Merge branch 'topic/ppc-kvm' into next

Merge our ppc-kvm topic branch to bring in the Ultravisor support
patches.

Documentation/powerpc/elfnote.rst

+==========================
+ELF Note PowerPC Namespace
+==========================
+
+The PowerPC namespace in an ELF Note of the kernel binary is used to store
+capabilities and information which can be used by a bootloader or userland.
+
+Types and Descriptors
+---------------------
+
+The types to be used with the "PowerPC" namesapce are defined in the
+include/uapi/asm/elfnote.h
+
+	1) PPC_ELFNOTE_CAPABILITIES
+
+Define the capabilities supported/required by the kernel. This type uses a
+bitmap as "descriptor" field. Each bit is described below:
+
+- Ultravisor-capable bit (PowerNV only).
+
+	#define PPCCAP_ULTRAVISOR_BIT (1 << 0)
+
+	Indicate that the powerpc kernel binary knows how to run in an
+	ultravisor-enabled system.
+
+	In an ultravisor-enabled system, some machine resources are now controlled
+	by the ultravisor. If the kernel is not ultravisor-capable, but it ends up
+	being run on a machine with ultravisor, the kernel will probably crash
+	trying to access ultravisor resources. For instance, it may crash in early
+	boot trying to set the partition table entry 0.
+
+	In an ultravisor-enabled system, a bootloader could warn the user or prevent
+   	the kernel from being run if the PowerPC ultravisor capability doesn't exist
+	or the Ultravisor-capable bit is not set.
+
+References
+----------
+
+arch/powerpc/include/asm/elfnote.h
+arch/powerpc/kernel/note.S
+
+

arch/powerpc/include/asm/asm-prototypes.h

@@ -15,6 +15,7 @@
 #include <asm/epapr_hcalls.h>
 #include <asm/dcr.h>
 #include <asm/mmu_context.h>
+#include <asm/ultravisor-api.h>
 
 #include <uapi/asm/ucontext.h>
 
@@ -34,6 +35,16 @@ extern struct static_key hcall_tracepoint_key;
 void __trace_hcall_entry(unsigned long opcode, unsigned long *args);
 void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf);
 
+/* Ultravisor */
+#ifdef CONFIG_PPC_POWERNV
+long ucall_norets(unsigned long opcode, ...);
+#else
+static inline long ucall_norets(unsigned long opcode, ...)
+{
+	return U_NOT_AVAILABLE;
+}
+#endif
+
 /* OPAL */
 int64_t __opal_call(int64_t a0, int64_t a1, int64_t a2, int64_t a3,
 		    int64_t a4, int64_t a5, int64_t a6, int64_t a7,

arch/powerpc/include/asm/elfnote.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * PowerPC ELF notes.
+ *
+ * Copyright 2019, IBM Corporation
+ */
+
+#ifndef __ASM_POWERPC_ELFNOTE_H__
+#define __ASM_POWERPC_ELFNOTE_H__
+
+/*
+ * These note types should live in a SHT_NOTE segment and have
+ * "PowerPC" in the name field.
+ */
+
+/*
+ * The capabilities supported/required by this kernel (bitmap).
+ *
+ * This type uses a bitmap as "desc" field. Each bit is described
+ * in arch/powerpc/kernel/note.S
+ */
+#define PPC_ELFNOTE_CAPABILITIES 1
+
+#endif /* __ASM_POWERPC_ELFNOTE_H__ */

arch/powerpc/include/asm/firmware.h

@@ -50,6 +50,7 @@
 #define FW_FEATURE_DRC_INFO	ASM_CONST(0x0000000800000000)
 #define FW_FEATURE_BLOCK_REMOVE ASM_CONST(0x0000001000000000)
 #define FW_FEATURE_PAPR_SCM 	ASM_CONST(0x0000002000000000)
+#define FW_FEATURE_ULTRAVISOR	ASM_CONST(0x0000004000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -68,9 +69,9 @@ enum {
 		FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN |
 		FW_FEATURE_HPT_RESIZE | FW_FEATURE_DRMEM_V2 |
 		FW_FEATURE_DRC_INFO | FW_FEATURE_BLOCK_REMOVE |
-		FW_FEATURE_PAPR_SCM,
+		FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR,
 	FW_FEATURE_PSERIES_ALWAYS = 0,
-	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL,
+	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_ULTRAVISOR,
 	FW_FEATURE_POWERNV_ALWAYS = 0,
 	FW_FEATURE_PS3_POSSIBLE = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,
 	FW_FEATURE_PS3_ALWAYS = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,

arch/powerpc/include/asm/iommu.h

@@ -48,15 +48,16 @@ struct iommu_table_ops {
 	 * returns old TCE and DMA direction mask.
 	 * @tce is a physical address.
 	 */
-	int (*exchange)(struct iommu_table *tbl,
+	int (*xchg_no_kill)(struct iommu_table *tbl,
 			long index,
 			unsigned long *hpa,
-			enum dma_data_direction *direction);
-	/* Real mode */
-	int (*exchange_rm)(struct iommu_table *tbl,
-			long index,
-			unsigned long *hpa,
-			enum dma_data_direction *direction);
+			enum dma_data_direction *direction,
+			bool realmode);
+
+	void (*tce_kill)(struct iommu_table *tbl,
+			unsigned long index,
+			unsigned long pages,
+			bool realmode);
 
