Merge tag 'pull-vfio-20230710' of https://github.com/legoater/qemu into staging

vfio queue:

* Fixes in error handling paths of VFIO PCI devices
* Improvements of reported errors for VFIO migration
* Linux header update
* Enablement of AtomicOps completers on root ports
* Fix for unplug of passthrough AP devices

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEoPZlSPBIlev+awtgUaNDx8/77KEFAmSrug0ACgkQUaNDx8/7
# 7KHYCRAAt6UeZi8nKPlN+cs6guOagCcAJOu13nm7XN0bFxjYf/Q2t618cpM7PLSk
# h+4VGsMUVJ1dumcCkBmv7LAn0G6CpVR3VDi5QuGfMODRhpWfSoaypPIizRgrbarL
# lSyaVaPIaddlDZ4AIfFA9Ebnytvm5/ecsyTr0cv7OejVKWI/jN6bC/v36AmNQKKQ
# J5RCDpQ6fOsdqf0Dzvn7xjuHRE4DYtsWkVoslDoBQMgPWHLF8UwRu/OPD6cBQYAR
# /fmgoOkkNDMdN3laqwAyfAUjKfOFpLuZzJ5KNFjtkBiktm66dw4Y8/lWoChVR+S6
# PRZ3nk0HxyzB96zCytfggBX905PBD54LIuockRaYKTlTxT19C3fDjDz5tsjKNhLR
# aFec4KiJaUJj0fa/Vw8DB/WUbCgbOXGHiWhY8vNdpVoc9AZe8xj9z4nB3hmzx1i/
# lZhsM/s3kTNHpVGlW7vTfbToFBmt1eoglu+ILe/HeHLi8LjzCsHy+wR5c0n0/HVI
# fLUuUS1AGQvi8+HCCUi7gwzpJkl4rPJsPx51wfXJk+q/3GQ8g9Mg9qotHNHm4N60
# zq/I5VqqEkJzdaMjup04ZqsMAWqGrnU2f4aNPvBhgaeO9CQE/buIsA34buQRwiG4
# wTodqm0jrkx0Z59jliZ0mFU/LxMvhMaQCEh+OdyZ9vRtfLBjF4c=
# =U2Hc
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 10 Jul 2023 08:58:05 AM BST
# gpg:                using RSA key A0F66548F04895EBFE6B0B6051A343C7CFFBECA1
# gpg: Good signature from "Cédric Le Goater <clg@kaod.org>" [undefined]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: A0F6 6548 F048 95EB FE6B  0B60 51A3 43C7 CFFB ECA1

* tag 'pull-vfio-20230710' of https://github.com/legoater/qemu:
  vfio/pci: Enable AtomicOps completers on root ports
  pcie: Add a PCIe capability version helper
  s390x/ap: Wire up the device request notifier interface
  linux-headers: update to v6.5-rc1
  vfio: Fix null pointer dereference bug in vfio_bars_finalize()
  vfio/migration: Return bool type for vfio_migration_realize()
  vfio/migration: Remove print of "Migration disabled"
  vfio/migration: Free resources when vfio_migration_realize fails
  vfio/migration: Change vIOMMU blocker from global to per device
  vfio/pci: Disable INTx in vfio_realize error path
  hw/vfio/pci-quirks: Sanitize capability pointer

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

7 files changed, 110 insertions, 6 deletions

diff --git a/linux-headers/linux/const.h b/linux-headers/linux/const.h
index 5e48987251..1eb84b5087 100644
--- a/linux-headers/linux/const.h
+++ b/linux-headers/linux/const.h
@@ -28,7 +28,7 @@
 #define _BITUL(x)	(_UL(1) << (x))
 #define _BITULL(x)	(_ULL(1) << (x))
 
-#define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
+#define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1)
 #define __ALIGN_KERNEL_MASK(x, mask)	(((x) + (mask)) & ~(mask))
 
