Merge tag 'kvm-3.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Avi Kivity:
 "Highlights include
  - full big real mode emulation on pre-Westmere Intel hosts (can be
    disabled with emulate_invalid_guest_state=0)
  - relatively small ppc and s390 updates
  - PCID/INVPCID support in guests
  - EOI avoidance; 3.6 guests should perform better on 3.6 hosts on
    interrupt intensive workloads)
  - Lockless write faults during live migration
  - EPT accessed/dirty bits support for new Intel processors"

Fix up conflicts in:
 - Documentation/virtual/kvm/api.txt:

   Stupid subchapter numbering, added next to each other.

 - arch/powerpc/kvm/booke_interrupts.S:

   PPC asm changes clashing with the KVM fixes

 - arch/s390/include/asm/sigp.h, arch/s390/kvm/sigp.c:

   Duplicated commits through the kvm tree and the s390 tree, with
   subsequent edits in the KVM tree.

* tag 'kvm-3.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (93 commits)
  KVM: fix race with level interrupts
  x86, hyper: fix build with !CONFIG_KVM_GUEST
  Revert "apic: fix kvm build on UP without IOAPIC"
  KVM guest: switch to apic_set_eoi_write, apic_write
  apic: add apic_set_eoi_write for PV use
  KVM: VMX: Implement PCID/INVPCID for guests with EPT
  KVM: Add x86_hyper_kvm to complete detect_hypervisor_platform check
  KVM: PPC: Critical interrupt emulation support
  KVM: PPC: e500mc: Fix tlbilx emulation for 64-bit guests
  KVM: PPC64: booke: Set interrupt computation mode for 64-bit host
  KVM: PPC: bookehv: Add ESR flag to Data Storage Interrupt
  KVM: PPC: bookehv64: Add support for std/ld emulation.
  booke: Added crit/mc exception handler for e500v2
  booke/bookehv: Add host crit-watchdog exception support
  KVM: MMU: document mmu-lock and fast page fault
  KVM: MMU: fix kvm_mmu_pagetable_walk tracepoint
  KVM: MMU: trace fast page fault
  KVM: MMU: fast path of handling guest page fault
  KVM: MMU: introduce SPTE_MMU_WRITEABLE bit
  KVM: MMU: fold tlb flush judgement into mmu_spte_update
  ...

Documentation/virtual/kvm/api.txt

@@ -1946,6 +1946,40 @@ the guest using the specified gsi pin.  The irqfd is removed using
 the KVM_IRQFD_FLAG_DEASSIGN flag, specifying both kvm_irqfd.fd
 and kvm_irqfd.gsi.
 
+4.76 KVM_PPC_ALLOCATE_HTAB
+
+Capability: KVM_CAP_PPC_ALLOC_HTAB
+Architectures: powerpc
+Type: vm ioctl
+Parameters: Pointer to u32 containing hash table order (in/out)
+Returns: 0 on success, -1 on error
+
+This requests the host kernel to allocate an MMU hash table for a
+guest using the PAPR paravirtualization interface.  This only does
+anything if the kernel is configured to use the Book 3S HV style of
+virtualization.  Otherwise the capability doesn't exist and the ioctl
+returns an ENOTTY error.  The rest of this description assumes Book 3S
+HV.
+
+There must be no vcpus running when this ioctl is called; if there
+are, it will do nothing and return an EBUSY error.
+
+The parameter is a pointer to a 32-bit unsigned integer variable
+containing the order (log base 2) of the desired size of the hash
+table, which must be between 18 and 46.  On successful return from the
+ioctl, it will have been updated with the order of the hash table that
+was allocated.
+
+If no hash table has been allocated when any vcpu is asked to run
+(with the KVM_RUN ioctl), the host kernel will allocate a
+default-sized hash table (16 MB).
+
+If this ioctl is called when a hash table has already been allocated,
+the kernel will clear out the existing hash table (zero all HPTEs) and
+return the hash table order in the parameter.  (If the guest is using
+the virtualized real-mode area (VRMA) facility, the kernel will
+re-create the VMRA HPTEs on the next KVM_RUN of any vcpu.)
+
 
 5. The kvm_run structure
 ------------------------

Documentation/virtual/kvm/locking.txt

@@ -6,7 +6,129 @@ KVM Lock Overview
 
 (to be written)
 
