diff options
Diffstat (limited to 'include')
28 files changed, 174 insertions, 64 deletions
diff --git a/include/linux/audit.h b/include/linux/audit.h index 0050ef288ab3..a394614ccd0b 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -417,7 +417,7 @@ extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); extern void __audit_openat2_how(struct open_how *how); -extern void __audit_log_kern_module(char *name); +extern void __audit_log_kern_module(const char *name); extern void __audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar); extern void __audit_tk_injoffset(struct timespec64 offset); extern void __audit_ntp_log(const struct audit_ntp_data *ad); @@ -519,7 +519,7 @@ static inline void audit_openat2_how(struct open_how *how) __audit_openat2_how(how); } -static inline void audit_log_kern_module(char *name) +static inline void audit_log_kern_module(const char *name) { if (!audit_dummy_context()) __audit_log_kern_module(name); @@ -677,9 +677,8 @@ static inline void audit_mmap_fd(int fd, int flags) static inline void audit_openat2_how(struct open_how *how) { } -static inline void audit_log_kern_module(char *name) -{ -} +static inline void audit_log_kern_module(const char *name) +{ } static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { } diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index e4ce1cae03bf..b3b53f8c1b28 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -596,7 +596,7 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, if (p_size != SIZE_MAX && p_size < size) fortify_panic(func, FORTIFY_WRITE, p_size, size, true); else if (q_size != SIZE_MAX && q_size < size) - fortify_panic(func, FORTIFY_READ, p_size, size, true); + fortify_panic(func, FORTIFY_READ, q_size, size, true); /* * Warn when writing beyond destination field size. diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index a19e4bd32e4d..7773eb870039 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -200,7 +200,7 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, */ #define infof(fc, fmt, ...) __logfc(fc, 'i', fmt, ## __VA_ARGS__) #define info_plog(p, fmt, ...) __plog(p, 'i', fmt, ## __VA_ARGS__) -#define infofc(p, fmt, ...) __plog((&(fc)->log), 'i', fmt, ## __VA_ARGS__) +#define infofc(fc, fmt, ...) __plog((&(fc)->log), 'i', fmt, ## __VA_ARGS__) /** * warnf - Store supplementary warning message diff --git a/include/linux/if_team.h b/include/linux/if_team.h index cdc684e04a2f..ce97d891cf72 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -191,8 +191,6 @@ struct team { const struct header_ops *header_ops_cache; - struct mutex lock; /* used for overall locking, e.g. port lists write */ - /* * List of enabled ports and their count */ @@ -223,7 +221,6 @@ struct team { atomic_t count_pending; struct delayed_work dw; } mcast_rejoin; - struct lock_class_key team_lock_key; long mode_priv[TEAM_MODE_PRIV_LONGS]; }; diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h index b25377b6ea98..5210e8371238 100644 --- a/include/linux/ioprio.h +++ b/include/linux/ioprio.h @@ -60,7 +60,8 @@ static inline int __get_task_ioprio(struct task_struct *p) int prio; if (!ioc) - return IOPRIO_DEFAULT; + return IOPRIO_PRIO_VALUE(task_nice_ioclass(p), + task_nice_ioprio(p)); if (p != current) lockdep_assert_held(&p->alloc_lock); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 6822cfa5f4ad..9d2467f982ad 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -280,6 +280,7 @@ enum { MLX5_MKEY_MASK_SMALL_FENCE = 1ull << 23, MLX5_MKEY_MASK_RELAXED_ORDERING_WRITE = 1ull << 25, MLX5_MKEY_MASK_FREE = 1ull << 29, + MLX5_MKEY_MASK_PAGE_SIZE_5 = 1ull << 42, MLX5_MKEY_MASK_RELAXED_ORDERING_READ = 1ull << 47, }; diff --git