diff options
Diffstat (limited to 'include/linux')
119 files changed, 1390 insertions, 627 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 60ab50cb8930..ddacac812094 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -94,6 +94,12 @@ static inline void acpi_preset_companion(struct device *dev, ACPI_COMPANION_SET(dev, acpi_find_child_device(parent, addr, false)); } +static inline void acpi_device_clear_deps(struct device *dev) +{ + if (has_acpi_companion(dev)) + acpi_dev_clear_dependencies(ACPI_COMPANION(dev)); +} + static inline const char *acpi_dev_name(struct acpi_device *adev) { return dev_name(&adev->dev); @@ -315,6 +321,19 @@ static inline int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu, } #endif +#ifdef CONFIG_ACPI_PROCESSOR_IDLE +int acpi_processor_extract_lpi_info(acpi_handle pr_handle, + struct acpi_processor_power *pr_power, + bool strict); +#else +static inline int acpi_processor_extract_lpi_info(acpi_handle pr_handle, + struct acpi_processor_power *pr_power, + bool strict) +{ + return -ENODEV; +} +#endif + #ifdef CONFIG_ACPI_HOTPLUG_CPU /* Arch dependent functions for cpu hotplug support */ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, @@ -360,9 +379,10 @@ int acpi_gsi_to_irq (u32 gsi, unsigned int *irq); int acpi_isa_irq_to_gsi (unsigned isa_irq, u32 *gsi); typedef struct fwnode_handle *(*acpi_gsi_domain_disp_fn)(u32); +typedef acpi_handle (*acpi_gsi_handle_disp_fn)(u32); void acpi_set_irq_model(enum acpi_irq_model_id model, - acpi_gsi_domain_disp_fn fn); + acpi_gsi_domain_disp_fn fn, acpi_gsi_handle_disp_fn gsi_dep_fn); acpi_gsi_domain_disp_fn acpi_get_gsi_dispatcher(void); void acpi_set_gsi_to_irq_fallback(u32 (*)(u32)); @@ -372,6 +392,8 @@ struct irq_domain *acpi_irq_create_hierarchy(unsigned int flags, const struct irq_domain_ops *ops, void *host_data); +u32 acpi_irq_add_auto_dep(acpi_handle handle); + #ifdef CONFIG_X86_IO_APIC extern int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity); #else @@ -448,6 +470,7 @@ extern char *wmi_get_acpi_device_uid(const char *guid); #define ACPI_VIDEO_OUTPUT_SWITCHING_DMI_VIDEO 0x0800 extern char acpi_video_backlight_string[]; +extern bool acpi_dev_is_video_device(struct acpi_device *adev); extern long acpi_is_video_device(acpi_handle handle); extern void acpi_osi_setup(char *str); @@ -908,6 +931,8 @@ static inline void acpi_preset_companion(struct device *dev, { } +static inline void acpi_device_clear_deps(struct device *dev) {} + static inline const char *acpi_dev_name(struct acpi_device *adev) { return NULL; diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 17bb3374f4ca..931eaa7bbf6a 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -27,7 +27,8 @@ int iort_register_domain_token(int trans_id, phys_addr_t base, struct fwnode_handle *fw_node); void iort_deregister_domain_token(int trans_id); struct fwnode_handle *iort_find_domain_token(int trans_id); -struct fwnode_handle *iort_iwb_handle(u32 iwb_id); +acpi_handle iort_iwb_handle(u32 iwb_id); +struct fwnode_handle *iort_iwb_handle_fwnode(u32 iwb_id); #ifdef CONFIG_ACPI_IORT u32 iort_msi_map_id(struct device *dev, u32 id); diff --git a/include/linux/acpi_pmtmr.h b/include/linux/acpi_pmtmr.h index 0ded9220d379..cceed294d0b5 100644 --- a/include/linux/acpi_pmtmr.h +++ b/include/linux/acpi_pmtmr.h @@ -27,15 +27,17 @@ static inline u32 acpi_pm_read_early(void) } /** - * Register callback for suspend and resume event + * acpi_pmtmr_register_suspend_resume_callback - Register callback for + * suspend and resume event * - * @cb Callback triggered on suspend and resume - * @data Data passed with the callback + * @cb: Callback triggered on suspend and resume + * @data: Data passed with the callback */ void acpi_pmtmr_register_suspend_resume_callback(void (*cb)(void *data, bool suspend), void *data); /** - * Remove registered callback for suspend and resume event + * acpi_pmtmr_unregister_suspend_resume_callback - Remove registered callback + * for suspend and resume event */ void acpi_pmtmr_unregister_suspend_resume_callback(void); diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 068ba2e77c5d..6ed9f82e639f 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -134,6 +134,8 @@ static inline bool mem_alloc_profiling_enabled(void) &mem_alloc_profiling_key); } +bool mem_alloc_profiling_permanently_disabled(void); + static inline struct alloc_tag_counters alloc_tag_read(struct alloc_tag *tag) { struct alloc_tag_counters v = { 0, 0 }; @@ -239,6 +241,7 @@ static inline bool alloc_tag_is_inaccurate(struct alloc_tag *tag) #define DEFINE_ALLOC_TAG(_alloc_tag) static inline bool mem_alloc_profiling_enabled(void) { return false; } +static inline bool mem_alloc_profiling_permanently_disabled(void) { return true; } static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) {} static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) {} diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index 17eca3dfc59e..e71d83ee0aef 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -421,6 +421,13 @@ struct ffa_mem_region { #define FFA_EMAD_HAS_IMPDEF_FIELD(version) ((version) >= FFA_VERSION_1_2) #define FFA_MEM_REGION_HAS_EP_MEM_OFFSET(version) ((version) > FFA_VERSION_1_0) +/* The layout changed from FFA_VERSION_1_0 and the region includes an + * ep_mem_offset. + */ +#define FFA_MEM_REGION_SZ(version) (!FFA_MEM_REGION_HAS_EP_MEM_OFFSET((version)) ?\ + offsetof(struct ffa_mem_region, ep_mem_offset) :\ + sizeof(struct ffa_mem_region)) + static inline u32 ffa_emad_size_get(u32 ffa_version) { u32 sz; @@ -445,7 +452,7 @@ ffa_mem_desc_offset(struct ffa_mem_region *buf, int count, u32 ffa_version) if (!FFA_MEM_REGION_HAS_EP_MEM_OFFSET(ffa_version)) offset += offsetof(struct ffa_mem_region, ep_mem_offset); else - offset += sizeof(struct ffa_mem_region); + offset += buf->ep_mem_offset; return offset; } diff --git a/include/linux/arm_sdei.h b/include/linux/arm_sdei.h index f652a5028b59..b9dc21c241be 100644 --- a/include/linux/arm_sdei.h +++ b/include/linux/arm_sdei.h @@ -37,6 +37,15 @@ int sdei_event_unregister(u32 event_num); int sdei_event_enable(u32 event_num); int sdei_event_disable(u32 event_num); +/* + * Signal the software-signalled event (event 0) to another PE, NMI-like. + * @mpidr is the target's MPIDR affinity. + */ +int sdei_event_signal(u32 event_num, u64 mpidr); + +/* Was SDEI firmware probed and usable? */ +bool sdei_is_present(void); + /* GHES register/unregister helpers */ int sdei_register_ghes(struct ghes *ghes, sdei_event_callback *normal_cb, sdei_event_callback *critical_cb); diff --git a/include/linux/ata.h b/include/linux/ata.h index 8fd48bcb2a46..7daad4cad985 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -762,8 +762,7 @@ static inline bool ata_id_sense_reporting_enabled(const u16 *id) return id[ATA_ID_COMMAND_SET_4] & BIT(6); } -/** - * +/* * Word: 206 - SCT Command Transport * 15:12 - Vendor Specific * 11:6 - Reserved @@ -810,8 +809,9 @@ static inline bool ata_id_sct_supported(const u16 *id) * * The practical impact of this is that ata_id_major_version cannot * reliably report on drives below ATA3. + * + * Returns: major version of ATA drive level or %0 if unknown */ - static inline unsigned int ata_id_major_version(const u16 *id) { unsigned int mver; diff --git a/include/linux/binfmt_misc.h b/include/linux/binfmt_misc.h new file mode 100644 index 000000000000..8045b10dd3e5 --- /dev/null +++ b/include/linux/binfmt_misc.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_BINFMT_MISC_H +#define _LINUX_BINFMT_MISC_H + +#include <linux/types.h> + +struct bpf_prog; +struct file; +struct linux_binprm; +struct ucounts; +struct user_namespace; + +#define BINFMT_MISC_OPS_NAME_MAX 16 + +/* Longest name a 'B' entry can bind an interpreter under. */ +#define BINFMT_MISC_INTERP_NAME_MAX 32 + +/* Most interpreters one entry can bind. */ +#define BINFMT_MISC_INTERP_MAX 100 + +/** + * struct binfmt_misc_interp - an interpreter an entry was registered with + * @list: link in the entry's list, in registration order + * @file: the file, opened at registration and never resolved again + * @ucounts: the UCOUNT_BINFMT_MISC_INTERPRETERS charge the binding took + * @path: the path it was registered under, used as the name the interpreter + * runs under; stored after @name in the same allocation + * @name: the name the load program selects it by; empty for the fixed + * interpreter of a static 'F' entry + * + * Owned by the entry and living exactly as long as it does. The list head + * is handed to the handler's load program for the duration of one exec, + * which picks one with bpf_binprm_select_interp(). + */ +struct binfmt_misc_interp { + struct list_head list; + struct file *file; + struct ucounts *ucounts; + const char *path; + char name[]; +}; + +const struct binfmt_misc_interp * +binfmt_misc_find_interp(const struct list_head *interps, const char *name); + +/** + * enum bpf_binprm_flags - per-exec invocation flags a load program can request + * @BPF_BINPRM_PRESERVE_ARGV0: keep the caller's argv[0] (like the 'P' flag) + * @BPF_BINPRM_CREDENTIALS: compute credentials from the binary; implies execfd + * (like the 'C' flag) + * @BPF_BINPRM_EXECFD: pass the binary via AT_EXECFD (like the 'O' flag) + * @BPF_BINPRM_TRANSPARENT: leave argv untouched, the interpreter takes the + * binary from AT_EXECFD (like the 'T' flag); implies + * execfd, excludes preserve-argv0 + * @BPF_BINPRM_LOADER: substitute the interpreter for the binary's PT_INTERP + * and run the binary as a native exec (like the 'L' + * flag); excludes every other flag + * + * Set from a load program with bpf_binprm_set_flags(). Unlike a static entry, + * a bpf handler chooses these per exec rather than once at registration. + */ +enum bpf_binprm_flags { + BPF_BINPRM_PRESERVE_ARGV0 = (1ULL << 0), + BPF_BINPRM_CREDENTIALS = (1ULL << 1), + BPF_BINPRM_EXECFD = (1ULL << 2), + BPF_BINPRM_TRANSPARENT = (1ULL << 3), + BPF_BINPRM_LOADER = (1ULL << 4), +}; + +/** + * struct binfmt_misc_ops - bpf-backed binary type handler + * @match: decide whether the handler applies to @bprm; consulted from the + * entry lookup walk like static magic and extension