From: Zhenzhong Duan <zhenzhong.duan@intel.com>
To: qemu-devel@nongnu.org
Cc: alex.williamson@redhat.com, clg@redhat.com,
eric.auger@redhat.com, mst@redhat.com, peterx@redhat.com,
jasowang@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com,
joao.m.martins@oracle.com, clement.mathieu--drif@eviden.com,
kevin.tian@intel.com, yi.l.liu@intel.com, chao.p.peng@intel.com,
Zhenzhong Duan <zhenzhong.duan@intel.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Richard Henderson <richard.henderson@linaro.org>,
Eduardo Habkost <eduardo@habkost.net>,
Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Subject: [PATCH v5 11/20] intel_iommu: Process PASID-based iotlb invalidation
Date: Mon, 11 Nov 2024 16:34:48 +0800 [thread overview]
Message-ID: <20241111083457.2090664-12-zhenzhong.duan@intel.com> (raw)
In-Reply-To: <20241111083457.2090664-1-zhenzhong.duan@intel.com>
PASID-based iotlb (piotlb) is used during walking Intel
VT-d stage-1 page table.
This emulates the stage-1 page table iotlb invalidation requested
by a PASID-based IOTLB Invalidate Descriptor (P_IOTLB).
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Clément Mathieu--Drif<clement.mathieu--drif@eviden.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
---
hw/i386/intel_iommu_internal.h | 3 +++
hw/i386/intel_iommu.c | 43 ++++++++++++++++++++++++++++++++++
2 files changed, 46 insertions(+)
diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h
index 22dd3faf0c..5e4e563e62 100644
--- a/hw/i386/intel_iommu_internal.h
+++ b/hw/i386/intel_iommu_internal.h
@@ -471,6 +471,9 @@ typedef union VTDInvDesc VTDInvDesc;
#define VTD_INV_DESC_PIOTLB_PSI_IN_PASID (3ULL << 4)
#define VTD_INV_DESC_PIOTLB_DID(val) (((val) >> 16) & VTD_DOMAIN_ID_MASK)
#define VTD_INV_DESC_PIOTLB_PASID(val) (((val) >> 32) & 0xfffffULL)
+#define VTD_INV_DESC_PIOTLB_AM(val) ((val) & 0x3fULL)
+#define VTD_INV_DESC_PIOTLB_IH(val) (((val) >> 6) & 0x1)
+#define VTD_INV_DESC_PIOTLB_ADDR(val) ((val) & ~0xfffULL)
#define VTD_INV_DESC_PIOTLB_RSVD_VAL0 0xfff000000000f1c0ULL
#define VTD_INV_DESC_PIOTLB_RSVD_VAL1 0xf80ULL
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index 4b0fb1f83d..71ef5d741a 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -322,6 +322,28 @@ static gboolean vtd_hash_remove_by_page(gpointer key, gpointer value,
return (entry->gfn & info->mask) == gfn || entry->gfn == gfn_tlb;
}
+static gboolean vtd_hash_remove_by_page_piotlb(gpointer key, gpointer value,
+ gpointer user_data)
+{
+ VTDIOTLBEntry *entry = (VTDIOTLBEntry *)value;
+ VTDIOTLBPageInvInfo *info = (VTDIOTLBPageInvInfo *)user_data;
+ uint64_t gfn = (info->addr >> VTD_PAGE_SHIFT_4K) & info->mask;
+ uint64_t gfn_tlb = (info->addr & entry->mask) >> VTD_PAGE_SHIFT_4K;
+
+ /*
+ * According to spec, PASID-based-IOTLB Invalidation in page granularity
+ * doesn't invalidate IOTLB entries caching second-stage (PGTT=010b)
+ * or pass-through (PGTT=100b) mappings. Nested isn't supported yet,
+ * so only need to check first-stage (PGTT=001b) mappings.
