[PATCH 0/4 v2] KVM: PPC: IOMMU in-kernel handling

@@ -2780,3 +2780,17 @@ Parameters: args[0] is the XICS device fd
             args[1] is the XICS CPU number (server ID) for this vcpu
 
 This capability connects the vcpu to an in-kernel XICS device.
+
+6.8 KVM_CAP_PPC_MULTITCE
+
+Architectures: ppc
+Parameters: none
+Returns: 0 on success; -1 on error
+
+This capability enables the guest to put/remove multiple TCE entries
+per hypercall which significanly accelerates DMA operations for PPC KVM
+guests.
+
+When this capability is enabled, H_PUT_TCE_INDIRECT and H_STUFF_TCE are
+expected to occur rather than H_PUT_TCE which supports only one TCE entry
+per call.

@@ -609,6 +609,8 @@ struct kvm_vcpu_arch {
 	spinlock_t tbacct_lock;
 	u64 busy_stolen;
 	u64 busy_preempt;
+
+	unsigned long *tce_tmp;    /* TCE cache for TCE_PUT_INDIRECT hall */
 #endif
 };
 

@@ -133,8 +133,20 @@ extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
 
 extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce *args);
-extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
-			     unsigned long ioba, unsigned long tce);
+extern struct kvmppc_spapr_tce_table *kvmppc_find_tce_table(
+		struct kvm_vcpu *vcpu, unsigned long liobn);
+extern long kvmppc_emulated_validate_tce(unsigned long tce);
+extern void kvmppc_emulated_put_tce(struct kvmppc_spapr_tce_table *tt,
+		unsigned long ioba, unsigned long tce);
+extern long kvmppc_virtmode_h_put_tce(struct kvm_vcpu *vcpu,
+		unsigned long liobn, unsigned long ioba,
+		unsigned long tce);
+extern long kvmppc_virtmode_h_put_tce_indirect(struct kvm_vcpu *vcpu,
+		unsigned long liobn, unsigned long ioba,
+		unsigned long tce_list, unsigned long npages);
+extern long kvmppc_virtmode_h_stuff_tce(struct kvm_vcpu *vcpu,
+		unsigned long liobn, unsigned long ioba,
+		unsigned long tce_value, unsigned long npages);
 extern long kvm_vm_ioctl_allocate_rma(struct kvm *kvm,
 				struct kvm_allocate_rma *rma);
 extern struct kvmppc_linear_info *kvm_alloc_rma(void);

@@ -14,6 +14,7 @@
  *
  * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  * Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com>
+ * Copyright 2013 Alexey Kardashevskiy, IBM Corporation <aik@au1.ibm.com>
  */
 
 #include <linux/types.h>

@@ -36,8 +37,11 @@
 #include <asm/ppc-opcode.h>
 #include <asm/kvm_host.h>
 #include <asm/udbg.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
 
 #define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
+#define ERROR_ADDR      ((void *)~(unsigned long)0x0)
 
