kvm.vger.kernel.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
Cc: mst@redhat.com, pbonzini@redhat.com, eric.auger@redhat.com,
	david@gibson.dropbear.id.au, jean-philippe@linaro.org,
	kevin.tian@intel.com, yi.l.liu@intel.com, jun.j.tian@intel.com,
	yi.y.sun@intel.com, hao.wu@intel.com, kvm@vger.kernel.org,
	jasowang@redhat.com, Jacob Pan <jacob.jun.pan@linux.intel.com>,
	Yi Sun <yi.y.sun@linux.intel.com>,
	Richard Henderson <rth@twiddle.net>
Subject: [RFC v7 18/25] intel_iommu: bind/unbind guest page table to host
Date: Sat,  4 Jul 2020 04:36:42 -0700	[thread overview]
Message-ID: <1593862609-36135-19-git-send-email-yi.l.liu@intel.com> (raw)
In-Reply-To: <1593862609-36135-1-git-send-email-yi.l.liu@intel.com>

This patch captures the guest PASID table entry modifications and
propagates the changes to host to setup dual stage DMA translation.
The guest page table is configured as 1st level page table (GVA->GPA)
whose translation result would further go through host VT-d 2nd
level page table(GPA->HPA) under nested translation mode. This is the
key part of vSVA support, and also a key to support IOVA over 1st-
level page table for Intel VT-d in virtualization environment.

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>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
---
 hw/i386/intel_iommu.c          | 99 +++++++++++++++++++++++++++++++++++++++---
 hw/i386/intel_iommu_internal.h | 18 ++++++++
 2 files changed, 112 insertions(+), 5 deletions(-)

diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index c3e8b20..cf0dad8 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -41,6 +41,7 @@
 #include "migration/vmstate.h"
 #include "trace.h"
 #include "qemu/jhash.h"
+#include <linux/iommu.h>
 
 /* context entry operations */
 #define VTD_CE_GET_RID2PASID(ce) \
@@ -700,6 +701,16 @@ static inline uint32_t vtd_sm_ce_get_pdt_entry_num(VTDContextEntry *ce)
     return 1U << (VTD_SM_CONTEXT_ENTRY_PDTS(ce->val[0]) + 7);
 }
 
+static inline uint32_t vtd_pe_get_fl_aw(VTDPASIDEntry *pe)
+{
+    return 48 + ((pe->val[2] >> 2) & VTD_SM_PASID_ENTRY_FLPM) * 9;
+}
+
+static inline dma_addr_t vtd_pe_get_flpt_base(VTDPASIDEntry *pe)
+{
+    return pe->val[2] & VTD_SM_PASID_ENTRY_FLPTPTR;
+}
+
 static inline bool vtd_pdire_present(VTDPASIDDirEntry *pdire)
 {
     return pdire->val & 1;
@@ -1861,6 +1872,83 @@ static void vtd_context_global_invalidate(IntelIOMMUState *s)
     vtd_iommu_replay_all(s);
 }
 
