diff options
Diffstat (limited to 'include/linux')
30 files changed, 283 insertions, 1799 deletions
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index c6fab004104a..5b2f8147d1ae 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -218,7 +218,6 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CQM_ONLINE, CPUHP_AP_PERF_X86_CSTATE_ONLINE, CPUHP_AP_PERF_X86_IDXD_ONLINE, - CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 366c730beaa3..402fc061de75 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -980,7 +980,7 @@ static inline void __ftrace_enabled_restore(int enabled) #define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5)) #define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6)) -static inline unsigned long get_lock_parent_ip(void) +static __always_inline unsigned long get_lock_parent_ip(void) { unsigned long addr = CALLER_ADDR0; diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h index 501fa8486749..1b608e00290a 100644 --- a/include/linux/instrumented.h +++ b/include/linux/instrumented.h @@ -15,12 +15,11 @@ /** * instrument_read - instrument regular read access + * @v: address of access + * @size: size of access * * Instrument a regular read access. The instrumentation should be inserted * before the actual read happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_read(const volatile void *v, size_t size) { @@ -30,12 +29,11 @@ static __always_inline void instrument_read(const volatile void *v, size_t size) /** * instrument_write - instrument regular write access + * @v: address of access + * @size: size of access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_write(const volatile void *v, size_t size) { @@ -45,12 +43,11 @@ static __always_inline void instrument_write(const volatile void *v, size_t size /** * instrument_read_write - instrument regular read-write access + * @v: address of access + * @size: size of access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_read_write(const volatile void *v, size_t size) { @@ -60,12 +57,11 @@ static __always_inline void instrument_read_write(const volatile void *v, size_t /** * instrument_atomic_read - instrument atomic read access + * @v: address of access + * @size: size of access * * Instrument an atomic read access. The instrumentation should be inserted * before the actual read happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_atomic_read(const volatile void *v, size_t size) { @@ -75,12 +71,11 @@ static __always_inline void instrument_atomic_read(const volatile void *v, size_ /** * instrument_atomic_write - instrument atomic write access + * @v: address of access + * @size: size of access * * Instrument an atomic write access. The instrumentation should be inserted * before the actual write happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_atomic_write(const volatile void *v, size_t size) { @@ -90,12 +85,11 @@ static __always_inline void instrument_atomic_write(const volatile void *v, size /** * instrument_atomic_read_write - instrument atomic read-write access + * @v: address of access + * @size: size of access * * Instrument an atomic read-write access. The instrumentation should be * inserted before the actual write happens. - * - * @ptr address of access - * @size size of access */ static __always_inline void instrument_atomic_read_write(const volatile void *v, size_t size) { @@ -105,13 +99,12 @@ static __always_inline void instrument_atomic_read_write(const volatile void *v, /** * instrument_copy_to_user - instrument reads of copy_to_user + * @to: destination address + * @from: source address + * @n: number of bytes to copy * * Instrument reads from kernel memory, that are due to copy_to_user (and * variants). The instrumentation must be inserted before the accesses. - * - * @to destination address - * @from source address - * @n number of bytes to copy */ static __always_inline void instrument_copy_to_user(void __user *to, const void *from, unsigned long n) @@ -123,13 +116,12 @@ instrument_copy_to_user(void __user *to, const void *from, unsigned long n) /** * instrument_copy_from_user_before - add instrumentation before copy_from_user + * @to: destination address + * @from: source address + * @n: number of bytes to copy * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted before the accesses. - * - * @to destination address - * @from source address - * @n number of bytes to copy */ static __always_inline void instrument_copy_from_user_before(const void *to, const void __user *from, unsigned long n) @@ -140,14 +132,13 @@ instrument_copy_from_user_before(const void *to, const void __user *from, unsign /** * instrument_copy_from_user_after - add instrumentation after copy_from_user + * @to: destination address + * @from: source address + * @n: number of bytes to copy + * @left: number of bytes not copied (as returned by copy_from_user) * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted after the accesses. - * - * @to destination address - * @from source address - * @n number of bytes to copy - * @left number of bytes not copied (as returned by copy_from_user) */ static __always_inline void instrument_copy_from_user_after(const void *to, const void __user *from, @@ -158,12 +149,11 @@ instrument_copy_from_user_after(const void *to, const void __user *from, /** * instrument_get_user() - add instrumentation to get_user()-like macros + * @to: destination variable, may not be address-taken * * get_user() and friends are fragile, so it may depend on the implementation * whether the instrumentation happens before or after the data is copied from * the userspace. - * - * @to destination variable, may not be address-taken */ #define instrument_get_user(to) \ ({ \ @@ -175,14 +165,13 @@ instrument_copy_from_user_after(const void *to, const void __user *from, /** * instrument_put_user() - add instrumentation to put_user()-like macros + * @from: source address + * @ptr: userspace pointer to copy to + * @size: number of bytes to copy * * put_user() and friends are fragile, so it may depend on the implementation * whether the instrumentation happens before or after the data is copied from * the userspace. - * - * @from source address - * @ptr userspace pointer to copy to - * @size number of bytes to copy */ #define instrument_put_user(from, ptr, size) \ ({ \ diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index e38ae3c34618..30b17647ce3c 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -134,11 +134,12 @@ void kmsan_kfree_large(const void *ptr); * @page_shift: page_shift passed to vmap_range_noflush(). * * KMSAN maps shadow and origin pages of @pages into contiguous ranges in - * vmalloc metadata address range. + * vmalloc metadata address range. Returns 0 on success, callers must check + * for non-zero return value. */ -void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, - pgprot_t prot, struct page **pages, - unsigned int page_shift); +int kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, + pgprot_t prot, struct page **pages, + unsigned int page_shift); /** * kmsan_vunmap_kernel_range_noflush() - Notify KMSAN about a vunmap. @@ -159,11 +160,12 @@ void kmsan_vunmap_range_noflush(unsigned long start, unsigned long end); * @page_shift: page_shift argument passed to vmap_range_noflush(). * * KMSAN creates new metadata pages for the physical pages mapped into the - * virtual memory. + * virtual memory. Returns 0 on success, callers must check for non-zero return + * value. */ -void kmsan_ioremap_page_range(unsigned long addr, unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int page_shift); +int kmsan_ioremap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift); /** * kmsan_iounmap_page_range() - Notify KMSAN about a iounmap_page_range() call. @@ -281,12 +283,13 @@ static inline void kmsan_kfree_large(const void *ptr) { } -static inline void kmsan_vmap_pages_range_noflush(unsigned long start, - unsigned long end, - pgprot_t prot, - struct page **pages, - unsigned int page_shift) +static inline int kmsan_vmap_pages_range_noflush(unsigned long start, + unsigned long end, + pgprot_t prot, + struct page **pages, + unsigned int page_shift) { + return 0; } static inline void kmsan_vunmap_range_noflush(unsigned long start, @@ -294,12 +297,12 @@ static inline void kmsan_vunmap_range_noflush(unsigned long start, { } -static inline void kmsan_ioremap_page_range(unsigned long start, - unsigned long end, - phys_addr_t phys_addr, - pgprot_t prot, - unsigned int page_shift) +static inline int kmsan_ioremap_page_range(unsigned long start, + unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift) { + return 0; } static inline void kmsan_iounmap_page_range(unsigned long start, diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8ada23756b0e..a9adf75344be 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -755,6 +755,7 @@ struct kvm { struct { spinlock_t lock; struct list_head items; + /* resampler_list update side is protected by resampler_lock. */ struct list_head resampler_list; struct mutex resampler_lock; } irqfds; @@ -1986,6 +1987,9 @@ int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args); #ifdef CONFIG_HAVE_KVM_IRQFD int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args); void kvm_irqfd_release(struct kvm *kvm); +bool kvm_notify_irqfd_resampler(struct kvm *kvm, + unsigned int irqchip, + unsigned int pin); void kvm_irq_routing_update(struct kvm *); #else static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) @@ -1994,6 +1998,13 @@ static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args) } static inline void kvm_irqfd_release(struct kvm *kvm) {} + +static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm, + unsigned int irqchip, + unsigned int pin) +{ + return false; +} #endif #else diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h index dac047abdba7..8ad43692e3bb 100644 --- a/include/linux/kvm_irqfd.h +++ b/include/linux/kvm_irqfd.h @@ -31,7 +31,7 @@ struct kvm_kernel_irqfd_resampler { /* * Entry in list of kvm->irqfd.resampler_list. Use for sharing * resamplers among irqfds on the same gsi. - * Accessed and modified under kvm->irqfds.resampler_lock + * RCU list modified under kvm->irqfds.resampler_lock */ struct list_head link; }; diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 1023f349af71..b32256e9e944 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -134,7 +134,8 @@ struct held_lock { unsigned int read:2; /* see lock_acquire() comment */ unsigned int check:1; /* see lock_acquire() comment */ unsigned int hardirqs_off:1; - unsigned int references:12; /* 32 bits */ + unsigned int sync:1; + unsigned int references:11; /* 32 bits */ unsigned int pin_count; }; @@ -268,6 +269,10 @@ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass, extern void lock_release(struct lockdep_map *lock, unsigned long ip); +extern void lock_sync(struct lockdep_map *lock, unsigned int subclass, + int read, int check, struct lockdep_map *nest_lock, + unsigned long ip); + /* lock_is_held_type() returns */ #define LOCK_STATE_UNKNOWN -1 #define LOCK_STATE_NOT_HELD 0 @@ -554,6 +559,7 @@ do { \ #define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_tryread(l) lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_release(l) lock_release(l, _THIS_IP_) +#define lock_map_sync(l) lock_sync(l, 0, 0, 1, NULL, _THIS_IP_) #ifdef CONFIG_PROVE_LOCKING # define might_lock(lock) \ diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 094b76dc7164..6bb55e61e8e8 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -381,7 +381,7 @@ LSM_HOOK(int, 0, key_alloc, struct key *key, const struct cred *cred, LSM_HOOK(void, LSM_RET_VOID, key_free, struct key *key) LSM_HOOK(int, 0, key_permission, key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) -LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **_buffer) +LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **buffer) #endif /* CONFIG_KEYS */ #ifdef CONFIG_AUDIT diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 6e156d2acffc..ab2b2fafa4a4 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -29,1630 +29,6 @@ #include <linux/init.h> #include <linux/rculist.h> -/** - * union security_list_options - Linux Security Module hook function list - * - * Security hooks for program execution operations. - * - * @bprm_creds_for_exec: - * If the setup in prepare_exec_creds did not setup @bprm->cred->security - * properly for executing @bprm->file, update the LSM's portion of - * @bprm->cred->security to be what commit_creds needs to install for the - * new program. This hook may also optionally check permissions - * (e.g. for transitions between security domains). - * The hook must set @bprm->secureexec to 1 if AT_SECURE should be set to - * request libc enable secure mode. - * @bprm contains the linux_binprm structure. - * Return 0 if the hook is successful and permission is granted. - * @bprm_creds_from_file: - * If @file is setpcap, suid, sgid or otherwise marked to change - * privilege upon exec, update @bprm->cred to reflect that change. - * This is called after finding the binary that will be executed. - * without an interpreter. This ensures that the credentials will not - * be derived from a script that the binary will need to reopen, which - * when reopend may end up being a completely different file. This - * hook may also optionally check permissions (e.g. for transitions - * between security domains). - * The hook must set @bprm->secureexec to 1 if AT_SECURE should be set to - * request libc enable secure mode. - * The hook must add to @bprm->per_clear any personality flags that - * should be cleared from current->personality. - * @bprm contains the linux_binprm structure. - * Return 0 if the hook is successful and permission is granted. - * @bprm_check_security: - * This hook mediates the point when a search for a binary handler will - * begin. It allows a check against the @bprm->cred->security value - * which was set in the preceding creds_for_exec call. The argv