From cf87ac739e488055a6046a410caa8f4da108948f Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Thu, 10 Nov 2022 18:49:08 +0800
Subject: KVM: x86: Introduce KVM_REQ_DIRTY_RING_SOFT_FULL

The VCPU isn't expected to be runnable when the dirty ring becomes soft
full, until the dirty pages are harvested and the dirty ring is reset
from userspace. So there is a check in each guest's entrace to see if
the dirty ring is soft full or not. The VCPU is stopped from running if
its dirty ring has been soft full. The similar check will be needed when
the feature is going to be supported on ARM64. As Marc Zyngier suggested,
a new event will avoid pointless overhead to check the size of the dirty
ring ('vcpu->kvm->dirty_ring_size') in each guest's entrance.

Add KVM_REQ_DIRTY_RING_SOFT_FULL. The event is raised when the dirty ring
becomes soft full in kvm_dirty_ring_push(). The event is only cleared in
the check, done in the newly added helper kvm_dirty_ring_check_request().
Since the VCPU is not runnable when the dirty ring becomes soft full, the
KVM_REQ_DIRTY_RING_SOFT_FULL event is always set to prevent the VCPU from
running until the dirty pages are harvested and the dirty ring is reset by
userspace.

kvm_dirty_ring_soft_full() becomes a private function with the newly added
helper kvm_dirty_ring_check_request(). The alignment for the various event
definitions in kvm_host.h is changed to tab character by the way. In order
to avoid using 'container_of()', the argument @ring is replaced by @vcpu
in kvm_dirty_ring_push().

Link: https://lore.kernel.org/kvmarm/87lerkwtm5.wl-maz@kernel.org
Suggested-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221110104914.31280-2-gshan@redhat.com
---
 include/linux/kvm_dirty_ring.h | 12 ++++--------
 include/linux/kvm_host.h       |  9 +++++----
 2 files changed, 9 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h
index 906f899813dc..9c13c4c3d30c 100644
--- a/include/linux/kvm_dirty_ring.h
+++ b/include/linux/kvm_dirty_ring.h
@@ -49,7 +49,7 @@ static inline int kvm_dirty_ring_reset(struct kvm *kvm,
 	return 0;
 }
 
-static inline void kvm_dirty_ring_push(struct kvm_dirty_ring *ring,
+static inline void kvm_dirty_ring_push(struct kvm_vcpu *vcpu,
 				       u32 slot, u64 offset)
 {
 }
@@ -64,11 +64,6 @@ static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
 {
 }
 
-static inline bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring)
-{
-	return true;
-}
-
 #else /* CONFIG_HAVE_KVM_DIRTY_RING */
 
 u32 kvm_dirty_ring_get_rsvd_entries(void);
@@ -84,13 +79,14 @@ int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring);
  * returns =0: successfully pushed
  *         <0: unable to push, need to wait
  */
-void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset);
+void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, u32 slot, u64 offset);
+
+bool kvm_dirty_ring_check_request(struct kvm_vcpu *vcpu);
 
 /* for use in vm_operations_struct */
 struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset);
 
 void kvm_dirty_ring_free(struct kvm_dirty_ring *ring);
-bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring);
 
 #endif /* CONFIG_HAVE_KVM_DIRTY_RING */
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 00c3448ba7f8..648d663f32c4 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -153,10 +153,11 @@ static inline bool is_error_page(struct page *page)
  * Architecture-independent vcpu->requests bit members
  * Bits 3-7 are reserved for more arch-independent bits.
  */
-#define KVM_REQ_TLB_FLUSH         (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
-#define KVM_REQ_VM_DEAD           (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
-#define KVM_REQ_UNBLOCK           2
-#define KVM_REQUEST_ARCH_BASE     8
+#define KVM_REQ_TLB_FLUSH		(0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_VM_DEAD			(1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_UNBLOCK			2
+#define KVM_REQ_DIRTY_RING_SOFT_FULL	3
+#define KVM_REQUEST_ARCH_BASE		8
 
 /*
  * KVM_REQ_OUTSIDE_GUEST_MODE exists is purely as way to force the vCPU to
-- 
cgit v1.2.3


From e8a18565e59303ac12c626a161d72bd890bd2062 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Thu, 10 Nov 2022 18:49:09 +0800
Subject: KVM: Move declaration of kvm_cpu_dirty_log_size() to kvm_dirty_ring.h

Not all architectures like ARM64 need to override the function. Move
its declaration to kvm_dirty_ring.h to avoid the following compiling
warning on ARM64 when the feature is enabled.

  arch/arm64/kvm/../../../virt/kvm/dirty_ring.c:14:12:        \
  warning: no previous prototype for 'kvm_cpu_dirty_log_size' \
  [-Wmissing-prototypes]                                      \
  int __weak kvm_cpu_dirty_log_size(void)

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221110104914.31280-3-gshan@redhat.com
---
 arch/x86/include/asm/kvm_host.h | 2 --
 include/linux/kvm_dirty_ring.h  | 1 +
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7551b6f9c31c..b4dbde7d9eb1 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -2090,8 +2090,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
 #define GET_SMSTATE(type, buf, offset)		\
 	(*(type *)((buf) + (offset) - 0x7e00))
 
-int kvm_cpu_dirty_log_size(void);
-
 int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
 
 #define KVM_CLOCK_VALID_FLAGS						\
diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h
index 9c13c4c3d30c..199ead37b104 100644
--- a/include/linux/kvm_dirty_ring.h
+++ b/include/linux/kvm_dirty_ring.h
@@ -66,6 +66,7 @@ static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
 
 #else /* CONFIG_HAVE_KVM_DIRTY_RING */
 
+int kvm_cpu_dirty_log_size(void);
 u32 kvm_dirty_ring_get_rsvd_entries(void);
 int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size);
 
-- 
cgit v1.2.3


From 86bdf3ebcfe1ded055282536fecce13001874740 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Thu, 10 Nov 2022 18:49:10 +0800
Subject: KVM: Support dirty ring in conjunction with bitmap

ARM64 needs to dirty memory outside of a VCPU context when VGIC/ITS is
enabled. It's conflicting with that ring-based dirty page tracking always
requires a running VCPU context.

Introduce a new flavor of dirty ring that requires the use of both VCPU
dirty rings and a dirty bitmap. The expectation is that for non-VCPU
sources of dirty memory (such as the VGIC/ITS on arm64), KVM writes to
the dirty bitmap. Userspace should scan the dirty bitmap before migrating
the VM to the target.

Use an additional capability to advertise this behavior. The newly added
capability (KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP) can't be enabled before
KVM_CAP_DIRTY_LOG_RING_ACQ_REL on ARM64. In this way, the newly added
capability is treated as an extension of KVM_CAP_DIRTY_LOG_RING_ACQ_REL.

Suggested-by: Marc Zyngier <maz@kernel.org>
Suggested-by: Peter Xu <peterx@redhat.com>
Co-developed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Gavin Shan <gshan@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221110104914.31280-4-gshan@redhat.com
---
 Documentation/virt/kvm/api.rst                  | 34 +++++++++++---
 Documentation/virt/kvm/devices/arm-vgic-its.rst |  5 +-
 include/linux/kvm_dirty_ring.h                  |  7 +++
 include/linux/kvm_host.h                        |  1 +
 include/uapi/linux/kvm.h                        |  1 +
 virt/kvm/Kconfig                                |  6 +++
 virt/kvm/dirty_ring.c                           | 14 ++++++
 virt/kvm/kvm_main.c                             | 61 +++++++++++++++++++++----
 8 files changed, 112 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index eee9f857a986..1f1b09aa6db4 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -8003,13 +8003,6 @@ flushing is done by the KVM_GET_DIRTY_LOG ioctl).  To achieve that, one
 needs to kick the vcpu out of KVM_RUN using a signal.  The resulting
 vmexit ensures that all dirty GFNs are flushed to the dirty rings.
 
