Linux-PCI Archive on lore.kernel.org
 help / color / Atom feed
From: Bjorn Helgaas <helgaas@kernel.org>
To: Kuppuswamy Sathyanarayanan  <sathyanarayanan.kuppuswamy@linux.intel.com>
Cc: linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org,
	ashok.raj@intel.com, keith.busch@intel.com
Subject: Re: [PATCH v5 5/7] PCI/ATS: Add PASID support for PCIe VF devices
Date: Thu, 15 Aug 2019 00:04:30 -0500
Message-ID: <20190815050430.GG253360@google.com> (raw)
In-Reply-To: <20190813221958.GA139211@skuppusw-desk.amr.corp.intel.com>

On Tue, Aug 13, 2019 at 03:19:58PM -0700, Kuppuswamy Sathyanarayanan wrote:
> On Mon, Aug 12, 2019 at 03:05:08PM -0500, Bjorn Helgaas wrote:
> > On Thu, Aug 01, 2019 at 05:06:02PM -0700, sathyanarayanan.kuppuswamy@linux.intel.com wrote:
> > > From: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
> > > 
> > > When IOMMU tries to enable PASID for VF device in
> > > iommu_enable_dev_iotlb(), it always fails because PASID support for PCIe
> > > VF device is currently broken in PCIE driver. Current implementation
> > > expects the given PCIe device (PF & VF) to implement PASID capability
> > > before enabling the PASID support. But this assumption is incorrect. As
> > > per PCIe spec r4.0, sec 9.3.7.14, all VFs associated with PF can only
> > > use the PASID of the PF and not implement it.
> > > 
> > > Also, since PASID is a shared resource between PF/VF, following rules
> > > should apply.
> > > 
> > > 1. Use proper locking before accessing/modifying PF resources in VF
> > >    PASID enable/disable call.
> > > 2. Use reference count logic to track the usage of PASID resource.
> > > 3. Disable PASID only if the PASID reference count (pasid_ref_cnt) is zero.
> > > 
> > > Cc: Ashok Raj <ashok.raj@intel.com>
> > > Cc: Keith Busch <keith.busch@intel.com>
> > > Suggested-by: Ashok Raj <ashok.raj@intel.com>
> > > Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
> > > ---
> > >  drivers/pci/ats.c   | 113 ++++++++++++++++++++++++++++++++++----------
> > >  include/linux/pci.h |   2 +
> > >  2 files changed, 90 insertions(+), 25 deletions(-)
> > > 
> > > diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c
> > > index 079dc5444444..9384afd7d00e 100644
> > > --- a/drivers/pci/ats.c
> > > +++ b/drivers/pci/ats.c
> > > @@ -402,6 +402,8 @@ void pci_pasid_init(struct pci_dev *pdev)
> > >  	if (pdev->is_virtfn)
> > >  		return;
> > >  
> > > +	mutex_init(&pdev->pasid_lock);
> > > +
> > >  	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID);
> > >  	if (!pos)
> > >  		return;
> > > @@ -436,32 +438,57 @@ void pci_pasid_init(struct pci_dev *pdev)
> > >  int pci_enable_pasid(struct pci_dev *pdev, int features)
> > >  {
> > >  	u16 control, supported;
> > > +	int ret = 0;
> > > +	struct pci_dev *pf = pci_physfn(pdev);
> > >  
> > > -	if (WARN_ON(pdev->pasid_enabled))
> > > -		return -EBUSY;
> > > +	mutex_lock(&pf->pasid_lock);
> > >  
> > > -	if (!pdev->eetlp_prefix_path)
> > > -		return -EINVAL;
> > > +	if (WARN_ON(pdev->pasid_enabled)) {
> > > +		ret = -EBUSY;
> > > +		goto pasid_unlock;
> > > +	}
> > >  
> > > -	if (!pdev->pasid_cap)
> > > -		return -EINVAL;
> > > +	if (!pdev->eetlp_prefix_path) {
> > > +		ret = -EINVAL;
> > > +		goto pasid_unlock;
> > > +	}
> > >  
> > > -	pci_read_config_word(pdev, pdev->pasid_cap + PCI_PASID_CAP,
> > > -			     &supported);
> > > +	if (!pf->pasid_cap) {
> > > +		ret = -EINVAL;
> > > +		goto pasid_unlock;
> > > +	}
> > > +
> > > +	if (pdev->is_virtfn && pf->pasid_enabled)
> > > +		goto update_status;
> > > +
> > > +	pci_read_config_word(pf, pf->pasid_cap + PCI_PASID_CAP, &supported);
> > >  	supported &= PCI_PASID_CAP_EXEC | PCI_PASID_CAP_PRIV;
> > >  
> > >  	/* User wants to enable anything unsupported? */
> > > -	if ((supported & features) != features)
> > > -		return -EINVAL;
> > > +	if ((supported & features) != features) {
> > > +		ret = -EINVAL;
> > > +		goto pasid_unlock;
> > > +	}
> > >  
> > >  	control = PCI_PASID_CTRL_ENABLE | features;
> > > -	pdev->pasid_features = features;
> > > -
> > > +	pf->pasid_features = features;
> > >  	pci_write_config_word(pdev, pdev->pasid_cap + PCI_PASID_CTRL, control);
> > >  
> > > -	pdev->pasid_enabled = 1;
> > > +	/*
> > > +	 * If PASID is not already enabled in PF, increment pasid_ref_cnt
> > > +	 * to count PF PASID usage.
> > > +	 */
> > > +	if (pdev->is_virtfn && !pf->pasid_enabled) {
