From 519192aaae38e24d6b32d3d55d791fe294981185 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@linux.vnet.ibm.com>
Date: Mon, 9 Sep 2013 17:32:56 +0200
Subject: KVM: Add documentation for kvm->srcu lock

This patch documents the kvm->srcu lock (using the information from
a mail which has been posted by Marcelo Tosatti to the kvm mailing
list some months ago, see the following URL for details:
http://www.mail-archive.com/kvm@vger.kernel.org/msg90040.html )

Signed-off-by: Thomas Huth <thuth@linux.vnet.ibm.com>
Reviewed-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/locking.txt | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/locking.txt b/Documentation/virtual/kvm/locking.txt
index 41b7ac9884b5..a9f366e73c8e 100644
--- a/Documentation/virtual/kvm/locking.txt
+++ b/Documentation/virtual/kvm/locking.txt
@@ -151,3 +151,14 @@ Type:		spinlock_t
 Arch:		any
 Protects:	-shadow page/shadow tlb entry
 Comment:	it is a spinlock since it is used in mmu notifier.
+
+Name:		kvm->srcu
+Type:		srcu lock
+Arch:		any
+Protects:	- kvm->memslots
+		- kvm->buses
+Comment:	The srcu read lock must be held while accessing memslots (e.g.
+		when using gfn_to_* functions) and while accessing in-kernel
+		MMIO/PIO address->device structure mapping (kvm->buses).
+		The srcu index can be stored in kvm_vcpu->srcu_idx per vcpu
+		if it is needed by multiple functions.
-- 
cgit v1.2.3


From 56aba608257b451f663d25313d5ecae134d5557f Mon Sep 17 00:00:00 2001
From: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Date: Thu, 12 Sep 2013 13:00:11 +0530
Subject: Documentation/kvm: Update cpuid documentation for steal time and pv
 eoi

Thanks Michael S Tsirkin for rewriting the description and suggestions.

Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 Documentation/virtual/kvm/cpuid.txt | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt
index 22ff659bc0fb..3c65feb83010 100644
--- a/Documentation/virtual/kvm/cpuid.txt
+++ b/Documentation/virtual/kvm/cpuid.txt
@@ -43,6 +43,13 @@ KVM_FEATURE_CLOCKSOURCE2           ||     3 || kvmclock available at msrs
 KVM_FEATURE_ASYNC_PF               ||     4 || async pf can be enabled by
                                    ||       || writing to msr 0x4b564d02
 ------------------------------------------------------------------------------
+KVM_FEATURE_STEAL_TIME             ||     5 || steal time can be enabled by
+                                   ||       || writing to msr 0x4b564d03.
+------------------------------------------------------------------------------
+KVM_FEATURE_PV_EOI                 ||     6 || paravirtualized end of interrupt
+                                   ||       || handler can be enabled by writing
+                                   ||       || to msr 0x4b564d04.
+------------------------------------------------------------------------------
 KVM_FEATURE_PV_UNHALT              ||     7 || guest checks this feature bit
                                    ||       || before enabling paravirtualized
                                    ||       || spinlock support.
-- 
cgit v1.2.3


From 4a937f96f3a29c58b7edd349d2e4dfac371efdf2 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Tue, 10 Sep 2013 12:58:35 +0200
Subject: KVM: protect kvm_usage_count with its own spinlock

The VM list need not be protected by a raw spinlock.  Separate the
two so that kvm_lock can be made non-raw.

Cc: kvm@vger.kernel.org
Cc: gleb@redhat.com
Cc: jan.kiszka@siemens.com
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/locking.txt |  6 +++++-
 virt/kvm/kvm_main.c                   | 19 ++++++++++---------
 2 files changed, 15 insertions(+), 10 deletions(-)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/locking.txt b/Documentation/virtual/kvm/locking.txt
index a9f366e73c8e..ba9e1c2150c2 100644
--- a/Documentation/virtual/kvm/locking.txt
+++ b/Documentation/virtual/kvm/locking.txt
@@ -135,7 +135,11 @@ Name:		kvm_lock
 Type:		raw_spinlock
 Arch:		any
 Protects:	- vm_list
-		- hardware virtualization enable/disable
+
+Name:		kvm_count_lock
+Type:		raw_spinlock_t
+Arch:		any
+Protects:	- hardware virtualization enable/disable
 Comment:	'raw' because hardware enabling/disabling must be atomic /wrt
 		migration.
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 426051d66173..eb94343c2ed2 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -71,6 +71,7 @@ MODULE_LICENSE("GPL");
  */
 
 DEFINE_RAW_SPINLOCK(kvm_lock);
+static DEFINE_RAW_SPINLOCK(kvm_count_lock);
 LIST_HEAD(vm_list);
 
 static cpumask_var_t cpus_hardware_enabled;
@@ -2683,10 +2684,10 @@ static void hardware_enable_nolock(void *junk)
 
 static void hardware_enable(void)
 {
-	raw_spin_lock(&kvm_lock);
+	raw_spin_lock(&kvm_count_lock);
 	if (kvm_usage_count)
 		hardware_enable_nolock(NULL);
-	raw_spin_unlock(&kvm_lock);
+	raw_spin_unlock(&kvm_count_lock);
 }
 
 static void hardware_disable_nolock(void *junk)
@@ -2701,10 +2702,10 @@ static void hardware_disable_nolock(void *junk)
 
 static void hardware_disable(void)
 {
-	raw_spin_lock(&kvm_lock);
+	raw_spin_lock(&kvm_count_lock);
 	if (kvm_usage_count)
 		hardware_disable_nolock(NULL);
-	raw_spin_unlock(&kvm_lock);
+	raw_spin_unlock(&kvm_count_lock);
 }
 
 static void hardware_disable_all_nolock(void)
@@ -2718,16 +2719,16 @@ static void hardware_disable_all_nolock(void)
 
 static void hardware_disable_all(void)
 {
-	raw_spin_lock(&kvm_lock);
+	raw_spin_lock(&kvm_count_lock);
 	hardware_disable_all_nolock();
-	raw_spin_unlock(&kvm_lock);
+	raw_spin_unlock(&kvm_count_lock);
 }
 
 static int hardware_enable_all(void)
 {
 	int r = 0;
 
-	raw_spin_lock(&kvm_lock);
+	raw_spin_lock(&kvm_count_lock);
 
 	kvm_usage_count++;
 	if (kvm_usage_count == 1) {
@@ -2740,7 +2741,7 @@ static int hardware_enable_all(void)
 		}
 	}
 
-	raw_spin_unlock(&kvm_lock);
+	raw_spin_unlock(&kvm_count_lock);
 
 	return r;
 }
@@ -3130,7 +3131,7 @@ static int kvm_suspend(void)
 static void kvm_resume(void)
 {
 	if (kvm_usage_count) {
-		WARN_ON(raw_spin_is_locked(&kvm_lock));
+		WARN_ON(raw_spin_is_locked(&kvm_count_lock));
 		hardware_enable_nolock(NULL);
 	}
 }
-- 
cgit v1.2.3


From 2f303b74a62fb74983c0a66e2df353be963c527c Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 25 Sep 2013 13:53:07 +0200
Subject: KVM: Convert kvm_lock back to non-raw spinlock

In commit e935b8372cf8 ("KVM: Convert kvm_lock to raw_spinlock"),
the kvm_lock was made a raw lock.  However, the kvm mmu_shrink()
function tries to grab the (non-raw) mmu_lock within the scope of
the raw locked kvm_lock being held.  This leads to the following:

BUG: sleeping function called from invalid context at kernel/rtmutex.c:659
in_atomic(): 1, irqs_disabled(): 0, pid: 55, name: kswapd0
Preemption disabled at:[<ffffffffa0376eac>] mmu_shrink+0x5c/0x1b0 [kvm]

Pid: 55, comm: kswapd0 Not tainted 3.4.34_preempt-rt
Call Trace:
 [<ffffffff8106f2ad>] __might_sleep+0xfd/0x160
 [<ffffffff817d8d64>] rt_spin_lock+0x24/0x50
 [<ffffffffa0376f3c>] mmu_shrink+0xec/0x1b0 [kvm]
 [<ffffffff8111455d>] shrink_slab+0x17d/0x3a0
 [<ffffffff81151f00>] ? mem_cgroup_iter+0x130/0x260
 [<ffffffff8111824a>] balance_pgdat+0x54a/0x730
 [<ffffffff8111fe47>] ? set_pgdat_percpu_threshold+0xa7/0xd0
 [<ffffffff811185bf>] kswapd+0x18f/0x490
 [<ffffffff81070961>] ? get_parent_ip+0x11/0x50
 [<ffffffff81061970>] ? __init_waitqueue_head+0x50/0x50
 [<ffffffff81118430>] ? balance_pgdat+0x730/0x730
 [<ffffffff81060d2b>] kthread+0xdb/0xe0
 [<ffffffff8106e122>] ? finish_task_switch+0x52/0x100
 [<ffffffff817e1e94>] kernel_thread_helper+0x4/0x10
 [<ffffffff81060c50>] ? __init_kthread_worker+0x

After the previous patch, kvm_lock need not be a raw spinlock anymore,
so change it back.

Reported-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: kvm@vger.kernel.org
Cc: gleb@redhat.com
Cc: jan.kiszka@siemens.com
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/locking.txt |  2 +-
 arch/x86/kvm/mmu.c                    |  5 ++---
 arch/x86/kvm/x86.c                    |  8 ++++----
 include/linux/kvm_host.h              |  2 +-
 virt/kvm/kvm_main.c                   | 18 +++++++++---------
 5 files changed, 17 insertions(+), 18 deletions(-)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/locking.txt b/Documentation/virtual/kvm/locking.txt
index ba9e1c2150c2..f8869410d40c 100644
--- a/Documentation/virtual/kvm/locking.txt
+++ b/Documentation/virtual/kvm/locking.txt
@@ -132,7 +132,7 @@ See the comments in spte_has_volatile_bits() and mmu_spte_update().
 ------------
 
 Name:		kvm_lock
-Type:		raw_spinlock
+Type:		spinlock_t
 Arch:		any
 Protects:	- vm_list
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index dce0df8150df..cf95cfe050a6 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4428,7 +4428,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 	int nr_to_scan = sc->nr_to_scan;
 	unsigned long freed = 0;
 
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		int idx;
@@ -4478,9 +4478,8 @@ unlock:
 		break;
 	}
 
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 	return freed;
-
 }
 
 static unsigned long
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e5ca72a5cdb6..187f824b1454 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5263,7 +5263,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
 
 	smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1);
 
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			if (vcpu->cpu != freq->cpu)
@@ -5273,7 +5273,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
 				send_ipi = 1;
 		}
 	}
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 
 	if (freq->old < freq->new && send_ipi) {
 		/*
@@ -5426,12 +5426,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work)
 	struct kvm_vcpu *vcpu;
 	int i;
 
