Merge branch 'topic/ppc-kvm' into next

Merge in some commits we're sharing with the KVM tree.

I manually propagated the change from commit d3d4ffaae439
("powerpc/powernv/ioda2: Reduce upper limit for DMA window size") into
pci-ioda-tce.c.

Conflicts:
        arch/powerpc/include/asm/cputable.h
        arch/powerpc/platforms/powernv/pci-ioda.c
        arch/powerpc/platforms/powernv/pci.h

37 files changed, 521 insertions, 858 deletions

diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index c459f937d484..50888388a359 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -32,26 +32,6 @@ static inline int hstate_get_psize(struct hstate *hstate)
 	}
 }
 
-#define arch_make_huge_pte arch_make_huge_pte
-static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
-				       struct page *page, int writable)
-{
-	unsigned long page_shift;
-
-	if (!cpu_has_feature(CPU_FTR_POWER9_DD1))
-		return entry;
-
-	page_shift = huge_page_shift(hstate_vma(vma));
-	/*
-	 * We don't support 1G hugetlb pages yet.
-	 */
-	VM_WARN_ON(page_shift == mmu_psize_defs[MMU_PAGE_1G].shift);
-	if (page_shift == mmu_psize_defs[MMU_PAGE_2M].shift)
-		return __pte(pte_val(entry) | R_PAGE_LARGE);
-	else
-		return entry;
-}
-
 #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
 static inline bool gigantic_page_supported(void)
 {
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 42aafba7a308..676118743a06 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -479,9 +479,8 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 {
 	if (full && radix_enabled()) {
 		/*
-		 * Let's skip the DD1 style pte update here. We know that
-		 * this is a full mm pte clear and hence can be sure there is
-		 * no parallel set_pte.
+		 * We know that this is a full mm pte clear and
+		 * hence can be sure there is no parallel set_pte.
 		 */
 		return radix__ptep_get_and_clear_full(mm, addr, ptep, full);
 	}
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index ef9f96742ce1..3ab3f7aef022 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -12,12 +12,6 @@
 #include <asm/book3s/64/radix-4k.h>
 #endif
 
-/*
- * For P9 DD1 only, we need to track whether the pte's huge.
- */
-#define R_PAGE_LARGE	_RPAGE_RSV1
-
-
 #ifndef __ASSEMBLY__
 #include <asm/book3s/64/tlbflush-radix.h>
 #include <asm/cpu_has_feature.h>
@@ -154,20 +148,7 @@ static inline unsigned long radix__pte_update(struct mm_struct *mm,
 {
 	unsigned long old_pte;
 
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
-
-		unsigned long new_pte;
-
-		old_pte = __radix_pte_update(ptep, ~0ul, 0);
-		/*
-		 * new value of pte
-		 */
-		new_pte = (old_pte | set) & ~clr;
-		radix__flush_tlb_pte_p9_dd1(old_pte, mm, addr);
-		if (new_pte)
-			__radix_pte_update(ptep, 0, new_pte);
-	} else
-		old_pte = __radix_pte_update(ptep, clr, set);
+	old_pte = __radix_pte_update(ptep, clr, set);
 	if (!huge)
 		assert_pte_locked(mm, addr);
 
@@ -253,8 +234,6 @@ static inline int radix__pmd_trans_huge(pmd_t pmd)
 
 static inline pmd_t radix__pmd_mkhuge(pmd_t pmd)
 {
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-		return __pmd(pmd_val(pmd) | _PAGE_PTE | R_PAGE_LARGE);
 	return __pmd(pmd_val(pmd) | _PAGE_PTE);
 }
 
