From 0f8a4de3e088797576ac76200b634b802e5c7781 Mon Sep 17 00:00:00 2001
From: Christoffer Dall
Date: Tue, 26 Aug 2014 14:00:37 +0200
Subject: KVM: Unconditionally export KVM_CAP_READONLY_MEM

The idea between capabilities and the KVM_CHECK_EXTENSION ioctl is that
userspace can, at run-time, determine if a feature is supported or not.
This allows KVM to being supporting a new feature with a new kernel
version without any need to update user space.  Unfortunately, since the
definition of KVM_CAP_READONLY_MEM was guarded by #ifdef
__KVM_HAVE_READONLY_MEM, such discovery still required a user space
update.

Therefore, unconditionally export KVM_CAP_READONLY_MEM and change the
in-kernel conditional to rely on __KVM_HAVE_READONLY_MEM.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 virt/kvm/kvm_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'virt')

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5a0817ee996e..1d03967def40 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -708,7 +708,7 @@ static int check_memory_region_flags(struct kvm_userspace_memory_region *mem)
 {
 	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
 
-#ifdef KVM_CAP_READONLY_MEM
+#ifdef __KVM_HAVE_READONLY_MEM
 	valid_flags |= KVM_MEM_READONLY;
 #endif
 
-- 
cgit v1.2.3-55-g7522


From 13a34e067eab24fec882e1834fbf2cc31911d474 Mon Sep 17 00:00:00 2001
From: Radim Krčmář
Date: Thu, 28 Aug 2014 15:13:03 +0200
Subject: KVM: remove garbage arg to *hardware_{en,dis}able

In the beggining was on_each_cpu(), which required an unused argument to
kvm_arch_ops.hardware_{en,dis}able, but this was soon forgotten.

Remove unnecessary arguments that stem from this.

Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm/include/asm/kvm_host.h     |  2 +-
 arch/arm/kvm/arm.c                  |  2 +-
 arch/arm64/include/asm/kvm_host.h   |  2 +-
 arch/ia64/kvm/kvm-ia64.c            |  4 ++--
 arch/mips/include/asm/kvm_host.h    |  2 +-
 arch/mips/kvm/mips.c                |  2 +-
 arch/powerpc/include/asm/kvm_host.h |  2 +-
 arch/powerpc/kvm/powerpc.c          |  2 +-
 arch/s390/include/asm/kvm_host.h    |  2 +-
 arch/s390/kvm/kvm-s390.c            |  2 +-
 arch/x86/include/asm/kvm_host.h     |  4 ++--
 arch/x86/kvm/svm.c                  |  4 ++--
 arch/x86/kvm/vmx.c                  |  4 ++--
 arch/x86/kvm/x86.c                  | 12 ++++++------
 include/linux/kvm_host.h            |  4 ++--
 virt/kvm/kvm_main.c                 |  4 ++--
 16 files changed, 27 insertions(+), 27 deletions(-)

(limited to 'virt')

diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index aea259e9431f..032a8538318a 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -230,7 +230,7 @@ static inline void vgic_arch_setup(const struct vgic_params *vgic)
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
-static inline void kvm_arch_hardware_disable(void *garbage) {}
+static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 132bb0d9c5ad..005a7b5fd0aa 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -87,7 +87,7 @@ struct kvm_vcpu __percpu **kvm_get_running_vcpus(void)
 	return &kvm_arm_running_vcpu;
 }
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	return 0;
 }
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index b5045e3e05f8..be9970a59497 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -242,7 +242,7 @@ static inline void vgic_arch_setup(const struct vgic_params *vgic)
 	}
 }
 
-static inline void kvm_arch_hardware_disable(void *garbage) {}
+static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 5e14dcaf844e..ec6b9acb6bea 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -125,7 +125,7 @@ long ia64_pal_vp_create(u64 *vpd, u64 *host_iva, u64 *opt_handler)
 
 static  DEFINE_SPINLOCK(vp_lock);
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	long  status;
 	long  tmp_base;
@@ -160,7 +160,7 @@ int kvm_arch_hardware_enable(void *garbage)
 	return 0;
 }
 
-void kvm_arch_hardware_disable(void *garbage)
+void kvm_arch_hardware_disable(void)
 {
 
 	long status;
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 0b24d6622ec1..f2c249796ea8 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -762,7 +762,7 @@ extern int kvm_mips_trans_mtc0(uint32_t inst, uint32_t *opc,
 extern void kvm_mips_dump_stats(struct kvm_vcpu *vcpu);
 extern unsigned long kvm_mips_get_ramsize(struct kvm *kvm);
 
-static inline void kvm_arch_hardware_disable(void *garbage) {}
+static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_free_memslot(struct kvm *kvm,
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 0ec7490d70bd..e3b21e51ff7e 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -77,7 +77,7 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	return 0;
 }
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 237cc0cc80a2..604000882352 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -682,7 +682,7 @@ struct kvm_vcpu_arch {
 #define __KVM_HAVE_ARCH_WQP
 #define __KVM_HAVE_CREATE_DEVICE
 
-static inline void kvm_arch_hardware_disable(void *garbage) {}
+static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 72c3fc085207..da505237a664 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -384,7 +384,7 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 }
 EXPORT_SYMBOL_GPL(kvmppc_ld);
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	return 0;
 }
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index f6dd90684b97..a76a124dff48 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -452,7 +452,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 extern int sie64a(struct kvm_s390_sie_block *, u64 *);
 extern char sie_exit;
 
-static inline void kvm_arch_hardware_disable(void *garbage) {}
+static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_check_processor_compat(void *rtn) {}
 static inline void kvm_arch_exit(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index b8fe1ae777db..628e992eeded 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -100,7 +100,7 @@ int test_vfacility(unsigned long nr)
 }
 
