diff options
Diffstat (limited to 'include/linux')
60 files changed, 404 insertions, 257 deletions
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3177181c4326..d3afea47ade6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -57,7 +57,7 @@ struct blk_keyslot_manager; * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ -#define BLKCG_MAX_POLS 5 +#define BLKCG_MAX_POLS 6 typedef void (rq_end_io_fn)(struct request *, blk_status_t); diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 8b77d08d4b47..6c9b10d82c80 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -201,8 +201,8 @@ static inline void bpf_cgroup_storage_unset(void) { int i; - for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { - if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) + for (i = BPF_CGROUP_STORAGE_NEST_MAX - 1; i >= 0; i--) { + if (likely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) continue; this_cpu_write(bpf_cgroup_storage_info[i].task, NULL); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f309fc1509f2..e8e2b0393ca9 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -780,6 +780,7 @@ struct bpf_jit_poke_descriptor { void *tailcall_target; void *tailcall_bypass; void *bypass_addr; + void *aux; union { struct { struct bpf_map *map; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index a9db1eae6796..ae3ac3a2018c 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -134,4 +134,5 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup) BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter) #ifdef CONFIG_NET BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns) +BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) #endif diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e774ecc1cd1f..828d08afeee0 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -340,8 +340,8 @@ struct bpf_insn_aux_data { }; u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ - int sanitize_stack_off; /* stack slot to be cleared */ u32 seen; /* this insn was processed by the verifier at env->pass_cnt */ + bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */ bool zext_dst; /* this insn zero extends dst reg */ u8 alu_state; /* used in combination with alu_limit */ @@ -414,6 +414,7 @@ struct bpf_verifier_env { u32 used_map_cnt; /* number of used maps */ u32 used_btf_cnt; /* number of used BTF objects */ u32 id_gen; /* used to generate unique reg IDs */ + bool explore_alu_limits; bool allow_ptr_leaks; bool allow_uninit_stack; bool allow_ptr_to_map_access; diff --git a/include/linux/device.h b/include/linux/device.h index 59940f1744c1..65d84b67b024 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -407,6 +407,7 @@ struct dev_links_info { * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pin-control.rst for details. + * @msi_lock: Lock to protect MSI mask cache and mask register * @msi_list: Hosts MSI descriptors * @msi_domain: The generic MSI domain this device is using. * @numa_node: NUMA node this device is close to. @@ -506,6 +507,7 @@ struct device { struct dev_pin_info *pins; #endif #ifdef CONFIG_GENERIC_MSI_IRQ + raw_spinlock_t msi_lock; struct list_head msi_list; #endif #ifdef CONFIG_DMA_OPS diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 29dbb603bc91..232daaec56e4 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -758,6 +758,16 @@ ethtool_params_from_link_mode(struct ethtool_link_ksettings *link_ksettings, enum ethtool_link_mode_bit_indices link_mode); /** + * ethtool_get_phc_vclocks - Derive phc vclocks information, and caller + * is responsible to free memory of vclock_index + * @dev: pointer to net_device structure + * @vclock_index: pointer to pointer of vclock index + * + * Return number of phc vclocks + */ +int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index); + +/** * ethtool_sprintf - Write formatted string to ethtool string data * @data: Pointer to start of string to update * @fmt: Format of string to write diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index a16dbeced152..eec3b7c40811 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -27,6 +27,8 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ #define FANOTIFY_FID_BITS (FAN_REPORT_FID | FAN_REPORT_DFID_NAME) +#define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS | FAN_REPORT_PIDFD) + /* * fanotify_init() flags that require CAP_SYS_ADMIN. * We do not allow unprivileged groups to request permission events. @@ -35,6 +37,7 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ */ #define FANOTIFY_ADMIN_INIT_FLAGS (FANOTIFY_PERM_CLASSES | \ FAN_REPORT_TID | \ + FAN_REPORT_PIDFD | \ FAN_UNLIMITED_QUEUE | \ FAN_UNLIMITED_MARKS) diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h index 4e624c466583..c50882f19235 100644 --- a/include/linux/fiemap.h +++ b/include/linux/fiemap.h @@ -18,8 +18,4 @@ int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo, int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, u64 phys, u64 len, u32 flags); -int generic_block_fiemap(struct inode *inode, - struct fiemap_extent_info *fieinfo, u64 start, u64 len, - get_block_t *get_block); - #endif /* _LINUX_FIEMAP_H 1 */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 