a/include/linux/mm.h b/include/linux/mm.h index 2e4584e1bfcd..82b7bea9fa7c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -33,6 +33,7 @@ #include <linux/slab.h> #include <linux/cacheinfo.h> #include <linux/rcuwait.h> +#include <linux/sched/mm.h> struct mempolicy; struct anon_vma; @@ -716,6 +717,10 @@ static inline void vma_refcount_put(struct vm_area_struct *vma) * reused and attached to a different mm before we lock it. * Returns the vma on success, NULL on failure to lock and EAGAIN if vma got * detached. + * + * WARNING! The vma passed to this function cannot be used if the function + * fails to lock it because in certain cases RCU lock is dropped and then + * reacquired. Once RCU lock is dropped the vma can be concurently freed. */ static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, struct vm_area_struct *vma) @@ -745,6 +750,31 @@ static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm, } rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); + + /* + * If vma got attached to another mm from under us, that mm is not + * stable and can be freed in the narrow window after vma->vm_refcnt + * is dropped and before rcuwait_wake_up(mm) is called. Grab it before + * releasing vma->vm_refcnt. + */ + if (unlikely(vma->vm_mm != mm)) { + /* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */ + struct mm_struct *other_mm = vma->vm_mm; + + /* + * __mmdrop() is a heavy operation and we don't need RCU + * protection here. Release RCU lock during these operations. + * We reinstate the RCU read lock as the caller expects it to + * be held when this function returns even on error. + */ + rcu_read_unlock(); + mmgrab(other_mm); + vma_refcount_put(vma); + mmdrop(other_mm); + rcu_read_lock(); + return NULL; + } + /* * Overflow of vm_lock_seq/mm_lock_seq might produce false locked result. * False unlocked result is impossible because we modify and check diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index bfb85fd13e1f..110e9d09de24 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -282,10 +282,9 @@ struct kparam_array #define __moduleparam_const const #endif -/* This is the fundamental function for registering boot/module - parameters. */ +/* This is the fundamental function for registering boot/module parameters. */ #define __module_param_call(prefix, name, ops, arg, perm, level, flags) \ - /* Default value instead of permissions? */ \ + static_assert(sizeof(""prefix) - 1 <= MAX_PARAM_PREFIX_LEN); \ static const char __param_str_##name[] = prefix #name; \ static struct kernel_param __moduleparam_const __param_##name \ __used __section("__param") \ diff --git a/include/linux/padata.h b/include/linux/padata.h index 0146daf34430..765f2778e264 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -90,8 +90,6 @@ struct padata_cpumask { * @processed: Number of already processed objects. * @cpu: Next CPU to be processed. * @cpumask: The cpumasks in use for parallel and serial workers. - * @reorder_work: work struct for reordering. - * @lock: Reorder lock. */ struct parallel_data { struct padata_shell *ps; @@ -102,8 +100,6 @@ struct parallel_data { unsigned int processed; int cpu; struct padata_cpumask cpumask; - struct work_struct reorder_work; - spinlock_t ____cacheline_aligned lock; }; /** diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index c7abce28ed29..aab0aebb529e 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -52,6 +52,7 @@ struct pps_device { int current_mode; /* PPS mode at event time */ unsigned int last_ev; /* last PPS event id */ + unsigned int last_fetched_ev; /* last fetched PPS event id */ wait_queue_head_t queue; /* PPS event queue */ unsigned int id; /* PPS source unique ID */ diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index ea62201c74c4..703d0c76cc9a 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -27,6 +27,7 @@ enum { PROC_ENTRY_proc_read_iter = 1U << 1, PROC_ENTRY_proc_compat_ioctl = 1U << 2, + PROC_ENTRY_proc_lseek = 1U << 3, }; struct proc_ops { diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index f1fd3a8044e0..dd10c22299ab 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -84,11 +84,9 @@ enum psi_aggregators { struct psi_group_cpu { /* 1st cacheline updated by the scheduler */ - /* Aggregator needs to know of concurrent changes */ - seqcount_t seq ____cacheline_aligned_in_smp; - /* States of the tasks belonging to this group */ - unsigned int tasks[NR_PSI_TASK_COUNTS]; + unsigned int tasks[NR_PSI_TASK_COUNTS] + ____cacheline_aligned_in_smp; /* Aggregate pressure state derived from the tasks */ u32 state_mask; diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 56e27263acf8..00e232f3c2e8 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -152,9 +152,7 @@ ring_buffer_consume(struct trace_buffer *buffer, int cpu, u64 *ts, unsigned long *lost_events); struct ring_buffer_iter * -ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags); -void ring_buffer_read_prepare_sync(void); -void ring_buffer_read_start(struct ring_buffer_iter *iter); +ring_buffer_read_start(struct trace_buffer *buffer, int cpu, gfp_t flags); void ring_buffer_read_finish(struct ring_buffer_iter *iter); struct ring_buffer_event * diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b974a277975a..fad2fc972d23 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3032,6 +3032,29 @@ static inline void skb_reset_transport_header(struct sk_buff *skb) skb->transport_header = offset; } +/** + * skb_reset_transport_header_careful - conditionally reset transport header + * @skb: buffer to alter + * + * Hardened version of skb_reset_transport_header(). + * + * Returns: true if the operation was a success. + */ +static inline bool __must_check +skb_reset_transport_header_careful(struct sk_buff *skb) +{ + long offset = skb->data - skb->head; + + if (unlikely(offset != (typeof(skb->transport_header))offset)) + return false; + + if (unlikely(offset == (typeof(skb->transport_header))~0U)) + return false; + + skb->transport_header = offset; + return true; +} + static inline void skb_set_transport_header(struct sk_buff *skb, const int offset) { diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 0b9f1e598e3a..4bc6bb01a0eb 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -76,6 +76,7 @@ struct usbnet { # define EVENT_LINK_CHANGE 11 # define EVENT_SET_RX_MODE 12 # define EVENT_NO_IP_ALIGN 13 +# define EVENT_LINK_CARRIER_ON 14 /* This one is special, as it indicates that the device is going away * there are cyclic dependencies between tasklet, timer and bh * that must be broken diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 707b00772ce1..eb563f538dee 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -105,6 +105,9 @@ struct vfio_device { * @match: Optional device name match callback (return: 0 for no-match, >0 for * match, -errno for abort (ex. match with insufficient or incorrect * additional args) + * @match_token_uuid: Optional device token match/validation. Return 0 + * if the uuid is valid for the device, -errno otherwise. uuid is NULL + * if none was provided. * @dma_unmap: Called when userspace unmaps IOVA from the container * this device is attached to. * @device_feature: Optional, fill in the VFIO_DEVICE_FEATURE ioctl @@ -132,6 +135,7 @@ struct vfio_device_ops { int (*mmap)(struct vfio_device *vdev, struct vm_area_struct *vma); void (*request)(struct vfio_device *vdev, unsigned