@@ -285,18 +264,14 @@ static inline unsigned long radix__get_tree_size(void)
 	unsigned long rts_field;
 	/*
 	 * We support 52 bits, hence:
-	 *  DD1    52-28 = 24, 0b11000
-	 *  Others 52-31 = 21, 0b10101
+	 * bits 52 - 31 = 21, 0b10101
 	 * RTS encoding details
 	 * bits 0 - 3 of rts -> bits 6 - 8 unsigned long
 	 * bits 4 - 5 of rts -> bits 62 - 63 of unsigned long
 	 */
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-		rts_field = (0x3UL << 61);
-	else {
-		rts_field = (0x5UL << 5); /* 6 - 8 bits */
-		rts_field |= (0x2UL << 61);
-	}
+	rts_field = (0x5UL << 5); /* 6 - 8 bits */
+	rts_field |= (0x2UL << 61);
+
 	return rts_field;
 }
 
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index ef5c3f2994c9..1154a6dc6d26 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -48,8 +48,6 @@ extern void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmad
 extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 extern void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr);
 extern void radix__flush_tlb_all(void);
-extern void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm,
-					unsigned long address);
 
 extern void radix__flush_tlb_lpid_page(unsigned int lpid,
 					unsigned long addr,
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 7711ebfb7d5f..82816a2043b9 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -210,7 +210,6 @@ static inline void cpu_feature_keys_init(void) { }
 #define CPU_FTR_DAWR			LONG_ASM_CONST(0x0000008000000000)
 #define CPU_FTR_DABRX			LONG_ASM_CONST(0x0000010000000000)
 #define CPU_FTR_PMAO_BUG		LONG_ASM_CONST(0x0000020000000000)
-#define CPU_FTR_POWER9_DD1		LONG_ASM_CONST(0x0000040000000000)
 #define CPU_FTR_POWER9_DD2_1		LONG_ASM_CONST(0x0000080000000000)
 #define CPU_FTR_P9_TM_HV_ASSIST		LONG_ASM_CONST(0x0000100000000000)
 #define CPU_FTR_P9_TM_XER_SO_BUG	LONG_ASM_CONST(0x0000200000000000)
@@ -463,8 +462,6 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
 	    CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_PKEY | \
 	    CPU_FTR_P9_TLBIE_BUG | CPU_FTR_P9_TIDR)
-#define CPU_FTRS_POWER9_DD1 ((CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) & \
-			     (~CPU_FTR_SAO))
 #define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9
 #define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1)
 #define CPU_FTRS_POWER9_DD2_2 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1 | \
@@ -488,16 +485,14 @@ static inline void cpu_feature_keys_init(void) { }
 #define CPU_FTRS_POSSIBLE	\
 	    (CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | CPU_FTRS_POWER8 | \
