iommu/vt-d: Add custom allocator for IOASID

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>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/20200516062101.29541-9-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>

3 files changed, 93 insertions, 0 deletions

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 627bb5093317..80d0bd561bdd 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -1726,6 +1726,9 @@ 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
 }
 
@@ -3038,6 +3041,85 @@ out_unmap:
 	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;
@@ -3155,6 +3237,9 @@ 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 addb310b4ded..e14124f74b3a 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 {									\
@@ -555,6 +560,7 @@ 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 */
@@ -575,6 +581,7 @@ 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.*/