All of lore.kernel.org
 help / color / mirror / Atom feed
From: Alexander Gordeev <agordeev@redhat.com>
To: Christoph Hellwig <hch@lst.de>
Cc: tglx@linutronix.de, axboe@fb.com, linux-block@vger.kernel.org,
	linux-pci@vger.kernel.org, linux-nvme@lists.infradead.org,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH 08/13] pci: spread interrupt vectors in pci_alloc_irq_vectors
Date: Sat, 25 Jun 2016 22:22:49 +0200	[thread overview]
Message-ID: <20160625202249.GB29251@dhcp-27-118.brq.redhat.com> (raw)
In-Reply-To: <1465934346-20648-9-git-send-email-hch@lst.de>

On Tue, Jun 14, 2016 at 09:59:01PM +0200, Christoph Hellwig wrote:
> Set the affinity_mask before allocating vectors.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
>  drivers/pci/msi.c   | 26 ++++++++++++++++++++++++--
>  include/linux/pci.h |  1 +
>  2 files changed, 25 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
> index a33adec..50d694c 100644
> --- a/drivers/pci/msi.c
> +++ b/drivers/pci/msi.c
> @@ -568,6 +568,7 @@ static struct msi_desc *msi_setup_entry(struct pci_dev *dev, int nvec)
>  	entry->msi_attrib.multi_cap	= (control & PCI_MSI_FLAGS_QMASK) >> 1;
>  	entry->msi_attrib.multiple	= ilog2(__roundup_pow_of_two(nvec));
>  	entry->nvec_used		= nvec;
> +	entry->affinity			= dev->irq_affinity;
>  
>  	if (control & PCI_MSI_FLAGS_64BIT)
>  		entry->mask_pos = dev->msi_cap + PCI_MSI_MASK_64;
> @@ -679,10 +680,18 @@ static void __iomem *msix_map_region(struct pci_dev *dev, unsigned nr_entries)
>  static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
>  			      struct msix_entry *entries, int nvec)
>  {
> +	const struct cpumask *mask = NULL;
>  	struct msi_desc *entry;
> -	int i;
> +	int cpu = -1, i;
>  
>  	for (i = 0; i < nvec; i++) {
> +		if (dev->irq_affinity) {
> +			cpu = cpumask_next(cpu, dev->irq_affinity);
> +			if (cpu >= nr_cpu_ids)
> +				cpu = cpumask_first(dev->irq_affinity);
> +			mask = cpumask_of(cpu);
> +		}
> +
>  		entry = alloc_msi_entry(&dev->dev);
>  		if (!entry) {
>  			if (!i)
> @@ -699,6 +708,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
>  		entry->msi_attrib.default_irq	= dev->irq;
>  		entry->mask_base		= base;
>  		entry->nvec_used		= 1;
> +		entry->affinity			= mask;
>  
>  		list_add_tail(&entry->list, dev_to_msi_list(&dev->dev));
>  	}
> @@ -1176,12 +1186,20 @@ int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs,
>  {
>  	unsigned int vecs, i;
>  	u32 *irqs;
> +	int ret;
>  
>  	max_vecs = min(max_vecs, pci_nr_irq_vectors(dev));
>  
> +	ret = irq_create_affinity_mask(&dev->irq_affinity, &max_vecs);

	dev->irq_affinity = irq_create_affinity_mask(&max_vecs); ?


> +	if (ret)
> +		return ret;
> +	if (max_vecs < min_vecs)
> +		return -ENOSPC;

irq_create_affinity_mask() should be called after MSI-X/MSI is enabled,
because we do not know number of vectors before the range functions
returned that number.

Since affinity masks is a function of number of vectors and CPU topology
the resulting masks might turn out suboptimal in general case (and
this code supposed to be general, right?).

I.e irq_create_affinity_mask() could decide "per-first-sibling" spreading
given number of available vectors, but only a subset of MSI vectors
were actually allocated. For that subset "per-core" affinity mask could
have been initialized, but we will still go with "per-first-sibling".