 #define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
index 599de3c6e3..1f3f3333a4 100644
--- a/linux-headers/linux/kvm.h
+++ b/linux-headers/linux/kvm.h
@@ -341,8 +341,11 @@ struct kvm_run {
 			__u64 nr;
 			__u64 args[6];
 			__u64 ret;
-			__u32 longmode;
-			__u32 pad;
+
+			union {
+				__u32 longmode;
+				__u64 flags;
+			};
 		} hypercall;
 		/* KVM_EXIT_TPR_ACCESS */
 		struct {
@@ -1182,6 +1185,9 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224
 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225
 #define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226
+#define KVM_CAP_COUNTER_OFFSET 227
+#define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
+#define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1434,6 +1440,8 @@ enum kvm_device_type {
 #define KVM_DEV_TYPE_XIVE		KVM_DEV_TYPE_XIVE
 	KVM_DEV_TYPE_ARM_PV_TIME,
 #define KVM_DEV_TYPE_ARM_PV_TIME	KVM_DEV_TYPE_ARM_PV_TIME
+	KVM_DEV_TYPE_RISCV_AIA,
+#define KVM_DEV_TYPE_RISCV_AIA		KVM_DEV_TYPE_RISCV_AIA
 	KVM_DEV_TYPE_MAX,
 };
 
@@ -1449,7 +1457,7 @@ struct kvm_vfio_spapr_tce {
 #define KVM_CREATE_VCPU           _IO(KVMIO,   0x41)
 #define KVM_GET_DIRTY_LOG         _IOW(KVMIO,  0x42, struct kvm_dirty_log)
 #define KVM_SET_NR_MMU_PAGES      _IO(KVMIO,   0x44)
-#define KVM_GET_NR_MMU_PAGES      _IO(KVMIO,   0x45)
+#define KVM_GET_NR_MMU_PAGES      _IO(KVMIO,   0x45)  /* deprecated */
 #define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \
 					struct kvm_userspace_memory_region)
 #define KVM_SET_TSS_ADDR          _IO(KVMIO,   0x47)
@@ -1541,6 +1549,8 @@ struct kvm_s390_ucas_mapping {
 #define KVM_SET_PMU_EVENT_FILTER  _IOW(KVMIO,  0xb2, struct kvm_pmu_event_filter)
 #define KVM_PPC_SVM_OFF		  _IO(KVMIO,  0xb3)
 #define KVM_ARM_MTE_COPY_TAGS	  _IOR(KVMIO,  0xb4, struct kvm_arm_copy_mte_tags)
+/* Available with KVM_CAP_COUNTER_OFFSET */
+#define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO,  0xb5, struct kvm_arm_counter_offset)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
@@ -1603,7 +1613,7 @@ struct kvm_s390_ucas_mapping {
 #define KVM_GET_DEBUGREGS         _IOR(KVMIO,  0xa1, struct kvm_debugregs)
 #define KVM_SET_DEBUGREGS         _IOW(KVMIO,  0xa2, struct kvm_debugregs)
 /*
- * vcpu version available with KVM_ENABLE_CAP
+ * vcpu version available with KVM_CAP_ENABLE_CAP
  * vm version available with KVM_CAP_ENABLE_CAP_VM
  */
 #define KVM_ENABLE_CAP            _IOW(KVMIO,  0xa3, struct kvm_enable_cap)
diff --git a/linux-headers/linux/mman.h b/linux-headers/linux/mman.h
index 434986fbe3..4e8cb60780 100644
--- a/linux-headers/linux/mman.h
+++ b/linux-headers/linux/mman.h
@@ -4,6 +4,7 @@
 
 #include <asm/mman.h>
 #include <asm-generic/hugetlb_encode.h>
+#include <linux/types.h>
 
 #define MREMAP_MAYMOVE		1
 #define MREMAP_FIXED		2
@@ -41,4 +42,17 @@
 #define MAP_HUGE_2GB	HUGETLB_FLAG_ENCODE_2GB
 #define MAP_HUGE_16GB	HUGETLB_FLAG_ENCODE_16GB
 