 /* Section: not file related */
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	/* every s390 is virtualization enabled ;-) */
 	return 0;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 567fface45f8..73e4149eda33 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -661,8 +661,8 @@ struct msr_data {
 struct kvm_x86_ops {
 	int (*cpu_has_kvm_support)(void);          /* __init */
 	int (*disabled_by_bios)(void);             /* __init */
-	int (*hardware_enable)(void *dummy);
-	void (*hardware_disable)(void *dummy);
+	int (*hardware_enable)(void);
+	void (*hardware_disable)(void);
 	void (*check_processor_compatibility)(void *rtn);
 	int (*hardware_setup)(void);               /* __init */
 	void (*hardware_unsetup)(void);            /* __exit */
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 7cd230e55118..8ef704037370 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -622,7 +622,7 @@ static int has_svm(void)
 	return 1;
 }
 
-static void svm_hardware_disable(void *garbage)
+static void svm_hardware_disable(void)
 {
 	/* Make sure we clean up behind us */
 	if (static_cpu_has(X86_FEATURE_TSCRATEMSR))
@@ -633,7 +633,7 @@ static void svm_hardware_disable(void *garbage)
 	amd_pmu_disable_virt();
 }
 
-static int svm_hardware_enable(void *garbage)
+static int svm_hardware_enable(void)
 {
 
 	struct svm_cpu_data *sd;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index d70550d0bcff..671ca5edc709 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2728,7 +2728,7 @@ static void kvm_cpu_vmxon(u64 addr)
 			: "memory", "cc");
 }
 
-static int hardware_enable(void *garbage)
+static int hardware_enable(void)
 {
 	int cpu = raw_smp_processor_id();
 	u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
@@ -2792,7 +2792,7 @@ static void kvm_cpu_vmxoff(void)
 	asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
 }
 
-static void hardware_disable(void *garbage)
+static void hardware_disable(void)
 {
 	if (vmm_exclusive) {
 		vmclear_local_loaded_vmcss();
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c10408ef9ab1..a375dfc42f6a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -246,7 +246,7 @@ void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
 }
 EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
 
-static void drop_user_return_notifiers(void *ignore)
+static void drop_user_return_notifiers(void)
 {
 	unsigned int cpu = smp_processor_id();
 	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
@@ -6959,7 +6959,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector)
 	kvm_rip_write(vcpu, 0);
 }
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	struct kvm *kvm;
 	struct kvm_vcpu *vcpu;
@@ -6970,7 +6970,7 @@ int kvm_arch_hardware_enable(void *garbage)
 	bool stable, backwards_tsc = false;
 
 	kvm_shared_msr_cpu_online();
-	ret = kvm_x86_ops->hardware_enable(garbage);
+	ret = kvm_x86_ops->hardware_enable();
 	if (ret != 0)
 		return ret;
 
@@ -7051,10 +7051,10 @@ int kvm_arch_hardware_enable(void *garbage)
 	return 0;
 }
 
-void kvm_arch_hardware_disable(void *garbage)
+void kvm_arch_hardware_disable(void)
 {
-	kvm_x86_ops->hardware_disable(garbage);
-	drop_user_return_notifiers(garbage);
+	kvm_x86_ops->hardware_disable();
+	drop_user_return_notifiers();
 }
 
 int kvm_arch_hardware_setup(void)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index e1cb915a1096..e098dce179df 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -630,8 +630,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);
 
-int kvm_arch_hardware_enable(void *garbage);
-void kvm_arch_hardware_disable(void *garbage);
+int kvm_arch_hardware_enable(void);
+void kvm_arch_hardware_disable(void);
 int kvm_arch_hardware_setup(void);
 void kvm_arch_hardware_unsetup(void);
 void kvm_arch_check_processor_compat(void *rtn);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 1d03967def40..7176929a4cda 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2669,7 +2669,7 @@ static void hardware_enable_nolock(void *junk)
 
 	cpumask_set_cpu(cpu, cpus_hardware_enabled);
 
-	r = kvm_arch_hardware_enable(NULL);
+	r = kvm_arch_hardware_enable();
 
 	if (r) {
 		cpumask_clear_cpu(cpu, cpus_hardware_enabled);
@@ -2694,7 +2694,7 @@ static void hardware_disable_nolock(void *junk)
 	if (!cpumask_test_cpu(cpu, cpus_hardware_enabled))
 		return;
 	cpumask_clear_cpu(cpu, cpus_hardware_enabled);
-	kvm_arch_hardware_disable(NULL);
+	kvm_arch_hardware_disable();
 }
 
 static void hardware_disable(void)
-- 
cgit v1.2.3-55-g7522


From 00f034a12fdd81210d58116326d92780aac5c238 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini
Date: Wed, 20 Aug 2014 14:29:21 +0200
Subject: KVM: do not bias the generation number in kvm_current_mmio_generation

The next patch will give a meaning (a la seqcount) to the low bit of the
generation number.  Ensure that it matches between kvm->memslots->generation
and kvm_current_mmio_generation().

Cc: stable@vger.kernel.org
Reviewed-by: David Matlack <dmatlack@google.com>
Reviewed-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu.c  | 7 +------
 virt/kvm/kvm_main.c | 7 +++++++
 2 files changed, 8 insertions(+), 6 deletions(-)

(limited to 'virt')

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 931467881da7..323c3f5f5c84 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -236,12 +236,7 @@ static unsigned int get_mmio_spte_generation(u64 spte)
 
 static unsigned int kvm_current_mmio_generation(struct kvm *kvm)
 {
-	/*
-	 * Init kvm generation close to MMIO_MAX_GEN to easily test the
-	 * code of handling generation number wrap-around.
-	 */
-	return (kvm_memslots(kvm)->generation +
-		      MMIO_MAX_GEN - 150) & MMIO_GEN_MASK;
+	return kvm_memslots(kvm)->generation & MMIO_GEN_MASK;
 }
 
 static void mark_mmio_spte(struct kvm *kvm, u64 *sptep, u64 gfn,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7176929a4cda..0bfdb673db26 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -477,6 +477,13 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
 	if (!kvm->memslots)
 		goto out_err_no_srcu;
+
+	/*
+	 * Init kvm generation close to the maximum to easily test the
+	 * code of handling generation number wrap-around.
+	 */
+	kvm->memslots->generation = -150;
+
 	kvm_init_memslots_id(kvm);
 	if (init_srcu_struct(&kvm->srcu))
 		goto out_err_no_srcu;
-- 
cgit v1.2.3-55-g7522