-NOTE: the capability KVM_CAP_DIRTY_LOG_RING and the corresponding
-ioctl KVM_RESET_DIRTY_RINGS are mutual exclusive to the existing ioctls
-KVM_GET_DIRTY_LOG and KVM_CLEAR_DIRTY_LOG.  After enabling
-KVM_CAP_DIRTY_LOG_RING with an acceptable dirty ring size, the virtual
-machine will switch to ring-buffer dirty page tracking and further
-KVM_GET_DIRTY_LOG or KVM_CLEAR_DIRTY_LOG ioctls will fail.
-
 NOTE: KVM_CAP_DIRTY_LOG_RING_ACQ_REL is the only capability that
 should be exposed by weakly ordered architecture, in order to indicate
 the additional memory ordering requirements imposed on userspace when
@@ -8018,6 +8011,33 @@ Architecture with TSO-like ordering (such as x86) are allowed to
 expose both KVM_CAP_DIRTY_LOG_RING and KVM_CAP_DIRTY_LOG_RING_ACQ_REL
 to userspace.
 
+After enabling the dirty rings, the userspace needs to detect the
+capability of KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP to see whether the
+ring structures can be backed by per-slot bitmaps. With this capability
+advertised, it means the architecture can dirty guest pages without
+vcpu/ring context, so that some of the dirty information will still be
+maintained in the bitmap structure. KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP
+can't be enabled if the capability of KVM_CAP_DIRTY_LOG_RING_ACQ_REL
+hasn't been enabled, or any memslot has been existing.
+
+Note that the bitmap here is only a backup of the ring structure. The
+use of the ring and bitmap combination is only beneficial if there is
+only a very small amount of memory that is dirtied out of vcpu/ring
+context. Otherwise, the stand-alone per-slot bitmap mechanism needs to
+be considered.
+
+To collect dirty bits in the backup bitmap, userspace can use the same
+KVM_GET_DIRTY_LOG ioctl. KVM_CLEAR_DIRTY_LOG isn't needed as long as all
+the generation of the dirty bits is done in a single pass. Collecting
+the dirty bitmap should be the very last thing that the VMM does before
+considering the state as complete. VMM needs to ensure that the dirty
+state is final and avoid missing dirty pages from another ioctl ordered
+after the bitmap collection.
+
+NOTE: One example of using the backup bitmap is saving arm64 vgic/its
+tables through KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_SAVE_TABLES} command on
+KVM device "kvm-arm-vgic-its" when dirty ring is enabled.
+
 8.30 KVM_CAP_XEN_HVM
 --------------------
 
diff --git a/Documentation/virt/kvm/devices/arm-vgic-its.rst b/Documentation/virt/kvm/devices/arm-vgic-its.rst
index d257eddbae29..e053124f77c4 100644
--- a/Documentation/virt/kvm/devices/arm-vgic-its.rst
+++ b/Documentation/virt/kvm/devices/arm-vgic-its.rst
@@ -52,7 +52,10 @@ KVM_DEV_ARM_VGIC_GRP_CTRL
 
     KVM_DEV_ARM_ITS_SAVE_TABLES
       save the ITS table data into guest RAM, at the location provisioned
-      by the guest in corresponding registers/table entries.
+      by the guest in corresponding registers/table entries. Should userspace
+      require a form of dirty tracking to identify which pages are modified
+      by the saving process, it should use a bitmap even if using another
+      mechanism to track the memory dirtied by the vCPUs.
 
       The layout of the tables in guest memory defines an ABI. The entries
       are laid out in little endian format as described in the last paragraph.
diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h
index 199ead37b104..4862c98d80d3 100644
--- a/include/linux/kvm_dirty_ring.h
+++ b/include/linux/kvm_dirty_ring.h
@@ -37,6 +37,11 @@ static inline u32 kvm_dirty_ring_get_rsvd_entries(void)
 	return 0;
 }
 
+static inline bool kvm_use_dirty_bitmap(struct kvm *kvm)
+{
+	return true;
+}
+
 static inline int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring,
 				       int index, u32 size)
 {
@@ -67,6 +72,8 @@ static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
 #else /* CONFIG_HAVE_KVM_DIRTY_RING */
 
 int kvm_cpu_dirty_log_size(void);
+bool kvm_use_dirty_bitmap(struct kvm *kvm);
+bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm);
 u32 kvm_dirty_ring_get_rsvd_entries(void);
 int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size);
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 648d663f32c4..db83f63f4e61 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -779,6 +779,7 @@ struct kvm {
 	pid_t userspace_pid;
 	unsigned int max_halt_poll_ns;
 	u32 dirty_ring_size;
+	bool dirty_ring_with_bitmap;
 	bool vm_bugged;
 	bool vm_dead;
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 0d5d4419139a..c87b5882d7ae 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1178,6 +1178,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_ZPCI_OP 221
 #define KVM_CAP_S390_CPU_TOPOLOGY 222
 #define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223
+#define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 224
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 800f9470e36b..9fb1ff6f19e5 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -33,6 +33,12 @@ config HAVE_KVM_DIRTY_RING_ACQ_REL
        bool
        select HAVE_KVM_DIRTY_RING
 
+# Allow enabling both the dirty bitmap and dirty ring. Only architectures
+# that need to dirty memory outside of a vCPU context should select this.
+config NEED_KVM_DIRTY_RING_WITH_BITMAP
+	bool
+	depends on HAVE_KVM_DIRTY_RING
+
 config HAVE_KVM_EVENTFD
        bool
        select EVENTFD
diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c
index fecbb7d75ad2..c1cd7dfe4a90 100644
--- a/virt/kvm/dirty_ring.c
+++ b/virt/kvm/dirty_ring.c
@@ -21,6 +21,20 @@ u32 kvm_dirty_ring_get_rsvd_entries(void)
 	return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size();
 }
 
+bool kvm_use_dirty_bitmap(struct kvm *kvm)
+{
+	lockdep_assert_held(&kvm->slots_lock);
+
+	return !kvm->dirty_ring_size || kvm->dirty_ring_with_bitmap;
+}
+
+#ifndef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP
+bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm)
+{
+	return false;
+}
+#endif
+
 static u32 kvm_dirty_ring_used(struct kvm_dirty_ring *ring)
 {
 	return READ_ONCE(ring->dirty_index) - READ_ONCE(ring->reset_index);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 04b22d2f99d8..be40d1ce6e91 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1617,7 +1617,7 @@ static int kvm_prepare_memory_region(struct kvm *kvm,
 			new->dirty_bitmap = NULL;
 		else if (old && old->dirty_bitmap)
 			new->dirty_bitmap = old->dirty_bitmap;
-		else if (!kvm->dirty_ring_size) {
+		else if (kvm_use_dirty_bitmap(kvm)) {
 			r = kvm_alloc_dirty_bitmap(new);
 			if (r)
 				return r;
@@ -2060,8 +2060,8 @@ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
 	unsigned long n;
 	unsigned long any = 0;
 