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		kvm_for_each_vcpu(i, vcpu, kvm)
 			set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests);
 	atomic_set(&kvm_guest_has_master_clock, 0);
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 }
 
 static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 749bdb12cd15..7c961e1e9270 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -142,7 +142,7 @@ struct kvm;
 struct kvm_vcpu;
 extern struct kmem_cache *kvm_vcpu_cache;
 
-extern raw_spinlock_t kvm_lock;
+extern spinlock_t kvm_lock;
 extern struct list_head vm_list;
 
 struct kvm_io_range {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index eb94343c2ed2..d469114aff09 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -70,7 +70,7 @@ MODULE_LICENSE("GPL");
  * 		kvm->lock --> kvm->slots_lock --> kvm->irq_lock
  */
 
-DEFINE_RAW_SPINLOCK(kvm_lock);
+DEFINE_SPINLOCK(kvm_lock);
 static DEFINE_RAW_SPINLOCK(kvm_count_lock);
 LIST_HEAD(vm_list);
 
@@ -491,9 +491,9 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	if (r)
 		goto out_err;
 
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 
 	return kvm;
 
@@ -582,9 +582,9 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	struct mm_struct *mm = kvm->mm;
 
 	kvm_arch_sync_events(kvm);
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_del(&kvm->vm_list);
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 	kvm_free_irq_routing(kvm);
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kvm_io_bus_destroy(kvm->buses[i]);
@@ -3054,10 +3054,10 @@ static int vm_stat_get(void *_offset, u64 *val)
 	struct kvm *kvm;
 
 	*val = 0;
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		*val += *(u32 *)((void *)kvm + offset);
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 	return 0;
 }
 
@@ -3071,12 +3071,12 @@ static int vcpu_stat_get(void *_offset, u64 *val)
 	int i;
 
 	*val = 0;
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		kvm_for_each_vcpu(i, vcpu, kvm)
 			*val += *(u32 *)((void *)vcpu + offset);
 
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 740edfc0a35dd688c97ae8907c4377df49219bf3 Mon Sep 17 00:00:00 2001
From: Anup Patel <anup.patel@linaro.org>
Date: Mon, 30 Sep 2013 14:20:08 +0530
Subject: KVM: Add documentation for KVM_ARM_PREFERRED_TARGET ioctl

To implement CPU=Host we have added KVM_ARM_PREFERRED_TARGET
vm ioctl which provides information to user space required for
creating VCPU matching underlying Host.

This patch adds info related to this new KVM_ARM_PREFERRED_TARGET
vm ioctl in the KVM API documentation.

Signed-off-by: Anup Patel <anup.patel@linaro.org>
Signed-off-by: Pranavkumar Sawargaonkar <pranavkumar@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
---
 Documentation/virtual/kvm/api.txt | 31 +++++++++++++++++++++++++++----
 1 file changed, 27 insertions(+), 4 deletions(-)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 858aecf21db2..076b8492d810 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2304,7 +2304,31 @@ Possible features:
 	  Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
 
 
-4.83 KVM_GET_REG_LIST
+4.83 KVM_ARM_PREFERRED_TARGET
+
+Capability: basic
+Architectures: arm, arm64
+Type: vm ioctl
+Parameters: struct struct kvm_vcpu_init (out)
+Returns: 0 on success; -1 on error
+Errors:
+  ENODEV:    no preferred target available for the host
+
+This queries KVM for preferred CPU target type which can be emulated
+by KVM on underlying host.
+
+The ioctl returns struct kvm_vcpu_init instance containing information
+about preferred CPU target type and recommended features for it.  The
+kvm_vcpu_init->features bitmap returned will have feature bits set if
+the preferred target recommends setting these features, but this is
+not mandatory.
+
+The information returned by this ioctl can be used to prepare an instance
+of struct kvm_vcpu_init for KVM_ARM_VCPU_INIT ioctl which will result in
+in VCPU matching underlying host.
+
+
+4.84 KVM_GET_REG_LIST
 
 Capability: basic
 Architectures: arm, arm64
@@ -2323,8 +2347,7 @@ struct kvm_reg_list {
 This ioctl returns the guest registers that are supported for the
 KVM_GET_ONE_REG/KVM_SET_ONE_REG calls.
 
-
-4.84 KVM_ARM_SET_DEVICE_ADDR
+4.85 KVM_ARM_SET_DEVICE_ADDR
 
 Capability: KVM_CAP_ARM_SET_DEVICE_ADDR
 Architectures: arm, arm64
@@ -2362,7 +2385,7 @@ must be called after calling KVM_CREATE_IRQCHIP, but before calling
 KVM_RUN on any of the VCPUs.  Calling this ioctl twice for any of the
 base addresses will return -EEXIST.
 
-4.85 KVM_PPC_RTAS_DEFINE_TOKEN
+4.86 KVM_PPC_RTAS_DEFINE_TOKEN
 
 Capability: KVM_CAP_PPC_RTAS
 Architectures: ppc
-- 
cgit v1.2.3


From a7265fb1751ffbfad553afc7f592a6dac6be48de Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@linaro.org>
Date: Tue, 15 Oct 2013 17:43:00 -0700
Subject: KVM: ARM: Remove non-ASCII space characters

Some strange character leaped into the documentation, which makes
git-send-email behave quite strangely.  Get rid of this before it bites
anyone else.

Cc: Anup Patel <anup.patel@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
---
 Documentation/virtual/kvm/api.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 076b8492d810..a89a5ee0b940 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2312,7 +2312,7 @@ Type: vm ioctl
 Parameters: struct struct kvm_vcpu_init (out)
 Returns: 0 on success; -1 on error
 Errors:
-  ENODEV:    no preferred target available for the host
+  ENODEV:    no preferred target available for the host
 
 This queries KVM for preferred CPU target type which can be emulated
 by KVM on underlying host.
-- 
cgit v1.2.3


From 3b7834743f9492e3509930feb4ca47135905e640 Mon Sep 17 00:00:00 2001
From: Michael Neuling <mikey@neuling.org>
Date: Tue, 3 Sep 2013 11:13:12 +1000
Subject: KVM: PPC: Book3S HV: Reserve POWER8 space in get/set_one_reg

This reserves space in get/set_one_reg ioctl for the extra guest state
needed for POWER8.  It doesn't implement these at all, it just reserves
them so that the ABI is defined now.

A few things to note here:

- This add *a lot* state for transactional memory.  TM suspend mode,
  this is unavoidable, you can't simply roll back all transactions and
  store only the checkpointed state.  I've added this all to
  get/set_one_reg (including GPRs) rather than creating a new ioctl
  which returns a struct kvm_regs like KVM_GET_REGS does.  This means we
  if we need to extract the TM state, we are going to need a bucket load
  of IOCTLs.  Hopefully most of the time this will not be needed as we
  can look at the MSR to see if TM is active and only grab them when
  needed.  If this becomes a bottle neck in future we can add another
  ioctl to grab all this state in one go.

- The TM state is offset by 0x80000000.

- For TM, I've done away with VMX and FP and created a single 64x128 bit
  VSX register space.

- I've left a space of 1 (at 0x9c) since Paulus needs to add a value
  which applies to POWER7 as well.

Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt   | 39 +++++++++++++++++++++++++++
 arch/powerpc/include/uapi/asm/kvm.h | 54 +++++++++++++++++++++++++++++++++++++
 2 files changed, 93 insertions(+)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index a89a5ee0b940..354a51ba456b 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1810,6 +1810,45 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_TLB3PS	| 32
   PPC   | KVM_REG_PPC_EPTCFG	| 32
   PPC   | KVM_REG_PPC_ICP_STATE | 64
+  PPC   | KVM_REG_PPC_SPMC1	| 32
+  PPC   | KVM_REG_PPC_SPMC2	| 32
+  PPC   | KVM_REG_PPC_IAMR	| 64
+  PPC   | KVM_REG_PPC_TFHAR	| 64
+  PPC   | KVM_REG_PPC_TFIAR	| 64
+  PPC   | KVM_REG_PPC_TEXASR	| 64
+  PPC   | KVM_REG_PPC_FSCR	| 64
+  PPC   | KVM_REG_PPC_PSPB	| 32
+  PPC   | KVM_REG_PPC_EBBHR	| 64
+  PPC   | KVM_REG_PPC_EBBRR	| 64
+  PPC   | KVM_REG_PPC_BESCR	| 64
+  PPC   | KVM_REG_PPC_TAR	| 64
+  PPC   | KVM_REG_PPC_DPDES	| 64
+  PPC   | KVM_REG_PPC_DAWR	| 64
+  PPC   | KVM_REG_PPC_DAWRX	| 64
+  PPC   | KVM_REG_PPC_CIABR	| 64
+  PPC   | KVM_REG_PPC_IC	| 64
+  PPC   | KVM_REG_PPC_VTB	| 64
+  PPC   | KVM_REG_PPC_CSIGR	| 64
+  PPC   | KVM_REG_PPC_TACR	| 64
+  PPC   | KVM_REG_PPC_TCSCR	| 64
+  PPC   | KVM_REG_PPC_PID	| 64
+  PPC   | KVM_REG_PPC_ACOP	| 64
+  PPC   | KVM_REG_PPC_TM_GPR0	| 64
+          ...
+  PPC   | KVM_REG_PPC_TM_GPR31	| 64
+  PPC   | KVM_REG_PPC_TM_VSR0	| 128
+          ...
+  PPC   | KVM_REG_PPC_TM_VSR63	| 128
+  PPC   | KVM_REG_PPC_TM_CR	| 64
+  PPC   | KVM_REG_PPC_TM_LR	| 64
+  PPC   | KVM_REG_PPC_TM_CTR	| 64
+  PPC   | KVM_REG_PPC_TM_FPSCR	| 64
+  PPC   | KVM_REG_PPC_TM_AMR	| 64
+  PPC   | KVM_REG_PPC_TM_PPR	| 64
+  PPC   | KVM_REG_PPC_TM_VRSAVE	| 64
+  PPC   | KVM_REG_PPC_TM_VSCR	| 32
+  PPC   | KVM_REG_PPC_TM_DSCR	| 64
+  PPC   | KVM_REG_PPC_TM_TAR	| 64
 
 ARM registers are mapped using the lower 32 bits.  The upper 16 of that
 is the register group type, or coprocessor number:
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 0fb1a6e9ff90..7ed41c0b4045 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -429,6 +429,11 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_MMCR0	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x10)
 #define KVM_REG_PPC_MMCR1	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x11)
 #define KVM_REG_PPC_MMCRA	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x12)
+#define KVM_REG_PPC_MMCR2	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x13)
+#define KVM_REG_PPC_MMCRS	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x14)
+#define KVM_REG_PPC_SIAR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x15)
+#define KVM_REG_PPC_SDAR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x16)
+#define KVM_REG_PPC_SIER	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x17)
 
