From: Auger Eric <eric.auger@redhat.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>,
Alex Williamson <alex.williamson@redhat.com>,
Jean-Philippe Brucker <jean-philippe.brucker@arm.com>
Cc: "Tian, Kevin" <kevin.tian@intel.com>,
Raj Ashok <ashok.raj@intel.com>,
Andriy Shevchenko <andriy.shevchenko@linux.intel.com>
Subject: Re: [PATCH v4 14/22] iommu/vt-d: Add custom allocator for IOASID
Date: Tue, 16 Jul 2019 11:30:14 +0200 [thread overview]
Message-ID: <2f2ba561-793f-a6a0-5765-ef8e9a5a3ab6@redhat.com> (raw)
In-Reply-To: <1560087862-57608-15-git-send-email-jacob.jun.pan@linux.intel.com>
Hi Jacob,
On 6/9/19 3:44 PM, Jacob Pan wrote:
> When VT-d driver runs in the guest, PASID allocation must be
> performed via virtual command interface. This patch registers a
> custom IOASID allocator which takes precedence over the default
> XArray based allocator. The resulting IOASID allocation will always
> come from the host. This ensures that PASID namespace is system-
> wide.
>
> Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
> Signed-off-by: Liu, Yi L <yi.l.liu@intel.com>
> Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
> ---
> drivers/iommu/Kconfig | 1 +
> drivers/iommu/intel-iommu.c | 60 +++++++++++++++++++++++++++++++++++++++++++++
> include/linux/intel-iommu.h | 2 ++
> 3 files changed, 63 insertions(+)
>
> diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
> index c40c4b5..5d1bc2a 100644
> --- a/drivers/iommu/Kconfig
> +++ b/drivers/iommu/Kconfig
> @@ -213,6 +213,7 @@ config INTEL_IOMMU_SVM
> bool "Support for Shared Virtual Memory with Intel IOMMU"
> depends on INTEL_IOMMU && X86
> select PCI_PASID
> + select IOASID
> select MMU_NOTIFIER
> select IOASID
> help
> diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
> index 09b8ff0..5b84994 100644
> --- a/drivers/iommu/intel-iommu.c
> +++ b/drivers/iommu/intel-iommu.c
> @@ -1711,6 +1711,8 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
> if (ecap_prs(iommu->ecap))
> intel_svm_finish_prq(iommu);
> }
> + ioasid_unregister_allocator(&iommu->pasid_allocator);
> +
> #endif
> }
>
> @@ -4820,6 +4822,46 @@ static int __init platform_optin_force_iommu(void)
> return 1;
> }
>
> +#ifdef CONFIG_INTEL_IOMMU_SVM
> +static ioasid_t intel_ioasid_alloc(ioasid_t min, ioasid_t max, void *data)
> +{
> + struct intel_iommu *iommu = data;
> + ioasid_t ioasid;
> +
> + /*
> + * VT-d virtual command interface always uses the full 20 bit
> + * PASID range. Host can partition guest PASID range based on
> + * policies but it is out of guest's control.
> + */
> + if (min < PASID_MIN || max > PASID_MAX)
> + return -EINVAL;
ioasid_alloc() does not handle that error value, use INVALID_IOASID?
> +
> + if (vcmd_alloc_pasid(iommu, &ioasid))
> + return INVALID_IOASID;
> +
> + return ioasid;
> +}
> +
> +static void intel_ioasid_free(ioasid_t ioasid, void *data)
> +{
> + struct iommu_pasid_alloc_info *svm;
> + struct intel_iommu *iommu = data;
> +
> + if (!iommu)
> + return;
> + /*
> + * Sanity check the ioasid owner is done at upper layer, e.g. VFIO
> + * We can only free the PASID when all the devices are unbond.