-	/* Dirty ring tracking is exclusive to dirty log tracking */
-	if (kvm->dirty_ring_size)
+	/* Dirty ring tracking may be exclusive to dirty log tracking */
+	if (!kvm_use_dirty_bitmap(kvm))
 		return -ENXIO;
 
 	*memslot = NULL;
@@ -2125,8 +2125,8 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
 	unsigned long *dirty_bitmap_buffer;
 	bool flush;
 
-	/* Dirty ring tracking is exclusive to dirty log tracking */
-	if (kvm->dirty_ring_size)
+	/* Dirty ring tracking may be exclusive to dirty log tracking */
+	if (!kvm_use_dirty_bitmap(kvm))
 		return -ENXIO;
 
 	as_id = log->slot >> 16;
@@ -2237,8 +2237,8 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
 	unsigned long *dirty_bitmap_buffer;
 	bool flush;
 
-	/* Dirty ring tracking is exclusive to dirty log tracking */
-	if (kvm->dirty_ring_size)
+	/* Dirty ring tracking may be exclusive to dirty log tracking */
+	if (!kvm_use_dirty_bitmap(kvm))
 		return -ENXIO;
 
 	as_id = log->slot >> 16;
@@ -3305,7 +3305,10 @@ void mark_page_dirty_in_slot(struct kvm *kvm,
 	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
 
 #ifdef CONFIG_HAVE_KVM_DIRTY_RING
-	if (WARN_ON_ONCE(!vcpu) || WARN_ON_ONCE(vcpu->kvm != kvm))
+	if (WARN_ON_ONCE(vcpu && vcpu->kvm != kvm))
+		return;
+
+	if (WARN_ON_ONCE(!kvm_arch_allow_write_without_running_vcpu(kvm) && !vcpu))
 		return;
 #endif
 
@@ -3313,7 +3316,7 @@ void mark_page_dirty_in_slot(struct kvm *kvm,
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
 		u32 slot = (memslot->as_id << 16) | memslot->id;
 
-		if (kvm->dirty_ring_size)
+		if (kvm->dirty_ring_size && vcpu)
 			kvm_dirty_ring_push(vcpu, slot, rel_gfn);
 		else
 			set_bit_le(rel_gfn, memslot->dirty_bitmap);
@@ -4482,6 +4485,9 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 		return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn);
 #else
 		return 0;
+#endif
+#ifdef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP
+	case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP:
 #endif
 	case KVM_CAP_BINARY_STATS_FD:
 	case KVM_CAP_SYSTEM_EVENT_DATA:
@@ -4558,6 +4564,20 @@ int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 	return -EINVAL;
 }
 
+static bool kvm_are_all_memslots_empty(struct kvm *kvm)
+{
+	int i;
+
+	lockdep_assert_held(&kvm->slots_lock);
+
+	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+		if (!kvm_memslots_empty(__kvm_memslots(kvm, i)))
+			return false;
+	}
+
+	return true;
+}
+
 static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 					   struct kvm_enable_cap *cap)
 {
@@ -4588,6 +4608,29 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 			return -EINVAL;
 
 		return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]);
+	case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: {
+		int r = -EINVAL;
+
+		if (!IS_ENABLED(CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP) ||
+		    !kvm->dirty_ring_size || cap->flags)
+			return r;
+
+		mutex_lock(&kvm->slots_lock);
+
+		/*
+		 * For simplicity, allow enabling ring+bitmap if and only if
+		 * there are no memslots, e.g. to ensure all memslots allocate
+		 * a bitmap after the capability is enabled.
+		 */
+		if (kvm_are_all_memslots_empty(kvm)) {
+			kvm->dirty_ring_with_bitmap = true;
+			r = 0;
+		}
+
+		mutex_unlock(&kvm->slots_lock);
+
+		return r;
+	}
 	default:
 		return kvm_vm_ioctl_enable_cap(kvm, cap);
 	}
-- 
cgit v1.2.3


From 9cb1096f8590bc590326087bea65db932b53c3b5 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Thu, 10 Nov 2022 18:49:11 +0800
Subject: KVM: arm64: Enable ring-based dirty memory tracking

Enable ring-based dirty memory tracking on ARM64:

  - Enable CONFIG_HAVE_KVM_DIRTY_RING_ACQ_REL.

  - Enable CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP.

  - Set KVM_DIRTY_LOG_PAGE_OFFSET for the ring buffer's physical page
    offset.

  - Add ARM64 specific kvm_arch_allow_write_without_running_vcpu() to
    keep the site of saving vgic/its tables out of the no-running-vcpu
    radar.

Signed-off-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221110104914.31280-5-gshan@redhat.com
---
 Documentation/virt/kvm/api.rst    |  2 +-
 arch/arm64/include/uapi/asm/kvm.h |  1 +
 arch/arm64/kvm/Kconfig            |  2 ++
 arch/arm64/kvm/arm.c              |  3 +++
 arch/arm64/kvm/vgic/vgic-its.c    | 20 ++++++++++++++++++++
 include/kvm/arm_vgic.h            |  1 +
 6 files changed, 28 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 1f1b09aa6db4..773e4b202f47 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -7921,7 +7921,7 @@ regardless of what has actually been exposed through the CPUID leaf.
 8.29 KVM_CAP_DIRTY_LOG_RING/KVM_CAP_DIRTY_LOG_RING_ACQ_REL
 ----------------------------------------------------------
 
-:Architectures: x86
+:Architectures: x86, arm64
 :Parameters: args[0] - size of the dirty log ring
 
 KVM is capable of tracking dirty memory using ring buffers that are
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 316917b98707..a7a857f1784d 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -43,6 +43,7 @@
 #define __KVM_HAVE_VCPU_EVENTS
 
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+#define KVM_DIRTY_LOG_PAGE_OFFSET 64
 
 #define KVM_REG_SIZE(id)						\
 	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 815cc118c675..05da3c8f7e88 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -32,6 +32,8 @@ menuconfig KVM
 	select KVM_VFIO
 	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQFD
+	select HAVE_KVM_DIRTY_RING_ACQ_REL
+	select NEED_KVM_DIRTY_RING_WITH_BITMAP
 	select HAVE_KVM_MSI
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_IRQ_ROUTING
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 94d33e296e10..6b097605e38c 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -746,6 +746,9 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 
 		if (kvm_check_request(KVM_REQ_SUSPEND, vcpu))
 			return kvm_vcpu_suspend(vcpu);
+
+		if (kvm_dirty_ring_check_request(vcpu))
+			return 0;
 	}
 
 	return 1;
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index 733b53055f97..94a666dd1443 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -2743,6 +2743,7 @@ static int vgic_its_has_attr(struct kvm_device *dev,
 static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr)
 {
 	const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+	struct vgic_dist *dist = &kvm->arch.vgic;
 	int ret = 0;
 
 	if (attr == KVM_DEV_ARM_VGIC_CTRL_INIT) /* Nothing to do */
@@ -2762,7 +2763,9 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr)
 		vgic_its_reset(kvm, its);
 		break;
 	case KVM_DEV_ARM_ITS_SAVE_TABLES:
+		dist->save_its_tables_in_progress = true;
 		ret = abi->save_tables(its);
+		dist->save_its_tables_in_progress = false;
 		break;
 	case KVM_DEV_ARM_ITS_RESTORE_TABLES:
 		ret = abi->restore_tables(its);
@@ -2775,6 +2778,23 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr)
 	return ret;
 }
 
