Merge branch 'for-upstream' of git://github.com/agraf/linux-2.6 into next

Alex says:

"Changes this time include:

  - Generalize KVM_GUEST support to overall ePAPR code
  - Fix reset for Book3S HV
  - Fix machine check deferral when CONFIG_KVM_GUEST=y
  - Add support for BookE register DECAR"

* 'for-upstream' of git://github.com/agraf/linux-2.6:
  KVM: PPC: Not optimizing MSR_CE and MSR_ME with paravirt.
  KVM: PPC: booke: Added DECAR support
  KVM: PPC: Book3S HV: Make the guest hash table size configurable
  KVM: PPC: Factor out guest epapr initialization

Signed-off-by: Avi Kivity <avi@redhat.com>

18 files changed, 267 insertions, 90 deletions

diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h
index 976835d8f22e..bf2c06c33871 100644
--- a/arch/powerpc/include/asm/epapr_hcalls.h
+++ b/arch/powerpc/include/asm/epapr_hcalls.h
@@ -153,6 +153,8 @@
 #define EV_HCALL_CLOBBERS2 EV_HCALL_CLOBBERS3, "r5"
 #define EV_HCALL_CLOBBERS1 EV_HCALL_CLOBBERS2, "r4"
 
+extern bool epapr_paravirt_enabled;
+extern u32 epapr_hypercall_start[];
 
 /*
  * We use "uintptr_t" to define a register because it's guaranteed to be a
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index b0c08b142770..0dd1d86d3e31 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -36,11 +36,8 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
 #define SPAPR_TCE_SHIFT         12
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
-/* For now use fixed-size 16MB page table */
-#define HPT_ORDER       24
-#define HPT_NPTEG       (1ul << (HPT_ORDER - 7))        /* 128B per pteg */
-#define HPT_NPTE        (HPT_NPTEG << 3)                /* 8 PTEs per PTEG */
-#define HPT_HASH_MASK   (HPT_NPTEG - 1)
+#define KVM_DEFAULT_HPT_ORDER   24      /* 16MB HPT by default */
+extern int kvm_hpt_order;               /* order of preallocated HPTs */
 #endif
 
 #define VRMA_VSID       0x1ffffffUL     /* 1TB VSID reserved for VRMA */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index d848cdc49715..50ea12fd7bf5 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -237,6 +237,10 @@ struct kvm_arch {
         unsigned long vrma_slb_v;
         int rma_setup_done;
         int using_mmu_notifiers;
+        u32 hpt_order;
+        atomic_t vcpus_running;
+        unsigned long hpt_npte;
+        unsigned long hpt_mask;
         spinlock_t slot_phys_lock;
         unsigned long *slot_phys[KVM_MEM_SLOTS_NUM];
         int slot_npages[KVM_MEM_SLOTS_NUM];
@@ -414,7 +418,9 @@ struct kvm_vcpu_arch {
         ulong mcsrr1;
         ulong mcsr;
         u32 dec;
+#ifdef CONFIG_BOOKE
         u32 decar;
+#endif
         u32 tbl;
         u32 tbu;
         u32 tcr;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index f68c22fa2fce..0124937a23b9 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -119,7 +119,8 @@ extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu);
 extern int kvmppc_kvm_pv(struct kvm_vcpu *vcpu);
 extern void kvmppc_map_magic(struct kvm_vcpu *vcpu);
 
-extern long kvmppc_alloc_hpt(struct kvm *kvm);
+extern long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp);
+extern long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp);
 extern void kvmppc_free_hpt(struct kvm *kvm);
 extern long kvmppc_prepare_vrma(struct kvm *kvm,
                                 struct kvm_userspace_memory_region *mem);
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 83afacd3ba7b..bb282dd81612 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -128,6 +128,7 @@ ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
 obj-y                           += ppc_save_regs.o
 endif
 
+obj-$(CONFIG_EPAPR_PARAVIRT)    += epapr_paravirt.o epapr_hcalls.o
 obj-$(CONFIG_KVM_GUEST)         += kvm.o kvm_emul.o
 
