summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/linux/anon_inodes.h4
-rw-r--r--include/linux/kvm_host.h142
-rw-r--r--include/linux/kvm_types.h1
-rw-r--r--include/linux/pagemap.h19
-rw-r--r--include/uapi/linux/kvm.h49
5 files changed, 189 insertions, 26 deletions
diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h
index 5deaddbd7927..93a5f16d03f3 100644
--- a/include/linux/anon_inodes.h
+++ b/include/linux/anon_inodes.h
@@ -15,13 +15,13 @@ struct inode;
struct file *anon_inode_getfile(const char *name,
const struct file_operations *fops,
void *priv, int flags);
-struct file *anon_inode_getfile_secure(const char *name,
+struct file *anon_inode_create_getfile(const char *name,
const struct file_operations *fops,
void *priv, int flags,
const struct inode *context_inode);
int anon_inode_getfd(const char *name, const struct file_operations *fops,
void *priv, int flags);
-int anon_inode_getfd_secure(const char *name,
+int anon_inode_create_getfd(const char *name,
const struct file_operations *fops,
void *priv, int flags,
const struct inode *context_inode);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 4944136efaa2..ea1523a7b83a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -80,8 +80,8 @@
/* Two fragments for cross MMIO pages. */
#define KVM_MAX_MMIO_FRAGMENTS 2
-#ifndef KVM_ADDRESS_SPACE_NUM
-#define KVM_ADDRESS_SPACE_NUM 1
+#ifndef KVM_MAX_NR_ADDRESS_SPACES
+#define KVM_MAX_NR_ADDRESS_SPACES 1
#endif
/*
@@ -253,9 +253,10 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
#endif
-#ifdef KVM_ARCH_WANT_MMU_NOTIFIER
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
union kvm_mmu_notifier_arg {
pte_t pte;
+ unsigned long attributes;
};
struct kvm_gfn_range {
@@ -588,8 +589,20 @@ struct kvm_memory_slot {
u32 flags;
short id;
u16 as_id;
+
+#ifdef CONFIG_KVM_PRIVATE_MEM
+ struct {
+ struct file __rcu *file;
+ pgoff_t pgoff;
+ } gmem;
+#endif
};
+static inline bool kvm_slot_can_be_private(const struct kvm_memory_slot *slot)
+{
+ return slot && (slot->flags & KVM_MEM_GUEST_MEMFD);
+}
+
static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot)
{
return slot->flags & KVM_MEM_LOG_DIRTY_PAGES;
@@ -677,13 +690,29 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm);
#define KVM_MEM_SLOTS_NUM SHRT_MAX
#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS)
-#ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
+#if KVM_MAX_NR_ADDRESS_SPACES == 1
+static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm)
+{
+ return KVM_MAX_NR_ADDRESS_SPACES;
+}
+
static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
{
return 0;
}
#endif
+/*
+ * Arch code must define kvm_arch_has_private_mem if support for private memory
+ * is enabled.
+ */
+#if !defined(kvm_arch_has_private_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM)
+static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
+{
+ return false;
+}
+#endif
+
struct kvm_memslots {
u64 generation;
atomic_long_t last_used_slot;
@@ -721,9 +750,9 @@ struct kvm {
struct mm_struct *mm; /* userspace tied to this vm */
unsigned long nr_memslot_pages;
/* The two memslot sets - active and inactive (per address space) */
- struct kvm_memslots __memslots[KVM_ADDRESS_SPACE_NUM][2];
+ struct kvm_memslots __memslots[KVM_MAX_NR_ADDRESS_SPACES][2];
/* The current active memslot set for each address space */
- struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
+ struct kvm_memslots __rcu *memslots[KVM_MAX_NR_ADDRESS_SPACES];
struct xarray vcpu_array;
/*
* Protected by slots_lock, but can be read outside if an
@@ -783,12 +812,12 @@ struct kvm {
struct hlist_head irq_ack_notifier_list;
#endif
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
struct mmu_notifier mmu_notifier;
unsigned long mmu_invalidate_seq;
long mmu_invalidate_in_progress;
- unsigned long mmu_invalidate_range_start;
- unsigned long mmu_invalidate_range_end;
+ gfn_t mmu_invalidate_range_start;
+ gfn_t mmu_invalidate_range_end;
#endif
struct list_head devices;
u64 manual_dirty_log_protect;
@@ -807,6 +836,10 @@ struct kvm {
#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
struct notifier_block pm_notifier;
#endif
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+ /* Protected by slots_locks (for writes) and RCU (for reads) */
+ struct xarray mem_attr_array;
+#endif
char stats_id[KVM_STATS_NAME_SIZE];
};
@@ -989,7 +1022,7 @@ void kvm_put_kvm_no_destroy(struct kvm *kvm);
static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
{
- as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM);
+ as_id = array_index_nospec(as_id, KVM_MAX_NR_ADDRESS_SPACES);
return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
lockdep_is_held(&kvm->slots_lock) ||
!refcount_read(&kvm->users_count));
@@ -1146,9 +1179,9 @@ enum kvm_mr_change {
};
int kvm_set_memory_region(struct kvm *kvm,
- const struct kvm_userspace_memory_region *mem);
+ const struct kvm_userspace_memory_region2 *mem);
int __kvm_set_memory_region(struct kvm *kvm,
- const struct kvm_userspace_memory_region *mem);
+ const struct kvm_userspace_memory_region2 *mem);