+/*
+ * kvm_arch_allow_write_without_running_vcpu - allow writing guest memory
+ * without the running VCPU when dirty ring is enabled.
+ *
+ * The running VCPU is required to track dirty guest pages when dirty ring
+ * is enabled. Otherwise, the backup bitmap should be used to track the
+ * dirty guest pages. When vgic/its tables are being saved, the backup
+ * bitmap is used to track the dirty guest pages due to the missed running
+ * VCPU in the period.
+ */
+bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+
+	return dist->save_its_tables_in_progress;
+}
+
 static int vgic_its_set_attr(struct kvm_device *dev,
 			     struct kvm_device_attr *attr)
 {
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 4df9e73a8bb5..9270cd87da3f 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -263,6 +263,7 @@ struct vgic_dist {
 	struct vgic_io_device	dist_iodev;
 
 	bool			has_its;
+	bool			save_its_tables_in_progress;
 
 	/*
 	 * Contains the attributes and gpa of the LPI configuration table.
-- 
cgit v1.2.3


From bead02204e9806807bb290137b1ccabfcb4b16fd Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 13 Nov 2022 16:38:18 +0000
Subject: KVM: arm64: PMU: Align chained counter implementation with
 architecture pseudocode

Ricardo recently pointed out that the PMU chained counter emulation
in KVM wasn't quite behaving like the one on actual hardware, in
the sense that a chained counter would expose an overflow on
both halves of a chained counter, while KVM would only expose the
overflow on the top half.

The difference is subtle, but significant. What does the architecture
say (DDI0087 H.a):

- Up to PMUv3p4, all counters but the cycle counter are 32bit

- A 32bit counter that overflows generates a CHAIN event on the
  adjacent counter after exposing its own overflow status

- The CHAIN event is accounted if the counter is correctly
  configured (CHAIN event selected and counter enabled)

This all means that our current implementation (which uses 64bit
perf events) prevents us from emulating this overflow on the lower half.

How to fix this? By implementing the above, to the letter.

This largely results in code deletion, removing the notions of
"counter pair", "chained counters", and "canonical counter".
The code is further restructured to make the CHAIN handling similar
to SWINC, as the two are now extremely similar in behaviour.

Reported-by: Ricardo Koller <ricarkol@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Reiji Watanabe <reijiw@google.com>
Link: https://lore.kernel.org/r/20221113163832.3154370-3-maz@kernel.org
---
 arch/arm64/kvm/pmu-emul.c | 320 +++++++++++++---------------------------------
 include/kvm/arm_pmu.h     |   2 -
 2 files changed, 86 insertions(+), 236 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 0003c7d37533..57765be69bea 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -15,16 +15,14 @@
 #include <kvm/arm_pmu.h>
 #include <kvm/arm_vgic.h>
 
+#define PERF_ATTR_CFG1_COUNTER_64BIT	BIT(0)
+
 DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available);
 
 static LIST_HEAD(arm_pmus);
 static DEFINE_MUTEX(arm_pmus_lock);
 
 static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx);
-static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx);
-static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc);
-
-#define PERF_ATTR_CFG1_KVM_PMU_CHAINED 0x1
 
 static u32 kvm_pmu_event_mask(struct kvm *kvm)
 {
@@ -57,6 +55,11 @@ static bool kvm_pmu_idx_is_64bit(struct kvm_vcpu *vcpu, u64 select_idx)
 		__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_LC);
 }
 
+static bool kvm_pmu_counter_can_chain(struct kvm_vcpu *vcpu, u64 idx)
+{
+	return (!(idx & 1) && (idx + 1) < ARMV8_PMU_CYCLE_IDX);
+}
+
 static struct kvm_vcpu *kvm_pmc_to_vcpu(struct kvm_pmc *pmc)
 {
 	struct kvm_pmu *pmu;
@@ -69,91 +72,22 @@ static struct kvm_vcpu *kvm_pmc_to_vcpu(struct kvm_pmc *pmc)
 }
 
 /**
- * kvm_pmu_pmc_is_chained - determine if the pmc is chained
- * @pmc: The PMU counter pointer
- */
-static bool kvm_pmu_pmc_is_chained(struct kvm_pmc *pmc)
-{
-	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
-
-	return test_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
-}
-
-/**
- * kvm_pmu_idx_is_high_counter - determine if select_idx is a high/low counter
- * @select_idx: The counter index
- */
-static bool kvm_pmu_idx_is_high_counter(u64 select_idx)
-{
-	return select_idx & 0x1;
-}
-
-/**
- * kvm_pmu_get_canonical_pmc - obtain the canonical pmc
- * @pmc: The PMU counter pointer
- *
- * When a pair of PMCs are chained together we use the low counter (canonical)
- * to hold the underlying perf event.
- */
-static struct kvm_pmc *kvm_pmu_get_canonical_pmc(struct kvm_pmc *pmc)
-{
-	if (kvm_pmu_pmc_is_chained(pmc) &&
-	    kvm_pmu_idx_is_high_counter(pmc->idx))
-		return pmc - 1;
-
-	return pmc;
-}
-static struct kvm_pmc *kvm_pmu_get_alternate_pmc(struct kvm_pmc *pmc)
-{
-	if (kvm_pmu_idx_is_high_counter(pmc->idx))
-		return pmc - 1;
-	else
-		return pmc + 1;
-}
-
-/**
- * kvm_pmu_idx_has_chain_evtype - determine if the event type is chain
+ * kvm_pmu_get_counter_value - get PMU counter value
  * @vcpu: The vcpu pointer
  * @select_idx: The counter index
  */
-static bool kvm_pmu_idx_has_chain_evtype(struct kvm_vcpu *vcpu, u64 select_idx)
-{
-	u64 eventsel, reg;
-
-	select_idx |= 0x1;
-
-	if (select_idx == ARMV8_PMU_CYCLE_IDX)
-		return false;
-
-	reg = PMEVTYPER0_EL0 + select_idx;
-	eventsel = __vcpu_sys_reg(vcpu, reg) & kvm_pmu_event_mask(vcpu->kvm);
-
-	return eventsel == ARMV8_PMUV3_PERFCTR_CHAIN;
-}
-
-/**
- * kvm_pmu_get_pair_counter_value - get PMU counter value
- * @vcpu: The vcpu pointer
- * @pmc: The PMU counter pointer
- */
-static u64 kvm_pmu_get_pair_counter_value(struct kvm_vcpu *vcpu,
-					  struct kvm_pmc *pmc)
+u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
 {
-	u64 counter, counter_high, reg, enabled, running;
-
-	if (kvm_pmu_pmc_is_chained(pmc)) {
-		pmc = kvm_pmu_get_canonical_pmc(pmc);
-		reg = PMEVCNTR0_EL0 + pmc->idx;
+	u64 counter, reg, enabled, running;
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
 
-		counter = __vcpu_sys_reg(vcpu, reg);
-		counter_high = __vcpu_sys_reg(vcpu, reg + 1);
+	if (!kvm_vcpu_has_pmu(vcpu))
+		return 0;
 
-		counter = lower_32_bits(counter) | (counter_high << 32);
-	} else {
-		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
-		      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
-		counter = __vcpu_sys_reg(vcpu, reg);
-	}
+	reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
+		? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
+	counter = __vcpu_sys_reg(vcpu, reg);
 
 	/*
 	 * The real counter value is equal to the value of counter register plus
@@ -163,29 +97,7 @@ static u64 kvm_pmu_get_pair_counter_value(struct kvm_vcpu *vcpu,
 		counter += perf_event_read_value(pmc->perf_event, &enabled,
 						 &running);
 
