All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jacob Pan <jacob.jun.pan@linux.intel.com>
To: "Lu Baolu" <baolu.lu@linux.intel.com>,
	iommu@lists.linux-foundation.org,
	LKML <linux-kernel@vger.kernel.org>,
	Joerg Roedel <joro@8bytes.org>,
	David Woodhouse <dwmw2@infradead.org>,
	Jean-Philippe Brucker <jean-philippe@linaro.com>,
	Eric Auger <eric.auger@redhat.com>
Cc: Yi Liu <yi.l.liu@intel.com>, "Tian, Kevin" <kevin.tian@intel.com>,
	Raj Ashok <ashok.raj@intel.com>,
	Alex Williamson <alex.williamson@redhat.com>,
	"Christoph Hellwig" <hch@infradead.org>,
	Jonathan Cameron <jic23@kernel.org>,
	Jacob Pan <jacob.jun.pan@linux.intel.com>
Subject: [PATCH v13 8/8] iommu/vt-d: Add custom allocator for IOASID
Date: Wed, 13 May 2020 16:01:49 -0700	[thread overview]
Message-ID: <1589410909-38925-9-git-send-email-jacob.jun.pan@linux.intel.com> (raw)
In-Reply-To: <1589410909-38925-1-git-send-email-jacob.jun.pan@linux.intel.com>

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.

Virtual command registers are used in the guest only, to prevent
vmexit cost, we cache the capability and store it during initialization.

Signed-off-by: Liu, Yi L <yi.l.liu@intel.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>

---
v12     - squashed virtual command register caching patch with its user
        - reduce indentation
---
---
 drivers/iommu/dmar.c        |  1 +
 drivers/iommu/intel-iommu.c | 85 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/intel-iommu.h |  7 ++++
 3 files changed, 93 insertions(+)

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 34ee8f28555f..66af08ad10fb 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -963,6 +963,7 @@ static int map_iommu(struct intel_iommu *iommu, u64 phys_addr)
 		warn_invalid_dmar(phys_addr, " returns all ones");
 		goto unmap;
 	}
+	iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG);
 
 	/* the registers might be more than one page */
 	map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap),
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 17072442ceae..b28a84a9fca3 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -1732,6 +1732,9 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
 		if (ecap_prs(iommu->ecap))
 			intel_svm_finish_prq(iommu);
 	}
+	if (ecap_vcs(iommu->ecap) && vccap_pasid(iommu->vccap))
+		ioasid_unregister_allocator(&iommu->pasid_allocator);
+
 #endif
 }
 
@@ -3266,6 +3269,85 @@ static int copy_translation_tables(struct intel_iommu *iommu)
 	return ret;
 }
 