 static long kvmppc_stt_npages(unsigned long window_size)
 {

@@ -148,3 +152,117 @@ fail:
 	}
 	return ret;
 }
+
+/* Converts guest physical address into host virtual */
+static void __user *kvmppc_virtmode_gpa_to_hva(struct kvm_vcpu *vcpu,
+		unsigned long gpa)
+{
+	unsigned long hva, gfn = gpa >> PAGE_SHIFT;
+	struct kvm_memory_slot *memslot;
+
+	memslot = search_memslots(kvm_memslots(vcpu->kvm), gfn);
+	if (!memslot)
+		return ERROR_ADDR;
+
+	hva = __gfn_to_hva_memslot(memslot, gfn) + (gpa & ~PAGE_MASK);
+	return (void *) hva;
+}
+
+long kvmppc_virtmode_h_put_tce(struct kvm_vcpu *vcpu,
+		unsigned long liobn, unsigned long ioba,
+		unsigned long tce)
+{
+	long ret;
+	struct kvmppc_spapr_tce_table *tt;
+
+	tt = kvmppc_find_tce_table(vcpu, liobn);
+	/* Didn't find the liobn, put it to userspace */
+	if (!tt)
+		return H_TOO_HARD;
+
+	/* Emulated IO */
+	if (ioba >= tt->window_size)
+		return H_PARAMETER;
+
+	ret = kvmppc_emulated_validate_tce(tce);
+	if (ret)
+		return ret;
+
+	kvmppc_emulated_put_tce(tt, ioba, tce);
+
+	return H_SUCCESS;
+}
+
+long kvmppc_virtmode_h_put_tce_indirect(struct kvm_vcpu *vcpu,
+		unsigned long liobn, unsigned long ioba,
+		unsigned long tce_list, unsigned long npages)
+{
+	struct kvmppc_spapr_tce_table *tt;
+	long i, ret;
+	unsigned long __user *tces;
+
+	tt = kvmppc_find_tce_table(vcpu, liobn);
+	/* Didn't find the liobn, put it to userspace */
+	if (!tt)
+		return H_TOO_HARD;
+
+	/*
+	 * The spec says that the maximum size of the list is 512 TCEs so
+	 * so the whole table addressed resides in 4K page
+	 */
+	if (npages > 512)
+		return H_PARAMETER;
+
+	if (tce_list & ~IOMMU_PAGE_MASK)
+		return H_PARAMETER;
+
+	tces = kvmppc_virtmode_gpa_to_hva(vcpu, tce_list);
+	if (tces == ERROR_ADDR)
+		return H_TOO_HARD;
+
+	/* Emulated IO */
+	if ((ioba + (npages << IOMMU_PAGE_SHIFT)) > tt->window_size)
+		return H_PARAMETER;
+
+	for (i = 0; i < npages; ++i) {
+		if (get_user(vcpu->arch.tce_tmp[i], tces + i))
+			return H_PARAMETER;
+
+		ret = kvmppc_emulated_validate_tce(vcpu->arch.tce_tmp[i]);
+		if (ret)
+			return ret;
+	}
+
+	for (i = 0; i < npages; ++i)
+		kvmppc_emulated_put_tce(tt,
+				ioba + (i << IOMMU_PAGE_SHIFT),
+				vcpu->arch.tce_tmp[i]);
+
+	return H_SUCCESS;
+}
+
+long kvmppc_virtmode_h_stuff_tce(struct kvm_vcpu *vcpu,
+		unsigned long liobn, unsigned long ioba,
+		unsigned long tce_value, unsigned long npages)
+{
+	struct kvmppc_spapr_tce_table *tt;
+	long i, ret;
+
+	tt = kvmppc_find_tce_table(vcpu, liobn);
+	/* Didn't find the liobn, put it to userspace */
+	if (!tt)
+		return H_TOO_HARD;
+
+	/* Emulated IO */
+	if ((ioba + (npages << IOMMU_PAGE_SHIFT)) > tt->window_size)
+		return H_PARAMETER;
+
+	ret = kvmppc_emulated_validate_tce(tce_value);
+	if (ret || (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ)))
+		return H_PARAMETER;
+
+	for (i = 0; i < npages; ++i, ioba += IOMMU_PAGE_SIZE)
+		kvmppc_emulated_put_tce(tt, ioba, tce_value);
+
+	return H_SUCCESS;
+}

@@ -14,6 +14,7 @@
  *
  * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  * Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com>
+ * Copyright 2013 Alexey Kardashevskiy, IBM Corporation <aik@au1.ibm.com>
  */
 
 #include <linux/types.h>

@@ -35,42 +36,249 @@
 #include <asm/ppc-opcode.h>
 #include <asm/kvm_host.h>
 #include <asm/udbg.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
 
 #define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
+#define ERROR_ADDR      (~(unsigned long)0x0)
 