-	return counter;
-}
-
-/**
- * kvm_pmu_get_counter_value - get PMU counter value
- * @vcpu: The vcpu pointer
- * @select_idx: The counter index
- */
-u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
-{
-	u64 counter;
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
-
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return 0;
-
-	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
-
-	if (kvm_pmu_pmc_is_chained(pmc) &&
-	    kvm_pmu_idx_is_high_counter(select_idx))
-		counter = upper_32_bits(counter);
-	else if (select_idx != ARMV8_PMU_CYCLE_IDX)
+	if (select_idx != ARMV8_PMU_CYCLE_IDX)
 		counter = lower_32_bits(counter);
 
 	return counter;
@@ -218,7 +130,6 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
  */
 static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc)
 {
-	pmc = kvm_pmu_get_canonical_pmc(pmc);
 	if (pmc->perf_event) {
 		perf_event_disable(pmc->perf_event);
 		perf_event_release_kernel(pmc->perf_event);
@@ -236,11 +147,10 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
 {
 	u64 counter, reg, val;
 
-	pmc = kvm_pmu_get_canonical_pmc(pmc);
 	if (!pmc->perf_event)
 		return;
 
-	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
+	counter = kvm_pmu_get_counter_value(vcpu, pmc->idx);
 
 	if (pmc->idx == ARMV8_PMU_CYCLE_IDX) {
 		reg = PMCCNTR_EL0;
@@ -252,9 +162,6 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
 
 	__vcpu_sys_reg(vcpu, reg) = val;
 
-	if (kvm_pmu_pmc_is_chained(pmc))
-		__vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter);
-
 	kvm_pmu_release_perf_event(pmc);
 }
 
@@ -285,8 +192,6 @@ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
 
 	for_each_set_bit(i, &mask, 32)
 		kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]);
-
-	bitmap_zero(vcpu->arch.pmu.chained, ARMV8_PMU_MAX_COUNTER_PAIRS);
 }
 
 /**
@@ -340,12 +245,9 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 
 		pmc = &pmu->pmc[i];
 
-		/* A change in the enable state may affect the chain state */
-		kvm_pmu_update_pmc_chained(vcpu, i);
-		kvm_pmu_create_perf_event(vcpu, i);
-
-		/* At this point, pmc must be the canonical */
-		if (pmc->perf_event) {
+		if (!pmc->perf_event) {
+			kvm_pmu_create_perf_event(vcpu, i);
+		} else {
 			perf_event_enable(pmc->perf_event);
 			if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE)
 				kvm_debug("fail to enable perf event\n");
@@ -375,11 +277,6 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 
 		pmc = &pmu->pmc[i];
 
-		/* A change in the enable state may affect the chain state */
-		kvm_pmu_update_pmc_chained(vcpu, i);
-		kvm_pmu_create_perf_event(vcpu, i);
-
-		/* At this point, pmc must be the canonical */
 		if (pmc->perf_event)
 			perf_event_disable(pmc->perf_event);
 	}
@@ -484,6 +381,48 @@ static void kvm_pmu_perf_overflow_notify_vcpu(struct irq_work *work)
 	kvm_vcpu_kick(vcpu);
 }
 
+/*
+ * Perform an increment on any of the counters described in @mask,
+ * generating the overflow if required, and propagate it as a chained
+ * event if possible.
+ */
+static void kvm_pmu_counter_increment(struct kvm_vcpu *vcpu,
+				      unsigned long mask, u32 event)
+{
+	int i;
+
+	if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E))
+		return;
+
+	/* Weed out disabled counters */
+	mask &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
+
+	for_each_set_bit(i, &mask, ARMV8_PMU_CYCLE_IDX) {
+		u64 type, reg;
+
+		/* Filter on event type */
+		type = __vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i);
+		type &= kvm_pmu_event_mask(vcpu->kvm);
+		if (type != event)
+			continue;
+
+		/* Increment this counter */
+		reg = __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) + 1;
+		reg = lower_32_bits(reg);
+		__vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) = reg;
+
+		if (reg) /* No overflow? move on */
+			continue;
+
+		/* Mark overflow */
+		__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i);
+
+		if (kvm_pmu_counter_can_chain(vcpu, i))
+			kvm_pmu_counter_increment(vcpu, BIT(i + 1),
+						  ARMV8_PMUV3_PERFCTR_CHAIN);
+	}
+}
+
 /**
  * When the perf event overflows, set the overflow status and inform the vcpu.
  */
@@ -514,6 +453,10 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
 
 	__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx);
 
+	if (kvm_pmu_counter_can_chain(vcpu, idx))
+		kvm_pmu_counter_increment(vcpu, BIT(idx + 1),
+					  ARMV8_PMUV3_PERFCTR_CHAIN);
+
 	if (kvm_pmu_overflow_status(vcpu)) {
 		kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 
@@ -533,50 +476,7 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
  */
 void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
 {
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	int i;
-
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return;
-
-	if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E))
-		return;
-
-	/* Weed out disabled counters */
-	val &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
-
-	for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++) {
-		u64 type, reg;
-
-		if (!(val & BIT(i)))
-			continue;
-
-		/* PMSWINC only applies to ... SW_INC! */
-		type = __vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i);
-		type &= kvm_pmu_event_mask(vcpu->kvm);
-		if (type != ARMV8_PMUV3_PERFCTR_SW_INCR)
-			continue;
-
-		/* increment this even SW_INC counter */
-		reg = __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) + 1;
-		reg = lower_32_bits(reg);
-		__vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) = reg;
-
-		if (reg) /* no overflow on the low part */
-			continue;
-
-		if (kvm_pmu_pmc_is_chained(&pmu->pmc[i])) {
-			/* increment the high counter */
-			reg = __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i + 1) + 1;
-			reg = lower_32_bits(reg);
-			__vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i + 1) = reg;
-			if (!reg) /* mark overflow on the high counter */
-				__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i + 1);
-		} else {
-			/* mark overflow on low counter */
-			__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i);
-		}
-	}
+	kvm_pmu_counter_increment(vcpu, val, ARMV8_PMUV3_PERFCTR_SW_INCR);
 }
 
 /**
@@ -625,18 +525,11 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 {
 	struct arm_pmu *arm_pmu = vcpu->kvm->arch.arm_pmu;
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc;
+	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
 	struct perf_event *event;
 	struct perf_event_attr attr;
 	u64 eventsel, counter, reg, data;
 
-	/*
-	 * For chained counters the event type and filtering attributes are
-	 * obtained from the low/even counter. We also use this counter to
-	 * determine if the event is enabled/disabled.
-	 */
-	pmc = kvm_pmu_get_canonical_pmc(&pmu->pmc[select_idx]);
-
 	reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
 	      ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + pmc->idx;
 	data = __vcpu_sys_reg(vcpu, reg);
@@ -647,8 +540,12 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 	else
 		eventsel = data & kvm_pmu_event_mask(vcpu->kvm);
 
-	/* Software increment event doesn't need to be backed by a perf event */
-	if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR)
+	/*
+	 * Neither SW increment nor chained events need to be backed
+	 * by a perf event.
+	 */
+	if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR ||
+	    eventsel == ARMV8_PMUV3_PERFCTR_CHAIN)
 		return;
 
 	/*
@@ -670,30 +567,21 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 	attr.exclude_host = 1; /* Don't count host events */
 	attr.config = eventsel;
 
-	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
+	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
 