 # Disable GCOV in odd or sensitive code
diff --git a/arch/powerpc/kernel/epapr_hcalls.S b/arch/powerpc/kernel/epapr_hcalls.S
new file mode 100644
index 000000000000..697b390ebfd8
--- /dev/null
+++ b/arch/powerpc/kernel/epapr_hcalls.S
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/threads.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+
+/* Hypercall entry point. Will be patched with device tree instructions. */
+.global epapr_hypercall_start
+epapr_hypercall_start:
+        li      r3, -1
+        nop
+        nop
+        nop
+        blr
diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c
new file mode 100644
index 000000000000..028aeae370b6
--- /dev/null
+++ b/arch/powerpc/kernel/epapr_paravirt.c
@@ -0,0 +1,52 @@
+/*
+ * ePAPR para-virtualization support.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ */
+
+#include <linux/of.h>
+#include <asm/epapr_hcalls.h>
+#include <asm/cacheflush.h>
+#include <asm/code-patching.h>
+
+bool epapr_paravirt_enabled;
+
+static int __init epapr_paravirt_init(void)
+{
+        struct device_node *hyper_node;
+        const u32 *insts;
+        int len, i;
+
+        hyper_node = of_find_node_by_path("/hypervisor");
+        if (!hyper_node)
+                return -ENODEV;
+
+        insts = of_get_property(hyper_node, "hcall-instructions", &len);
+        if (!insts)
+                return -ENODEV;
+
+        if (len % 4 || len > (4 * 4))
+                return -ENODEV;
+
+        for (i = 0; i < (len / 4); i++)
+                patch_instruction(epapr_hypercall_start + i, insts[i]);
+
+        epapr_paravirt_enabled = true;
+
+        return 0;
+}
+
+early_initcall(epapr_paravirt_init);
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 62bdf2389669..1c13307e0308 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -31,6 +31,7 @@
 #include <asm/cacheflush.h>
 #include <asm/disassemble.h>
 #include <asm/ppc-opcode.h>
+#include <asm/epapr_hcalls.h>
 
 #define KVM_MAGIC_PAGE          (-4096L)
 #define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
@@ -726,7 +727,7 @@ unsigned long kvm_hypercall(unsigned long *in,
         unsigned long register r11 asm("r11") = nr;
         unsigned long register r12 asm("r12");
 
-        asm volatile("bl        kvm_hypercall_start"
+        asm volatile("bl        epapr_hypercall_start"
                      : "=r"(r0), "=r"(r3), "=r"(r4), "=r"(r5), "=r"(r6),
                        "=r"(r7), "=r"(r8), "=r"(r9), "=r"(r10), "=r"(r11),
                        "=r"(r12)
@@ -747,29 +748,6 @@ unsigned long kvm_hypercall(unsigned long *in,
 }
 EXPORT_SYMBOL_GPL(kvm_hypercall);
 
-static int kvm_para_setup(void)
-{
-        extern u32 kvm_hypercall_start;
-        struct device_node *hyper_node;
-        u32 *insts;
-        int len, i;
-
-        hyper_node = of_find_node_by_path("/hypervisor");
-        if (!hyper_node)
-                return -1;
-
-        insts = (u32*)of_get_property(hyper_node, "hcall-instructions", &len);
-        if (len % 4)
-                return -1;
-        if (len > (4 * 4))
-                return -1;
-
-        for (i = 0; i < (len / 4); i++)
-                kvm_patch_ins(&(&kvm_hypercall_start)[i], insts[i]);
-
-        return 0;
-}
-
 static __init void kvm_free_tmp(void)
 {
         unsigned long start, end;
@@ -791,7 +769,7 @@ static int __init kvm_guest_init(void)
         if (!kvm_para_available())
                 goto free_tmp;
 
-        if (kvm_para_setup())
+        if (!epapr_paravirt_enabled)
                 goto free_tmp;
 
         if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index e291cf3cf954..e100ff324a85 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -24,16 +24,6 @@
 #include <asm/page.h>
 #include <asm/asm-offsets.h>
 
-/* Hypercall entry point. Will be patched with device tree instructions. */
-
-.global kvm_hypercall_start
-kvm_hypercall_start:
-        li      r3, -1
-        nop
-        nop
-        nop
-        blr
-
 #define KVM_MAGIC_PAGE          (-4096)
 
 #ifdef CONFIG_64BIT
@@ -132,7 +122,7 @@ kvm_emulate_mtmsrd_len:
         .long (kvm_emulate_mtmsrd_end - kvm_emulate_mtmsrd) / 4
 