 	__be64 *(*useraddrptr)(struct iommu_table *tbl, long index, bool alloc);
 #endif
@@ -209,6 +210,12 @@ extern void iommu_del_device(struct device *dev);
 extern long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl,
 		unsigned long entry, unsigned long *hpa,
 		enum dma_data_direction *direction);
+extern long iommu_tce_xchg_no_kill(struct mm_struct *mm,
+		struct iommu_table *tbl,
+		unsigned long entry, unsigned long *hpa,
+		enum dma_data_direction *direction);
+extern void iommu_tce_kill(struct iommu_table *tbl,
+		unsigned long entry, unsigned long pages);
 #else
 static inline void iommu_register_group(struct iommu_table_group *table_group,
 					int pci_domain_number,

arch/powerpc/include/asm/kvm_host.h

@@ -283,6 +283,7 @@ struct kvm_arch {
 	cpumask_t cpu_in_guest;
 	u8 radix;
 	u8 fwnmi_enabled;
+	u8 secure_guest;
 	bool threads_indep;
 	bool nested_enable;
 	pgd_t *pgtable;

arch/powerpc/include/asm/ultravisor-api.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Ultravisor API.
+ *
+ * Copyright 2019, IBM Corporation.
+ *
+ */
+#ifndef _ASM_POWERPC_ULTRAVISOR_API_H
+#define _ASM_POWERPC_ULTRAVISOR_API_H
+
+#include <asm/hvcall.h>
+
+/* Return codes */
+#define U_BUSY			H_BUSY
+#define U_FUNCTION		H_FUNCTION
+#define U_NOT_AVAILABLE		H_NOT_AVAILABLE
+#define U_P2			H_P2
+#define U_P3			H_P3
+#define U_P4			H_P4
+#define U_P5			H_P5
+#define U_PARAMETER		H_PARAMETER
+#define U_PERMISSION		H_PERMISSION
+#define U_SUCCESS		H_SUCCESS
+
+/* opcodes */
+#define UV_WRITE_PATE			0xF104
+#define UV_RETURN			0xF11C
+
+#endif /* _ASM_POWERPC_ULTRAVISOR_API_H */

arch/powerpc/include/asm/ultravisor.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Ultravisor definitions
+ *
+ * Copyright 2019, IBM Corporation.
+ *
+ */
+#ifndef _ASM_POWERPC_ULTRAVISOR_H
+#define _ASM_POWERPC_ULTRAVISOR_H
+
+#include <asm/asm-prototypes.h>
+#include <asm/ultravisor-api.h>
+#include <asm/firmware.h>
+
+int early_init_dt_scan_ultravisor(unsigned long node, const char *uname,
+				  int depth, void *data);
+
+/*
+ * In ultravisor enabled systems, PTCR becomes ultravisor privileged only for
+ * writing and an attempt to write to it will cause a Hypervisor Emulation
+ * Assistance interrupt.
+ */
+static inline void set_ptcr_when_no_uv(u64 val)
+{
+	if (!firmware_has_feature(FW_FEATURE_ULTRAVISOR))
+		mtspr(SPRN_PTCR, val);
+}
+
+static inline int uv_register_pate(u64 lpid, u64 dw0, u64 dw1)
+{
+	return ucall_norets(UV_WRITE_PATE, lpid, dw0, dw1);
+}
+
+#endif	/* _ASM_POWERPC_ULTRAVISOR_H */

arch/powerpc/kernel/Makefile

@@ -53,7 +53,7 @@ obj-y				:= cputable.o ptrace.o syscalls.o \
 				   dma-common.o
 obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   signal_64.o ptrace32.o \
-				   paca.o nvram_64.o firmware.o
+				   paca.o nvram_64.o firmware.o note.o
 obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_PPC_WATCHDOG)	+= watchdog.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
@@ -156,6 +156,7 @@ endif
 
 obj-$(CONFIG_EPAPR_PARAVIRT)	+= epapr_paravirt.o epapr_hcalls.o
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvm_emul.o
+obj-$(CONFIG_PPC_POWERNV)	+= ucall.o
 
 # Disable GCOV, KCOV & sanitizers in odd or sensitive code
 GCOV_PROFILE_prom_init.o := n

arch/powerpc/kernel/asm-offsets.c

@@ -506,6 +506,7 @@ int main(void)
 	OFFSET(KVM_VRMA_SLB_V, kvm, arch.vrma_slb_v);
 	OFFSET(KVM_RADIX, kvm, arch.radix);
 	OFFSET(KVM_FWNMI, kvm, arch.fwnmi_enabled);
+	OFFSET(KVM_SECURE_GUEST, kvm, arch.secure_guest);
 	OFFSET(VCPU_DSISR, kvm_vcpu, arch.shregs.dsisr);
 	OFFSET(VCPU_DAR, kvm_vcpu, arch.shregs.dar);
 	OFFSET(VCPU_VPA, kvm_vcpu, arch.vpa.pinned_addr);

arch/powerpc/kernel/iommu.c

@@ -1013,29 +1013,32 @@ int iommu_tce_check_gpa(unsigned long page_shift, unsigned long gpa)
 }
 EXPORT_SYMBOL_GPL(iommu_tce_check_gpa);
 
-long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl,
+extern long iommu_tce_xchg_no_kill(struct mm_struct *mm,
+		struct iommu_table *tbl,
 		unsigned long entry, unsigned long *hpa,
 		enum dma_data_direction *direction)
 {
 	long ret;
 	unsigned long size = 0;
 
-	ret = tbl->it_ops->exchange(tbl, entry, hpa, direction);
-
+	ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction, false);
 	if (!ret && ((*direction == DMA_FROM_DEVICE) ||
 			(*direction == DMA_BIDIRECTIONAL)) &&
 			!mm_iommu_is_devmem(mm, *hpa, tbl->it_page_shift,
 					&size))
 		SetPageDirty(pfn_to_page(*hpa >> PAGE_SHIFT));
 