From ee3d1570b58677885b4552bce8217fda7b226a68 Mon Sep 17 00:00:00 2001
From: David Matlack
Date: Mon, 18 Aug 2014 15:46:06 -0700
Subject: kvm: fix potentially corrupt mmio cache

vcpu exits and memslot mutations can run concurrently as long as the
vcpu does not aquire the slots mutex. Thus it is theoretically possible
for memslots to change underneath a vcpu that is handling an exit.

If we increment the memslot generation number again after
synchronize_srcu_expedited(), vcpus can safely cache memslot generation
without maintaining a single rcu_dereference through an entire vm exit.
And much of the x86/kvm code does not maintain a single rcu_dereference
of the current memslots during each exit.

We can prevent the following case:

   vcpu (CPU 0)                             | thread (CPU 1)
--------------------------------------------+--------------------------
1  vm exit                                  |
2  srcu_read_unlock(&kvm->srcu)             |
3  decide to cache something based on       |
     old memslots                           |
4                                           | change memslots
                                            | (increments generation)
5                                           | synchronize_srcu(&kvm->srcu);
6  retrieve generation # from new memslots  |
7  tag cache with new memslot generation    |
8  srcu_read_unlock(&kvm->srcu)             |
...                                         |
   <action based on cache occurs even       |
    though the caching decision was based   |
    on the old memslots>                    |
...                                         |
   <action *continues* to occur until next  |
    memslot generation change, which may    |
    be never>                               |
                                            |

By incrementing the generation after synchronizing with kvm->srcu readers,
we ensure that the generation retrieved in (6) will become invalid soon
after (8).

Keeping the existing increment is not strictly necessary, but we
do keep it and just move it for consistency from update_memslots to
install_new_memslots.  It invalidates old cached MMIOs immediately,
instead of having to wait for the end of synchronize_srcu_expedited,
which makes the code more clearly correct in case CPU 1 is preempted
right after synchronize_srcu() returns.

To avoid halving the generation space in SPTEs, always presume that the
low bit of the generation is zero when reconstructing a generation number
out of an SPTE.  This effectively disables MMIO caching in SPTEs during
the call to synchronize_srcu_expedited.  Using the low bit this way is
somewhat like a seqcount---where the protected thing is a cache, and
instead of retrying we can simply punt if we observe the low bit to be 1.

Cc: stable@vger.kernel.org
Signed-off-by: David Matlack <dmatlack@google.com>
Reviewed-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Reviewed-by: David Matlack <dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virtual/kvm/mmu.txt | 14 ++++++++++++++
 arch/x86/kvm/mmu.c                | 20 ++++++++++++--------
 virt/kvm/kvm_main.c               | 23 ++++++++++++++++-------
 3 files changed, 42 insertions(+), 15 deletions(-)

(limited to 'virt')

diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index 290894176142..53838d9c6295 100644
--- a/Documentation/virtual/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
@@ -425,6 +425,20 @@ fault through the slow path.
 Since only 19 bits are used to store generation-number on mmio spte, all
 pages are zapped when there is an overflow.
 
+Unfortunately, a single memory access might access kvm_memslots(kvm) multiple
+times, the last one happening when the generation number is retrieved and
+stored into the MMIO spte.  Thus, the MMIO spte might be created based on
+out-of-date information, but with an up-to-date generation number.
+
+To avoid this, the generation number is incremented again after synchronize_srcu
+returns; thus, the low bit of kvm_memslots(kvm)->generation is only 1 during a
+memslot update, while some SRCU readers might be using the old copy.  We do not
+want to use an MMIO sptes created with an odd generation number, and we can do
+this without losing a bit in the MMIO spte.  The low bit of the generation
+is not stored in MMIO spte, and presumed zero when it is extracted out of the
+spte.  If KVM is unlucky and creates an MMIO spte while the low bit is 1,
+the next access to the spte will always be a cache miss.
+
 
 Further reading
 ===============
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 323c3f5f5c84..96515957ba82 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -199,16 +199,20 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask)
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);
 
 /*
- * spte bits of bit 3 ~ bit 11 are used as low 9 bits of generation number,
- * the bits of bits 52 ~ bit 61 are used as high 10 bits of generation
- * number.
+ * the low bit of the generation number is always presumed to be zero.
+ * This disables mmio caching during memslot updates.  The concept is
+ * similar to a seqcount but instead of retrying the access we just punt
+ * and ignore the cache.
+ *
+ * spte bits 3-11 are used as bits 1-9 of the generation number,
+ * the bits 52-61 are used as bits 10-19 of the generation number.
  */
-#define MMIO_SPTE_GEN_LOW_SHIFT		3
+#define MMIO_SPTE_GEN_LOW_SHIFT		2
 #define MMIO_SPTE_GEN_HIGH_SHIFT	52
 
-#define MMIO_GEN_SHIFT			19
-#define MMIO_GEN_LOW_SHIFT		9
-#define MMIO_GEN_LOW_MASK		((1 << MMIO_GEN_LOW_SHIFT) - 1)
+#define MMIO_GEN_SHIFT			20
+#define MMIO_GEN_LOW_SHIFT		10
+#define MMIO_GEN_LOW_MASK		((1 << MMIO_GEN_LOW_SHIFT) - 2)
 #define MMIO_GEN_MASK			((1 << MMIO_GEN_SHIFT) - 1)
 #define MMIO_MAX_GEN			((1 << MMIO_GEN_SHIFT) - 1)
 