matching, in + * registration order with first-match-wins semantics; sleepable, + * so it can read the binary to decide, but the verifier rejects + * the interpreter selection kfuncs in it + * @load: select an interpreter for the matched @bprm via + * bpf_binprm_set_interp(), or one the entry bound via + * bpf_binprm_select_interp(), and return zero; a match is + * committed, so a failure fails the exec instead of falling + * through to later entries; -ENOEXEC does not fail the exec but + * moves on to the remaining binary formats + * @name: name that 'B' entries reference the handler by + */ +struct binfmt_misc_ops { + bool (*match)(struct linux_binprm *bprm); + int (*load)(struct linux_binprm *bprm); + char name[BINFMT_MISC_OPS_NAME_MAX]; +}; + +#ifdef CONFIG_BINFMT_MISC_BPF +const struct binfmt_misc_ops *binfmt_misc_get_ops(struct user_namespace *user_ns, + const char *name); +void binfmt_misc_put_ops(const struct binfmt_misc_ops *ops); +bool bpf_prog_is_binfmt_misc_ops(const struct bpf_prog *prog); +#else +static inline const struct binfmt_misc_ops * +binfmt_misc_get_ops(struct user_namespace *user_ns, const char *name) +{ + return NULL; +} + +static inline void binfmt_misc_put_ops(const struct binfmt_misc_ops *ops) +{ +} + +static inline bool bpf_prog_is_binfmt_misc_ops(const struct bpf_prog *prog) +{ + return false; +} +#endif /* CONFIG_BINFMT_MISC_BPF */ + +#endif /* _LINUX_BINFMT_MISC_H */ diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 2c77e383e737..f686a37f7a0a 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -12,6 +12,16 @@ struct coredump_params; #define CORENAME_MAX_SIZE 128 +/* Interpreter selection staged by a bpf binfmt_misc handler. */ +struct binfmt_misc_bpf { + /* interpreters the matched entry bound, selectable by name */ + const struct list_head *bpf_interps; + const char *bpf_interp; /* interpreter selected by a bpf handler */ + struct file *bpf_interp_file; /* the bound interpreter it selected */ + const char *bpf_interp_arg; /* interpreter argument from a bpf handler */ + u64 bpf_flags; /* enum bpf_binprm_flags from a bpf handler */ +}; + /* * This structure is used to hold the arguments that are used when loading binaries. */ @@ -55,6 +65,7 @@ struct linux_binprm { is_check:1; struct file *executable; /* Executable to pass to the interpreter */ struct file *interpreter; + struct file *loader; struct file *file; struct cred *cred; /* new credentials */ int unsafe; /* how unsafe this exec is (mask of LSM_UNSAFE_*) */ @@ -65,6 +76,7 @@ struct linux_binprm { of the time same as filename, but could be different for binfmt_{misc,script} */ const char *fdpath; /* generated filename for execveat */ + struct binfmt_misc_bpf; /* bpf handler interpreter selection */ unsigned interp_flags; int execfd; /* File descriptor of the executable */ unsigned long exec; @@ -85,6 +97,28 @@ struct linux_binprm { #define BINPRM_FLAGS_PRESERVE_ARGV0_BIT 3 #define BINPRM_FLAGS_PRESERVE_ARGV0 (1 << BINPRM_FLAGS_PRESERVE_ARGV0_BIT) +/* binfmt_misc dispatched to the interpreter transparently */ +#define BINPRM_FLAGS_TRANSPARENT_INTERP_BIT 4 +#define BINPRM_FLAGS_TRANSPARENT_INTERP (1 << BINPRM_FLAGS_TRANSPARENT_INTERP_BIT) + +/** + * bprm_at_flags - the AT_FLAGS this invocation implies + * @bprm: binary that is being executed + * + * Tell the program on the receiving end which dispatch contract it got. + * + * Return: the AT_FLAGS value for this exec + */ +static inline unsigned long bprm_at_flags(const struct linux_binprm *bprm) +{ + /* Transparency preserves the whole argv, argv[0] included. */ + if (bprm->interp_flags & BINPRM_FLAGS_TRANSPARENT_INTERP) + return AT_FLAGS_TRANSPARENT_INTERP; + if (bprm->interp_flags & BINPRM_FLAGS_PRESERVE_ARGV0) + return AT_FLAGS_PRESERVE_ARGV0; + return 0; +} + /* * This structure defines the functions that are used to load the binary formats that * linux accepts. @@ -101,8 +135,8 @@ struct linux_binfmt { #if IS_ENABLED(CONFIG_BINFMT_MISC) struct binfmt_misc { - struct list_head entries; - rwlock_t entries_lock; + struct hlist_head entries; + spinlock_t entries_lock; bool enabled; } __randomize_layout; @@ -129,6 +163,8 @@ extern int begin_new_exec(struct linux_binprm * bprm); extern void setup_new_exec(struct linux_binprm * bprm); extern void finalize_exec(struct linux_binprm *bprm); extern void would_dump(struct linux_binprm *, struct file *); +struct file *bprm_open_interpreter(struct linux_binprm *bprm, const char *path); +void bprm_drop_loader(struct linux_binprm *bprm); extern int suid_dumpable; diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h index f7c3cb4a342f..938ff536838c 100644 --- a/include/linux/blk-crypto.h +++ b/include/linux/blk-crypto.h @@ -68,6 +68,15 @@ enum blk_crypto_key_type { */ #define BLK_CRYPTO_SW_SECRET_SIZE 32 +/* Flags for blk_crypto_config::flags: */ + +/* + * If set, inline encryption hardware will be used if available. + * If unset, CPU-based encryption will always be used (requires + * CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) + */ +#define BLK_CRYPTO_CFG_ALLOW_HW (1 << 0) + /** * struct blk_crypto_config - an inline encryption key's crypto configuration * @crypto_mode: encryption algorithm this key is for @@ -77,12 +86,14 @@ enum blk_crypto_key_type { * filesystem block size or the disk sector size. * @dun_bytes: the maximum number of bytes of DUN used when using this key * @key_type: the type of this key -- either raw or hardware-wrapped + * @flags: BLK_CRYPTO_CFG_* flags */ struct blk_crypto_config { enum blk_crypto_mode_num crypto_mode; unsigned int data_unit_size; unsigned int dun_bytes; enum blk_crypto_key_type key_type; + int flags; }; /** @@ -150,7 +161,7 @@ int blk_crypto_init_key(struct blk_crypto_key *blk_key, enum blk_crypto_key_type key_type, enum blk_crypto_mode_num crypto_mode, unsigned int dun_bytes, - unsigned int data_unit_size); + unsigned int data_unit_size, int flags); int blk_crypto_start_using_key(struct block_device *bdev, const struct blk_crypto_key *key); @@ -160,8 +171,6 @@ void blk_crypto_evict_key(struct block_device *bdev, bool blk_crypto_config_supported_natively(struct block_device *bdev, const struct blk_crypto_config *cfg); -bool blk_crypto_config_supported(struct block_device *bdev, - const struct blk_crypto_config *cfg); int blk_crypto_derive_sw_secret(struct block_device *bdev, const u8 *eph_key, size_t eph_key_size, diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 8808ee76e73c..5a725a0cd35f 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -66,7 +66,7 @@ struct block_device { int bd_holders; struct kobject *bd_holder_dir; - atomic_t bd_fsfreeze_count; /* number of freeze requests */ + atomic_t bd_fsfreeze_count; /* >0 freeze requests, <0 freeze deniers */ struct mutex bd_fsfreeze_mutex; /* serialize freeze/thaw */ struct partition_meta_info *bd_meta_info; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9213a5716f95..dbb549cdfb77 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -126,8 +126,6 @@ struct blk_integrity { unsigned char pi_tuple_size; }; -typedef unsigned int __bitwise blk_mode_t; - /* open for reading */ #define BLK_OPEN_READ ((__force blk_mode_t)(1 << 0)) /* open for writing */ @@ -1771,13 +1769,6 @@ struct blk_holder_ops { }; /* - * For filesystems using @fs_holder_ops, the @holder argument passed to - * helpers used to open and claim block devices via - * bd_prepare_to_claim() must point to a superblock. - */ -extern const struct blk_holder_ops fs_holder_ops; - -/* * Return the correct open flags for blkdev_get_by_* for super block flags * as stored in sb->s_flags. */ @@ -1837,7 +1828,10 @@ static inline int early_lookup_bdev(const char *pathname, dev_t *dev) int bdev_freeze(struct block_device *bdev); int bdev_thaw(struct block_device *bdev); +int bdev_deny_freeze(struct block_device *bdev); +void bdev_allow_freeze(struct block_device *bdev); void bdev_fput(struct file *bdev_file); +void bdev_yield_claim(struct file *bdev_file); struct io_comp_batch { struct rq_list req_list; diff --git a/include/linux/bnge/hsi.h b/include/linux/bnge/hsi.h index 8ea13d5407ee..1f7bd96415a5 100644 --- a/include/linux/bnge/hsi.h +++ b/include/linux/bnge/hsi.h @@ -8317,8 +8317,7 @@ struct hwrm_ring_alloc_output { __le16 req_type; __le16 seq_id; __le16 resp_len; - __le16 ring_id; - __le16 logical_ring_id; + __le32 ring_id; u8 push_buffer_index; #define RING_ALLOC_RESP_PUSH_BUFFER_INDEX_PING_BUFFER 0x0UL #define RING_ALLOC_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER 0x1UL @@ -8345,10 +8344,10 @@ struct hwrm_ring_free_input { u8 flags; #define RING_FREE_REQ_FLAGS_VIRTIO_RING_VALID 0x1UL #define RING_FREE_REQ_FLAGS_LAST RING_FREE_REQ_FLAGS_VIRTIO_RING_VALID - __le16 ring_id; + __le16 unused_1; __le32 prod_idx; __le32 opaque; - __le32 unused_1; + __le32 ring_id; }; /* hwrm_ring_free_output (size:128b/16B) */ diff --git a/include/linux/btf.h b/include/linux/btf.h index 240401d9b25b..c09b7994de4e 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -578,6 +578,7 @@ const char *btf_str_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); u32 *btf_kfunc_flags(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_prog *prog); +int btf_kfunc_check_flag(const struct btf *btf, u32 kfunc_btf_id, u32 flag); bool btf_kfunc_is_allowed(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_prog *prog); u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_prog *prog); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 8b23bc9a244c..fd2c7115c054 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -210,10 +210,6 @@ void bh_end_async_write(struct bio *bio); /* Things to do with metadata buffers list */ void mmb_mark_buffer_dirty(struct buffer_head *bh, struct mapping_metadata_bhs *mmb); -int mmb_fsync_noflush(struct file *file, struct mapping_metadata_bhs *mmb, - loff_t start, loff_t end, bool datasync); -int mmb_fsync(struct file *file, struct mapping_metadata_bhs *mmb, - loff_t start, loff_t end, bool datasync); void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len); static inline void clean_bdev_bh_alias(struct buffer_head *bh) diff --git a/include/linux/can/dev/peak_canfd.h