aboutsummaryrefslogtreecommitdiffstats
diff options
authorJens Axboe <axboe@kernel.dk>2025-07-01 10:24:39 -0600
committerJens Axboe <axboe@kernel.dk>2025-07-01 10:24:39 -0600
commit32f85e8468ce081d8e73ca3f0d588f1004013037 (patch)
treefe933e0db5698d11ea9d5251a793c4d74926d043
parentdf3f9755452c704df48ecb1ce5ac9095e0ba856b (diff)
parent0a50ed0574ffe853f15c3430794b5439b2e6150a (diff)
downloadlinux-block-for-next.tar.gz
Merge branch 'for-6.17/block' into for-nextfor-next
* for-6.17/block: virtio: blk/scsi: use block layer helpers to calculate num of queues scsi: use block layer helpers to calculate num of queues nvme-pci: use block layer helpers to calculate num of queues blk-mq: add number of queue calc helper lib/group_cpus: Let group_cpu_evenly() return the number of initialized masks
Diffstat
-rw-r--r--block/blk-mq-cpumap.c46
-rw-r--r--drivers/block/virtio_blk.c5
-rw-r--r--drivers/nvme/host/pci.c5
-rw-r--r--drivers/scsi/megaraid/megaraid_sas_base.c15
-rw-r--r--drivers/scsi/qla2xxx/qla_isr.c10
-rw-r--r--drivers/scsi/smartpqi/smartpqi_init.c5
-rw-r--r--drivers/scsi/virtio_scsi.c1
-rw-r--r--drivers/virtio/virtio_vdpa.c9
-rw-r--r--fs/fuse/virtio_fs.c6
-rw-r--r--include/linux/blk-mq.h2
-rw-r--r--include/linux/group_cpus.h2
-rw-r--r--kernel/irq/affinity.c11
-rw-r--r--lib/group_cpus.c16
13 files changed, 89 insertions, 44 deletions
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 444798c5374f48..705da074ad6c7e 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -12,16 +12,56 @@
#include <linux/cpu.h>
#include <linux/group_cpus.h>
#include <linux/device/bus.h>
+#include <linux/sched/isolation.h>
#include "blk.h"
#include "blk-mq.h"
+static unsigned int blk_mq_num_queues(const struct cpumask *mask,
+ unsigned int max_queues)
+{
+ unsigned int num;
+
+ num = cpumask_weight(mask);
+ return min_not_zero(num, max_queues);
+}
+
+/**
+ * blk_mq_num_possible_queues - Calc nr of queues for multiqueue devices
+ * @max_queues: The maximum number of queues the hardware/driver
+ * supports. If max_queues is 0, the argument is
+ * ignored.
+ *
+ * Calculates the number of queues to be used for a multiqueue
+ * device based on the number of possible CPUs.
+ */
+unsigned int blk_mq_num_possible_queues(unsigned int max_queues)
+{
+ return blk_mq_num_queues(cpu_possible_mask, max_queues);
+}
+EXPORT_SYMBOL_GPL(blk_mq_num_possible_queues);
+
+/**
+ * blk_mq_num_online_queues - Calc nr of queues for multiqueue devices
+ * @max_queues: The maximum number of queues the hardware/driver
+ * supports. If max_queues is 0, the argument is
+ * ignored.
+ *
+ * Calculates the number of queues to be used for a multiqueue
+ * device based on the number of online CPUs.