> + */
> + svm = ioasid_find(NULL, ioasid, NULL);
> + if (!svm) {
> + pr_warn("Freeing unbond IOASID %d\n", ioasid);
> + return;
> + }
> + vcmd_free_pasid(iommu, ioasid);
> +}
> +#endif
> +
> int __init intel_iommu_init(void)
> {
> int ret = -ENODEV;
> @@ -4924,6 +4966,24 @@ int __init intel_iommu_init(void)
> "%s", iommu->name);
> iommu_device_set_ops(&iommu->iommu, &intel_iommu_ops);
> iommu_device_register(&iommu->iommu);
> +#ifdef CONFIG_INTEL_IOMMU_SVM
> + if (cap_caching_mode(iommu->cap) && sm_supported(iommu)) {
> + /*
> + * Register a custom ASID allocator if we are running
> + * in a guest, the purpose is to have a system wide PASID
> + * namespace among all PASID users.
> + * There can be multiple vIOMMUs in each guest but only
> + * one allocator is active. All vIOMMU allocators will
> + * eventually be calling the same host allocator.
> + */
> + iommu->pasid_allocator.alloc = intel_ioasid_alloc;
> + iommu->pasid_allocator.free = intel_ioasid_free;
> + iommu->pasid_allocator.pdata = (void *)iommu;
> + ret = ioasid_register_allocator(&iommu->pasid_allocator);
> + if (ret)
> + pr_warn("Custom PASID allocator registeration failed\n");
what if it fails, don't you want a tear down path?
Thanks
Eric
> + }
> +#endif
> }
>
> bus_set_iommu(&pci_bus_type, &intel_iommu_ops);
> diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
> index bff907b..8605c74 100644
> --- a/include/linux/intel-iommu.h
> +++ b/include/linux/intel-iommu.h
> @@ -31,6 +31,7 @@
> #include <linux/iommu.h>
> #include <linux/io-64-nonatomic-lo-hi.h>
> #include <linux/dmar.h>
> +#include <linux/ioasid.h>
>
> #include <asm/cacheflush.h>
> #include <asm/iommu.h>
> @@ -549,6 +550,7 @@ struct intel_iommu {
> #ifdef CONFIG_INTEL_IOMMU_SVM
> struct page_req_dsc *prq;
> unsigned char prq_name[16]; /* Name for PRQ interrupt */
> + struct ioasid_allocator_ops pasid_allocator; /* Custom allocator for PASIDs */
> #endif
> struct q_inval *qi; /* Queued invalidation info */
> u32 *iommu_state; /* Store iommu states between suspend and resume.*/
>
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
next prev parent reply other threads:[~2019-07-16 9:30 UTC|newest]
Thread overview: 64+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-09 13:44 [PATCH v4 00/22] Shared virtual address IOMMU and VT-d support Jacob Pan
2019-06-09 13:44 ` [PATCH v4 01/22] driver core: Add per device iommu param Jacob Pan
2019-06-09 13:44 ` [PATCH v4 02/22] iommu: Introduce device fault data Jacob Pan
2019-06-18 15:42 ` Jonathan Cameron
2019-06-09 13:44 ` [PATCH v4 03/22] iommu: Introduce device fault report API Jacob Pan
2019-06-18 15:41 ` Jonathan Cameron
2019-06-09 13:44 ` [PATCH v4 04/22] iommu: Add recoverable fault reporting Jacob Pan
2019-06-18 15:44 ` Jonathan Cameron
2019-06-09 13:44 ` [PATCH v4 05/22] iommu: Add a timeout parameter for PRQ response Jacob Pan
2019-06-09 13:44 ` [PATCH v4 06/22] trace/iommu: Add sva trace events Jacob Pan
2019-06-09 13:44 ` [PATCH v4 07/22] iommu: Use device fault trace event Jacob Pan