+ */
+ if (entry->pgtt != VTD_SM_PASID_ENTRY_FLT) {
+ return false;
+ }
+
+ return entry->domain_id == info->domain_id && entry->pasid == info->pasid &&
+ ((entry->gfn & info->mask) == gfn || entry->gfn == gfn_tlb);
+}
+
/* Reset all the gen of VTDAddressSpace to zero and set the gen of
* IntelIOMMUState to 1. Must be called with IOMMU lock held.
*/
@@ -2937,11 +2959,29 @@ static void vtd_piotlb_pasid_invalidate(IntelIOMMUState *s,
}
}
+static void vtd_piotlb_page_invalidate(IntelIOMMUState *s, uint16_t domain_id,
+ uint32_t pasid, hwaddr addr, uint8_t am)
+{
+ VTDIOTLBPageInvInfo info;
+
+ info.domain_id = domain_id;
+ info.pasid = pasid;
+ info.addr = addr;
+ info.mask = ~((1 << am) - 1);
+
+ vtd_iommu_lock(s);
+ g_hash_table_foreach_remove(s->iotlb,
+ vtd_hash_remove_by_page_piotlb, &info);
+ vtd_iommu_unlock(s);
+}
+
static bool vtd_process_piotlb_desc(IntelIOMMUState *s,
VTDInvDesc *inv_desc)
{
uint16_t domain_id;
uint32_t pasid;
+ hwaddr addr;
+ uint8_t am;
uint64_t mask[4] = {VTD_INV_DESC_PIOTLB_RSVD_VAL0,
VTD_INV_DESC_PIOTLB_RSVD_VAL1,
VTD_INV_DESC_ALL_ONE, VTD_INV_DESC_ALL_ONE};
@@ -2959,6 +2999,9 @@ static bool vtd_process_piotlb_desc(IntelIOMMUState *s,
break;
case VTD_INV_DESC_PIOTLB_PSI_IN_PASID:
+ am = VTD_INV_DESC_PIOTLB_AM(inv_desc->val[1]);
+ addr = (hwaddr) VTD_INV_DESC_PIOTLB_ADDR(inv_desc->val[1]);
+ vtd_piotlb_page_invalidate(s, domain_id, pasid, addr, am);
break;
default:
--
2.34.1
next prev parent reply other threads:[~2024-11-11 8:39 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-11 8:34 [PATCH v5 00/20] intel_iommu: Enable stage-1 translation for emulated device Zhenzhong Duan
2024-11-11 8:34 ` [PATCH v5 01/20] intel_iommu: Use the latest fault reasons defined by spec Zhenzhong Duan
2024-11-11 8:34 ` [PATCH v5 02/20] intel_iommu: Make pasid entry type check accurate Zhenzhong Duan
2024-11-11 8:34 ` [PATCH v5 03/20] intel_iommu: Add a placeholder variable for scalable modern mode Zhenzhong Duan
2024-11-11 8:34 ` [PATCH v5 04/20] intel_iommu: Flush stage-2 cache in PASID-selective PASID-based iotlb invalidation Zhenzhong Duan
2024-11-11 8:34 ` [PATCH v5 05/20] intel_iommu: Rename slpte to pte Zhenzhong Duan
2024-11-11 8:34 ` [PATCH v5 06/20] intel_iommu: Implement stage-1 translation Zhenzhong Duan
2024-11-11 8:34 ` [PATCH v5 07/20] intel_iommu: Check if the input address is canonical Zhenzhong Duan
2024-11-11 8:34 ` [PATCH v5 08/20] intel_iommu: Check stage-1 translation result with interrupt range Zhenzhong Duan
2024-11-13 6:55 ` CLEMENT MATHIEU--DRIF
2024-11-13 8:49 ` Duan, Zhenzhong
2024-11-14 6:04 ` CLEMENT MATHIEU--DRIF
2024-12-04 2:11 ` Jason Wang
2024-11-11 8:34 ` [PATCH v5 09/20] intel_iommu: Set accessed and dirty bits during stage-1 translation Zhenzhong Duan