@@ -4428,7 +4432,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm)
 	 * The very rare case: if the generation-number is round,
 	 * zap all shadow pages.
 	 */
-	if (unlikely(kvm_current_mmio_generation(kvm) >= MMIO_MAX_GEN)) {
+	if (unlikely(kvm_current_mmio_generation(kvm) == 0)) {
 		printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n");
 		kvm_mmu_invalidate_zap_all_pages(kvm);
 	}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 0bfdb673db26..bb8641b5d83b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -95,8 +95,6 @@ static int hardware_enable_all(void);
 static void hardware_disable_all(void);
 
 static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
-static void update_memslots(struct kvm_memslots *slots,
-			    struct kvm_memory_slot *new, u64 last_generation);
 
 static void kvm_release_pfn_dirty(pfn_t pfn);
 static void mark_page_dirty_in_slot(struct kvm *kvm,
@@ -695,8 +693,7 @@ static void sort_memslots(struct kvm_memslots *slots)
 }
 
 static void update_memslots(struct kvm_memslots *slots,
-			    struct kvm_memory_slot *new,
-			    u64 last_generation)
+			    struct kvm_memory_slot *new)
 {
 	if (new) {
 		int id = new->id;
@@ -707,8 +704,6 @@ static void update_memslots(struct kvm_memslots *slots,
 		if (new->npages != npages)
 			sort_memslots(slots);
 	}
-
-	slots->generation = last_generation + 1;
 }
 
 static int check_memory_region_flags(struct kvm_userspace_memory_region *mem)
@@ -730,10 +725,24 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
 {
 	struct kvm_memslots *old_memslots = kvm->memslots;
 
-	update_memslots(slots, new, kvm->memslots->generation);
+	/*
+	 * Set the low bit in the generation, which disables SPTE caching
+	 * until the end of synchronize_srcu_expedited.
+	 */
+	WARN_ON(old_memslots->generation & 1);
+	slots->generation = old_memslots->generation + 1;
+
+	update_memslots(slots, new);
 	rcu_assign_pointer(kvm->memslots, slots);
 	synchronize_srcu_expedited(&kvm->srcu);
 
+	/*
+	 * Increment the new memslot generation a second time. This prevents
+	 * vm exits that race with memslot updates from caching a memslot
+	 * generation that will (potentially) be valid forever.
+	 */
+	slots->generation++;
+
 	kvm_arch_memslots_updated(kvm);
 
 	return old_memslots;
-- 
cgit v1.2.3-55-g7522


From 34656113182b704682e23d1363417536addfec97 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger
Date: Thu, 4 Sep 2014 21:13:31 +0200
Subject: KVM: remove redundant check of in_spin_loop

The expression `vcpu->spin_loop.in_spin_loop' is always true,
because it is evaluated only when the condition
`!vcpu->spin_loop.in_spin_loop' is false.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 virt/kvm/kvm_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'virt')

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index bb8641b5d83b..cc7bd286d135 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1785,8 +1785,7 @@ static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
 	bool eligible;
 
 	eligible = !vcpu->spin_loop.in_spin_loop ||
-			(vcpu->spin_loop.in_spin_loop &&
-			 vcpu->spin_loop.dy_eligible);
+		    vcpu->spin_loop.dy_eligible;
 
 	if (vcpu->spin_loop.in_spin_loop)
 		kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible);
-- 
cgit v1.2.3-55-g7522


From a13f533b2f1d53a7c0baa7490498caeab7bc8ba5 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger
Date: Thu, 4 Sep 2014 21:13:32 +0200
Subject: KVM: remove redundant assigment of return value in kvm_dev_ioctl

The first statement of kvm_dev_ioctl is
        long r = -EINVAL;

No need to reassign the same value.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 virt/kvm/kvm_main.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'virt')

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index cc7bd286d135..de1ae82ba192 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2627,7 +2627,6 @@ static long kvm_dev_ioctl(struct file *filp,
 
 	switch (ioctl) {
 	case KVM_GET_API_VERSION:
-		r = -EINVAL;
 		if (arg)
 			goto out;
 		r = KVM_API_VERSION;
@@ -2639,7 +2638,6 @@ static long kvm_dev_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_check_extension_generic(NULL, arg);
 		break;
 	case KVM_GET_VCPU_MMAP_SIZE:
-		r = -EINVAL;
 		if (arg)
 			goto out;
 		r = PAGE_SIZE;     /* struct kvm_run */
-- 
cgit v1.2.3-55-g7522


From f2a25160887e00434ce1361007009120e1fecbda Mon Sep 17 00:00:00 2001
From: Christian Borntraeger
Date: Thu, 4 Sep 2014 21:13:33 +0200
Subject: KVM: remove redundant assignments in __kvm_set_memory_region

__kvm_set_memory_region sets r to EINVAL very early.
Doing it again is not necessary. The same is true later on, where
r is assigned -ENOMEM twice.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 virt/kvm/kvm_main.c | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'virt')

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index de1ae82ba192..c338599804e0 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -793,7 +793,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
 	npages = mem->memory_size >> PAGE_SHIFT;
 
-	r = -EINVAL;
 	if (npages > KVM_MEM_MAX_NR_PAGES)
 		goto out;
 
@@ -807,7 +806,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	new.npages = npages;
 	new.flags = mem->flags;
 
-	r = -EINVAL;
 	if (npages) {
 		if (!old.npages)
 			change = KVM_MR_CREATE;
@@ -863,7 +861,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	}
 
 	if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) {
-		r = -ENOMEM;
 		slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
 				GFP_KERNEL);
 		if (!slots)
-- 
cgit v1.2.3-55-g7522


From 184564efae4d775225c8fe3b762a56956fb1f827 Mon Sep 17 00:00:00 2001
From: Zhang Haoyu
Date: Thu, 11 Sep 2014 16:47:04 +0800
Subject: kvm: ioapic: conditionally delay irq delivery duringeoi broadcast

Currently, we call ioapic_service() immediately when we find the irq is still
active during eoi broadcast. But for real hardware, there's some delay between
the EOI writing and irq delivery.  If we do not emulate this behavior, and
re-inject the interrupt immediately after the guest sends an EOI and re-enables
interrupts, a guest might spend all its time in the ISR if it has a broken
handler for a level-triggered interrupt.

