From: Lu Baolu <baolu.lu@linux.intel.com>
To: Jacob Pan <jacob.jun.pan@linux.intel.com>,
iommu@lists.linux-foundation.org,
LKML <linux-kernel@vger.kernel.org>,
Joerg Roedel <joro@8bytes.org>,
David Woodhouse <dwmw2@infradead.org>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Rafael Wysocki <rafael.j.wysocki@intel.com>,
Alex Williamson <alex.williamson@redhat.com>
Cc: Lan Tianyu <tianyu.lan@intel.com>, Jean Delvare <khali@linux-fr.org>
Subject: Re: [PATCH v3 13/16] iommu/intel-svm: notify page request to guest
Date: Tue, 5 Dec 2017 15:37:23 +0800 [thread overview]
Message-ID: <5A264CB3.2060603@linux.intel.com> (raw)
In-Reply-To: <1510944914-54430-14-git-send-email-jacob.jun.pan@linux.intel.com>
Hi,
On 11/18/2017 02:55 AM, Jacob Pan wrote:
> If the source device of a page request has its PASID table pointer
> bond to a guest, the first level page tables are owned by the guest.
> In this case, we shall let guest OS to manage page fault.
>
> This patch uses the IOMMU fault notification API to send notifications,
> possibly via VFIO, to the guest OS. Once guest pages are fault in, guest
> will issue page response which will be passed down via the invalidation
> passdown APIs.
>
> Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
> Signed-off-by: Ashok Raj <ashok.raj@intel.com>
> ---
> drivers/iommu/intel-svm.c | 80 ++++++++++++++++++++++++++++++++++++++++++-----
> include/linux/iommu.h | 1 +
> 2 files changed, 74 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
> index f6697e5..77c25d8 100644
> --- a/drivers/iommu/intel-svm.c
> +++ b/drivers/iommu/intel-svm.c
> @@ -555,6 +555,71 @@ static bool is_canonical_address(u64 addr)
> return (((saddr << shift) >> shift) == saddr);
> }
>
> +static int prq_to_iommu_prot(struct page_req_dsc *req)
> +{
> + int prot = 0;
> +
> + if (req->rd_req)
> + prot |= IOMMU_FAULT_READ;
> + if (req->wr_req)
> + prot |= IOMMU_FAULT_WRITE;
> + if (req->exe_req)
> + prot |= IOMMU_FAULT_EXEC;
> + if (req->priv_req)
> + prot |= IOMMU_FAULT_PRIV;
> +
> + return prot;
> +}
> +
> +static int intel_svm_prq_report(struct device *dev, struct page_req_dsc *desc)
> +{
> + int ret = 0;
It seems that "ret" should be initialized as -EINVAL. Otherwise, this function
will return 0 for devices which have no fault handlers, and all page requests
will be ignored by iommu driver.
> + struct iommu_fault_event event;
> + struct pci_dev *pdev;
> +
> + /**
> + * If caller does not provide struct device, this is the case where
> + * guest PASID table is bound to the device. So we need to retrieve
> + * struct device from the page request descriptor then proceed.