list and - * envp list are reliably available in @bprm. This hook may be called - * multiple times during a single execve. - * @bprm contains the linux_binprm structure. - * Return 0 if the hook is successful and permission is granted. - * @bprm_committing_creds: - * Prepare to install the new security attributes of a process being - * transformed by an execve operation, based on the old credentials - * pointed to by @current->cred and the information set in @bprm->cred by - * the bprm_creds_for_exec hook. @bprm points to the linux_binprm - * structure. This hook is a good place to perform state changes on the - * process such as closing open file descriptors to which access will no - * longer be granted when the attributes are changed. This is called - * immediately before commit_creds(). - * @bprm_committed_creds: - * Tidy up after the installation of the new security attributes of a - * process being transformed by an execve operation. The new credentials - * have, by this point, been set to @current->cred. @bprm points to the - * linux_binprm structure. This hook is a good place to perform state - * changes on the process such as clearing out non-inheritable signal - * state. This is called immediately after commit_creds(). - * - * Security hooks for mount using fs_context. - * [See also Documentation/filesystems/mount_api.rst] - * - * @fs_context_dup: - * Allocate and attach a security structure to sc->security. This pointer - * is initialised to NULL by the caller. - * @fc indicates the new filesystem context. - * @src_fc indicates the original filesystem context. - * Return 0 on success or a negative error code on failure. - * @fs_context_parse_param: - * Userspace provided a parameter to configure a superblock. The LSM may - * reject it with an error and may use it for itself, in which case it - * should return 0; otherwise it should return -ENOPARAM to pass it on to - * the filesystem. - * @fc indicates the filesystem context. - * @param The parameter. - * - * Security hooks for filesystem operations. - * - * @sb_alloc_security: - * Allocate and attach a security structure to the sb->s_security field. - * The s_security field is initialized to NULL when the structure is - * allocated. - * @sb contains the super_block structure to be modified. - * Return 0 if operation was successful. - * @sb_delete: - * Release objects tied to a superblock (e.g. inodes). - * @sb contains the super_block structure being released. - * @sb_free_security: - * Deallocate and clear the sb->s_security field. - * @sb contains the super_block structure to be modified. - * @sb_free_mnt_opts: - * Free memory associated with @mnt_ops. - * @sb_eat_lsm_opts: - * Eat (scan @orig options) and save them in @mnt_opts. - * Return 0 on success, negative values on failure. - * @sb_statfs: - * Check permission before obtaining filesystem statistics for the @mnt - * mountpoint. - * @dentry is a handle on the superblock for the filesystem. - * Return 0 if permission is granted. - * @sb_mount: - * Check permission before an object specified by @dev_name is mounted on - * the mount point named by @nd. For an ordinary mount, @dev_name - * identifies a device if the file system type requires a device. For a - * remount (@flags & MS_REMOUNT), @dev_name is irrelevant. For a - * loopback/bind mount (@flags & MS_BIND), @dev_name identifies the - * pathname of the object being mounted. - * @dev_name contains the name for object being mounted. - * @path contains the path for mount point object. - * @type contains the filesystem type. - * @flags contains the mount flags. - * @data contains the filesystem-specific data. - * Return 0 if permission is granted. - * @sb_mnt_opts_compat: - * Determine if the new mount options in @mnt_opts are allowed given - * the existing mounted filesystem at @sb. - * @sb superblock being compared. - * @mnt_opts new mount options. - * Return 0 if options are compatible. - * @sb_remount: - * Extracts security system specific mount options and verifies no changes - * are being made to those options. - * @sb superblock being remounted. - * @data contains the filesystem-specific data. - * Return 0 if permission is granted. - * @sb_kern_mount: - * Mount this @sb if allowed by permissions. - * Return 0 if permission is granted. - * @sb_show_options: - * Show (print on @m) mount options for this @sb. - * Return 0 on success, negative values on failure. - * @sb_umount: - * Check permission before the @mnt file system is unmounted. - * @mnt contains the mounted file system. - * @flags contains the unmount flags, e.g. MNT_FORCE. - * Return 0 if permission is granted. - * @sb_pivotroot: - * Check permission before pivoting the root filesystem. - * @old_path contains the path for the new location of the - * current root (put_old). - * @new_path contains the path for the new root (new_root). - * Return 0 if permission is granted. - * @sb_set_mnt_opts: - * Set the security relevant mount options used for a superblock - * @sb the superblock to set security mount options for. - * @opts binary data structure containing all lsm mount data. - * Return 0 on success, error on failure. - * @sb_clone_mnt_opts: - * Copy all security options from a given superblock to another - * @oldsb old superblock which contain information to clone. - * @newsb new superblock which needs filled in. - * Return 0 on success, error on failure. - * @move_mount: - * Check permission before a mount is moved. - * @from_path indicates the mount that is going to be moved. - * @to_path indicates the mountpoint that will be mounted upon. - * Return 0 if permission is granted. - * @dentry_init_security: - * Compute a context for a dentry as the inode is not yet available - * since NFSv4 has no label backed by an EA anyway. - * @dentry dentry to use in calculating the context. - * @mode mode used to determine resource type. - * @name name of the last path component used to create file. - * @xattr_name pointer to place the pointer to security xattr name. - * Caller does not have to free the resulting pointer. Its - * a pointer to static string. - * @ctx pointer to place the pointer to the resulting context in. - * @ctxlen point to place the length of the resulting context. - * Return 0 on success, negative values on failure. - * @dentry_create_files_as: - * Compute a context for a dentry as the inode is not yet available - * and set that context in passed in creds so that new files are - * created using that context. Context is calculated using the - * passed in creds and not the creds of the caller. - * @dentry dentry to use in calculating the context. - * @mode mode used to determine resource type. - * @name name of the last path component used to create file. - * @old creds which should be used for context calculation. - * @new creds to modify. - * Return 0 on success, error on failure. - * - * - * Security hooks for inode operations. - * - * @inode_alloc_security: - * Allocate and attach a security structure to @inode->i_security. The - * i_security field is initialized to NULL when the inode structure is - * allocated. - * @inode contains the inode structure. - * Return 0 if operation was successful. - * @inode_free_security: - * @inode contains the inode structure. - * Deallocate the inode security structure and set @inode->i_security to - * NULL. - * @inode_init_security: - * Obtain the security attribute name suffix and value to set on a newly - * created inode and set up the incore security field for the new inode. - * This hook is called by the fs code as part of the inode creation - * transaction and provides for atomic labeling of the inode, unlike - * the post_create/mkdir/... hooks called by the VFS. The hook function - * is expected to allocate the name and value via kmalloc, with the caller - * being responsible for calling kfree after using them. - * If the security module does not use security attributes or does - * not wish to put a security attribute on this particular inode, - * then it should return -EOPNOTSUPP to skip this processing. - * @inode contains the inode structure of the newly created inode. - * @dir contains the inode structure of the parent directory. - * @qstr contains the last path component of the new object. - * @name will be set to the allocated name suffix (e.g. selinux). - * @value will be set to the allocated attribute value. - * @len will be set to the length of the value. - * Returns 0 if @name and @value have been successfully set, - * -EOPNOTSUPP if no security attribute is needed, or - * -ENOMEM on memory allocation failure. - * @inode_init_security_anon: - * Set up the incore security field for the new anonymous inode - * and return whether the inode creation is permitted by the security - * module or not. - * @inode contains the inode structure. - * @name name of the anonymous inode class. - * @context_inode optional related inode. - * Returns 0 on success, -EACCES if the security module denies the - * creation of this inode, or another -errno upon other errors. - * @inode_create: - * Check permission to create a regular file. - * @dir contains inode structure of the parent of the new file. - * @dentry contains the dentry structure for the file to be created. - * @mode contains the file mode of the file to be created. - * Return 0 if permission is granted. - * @inode_link: - * Check permission before creating a new hard link to a file. - * @old_dentry contains the dentry structure for an existing - * link to the file. - * @dir contains the inode structure of the parent directory - * of the new link. - * @new_dentry contains the dentry structure for the new link. - * Return 0 if permission is granted. - * @path_link: - * Check permission before creating a new hard link to a file. - * @old_dentry contains the dentry structure for an existing link - * to the file. - * @new_dir contains the path structure of the parent directory of - * the new link. - * @new_dentry contains the dentry structure for the new link. - * Return 0 if permission is granted. - * @inode_unlink: - * Check the permission to remove a hard link to a file. - * @dir contains the inode structure of parent directory of the file. - * @dentry contains the dentry structure for file to be unlinked. - * Return 0 if permission is granted. - * @path_unlink: - * Check the permission to remove a hard link to a file. - * @dir contains the path structure of parent directory of the file. - * @dentry contains the dentry structure for file to be unlinked. - * Return 0 if permission is granted. - * @inode_symlink: - * Check the permission to create a symbolic link to a file. - * @dir contains the inode structure of parent directory of - * the symbolic link. - * @dentry contains the dentry structure of the symbolic link. - * @old_name contains the pathname of file. - * Return 0 if permission is granted. - * @path_symlink: - * Check the permission to create a symbolic link to a file. - * @dir contains the path structure of parent directory of - * the symbolic link. - * @dentry contains the dentry structure of the symbolic link. - * @old_name contains the pathname of file. - * Return 0 if permission is granted. - * @inode_mkdir: - * Check permissions to create a new directory in the existing directory - * associated with inode structure @dir. - * @dir contains the inode structure of parent of the directory - * to be created. - * @dentry contains the dentry structure of new directory. - * @mode contains the mode of new directory. - * Return 0 if permission is granted. - * @path_mkdir: - * Check permissions to create a new directory in the existing directory - * associated with path structure @path. - * @dir contains the path structure of parent of the directory - * to be created. - * @dentry contains the dentry structure of new directory. - * @mode contains the mode of new directory. - * Return 0 if permission is granted. - * @inode_rmdir: - * Check the permission to remove a directory. - * @dir contains the inode structure of parent of the directory - * to be removed. - * @dentry contains the dentry structure of directory to be removed. - * Return 0 if permission is granted. - * @path_rmdir: - * Check the permission to remove a directory. - * @dir contains the path structure of parent of the directory to be - * removed. - * @dentry contains the dentry structure of directory to be removed. - * Return 0 if permission is granted. - * @inode_mknod: - * Check permissions when creating a special file (or a socket or a fifo - * file created via the mknod system call). Note that if mknod operation - * is being done for a regular file, then the create hook will be called - * and not this hook. - * @dir contains the inode structure of parent of the new file. - * @dentry contains the dentry structure of the new file. - * @mode contains the mode of the new file. - * @dev contains the device number. - * Return 0 if permission is granted. - * @path_mknod: - * Check permissions when creating a file. Note that this hook is called - * even if mknod operation is being done for a regular file. - * @dir contains the path structure of parent of the new file. - * @dentry contains the dentry structure of the new file. - * @mode contains the mode of the new file. - * @dev contains the undecoded device number. Use new_decode_dev() to get - * the decoded device number. - * Return 0 if permission is granted. - * @inode_rename: - * Check for permission to rename a file or directory. - * @old_dir contains the inode structure for parent of the old link. - * @old_dentry contains the dentry structure of the old link. - * @new_dir contains the inode structure for parent of the new link. - * @new_dentry contains the dentry structure of the new link. - * Return 0 if permission is granted. - * @path_rename: - * Check for permission to rename a file or directory. - * @old_dir contains the path structure for parent of the old link. - * @old_dentry contains the dentry structure of the old