+struct cachestat_range {
+	__u64 off;
+	__u64 len;
+};
+
+struct cachestat {
+	__u64 nr_cache;
+	__u64 nr_dirty;
+	__u64 nr_writeback;
+	__u64 nr_evicted;
+	__u64 nr_recently_evicted;
+};
+
 #endif /* _LINUX_MMAN_H */
diff --git a/linux-headers/linux/psp-sev.h b/linux-headers/linux/psp-sev.h
index 51d8b3940e..12ccb70099 100644
--- a/linux-headers/linux/psp-sev.h
+++ b/linux-headers/linux/psp-sev.h
@@ -36,6 +36,13 @@ enum {
  * SEV Firmware status code
  */
 typedef enum {
+	/*
+	 * This error code is not in the SEV spec. Its purpose is to convey that
+	 * there was an error that prevented the SEV firmware from being called.
+	 * The SEV API error codes are 16 bits, so the -1 value will not overlap
+	 * with possible values from the specification.
+	 */
+	SEV_RET_NO_FW_CALL = -1,
 	SEV_RET_SUCCESS = 0,
 	SEV_RET_INVALID_PLATFORM_STATE,
 	SEV_RET_INVALID_GUEST_STATE,
diff --git a/linux-headers/linux/userfaultfd.h b/linux-headers/linux/userfaultfd.h
index ba5d0df52f..14e402263a 100644
--- a/linux-headers/linux/userfaultfd.h
+++ b/linux-headers/linux/userfaultfd.h
@@ -38,7 +38,8 @@
 			   UFFD_FEATURE_MINOR_HUGETLBFS |	\
 			   UFFD_FEATURE_MINOR_SHMEM |		\
 			   UFFD_FEATURE_EXACT_ADDRESS |		\
-			   UFFD_FEATURE_WP_HUGETLBFS_SHMEM)
+			   UFFD_FEATURE_WP_HUGETLBFS_SHMEM |	\
+			   UFFD_FEATURE_WP_UNPOPULATED)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -203,6 +204,12 @@ struct uffdio_api {
 	 *
 	 * UFFD_FEATURE_WP_HUGETLBFS_SHMEM indicates that userfaultfd
 	 * write-protection mode is supported on both shmem and hugetlbfs.
+	 *
+	 * UFFD_FEATURE_WP_UNPOPULATED indicates that userfaultfd
+	 * write-protection mode will always apply to unpopulated pages
+	 * (i.e. empty ptes).  This will be the default behavior for shmem
+	 * & hugetlbfs, so this flag only affects anonymous memory behavior
+	 * when userfault write-protection mode is registered.
 	 */
 #define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
 #define UFFD_FEATURE_EVENT_FORK			(1<<1)
@@ -217,6 +224,7 @@ struct uffdio_api {
 #define UFFD_FEATURE_MINOR_SHMEM		(1<<10)
 #define UFFD_FEATURE_EXACT_ADDRESS		(1<<11)
 #define UFFD_FEATURE_WP_HUGETLBFS_SHMEM		(1<<12)
+#define UFFD_FEATURE_WP_UNPOPULATED		(1<<13)
 	__u64 features;
 
 	__u64 ioctls;
@@ -297,6 +305,13 @@ struct uffdio_writeprotect {
 struct uffdio_continue {
 	struct uffdio_range range;
 #define UFFDIO_CONTINUE_MODE_DONTWAKE		((__u64)1<<0)
+	/*
+	 * UFFDIO_CONTINUE_MODE_WP will map the page write protected on
+	 * the fly.  UFFDIO_CONTINUE_MODE_WP is available only if the
+	 * write protected ioctl is implemented for the range
+	 * according to the uffdio_register.ioctls.
+	 */
+#define UFFDIO_CONTINUE_MODE_WP			((__u64)1<<1)
 	__u64 mode;
 
 	/*
diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
index 4a534edbdc..16db89071e 100644
--- a/linux-headers/linux/vfio.h
+++ b/linux-headers/linux/vfio.h
@@ -213,6 +213,7 @@ struct vfio_device_info {
 #define VFIO_DEVICE_FLAGS_AP	(1 << 5)	/* vfio-ap device */
 #define VFIO_DEVICE_FLAGS_FSL_MC (1 << 6)	/* vfio-fsl-mc device */
 #define VFIO_DEVICE_FLAGS_CAPS	(1 << 7)	/* Info supports caps */
+#define VFIO_DEVICE_FLAGS_CDX	(1 << 8)	/* vfio-cdx device */
 	__u32	num_regions;	/* Max region index + 1 */
 	__u32	num_irqs;	/* Max IRQ index + 1 */
 	__u32   cap_offset;	/* Offset within info struct of first cap */
@@ -240,6 +241,20 @@ struct vfio_device_info {
 #define VFIO_DEVICE_INFO_CAP_ZPCI_UTIL		3
 #define VFIO_DEVICE_INFO_CAP_ZPCI_PFIP		4
 
