Messages in this thread Patch in this message | | | From | Alexander Gordeev <> | Subject | [PATCH 01/14] NVMe: Fix setup of affinity hint for unallocated queues | Date | Tue, 28 Jan 2014 09:38:47 +0100 |
| |
IRQ affinity hints are attempted to setup for some or all queues which have not yet been allocated: either on device probe or resume. This update moves the setup after all queues are successfully created.
Signed-off-by: Alexander Gordeev <agordeev@redhat.com> --- drivers/block/nvme-core.c | 12 ++++++------ 1 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c index b59a93a..3dfb0d4 100644 --- a/drivers/block/nvme-core.c +++ b/drivers/block/nvme-core.c @@ -1956,12 +1956,6 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) } spin_unlock(&dev_list_lock); - cpu = cpumask_first(cpu_online_mask); - for (i = 0; i < nr_io_queues; i++) { - irq_set_affinity_hint(dev->entry[i].vector, get_cpu_mask(cpu)); - cpu = cpumask_next(cpu, cpu_online_mask); - } - q_depth = min_t(int, NVME_CAP_MQES(readq(&dev->bar->cap)) + 1, NVME_Q_DEPTH); for (i = dev->queue_count - 1; i < nr_io_queues; i++) { @@ -1986,6 +1980,12 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) } } + cpu = cpumask_first(cpu_online_mask); + for (i = 0; i < nr_io_queues; i++) { + irq_set_affinity_hint(dev->entry[i].vector, get_cpu_mask(cpu)); + cpu = cpumask_next(cpu, cpu_online_mask); + } + return 0; free_queues: -- 1.7.7.6
| |