2019-06-09 13:44 ` [PATCH v4 08/22] iommu: Introduce attach/detach_pasid_table API Jacob Pan
2019-06-18 15:41 ` Jonathan Cameron
2019-06-24 15:06 ` Auger Eric
2019-06-24 15:23 ` Jean-Philippe Brucker
2019-06-09 13:44 ` [PATCH v4 09/22] iommu: Introduce cache_invalidate API Jacob Pan
2019-06-18 15:41 ` Jonathan Cameron
2019-06-09 13:44 ` [PATCH v4 10/22] iommu: Fix compile error without IOMMU_API Jacob Pan
2019-06-18 14:10 ` Jonathan Cameron
2019-06-24 22:28 ` Jacob Pan
2019-06-09 13:44 ` [PATCH v4 11/22] iommu: Introduce guest PASID bind function Jacob Pan
2019-06-18 15:36 ` Jean-Philippe Brucker
2019-06-24 22:24 ` Jacob Pan
2019-07-16 16:44 ` Auger Eric
2019-08-05 21:02 ` Jacob Pan
2019-08-05 23:13 ` Jacob Pan
2019-06-09 13:44 ` [PATCH v4 12/22] iommu: Add I/O ASID allocator Jacob Pan
2019-06-18 16:50 ` Jonathan Cameron
2019-06-25 18:55 ` Jacob Pan
2019-06-09 13:44 ` [PATCH v4 13/22] iommu/vt-d: Enlightened PASID allocation Jacob Pan
2019-07-16 9:29 ` Auger Eric
2019-08-13 16:57 ` Jacob Pan
2019-06-09 13:44 ` [PATCH v4 14/22] iommu/vt-d: Add custom allocator for IOASID Jacob Pan
2019-07-16 9:30 ` Auger Eric [this message]
2019-08-05 20:02 ` Jacob Pan
2019-06-09 13:44 ` [PATCH v4 15/22] iommu/vt-d: Replace Intel specific PASID allocator with IOASID Jacob Pan
2019-06-18 15:57 ` Jonathan Cameron
2019-06-24 21:36 ` Jacob Pan
2019-06-27 1:53 ` Lu Baolu
2019-06-27 15:40 ` Jacob Pan
2019-06-09 13:44 ` [PATCH v4 16/22] iommu/vt-d: Move domain helper to header Jacob Pan
2019-07-16 9:33 ` Auger Eric
2019-06-09 13:44 ` [PATCH v4 17/22] iommu/vt-d: Avoid duplicated code for PASID setup Jacob Pan
2019-06-18 16:03 ` Jonathan Cameron
2019-06-24 23:44 ` Jacob Pan
2019-07-16 9:52 ` Auger Eric
2019-06-09 13:44 ` [PATCH v4 18/22] iommu/vt-d: Add nested translation helper function Jacob Pan
2019-06-09 13:44 ` [PATCH v4 19/22] iommu/vt-d: Clean up for SVM device list Jacob Pan
2019-06-18 16:42 ` Jonathan Cameron
2019-06-24 23:59 ` Jacob Pan
2019-06-09 13:44 ` [PATCH v4 20/22] iommu/vt-d: Add bind guest PASID support Jacob Pan
2019-06-18 16:44 ` Jonathan Cameron
2019-06-24 22:41 ` Jacob Pan
2019-06-27 2:50 ` Lu Baolu
2019-06-27 20:22 ` Jacob Pan
2019-07-05 2:21 ` Lu Baolu
2019-08-14 17:20 ` Jacob Pan
2019-07-16 16:45 ` Auger Eric
2019-07-16 17:04 ` Raj, Ashok
2019-07-18 7:47 ` Auger Eric
2019-06-09 13:44 ` [PATCH v4 21/22] iommu/vt-d: Support flushing more translation cache types Jacob Pan
2019-07-18 8:35 ` Auger Eric
2019-08-14 20:17 ` Jacob Pan
2019-06-09 13:44 ` [PATCH v4 22/22] iommu/vt-d: Add svm/sva invalidate function 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=2f2ba561-793f-a6a0-5765-ef8e9a5a3ab6@redhat.com \
--to=eric.auger@redhat.com \
--cc=alex.williamson@redhat.com \
--cc=andriy.shevchenko@linux.intel.com \
--cc=ashok.raj@intel.com \
--cc=dwmw2@infradead.org \
--cc=iommu@lists.linux-foundation.org \
--cc=jacob.jun.pan@linux.intel.com \
--cc=jean-philippe.brucker@arm.com \
--cc=joro@8bytes.org \
--cc=kevin.tian@intel.com \
--cc=linux-kernel@vger.kernel.org \
/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).