 
-#define MSR_SAFE_BITS (MSR_EE | MSR_CE | MSR_ME | MSR_RI)
+#define MSR_SAFE_BITS (MSR_EE | MSR_RI)
 #define MSR_CRITICAL_BITS ~MSR_SAFE_BITS
 
 .global kvm_emulate_mtmsr
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 80a577517584..d03eb6f7b058 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -37,56 +37,121 @@
 /* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */
 #define MAX_LPID_970    63
 
-long kvmppc_alloc_hpt(struct kvm *kvm)
+/* Power architecture requires HPT is at least 256kB */
+#define PPC_MIN_HPT_ORDER       18
+
+long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 {
         unsigned long hpt;
-        long lpid;
         struct revmap_entry *rev;
         struct kvmppc_linear_info *li;
+        long order = kvm_hpt_order;
 
-        /* Allocate guest's hashed page table */
-        li = kvm_alloc_hpt();
-        if (li) {
-                /* using preallocated memory */
-                hpt = (ulong)li->base_virt;
-                kvm->arch.hpt_li = li;
-        } else {
-                /* using dynamic memory */
+        if (htab_orderp) {
+                order = *htab_orderp;
+                if (order < PPC_MIN_HPT_ORDER)
+                        order = PPC_MIN_HPT_ORDER;
+        }
+
+        /*
+         * If the user wants a different size from default,
+         * try first to allocate it from the kernel page allocator.
+         */
+        hpt = 0;
+        if (order != kvm_hpt_order) {
                 hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
-                                       __GFP_NOWARN, HPT_ORDER - PAGE_SHIFT);
+                                       __GFP_NOWARN, order - PAGE_SHIFT);
+                if (!hpt)
+                        --order;
         }
 
+        /* Next try to allocate from the preallocated pool */
         if (!hpt) {
-                pr_err("kvm_alloc_hpt: Couldn't alloc HPT\n");
-                return -ENOMEM;
+                li = kvm_alloc_hpt();
+                if (li) {
+                        hpt = (ulong)li->base_virt;
+                        kvm->arch.hpt_li = li;
+                        order = kvm_hpt_order;
+                }
         }
+
+        /* Lastly try successively smaller sizes from the page allocator */
+        while (!hpt && order > PPC_MIN_HPT_ORDER) {
+                hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
+                                       __GFP_NOWARN, order - PAGE_SHIFT);
+                if (!hpt)
+                        --order;
+        }
+
+        if (!hpt)
+                return -ENOMEM;
+
         kvm->arch.hpt_virt = hpt;
+        kvm->arch.hpt_order = order;
+        /* HPTEs are 2**4 bytes long */
+        kvm->arch.hpt_npte = 1ul << (order - 4);
+        /* 128 (2**7) bytes in each HPTEG */
+        kvm->arch.hpt_mask = (1ul << (order - 7)) - 1;
 
         /* Allocate reverse map array */
-        rev = vmalloc(sizeof(struct revmap_entry) * HPT_NPTE);
+        rev = vmalloc(sizeof(struct revmap_entry) * kvm->arch.hpt_npte);
         if (!rev) {
                 pr_err("kvmppc_alloc_hpt: Couldn't alloc reverse map array\n");
                 goto out_freehpt;
         }
         kvm->arch.revmap = rev;
+        kvm->arch.sdr1 = __pa(hpt) | (order - 18);
 
-        lpid = kvmppc_alloc_lpid();
-        if (lpid < 0)
-                goto out_freeboth;
+        pr_info("KVM guest htab at %lx (order %ld), LPID %x\n",
+                hpt, order, kvm->arch.lpid);
 
-        kvm->arch.sdr1 = __pa(hpt) | (HPT_ORDER - 18);
-        kvm->arch.lpid = lpid;
-
-        pr_info("KVM guest htab at %lx, LPID %lx\n", hpt, lpid);
+        if (htab_orderp)
+                *htab_orderp = order;
         return 0;
 
- out_freeboth:
-        vfree(rev);
  out_freehpt:
-        free_pages(hpt, HPT_ORDER - PAGE_SHIFT);
+        if (kvm->arch.hpt_li)
+                kvm_release_hpt(kvm->arch.hpt_li);
+        else
+                free_pages(hpt, order - PAGE_SHIFT);
         return -ENOMEM;
 }
 