+ */
+unsigned int blk_mq_num_online_queues(unsigned int max_queues)
+{
+ return blk_mq_num_queues(cpu_online_mask, max_queues);
+}
+EXPORT_SYMBOL_GPL(blk_mq_num_online_queues);
+
void blk_mq_map_queues(struct blk_mq_queue_map *qmap)
{
const struct cpumask *masks;
- unsigned int queue, cpu;
+ unsigned int queue, cpu, nr_masks;
- masks = group_cpus_evenly(qmap->nr_queues);
+ masks = group_cpus_evenly(qmap->nr_queues, &nr_masks);
if (!masks) {
for_each_possible_cpu(cpu)
qmap->mq_map[cpu] = qmap->queue_offset;
@@ -29,7 +69,7 @@ void blk_mq_map_queues(struct blk_mq_queue_map *qmap)
}
for (queue = 0; queue < qmap->nr_queues; queue++) {
- for_each_cpu(cpu, &masks[queue])
+ for_each_cpu(cpu, &masks[queue % nr_masks])
qmap->mq_map[cpu] = qmap->queue_offset + queue;
}
kfree(masks);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 30bca8cb710604..e649fa67bac16b 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -976,9 +976,8 @@ static int init_vq(struct virtio_blk *vblk)
return -EINVAL;
}
- num_vqs = min_t(unsigned int,
- min_not_zero(num_request_queues, nr_cpu_ids),
- num_vqs);
+ num_vqs = blk_mq_num_possible_queues(
+ min_not_zero(num_request_queues, num_vqs));
num_poll_vqs = min_t(unsigned int, poll_queues, num_vqs - 1);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 38be1505dbd963..a509dc1f1d1400 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -108,7 +108,7 @@ static int io_queue_count_set(const char *val, const struct kernel_param *kp)
int ret;
ret = kstrtouint(val, 10, &n);
- if (ret != 0 || n > num_possible_cpus())
+ if (ret != 0 || n > blk_mq_num_possible_queues(0))
return -EINVAL;
return param_set_uint(val, kp);
}
@@ -2629,7 +2629,8 @@ static unsigned int nvme_max_io_queues(struct nvme_dev *dev)
*/
if (dev->ctrl.quirks & NVME_QUIRK_SHARED_TAGS)
return 1;
- return num_possible_cpus() + dev->nr_write_queues + dev->nr_poll_queues;
+ return blk_mq_num_possible_queues(0) + dev->nr_write_queues +
+ dev->nr_poll_queues;
}
static int nvme_setup_io_queues(struct nvme_dev *dev)
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 9179f8aee96444..615e06fd4ee8e5 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -5971,7 +5971,8 @@ megasas_alloc_irq_vectors(struct megasas_instance *instance)
else
instance->iopoll_q_count = 0;
- num_msix_req = num_online_cpus() + instance->low_latency_index_start;
+ num_msix_req = blk_mq_num_online_queues(0) +
+ instance->low_latency_index_start;
instance->msix_vectors = min(num_msix_req,
instance->msix_vectors);
@@ -5987,7 +5988,8 @@ megasas_alloc_irq_vectors(struct megasas_instance *instance)
/* Disable Balanced IOPS mode and try realloc vectors */
instance->perf_mode = MR_LATENCY_PERF_MODE;
instance->low_latency_index_start = 1;
- num_msix_req = num_online_cpus() + instance->low_latency_index_start;
+ num_msix_req = blk_mq_num_online_queues(0) +
+ instance->low_latency_index_start;
instance->msix_vectors = min(num_msix_req,
instance->msix_vectors);
@@ -6243,7 +6245,7 @@ static int megasas_init_fw(struct megasas_instance *instance)
intr_coalescing = (scratch_pad_1 & MR_INTR_COALESCING_SUPPORT_OFFSET) ?
true : false;
if (intr_coalescing &&
- (num_online_cpus() >= MR_HIGH_IOPS_QUEUE_COUNT) &&
+ (blk_mq_num_online_queues(0) >= MR_HIGH_IOPS_QUEUE_COUNT) &&
(instance->msix_vectors == MEGASAS_MAX_MSIX_QUEUES))
instance->perf_mode = MR_BALANCED_PERF_MODE;
else
@@ -6287,7 +6289,8 @@ static int megasas_init_fw(struct megasas_instance *instance)
else
instance->low_latency_index_start = 1;
- num_msix_req = num_online_cpus() + instance->low_latency_index_start;
+ num_msix_req = blk_mq_num_online_queues(0) +
+ instance->low_latency_index_start;
instance->msix_vectors = min(num_msix_req,
instance->msix_vectors);
@@ -6319,8 +6322,8 @@ static int megasas_init_fw(struct megasas_instance *instance)
megasas_setup_reply_map(instance);
dev_info(&instance->pdev->dev,
- "current msix/online cpus\t: (%d/%d)\n",
- instance->msix_vectors, (unsigned int)num_online_cpus());
+ "current msix/max num queues\t: (%d/%u)\n",
+ instance->msix_vectors, blk_mq_num_online_queues(0));
dev_info(&instance->pdev->dev,
"RDPQ mode\t: (%s)\n", instance->is_rdpq ? "enabled" : "disabled");
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index fe98c76e9be32f..c4c6b5c6658c07 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -4533,13 +4533,13 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
if (USER_CTRL_IRQ(ha) || !ha->mqiobase) {
/* user wants to control IRQ setting for target mode */
ret = pci_alloc_irq_vectors(ha->pdev, min_vecs,
- min((u16)ha->msix_count, (u16)(num_online_cpus() + min_vecs)),
- PCI_IRQ_MSIX);
+ blk_mq_num_online_queues(ha->msix_count) + min_vecs,
+ PCI_IRQ_MSIX);
} else
ret = pci_alloc_irq_vectors_affinity(ha->pdev, min_vecs,
