nvme: Cleanup nvme_dev_start() and fix IRQ leak

This is an attempt to make handling of admin queue in a
single scope. This update also fixes a IRQ leak in case
nvme_setup_io_queues() failed to allocate enough iomem
and bailed out with -ENOMEM errno.

Signed-off-by: Alexander Gordeev <agordeev@redhat.com>
---
 drivers/block/nvme-core.c |   44 +++++++++++++++++++++++---------------------
 1 files changed, 23 insertions(+), 21 deletions(-)

On Mon, 20 Jan 2014, Alexander Gordeev wrote:
> This is an attempt to make handling of admin queue in a
> single scope. This update also fixes a IRQ leak in case
> nvme_setup_io_queues() failed to allocate enough iomem
> and bailed out with -ENOMEM errno.

This definitely seems to improve the code flow, but this leak was already
fixed in the latest linux-nvme tree with this commit:

http://git.infradead.org/users/willy/linux-nvme.git/commit/c5dc9192d52a4a3a479f701e97386347d454af84

> Signed-off-by: Alexander Gordeev <agordeev@redhat.com>
> ---
> drivers/block/nvme-core.c |   44 +++++++++++++++++++++++---------------------
> 1 files changed, 23 insertions(+), 21 deletions(-)
>
> diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
> index 3e1ae55..e1e4ad4 100644
> --- a/drivers/block/nvme-core.c
> +++ b/drivers/block/nvme-core.c
> @@ -1287,6 +1287,7 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
> 	if (result)
> 		return result;
>
> +	dev->entry[0].vector = pdev->pci_dev->irq;
> 	result = queue_request_irq(dev, nvmeq, "nvme admin");
> 	if (result)
> 		return result;
> @@ -1297,6 +1298,11 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
> 	return result;
> }
>
> +static int nvme_teardown_admin_queue(struct nvme_dev *dev)
> +{
> +	free_irq(dev->entry[0].vector, dev->queues[0]);
> +}
> +
> struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
> 				unsigned long addr, unsigned length)
> {
> @@ -1744,17 +1750,10 @@ static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
> 	return 4096 + ((nr_io_queues + 1) << (dev->db_stride + 3));
> }
>
> -static int nvme_setup_io_queues(struct nvme_dev *dev)
> +static int nvme_setup_io_queues(struct nvme_dev *dev, int nr_io_queues)
> {
> 	struct pci_dev *pdev = dev->pci_dev;
> -	int result, cpu, i, vecs, nr_io_queues, size, q_depth;
> -
> -	nr_io_queues = num_online_cpus();
> -	result = set_queue_count(dev, nr_io_queues);
> -	if (result < 0)
> -		return result;
> -	if (result < nr_io_queues)
> -		nr_io_queues = result;
> +	int result, cpu, i, vecs, size, q_depth;
>
> 	size = db_bar_size(dev, nr_io_queues);
> 	if (size > 8192) {
> @@ -1771,20 +1770,15 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
> 		dev->queues[0]->q_db = dev->dbs;
> 	}
>
> -	/* Deregister the admin queue's interrupt */
> -	free_irq(dev->entry[0].vector, dev->queues[0]);
> -
> 	for (i = 0; i < nr_io_queues; i++)
> 		dev->entry[i].entry = i;
> 	vecs = pci_enable_msix_range(pdev, dev->entry, 1, nr_io_queues);
> 	if (vecs < 0) {
> 		vecs = pci_enable_msi_range(pdev, 1, min(nr_io_queues, 32));
> -		if (vecs < 0) {
> +		if (vecs < 0)
> 			vecs = 1;
> -		} else {
> -			for (i = 0; i < vecs; i++)
> -				dev->entry[i].vector = i + pdev->irq;
> -		}
> +		for (i = 0; i < vecs; i++)
> +			dev->entry[i].vector = i + pdev->irq;
> 	}
>
> 	/*
> @@ -1928,7 +1922,6 @@ static int nvme_dev_map(struct nvme_dev *dev)
> 	if (pci_enable_device_mem(pdev))
> 		return result;
>
> -	dev->entry[0].vector = pdev->irq;
> 	pci_set_master(pdev);
> 	bars = pci_select_bars(pdev, IORESOURCE_MEM);
> 	if (pci_request_selected_regions(pdev, bars, "nvme"))
> @@ -2116,11 +2109,20 @@ static int nvme_dev_start(struct nvme_dev *dev)
> 	list_add(&dev->node, &dev_list);
> 	spin_unlock(&dev_list_lock);
>
> -	result = nvme_setup_io_queues(dev);
> -	if (result && result != -EBUSY)
> +	result = set_queue_count(dev, num_online_cpus());
> +	if (result == -EBUSY)
> +		return -EBUSY;
> +
> +	nvme_teardown_admin_queue(dev);
> +
> +	if (result)
> 		goto disable;
>
> -	return result;
> +	result = nvme_setup_io_queues(dev, result);
> +	if (result)
> +		goto disable;
> +
> +	return 0;
>
>  disable:
> 	spin_lock(&dev_list_lock);
> --
--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

On Mon, Jan 20, 2014 at 03:48:56PM -0700, Keith Busch wrote:
> On Mon, 20 Jan 2014, Alexander Gordeev wrote:
> >This is an attempt to make handling of admin queue in a
> >single scope. This update also fixes a IRQ leak in case
> >nvme_setup_io_queues() failed to allocate enough iomem
> >and bailed out with -ENOMEM errno.
> 
> This definitely seems to improve the code flow, but this leak was already
> fixed in the latest linux-nvme tree with this commit:
> 
> http://git.infradead.org/users/willy/linux-nvme.git/commit/c5dc9192d52a4a3a479f701e97386347d454af84

Oh, that one seems to complicate things even further to me.
Whould you consider the revert?
Sending an improved version against your tree.