 #define KVM_REG_PPC_PMC1	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x18)
 #define KVM_REG_PPC_PMC2	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x19)
@@ -499,6 +504,55 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_TLB3PS	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9a)
 #define KVM_REG_PPC_EPTCFG	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9b)
 
+/* POWER8 registers */
+#define KVM_REG_PPC_SPMC1	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9d)
+#define KVM_REG_PPC_SPMC2	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9e)
+#define KVM_REG_PPC_IAMR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9f)
+#define KVM_REG_PPC_TFHAR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa0)
+#define KVM_REG_PPC_TFIAR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa1)
+#define KVM_REG_PPC_TEXASR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa2)
+#define KVM_REG_PPC_FSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa3)
+#define KVM_REG_PPC_PSPB	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xa4)
+#define KVM_REG_PPC_EBBHR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa5)
+#define KVM_REG_PPC_EBBRR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa6)
+#define KVM_REG_PPC_BESCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa7)
+#define KVM_REG_PPC_TAR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa8)
+#define KVM_REG_PPC_DPDES	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa9)
+#define KVM_REG_PPC_DAWR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xaa)
+#define KVM_REG_PPC_DAWRX	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xab)
+#define KVM_REG_PPC_CIABR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xac)
+#define KVM_REG_PPC_IC		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xad)
+#define KVM_REG_PPC_VTB		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xae)
+#define KVM_REG_PPC_CSIGR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xaf)
+#define KVM_REG_PPC_TACR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb0)
+#define KVM_REG_PPC_TCSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb1)
+#define KVM_REG_PPC_PID		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb2)
+#define KVM_REG_PPC_ACOP	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb3)
+
+/* Transactional Memory checkpointed state:
+ * This is all GPRs, all VSX regs and a subset of SPRs
+ */
+#define KVM_REG_PPC_TM		(KVM_REG_PPC | 0x80000000)
+/* TM GPRs */
+#define KVM_REG_PPC_TM_GPR0	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0)
+#define KVM_REG_PPC_TM_GPR(n)	(KVM_REG_PPC_TM_GPR0 + (n))
+#define KVM_REG_PPC_TM_GPR31	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x1f)
+/* TM VSX */
+#define KVM_REG_PPC_TM_VSR0	(KVM_REG_PPC_TM | KVM_REG_SIZE_U128 | 0x20)
+#define KVM_REG_PPC_TM_VSR(n)	(KVM_REG_PPC_TM_VSR0 + (n))
+#define KVM_REG_PPC_TM_VSR63	(KVM_REG_PPC_TM | KVM_REG_SIZE_U128 | 0x5f)
+/* TM SPRS */
+#define KVM_REG_PPC_TM_CR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x60)
+#define KVM_REG_PPC_TM_LR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x61)
+#define KVM_REG_PPC_TM_CTR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x62)
+#define KVM_REG_PPC_TM_FPSCR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x63)
+#define KVM_REG_PPC_TM_AMR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x64)
+#define KVM_REG_PPC_TM_PPR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x65)
+#define KVM_REG_PPC_TM_VRSAVE	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x66)
+#define KVM_REG_PPC_TM_VSCR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67)
+#define KVM_REG_PPC_TM_DSCR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68)
+#define KVM_REG_PPC_TM_TAR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69)
+
 /* PPC64 eXternal Interrupt Controller Specification */
 #define KVM_DEV_XICS_GRP_SOURCES	1	/* 64-bit source attributes */
 
-- 
cgit v1.2.3


From 93b0f4dc29c5f077a1c97bd1d484147230c3779a Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 6 Sep 2013 13:17:46 +1000
Subject: KVM: PPC: Book3S HV: Implement timebase offset for guests

This allows guests to have a different timebase origin from the host.
This is needed for migration, where a guest can migrate from one host
to another and the two hosts might have a different timebase origin.
However, the timebase seen by the guest must not go backwards, and
should go forwards only by a small amount corresponding to the time
taken for the migration.

Therefore this provides a new per-vcpu value accessed via the one_reg
interface using the new KVM_REG_PPC_TB_OFFSET identifier.  This value
defaults to 0 and is not modified by KVM.  On entering the guest, this
value is added onto the timebase, and on exiting the guest, it is
subtracted from the timebase.

This is only supported for recent POWER hardware which has the TBU40
(timebase upper 40 bits) register.  Writing to the TBU40 register only
alters the upper 40 bits of the timebase, leaving the lower 24 bits
unchanged.  This provides a way to modify the timebase for guest
migration without disturbing the synchronization of the timebase
registers across CPU cores.  The kernel rounds up the value given
to a multiple of 2^24.

Timebase values stored in KVM structures (struct kvm_vcpu, struct
kvmppc_vcore, etc.) are stored as host timebase values.  The timebase
values in the dispatch trace log need to be guest timebase values,
however, since that is read directly by the guest.  This moves the
setting of vcpu->arch.dec_expires on guest exit to a point after we
have restored the host timebase so that vcpu->arch.dec_expires is a
host timebase value.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt       |  1 +
 arch/powerpc/include/asm/kvm_host.h     |  1 +
 arch/powerpc/include/asm/reg.h          |  1 +
 arch/powerpc/include/uapi/asm/kvm.h     |  3 ++
 arch/powerpc/kernel/asm-offsets.c       |  1 +
 arch/powerpc/kvm/book3s_hv.c            | 10 ++++++-
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 50 +++++++++++++++++++++++++++------
 7 files changed, 57 insertions(+), 10 deletions(-)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 354a51ba456b..e43c6f14c225 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1810,6 +1810,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_TLB3PS	| 32
   PPC   | KVM_REG_PPC_EPTCFG	| 32
   PPC   | KVM_REG_PPC_ICP_STATE | 64
+  PPC   | KVM_REG_PPC_TB_OFFSET	| 64
   PPC   | KVM_REG_PPC_SPMC1	| 32
   PPC   | KVM_REG_PPC_SPMC2	| 32
   PPC   | KVM_REG_PPC_IAMR	| 64
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index d9b21af62610..e4d67a606e43 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -289,6 +289,7 @@ struct kvmppc_vcore {
 	u64 stolen_tb;
 	u64 preempt_tb;
 	struct kvm_vcpu *runner;
+	u64 tb_offset;		/* guest timebase - host timebase */
 };
 
 #define VCORE_ENTRY_COUNT(vc)	((vc)->entry_exit_count & 0xff)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 10d1ef016bf1..fd4db15e6f2a 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -243,6 +243,7 @@
 #define SPRN_TBRU	0x10D	/* Time Base Read Upper Register (user, R/O) */
 #define SPRN_TBWL	0x11C	/* Time Base Lower Register (super, R/W) */
 #define SPRN_TBWU	0x11D	/* Time Base Upper Register (super, R/W) */
+#define SPRN_TBU40	0x11E	/* Timebase upper 40 bits (hyper, R/W) */
 #define SPRN_SPURR	0x134	/* Scaled PURR */
 #define SPRN_HSPRG0	0x130	/* Hypervisor Scratch 0 */
 #define SPRN_HSPRG1	0x131	/* Hypervisor Scratch 1 */
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 7ed41c0b4045..a8124fe93fb9 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -504,6 +504,9 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_TLB3PS	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9a)
 #define KVM_REG_PPC_EPTCFG	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9b)
 
+/* Timebase offset */
+#define KVM_REG_PPC_TB_OFFSET	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9c)
+
 /* POWER8 registers */
 #define KVM_REG_PPC_SPMC1	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9d)
 #define KVM_REG_PPC_SPMC2	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9e)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 19e699d747b7..34d63d871917 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -523,6 +523,7 @@ int main(void)
 	DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count));
 	DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
 	DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
+	DEFINE(VCORE_TB_OFFSET, offsetof(struct kvmppc_vcore, tb_offset));
 	DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
 			   offsetof(struct kvmppc_vcpu_book3s, vcpu));
 	DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 45a9b876b0a0..56f57af7e738 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -489,7 +489,7 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
 	memset(dt, 0, sizeof(struct dtl_entry));
 	dt->dispatch_reason = 7;
 	dt->processor_id = vc->pcpu + vcpu->arch.ptid;
-	dt->timebase = now;
+	dt->timebase = now + vc->tb_offset;
 	dt->enqueue_to_dispatch_time = stolen;
 	dt->srr0 = kvmppc_get_pc(vcpu);
 	dt->srr1 = vcpu->arch.shregs.msr;
@@ -793,6 +793,9 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 		val->vpaval.length = vcpu->arch.dtl.len;
 		spin_unlock(&vcpu->arch.vpa_update_lock);
 		break;
+	case KVM_REG_PPC_TB_OFFSET:
+		*val = get_reg_val(id, vcpu->arch.vcore->tb_offset);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -892,6 +895,11 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 		len -= len % sizeof(struct dtl_entry);
 		r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len);
 		break;
+	case KVM_REG_PPC_TB_OFFSET:
+		/* round up to multiple of 2^24 */
+		vcpu->arch.vcore->tb_offset =
+			ALIGN(set_reg_val(id, *val), 1UL << 24);
+		break;
 	default:
 		r = -EINVAL;
 		break;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 541aea0ce91a..82b06dfe2d27 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -347,7 +347,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	bdnz	28b
 	ptesync
 
-22:	li	r0,1
+	/* Add timebase offset onto timebase */
+22:	ld	r8,VCORE_TB_OFFSET(r5)
+	cmpdi	r8,0
+	beq	37f
+	mftb	r6		/* current host timebase */
+	add	r8,r8,r6
+	mtspr	SPRN_TBU40,r8	/* update upper 40 bits */
+	mftb	r7		/* check if lower 24 bits overflowed */
+	clrldi	r6,r6,40
+	clrldi	r7,r7,40
+	cmpld	r7,r6
+	bge	37f
+	addis	r8,r8,0x100	/* if so, increment upper 40 bits */
+	mtspr	SPRN_TBU40,r8
+
+37:	li	r0,1
 	stb	r0,VCORE_IN_GUEST(r5)	/* signal secondaries to continue */
 	b	10f
 