- min((u16)ha->msix_count, (u16)(num_online_cpus() + min_vecs)),
- PCI_IRQ_MSIX | PCI_IRQ_AFFINITY,
- &desc);
+ blk_mq_num_online_queues(ha->msix_count) + min_vecs,
+ PCI_IRQ_MSIX | PCI_IRQ_AFFINITY,
+ &desc);
if (ret < 0) {
ql_log(ql_log_fatal, vha, 0x00c7,
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 3d40a63e378d79..125944941601e6 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -5294,15 +5294,14 @@ static void pqi_calculate_queue_resources(struct pqi_ctrl_info *ctrl_info)
if (is_kdump_kernel()) {
num_queue_groups = 1;
} else {
- int num_cpus;
int max_queue_groups;
max_queue_groups = min(ctrl_info->max_inbound_queues / 2,
ctrl_info->max_outbound_queues - 1);
max_queue_groups = min(max_queue_groups, PQI_MAX_QUEUE_GROUPS);
- num_cpus = num_online_cpus();
- num_queue_groups = min(num_cpus, ctrl_info->max_msix_vectors);
+ num_queue_groups =
+ blk_mq_num_online_queues(ctrl_info->max_msix_vectors);
num_queue_groups = min(num_queue_groups, max_queue_groups);
}
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 21ce3e9401929c..96a69edddbe555 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -919,6 +919,7 @@ static int virtscsi_probe(struct virtio_device *vdev)
/* We need to know how many queues before we allocate. */
num_queues = virtscsi_config_get(vdev, num_queues) ? : 1;
num_queues = min_t(unsigned int, nr_cpu_ids, num_queues);
+ num_queues = blk_mq_num_possible_queues(num_queues);
num_targets = virtscsi_config_get(vdev, max_target) + 1;
diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c
index 1f60c9d5cb1810..a7b297dae4890c 100644
--- a/drivers/virtio/virtio_vdpa.c
+++ b/drivers/virtio/virtio_vdpa.c
@@ -329,20 +329,21 @@ create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd)
for (i = 0, usedvecs = 0; i < affd->nr_sets; i++) {
unsigned int this_vecs = affd->set_size[i];
+ unsigned int nr_masks;
int j;
- struct cpumask *result = group_cpus_evenly(this_vecs);
+ struct cpumask *result = group_cpus_evenly(this_vecs, &nr_masks);
if (!result) {
kfree(masks);
return NULL;
}
- for (j = 0; j < this_vecs; j++)
+ for (j = 0; j < nr_masks; j++)
cpumask_copy(&masks[curvec + j], &result[j]);
kfree(result);
- curvec += this_vecs;
- usedvecs += this_vecs;
+ curvec += nr_masks;
+ usedvecs += nr_masks;
}
/* Fill out vectors at the end that don't need affinity */
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 53c2626e90e723..3fbfb1a2942b75 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -862,7 +862,7 @@ static void virtio_fs_requests_done_work(struct work_struct *work)
static void virtio_fs_map_queues(struct virtio_device *vdev, struct virtio_fs *fs)
{
const struct cpumask *mask, *masks;
- unsigned int q, cpu;
+ unsigned int q, cpu, nr_masks;
/* First attempt to map using existing transport layer affinities
* e.g. PCIe MSI-X
@@ -882,7 +882,7 @@ static void virtio_fs_map_queues(struct virtio_device *vdev, struct virtio_fs *f
return;
fallback:
/* Attempt to map evenly in groups over the CPUs */
- masks = group_cpus_evenly(fs->num_request_queues);
+ masks = group_cpus_evenly(fs->num_request_queues, &nr_masks);
/* If even this fails we default to all CPUs use first request queue */
if (!masks) {
for_each_possible_cpu(cpu)
@@ -891,7 +891,7 @@ fallback:
}
for (q = 0; q < fs->num_request_queues; q++) {
- for_each_cpu(cpu, &masks[q])
+ for_each_cpu(cpu, &masks[q % nr_masks])
fs->mq_map[cpu] = q + VQ_REQUEST;
}
kfree(masks);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index de8c85a03bb7f4..2a5a828f19a0ba 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -947,6 +947,8 @@ int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
void blk_mq_unfreeze_queue_non_owner(struct request_queue *q);
void blk_freeze_queue_start_non_owner(struct request_queue *q);
+unsigned int blk_mq_num_possible_queues(unsigned int max_queues);
+unsigned int blk_mq_num_online_queues(unsigned int max_queues);
void blk_mq_map_queues(struct blk_mq_queue_map *qmap);
void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap,
struct device *dev, unsigned int offset);
diff --git a/include/linux/group_cpus.h b/include/linux/group_cpus.h
index e42807ec61f6e8..9d4e5ab6c314b3 100644
--- a/include/linux/group_cpus.h
+++ b/include/linux/group_cpus.h
@@ -9,6 +9,6 @@
#include <linux/kernel.h>
#include <linux/cpu.h>
-struct cpumask *group_cpus_evenly(unsigned int numgrps);
+struct cpumask *group_cpus_evenly(unsigned int numgrps, unsigned int *nummasks);
#endif
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index 44a4eba80315cc..4013e6ad2b2f1c 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -69,21 +69,20 @@ irq_create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd)
* have multiple sets, build each sets affinity mask separately.