link. - * @new_dir contains the path structure for parent of the new link. - * @new_dentry contains the dentry structure of the new link. - * @flags may contain rename options such as RENAME_EXCHANGE. - * Return 0 if permission is granted. - * @path_chmod: - * Check for permission to change a mode of the file @path. The new - * mode is specified in @mode. - * @path contains the path structure of the file to change the mode. - * @mode contains the new DAC's permission, which is a bitmask of - * constants from <include/uapi/linux/stat.h>. - * Return 0 if permission is granted. - * @path_chown: - * Check for permission to change owner/group of a file or directory. - * @path contains the path structure. - * @uid contains new owner's ID. - * @gid contains new group's ID. - * Return 0 if permission is granted. - * @path_chroot: - * Check for permission to change root directory. - * @path contains the path structure. - * Return 0 if permission is granted. - * @path_notify: - * Check permissions before setting a watch on events as defined by @mask, - * on an object at @path, whose type is defined by @obj_type. - * Return 0 if permission is granted. - * @inode_readlink: - * Check the permission to read the symbolic link. - * @dentry contains the dentry structure for the file link. - * Return 0 if permission is granted. - * @inode_follow_link: - * Check permission to follow a symbolic link when looking up a pathname. - * @dentry contains the dentry structure for the link. - * @inode contains the inode, which itself is not stable in RCU-walk. - * @rcu indicates whether we are in RCU-walk mode. - * Return 0 if permission is granted. - * @inode_permission: - * Check permission before accessing an inode. This hook is called by the - * existing Linux permission function, so a security module can use it to - * provide additional checking for existing Linux permission checks. - * Notice that this hook is called when a file is opened (as well as many - * other operations), whereas the file_security_ops permission hook is - * called when the actual read/write operations are performed. - * @inode contains the inode structure to check. - * @mask contains the permission mask. - * Return 0 if permission is granted. - * @inode_setattr: - * Check permission before setting file attributes. Note that the kernel - * call to notify_change is performed from several locations, whenever - * file attributes change (such as when a file is truncated, chown/chmod - * operations, transferring disk quotas, etc). - * @dentry contains the dentry structure for the file. - * @attr is the iattr structure containing the new file attributes. - * Return 0 if permission is granted. - * @path_truncate: - * Check permission before truncating the file indicated by path. - * Note that truncation permissions may also be checked based on - * already opened files, using the @file_truncate hook. - * @path contains the path structure for the file. - * Return 0 if permission is granted. - * @inode_getattr: - * Check permission before obtaining file attributes. - * @path contains the path structure for the file. - * Return 0 if permission is granted. - * @inode_setxattr: - * Check permission before setting the extended attributes - * @value identified by @name for @dentry. - * Return 0 if permission is granted. - * @inode_post_setxattr: - * Update inode security field after successful setxattr operation. - * @value identified by @name for @dentry. - * @inode_getxattr: - * Check permission before obtaining the extended attributes - * identified by @name for @dentry. - * Return 0 if permission is granted. - * @inode_listxattr: - * Check permission before obtaining the list of extended attribute - * names for @dentry. - * Return 0 if permission is granted. - * @inode_removexattr: - * Check permission before removing the extended attribute - * identified by @name for @dentry. - * Return 0 if permission is granted. - * @inode_set_acl: - * Check permission before setting posix acls - * The posix acls in @kacl are identified by @acl_name. - * Return 0 if permission is granted. - * @inode_get_acl: - * Check permission before getting osix acls - * The posix acls are identified by @acl_name. - * Return 0 if permission is granted. - * @inode_remove_acl: - * Check permission before removing posix acls - * The posix acls are identified by @acl_name. - * Return 0 if permission is granted. - * @inode_getsecurity: - * Retrieve a copy of the extended attribute representation of the - * security label associated with @name for @inode via @buffer. Note that - * @name is the remainder of the attribute name after the security prefix - * has been removed. @alloc is used to specify if the call should return a - * value via the buffer or just the value length. - * Return size of buffer on success. - * @inode_setsecurity: - * Set the security label associated with @name for @inode from the - * extended attribute value @value. @size indicates the size of the - * @value in bytes. @flags may be XATTR_CREATE, XATTR_REPLACE, or 0. - * Note that @name is the remainder of the attribute name after the - * security. prefix has been removed. - * Return 0 on success. - * @inode_listsecurity: - * Copy the extended attribute names for the security labels - * associated with @inode into @buffer. The maximum size of @buffer - * is specified by @buffer_size. @buffer may be NULL to request - * the size of the buffer required. - * Returns number of bytes used/required on success. - * @inode_need_killpriv: - * Called when an inode has been changed. - * @dentry is the dentry being changed. - * Return <0 on error to abort the inode change operation. - * Return 0 if inode_killpriv does not need to be called. - * Return >0 if inode_killpriv does need to be called. - * @inode_killpriv: - * The setuid bit is being removed. Remove similar security labels. - * Called with the dentry->d_inode->i_mutex held. - * @idmap: idmap of the mount. - * @dentry is the dentry being changed. - * Return 0 on success. If error is returned, then the operation - * causing setuid bit removal is failed. - * @inode_getsecid: - * Get the secid associated with the node. - * @inode contains a pointer to the inode. - * @secid contains a pointer to the location where result will be saved. - * In case of failure, @secid will be set to zero. - * @inode_copy_up: - * A file is about to be copied up from lower layer to upper layer of - * overlay filesystem. Security module can prepare a set of new creds - * and modify as need be and return new creds. Caller will switch to - * new creds temporarily to create new file and release newly allocated - * creds. - * @src indicates the union dentry of file that is being copied up. - * @new pointer to pointer to return newly allocated creds. - * Returns 0 on success or a negative error code on error. - * @inode_copy_up_xattr: - * Filter the xattrs being copied up when a unioned file is copied - * up from a lower layer to the union/overlay layer. - * @name indicates the name of the xattr. - * Returns 0 to accept the xattr, 1 to discard the xattr, -EOPNOTSUPP if - * security module does not know about attribute or a negative error code - * to abort the copy up. Note that the caller is responsible for reading - * and writing the xattrs as this hook is merely a filter. - * @d_instantiate: - * Fill in @inode security information for a @dentry if allowed. - * @getprocattr: - * Read attribute @name for process @p and store it into @value if allowed. - * Return the length of @value on success, a negative value otherwise. - * @setprocattr: - * Write (set) attribute @name to @value, size @size if allowed. - * Return written bytes on success, a negative value otherwise. - * - * Security hooks for kernfs node operations - * - * @kernfs_init_security: - * Initialize the security context of a newly created kernfs node based - * on its own and its parent's attributes. - * @kn_dir the parent kernfs node. - * @kn the new child kernfs node. - * Return 0 if permission is granted. - * - * Security hooks for file operations - * - * @file_permission: - * Check file permissions before accessing an open file. This hook is - * called by various operations that read or write files. A security - * module can use this hook to perform additional checking on these - * operations, e.g. to revalidate permissions on use to support privilege - * bracketing or policy changes. Notice that this hook is used when the - * actual read/write operations are performed, whereas the - * inode_security_ops hook is called when a file is opened (as well as - * many other operations). - * Caveat: Although this hook can be used to revalidate permissions for - * various system call operations that read or write files, it does not - * address the revalidation of permissions for memory-mapped files. - * Security modules must handle this separately if they need such - * revalidation. - * @file contains the file structure being accessed. - * @mask contains the requested permissions. - * Return 0 if permission is granted. - * @file_alloc_security: - * Allocate and attach a security structure to the file->f_security field. - * The security field is initialized to NULL when the structure is first - * created. - * @file contains the file structure to secure. - * Return 0 if the hook is successful and permission is granted. - * @file_free_security: - * Deallocate and free any security structures stored in file->f_security. - * @file contains the file structure being modified. - * @file_ioctl: - * @file contains the file structure. - * @cmd contains the operation to perform. - * @arg contains the operational arguments. - * Check permission for an ioctl operation on @file. Note that @arg - * sometimes represents a user space pointer; in other cases, it may be a - * simple integer value. When @arg represents a user space pointer, it - * should never be used by the security module. - * Return 0 if permission is granted. - * @mmap_addr: - * Check permissions for a mmap operation at @addr. - * @addr contains virtual address that will be used for the operation. - * Return 0 if permission is granted. - * @mmap_file: - * Check permissions for a mmap operation. The @file may be NULL, e.g. - * if mapping anonymous memory. - * @file contains the file structure for file to map (may be NULL). - * @reqprot contains the protection requested by the application. - * @prot contains the protection that will be applied by the kernel. - * @flags contains the operational flags. - * Return 0 if permission is granted. - * @file_mprotect: - * Check permissions before changing memory access permissions. - * @vma contains the memory region to modify. - * @reqprot contains the protection requested by the application. - * @prot contains the protection that will be applied by the kernel. - * Return 0 if permission is granted. - * @file_lock: - * Check permission before performing file locking operations. - * Note the hook mediates both flock and fcntl style locks. - * @file contains the file structure. - * @cmd contains the posix-translated lock operation to perform - * (e.g. F_RDLCK, F_WRLCK). - * Return 0 if permission is granted. - * @file_fcntl: - * Check permission before allowing the file operation specified by @cmd - * from being performed on the file @file. Note that @arg sometimes - * represents a user space pointer; in other cases, it may be a simple - * integer value. When @arg represents a user space pointer, it should - * never be used by the security module. - * @file contains the file structure. - * @cmd contains the operation to be performed. - * @arg contains the operational arguments. - * Return 0 if permission is granted. - * @file_set_fowner: - * Save owner security information (typically from current->security) in - * file->f_security for later use by the send_sigiotask hook. - * @file contains the file structure to update. - * Return 0 on success. - * @file_send_sigiotask: - * Check permission for the file owner @fown to send SIGIO or SIGURG to the - * process @tsk. Note that this hook is sometimes called from interrupt. - * Note that the fown_struct, @fown, is never outside the context of a - * struct file, so the file structure (and associated security information) - * can always be obtained: container_of(fown, struct file, f_owner) - * @tsk contains the structure of task receiving signal. - * @fown contains the file owner information. - * @sig is the signal that will be sent. When 0, kernel sends SIGIO. - * Return 0 if permission is granted. - * @file_receive: - * This hook allows security modules to control the ability of a process - * to receive an open file descriptor via socket IPC. - * @file contains the file structure being received. - * Return 0 if permission is granted. - * @file_truncate: - * Check permission before truncating a file, i.e. using ftruncate. - * Note that truncation permission may also be checked based on the path, - * using the @path_truncate hook. - * @file contains the file structure for the file. - * Return 0 if permission is granted. - * @file_open: - * Save open-time permission checking state for later use upon - * file_permission, and recheck access if anything has changed - * since inode_permission. - * Return 0 if permission is granted. - * - * Security hooks for task operations. - * - * @task_alloc: - * @task task being allocated. - * @clone_flags contains the flags indicating what should be shared. - * Handle allocation of task-related resources. - * Returns a zero on success, negative values on failure. - * @task_free: - * @task task about to be freed. - * Handle release of task-related resources. (Note that this can be called - * from interrupt context.) - * @cred_alloc_blank: - * @cred points to the credentials. - * @gfp indicates the atomicity of any memory allocations. - * Only allocate sufficient memory and attach to @cred such that - * cred_transfer() will not get ENOMEM. - * Return 0 on success, negative