+long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp)
+{
+        long err = -EBUSY;
+        long order;
+
+        mutex_lock(&kvm->lock);
+        if (kvm->arch.rma_setup_done) {
+                kvm->arch.rma_setup_done = 0;
+                /* order rma_setup_done vs. vcpus_running */
+                smp_mb();
+                if (atomic_read(&kvm->arch.vcpus_running)) {
+                        kvm->arch.rma_setup_done = 1;
+                        goto out;
+                }
+        }
+        if (kvm->arch.hpt_virt) {
+                order = kvm->arch.hpt_order;
+                /* Set the entire HPT to 0, i.e. invalid HPTEs */
+                memset((void *)kvm->arch.hpt_virt, 0, 1ul << order);
+                /*
+                 * Set the whole last_vcpu array to an invalid vcpu number.
+                 * This ensures that each vcpu will flush its TLB on next entry.
+                 */
+                memset(kvm->arch.last_vcpu, 0xff, sizeof(kvm->arch.last_vcpu));
+                *htab_orderp = order;
+                err = 0;
+        } else {
+                err = kvmppc_alloc_hpt(kvm, htab_orderp);
+                order = *htab_orderp;
+        }
+ out:
+        mutex_unlock(&kvm->lock);
+        return err;
+}
+
 void kvmppc_free_hpt(struct kvm *kvm)
 {
         kvmppc_free_lpid(kvm->arch.lpid);
@@ -94,7 +159,8 @@ void kvmppc_free_hpt(struct kvm *kvm)
         if (kvm->arch.hpt_li)
                 kvm_release_hpt(kvm->arch.hpt_li);
         else
-                free_pages(kvm->arch.hpt_virt, HPT_ORDER - PAGE_SHIFT);
+                free_pages(kvm->arch.hpt_virt,
+                           kvm->arch.hpt_order - PAGE_SHIFT);
 }
 
 /* Bits in first HPTE dword for pagesize 4k, 64k or 16M */
@@ -119,6 +185,7 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
         unsigned long psize;
         unsigned long hp0, hp1;
         long ret;
+        struct kvm *kvm = vcpu->kvm;
 
         psize = 1ul << porder;
         npages = memslot->npages >> (porder - PAGE_SHIFT);
@@ -127,8 +194,8 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
         if (npages > 1ul << (40 - porder))
                 npages = 1ul << (40 - porder);
         /* Can't use more than 1 HPTE per HPTEG */
-        if (npages > HPT_NPTEG)
-                npages = HPT_NPTEG;
+        if (npages > kvm->arch.hpt_mask + 1)
+                npages = kvm->arch.hpt_mask + 1;
 
         hp0 = HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)) |
                 HPTE_V_BOLTED | hpte0_pgsize_encoding(psize);
@@ -138,7 +205,7 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
         for (i = 0; i < npages; ++i) {
                 addr = i << porder;
                 /* can't use hpt_hash since va > 64 bits */
-                hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & HPT_HASH_MASK;
+                hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & kvm->arch.hpt_mask;
                 /*
                  * We assume that the hash table is empty and no
                  * vcpus are using it at this stage.  Since we create
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index c6af1d623839..d084e412b3c5 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -56,7 +56,7 @@
 /* #define EXIT_DEBUG_INT */
 
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
-static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu);
+static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
@@ -1068,11 +1068,15 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
                 return -EINTR;
         }
 
-        /* On the first time here, set up VRMA or RMA */
+        atomic_inc(&vcpu->kvm->arch.vcpus_running);
+        /* Order vcpus_running vs. rma_setup_done, see kvmppc_alloc_reset_hpt */
+        smp_mb();
+
+        /* On the first time here, set up HTAB and VRMA or RMA */
         if (!vcpu->kvm->arch.rma_setup_done) {
-                r = kvmppc_hv_setup_rma(vcpu);
+                r = kvmppc_hv_setup_htab_rma(vcpu);
                 if (r)
-                        return r;
+                        goto out;
         }
 
         flush_fp_to_thread(current);
@@ -1090,6 +1094,9 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
                         kvmppc_core_prepare_to_enter(vcpu);
                 }
         } while (r == RESUME_GUEST);
+
+ out:
+        atomic_dec(&vcpu->kvm->arch.vcpus_running);
         return r;
 }
 