@@ -782,13 +797,6 @@ ext_stash_for_host:
 ext_interrupt_to_host:
 
 guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
-	/* Save DEC */
-	mfspr	r5,SPRN_DEC
-	mftb	r6
-	extsw	r5,r5
-	add	r5,r5,r6
-	std	r5,VCPU_DEC_EXPIRES(r9)
-
 	/* Save more register state  */
 	mfdar	r6
 	mfdsisr	r7
@@ -958,7 +966,24 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	mtspr	SPRN_SDR1,r6		/* switch to partition page table */
 	mtspr	SPRN_LPID,r7
 	isync
-	li	r0,0
+
+	/* Subtract timebase offset from timebase */
+	ld	r8,VCORE_TB_OFFSET(r5)
+	cmpdi	r8,0
+	beq	17f
+	mftb	r6			/* current host timebase */
+	subf	r8,r8,r6
+	mtspr	SPRN_TBU40,r8		/* update upper 40 bits */
+	mftb	r7			/* check if lower 24 bits overflowed */
+	clrldi	r6,r6,40
+	clrldi	r7,r7,40
+	cmpld	r7,r6
+	bge	17f
+	addis	r8,r8,0x100		/* if so, increment upper 40 bits */
+	mtspr	SPRN_TBU40,r8
+
+	/* Signal secondary CPUs to continue */
+17:	li	r0,0
 	stb	r0,VCORE_IN_GUEST(r5)
 	lis	r8,0x7fff		/* MAX_INT@h */
 	mtspr	SPRN_HDEC,r8
@@ -1056,6 +1081,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 1:	addi	r8,r8,16
 	.endr
 
+	/* Save DEC */
+	mfspr	r5,SPRN_DEC
+	mftb	r6
+	extsw	r5,r5
+	add	r5,r5,r6
+	std	r5,VCPU_DEC_EXPIRES(r9)
+
 	/* Save and reset AMR and UAMOR before turning on the MMU */
 BEGIN_FTR_SECTION
 	mfspr	r5,SPRN_AMR
-- 
cgit v1.2.3


From c0867fd50943d71d9f0bc5078393ce4ec76b3923 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 6 Sep 2013 13:18:32 +1000
Subject: KVM: PPC: Book3S: Add GET/SET_ONE_REG interface for VRSAVE

The VRSAVE register value for a vcpu is accessible through the
GET/SET_SREGS interface for Book E processors, but not for Book 3S
processors.  In order to make this accessible for Book 3S processors,
this adds a new register identifier for GET/SET_ONE_REG, and adds
the code to implement it.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt   |  1 +
 arch/powerpc/include/uapi/asm/kvm.h |  2 ++
 arch/powerpc/kvm/book3s.c           | 10 ++++++++++
 3 files changed, 13 insertions(+)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index e43c6f14c225..26fc37355dcb 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1834,6 +1834,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_TCSCR	| 64
   PPC   | KVM_REG_PPC_PID	| 64
   PPC   | KVM_REG_PPC_ACOP	| 64
+  PPC   | KVM_REG_PPC_VRSAVE	| 32
   PPC   | KVM_REG_PPC_TM_GPR0	| 64
           ...
   PPC   | KVM_REG_PPC_TM_GPR31	| 64
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index a8124fe93fb9..b98bf3f50527 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -532,6 +532,8 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_PID		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb2)
 #define KVM_REG_PPC_ACOP	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb3)
 
+#define KVM_REG_PPC_VRSAVE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4)
+
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
  */
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 700df6f1d32c..f97369dc457c 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -528,6 +528,9 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 			}
 			val = get_reg_val(reg->id, vcpu->arch.vscr.u[3]);
 			break;
+		case KVM_REG_PPC_VRSAVE:
+			val = get_reg_val(reg->id, vcpu->arch.vrsave);
+			break;
 #endif /* CONFIG_ALTIVEC */
 		case KVM_REG_PPC_DEBUG_INST: {
 			u32 opcode = INS_TW;
@@ -605,6 +608,13 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 			}
 			vcpu->arch.vscr.u[3] = set_reg_val(reg->id, val);
 			break;
+		case KVM_REG_PPC_VRSAVE:
+			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+				r = -ENXIO;
+				break;
+			}
+			vcpu->arch.vrsave = set_reg_val(reg->id, val);
+			break;
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_KVM_XICS
 		case KVM_REG_PPC_ICP_STATE:
-- 
cgit v1.2.3


From a0144e2a6b0b4a137a32f0102354782547bf0935 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:38 +1000
Subject: KVM: PPC: Book3S HV: Store LPCR value for each virtual core

This adds the ability to have a separate LPCR (Logical Partitioning
Control Register) value relating to a guest for each virtual core,
rather than only having a single value for the whole VM.  This
corresponds to what real POWER hardware does, where there is a LPCR
per CPU thread but most of the fields are required to have the same
value on all active threads in a core.

The per-virtual-core LPCR can be read and written using the
GET/SET_ONE_REG interface.  Userspace can can only modify the
following fields of the LPCR value:

DPFD	Default prefetch depth
ILE	Interrupt little-endian
TC	Translation control (secondary HPT hash group search disable)

We still maintain a per-VM default LPCR value in kvm->arch.lpcr, which
contains bits relating to memory management, i.e. the Virtualized
Partition Memory (VPM) bits and the bits relating to guest real mode.
When this default value is updated, the update needs to be propagated
to the per-vcore values, so we add a kvmppc_update_lpcr() helper to do
that.

Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: fix whitespace]
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt       |  1 +
 arch/powerpc/include/asm/kvm_book3s.h   |  2 +
 arch/powerpc/include/asm/kvm_host.h     |  1 +
 arch/powerpc/include/asm/reg.h          |  3 ++
 arch/powerpc/include/uapi/asm/kvm.h     |  1 +
 arch/powerpc/kernel/asm-offsets.c       |  1 +
 arch/powerpc/kvm/book3s_64_mmu_hv.c     |  5 +--
 arch/powerpc/kvm/book3s_hv.c            | 73 +++++++++++++++++++++++++++------
 arch/powerpc/kvm/book3s_hv_rmhandlers.S |  5 ++-
 9 files changed, 75 insertions(+), 17 deletions(-)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 26fc37355dcb..387f4c7dad9f 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1835,6 +1835,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_PID	| 64
   PPC   | KVM_REG_PPC_ACOP	| 64
   PPC   | KVM_REG_PPC_VRSAVE	| 32
+  PPC   | KVM_REG_PPC_LPCR	| 64
   PPC   | KVM_REG_PPC_TM_GPR0	| 64
           ...
   PPC   | KVM_REG_PPC_TM_GPR31	| 64
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index fa19e2f1a874..14a47416bdd4 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -172,6 +172,8 @@ extern long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 			unsigned long *hpret);
 extern long kvmppc_hv_get_dirty_log(struct kvm *kvm,
 			struct kvm_memory_slot *memslot, unsigned long *map);
+extern void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr,
+			unsigned long mask);
 
 extern void kvmppc_entry_trampoline(void);
 extern void kvmppc_hv_entry_trampoline(void);
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index e4d67a606e43..6eabffcb1c3c 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -290,6 +290,7 @@ struct kvmppc_vcore {
 	u64 preempt_tb;
 	struct kvm_vcpu *runner;
 	u64 tb_offset;		/* guest timebase - host timebase */
+	ulong lpcr;
 };
 
 #define VCORE_ENTRY_COUNT(vc)	((vc)->entry_exit_count & 0xff)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index fd4db15e6f2a..4bec4df3fb98 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -284,6 +284,7 @@
 #define   LPCR_ISL	(1ul << (63-2))
 #define   LPCR_VC_SH	(63-2)
 #define   LPCR_DPFD_SH	(63-11)
+#define   LPCR_DPFD	(7ul << LPCR_DPFD_SH)
 #define   LPCR_VRMASD	(0x1ful << (63-16))
 #define   LPCR_VRMA_L	(1ul << (63-12))
 #define   LPCR_VRMA_LP0	(1ul << (63-15))
@@ -300,6 +301,7 @@
 #define     LPCR_PECE2	0x00001000	/* machine check etc can cause exit */
 #define   LPCR_MER	0x00000800	/* Mediated External Exception */
 #define   LPCR_MER_SH	11
+#define   LPCR_TC      0x00000200	/* Translation control */
 #define   LPCR_LPES    0x0000000c
 #define   LPCR_LPES0   0x00000008      /* LPAR Env selector 0 */
 #define   LPCR_LPES1   0x00000004      /* LPAR Env selector 1 */
@@ -421,6 +423,7 @@
 #define	 HID4_RMLS2_SH	 (63 - 2)	/* Real mode limit bottom 2 bits */
 #define	 HID4_LPID5_SH	 (63 - 6)	/* partition ID bottom 4 bits */
 #define	 HID4_RMOR_SH	 (63 - 22)	/* real mode offset (16 bits) */
+#define  HID4_RMOR	 (0xFFFFul << HID4_RMOR_SH)
 #define  HID4_LPES1	 (1 << (63-57))	/* LPAR env. sel. bit 1 */
 #define  HID4_RMLS0_SH	 (63 - 58)	/* Real mode limit top bit */
 #define	 HID4_LPID1_SH	 0		/* partition ID top 2 bits */
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index b98bf3f50527..e42127d1ae8e 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -533,6 +533,7 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_ACOP	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb3)
 
 #define KVM_REG_PPC_VRSAVE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4)
+#define KVM_REG_PPC_LPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 34d63d871917..fd7513f8014b 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -524,6 +524,7 @@ int main(void)
 	DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
 	DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
 	DEFINE(VCORE_TB_OFFSET, offsetof(struct kvmppc_vcore, tb_offset));
+	DEFINE(VCORE_LPCR, offsetof(struct kvmppc_vcore, lpcr));
 	DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
 			   offsetof(struct kvmppc_vcpu_book3s, vcpu));
 	DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 043eec8461e7..ccb89a048bf8 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -1512,9 +1512,8 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 
 				kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
 					(VRMA_VSID << SLB_VSID_SHIFT_1T);
-				lpcr = kvm->arch.lpcr & ~LPCR_VRMASD;
-				lpcr |= senc << (LPCR_VRMASD_SH - 4);
-				kvm->arch.lpcr = lpcr;
+				lpcr = senc << (LPCR_VRMASD_SH - 4);
+				kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
 				rma_setup = 1;
 			}
 			++i;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index a010aa4cd026..36eb95cc48ae 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -195,7 +195,7 @@ void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 		pr_err("  ESID = %.16llx VSID = %.16llx\n",
 		       vcpu->arch.slb[r].orige, vcpu->arch.slb[r].origv);
 	pr_err("lpcr = %.16lx sdr1 = %.16lx last_inst = %.8x\n",
-	       vcpu->kvm->arch.lpcr, vcpu->kvm->arch.sdr1,
+	       vcpu->arch.vcore->lpcr, vcpu->kvm->arch.sdr1,
 	       vcpu->arch.last_inst);
 }
 
