021-07-14 12:01 ` [Intel-wired-lan] " Leon Romanovsky
2021-07-13 21:15 ` [PATCH v3 14/14] net/mlx4: Use irq_update_affinity_hint Nitesh Narayan Lal
2021-07-13 21:15 ` [Intel-wired-lan] " Nitesh Narayan Lal
2021-07-14 11:19 ` Tariq Toukan
2021-07-14 11:19 ` [Intel-wired-lan] " Tariq Toukan
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=20210713211502.464259-6-nitesh@redhat.com \
--to=nitesh@redhat.com \
--cc=abelits@marvell.com \
--cc=ahleihel@redhat.com \
--cc=ahs3@redhat.com \
--cc=ajit.khaparde@broadcom.com \
--cc=akpm@linux-foundation.org \
--cc=benve@cisco.com \
--cc=bhelgaas@google.com \
--cc=borisp@nvidia.com \
--cc=chandrakanth.patil@broadcom.com \
--cc=chris.friesen@windriver.com \
--cc=davem@davemloft.net \
--cc=dick.kennedy@broadcom.com \
--cc=faisal.latif@intel.com \
--cc=frederic@kernel.org \
--cc=govind@gmx.com \
--cc=intel-wired-lan@lists.osuosl.org \
--cc=james.smart@broadcom.com \
--cc=jassisinghbrar@gmail.com \
--cc=jbrandeb@kernel.org \
--cc=jesse.brandeburg@intel.com \
--cc=jkc@redhat.com \
--cc=juri.lelli@redhat.com \
--cc=kashyap.desai@broadcom.com \
--cc=kheib@redhat.com \
--cc=leonro@nvidia.com \
--cc=linux-api@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=maz@kernel.org \
--cc=mingo@kernel.org \
--cc=mtosatti@redhat.com \
--cc=mustafa.ismail@intel.com \
--cc=netdev@vger.kernel.org \
--cc=nhorman@tuxdriver.com \
--cc=nilal@redhat.com \
--cc=peterz@infradead.org \
--cc=pjwaskiewicz@gmail.com \
--cc=robin.murphy@arm.com \
--cc=rostedt@goodmis.org \
--cc=rppt@linux.vnet.ibm.com \
--cc=saeedm@nvidia.com \
--cc=sassmann@redhat.com \
--cc=sathya.prakash@broadcom.com \
--cc=sfr@canb.auug.org.au \
--cc=shiraz.saleem@intel.com \
--cc=shivasharan.srikanteshwara@broadcom.com \
--cc=somnath.kotur@broadcom.com \
--cc=sreekanth.reddy@broadcom.com \
--cc=sriharsha.basavapatna@broadcom.com \
--cc=stephen@networkplumber.org \
--cc=suganath-prabu.subramani@broadcom.com \
--cc=sumit.saxena@broadcom.com \
--cc=tariqt@nvidia.com \
--cc=tatyana.e.nikolova@intel.com \
--cc=tglx@linutronix.de \
--cc=thenzl@redhat.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.