> +	ret = -ENOMEM;
>  	irqs = kcalloc(max_vecs, sizeof(u32), GFP_KERNEL);
>  	if (!irqs)
> -		return -ENOMEM;
> +		goto out_free_affinity;
>  
>  	if (!(flags & PCI_IRQ_NOMSIX)) {
>  		vecs = pci_enable_msix_range_wrapper(dev, irqs, min_vecs,
> @@ -1208,6 +1226,10 @@ int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs,
>  done:
>  	dev->irqs = irqs;
>  	return vecs;
> +out_free_affinity:
> +	kfree(dev->irq_affinity);
> +	dev->irq_affinity = NULL;
> +	return ret;
>  }
>  EXPORT_SYMBOL(pci_alloc_irq_vectors);
>  
> diff --git a/include/linux/pci.h b/include/linux/pci.h
> index 84a20fc..f474611 100644
> --- a/include/linux/pci.h
> +++ b/include/linux/pci.h
> @@ -321,6 +321,7 @@ struct pci_dev {
>  	 */
>  	unsigned int	irq;
>  	unsigned int	*irqs;
> +	struct cpumask	*irq_affinity;
>  	struct resource resource[DEVICE_COUNT_RESOURCE]; /* I/O and memory regions + expansion ROMs */
>  
>  	bool match_driver;		/* Skip attaching driver */
> -- 
> 2.1.4
> 

WARNING: multiple messages have this Message-ID (diff)
From: agordeev@redhat.com (Alexander Gordeev)
Subject: [PATCH 08/13] pci: spread interrupt vectors in pci_alloc_irq_vectors
Date: Sat, 25 Jun 2016 22:22:49 +0200	[thread overview]
Message-ID: <20160625202249.GB29251@dhcp-27-118.brq.redhat.com> (raw)
In-Reply-To: <1465934346-20648-9-git-send-email-hch@lst.de>

On Tue, Jun 14, 2016@09:59:01PM +0200, Christoph Hellwig wrote:
> Set the affinity_mask before allocating vectors.
> 
> Signed-off-by: Christoph Hellwig <hch at lst.de>
> ---
>  drivers/pci/msi.c   | 26 ++++++++++++++++++++++++--
>  include/linux/pci.h |  1 +
>  2 files changed, 25 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
> index a33adec..50d694c 100644
> --- a/drivers/pci/msi.c
> +++ b/drivers/pci/msi.c
> @@ -568,6 +568,7 @@ static struct msi_desc *msi_setup_entry(struct pci_dev *dev, int nvec)
>  	entry->msi_attrib.multi_cap	= (control & PCI_MSI_FLAGS_QMASK) >> 1;
>  	entry->msi_attrib.multiple	= ilog2(__roundup_pow_of_two(nvec));
>  	entry->nvec_used		= nvec;
> +	entry->affinity			= dev->irq_affinity;
>  
>  	if (control & PCI_MSI_FLAGS_64BIT)
>  		entry->mask_pos = dev->msi_cap + PCI_MSI_MASK_64;
> @@ -679,10 +680,18 @@ static void __iomem *msix_map_region(struct pci_dev *dev, unsigned nr_entries)
>  static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
>  			      struct msix_entry *entries, int nvec)
>  {
> +	const struct cpumask *mask = NULL;
>  	struct msi_desc *entry;
> -	int i;
> +	int cpu = -1, i;
>  
>  	for (i = 0; i < nvec; i++) {
> +		if (dev->irq_affinity) {
> +			cpu = cpumask_next(cpu, dev->irq_affinity);
> +			if (cpu >= nr_cpu_ids)
> +				cpu = cpumask_first(dev->irq_affinity);
> +			mask = cpumask_of(cpu);
> +		}
> +
>  		entry = alloc_msi_entry(&dev->dev);
>  		if (!entry) {
>  			if (!i)
> @@ -699,6 +708,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
>  		entry->msi_attrib.default_irq	= dev->irq;
>  		entry->mask_base		= base;
>  		entry->nvec_used		= 1;
> +		entry->affinity			= mask;
>  
>  		list_add_tail(&entry->list, dev_to_msi_list(&dev->dev));
>  	}
> @@ -1176,12 +1186,20 @@ int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs,
>  {
>  	unsigned int vecs, i;
>  	u32 *irqs;
> +	int ret;
>  
>  	max_vecs = min(max_vecs, pci_nr_irq_vectors(dev));
>  
> +	ret = irq_create_affinity_mask(&dev->irq_affinity, &max_vecs);

	dev->irq_affinity = irq_create_affinity_mask(&max_vecs); ?