@@ -723,6 +723,21 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	u64 mask;
+
+	spin_lock(&vc->lock);
+	/*
+	 * Userspace can only modify DPFD (default prefetch depth),
+	 * ILE (interrupt little-endian) and TC (translation control).
+	 */
+	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC;
+	vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
+	spin_unlock(&vc->lock);
+}
+
 int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 {
 	int r = 0;
@@ -805,6 +820,9 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	case KVM_REG_PPC_TB_OFFSET:
 		*val = get_reg_val(id, vcpu->arch.vcore->tb_offset);
 		break;
+	case KVM_REG_PPC_LPCR:
+		*val = get_reg_val(id, vcpu->arch.vcore->lpcr);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -909,6 +927,9 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 		vcpu->arch.vcore->tb_offset =
 			ALIGN(set_reg_val(id, *val), 1UL << 24);
 		break;
+	case KVM_REG_PPC_LPCR:
+		kvmppc_set_lpcr(vcpu, set_reg_val(id, *val));
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -969,6 +990,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 			spin_lock_init(&vcore->lock);
 			init_waitqueue_head(&vcore->wq);
 			vcore->preempt_tb = TB_NIL;
+			vcore->lpcr = kvm->arch.lpcr;
 		}
 		kvm->arch.vcores[core] = vcore;
 		kvm->arch.online_vcores++;
@@ -1758,6 +1780,32 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm,
 	}
 }
 
+/*
+ * Update LPCR values in kvm->arch and in vcores.
+ * Caller must hold kvm->lock.
+ */
+void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask)
+{
+	long int i;
+	u32 cores_done = 0;
+
+	if ((kvm->arch.lpcr & mask) == lpcr)
+		return;
+
+	kvm->arch.lpcr = (kvm->arch.lpcr & ~mask) | lpcr;
+
+	for (i = 0; i < KVM_MAX_VCORES; ++i) {
+		struct kvmppc_vcore *vc = kvm->arch.vcores[i];
+		if (!vc)
+			continue;
+		spin_lock(&vc->lock);
+		vc->lpcr = (vc->lpcr & ~mask) | lpcr;
+		spin_unlock(&vc->lock);
+		if (++cores_done >= kvm->arch.online_vcores)
+			break;
+	}
+}
+
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 {
 	int err = 0;
@@ -1766,7 +1814,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 	unsigned long hva;
 	struct kvm_memory_slot *memslot;
 	struct vm_area_struct *vma;
-	unsigned long lpcr, senc;
+	unsigned long lpcr = 0, senc;
+	unsigned long lpcr_mask = 0;
 	unsigned long psize, porder;
 	unsigned long rma_size;
 	unsigned long rmls;
@@ -1831,9 +1880,9 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		senc = slb_pgsize_encoding(psize);
 		kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
 			(VRMA_VSID << SLB_VSID_SHIFT_1T);
-		lpcr = kvm->arch.lpcr & ~LPCR_VRMASD;
-		lpcr |= senc << (LPCR_VRMASD_SH - 4);
-		kvm->arch.lpcr = lpcr;
+		lpcr_mask = LPCR_VRMASD;
+		/* the -4 is to account for senc values starting at 0x10 */
+		lpcr = senc << (LPCR_VRMASD_SH - 4);
 
 		/* Create HPTEs in the hash page table for the VRMA */
 		kvmppc_map_vrma(vcpu, memslot, porder);
@@ -1854,23 +1903,21 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		kvm->arch.rma = ri;
 
 		/* Update LPCR and RMOR */
-		lpcr = kvm->arch.lpcr;
 		if (cpu_has_feature(CPU_FTR_ARCH_201)) {
 			/* PPC970; insert RMLS value (split field) in HID4 */
-			lpcr &= ~((1ul << HID4_RMLS0_SH) |
-				  (3ul << HID4_RMLS2_SH));
-			lpcr |= ((rmls >> 2) << HID4_RMLS0_SH) |
+			lpcr_mask = (1ul << HID4_RMLS0_SH) |
+				(3ul << HID4_RMLS2_SH) | HID4_RMOR;
+			lpcr = ((rmls >> 2) << HID4_RMLS0_SH) |
 				((rmls & 3) << HID4_RMLS2_SH);
 			/* RMOR is also in HID4 */
 			lpcr |= ((ri->base_pfn >> (26 - PAGE_SHIFT)) & 0xffff)
 				<< HID4_RMOR_SH;
 		} else {
 			/* POWER7 */
-			lpcr &= ~(LPCR_VPM0 | LPCR_VRMA_L);
-			lpcr |= rmls << LPCR_RMLS_SH;
+			lpcr_mask = LPCR_VPM0 | LPCR_VRMA_L | LPCR_RMLS;
+			lpcr = rmls << LPCR_RMLS_SH;
 			kvm->arch.rmor = ri->base_pfn << PAGE_SHIFT;
 		}
-		kvm->arch.lpcr = lpcr;
 		pr_info("KVM: Using RMO at %lx size %lx (LPCR = %lx)\n",
 			ri->base_pfn << PAGE_SHIFT, rma_size, lpcr);
 
@@ -1889,6 +1936,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		}
 	}
 
+	kvmppc_update_lpcr(kvm, lpcr, lpcr_mask);
+
 	/* Order updates to kvm->arch.lpcr etc. vs. rma_setup_done */
 	smp_wmb();
 	kvm->arch.rma_setup_done = 1;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 0effcd144241..295fd58af39a 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -509,7 +509,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	beq	20b
 
 	/* Set LPCR and RMOR. */
-10:	ld	r8,KVM_LPCR(r9)
+10:	ld	r8,VCORE_LPCR(r5)
 	mtspr	SPRN_LPCR,r8
 	ld	r8,KVM_RMOR(r9)
 	mtspr	SPRN_RMOR,r8
@@ -571,7 +571,8 @@ toc_tlbie_lock:
 	bne	24b
 	isync
 
-	ld	r7,KVM_LPCR(r9)		/* use kvm->arch.lpcr to store HID4 */
+	ld	r5,HSTATE_KVM_VCORE(r13)
+	ld	r7,VCORE_LPCR(r5)	/* use vcore->lpcr to store HID4 */
 	li	r0,0x18f
 	rotldi	r0,r0,HID4_LPID5_SH	/* all lpid bits in HID4 = 1 */
 	or	r0,r7,r0
-- 
cgit v1.2.3


From 4b8473c9c19dff1b0c672f182cc50b9952cf42e7 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Sep 2013 14:52:39 +1000
Subject: KVM: PPC: Book3S HV: Add support for guest Program Priority Register

POWER7 and later IBM server processors have a register called the
Program Priority Register (PPR), which controls the priority of
each hardware CPU SMT thread, and affects how fast it runs compared
to other SMT threads.  This priority can be controlled by writing to
the PPR or by use of a set of instructions of the form or rN,rN,rN
which are otherwise no-ops but have been defined to set the priority
to particular levels.

This adds code to context switch the PPR when entering and exiting
guests and to make the PPR value accessible through the SET/GET_ONE_REG
interface.  When entering the guest, we set the PPR as late as
possible, because if we are setting a low thread priority it will
make the code run slowly from that point on.  Similarly, the
first-level interrupt handlers save the PPR value in the PACA very
early on, and set the thread priority to the medium level, so that
the interrupt handling code runs at a reasonable speed.

Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt         |  1 +
 arch/powerpc/include/asm/exception-64s.h  |  8 ++++++++
 arch/powerpc/include/asm/kvm_book3s_asm.h |  1 +
 arch/powerpc/include/asm/kvm_host.h       |  1 +
 arch/powerpc/include/uapi/asm/kvm.h       |  1 +
 arch/powerpc/kernel/asm-offsets.c         |  2 ++
 arch/powerpc/kvm/book3s_hv.c              |  6 ++++++
 arch/powerpc/kvm/book3s_hv_rmhandlers.S   | 12 +++++++++++-
 8 files changed, 31 insertions(+), 1 deletion(-)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 387f4c7dad9f..a9d1072dcbec 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1836,6 +1836,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_ACOP	| 64
   PPC   | KVM_REG_PPC_VRSAVE	| 32
   PPC   | KVM_REG_PPC_LPCR	| 64
+  PPC   | KVM_REG_PPC_PPR	| 64
   PPC   | KVM_REG_PPC_TM_GPR0	| 64
           ...
   PPC   | KVM_REG_PPC_TM_GPR31	| 64
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index cca12f084842..402c1c466509 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -204,6 +204,10 @@ do_kvm_##n:								\
 	ld	r10,area+EX_CFAR(r13);					\
 	std	r10,HSTATE_CFAR(r13);					\
 	END_FTR_SECTION_NESTED(CPU_FTR_CFAR,CPU_FTR_CFAR,947);		\
+	BEGIN_FTR_SECTION_NESTED(948)					\
+	ld	r10,area+EX_PPR(r13);					\
+	std	r10,HSTATE_PPR(r13);					\
+	END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948);	\
 	ld	r10,area+EX_R10(r13);					\
 	stw	r9,HSTATE_SCRATCH1(r13);				\
 	ld	r9,area+EX_R9(r13);					\
@@ -217,6 +221,10 @@ do_kvm_##n:								\
 	ld	r10,area+EX_R10(r13);					\
 	beq	89f;							\
 	stw	r9,HSTATE_SCRATCH1(r13);			\
+	BEGIN_FTR_SECTION_NESTED(948)					\
+	ld	r9,area+EX_PPR(r13);					\
+	std	r9,HSTATE_PPR(r13);					\
+	END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948);	\
 	ld	r9,area+EX_R9(r13);					\
 	std	r12,HSTATE_SCRATCH0(r13);			\
 	li	r12,n;							\
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 9039d3c97eec..22f46061ae84 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -101,6 +101,7 @@ struct kvmppc_host_state {
 #endif
 #ifdef CONFIG_PPC_BOOK3S_64
 	u64 cfar;
+	u64 ppr;
 #endif
 };
 
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 6eabffcb1c3c..4934e13fb23c 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -460,6 +460,7 @@ struct kvm_vcpu_arch {
 	u32 ctrl;
 	ulong dabr;
 	ulong cfar;
+	ulong ppr;
 #endif
 	u32 vrsave; /* also USPRG0 */
 	u32 mmucr;
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index e42127d1ae8e..fab6bc1f8e90 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -534,6 +534,7 @@ struct kvm_get_htab_header {
 