-	if (kvm_pmu_pmc_is_chained(pmc)) {
-		/**
-		 * The initial sample period (overflow count) of an event. For
-		 * chained counters we only support overflow interrupts on the
-		 * high counter.
-		 */
+	/*
+	 * If counting with a 64bit counter, advertise it to the perf
+	 * code, carefully dealing with the initial sample period.
+	 */
+	if (kvm_pmu_idx_is_64bit(vcpu, select_idx)) {
+		attr.config1 |= PERF_ATTR_CFG1_COUNTER_64BIT;
 		attr.sample_period = (-counter) & GENMASK(63, 0);
-		attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
-
-		event = perf_event_create_kernel_counter(&attr, -1, current,
-							 kvm_pmu_perf_overflow,
-							 pmc + 1);
 	} else {
-		/* The initial sample period (overflow count) of an event. */
-		if (kvm_pmu_idx_is_64bit(vcpu, pmc->idx))
-			attr.sample_period = (-counter) & GENMASK(63, 0);
-		else
-			attr.sample_period = (-counter) & GENMASK(31, 0);
+		attr.sample_period = (-counter) & GENMASK(31, 0);
+	}
 
-		event = perf_event_create_kernel_counter(&attr, -1, current,
+	event = perf_event_create_kernel_counter(&attr, -1, current,
 						 kvm_pmu_perf_overflow, pmc);
-	}
 
 	if (IS_ERR(event)) {
 		pr_err_once("kvm: pmu event creation failed %ld\n",
@@ -704,41 +592,6 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 	pmc->perf_event = event;
 }
 
-/**
- * kvm_pmu_update_pmc_chained - update chained bitmap
- * @vcpu: The vcpu pointer
- * @select_idx: The number of selected counter
- *
- * Update the chained bitmap based on the event type written in the
- * typer register and the enable state of the odd register.
- */
-static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx)
-{
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc = &pmu->pmc[select_idx], *canonical_pmc;
-	bool new_state, old_state;
-
-	old_state = kvm_pmu_pmc_is_chained(pmc);
-	new_state = kvm_pmu_idx_has_chain_evtype(vcpu, pmc->idx) &&
-		    kvm_pmu_counter_is_enabled(vcpu, pmc->idx | 0x1);
-
-	if (old_state == new_state)
-		return;
-
-	canonical_pmc = kvm_pmu_get_canonical_pmc(pmc);
-	kvm_pmu_stop_counter(vcpu, canonical_pmc);
-	if (new_state) {
-		/*
-		 * During promotion from !chained to chained we must ensure
-		 * the adjacent counter is stopped and its event destroyed
-		 */
-		kvm_pmu_stop_counter(vcpu, kvm_pmu_get_alternate_pmc(pmc));
-		set_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
-		return;
-	}
-	clear_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
-}
-
 /**
  * kvm_pmu_set_counter_event_type - set selected counter to monitor some event
  * @vcpu: The vcpu pointer
@@ -766,7 +619,6 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 
 	__vcpu_sys_reg(vcpu, reg) = data & mask;
 
-	kvm_pmu_update_pmc_chained(vcpu, select_idx);
 	kvm_pmu_create_perf_event(vcpu, select_idx);
 }
 
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index c0b868ce6a8f..96b192139a23 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -11,7 +11,6 @@
 #include <asm/perf_event.h>
 
 #define ARMV8_PMU_CYCLE_IDX		(ARMV8_PMU_MAX_COUNTERS - 1)
-#define ARMV8_PMU_MAX_COUNTER_PAIRS	((ARMV8_PMU_MAX_COUNTERS + 1) >> 1)
 
 #ifdef CONFIG_HW_PERF_EVENTS
 
@@ -29,7 +28,6 @@ struct kvm_pmu {
 	struct irq_work overflow_work;
 	struct kvm_pmu_events events;
 	struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS];
-	DECLARE_BITMAP(chained, ARMV8_PMU_MAX_COUNTER_PAIRS);
 	int irq_num;
 	bool created;
 	bool irq_level;
-- 
cgit v1.2.3


From 3d0dba5764b94308b8c4257ad64e383f11ce0c92 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 13 Nov 2022 16:38:26 +0000
Subject: KVM: arm64: PMU: Move the ID_AA64DFR0_EL1.PMUver limit to VM creation

As further patches will enable the selection of a PMU revision
from userspace, sample the supported PMU revision at VM creation
time, rather than building each time the ID_AA64DFR0_EL1 register
is accessed.

This shouldn't result in any change in behaviour.

Reviewed-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221113163832.3154370-11-maz@kernel.org
---
 arch/arm64/include/asm/kvm_host.h |  4 ++++
 arch/arm64/kvm/arm.c              |  6 ++++++
 arch/arm64/kvm/pmu-emul.c         | 11 +++++++++++
 arch/arm64/kvm/sys_regs.c         | 36 ++++++++++++++++++++++++++++--------
 include/kvm/arm_pmu.h             |  6 ++++++
 5 files changed, 55 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 45e2136322ba..cc44e3bc528d 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -163,6 +163,10 @@ struct kvm_arch {
 
 	u8 pfr0_csv2;
 	u8 pfr0_csv3;
+	struct {
+		u8 imp:4;
+		u8 unimp:4;
+	} dfr0_pmuver;
 
 	/* Hypercall features firmware registers' descriptor */
 	struct kvm_smccc_features smccc_feat;
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 94d33e296e10..f956aab438c7 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -164,6 +164,12 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	set_default_spectre(kvm);
 	kvm_arm_init_hypercalls(kvm);
 
+	/*
+	 * Initialise the default PMUver before there is a chance to
+	 * create an actual PMU.
+	 */
+	kvm->arch.dfr0_pmuver.imp = kvm_arm_pmu_get_pmuver_limit();
+
 	return ret;
 out_free_stage2_pgd:
 	kvm_free_stage2_pgd(&kvm->arch.mmu);
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 7a945fa6dd03..94ca2d17a4e4 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -1047,3 +1047,14 @@ int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 
 	return -ENXIO;
 }
+
+u8 kvm_arm_pmu_get_pmuver_limit(void)
+{
+	u64 tmp;
+
+	tmp = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1);
+	tmp = cpuid_feature_cap_perfmon_field(tmp,
+					      ID_AA64DFR0_EL1_PMUVer_SHIFT,
+					      ID_AA64DFR0_EL1_PMUVer_V3P4);
+	return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), tmp);
+}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index f4a7c5abcbca..297b4fcbf969 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1062,6 +1062,27 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static u8 vcpu_pmuver(const struct kvm_vcpu *vcpu)
+{
+	if (kvm_vcpu_has_pmu(vcpu))
+		return vcpu->kvm->arch.dfr0_pmuver.imp;
+
+	return vcpu->kvm->arch.dfr0_pmuver.unimp;
+}
+
+static u8 pmuver_to_perfmon(u8 pmuver)
+{
+	switch (pmuver) {
+	case ID_AA64DFR0_EL1_PMUVer_IMP:
+		return ID_DFR0_PERFMON_8_0;
+	case ID_AA64DFR0_EL1_PMUVer_IMP_DEF:
+		return ID_DFR0_PERFMON_IMP_DEF;
+	default:
+		/* Anything ARMv8.1+ and NI have the same value. For now. */
+		return pmuver;
+	}
+}
+
 /* Read a sanitised cpufeature ID register by sys_reg_desc */
 static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r)
 {
@@ -1111,18 +1132,17 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r
 		/* Limit debug to ARMv8.0 */
 		val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer);
 		val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer), 6);
-		/* Limit guests to PMUv3 for ARMv8.4 */
-		val = cpuid_feature_cap_perfmon_field(val,
-						      ID_AA64DFR0_EL1_PMUVer_SHIFT,
-						      kvm_vcpu_has_pmu(vcpu) ? ID_AA64DFR0_EL1_PMUVer_V3P4 : 0);
+		/* Set PMUver to the required version */
+		val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer);
+		val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer),
+				  vcpu_pmuver(vcpu));
 		/* Hide SPE from guests */
 		val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMSVer);
 		break;
 	case SYS_ID_DFR0_EL1:
-		/* Limit guests to PMUv3 for ARMv8.4 */
-		val = cpuid_feature_cap_perfmon_field(val,
-						      ID_DFR0_PERFMON_SHIFT,
-						      kvm_vcpu_has_pmu(vcpu) ? ID_DFR0_PERFMON_8_4 : 0);
+		val &= ~ARM64_FEATURE_MASK(ID_DFR0_PERFMON);
+		val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_DFR0_PERFMON),
+				  pmuver_to_perfmon(vcpu_pmuver(vcpu)));
 		break;
 	}
 