values on failure. - * @cred_free: - * @cred points to the credentials. - * Deallocate and clear the cred->security field in a set of credentials. - * @cred_prepare: - * @new points to the new credentials. - * @old points to the original credentials. - * @gfp indicates the atomicity of any memory allocations. - * Prepare a new set of credentials by copying the data from the old set. - * Return 0 on success, negative values on failure. - * @cred_transfer: - * @new points to the new credentials. - * @old points to the original credentials. - * Transfer data from original creds to new creds - * @cred_getsecid: - * Retrieve the security identifier of the cred structure @c - * @c contains the credentials, secid will be placed into @secid. - * In case of failure, @secid will be set to zero. - * @kernel_act_as: - * Set the credentials for a kernel service to act as (subjective context). - * @new points to the credentials to be modified. - * @secid specifies the security ID to be set. - * The current task must be the one that nominated @secid. - * Return 0 if successful. - * @kernel_create_files_as: - * Set the file creation context in a set of credentials to be the same as - * the objective context of the specified inode. - * @new points to the credentials to be modified. - * @inode points to the inode to use as a reference. - * The current task must be the one that nominated @inode. - * Return 0 if successful. - * @kernel_module_request: - * Ability to trigger the kernel to automatically upcall to userspace for - * userspace to load a kernel module with the given name. - * @kmod_name name of the module requested by the kernel. - * Return 0 if successful. - * @kernel_load_data: - * Load data provided by userspace. - * @id kernel load data identifier. - * @contents if a subsequent @kernel_post_load_data will be called. - * Return 0 if permission is granted. - * @kernel_post_load_data: - * Load data provided by a non-file source (usually userspace buffer). - * @buf pointer to buffer containing the data contents. - * @size length of the data contents. - * @id kernel load data identifier. - * @description a text description of what was loaded, @id-specific. - * Return 0 if permission is granted. - * This must be paired with a prior @kernel_load_data call that had - * @contents set to true. - * @kernel_read_file: - * Read a file specified by userspace. - * @file contains the file structure pointing to the file being read - * by the kernel. - * @id kernel read file identifier. - * @contents if a subsequent @kernel_post_read_file will be called. - * Return 0 if permission is granted. - * @kernel_post_read_file: - * Read a file specified by userspace. - * @file contains the file structure pointing to the file being read - * by the kernel. - * @buf pointer to buffer containing the file contents. - * @size length of the file contents. - * @id kernel read file identifier. - * This must be paired with a prior @kernel_read_file call that had - * @contents set to true. - * Return 0 if permission is granted. - * @task_fix_setuid: - * Update the module's state after setting one or more of the user - * identity attributes of the current process. The @flags parameter - * indicates which of the set*uid system calls invoked this hook. If - * @new is the set of credentials that will be installed. Modifications - * should be made to this rather than to @current->cred. - * @old is the set of credentials that are being replaced. - * @flags contains one of the LSM_SETID_* values. - * Return 0 on success. - * @task_fix_setgid: - * Update the module's state after setting one or more of the group - * identity attributes of the current process. The @flags parameter - * indicates which of the set*gid system calls invoked this hook. - * @new is the set of credentials that will be installed. Modifications - * should be made to this rather than to @current->cred. - * @old is the set of credentials that are being replaced. - * @flags contains one of the LSM_SETID_* values. - * Return 0 on success. - * @task_fix_setgroups: - * Update the module's state after setting the supplementary group - * identity attributes of the current process. - * @new is the set of credentials that will be installed. Modifications - * should be made to this rather than to @current->cred. - * @old is the set of credentials that are being replaced. - * Return 0 on success. - * @task_setpgid: - * Check permission before setting the process group identifier of the - * process @p to @pgid. - * @p contains the task_struct for process being modified. - * @pgid contains the new pgid. - * Return 0 if permission is granted. - * @task_getpgid: - * Check permission before getting the process group identifier of the - * process @p. - * @p contains the task_struct for the process. - * Return 0 if permission is granted. - * @task_getsid: - * Check permission before getting the session identifier of the process - * @p. - * @p contains the task_struct for the process. - * Return 0 if permission is granted. - * @current_getsecid_subj: - * Retrieve the subjective security identifier of the current task and - * return it in @secid. - * In case of failure, @secid will be set to zero. - * @task_getsecid_obj: - * Retrieve the objective security identifier of the task_struct in @p - * and return it in @secid. - * In case of failure, @secid will be set to zero. - * - * @task_setnice: - * Check permission before setting the nice value of @p to @nice. - * @p contains the task_struct of process. - * @nice contains the new nice value. - * Return 0 if permission is granted. - * @task_setioprio: - * Check permission before setting the ioprio value of @p to @ioprio. - * @p contains the task_struct of process. - * @ioprio contains the new ioprio value. - * Return 0 if permission is granted. - * @task_getioprio: - * Check permission before getting the ioprio value of @p. - * @p contains the task_struct of process. - * Return 0 if permission is granted. - * @task_prlimit: - * Check permission before getting and/or setting the resource limits of - * another task. - * @cred points to the cred structure for the current task. - * @tcred points to the cred structure for the target task. - * @flags contains the LSM_PRLIMIT_* flag bits indicating whether the - * resource limits are being read, modified, or both. - * Return 0 if permission is granted. - * @task_setrlimit: - * Check permission before setting the resource limits of process @p - * for @resource to @new_rlim. The old resource limit values can - * be examined by dereferencing (p->signal->rlim + resource). - * @p points to the task_struct for the target task's group leader. - * @resource contains the resource whose limit is being set. - * @new_rlim contains the new limits for @resource. - * Return 0 if permission is granted. - * @task_setscheduler: - * Check permission before setting scheduling policy and/or parameters of - * process @p. - * @p contains the task_struct for process. - * Return 0 if permission is granted. - * @task_getscheduler: - * Check permission before obtaining scheduling information for process - * @p. - * @p contains the task_struct for process. - * Return 0 if permission is granted. - * @task_movememory: - * Check permission before moving memory owned by process @p. - * @p contains the task_struct for process. - * Return 0 if permission is granted. - * @task_kill: - * Check permission before sending signal @sig to @p. @info can be NULL, - * the constant 1, or a pointer to a kernel_siginfo structure. If @info is 1 or - * SI_FROMKERNEL(info) is true, then the signal should be viewed as coming - * from the kernel and should typically be permitted. - * SIGIO signals are handled separately by the send_sigiotask hook in - * file_security_ops. - * @p contains the task_struct for process. - * @info contains the signal information. - * @sig contains the signal value. - * @cred contains the cred of the process where the signal originated, or - * NULL if the current task is the originator. - * Return 0 if permission is granted. - * @task_prctl: - * Check permission before performing a process control operation on the - * current process. - * @option contains the operation. - * @arg2 contains a argument. - * @arg3 contains a argument. - * @arg4 contains a argument. - * @arg5 contains a argument. - * Return -ENOSYS if no-one wanted to handle this op, any other value to - * cause prctl() to return immediately with that value. - * @task_to_inode: - * Set the security attributes for an inode based on an associated task's - * security attributes, e.g. for /proc/pid inodes. - * @p contains the task_struct for the task. - * @inode contains the inode structure for the inode. - * @userns_create: - * Check permission prior to creating a new user namespace. - * @cred points to prepared creds. - * Return 0 if successful, otherwise < 0 error code. - * - * Security hooks for Netlink messaging. - * - * @netlink_send: - * Save security information for a netlink message so that permission - * checking can be performed when the message is processed. The security - * information can be saved using the eff_cap field of the - * netlink_skb_parms structure. Also may be used to provide fine - * grained control over message transmission. - * @sk associated sock of task sending the message. - * @skb contains the sk_buff structure for the netlink message. - * Return 0 if the information was successfully saved and message - * is allowed to be transmitted. - * - * Security hooks for Unix domain networking. - * - * @unix_stream_connect: - * Check permissions before establishing a Unix domain stream connection - * between @sock and @other. - * @sock contains the sock structure. - * @other contains the peer sock structure. - * @newsk contains the new sock structure. - * Return 0 if permission is granted. - * @unix_may_send: - * Check permissions before connecting or sending datagrams from @sock to - * @other. - * @sock contains the socket structure. - * @other contains the peer socket structure. - * Return 0 if permission is granted. - * - * The @unix_stream_connect and @unix_may_send hooks were necessary because - * Linux provides an alternative to the conventional file name space for Unix - * domain sockets. Whereas binding and connecting to sockets in the file name - * space is mediated by the typical file permissions (and caught by the mknod - * and permission hooks in inode_security_ops), binding and connecting to - * sockets in the abstract name space is completely unmediated. Sufficient - * control of Unix domain sockets in the abstract name space isn't possible - * using only the socket layer hooks, since we need to know the actual target - * socket, which is not looked up until we are inside the af_unix code. - * - * Security hooks for socket operations. - * - * @socket_create: - * Check permissions prior to creating a new socket. - * @family contains the requested protocol family. - * @type contains the requested communications type. - * @protocol contains the requested protocol. - * @kern set to 1 if a kernel socket. - * Return 0 if permission is granted. - * @socket_post_create: - * This hook allows a module to update or allocate a per-socket security - * structure. Note that the security field was not added directly to the - * socket structure, but rather, the socket security information is stored - * in the associated inode. Typically, the inode alloc_security hook will - * allocate and attach security information to - * SOCK_INODE(sock)->i_security. This hook may be used to update the - * SOCK_INODE(sock)->i_security field with additional information that - * wasn't available when the inode was allocated. - * @sock contains the newly created socket structure. - * @family contains the requested protocol family. - * @type contains the requested communications type. - * @protocol contains the requested protocol. - * @kern set to 1 if a kernel socket. - * Return 0 if permission is granted. - * @socket_socketpair: - * Check permissions before creating a fresh pair of sockets. - * @socka contains the first socket structure. - * @sockb contains the second socket structure. - * Return 0 if permission is granted and the connection was established. - * @socket_bind: - * Check permission before socket protocol layer bind operation is - * performed and the socket @sock is bound to the address specified in the - * @address parameter. - * @sock contains the socket structure. - * @address contains the address to bind to. - * @addrlen contains the length of address. - * Return 0 if permission is granted. - * @socket_connect: - * Check permission before socket protocol layer connect operation - * attempts to connect socket @sock to a remote address, @address. - * @sock contains the socket structure. - * @address contains the address of remote endpoint. - * @addrlen contains the length of address. - * Return 0 if permission is granted. - * @socket_listen: - * Check permission before socket protocol layer listen operation. - * @sock contains the socket structure. - * @backlog contains the maximum length for the pending connection queue. - * Return 0 if permission is granted. - * @socket_accept: - * Check permission before accepting a new connection. Note that the new - * socket, @newsock, has been created and some information copied to it, - * but the accept operation has not actually been performed. - * @sock contains the listening socket structure. - * @newsock contains the newly created server socket for connection. - * Return 0 if permission is granted. - * @socket_sendmsg: - * Check permission before transmitting a message to another socket. - * @sock contains the socket structure. - * @msg contains the message to be transmitted. - * @size contains the size of message. - * Return 0 if permission is granted. - * @socket_recvmsg: - * Check permission before receiving a message from a socket. - * @sock contains the socket structure. - * @msg contains