-/* WARNING: This will be called in real-mode on HV KVM and virtual
- *          mode on PR KVM
+/* Finds a TCE table descriptor by LIOBN */
+struct kvmppc_spapr_tce_table *kvmppc_find_tce_table(struct kvm_vcpu *vcpu,
+		unsigned long liobn)
+{
+	struct kvmppc_spapr_tce_table *tt;
+
+	list_for_each_entry(tt, &vcpu->kvm->arch.spapr_tce_tables, list) {
+		if (tt->liobn == liobn)
+			return tt;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(kvmppc_find_tce_table);
+
+/*
+ * Validate TCE address.
+ * At the moment only flags are validated
+ * as other check will significantly slow down
+ * or can make it even impossible to handle TCE requests
+ * in real mode.
+ */
+long kvmppc_emulated_validate_tce(unsigned long tce)
+{
+	if (tce & ~(IOMMU_PAGE_MASK | TCE_PCI_WRITE | TCE_PCI_READ))
+		return H_PARAMETER;
+
+	return H_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(kvmppc_emulated_validate_tce);
+
+/*
+ * kvmppc_emulated_put_tce() handles TCE requests for devices emulated
+ * by QEMU. It puts guest TCE values into the table and expects
+ * the QEMU to convert them later in the QEMU device implementation.
+ * Wiorks in both real and virtual modes.
+ * It cannot fail so kvmppc_emulated_validate_tce must be called before it.
  */
+void kvmppc_emulated_put_tce(struct kvmppc_spapr_tce_table *tt,
+		unsigned long ioba, unsigned long tce)
+{
+	unsigned long idx = ioba >> SPAPR_TCE_SHIFT;
+	struct page *page;
+	u64 *tbl;
+
+	/*
+	 * Note on the use of page_address() in real mode,
+	 *
+	 * It is safe to use page_address() in real mode on ppc64 because
+	 * page_address() is always defined as lowmem_page_address()
+	 * which returns __va(PFN_PHYS(page_to_pfn(page))) which is arithmetial
+	 * operation and does not access page struct.
+	 *
+	 * Theoretically page_address() could be defined different
+	 * but either WANT_PAGE_VIRTUAL or HASHED_PAGE_VIRTUAL
+	 * should be enabled.
+	 * WANT_PAGE_VIRTUAL is never enabled on ppc32/ppc64,
+	 * HASHED_PAGE_VIRTUAL could be enabled for ppc32 only and only
+	 * if CONFIG_HIGHMEM is defined. As CONFIG_SPARSEMEM_VMEMMAP
+	 * is not expected to be enabled on ppc32, page_address()
+	 * is safe for ppc32 as well.
+	 */
+#if defined(HASHED_PAGE_VIRTUAL) || defined(WANT_PAGE_VIRTUAL)
+#error TODO: fix to avoid page_address() here
+#endif
+	page = tt->pages[idx / TCES_PER_PAGE];
+	tbl = (u64 *)page_address(page);
+
+	/* udbg_printf("tce @ %p\n", &tbl[idx % TCES_PER_PAGE]); */
+	tbl[idx % TCES_PER_PAGE] = tce;
+}
+EXPORT_SYMBOL_GPL(kvmppc_emulated_put_tce);
+
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+
+static pte_t kvmppc_lookup_pte(pgd_t *pgdir, unsigned long hva, bool writing,
+			unsigned long *pte_sizep)
+{
+	pte_t *ptep;
+	unsigned int shift = 0;
+	pte_t pte, tmp, ret;
+
+	ptep = find_linux_pte_or_hugepte(pgdir, hva, &shift);
+	if (!ptep)
+		return __pte(0);
+	if (shift)
+		*pte_sizep = 1ul << shift;
+	else
+		*pte_sizep = PAGE_SIZE;
+
+	if (!pte_present(*ptep))
+		return __pte(0);
+
+	/* wait until _PAGE_BUSY is clear then set it atomically */
+	__asm__ __volatile__ (
+		"1:	ldarx	%0,0,%3\n"
+		"	andi.	%1,%0,%4\n"
+		"	bne-	1b\n"
+		"	ori	%1,%0,%4\n"
+		"	stdcx.	%1,0,%3\n"
+		"	bne-	1b"
+		: "=&r" (pte), "=&r" (tmp), "=m" (*ptep)
+		: "r" (ptep), "i" (_PAGE_BUSY)
+		: "cc");
+
+	ret = pte;
+
+	return ret;
+}
+
+/*
+ * Converts guest physical address into host physical address.
+ * Also returns pte and page size if the page is present in page table.
+ */
+static unsigned long kvmppc_realmode_gpa_to_hpa(struct kvm_vcpu *vcpu,
+		unsigned long gpa)
+{
+	struct kvm_memory_slot *memslot;
+	pte_t pte;
+	unsigned long hva, hpa, pg_size = 0, offset;
+	unsigned long gfn = gpa >> PAGE_SHIFT;
+	bool writing = gpa & TCE_PCI_WRITE;
+
+	/* Find a KVM memslot */
+	memslot = search_memslots(kvm_memslots(vcpu->kvm), gfn);
+	if (!memslot)
+		return ERROR_ADDR;
+
+	/* Convert guest physical address to host virtual */
+	hva = __gfn_to_hva_memslot(memslot, gfn);
+
+	/* Find a PTE and determine the size */
+	pte = kvmppc_lookup_pte(vcpu->arch.pgdir, hva,
+			writing, &pg_size);
+	if (!pte)
+		return ERROR_ADDR;
+
+	/* Calculate host phys address keeping flags and offset in the page */
+	offset = gpa & (pg_size - 1);
+
+	/* pte_pfn(pte) should return an address aligned to pg_size */
+	hpa = (pte_pfn(pte) << PAGE_SHIFT) + offset;
+
+	return hpa;
+}
+
 long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		      unsigned long ioba, unsigned long tce)
 {
-	struct kvm *kvm = vcpu->kvm;
-	struct kvmppc_spapr_tce_table *stt;
-
-	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
-	/* 	    liobn, ioba, tce); */
-
-	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
-		if (stt->liobn == liobn) {
-			unsigned long idx = ioba >> SPAPR_TCE_SHIFT;
-			struct page *page;
-			u64 *tbl;
-
-			/* udbg_printf("H_PUT_TCE: liobn 0x%lx => stt=%p  window_size=0x%x\n", */
-			/* 	    liobn, stt, stt->window_size); */
-			if (ioba >= stt->window_size)
-				return H_PARAMETER;
-
-			page = stt->pages[idx / TCES_PER_PAGE];
-			tbl = (u64 *)page_address(page);
-
-			/* FIXME: Need to validate the TCE itself */
-			/* udbg_printf("tce @ %p\n", &tbl[idx % TCES_PER_PAGE]); */
-			tbl[idx % TCES_PER_PAGE] = tce;
-			return H_SUCCESS;
-		}
+	long ret;
+	struct kvmppc_spapr_tce_table *tt;
+
+	tt = kvmppc_find_tce_table(vcpu, liobn);
+	/* Didn't find the liobn, put it to virtual space */
+	if (!tt)
+		return H_TOO_HARD;
+
+	/* Emulated IO */
+	if (ioba >= tt->window_size)
+		return H_PARAMETER;
+
+	ret = kvmppc_emulated_validate_tce(tce);
+	if (ret)
+		return ret;
+
+	kvmppc_emulated_put_tce(tt, ioba, tce);
+
+	return H_SUCCESS;
+}
+
+long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
+		unsigned long liobn, unsigned long ioba,
+		unsigned long tce_list,	unsigned long npages)
+{
+	struct kvmppc_spapr_tce_table *tt;
+	long i, ret;
+	unsigned long *tces;
+
+	tt = kvmppc_find_tce_table(vcpu, liobn);
+	/* Didn't find the liobn, put it to virtual space */
+	if (!tt)
+		return H_TOO_HARD;
+
+	/*
+	 * The spec says that the maximum size of the list is 512 TCEs so
+	 * so the whole table addressed resides in 4K page
+	 */
+	if (npages > 512)
+		return H_PARAMETER;
+
+	if (tce_list & ~IOMMU_PAGE_MASK)
+		return H_PARAMETER;
+
+	tces = (unsigned long *) kvmppc_realmode_gpa_to_hpa(vcpu, tce_list);
+	if ((unsigned long)tces == ERROR_ADDR)
+		return H_TOO_HARD;
+
+	/* Emulated IO */
+	if ((ioba + (npages << IOMMU_PAGE_SHIFT)) > tt->window_size)
+		return H_PARAMETER;
+
+	for (i = 0; i < npages; ++i) {
+		ret = kvmppc_emulated_validate_tce(tces[i]);
+		if (ret)
+			return ret;
 	}
 
