qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Liu Yi L <yi.l.liu@intel.com>
To: qemu-devel@nongnu.org, alex.williamson@redhat.com,
	peterx@redhat.com, jasowang@redhat.com
Cc: jean-philippe@linaro.org, kevin.tian@intel.com,
	yi.l.liu@intel.com, Yi Sun <yi.y.sun@linux.intel.com>,
	Eduardo Habkost <ehabkost@redhat.com>,
	kvm@vger.kernel.org, mst@redhat.com, jun.j.tian@intel.com,
	eric.auger@redhat.com, yi.y.sun@intel.com,
	Jacob Pan <jacob.jun.pan@linux.intel.com>,
	pbonzini@redhat.com, hao.wu@intel.com,
	Richard Henderson <rth@twiddle.net>,
	david@gibson.dropbear.id.au
Subject: [RFC v10 23/25] intel_iommu: propagate PASID-based iotlb invalidation to host
Date: Thu, 10 Sep 2020 03:56:36 -0700	[thread overview]
Message-ID: <1599735398-6829-24-git-send-email-yi.l.liu@intel.com> (raw)
In-Reply-To: <1599735398-6829-1-git-send-email-yi.l.liu@intel.com>

This patch propagates PASID-based iotlb invalidation to host.

Intel VT-d 3.0 supports nested translation in PASID granular.
Guest SVA support could be implemented by configuring nested
translation on specific PASID. This is also known as dual stage
DMA translation.

Under such configuration, guest owns the GVA->GPA translation
which is configured as first level page table in host side for
a specific pasid, and host owns GPA->HPA translation. As guest
owns first level translation table, piotlb invalidation should
be propagated to host since host IOMMU will cache first level
page table related mappings during DMA address translation.

This patch traps the guest PASID-based iotlb flush and propagate
it to host.

Cc: Kevin Tian <kevin.tian@intel.com>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Yi Sun <yi.y.sun@linux.intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
---
rfcv4 (v1) -> rfcv5 (v2):
*) removed the valid check to vtd_pasid_as instance as rfcv5 ensures
   all vtd_pasid_as instances in hash table should be valid.
---
 hw/i386/intel_iommu.c          | 113 +++++++++++++++++++++++++++++++++++++++++
 hw/i386/intel_iommu_internal.h |   7 +++
 2 files changed, 120 insertions(+)

diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index 516d7ff..32b0029 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -3038,16 +3038,129 @@ static bool vtd_process_pasid_desc(IntelIOMMUState *s,
     return true;
 }
 
+/**
+ * Caller of this function should hold iommu_lock.
+ */
+static void vtd_invalidate_piotlb(IntelIOMMUState *s,
+                                  VTDBus *vtd_bus,
+                                  int devfn,
+                                  struct iommu_cache_invalidate_info *cache)
+{
+    VTDHostIOMMUContext *vtd_dev_icx;
+    HostIOMMUContext *iommu_ctx;
+
+    vtd_dev_icx = vtd_bus->dev_icx[devfn];
+    if (!vtd_dev_icx) {
+        goto out;
+    }
+    iommu_ctx = vtd_dev_icx->iommu_ctx;
+    if (!iommu_ctx) {
+        goto out;
+    }
+    if (host_iommu_ctx_flush_stage1_cache(iommu_ctx, cache)) {
+        error_report("Cache flush failed");
+    }
+out:
+    return;
+}
+
+/**
+ * This function is a loop function for the s->vtd_pasid_as
+ * list with VTDPIOTLBInvInfo as execution filter. It propagates
+ * the piotlb invalidation to host. Caller of this function
+ * should hold iommu_lock.
+ */
+static void vtd_flush_pasid_iotlb(gpointer key, gpointer value,
+                                  gpointer user_data)
+{
+    VTDPIOTLBInvInfo *piotlb_info = user_data;
+    VTDPASIDAddressSpace *vtd_pasid_as = value;
+    VTDPASIDCacheEntry *pc_entry = &vtd_pasid_as->pasid_cache_entry;
+    uint16_t did;
+
+    did = vtd_pe_get_domain_id(&pc_entry->pasid_entry);
+
+    if ((piotlb_info->domain_id == did) &&
+        (piotlb_info->pasid == vtd_pasid_as->pasid)) {
+        vtd_invalidate_piotlb(vtd_pasid_as->iommu_state,
+                              vtd_pasid_as->vtd_bus,
+                              vtd_pasid_as->devfn,
+                              piotlb_info->cache_info);
+    }
+
+    /*
+     * TODO: needs to add QEMU piotlb flush when QEMU piotlb
+     * infrastructure is ready. For now, it is enough for passthru
+     * devices.
+     */
+}
+
 static void vtd_piotlb_pasid_invalidate(IntelIOMMUState *s,
                                         uint16_t domain_id,
                                         uint32_t pasid)
 {
+    VTDPIOTLBInvInfo piotlb_info;
+    struct iommu_cache_invalidate_info *cache_info;
+
+    cache_info = g_malloc0(sizeof(*cache_info));
+
+    cache_info->argsz = sizeof(*cache_info);
+    cache_info->version = IOMMU_CACHE_INVALIDATE_INFO_VERSION_1;
+    cache_info->cache = IOMMU_CACHE_INV_TYPE_IOTLB;
+    cache_info->granularity = IOMMU_INV_GRANU_PASID;
+    cache_info->granu.pasid_info.pasid = pasid;
+    cache_info->granu.pasid_info.flags = IOMMU_INV_PASID_FLAGS_PASID;
+
+    piotlb_info.domain_id = domain_id;
+    piotlb_info.pasid = pasid;
+    piotlb_info.cache_info = cache_info;
+
+    vtd_iommu_lock(s);
+    /*
+     * Here loops all the vtd_pasid_as instances in s->vtd_pasid_as
+     * to find out the affected devices since piotlb invalidation
+     * should check pasid cache per architecture point of view.
+     */
+    g_hash_table_foreach(s->vtd_pasid_as,
+                         vtd_flush_pasid_iotlb, &piotlb_info);
+    vtd_iommu_unlock(s);
+    g_free(cache_info);
 }
 