+#ifdef CONFIG_INTEL_IOMMU_SVM
+static ioasid_t intel_vcmd_ioasid_alloc(ioasid_t min, ioasid_t max, void *data)
+{
+	struct intel_iommu *iommu = data;
+	ioasid_t ioasid;
+
+	if (!iommu)
+		return INVALID_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 > intel_pasid_max_id)
+		return INVALID_IOASID;
+
+	if (vcmd_alloc_pasid(iommu, &ioasid))
+		return INVALID_IOASID;
+
+	return ioasid;
+}
+
+static void intel_vcmd_ioasid_free(ioasid_t ioasid, void *data)
+{
+	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 unbound.
+	 */
+	if (ioasid_find(NULL, ioasid, NULL)) {
+		pr_alert("Cannot free active IOASID %d\n", ioasid);
+		return;
+	}
+	vcmd_free_pasid(iommu, ioasid);
+}
+
+static void register_pasid_allocator(struct intel_iommu *iommu)
+{
+	/*
+	 * If we are running in the host, no need for custom allocator
+	 * in that PASIDs are allocated from the host system-wide.
+	 */
+	if (!cap_caching_mode(iommu->cap))
+		return;
+
+	if (!sm_supported(iommu)) {
+		pr_warn("VT-d Scalable Mode not enabled, no PASID allocation\n");
+		return;
+	}
+
+	/*
+	 * Register a custom PASID allocator if we are running in a guest,
+	 * guest PASID must be obtained via virtual command interface.
+	 * 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.
+	 */
+	if (!ecap_vcs(iommu->ecap) || !vccap_pasid(iommu->vccap))
+		return;
+
+	pr_info("Register custom PASID allocator\n");
+	iommu->pasid_allocator.alloc = intel_vcmd_ioasid_alloc;
+	iommu->pasid_allocator.free = intel_vcmd_ioasid_free;
+	iommu->pasid_allocator.pdata = (void *)iommu;
+	if (ioasid_register_allocator(&iommu->pasid_allocator)) {
+		pr_warn("Custom PASID allocator failed, scalable mode disabled\n");
+		/*
+		 * Disable scalable mode on this IOMMU if there
+		 * is no custom allocator. Mixing SM capable vIOMMU
+		 * and non-SM vIOMMU are not supported.
+		 */
+		intel_iommu_sm = 0;
+	}
+}
+#endif
+
 static int __init init_dmars(void)
 {
 	struct dmar_drhd_unit *drhd;
@@ -3383,6 +3465,9 @@ static int __init init_dmars(void)
 	 */
 	for_each_active_iommu(iommu, drhd) {
 		iommu_flush_write_buffer(iommu);
+#ifdef CONFIG_INTEL_IOMMU_SVM
+		register_pasid_allocator(iommu);
+#endif
 		iommu_set_root_entry(iommu);
 		iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
 		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index fd641af55494..1d03aa42bf2d 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -19,6 +19,7 @@
 #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>
@@ -195,6 +196,9 @@
 #define ecap_max_handle_mask(e) ((e >> 20) & 0xf)
 #define ecap_sc_support(e)	((e >> 7) & 0x1) /* Snooping Control */
 
+/* Virtual command interface capability */
+#define vccap_pasid(v)		(((v) & DMA_VCS_PAS)) /* PASID allocation */
+
 /* IOTLB_REG */
 #define DMA_TLB_FLUSH_GRANU_OFFSET  60
 #define DMA_TLB_GLOBAL_FLUSH (((u64)1) << 60)
@@ -288,6 +292,7 @@
 
 /* PRS_REG */
 #define DMA_PRS_PPR	((u32)1)
+#define DMA_VCS_PAS	((u64)1)
 
 #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts)			\
 do {									\
@@ -563,6 +568,7 @@ struct intel_iommu {
 	u64		reg_size; /* size of hw register set */
 	u64		cap;
 	u64		ecap;
+	u64		vccap;
 	u32		gcmd; /* Holds TE, EAFL. Don't need SRTP, SFL, WBF */
 	raw_spinlock_t	register_lock; /* protect register handling */
 	int		seq_id;	/* sequence id of the iommu */
@@ -583,6 +589,7 @@ 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.*/
-- 
2.7.4


WARNING: multiple messages have this Message-ID (diff)
From: Jacob Pan <jacob.jun.pan@linux.intel.com>
To: "Lu Baolu" <baolu.lu@linux.intel.com>,
	iommu@lists.linux-foundation.org,
	LKML <linux-kernel@vger.kernel.org>,
	Joerg Roedel <joro@8bytes.org>,
	David Woodhouse <dwmw2@infradead.org>,
	Jean-Philippe Brucker <jean-philippe@linaro.com>,
	Eric Auger <eric.auger@redhat.com>
Cc: "Tian, Kevin" <kevin.tian@intel.com>,
	Raj Ashok <ashok.raj@intel.com>,
	Christoph Hellwig <hch@infradead.org>,
	Alex Williamson <alex.williamson@redhat.com>,
	Jonathan Cameron <jic23@kernel.org>
Subject: [PATCH v13 8/8] iommu/vt-d: Add custom allocator for IOASID
Date: Wed, 13 May 2020 16:01:49 -0700	[thread overview]
Message-ID: <1589410909-38925-9-git-send-email-jacob.jun.pan@linux.intel.com> (raw)
In-Reply-To: <1589410909-38925-1-git-send-email-jacob.jun.pan@linux.intel.com>

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.

Virtual command registers are used in the guest only, to prevent
vmexit cost, we cache the capability and store it during initialization.