 	     CPU_FTR_ALTIVEC_COMP | CPU_FTR_VSX_COMP | CPU_FTRS_POWER9 | \
-	     CPU_FTRS_POWER9_DD1 | CPU_FTRS_POWER9_DD2_1 | \
-	     CPU_FTRS_POWER9_DD2_2)
+	     CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2)
 #else
 #define CPU_FTRS_POSSIBLE	\
 	    (CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | \
 	     CPU_FTRS_POWER6 | CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | \
 	     CPU_FTRS_POWER8 | CPU_FTRS_CELL | CPU_FTRS_PA6T | \
 	     CPU_FTR_VSX_COMP | CPU_FTR_ALTIVEC_COMP | CPU_FTRS_POWER9 | \
-	     CPU_FTRS_POWER9_DD1 | CPU_FTRS_POWER9_DD2_1 | \
-	     CPU_FTRS_POWER9_DD2_2)
+	     CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2)
 #endif /* CONFIG_CPU_LITTLE_ENDIAN */
 #endif
 #else
@@ -565,17 +560,15 @@ enum {
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
 #define CPU_FTRS_ALWAYS \
 	    (CPU_FTRS_POSSIBLE & ~CPU_FTR_HVMODE & CPU_FTRS_POWER7 & \
-	     CPU_FTRS_POWER8E & CPU_FTRS_POWER8 & \
-	     CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD1 & CPU_FTRS_POWER9_DD2_1 & \
-	     CPU_FTRS_DT_CPU_BASE)
+	     CPU_FTRS_POWER8E & CPU_FTRS_POWER8 & CPU_FTRS_POWER9 & \
+	     CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_DT_CPU_BASE)
 #else
 #define CPU_FTRS_ALWAYS		\
 	    (CPU_FTRS_PPC970 & CPU_FTRS_POWER5 & \
 	     CPU_FTRS_POWER6 & CPU_FTRS_POWER7 & CPU_FTRS_CELL & \
 	     CPU_FTRS_PA6T & CPU_FTRS_POWER8 & CPU_FTRS_POWER8E & \
-	     ~CPU_FTR_HVMODE & CPU_FTRS_POSSIBLE & \
-	     CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD1 & CPU_FTRS_POWER9_DD2_1 & \
-	     CPU_FTRS_DT_CPU_BASE)
+	     ~CPU_FTR_HVMODE & CPU_FTRS_POSSIBLE & CPU_FTRS_POWER9 & \
+	     CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_DT_CPU_BASE)
 #endif /* CONFIG_CPU_LITTLE_ENDIAN */
 #endif
 #else
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 20febe0b7f32..daa3ee5d7ad2 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -69,6 +69,8 @@ struct iommu_table_ops {
 			long index,
 			unsigned long *hpa,
 			enum dma_data_direction *direction);
+
+	__be64 *(*useraddrptr)(struct iommu_table *tbl, long index, bool alloc);
 #endif
 	void (*clear)(struct iommu_table *tbl,
 			long index, long npages);
@@ -117,15 +119,16 @@ struct iommu_table {
 	unsigned long *it_map;       /* A simple allocation bitmap for now */
 	unsigned long  it_page_shift;/* table iommu page size */
 	struct list_head it_group_list;/* List of iommu_table_group_link */
-	unsigned long *it_userspace; /* userspace view of the table */
+	__be64 *it_userspace; /* userspace view of the table */
 	struct iommu_table_ops *it_ops;
 	struct kref    it_kref;
+	int it_nid;
 };
 