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot);
void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen);
int kvm_arch_prepare_memory_region(struct kvm *kvm,
@@ -1392,10 +1425,10 @@ void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc);
void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
#endif
-void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
- unsigned long end);
-void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
- unsigned long end);
+void kvm_mmu_invalidate_begin(struct kvm *kvm);
+void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end);
+void kvm_mmu_invalidate_end(struct kvm *kvm);
+bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
long kvm_arch_dev_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg);
@@ -1947,7 +1980,7 @@ extern const struct _kvm_stats_desc kvm_vm_stats_desc[];
extern const struct kvm_stats_header kvm_vcpu_stats_header;
extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
{
if (unlikely(kvm->mmu_invalidate_in_progress))
@@ -1970,9 +2003,9 @@ static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
return 0;
}
-static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
+static inline int mmu_invalidate_retry_gfn(struct kvm *kvm,
unsigned long mmu_seq,
- unsigned long hva)
+ gfn_t gfn)
{
lockdep_assert_held(&kvm->mmu_lock);
/*
@@ -1981,10 +2014,20 @@ static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
* that might be being invalidated. Note that it may include some false
* positives, due to shortcuts when handing concurrent invalidations.
*/
- if (unlikely(kvm->mmu_invalidate_in_progress) &&
- hva >= kvm->mmu_invalidate_range_start &&
- hva < kvm->mmu_invalidate_range_end)
- return 1;
+ if (unlikely(kvm->mmu_invalidate_in_progress)) {
+ /*
+ * Dropping mmu_lock after bumping mmu_invalidate_in_progress
+ * but before updating the range is a KVM bug.
+ */
+ if (WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA ||
+ kvm->mmu_invalidate_range_end == INVALID_GPA))
+ return 1;
+
+ if (gfn >= kvm->mmu_invalidate_range_start &&
+ gfn < kvm->mmu_invalidate_range_end)
+ return 1;
+ }
+
if (kvm->mmu_invalidate_seq != mmu_seq)
return 1;
return 0;
@@ -2318,4 +2361,57 @@ static inline void kvm_account_pgtable_pages(void *virt, int nr)
/* Max number of entries allowed for each kvm dirty ring */
#define KVM_DIRTY_RING_MAX_ENTRIES 65536
+static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
+ gpa_t gpa, gpa_t size,
+ bool is_write, bool is_exec,
+ bool is_private)
+{
+ vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
+ vcpu->run->memory_fault.gpa = gpa;
+ vcpu->run->memory_fault.size = size;
+
+ /* RWX flags are not (yet) defined or communicated to userspace. */
+ vcpu->run->memory_fault.flags = 0;
+ if (is_private)
+ vcpu->run->memory_fault.flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE;
+}
+
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
+{
+ return xa_to_value(xa_load(&kvm->mem_attr_array, gfn));
+}
+
+bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+ unsigned long attrs);
+bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
+ struct kvm_gfn_range *range);
+bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
+ struct kvm_gfn_range *range);
+
+static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
+{
+ return IS_ENABLED(CONFIG_KVM_PRIVATE_MEM) &&
+ kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE;
+}
+#else
+static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
+{
+ return false;
+}
+#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
+
+#ifdef CONFIG_KVM_PRIVATE_MEM
+int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+ gfn_t gfn, kvm_pfn_t *pfn, int *max_order);
+#else
+static inline int kvm_gmem_get_pfn(struct kvm *kvm,
+ struct kvm_memory_slot *slot, gfn_t gfn,
+ kvm_pfn_t *pfn, int *max_order)
+{
+ KVM_BUG_ON(1, kvm);
+ return -EIO;
+}
+#endif /* CONFIG_KVM_PRIVATE_MEM */
+
#endif
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 6f4737d5046a..9d1f7835d8c1 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -6,6 +6,7 @@
struct kvm;
struct kvm_async_pf;
struct kvm_device_ops;
+struct kvm_gfn_range;
struct kvm_interrupt;
struct kvm_irq_routing_table;
struct kvm_memory_slot;
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index bcc1ea44b4e8..bf2965b01b35 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -203,7 +203,8 @@ enum mapping_flags {
/* writeback related tags are not used */
AS_NO_WRITEBACK_TAGS = 5,
AS_LARGE_FOLIO_SUPPORT = 6,
- AS_RELEASE_ALWAYS, /* Call ->release_folio(), even if no private data */
+ AS_RELEASE_ALWAYS = 7, /* Call ->release_folio(), even if no private data */
+ AS_UNMOVABLE = 8, /* The mapping cannot be moved, ever */
};
/**
@@ -289,6 +290,22 @@ static inline void mapping_clear_release_always(struct address_space *mapping)
clear_bit(AS_RELEASE_ALWAYS, &mapping->flags);
}
+static inline void mapping_set_unmovable(struct address_space *mapping)
+{
+ /*
+ * It's expected unmovable mappings are also unevictable. Compaction
+ * migrate scanner (isolate_migratepages_block()) relies on this to
+ * reduce page locking.