*/
for (i = 0, usedvecs = 0; i < affd->nr_sets; i++) {
- unsigned int this_vecs = affd->set_size[i];
- int j;
- struct cpumask *result = group_cpus_evenly(this_vecs);
+ unsigned int nr_masks, this_vecs = affd->set_size[i];
+ struct cpumask *result = group_cpus_evenly(this_vecs, &nr_masks);
if (!result) {
kfree(masks);
return NULL;
}
- for (j = 0; j < this_vecs; j++)
+ for (int j = 0; j < nr_masks; j++)
cpumask_copy(&masks[curvec + j].mask, &result[j]);
kfree(result);
- curvec += this_vecs;
- usedvecs += this_vecs;
+ curvec += nr_masks;
+ usedvecs += nr_masks;
}
/* Fill out vectors at the end that don't need affinity */
diff --git a/lib/group_cpus.c b/lib/group_cpus.c
index 18d43a406114b9..6d08ac05f371bf 100644
--- a/lib/group_cpus.c
+++ b/lib/group_cpus.c
@@ -332,9 +332,11 @@ static int __group_cpus_evenly(unsigned int startgrp, unsigned int numgrps,
/**
* group_cpus_evenly - Group all CPUs evenly per NUMA/CPU locality
* @numgrps: number of groups
+ * @nummasks: number of initialized cpumasks
*
* Return: cpumask array if successful, NULL otherwise. And each element
- * includes CPUs assigned to this group
+ * includes CPUs assigned to this group. nummasks contains the number
+ * of initialized masks which can be less than numgrps.
*
* Try to put close CPUs from viewpoint of CPU and NUMA locality into
* same group, and run two-stage grouping:
@@ -344,7 +346,7 @@ static int __group_cpus_evenly(unsigned int startgrp, unsigned int numgrps,
* We guarantee in the resulted grouping that all CPUs are covered, and
* no same CPU is assigned to multiple groups
*/
-struct cpumask *group_cpus_evenly(unsigned int numgrps)
+struct cpumask *group_cpus_evenly(unsigned int numgrps, unsigned int *nummasks)
{
unsigned int curgrp = 0, nr_present = 0, nr_others = 0;
cpumask_var_t *node_to_cpumask;
@@ -389,7 +391,7 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask,
npresmsk, nmsk, masks);
if (ret < 0)
- goto fail_build_affinity;
+ goto fail_node_to_cpumask;
nr_present = ret;
/*
@@ -408,10 +410,6 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
if (ret >= 0)
nr_others = ret;
- fail_build_affinity:
- if (ret >= 0)
- WARN_ON(nr_present + nr_others < numgrps);
-
fail_node_to_cpumask:
free_node_to_cpumask(node_to_cpumask);
@@ -424,10 +422,11 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
kfree(masks);
return NULL;
}
+ *nummasks = min(nr_present + nr_others, numgrps);
return masks;
}
#else /* CONFIG_SMP */
-struct cpumask *group_cpus_evenly(unsigned int numgrps)
+struct cpumask *group_cpus_evenly(unsigned int numgrps, unsigned int *nummasks)
{
struct cpumask *masks;
@@ -440,6 +439,7 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
/* assign all CPUs(cpu 0) to the 1st group only */
cpumask_copy(&masks[0], cpu_possible_mask);
+ *nummasks = 1;
return masks;
}
#endif /* CONFIG_SMP */
generated by cgit 1.2.3-korg (git 2.43.0) at 2025-07-02 07:00:59 +0000