-	/* Didn't find the liobn, punt it to userspace */
-	return H_TOO_HARD;
+	for (i = 0; i < npages; ++i)
+		kvmppc_emulated_put_tce(tt, ioba + (i << IOMMU_PAGE_SHIFT),
+				tces[i]);
+
+	return H_SUCCESS;
+}
+
+long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
+		unsigned long liobn, unsigned long ioba,
+		unsigned long tce_value, unsigned long npages)
+{
+	struct kvmppc_spapr_tce_table *tt;
+	long i, ret;
+
+	tt = kvmppc_find_tce_table(vcpu, liobn);
+	/* Didn't find the liobn, put it to virtual space */
+	if (!tt)
+		return H_TOO_HARD;
+
+	/* Emulated IO */
+	if ((ioba + (npages << IOMMU_PAGE_SHIFT)) > tt->window_size)
+		return H_PARAMETER;
+
+	ret = kvmppc_emulated_validate_tce(tce_value);
+	if (ret || (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ)))
+		return H_PARAMETER;
+
+	for (i = 0; i < npages; ++i, ioba += IOMMU_PAGE_SIZE)
+		kvmppc_emulated_put_tce(tt, ioba, tce_value);
+
+	return H_SUCCESS;
 }
+#endif /* CONFIG_KVM_BOOK3S_64_HV */

@@ -566,6 +566,30 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 			ret = kvmppc_xics_hcall(vcpu, req);
 			break;
 		} /* fallthrough */
+		return RESUME_HOST;
+	case H_PUT_TCE:
+		ret = kvmppc_virtmode_h_put_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
+						kvmppc_get_gpr(vcpu, 5),
+						kvmppc_get_gpr(vcpu, 6));
+		if (ret == H_TOO_HARD)
+			return RESUME_HOST;
+		break;
+	case H_PUT_TCE_INDIRECT:
+		ret = kvmppc_virtmode_h_put_tce_indirect(vcpu, kvmppc_get_gpr(vcpu, 4),
+						kvmppc_get_gpr(vcpu, 5),
+						kvmppc_get_gpr(vcpu, 6),
+						kvmppc_get_gpr(vcpu, 7));
+		if (ret == H_TOO_HARD)
+			return RESUME_HOST;
+		break;
+	case H_STUFF_TCE:
+		ret = kvmppc_virtmode_h_stuff_tce(vcpu, kvmppc_get_gpr(vcpu, 4),
+						kvmppc_get_gpr(vcpu, 5),
+						kvmppc_get_gpr(vcpu, 6),
+						kvmppc_get_gpr(vcpu, 7));
+		if (ret == H_TOO_HARD)
+			return RESUME_HOST;
+		break;
 	default:
 		return RESUME_HOST;
 	}