-	/* if (unlikely(ret))
-		pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n",
-			__func__, hwaddr, entry << tbl->it_page_shift,
-				hwaddr, ret); */
-
 	return ret;
 }
-EXPORT_SYMBOL_GPL(iommu_tce_xchg);
+EXPORT_SYMBOL_GPL(iommu_tce_xchg_no_kill);
+
+void iommu_tce_kill(struct iommu_table *tbl,
+		unsigned long entry, unsigned long pages)
+{
+	if (tbl->it_ops->tce_kill)
+		tbl->it_ops->tce_kill(tbl, entry, pages, false);
+}
+EXPORT_SYMBOL_GPL(iommu_tce_kill);
 
 int iommu_take_ownership(struct iommu_table *tbl)
 {
@@ -1049,7 +1052,7 @@ int iommu_take_ownership(struct iommu_table *tbl)
 	 * requires exchange() callback defined so if it is not
 	 * implemented, we disallow taking ownership over the table.
 	 */
-	if (!tbl->it_ops->exchange)
+	if (!tbl->it_ops->xchg_no_kill)
 		return -EINVAL;
 
 	spin_lock_irqsave(&tbl->large_pool.lock, flags);

arch/powerpc/kernel/note.S

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * PowerPC ELF notes.
+ *
+ * Copyright 2019, IBM Corporation
+ */
+
+#include <linux/elfnote.h>
+#include <asm/elfnote.h>
+
+/*
+ * Ultravisor-capable bit (PowerNV only).
+ *
+ * Bit 0 indicates that the powerpc kernel binary knows how to run in an
+ * ultravisor-enabled system.
+ *
+ * In an ultravisor-enabled system, some machine resources are now controlled
+ * by the ultravisor. If the kernel is not ultravisor-capable, but it ends up
+ * being run on a machine with ultravisor, the kernel will probably crash
+ * trying to access ultravisor resources. For instance, it may crash in early
+ * boot trying to set the partition table entry 0.
+ *
+ * In an ultravisor-enabled system, a bootloader could warn the user or prevent
+ * the kernel from being run if the PowerPC ultravisor capability doesn't exist
+ * or the Ultravisor-capable bit is not set.
+ */
+#ifdef CONFIG_PPC_POWERNV
+#define PPCCAP_ULTRAVISOR_BIT		(1 << 0)
+#else
+#define PPCCAP_ULTRAVISOR_BIT		0
+#endif
+
+/*
+ * Add the PowerPC Capabilities in the binary ELF note. It is a bitmap that
+ * can be used to advertise kernel capabilities to userland.
+ */
+#define PPC_CAPABILITIES_BITMAP (PPCCAP_ULTRAVISOR_BIT)
+
+ELFNOTE(PowerPC, PPC_ELFNOTE_CAPABILITIES,
+	.long PPC_CAPABILITIES_BITMAP)

arch/powerpc/kernel/prom.c

@@ -55,6 +55,7 @@
 #include <asm/firmware.h>
 #include <asm/dt_cpu_ftrs.h>
 #include <asm/drmem.h>
+#include <asm/ultravisor.h>
 
 #include <mm/mmu_decl.h>
 
@@ -702,6 +703,9 @@ void __init early_init_devtree(void *params)
 #ifdef CONFIG_PPC_POWERNV
 	/* Some machines might need OPAL info for debugging, grab it now. */
 	of_scan_flat_dt(early_init_dt_scan_opal, NULL);
+
+	/* Scan tree for ultravisor feature */
+	of_scan_flat_dt(early_init_dt_scan_ultravisor, NULL);
 #endif
 
 #ifdef CONFIG_FA_DUMP

arch/powerpc/kernel/ucall.S

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Generic code to perform an ultravisor call.
+ *
+ * Copyright 2019, IBM Corporation.
+ *
+ */
+#include <asm/ppc_asm.h>
+#include <asm/export.h>
+
+_GLOBAL(ucall_norets)
+EXPORT_SYMBOL_GPL(ucall_norets)
+	sc	2	/* Invoke the ultravisor */
+	blr		/* Return r3 = status */

arch/powerpc/kvm/book3s_64_vio.c

@@ -416,7 +416,7 @@ static void kvmppc_clear_tce(struct mm_struct *mm, struct iommu_table *tbl,
 	unsigned long hpa = 0;
 	enum dma_data_direction dir = DMA_NONE;
 
-	iommu_tce_xchg(mm, tbl, entry, &hpa, &dir);
+	iommu_tce_xchg_no_kill(mm, tbl, entry, &hpa, &dir);
 }
 
 static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm,
@@ -447,7 +447,8 @@ static long kvmppc_tce_iommu_do_unmap(struct kvm *kvm,
 	unsigned long hpa = 0;
 	long ret;
 
-	if (WARN_ON_ONCE(iommu_tce_xchg(kvm->mm, tbl, entry, &hpa, &dir)))
+	if (WARN_ON_ONCE(iommu_tce_xchg_no_kill(kvm->mm, tbl, entry, &hpa,
+					&dir)))
 		return H_TOO_HARD;
 
 	if (dir == DMA_NONE)
@@ -455,7 +456,7 @@ static long kvmppc_tce_iommu_do_unmap(struct kvm *kvm,
 
 	ret = kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
 	if (ret != H_SUCCESS)
-		iommu_tce_xchg(kvm->mm, tbl, entry, &hpa, &dir);
+		iommu_tce_xchg_no_kill(kvm->mm, tbl, entry, &hpa, &dir);
 
 	return ret;
 }
@@ -501,7 +502,7 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 	if (mm_iommu_mapped_inc(mem))
 		return H_TOO_HARD;
 
-	ret = iommu_tce_xchg(kvm->mm, tbl, entry, &hpa, &dir);
+	ret = iommu_tce_xchg_no_kill(kvm->mm, tbl, entry, &hpa, &dir);
 	if (WARN_ON_ONCE(ret)) {
 		mm_iommu_mapped_dec(mem);
 		return H_TOO_HARD;
@@ -579,6 +580,8 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 			ret = kvmppc_tce_iommu_map(vcpu->kvm, stt, stit->tbl,
 					entry, ua, dir);
 