@@ -1305,7 +1312,7 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm,
 {
 }
 
-static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu)
+static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 {
         int err = 0;
         struct kvm *kvm = vcpu->kvm;
@@ -1324,6 +1331,15 @@ static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu)
         if (kvm->arch.rma_setup_done)
                 goto out;       /* another vcpu beat us to it */
 
+        /* Allocate hashed page table (if not done already) and reset it */
+        if (!kvm->arch.hpt_virt) {
+                err = kvmppc_alloc_hpt(kvm, NULL);
+                if (err) {
+                        pr_err("KVM: Couldn't alloc HPT\n");
+                        goto out;
+                }
+        }
+
         /* Look up the memslot for guest physical address 0 */
         memslot = gfn_to_memslot(kvm, 0);
 
@@ -1435,13 +1451,14 @@ static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu)
 
 int kvmppc_core_init_vm(struct kvm *kvm)
 {
-        long r;
-        unsigned long lpcr;
+        unsigned long lpcr, lpid;
 
-        /* Allocate hashed page table */
-        r = kvmppc_alloc_hpt(kvm);
-        if (r)
-                return r;
+        /* Allocate the guest's logical partition ID */
+
+        lpid = kvmppc_alloc_lpid();
+        if (lpid < 0)
+                return -ENOMEM;
+        kvm->arch.lpid = lpid;
 
         INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
 
@@ -1451,7 +1468,6 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 
         if (cpu_has_feature(CPU_FTR_ARCH_201)) {
                 /* PPC970; HID4 is effectively the LPCR */
-                unsigned long lpid = kvm->arch.lpid;
                 kvm->arch.host_lpid = 0;
                 kvm->arch.host_lpcr = lpcr = mfspr(SPRN_HID4);
                 lpcr &= ~((3 << HID4_LPID1_SH) | (0xful << HID4_LPID5_SH));
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index e1b60f56f2a1..fb4eac290fef 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -25,6 +25,9 @@ static void __init kvm_linear_init_one(ulong size, int count, int type);
 static struct kvmppc_linear_info *kvm_alloc_linear(int type);
 static void kvm_release_linear(struct kvmppc_linear_info *ri);
 
+int kvm_hpt_order = KVM_DEFAULT_HPT_ORDER;
+EXPORT_SYMBOL_GPL(kvm_hpt_order);
+
 /*************** RMA *************/
 
 /*
@@ -209,7 +212,7 @@ static void kvm_release_linear(struct kvmppc_linear_info *ri)
 void __init kvm_linear_init(void)
 {
         /* HPT */
-        kvm_linear_init_one(1 << HPT_ORDER, kvm_hpt_count, KVM_LINEAR_HPT);
+        kvm_linear_init_one(1 << kvm_hpt_order, kvm_hpt_count, KVM_LINEAR_HPT);
 
         /* RMA */
         /* Only do this on PPC970 in HV mode */
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index cec4daddbf31..5c70d19494f9 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -237,7 +237,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 
         /* Find and lock the HPTEG slot to use */
  do_insert:
-        if (pte_index >= HPT_NPTE)
+        if (pte_index >= kvm->arch.hpt_npte)
                 return H_PARAMETER;
         if (likely((flags & H_EXACT) == 0)) {
                 pte_index &= ~7UL;
@@ -352,7 +352,7 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
         unsigned long v, r, rb;
         struct revmap_entry *rev;
 
-        if (pte_index >= HPT_NPTE)
+        if (pte_index >= kvm->arch.hpt_npte)
                 return H_PARAMETER;
         hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
         while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
@@ -419,7 +419,8 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
                                 i = 4;
                                 break;
                         }
-                        if (req != 1 || flags == 3 || pte_index >= HPT_NPTE) {
+                        if (req != 1 || flags == 3 ||
+                            pte_index >= kvm->arch.hpt_npte) {
                                 /* parameter error */
                                 args[j] = ((0xa0 | flags) << 56) + pte_index;
                                 ret = H_PARAMETER;
@@ -521,7 +522,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
         struct revmap_entry *rev;
         unsigned long v, r, rb, mask, bits;
 
