[PATCH 6/8] KVM: PPC: Add support for multiple-TCE hcalls

Alexey Kardashevskiy aik at ozlabs.ru
Thu Jun 27 15:02:34 EST 2013


This adds real mode handlers for the H_PUT_TCE_INDIRECT and
H_STUFF_TCE hypercalls for QEMU emulated devices such as IBMVIO
devices or emulated PCI.  These calls allow adding multiple entries
(up to 512) into the TCE table in one call which saves time on
transition to/from real mode.

This adds a tce_tmp cache to kvm_vcpu_arch to save valid TCEs
(copied from user and verified) before writing the whole list into
the TCE table. This cache will be utilized more in the upcoming
VFIO/IOMMU support to continue TCE list processing in the virtual
mode in the case if the real mode handler failed for some reason.

This adds a guest physical to host real address converter
and calls the existing H_PUT_TCE handler. The converting function
is going to be fully utilized by upcoming VFIO supporting patches.

This also implements the KVM_CAP_PPC_MULTITCE capability,
so in order to support the functionality of this patch, QEMU
needs to query for this capability and set the "hcall-multi-tce"
hypertas property only if the capability is present, otherwise
there will be serious performance degradation.

Signed-off-by: Paul Mackerras <paulus at samba.org>
Signed-off-by: Alexey Kardashevskiy <aik at ozlabs.ru>

---
Changelog:
2013/06/27:
* fixed clear of BUSY bit in kvmppc_lookup_pte()
* H_PUT_TCE_INDIRECT does realmode_get_page() now
* KVM_CAP_SPAPR_MULTITCE now depends on CONFIG_PPC_BOOK3S_64
* updated doc

2013/06/05:
* fixed mistype about IBMVIO in the commit message
* updated doc and moved it to another section
* changed capability number

2013/05/21:
* added kvm_vcpu_arch::tce_tmp
* removed cleanup if put_indirect failed, instead we do not even start
writing to TCE table if we cannot get TCEs from the user and they are
invalid
* kvmppc_emulated_h_put_tce is split to kvmppc_emulated_put_tce
and kvmppc_emulated_validate_tce (for the previous item)
* fixed bug with failthrough for H_IPI
* removed all get_user() from real mode handlers
* kvmppc_lookup_pte() added (instead of making lookup_linux_pte public)
---
 Documentation/virtual/kvm/api.txt       |   25 +++
 arch/powerpc/include/asm/kvm_host.h     |    2 +
 arch/powerpc/include/asm/kvm_ppc.h      |   16 +-
 arch/powerpc/kvm/book3s_64_vio.c        |  123 ++++++++++++++
 arch/powerpc/kvm/book3s_64_vio_hv.c     |  270 +++++++++++++++++++++++++++----
 arch/powerpc/kvm/book3s_hv.c            |   41 ++++-
 arch/powerpc/kvm/book3s_hv_rmhandlers.S |    6 +
 arch/powerpc/kvm/book3s_pr_papr.c       |   37 ++++-
 arch/powerpc/kvm/powerpc.c              |    3 +
 9 files changed, 490 insertions(+), 33 deletions(-)

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 6365fef..762c703 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2362,6 +2362,31 @@ calls by the guest for that service will be passed to userspace to be
 handled.
 
 
+4.86 KVM_CAP_PPC_MULTITCE
+
+Capability: KVM_CAP_PPC_MULTITCE
+Architectures: ppc
+Type: vm
+
+This capability means the kernel is capable of handling hypercalls
+H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user
+space. This significanly accelerates DMA operations for PPC KVM guests.
+The user space should expect that its handlers for these hypercalls
+are not going to be called.
+
+In order to enable H_PUT_TCE_INDIRECT and H_STUFF_TCE use in the guest,
+the user space might have to advertise it for the guest. For example,
+IBM pSeries guest starts using them if "hcall-multi-tce" is present in
+the "ibm,hypertas-functions" device-tree property.
+
+Without this capability, only H_PUT_TCE is handled by the kernel and
+therefore the use of H_PUT_TCE_INDIRECT and H_STUFF_TCE is not recommended
+unless the capability is present as passing hypercalls to the userspace
+slows operations a lot.
+
+Unlike other capabilities of this section, this one is always enabled.
+
+
 5. The kvm_run structure
 ------------------------
 
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index af326cd..3bf407b 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -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 hcall */
 #endif
 };
 
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index a5287fe..e852921b 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -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);
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index b2d3f3b..45ee05a 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -14,6 +14,7 @@
  *
  * Copyright 2010 Paul Mackerras, IBM Corp. <paulus at au1.ibm.com>
  * Copyright 2011 David Gibson, IBM Corporation <dwg at au1.ibm.com>
+ * Copyright 2013 Alexey Kardashevskiy, IBM Corporation <aik at 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 +152,122 @@ fail:
 	}
 	return ret;
 }
+
+/* Converts guest physical address to host virtual address */
+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;
+
+	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 = H_SUCCESS;
+	unsigned long __user *tces;
+	struct page *pg;
+
+	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;
+
+	if ((ioba + (npages << IOMMU_PAGE_SHIFT)) > tt->window_size)
+		return H_PARAMETER;
+
+	tces = kvmppc_virtmode_gpa_to_hva(vcpu, tce_list);
+	if (tces == ERROR_ADDR)
+		return H_TOO_HARD;
+
+	if (get_user_pages_fast((unsigned long) tces & PAGE_MASK,
+			1, 0, &pg) != 1)
+		return H_TOO_HARD;
+
+	for (i = 0; i < npages; ++i) {
+		if (get_user(vcpu->arch.tce_tmp[i], tces + i)) {
+			ret = H_PARAMETER;
+			goto put_list_page_exit;
+		}
+
+		ret = kvmppc_emulated_validate_tce(vcpu->arch.tce_tmp[i]);
+		if (ret)
+			goto put_list_page_exit;
+	}
+
+	for (i = 0; i < npages; ++i)
+		kvmppc_emulated_put_tce(tt, ioba + (i << IOMMU_PAGE_SHIFT),
+				vcpu->arch.tce_tmp[i]);
+put_list_page_exit:
+	put_page(pg);
+
+	return ret;
+}
+
+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;
+
+	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;
+}
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 30c2f3b..108cc08 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -14,6 +14,7 @@
  *
  * Copyright 2010 Paul Mackerras, IBM Corp. <paulus at au1.ibm.com>
  * Copyright 2011 David Gibson, IBM Corporation <dwg at au1.ibm.com>
+ * Copyright 2013 Alexey Kardashevskiy, IBM Corporation <aik at au1.ibm.com>
  */
 