 static void vtd_piotlb_page_invalidate(IntelIOMMUState *s, uint16_t domain_id,
                                        uint32_t pasid, hwaddr addr, uint8_t am,
                                        bool ih)
 {
+    VTDPIOTLBInvInfo piotlb_info;
+    struct iommu_cache_invalidate_info *cache_info;
+
+    cache_info = g_malloc0(sizeof(*cache_info));
+
+    cache_info->argsz = sizeof(*cache_info);
+    cache_info->version = IOMMU_CACHE_INVALIDATE_INFO_VERSION_1;
+    cache_info->cache = IOMMU_CACHE_INV_TYPE_IOTLB;
+    cache_info->granularity = IOMMU_INV_GRANU_ADDR;
+    cache_info->granu.addr_info.flags = IOMMU_INV_ADDR_FLAGS_PASID;
+    cache_info->granu.addr_info.flags |= ih ? IOMMU_INV_ADDR_FLAGS_LEAF : 0;
+    cache_info->granu.addr_info.pasid = pasid;
+    cache_info->granu.addr_info.addr = addr;
+    cache_info->granu.addr_info.granule_size = 1 << (12 + am);
+    cache_info->granu.addr_info.nb_granules = 1;
+
+    piotlb_info.domain_id = domain_id;
+    piotlb_info.pasid = pasid;
+    piotlb_info.cache_info = cache_info;
+
+    vtd_iommu_lock(s);
+    /*
+     * Here loops all the vtd_pasid_as instances in s->vtd_pasid_as
+     * to find out the affected devices since piotlb invalidation
+     * should check pasid cache per architecture point of view.
+     */
+    g_hash_table_foreach(s->vtd_pasid_as,
+                         vtd_flush_pasid_iotlb, &piotlb_info);
+    vtd_iommu_unlock(s);
+    g_free(cache_info);
 }
 
 static bool vtd_process_piotlb_desc(IntelIOMMUState *s,
diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h
index 118d568..08ff58e 100644
--- a/hw/i386/intel_iommu_internal.h
+++ b/hw/i386/intel_iommu_internal.h
@@ -575,6 +575,13 @@ struct VTDPASIDCacheInfo {
 };
 typedef struct VTDPASIDCacheInfo VTDPASIDCacheInfo;
 
