v5.14

tools/include/uapi/linux/bpf.h

@@ -527,6 +527,15 @@ union bpf_iter_link_info {
  *		Look up an element with the given *key* in the map referred to
  *		by the file descriptor *fd*, and if found, delete the element.
  *
+ *		For **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map
+ *		types, the *flags* argument needs to be set to 0, but for other
+ *		map types, it may be specified as:
+ *
+ *		**BPF_F_LOCK**
+ *			Look up and delete the value of a spin-locked map
+ *			without returning the lock. This must be specified if
+ *			the elements contain a spinlock.
+ *
  *		The **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map types
  *		implement this command as a "pop" operation, deleting the top
  *		element rather than one corresponding to *key*.
@@ -536,6 +545,10 @@ union bpf_iter_link_info {
  *		This command is only valid for the following map types:
  *		* **BPF_MAP_TYPE_QUEUE**
  *		* **BPF_MAP_TYPE_STACK**
+ *		* **BPF_MAP_TYPE_HASH**
+ *		* **BPF_MAP_TYPE_PERCPU_HASH**
+ *		* **BPF_MAP_TYPE_LRU_HASH**
+ *		* **BPF_MAP_TYPE_LRU_PERCPU_HASH**
  *
  *	Return
  *		Returns zero on success. On error, -1 is returned and *errno*
@@ -837,6 +850,7 @@ enum bpf_cmd {
 	BPF_PROG_ATTACH,
 	BPF_PROG_DETACH,
 	BPF_PROG_TEST_RUN,
+	BPF_PROG_RUN = BPF_PROG_TEST_RUN,
 	BPF_PROG_GET_NEXT_ID,
 	BPF_MAP_GET_NEXT_ID,
 	BPF_PROG_GET_FD_BY_ID,
@@ -937,6 +951,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_EXT,
 	BPF_PROG_TYPE_LSM,
 	BPF_PROG_TYPE_SK_LOOKUP,
+	BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */
 };
 
 enum bpf_attach_type {
@@ -979,6 +994,8 @@ enum bpf_attach_type {
 	BPF_SK_LOOKUP,
 	BPF_XDP,
 	BPF_SK_SKB_VERDICT,
+	BPF_SK_REUSEPORT_SELECT,
+	BPF_SK_REUSEPORT_SELECT_OR_MIGRATE,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1097,8 +1114,8 @@ enum bpf_link_type {
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * the following extensions:
  *
- * insn[0].src_reg:  BPF_PSEUDO_MAP_FD
- * insn[0].imm:      map fd
+ * insn[0].src_reg:  BPF_PSEUDO_MAP_[FD|IDX]
+ * insn[0].imm:      map fd or fd_idx
  * insn[1].imm:      0
  * insn[0].off:      0
  * insn[1].off:      0
@@ -1106,15 +1123,19 @@ enum bpf_link_type {
  * verifier type:    CONST_PTR_TO_MAP
  */
 #define BPF_PSEUDO_MAP_FD	1
-/* insn[0].src_reg:  BPF_PSEUDO_MAP_VALUE
- * insn[0].imm:      map fd
+#define BPF_PSEUDO_MAP_IDX	5
+
+/* insn[0].src_reg:  BPF_PSEUDO_MAP_[IDX_]VALUE
+ * insn[0].imm:      map fd or fd_idx
  * insn[1].imm:      offset into value
  * insn[0].off:      0
  * insn[1].off:      0
  * ldimm64 rewrite:  address of map[0]+offset
  * verifier type:    PTR_TO_MAP_VALUE
  */
-#define BPF_PSEUDO_MAP_VALUE	2
+#define BPF_PSEUDO_MAP_VALUE		2
+#define BPF_PSEUDO_MAP_IDX_VALUE	6
+
 /* insn[0].src_reg:  BPF_PSEUDO_BTF_ID
  * insn[0].imm:      kernel btd id of VAR
  * insn[1].imm:      0
@@ -1314,6 +1335,8 @@ union bpf_attr {
 			/* or valid module BTF object fd or 0 to attach to vmlinux */
 			__u32		attach_btf_obj_fd;
 		};
+		__u32		:32;		/* pad */
+		__aligned_u64	fd_array;	/* array of FDs */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -2534,8 +2557,12 @@ union bpf_attr {
  * 		The lower two bits of *flags* are used as the return code if
  * 		the map lookup fails. This is so that the return value can be
  * 		one of the XDP program return codes up to **XDP_TX**, as chosen
- * 		by the caller. Any higher bits in the *flags* argument must be
- * 		unset.
+ * 		by the caller. The higher bits of *flags* can be set to
+ * 		BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below.
+ *
+ * 		With BPF_F_BROADCAST the packet will be broadcasted to all the
+ * 		interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress
+ * 		interface will be excluded when do broadcasting.
  *
  * 		See also **bpf_redirect**\ (), which only supports redirecting
  * 		to an ifindex, but doesn't require a map to do so.
@@ -4735,6 +4762,24 @@ union bpf_attr {
  *		be zero-terminated except when **str_size** is 0.
  *
  *		Or **-EBUSY** if the per-CPU memory copy buffer is busy.
+ *
+ * long bpf_sys_bpf(u32 cmd, void *attr, u32 attr_size)
+ * 	Description
+ * 		Execute bpf syscall with given arguments.
+ * 	Return
+ * 		A syscall result.
+ *
+ * long bpf_btf_find_by_name_kind(char *name, int name_sz, u32 kind, int flags)
+ * 	Description
+ * 		Find BTF type with given name and kind in vmlinux BTF or in module's BTFs.
+ * 	Return
+ * 		Returns btf_id and btf_obj_fd in lower and upper 32 bits.
+ *
+ * long bpf_sys_close(u32 fd)
+ * 	Description
+ * 		Execute close syscall for given FD.
+ * 	Return
+ * 		A syscall result.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -4903,6 +4948,9 @@ union bpf_attr {
 	FN(check_mtu),			\
 	FN(for_each_map_elem),		\
 	FN(snprintf),			\
+	FN(sys_bpf),			\
+	FN(btf_find_by_name_kind),	\
+	FN(sys_close),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5080,6 +5128,12 @@ enum {
 	BPF_F_BPRM_SECUREEXEC	= (1ULL << 0),
 };
 