> > > +		atomic_inc(&pf->pasid_ref_cnt);
> > > +		pf->pasid_enabled = 1;
> > > +	}
> > >  
> > > -	return 0;
> > > +update_status:
> > > +	atomic_inc(&pf->pasid_ref_cnt);
> > > +	pdev->pasid_enabled = 1;
> > > +pasid_unlock:
> > > +	mutex_unlock(&pf->pasid_lock);
> > > +	return ret;
> > >  }
> > >  EXPORT_SYMBOL_GPL(pci_enable_pasid);
> > >  
> > > @@ -472,16 +499,29 @@ EXPORT_SYMBOL_GPL(pci_enable_pasid);
> > >  void pci_disable_pasid(struct pci_dev *pdev)
> > >  {
> > >  	u16 control = 0;
> > > +	struct pci_dev *pf = pci_physfn(pdev);
> > > +
> > > +	mutex_lock(&pf->pasid_lock);
> > >  
> > >  	if (WARN_ON(!pdev->pasid_enabled))
> > > -		return;
> > > +		goto pasid_unlock;
> > >  
> > > -	if (!pdev->pasid_cap)
> > > -		return;
> > > +	if (!pf->pasid_cap)
> > > +		goto pasid_unlock;
> > >  
> > > -	pci_write_config_word(pdev, pdev->pasid_cap + PCI_PASID_CTRL, control);
> > > +	atomic_dec(&pf->pasid_ref_cnt);
> > >  
> > > +	if (atomic_read(&pf->pasid_ref_cnt))
> > > +		goto done;
> > > +
> > > +	/* Disable PASID only if pasid_ref_cnt is zero */
> > > +	pci_write_config_word(pf, pf->pasid_cap + PCI_PASID_CTRL, control);
> > > +
> > > +done:
> > >  	pdev->pasid_enabled = 0;
> > > +pasid_unlock:
> > > +	mutex_unlock(&pf->pasid_lock);
> > > +
> > >  }
> > >  EXPORT_SYMBOL_GPL(pci_disable_pasid);
> > >  
> > > @@ -492,15 +532,25 @@ EXPORT_SYMBOL_GPL(pci_disable_pasid);
> > >  void pci_restore_pasid_state(struct pci_dev *pdev)
> > >  {
> > >  	u16 control;
> > > +	struct pci_dev *pf = pci_physfn(pdev);
> > >  
> > >  	if (!pdev->pasid_enabled)
> > >  		return;
> > >  
> > > -	if (!pdev->pasid_cap)
> > > +	if (!pf->pasid_cap)
> > >  		return;
> > >  
> > > +	mutex_lock(&pf->pasid_lock);
> > > +
> > > +	pci_read_config_word(pf, pf->pasid_cap + PCI_PASID_CTRL, &control);
> > > +	if (control & PCI_PASID_CTRL_ENABLE)
> > > +		goto pasid_unlock;
> > > +
> > >  	control = PCI_PASID_CTRL_ENABLE | pdev->pasid_features;
> > > -	pci_write_config_word(pdev, pdev->pasid_cap + PCI_PASID_CTRL, control);
> > > +	pci_write_config_word(pf, pf->pasid_cap + PCI_PASID_CTRL, control);
> > > +
> > > +pasid_unlock:
> > > +	mutex_unlock(&pf->pasid_lock);
> > >  }
> > >  EXPORT_SYMBOL_GPL(pci_restore_pasid_state);
> > >  
> > > @@ -517,15 +567,22 @@ EXPORT_SYMBOL_GPL(pci_restore_pasid_state);
> > >  int pci_pasid_features(struct pci_dev *pdev)
> > >  {
> > >  	u16 supported;
> > > +	struct pci_dev *pf = pci_physfn(pdev);
> > > +
> > > +	mutex_lock(&pf->pasid_lock);
> > >  
> > > -	if (!pdev->pasid_cap)
> > > +	if (!pf->pasid_cap) {
> > > +		mutex_unlock(&pf->pasid_lock);
> > >  		return -EINVAL;
> > > +	}
> > >  
> > > -	pci_read_config_word(pdev, pdev->pasid_cap + PCI_PASID_CAP,
> > > +	pci_read_config_word(pf, pf->pasid_cap + PCI_PASID_CAP,
> > >  			     &supported);
> > >  
> > >  	supported &= PCI_PASID_CAP_EXEC | PCI_PASID_CAP_PRIV;
> > >  
> > > +	mutex_unlock(&pf->pasid_lock);
> > > +
> > >  	return supported;
> > >  }
> > >  EXPORT_SYMBOL_GPL(pci_pasid_features);
> > > @@ -579,15 +636,21 @@ EXPORT_SYMBOL_GPL(pci_prg_resp_pasid_required);
> > >  int pci_max_pasids(struct pci_dev *pdev)
> > >  {
> > >  	u16 supported;
> > > +	struct pci_dev *pf = pci_physfn(pdev);
> > > +
> > > +	mutex_lock(&pf->pasid_lock);
> > >  
> > > -	if (!pdev->pasid_cap)
> > > +	if (!pf->pasid_cap) {
> > > +		mutex_unlock(&pf->pasid_lock);
> > >  		return -EINVAL;
> > > +	}
> > >  
> > > -	pci_read_config_word(pdev, pdev->pasid_cap + PCI_PASID_CAP,
> > > -			     &supported);
> > > +	pci_read_config_word(pf, pf->pasid_cap + PCI_PASID_CAP, &supported);
> > >  
> > >  	supported = (supported & PASID_NUMBER_MASK) >> PASID_NUMBER_SHIFT;
> > >  
> > > +	mutex_unlock(&pf->pasid_lock);
> > > +
> > >  	return (1 << supported);
> > >  }
> > >  EXPORT_SYMBOL_GPL(pci_max_pasids);
> > > diff --git a/include/linux/pci.h b/include/linux/pci.h
> > > index 3c9c4c82be27..4bfcca045afd 100644
> > > --- a/include/linux/pci.h
> > > +++ b/include/linux/pci.h
> > > @@ -461,8 +461,10 @@ struct pci_dev {
> > >  	atomic_t	pri_ref_cnt;	/* Number of PF/VF PRI users */
> > >  #endif
> > >  #ifdef CONFIG_PCI_PASID
> > > +	struct mutex	pasid_lock;	/* PASID enable lock */
> > 
> > I think these locks are finer-grained than necessary.  I'm not sure
> > it's worth having two mutexes for every device (one for PRI and
> > another for PASID).  Is there really a performance benefit for having
> > two?