+ */
+ set_bit(AS_UNEVICTABLE, &mapping->flags);
+ set_bit(AS_UNMOVABLE, &mapping->flags);
+}
+
+static inline bool mapping_unmovable(struct address_space *mapping)
+{
+ return test_bit(AS_UNMOVABLE, &mapping->flags);
+}
+
static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
{
return mapping->gfp_mask;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 211b86de35ac..e9cb2df67a1d 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -95,6 +95,19 @@ struct kvm_userspace_memory_region {
__u64 userspace_addr; /* start of the userspace allocated memory */
};
+/* for KVM_SET_USER_MEMORY_REGION2 */
+struct kvm_userspace_memory_region2 {
+ __u32 slot;
+ __u32 flags;
+ __u64 guest_phys_addr;
+ __u64 memory_size;
+ __u64 userspace_addr;
+ __u64 guest_memfd_offset;
+ __u32 guest_memfd;
+ __u32 pad1;
+ __u64 pad2[14];
+};
+
/*
* The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for
* userspace, other bits are reserved for kvm internal use which are defined
@@ -102,6 +115,7 @@ struct kvm_userspace_memory_region {
*/
#define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0)
#define KVM_MEM_READONLY (1UL << 1)
+#define KVM_MEM_GUEST_MEMFD (1UL << 2)
/* for KVM_IRQ_LINE */
struct kvm_irq_level {
@@ -265,6 +279,7 @@ struct kvm_xen_exit {
#define KVM_EXIT_RISCV_CSR 36
#define KVM_EXIT_NOTIFY 37
#define KVM_EXIT_LOONGARCH_IOCSR 38
+#define KVM_EXIT_MEMORY_FAULT 39
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
@@ -518,6 +533,13 @@ struct kvm_run {
#define KVM_NOTIFY_CONTEXT_INVALID (1 << 0)
__u32 flags;
} notify;
+ /* KVM_EXIT_MEMORY_FAULT */
+ struct {
+#define KVM_MEMORY_EXIT_FLAG_PRIVATE (1ULL << 3)
+ __u64 flags;
+ __u64 gpa;
+ __u64 size;
+ } memory_fault;
/* Fix the size of the union. */
char padding[256];
};
@@ -1201,6 +1223,11 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
#define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
#define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
+#define KVM_CAP_USER_MEMORY2 231
+#define KVM_CAP_MEMORY_FAULT_INFO 232
+#define KVM_CAP_MEMORY_ATTRIBUTES 233
+#define KVM_CAP_GUEST_MEMFD 234
+#define KVM_CAP_VM_TYPES 235
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1483,6 +1510,8 @@ struct kvm_vfio_spapr_tce {
struct kvm_userspace_memory_region)
#define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47)
#define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO, 0x48, __u64)
+#define KVM_SET_USER_MEMORY_REGION2 _IOW(KVMIO, 0x49, \
+ struct kvm_userspace_memory_region2)
/* enable ucontrol for s390 */
struct kvm_s390_ucas_mapping {
@@ -2267,4 +2296,24 @@ struct kvm_s390_zpci_op {
/* flags for kvm_s390_zpci_op->u.reg_aen.flags */
#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0)
+/* Available with KVM_CAP_MEMORY_ATTRIBUTES */
+#define KVM_SET_MEMORY_ATTRIBUTES _IOW(KVMIO, 0xd2, struct kvm_memory_attributes)
+
+struct kvm_memory_attributes {
+ __u64 address;
+ __u64 size;
+ __u64 attributes;
+ __u64 flags;
+};
+
+#define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3)
+
+#define KVM_CREATE_GUEST_MEMFD _IOWR(KVMIO, 0xd4, struct kvm_create_guest_memfd)
+
+struct kvm_create_guest_memfd {
+ __u64 size;
+ __u64 flags;
+ __u64 reserved[6];
+};
+
#endif /* __LINUX_KVM_H */
generated by cgit (git 2.34.1) at 2024-06-28 03:17:19 +0000