> +	if (ret)
> +		return ret;
> +	if (max_vecs < min_vecs)
> +		return -ENOSPC;

irq_create_affinity_mask() should be called after MSI-X/MSI is enabled,
because we do not know number of vectors before the range functions
returned that number.

Since affinity masks is a function of number of vectors and CPU topology
the resulting masks might turn out suboptimal in general case (and
this code supposed to be general, right?).

I.e irq_create_affinity_mask() could decide "per-first-sibling" spreading
given number of available vectors, but only a subset of MSI vectors
were actually allocated. For that subset "per-core" affinity mask could
have been initialized, but we will still go with "per-first-sibling".

> +	ret = -ENOMEM;
>  	irqs = kcalloc(max_vecs, sizeof(u32), GFP_KERNEL);
>  	if (!irqs)
> -		return -ENOMEM;
> +		goto out_free_affinity;
>  
>  	if (!(flags & PCI_IRQ_NOMSIX)) {
>  		vecs = pci_enable_msix_range_wrapper(dev, irqs, min_vecs,
> @@ -1208,6 +1226,10 @@ int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs,
>  done:
>  	dev->irqs = irqs;
>  	return vecs;
> +out_free_affinity:
> +	kfree(dev->irq_affinity);
> +	dev->irq_affinity = NULL;
> +	return ret;
>  }
>  EXPORT_SYMBOL(pci_alloc_irq_vectors);
>  
> diff --git a/include/linux/pci.h b/include/linux/pci.h
> index 84a20fc..f474611 100644
> --- a/include/linux/pci.h
> +++ b/include/linux/pci.h
> @@ -321,6 +321,7 @@ struct pci_dev {
>  	 */
>  	unsigned int	irq;
>  	unsigned int	*irqs;
> +	struct cpumask	*irq_affinity;
>  	struct resource resource[DEVICE_COUNT_RESOURCE]; /* I/O and memory regions + expansion ROMs */
>  
>  	bool match_driver;		/* Skip attaching driver */
> -- 
> 2.1.4
> 

  reply	other threads:[~2016-06-25 20:22 UTC|newest]