 #define KVM_REG_PPC_VRSAVE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4)
 #define KVM_REG_PPC_LPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5)
+#define KVM_REG_PPC_PPR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb6)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index fd7513f8014b..5fda4ef489ad 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -519,6 +519,7 @@ int main(void)
 	DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap));
 	DEFINE(VCPU_PTID, offsetof(struct kvm_vcpu, arch.ptid));
 	DEFINE(VCPU_CFAR, offsetof(struct kvm_vcpu, arch.cfar));
+	DEFINE(VCPU_PPR, offsetof(struct kvm_vcpu, arch.ppr));
 	DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count));
 	DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count));
 	DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
@@ -604,6 +605,7 @@ int main(void)
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	HSTATE_FIELD(HSTATE_CFAR, cfar);
+	HSTATE_FIELD(HSTATE_PPR, ppr);
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 #else /* CONFIG_PPC_BOOK3S */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 36eb95cc48ae..2a0e38feec1d 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -823,6 +823,9 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	case KVM_REG_PPC_LPCR:
 		*val = get_reg_val(id, vcpu->arch.vcore->lpcr);
 		break;
+	case KVM_REG_PPC_PPR:
+		*val = get_reg_val(id, vcpu->arch.ppr);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -930,6 +933,9 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	case KVM_REG_PPC_LPCR:
 		kvmppc_set_lpcr(vcpu, set_reg_val(id, *val));
 		break;
+	case KVM_REG_PPC_PPR:
+		vcpu->arch.ppr = set_reg_val(id, *val);
+		break;
 	default:
 		r = -EINVAL;
 		break;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 295fd58af39a..a81979becf41 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -717,13 +717,15 @@ BEGIN_FTR_SECTION
 	ld	r5, VCPU_CFAR(r4)
 	mtspr	SPRN_CFAR, r5
 END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+BEGIN_FTR_SECTION
+	ld	r0, VCPU_PPR(r4)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
 	ld	r5, VCPU_LR(r4)
 	lwz	r6, VCPU_CR(r4)
 	mtlr	r5
 	mtcr	r6
 
-	ld	r0, VCPU_GPR(R0)(r4)
 	ld	r1, VCPU_GPR(R1)(r4)
 	ld	r2, VCPU_GPR(R2)(r4)
 	ld	r3, VCPU_GPR(R3)(r4)
@@ -737,6 +739,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	ld	r12, VCPU_GPR(R12)(r4)
 	ld	r13, VCPU_GPR(R13)(r4)
 
+BEGIN_FTR_SECTION
+	mtspr	SPRN_PPR, r0
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+	ld	r0, VCPU_GPR(R0)(r4)
 	ld	r4, VCPU_GPR(R4)(r4)
 
 	hrfid
@@ -787,6 +793,10 @@ BEGIN_FTR_SECTION
 	ld	r3, HSTATE_CFAR(r13)
 	std	r3, VCPU_CFAR(r9)
 END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+BEGIN_FTR_SECTION
+	ld	r4, HSTATE_PPR(r13)
+	std	r4, VCPU_PPR(r9)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
 	/* Restore R1/R2 so we can handle faults */
 	ld	r1, HSTATE_HOST_R1(r13)
-- 
cgit v1.2.3


From 388cc6e133132e6c9b64e7d5361114a3a7d57663 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Sat, 21 Sep 2013 14:35:02 +1000
Subject: KVM: PPC: Book3S HV: Support POWER6 compatibility mode on POWER7

This enables us to use the Processor Compatibility Register (PCR) on
POWER7 to put the processor into architecture 2.05 compatibility mode
when running a guest.  In this mode the new instructions and registers
that were introduced on POWER7 are disabled in user mode.  This
includes all the VSX facilities plus several other instructions such
as ldbrx, stdbrx, popcntw, popcntd, etc.

To select this mode, we have a new register accessible through the
set/get_one_reg interface, called KVM_REG_PPC_ARCH_COMPAT.  Setting
this to zero gives the full set of capabilities of the processor.
Setting it to one of the "logical" PVR values defined in PAPR puts
the vcpu into the compatibility mode for the corresponding
architecture level.  The supported values are:

0x0f000002	Architecture 2.05 (POWER6)
0x0f000003	Architecture 2.06 (POWER7)
0x0f100003	Architecture 2.06+ (POWER7+)

Since the PCR is per-core, the architecture compatibility level and
the corresponding PCR value are stored in the struct kvmppc_vcore, and
are therefore shared between all vcpus in a virtual core.

Signed-off-by: Paul Mackerras <paulus@samba.org>
[agraf: squash in fix to add missing break statements and documentation]
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 Documentation/virtual/kvm/api.txt       |  1 +
 arch/powerpc/include/asm/kvm_host.h     |  2 ++
 arch/powerpc/include/asm/reg.h          | 11 +++++++++++
 arch/powerpc/include/uapi/asm/kvm.h     |  3 +++
 arch/powerpc/kernel/asm-offsets.c       |  1 +
 arch/powerpc/kvm/book3s_hv.c            | 35 +++++++++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 16 +++++++++++++--
 7 files changed, 67 insertions(+), 2 deletions(-)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index a9d1072dcbec..25a19576493f 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1837,6 +1837,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_VRSAVE	| 32
   PPC   | KVM_REG_PPC_LPCR	| 64
   PPC   | KVM_REG_PPC_PPR	| 64
+  PPC   | KVM_REG_PPC_ARCH_COMPAT 32
   PPC   | KVM_REG_PPC_TM_GPR0	| 64
           ...
   PPC   | KVM_REG_PPC_TM_GPR31	| 64
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 4934e13fb23c..b1e8f2ba2a9d 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -291,6 +291,8 @@ struct kvmppc_vcore {
 	struct kvm_vcpu *runner;
 	u64 tb_offset;		/* guest timebase - host timebase */
 	ulong lpcr;
+	u32 arch_compat;
+	ulong pcr;
 };
 
 #define VCORE_ENTRY_COUNT(vc)	((vc)->entry_exit_count & 0xff)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 4bec4df3fb98..e294673e9d4b 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -314,6 +314,10 @@
 #define   LPID_RSVD	0x3ff		/* Reserved LPID for partn switching */
 #define	SPRN_HMER	0x150	/* Hardware m? error recovery */
 #define	SPRN_HMEER	0x151	/* Hardware m? enable error recovery */
+#define SPRN_PCR	0x152	/* Processor compatibility register */
+#define   PCR_VEC_DIS	(1ul << (63-0))	/* Vec. disable (bit NA since POWER8) */
+#define   PCR_VSX_DIS	(1ul << (63-1))	/* VSX disable (bit NA since POWER8) */
+#define   PCR_ARCH_205	0x2		/* Architecture 2.05 */
 #define	SPRN_HEIR	0x153	/* Hypervisor Emulated Instruction Register */
 #define SPRN_TLBINDEXR	0x154	/* P7 TLB control register */
 #define SPRN_TLBVPNR	0x155	/* P7 TLB control register */
@@ -1106,6 +1110,13 @@
 #define PVR_BE		0x0070
 #define PVR_PA6T	0x0090
 
+/* "Logical" PVR values defined in PAPR, representing architecture levels */
+#define PVR_ARCH_204	0x0f000001
+#define PVR_ARCH_205	0x0f000002
+#define PVR_ARCH_206	0x0f000003
+#define PVR_ARCH_206p	0x0f100003
+#define PVR_ARCH_207	0x0f000004
+
 /* Macros for setting and retrieving special purpose registers */
 #ifndef __ASSEMBLY__
 #define mfmsr()		({unsigned long rval; \
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index fab6bc1f8e90..e420d46d363f 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -536,6 +536,9 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_LPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5)
 #define KVM_REG_PPC_PPR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb6)
 
+/* Architecture compatibility level */
+#define KVM_REG_PPC_ARCH_COMPAT	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb7)
+
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
  */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 5fda4ef489ad..5a285efba174 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -526,6 +526,7 @@ int main(void)
 	DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
 	DEFINE(VCORE_TB_OFFSET, offsetof(struct kvmppc_vcore, tb_offset));
 	DEFINE(VCORE_LPCR, offsetof(struct kvmppc_vcore, lpcr));
+	DEFINE(VCORE_PCR, offsetof(struct kvmppc_vcore, pcr));
 	DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
 			   offsetof(struct kvmppc_vcpu_book3s, vcpu));
 	DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 2a0e38feec1d..e42fb5448608 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -166,6 +166,35 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
 	vcpu->arch.pvr = pvr;
 }
 
+int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
+{
+	unsigned long pcr = 0;
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+	if (arch_compat) {
+		if (!cpu_has_feature(CPU_FTR_ARCH_206))
+			return -EINVAL;	/* 970 has no compat mode support */
+
+		switch (arch_compat) {
+		case PVR_ARCH_205:
+			pcr = PCR_ARCH_205;
+			break;
+		case PVR_ARCH_206:
+		case PVR_ARCH_206p:
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	spin_lock(&vc->lock);
+	vc->arch_compat = arch_compat;
+	vc->pcr = pcr;
+	spin_unlock(&vc->lock);
+
+	return 0;
+}
+
 void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 {
 	int r;
@@ -826,6 +855,9 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	case KVM_REG_PPC_PPR:
 		*val = get_reg_val(id, vcpu->arch.ppr);
 		break;
+	case KVM_REG_PPC_ARCH_COMPAT:
+		*val = get_reg_val(id, vcpu->arch.vcore->arch_compat);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -936,6 +968,9 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id, union kvmppc_one_reg *val)
 	case KVM_REG_PPC_PPR:
 		vcpu->arch.ppr = set_reg_val(id, *val);
 		break;
+	case KVM_REG_PPC_ARCH_COMPAT:
+		r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val));
+		break;
 	default:
 		r = -EINVAL;
 		break;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index a81979becf41..cd39632a646e 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -499,7 +499,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	addis	r8,r8,0x100	/* if so, increment upper 40 bits */
 	mtspr	SPRN_TBU40,r8
 
-37:	li	r0,1
+	/* Load guest PCR value to select appropriate compat mode */
+37:	ld	r7, VCORE_PCR(r5)
+	cmpdi	r7, 0
+	beq	38f
+	mtspr	SPRN_PCR, r7
+38:
+	li	r0,1
 	stb	r0,VCORE_IN_GUEST(r5)	/* signal secondaries to continue */
 	b	10f
 
@@ -1094,8 +1100,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	addis	r8,r8,0x100		/* if so, increment upper 40 bits */
 	mtspr	SPRN_TBU40,r8
 
+	/* Reset PCR */
+17:	ld	r0, VCORE_PCR(r5)
+	cmpdi	r0, 0
+	beq	18f
+	li	r0, 0
+	mtspr	SPRN_PCR, r0
+18:
 	/* Signal secondary CPUs to continue */
-17:	li	r0,0
 	stb	r0,VCORE_IN_GUEST(r5)
 	lis	r8,0x7fff		/* MAX_INT@h */
 	mtspr	SPRN_HDEC,r8
-- 
cgit v1.2.3


From 9c15bb1d0a8411f9bb3395d21d5309bde7da0c1c Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Sun, 22 Sep 2013 16:44:50 +0200
Subject: kvm: Add KVM_GET_EMULATED_CPUID

Add a kvm ioctl which states which system functionality kvm emulates.
The format used is that of CPUID and we return the corresponding CPUID
bits set for which we do emulate functionality.