b/include/linux/can/dev/peak_canfd.h index d3788a3d0942..056e0efa649f 100644 --- a/include/linux/can/dev/peak_canfd.h +++ b/include/linux/can/dev/peak_canfd.h @@ -3,7 +3,7 @@ * CAN driver for PEAK System micro-CAN based adapters * * Copyright (C) 2003-2025 PEAK System-Technik GmbH - * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com> + * Author: Stéphane Grosjean <s.grosjean@peak-system.fr> */ #ifndef PUCAN_H #define PUCAN_H diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index ae9d1ce4f49c..35ce665edfd8 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -379,6 +379,7 @@ struct cpufreq_driver { void (*adjust_perf)(struct cpufreq_policy *policy, unsigned long min_perf, unsigned long target_perf, + unsigned long max_perf, unsigned long capacity); /* @@ -624,6 +625,7 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy, void cpufreq_driver_adjust_perf(struct cpufreq_policy *policy, unsigned long min_perf, unsigned long target_perf, + unsigned long max_perf, unsigned long capacity); bool cpufreq_driver_has_adjust_perf(void); int cpufreq_driver_target(struct cpufreq_policy *policy, diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 0fb3a2a62eb0..feb32949aeea 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -180,7 +180,6 @@ enum cpuhp_state { CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, CPUHP_AP_ARM_XEN_RUNSTATE_STARTING, - CPUHP_AP_ARM_CORESIGHT_CTI_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_SMPCFD_DYING, CPUHP_AP_HRTIMERS_DYING, diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 65d76a38974b..9db2d4fcead1 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -80,6 +80,7 @@ extern void lockdep_assert_cpuset_lock_held(void); extern void cpuset_cpus_allowed_locked(struct task_struct *p, struct cpumask *mask); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern bool cpuset_cpus_allowed_fallback(struct task_struct *p); +extern int cpuset_num_cpus(struct cgroup *cgroup); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); @@ -216,6 +217,11 @@ static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p) return false; } +static inline int cpuset_num_cpus(struct cgroup *cgroup) +{ + return num_online_cpus(); +} + static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) { return node_possible_map; diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index c1dee3f971a9..bc087124cd78 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -59,6 +59,9 @@ extern int crash_exclude_mem_range(struct crash_mem *mem, unsigned long long mend); extern int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, void **addr, unsigned long *sz); +extern int crash_prepare_headers(int need_kernel_map, void **addr, + unsigned long *sz, unsigned long *nr_mem_ranges); +extern int crash_exclude_core_ranges(struct crash_mem **cmem); struct kimage; struct kexec_segment; @@ -76,6 +79,12 @@ int kexec_should_crash(struct task_struct *p); int kexec_crash_loaded(void); void crash_save_cpu(struct pt_regs *regs, int cpu); extern int kimage_crash_copy_vmcoreinfo(struct kimage *image); +extern unsigned int arch_get_system_nr_ranges(void); +extern int arch_crash_populate_cmem(struct crash_mem *cmem); +extern int arch_crash_exclude_ranges(struct crash_mem *cmem); +extern int arch_crash_exclude_mem_range(struct crash_mem **mem, + unsigned long long mstart, + unsigned long long mend); #else /* !CONFIG_CRASH_DUMP*/ struct pt_regs; diff --git a/include/linux/crash_reserve.h b/include/linux/crash_reserve.h index f0dc03d94ca2..30864d90d7f5 100644 --- a/include/linux/crash_reserve.h +++ b/include/linux/crash_reserve.h @@ -14,9 +14,11 @@ extern struct resource crashk_res; extern struct resource crashk_low_res; extern struct range crashk_cma_ranges[]; + +#define CRASHK_CMA_RANGES_MAX 4 #if defined(CONFIG_CMA) && defined(CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION) #define CRASHKERNEL_CMA -#define CRASHKERNEL_CMA_RANGES_MAX 4 +#define CRASHKERNEL_CMA_RANGES_MAX (CRASHK_CMA_RANGES_MAX) extern int crashk_cma_cnt; #else #define crashk_cma_cnt 0 diff --git a/include/linux/damon.h b/include/linux/damon.h index 02ac34537df9..cfbbf8ba28f6 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -1,8 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * DAMON api - * - * Author: SeongJae Park <sj@kernel.org> */ #ifndef _DAMON_H_ diff --git a/include/linux/delay.h b/include/linux/delay.h index 68b2a69dd24d..82409e55b6ae 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -17,6 +17,8 @@ extern unsigned long loops_per_jiffy; #include <asm/delay.h> +bool delay_read_timer(unsigned long *t); + /* * Using udelay() for intervals greater than a few milliseconds can * risk overflow for high loops_per_jiffy (high bogomips) machines. The diff --git a/include/linux/device.h b/include/linux/device.h index 7b2baffdd2f5..aee79fd6b32b 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -99,7 +99,9 @@ struct device_type { * struct device_attribute - Interface for exporting device attributes. * @attr: sysfs attribute definition. * @show: Show handler. + * @show_const: Show handler (read-only). * @store: Store handler. + * @store_const: Store handler (read-only). */ struct device_attribute { struct attribute attr; diff --git a/include/linux/dibs.h b/include/linux/dibs.h index c75607f8a5cf..d3e0777f25ae 100644 --- a/include/linux/dibs.h +++ b/include/linux/dibs.h @@ -439,7 +439,7 @@ static inline void *dibs_get_priv(struct dibs_dev *dev, /** * dibs_dev_alloc() - allocate and reference device structure * - * The following fields will be valid upon successful return: dev + * The following fields will be valid upon successful return: dev, lock * NOTE: Use put_device(dibs_get_dev(@dibs)) to give up your reference instead * of freeing @dibs @dev directly once you have successfully called this * function. diff --git a/include/linux/dma/qcom_bam_dma.h b/include/linux/dma/qcom_bam_dma.h index 68fc0e643b1b..d9d07a9ab313 100644 --- a/include/linux/dma/qcom_bam_dma.h +++ b/include/linux/dma/qcom_bam_dma.h @@ -13,9 +13,12 @@ * supported by BAM DMA Engine. * * @cmd_and_addr - upper 8 bits command and lower 24 bits register address. - * @data - for write command: content to be written into peripheral register. - * for read command: dest addr to write peripheral register value. - * @mask - register mask. + * @data - For write command: content to be written into peripheral register. + * For read command: lower 32 bits of destination address. + * @mask - For write command: register write mask. + * For read command on BAM v1.6.0+: upper 4 bits of destination address. + * For read command on BAM < v1.6.0: ignored by hardware. + * Setting to 0 ensures 32-bit addressing compatibility. * @reserved - for future usage. * */ @@ -42,6 +45,10 @@ enum bam_command_type { * @addr: target address * @cmd: BAM command * @data: actual data for write and dest addr for read in le32 + * + * For BAM v1.6.0+, the mask field behavior depends on command type: + * - Write commands: mask = write mask (typically 0xffffffff) + * - Read commands: mask = upper 4 bits of destination address (0 for 32-bit) */ static inline void bam_prep_ce_le32(struct bam_cmd_element *bam_ce, u32 addr, @@ -50,7 +57,11 @@ bam_prep_ce_le32(struct bam_cmd_element *bam_ce, u32 addr, bam_ce->cmd_and_addr = cpu_to_le32((addr & 0xffffff) | ((cmd & 0xff) << 24)); bam_ce->data = data; - bam_ce->mask = cpu_to_le32(0xffffffff); + if (cmd == BAM_READ_COMMAND) + bam_ce->mask = cpu_to_le32(0x0); /* 32-bit addressing */ + else + bam_ce->mask = cpu_to_le32(0xffffffff); /* Write mask */ + bam_ce->reserved = 0; } /* @@ -60,7 +71,7 @@ bam_prep_ce_le32(struct bam_cmd_element *bam_ce, u32 addr, * @bam_ce: BAM command element * @addr: target address * @cmd: BAM command - * @data: actual data for write and dest addr for read + * @data: actual data for write and destination address for read */ static inline void bam_prep_ce(struct bam_cmd_element *bam_ce, u32 addr, diff --git a/include/linux/efs_vh.h b/include/linux/efs_vh.h deleted file mode 100644 index 206c5270f7b8..000000000000 --- a/include/linux/efs_vh.h +++ /dev/null @@ -1,54 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * efs_vh.h - * - * Copyright (c) 1999 Al Smith - * - * Portions derived from IRIX header files (c) 1985 MIPS Computer Systems, Inc. - */ - -#ifndef __EFS_VH_H__ -#define __EFS_VH_H__ - -#define VHMAGIC 0xbe5a941 /* volume header magic number */ -#define NPARTAB 16 /* 16 unix partitions */ -#define NVDIR 15 /* max of 15 directory entries */ -#define BFNAMESIZE 16 /* max 16 chars in boot file name */ -#define VDNAMESIZE 8 - -struct volume_directory { - char vd_name[VDNAMESIZE]; /* name */ - __be32 vd_lbn; /* logical block number */ - __be32 vd_nbytes; /* file length in bytes */ -}; - -struct partition_table { /* one per logical partition */ - __be32 pt_nblks; /* # of logical blks in partition */ - __be32 pt_firstlbn; /* first lbn of partition */ - __be32 pt_type; /* use of partition */ -}; - -struct volume_header { - __be32 vh_magic; /* identifies volume header */ - __be16 vh_rootpt; /* root partition number */ - __be16 vh_swappt; /* swap partition number */ - char vh_bootfile[BFNAMESIZE]; /* name of file to boot */ - char pad[48]; /* device param space */ - struct volume_directory vh_vd[NVDIR]; /* other vol hdr contents */ - struct partition_table vh_pt[NPARTAB]; /* device partition layout */ - __be32 vh_csum; /* volume header checksum */ - __be32 vh_fill; /* fill out to 512 bytes */ -}; - -/* partition type sysv is used for EFS format CD-ROM partitions */ -#define SGI_SYSV 0x05 -#define SGI_EFS 0x07 -#define IS_EFS(x) (((x) == SGI_EFS) || ((x) == SGI_SYSV)) - -struct pt_types { - int pt_type; - char *pt_name; -}; - -#endif /* __EFS_VH_H__ */ - diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 416a3352261f..6574b7183c01 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -6,9 +6,11 @@ #include <linux/irq-entry-common.h> #include <linux/livepatch.h> #include <linux/ptrace.h> +#include <linux/randomize_kstack.h> #include <linux/resume_user_mode.h> #include <linux/seccomp.h> #include <linux/sched.h> +#include <linux/syscall_user_dispatch.h> #include <asm/entry-common.h> #include <asm/syscall.h> @@ -18,7 +20,7 @@ #endif /* - * SYSCALL_WORK flags handled in syscall_enter_from_user_mode() + * SYSCALL_WORK flags handled in syscall_enter_from_user_mode_work() */ #define SYSCALL_WORK_ENTER (SYSCALL_WORK_SECCOMP | \ SYSCALL_WORK_SYSCALL_TRACEPOINT | \ @@ -37,42 +39,32 @@ SYSCALL_WORK_SYSCALL_EXIT_TRAP) /** - * arch_ptrace_report_syscall_entry - Architecture specific ptrace_report_syscall_entry() wrapper + * arch_ptrace_report_syscall_permit_entry - Architecture specific wrapper for + * ptrace_report_syscall_permit_entry() * @regs: Pointer to the register state at syscall entry * - * Invoked from syscall_trace_enter() to wrap ptrace_report_syscall_entry(). + * Invoked from syscall_trace_enter() to wrap ptrace_report_syscall_permit_entry(). * - * This allows architecture specific ptrace_report_syscall_entry() + * This allows architecture specific ptrace_report_syscall_permit_entry() * implementations. If not defined by the architecture this falls back to - * to ptrace_report_syscall_entry(). + * to ptrace_report_syscall_permit_entry(). */ -static __always_inline int arch_ptrace_report_syscall_entry(struct pt_regs *regs); +static __always_inline bool arch_ptrace_report_syscall_permit_entry(struct pt_regs *regs); -#ifndef arch_ptrace_report_syscall_entry -static __always_inline int arch_ptrace_report_syscall_entry(struct pt_regs *regs) +#ifndef arch_ptrace_report_syscall_permit_entry +static __always_inline bool arch_ptrace_report_syscall_permit_entry(struct pt_regs *regs) { - return ptrace_report_syscall_entry(regs); + return ptrace_report_syscall_permit_entry(regs); } #endif -bool syscall_user_dispatch(struct pt_regs *regs); -long trace_syscall_enter(struct pt_regs *regs, long syscall); +void trace_syscall_enter(struct pt_regs *regs); void trace_syscall_exit(struct pt_regs *regs, long ret); +void syscall_enter_audit(struct pt_regs *regs); -static inline void syscall_enter_audit(struct pt_regs *regs, long syscall) +static __always_inline long syscall_trace_enter(struct pt_regs *regs, unsigned long work, + long syscall) { - if (unlikely(audit_context())) { - unsigned long args[6]; - - syscall_get_arguments(current, regs, args); - audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]); - } -} - -static __always_inline long syscall_trace_enter(struct pt_regs *regs, unsigned long work) -{ - long syscall, ret = 0; - /* * Handle Syscall User Dispatch. This must comes first, since * the ABI here can be something that doesn't make sense for @@ -80,7 +72,7 @@ static __always_inline long syscall_trace_enter(struct pt_regs *regs, unsigned l */ if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) { if (syscall_user_dispatch(regs)) - return -1L; + return false; } /* @@ -89,31 +81,31 @@ static __always_inline long syscall_trace_enter(struct pt_regs *regs, unsigned l * through hrtimer_interrupt(). */ if (work & SYSCALL_WORK_SYSCALL_RSEQ_SLICE) - rseq_syscall_enter_work(syscall_get_nr(current, regs)); + rseq_syscall_enter_work(syscall); /* Handle ptrace */ if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) { - ret = arch_ptrace_report_syscall_entry(regs); - if (ret || (work & SYSCALL_WORK_SYSCALL_EMU)) - return -1L; + if (!arch_ptrace_report_syscall_permit_entry(regs) || + (work & SYSCALL_WORK_SYSCALL_EMU)) + return false; + + /* ptrace might have changed work flags */ + work = READ_ONCE(current_thread_info()->syscall_work); } /* Do seccomp after ptrace, to catch any tracer changes. */ if (work & SYSCALL_WORK_SECCOMP) { - ret = __secure_computing(); - if (ret == -1L) - return ret; + if (!__seccomp_permit_syscall()) + return false; } - /* Either of the above might have changed the syscall number */ - syscall = syscall_get_nr(current, regs); - if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) - syscall = trace_syscall_enter(regs, syscall); + trace_syscall_enter(regs); - syscall_enter_audit(regs, syscall); + if (unlikely(audit_context())) + syscall_enter_audit(regs); - return ret ? : syscall; + return true; } /** @@ -122,36 +114,63 @@ static __always_inline long syscall_trace_enter(struct pt_regs *regs, unsigned l * @regs: Pointer to currents pt_regs * @syscall: The syscall number * - * Invoked from architecture specific syscall entry code with interrupts - * enabled after invoking enter_from_user_mode(), enabling interrupts and - * extra architecture specific work. + * Invoked from architecture specific syscall entry code with interrupts enabled + * after invoking enter_from_user_mode(), enabling interrupts and extra + * architecture specific work with the syscall return value preset to -ENOSYS. * - * Returns: The original or a modified syscall number + * Returns: True if the syscall should be invoked, False otherwise. * - * If the returned syscall number is -1 then the syscall should be - * skipped. In this case the caller may invoke syscall_set_error() or - * syscall_set_return_value() first. If neither of those are called and -1 - * is returned, then the syscall will fail with ENOSYS. + * If the return value is false, the caller must skip the syscall and leave the + * syscall return value unmodified as it might have been set by one of the entry + * work functions. * * It handles the following work items: * * 1) syscall_work flag dependent invocations of - * ptrace_report_syscall_entry(), __secure_computing(), trace_sys_enter() + * ptrace_report_syscall_permit_entry(), __seccomp_permit_syscall(), trace_sys_enter() * 2) Invocation of audit_syscall_entry() */ -static __always_inline long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall) +static __always_inline bool syscall_enter_from_user_mode_work(struct pt_regs *regs, long *syscall) { unsigned long work = READ_ONCE(current_thread_info()->syscall_work); - if (work & SYSCALL_WORK_ENTER) - syscall = syscall_trace_enter(regs, work); + if (!(work & SYSCALL_WORK_ENTER)) + return true; + + if (unlikely(!syscall_trace_enter(regs, work, *syscall))) + return false; - return syscall; + /* Reread the syscall number as it might have been modified */ + *syscall = syscall_get_nr(current, regs); + + return true; } /** - * syscall_enter_from_user_mode - Establish state and check and handle work - * before invoking a syscall + * enter_from_user_mode_randomize_stack - Establish state and add stack randomization + * before invoking syscall_enter_from_user_mode_work() + * @regs: Pointer to currents pt_regs + * + * Invoked from architecture specific syscall entry code with interrupts + * disabled. The calling code has to be non-instrumentable. When the function + * returns all state is correct, interrupts are still disabled and the + * subsequent functions can be instrumented. + * + * Implemented as a macro so that the stack randomization is effective + * throughout the function in which it is invoked. An inline would only make it + * effective in the scope of the inline function. + */ +#define enter_from_user_mode_randomize_stack(regs) \ +do { \ + enter_from_user_mode(regs); \ + instrumentation_begin(); \ + add_random_kstack_offset_irqsoff(); \ + instrumentation_end(); \ +} while (0) + +/** + * syscall_enter_from_user_mode_randomize_stack - Establish state and check and handle work + * before invoking a syscall * @regs: Pointer to currents pt_regs * @syscall: The syscall number * @@ -160,31 +179,32 @@ static __always_inline long syscall_enter_from_user_mode_work(struct pt_regs *re * function returns all state is correct, interrupts are enabled and the * subsequent functions can be instrumented. * - * This is the combination of enter_from_user_mode() and + * This is the combination of enter_from_user_mode_randomize_stack() and * syscall_enter_from_user_mode_work() to be used when there is no * architecture specific work to be done between the two. * * Returns: The original or a modified syscall number. See * syscall_enter_from_user_mode_work() for further explanation. + * + * Implemented as a macro to make stack randomization effective in the calling + * scope. */ -static __always_inline long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall) -{ - long ret; - - enter_from_user_mode(regs); - - instrumentation_begin(); - local_irq_enable(); - ret = syscall_enter_from_user_mode_work(regs, syscall); - instrumentation_end(); - - return ret; -} +#define syscall_enter_from_user_mode_randomize_stack(regs, syscall) \ +({ \ + enter_from_user_mode_randomize_stack(regs); \ + \ + instrumentation_begin(); \ + local_irq_enable(); \ + long _ret = syscall_enter_from_user_mode_work(regs, syscall); \ + instrumentation_end(); \ + \ + _ret; \ +}) /* - * If SYSCALL_EMU is set, then the only reason to report is when - * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall - * instruction has been already reported in syscall_enter_from_user_mode(). + * If SYSCALL_EMU is set, then the only reason to report is when SINGLESTEP is + * set (i.e. PTRACE_SYSEMU_SINGLESTEP). This syscall instruction has been + * already reported in syscall_enter_from_user_mode_work(). */ static __always_inline bool report_single_step(unsigned long work) { @@ -232,10 +252,8 @@ static __always_inline void syscall_exit_work(struct pt_regs *regs, unsigned lon * of these syscalls is unknown. */ if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) { - if (unlikely(current->syscall_dispatch.on_dispatch)) { - current->syscall_dispatch.on_dispatch = false; + if (syscall_user_dispatch_clear_on_dispatch()) return; - } } audit_syscall_exit(regs); diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 5d491a98265e..12683b5d125e 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -562,6 +562,7 @@ struct ethtool_fec_hist { u64 per_lane[ETHTOOL_MAX_LANES]; } values[ETHTOOL_FEC_HIST_MAX]; const struct ethtool_fec_hist_range *ranges; + struct ethtool_fec_hist_range ranges_buf[ETHTOOL_FEC_HIST_MAX]; }; /** * struct ethtool_fec_stats - statistics for IEEE 802.3 FEC diff --git a/include/linux/firmware/intel/stratix10-smc.h b/include/linux/firmware/intel/stratix10-smc.h index 9116512169dc..9224974fffc4 100644 --- a/include/linux/firmware/intel/stratix10-smc.h +++ b/include/linux/firmware/intel/stratix10-smc.h @@ -67,6 +67,9 @@ * INTEL_SIP_SMC_STATUS_REJECTED: * Secure monitor software reject the service client's request. * + * INTEL_SIP_SMC_STATUS_NO_RESPONSE: + * Secure monitor software has no response for the request yet. + * * INTEL_SIP_SMC_STATUS_ERROR: * There is error during the process of service request. * @@ -77,6 +80,7 @@ #define INTEL_SIP_SMC_STATUS_OK 0x0 #define INTEL_SIP_SMC_STATUS_BUSY 0x1 #define INTEL_SIP_SMC_STATUS_REJECTED 0x2 +#define INTEL_SIP_SMC_STATUS_NO_RESPONSE 0x3 #define INTEL_SIP_SMC_STATUS_ERROR 0x4 #define INTEL_SIP_SMC_RSU_ERROR 0x7 @@ -606,7 +610,7 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) /** * Request INTEL_SIP_SMC_FUNCID_FCS_SEND_CERTIFICATE - * Sync call to send a signed certificate + * Async call to send a signed certificate * * Call register usage: * a0 INTEL_SIP_SMC_FCS_SEND_CERTIFICATE @@ -615,7 +619,7 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) * a3-a7 not used * * Return status: - * a0 INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_FCS_REJECTED + * a0 INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_REJECTED * a1-a3 not used */ #define INTEL_SIP_SMC_FUNCID_FCS_SEND_CERTIFICATE 93 @@ -631,9 +635,11 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) * a1-a7 not used * * Return status: - * a0 INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_FCS_ERROR or - * INTEL_SIP_SMC_FCS_REJECTED - * a1-a3 not used + * a0 INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_STATUS_ERROR or + * INTEL_SIP_SMC_STATUS_REJECTED + * a1 mailbox error if a0 is INTEL_SIP_SMC_STATUS_ERROR + * a2 physical address for the structure of fuse and key hashes + * a3 the size of structure * */ #define INTEL_SIP_SMC_FUNCID_FCS_GET_PROVISION_DATA 94 diff --git a/include/linux/firmware/qcom/qcom_pas.h b/include/linux/firmware/qcom/qcom_pas.h new file mode 100644 index 000000000000..65b1c9564458 --- /dev/null +++ b/include/linux/firmware/qcom/qcom_pas.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2010-2015, 2018-2019 The Linux Foundation. All rights reserved. + * Copyright (C) 2015 Linaro Ltd. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. + */ + +#ifndef __QCOM_PAS_H +#define __QCOM_PAS_H + +#include <linux/err.h> +#include <linux/types.h> + +struct qcom_pas_context { + struct device *dev; + u32 pas_id; + phys_addr_t mem_phys; + size_t mem_size; + void *ptr; + dma_addr_t phys; + ssize_t size; + bool use_tzmem; +}; + +bool qcom_pas_is_available(void); +struct qcom_pas_context *devm_qcom_pas_context_alloc(struct device *dev, + u32 pas_id, + phys_addr_t mem_phys, + size_t mem_size); +int qcom_pas_init_image(u32 pas_id, const void *metadata, size_t size, + struct qcom_pas_context *ctx); +struct resource_table *qcom_pas_get_rsc_table(struct qcom_pas_context *ctx, + void *input_rt, size_t input_rt_size, + size_t *output_rt_size); +int qcom_pas_mem_setup(u32 pas_id, phys_addr_t addr, phys_addr_t size); +int qcom_pas_auth_and_reset(u32 pas_id); +int qcom_pas_prepare_and_auth_reset(struct qcom_pas_context *ctx); +int qcom_pas_set_remote_state(u32 state, u32 pas_id); +int qcom_pas_shutdown(u32 pas_id); +bool qcom_pas_supported(u32 pas_id); +void qcom_pas_metadata_release(struct qcom_pas_context *ctx); + +#endif /* __QCOM_PAS_H */ diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 7e27b0f7bf7e..69a2f74269f3 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -3,7 +3,7 @@ * Xilinx Zynq MPSoC Firmware layer * * Copyright (C) 2014-2021 Xilinx - * Copyright (C) 2022 - 2025 Advanced Micro Devices, Inc. + * Copyright (C) 2022 - 2026 Advanced Micro Devices, Inc. * * Michal Simek <michal.simek@amd.com> * Davorin Mista <davorin.mista@aggios.com> @@ -50,6 +50,7 @@ /* PM API versions */ #define PM_API_VERSION_1 1 #define PM_API_VERSION_2 2 +#define PM_API_VERSION_3 3 #define PM_PINCTRL_PARAM_SET_VERSION 2 @@ -66,6 +67,7 @@ #define FIRMWARE_VERSION_MASK 0xFFFFU /* ATF only commands */ +#define TF_A_CLEAR_PM_STATE 0xa05 #define TF_A_PM_REGISTER_SGI 0xa04 #define PM_GET_TRUSTZONE_VERSION 0xa03 #define PM_SET_SUSPEND_MODE 0xa02 @@ -144,6 +146,12 @@ #define XPM_EVENT_ERROR_MASK_NOC_NCR BIT(13) #define XPM_EVENT_ERROR_MASK_NOC_CR BIT(12) +/* Node ID for all peripheral devices */ +#define PM_DEV_ALL_PERIPH 0x18224FFFU + +/* Node ID for all notifier callbacks */ +#define PM_ALL_NOTIFIERS 0xFFFFFFFFU + enum pm_module_id { PM_MODULE_ID = 0x0, XPM_MODULE_ID = 0x2, diff --git a/include/linux/fixp-arith.h b/include/linux/fixp-arith.h index e485fb0c1201..4d4f4a7d4749 100644 --- a/include/linux/fixp-arith.h +++ b/include/linux/fixp-arith.h @@ -40,7 +40,7 @@ static const s32 sin_table[] = { }; /** - * __fixp_sin32() returns the sin of an angle in degrees + * __fixp_sin32() - returns the sin of an angle in degrees * * @degrees: angle, in degrees, from 0 to 360. * @@ -64,7 +64,7 @@ static inline s32 __fixp_sin32(int degrees) } /** - * fixp_sin32() returns the sin of an angle in degrees + * fixp_sin32() - returns the sin of an angle in degrees * * @degrees: angle, in degrees. The angle can be positive or negative * diff --git a/include/linux/fs.h b/include/linux/fs.h index 50ce731a2b78..8e9bc9dda0cb 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -740,7 +740,8 @@ enum inode_state_flags_enum { I_CREATING = (1U << 15), I_DONTCACHE = (1U << 16), I_SYNC_QUEUED = (1U << 17), - I_PINNING_NETFS_WB = (1U << 18) + I_PINNING_NETFS_WB = (1U << 18), + I_METADATA_WRITEBACK = (1U << 19), }; #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) @@ -1598,12 +1599,12 @@ struct timespec64 inode_set_ctime_deleg(struct inode *inode, static inline time64_t inode_get_atime_sec(const struct inode *inode) { - return inode->i_atime_sec; + return READ_ONCE(inode->i_atime_sec); } static inline long inode_get_atime_nsec(const struct inode *inode) { - return inode->i_atime_nsec; + return READ_ONCE(inode->i_atime_nsec); } static inline struct timespec64 inode_get_atime(const struct inode *inode) @@ -1617,8 +1618,8 @@ static inline struct timespec64 inode_get_atime(const struct inode *inode) static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode, struct timespec64 ts) { - inode->i_atime_sec = ts.tv_sec; - inode->i_atime_nsec = ts.tv_nsec; + WRITE_ONCE(inode->i_atime_sec, ts.tv_sec); + WRITE_ONCE(inode->i_atime_nsec, ts.tv_nsec); return ts; } @@ -1633,12 +1634,12 @@ static inline struct timespec64 inode_set_atime(struct inode *inode, static inline time64_t inode_get_mtime_sec(const struct inode *inode) { - return inode->i_mtime_sec; + return READ_ONCE(inode->i_mtime_sec); } static inline long inode_get_mtime_nsec(const struct inode *inode) { - return inode->i_mtime_nsec; + return READ_ONCE(inode->i_mtime_nsec); } static inline struct timespec64 inode_get_mtime(const struct inode *inode) @@ -1651,8 +1652,8 @@ static inline struct timespec64 inode_get_mtime(const struct inode *inode) static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode, struct timespec64 ts) { - inode->i_mtime_sec = ts.tv_sec; - inode->i_mtime_nsec = ts.tv_nsec; + WRITE_ONCE(inode->i_mtime_sec, ts.tv_sec); + WRITE_ONCE(inode->i_mtime_nsec, ts.tv_nsec); return ts; } @@ -1677,12 +1678,12 @@ static inline struct timespec64 inode_set_mtime(struct inode *inode, static inline time64_t inode_get_ctime_sec(const struct inode *inode) { - return inode->i_ctime_sec; + return READ_ONCE(inode->i_ctime_sec); } static inline long inode_get_ctime_nsec(const struct inode *inode) { - return inode->i_ctime_nsec & ~I_CTIME_QUERIED; + return READ_ONCE(inode->i_ctime_nsec) & ~I_CTIME_QUERIED; } static inline struct timespec64 inode_get_ctime(const struct inode *inode) @@ -1916,8 +1917,6 @@ struct dir_context { struct io_uring_cmd; struct offset_ctx; -typedef unsigned int __bitwise fop_flags_t; - struct file_operations { struct module *owner; fop_flags_t fop_flags; @@ -2002,7 +2001,7 @@ struct inode_operations { int (*readlink) (struct dentry *, char __user *,int); int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, - umode_t, bool); + umode_t); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, @@ -2213,6 +2212,13 @@ static inline void mark_inode_dirty_sync(struct inode *inode) __mark_inode_dirty(inode, I_DIRTY_SYNC); } +static inline void set_inode_metadata_writeback(struct inode *inode) +{ + spin_lock(&inode->i_lock); + inode_state_set(inode, I_METADATA_WRITEBACK); + spin_unlock(&inode->i_lock); +} + /* * returns the refcount on the inode. it can change arbitrarily. */ diff --git a/include/linux/fs/super.h b/include/linux/fs/super.h index 405612678115..733d439f01ed 100644 --- a/include/linux/fs/super.h +++ b/include/linux/fs/super.h @@ -237,4 +237,12 @@ int thaw_super(struct super_block *super, enum freeze_holder who, int sb_init_dio_done_wq(struct super_block *sb); +struct file; +struct file *fs_bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder, + struct super_block *sb); +struct file *fs_bdev_file_open_by_path(const char *path, blk_mode_t mode, + void *holder, struct super_block *sb); +void fs_bdev_unregister(struct file *bdev_file, struct super_block *sb); +void fs_bdev_file_release(struct file *bdev_file, struct super_block *sb); + #endif /* _LINUX_FS_SUPER_H */ diff --git a/include/linux/fs/super_types.h b/include/linux/fs/super_types.h index ef7941e9dc79..ecd96aeb1cee 100644 --- a/include/linux/fs/super_types.h +++ b/include/linux/fs/super_types.h @@ -30,6 +30,7 @@ struct mount; struct mtd_info; struct quotactl_ops; struct shrinker; +struct super_dev; struct unicode_map; struct user_namespace; struct workqueue_struct; @@ -86,6 +87,8 @@ struct super_operations { void (*free_inode)(struct inode *inode); void (*dirty_inode)(struct inode *inode, int flags); int (*write_inode)(struct inode *inode, struct writeback_control *wbc); + int (*sync_inode_metadata)(struct inode *inode, + struct writeback_control *wbc); int (*drop_inode)(struct inode *inode); void (*evict_inode)(struct inode *inode); void (*put_super)(struct super_block *sb); @@ -132,6 +135,7 @@ struct super_operations { struct super_block { struct list_head s_list; /* Keep this first */ dev_t s_dev; /* search index; _not_ kdev_t */ + struct super_dev *s_super_dev; /* sget_fc()'s device table claim */ unsigned char s_blocksize_bits; unsigned long s_blocksize; loff_t s_maxbytes; /* Max file size */ @@ -145,7 +149,7 @@ struct super_block { unsigned long s_magic; struct dentry *s_root; struct rw_semaphore s_umount; - int s_count; + refcount_t s_passive; atomic_t s_active; #ifdef CONFIG_SECURITY void *s_security; @@ -300,7 +304,7 @@ struct super_block { #define SB_NODIRATIME BIT(11) /* Do not update directory access times */ #define SB_SILENT BIT(15) #define SB_POSIXACL BIT(16) /* Supports POSIX ACLs */ -#define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ +#define SB_INLINECRYPT BIT(17) /* Use inline crypto hardware if available */ #define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ #define SB_I_VERSION BIT(23) /* Update inode I_version field */ #define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 0070764b790a..97eef8d3863d 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -6,6 +6,7 @@ #include <linux/path.h> #include <linux/spinlock.h> #include <linux/seqlock.h> +#include <linux/vfsdebug.h> struct fs_struct { int users; @@ -16,6 +17,7 @@ struct fs_struct { } __randomize_layout; extern struct kmem_cache *fs_cachep; +extern struct fs_struct *userspace_init_fs; extern void exit_fs(struct task_struct *); extern void set_fs_root(struct fs_struct *, const struct path *); @@ -40,6 +42,8 @@ static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd) read_sequnlock_excl(&fs->seq); } +struct fs_struct *switch_fs_struct(struct fs_struct *new_fs); + extern bool current_chrooted(void); static inline int current_umask(void) @@ -47,4 +51,34 @@ static inline int current_umask(void) return current->fs->umask; } +/* + * Temporarily use userspace_init_fs for path resolution in kthreads. + * Callers should use scoped_with_init_fs() which automatically + * restores the original fs_struct at scope exit. + */ +static inline struct fs_struct *__override_init_fs(void) +{ + struct fs_struct *old_fs; + + old_fs = current->fs; + WRITE_ONCE(current->fs, userspace_init_fs); + return old_fs; +} + +static inline void __revert_init_fs(struct fs_struct *old_fs) +{ + VFS_WARN_ON_ONCE(current->fs != userspace_init_fs); + WRITE_ONCE(current->fs, old_fs); +} + +DEFINE_CLASS(__override_init_fs, + struct fs_struct *, + __revert_init_fs(_T), + __override_init_fs(), void) + +#define scoped_with_init_fs() \ + scoped_class(__override_init_fs, __UNIQUE_ID(label)) + +void __init init_userspace_fs(void); + #endif /* _LINUX_FS_STRUCT_H */ diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 54712ec61ffb..28f2108e29f3 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -57,6 +57,9 @@ struct fscrypt_name { /* Maximum value for the third parameter of fscrypt_operations.set_context(). */ #define FSCRYPT_SET_CONTEXT_MAX_SIZE 40 +/* Maximum supported number of block devices per filesystem */ +#define FSCRYPT_MAX_DEVICES 8 + #ifdef CONFIG_FS_ENCRYPTION /* Crypto operations for filesystems */ @@ -69,14 +72,15 @@ struct fscrypt_operations { ptrdiff_t inode_info_offs; /* - * If set, then fs/crypto/ will allocate a global bounce page pool the - * first time an encryption key is set up for a file. The bounce page - * pool is required by the following functions: - * - * - fscrypt_encrypt_pagecache_blocks() - * - fscrypt_zeroout_range() for files not using inline crypto - * - * If the filesystem doesn't use those, it doesn't need to set this. + * Set to 1 if the filesystem is block-based. This causes fs/crypto/ to + * set up the key for regular files as a blk_crypto_key. The filesystem + * then uses fscrypt_set_bio_crypt_ctx() and similar functions. + */ + unsigned int is_block_based : 1; + + /* + * Set to 1 if the filesystem uses fscrypt_encrypt_pagecache_blocks(). + * This enables the allocation of the bounce page pool it requires. */ unsigned int needs_bounce_pages : 1; @@ -181,21 +185,20 @@ struct fscrypt_operations { bool (*has_stable_inodes)(struct super_block *sb); /* - * Return an array of pointers to the block devices to which the - * filesystem may write encrypted file contents, NULL if the filesystem - * only has a single such block device, or an ERR_PTR() on error. + * Retrieve the list of block devices to which the filesystem may write + * encrypted file contents. * - * On successful non-NULL return, *num_devs is set to the number of - * devices in the returned array. The caller must free the returned - * array using kfree(). + * This writes the block_device pointers to @devs and returns the count + * (between 1 and FSCRYPT_MAX_DEVICES inclusively). * * If the filesystem can use multiple block devices (other than block * devices that aren't used for encrypted file contents, such as * external journal devices), and wants to support inline encryption, * then it must implement this function. Otherwise it's not needed. */ - struct block_device **(*get_devices)(struct super_block *sb, - unsigned int *num_devs); + unsigned int (*get_devices)( + struct super_block *sb, + struct block_device *devs[FSCRYPT_MAX_DEVICES]); }; int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name, @@ -342,7 +345,6 @@ static inline void fscrypt_prepare_dentry(struct dentry *dentry, } /* crypto.c */ -void fscrypt_enqueue_decrypt_work(struct work_struct *); struct page *fscrypt_encrypt_pagecache_blocks(struct folio *folio, size_t len, size_t offs, gfp_t gfp_flags); @@ -350,8 +352,6 @@ int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page, unsigned int len, unsigned int offs, u64 lblk_num); -int fscrypt_decrypt_pagecache_blocks(struct folio *folio, size_t len, - size_t offs); int fscrypt_decrypt_block_inplace(const struct inode *inode, struct page *page, unsigned int len, unsigned int offs, u64 lblk_num); @@ -448,11 +448,6 @@ bool fscrypt_match_name(const struct fscrypt_name *fname, const u8 *de_name, u32 de_name_len); u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name); -/* bio.c */ -bool fscrypt_decrypt_bio(struct bio *bio); -int fscrypt_zeroout_range(const struct inode *inode, loff_t pos, - sector_t sector, u64 len); - /* hooks.c */ int fscrypt_file_open(struct inode *inode, struct file *filp); int __fscrypt_prepare_link(struct inode *inode, struct inode *dir, @@ -509,9 +504,6 @@ static inline void fscrypt_prepare_dentry(struct dentry *dentry, } /* crypto.c */ -static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work) -{ -} static inline struct page *fscrypt_encrypt_pagecache_blocks(struct folio *folio, size_t len, size_t offs, gfp_t gfp_flags) @@ -527,12 +519,6 @@ static inline int fscrypt_encrypt_block_inplace(const struct inode *inode, return -EOPNOTSUPP; } -static inline int fscrypt_decrypt_pagecache_blocks(struct folio *folio, - size_t len, size_t offs) -{ - return -EOPNOTSUPP; -} - static inline int fscrypt_decrypt_block_inplace(const struct inode *inode, struct page *page, unsigned int len, @@ -749,18 +735,6 @@ static inline int fscrypt_d_revalidate(struct inode *dir, const struct qstr *nam return 1; } -/* bio.c */ -static inline bool fscrypt_decrypt_bio(struct bio *bio) -{ - return true; -} - -static inline int fscrypt_zeroout_range(const struct inode *inode, loff_t pos, - sector_t sector, u64 len) -{ - return -EOPNOTSUPP; -} - /* hooks.c */ static inline int fscrypt_file_open(struct inode *inode, struct file *filp) @@ -860,28 +834,21 @@ static inline void fscrypt_set_ops(struct super_block *sb, #endif /* !CONFIG_FS_ENCRYPTION */ -/* inline_crypt.c */ +/* block.c */ #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT -bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode); - void fscrypt_set_bio_crypt_ctx(struct bio *bio, const struct inode *inode, loff_t pos, gfp_t gfp_mask); bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode, loff_t pos); -bool fscrypt_dio_supported(struct inode *inode); - u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk, u64 nr_blocks); +int fscrypt_zeroout_range(const struct inode *inode, loff_t pos, + sector_t sector, u64 len); #else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ -static inline bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode) -{ - return false; -} - static inline void fscrypt_set_bio_crypt_ctx(struct bio *bio, const struct inode *inode, loff_t pos, gfp_t gfp_mask) { } @@ -893,47 +860,18 @@ static inline bool fscrypt_mergeable_bio(struct bio *bio, return true; } -static inline bool fscrypt_dio_supported(struct inode *inode) -{ - return !fscrypt_needs_contents_encryption(inode); -} - static inline u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk, u64 nr_blocks) { return nr_blocks; } -#endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ -/** - * fscrypt_inode_uses_inline_crypto() - test whether an inode uses inline - * encryption - * @inode: an inode. If encrypted, its key must be set up. - * - * Return: true if the inode requires file contents encryption and if the - * encryption should be done in the block layer via blk-crypto rather - * than in the filesystem layer. - */ -static inline bool fscrypt_inode_uses_inline_crypto(const struct inode *inode) -{ - return fscrypt_needs_contents_encryption(inode) && - __fscrypt_inode_uses_inline_crypto(inode); -} - -/** - * fscrypt_inode_uses_fs_layer_crypto() - test whether an inode uses fs-layer - * encryption - * @inode: an inode. If encrypted, its key must be set up. - * - * Return: true if the inode requires file contents encryption and if the - * encryption should be done in the filesystem layer rather than in the - * block layer via blk-crypto. - */ -static inline bool fscrypt_inode_uses_fs_layer_crypto(const struct inode *inode) +static inline int fscrypt_zeroout_range(const struct inode *inode, loff_t pos, + sector_t sector, u64 len) { - return fscrypt_needs_contents_encryption(inode) && - !