+		iommu_tce_kill(stit->tbl, entry, 1);
+
 		if (ret != H_SUCCESS) {
 			kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry);
 			goto unlock_exit;
@@ -656,12 +659,14 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		 */
 		if (get_user(tce, tces + i)) {
 			ret = H_TOO_HARD;
-			goto unlock_exit;
+			goto invalidate_exit;
 		}
 		tce = be64_to_cpu(tce);
 
-		if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua))
-			return H_PARAMETER;
+		if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua)) {
+			ret = H_PARAMETER;
+			goto invalidate_exit;
+		}
 
 		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
 			ret = kvmppc_tce_iommu_map(vcpu->kvm, stt,
@@ -671,13 +676,17 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 			if (ret != H_SUCCESS) {
 				kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl,
 						entry);
-				goto unlock_exit;
+				goto invalidate_exit;
 			}
 		}
 
 		kvmppc_tce_put(stt, entry + i, tce);
 	}
 
+invalidate_exit:
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next)
+		iommu_tce_kill(stit->tbl, entry, npages);
+
 unlock_exit:
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 
@@ -716,7 +725,7 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
 				continue;
 
 			if (ret == H_TOO_HARD)
-				return ret;
+				goto invalidate_exit;
 
 			WARN_ON_ONCE(1);
 			kvmppc_clear_tce(vcpu->kvm->mm, stit->tbl, entry);
@@ -726,6 +735,10 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
 	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
 		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
 
-	return H_SUCCESS;
+invalidate_exit:
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next)
+		iommu_tce_kill(stit->tbl, ioba >> stt->page_shift, npages);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(kvmppc_h_stuff_tce);

arch/powerpc/kvm/book3s_64_vio_hv.c

@@ -218,13 +218,14 @@ static long kvmppc_rm_ioba_validate(struct kvmppc_spapr_tce_table *stt,
 	return H_SUCCESS;
 }
 
-static long iommu_tce_xchg_rm(struct mm_struct *mm, struct iommu_table *tbl,
+static long iommu_tce_xchg_no_kill_rm(struct mm_struct *mm,
+		struct iommu_table *tbl,
 		unsigned long entry, unsigned long *hpa,
 		enum dma_data_direction *direction)
 {
 	long ret;
 
-	ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction);
+	ret = tbl->it_ops->xchg_no_kill(tbl, entry, hpa, direction, true);
 
 	if (!ret && ((*direction == DMA_FROM_DEVICE) ||
 				(*direction == DMA_BIDIRECTIONAL))) {
@@ -240,13 +241,20 @@ static long iommu_tce_xchg_rm(struct mm_struct *mm, struct iommu_table *tbl,
 	return ret;
 }
 
+extern void iommu_tce_kill_rm(struct iommu_table *tbl,
+		unsigned long entry, unsigned long pages)
+{
+	if (tbl->it_ops->tce_kill)
+		tbl->it_ops->tce_kill(tbl, entry, pages, true);
+}
+
 static void kvmppc_rm_clear_tce(struct kvm *kvm, struct iommu_table *tbl,
 		unsigned long entry)
 {
 	unsigned long hpa = 0;
 	enum dma_data_direction dir = DMA_NONE;
 
-	iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir);
+	iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir);
 }
 
 static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm,
@@ -278,7 +286,7 @@ static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm,
 	unsigned long hpa = 0;
 	long ret;
 
-	if (iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir))
+	if (iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir))
 		/*
 		 * real mode xchg can fail if struct page crosses
 		 * a page boundary
@@ -290,7 +298,7 @@ static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm,
 
 	ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
 	if (ret)
-		iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir);
+		iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir);
 
 	return ret;
 }
@@ -336,7 +344,7 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 	if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem)))
 		return H_TOO_HARD;
 
-	ret = iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir);
+	ret = iommu_tce_xchg_no_kill_rm(kvm->mm, tbl, entry, &hpa, &dir);
 	if (ret) {
 		mm_iommu_mapped_dec(mem);
 		/*
@@ -417,6 +425,8 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt,
 					stit->tbl, entry, ua, dir);
 
+		iommu_tce_kill_rm(stit->tbl, entry, 1);
+
 		if (ret != H_SUCCESS) {
 			kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry);
 			return ret;
@@ -556,8 +566,10 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		unsigned long tce = be64_to_cpu(((u64 *)tces)[i]);
 
 		ua = 0;
-		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
-			return H_PARAMETER;
+		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) {
+			ret = H_PARAMETER;
+			goto invalidate_exit;
+		}
 
 		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
 			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt,
@@ -567,13 +579,17 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 			if (ret != H_SUCCESS) {
 				kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl,
 						entry);
-				goto unlock_exit;
+				goto invalidate_exit;
 			}
 		}
 
 		kvmppc_rm_tce_put(stt, entry + i, tce);
 	}
 
+invalidate_exit:
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next)
+		iommu_tce_kill_rm(stit->tbl, entry, npages);
+
 unlock_exit:
 	if (rmap)
 		unlock_rmap(rmap);
@@ -616,7 +632,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 				continue;
 
 			if (ret == H_TOO_HARD)
-				return ret;
+				goto invalidate_exit;
 
 			WARN_ON_ONCE_RM(1);
 			kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry);
@@ -626,7 +642,11 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
 		kvmppc_rm_tce_put(stt, ioba >> stt->page_shift, tce_value);
 
-	return H_SUCCESS;
+invalidate_exit:
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next)
+		iommu_tce_kill_rm(stit->tbl, ioba >> stt->page_shift, npages);
+
+	return ret;
 }
 
 /* This can be called in either virtual mode or real mode */

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -29,6 +29,7 @@
 #include <asm/asm-compat.h>
 #include <asm/feature-fixups.h>
 #include <asm/cpuidle.h>
+#include <asm/ultravisor-api.h>
 