472f97074da0..83b896044e79 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -73,6 +73,11 @@ struct ctl_table_header; /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 +/* unused opcode to mark speculation barrier for mitigating + * Speculative Store Bypass + */ +#define BPF_NOSPEC 0xc0 + /* As per nm, we expose JITed images as text (code) section for * kallsyms. That way, tools like perf can find it to match * addresses. @@ -390,6 +395,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) .off = 0, \ .imm = 0 }) +/* Speculation barrier */ + +#define BPF_ST_NOSPEC() \ + ((struct bpf_insn) { \ + .code = BPF_ST | BPF_NOSPEC, \ + .dst_reg = 0, \ + .src_reg = 0, \ + .off = 0, \ + .imm = 0 }) + /* Internal classic blocks for direct assignment */ #define __BPF_STMT(CODE, K) \ diff --git a/include/linux/fs.h b/include/linux/fs.h index 640574294216..719345723911 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -436,6 +436,10 @@ int pagecache_write_end(struct file *, struct address_space *mapping, * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. * @i_pages: Cached pages. + * @invalidate_lock: Guards coherency between page cache contents and + * file offset->disk block mappings in the filesystem during invalidates. + * It is also used to block modification of page cache contents through + * memory mappings. * @gfp_mask: Memory allocation flags to use for allocating pages. * @i_mmap_writable: Number of VM_SHARED mappings. * @nr_thps: Number of THPs in the pagecache (non-shmem only). @@ -453,6 +457,7 @@ int pagecache_write_end(struct file *, struct address_space *mapping, struct address_space { struct inode *host; struct xarray i_pages; + struct rw_semaphore invalidate_lock; gfp_t gfp_mask; atomic_t i_mmap_writable; #ifdef CONFIG_READ_ONLY_THP_FOR_FS @@ -814,9 +819,42 @@ static inline void inode_lock_shared_nested(struct inode *inode, unsigned subcla down_read_nested(&inode->i_rwsem, subclass); } +static inline void filemap_invalidate_lock(struct address_space *mapping) +{ + down_write(&mapping->invalidate_lock); +} + +static inline void filemap_invalidate_unlock(struct address_space *mapping) +{ + up_write(&mapping->invalidate_lock); +} + +static inline void filemap_invalidate_lock_shared(struct address_space *mapping) +{ + down_read(&mapping->invalidate_lock); +} + +static inline int filemap_invalidate_trylock_shared( + struct address_space *mapping) +{ + return down_read_trylock(&mapping->invalidate_lock); +} + +static inline void filemap_invalidate_unlock_shared( + struct address_space *mapping) +{ + up_read(&mapping->invalidate_lock); +} + void lock_two_nondirectories(struct inode *, struct inode*); void unlock_two_nondirectories(struct inode *, struct inode*); +void filemap_invalidate_lock_two(struct address_space *mapping1, + struct address_space *mapping2); +void filemap_invalidate_unlock_two(struct address_space *mapping1, + struct address_space *mapping2); + + /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic @@ -1507,8 +1545,11 @@ struct super_block { /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; - /* Pending fsnotify inode refs */ - atomic_long_t s_fsnotify_inode_refs; + /* + * Number of inode/mount/sb objects that are being watched, note that + * inodes objects are currently double-accounted. + */ + atomic_long_t s_fsnotify_connectors; /* Being remounted read-only */ int s_readonly_remount; @@ -2487,6 +2528,7 @@ struct file_system_type { struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; + struct lock_class_key invalidate_lock_key; struct lock_class_key i_mutex_dir_key; }; @@ -2570,90 +2612,6 @@ extern struct kobject *fs_kobj; #define MAX_RW_COUNT (INT_MAX & PAGE_MASK) -#ifdef CONFIG_MANDATORY_FILE_LOCKING -extern int locks_mandatory_locked(struct file *); -extern int locks_mandatory_area(struct inode *, struct file *, loff_t, loff_t, unsigned char); - -/* - * Candidates for mandatory locking have the setgid bit set - * but no group execute bit - an otherwise meaningless combination. - */ - -static inline int __mandatory_lock(struct inode *ino) -{ - return (ino->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID; -} - -/* - * ... and these candidates should be on SB_MANDLOCK mounted fs, - * otherwise these will be advisory locks - */ - -static inline int mandatory_lock(struct inode *ino) -{ - return IS_MANDLOCK(ino) && __mandatory_lock(ino); -} - -static inline int locks_verify_locked(struct file *file) -{ - if (mandatory_lock(locks_inode(file))) - return locks_mandatory_locked(file); - return 0; -} - -static inline int locks_verify_truncate(struct inode *inode, - struct file *f, - loff_t size) -{ - if (!inode->i_flctx || !mandatory_lock(inode)) - return 0; - - if (size < inode->i_size) { - return locks_mandatory_area(inode, f, size, inode->i_size - 1, - F_WRLCK); - } else { - return locks_mandatory_area(inode, f, inode->i_size, size - 1, - F_WRLCK); - } -} - -#else /* !CONFIG_MANDATORY_FILE_LOCKING */ - -static inline int locks_mandatory_locked(struct file *file) -{ - return 0; -} - -static inline int locks_mandatory_area(struct inode *inode, struct file *filp, - loff_t start, loff_t end, unsigned char type) -{ - return 