> Performance benefit should be minimal. But, PRI and PASID are functionally
> independent. So I don't think its correct to protect its resources with
> a common lock. Let me know your comments.

I'm not an expert on PRI and PASID, but if we can figure out a place
to put it and a way to manage it, I think it's OK to have a lock that
protects both.  I'm thinking about the size of the pci_dev -- I'm not
sure the benefit of having two locks is commensurate with the size
cost.

> > Do it (or do they) need to be in struct pci_dev?  You only use the PF
> > mutexes, so maybe it could be in the struct pci_sriov, which I think
> > is only one per PF.

> Its possible to move it to pci_sriov structure. But is that the right
> place for it? This lock is only used for protecting PRI and PASID feature
> updates and PRI/PASID are not dependent on IOV feature. Let me know your
> comments.

Hmm.  I misunderstood the use of these.  I had the impression they
were only used for PFs.  If that were the case, pci_sriov might make
sense because we only allocate that for PFs (when we enable SR-IOV in
sriov_init()).  But IIUC that's *not* the case: even non-SR-IOV
devices can use PRI/PASID; it's just that if a *VF* uses them, the VF
is actually using the PRI of the PF.

> If you want to move this lock to pci_sriov structure and use one lock
> for both PRI/PASID, then the implementation would look like following. We
> could create physfn lock/unlock functions in include/linux/pci.h similar
> to pci_physfn() function.