the message structure. - * @size contains the size of message structure. - * @flags contains the operational flags. - * Return 0 if permission is granted. - * @socket_getsockname: - * Check permission before the local address (name) of the socket object - * @sock is retrieved. - * @sock contains the socket structure. - * Return 0 if permission is granted. - * @socket_getpeername: - * Check permission before the remote address (name) of a socket object - * @sock is retrieved. - * @sock contains the socket structure. - * Return 0 if permission is granted. - * @socket_getsockopt: - * Check permissions before retrieving the options associated with socket - * @sock. - * @sock contains the socket structure. - * @level contains the protocol level to retrieve option from. - * @optname contains the name of option to retrieve. - * Return 0 if permission is granted. - * @socket_setsockopt: - * Check permissions before setting the options associated with socket - * @sock. - * @sock contains the socket structure. - * @level contains the protocol level to set options for. - * @optname contains the name of the option to set. - * Return 0 if permission is granted. - * @socket_shutdown: - * Checks permission before all or part of a connection on the socket - * @sock is shut down. - * @sock contains the socket structure. - * @how contains the flag indicating how future sends and receives - * are handled. - * Return 0 if permission is granted. - * @socket_sock_rcv_skb: - * Check permissions on incoming network packets. This hook is distinct - * from Netfilter's IP input hooks since it is the first time that the - * incoming sk_buff @skb has been associated with a particular socket, @sk. - * Must not sleep inside this hook because some callers hold spinlocks. - * @sk contains the sock (not socket) associated with the incoming sk_buff. - * @skb contains the incoming network data. - * Return 0 if permission is granted. - * @socket_getpeersec_stream: - * This hook allows the security module to provide peer socket security - * state for unix or connected tcp sockets to userspace via getsockopt - * SO_GETPEERSEC. For tcp sockets this can be meaningful if the - * socket is associated with an ipsec SA. - * @sock is the local socket. - * @optval memory where the security state is to be copied. - * @optlen memory where the module should copy the actual length - * of the security state. - * @len as input is the maximum length to copy to userspace provided - * by the caller. - * Return 0 if all is well, otherwise, typical getsockopt return - * values. - * @socket_getpeersec_dgram: - * This hook allows the security module to provide peer socket security - * state for udp sockets on a per-packet basis to userspace via - * getsockopt SO_GETPEERSEC. The application must first have indicated - * the IP_PASSSEC option via getsockopt. It can then retrieve the - * security state returned by this hook for a packet via the SCM_SECURITY - * ancillary message type. - * @sock contains the peer socket. May be NULL. - * @skb is the sk_buff for the packet being queried. May be NULL. - * @secid pointer to store the secid of the packet. - * Return 0 on success, error on failure. - * @sk_alloc_security: - * Allocate and attach a security structure to the sk->sk_security field, - * which is used to copy security attributes between local stream sockets. - * Return 0 on success, error on failure. - * @sk_free_security: - * Deallocate security structure. - * @sk_clone_security: - * Clone/copy security structure. - * @sk_getsecid: - * Retrieve the LSM-specific secid for the sock to enable caching - * of network authorizations. - * @sock_graft: - * Sets the socket's isec sid to the sock's sid. - * @inet_conn_request: - * Sets the openreq's sid to socket's sid with MLS portion taken - * from peer sid. - * Return 0 if permission is granted. - * @inet_csk_clone: - * Sets the new child socket's sid to the openreq sid. - * @inet_conn_established: - * Sets the connection's peersid to the secmark on skb. - * @secmark_relabel_packet: - * Check if the process should be allowed to relabel packets to - * the given secid. - * Return 0 if permission is granted. - * @secmark_refcount_inc: - * Tells the LSM to increment the number of secmark labeling rules loaded. - * @secmark_refcount_dec: - * Tells the LSM to decrement the number of secmark labeling rules loaded. - * @req_classify_flow: - * Sets the flow's sid to the openreq sid. - * @tun_dev_alloc_security: - * This hook allows a module to allocate a security structure for a TUN - * device. - * @security pointer to a security structure pointer. - * Returns a zero on success, negative values on failure. - * @tun_dev_free_security: - * This hook allows a module to free the security structure for a TUN - * device. - * @security pointer to the TUN device's security structure. - * @tun_dev_create: - * Check permissions prior to creating a new TUN device. - * Return 0 if permission is granted. - * @tun_dev_attach_queue: - * Check permissions prior to attaching to a TUN device queue. - * @security pointer to the TUN device's security structure. - * Return 0 if permission is granted. - * @tun_dev_attach: - * This hook can be used by the module to update any security state - * associated with the TUN device's sock structure. - * @sk contains the existing sock structure. - * @security pointer to the TUN device's security structure. - * Return 0 if permission is granted. - * @tun_dev_open: - * This hook can be used by the module to update any security state - * associated with the TUN device's security structure. - * @security pointer to the TUN devices's security structure. - * Return 0 if permission is granted. - * - * Security hooks for SCTP - * - * @sctp_assoc_request: - * Passes the @asoc and @chunk->skb of the association INIT packet to - * the security module. - * @asoc pointer to sctp association structure. - * @skb pointer to skbuff of association packet. - * Return 0 on success, error on failure. - * @sctp_bind_connect: - * Validiate permissions required for each address associated with sock - * @sk. Depending on @optname, the addresses will be treated as either - * for a connect or bind service. The @addrlen is calculated on each - * ipv4 and ipv6 address using sizeof(struct sockaddr_in) or - * sizeof(struct sockaddr_in6). - * @sk pointer to sock structure. - * @optname name of the option to validate. - * @address list containing one or more ipv4/ipv6 addresses. - * @addrlen total length of address(s). - * Return 0 on success, error on failure. - * @sctp_sk_clone: - * Called whenever a new socket is created by accept(2) (i.e. a TCP - * style socket) or when a socket is 'peeled off' e.g userspace - * calls sctp_peeloff(3). - * @asoc pointer to current sctp association structure. - * @sk pointer to current sock structure. - * @newsk pointer to new sock structure. - * @sctp_assoc_established: - * Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet - * to the security module. - * @asoc pointer to sctp association structure. - * @skb pointer to skbuff of association packet. - * Return 0 if permission is granted. - * - * Security hooks for Infiniband - * - * @ib_pkey_access: - * Check permission to access a pkey when modifing a QP. - * @subnet_prefix the subnet prefix of the port being used. - * @pkey the pkey to be accessed. - * @sec pointer to a security structure. - * Return 0 if permission is granted. - * @ib_endport_manage_subnet: - * Check permissions to send and receive SMPs on a end port. - * @dev_name the IB device name (i.e. mlx4_0). - * @port_num the port number. - * @sec pointer to a security structure. - * Return 0 if permission is granted. - * @ib_alloc_security: - * Allocate a security structure for Infiniband objects. - * @sec pointer to a security structure pointer. - * Returns 0 on success, non-zero on failure. - * @ib_free_security: - * Deallocate an Infiniband security structure. - * @sec contains the security structure to be freed. - * - * Security hooks for XFRM operations. - * - * @xfrm_policy_alloc_security: - * @ctxp is a pointer to the xfrm_sec_ctx being added to Security Policy - * Database used by the XFRM system. - * @sec_ctx contains the security context information being provided by - * the user-level policy update program (e.g., setkey). - * @gfp is to specify the context for the allocation. - * Allocate a security structure to the xp->security field; the security - * field is initialized to NULL when the xfrm_policy is allocated. - * Return 0 if operation was successful (memory to allocate, legal - * context). - * @xfrm_policy_clone_security: - * @old_ctx contains an existing xfrm_sec_ctx. - * @new_ctxp contains a new xfrm_sec_ctx being cloned from old. - * Allocate a security structure in new_ctxp that contains the - * information from the old_ctx structure. - * Return 0 if operation was successful (memory to allocate). - * @xfrm_policy_free_security: - * @ctx contains the xfrm_sec_ctx. - * Deallocate xp->security. - * @xfrm_policy_delete_security: - * @ctx contains the xfrm_sec_ctx. - * Authorize deletion of xp->security. - * Return 0 if permission is granted. - * @xfrm_state_alloc: - * @x contains the xfrm_state being added to the Security Association - * Database by the XFRM system. - * @sec_ctx contains the security context information being provided by - * the user-level SA generation program (e.g., setkey or racoon). - * Allocate a security structure to the x->security field; the security - * field is initialized to NULL when the xfrm_state is allocated. Set the - * context to correspond to sec_ctx. Return 0 if operation was successful - * (memory to allocate, legal context). - * @xfrm_state_alloc_acquire: - * @x contains the xfrm_state being added to the Security Association - * Database by the XFRM system. - * @polsec contains the policy's security context. - * @secid contains the secid from which to take the mls portion of the - * context. - * Allocate a security structure to the x->security field; the security - * field is initialized to NULL when the xfrm_state is allocated. Set the - * context to correspond to secid. Return 0 if operation was successful - * (memory to allocate, legal context). - * @xfrm_state_free_security: - * @x contains the xfrm_state. - * Deallocate x->security. - * @xfrm_state_delete_security: - * @x contains the xfrm_state. - * Authorize deletion of x->security. - * Return 0 if permission is granted. - * @xfrm_policy_lookup: - * @ctx contains the xfrm_sec_ctx for which the access control is being - * checked. - * @fl_secid contains the flow security label that is used to authorize - * access to the policy xp. - * @dir contains the direction of the flow (input or output). - * Check permission when a flow selects a xfrm_policy for processing - * XFRMs on a packet. The hook is called when selecting either a - * per-socket policy or a generic xfrm policy. - * Return 0 if permission is granted, -ESRCH otherwise, or -errno - * on other errors. - * @xfrm_state_pol_flow_match: - * @x contains the state to match. - * @xp contains the policy to check for a match. - * @flic contains the flowi_common struct to check for a match. - * Return 1 if there is a match. - * @xfrm_decode_session: - * @skb points to skb to decode. - * @secid points to the flow key secid to set. - * @ckall says if all xfrms used should be checked for same secid. - * Return 0 if ckall is zero or all xfrms used have the same secid. - * - * Security hooks affecting all Key Management operations - * - * @key_alloc: - * Permit allocation of a key and assign security data. Note that key does - * not have a serial number assigned at this point. - * @key points to the key. - * @flags is the allocation flags. - * Return 0 if permission is granted, -ve error otherwise. - * @key_free: - * Notification of destruction; free security data. - * @key points to the key. - * No return value. - * @key_permission: - * See whether a specific operational right is granted to a process on a - * key. - * @key_ref refers to the key (key pointer + possession attribute bit). - * @cred points to the credentials to provide the context against which to - * evaluate the security data on the key. - * @perm describes the combination of permissions required of this key. - * Return 0 if permission is granted, -ve error otherwise. - * @key_getsecurity: - * Get a textual representation of the security context attached to a key - * for the purposes of honouring KEYCTL_GETSECURITY. This function - * allocates the storage for the NUL-terminated string and the caller - * should free it. - * @key points to the key to be queried. - * @_buffer points to a pointer that should be set to point to the - * resulting string (if no label or an error occurs). - * Return the length of the string (including terminating NUL) or -ve if - * an error. - * May also return 0 (and a NULL buffer pointer) if there is no label. - * - * Security hooks affecting all System V IPC operations. - * - * @ipc_permission: - * Check permissions for access to IPC - * @ipcp contains the kernel IPC permission structure. - * @flag contains the desired (requested) permission set. - * Return 0 if permission is granted. - * @ipc_getsecid: - * Get the secid associated with the ipc object. - * @ipcp contains the kernel IPC permission structure. - * @secid contains a pointer to the location where result will be saved. - * In case of failure, @secid will be set to zero. - * - * Security hooks for individual messages held in System V IPC message queues - * - * @msg_msg_alloc_security: - * Allocate and attach a security structure to the msg->security field. - * The security field is initialized to NULL when the structure is first - * created. - * @msg contains the message structure to be modified. - * Return 0 if operation was successful and permission is granted. - * @msg_msg_free_security: - * Deallocate the security structure for this message. - * @msg contains