-2. Reference
+2: Exception
+------------
+
+Fast page fault:
+
+Fast page fault is the fast path which fixes the guest page fault out of
+the mmu-lock on x86. Currently, the page fault can be fast only if the
+shadow page table is present and it is caused by write-protect, that means
+we just need change the W bit of the spte.
+
+What we use to avoid all the race is the SPTE_HOST_WRITEABLE bit and
+SPTE_MMU_WRITEABLE bit on the spte:
+- SPTE_HOST_WRITEABLE means the gfn is writable on host.
+- SPTE_MMU_WRITEABLE means the gfn is writable on mmu. The bit is set when
+  the gfn is writable on guest mmu and it is not write-protected by shadow
+  page write-protection.
+
+On fast page fault path, we will use cmpxchg to atomically set the spte W
+bit if spte.SPTE_HOST_WRITEABLE = 1 and spte.SPTE_WRITE_PROTECT = 1, this
+is safe because whenever changing these bits can be detected by cmpxchg.
+
+But we need carefully check these cases:
+1): The mapping from gfn to pfn
+The mapping from gfn to pfn may be changed since we can only ensure the pfn
+is not changed during cmpxchg. This is a ABA problem, for example, below case
+will happen:
+
+At the beginning:
+gpte = gfn1
+gfn1 is mapped to pfn1 on host
+spte is the shadow page table entry corresponding with gpte and
+spte = pfn1
+
+   VCPU 0                           VCPU0
+on fast page fault path:
+
+   old_spte = *spte;
+                                 pfn1 is swapped out:
+                                    spte = 0;
+
+                                 pfn1 is re-alloced for gfn2.
+
+                                 gpte is changed to point to
+                                 gfn2 by the guest:
+                                    spte = pfn1;
+
+   if (cmpxchg(spte, old_spte, old_spte+W)
+	mark_page_dirty(vcpu->kvm, gfn1)
+             OOPS!!!
+
+We dirty-log for gfn1, that means gfn2 is lost in dirty-bitmap.
+
+For direct sp, we can easily avoid it since the spte of direct sp is fixed
+to gfn. For indirect sp, before we do cmpxchg, we call gfn_to_pfn_atomic()
+to pin gfn to pfn, because after gfn_to_pfn_atomic():
+- We have held the refcount of pfn that means the pfn can not be freed and
+  be reused for another gfn.
+- The pfn is writable that means it can not be shared between different gfns
+  by KSM.
+
+Then, we can ensure the dirty bitmaps is correctly set for a gfn.
+
+Currently, to simplify the whole things, we disable fast page fault for
+indirect shadow page.
+
+2): Dirty bit tracking
+In the origin code, the spte can be fast updated (non-atomically) if the
+spte is read-only and the Accessed bit has already been set since the
+Accessed bit and Dirty bit can not be lost.
+
+But it is not true after fast page fault since the spte can be marked
+writable between reading spte and updating spte. Like below case:
+
+At the beginning:
+spte.W = 0
+spte.Accessed = 1
+
+   VCPU 0                                       VCPU0
+In mmu_spte_clear_track_bits():
+
+   old_spte = *spte;
+
+   /* 'if' condition is satisfied. */
+   if (old_spte.Accssed == 1 &&
+        old_spte.W == 0)
+      spte = 0ull;
+                                         on fast page fault path:
+                                             spte.W = 1
+                                         memory write on the spte:
+                                             spte.Dirty = 1
+
+
+   else
+      old_spte = xchg(spte, 0ull)
+
+
+   if (old_spte.Accssed == 1)
+      kvm_set_pfn_accessed(spte.pfn);
+   if (old_spte.Dirty == 1)
+      kvm_set_pfn_dirty(spte.pfn);
+      OOPS!!!
+
+The Dirty bit is lost in this case.
+
+In order to avoid this kind of issue, we always treat the spte as "volatile"
+if it can be updated out of mmu-lock, see spte_has_volatile_bits(), it means,
+the spte is always atomicly updated in this case.
+
+3): flush tlbs due to spte updated
+If the spte is updated from writable to readonly, we should flush all TLBs,
+otherwise rmap_write_protect will find a read-only spte, even though the
+writable spte might be cached on a CPU's TLB.
+
+As mentioned before, the spte can be updated to writable out of mmu-lock on
+fast page fault path, in order to easily audit the path, we see if TLBs need
+be flushed caused by this reason in mmu_spte_update() since this is a common
+function to update spte (present -> present).
+
+Since the spte is "volatile" if it can be updated out of mmu-lock, we always
+atomicly update the spte, the race caused by fast page fault can be avoided,
+See the comments in spte_has_volatile_bits() and mmu_spte_update().
+
+3. Reference
 ------------
 
 Name:		kvm_lock
@@ -23,3 +145,9 @@ Arch:		x86
 Protects:	- kvm_arch::{last_tsc_write,last_tsc_nsec,last_tsc_offset}
 		- tsc offset in vmcb
 Comment:	'raw' because updating the tsc offsets must not be preempted.
+
+Name:		kvm->mmu_lock
+Type:		spinlock_t
+Arch:		any
+Protects:	-shadow page/shadow tlb entry
+Comment:	it is a spinlock since it is used in mmu notifier.