@@ -956,6 +980,20 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	vcpu->arch.cpu_type = KVM_CPU_3S_64;
 	kvmppc_sanity_check(vcpu);
 
+	/*
+	 * As we want to minimize the chance of having H_PUT_TCE_INDIRECT
+	 * half executed, we first read TCEs from the user, check them and
+	 * return error if something went wrong and only then put TCEs into
+	 * the TCE table.
+	 *
+	 * tce_tmp is a cache for TCEs to avoid stack allocation or
+	 * kmalloc as the whole TCE list can take up to 512 items 8 bytes
+	 * each (4096 bytes).
+	 */
+	vcpu->arch.tce_tmp = kmalloc(4096, GFP_KERNEL);
+	if (!vcpu->arch.tce_tmp)
+		goto free_vcpu;
+
 	return vcpu;
 
 free_vcpu:

@@ -978,6 +1016,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	unpin_vpa(vcpu->kvm, &vcpu->arch.slb_shadow);
 	unpin_vpa(vcpu->kvm, &vcpu->arch.vpa);
 	spin_unlock(&vcpu->arch.vpa_update_lock);
+	kfree(vcpu->arch.tce_tmp);
 	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }

@@ -1490,6 +1490,12 @@ hcall_real_table:
 	.long	0		/* 0x11c */
 	.long	0		/* 0x120 */
 	.long	.kvmppc_h_bulk_remove - hcall_real_table
+	.long	0		/* 0x128 */
+	.long	0		/* 0x12c */
+	.long	0		/* 0x130 */
+	.long	0		/* 0x134 */
+	.long	.kvmppc_h_stuff_tce - hcall_real_table
+	.long	.kvmppc_h_put_tce_indirect - hcall_real_table
 hcall_real_table_end:
 
 ignore_hdec:

@@ -220,7 +220,38 @@ static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
 	unsigned long tce = kvmppc_get_gpr(vcpu, 6);
 	long rc;
 
-	rc = kvmppc_h_put_tce(vcpu, liobn, ioba, tce);
+	rc = kvmppc_virtmode_h_put_tce(vcpu, liobn, ioba, tce);
+	if (rc == H_TOO_HARD)
+		return EMULATE_FAIL;
+	kvmppc_set_gpr(vcpu, 3, rc);
+	return EMULATE_DONE;
+}
+
+static int kvmppc_h_pr_put_tce_indirect(struct kvm_vcpu *vcpu)
+{
+	unsigned long liobn = kvmppc_get_gpr(vcpu, 4);
+	unsigned long ioba = kvmppc_get_gpr(vcpu, 5);
+	unsigned long tce = kvmppc_get_gpr(vcpu, 6);
+	unsigned long npages = kvmppc_get_gpr(vcpu, 7);
+	long rc;
+
+	rc = kvmppc_virtmode_h_put_tce_indirect(vcpu, liobn, ioba,
+			tce, npages);
+	if (rc == H_TOO_HARD)
+		return EMULATE_FAIL;
+	kvmppc_set_gpr(vcpu, 3, rc);
+	return EMULATE_DONE;
+}
+
+static int kvmppc_h_pr_stuff_tce(struct kvm_vcpu *vcpu)
+{
+	unsigned long liobn = kvmppc_get_gpr(vcpu, 4);
+	unsigned long ioba = kvmppc_get_gpr(vcpu, 5);
+	unsigned long tce_value = kvmppc_get_gpr(vcpu, 6);
+	unsigned long npages = kvmppc_get_gpr(vcpu, 7);
+	long rc;
+
+	rc = kvmppc_virtmode_h_stuff_tce(vcpu, liobn, ioba, tce_value, npages);
 	if (rc == H_TOO_HARD)
 		return EMULATE_FAIL;
 	kvmppc_set_gpr(vcpu, 3, rc);

@@ -247,6 +278,10 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
 		return kvmppc_h_pr_bulk_remove(vcpu);
 	case H_PUT_TCE:
 		return kvmppc_h_pr_put_tce(vcpu);
+	case H_PUT_TCE_INDIRECT:
+		return kvmppc_h_pr_put_tce_indirect(vcpu);
+	case H_STUFF_TCE:
+		return kvmppc_h_pr_stuff_tce(vcpu);
 	case H_CEDE:
 		vcpu->arch.shared->msr |= MSR_EE;
 		kvm_vcpu_block(vcpu);