+/**
+ * Caller should hold iommu_lock.
+ */
+static int vtd_bind_guest_pasid(IntelIOMMUState *s, VTDBus *vtd_bus,
+                                int devfn, int pasid, VTDPASIDEntry *pe,
+                                VTDPASIDOp op)
+{
+    VTDHostIOMMUContext *vtd_dev_icx;
+    HostIOMMUContext *iommu_ctx;
+    int ret = -1;
+
+    vtd_dev_icx = vtd_bus->dev_icx[devfn];
+    if (!vtd_dev_icx) {
+        /* means no need to go further, e.g. for emulated devices */
+        return 0;
+    }
+
+    iommu_ctx = vtd_dev_icx->iommu_ctx;
+    if (!iommu_ctx) {
+        return -EINVAL;
+    }
+
+    switch (op) {
+    case VTD_PASID_BIND:
+    {
+        struct iommu_gpasid_bind_data *g_bind_data;
+
+        g_bind_data = g_malloc0(sizeof(*g_bind_data));
+
+        g_bind_data->argsz = sizeof(*g_bind_data);
+        g_bind_data->version = IOMMU_GPASID_BIND_VERSION_1;
+        g_bind_data->format = IOMMU_PASID_FORMAT_INTEL_VTD;
+        g_bind_data->gpgd = vtd_pe_get_flpt_base(pe);
+        g_bind_data->addr_width = vtd_pe_get_fl_aw(pe);
+        g_bind_data->hpasid = pasid;
+        g_bind_data->gpasid = pasid;
+        g_bind_data->flags |= IOMMU_SVA_GPASID_VAL;
+        g_bind_data->vendor.vtd.flags =
+                             (VTD_SM_PASID_ENTRY_SRE_BIT(pe->val[2]) ?
+                                            IOMMU_SVA_VTD_GPASID_SRE : 0)
+                           | (VTD_SM_PASID_ENTRY_EAFE_BIT(pe->val[2]) ?
+                                            IOMMU_SVA_VTD_GPASID_EAFE : 0)
+                           | (VTD_SM_PASID_ENTRY_PCD_BIT(pe->val[1]) ?
+                                            IOMMU_SVA_VTD_GPASID_PCD : 0)
+                           | (VTD_SM_PASID_ENTRY_PWT_BIT(pe->val[1]) ?
+                                            IOMMU_SVA_VTD_GPASID_PWT : 0)
+                           | (VTD_SM_PASID_ENTRY_EMTE_BIT(pe->val[1]) ?
+                                            IOMMU_SVA_VTD_GPASID_EMTE : 0)
+                           | (VTD_SM_PASID_ENTRY_CD_BIT(pe->val[1]) ?
+                                            IOMMU_SVA_VTD_GPASID_CD : 0);
+        g_bind_data->vendor.vtd.pat = VTD_SM_PASID_ENTRY_PAT(pe->val[1]);
+        g_bind_data->vendor.vtd.emt = VTD_SM_PASID_ENTRY_EMT(pe->val[1]);
+        ret = host_iommu_ctx_bind_stage1_pgtbl(iommu_ctx, g_bind_data);
+        g_free(g_bind_data);
+        break;
+    }
+    case VTD_PASID_UNBIND:
+    {
+        struct iommu_gpasid_bind_data *g_unbind_data;
+
+        g_unbind_data = g_malloc0(sizeof(*g_unbind_data));
+
+        g_unbind_data->argsz = sizeof(*g_unbind_data);
+        g_unbind_data->hpasid = pasid;
+        ret = host_iommu_ctx_unbind_stage1_pgtbl(iommu_ctx, g_unbind_data);
+        g_free(g_unbind_data);
+        break;
+    }
+    default:
+        error_report_once("Unknown VTDPASIDOp!!!\n");
+        break;
+    }
+
+
+    return ret;
+}
+
 /* Do a context-cache device-selective invalidation.
  * @func_mask: FM field after shifting
  */
@@ -2489,10 +2577,10 @@ static void vtd_fill_pe_in_cache(IntelIOMMUState *s,
     }
 
     pc_entry->pasid_entry = *pe;
-    /*
-     * TODO:
-     * - send pasid bind to host for passthru devices
-     */
+    vtd_bind_guest_pasid(s, vtd_pasid_as->vtd_bus,
+                         vtd_pasid_as->devfn,
+                         vtd_pasid_as->pasid,
+                         pe, VTD_PASID_BIND);
 }
 
 /**
@@ -2565,10 +2653,11 @@ static gboolean vtd_flush_pasid(gpointer key, gpointer value,
 remove:
     /*
      * TODO:
-     * - send pasid bind to host for passthru devices
      * - when pasid-base-iotlb(piotlb) infrastructure is ready,
      *   should invalidate QEMU piotlb togehter with this change.
      */
+    vtd_bind_guest_pasid(s, vtd_bus, devfn,
+                         pasid, NULL, VTD_PASID_UNBIND);
     return true;
 }
 
diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h
index a57ef3d..51691d0 100644
--- a/hw/i386/intel_iommu_internal.h
+++ b/hw/i386/intel_iommu_internal.h
@@ -536,6 +536,13 @@ typedef struct VTDRootEntry VTDRootEntry;
 #define VTD_SM_CONTEXT_ENTRY_RSVD_VAL0(aw)  (0x1e0ULL | ~VTD_HAW_MASK(aw))
 #define VTD_SM_CONTEXT_ENTRY_RSVD_VAL1      0xffffffffffe00000ULL
 
+enum VTDPASIDOp {
+    VTD_PASID_BIND,
+    VTD_PASID_UNBIND,
+    VTD_OP_NUM
+};
+typedef enum VTDPASIDOp VTDPASIDOp;
+
 typedef enum VTDPCInvType {
     /* force reset all */
     VTD_PASID_CACHE_FORCE_RESET = 0,
@@ -578,6 +585,17 @@ typedef struct VTDPASIDCacheInfo VTDPASIDCacheInfo;
 #define VTD_SM_PASID_ENTRY_AW          7ULL /* Adjusted guest-address-width */
 #define VTD_SM_PASID_ENTRY_DID(val)    ((val) & VTD_DOMAIN_ID_MASK)
 