> + */
> + if (!dev) {
> + pdev = pci_get_bus_and_slot(desc->bus, desc->devfn);
> + if (!pdev) {
> + pr_err("No PCI device found for PRQ [%02x:%02x.%d]\n",
> + desc->bus, PCI_SLOT(desc->devfn),
> + PCI_FUNC(desc->devfn));
> + return -ENODEV;
> + }
> + dev = &pdev->dev;
> + } else if (dev_is_pci(dev)) {
> + pdev = to_pci_dev(dev);
> + pci_dev_get(pdev);
> + } else
> + return -ENODEV;
> +
> + pr_debug("Notify PRQ device [%02x:%02x.%d]\n",
> + desc->bus, PCI_SLOT(desc->devfn),
> + PCI_FUNC(desc->devfn));
> +
> + /* invoke device fault handler if registered */
> + if (iommu_has_device_fault_handler(dev)) {
> + /* Fill in event data for device specific processing */
> + event.type = IOMMU_FAULT_PAGE_REQ;
> + event.addr = desc->addr;
> + event.pasid = desc->pasid;
> + event.page_req_group_id = desc->prg_index;
> + event.prot = prq_to_iommu_prot(desc);
> + event.last_req = desc->lpig;
> + event.pasid_valid = 1;
> + event.iommu_private = desc->private;
> + ret = iommu_report_device_fault(&pdev->dev, &event);
> + }
> +
> + pci_dev_put(pdev);
> +
> + return ret;
> +}
> +
> static irqreturn_t prq_event_thread(int irq, void *d)
> {
> struct intel_iommu *iommu = d;
> @@ -578,7 +643,12 @@ static irqreturn_t prq_event_thread(int irq, void *d)
> handled = 1;
>
> req = &iommu->prq[head / sizeof(*req)];
> -
> + /**
> + * If prq is to be handled outside iommu driver via receiver of
> + * the fault notifiers, we skip the page response here.
> + */
> + if (!intel_svm_prq_report(NULL, req))
> + goto prq_advance;
> result = QI_RESP_FAILURE;
> address = (u64)req->addr << VTD_PAGE_SHIFT;
> if (!req->pasid_present) {
> @@ -649,11 +719,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
> if (WARN_ON(&sdev->list == &svm->devs))
> sdev = NULL;
>
> - if (sdev && sdev->ops && sdev->ops->fault_cb) {
> - int rwxp = (req->rd_req << 3) | (req->wr_req << 2) |
> - (req->exe_req << 1) | (req->priv_req);
> - sdev->ops->fault_cb(sdev->dev, req->pasid, req->addr, req->private, rwxp, result);
> - }
> + intel_svm_prq_report(sdev->dev, req);
Do you mind explaining why we need to report this request twice?
Best regards,
Lu Baolu
> /* We get here in the error case where the PASID lookup failed,
> and these can be NULL. Do not use them below this point! */
> sdev = NULL;
> @@ -679,7 +745,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
>
> qi_submit_sync(&resp, iommu);
> }
> -
> + prq_advance:
> head = (head + sizeof(*req)) & PRQ_RING_MASK;
> }
>
> diff --git a/include/linux/iommu.h b/include/linux/iommu.h
> index 841c044..3083796b 100644
> --- a/include/linux/iommu.h
> +++ b/include/linux/iommu.h
> @@ -42,6 +42,7 @@
> * if the IOMMU page table format is equivalent.
> */
> #define IOMMU_PRIV (1 << 5)
> +#define IOMMU_EXEC (1 << 6)
>
> struct iommu_ops;
> struct iommu_group;
next prev parent reply other threads:[~2017-12-05 7:37 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-11-17 18:54 [PATCH v3 00/16] [PATCH v3 00/16] IOMMU driver support for SVM virtualization Jacob Pan
2017-11-17 18:54 ` [PATCH v3 01/16] iommu: introduce bind_pasid_table API function Jacob Pan
2017-11-24 12:04 ` Jean-Philippe Brucker
2017-11-29 22:01 ` Jacob Pan