+#define IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry) \
+		((tbl)->it_ops->useraddrptr((tbl), (entry), false))
 #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \
-		((tbl)->it_userspace ? \
-			&((tbl)->it_userspace[(entry) - (tbl)->it_offset]) : \
-			NULL)
+		((tbl)->it_ops->useraddrptr((tbl), (entry), true))
 
 /* Pure 2^n version of get_order */
 static inline __attribute_const__
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 6d34bd71139d..4e9cede5a7e7 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -187,11 +187,6 @@ struct paca_struct {
 	u8 subcore_sibling_mask;
 	/* Flag to request this thread not to stop */
 	atomic_t dont_stop;
-	/*
-	 * Pointer to an array which contains pointer
-	 * to the sibling threads' paca.
-	 */
-	struct paca_struct **thread_sibling_pacas;
 	/* The PSSCR value that the kernel requested before going to stop */
 	u64 requested_psscr;
 
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 0a0544335950..89cf15566c4e 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -766,7 +766,6 @@ int main(void)
 	OFFSET(PACA_THREAD_IDLE_STATE, paca_struct, thread_idle_state);
 	OFFSET(PACA_THREAD_MASK, paca_struct, thread_mask);
 	OFFSET(PACA_SUBCORE_SIBLING_MASK, paca_struct, subcore_sibling_mask);
-	OFFSET(PACA_SIBLING_PACA_PTRS, paca_struct, thread_sibling_pacas);
 	OFFSET(PACA_REQ_PSSCR, paca_struct, requested_psscr);
 	OFFSET(PACA_DONT_STOP, paca_struct, dont_stop);
 #define STOP_SPR(x, f)	OFFSET(x, paca_struct, stop_sprs.f)
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 9169ffdbab08..2da01340c84c 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -466,25 +466,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
-	{	/* Power9 DD1*/
-		.pvr_mask		= 0xffffff00,
-		.pvr_value		= 0x004e0100,
-		.cpu_name		= "POWER9 (raw)",
-		.cpu_features		= CPU_FTRS_POWER9_DD1,
-		.cpu_user_features	= COMMON_USER_POWER9,
-		.cpu_user_features2	= COMMON_USER2_POWER9,
-		.mmu_features		= MMU_FTRS_POWER9,
-		.icache_bsize		= 128,
-		.dcache_bsize		= 128,
-		.num_pmcs		= 6,
-		.pmc_type		= PPC_PMC_IBM,
-		.oprofile_cpu_type	= "ppc64/power9",
-		.oprofile_type		= PPC_OPROFILE_INVALID,
-		.cpu_setup		= __setup_cpu_power9,
-		.cpu_restore		= __restore_cpu_power9,
-		.machine_check_early	= __machine_check_early_realmode_p9,
-		.platform		= "power9",
-	},
 	{	/* Power9 DD2.0 */
 		.pvr_mask		= 0xffffefff,
 		.pvr_value		= 0x004e0200,
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 96dd3d871986..f432054234a4 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -701,9 +701,7 @@ static __init void cpufeatures_cpu_quirks(void)
 	/*
 	 * Not all quirks can be derived from the cpufeatures device tree.
 	 */
-	if ((version & 0xffffff00) == 0x004e0100)
-		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD1;
-	else if ((version & 0xffffefff) == 0x004e0200)
+	if ((version & 0xffffefff) == 0x004e0200)
 		; /* DD2.0 has no feature flag */
 	else if ((version & 0xffffefff) == 0x004e0201)
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 285c6465324a..76a14702cb9c 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -276,9 +276,7 @@ BEGIN_FTR_SECTION
 	 *
 	 * This interrupt can wake directly from idle. If that is the case,
 	 * the machine check is handled then the idle wakeup code is called
-	 * to restore state. In that case, the POWER9 DD1 idle PACA workaround
-	 * is not applied in the early machine check code, which will cause
-	 * bugs.
+	 * to restore state.
 	 */
 	mr	r11,r1			/* Save r1 */
 	lhz	r10,PACA_IN_MCE(r13)
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index e734f6e45abc..d85d5515a091 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -467,43 +467,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
 #endif
 
 /*
- * On waking up from stop 0,1,2 with ESL=1 on POWER9 DD1,
- * HSPRG0 will be set to the HSPRG0 value of one of the
- * threads in this core. Thus the value we have in r13
- * may not be this thread's paca pointer.
- *
- * Fortunately, the TIR remains invariant. Since this thread's
- * paca pointer is recorded in all its sibling's paca, we can
- * correctly recover this thread's paca pointer if we
- * know the index of this thread in the core.
- *
- * This index can be obtained from the TIR.
- *
- * i.e, thread's position in the core = TIR.
- * If this value is i, then this thread's paca is
- * paca->thread_sibling_pacas[i].
- */
-power9_dd1_recover_paca:
-	mfspr	r4, SPRN_TIR
-	/*
-	 * Since each entry in thread_sibling_pacas is 8 bytes
-	 * we need to left-shift by 3 bits. Thus r4 = i * 8
-	 */
-	sldi	r4, r4, 3
-	/* Get &paca->thread_sibling_pacas[0] in r5 */
-	ld	r5, PACA_SIBLING_PACA_PTRS(r13)
-	/* Load paca->thread_sibling_pacas[i] into r13 */
-	ldx	r13, r4, r5
-	SET_PACA(r13)
-	/*
-	 * Indicate that we have lost NVGPR state
-	 * which needs to be restored from the stack.
-	 */
-	li	r3, 1
-	stb	r3,PACA_NAPSTATELOST(r13)
-	blr
-
-/*
  * Called from machine check handler for powersave wakeups.
  * Low level machine check processing has already been done. Now just
  * go through the wake up path to get everything in order.
@@ -537,9 +500,6 @@ pnv_powersave_wakeup:
 	ld	r2, PACATOC(r13)
 