Thread overview: 138+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-14 19:58 automatic interrupt affinity for MSI/MSI-X capable devices V2 Christoph Hellwig
2016-06-14 19:58 ` Christoph Hellwig
2016-06-14 19:58 ` [PATCH 01/13] irq/msi: Remove unused MSI_FLAG_IDENTITY_MAP Christoph Hellwig
2016-06-14 19:58   ` Christoph Hellwig
2016-06-14 19:58   ` Christoph Hellwig
2016-06-16  9:05   ` Bart Van Assche
2016-06-16  9:05     ` Bart Van Assche
2016-06-14 19:58 ` [PATCH 02/13] irq: Introduce IRQD_AFFINITY_MANAGED flag Christoph Hellwig
2016-06-14 19:58   ` Christoph Hellwig
2016-06-14 19:58   ` Christoph Hellwig
2016-06-15  8:44   ` Bart Van Assche
2016-06-15  8:44     ` Bart Van Assche
2016-06-15 10:23     ` Christoph Hellwig
2016-06-15 10:23       ` Christoph Hellwig
2016-06-15 10:42       ` Bart Van Assche
2016-06-15 10:42         ` Bart Van Assche
2016-06-15 10:42         ` Bart Van Assche
2016-06-15 15:14         ` Keith Busch
2016-06-15 15:14           ` Keith Busch
2016-06-15 15:28           ` Bart Van Assche
2016-06-15 15:28             ` Bart Van Assche
2016-06-15 16:03             ` Keith Busch
2016-06-15 16:03               ` Keith Busch
2016-06-15 19:36               ` Bart Van Assche
2016-06-15 19:36                 ` Bart Van Assche
2016-06-15 20:06                 ` Keith Busch
2016-06-15 20:06                   ` Keith Busch
2016-06-15 20:12                   ` Keith Busch
2016-06-15 20:12                     ` Keith Busch
2016-06-15 20:50                     ` Bart Van Assche
2016-06-15 20:50                       ` Bart Van Assche
2016-06-16 15:19                       ` Keith Busch
2016-06-16 15:19                         ` Keith Busch
2016-06-22 11:56                         ` Alexander Gordeev
2016-06-22 11:56                           ` Alexander Gordeev
2016-06-22 11:56                           ` Alexander Gordeev
2016-06-16 15:20                 ` Christoph Hellwig
2016-06-16 15:20                   ` Christoph Hellwig
2016-06-16 15:39                   ` Bart Van Assche
2016-06-16 15:39                     ` Bart Van Assche
2016-06-20 12:22                     ` Christoph Hellwig
2016-06-20 12:22                       ` Christoph Hellwig
2016-06-20 12:22                       ` Christoph Hellwig
2016-06-20 13:21                       ` Bart Van Assche
2016-06-20 13:21                         ` Bart Van Assche
2016-06-20 13:21                         ` Bart Van Assche
2016-06-21 14:31                         ` Christoph Hellwig
2016-06-21 14:31                           ` Christoph Hellwig
2016-06-21 14:31                           ` Christoph Hellwig
2016-06-16  9:08   ` Bart Van Assche
2016-06-16  9:08     ` Bart Van Assche
2016-06-14 19:58 ` [PATCH 03/13] irq: Add affinity hint to irq allocation Christoph Hellwig
2016-06-14 19:58   ` Christoph Hellwig
2016-06-14 19:58   ` Christoph Hellwig
2016-06-14 19:58 ` [PATCH 04/13] irq: Use affinity hint in irqdesc allocation Christoph Hellwig
2016-06-14 19:58   ` Christoph Hellwig
2016-06-14 19:58   ` Christoph Hellwig
2016-06-14 19:58 ` [PATCH 05/13] irq/msi: Make use of affinity aware allocations Christoph Hellwig
2016-06-14 19:58   ` Christoph Hellwig
2016-06-14 19:58   ` Christoph Hellwig
2016-06-14 19:58 ` [PATCH 06/13] irq: add a helper spread an affinity mask for MSI/MSI-X vectors Christoph Hellwig
2016-06-14 19:58   ` Christoph Hellwig
2016-06-14 19:58   ` Christoph Hellwig
2016-06-14 21:54   ` Guilherme G. Piccoli
2016-06-14 21:54     ` Guilherme G. Piccoli
2016-06-15  8:35     ` Bart Van Assche
2016-06-15  8:35       ` Bart Van Assche
2016-06-15  8:35       ` Bart Van Assche
2016-06-15 10:10     ` Christoph Hellwig
2016-06-15 10:10       ` Christoph Hellwig
2016-06-15 13:09       ` Guilherme G. Piccoli