+struct VTDPIOTLBInvInfo {
+    uint16_t domain_id;
+    uint32_t pasid;
+    struct iommu_cache_invalidate_info *cache_info;
+};
+typedef struct VTDPIOTLBInvInfo VTDPIOTLBInvInfo;
+
 /* PASID Table Related Definitions */
 #define VTD_PASID_DIR_BASE_ADDR_MASK  (~0xfffULL)
 #define VTD_PASID_TABLE_BASE_ADDR_MASK (~0xfffULL)
-- 
2.7.4



  parent reply	other threads:[~2020-09-10 11:07 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-09-10 10:56 [RFC v10 00/25] intel_iommu: expose Shared Virtual Addressing to VMs Liu Yi L
2020-09-10 10:56 ` [RFC v10 01/25] scripts/update-linux-headers: Import iommu.h Liu Yi L
2020-09-10 10:56 ` [RFC v10 02/25] header file update VFIO/IOMMU vSVA APIs kernel 5.9-rc2 Liu Yi L
2020-09-10 10:56 ` [RFC v10 03/25] hw/pci: modify pci_setup_iommu() to set PCIIOMMUOps Liu Yi L
2020-09-10 10:56 ` [RFC v10 04/25] hw/pci: introduce pci_device_get_iommu_attr() Liu Yi L
2020-09-10 10:56 ` [RFC v10 05/25] intel_iommu: add get_iommu_attr() callback Liu Yi L
2020-09-10 10:56 ` [RFC v10 06/25] vfio: pass nesting requirement into vfio_get_group() Liu Yi L
2020-09-10 10:56 ` [RFC v10 07/25] vfio: check VFIO_TYPE1_NESTING_IOMMU support Liu Yi L
2020-09-10 10:56 ` [RFC v10 08/25] hw/iommu: introduce HostIOMMUContext Liu Yi L
2020-09-10 10:56 ` [RFC v10 09/25] hw/pci: introduce pci_device_set/unset_iommu_context() Liu Yi L
2020-09-10 10:56 ` [RFC v10 10/25] intel_iommu: add set/unset_iommu_context callback Liu Yi L
2020-09-10 10:56 ` [RFC v10 11/25] vfio/common: provide PASID alloc/free hooks Liu Yi L
2020-09-10 10:56 ` [RFC v10 12/25] vfio: init HostIOMMUContext per-container Liu Yi L
2020-09-10 10:56 ` [RFC v10 13/25] intel_iommu: add virtual command capability support Liu Yi L
2020-09-10 10:56 ` [RFC v10 14/25] intel_iommu: process PASID cache invalidation Liu Yi L
2020-09-10 10:56 ` [RFC v10 15/25] intel_iommu: add PASID cache management infrastructure Liu Yi L
2020-09-10 10:56 ` [RFC v10 16/25] vfio: add bind stage-1 page table support Liu Yi L
2020-09-10 10:56 ` [RFC v10 17/25] intel_iommu: sync IOMMU nesting cap info for assigned devices Liu Yi L
2020-09-10 10:56 ` [RFC v10 18/25] intel_iommu: bind/unbind guest page table to host Liu Yi L
2020-09-10 10:56 ` [RFC v10 19/25] intel_iommu: replay pasid binds after context cache invalidation Liu Yi L
2020-09-10 10:56 ` [RFC v10 20/25] intel_iommu: do not pass down pasid bind for PASID #0 Liu Yi L
2020-09-10 10:56 ` [RFC v10 21/25] vfio: add support for flush iommu stage-1 cache Liu Yi L
2020-09-10 10:56 ` [RFC v10 22/25] intel_iommu: process PASID-based iotlb invalidation Liu Yi L
2020-09-10 10:56 ` Liu Yi L [this message]
2020-09-10 10:56 ` [RFC v10 24/25] intel_iommu: process PASID-based Device-TLB invalidation Liu Yi L
2020-09-10 10:56 ` [RFC v10 25/25] intel_iommu: modify x-scalable-mode to be string option Liu Yi L
2021-02-25 14:14 ` [RFC v10 00/25] intel_iommu: expose Shared Virtual Addressing to VMs Zenghui Yu

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=1599735398-6829-24-git-send-email-yi.l.liu@intel.com \
    --to=yi.l.liu@intel.com \
    --cc=alex.williamson@redhat.com \
    --cc=david@gibson.dropbear.id.au \
    --cc=ehabkost@redhat.com \
    --cc=eric.auger@redhat.com \
    --cc=hao.wu@intel.com \
    --cc=jacob.jun.pan@linux.intel.com \
    --cc=jasowang@redhat.com \
    --cc=jean-philippe@linaro.org \
    --cc=jun.j.tian@intel.com \
    --cc=kevin.tian@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=rth@twiddle.net \
    --cc=yi.y.sun@intel.com \
    --cc=yi.y.sun@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
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).