 BEGIN_FTR_SECTION
-BEGIN_FTR_SECTION_NESTED(70)
-	bl	power9_dd1_recover_paca
-END_FTR_SECTION_NESTED_IFSET(CPU_FTR_POWER9_DD1, 70)
 	bl	pnv_restore_hyp_resource_arch300
 FTR_SECTION_ELSE
 	bl	pnv_restore_hyp_resource_arch207
@@ -602,22 +562,12 @@ END_FTR_SECTION_IFCLR(CPU_FTR_POWER9_DD2_1)
 	LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
 	ld	r4,ADDROFF(pnv_first_deep_stop_state)(r5)
 
-BEGIN_FTR_SECTION_NESTED(71)
-	/*
-	 * Assume that we are waking up from the state
-	 * same as the Requested Level (RL) in the PSSCR
-	 * which are Bits 60-63
-	 */
-	ld	r5,PACA_REQ_PSSCR(r13)
-	rldicl  r5,r5,0,60
-FTR_SECTION_ELSE_NESTED(71)
 	/*
 	 * 0-3 bits correspond to Power-Saving Level Status
 	 * which indicates the idle state we are waking up from
 	 */
 	mfspr	r5, SPRN_PSSCR
 	rldicl  r5,r5,4,60
-ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_POWER9_DD1, 71)
 	li	r0, 0		/* clear requested_psscr to say we're awake */
 	std	r0, PACA_REQ_PSSCR(r13)
 	cmpd	cr4,r5,r4
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 9ef4aea9fffe..27f0caee55ea 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1250,17 +1250,9 @@ struct task_struct *__switch_to(struct task_struct *prev,
 		 * mappings. If the new process has the foreign real address
 		 * mappings, we must issue a cp_abort to clear any state and
 		 * prevent snooping, corruption or a covert channel.
-		 *
-		 * DD1 allows paste into normal system memory so we do an
-		 * unpaired copy, rather than cp_abort, to clear the buffer,
-		 * since cp_abort is quite expensive.
 		 */
-		if (current_thread_info()->task->thread.used_vas) {
+		if (current_thread_info()->task->thread.used_vas)
 			asm volatile(PPC_CP_ABORT);
-		} else if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
-			asm volatile(PPC_COPY(%0, %1)
-					: : "r"(dummy_copy_buffer), "r"(0));
-		}
 	}
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 176f911ee983..0af1c0aea1fe 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -66,10 +66,7 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	bits = root & RPDS_MASK;
 	root = root & RPDB_MASK;
 
-	/* P9 DD1 interprets RTS (radix tree size) differently */
 	offset = rts + 31;
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-		offset -= 3;
 
 	/* current implementations only support 52-bit space */
 	if (offset != 52)
@@ -160,17 +157,7 @@ static unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep,
 				      unsigned long clr, unsigned long set,
 				      unsigned long addr, unsigned int shift)
 {
-	unsigned long old = 0;
-
-	if (!(clr & _PAGE_PRESENT) && cpu_has_feature(CPU_FTR_POWER9_DD1) &&
-	    pte_present(*ptep)) {
-		/* have to invalidate it first */
-		old = __radix_pte_update(ptep, _PAGE_PRESENT, 0);
-		kvmppc_radix_tlbie_page(kvm, addr, shift);
-		set |= _PAGE_PRESENT;
-		old &= _PAGE_PRESENT;
-	}
-	return __radix_pte_update(ptep, clr, set) | old;
+	return __radix_pte_update(ptep, clr, set);
 }
 
 void kvmppc_radix_set_pte_at(struct kvm *kvm, unsigned long addr,
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index d066e37551ec..8b9aaf24b0a2 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -378,19 +378,19 @@ static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm,
 {
 	struct mm_iommu_table_group_mem_t *mem = NULL;
 	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
-	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
 
 	if (!pua)
 		/* it_userspace allocation might be delayed */
 		return H_TOO_HARD;
 