int count); int (*match)(struct vfio_device *vdev, char *buf); + int (*match_token_uuid)(struct vfio_device *vdev, const uuid_t *uuid); void (*dma_unmap)(struct vfio_device *vdev, u64 iova, u64 length); int (*device_feature)(struct vfio_device *device, u32 flags, void __user *arg, size_t argsz); diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index fbb472dd99b3..f541044e42a2 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -122,6 +122,8 @@ ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *bu int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma); void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count); int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf); +int vfio_pci_core_match_token_uuid(struct vfio_device *core_vdev, + const uuid_t *uuid); int vfio_pci_core_enable(struct vfio_pci_core_device *vdev); void vfio_pci_core_disable(struct vfio_pci_core_device *vdev); void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index f47dfb8b5be7..ebe01eb28264 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -2633,6 +2633,7 @@ struct hci_ev_le_conn_complete { #define LE_EXT_ADV_DIRECT_IND 0x0004 #define LE_EXT_ADV_SCAN_RSP 0x0008 #define LE_EXT_ADV_LEGACY_PDU 0x0010 +#define LE_EXT_ADV_DATA_STATUS_MASK 0x0060 #define LE_EXT_ADV_EVT_TYPE_MASK 0x007f #define ADDR_LE_DEV_PUBLIC 0x00 diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d22468bb4341..351a9057e70e 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -29,6 +29,7 @@ #include <linux/idr.h> #include <linux/leds.h> #include <linux/rculist.h> +#include <linux/spinlock.h> #include <linux/srcu.h> #include <net/bluetooth/hci.h> @@ -93,6 +94,7 @@ struct discovery_state { u16 uuid_count; u8 (*uuids)[16]; unsigned long name_resolve_timeout; + spinlock_t lock; }; #define SUSPEND_NOTIFIER_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ @@ -885,6 +887,7 @@ static inline void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, static inline void discovery_init(struct hci_dev *hdev) { + spin_lock_init(&hdev->discovery.lock); hdev->discovery.state = DISCOVERY_STOPPED; INIT_LIST_HEAD(&hdev->discovery.all); INIT_LIST_HEAD(&hdev->discovery.unknown); @@ -899,8 +902,11 @@ static inline void hci_discovery_filter_clear(struct hci_dev *hdev) hdev->discovery.report_invalid_rssi = true; hdev->discovery.rssi = HCI_RSSI_INVALID; hdev->discovery.uuid_count = 0; + + spin_lock(&hdev->discovery.lock); kfree(hdev->discovery.uuids); hdev->discovery.uuids = NULL; + spin_unlock(&hdev->discovery.lock); } bool hci_discovery_active(struct hci_dev *hdev); diff --git a/include/net/dst.h b/include/net/dst.h index 78c78cdce0e9..32dafbab4cd0 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -456,7 +456,7 @@ INDIRECT_CALLABLE_DECLARE(int ip_output(struct net *, struct sock *, /* Output packet to network from transport. */ static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - return INDIRECT_CALL_INET(skb_dst(skb)->output, + return INDIRECT_CALL_INET(READ_ONCE(skb_dst(skb)->output), ip6_output, ip_output, net, sk, skb); } @@ -466,7 +466,7 @@ INDIRECT_CALLABLE_DECLARE(int ip_local_deliver(struct sk_buff *)); /* Input packet from network to transport. */ static inline int dst_input(struct sk_buff *skb) { - return INDIRECT_CALL_INET(skb_dst(skb)->input, + return INDIRECT_CALL_INET(READ_ONCE(skb_dst(skb)->input), ip6_input, ip_local_deliver, skb); } @@ -561,6 +561,26 @@ static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu) dst->ops->update_pmtu(dst, NULL, skb, mtu, false); } +static inline struct net_device *dst_dev(const struct dst_entry *dst) +{ + return READ_ONCE(dst->dev); +} + +static inline struct net_device *skb_dst_dev(const struct