Make sure ->padding is being passed on clean from userspace so that we
can use it for something in the future, after the ioctl gets cast in
stone.

s/kvm_dev_ioctl_get_supported_cpuid/kvm_dev_ioctl_get_cpuid/ while at
it.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/api.txt | 77 +++++++++++++++++++++++++++++++++++++--
 arch/x86/include/uapi/asm/kvm.h   |  6 +--
 arch/x86/kvm/cpuid.c              | 57 ++++++++++++++++++++++++++---
 arch/x86/kvm/cpuid.h              |  5 ++-
 arch/x86/kvm/x86.c                |  9 +++--
 include/uapi/linux/kvm.h          |  2 +
 6 files changed, 139 insertions(+), 17 deletions(-)

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index a89a5ee0b940..488964414f04 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1122,9 +1122,9 @@ struct kvm_cpuid2 {
 	struct kvm_cpuid_entry2 entries[0];
 };
 
-#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1
-#define KVM_CPUID_FLAG_STATEFUL_FUNC    2
-#define KVM_CPUID_FLAG_STATE_READ_NEXT  4
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		BIT(0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC		BIT(1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT		BIT(2)
 
 struct kvm_cpuid_entry2 {
 	__u32 function;
@@ -2684,6 +2684,77 @@ and usually define the validity of a groups of registers. (e.g. one bit
 };
 
 
+4.81 KVM_GET_EMULATED_CPUID
+
+Capability: KVM_CAP_EXT_EMUL_CPUID
+Architectures: x86
+Type: system ioctl
+Parameters: struct kvm_cpuid2 (in/out)
+Returns: 0 on success, -1 on error
+
+struct kvm_cpuid2 {
+	__u32 nent;
+	__u32 flags;
+	struct kvm_cpuid_entry2 entries[0];
+};
+
+The member 'flags' is used for passing flags from userspace.
+
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		BIT(0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC		BIT(1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT		BIT(2)
+
+struct kvm_cpuid_entry2 {
+	__u32 function;
+	__u32 index;
+	__u32 flags;
+	__u32 eax;
+	__u32 ebx;
+	__u32 ecx;
+	__u32 edx;
+	__u32 padding[3];
+};
+
+This ioctl returns x86 cpuid features which are emulated by
+kvm.Userspace can use the information returned by this ioctl to query
+which features are emulated by kvm instead of being present natively.
+
+Userspace invokes KVM_GET_EMULATED_CPUID by passing a kvm_cpuid2
+structure with the 'nent' field indicating the number of entries in
+the variable-size array 'entries'. If the number of entries is too low
+to describe the cpu capabilities, an error (E2BIG) is returned. If the
+number is too high, the 'nent' field is adjusted and an error (ENOMEM)
+is returned. If the number is just right, the 'nent' field is adjusted
+to the number of valid entries in the 'entries' array, which is then
+filled.
+
+The entries returned are the set CPUID bits of the respective features
+which kvm emulates, as returned by the CPUID instruction, with unknown
+or unsupported feature bits cleared.
+
+Features like x2apic, for example, may not be present in the host cpu
+but are exposed by kvm in KVM_GET_SUPPORTED_CPUID because they can be
+emulated efficiently and thus not included here.
+
+The fields in each entry are defined as follows:
+
+  function: the eax value used to obtain the entry
+  index: the ecx value used to obtain the entry (for entries that are
+         affected by ecx)
+  flags: an OR of zero or more of the following:
+        KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
+           if the index field is valid
+        KVM_CPUID_FLAG_STATEFUL_FUNC:
+           if cpuid for this function returns different values for successive
+           invocations; there will be several entries with the same function,
+           all with this flag set
+        KVM_CPUID_FLAG_STATE_READ_NEXT:
+           for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
+           the first entry to be read by a cpu
+   eax, ebx, ecx, edx: the values returned by the cpuid instruction for
+         this function/index combination
+
+
 6. Capabilities that can be enabled
 -----------------------------------
 
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 5d9a3033b3d7..d3a87780c70b 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -211,9 +211,9 @@ struct kvm_cpuid_entry2 {
 	__u32 padding[3];
 };
 
-#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1
-#define KVM_CPUID_FLAG_STATEFUL_FUNC    2
-#define KVM_CPUID_FLAG_STATE_READ_NEXT  4
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		BIT(0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC		BIT(1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT		BIT(2)
 
 /* for KVM_SET_CPUID2 */
 struct kvm_cpuid2 {
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 0a1e3b8b964d..78a4439bfdc5 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -219,8 +219,14 @@ static bool supported_xcr0_bit(unsigned bit)
 
 #define F(x) bit(X86_FEATURE_##x)
 
-static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
-			 u32 index, int *nent, int maxnent)
+static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry,
+				   u32 func, u32 index, int *nent, int maxnent)
+{
+	return 0;
+}
+
+static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
+				 u32 index, int *nent, int maxnent)
 {
 	int r;
 	unsigned f_nx = is_efer_nx() ? F(NX) : 0;
@@ -515,6 +521,15 @@ out:
 	return r;
 }
 
+static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func,
+			u32 idx, int *nent, int maxnent, unsigned int type)
+{
+	if (type == KVM_GET_EMULATED_CPUID)
+		return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent);
+
+	return __do_cpuid_ent(entry, func, idx, nent, maxnent);
+}
+
 #undef F
 
 struct kvm_cpuid_param {
@@ -529,8 +544,34 @@ static bool is_centaur_cpu(const struct kvm_cpuid_param *param)
 	return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR;
 }
 
-int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
-				      struct kvm_cpuid_entry2 __user *entries)
+static bool sanity_check_entries(struct kvm_cpuid_entry2 __user *entries,
+				 __u32 num_entries, unsigned int ioctl_type)
+{
+	int i;
+
+	if (ioctl_type != KVM_GET_EMULATED_CPUID)
+		return false;
+
+	/*
+	 * We want to make sure that ->padding is being passed clean from
+	 * userspace in case we want to use it for something in the future.
+	 *
+	 * Sadly, this wasn't enforced for KVM_GET_SUPPORTED_CPUID and so we
+	 * have to give ourselves satisfied only with the emulated side. /me
+	 * sheds a tear.
+	 */
+	for (i = 0; i < num_entries; i++) {
+		if (entries[i].padding[0] ||
+		    entries[i].padding[1] ||
+		    entries[i].padding[2])
+			return true;
+	}
+	return false;
+}
+
+int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
+			    struct kvm_cpuid_entry2 __user *entries,
+			    unsigned int type)
 {
 	struct kvm_cpuid_entry2 *cpuid_entries;
 	int limit, nent = 0, r = -E2BIG, i;
@@ -547,6 +588,10 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 		goto out;
 	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
 		cpuid->nent = KVM_MAX_CPUID_ENTRIES;
+
+	if (sanity_check_entries(entries, cpuid->nent, type))
+		return -EINVAL;
+
 	r = -ENOMEM;
 	cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent);
 	if (!cpuid_entries)
@@ -560,7 +605,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 			continue;
 
 		r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx,
-				&nent, cpuid->nent);
+				&nent, cpuid->nent, type);
 
 		if (r)
 			goto out_free;
@@ -571,7 +616,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 		limit = cpuid_entries[nent - 1].eax;
 		for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func)
 			r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx,
-				     &nent, cpuid->nent);
+				     &nent, cpuid->nent, type);
 
 		if (r)
 			goto out_free;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index b7fd07984888..f1e4895174b2 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -6,8 +6,9 @@
 void kvm_update_cpuid(struct kvm_vcpu *vcpu);
 struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
 					      u32 function, u32 index);
-int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
-				      struct kvm_cpuid_entry2 __user *entries);
+int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
+			    struct kvm_cpuid_entry2 __user *entries,
+			    unsigned int type);
 int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 			     struct kvm_cpuid *cpuid,
 			     struct kvm_cpuid_entry __user *entries);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index edf2a07df3a3..3d1e3ee8b39e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2564,6 +2564,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
 	case KVM_CAP_SET_TSS_ADDR:
 	case KVM_CAP_EXT_CPUID:
+	case KVM_CAP_EXT_EMUL_CPUID:
 	case KVM_CAP_CLOCKSOURCE:
 	case KVM_CAP_PIT:
 	case KVM_CAP_NOP_IO_DELAY:
@@ -2673,15 +2674,17 @@ long kvm_arch_dev_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
-	case KVM_GET_SUPPORTED_CPUID: {
+	case KVM_GET_SUPPORTED_CPUID:
+	case KVM_GET_EMULATED_CPUID: {
 		struct kvm_cpuid2 __user *cpuid_arg = argp;
 		struct kvm_cpuid2 cpuid;
 
 		r = -EFAULT;
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
 			goto out;
-		r = kvm_dev_ioctl_get_supported_cpuid(&cpuid,
-						      cpuid_arg->entries);
+
+		r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries,
+					    ioctl);
 		if (r)
 			goto out;
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e32e776f20c0..32c60b98ddf8 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -541,6 +541,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_TRACE_ENABLE          __KVM_DEPRECATED_MAIN_W_0x06
 #define KVM_TRACE_PAUSE           __KVM_DEPRECATED_MAIN_0x07
 #define KVM_TRACE_DISABLE         __KVM_DEPRECATED_MAIN_0x08
+#define KVM_GET_EMULATED_CPUID	  _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
 
 /*
  * Extension capability list.
@@ -668,6 +669,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_IRQ_XICS 92
 #define KVM_CAP_ARM_EL1_32BIT 93
 #define KVM_CAP_SPAPR_MULTITCE 94
+#define KVM_CAP_EXT_EMUL_CPUID 95
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3


From ec53500fae421e07c5d035918ca454a429732ef4 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Wed, 30 Oct 2013 11:02:17 -0600
Subject: kvm: Add VFIO device

So far we've succeeded at making KVM and VFIO mostly unaware of each
other, but areas are cropping up where a connection beyond eventfds
and irqfds needs to be made.  This patch introduces a KVM-VFIO device
that is meant to be a gateway for such interaction.  The user creates
the device and can add and remove VFIO groups to it via file
descriptors.  When a group is added, KVM verifies the group is valid
and gets a reference to it via the VFIO external user interface.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/devices/vfio.txt |  22 +++
 arch/x86/kvm/Kconfig                       |   1 +
 arch/x86/kvm/Makefile                      |   2 +-
 include/linux/kvm_host.h                   |   1 +
 include/uapi/linux/kvm.h                   |   4 +
 virt/kvm/Kconfig                           |   3 +
 virt/kvm/kvm_main.c                        |   5 +
 virt/kvm/vfio.c                            | 220 +++++++++++++++++++++++++++++
 8 files changed, 257 insertions(+), 1 deletion(-)
 create mode 100644 Documentation/virtual/kvm/devices/vfio.txt
 create mode 100644 virt/kvm/vfio.c