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 96b192139a23..812f729c9108 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -89,6 +89,8 @@ void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu);
 			vcpu->arch.pmu.events = *kvm_get_pmu_events();	\
 	} while (0)
 
+u8 kvm_arm_pmu_get_pmuver_limit(void);
+
 #else
 struct kvm_pmu {
 };
@@ -154,6 +156,10 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 static inline void kvm_pmu_update_vcpu_events(struct kvm_vcpu *vcpu) {}
 static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {}
 static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {}
+static inline u8 kvm_arm_pmu_get_pmuver_limit(void)
+{
+	return 0;
+}
 
 #endif
 
-- 
cgit v1.2.3


From 11af4c37165e36a6090172ded5d06acdf15206da Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 13 Nov 2022 16:38:29 +0000
Subject: KVM: arm64: PMU: Implement PMUv3p5 long counter support

PMUv3p5 (which is mandatory with ARMv8.5) comes with some extra
features:

- All counters are 64bit

- The overflow point is controlled by the PMCR_EL0.LP bit

Add the required checks in the helpers that control counter
width and overflow, as well as the sysreg handling for the LP
bit. A new kvm_pmu_is_3p5() helper makes it easy to spot the
PMUv3p5 specific handling.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221113163832.3154370-14-maz@kernel.org
---
 arch/arm64/kvm/pmu-emul.c | 8 +++++---
 arch/arm64/kvm/sys_regs.c | 4 ++++
 include/kvm/arm_pmu.h     | 7 +++++++
 3 files changed, 16 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 94ca2d17a4e4..7e25ff73cbba 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -52,13 +52,15 @@ static u32 kvm_pmu_event_mask(struct kvm *kvm)
  */
 static bool kvm_pmu_idx_is_64bit(struct kvm_vcpu *vcpu, u64 select_idx)
 {
-	return (select_idx == ARMV8_PMU_CYCLE_IDX);
+	return (select_idx == ARMV8_PMU_CYCLE_IDX || kvm_pmu_is_3p5(vcpu));
 }
 
 static bool kvm_pmu_idx_has_64bit_overflow(struct kvm_vcpu *vcpu, u64 select_idx)
 {
-	return (select_idx == ARMV8_PMU_CYCLE_IDX &&
-		__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_LC);
+	u64 val = __vcpu_sys_reg(vcpu, PMCR_EL0);
+
+	return (select_idx < ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LP)) ||
+	       (select_idx == ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LC));
 }
 
 static bool kvm_pmu_counter_can_chain(struct kvm_vcpu *vcpu, u64 idx)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index b8ac58723459..67eac0f747be 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -654,6 +654,8 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	       | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E);
 	if (!kvm_supports_32bit_el0())
 		val |= ARMV8_PMU_PMCR_LC;
+	if (!kvm_pmu_is_3p5(vcpu))
+		val &= ~ARMV8_PMU_PMCR_LP;
 	__vcpu_sys_reg(vcpu, r->reg) = val;
 }
 
@@ -703,6 +705,8 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		val |= p->regval & ARMV8_PMU_PMCR_MASK;
 		if (!kvm_supports_32bit_el0())
 			val |= ARMV8_PMU_PMCR_LC;
+		if (!kvm_pmu_is_3p5(vcpu))
+			val &= ~ARMV8_PMU_PMCR_LP;
 		__vcpu_sys_reg(vcpu, PMCR_EL0) = val;
 		kvm_pmu_handle_pmcr(vcpu, val);
 		kvm_vcpu_pmu_restore_guest(vcpu);
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 812f729c9108..628775334d5e 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -89,6 +89,12 @@ void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu);
 			vcpu->arch.pmu.events = *kvm_get_pmu_events();	\
 	} while (0)
 
+/*
+ * Evaluates as true when emulating PMUv3p5, and false otherwise.
+ */
+#define kvm_pmu_is_3p5(vcpu)						\
+	(vcpu->kvm->arch.dfr0_pmuver.imp >= ID_AA64DFR0_EL1_PMUVer_V3P5)
+
 u8 kvm_arm_pmu_get_pmuver_limit(void);
 
 #else
@@ -153,6 +159,7 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 }
 
 #define kvm_vcpu_has_pmu(vcpu)		({ false; })
+#define kvm_pmu_is_3p5(vcpu)		({ false; })
 static inline void kvm_pmu_update_vcpu_events(struct kvm_vcpu *vcpu) {}
 static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {}
 static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {}
-- 
cgit v1.2.3


From b0284cd29a957e62d60c2886fd663be93c56f9c0 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Thu, 3 Nov 2022 18:10:34 -0700
Subject: mm: Do not enable PG_arch_2 for all 64-bit architectures

Commit 4beba9486abd ("mm: Add PG_arch_2 page flag") introduced a new
page flag for all 64-bit architectures. However, even if an architecture
is 64-bit, it may still have limited spare bits in the 'flags' member of
'struct page'. This may happen if an architecture enables SPARSEMEM
without SPARSEMEM_VMEMMAP as is the case with the newly added loongarch.
This architecture port needs 19 more bits for the sparsemem section
information and, while it is currently fine with PG_arch_2, adding any
more PG_arch_* flags will trigger build-time warnings.