 /* Sign-extend HDEC if not on POWER9 */
 #define EXTEND_HDEC(reg)			\
@@ -1085,16 +1086,10 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
 	ld	r5, VCPU_LR(r4)
-	ld	r6, VCPU_CR(r4)
 	mtlr	r5
-	mtcr	r6
 
 	ld	r1, VCPU_GPR(R1)(r4)
-	ld	r2, VCPU_GPR(R2)(r4)
-	ld	r3, VCPU_GPR(R3)(r4)
 	ld	r5, VCPU_GPR(R5)(r4)
-	ld	r6, VCPU_GPR(R6)(r4)
-	ld	r7, VCPU_GPR(R7)(r4)
 	ld	r8, VCPU_GPR(R8)(r4)
 	ld	r9, VCPU_GPR(R9)(r4)
 	ld	r10, VCPU_GPR(R10)(r4)
@@ -1112,10 +1107,42 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_HDSISR, r0
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
+	ld	r6, VCPU_KVM(r4)
+	lbz	r7, KVM_SECURE_GUEST(r6)
+	cmpdi	r7, 0
+	ld	r6, VCPU_GPR(R6)(r4)
+	ld	r7, VCPU_GPR(R7)(r4)
+	bne	ret_to_ultra
+
+	lwz	r0, VCPU_CR(r4)
+	mtcr	r0
+
 	ld	r0, VCPU_GPR(R0)(r4)
+	ld	r2, VCPU_GPR(R2)(r4)
+	ld	r3, VCPU_GPR(R3)(r4)
 	ld	r4, VCPU_GPR(R4)(r4)
 	HRFI_TO_GUEST
 	b	.
+/*
+ * Use UV_RETURN ultracall to return control back to the Ultravisor after
+ * processing an hypercall or interrupt that was forwarded (a.k.a. reflected)
+ * to the Hypervisor.
+ *
+ * All registers have already been loaded, except:
+ *   R0 = hcall result
+ *   R2 = SRR1, so UV can detect a synthesized interrupt (if any)
+ *   R3 = UV_RETURN
+ */
+ret_to_ultra:
+	lwz	r0, VCPU_CR(r4)
+	mtcr	r0
+
+	ld	r0, VCPU_GPR(R3)(r4)
+	mfspr	r2, SPRN_SRR1
+	li	r3, 0
+	ori	r3, r3, UV_RETURN
+	ld	r4, VCPU_GPR(R4)(r4)
+	sc	2
 
 /*
  * Enter the guest on a P9 or later system where we have exactly

arch/powerpc/mm/book3s64/hash_utils.c

@@ -62,6 +62,7 @@
 #include <asm/ps3.h>
 #include <asm/pte-walk.h>
 #include <asm/asm-prototypes.h>
+#include <asm/ultravisor.h>
 
 #include <mm/mmu_decl.h>
 
@@ -1076,8 +1077,8 @@ void hash__early_init_mmu_secondary(void)
 		if (!cpu_has_feature(CPU_FTR_ARCH_300))
 			mtspr(SPRN_SDR1, _SDR1);
 		else
-			mtspr(SPRN_PTCR,
-			      __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
+			set_ptcr_when_no_uv(__pa(partition_tb) |
+					    (PATB_SIZE_SHIFT - 12));
 	}
 	/* Initialize SLB */
 	slb_initialize();

arch/powerpc/mm/book3s64/pgtable.c

@@ -12,6 +12,8 @@
 #include <asm/tlb.h>
 #include <asm/trace.h>
 #include <asm/powernv.h>
+#include <asm/firmware.h>
+#include <asm/ultravisor.h>
 
 #include <mm/mmu_decl.h>
 #include <trace/events/thp.h>
@@ -205,25 +207,14 @@ void __init mmu_partition_table_init(void)
 	 * 64 K size.
 	 */
 	ptcr = __pa(partition_tb) | (PATB_SIZE_SHIFT - 12);
-	mtspr(SPRN_PTCR, ptcr);
+	set_ptcr_when_no_uv(ptcr);
 	powernv_set_nmmu_ptcr(ptcr);
 }
 
-void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
-				   unsigned long dw1)
+static void flush_partition(unsigned int lpid, bool radix)
 {
-	unsigned long old = be64_to_cpu(partition_tb[lpid].patb0);
-
-	partition_tb[lpid].patb0 = cpu_to_be64(dw0);
-	partition_tb[lpid].patb1 = cpu_to_be64(dw1);
-
-	/*
-	 * Global flush of TLBs and partition table caches for this lpid.
-	 * The type of flush (hash or radix) depends on what the previous
-	 * use of this partition ID was, not the new use.
-	 */
 	asm volatile("ptesync" : : : "memory");
-	if (old & PATB_HR) {
+	if (radix) {
 		asm volatile(PPC_TLBIE_5(%0,%1,2,0,1) : :
 			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
 		asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : :
@@ -237,6 +228,39 @@ void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
 	/* do we need fixup here ?*/
 	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 }
+
+void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
+				  unsigned long dw1)
+{
+	unsigned long old = be64_to_cpu(partition_tb[lpid].patb0);
+
+	/*
+	 * When ultravisor is enabled, the partition table is stored in secure
+	 * memory and can only be accessed doing an ultravisor call. However, we
+	 * maintain a copy of the partition table in normal memory to allow Nest
+	 * MMU translations to occur (for normal VMs).
+	 *
+	 * Therefore, here we always update partition_tb, regardless of whether
+	 * we are running under an ultravisor or not.
+	 */
+	partition_tb[lpid].patb0 = cpu_to_be64(dw0);
+	partition_tb[lpid].patb1 = cpu_to_be64(dw1);
+
+	/*
+	 * If ultravisor is enabled, we do an ultravisor call to register the
+	 * partition table entry (PATE), which also do a global flush of TLBs
+	 * and partition table caches for the lpid. Otherwise, just do the
+	 * flush. The type of flush (hash or radix) depends on what the previous
+	 * use of the partition ID was, not the new use.
+	 */
+	if (firmware_has_feature(FW_FEATURE_ULTRAVISOR)) {
+		uv_register_pate(lpid, dw0, dw1);
+		pr_info("PATE registered by ultravisor: dw0 = 0x%lx, dw1 = 0x%lx\n",
+			dw0, dw1);
+	} else {
+		flush_partition(lpid, (old & PATB_HR));
+	}
+}
 EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry);
 
 static pmd_t *get_pmd_from_cache(struct mm_struct *mm)

arch/powerpc/mm/book3s64/radix_pgtable.c

@@ -27,6 +27,7 @@
 #include <asm/sections.h>
 #include <asm/trace.h>
 #include <asm/uaccess.h>
+#include <asm/ultravisor.h>
 