2024-11-11 8:34 ` [PATCH v5 10/20] intel_iommu: Flush stage-1 cache in iotlb invalidation Zhenzhong Duan
2024-11-11 8:34 ` Zhenzhong Duan [this message]
2024-11-11 8:34 ` [PATCH v5 12/20] intel_iommu: Add an internal API to find an address space with PASID Zhenzhong Duan
2024-11-11 8:34 ` [PATCH v5 13/20] intel_iommu: Add support for PASID-based device IOTLB invalidation Zhenzhong Duan
2024-12-04 3:27 ` Jason Wang
2024-11-11 8:34 ` [PATCH v5 14/20] intel_iommu: piotlb invalidation should notify unmap Zhenzhong Duan
2024-11-11 8:34 ` [PATCH v5 15/20] tests/acpi: q35: allow DMAR acpi table changes Zhenzhong Duan
2024-11-20 6:09 ` CLEMENT MATHIEU--DRIF
2024-12-04 3:27 ` Jason Wang
2024-11-11 8:34 ` [PATCH v5 16/20] intel_iommu: Set default aw_bits to 48 starting from QEMU 9.2 Zhenzhong Duan
2024-12-04 3:28 ` Jason Wang
2024-11-11 8:34 ` [PATCH v5 17/20] tests/acpi: q35: Update host address width in DMAR Zhenzhong Duan
2024-11-13 7:16 ` CLEMENT MATHIEU--DRIF
2024-11-13 8:50 ` Duan, Zhenzhong
2024-11-11 8:34 ` [PATCH v5 18/20] intel_iommu: Introduce a property x-flts for scalable modern mode Zhenzhong Duan
2024-11-19 6:54 ` CLEMENT MATHIEU--DRIF
2024-11-19 7:28 ` Duan, Zhenzhong
2024-11-19 8:59 ` CLEMENT MATHIEU--DRIF
2024-11-19 9:25 ` Duan, Zhenzhong
2024-11-20 6:11 ` CLEMENT MATHIEU--DRIF
2024-12-04 3:34 ` Jason Wang
2024-12-04 6:14 ` CLEMENT MATHIEU--DRIF
2024-12-09 3:13 ` Jason Wang
2024-12-09 6:14 ` CLEMENT MATHIEU--DRIF
2024-12-09 6:24 ` Jason Wang
2024-12-09 6:42 ` CLEMENT MATHIEU--DRIF
2024-12-11 2:22 ` Duan, Zhenzhong
2024-12-11 3:03 ` Jason Wang
2024-12-11 6:08 ` CLEMENT MATHIEU--DRIF
2024-11-11 8:34 ` [PATCH v5 19/20] intel_iommu: Introduce a property to control FS1GP cap bit setting Zhenzhong Duan
2024-11-11 8:34 ` [PATCH v5 20/20] tests/qtest: Add intel-iommu test Zhenzhong Duan
2024-12-03 9:00 ` [PATCH v5 00/20] intel_iommu: Enable stage-1 translation for emulated device Duan, Zhenzhong
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=20241111083457.2090664-12-zhenzhong.duan@intel.com \
--to=zhenzhong.duan@intel.com \
--cc=alex.williamson@redhat.com \
--cc=chao.p.peng@intel.com \
--cc=clement.mathieu--drif@eviden.com \
--cc=clg@redhat.com \
--cc=eduardo@habkost.net \
--cc=eric.auger@redhat.com \
--cc=jasowang@redhat.com \
--cc=jgg@nvidia.com \
--cc=joao.m.martins@oracle.com \
--cc=kevin.tian@intel.com \
--cc=marcel.apfelbaum@gmail.com \
--cc=mst@redhat.com \
--cc=nicolinc@nvidia.com \
--cc=pbonzini@redhat.com \
--cc=peterx@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=richard.henderson@linaro.org \
--cc=yi.l.liu@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).