 #include <linux/types.h>
@@ -35,42 +36,253 @@
 #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);
+
+/*
+ * Validates TCE address.
+ * At the moment only flags are validated as other checks 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);
+
+/*
+ * Handles TCE requests for QEMU emulated devices.
+ * Puts guest TCE values to the table and expects QEMU to convert them
+ * later in a QEMU device implementation.
+ * Called in both real and virtual modes.
+ * 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
+/*
+ * Converts guest physical address to host physical address.
+ * Tries to increase page counter via realmode_get_page() and
+ * returns ERROR_ADDR if failed.
  */
+static unsigned long kvmppc_realmode_gpa_to_hpa(struct kvm_vcpu *vcpu,
+		unsigned long gpa)
+{
+	struct kvm_memory_slot *memslot;
+	pte_t *ptep, pte;
+	unsigned long hva, hpa = ERROR_ADDR;
+	unsigned long gfn = gpa >> PAGE_SHIFT;
+	unsigned shift = 0;
+	struct page *pg;
+
+	memslot = search_memslots(kvm_memslots(vcpu->kvm), gfn);
+	if (!memslot)
+		return ERROR_ADDR;
+
+	hva = __gfn_to_hva_memslot(memslot, gfn);
+
+	ptep = find_linux_pte_or_hugepte(vcpu->arch.pgdir, hva, &shift);
+	if (!ptep || !pte_present(*ptep))
+		return ERROR_ADDR;
+	pte = *ptep;
+
+	if (((gpa & TCE_PCI_WRITE) || pte_write(pte)) && !pte_dirty(pte))
+		return ERROR_ADDR;
+
+	if (!pte_young(pte))
+		return ERROR_ADDR;
+
+	if (!shift)
+		shift = PAGE_SHIFT;
+
+	/* Put huge pages handling to the virtual mode */
+	if (shift > PAGE_SHIFT)
+		return ERROR_ADDR;
+
+	pg = realmode_pfn_to_page(pte_pfn(pte));
+	if (!pg || realmode_get_page(pg))
+		return ERROR_ADDR;
+
+	/* pte_pfn(pte) returns address aligned to pg_size */
+	hpa = (pte_pfn(pte) << PAGE_SHIFT) +
+			(gpa & ((1 << shift) - 1));
+
+	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
+		hpa = ERROR_ADDR;
+		realmode_put_page(pg);
+	}
+
+	return hpa;
+}
+
+static long kvmppc_realmode_put_hpa(unsigned long hpa, bool dirty)
+{
+	struct page *pg;
+
+	pg = realmode_pfn_to_page(hpa >> PAGE_SHIFT);
+	if (!pg)
+		return H_TOO_HARD;
+
+	if (dirty)
+		SetPageDirty(pg);
+
+	if (PageCompound(pg))
+		return H_SUCCESS;
+
+	if (realmode_put_page(pg))
+		return H_TOO_HARD;
+
+	return H_SUCCESS;
+}
+
 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;
+
+	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 = H_SUCCESS;
+	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;
+
+	if ((ioba + (npages << IOMMU_PAGE_SHIFT)) > tt->window_size)
+		return H_PARAMETER;
+
+	tces = (unsigned long *) kvmppc_realmode_gpa_to_hpa(vcpu, tce_list);
+	if ((unsigned long)tces == ERROR_ADDR)
+		return H_TOO_HARD;
+
+	for (i = 0; i < npages; ++i) {
+		ret = kvmppc_emulated_validate_tce(tces[i]);
+		if (ret)
+			goto put_list_page_exit;
+	}
+
+	for (i = 0; i < npages; ++i)
+		kvmppc_emulated_put_tce(tt, ioba + (i << IOMMU_PAGE_SHIFT),
+				tces[i]);
+
+put_list_page_exit:
+	if (kvmppc_realmode_put_hpa((unsigned long)tces, false)) {
+		vcpu->arch.tce_reason = H_TOO_HARD;
+		ret = H_TOO_HARD;
 	}
 
-	/* Didn't find the liobn, punt it to userspace */
-	return H_TOO_HARD;
+	return ret;
+}
+
+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;
+
+	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 */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 550f592..b18b076 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -567,7 +567,31 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		if (kvmppc_xics_enabled(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;
 	}
@@ -958,6 +982,20 @@ 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:
@@ -980,6 +1018,7 @@ 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);
 }
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index b02f91e..d35554e 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -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:
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index da0e0bc..91d4b45 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -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);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 6316ee3..ccb578b 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -394,6 +394,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_PPC_GET_SMMU_INFO:
 		r = 1;
 		break;
+	case KVM_CAP_SPAPR_MULTITCE:
+		r = 1;
+		break;
 #endif
 	default:
 		r = 0;
-- 
1.7.10.4



More information about the Linuxppc-dev mailing list