@@ -395,6 +395,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 		r = 1;
 		break;
 #endif
+	case KVM_CAP_SPAPR_MULTITCE:
+		r = 1;
+		break;
 	default:
 		r = 0;
 		break;

@@ -666,6 +666,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_IRQ_MPIC 90
 #define KVM_CAP_PPC_RTAS 91
 #define KVM_CAP_IRQ_XICS 92
+#define KVM_CAP_SPAPR_MULTITCE (0x110000 + 89)
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

@@ -376,6 +376,10 @@ static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
 }
 #endif /* !CONFIG_HUGETLB_PAGE */
 
+struct page *realmode_pfn_to_page(unsigned long pfn);
+int realmode_get_page(struct page *page);
+int realmode_put_page(struct page *page);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_PGTABLE_PPC64_H_ */

@@ -296,5 +296,80 @@ void vmemmap_free(unsigned long start, unsigned long end)
 {
 }
 
-#endif /* CONFIG_SPARSEMEM_VMEMMAP */
+/*
+ * We do not have access to the sparsemem vmemmap, so we fallback to
+ * walking the list of sparsemem blocks which we already maintain for
+ * the sake of crashdump. In the long run, we might want to maintain
+ * a tree if performance of that linear walk becomes a problem.
+ *
+ * Any of realmode_XXXX functions can fail due to:
+ * 1) As real sparsemem blocks do not lay in RAM continously (they
+ * are in virtual address space which is not available in the real mode),
+ * the requested page struct can be split between blocks so get_page/put_page
+ * may fail.
+ * 2) When huge pages are used, the get_page/put_page API will fail
+ * in real mode as the linked addresses in the page struct are virtual
+ * too.
+ * When 1) or 2) takes place, the API returns an error code to cause
+ * an exit to kernel virtual mode where the operation will be completed.
+ */
+struct page *realmode_pfn_to_page(unsigned long pfn)
+{
+	struct vmemmap_backing *vmem_back;
+	struct page *page;
+	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
+	unsigned long pg_va = (unsigned long) pfn_to_page(pfn);
+
+	for (vmem_back = vmemmap_list; vmem_back; vmem_back = vmem_back->list) {
+		if (pg_va < vmem_back->virt_addr)
+			continue;
 
+		/* Check that page struct is not split between real pages */
+		if ((pg_va + sizeof(struct page)) >
+				(vmem_back->virt_addr + page_size))
+			return NULL;
+
+		page = (struct page *) (vmem_back->phys + pg_va -
+				vmem_back->virt_addr);
+		return page;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
+
+#elif defined(CONFIG_FLATMEM)
+
+struct page *realmode_pfn_to_page(unsigned long pfn)
+{
+	struct page *page = pfn_to_page(pfn);
+	return page;
+}
+EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
+
+#endif /* CONFIG_SPARSEMEM_VMEMMAP/CONFIG_FLATMEM */
+
+#if defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_FLATMEM)
+int realmode_get_page(struct page *page)
+{
+	if (PageCompound(page))
+		return -EAGAIN;
+
+	get_page(page);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(realmode_get_page);
+
+int realmode_put_page(struct page *page)
+{
+	if (PageCompound(page))
+		return -EAGAIN;
+
+	if (!atomic_add_unless(&page->_count, -1, 1))
+		return -EAGAIN;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(realmode_put_page);
+#endif

@@ -2362,6 +2362,34 @@ calls by the guest for that service will be passed to userspace to be
 handled.
 
 
+4.79 KVM_CREATE_SPAPR_TCE_IOMMU
+
+Capability: KVM_CAP_SPAPR_TCE_IOMMU
+Architectures: powerpc
+Type: vm ioctl
+Parameters: struct kvm_create_spapr_tce_iommu (in)
+Returns: 0 on success, -1 on error
+
+This creates a link between IOMMU group and a hardware TCE (translation
+control entry) table. This link lets the host kernel know what IOMMU
+group (i.e. TCE table) to use for the LIOBN number passed with
+H_PUT_TCE, H_PUT_TCE_INDIRECT, H_STUFF_TCE hypercalls.
+
+/* for KVM_CAP_SPAPR_TCE_IOMMU */
+struct kvm_create_spapr_tce_iommu {
+	__u64 liobn;
+	__u32 iommu_id;
+	__u32 flags;
+};
+
+No flag is supported at the moment.
+
+When the guest issues TCE call on a liobn for which a TCE table has been
+registered, the kernel will handle it in real mode, updating the hardware
+TCE table. TCE table calls for other liobns will cause a vm exit and must
+be handled by userspace.
+
+
 5. The kvm_run structure
 ------------------------
 