Add a new CONFIG_ARCH_USES_PG_ARCH_X option which can be selected by
architectures that need more PG_arch_* flags beyond PG_arch_1. Select it
on arm64.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
[pcc@google.com: fix build with CONFIG_ARM64_MTE disabled]
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Steven Price <steven.price@arm.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221104011041.290951-2-pcc@google.com
---
 arch/arm64/Kconfig             | 1 +
 fs/proc/page.c                 | 2 +-
 include/linux/page-flags.h     | 2 +-
 include/trace/events/mmflags.h | 8 ++++----
 mm/Kconfig                     | 8 ++++++++
 mm/huge_memory.c               | 2 +-
 6 files changed, 16 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 505c8a1ccbe0..cd93d0738425 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1965,6 +1965,7 @@ config ARM64_MTE
 	depends on ARM64_PAN
 	select ARCH_HAS_SUBPAGE_FAULTS
 	select ARCH_USES_HIGH_VMA_FLAGS
+	select ARCH_USES_PG_ARCH_X
 	help
 	  Memory Tagging (part of the ARMv8.5 Extensions) provides
 	  architectural support for run-time, always-on detection of
diff --git a/fs/proc/page.c b/fs/proc/page.c
index f2273b164535..882525c8e94c 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -219,7 +219,7 @@ u64 stable_page_flags(struct page *page)
 	u |= kpf_copy_bit(k, KPF_PRIVATE_2,	PG_private_2);
 	u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE,	PG_owner_priv_1);
 	u |= kpf_copy_bit(k, KPF_ARCH,		PG_arch_1);
-#ifdef CONFIG_64BIT
+#ifdef CONFIG_ARCH_USES_PG_ARCH_X
 	u |= kpf_copy_bit(k, KPF_ARCH_2,	PG_arch_2);
 #endif
 
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 0b0ae5084e60..5dc7977edf9d 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -132,7 +132,7 @@ enum pageflags {
 	PG_young,
 	PG_idle,
 #endif
-#ifdef CONFIG_64BIT
+#ifdef CONFIG_ARCH_USES_PG_ARCH_X
 	PG_arch_2,
 #endif
 #ifdef CONFIG_KASAN_HW_TAGS
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index e87cb2b80ed3..d9f6d35fb150 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -91,10 +91,10 @@
 #define IF_HAVE_PG_IDLE(flag,string)
 #endif
 
-#ifdef CONFIG_64BIT
-#define IF_HAVE_PG_ARCH_2(flag,string) ,{1UL << flag, string}
+#ifdef CONFIG_ARCH_USES_PG_ARCH_X
+#define IF_HAVE_PG_ARCH_X(flag,string) ,{1UL << flag, string}
 #else
-#define IF_HAVE_PG_ARCH_2(flag,string)
+#define IF_HAVE_PG_ARCH_X(flag,string)
 #endif
 
 #ifdef CONFIG_KASAN_HW_TAGS
@@ -130,7 +130,7 @@ IF_HAVE_PG_UNCACHED(PG_uncached,	"uncached"	)		\
 IF_HAVE_PG_HWPOISON(PG_hwpoison,	"hwpoison"	)		\
 IF_HAVE_PG_IDLE(PG_young,		"young"		)		\
 IF_HAVE_PG_IDLE(PG_idle,		"idle"		)		\
-IF_HAVE_PG_ARCH_2(PG_arch_2,		"arch_2"	)		\
+IF_HAVE_PG_ARCH_X(PG_arch_2,		"arch_2"	)		\
 IF_HAVE_PG_SKIP_KASAN_POISON(PG_skip_kasan_poison, "skip_kasan_poison")
 
 #define show_page_flags(flags)						\
diff --git a/mm/Kconfig b/mm/Kconfig
index 57e1d8c5b505..807bd7192f51 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1005,6 +1005,14 @@ config ARCH_USES_HIGH_VMA_FLAGS
 config ARCH_HAS_PKEYS
 	bool
 
+config ARCH_USES_PG_ARCH_X
+	bool
+	help
+	  Enable the definition of PG_arch_x page flags with x > 1. Only
+	  suitable for 64-bit architectures with CONFIG_FLATMEM or
+	  CONFIG_SPARSEMEM_VMEMMAP enabled, otherwise there may not be
+	  enough room for additional bits in page->flags.
+
 config VM_EVENT_COUNTERS
 	default y
 	bool "Enable VM event counters for /proc/vmstat" if EXPERT
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 561a42567477..76e7b973919c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2444,7 +2444,7 @@ static void __split_huge_page_tail(struct page *head, int tail,
 			 (1L << PG_workingset) |
 			 (1L << PG_locked) |
 			 (1L << PG_unevictable) |
-#ifdef CONFIG_64BIT
+#ifdef CONFIG_ARCH_USES_PG_ARCH_X
 			 (1L << PG_arch_2) |
 #endif
 			 (1L << PG_dirty) |
-- 
cgit v1.2.3


From ef6458b1b6ca3fdb991ce4182e981a88d4c58c0f Mon Sep 17 00:00:00 2001
From: Peter Collingbourne <pcc@google.com>
Date: Thu, 3 Nov 2022 18:10:37 -0700
Subject: mm: Add PG_arch_3 page flag

As with PG_arch_2, this flag is only allowed on 64-bit architectures due
to the shortage of bits available. It will be used by the arm64 MTE code
in subsequent patches.

Signed-off-by: Peter Collingbourne <pcc@google.com>
Cc: Will Deacon <will@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Steven Price <steven.price@arm.com>
[catalin.marinas@arm.com: added flag preserving in __split_huge_page_tail()]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221104011041.290951-5-pcc@google.com
---
 fs/proc/page.c                    | 1 +
 include/linux/kernel-page-flags.h | 1 +
 include/linux/page-flags.h        | 1 +
 include/trace/events/mmflags.h    | 1 +
 mm/huge_memory.c                  | 1 +
 5 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/fs/proc/page.c b/fs/proc/page.c
index 882525c8e94c..6249c347809a 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -221,6 +221,7 @@ u64 stable_page_flags(struct page *page)
 	u |= kpf_copy_bit(k, KPF_ARCH,		PG_arch_1);
 #ifdef CONFIG_ARCH_USES_PG_ARCH_X
 	u |= kpf_copy_bit(k, KPF_ARCH_2,	PG_arch_2);
+	u |= kpf_copy_bit(k, KPF_ARCH_3,	PG_arch_3);
 #endif
 
 	return u;
diff --git a/include/linux/kernel-page-flags.h b/include/linux/kernel-page-flags.h
index eee1877a354e..859f4b0c1b2b 100644
--- a/include/linux/kernel-page-flags.h
+++ b/include/linux/kernel-page-flags.h
@@ -18,5 +18,6 @@
 #define KPF_UNCACHED		39
 #define KPF_SOFTDIRTY		40
 #define KPF_ARCH_2		41
+#define KPF_ARCH_3		42
 
 #endif /* LINUX_KERNEL_PAGE_FLAGS_H */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 5dc7977edf9d..c50ce2812f17 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -134,6 +134,7 @@ enum pageflags {
 #endif
 #ifdef CONFIG_ARCH_USES_PG_ARCH_X
 	PG_arch_2,
+	PG_arch_3,
 #endif
 #ifdef CONFIG_KASAN_HW_TAGS
 	PG_skip_kasan_poison,
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index d9f6d35fb150..412b5a46374c 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -131,6 +131,7 @@ IF_HAVE_PG_HWPOISON(PG_hwpoison,	"hwpoison"	)		\
 IF_HAVE_PG_IDLE(PG_young,		"young"		)		\
 IF_HAVE_PG_IDLE(PG_idle,		"idle"		)		\
 IF_HAVE_PG_ARCH_X(PG_arch_2,		"arch_2"	)		\
+IF_HAVE_PG_ARCH_X(PG_arch_3,		"arch_3"	)		\
 IF_HAVE_PG_SKIP_KASAN_POISON(PG_skip_kasan_poison, "skip_kasan_poison")
 
 #define show_page_flags(flags)						\
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 76e7b973919c..dfe72ea23c5f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2446,6 +2446,7 @@ static void __split_huge_page_tail(struct page *head, int tail,
 			 (1L << PG_unevictable) |
 #ifdef CONFIG_ARCH_USES_PG_ARCH_X
 			 (1L << PG_arch_2) |
+			 (1L << PG_arch_3) |
 #endif
 			 (1L << PG_dirty) |
 			 LRU_GEN_MASK | LRU_REFS_MASK));
-- 
cgit v1.2.3