the message structure to be modified. - * - * Security hooks for System V IPC Message Queues - * - * @msg_queue_alloc_security: - * Allocate and attach a security structure to the - * @perm->security field. The security field is initialized to - * NULL when the structure is first created. - * @perm contains the IPC permissions of the message queue. - * Return 0 if operation was successful and permission is granted. - * @msg_queue_free_security: - * Deallocate security field @perm->security for the message queue. - * @perm contains the IPC permissions of the message queue. - * @msg_queue_associate: - * Check permission when a message queue is requested through the - * msgget system call. This hook is only called when returning the - * message queue identifier for an existing message queue, not when a - * new message queue is created. - * @perm contains the IPC permissions of the message queue. - * @msqflg contains the operation control flags. - * Return 0 if permission is granted. - * @msg_queue_msgctl: - * Check permission when a message control operation specified by @cmd - * is to be performed on the message queue with permissions @perm. - * The @perm may be NULL, e.g. for IPC_INFO or MSG_INFO. - * @perm contains the IPC permissions of the msg queue. May be NULL. - * @cmd contains the operation to be performed. - * Return 0 if permission is granted. - * @msg_queue_msgsnd: - * Check permission before a message, @msg, is enqueued on the message - * queue with permissions @perm. - * @perm contains the IPC permissions of the message queue. - * @msg contains the message to be enqueued. - * @msqflg contains operational flags. - * Return 0 if permission is granted. - * @msg_queue_msgrcv: - * Check permission before a message, @msg, is removed from the message - * queue. The @target task structure contains a pointer to the - * process that will be receiving the message (not equal to the current - * process when inline receives are being performed). - * @perm contains the IPC permissions of the message queue. - * @msg contains the message destination. - * @target contains the task structure for recipient process. - * @type contains the type of message requested. - * @mode contains the operational flags. - * Return 0 if permission is granted. - * - * Security hooks for System V Shared Memory Segments - * - * @shm_alloc_security: - * Allocate and attach a security structure to the @perm->security - * field. The security field is initialized to NULL when the structure is - * first created. - * @perm contains the IPC permissions of the shared memory structure. - * Return 0 if operation was successful and permission is granted. - * @shm_free_security: - * Deallocate the security structure @perm->security for the memory segment. - * @perm contains the IPC permissions of the shared memory structure. - * @shm_associate: - * Check permission when a shared memory region is requested through the - * shmget system call. This hook is only called when returning the shared - * memory region identifier for an existing region, not when a new shared - * memory region is created. - * @perm contains the IPC permissions of the shared memory structure. - * @shmflg contains the operation control flags. - * Return 0 if permission is granted. - * @shm_shmctl: - * Check permission when a shared memory control operation specified by - * @cmd is to be performed on the shared memory region with permissions @perm. - * The @perm may be NULL, e.g. for IPC_INFO or SHM_INFO. - * @perm contains the IPC permissions of the shared memory structure. - * @cmd contains the operation to be performed. - * Return 0 if permission is granted. - * @shm_shmat: - * Check permissions prior to allowing the shmat system call to attach the - * shared memory segment with permissions @perm to the data segment of the - * calling process. The attaching address is specified by @shmaddr. - * @perm contains the IPC permissions of the shared memory structure. - * @shmaddr contains the address to attach memory region to. - * @shmflg contains the operational flags. - * Return 0 if permission is granted. - * - * Security hooks for System V Semaphores - * - * @sem_alloc_security: - * Allocate and attach a security structure to the @perm->security - * field. The security field is initialized to NULL when the structure is - * first created. - * @perm contains the IPC permissions of the semaphore. - * Return 0 if operation was successful and permission is granted. - * @sem_free_security: - * Deallocate security structure @perm->security for the semaphore. - * @perm contains the IPC permissions of the semaphore. - * @sem_associate: - * Check permission when a semaphore is requested through the semget - * system call. This hook is only called when returning the semaphore - * identifier for an existing semaphore, not when a new one must be - * created. - * @perm contains the IPC permissions of the semaphore. - * @semflg contains the operation control flags. - * Return 0 if permission is granted. - * @sem_semctl: - * Check permission when a semaphore operation specified by @cmd is to be - * performed on the semaphore. The @perm may be NULL, e.g. for - * IPC_INFO or SEM_INFO. - * @perm contains the IPC permissions of the semaphore. May be NULL. - * @cmd contains the operation to be performed. - * Return 0 if permission is granted. - * @sem_semop: - * Check permissions before performing operations on members of the - * semaphore set. If the @alter flag is nonzero, the semaphore set - * may be modified. - * @perm contains the IPC permissions of the semaphore. - * @sops contains the operations to perform. - * @nsops contains the number of operations to perform. - * @alter contains the flag indicating whether changes are to be made. - * Return 0 if permission is granted. - * - * @binder_set_context_mgr: - * Check whether @mgr is allowed to be the binder context manager. - * @mgr contains the struct cred for the current binder process. - * Return 0 if permission is granted. - * @binder_transaction: - * Check whether @from is allowed to invoke a binder transaction call - * to @to. - * @from contains the struct cred for the sending process. - * @to contains the struct cred for the receiving process. - * Return 0 if permission is granted. - * @binder_transfer_binder: - * Check whether @from is allowed to transfer a binder reference to @to. - * @from contains the struct cred for the sending process. - * @to contains the struct cred for the receiving process. - * Return 0 if permission is granted. - * @binder_transfer_file: - * Check whether @from is allowed to transfer @file to @to. - * @from contains the struct cred for the sending process. - * @file contains the struct file being transferred. - * @to contains the struct cred for the receiving process. - * Return 0 if permission is granted. - * - * @ptrace_access_check: - * Check permission before allowing the current process to trace the - * @child process. - * Security modules may also want to perform a process tracing check - * during an execve in the set_security or apply_creds hooks of - * tracing check during an execve in the bprm_set_creds hook of - * binprm_security_ops if the process is being traced and its security - * attributes would be changed by the execve. - * @child contains the task_struct structure for the target process. - * @mode contains the PTRACE_MODE flags indicating the form of access. - * Return 0 if permission is granted. - * @ptrace_traceme: - * Check that the @parent process has sufficient permission to trace the - * current process before allowing the current process to present itself - * to the @parent process for tracing. - * @parent contains the task_struct structure for debugger process. - * Return 0 if permission is granted. - * @capget: - * Get the @effective, @inheritable, and @permitted capability sets for - * the @target process. The hook may also perform permission checking to - * determine if the current process is allowed to see the capability sets - * of the @target process. - * @target contains the task_struct structure for target process. - * @effective contains the effective capability set. - * @inheritable contains the inheritable capability set. - * @permitted contains the permitted capability set. - * Return 0 if the capability sets were successfully obtained. - * @capset: - * Set the @effective, @inheritable, and @permitted capability sets for - * the current process. - * @new contains the new credentials structure for target process. - * @old contains the current credentials structure for target process. - * @effective contains the effective capability set. - * @inheritable contains the inheritable capability set. - * @permitted contains the permitted capability set. - * Return 0 and update @new if permission is granted. - * @capable: - * Check whether the @tsk process has the @cap capability in the indicated - * credentials. - * @cred contains the credentials to use. - * @ns contains the user namespace we want the capability in. - * @cap contains the capability <include/linux/capability.h>. - * @opts contains options for the capable check <include/linux/security.h>. - * Return 0 if the capability is granted for @tsk. - * @quotactl: - * Check whether the quotactl syscall is allowed for this @sb. - * Return 0 if permission is granted. - * @quota_on: - * Check whether QUOTAON is allowed for this @dentry. - * Return 0 if permission is granted. - * @syslog: - * Check permission before accessing the kernel message ring or changing - * logging to the console. - * See the syslog(2) manual page for an explanation of the @type values. - * @type contains the SYSLOG_ACTION_* constant from - * <include/linux/syslog.h>. - * Return 0 if permission is granted. - * @settime: - * Check permission to change the system time. - * struct timespec64 is defined in <include/linux/time64.h> and timezone - * is defined in <include/linux/time.h> - * @ts contains new time. - * @tz contains new timezone. - * Return 0 if permission is granted. - * @vm_enough_memory: - * Check permissions for allocating a new virtual mapping. - * @mm contains the mm struct it is being added to. - * @pages contains the number of pages. - * Return 0 if permission is granted by the LSM infrastructure to the - * caller. If all LSMs return a positive value, __vm_enough_memory() will - * be called with cap_sys_admin set. If at least one LSM returns 0 or - * negative, __vm_enough_memory() will be called with cap_sys_admin - * cleared. - * - * @ismaclabel: - * Check if the extended attribute specified by @name - * represents a MAC label. Returns 1 if name is a MAC - * attribute otherwise returns 0. - * @name full extended attribute name to check against - * LSM as a MAC label. - * - * @secid_to_secctx: - * Convert secid to security context. If secdata is NULL the length of - * the result will be returned in seclen, but no secdata will be returned. - * This does mean that the length could change between calls to check the - * length and the next call which actually allocates and returns the - * secdata. - * @secid contains the security ID. - * @secdata contains the pointer that stores the converted security - * context. - * @seclen pointer which contains the length of the data. - * Return 0 on success, error on failure. - * @secctx_to_secid: - * Convert security context to secid. - * @secid contains the pointer to the generated security ID. - * @secdata contains the security context. - * Return 0 on success, error on failure. - * - * @release_secctx: - * Release the security context. - * @secdata contains the security context. - * @seclen contains the length of the security context. - * - * Security hooks for Audit - * - * @audit_rule_init: - * Allocate and initialize an LSM audit rule structure. - * @field contains the required Audit action. - * Fields flags are defined in <include/linux/audit.h> - * @op contains the operator the rule uses. - * @rulestr contains the context where the rule will be applied to. - * @lsmrule contains a pointer to receive the result. - * Return 0 if @lsmrule has been successfully set, - * -EINVAL in case of an invalid rule. - * - * @audit_rule_known: - * Specifies whether given @krule contains any fields related to - * current LSM. - * @krule contains the audit rule of interest. - * Return 1 in case of relation found, 0 otherwise. - * - * @audit_rule_match: - * Determine if given @secid matches a rule previously approved - * by @audit_rule_known. - * @secid contains the security id in question. - * @field contains the field which relates to current LSM. - * @op contains the operator that will be used for matching. - * @lrule points to the audit rule that will be checked against. - * Return 1 if secid matches the rule, 0 if it does not, -ERRNO on failure. - * - * @audit_rule_free: - * Deallocate the LSM audit rule structure previously allocated by - * audit_rule_init. - * @lsmrule contains the allocated rule. - * - * @inode_invalidate_secctx: - * Notify the security module that it must revalidate the security context - * of an inode. - * - * @inode_notifysecctx: - * Notify the security module of what the security context of an inode - * should be. Initializes the incore security context managed by the - * security module for this inode. Example usage: NFS client invokes - * this hook to initialize the security context in its incore inode to the - * value provided by the server for the file when the server returned the - * file's attributes to the client. - * Must be called with inode->i_mutex locked. - * @inode we wish to set the security context of. - * @ctx contains the string which we wish to set in the inode. - * @ctxlen contains the length of @ctx. - * Return 0 on success, error on failure. - * - * @inode_setsecctx: - * Change the security context of an inode. Updates the - * incore security context managed by the security module and invokes the - * fs code as needed (via __vfs_setxattr_noperm) to