@@ -180,6 +180,7 @@ struct kvmppc_spapr_tce_table {
 	struct kvm *kvm;
 	u64 liobn;
 	u32 window_size;
+	struct iommu_group *grp;    /* used for IOMMU groups */
 	struct page *pages[0];
 };
 

@@ -611,6 +612,8 @@ struct kvm_vcpu_arch {
 	u64 busy_preempt;
 
 	unsigned long *tce_tmp;    /* TCE cache for TCE_PUT_INDIRECT hall */
+	unsigned long tce_tmp_num; /* Number of handled TCEs in the cache */
+	unsigned long tce_reason;  /* The reason of switching to the virtmode */
 #endif
 };
 

@@ -133,6 +133,8 @@ extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
 
 extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce *args);
+extern long kvm_vm_ioctl_create_spapr_tce_iommu(struct kvm *kvm,
+				struct kvm_create_spapr_tce_iommu *args);
 extern struct kvmppc_spapr_tce_table *kvmppc_find_tce_table(
 		struct kvm_vcpu *vcpu, unsigned long liobn);
 extern long kvmppc_emulated_validate_tce(unsigned long tce);

@@ -319,6 +319,13 @@ struct kvm_create_spapr_tce {
 	__u32 window_size;
 };
 
+/* for KVM_CAP_SPAPR_TCE_IOMMU */
+struct kvm_create_spapr_tce_iommu {
+	__u64 liobn;
+	__u32 iommu_id;
+	__u32 flags;
+};
+
 /* for KVM_ALLOCATE_RMA */
 struct kvm_allocate_rma {
 	__u64 rma_size;

@@ -27,6 +27,8 @@
 #include <linux/hugetlb.h>
 #include <linux/list.h>
 #include <linux/anon_inodes.h>
+#include <linux/pci.h>
+#include <linux/iommu.h>
 
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>

@@ -56,8 +58,13 @@ static void release_spapr_tce_table(struct kvmppc_spapr_tce_table *stt)
 
 	mutex_lock(&kvm->lock);
 	list_del(&stt->list);
-	for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++)
-		__free_page(stt->pages[i]);
+#ifdef CONFIG_IOMMU_API
+	if (stt->grp) {
+		iommu_group_put(stt->grp);
+	} else
+#endif
+		for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++)
+			__free_page(stt->pages[i]);
 	kfree(stt);
 	mutex_unlock(&kvm->lock);
 

@@ -153,6 +160,62 @@ fail:
 	return ret;
 }
 
+#ifdef CONFIG_IOMMU_API
+static const struct file_operations kvm_spapr_tce_iommu_fops = {
+	.release	= kvm_spapr_tce_release,
+};
+
+long kvm_vm_ioctl_create_spapr_tce_iommu(struct kvm *kvm,
+		struct kvm_create_spapr_tce_iommu *args)
+{
+	struct kvmppc_spapr_tce_table *tt = NULL;
+	struct iommu_group *grp;
+	struct iommu_table *tbl;
+
+	/* Find an IOMMU table for the given ID */
+	grp = iommu_group_get_by_id(args->iommu_id);
+	if (!grp)
+		return -ENXIO;
+
+	tbl = iommu_group_get_iommudata(grp);
+	if (!tbl)
+		return -ENXIO;
+
+	/* Check this LIOBN hasn't been previously allocated */
+	list_for_each_entry(tt, &kvm->arch.spapr_tce_tables, list) {
+		if (tt->liobn == args->liobn)
+			return -EBUSY;
+	}
+
+	tt = kzalloc(sizeof(*tt), GFP_KERNEL);
+	if (!tt)
+		return -ENOMEM;
+
+	tt->liobn = args->liobn;
+	tt->kvm = kvm;
+	tt->grp = grp;
+
+	kvm_get_kvm(kvm);
+
+	mutex_lock(&kvm->lock);
+	list_add(&tt->list, &kvm->arch.spapr_tce_tables);
+
+	mutex_unlock(&kvm->lock);
+
+	pr_debug("LIOBN=%llX hooked to IOMMU %d, flags=%u\n",
+			args->liobn, args->iommu_id, args->flags);
+
+	return anon_inode_getfd("kvm-spapr-tce-iommu",
+			&kvm_spapr_tce_iommu_fops, tt, O_RDWR);
+}
+#else
+long kvm_vm_ioctl_create_spapr_tce_iommu(struct kvm *kvm,
+		struct kvm_create_spapr_tce_iommu *args)
+{
+	return -ENOSYS;
+}
+#endif /* CONFIG_IOMMU_API */
+
 /* Converts guest physical address into host virtual */
 static void __user *kvmppc_virtmode_gpa_to_hva(struct kvm_vcpu *vcpu,
 		unsigned long gpa)