2016-06-15 13:09         ` Guilherme G. Piccoli
2016-06-16 15:16         ` Christoph Hellwig
2016-06-16 15:16           ` Christoph Hellwig
2016-06-25 20:05   ` Alexander Gordeev
2016-06-25 20:05     ` Alexander Gordeev
2016-06-30 17:48     ` Christoph Hellwig
2016-06-30 17:48       ` Christoph Hellwig
2016-06-30 17:48       ` Christoph Hellwig
2016-07-01  7:25       ` Alexander Gordeev
2016-07-01  7:25         ` Alexander Gordeev
2016-06-14 19:59 ` [PATCH 07/13] pci: Provide sensible irq vector alloc/free routines Christoph Hellwig
2016-06-14 19:59   ` Christoph Hellwig
2016-06-14 19:59   ` Christoph Hellwig
2016-06-23 11:16   ` Alexander Gordeev
2016-06-23 11:16     ` Alexander Gordeev
2016-06-30 16:54     ` Christoph Hellwig
2016-06-30 16:54       ` Christoph Hellwig
2016-06-30 17:28       ` Alexander Gordeev
2016-06-30 17:28         ` Alexander Gordeev
2016-06-30 17:35         ` Christoph Hellwig
2016-06-30 17:35           ` Christoph Hellwig
2016-06-14 19:59 ` [PATCH 08/13] pci: spread interrupt vectors in pci_alloc_irq_vectors Christoph Hellwig
2016-06-14 19:59   ` Christoph Hellwig
2016-06-14 19:59   ` Christoph Hellwig
2016-06-25 20:22   ` Alexander Gordeev [this message]
2016-06-25 20:22     ` Alexander Gordeev
2016-06-14 19:59 ` [PATCH 09/13] blk-mq: don't redistribute hardware queues on a CPU hotplug event Christoph Hellwig
2016-06-14 19:59   ` Christoph Hellwig
2016-06-14 19:59   ` Christoph Hellwig
2016-06-14 19:59 ` [PATCH 10/13] blk-mq: only allocate a single mq_map per tag_set Christoph Hellwig
2016-06-14 19:59   ` Christoph Hellwig
2016-06-14 19:59   ` Christoph Hellwig
2016-06-14 19:59 ` [PATCH 11/13] blk-mq: allow the driver to pass in an affinity mask Christoph Hellwig
2016-06-14 19:59   ` Christoph Hellwig
2016-06-14 19:59   ` Christoph Hellwig
2016-07-04  8:15   ` Alexander Gordeev
2016-07-04  8:15     ` Alexander Gordeev
2016-07-04  8:38     ` Christoph Hellwig
2016-07-04  8:38       ` Christoph Hellwig
2016-07-04  9:35       ` Alexander Gordeev
2016-07-04  9:35         ` Alexander Gordeev
2016-07-10  3:41         ` Christoph Hellwig
2016-07-10  3:41           ` Christoph Hellwig
2016-07-12  6:42           ` Alexander Gordeev
2016-07-12  6:42             ` Alexander Gordeev
2016-06-14 19:59 ` [PATCH 12/13] nvme: switch to use pci_alloc_irq_vectors Christoph Hellwig
2016-06-14 19:59   ` Christoph Hellwig
2016-06-14 19:59   ` Christoph Hellwig
2016-06-14 19:59 ` [PATCH 13/13] nvme: remove the post_scan callout Christoph Hellwig
2016-06-14 19:59   ` Christoph Hellwig
2016-06-14 19:59   ` Christoph Hellwig
2016-06-16  9:45 ` automatic interrupt affinity for MSI/MSI-X capable devices V2 Bart Van Assche
2016-06-16  9:45   ` Bart Van Assche
2016-06-16  9:45   ` Bart Van Assche
2016-06-16 15:22   ` Christoph Hellwig
2016-06-16 15:22     ` Christoph Hellwig
2016-06-26 19:40 ` Alexander Gordeev
2016-06-26 19:40   ` Alexander Gordeev
2016-07-04  8:39 automatic interrupt affinity for MSI/MSI-X capable devices V3 Christoph Hellwig
2016-07-04  8:39 ` [PATCH 08/13] pci: spread interrupt vectors in pci_alloc_irq_vectors Christoph Hellwig
2016-07-04  8:39   ` Christoph Hellwig
2016-07-04  8:39   ` Christoph Hellwig
2016-07-07 11:05   ` Alexander Gordeev
2016-07-07 11:05     ` Alexander Gordeev
2016-07-10  3:57     ` Christoph Hellwig
2016-07-10  3:57       ` Christoph Hellwig
2016-07-12  6:49       ` Alexander Gordeev
2016-07-12  6:49         ` Alexander Gordeev

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=20160625202249.GB29251@dhcp-27-118.brq.redhat.com \
    --to=agordeev@redhat.com \
    --cc=axboe@fb.com \
    --cc=hch@lst.de \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=tglx@linutronix.de \
    /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.