IOMMU Archive on lore.kernel.org
 help / color / Atom feed
From: Jacob Pan <jacob.jun.pan@linux.intel.com>
To: iommu@lists.linux-foundation.org,
	LKML <linux-kernel@vger.kernel.org>,
	"Lu Baolu" <baolu.lu@linux.intel.com>,
	Joerg Roedel <joro@8bytes.org>,
	David Woodhouse <dwmw2@infradead.org>
Cc: Yi L <yi.l.liu@linux.intel.com>,
	"Tian, Kevin" <kevin.tian@intel.com>,
	Raj Ashok <ashok.raj@intel.com>,
	Alex Williamson <alex.williamson@redhat.com>,
	Liu@osuosl.org, Jean-Philippe Brucker <jean-philippe@linaro.com>,
	Jonathan Cameron <jic23@kernel.org>
Subject: [PATCH V9 03/10] iommu/vt-d: Add nested translation helper function
Date: Tue, 28 Jan 2020 22:01:46 -0800
Message-ID: <1580277713-66934-4-git-send-email-jacob.jun.pan@linux.intel.com> (raw)
In-Reply-To: <1580277713-66934-1-git-send-email-jacob.jun.pan@linux.intel.com>

Nested translation mode is supported in VT-d 3.0 Spec.CH 3.8.
With PASID granular translation type set to 0x11b, translation
result from the first level(FL) also subject to a second level(SL)
page table translation. This mode is used for SVA virtualization,
where FL performs guest virtual to guest physical translation and
SL performs guest physical to host physical translation.

Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Liu, Yi L <yi.l.liu@linux.intel.com>
---
 drivers/iommu/intel-pasid.c | 225 ++++++++++++++++++++++++++++++++++++++++++++
 drivers/iommu/intel-pasid.h |  12 +++
 include/linux/intel-iommu.h |   3 +
 3 files changed, 240 insertions(+)

diff --git a/drivers/iommu/intel-pasid.c b/drivers/iommu/intel-pasid.c
index 22b30f10b396..bd067af4d20b 100644
--- a/drivers/iommu/intel-pasid.c
+++ b/drivers/iommu/intel-pasid.c
@@ -359,6 +359,76 @@ pasid_set_flpm(struct pasid_entry *pe, u64 value)
 	pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2);
 }
 