@@ -180,6 +243,46 @@ long kvmppc_virtmode_h_put_tce(struct kvm_vcpu *vcpu,
 	if (!tt)
 		return H_TOO_HARD;
 
+#ifdef CONFIG_IOMMU_API
+	if (tt->grp) {
+		unsigned long entry = ioba >> IOMMU_PAGE_SHIFT;
+		struct iommu_table *tbl = iommu_group_get_iommudata(tt->grp);
+
+		/* Return error if the group is being destroyed */
+		if (!tbl)
+			return H_RESCINDED;
+
+		if (vcpu->arch.tce_reason == H_HARDWARE) {
+			iommu_clear_tces_and_put_pages(tbl, entry, 1);
+			return H_HARDWARE;
+
+		} else if (!(tce & (TCE_PCI_READ | TCE_PCI_WRITE))) {
+			if (iommu_tce_clear_param_check(tbl, ioba, 0, 1))
+				return H_PARAMETER;
+
+			ret = iommu_clear_tces_and_put_pages(tbl, entry, 1);
+		} else {
+			void *hva;
+
+			if (iommu_tce_put_param_check(tbl, ioba, tce))
+				return H_PARAMETER;
+
+			hva = kvmppc_virtmode_gpa_to_hva(vcpu, tce);
+			if (hva == ERROR_ADDR)
+				return H_HARDWARE;
+
+			ret = iommu_put_tce_user_mode(tbl,
+					ioba >> IOMMU_PAGE_SHIFT,
+					(unsigned long) hva);
+		}
+		iommu_flush_tce(tbl);
+
+		if (ret)
+			return H_HARDWARE;
+
+		return H_SUCCESS;
+	}
+#endif
 	/* Emulated IO */
 	if (ioba >= tt->window_size)
 		return H_PARAMETER;

@@ -220,6 +323,70 @@ long kvmppc_virtmode_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	if (tces == ERROR_ADDR)
 		return H_TOO_HARD;
 
+#ifdef CONFIG_IOMMU_API
+	if (tt->grp) {
+		struct iommu_table *tbl = iommu_group_get_iommudata(tt->grp);
+
+		/* Return error if the group is being destroyed */
+		if (!tbl)
+			return H_RESCINDED;
+
+		/* Something bad happened, do cleanup and exit */
+		if (vcpu->arch.tce_reason == H_HARDWARE) {
+			i = vcpu->arch.tce_tmp_num;
+			goto fail_clear_tce;
+		} else if (vcpu->arch.tce_reason != H_TOO_HARD) {
+			/*
+			 * We get here only in PR KVM mode, otherwise
+			 * the real mode handler would have checked TCEs
+			 * already and failed on guest TCE translation.
+			 */
+			for (i = 0; i < npages; ++i) {
+				if (get_user(vcpu->arch.tce_tmp[i], tces + i))
+					return H_HARDWARE;
+
+				if (iommu_tce_put_param_check(tbl, ioba +
+						(i << IOMMU_PAGE_SHIFT),
+						vcpu->arch.tce_tmp[i]))
+					return H_PARAMETER;
+			}
+		} /* else: The real mode handler checked TCEs already */
+
+		/* Translate TCEs */
+		for (i = vcpu->arch.tce_tmp_num; i < npages; ++i) {
+			void *hva = kvmppc_virtmode_gpa_to_hva(vcpu,
+					vcpu->arch.tce_tmp[i]);
+
+			if (hva == ERROR_ADDR)
+				goto fail_clear_tce;
+
+			vcpu->arch.tce_tmp[i] = (unsigned long) hva;
+		}
+
+		/* Do get_page and put TCEs for all pages */
+		for (i = 0; i < npages; ++i) {
+			if (iommu_put_tce_user_mode(tbl,
+					(ioba >> IOMMU_PAGE_SHIFT) + i,
+					vcpu->arch.tce_tmp[i])) {
+				i = npages;
+				goto fail_clear_tce;
+			}
+		}
+
+		iommu_flush_tce(tbl);
+
+		return H_SUCCESS;
+
+fail_clear_tce:
+		/* Cannot complete the translation, clean up and exit */
+		iommu_clear_tces_and_put_pages(tbl,
+				ioba >> IOMMU_PAGE_SHIFT, i);
+
+		iommu_flush_tce(tbl);
+
+		return H_HARDWARE;
+	}
+#endif
 	/* Emulated IO */
 	if ((ioba + (npages << IOMMU_PAGE_SHIFT)) > tt->window_size)
 		return H_PARAMETER;