update any backing - * xattrs that represent the context. Example usage: NFS server invokes - * this hook to change the security context in its incore inode and on the - * backing filesystem to a value provided by the client on a SETATTR - * operation. - * Must be called with inode->i_mutex locked. - * @dentry contains the inode we wish to set the security context of. - * @ctx contains the string which we wish to set in the inode. - * @ctxlen contains the length of @ctx. - * Return 0 on success, error on failure. - * - * @inode_getsecctx: - * On success, returns 0 and fills out @ctx and @ctxlen with the security - * context for the given @inode. - * @inode we wish to get the security context of. - * @ctx is a pointer in which to place the allocated security context. - * @ctxlen points to the place to put the length of @ctx. - * Return 0 on success, error on failure. - * - * Security hooks for the general notification queue: - * - * @post_notification: - * Check to see if a watch notification can be posted to a particular - * queue. - * @w_cred: The credentials of the whoever set the watch. - * @cred: The event-triggerer's credentials. - * @n: The notification being posted. - * Return 0 if permission is granted. - * - * @watch_key: - * Check to see if a process is allowed to watch for event notifications - * from a key or keyring. - * @key: The key to watch. - * Return 0 if permission is granted. - * - * Security hooks for using the eBPF maps and programs functionalities through - * eBPF syscalls. - * - * @bpf: - * Do a initial check for all bpf syscalls after the attribute is copied - * into the kernel. The actual security module can implement their own - * rules to check the specific cmd they need. - * Return 0 if permission is granted. - * - * @bpf_map: - * Do a check when the kernel generate and return a file descriptor for - * eBPF maps. - * @map: bpf map that we want to access. - * @mask: the access flags. - * Return 0 if permission is granted. - * - * @bpf_prog: - * Do a check when the kernel generate and return a file descriptor for - * eBPF programs. - * @prog: bpf prog that userspace want to use. - * Return 0 if permission is granted. - * - * @bpf_map_alloc_security: - * Initialize the security field inside bpf map. - * Return 0 on success, error on failure. - * - * @bpf_map_free_security: - * Clean up the security information stored inside bpf map. - * - * @bpf_prog_alloc_security: - * Initialize the security field inside bpf program. - * Return 0 on success, error on failure. - * - * @bpf_prog_free_security: - * Clean up the security information stored inside bpf prog. - * - * @locked_down: - * Determine whether a kernel feature that potentially enables arbitrary - * code execution in kernel space should be permitted. - * @what: kernel feature being accessed. - * Return 0 if permission is granted. - * - * Security hooks for perf events - * - * @perf_event_open: - * Check whether the @type of perf_event_open syscall is allowed. - * Return 0 if permission is granted. - * @perf_event_alloc: - * Allocate and save perf_event security info. - * Return 0 on success, error on failure. - * @perf_event_free: - * Release (free) perf_event security info. - * @perf_event_read: - * Read perf_event security info if allowed. - * Return 0 if permission is granted. - * @perf_event_write: - * Write perf_event security info if allowed. - * Return 0 if permission is granted. - * - * Security hooks for io_uring - * - * @uring_override_creds: - * Check if the current task, executing an io_uring operation, is allowed - * to override it's credentials with @new. - * @new: the new creds to use. - * Return 0 if permission is granted. - * - * @uring_sqpoll: - * Check whether the current task is allowed to spawn a io_uring polling - * thread (IORING_SETUP_SQPOLL). - * Return 0 if permission is granted. - * - * @uring_cmd: - * Check whether the file_operations uring_cmd is allowed to run. - * Return 0 if permission is granted. - * - */ union security_list_options { #define LSM_HOOK(RET, DEFAULT, NAME, ...) RET (*NAME)(__VA_ARGS__); #include "lsm_hook_defs.h" @@ -1716,6 +92,7 @@ extern void security_add_hooks(struct security_hook_list *hooks, int count, enum lsm_order { LSM_ORDER_FIRST = -1, /* This is only for capabilities. */ LSM_ORDER_MUTABLE = 0, + LSM_ORDER_LAST = 1, /* This is only for integrity. */ }; struct lsm_info { @@ -1740,36 +117,6 @@ extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[]; __used __section(".early_lsm_info.init") \ __aligned(sizeof(unsigned long)) -#ifdef CONFIG_SECURITY_SELINUX_DISABLE -/* - * Assuring the safety of deleting a security module is up to - * the security module involved. This may entail ordering the - * module's hook list in a particular way, refusing to disable - * the module once a policy is loaded or any number of other - * actions better imagined than described. - * - * The name of the configuration option reflects the only module - * that currently uses the mechanism. Any developer who thinks - * disabling their module is a good idea needs to be at least as - * careful as the SELinux team. - */ -static inline void security_delete_hooks(struct security_hook_list *hooks, - int count) -{ - int i; - - for (i = 0; i < count; i++) - hlist_del_rcu(&hooks[i].list); -} -#endif /* CONFIG_SECURITY_SELINUX_DISABLE */ - -/* Currently required to handle SELinux runtime hook disable. */ -#ifdef CONFIG_SECURITY_WRITABLE_HOOKS -#define __lsm_ro_after_init -#else -#define __lsm_ro_after_init __ro_after_init -#endif /* CONFIG_SECURITY_WRITABLE_HOOKS */ - extern int lsm_inode_alloc(struct inode *inode); #endif /* ! __LINUX_LSM_HOOKS_H */ diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 71b06ebad402..1db19a9d26e3 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -36,6 +36,7 @@ #include <linux/types.h> #include <rdma/ib_verbs.h> #include <linux/mlx5/mlx5_ifc.h> +#include <linux/bitfield.h> #if defined(__LITTLE_ENDIAN) #define MLX5_SET_HOST_ENDIANNESS 0 @@ -980,14 +981,23 @@ enum { }; enum { - CQE_RSS_HTYPE_IP = 0x3 << 2, + CQE_RSS_HTYPE_IP = GENMASK(3, 2), /* cqe->rss_hash_type[3:2] - IP destination selected for hash * (00 = none, 01 = IPv4, 10 = IPv6, 11 = Reserved) */ - CQE_RSS_HTYPE_L4 = 0x3 << 6, + CQE_RSS_IP_NONE = 0x0, + CQE_RSS_IPV4 = 0x1, + CQE_RSS_IPV6 = 0x2, + CQE_RSS_RESERVED = 0x3, + + CQE_RSS_HTYPE_L4 = GENMASK(7, 6), /* cqe->rss_hash_type[7:6] - L4 destination selected for hash * (00 = none, 01 = TCP. 10 = UDP, 11 = IPSEC.SPI */ + CQE_RSS_L4_NONE = 0x0, + CQE_RSS_L4_TCP = 0x1, + CQE_RSS_L4_UDP = 0x2, + CQE_RSS_L4_IPSEC = 0x3, }; enum { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f33389b42209..7e225e41d55b 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1211,11 +1211,6 @@ static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev) return dev->coredev_type == MLX5_COREDEV_VF; } -static inline bool mlx5_core_is_management_pf(const struct mlx5_core_dev *dev) -{ - return MLX5_CAP_GEN(dev, num_ports) == 1 && !MLX5_CAP_GEN(dev, native_port_num); -} - static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev) { return dev->caps.embedded_cpu; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0722859c3647..a57e6ae78e65 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -774,7 +774,8 @@ struct mm_struct { unsigned long cpu_bitmap[]; }; -#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN) +#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | \ + MT_FLAGS_USE_RCU) extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 470085b121d3..c35f04f636f1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1624,7 +1624,8 @@ struct net_device_ops { struct xdp_metadata_ops { int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp); - int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash); + int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type); }; /** diff --git a/include/linux/notifier.h b/include/linux/notifier.h index aef88c2d1173..2aba75145144 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -73,6 +73,9 @@ struct raw_notifier_head { struct srcu_notifier_head { struct mutex mutex; +#ifdef CONFIG_TREE_SRCU + struct srcu_usage srcuu; +#endif struct srcu_struct srcu; struct notifier_block __rcu *head; }; @@ -107,7 +110,7 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); { \ .mutex = __MUTEX_INITIALIZER(name.mutex), \ .head = NULL, \ - .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu), \ + .srcu = __SRCU_STRUCT_INIT(name.srcu, name.srcuu, pcpu), \ } #define ATOMIC_NOTIFIER_HEAD(name) \ diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h index ed9b4df792b8..43765eaf2342 100644 --- a/include/linux/pci-doe.h +++ b/include/linux/pci-doe.h @@ -34,6 +34,10 @@ struct pci_doe_mb; * @work: Used internally by the mailbox * @doe_mb: Used internally by the mailbox * + * Payloads are treated as opaque byte streams which are transmitted verbatim, + * without byte-swapping. If payloads contain little-endian register values, + * the caller is responsible for conversion with cpu_to_le32() / le32_to_cpu(). + * * The payload sizes and rv are specified in bytes with the following * restrictions concerning the protocol. * @@ -45,9 +49,9 @@ struct pci_doe_mb; */ struct pci_doe_task { struct pci_doe_protocol prot; - u32 *request_pl; + __le32 *request_pl; size_t request_pl_sz; - u32 *response_pl; + __le32 *response_pl; size_t response_pl_sz; int rv; void (*complete)(struct pci_doe_task *task); diff --git a/include/linux/pci.h b/include/linux/pci.h index b50e5c79f7e3..a5dda515fcd1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1624,6 +1624,8 @@ pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, flags, NULL); } +static inline bool pci_msix_can_alloc_dyn(struct pci_dev *dev) +{ return false; } static inline struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index, const struct irq_affinity_desc *affdesc) { diff --git a/include/linux/phy.h b/include/linux/phy.h index 36bf0bbc8efa..db7c0bd67559 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1547,7 +1547,7 @@ int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id); struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode); struct phy_device *device_phy_find_device(struct device *dev); -struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_get_phy_node(const struct fwnode_handle *fwnode); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index c492c26202b5..637698ed5cb6 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -574,6 +574,7 @@ struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, phy_interface_t iface, const struct phylink_mac_ops *mac_ops); void phylink_destroy(struct phylink *); +bool phylink_expects_phy(struct phylink *pl); int phylink_connect_phy(struct phylink *, struct phy_device *); int phylink_of_phy_connect(struct phylink *, struct device_node *, u32 flags); diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 92ad75549e9c..b6e6378dcbbd 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -25,7 +25,8 @@ void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned change, u32 event, gfp_t flags, int *new_nsid, - int new_ifindex, u32 portid, u32 seq); + int new_ifindex, u32 portid, + const struct nlmsghdr *nlh); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags, u32 portid, const struct nlmsghdr *nlh); diff --git a/include/linux/sched.h b/include/linux/sched.h index 63d242164b1a..e1e605b1255b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1729,7 +1729,7 @@ extern struct pid *cad_pid; #define PF_MEMALLOC 0x00000800 /* Allocating memory */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ -#define PF__HOLE__00004000 0x00004000 +#define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ #define PF__HOLE__00010000 0x00010000 #define PF_KSWAPD 0x00020000 /* I am kswapd */ diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 357e0068497c..537cbf9a2ade 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -23,7 +23,13 @@ struct kernel_clone_args { int __user *pidfd; int __user *child_tid; int __user *parent_tid; + const char *name; int exit_signal; + u32 kthread:1; + u32 io_thread:1; + u32 user_worker:1; + u32 no_files:1; + u32 ignore_signals:1; unsigned long stack; unsigned long stack_size; unsigned long tls; @@ -31,8 +37,6 @@ struct kernel_clone_args { /* Number of elements in *set_tid */ size_t set_tid_size; int cgroup; - int io_thread; - int kthread; int idle; int (*fn)(void *); void *fn_arg; @@ -89,9 +93,12 @@ extern void exit_files(struct task_struct *); extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); +struct task_struct *copy_process(struct pid *pid, int trace, int node, + struct kernel_clone_args *args); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); -extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); +extern pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name, + unsigned long flags); extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); int kernel_wait(pid_t pid, int *stat); diff --git a/include/linux/sched/vhost_task.h b/include/linux/sched/vhost_task.h new file mode 100644 index 000000000000..6123c10b99cf --- /dev/null +++ b/include/linux/sched/vhost_task.