+/* Flags for bpf_redirect_map helper */
+enum {
+	BPF_F_BROADCAST		= (1ULL << 3),
+	BPF_F_EXCLUDE_INGRESS	= (1ULL << 4),
+};
+
 #define __bpf_md_ptr(type, name)	\
 union {					\
 	type name;			\
@@ -5364,6 +5418,20 @@ struct sk_reuseport_md {
 	__u32 ip_protocol;	/* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
 	__u32 bind_inany;	/* Is sock bound to an INANY address? */
 	__u32 hash;		/* A hash of the packet 4 tuples */
+	/* When reuse->migrating_sk is NULL, it is selecting a sk for the
+	 * new incoming connection request (e.g. selecting a listen sk for
+	 * the received SYN in the TCP case).  reuse->sk is one of the sk
+	 * in the reuseport group. The bpf prog can use reuse->sk to learn
+	 * the local listening ip/port without looking into the skb.
+	 *
+	 * When reuse->migrating_sk is not NULL, reuse->sk is closed and
+	 * reuse->migrating_sk is the socket that needs to be migrated
+	 * to another listening socket.  migrating_sk could be a fullsock
+	 * sk that is fully established or a reqsk that is in-the-middle
+	 * of 3-way handshake.
+	 */
+	__bpf_md_ptr(struct bpf_sock *, sk);
+	__bpf_md_ptr(struct bpf_sock *, migrating_sk);
 };
 
 #define BPF_TAG_SIZE	8

tools/include/uapi/linux/kvm.h

@@ -280,6 +280,9 @@ struct kvm_xen_exit {
 /* Encounter unexpected vm-exit reason */
 #define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON	4
 
+/* Flags that describe what fields in emulation_failure hold valid data. */
+#define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0)
+
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
 	/* in */
@@ -383,6 +386,25 @@ struct kvm_run {
 			__u32 ndata;
 			__u64 data[16];
 		} internal;
+		/*
+		 * KVM_INTERNAL_ERROR_EMULATION
+		 *
+		 * "struct emulation_failure" is an overlay of "struct internal"
+		 * that is used for the KVM_INTERNAL_ERROR_EMULATION sub-type of
+		 * KVM_EXIT_INTERNAL_ERROR.  Note, unlike other internal error
+		 * sub-types, this struct is ABI!  It also needs to be backwards
+		 * compatible with "struct internal".  Take special care that
+		 * "ndata" is correct, that new fields are enumerated in "flags",
+		 * and that each flag enumerates fields that are 64-bit aligned
+		 * and sized (so that ndata+internal.data[] is valid/accurate).
+		 */
+		struct {
+			__u32 suberror;
+			__u32 ndata;
+			__u64 flags;
+			__u8  insn_size;
+			__u8  insn_bytes[15];
+		} emulation_failure;
 		/* KVM_EXIT_OSI */
 		struct {
 			__u64 gprs[32];
@@ -1083,6 +1105,13 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_SGX_ATTRIBUTE 196
 #define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197
 #define KVM_CAP_PTP_KVM 198
+#define KVM_CAP_HYPERV_ENFORCE_CPUID 199
+#define KVM_CAP_SREGS2 200
+#define KVM_CAP_EXIT_HYPERCALL 201
+#define KVM_CAP_PPC_RPT_INVALIDATE 202
+#define KVM_CAP_BINARY_STATS_FD 203
+#define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204
+#define KVM_CAP_ARM_MTE 205
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1428,6 +1457,7 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_PMU_EVENT_FILTER */
 #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)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
@@ -1621,6 +1651,9 @@ struct kvm_xen_hvm_attr {
 #define KVM_XEN_VCPU_GET_ATTR	_IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr)
 #define KVM_XEN_VCPU_SET_ATTR	_IOW(KVMIO,  0xcb, struct kvm_xen_vcpu_attr)
 