 #include <trace/events/thp.h>
 
@@ -650,8 +651,9 @@ void radix__early_init_mmu_secondary(void)
 		lpcr = mfspr(SPRN_LPCR);
 		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
 
-		mtspr(SPRN_PTCR,
-		      __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
+		set_ptcr_when_no_uv(__pa(partition_tb) |
+				    (PATB_SIZE_SHIFT - 12));
+
 		radix_init_amor();
 	}
 
@@ -667,7 +669,7 @@ void radix__mmu_cleanup_all(void)
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
 		lpcr = mfspr(SPRN_LPCR);
 		mtspr(SPRN_LPCR, lpcr & ~LPCR_UPRT);
-		mtspr(SPRN_PTCR, 0);
+		set_ptcr_when_no_uv(0);
 		powernv_set_nmmu_ptcr(0);
 		radix__flush_tlb_all();
 	}

arch/powerpc/platforms/powernv/Makefile

@@ -4,6 +4,7 @@ obj-y			+= idle.o opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
 obj-y			+= rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o
 obj-y			+= opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o
 obj-y			+= opal-kmsg.o opal-powercap.o opal-psr.o opal-sensor-groups.o
+obj-y			+= ultravisor.o
 
 obj-$(CONFIG_SMP)	+= smp.o subcore.o subcore-asm.o
 obj-$(CONFIG_PCI)	+= pci.o pci-ioda.o npu-dma.o pci-ioda-tce.o

arch/powerpc/platforms/powernv/idle.c

@@ -675,6 +675,7 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
 		sprs.ptcr	= mfspr(SPRN_PTCR);
 		sprs.rpr	= mfspr(SPRN_RPR);
 		sprs.tscr	= mfspr(SPRN_TSCR);
+		if (!firmware_has_feature(FW_FEATURE_ULTRAVISOR))
 			sprs.ldbar = mfspr(SPRN_LDBAR);
 
 		sprs_saved = true;
@@ -789,6 +790,7 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
 	mtspr(SPRN_MMCR0,	sprs.mmcr0);
 	mtspr(SPRN_MMCR1,	sprs.mmcr1);
 	mtspr(SPRN_MMCR2,	sprs.mmcr2);
+	if (!firmware_has_feature(FW_FEATURE_ULTRAVISOR))
 		mtspr(SPRN_LDBAR, sprs.ldbar);
 
 	mtspr(SPRN_SPRG3,	local_paca->sprg_vdso);

arch/powerpc/platforms/powernv/opal-msglog.c

@@ -29,23 +29,23 @@ struct memcons {
 
 static struct memcons *opal_memcons = NULL;
 
-ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count)
+ssize_t memcons_copy(struct memcons *mc, char *to, loff_t pos, size_t count)
 {
 	const char *conbuf;
 	ssize_t ret;
 	size_t first_read = 0;
 	uint32_t out_pos, avail;
 
-	if (!opal_memcons)
+	if (!mc)
 		return -ENODEV;
 
-	out_pos = be32_to_cpu(READ_ONCE(opal_memcons->out_pos));
+	out_pos = be32_to_cpu(READ_ONCE(mc->out_pos));
 
 	/* Now we've read out_pos, put a barrier in before reading the new
 	 * data it points to in conbuf. */
 	smp_rmb();
 
-	conbuf = phys_to_virt(be64_to_cpu(opal_memcons->obuf_phys));
+	conbuf = phys_to_virt(be64_to_cpu(mc->obuf_phys));
 
 	/* When the buffer has wrapped, read from the out_pos marker to the end
 	 * of the buffer, and then read the remaining data as in the un-wrapped
@@ -53,7 +53,7 @@ ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count)
 	if (out_pos & MEMCONS_OUT_POS_WRAP) {
 
 		out_pos &= MEMCONS_OUT_POS_MASK;
-		avail = be32_to_cpu(opal_memcons->obuf_size) - out_pos;
+		avail = be32_to_cpu(mc->obuf_size) - out_pos;
 
 		ret = memory_read_from_buffer(to, count, &pos,
 				conbuf + out_pos, avail);
@@ -71,7 +71,7 @@ ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count)
 	}
 
 	/* Sanity check. The firmware should not do this to us. */
-	if (out_pos > be32_to_cpu(opal_memcons->obuf_size)) {
+	if (out_pos > be32_to_cpu(mc->obuf_size)) {
 		pr_err("OPAL: memory console corruption. Aborting read.\n");
 		return -EINVAL;
 	}
@@ -86,6 +86,11 @@ ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count)
 	return ret;
 }
 
+ssize_t opal_msglog_copy(char *to, loff_t pos, size_t count)
+{
+	return memcons_copy(opal_memcons, to, pos, count);
+}
+
 static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj,
 				struct bin_attribute *bin_attr, char *to,
 				loff_t pos, size_t count)
@@ -98,32 +103,48 @@ static struct bin_attribute opal_msglog_attr = {
 	.read = opal_msglog_read
 };
 
-void __init opal_msglog_init(void)
+struct memcons *memcons_init(struct device_node *node, const char *mc_prop_name)
 {
 	u64 mcaddr;
 	struct memcons *mc;
 