sk_buff *skb) +{ + return dst_dev(skb_dst(skb)); +} + +static inline struct net *skb_dst_dev_net(const struct sk_buff *skb) +{ + return dev_net(skb_dst_dev(skb)); +} + +static inline struct net *skb_dst_dev_net_rcu(const struct sk_buff *skb) +{ + return dev_net_rcu(skb_dst_dev(skb)); +} + struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie); void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index 39cd50300a18..eabe80d52a6c 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -140,12 +140,12 @@ int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, static inline void lwtunnel_set_redirect(struct dst_entry *dst) { if (lwtunnel_output_redirect(dst->lwtstate)) { - dst->lwtstate->orig_output = dst->output; - dst->output = lwtunnel_output; + dst->lwtstate->orig_output = READ_ONCE(dst->output); + WRITE_ONCE(dst->output, lwtunnel_output); } if (lwtunnel_input_redirect(dst->lwtstate)) { - dst->lwtstate->orig_input = dst->input; - dst->input = lwtunnel_input; + dst->lwtstate->orig_input = READ_ONCE(dst->input); + WRITE_ONCE(dst->input, lwtunnel_input); } } #else diff --git a/include/net/tc_act/tc_ctinfo.h b/include/net/tc_act/tc_ctinfo.h index f071c1d70a25..a04bcac7adf4 100644 --- a/include/net/tc_act/tc_ctinfo.h +++ b/include/net/tc_act/tc_ctinfo.h @@ -18,9 +18,9 @@ struct tcf_ctinfo_params { struct tcf_ctinfo { struct tc_action common; struct tcf_ctinfo_params __rcu *params; - u64 stats_dscp_set; - u64 stats_dscp_error; - u64 stats_cpmark_set; + atomic64_t stats_dscp_set; + atomic64_t stats_dscp_error; + atomic64_t stats_cpmark_set; }; enum { diff --git a/include/net/udp.h b/include/net/udp.h index 6e89520e100d..b59462c5b97a 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -586,6 +586,16 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk, { netdev_features_t features = NETIF_F_SG; struct sk_buff *segs; + int drop_count; + + /* + * Segmentation in UDP receive path is only for UDP GRO, drop udp + * fragmentation offload (UFO) packets. + */ + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP) { + drop_count = 1; + goto drop; + } /* Avoid csum recalculation by skb_segment unless userspace explicitly * asks for the final checksum values @@ -609,16 +619,18 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk, */ segs = __skb_gso_segment(skb, features, false); if (IS_ERR_OR_NULL(segs)) { - int segs_nr = skb_shinfo(skb)->gso_segs; - - atomic_add(segs_nr, &sk->sk_drops); - SNMP_ADD_STATS(__UDPX_MIB(sk, ipv4), UDP_MIB_INERRORS, segs_nr); - kfree_skb(skb); - return NULL; + drop_count = skb_shinfo(skb)->gso_segs; + goto drop; } consume_skb(skb); return segs; + +drop: + atomic_add(drop_count, &sk->sk_drops); + SNMP_ADD_STATS(__UDPX_MIB(sk, ipv4), UDP_MIB_INERRORS, drop_count); + kfree_skb(skb); + return NULL; } static inline void udp_post_segment_fix_csum(struct sk_buff *skb) diff --git a/include/sound/tas2781-tlv.h b/include/sound/tas2781-tlv.h index d87263e43fdb..ef9b9f19d212 100644 --- a/include/sound/tas2781-tlv.h +++ b/include/sound/tas2781-tlv.h @@ -15,7 +15,7 @@ #ifndef __TAS2781_TLV_H__ #define __TAS2781_TLV_H__ -static const __maybe_unused DECLARE_TLV_DB_SCALE(dvc_tlv, -10000, 100, 0); +static const __maybe_unused DECLARE_TLV_DB_SCALE(dvc_tlv, -10000, 50, 0); static const __maybe_unused DECLARE_TLV_DB_SCALE(amp_vol_tlv, 1100, 50, 0); #endif diff --git a/include/trace/events/power.h b/include/trace/events/power.h index 9253e83b9bb4..ff0974e9be9a 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -99,28 +99,6 @@ DEFINE_EVENT(psci_domain_idle, psci_domain_idle_exit, TP_ARGS(cpu_id, state, s2idle) ); -TRACE_EVENT(powernv_throttle, - - TP_PROTO(int chip_id, const char *reason, int