+#define VTD_SM_PASID_ENTRY_FLPM          3ULL
+#define VTD_SM_PASID_ENTRY_FLPTPTR       (~0xfffULL)
+#define VTD_SM_PASID_ENTRY_SRE_BIT(val)  (!!((val) & 1ULL))
+#define VTD_SM_PASID_ENTRY_EAFE_BIT(val) (!!(((val) >> 7) & 1ULL))
+#define VTD_SM_PASID_ENTRY_PCD_BIT(val)  (!!(((val) >> 31) & 1ULL))
+#define VTD_SM_PASID_ENTRY_PWT_BIT(val)  (!!(((val) >> 30) & 1ULL))
+#define VTD_SM_PASID_ENTRY_EMTE_BIT(val) (!!(((val) >> 26) & 1ULL))
+#define VTD_SM_PASID_ENTRY_CD_BIT(val)   (!!(((val) >> 25) & 1ULL))
+#define VTD_SM_PASID_ENTRY_PAT(val)      (((val) >> 32) & 0xFFFFFFFFULL)
+#define VTD_SM_PASID_ENTRY_EMT(val)      (((val) >> 27) & 0x7ULL)
+
 /* Second Level Page Translation Pointer*/
 #define VTD_SM_PASID_ENTRY_SLPTPTR     (~0xfffULL)
 
-- 
2.7.4


  parent reply	other threads:[~2020-07-04 11:30 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-04 11:36 [RFC v7 00/25] intel_iommu: expose Shared Virtual Addressing to VMs Liu Yi L
2020-07-04 11:36 ` [RFC v7 01/25] scripts/update-linux-headers: Import iommu.h Liu Yi L
2020-07-04 11:36 ` [RFC v7 02/25] header file update VFIO/IOMMU vSVA APIs kernel 5.8-rc3 Liu Yi L
2020-07-04 11:36 ` [RFC v7 03/25] hw/pci: modify pci_setup_iommu() to set PCIIOMMUOps Liu Yi L
2020-07-04 11:36 ` [RFC v7 04/25] hw/pci: introduce pci_device_get_iommu_attr() Liu Yi L
2020-07-04 11:36 ` [RFC v7 05/25] intel_iommu: add get_iommu_attr() callback Liu Yi L
2020-07-04 11:36 ` [RFC v7 06/25] vfio: pass nesting requirement into vfio_get_group() Liu Yi L
2020-07-04 11:36 ` [RFC v7 07/25] vfio: check VFIO_TYPE1_NESTING_IOMMU support Liu Yi L
2020-07-04 11:36 ` [RFC v7 08/25] hw/iommu: introduce HostIOMMUContext Liu Yi L
2020-07-04 11:36 ` [RFC v7 09/25] hw/pci: introduce pci_device_set/unset_iommu_context() Liu Yi L
2020-07-04 11:36 ` [RFC v7 10/25] intel_iommu: add set/unset_iommu_context callback Liu Yi L
2020-07-04 11:36 ` [RFC v7 11/25] vfio/common: provide PASID alloc/free hooks Liu Yi L
2020-07-04 11:36 ` [RFC v7 12/25] vfio: init HostIOMMUContext per-container Liu Yi L
2020-07-04 11:36 ` [RFC v7 13/25] intel_iommu: add virtual command capability support Liu Yi L
2020-07-04 11:36 ` [RFC v7 14/25] intel_iommu: process PASID cache invalidation Liu Yi L
2020-07-04 11:36 ` [RFC v7 15/25] intel_iommu: add PASID cache management infrastructure Liu Yi L
2020-07-04 11:36 ` [RFC v7 16/25] vfio: add bind stage-1 page table support Liu Yi L
2020-07-04 11:36 ` [RFC v7 17/25] intel_iommu: sync IOMMU nesting cap info for assigned devices Liu Yi L
2020-07-04 11:36 ` Liu Yi L [this message]
2020-07-04 11:36 ` [RFC v7 19/25] intel_iommu: replay pasid binds after context cache invalidation Liu Yi L
2020-07-04 11:36 ` [RFC v7 20/25] intel_iommu: do not pass down pasid bind for PASID #0 Liu Yi L
2020-07-04 11:36 ` [RFC v7 21/25] vfio: add support for flush iommu stage-1 cache Liu Yi L
2020-07-04 11:36 ` [RFC v7 22/25] intel_iommu: process PASID-based iotlb invalidation Liu Yi L
2020-07-04 11:36 ` [RFC v7 23/25] intel_iommu: propagate PASID-based iotlb invalidation to host Liu Yi L
2020-07-04 11:36 ` [RFC v7 24/25] intel_iommu: process PASID-based Device-TLB invalidation Liu Yi L
2020-07-04 11:36 ` [RFC v7 25/25] intel_iommu: modify x-scalable-mode to be string option Liu Yi L
2020-07-04 11:58 ` [RFC v7 00/25] intel_iommu: expose Shared Virtual Addressing to VMs no-reply

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=1593862609-36135-19-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=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).