-	mem = mm_iommu_lookup(kvm->mm, *pua, pgsize);
+	mem = mm_iommu_lookup(kvm->mm, be64_to_cpu(*pua), pgsize);
 	if (!mem)
 		return H_TOO_HARD;
 
 	mm_iommu_mapped_dec(mem);
 
-	*pua = 0;
+	*pua = cpu_to_be64(0);
 
 	return H_SUCCESS;
 }
@@ -437,7 +437,8 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 		enum dma_data_direction dir)
 {
 	long ret;
-	unsigned long hpa, *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+	unsigned long hpa;
+	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
 	struct mm_iommu_table_group_mem_t *mem;
 
 	if (!pua)
@@ -464,7 +465,7 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 	if (dir != DMA_NONE)
 		kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
 
-	*pua = ua;
+	*pua = cpu_to_be64(ua);
 
 	return 0;
 }
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 925fc316a104..d4bcd1b17b09 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -200,23 +200,19 @@ static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm,
 {
 	struct mm_iommu_table_group_mem_t *mem = NULL;
 	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
-	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry);
 
 	if (!pua)
 		/* it_userspace allocation might be delayed */
 		return H_TOO_HARD;
 
-	pua = (void *) vmalloc_to_phys(pua);
-	if (WARN_ON_ONCE_RM(!pua))
-		return H_HARDWARE;
-
-	mem = mm_iommu_lookup_rm(kvm->mm, *pua, pgsize);
+	mem = mm_iommu_lookup_rm(kvm->mm, be64_to_cpu(*pua), pgsize);
 	if (!mem)
 		return H_TOO_HARD;
 
 	mm_iommu_mapped_dec(mem);
 
-	*pua = 0;
+	*pua = cpu_to_be64(0);
 
 	return H_SUCCESS;
 }
@@ -268,7 +264,7 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 {
 	long ret;
 	unsigned long hpa = 0;
-	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry);
 	struct mm_iommu_table_group_mem_t *mem;
 
 	if (!pua)
@@ -282,10 +278,6 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
 		return H_HARDWARE;
 
-	pua = (void *) vmalloc_to_phys(pua);
-	if (WARN_ON_ONCE_RM(!pua))
-		return H_HARDWARE;
-
 	if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem)))
 		return H_CLOSED;
 
@@ -302,7 +294,7 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 	if (dir != DMA_NONE)
 		kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
 
-	*pua = ua;
+	*pua = cpu_to_be64(ua);
 
 	return 0;
 }
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index de686b340f4a..b568582120a3 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1693,14 +1693,6 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len);
 		break;
 	case KVM_REG_PPC_TB_OFFSET:
-		/*
-		 * POWER9 DD1 has an erratum where writing TBU40 causes
-		 * the timebase to lose ticks.  So we don't let the
-		 * timebase offset be changed on P9 DD1.  (It is
-		 * initialized to zero.)
-		 */
-		if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-			break;
 		/* round up to multiple of 2^24 */
 		vcpu->arch.vcore->tb_offset =
 			ALIGN(set_reg_val(id, *val), 1UL << 24);
@@ -2026,8 +2018,6 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 	/*
 	 * Set the default HFSCR for the guest from the host value.
 	 * This value is only used on POWER9.
-	 * On POWER9 DD1, TM doesn't work, so we make sure to
-	 * prevent the guest from using it.
 	 * On POWER9, we want to virtualize the doorbell facility, so we
 	 * turn off the HFSCR bit, which causes those instructions to trap.
 	 */
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 153988d878e8..6e4554b273f1 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -917,9 +917,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR)
 	mtspr	SPRN_PID, r7
 	mtspr	SPRN_WORT, r8
 BEGIN_FTR_SECTION
-	PPC_INVALIDATE_ERAT
-END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1)
-BEGIN_FTR_SECTION
 	/* POWER8-only registers */
 	ld	r5, VCPU_TCSCR(r4)
 	ld	r6, VCPU_ACOP(r4)
@@ -1912,7 +1909,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	ld	r5, VCPU_KVM(r9)
 	lbz	r0, KVM_RADIX(r5)
 	cmpwi	cr2, r0, 0
-	beq	cr2, 4f
+	beq	cr2, 2f
 