+/*
+ * Setup the Extended Memory Type(EMT) field (Bits 91-93)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_emt(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[1], GENMASK_ULL(29, 27), value << 27);
+}
+
+/*
+ * Setup the Page Attribute Table (PAT) field (Bits 96-127)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_pat(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[1], GENMASK_ULL(63, 32), value << 32);
+}
+
+/*
+ * Setup the Cache Disable (CD) field (Bit 89)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_cd(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[1], 1 << 25, 1 << 25);
+}
+
+/*
+ * Setup the Extended Memory Type Enable (EMTE) field (Bit 90)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_emte(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[1], 1 << 26, 1 << 26);
+}
+
+/*
+ * Setup the Extended Access Flag Enable (EAFE) field (Bit 135)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_eafe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 7, 1 << 7);
+}
+
+/*
+ * Setup the Page-level Cache Disable (PCD) field (Bit 95)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_pcd(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[1], 1 << 31, 1 << 31);
+}
+
+/*
+ * Setup the Page-level Write-Through (PWT)) field (Bit 94)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_pwt(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[1], 1 << 30, 1 << 30);
+}
+
 static void
 pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu,
 				    u16 did, int pasid)
@@ -596,3 +666,158 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 
 	return 0;
 }
+
+static int intel_pasid_setup_bind_data(struct intel_iommu *iommu,
+				struct pasid_entry *pte,
+				struct iommu_gpasid_bind_data_vtd *pasid_data)
+{
+	/*
+	 * Not all guest PASID table entry fields are passed down during bind,
+	 * here we only set up the ones that are dependent on guest settings.
+	 * Execution related bits such as NXE, SMEP are not meaningful to IOMMU,
+	 * therefore not set. Other fields, such as snoop related, are set based
+	 * on host needs regardless of  guest settings.
+	 */
+	if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_SRE) {
+		if (!ecap_srs(iommu->ecap)) {
+			pr_err("No supervisor request support on %s\n",
+			       iommu->name);
+			return -EINVAL;
+		}
+		pasid_set_sre(pte);
+	}
+
+	if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_EAFE) {
+		if (!ecap_eafs(iommu->ecap)) {
+			pr_err("No extended access flag support on %s\n",
+				iommu->name);
+			return -EINVAL;
+		}
+		pasid_set_eafe(pte);
+	}
+
+	/*
+	 * Memory type is only applicable to devices inside processor coherent
+	 * domain. PCIe devices are not included. We can skip the rest of the
+	 * flags if IOMMU does not support MTS.
+	 */
+	if (ecap_mts(iommu->ecap)) {
+		if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_EMTE) {
+			pasid_set_emte(pte);
+			pasid_set_emt(pte, pasid_data->emt);
+		}
+		if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_PCD)
+			pasid_set_pcd(pte);
+		if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_PWT)
+			pasid_set_pwt(pte);
+		if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_CD)
+			pasid_set_cd(pte);
+		pasid_set_pat(pte, pasid_data->pat);
+	} else if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_EMT_MASK) {
+		pr_warn("No memory type support for bind guest PASID on %s\n",
+			iommu->name);
+		return -EINVAL;
+	}
+
+	return 0;
+
+}
+
+/**
+ * intel_pasid_setup_nested() - Set up PASID entry for nested translation.
+ * This could be used for guest shared virtual address. In this case, the
+ * first level page tables are used for GVA-GPA translation in the guest,
+ * second level page tables are used for GPA-HPA translation.
+ *
+ * @iommu:      Iommu which the device belong to
+ * @dev:        Device to be set up for translation
+ * @gpgd:       FLPTPTR: First Level Page translation pointer in GPA
+ * @pasid:      PASID to be programmed in the device PASID table
+ * @pasid_data: Additional PASID info from the guest bind request
+ * @domain:     Domain info for setting up second level page tables
+ * @addr_width: Address width of the first level (guest)
+ */
+int intel_pasid_setup_nested(struct intel_iommu *iommu,
+			struct device *dev, pgd_t *gpgd,
+			int pasid, struct iommu_gpasid_bind_data_vtd *pasid_data,
+			struct dmar_domain *domain,
+			int addr_width)
+{
+	struct pasid_entry *pte;
+	struct dma_pte *pgd;
+	int ret = 0;
+	u64 pgd_val;
+	int agaw;
+	u16 did;
+
+	if (!ecap_nest(iommu->ecap)) {
+		pr_err("IOMMU: %s: No nested translation support\n",
+		       iommu->name);
+		return -EINVAL;
+	}
+
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (WARN_ON(!pte))
+		return -EINVAL;
+
+	/*
+	 * Caller must ensure PASID entry is not in use, i.e. not bind the
+	 * same PASID to the same device twice.
+	 */
+	if (pasid_pte_is_present(pte))
+		return -EBUSY;
+
+	pasid_clear_entry(pte);
+
+	/* Sanity checking performed by caller to make sure address
+	 * width matching in two dimensions:
+	 * 1. CPU vs. IOMMU
+	 * 2. Guest vs. Host.
+	 */
+	switch (addr_width) {
+	case ADDR_WIDTH_5LEVEL:
+		pasid_set_flpm(pte, 1);
+		break;
+	case ADDR_WIDTH_4LEVEL:
+		pasid_set_flpm(pte, 0);
+		break;
+	default:
+		dev_err(dev, "Invalid guest address width %d\n", addr_width);
+		return -EINVAL;
+	}
+
+	pasid_set_flptr(pte, (u64)gpgd);
+
+	ret = intel_pasid_setup_bind_data(iommu, pte, pasid_data);
+	if (ret) {
+		dev_err(dev, "Guest PASID bind data not supported\n");
+		return ret;
+	}
+
+	/* Setup the second level based on the given domain */
+	pgd = domain->pgd;
+
+	for (agaw = domain->agaw; agaw != iommu->agaw; agaw--) {
+		pgd = phys_to_virt(dma_pte_addr(pgd));
+		if (!dma_pte_present(pgd)) {
+			pasid_clear_entry(pte);
+			dev_err(dev, "Invalid domain page table\n");
+			return -EINVAL;
+		}
+	}
+	pgd_val = virt_to_phys(pgd);
+	pasid_set_slptr(pte, pgd_val);
+	pasid_set_fault_enable(pte);
+
+	did = domain->iommu_did[iommu->seq_id];
+	pasid_set_domain_id(pte, did);
+
+	pasid_set_address_width(pte, agaw);
+	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
+
+	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_NESTED);
+	pasid_set_present(pte);
+	pasid_flush_caches(iommu, pte, pasid, did);
+
+	return ret;
+}
diff --git a/drivers/iommu/intel-pasid.h b/drivers/iommu/intel-pasid.h
index 92de6df24ccb..698015ee3f04 100644
--- a/drivers/iommu/intel-pasid.h
+++ b/drivers/iommu/intel-pasid.h
@@ -36,6 +36,7 @@
  * to vmalloc or even module mappings.
  */
 #define PASID_FLAG_SUPERVISOR_MODE	BIT(0)
+#define PASID_FLAG_NESTED		BIT(1)
 
 /*
  * The PASID_FLAG_FL5LP flag Indicates using 5-level paging for first-
@@ -51,6 +52,11 @@ struct pasid_entry {
 	u64 val[8];
 };
 