Such livelock actually happens with Windows guests when resuming from
hibernation.

As there's no way to recognize the broken handle from new raised ones, this patch
delays an interrupt if 10.000 consecutive EOIs found that the interrupt was
still high.  The guest can then make a little forward progress, until a proper
IRQ handler is set or until some detection routine in the guest (such as
Linux's note_interrupt()) recognizes the situation.

Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Zhang Haoyu <zhanghy@sangfor.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/trace/events/kvm.h | 20 ++++++++++++++++++++
 virt/kvm/ioapic.c          | 46 ++++++++++++++++++++++++++++++++++++++++++++--
 virt/kvm/ioapic.h          |  2 ++
 3 files changed, 66 insertions(+), 2 deletions(-)

(limited to 'virt')

diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 908925ace776..ab679c395042 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -95,6 +95,26 @@ TRACE_EVENT(kvm_ioapic_set_irq,
 		  __entry->coalesced ? " (coalesced)" : "")
 );
 
+TRACE_EVENT(kvm_ioapic_delayed_eoi_inj,
+	    TP_PROTO(__u64 e),
+	    TP_ARGS(e),
+
+	TP_STRUCT__entry(
+		__field(	__u64,		e		)
+	),
+
+	TP_fast_assign(
+		__entry->e		= e;
+	),
+
+	TP_printk("dst %x vec=%u (%s|%s|%s%s)",
+		  (u8)(__entry->e >> 56), (u8)__entry->e,
+		  __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode),
+		  (__entry->e & (1<<11)) ? "logical" : "physical",
+		  (__entry->e & (1<<15)) ? "level" : "edge",
+		  (__entry->e & (1<<16)) ? "|masked" : "")
+);
+
 TRACE_EVENT(kvm_msi_set_irq,
 	    TP_PROTO(__u64 address, __u64 data),
 	    TP_ARGS(address, data),
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index e8ce34c9db32..0ba4057d271b 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -405,6 +405,26 @@ void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id)
 	spin_unlock(&ioapic->lock);
 }
 
+static void kvm_ioapic_eoi_inject_work(struct work_struct *work)
+{
+	int i;
+	struct kvm_ioapic *ioapic = container_of(work, struct kvm_ioapic,
+						 eoi_inject.work);
+	spin_lock(&ioapic->lock);
+	for (i = 0; i < IOAPIC_NUM_PINS; i++) {
+		union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
+
+		if (ent->fields.trig_mode != IOAPIC_LEVEL_TRIG)
+			continue;
+
+		if (ioapic->irr & (1 << i) && !ent->fields.remote_irr)
+			ioapic_service(ioapic, i, false);
+	}
+	spin_unlock(&ioapic->lock);
+}
+
+#define IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT 10000
+
 static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
 			struct kvm_ioapic *ioapic, int vector, int trigger_mode)
 {
@@ -435,8 +455,26 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
 
 		ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
 		ent->fields.remote_irr = 0;
-		if (ioapic->irr & (1 << i))
-			ioapic_service(ioapic, i, false);
+		if (!ent->fields.mask && (ioapic->irr & (1 << i))) {
+			++ioapic->irq_eoi[i];
+			if (ioapic->irq_eoi[i] == IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT) {
+				/*
+				 * Real hardware does not deliver the interrupt
+				 * immediately during eoi broadcast, and this
+				 * lets a buggy guest make slow progress
+				 * even if it does not correctly handle a
+				 * level-triggered interrupt.  Emulate this
+				 * behavior if we detect an interrupt storm.
+				 */
+				schedule_delayed_work(&ioapic->eoi_inject, HZ / 100);
+				ioapic->irq_eoi[i] = 0;
+				trace_kvm_ioapic_delayed_eoi_inj(ent->bits);
+			} else {
+				ioapic_service(ioapic, i, false);
+			}
+		} else {
+			ioapic->irq_eoi[i] = 0;
+		}
 	}
 }
 
@@ -565,12 +603,14 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
 {
 	int i;
 
+	cancel_delayed_work_sync(&ioapic->eoi_inject);
 	for (i = 0; i < IOAPIC_NUM_PINS; i++)
 		ioapic->redirtbl[i].fields.mask = 1;
 	ioapic->base_address = IOAPIC_DEFAULT_BASE_ADDRESS;
 	ioapic->ioregsel = 0;
 	ioapic->irr = 0;
 	ioapic->id = 0;
+	memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS);
 	rtc_irq_eoi_tracking_reset(ioapic);
 	update_handled_vectors(ioapic);
 }
@@ -589,6 +629,7 @@ int kvm_ioapic_init(struct kvm *kvm)
 	if (!ioapic)
 		return -ENOMEM;
 	spin_lock_init(&ioapic->lock);
+	INIT_DELAYED_WORK(&ioapic->eoi_inject, kvm_ioapic_eoi_inject_work);
 	kvm->arch.vioapic = ioapic;
 	kvm_ioapic_reset(ioapic);
 	kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
@@ -609,6 +650,7 @@ void kvm_ioapic_destroy(struct kvm *kvm)
 {
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
 