-	if (of_property_read_u64(opal_node, "ibm,opal-memcons", &mcaddr)) {
-		pr_warn("OPAL: Property ibm,opal-memcons not found, no message log\n");
-		return;
+	if (of_property_read_u64(node, mc_prop_name, &mcaddr)) {
+		pr_warn("%s property not found, no message log\n",
+			mc_prop_name);
+		goto out_err;
 	}
 
 	mc = phys_to_virt(mcaddr);
 	if (!mc) {
-		pr_warn("OPAL: memory console address is invalid\n");
-		return;
+		pr_warn("memory console address is invalid\n");
+		goto out_err;
 	}
 
 	if (be64_to_cpu(mc->magic) != MEMCONS_MAGIC) {
-		pr_warn("OPAL: memory console version is invalid\n");
-		return;
+		pr_warn("memory console version is invalid\n");
+		goto out_err;
 	}
 
-	/* Report maximum size */
-	opal_msglog_attr.size =  be32_to_cpu(mc->ibuf_size) +
-		be32_to_cpu(mc->obuf_size);
+	return mc;
+
+out_err:
+	return NULL;
+}
+
+u32 memcons_get_size(struct memcons *mc)
+{
+	return be32_to_cpu(mc->ibuf_size) + be32_to_cpu(mc->obuf_size);
+}
+
+void __init opal_msglog_init(void)
+{
+	opal_memcons = memcons_init(opal_node, "ibm,opal-memcons");
+	if (!opal_memcons) {
+		pr_warn("OPAL: memcons failed to load from ibm,opal-memcons\n");
+		return;
+	}
 
-	opal_memcons = mc;
+	opal_msglog_attr.size = memcons_get_size(opal_memcons);
 }
 
 void __init opal_msglog_sysfs_init(void)

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -1939,26 +1939,12 @@ static int pnv_ioda1_tce_build(struct iommu_table *tbl, long index,
 }
 
 #ifdef CONFIG_IOMMU_API
-static int pnv_ioda1_tce_xchg(struct iommu_table *tbl, long index,
-		unsigned long *hpa, enum dma_data_direction *direction)
+/* Common for IODA1 and IODA2 */
+static int pnv_ioda_tce_xchg_no_kill(struct iommu_table *tbl, long index,
+		unsigned long *hpa, enum dma_data_direction *direction,
+		bool realmode)
 {
-	long ret = pnv_tce_xchg(tbl, index, hpa, direction, true);
-
-	if (!ret)
-		pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, false);
-
-	return ret;
-}
-
-static int pnv_ioda1_tce_xchg_rm(struct iommu_table *tbl, long index,
-		unsigned long *hpa, enum dma_data_direction *direction)
-{
-	long ret = pnv_tce_xchg(tbl, index, hpa, direction, false);
-
-	if (!ret)
-		pnv_pci_p7ioc_tce_invalidate(tbl, index, 1, true);
-
-	return ret;
+	return pnv_tce_xchg(tbl, index, hpa, direction, !realmode);
 }
 #endif
 
@@ -1973,8 +1959,8 @@ static void pnv_ioda1_tce_free(struct iommu_table *tbl, long index,
 static struct iommu_table_ops pnv_ioda1_iommu_ops = {
 	.set = pnv_ioda1_tce_build,
 #ifdef CONFIG_IOMMU_API
-	.exchange = pnv_ioda1_tce_xchg,
-	.exchange_rm = pnv_ioda1_tce_xchg_rm,
+	.xchg_no_kill = pnv_ioda_tce_xchg_no_kill,
+	.tce_kill = pnv_pci_p7ioc_tce_invalidate,
 	.useraddrptr = pnv_tce_useraddrptr,
 #endif
 	.clear = pnv_ioda1_tce_free,
@@ -2103,30 +2089,6 @@ static int pnv_ioda2_tce_build(struct iommu_table *tbl, long index,
 	return ret;
 }
 
-#ifdef CONFIG_IOMMU_API
-static int pnv_ioda2_tce_xchg(struct iommu_table *tbl, long index,
-		unsigned long *hpa, enum dma_data_direction *direction)
-{
-	long ret = pnv_tce_xchg(tbl, index, hpa, direction, true);
-
-	if (!ret)
-		pnv_pci_ioda2_tce_invalidate(tbl, index, 1, false);
-
-	return ret;
-}
-
-static int pnv_ioda2_tce_xchg_rm(struct iommu_table *tbl, long index,
-		unsigned long *hpa, enum dma_data_direction *direction)
-{
-	long ret = pnv_tce_xchg(tbl, index, hpa, direction, false);
-
-	if (!ret)
-		pnv_pci_ioda2_tce_invalidate(tbl, index, 1, true);
-
-	return ret;
-}
-#endif
-
 static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
 		long npages)
 {
@@ -2138,8 +2100,8 @@ static void pnv_ioda2_tce_free(struct iommu_table *tbl, long index,
 static struct iommu_table_ops pnv_ioda2_iommu_ops = {
 	.set = pnv_ioda2_tce_build,
 #ifdef CONFIG_IOMMU_API
-	.exchange = pnv_ioda2_tce_xchg,
-	.exchange_rm = pnv_ioda2_tce_xchg_rm,
+	.xchg_no_kill = pnv_ioda_tce_xchg_no_kill,
+	.tce_kill = pnv_pci_ioda2_tce_invalidate,
 	.useraddrptr = pnv_tce_useraddrptr,
 #endif
 	.clear = pnv_ioda2_tce_free,

arch/powerpc/platforms/powernv/powernv.h

@@ -30,4 +30,9 @@ extern void opal_event_shutdown(void);
 
 bool cpu_core_split_required(void);
 