+#define PASID_ENTRY_PGTT_FL_ONLY	(1)
+#define PASID_ENTRY_PGTT_SL_ONLY	(2)
+#define PASID_ENTRY_PGTT_NESTED		(3)
+#define PASID_ENTRY_PGTT_PT		(4)
+
 /* The representative of a PASID table */
 struct pasid_table {
 	void			*table;		/* pasid table pointer */
@@ -99,6 +105,12 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 				   struct dmar_domain *domain,
 				   struct device *dev, int pasid);
+int intel_pasid_setup_nested(struct intel_iommu *iommu,
+			struct device *dev, pgd_t *pgd,
+			int pasid,
+			struct iommu_gpasid_bind_data_vtd *pasid_data,
+			struct dmar_domain *domain,
+			int addr_width);
 void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
 				 struct device *dev, int pasid);
 
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 27c6bbb0a333..c8abf051b2d5 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -42,6 +42,9 @@
 #define DMA_FL_PTE_PRESENT	BIT_ULL(0)
 #define DMA_FL_PTE_XD		BIT_ULL(63)
 
+#define ADDR_WIDTH_5LEVEL	(57)
+#define ADDR_WIDTH_4LEVEL	(48)
+
 #define CONTEXT_TT_MULTI_LEVEL	0
 #define CONTEXT_TT_DEV_IOTLB	1
 #define CONTEXT_TT_PASS_THROUGH 2
-- 
2.7.4

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

  parent reply index

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-29  6:01 [PATCH V9 00/10] Nested Shared Virtual Address (SVA) VT-d support Jacob Pan
2020-01-29  6:01 ` [PATCH V9 01/10] iommu/vt-d: Move domain helper to header Jacob Pan
2020-01-29  6:01 ` [PATCH V9 02/10] iommu/uapi: Define a mask for bind data Jacob Pan
2020-02-12 12:43   ` Auger Eric
2020-03-20 21:35     ` Jacob Pan
2020-01-29  6:01 ` Jacob Pan [this message]
2020-02-12 12:43   ` [PATCH V9 03/10] iommu/vt-d: Add nested translation helper function Auger Eric
2020-02-24 22:55     ` Jacob Pan
2020-01-29  6:01 ` [PATCH V9 04/10] iommu/vt-d: Add bind guest PASID support Jacob Pan
2020-01-30  7:22   ` Lu Baolu
2020-01-31 21:48     ` Jacob Pan
2020-01-29  6:01 ` [PATCH V9 05/10] iommu/vt-d: Support flushing more translation cache types Jacob Pan
2020-02-12 12:55   ` Auger Eric
2020-02-14 23:27     ` Jacob Pan
2020-02-25  8:32       ` Auger Eric
2020-01-29  6:01 ` [PATCH V9 06/10] iommu/vt-d: Add svm/sva invalidate function Jacob Pan
2020-02-12 13:13   ` Auger Eric
2020-02-14 23:48     ` Jacob Pan
2020-02-21  6:34   ` Liu, Yi L
2020-02-21 19:08     ` Jacob Pan
2020-01-29  6:01 ` [PATCH V9 07/10] iommu/vt-d: Cache virtual command capability register Jacob Pan
2020-02-12 13:00   ` Auger Eric
2020-02-21 20:20     ` Jacob Pan
2020-01-29  6:01 ` [PATCH V9 08/10] iommu/vt-d: Enlightened PASID allocation Jacob Pan
2020-01-29  6:01 ` [PATCH V9 09/10] iommu/vt-d: Add custom allocator for IOASID Jacob Pan
2020-01-29  6:01 ` [PATCH V9 10/10] iommu/vt-d: Report PASID format as domain attribute Jacob Pan
2020-01-30  7:54   ` Lu Baolu
2020-02-04  5:43     ` Jacob Pan
2020-01-29 12:18 ` [PATCH V9 00/10] Nested Shared Virtual Address (SVA) VT-d support Liu, Yi L

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=1580277713-66934-4-git-send-email-jacob.jun.pan@linux.intel.com \
    --to=jacob.jun.pan@linux.intel.com \
    --cc=Liu@osuosl.org \
    --cc=alex.williamson@redhat.com \
    --cc=ashok.raj@intel.com \
    --cc=baolu.lu@linux.intel.com \
    --cc=dwmw2@infradead.org \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jean-philippe@linaro.com \
    --cc=jic23@kernel.org \
    --cc=joro@8bytes.org \
    --cc=kevin.tian@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=yi.l.liu@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

IOMMU Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-iommu/0 linux-iommu/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-iommu linux-iommu/ https://lore.kernel.org/linux-iommu \
		iommu@lists.linux-foundation.org
	public-inbox-index linux-iommu

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.linux-foundation.lists.iommu


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git