0; -} - -static inline int __mandatory_lock(struct inode *inode) -{ - return 0; -} - -static inline int mandatory_lock(struct inode *inode) -{ - return 0; -} - -static inline int locks_verify_locked(struct file *file) -{ - return 0; -} - -static inline int locks_verify_truncate(struct inode *inode, struct file *filp, - size_t size) -{ - return 0; -} - -#endif /* CONFIG_MANDATORY_FILE_LOCKING */ - - #ifdef CONFIG_FILE_LOCKING static inline int break_lease(struct inode *inode, unsigned int mode) { diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 37e1e8f7f08d..6b54982fc5f3 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -139,6 +139,9 @@ extern int vfs_parse_fs_string(struct fs_context *fc, const char *key, extern int generic_parse_monolithic(struct fs_context *fc, void *data); extern int vfs_get_tree(struct fs_context *fc); extern void put_fs_context(struct fs_context *fc); +extern int vfs_parse_fs_param_source(struct fs_context *fc, + struct fs_parameter *param); +extern void fc_drop_locked(struct fs_context *fc); /* * sget() wrappers to be called from the ->get_tree() op. diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index f8acddcf54fb..12d3a7d308ab 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -30,6 +30,9 @@ static inline void fsnotify_name(struct inode *dir, __u32 mask, struct inode *child, const struct qstr *name, u32 cookie) { + if (atomic_long_read(&dir->i_sb->s_fsnotify_connectors) == 0) + return; + fsnotify(mask, child, FSNOTIFY_EVENT_INODE, dir, name, NULL, cookie); } @@ -41,6 +44,9 @@ static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, static inline void fsnotify_inode(struct inode *inode, __u32 mask) { + if (atomic_long_read(&inode->i_sb->s_fsnotify_connectors) == 0) + return; + if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; @@ -53,6 +59,9 @@ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, { struct inode *inode = d_inode(dentry); + if (atomic_long_read(&inode->i_sb->s_fsnotify_connectors) == 0) + return 0; + if (S_ISDIR(inode->i_mode)) { mask |= FS_ISDIR; diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 8c6e8e996c87..d9a606a9fc64 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -318,14 +318,16 @@ static inline void memcpy_to_page(struct page *page, size_t offset, VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to + offset, from, len); + flush_dcache_page(page); kunmap_local(to); } static inline void memzero_page(struct page *page, size_t offset, size_t len) { - char *addr = kmap_atomic(page); + char *addr = kmap_local_page(page); memset(addr + offset, 0, len); - kunmap_atomic(addr); + flush_dcache_page(page); + kunmap_local(addr); } #endif /* _LINUX_HIGHMEM_H */ diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 53aa0343bf69..aaf4f1b4c277 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -41,7 +41,7 @@ struct in_device { unsigned long mr_qri; /* Query Response Interval */ unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; - unsigned char mr_ifc_count; + u32 mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ struct timer_list mr_ifc_timer; /* interface change timer */ diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index 25e2b4e80502..aee8ff4739b1 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -81,6 +81,8 @@ int ishtp_register_event_cb(struct ishtp_cl_device *device, /* Get the device * from ishtp device instance */ struct device *ishtp_device(struct ishtp_cl_device *cl_device); +/* wait for IPC resume */ +bool ishtp_wait_resume(struct ishtp_device *dev); /* Trace interface for clients */ ishtp_print_log ishtp_trace_callback(struct ishtp_cl_device *cl_device); /* Get device pointer of PCI device for DMA acces */ diff --git a/include/linux/irq.h b/include/linux/irq.h index 8e9a9ae471a6..c8293c817646 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -569,6 +569,7 @@ struct irq_chip { * IRQCHIP_SUPPORTS_NMI: Chip can deliver NMIs, only for root irqchips * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND: Invokes __enable_irq()/__disable_irq() for wake irqs * in the suspend path if they are in disabled state + * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), @@ -581,6 +582,7 @@ enum { IRQCHIP_SUPPORTS_LEVEL_MSI = (1 << 7), IRQCHIP_SUPPORTS_NMI = (1 << 8), IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9), + IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10), }; #include <linux/irqdesc.h> diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 5310e217bd74..dd874a1ee862 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -3,6 +3,7 @@ #define _LINUX_KASAN_H #include <linux/bug.h> +#include <linux/kernel.h> #include <linux/static_key.h> #include <linux/types.h> diff --git a/include/linux/kfence.h b/include/linux/kfence.h index a70d1ea03532..3fe6dd8a18c1 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -51,10 +51,11 @@ extern atomic_t kfence_allocation_gate; static __always_inline bool is_kfence_address(const void *addr) { /* - * The non-NULL check is required in case the __kfence_pool pointer was - * never initialized; keep it in the slow-path after the range-check. + * The __kfence_pool != NULL check is required to deal with |