 	/*
 	 * Radix: do eieio; tlbsync; ptesync sequence in case we
@@ -1952,11 +1949,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	bdnz	1b
 	ptesync
 
-2:	/* Flush the ERAT on radix P9 DD1 guest exit */
-BEGIN_FTR_SECTION
-	PPC_INVALIDATE_ERAT
-END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1)
-4:
+2:
 #endif /* CONFIG_PPC_RADIX_MMU */
 
 	/*
@@ -3367,11 +3360,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	mtspr	SPRN_CIABR, r0
 	mtspr	SPRN_DAWRX, r0
 
-	/* Flush the ERAT on radix P9 DD1 guest exit */
-BEGIN_FTR_SECTION
-	PPC_INVALIDATE_ERAT
-END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1)
-
 BEGIN_MMU_FTR_SECTION
 	b	4f
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
diff --git a/arch/powerpc/kvm/book3s_xive_template.c b/arch/powerpc/kvm/book3s_xive_template.c
index 6e41ba7ec8f4..4171ede8722b 100644
--- a/arch/powerpc/kvm/book3s_xive_template.c
+++ b/arch/powerpc/kvm/book3s_xive_template.c
@@ -25,18 +25,6 @@ static void GLUE(X_PFX,ack_pending)(struct kvmppc_xive_vcpu *xc)
 	 */
 	eieio();
 
-	/*
-	 * DD1 bug workaround: If PIPR is less favored than CPPR
-	 * ignore the interrupt or we might incorrectly lose an IPB
-	 * bit.
-	 */
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
-		__be64 qw1 = __x_readq(__x_tima + TM_QW1_OS);
-		u8 pipr = be64_to_cpu(qw1) & 0xff;
-		if (pipr >= xc->hw_cppr)
-			return;
-	}
-
 	/* Perform the acknowledge OS to register cycle. */
 	ack = be16_to_cpu(__x_readw(__x_tima + TM_SPC_ACK_OS_REG));
 
@@ -89,8 +77,15 @@ static void GLUE(X_PFX,source_eoi)(u32 hw_irq, struct xive_irq_data *xd)
 	/* If the XIVE supports the new "store EOI facility, use it */
 	if (xd->flags & XIVE_IRQ_FLAG_STORE_EOI)
 		__x_writeq(0, __x_eoi_page(xd) + XIVE_ESB_STORE_EOI);
-	else if (hw_irq && xd->flags & XIVE_IRQ_FLAG_EOI_FW) {
+	else if (hw_irq && xd->flags & XIVE_IRQ_FLAG_EOI_FW)
 		opal_int_eoi(hw_irq);
+	else if (xd->flags & XIVE_IRQ_FLAG_LSI) {
+		/*
+		 * For LSIs the HW EOI cycle is used rather than PQ bits,
+		 * as they are automatically re-triggred in HW when still
+		 * pending.
+		 */
+		__x_readq(__x_eoi_page(xd) + XIVE_ESB_LOAD_EOI);
 	} else {
 		uint64_t eoi_val;
 
@@ -102,20 +97,12 @@ static void GLUE(X_PFX,source_eoi)(u32 hw_irq, struct xive_irq_data *xd)
 		 *
 		 * This allows us to then do a re-trigger if