Signed-off-by: Liu, Yi L <yi.l.liu@intel.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>

---
v12     - squashed virtual command register caching patch with its user
        - reduce indentation
---
---
 drivers/iommu/dmar.c        |  1 +
 drivers/iommu/intel-iommu.c | 85 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/intel-iommu.h |  7 ++++
 3 files changed, 93 insertions(+)

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 34ee8f28555f..66af08ad10fb 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -963,6 +963,7 @@ static int map_iommu(struct intel_iommu *iommu, u64 phys_addr)
 		warn_invalid_dmar(phys_addr, " returns all ones");
 		goto unmap;
 	}
+	iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG);
 
 	/* the registers might be more than one page */
 	map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap),
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 17072442ceae..b28a84a9fca3 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -1732,6 +1732,9 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
 		if (ecap_prs(iommu->ecap))
 			intel_svm_finish_prq(iommu);
 	}
+	if (ecap_vcs(iommu->ecap) && vccap_pasid(iommu->vccap))
+		ioasid_unregister_allocator(&iommu->pasid_allocator);
+
 #endif
 }
 
@@ -3266,6 +3269,85 @@ static int copy_translation_tables(struct intel_iommu *iommu)
 	return ret;
 }
 
+#ifdef CONFIG_INTEL_IOMMU_SVM
+static ioasid_t intel_vcmd_ioasid_alloc(ioasid_t min, ioasid_t max, void *data)
+{
+	struct intel_iommu *iommu = data;
+	ioasid_t ioasid;
+
+	if (!iommu)
+		return INVALID_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 > intel_pasid_max_id)
+		return INVALID_IOASID;
+
+	if (vcmd_alloc_pasid(iommu, &ioasid))
+		return INVALID_IOASID;
+
+	return ioasid;
+}
+
+static void intel_vcmd_ioasid_free(ioasid_t ioasid, void *data)
+{
+	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 unbound.
+	 */
+	if (ioasid_find(NULL, ioasid, NULL)) {
+		pr_alert("Cannot free active IOASID %d\n", ioasid);
+		return;
+	}
+	vcmd_free_pasid(iommu, ioasid);
+}
+
+static void register_pasid_allocator(struct intel_iommu *iommu)
+{
+	/*
+	 * If we are running in the host, no need for custom allocator
+	 * in that PASIDs are allocated from the host system-wide.
+	 */
+	if (!cap_caching_mode(iommu->cap))
+		return;
+
+	if (!sm_supported(iommu)) {
+		pr_warn("VT-d Scalable Mode not enabled, no PASID allocation\n");
+		return;
+	}
+
+	/*
+	 * Register a custom PASID allocator if we are running in a guest,
+	 * guest PASID must be obtained via virtual command interface.
+	 * 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.
+	 */
+	if (!ecap_vcs(iommu->ecap) || !vccap_pasid(iommu->vccap))
+		return;
+
+	pr_info("Register custom PASID allocator\n");
+	iommu->pasid_allocator.alloc = intel_vcmd_ioasid_alloc;
+	iommu->pasid_allocator.free = intel_vcmd_ioasid_free;
+	iommu->pasid_allocator.pdata = (void *)iommu;
+	if (ioasid_register_allocator(&iommu->pasid_allocator)) {
+		pr_warn("Custom PASID allocator failed, scalable mode disabled\n");
+		/*
+		 * Disable scalable mode on this IOMMU if there
+		 * is no custom allocator. Mixing SM capable vIOMMU
+		 * and non-SM vIOMMU are not supported.
+		 */
+		intel_iommu_sm = 0;
+	}
+}
+#endif
+
 static int __init init_dmars(void)
 {
 	struct dmar_drhd_unit *drhd;
@@ -3383,6 +3465,9 @@ static int __init init_dmars(void)
 	 */
 	for_each_active_iommu(iommu, drhd) {
 		iommu_flush_write_buffer(iommu);
+#ifdef CONFIG_INTEL_IOMMU_SVM
+		register_pasid_allocator(iommu);
+#endif
 		iommu_set_root_entry(iommu);
 		iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
 		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index fd641af55494..1d03aa42bf2d 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -19,6 +19,7 @@
 #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>
@@ -195,6 +196,9 @@
 #define ecap_max_handle_mask(e) ((e >> 20) & 0xf)
 #define ecap_sc_support(e)	((e >> 7) & 0x1) /* Snooping Control */
 