+struct memcons;
+ssize_t memcons_copy(struct memcons *mc, char *to, loff_t pos, size_t count);
+u32 memcons_get_size(struct memcons *mc);
+struct memcons *memcons_init(struct device_node *node, const char *mc_prop_name);
+
 #endif /* _POWERNV_H */

arch/powerpc/platforms/powernv/ultravisor.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Ultravisor high level interfaces
+ *
+ * Copyright 2019, IBM Corporation.
+ *
+ */
+#include <linux/init.h>
+#include <linux/printk.h>
+#include <linux/of_fdt.h>
+#include <linux/of.h>
+
+#include <asm/ultravisor.h>
+#include <asm/firmware.h>
+#include <asm/machdep.h>
+
+#include "powernv.h"
+
+static struct kobject *ultravisor_kobj;
+
+int __init early_init_dt_scan_ultravisor(unsigned long node, const char *uname,
+					 int depth, void *data)
+{
+	if (!of_flat_dt_is_compatible(node, "ibm,ultravisor"))
+		return 0;
+
+	powerpc_firmware_features |= FW_FEATURE_ULTRAVISOR;
+	pr_debug("Ultravisor detected!\n");
+	return 1;
+}
+
+static struct memcons *uv_memcons;
+
+static ssize_t uv_msglog_read(struct file *file, struct kobject *kobj,
+			      struct bin_attribute *bin_attr, char *to,
+			      loff_t pos, size_t count)
+{
+	return memcons_copy(uv_memcons, to, pos, count);
+}
+
+static struct bin_attribute uv_msglog_attr = {
+	.attr = {.name = "msglog", .mode = 0400},
+	.read = uv_msglog_read
+};
+
+static int __init uv_init(void)
+{
+	struct device_node *node;
+
+	if (!firmware_has_feature(FW_FEATURE_ULTRAVISOR))
+		return 0;
+
+	node = of_find_compatible_node(NULL, NULL, "ibm,uv-firmware");
+	if (!node)
+		return -ENODEV;
+
+	uv_memcons = memcons_init(node, "memcons");
+	if (!uv_memcons)
+		return -ENOENT;
+
+	uv_msglog_attr.size = memcons_get_size(uv_memcons);
+
+	ultravisor_kobj = kobject_create_and_add("ultravisor", firmware_kobj);
+	if (!ultravisor_kobj)
+		return -ENOMEM;
+
+	return sysfs_create_bin_file(ultravisor_kobj, &uv_msglog_attr);
+}
+machine_subsys_initcall(powernv, uv_init);

arch/powerpc/platforms/pseries/iommu.c

@@ -621,7 +621,8 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 
 #ifdef CONFIG_IOMMU_API
 static int tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned
-				long *tce, enum dma_data_direction *direction)
+				long *tce, enum dma_data_direction *direction,
+				bool realmode)
 {
 	long rc;
 	unsigned long ioba = (unsigned long) index << tbl->it_page_shift;
@@ -649,7 +650,7 @@ static int tce_exchange_pseries(struct iommu_table *tbl, long index, unsigned
 struct iommu_table_ops iommu_table_lpar_multi_ops = {
 	.set = tce_buildmulti_pSeriesLP,
 #ifdef CONFIG_IOMMU_API
-	.exchange = tce_exchange_pseries,
+	.xchg_no_kill = tce_exchange_pseries,
 #endif
 	.clear = tce_freemulti_pSeriesLP,
 	.get = tce_get_pSeriesLP

drivers/vfio/vfio_iommu_spapr_tce.c

@@ -435,7 +435,7 @@ static int tce_iommu_clear(struct tce_container *container,
 	unsigned long oldhpa;
 	long ret;
 	enum dma_data_direction direction;
-	unsigned long lastentry = entry + pages;
+	unsigned long lastentry = entry + pages, firstentry = entry;
 
 	for ( ; entry < lastentry; ++entry) {
 		if (tbl->it_indirect_levels && tbl->it_userspace) {
@@ -460,7 +460,7 @@ static int tce_iommu_clear(struct tce_container *container,
 
 		direction = DMA_NONE;
 		oldhpa = 0;
-		ret = iommu_tce_xchg(container->mm, tbl, entry, &oldhpa,
+		ret = iommu_tce_xchg_no_kill(container->mm, tbl, entry, &oldhpa,
 				&direction);
 		if (ret)
 			continue;
@@ -476,6 +476,8 @@ static int tce_iommu_clear(struct tce_container *container,
 		tce_iommu_unuse_page(container, oldhpa);
 	}
 
+	iommu_tce_kill(tbl, firstentry, pages);
+
 	return 0;
 }
 
@@ -518,8 +520,8 @@ static long tce_iommu_build(struct tce_container *container,
 
 		hpa |= offset;
 		dirtmp = direction;
-		ret = iommu_tce_xchg(container->mm, tbl, entry + i, &hpa,
-				&dirtmp);
+		ret = iommu_tce_xchg_no_kill(container->mm, tbl, entry + i,
+				&hpa, &dirtmp);
 		if (ret) {
 			tce_iommu_unuse_page(container, hpa);
 			pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%ld\n",
@@ -536,6 +538,8 @@ static long tce_iommu_build(struct tce_container *container,
 
 	if (ret)
 		tce_iommu_clear(container, tbl, entry, i);
+	else
+		iommu_tce_kill(tbl, entry, pages);
 
 	return ret;
 }
@@ -572,8 +576,8 @@ static long tce_iommu_build_v2(struct tce_container *container,
 		if (mm_iommu_mapped_inc(mem))
 			break;
 
-		ret = iommu_tce_xchg(container->mm, tbl, entry + i, &hpa,
-				&dirtmp);
+		ret = iommu_tce_xchg_no_kill(container->mm, tbl, entry + i,
+				&hpa, &dirtmp);
 		if (ret) {
 			/* dirtmp cannot be DMA_NONE here */
 			tce_iommu_unuse_page_v2(container, tbl, entry + i);
@@ -593,6 +597,8 @@ static long tce_iommu_build_v2(struct tce_container *container,
 
 	if (ret)
 		tce_iommu_clear(container, tbl, entry, i);
+	else
+		iommu_tce_kill(tbl, entry, pages);
 
 	return ret;
 }