+	cancel_delayed_work_sync(&ioapic->eoi_inject);
 	if (ioapic) {
 		kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
 		kvm->arch.vioapic = NULL;
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index 90d43e95dcf8..e23b70634f1e 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -59,6 +59,8 @@ struct kvm_ioapic {
 	spinlock_t lock;
 	DECLARE_BITMAP(handled_vectors, 256);
 	struct rtc_status rtc_status;
+	struct delayed_work eoi_inject;
+	u32 irq_eoi[IOAPIC_NUM_PINS];
 };
 
 #ifdef DEBUG
-- 
cgit v1.2.3-55-g7522


From d60eacb07053142bfb9b41582074a89a790a9d46 Mon Sep 17 00:00:00 2001
From: Will Deacon
Date: Tue, 2 Sep 2014 10:27:33 +0100
Subject: KVM: device: add simple registration mechanism for kvm_device_ops

kvm_ioctl_create_device currently has knowledge of all the device types
and their associated ops. This is fairly inflexible when adding support
for new in-kernel device emulations, so move what we currently have out
into a table, which can support dynamic registration of ops by new
drivers for virtual hardware.

Cc: Alex Williamson <Alex.Williamson@redhat.com>
Cc: Alex Graf <agraf@suse.de>
Cc: Gleb Natapov <gleb@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h |  1 +
 include/uapi/linux/kvm.h | 22 +++++++++++-----
 virt/kvm/kvm_main.c      | 65 ++++++++++++++++++++++++++++--------------------
 3 files changed, 55 insertions(+), 33 deletions(-)

(limited to 'virt')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index e098dce179df..b6e954742951 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1064,6 +1064,7 @@ struct kvm_device_ops {
 void kvm_device_get(struct kvm_device *dev);
 void kvm_device_put(struct kvm_device *dev);
 struct kvm_device *kvm_device_from_filp(struct file *filp);
+int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type);
 
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 0695a1e3e332..60768822b140 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -943,15 +943,25 @@ struct kvm_device_attr {
 	__u64	addr;		/* userspace address of attr data */
 };
 
-#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
-#define KVM_DEV_TYPE_ARM_VGIC_V2	5
-#define KVM_DEV_TYPE_FLIC		6
+
+enum kvm_device_type {
+	KVM_DEV_TYPE_FSL_MPIC_20	= 1,
+#define KVM_DEV_TYPE_FSL_MPIC_20	KVM_DEV_TYPE_FSL_MPIC_20
+	KVM_DEV_TYPE_FSL_MPIC_42,
+#define KVM_DEV_TYPE_FSL_MPIC_42	KVM_DEV_TYPE_FSL_MPIC_42
+	KVM_DEV_TYPE_XICS,
+#define KVM_DEV_TYPE_XICS		KVM_DEV_TYPE_XICS
+	KVM_DEV_TYPE_VFIO,
+#define KVM_DEV_TYPE_VFIO		KVM_DEV_TYPE_VFIO
+	KVM_DEV_TYPE_ARM_VGIC_V2,
+#define KVM_DEV_TYPE_ARM_VGIC_V2	KVM_DEV_TYPE_ARM_VGIC_V2
+	KVM_DEV_TYPE_FLIC,
+#define KVM_DEV_TYPE_FLIC		KVM_DEV_TYPE_FLIC
+	KVM_DEV_TYPE_MAX,
+};
 
 /*
  * ioctls for VM fds
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index c338599804e0..686d783387a0 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2272,44 +2272,55 @@ struct kvm_device *kvm_device_from_filp(struct file *filp)
 	return filp->private_data;
 }
 
-static int kvm_ioctl_create_device(struct kvm *kvm,
-				   struct kvm_create_device *cd)
-{
-	struct kvm_device_ops *ops = NULL;
-	struct kvm_device *dev;
-	bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
-	int ret;
-
-	switch (cd->type) {
+static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
 #ifdef CONFIG_KVM_MPIC
-	case KVM_DEV_TYPE_FSL_MPIC_20:
-	case KVM_DEV_TYPE_FSL_MPIC_42:
-		ops = &kvm_mpic_ops;
-		break;
+	[KVM_DEV_TYPE_FSL_MPIC_20]	= &kvm_mpic_ops,
+	[KVM_DEV_TYPE_FSL_MPIC_42]	= &kvm_mpic_ops,
 #endif
+
 #ifdef CONFIG_KVM_XICS
-	case KVM_DEV_TYPE_XICS:
-		ops = &kvm_xics_ops;
-		break;
+	[KVM_DEV_TYPE_XICS]		= &kvm_xics_ops,
 #endif
+
 #ifdef CONFIG_KVM_VFIO
-	case KVM_DEV_TYPE_VFIO:
-		ops = &kvm_vfio_ops;
-		break;
+	[KVM_DEV_TYPE_VFIO]		= &kvm_vfio_ops,
 #endif
+
 #ifdef CONFIG_KVM_ARM_VGIC
-	case KVM_DEV_TYPE_ARM_VGIC_V2:
-		ops = &kvm_arm_vgic_v2_ops;
-		break;
+	[KVM_DEV_TYPE_ARM_VGIC_V2]	= &kvm_arm_vgic_v2_ops,
 #endif
+
 #ifdef CONFIG_S390
-	case KVM_DEV_TYPE_FLIC:
-		ops = &kvm_flic_ops;
-		break;
+	[KVM_DEV_TYPE_FLIC]		= &kvm_flic_ops,
 #endif
-	default:
+};
+
+int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type)
+{
+	if (type >= ARRAY_SIZE(kvm_device_ops_table))
+		return -ENOSPC;
+
+	if (kvm_device_ops_table[type] != NULL)
+		return -EEXIST;
+
+	kvm_device_ops_table[type] = ops;
+	return 0;
+}
+
+static int kvm_ioctl_create_device(struct kvm *kvm,
+				   struct kvm_create_device *cd)
+{
+	struct kvm_device_ops *ops = NULL;
+	struct kvm_device *dev;
+	bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
+	int ret;
+
+	if (cd->type >= ARRAY_SIZE(kvm_device_ops_table))
+		return -ENODEV;
+
+	ops = kvm_device_ops_table[cd->type];
+	if (ops == NULL)
 		return -ENODEV;
-	}
 
 	if (test)
 		return 0;
-- 
cgit v1.2.3-55-g7522


From c06a841bf36340e9e917ce60d11a6425ac85d0bd Mon Sep 17 00:00:00 2001
From: Will Deacon
Date: Tue, 2 Sep 2014 10:27:34 +0100
Subject: KVM: ARM: vgic: register kvm_device_ops dynamically

Now that we have a dynamic means to register kvm_device_ops, use that
for the ARM VGIC, instead of relying on the static table.