+/* Virtual command interface capability */
+#define vccap_pasid(v)		(((v) & DMA_VCS_PAS)) /* PASID allocation */
+
 /* IOTLB_REG */
 #define DMA_TLB_FLUSH_GRANU_OFFSET  60
 #define DMA_TLB_GLOBAL_FLUSH (((u64)1) << 60)
@@ -288,6 +292,7 @@
 
 /* PRS_REG */
 #define DMA_PRS_PPR	((u32)1)
+#define DMA_VCS_PAS	((u64)1)
 
 #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts)			\
 do {									\
@@ -563,6 +568,7 @@ struct intel_iommu {
 	u64		reg_size; /* size of hw register set */
 	u64		cap;
 	u64		ecap;
+	u64		vccap;
 	u32		gcmd; /* Holds TE, EAFL. Don't need SRTP, SFL, WBF */
 	raw_spinlock_t	register_lock; /* protect register handling */
 	int		seq_id;	/* sequence id of the iommu */
@@ -583,6 +589,7 @@ 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.*/
-- 
2.7.4

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

  parent reply	other threads:[~2020-05-13 22:55 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-13 23:01 [PATCH v13 0/8] Nested Shared Virtual Address (SVA) VT-d support Jacob Pan
2020-05-13 23:01 ` Jacob Pan
2020-05-13 23:01 ` [PATCH v13 1/8] iommu/vt-d: Move domain helper to header Jacob Pan
2020-05-13 23:01   ` Jacob Pan
2020-05-13 23:01 ` [PATCH v13 2/8] iommu/vt-d: Use a helper function to skip agaw for SL Jacob Pan
2020-05-13 23:01   ` Jacob Pan
2020-05-14  5:51   ` Christoph Hellwig
2020-05-14  5:51     ` Christoph Hellwig
2020-05-14 15:20     ` Jacob Pan
2020-05-14 15:20       ` Jacob Pan
2020-05-13 23:01 ` [PATCH v13 3/8] iommu/vt-d: Add nested translation helper function Jacob Pan
2020-05-13 23:01   ` Jacob Pan
2020-05-14  5:54   ` Christoph Hellwig
2020-05-14  5:54     ` Christoph Hellwig
2020-05-14 15:31     ` Jacob Pan
2020-05-14 15:31       ` Jacob Pan
2020-05-13 23:01 ` [PATCH v13 4/8] iommu/vt-d: Add bind guest PASID support Jacob Pan
2020-05-13 23:01   ` Jacob Pan
2020-05-14  5:59   ` Christoph Hellwig
2020-05-14  5:59     ` Christoph Hellwig
2020-05-14 15:57     ` Jacob Pan
2020-05-14 15:57       ` Jacob Pan
2020-05-15  1:01       ` Lu Baolu
2020-05-15  1:01         ` Lu Baolu
2020-05-16  6:02       ` Lu Baolu
2020-05-16  6:02         ` Lu Baolu
2020-05-13 23:01 ` [PATCH v13 5/8] iommu/vt-d: Support flushing more translation cache types Jacob Pan
2020-05-13 23:01   ` Jacob Pan
2020-05-13 23:01 ` [PATCH v13 6/8] iommu/vt-d: Add svm/sva invalidate function Jacob Pan
2020-05-13 23:01   ` Jacob Pan
2020-05-13 23:01 ` [PATCH v13 7/8] iommu/vt-d: Enlightened PASID allocation Jacob Pan
2020-05-13 23:01   ` Jacob Pan
2020-05-13 23:01 ` Jacob Pan [this message]
2020-05-13 23:01   ` [PATCH v13 8/8] iommu/vt-d: Add custom allocator for IOASID Jacob Pan
2020-05-16  6:31 ` [PATCH v13 0/8] Nested Shared Virtual Address (SVA) VT-d support Lu Baolu
2020-05-16  6:31   ` Lu Baolu

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=1589410909-38925-9-git-send-email-jacob.jun.pan@linux.intel.com \
    --to=jacob.jun.pan@linux.intel.com \
    --cc=alex.williamson@redhat.com \
    --cc=ashok.raj@intel.com \
    --cc=baolu.lu@linux.intel.com \
    --cc=dwmw2@infradead.org \
    --cc=eric.auger@redhat.com \
    --cc=hch@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@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.