+#define KVM_GET_SREGS2             _IOR(KVMIO,  0xcc, struct kvm_sregs2)
+#define KVM_SET_SREGS2             _IOW(KVMIO,  0xcd, struct kvm_sregs2)
+
 struct kvm_xen_vcpu_attr {
 	__u16 type;
 	__u16 pad[3];
@@ -1899,4 +1932,76 @@ struct kvm_dirty_gfn {
 #define KVM_BUS_LOCK_DETECTION_OFF             (1 << 0)
 #define KVM_BUS_LOCK_DETECTION_EXIT            (1 << 1)
 
+/**
+ * struct kvm_stats_header - Header of per vm/vcpu binary statistics data.
+ * @flags: Some extra information for header, always 0 for now.
+ * @name_size: The size in bytes of the memory which contains statistics
+ *             name string including trailing '\0'. The memory is allocated
+ *             at the send of statistics descriptor.
+ * @num_desc: The number of statistics the vm or vcpu has.
+ * @id_offset: The offset of the vm/vcpu stats' id string in the file pointed
+ *             by vm/vcpu stats fd.
+ * @desc_offset: The offset of the vm/vcpu stats' descriptor block in the file
+ *               pointd by vm/vcpu stats fd.
+ * @data_offset: The offset of the vm/vcpu stats' data block in the file
+ *               pointed by vm/vcpu stats fd.
+ *
+ * This is the header userspace needs to read from stats fd before any other
+ * readings. It is used by userspace to discover all the information about the
+ * vm/vcpu's binary statistics.
+ * Userspace reads this header from the start of the vm/vcpu's stats fd.
+ */
+struct kvm_stats_header {
+	__u32 flags;
+	__u32 name_size;
+	__u32 num_desc;
+	__u32 id_offset;
+	__u32 desc_offset;
+	__u32 data_offset;
+};
+
+#define KVM_STATS_TYPE_SHIFT		0
+#define KVM_STATS_TYPE_MASK		(0xF << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_CUMULATIVE	(0x0 << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_INSTANT		(0x1 << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_PEAK		(0x2 << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_MAX		KVM_STATS_TYPE_PEAK
+
+#define KVM_STATS_UNIT_SHIFT		4
+#define KVM_STATS_UNIT_MASK		(0xF << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_NONE		(0x0 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_BYTES		(0x1 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_SECONDS		(0x2 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_CYCLES		(0x3 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_MAX		KVM_STATS_UNIT_CYCLES
+
+#define KVM_STATS_BASE_SHIFT		8
+#define KVM_STATS_BASE_MASK		(0xF << KVM_STATS_BASE_SHIFT)
+#define KVM_STATS_BASE_POW10		(0x0 << KVM_STATS_BASE_SHIFT)
+#define KVM_STATS_BASE_POW2		(0x1 << KVM_STATS_BASE_SHIFT)
+#define KVM_STATS_BASE_MAX		KVM_STATS_BASE_POW2
+
+/**
+ * struct kvm_stats_desc - Descriptor of a KVM statistics.
+ * @flags: Annotations of the stats, like type, unit, etc.
+ * @exponent: Used together with @flags to determine the unit.
+ * @size: The number of data items for this stats.
+ *        Every data item is of type __u64.
+ * @offset: The offset of the stats to the start of stat structure in
+ *          struture kvm or kvm_vcpu.
+ * @unused: Unused field for future usage. Always 0 for now.
+ * @name: The name string for the stats. Its size is indicated by the
+ *        &kvm_stats_header->name_size.
+ */
+struct kvm_stats_desc {
+	__u32 flags;
+	__s16 exponent;
+	__u16 size;
+	__u32 offset;
+	__u32 unused;
+	char name[];
+};
+
+#define KVM_GET_STATS_FD  _IO(KVMIO,  0xce)
+
 #endif /* __LINUX_KVM_H */

tools/include/uapi/linux/mount.h

@@ -120,6 +120,7 @@ enum fsconfig_command {
 #define MOUNT_ATTR_STRICTATIME	0x00000020 /* - Always perform atime updates */
 #define MOUNT_ATTR_NODIRATIME	0x00000080 /* Do not update directory access times */
 #define MOUNT_ATTR_IDMAP	0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */
+#define MOUNT_ATTR_NOSYMFOLLOW	0x00200000 /* Do not follow symlinks */
 
 /*
  * mount_setattr()

tools/include/uapi/linux/prctl.h

@@ -259,4 +259,12 @@ struct prctl_mm_map {
 #define PR_PAC_SET_ENABLED_KEYS		60
 #define PR_PAC_GET_ENABLED_KEYS		61
 
+/* Request the scheduler to share a core */
+#define PR_SCHED_CORE			62
+# define PR_SCHED_CORE_GET		0
+# define PR_SCHED_CORE_CREATE		1 /* create unique core_sched cookie */
+# define PR_SCHED_CORE_SHARE_TO		2 /* push core_sched cookie to pid */
+# define PR_SCHED_CORE_SHARE_FROM	3 /* pull core_sched cookie to pid */
+# define PR_SCHED_CORE_MAX		4
+
 #endif /* _LINUX_PRCTL_H */