__fscrypt_inode_uses_inline_crypto(inode); + return -EOPNOTSUPP; } +#endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ /** * fscrypt_has_encryption_key() - check whether an inode has had its key set up @@ -1121,15 +1059,4 @@ static inline int fscrypt_encrypt_symlink(struct inode *inode, return 0; } -/* If *pagep is a bounce page, free it and set *pagep to the pagecache page */ -static inline void fscrypt_finalize_bounce_page(struct page **pagep) -{ - struct page *page = *pagep; - - if (fscrypt_is_bounce_page(page)) { - *pagep = fscrypt_pagecache_page(page); - fscrypt_free_bounce_page(page); - } -} - #endif /* _LINUX_FSCRYPT_H */ diff --git a/include/linux/fsl/guts.h b/include/linux/fsl/guts.h index fdb55ca47a4f..8d5ffb985fee 100644 --- a/include/linux/fsl/guts.h +++ b/include/linux/fsl/guts.h @@ -13,6 +13,7 @@ #include <linux/types.h> #include <linux/io.h> +#include <soc/fsl/phy-fsl-lynx.h> /* * Global Utility Registers. @@ -91,9 +92,15 @@ struct ccsr_guts { u32 iovselsr; /* 0x.00c0 - I/O voltage select status register Called 'elbcvselcr' on 86xx SOCs */ u8 res0c4[0x100 - 0xc4]; - u32 rcwsr[16]; /* 0x.0100 - Reset Control Word Status registers - There are 16 registers */ - u8 res140[0x224 - 0x140]; + /* 0x.0100 - read-only Reset Configuration Word Status registers in + * CCSR, or write-only Reset Configuration Word Control registers in + * DCSR. In both cases there are 32 registers. + */ + union { + u32 rcwsr[32]; + u32 rcwcr[32]; + }; + u8 res180[0x224 - 0x180]; u32 iodelay1; /* 0x.0224 - IO delay control register 1 */ u32 iodelay2; /* 0x.0228 - IO delay control register 2 */ u8 res22c[0x604 - 0x22c]; @@ -131,6 +138,11 @@ struct ccsr_guts { u32 srds2cr1; /* 0x.0f44 - SerDes2 Control Register 0 */ } __attribute__ ((packed)); +int fsl_guts_lane_validate(int serdes_idx, int lane, + enum lynx_lane_mode lane_mode); +int fsl_guts_lane_set_mode(int serdes_idx, int lane, + enum lynx_lane_mode lane_mode); + /* Alternate function signal multiplex control */ #define MPC85xx_PMUXCR_QE(x) (0x8000 >> (x)) diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index d57cab4d4c06..73b48dd9f135 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -92,6 +92,37 @@ void irq_exit_rcu(void); #define arch_nmi_exit() do { } while (0) #endif +#ifdef CONFIG_HAS_SEPARATE_PREEMPT_RESCHED_BITS +static __always_inline void __preempt_count_nmi_enter(void) +{ + __preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); +} + +static __always_inline void __preempt_count_nmi_exit(void) +{ + __preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); +} +#else +DECLARE_PER_CPU(unsigned int, nmi_nesting); + +#define __preempt_count_nmi_enter() \ + do { \ + __preempt_count_add(HARDIRQ_OFFSET); \ + /* Maximum NMI nesting is 15. */ \ + BUG_ON(__this_cpu_read(nmi_nesting) >= 15); \ + __this_cpu_inc(nmi_nesting); \ + preempt_count_set(preempt_count() | NMI_MASK); \ + } while (0) + +#define __preempt_count_nmi_exit() \ + do { \ + __preempt_count_sub(HARDIRQ_OFFSET); \ + if (!__this_cpu_dec_return(nmi_nesting)) \ + preempt_count_set(preempt_count() & ~NMI_MASK); \ + } while (0) + +#endif + /* * NMI vs Tracing * -------------- @@ -102,21 +133,20 @@ void irq_exit_rcu(void); */ /* - * nmi_enter() can nest up to 15 times; see NMI_BITS. + * nmi_enter() can nest - nesting is tracked in a per-CPU counter. */ #define __nmi_enter() \ do { \ lockdep_off(); \ arch_nmi_enter(); \ - BUG_ON(in_nmi() == NMI_MASK); \ - __preempt_count_add(NMI_OFFSET + HARDIRQ_OFFSET); \ + __preempt_count_nmi_enter(); \ } while (0) #define nmi_enter() \ do { \ __nmi_enter(); \ lockdep_hardirq_enter(); \ - ct_nmi_enter(); \ + ct_nmi_enter(); \ instrumentation_begin(); \ ftrace_nmi_enter(); \ instrumentation_end(); \ @@ -125,7 +155,7 @@ void irq_exit_rcu(void); #define __nmi_exit() \ do { \ BUG_ON(!in_nmi()); \ - __preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET); \ + __preempt_count_nmi_exit(); \ arch_nmi_exit(); \ lockdep_on(); \ } while (0) diff --git a/include/linux/hfs_common.h b/include/linux/hfs_common.h index 45fb4c9ff9f5..d6a615e74b26 100644 --- a/include/linux/hfs_common.h +++ b/include/linux/hfs_common.h @@ -510,14 +510,21 @@ struct hfs_btree_header_rec { b-tree but not in extents b-tree (hfsplus). */ +/* HFS BTree misc info */ +#define HFS_TREE_HEAD 0 +#define HFS_BTREE_HDR_MAP_REC_INDEX 2 /* Map (bitmap) record in Header node */ +#define HFS_BTREE_MAP_NODE_REC_INDEX 0 /* Map record in Map Node */ + /* HFS+ BTree misc info */ -#define HFSPLUS_TREE_HEAD 0 +#define HFSPLUS_TREE_HEAD HFS_TREE_HEAD #define HFSPLUS_NODE_MXSZ 32768 #define HFSPLUS_NODE_MINSZ 512 #define HFSPLUS_ATTR_TREE_NODE_SIZE 8192 #define HFSPLUS_BTREE_HDR_NODE_RECS_COUNT 3 -#define HFSPLUS_BTREE_HDR_MAP_REC_INDEX 2 /* Map (bitmap) record in Header node */ -#define HFSPLUS_BTREE_MAP_NODE_REC_INDEX 0 /* Map record in Map Node */ +/* Map (bitmap) record in Header node */ +#define HFSPLUS_BTREE_HDR_MAP_REC_INDEX HFS_BTREE_HDR_MAP_REC_INDEX +/* Map record in Map Node */ +#define HFSPLUS_BTREE_MAP_NODE_REC_INDEX HFS_BTREE_MAP_NODE_REC_INDEX #define HFSPLUS_BTREE_HDR_USER_BYTES 128 #define HFSPLUS_BTREE_MAP_NODE_RECS_COUNT 2 #define HFSPLUS_BTREE_MAP_NODE_RESERVED_BYTES 2 diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 6862dea0acc5..29072d89e5cb 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -12,7 +12,6 @@ #ifndef _LINUX_HRTIMER_H #define _LINUX_HRTIMER_H -#include <linux/hrtimer_defs.h> #include <linux/hrtimer_rearm.h> #include <linux/hrtimer_types.h> #include <linux/init.h> @@ -287,37 +286,8 @@ static inline bool hrtimer_is_queued(struct hrtimer *timer) return READ_ONCE(timer->is_queued); } -/* - * Helper function to check, whether the timer is running the callback - * function - */ -static inline int hrtimer_callback_running(struct hrtimer *timer) -{ - return timer->base->running == timer; -} - -/** - * hrtimer_update_function - Update the timer's callback function - * @timer: Timer to update - * @function: New callback function - * - * Only safe to call if the timer is not enqueued. Can be called in the callback function if the - * timer is not enqueued at the same time (see the comments above HRTIMER_STATE_ENQUEUED). - */ -static inline void hrtimer_update_function(struct hrtimer *timer, - enum hrtimer_restart (*function)(struct hrtimer *)) -{ -#ifdef CONFIG_PROVE_LOCKING - guard(raw_spinlock_irqsave)(&timer->base->cpu_base->lock); - - if (WARN_ON_ONCE(hrtimer_is_queued(timer))) - return; - - if (WARN_ON_ONCE(!function)) - return; -#endif - ACCESS_PRIVATE(timer, function) = function; -} +void hrtimer_update_function(struct hrtimer *timer, + enum hrtimer_restart (*function)(struct hrtimer *)); /* Forward a hrtimer so it expires after now: */ extern u64 diff --git a/include/linux/hrtimer_defs.h b/include/linux/hrtimer_bases.h index 52ed9e46ff13..d4c83ec5c0f8 100644 --- a/include/linux/hrtimer_defs.h +++ b/include/linux/hrtimer_bases.h @@ -1,7 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_HRTIMER_DEFS_H -#define _LINUX_HRTIMER_DEFS_H +#ifndef _LINUX_HRTIMER_BASES_H +#define _LINUX_HRTIMER_BASES_H +#include <linux/hrtimer.h> #include <linux/ktime.h> #include <linux/timerqueue.h> #include <linux/seqlock.h> @@ -83,7 +84,7 @@ struct hrtimer_cpu_base { raw_spinlock_t lock; unsigned int cpu; unsigned int active_bases; - unsigned int clock_was_set_seq; + u32 clock_was_set_seq; bool hres_active; bool deferred_rearm; bool deferred_needs_update; @@ -110,4 +111,13 @@ struct hrtimer_cpu_base { } ____cacheline_aligned; +/* + * Helper function to check, whether the timer is running the callback + * function + */ +static inline int hrtimer_callback_running(struct hrtimer *timer) +{ + return timer->base->running == timer; +} + #endif diff --git a/include/linux/hrtimer_rearm.h b/include/linux/hrtimer_rearm.h index a6f2e5d5e1c7..17a81826bd9a 100644 --- a/include/linux/hrtimer_rearm.h +++ b/include/linux/hrtimer_rearm.h @@ -2,7 +2,12 @@ #ifndef _LINUX_HRTIMER_REARM_H #define _LINUX_HRTIMER_REARM_H +#include <linux/types.h> + #ifdef CONFIG_HRTIMER_REARM_DEFERRED +#include <linux/irqflags.h> +#include <linux/lockdep.h> +#include <linux/preempt.h> #include <linux/thread_info.h> void __hrtimer_rearm_deferred(void); diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 77a6f2bffcba..dd713e193d0c 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -480,8 +480,7 @@ hwmon_device_register_with_info(struct device *dev, const struct attribute_group **extra_groups); struct device * hwmon_device_register_for_thermal(struct device *dev, const char *name, - void *drvdata, - const struct attribute_group **extra_groups); + void *drvdata); struct device * devm_hwmon_device_register_with_info(struct device *dev, const char *name, void *drvdata, diff --git a/include/linux/ieee80211-eht.h b/include/linux/ieee80211-eht.h index 18f9c662cf4c..c109722b1969 100644 --- a/include/linux/ieee80211-eht.h +++ b/include/linux/ieee80211-eht.h @@ -857,7 +857,7 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) const struct ieee80211_multi_link_elem *mle = (const void *)data; u8 fixed = sizeof(*mle); u8 common = 0; - bool check_common_len = false; + u8 common_len; u16 control; if (!data || len < fixed) @@ -868,7 +868,6 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { case IEEE80211_ML_CONTROL_TYPE_BASIC: common += sizeof(struct ieee80211_mle_basic_common_info); - check_common_len = true; if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) common += 1; if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) @@ -888,9 +887,9 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) common += sizeof(struct ieee80211_mle_preq_common_info); if (control & IEEE80211_MLC_PREQ_PRES_MLD_ID) common += 1; - check_common_len = true; break; case IEEE80211_ML_CONTROL_TYPE_RECONF: + common += 1; if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR) common += ETH_ALEN; if (control & IEEE80211_MLC_RECONF_PRES_EML_CAPA) @@ -902,7 +901,6 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) break; case IEEE80211_ML_CONTROL_TYPE_TDLS: common += sizeof(struct ieee80211_mle_tdls_common_info); - check_common_len = true; break; case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: common = ETH_ALEN + 1; @@ -915,11 +913,9 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) if (len < fixed + common) return false; - if (!check_common_len) - return true; + common_len = mle->variable[0]; - /* if present, common length is the first octet there */ - return mle->variable[0] >= common; + return common_len >= common && common_len <= len - fixed; } /** diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 5f3e206c7a73..80166eb62f41 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -22,7 +22,6 @@ struct tun_msg_ctl { #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) struct socket *tun_get_socket(struct file *); struct ptr_ring *tun_get_tx_ring(struct file *file); -void tun_wake_queue(struct file *file, int consumed); static inline bool tun_is_xdp_frame(void *ptr) { @@ -56,8 +55,6 @@ static inline struct ptr_ring *tun_get_tx_ring(struct file *f) return ERR_PTR(-EINVAL); } -static inline void tun_wake_queue(struct file *f, int consumed) {} - static inline bool tun_is_xdp_frame(void *ptr) { return false; diff --git a/include/linux/init_task.h b/include/linux/init_task.h index a6cb241ea00c..61536be773f5 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -24,6 +24,7 @@ extern struct files_struct init_files; extern struct fs_struct init_fs; +extern struct fs_struct *userspace_init_fs; extern struct nsproxy init_nsproxy; #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE diff --git a/include/linux/interrupt_rc.h b/include/linux/interrupt_rc.h new file mode 100644 index 000000000000..b9a7f05ecf42 --- /dev/null +++ b/include/linux/interrupt_rc.