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_VHOST_TASK_H +#define _LINUX_VHOST_TASK_H + +#include <linux/completion.h> + +struct task_struct; + +struct vhost_task { + int (*fn)(void *data); + void *data; + struct completion exited; + unsigned long flags; + struct task_struct *task; +}; + +struct vhost_task *vhost_task_create(int (*fn)(void *), void *arg, + const char *name); +void vhost_task_start(struct vhost_task *vtsk); +void vhost_task_stop(struct vhost_task *vtsk); +bool vhost_task_should_stop(struct vhost_task *vtsk); + +#endif diff --git a/include/linux/security.h b/include/linux/security.h index 5984d0d550b4..cd23221ce9e6 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -336,9 +336,6 @@ int security_inode_init_security(struct inode *inode, struct inode *dir, int security_inode_init_security_anon(struct inode *inode, const struct qstr *name, const struct inode *context_inode); -int security_old_inode_init_security(struct inode *inode, struct inode *dir, - const struct qstr *qstr, const char **name, - void **value, size_t *len); int security_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode); int security_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry); @@ -778,15 +775,6 @@ static inline int security_inode_init_security_anon(struct inode *inode, return 0; } -static inline int security_old_inode_init_security(struct inode *inode, - struct inode *dir, - const struct qstr *qstr, - const char **name, - void **value, size_t *len) -{ - return -EOPNOTSUPP; -} - static inline int security_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode) diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 52b98f9666a2..ef06a195b3c2 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -557,7 +557,7 @@ int sfp_get_module_eeprom_by_page(struct sfp_bus *bus, void sfp_upstream_start(struct sfp_bus *bus); void sfp_upstream_stop(struct sfp_bus *bus); void sfp_bus_put(struct sfp_bus *bus); -struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode); +struct sfp_bus *sfp_bus_find_fwnode(const struct fwnode_handle *fwnode); int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, const struct sfp_upstream_ops *ops); void sfp_bus_del_upstream(struct sfp_bus *bus); @@ -619,7 +619,8 @@ static inline void sfp_bus_put(struct sfp_bus *bus) { } -static inline struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode) +static inline struct sfp_bus * +sfp_bus_find_fwnode(const struct fwnode_handle *fwnode) { return NULL; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ff7ad331fb82..dbcaac8b6966 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -294,6 +294,7 @@ struct nf_bridge_info { u8 pkt_otherhost:1; u8 in_prerouting:1; u8 bridged_dnat:1; + u8 sabotage_in_done:1; __u16 frag_max_size; struct net_device *physindev; @@ -4712,7 +4713,7 @@ static inline void nf_reset_ct(struct sk_buff *skb) static inline void nf_reset_trace(struct sk_buff *skb) { -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } @@ -4732,7 +4733,7 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, dst->_nfct = src->_nfct; nf_conntrack_get(skb_nfct(src)); #endif -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) if (copy) dst->nf_trace = src->nf_trace; #endif diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 74796cd7e7a9..41c4b26fb1c1 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -102,6 +102,32 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) return lock_is_held(&ssp->dep_map); } +/* + * Annotations provide deadlock detection for SRCU. + * + * Similar to other lockdep annotations, except there is an additional + * srcu_lock_sync(), which is basically an empty *write*-side critical section, + * see lock_sync() for more information. + */ + +/* Annotates a srcu_read_lock() */ +static inline void srcu_lock_acquire(struct lockdep_map *map) +{ + lock_map_acquire_read(map); +} + +/* Annotates a srcu_read_lock() */ +static inline void srcu_lock_release(struct lockdep_map *map) +{ + lock_map_release(map); +} + +/* Annotates a synchronize_srcu() */ +static inline void srcu_lock_sync(struct lockdep_map *map) +{ + lock_map_sync(map); +} + #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) @@ -109,6 +135,10 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) return 1; } +#define srcu_lock_acquire(m) do { } while (0) +#define srcu_lock_release(m) do { } while (0) +#define srcu_lock_sync(m) do { } while (0) + #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #define SRCU_NMI_UNKNOWN 0x0 @@ -182,7 +212,7 @@ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) srcu_check_nmi_safety(ssp, false); retval = __srcu_read_lock(ssp); - rcu_lock_acquire(&(ssp)->dep_map); + srcu_lock_acquire(&(ssp)->dep_map); return retval; } @@ -254,7 +284,7 @@ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) { WARN_ON_ONCE(idx & ~0x1); srcu_check_nmi_safety(ssp, false); - rcu_lock_release(&(ssp)->dep_map); + srcu_lock_release(&(ssp)->dep_map); __srcu_read_unlock(ssp, idx); } diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 5aa5e0faf6a1..ebd72491af99 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -31,7 +31,7 @@ struct srcu_struct { void srcu_drive_gp(struct work_struct *wp); -#define __SRCU_STRUCT_INIT(name, __ignored) \ +#define __SRCU_STRUCT_INIT(name, __ignored, ___ignored) \ { \ .srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \ .srcu_cb_tail = &name.srcu_cb_head, \ @@ -44,9 +44,9 @@ void srcu_drive_gp(struct work_struct *wp); * Tree SRCU, which needs some per-CPU data. */ #define DEFINE_SRCU(name) \ - struct srcu_struct name = __SRCU_STRUCT_INIT(name, name) + struct srcu_struct name = __SRCU_STRUCT_INIT(name, name, name) #define DEFINE_STATIC_SRCU(name) \ - static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name) + static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name, name) void synchronize_srcu(struct srcu_struct *ssp); diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 558057b517b7..8f3f72480e78 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -58,9 +58,9 @@ struct srcu_node { }; /* - * Per-SRCU-domain structure, similar in function to rcu_state. + * Per-SRCU-domain structure, update-side data linked from srcu_struct. */ -struct srcu_struct { +struct srcu_usage { struct srcu_node *node; /* Combining tree. */ struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ @@ -68,7 +68,6 @@ struct srcu_struct { struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ - unsigned int srcu_idx; /* Current rdr array element. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ @@ -77,7 +76,6 @@ struct srcu_struct { unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ unsigned long srcu_n_exp_nodelay; /* # expedited no-delays in current GP phase. */ - struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ struct mutex srcu_barrier_mutex; /* Serialize barrier ops. */ @@ -89,32 +87,68 @@ struct srcu_struct { unsigned long reschedule_jiffies; unsigned long reschedule_count; struct delayed_work work; + struct srcu_struct *srcu_ssp; +}; + +/* + * Per-SRCU-domain structure, similar in function to rcu_state. + */ +struct srcu_struct { + unsigned int srcu_idx; /* Current rdr array element. */ + struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ struct lockdep_map dep_map; + struct srcu_usage *srcu_sup; /* Update-side data. */ }; -/* Values for size state variable (->srcu_size_state). */ -#define SRCU_SIZE_SMALL 0 -#define SRCU_SIZE_ALLOC 1 -#define SRCU_SIZE_WAIT_BARRIER 2 -#define SRCU_SIZE_WAIT_CALL 3 -#define SRCU_SIZE_WAIT_CBS1 4 -#define SRCU_SIZE_WAIT_CBS2 5 -#define SRCU_SIZE_WAIT_CBS3 6 -#define SRCU_SIZE_WAIT_CBS4 7 -#define SRCU_SIZE_BIG 8 +// Values for size state variable (->srcu_size_state). Once the state +// has been set to SRCU_SIZE_ALLOC, the grace-period code advances through +// this state machine one step per grace period until the SRCU_SIZE_BIG state +// is reached. Otherwise, the state machine remains in the SRCU_SIZE_SMALL +// state indefinitely. +#define SRCU_SIZE_SMALL 0 // No srcu_node combining tree, ->node == NULL +#define SRCU_SIZE_ALLOC 1 // An srcu_node tree is being allocated, initialized, + // and then referenced by ->node. It will not be used. +#define SRCU_SIZE_WAIT_BARRIER 2 // The srcu_node tree starts being used by everything + // except call_srcu(), especially by srcu_barrier(). + // By the end of this state, all CPUs and threads + // are aware of this tree's existence. +#define SRCU_SIZE_WAIT_CALL 3 // The srcu_node tree starts being used by call_srcu(). + // By the end of this state, all of the call_srcu() + // invocations that were running on a non-boot CPU + // and using the boot CPU's callback queue will have + // completed. +#define SRCU_SIZE_WAIT_CBS1 4 // Don't trust the ->srcu_have_cbs[] grace-period +#define SRCU_SIZE_WAIT_CBS2 5 // sequence elements or the ->srcu_data_have_cbs[] +#define SRCU_SIZE_WAIT_CBS3 6 // CPU-bitmask elements until all four elements of +#define SRCU_SIZE_WAIT_CBS4 7 // each array have been initialized. +#define SRCU_SIZE_BIG 8 // The srcu_node combining tree is fully initialized + // and all aspects of it are being put to use. /* Values for state variable (bottom bits of ->srcu_gp_seq). */ #define SRCU_STATE_IDLE 0 #define SRCU_STATE_SCAN1 1 #define SRCU_STATE_SCAN2 2 -#define __SRCU_STRUCT_INIT(name, pcpu_name) \ -{ \ - .sda = &pcpu_name, \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ - .srcu_gp_seq_needed = -1UL, \ - .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \ - __SRCU_DEP_MAP_INIT(name) \ +#define __SRCU_USAGE_INIT(name) \ +{ \ + .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .srcu_gp_seq_needed = -1UL, \ + .work = __DELAYED_WORK_INITIALIZER(name.work, NULL, 0), \ +} + +#define __SRCU_STRUCT_INIT_COMMON(name, usage_name) \ + .srcu_sup = &usage_name, \ + __SRCU_DEP_MAP_INIT(name) + +#define __SRCU_STRUCT_INIT_MODULE(name, usage_name) \ +{ \ + __SRCU_STRUCT_INIT_COMMON(name, usage_name) \ +} + +#define __SRCU_STRUCT_INIT(name, usage_name, pcpu_name) \ +{ \ + .sda = &pcpu_name, \ + __SRCU_STRUCT_INIT_COMMON(name, usage_name) \ } /* @@ -137,16 +171,18 @@ struct srcu_struct { * See include/linux/percpu-defs.h for the rules on per-CPU variables. */ #ifdef MODULE -# define __DEFINE_SRCU(name, is_static) \ - is_static struct srcu_struct name; \ - extern struct srcu_struct * const __srcu_struct_##name; \ - struct srcu_struct * const __srcu_struct_##name \ +# define __DEFINE_SRCU(name, is_static) \ + static struct srcu_usage name##_srcu_usage = __SRCU_USAGE_INIT(name##_srcu_usage); \ + is_static struct srcu_struct name = __SRCU_STRUCT_INIT_MODULE(name, name##_srcu_usage); \ + extern struct srcu_struct * const __srcu_struct_##name; \ + struct srcu_struct * const __srcu_struct_##name \ __section("___srcu_struct_ptrs") = &name #else -# define __DEFINE_SRCU(name, is_static) \ - static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data); \ - is_static struct srcu_struct name = \ - __SRCU_STRUCT_INIT(name, name##_srcu_data) +# define __DEFINE_SRCU(name, is_static) \ + static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data); \ + static struct srcu_usage name##_srcu_usage = __SRCU_USAGE_INIT(name##_srcu_usage); \ + is_static struct srcu_struct name = \ + __SRCU_STRUCT_INIT(name, name##_srcu_usage, name##_srcu_data) #endif #define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) #define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) diff --git a/include/linux/tick.h b/include/linux/tick.h index bfd571f18cfd..9459fef5b857 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -216,6 +216,7 @@ extern void tick_nohz_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit); extern void tick_nohz_dep_clear_signal(struct signal_struct *signal, enum tick_dep_bits bit); +extern bool tick_nohz_cpu_hotpluggable(unsigned int cpu); /* * The below are tick_nohz_[set,clear]_dep() wrappers that optimize off-cases @@ -280,6 +281,7 @@ static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { } static inline void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { } static inline void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { } +static inline bool tick_nohz_cpu_hotpluggable(unsigned int cpu) { return true; } static inline void tick_dep_set(enum tick_dep_bits bit) { } static inline void tick_dep_clear(enum tick_dep_bits bit) { } diff --git a/include/linux/uio.h b/include/linux/uio.h index 27e3fd942960..ed35f4427a0a 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -49,14 +49,35 @@ struct iov_iter { size_t iov_offset; int last_offset; }; - size_t count; + /* + * Hack alert: overlay ubuf_iovec with iovec + count, so + * that the members resolve correctly regardless of the type + * of iterator used. This means that you can use: + * + * &iter->__ubuf_iovec or iter->__iov + * + * interchangably for the user_backed cases, hence simplifying + * some of the cases that need to deal with both. + */ union { - const struct iovec *iov; - const struct kvec *kvec; - const struct bio_vec *bvec; - struct xarray *xarray; - struct pipe_inode_info *pipe; - void __user *ubuf; + /* + * This really should be a const, but we cannot do that without + * also modifying any of the zero-filling iter init functions. + * Leave it non-const for now, but it should be treated as such. + */ + struct iovec __ubuf_iovec; + struct { + union { + /* use iter_iov() to get the current vec */ + const struct iovec *__iov; + const struct kvec *kvec; + const struct bio_vec *bvec; + struct xarray *xarray; + struct pipe_inode_info *pipe; + void __user *ubuf; + }; + size_t count; + }; }; union { unsigned long nr_segs; @@ -68,6 +89,16 @@ struct iov_iter { }; }; +static inline const struct iovec *iter_iov(const struct iov_iter *iter) +{ + if (iter->iter_type == ITER_UBUF) + return (const struct iovec *) &iter->__ubuf_iovec; + return iter->__iov; +} + +#define iter_iov_addr(iter) (iter_iov(iter)->iov_base + (iter)->iov_offset) +#define iter_iov_len(iter) (iter_iov(iter)->iov_len - (iter)->iov_offset) + static inline enum iter_type iov_iter_type(const struct iov_iter *i) { return i->iter_type; @@ -143,15 +174,6 @@ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs) return ret; } -static inline struct iovec iov_iter_iovec(const struct iov_iter *iter) -{ - return (struct iovec) { - .iov_base = iter->iov->iov_base + iter->iov_offset, - .iov_len = min(iter->count, - iter->iov->iov_len - iter->iov_offset), - }; -} - size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, size_t bytes, struct iov_iter *i); void iov_iter_advance(struct iov_iter *i, size_t bytes); @@ -359,7 +381,8 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, .user_backed = true, .data_source = direction, .ubuf = buf, - .count = count + .count = count, + .nr_segs = 1 }; } /* Flags for iov_iter_get/extract_pages*() */ |