pmax), - - TP_ARGS(chip_id, reason, pmax), - - TP_STRUCT__entry( - __field(int, chip_id) - __string(reason, reason) - __field(int, pmax) - ), - - TP_fast_assign( - __entry->chip_id = chip_id; - __assign_str(reason); - __entry->pmax = pmax; - ), - - TP_printk("Chip %d Pmax %d %s", __entry->chip_id, - __entry->pmax, __get_str(reason)) -); - TRACE_EVENT(pstate_sample, TP_PROTO(u32 core_busy, diff --git a/include/uapi/drm/panthor_drm.h b/include/uapi/drm/panthor_drm.h index 97e2c4510e69..dbb907eae443 100644 --- a/include/uapi/drm/panthor_drm.h +++ b/include/uapi/drm/panthor_drm.h @@ -293,6 +293,9 @@ struct drm_panthor_gpu_info { /** @as_present: Bitmask encoding the number of address-space exposed by the MMU. */ __u32 as_present; + /** @pad0: MBZ. */ + __u32 pad0; + /** @shader_present: Bitmask encoding the shader cores exposed by the GPU. */ __u64 shader_present; diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 5764f315137f..75100bf009ba 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -905,10 +905,12 @@ struct vfio_device_feature { * VFIO_DEVICE_BIND_IOMMUFD - _IOR(VFIO_TYPE, VFIO_BASE + 18, * struct vfio_device_bind_iommufd) * @argsz: User filled size of this data. - * @flags: Must be 0. + * @flags: Must be 0 or a bit flags of VFIO_DEVICE_BIND_* * @iommufd: iommufd to bind. * @out_devid: The device id generated by this bind. devid is a handle for * this device/iommufd bond and can be used in IOMMUFD commands. + * @token_uuid_ptr: Valid if VFIO_DEVICE_BIND_FLAG_TOKEN. Points to a 16 byte + * UUID in the same format as VFIO_DEVICE_FEATURE_PCI_VF_TOKEN. * * Bind a vfio_device to the specified iommufd. * @@ -917,13 +919,21 @@ struct vfio_device_feature { * * Unbind is automatically conducted when device fd is closed. * + * A token is sometimes required to open the device, unless this is known to be + * needed VFIO_DEVICE_BIND_FLAG_TOKEN should not be set and token_uuid_ptr is + * ignored. The only case today is a PF/VF relationship where the VF bind must + * be provided the same token as VFIO_DEVICE_FEATURE_PCI_VF_TOKEN provided to + * the PF. + * * Return: 0 on success, -errno on failure. */ struct vfio_device_bind_iommufd { __u32 argsz; __u32 flags; +#define VFIO_DEVICE_BIND_FLAG_TOKEN (1 << 0) __s32 iommufd; __u32 out_devid; + __aligned_u64 token_uuid_ptr; }; #define VFIO_DEVICE_BIND_IOMMUFD _IO(VFIO_TYPE, VFIO_BASE + 18) diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index d4b3e2ae1314..e72f2655459e 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -235,4 +235,33 @@ */ #define VHOST_VDPA_GET_VRING_SIZE _IOWR(VHOST_VIRTIO, 0x82, \ struct vhost_vring_state) + +/* fork_owner values for vhost */ +#define VHOST_FORK_OWNER_KTHREAD 0 +#define VHOST_FORK_OWNER_TASK 1 + +/** + * VHOST_SET_FORK_FROM_OWNER - Set the fork_owner flag for the vhost device, + * This ioctl must called before VHOST_SET_OWNER. + * Only available when CONFIG_VHOST_ENABLE_FORK_OWNER_CONTROL=y + * + * @param fork_owner: An 8-bit value that determines the vhost thread mode + * + * When fork_owner is set to VHOST_FORK_OWNER_TASK(default value): + * - Vhost will create vhost worker as tasks forked from the owner, + * inheriting all of the owner's attributes. + * + * When fork_owner is set to VHOST_FORK_OWNER_KTHREAD: + * - Vhost will create vhost workers as kernel threads. + */ +#define VHOST_SET_FORK_FROM_OWNER _IOW(VHOST_VIRTIO, 0x83, __u8) + +/** + * VHOST_GET_FORK_OWNER - Get the current fork_owner flag for the vhost device. + * Only available when CONFIG_VHOST_ENABLE_FORK_OWNER_CONTROL=y + * + * @return: An 8-bit value indicating the current thread mode. + */ +#define VHOST_GET_FORK_FROM_OWNER _IOR(VHOST_VIRTIO, 0x84, __u8) + #endif |