2017-11-17 18:55 ` [PATCH v3 02/16] iommu/vt-d: add bind_pasid_table function Jacob Pan
2017-11-17 18:55 ` [PATCH v3 03/16] iommu: introduce iommu invalidate API function Jacob Pan
2017-11-24 12:04 ` Jean-Philippe Brucker
2017-12-15 19:02 ` Jean-Philippe Brucker
2017-12-28 19:25 ` Jacob Pan
2018-01-10 12:00 ` Jean-Philippe Brucker
2017-11-17 18:55 ` [PATCH v3 04/16] iommu/vt-d: move device_domain_info to header Jacob Pan
2017-11-17 18:55 ` [PATCH v3 05/16] iommu/vt-d: support flushing more TLB types Jacob Pan
2017-11-20 14:20 ` Lukoshkov, Maksim
2017-11-20 18:40 ` Jacob Pan
2017-11-17 18:55 ` [PATCH v3 06/16] iommu/vt-d: add svm/sva invalidate function Jacob Pan
2017-12-05 5:43 ` Lu Baolu
2017-11-17 18:55 ` [PATCH v3 07/16] iommu/vt-d: assign PFSID in device TLB invalidation Jacob Pan
2017-12-05 5:45 ` Lu Baolu
2017-11-17 18:55 ` [PATCH v3 08/16] iommu: introduce device fault data Jacob Pan
2017-11-24 12:03 ` Jean-Philippe Brucker
2017-11-29 21:55 ` Jacob Pan
2018-01-10 11:41 ` Jean-Philippe Brucker
2018-01-11 21:10 ` Jacob Pan
2017-11-17 18:55 ` [PATCH v3 09/16] driver core: add iommu device fault reporting data Jacob Pan
2017-12-18 14:37 ` Greg Kroah-Hartman
2017-11-17 18:55 ` [PATCH v3 10/16] iommu: introduce device fault report API Jacob Pan
2017-12-05 6:22 ` Lu Baolu
2017-12-08 21:22 ` Jacob Pan
2017-12-07 21:27 ` Alex Williamson
2017-12-08 20:23 ` Jacob Pan
2017-12-08 20:59 ` Alex Williamson
2017-12-08 21:22 ` Jacob Pan
2018-01-10 12:39 ` Jean-Philippe Brucker
2018-01-18 19:24 ` Jean-Philippe Brucker
2018-01-23 20:01 ` Jacob Pan
2017-11-17 18:55 ` [PATCH v3 11/16] iommu/vt-d: use threaded irq for dmar_fault Jacob Pan
2017-11-17 18:55 ` [PATCH v3 12/16] iommu/vt-d: report unrecoverable device faults Jacob Pan
2017-12-05 6:34 ` Lu Baolu
2017-11-17 18:55 ` [PATCH v3 13/16] iommu/intel-svm: notify page request to guest Jacob Pan
2017-12-05 7:37 ` Lu Baolu [this message]
2017-11-17 18:55 ` [PATCH v3 14/16] iommu/intel-svm: replace dev ops with fault report API Jacob Pan
2017-11-17 18:55 ` [PATCH v3 15/16] iommu: introduce page response function Jacob Pan
2017-11-24 12:03 ` Jean-Philippe Brucker
2017-12-04 21:37 ` Jacob Pan
2017-12-05 17:21 ` Jean-Philippe Brucker
2017-12-06 19:25 ` Jacob Pan
2017-12-07 12:56 ` Jean-Philippe Brucker
2017-12-07 21:56 ` Alex Williamson
2017-12-08 13:51 ` Jean-Philippe Brucker
2017-12-08 1:17 ` Jacob Pan
2017-12-08 13:51 ` Jean-Philippe Brucker
2017-12-07 21:51 ` Alex Williamson
2017-12-08 13:52 ` Jean-Philippe Brucker
2017-12-08 20:40 ` Jacob Pan
2017-12-08 23:01 ` Alex Williamson
2017-11-17 18:55 ` [PATCH v3 16/16] iommu/vt-d: add intel iommu " Jacob Pan
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=5A264CB3.2060603@linux.intel.com \
--to=baolu.lu@linux.intel.com \
--cc=alex.williamson@redhat.com \
--cc=dwmw2@infradead.org \
--cc=gregkh@linuxfoundation.org \
--cc=iommu@lists.linux-foundation.org \
--cc=jacob.jun.pan@linux.intel.com \
--cc=joro@8bytes.org \
--cc=khali@linux-fr.org \
--cc=linux-kernel@vger.kernel.org \
--cc=rafael.j.wysocki@intel.com \
--cc=tianyu.lan@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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).