Cc: Gleb Natapov <gleb@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h |   1 -
 virt/kvm/arm/vgic.c      | 157 ++++++++++++++++++++++++-----------------------
 virt/kvm/kvm_main.c      |   4 --
 3 files changed, 79 insertions(+), 83 deletions(-)

(limited to 'virt')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b6e954742951..601d321f96e7 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1069,7 +1069,6 @@ int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type);
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
 extern struct kvm_device_ops kvm_vfio_ops;
-extern struct kvm_device_ops kvm_arm_vgic_v2_ops;
 extern struct kvm_device_ops kvm_flic_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 73eba793b17f..3ee3ce06bbec 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -1522,83 +1522,6 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static void vgic_init_maintenance_interrupt(void *info)
-{
-	enable_percpu_irq(vgic->maint_irq, 0);
-}
-
-static int vgic_cpu_notify(struct notifier_block *self,
-			   unsigned long action, void *cpu)
-{
-	switch (action) {
-	case CPU_STARTING:
-	case CPU_STARTING_FROZEN:
-		vgic_init_maintenance_interrupt(NULL);
-		break;
-	case CPU_DYING:
-	case CPU_DYING_FROZEN:
-		disable_percpu_irq(vgic->maint_irq);
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block vgic_cpu_nb = {
-	.notifier_call = vgic_cpu_notify,
-};
-
-static const struct of_device_id vgic_ids[] = {
-	{ .compatible = "arm,cortex-a15-gic", .data = vgic_v2_probe, },
-	{ .compatible = "arm,gic-v3", .data = vgic_v3_probe, },
-	{},
-};
-
-int kvm_vgic_hyp_init(void)
-{
-	const struct of_device_id *matched_id;
-	int (*vgic_probe)(struct device_node *,const struct vgic_ops **,
-			  const struct vgic_params **);
-	struct device_node *vgic_node;
-	int ret;
-
-	vgic_node = of_find_matching_node_and_match(NULL,
-						    vgic_ids, &matched_id);
-	if (!vgic_node) {
-		kvm_err("error: no compatible GIC node found\n");
-		return -ENODEV;
-	}
-
-	vgic_probe = matched_id->data;
-	ret = vgic_probe(vgic_node, &vgic_ops, &vgic);
-	if (ret)
-		return ret;
-
-	ret = request_percpu_irq(vgic->maint_irq, vgic_maintenance_handler,
-				 "vgic", kvm_get_running_vcpus());
-	if (ret) {
-		kvm_err("Cannot register interrupt %d\n", vgic->maint_irq);
-		return ret;
-	}
-
-	ret = __register_cpu_notifier(&vgic_cpu_nb);
-	if (ret) {
-		kvm_err("Cannot register vgic CPU notifier\n");
-		goto out_free_irq;
-	}
-
-	/* Callback into for arch code for setup */
-	vgic_arch_setup(vgic);
-
-	on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
-
-	return 0;
-
-out_free_irq:
-	free_percpu_irq(vgic->maint_irq, kvm_get_running_vcpus());
-	return ret;
-}
-
 /**
  * kvm_vgic_init - Initialize global VGIC state before running any VCPUs
  * @kvm: pointer to the kvm struct
@@ -2062,7 +1985,7 @@ static int vgic_create(struct kvm_device *dev, u32 type)
 	return kvm_vgic_create(dev->kvm);
 }
 
-struct kvm_device_ops kvm_arm_vgic_v2_ops = {
+static struct kvm_device_ops kvm_arm_vgic_v2_ops = {
 	.name = "kvm-arm-vgic",
 	.create = vgic_create,
 	.destroy = vgic_destroy,
@@ -2070,3 +1993,81 @@ struct kvm_device_ops kvm_arm_vgic_v2_ops = {
 	.get_attr = vgic_get_attr,
 	.has_attr = vgic_has_attr,
 };
+
+static void vgic_init_maintenance_interrupt(void *info)
+{
+	enable_percpu_irq(vgic->maint_irq, 0);
+}
+
+static int vgic_cpu_notify(struct notifier_block *self,
+			   unsigned long action, void *cpu)
+{
+	switch (action) {
+	case CPU_STARTING:
+	case CPU_STARTING_FROZEN:
+		vgic_init_maintenance_interrupt(NULL);
+		break;
+	case CPU_DYING:
+	case CPU_DYING_FROZEN:
+		disable_percpu_irq(vgic->maint_irq);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block vgic_cpu_nb = {
+	.notifier_call = vgic_cpu_notify,
+};
+
+static const struct of_device_id vgic_ids[] = {
+	{ .compatible = "arm,cortex-a15-gic", .data = vgic_v2_probe, },
+	{ .compatible = "arm,gic-v3", .data = vgic_v3_probe, },
+	{},
+};
+
+int kvm_vgic_hyp_init(void)
+{
+	const struct of_device_id *matched_id;
+	int (*vgic_probe)(struct device_node *,const struct vgic_ops **,
+			  const struct vgic_params **);
+	struct device_node *vgic_node;
+	int ret;
+
+	vgic_node = of_find_matching_node_and_match(NULL,
+						    vgic_ids, &matched_id);
+	if (!vgic_node) {
+		kvm_err("error: no compatible GIC node found\n");
+		return -ENODEV;
+	}
+
+	vgic_probe = matched_id->data;
+	ret = vgic_probe(vgic_node, &vgic_ops, &vgic);
+	if (ret)
+		return ret;
+
+	ret = request_percpu_irq(vgic->maint_irq, vgic_maintenance_handler,
+				 "vgic", kvm_get_running_vcpus());
+	if (ret) {
+		kvm_err("Cannot register interrupt %d\n", vgic->maint_irq);
+		return ret;
+	}
+
+	ret = __register_cpu_notifier(&vgic_cpu_nb);
+	if (ret) {
+		kvm_err("Cannot register vgic CPU notifier\n");
+		goto out_free_irq;
+	}
+
+	/* Callback into for arch code for setup */
+	vgic_arch_setup(vgic);
+
+	on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
+
+	return kvm_register_device_ops(&kvm_arm_vgic_v2_ops,
+				       KVM_DEV_TYPE_ARM_VGIC_V2);
+
+out_free_irq:
+	free_percpu_irq(vgic->maint_irq, kvm_get_running_vcpus());
+	return ret;
+}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 686d783387a0..68d96f5dbfe2 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2286,10 +2286,6 @@ static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
 	[KVM_DEV_TYPE_VFIO]		= &kvm_vfio_ops,
 #endif
 