> #ifdef CONFIG_PCI_IOV
> static inline void pci_physfn_reslock(struct pci_dev *dev)
> {
>     struct pci_dev *pf = pci_physfn(dev);
> 
>     if (!pf->is_physfn)
>         return;
> 
>     mutex_lock(&pf->sriov->reslock);
> 
> }
> #else
> static inline void pci_physfn_reslock(struct pci_dev *dev) {}; 
> #endif

Yeah, that's not a pretty solution.  IIUC, we don't need to lock at
all for non-SR-IOV devices, because we're operating on our own device
and nobody else should be touching it.  Right?

Only the SR-IOV case (operating on a PF with SR-IOV enabled or on one
of its VFs) needs locking because these are all sharing one resource.

So it's kind of a shame to allocate the lock for *every* pci_dev, when
we only need it for PFs with SR-IOV enabled.

Bjorn

  reply index

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-02  0:05 [PATCH v5 0/7] Fix PF/VF dependency issue sathyanarayanan.kuppuswamy
2019-08-02  0:05 ` [PATCH v5 1/7] PCI/ATS: Fix pci_prg_resp_pasid_required() dependency issues sathyanarayanan.kuppuswamy
2019-08-12 20:04   ` Bjorn Helgaas
2019-08-12 20:20     ` sathyanarayanan kuppuswamy
2019-08-13  3:51       ` Bjorn Helgaas
2019-08-16 18:06         ` Kuppuswamy Sathyanarayanan
2019-08-02  0:05 ` [PATCH v5 2/7] PCI/ATS: Initialize PRI in pci_ats_init() sathyanarayanan.kuppuswamy
2019-08-12 20:04   ` Bjorn Helgaas
2019-08-12 21:35     ` sathyanarayanan kuppuswamy
2019-08-13  4:10       ` Bjorn Helgaas
2019-08-15  4:46   ` Bjorn Helgaas
2019-08-15 17:30     ` Kuppuswamy Sathyanarayanan
2019-08-16 17:31       ` Bjorn Helgaas
2019-08-02  0:06 ` [PATCH v5 3/7] PCI/ATS: Initialize PASID " sathyanarayanan.kuppuswamy
2019-08-12 20:04   ` Bjorn Helgaas
2019-08-15  4:48   ` Bjorn Helgaas
2019-08-15  4:56   ` Bjorn Helgaas
2019-08-15 17:31     ` Kuppuswamy Sathyanarayanan
2019-08-02  0:06 ` [PATCH v5 4/7] PCI/ATS: Add PRI support for PCIe VF devices sathyanarayanan.kuppuswamy
2019-08-12 20:04   ` Bjorn Helgaas
2019-08-12 21:40     ` sathyanarayanan kuppuswamy
2019-08-13  4:16   ` Bjorn Helgaas
2019-08-15 22:20   ` Bjorn Helgaas
2019-08-15 22:39     ` Kuppuswamy Sathyanarayanan
2019-08-19 14:15       ` Bjorn Helgaas
2019-08-19 22:53         ` Kuppuswamy Sathyanarayanan
2019-08-19 23:19           ` Bjorn Helgaas
2019-08-28 18:21             ` Kuppuswamy Sathyanarayanan
2019-08-28 18:57               ` Bjorn Helgaas
2019-08-02  0:06 ` [PATCH v5 5/7] PCI/ATS: Add PASID " sathyanarayanan.kuppuswamy
2019-08-12 20:05   ` Bjorn Helgaas
2019-08-13 22:19     ` Kuppuswamy Sathyanarayanan
2019-08-15  5:04       ` Bjorn Helgaas [this message]
2019-08-16  1:21         ` Kuppuswamy Sathyanarayanan
2019-08-02  0:06 ` [PATCH v5 6/7] PCI/ATS: Disable PF/VF ATS service independently sathyanarayanan.kuppuswamy
2019-08-02  0:06 ` [PATCH v5 7/7] PCI: Skip Enhanced Allocation (EA) initialization for VF device sathyanarayanan.kuppuswamy

Reply instructions:

You may reply publically 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=20190815050430.GG253360@google.com \
    --to=helgaas@kernel.org \
    --cc=ashok.raj@intel.com \
    --cc=keith.busch@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=sathyanarayanan.kuppuswamy@linux.intel.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

Linux-PCI Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-pci/0 linux-pci/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-pci linux-pci/ https://lore.kernel.org/linux-pci \
		linux-pci@vger.kernel.org
	public-inbox-index linux-pci

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-pci


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git