+/*
+ * The following VFIO_DEVICE_INFO capability reports support for PCIe AtomicOp
+ * completion to the root bus with supported widths provided via flags.
+ */
+#define VFIO_DEVICE_INFO_CAP_PCI_ATOMIC_COMP	5
+struct vfio_device_info_cap_pci_atomic_comp {
+	struct vfio_info_cap_header header;
+	__u32 flags;
+#define VFIO_PCI_ATOMIC_COMP32	(1 << 0)
+#define VFIO_PCI_ATOMIC_COMP64	(1 << 1)
+#define VFIO_PCI_ATOMIC_COMP128	(1 << 2)
+	__u32 reserved;
+};
+
 /**
  * VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8,
  *				       struct vfio_region_info)
@@ -511,6 +526,9 @@ struct vfio_region_info_cap_nvlink2_lnkspd {
  * then add and unmask vectors, it's up to userspace to make the decision
  * whether to allocate the maximum supported number of vectors or tear
  * down setup and incrementally increase the vectors as each is enabled.
+ * Absence of the NORESIZE flag indicates that vectors can be enabled
+ * and disabled dynamically without impacting other vectors within the
+ * index.
  */
 struct vfio_irq_info {
 	__u32	argsz;
@@ -646,6 +664,15 @@ enum {
 	VFIO_CCW_NUM_IRQS
 };
 
+/*
+ * The vfio-ap bus driver makes use of the following IRQ index mapping.
+ * Unimplemented IRQ types return a count of zero.
+ */
+enum {
+	VFIO_AP_REQ_IRQ_INDEX,
+	VFIO_AP_NUM_IRQS
+};
+
 /**
  * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 12,
  *					      struct vfio_pci_hot_reset_info)
diff --git a/linux-headers/linux/vhost.h b/linux-headers/linux/vhost.h
index 92e1b700b5..f5c48b61ab 100644
--- a/linux-headers/linux/vhost.h
+++ b/linux-headers/linux/vhost.h
@@ -45,6 +45,25 @@
 #define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64)
 /* Specify an eventfd file descriptor to signal on log write. */
 #define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int)
+/* By default, a device gets one vhost_worker that its virtqueues share. This
+ * command allows the owner of the device to create an additional vhost_worker
+ * for the device. It can later be bound to 1 or more of its virtqueues using
+ * the VHOST_ATTACH_VRING_WORKER command.
+ *
+ * This must be called after VHOST_SET_OWNER and the caller must be the owner
+ * of the device. The new thread will inherit caller's cgroups and namespaces,
+ * and will share the caller's memory space. The new thread will also be
+ * counted against the caller's RLIMIT_NPROC value.
+ *
+ * The worker's ID used in other commands will be returned in
+ * vhost_worker_state.
+ */
+#define VHOST_NEW_WORKER _IOR(VHOST_VIRTIO, 0x8, struct vhost_worker_state)
+/* Free a worker created with VHOST_NEW_WORKER if it's not attached to any
+ * virtqueue. If userspace is not able to call this for workers its created,
+ * the kernel will free all the device's workers when the device is closed.
+ */
+#define VHOST_FREE_WORKER _IOW(VHOST_VIRTIO, 0x9, struct vhost_worker_state)
 
 /* Ring setup. */
 /* Set number of descriptors in ring. This parameter can not
@@ -70,6 +89,18 @@
 #define VHOST_VRING_BIG_ENDIAN 1
 #define VHOST_SET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x13, struct vhost_vring_state)
 #define VHOST_GET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x14, struct vhost_vring_state)
+/* Attach a vhost_worker created with VHOST_NEW_WORKER to one of the device's
+ * virtqueues.
+ *
+ * This will replace the virtqueue's existing worker. If the replaced worker
+ * is no longer attached to any virtqueues, it can be freed with
+ * VHOST_FREE_WORKER.
+ */
+#define VHOST_ATTACH_VRING_WORKER _IOW(VHOST_VIRTIO, 0x15,		\
+				       struct vhost_vring_worker)
+/* Return the vring worker's ID */
+#define VHOST_GET_VRING_WORKER _IOWR(VHOST_VIRTIO, 0x16,		\
+				     struct vhost_vring_worker)
 
 /* The following ioctls use eventfd file descriptors to signal and poll
  * for events. */