Documentation/virtual/kvm/msr.txt

@@ -223,3 +223,36 @@ MSR_KVM_STEAL_TIME: 0x4b564d03
 		steal: the amount of time in which this vCPU did not run, in
 		nanoseconds. Time during which the vcpu is idle, will not be
 		reported as steal time.
+
+MSR_KVM_EOI_EN: 0x4b564d04
+	data: Bit 0 is 1 when PV end of interrupt is enabled on the vcpu; 0
+	when disabled.  Bit 1 is reserved and must be zero.  When PV end of
+	interrupt is enabled (bit 0 set), bits 63-2 hold a 4-byte aligned
+	physical address of a 4 byte memory area which must be in guest RAM and
+	must be zeroed.
+
+	The first, least significant bit of 4 byte memory location will be
+	written to by the hypervisor, typically at the time of interrupt
+	injection.  Value of 1 means that guest can skip writing EOI to the apic
+	(using MSR or MMIO write); instead, it is sufficient to signal
+	EOI by clearing the bit in guest memory - this location will
+	later be polled by the hypervisor.
+	Value of 0 means that the EOI write is required.
+
+	It is always safe for the guest to ignore the optimization and perform
+	the APIC EOI write anyway.
+
+	Hypervisor is guaranteed to only modify this least
+	significant bit while in the current VCPU context, this means that
+	guest does not need to use either lock prefix or memory ordering
+	primitives to synchronise with the hypervisor.
+
+	However, hypervisor can set and clear this memory bit at any time:
+	therefore to make sure hypervisor does not interrupt the
+	guest and clear the least significant bit in the memory area
+	in the window between guest testing it to detect
+	whether it can skip EOI apic write and between guest
+	clearing it to signal EOI to the hypervisor,
+	guest must both read the least significant bit in the memory area and
+	clear it using a single CPU instruction, such as test and clear, or
+	compare and exchange.

Documentation/virtual/kvm/ppc-pv.txt

@@ -109,8 +109,6 @@ The following bits are safe to be set inside the guest:
 
   MSR_EE
   MSR_RI
-  MSR_CR
-  MSR_ME
 
 If any other bit changes in the MSR, please still use mtmsr(d).
 

MAINTAINERS

@@ -4002,8 +4002,8 @@ F:	arch/ia64/include/asm/kvm*
 F:	arch/ia64/kvm/
 
 KERNEL VIRTUAL MACHINE for s390 (KVM/s390)
-M:	Carsten Otte <cotte@de.ibm.com>
 M:	Christian Borntraeger <borntraeger@de.ibm.com>
+M:	Cornelia Huck <cornelia.huck@de.ibm.com>
 M:	linux390@de.ibm.com
 L:	linux-s390@vger.kernel.org
 W:	http://www.ibm.com/developerworks/linux/linux390/

arch/ia64/include/asm/kvm.h

@@ -26,6 +26,7 @@
 
 /* Select x86 specific features in <linux/kvm.h> */
 #define __KVM_HAVE_IOAPIC
+#define __KVM_HAVE_IRQ_LINE
 #define __KVM_HAVE_DEVICE_ASSIGNMENT
 
 /* Architectural interrupt line count. */

arch/ia64/kvm/Kconfig

@@ -19,6 +19,7 @@ if VIRTUALIZATION
 
 config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support"
+	depends on BROKEN
 	depends on HAVE_KVM && MODULES && EXPERIMENTAL
 	# for device assignment:
 	depends on PCI

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

arch/powerpc/include/asm/hw_irq.h

@@ -34,6 +34,8 @@ extern void __replay_interrupt(unsigned int vector);
 
 extern void timer_interrupt(struct pt_regs *);
 extern void performance_monitor_exception(struct pt_regs *regs);
+extern void WatchdogException(struct pt_regs *regs);
+extern void unknown_exception(struct pt_regs *regs);
 
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>

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 */

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;

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);

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

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

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);

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))

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

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

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)
 {
@@ -1104,11 +1104,15 @@ 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);
@@ -1126,6 +1130,9 @@ 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;
 }
 
@@ -1341,7 +1348,7 @@ 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;
@@ -1360,6 +1367,15 @@ 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);
 
@@ -1471,13 +1487,14 @@ 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);
 
@@ -1487,7 +1504,6 @@ 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));

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 */