-#ifdef CONFIG_KVM_ARM_VGIC
-	[KVM_DEV_TYPE_ARM_VGIC_V2]	= &kvm_arm_vgic_v2_ops,
-#endif
-
 #ifdef CONFIG_S390
 	[KVM_DEV_TYPE_FLIC]		= &kvm_flic_ops,
 #endif
-- 
cgit v1.2.3-55-g7522


From 84877d93336de21a6251db00b841468a83c65906 Mon Sep 17 00:00:00 2001
From: Cornelia Huck
Date: Tue, 2 Sep 2014 10:27:35 +0100
Subject: KVM: s390: register flic ops dynamically

Using the new kvm_register_device_ops() interface makes us get rid of
an #ifdef in common code.

Cc: Gleb Natapov <gleb@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/s390/kvm/kvm-s390.c | 3 ++-
 arch/s390/kvm/kvm-s390.h | 1 +
 include/linux/kvm_host.h | 1 -
 virt/kvm/kvm_main.c      | 4 ----
 4 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'virt')

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index b95d4a481b0c..56a411c0245a 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -122,7 +122,8 @@ void kvm_arch_hardware_unsetup(void)
 
 int kvm_arch_init(void *opaque)
 {
-	return 0;
+	/* Register floating interrupt controller interface. */
+	return kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC);
 }
 
 /* Section: device related */
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index b1a77669137b..244d02303182 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -227,6 +227,7 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int psw_extint_disabled(struct kvm_vcpu *vcpu);
 void kvm_s390_destroy_adapters(struct kvm *kvm);
 int kvm_s390_si_ext_call_pending(struct kvm_vcpu *vcpu);
+extern struct kvm_device_ops kvm_flic_ops;
 
 /* implemented in guestdbg.c */
 void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 601d321f96e7..7ef088bec715 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1069,7 +1069,6 @@ int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type);
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
 extern struct kvm_device_ops kvm_vfio_ops;
-extern struct kvm_device_ops kvm_flic_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 68d96f5dbfe2..f4e792fedb4f 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2285,10 +2285,6 @@ static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
 #ifdef CONFIG_KVM_VFIO
 	[KVM_DEV_TYPE_VFIO]		= &kvm_vfio_ops,
 #endif
-
-#ifdef CONFIG_S390
-	[KVM_DEV_TYPE_FLIC]		= &kvm_flic_ops,
-#endif
 };
 
 int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type)
-- 
cgit v1.2.3-55-g7522


From 80ce1639727e9d38729c34f162378508c307ca25 Mon Sep 17 00:00:00 2001
From: Will Deacon
Date: Tue, 2 Sep 2014 10:27:36 +0100
Subject: KVM: VFIO: register kvm_device_ops dynamically

Now that we have a dynamic means to register kvm_device_ops, use that
for the VFIO kvm device, instead of relying on the static table.

This is achieved by a module_init call to register the ops with KVM.

Cc: Gleb Natapov <gleb@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Alex Williamson <Alex.Williamson@redhat.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h |  1 -
 virt/kvm/kvm_main.c      |  4 ----
 virt/kvm/vfio.c          | 22 +++++++++++++++-------
 3 files changed, 15 insertions(+), 12 deletions(-)

(limited to 'virt')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7ef088bec715..d44a2d640551 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1068,7 +1068,6 @@ int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type);
 
 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/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f4e792fedb4f..db57363cc287 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2281,10 +2281,6 @@ static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
 #ifdef CONFIG_KVM_XICS
 	[KVM_DEV_TYPE_XICS]		= &kvm_xics_ops,
 #endif
-
-#ifdef CONFIG_KVM_VFIO
-	[KVM_DEV_TYPE_VFIO]		= &kvm_vfio_ops,
-#endif
 };
 
 int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type)
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index ba1a93f935c7..bb11b36ee8a2 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -246,6 +246,16 @@ static void kvm_vfio_destroy(struct kvm_device *dev)
 	kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */
 }
 
+static int kvm_vfio_create(struct kvm_device *dev, u32 type);
+
+static 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,
+};
+
 static int kvm_vfio_create(struct kvm_device *dev, u32 type)
 {
 	struct kvm_device *tmp;
@@ -268,10 +278,8 @@ static int kvm_vfio_create(struct kvm_device *dev, u32 type)
 	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,
-};
+static int __init kvm_vfio_ops_init(void)
+{
+	return kvm_register_device_ops(&kvm_vfio_ops, KVM_DEV_TYPE_VFIO);
+}
+module_init(kvm_vfio_ops_init);
-- 
cgit v1.2.3-55-g7522