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/devices/vfio.txt b/Documentation/virtual/kvm/devices/vfio.txt
new file mode 100644
index 000000000000..ef51740c67ca
--- /dev/null
+++ b/Documentation/virtual/kvm/devices/vfio.txt
@@ -0,0 +1,22 @@
+VFIO virtual device
+===================
+
+Device types supported:
+  KVM_DEV_TYPE_VFIO
+
+Only one VFIO instance may be created per VM.  The created device
+tracks VFIO groups in use by the VM and features of those groups
+important to the correctness and acceleration of the VM.  As groups
+are enabled and disabled for use by the VM, KVM should be updated
+about their presence.  When registered with KVM, a reference to the
+VFIO-group is held by KVM.
+
+Groups:
+  KVM_DEV_VFIO_GROUP
+
+KVM_DEV_VFIO_GROUP attributes:
+  KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
+  KVM_DEV_VFIO_GROUP_DEL: Remove a VFIO group from VFIO-KVM device tracking
+
+For each, kvm_device_attr.addr points to an int32_t file descriptor
+for the VFIO group.
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index a47a3e54b964..b89c5db2b832 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -38,6 +38,7 @@ config KVM
 	select PERF_EVENTS
 	select HAVE_KVM_MSI
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
+	select KVM_VFIO
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index bf4fb04d0112..25d22b2d6509 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -9,7 +9,7 @@ KVM := ../../../virt/kvm
 
 kvm-y			+= $(KVM)/kvm_main.o $(KVM)/ioapic.o \
 				$(KVM)/coalesced_mmio.o $(KVM)/irq_comm.o \
-				$(KVM)/eventfd.o $(KVM)/irqchip.o
+				$(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o
 kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT)	+= $(KVM)/assigned-dev.o $(KVM)/iommu.o
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c9d4236ab442..7beddbd38ac7 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1058,6 +1058,7 @@ struct kvm_device *kvm_device_from_filp(struct file *filp);
 
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
+extern struct kvm_device_ops kvm_vfio_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 32c60b98ddf8..509cfbfe9658 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -845,6 +845,10 @@ struct kvm_device_attr {
 #define KVM_DEV_TYPE_FSL_MPIC_20	1
 #define KVM_DEV_TYPE_FSL_MPIC_42	2
 #define KVM_DEV_TYPE_XICS		3
+#define KVM_DEV_TYPE_VFIO		4
+#define  KVM_DEV_VFIO_GROUP			1
+#define   KVM_DEV_VFIO_GROUP_ADD			1
+#define   KVM_DEV_VFIO_GROUP_DEL			2
 
 /*
  * ioctls for VM fds
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 779262f59e25..fbe1a48bd629 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -27,3 +27,6 @@ config HAVE_KVM_MSI
 
 config HAVE_KVM_CPU_RELAX_INTERCEPT
        bool
+
+config KVM_VFIO
+       bool
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9ca014da134d..82c4047aa0e3 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2270,6 +2270,11 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 	case KVM_DEV_TYPE_XICS:
 		ops = &kvm_xics_ops;
 		break;
+#endif
+#ifdef CONFIG_KVM_VFIO
+	case KVM_DEV_TYPE_VFIO:
+		ops = &kvm_vfio_ops;
+		break;
 #endif
 	default:
 		return -ENODEV;
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
new file mode 100644
index 000000000000..597c258245ea
--- /dev/null
+++ b/virt/kvm/vfio.c
@@ -0,0 +1,220 @@
+/*
+ * VFIO-KVM bridge pseudo device
+ *
+ * Copyright (C) 2013 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ *
+ * 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.
+ */
+
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/kvm_host.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+
+struct kvm_vfio_group {
+	struct list_head node;
+	struct vfio_group *vfio_group;
+};
+
+struct kvm_vfio {
+	struct list_head group_list;
+	struct mutex lock;
+};
+
+static struct vfio_group *kvm_vfio_group_get_external_user(struct file *filep)
+{
+	struct vfio_group *vfio_group;
+	struct vfio_group *(*fn)(struct file *);
+
+	fn = symbol_get(vfio_group_get_external_user);
+	if (!fn)
+		return ERR_PTR(-EINVAL);
+
+	vfio_group = fn(filep);
+
+	symbol_put(vfio_group_get_external_user);
+
+	return vfio_group;
+}
+
+static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
+{
+	void (*fn)(struct vfio_group *);
+
+	fn = symbol_get(vfio_group_put_external_user);
+	if (!fn)
+		return;
+
+	fn(vfio_group);
+
+	symbol_put(vfio_group_put_external_user);
+}
+
+static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
+{
+	struct kvm_vfio *kv = dev->private;
+	struct vfio_group *vfio_group;
+	struct kvm_vfio_group *kvg;
+	void __user *argp = (void __user *)arg;
+	struct fd f;
+	int32_t fd;
+	int ret;
+
+	switch (attr) {
+	case KVM_DEV_VFIO_GROUP_ADD:
+		if (get_user(fd, (int32_t __user *)argp))
+			return -EFAULT;
+
+		f = fdget(fd);
+		if (!f.file)
+			return -EBADF;
+
+		vfio_group = kvm_vfio_group_get_external_user(f.file);
+		fdput(f);
+
+		if (IS_ERR(vfio_group))
+			return PTR_ERR(vfio_group);
+
+		mutex_lock(&kv->lock);
+
+		list_for_each_entry(kvg, &kv->group_list, node) {
+			if (kvg->vfio_group == vfio_group) {
+				mutex_unlock(&kv->lock);
+				kvm_vfio_group_put_external_user(vfio_group);
+				return -EEXIST;
+			}
+		}
+
+		kvg = kzalloc(sizeof(*kvg), GFP_KERNEL);
+		if (!kvg) {
+			mutex_unlock(&kv->lock);
+			kvm_vfio_group_put_external_user(vfio_group);
+			return -ENOMEM;
+		}
+
+		list_add_tail(&kvg->node, &kv->group_list);
+		kvg->vfio_group = vfio_group;
+
+		mutex_unlock(&kv->lock);
+
+		return 0;
+
+	case KVM_DEV_VFIO_GROUP_DEL:
+		if (get_user(fd, (int32_t __user *)argp))
+			return -EFAULT;
+
+		f = fdget(fd);
+		if (!f.file)
+			return -EBADF;
+
+		vfio_group = kvm_vfio_group_get_external_user(f.file);
+		fdput(f);
+
+		if (IS_ERR(vfio_group))
+			return PTR_ERR(vfio_group);
+
+		ret = -ENOENT;
+
+		mutex_lock(&kv->lock);
+
+		list_for_each_entry(kvg, &kv->group_list, node) {
+			if (kvg->vfio_group != vfio_group)
+				continue;
+
+			list_del(&kvg->node);
+			kvm_vfio_group_put_external_user(kvg->vfio_group);
+			kfree(kvg);
+			ret = 0;
+			break;
+		}
+
+		mutex_unlock(&kv->lock);
+
+		kvm_vfio_group_put_external_user(vfio_group);
+
+		return ret;
+	}
+
+	return -ENXIO;
+}
+
+static int kvm_vfio_set_attr(struct kvm_device *dev,
+			     struct kvm_device_attr *attr)
+{
+	switch (attr->group) {
+	case KVM_DEV_VFIO_GROUP:
+		return kvm_vfio_set_group(dev, attr->attr, attr->addr);
+	}
+
+	return -ENXIO;
+}
+
+static int kvm_vfio_has_attr(struct kvm_device *dev,
+			     struct kvm_device_attr *attr)
+{
+	switch (attr->group) {
+	case KVM_DEV_VFIO_GROUP:
+		switch (attr->attr) {
+		case KVM_DEV_VFIO_GROUP_ADD:
+		case KVM_DEV_VFIO_GROUP_DEL:
+			return 0;
+		}
+
+		break;
+	}
+
+	return -ENXIO;
+}
+
+static void kvm_vfio_destroy(struct kvm_device *dev)
+{
+	struct kvm_vfio *kv = dev->private;
+	struct kvm_vfio_group *kvg, *tmp;
+
+	list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
+		kvm_vfio_group_put_external_user(kvg->vfio_group);
+		list_del(&kvg->node);
+		kfree(kvg);
+	}
+
+	kfree(kv);
+	kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */
+}
+
+static int kvm_vfio_create(struct kvm_device *dev, u32 type)
+{
+	struct kvm_device *tmp;
+	struct kvm_vfio *kv;
+
+	/* Only one VFIO "device" per VM */
+	list_for_each_entry(tmp, &dev->kvm->devices, vm_node)
+		if (tmp->ops == &kvm_vfio_ops)
+			return -EBUSY;
+
+	kv = kzalloc(sizeof(*kv), GFP_KERNEL);
+	if (!kv)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&kv->group_list);
+	mutex_init(&kv->lock);
+
+	dev->private = kv;
+
+	return 0;
+}
+
+struct kvm_device_ops kvm_vfio_ops = {
+	.name = "kvm-vfio",
+	.create = kvm_vfio_create,
+	.destroy = kvm_vfio_destroy,
+	.set_attr = kvm_vfio_set_attr,
+	.has_attr = kvm_vfio_has_attr,
+};
-- 
cgit v1.2.3


From 6beda1e5dd269144d836ccc76141b2cc82b296ba Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <artagnon@gmail.com>
Date: Thu, 31 Oct 2013 16:16:36 +0530
Subject: Documentation/kvm: add a 00-INDEX file

Cc: Gleb Natapov <gleb@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Ramkumar Ramachandra <artagnon@gmail.com>
[Some editing. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/00-INDEX | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)
 create mode 100644 Documentation/virtual/kvm/00-INDEX

(limited to 'Documentation')

diff --git a/Documentation/virtual/kvm/00-INDEX b/Documentation/virtual/kvm/00-INDEX
new file mode 100644
index 000000000000..641ec9220179
--- /dev/null
+++ b/Documentation/virtual/kvm/00-INDEX
@@ -0,0 +1,24 @@
+00-INDEX
+	- this file.
+api.txt
+	- KVM userspace API.
+cpuid.txt
+	- KVM-specific cpuid leaves (x86).
+devices/
+	- KVM_CAP_DEVICE_CTRL userspace API.
+hypercalls.txt
+	- KVM hypercalls.
+locking.txt
+	- notes on KVM locks.
+mmu.txt
+	- the x86 kvm shadow mmu.
+msr.txt
+	- KVM-specific MSRs (x86).
+nested-vmx.txt
+	- notes on nested virtualization for Intel x86 processors.
+ppc-pv.txt
+	- the paravirtualization interface on PowerPC.
+review-checklist.txt
+	- review checklist for KVM patches.
+timekeeping.txt
+	- timekeeping virtualization for x86-based architectures.
-- 
cgit v1.2.3