-        if (pte_index >= HPT_NPTE)
+        if (pte_index >= kvm->arch.hpt_npte)
                 return H_PARAMETER;
 
         hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
@@ -583,7 +584,7 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
         int i, n = 1;
         struct revmap_entry *rev = NULL;
 
-        if (pte_index >= HPT_NPTE)
+        if (pte_index >= kvm->arch.hpt_npte)
                 return H_PARAMETER;
         if (flags & H_READ_4) {
                 pte_index &= ~3;
@@ -678,7 +679,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
                 somask = (1UL << 28) - 1;
                 vsid = (slb_v & ~SLB_VSID_B) >> SLB_VSID_SHIFT;
         }
-        hash = (vsid ^ ((eaddr & somask) >> pshift)) & HPT_HASH_MASK;
+        hash = (vsid ^ ((eaddr & somask) >> pshift)) & kvm->arch.hpt_mask;
         avpn = slb_v & ~(somask >> 16); /* also includes B */
         avpn |= (eaddr & somask) >> 16;
 
@@ -723,7 +724,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
                 if (val & HPTE_V_SECONDARY)
                         break;
                 val |= HPTE_V_SECONDARY;
-                hash = hash ^ HPT_HASH_MASK;
+                hash = hash ^ kvm->arch.hpt_mask;
         }
         return -1;
 }
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 72f13f4a06e0..86681eec60b1 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1267,6 +1267,11 @@ void kvmppc_decrementer_func(unsigned long data)
 {
         struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
 
+        if (vcpu->arch.tcr & TCR_ARE) {
+                vcpu->arch.dec = vcpu->arch.decar;
+                kvmppc_emulate_dec(vcpu);
+        }
+
         kvmppc_set_tsr_bits(vcpu, TSR_DIS);
 }
 
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index 6c76397f2af4..9eb9809eb13e 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -129,6 +129,9 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
                 kvmppc_set_tcr(vcpu, spr_val);
                 break;
 
+        case SPRN_DECAR:
+                vcpu->arch.decar = spr_val;
+                break;
         /*
          * Note: SPRG4-7 are user-readable.
          * These values are loaded into the real SPRGs when resuming the
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index 8b99e076dc81..e04b0ef55ce0 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -269,6 +269,9 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
                 *spr_val = vcpu->arch.shared->mas7_3 >> 32;
                 break;
 #endif
+        case SPRN_DECAR:
+                *spr_val = vcpu->arch.decar;
+                break;
         case SPRN_TLB0CFG:
                 *spr_val = vcpu->arch.tlbcfg[0];
                 break;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 1493c8de947b..87f4dc886076 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -246,6 +246,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 #endif
 #ifdef CONFIG_PPC_BOOK3S_64
         case KVM_CAP_SPAPR_TCE:
+        case KVM_CAP_PPC_ALLOC_HTAB:
                 r = 1;
                 break;
 #endif /* CONFIG_PPC_BOOK3S_64 */
@@ -802,6 +803,23 @@ long kvm_arch_vm_ioctl(struct file *filp,
                         r = -EFAULT;
                 break;
         }
+
+        case KVM_PPC_ALLOCATE_HTAB: {
+                struct kvm *kvm = filp->private_data;
+                u32 htab_order;
+
+                r = -EFAULT;
+                if (get_user(htab_order, (u32 __user *)argp))
+                        break;
+                r = kvmppc_alloc_reset_hpt(kvm, &htab_order);
+                if (r)
+                        break;
+                r = -EFAULT;
+                if (put_user(htab_order, (u32 __user *)argp))
+                        break;
+                r = 0;
+                break;
+        }
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 
 #ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index a35ca44ade66..e7a896acd982 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -25,6 +25,7 @@ source "arch/powerpc/platforms/wsp/Kconfig"
 config KVM_GUEST
         bool "KVM Guest support"
         default n
+        select EPAPR_PARAVIRT
         ---help---
           This option enables various optimizations for running under the KVM
           hypervisor. Overhead for the kernel when not running inside KVM should
@@ -32,6 +33,14 @@ config KVM_GUEST
 
           In case of doubt, say Y
 
+config EPAPR_PARAVIRT
+        bool "ePAPR para-virtualization support"
+        default n
+        help
+          Enables ePAPR para-virtualization support for guests.
+
+          In case of doubt, say Y
+
 config PPC_NATIVE
         bool
         depends on 6xx || PPC64