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_INTERRUPT_RC_H +#define __LINUX_INTERRUPT_RC_H + +/* + * include/linux/interrupt_rc.h - refcounted local processor interrupt + * management. + * + * Since the implementation of this API currently depends on + * local_irq_save()/local_irq_restore(), we split this into its own header to + * make it easier to include without hitting circular header dependencies. + */ + +#include <linux/irqflags.h> +#include <linux/preempt.h> +#include <linux/processor.h> +#include <linux/smp.h> + +#ifndef MODULE +/* Per-CPU interrupt disabling state for local_interrupt_{disable,enable}(). */ +DECLARE_PER_CPU(unsigned long, local_interrupt_disable_state); + +static __always_inline void __local_interrupt_disable(void) +{ + unsigned long flags; + + local_irq_save(flags); + raw_cpu_write(local_interrupt_disable_state, flags); +} + +static __always_inline void __local_interrupt_enable(void) +{ + unsigned long flags = raw_cpu_read(local_interrupt_disable_state); + + local_irq_restore(flags); +} + +#ifndef INSTANTIATE_EXPORTED_INTERRUPT_DISABLE +static __always_inline void _local_interrupt_disable(void) +{ + __local_interrupt_disable(); +} + +static __always_inline void _local_interrupt_enable(void) +{ + __local_interrupt_enable(); +} +#else +extern void _local_interrupt_disable(void); +extern void _local_interrupt_enable(void); +#endif + +#else /* !MODULE */ +extern void _local_interrupt_disable(void); +extern void _local_interrupt_enable(void); +#endif /* !MODULE */ + +static inline void local_interrupt_disable(void) +{ + int new_count; + + WARN_ON_ONCE(in_nmi()); + + new_count = hardirq_disable_enter(); + + /* Interrupts can happen here, but it's OK, see __irq_exit_rcu(). */ + + if ((new_count & HARDIRQ_DISABLE_MASK) == HARDIRQ_DISABLE_OFFSET) + _local_interrupt_disable(); +} + +static inline void local_interrupt_enable(void) +{ + int new_count; + + new_count = hardirq_disable_exit(); + + if ((new_count & HARDIRQ_DISABLE_MASK) == 0) + _local_interrupt_enable(); +} + +#endif /* !__LINUX_INTERRUPT_RC_H */ diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 56b43d594e6e..8c754eb974fb 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -10,6 +10,7 @@ #include <linux/mm_types.h> #include <linux/blkdev.h> #include <linux/folio_batch.h> +#include <linux/pagemap.h> struct address_space; struct fiemap_extent_info; @@ -212,24 +213,36 @@ struct iomap_write_ops { #define IOMAP_ATOMIC (1 << 9) /* torn-write protection */ #define IOMAP_DONTCACHE (1 << 10) -struct iomap_ops { - /* - * Return the existing mapping at pos, or reserve space starting at - * pos for up to length, as long as we can do it as a single mapping. - * The actual length is returned in iomap->length. - */ - int (*iomap_begin)(struct inode *inode, loff_t pos, loff_t length, - unsigned flags, struct iomap *iomap, - struct iomap *srcmap); +/* + * Return the existing mapping at pos, or reserve space starting at pos for up + * to length, as long as we can do it as a single mapping. + * The actual length is returned in iomap->length. + */ +typedef int (*iomap_iter_begin_fn)(struct inode *inode, loff_t pos, + loff_t length, unsigned flags, struct iomap *iomap, + struct iomap *srcmap); - /* - * Commit and/or unreserve space previous allocated using iomap_begin. - * Written indicates the length of the successful write operation which - * needs to be commited, while the rest needs to be unreserved. - * Written might be zero if no data was written. - */ - int (*iomap_end)(struct inode *inode, loff_t pos, loff_t length, - ssize_t written, unsigned flags, struct iomap *iomap); +/* + * Commit and/or unreserve space previously allocated by iomap_iter_begin_fn. + * Written indicates the length of the successful write operation which needs + * to be committed, while the rest needs to be unreserved. + * Written might be zero if no data was written. + */ +typedef int (*iomap_iter_end_fn)(struct inode *inode, loff_t pos, loff_t length, + ssize_t written, unsigned flags, struct iomap *iomap); + +/* + * Produce the next mapping (finishing the previous one if needed). + * Return 1 to continue iterating, 0 if the range is fully consumed, or a + * negative error on failure. + */ +typedef int (*iomap_iter_next_fn)(const struct iomap_iter *iter, + struct iomap *iomap, struct iomap *srcmap); + +struct iomap_ops { + iomap_iter_begin_fn iomap_begin; + iomap_iter_end_fn iomap_end; + iomap_iter_next_fn iomap_next; }; /** @@ -317,6 +330,71 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i) return &i->iomap; } +int iomap_iter_continue(const struct iomap_iter *iter, struct iomap *iomap, + struct iomap *srcmap, int ret); + +/** + * iomap_iter_next - finish the previous mapping and produce the next one + * @iter: iteration structure + * @iomap: mapping to finish and then repopulate + * @srcmap: source mapping to finish and then repopulate + * @begin: callback that produces a mapping for the current position + * @end: optional callback that finishes the previous mapping, or NULL + * + * Inline helper that implements the common body of an ->iomap_next() + * callback: it finishes the previous mapping via @end (if present), decides + * via iomap_iter_continue() whether to keep going, and obtains the next + * mapping via @begin. + * + * This helper is marked __always_inline so that when a caller passes + * compile-time-constant @begin and @end callbacks, the compiler can call them + * directly, avoiding the indirect-call overhead. + * + * Returns 1 to continue iterating, 0 once the range is fully consumed, or a + * negative errno on error. + */ +static __always_inline int iomap_iter_next(const struct iomap_iter *iter, + struct iomap *iomap, struct iomap *srcmap, + iomap_iter_begin_fn begin, iomap_iter_end_fn end) +{ + int ret = 0; + + if (iomap->length) { + if (end) { + /* + * Calculate how far the iter was advanced and the + * original length bytes for end(). + */ + ssize_t advanced = iter->pos - iter->iter_start_pos; + loff_t len; + + len = iomap_length_trim(iter, iter->iter_start_pos, + iter->len + advanced); + + ret = end(iter->inode, iter->iter_start_pos, len, + advanced, iter->flags, iomap); + } + ret = iomap_iter_continue(iter, iomap, srcmap, ret); + if (ret <= 0) + return ret; + } + + ret = begin(iter->inode, iter->pos, iter->len, iter->flags, iomap, + srcmap); + + return ret < 0 ? ret : 1; +} + +#define DEFINE_IOMAP_ITER_NEXT_END(name, begin_fn, end_fn) \ +int name(const struct iomap_iter *iter, struct iomap *iomap, \ + struct iomap *srcmap) \ +{ \ + return iomap_iter_next(iter, iomap, srcmap, begin_fn, end_fn); \ +} + +#define DEFINE_IOMAP_ITER_NEXT(name, begin_fn) \ + DEFINE_IOMAP_ITER_NEXT_END(name, begin_fn, NULL) + /* * Return the file offset for the first unchanged block after a short write. * @@ -365,6 +443,7 @@ struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len); bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags); void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len); bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio); +void iomap_folio_mark_uptodate(struct folio *folio); int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops, const struct iomap_write_ops *write_ops); @@ -606,6 +685,71 @@ struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, ssize_t iomap_dio_complete(struct iomap_dio *dio); void iomap_dio_bio_end_io(struct bio *bio); +/* + * Fast path for small, block-aligned direct I/Os that map to a single + * contiguous on-disk extent. + * + * @iter must describe a non-empty READ no larger than the inode block size: + * writes, zero-length I/O, and larger requests need the generic iomap direct + * I/O path. + * + * Does not support iomap_dio_ops, dio_flags, done_before or private data. + * The range must also stay within i_size and encrypted inodes must use the + * generic iomap direct I/O path. + * + * -ENOTBLK indicates the generic path must be used by the caller instead. + * Any other errno is a real result and is propagated as-is, in particular + * -EAGAIN for IOCB_NOWAIT must reach the caller. + * + * The caller can only provide an iomap begin handler, and the iterator + * is never advanced. + */ +ssize_t __iomap_dio_read_simple(struct kiocb *iocb, struct iov_iter *iter, + struct iomap_iter *iomi); +static __always_inline ssize_t iomap_dio_read_simple(struct kiocb *iocb, + struct iov_iter *iter, iomap_iter_begin_fn begin) +{ + struct iomap_iter iomi = { + .inode = file_inode(iocb->ki_filp), + .pos = iocb->ki_pos, + .len = iov_iter_count(iter), + .flags = IOMAP_DIRECT, + }; + ssize_t ret; + + if (!iomi.len) + return 0; + + /* + * Simple dio is an optimization for small IO. Filter out large IO + * early as it's the most common case to fail for typical direct IO + * workloads. + */ + if (iomi.len > iomi.inode->i_sb->s_blocksize) + return -ENOTBLK; + if (iocb->ki_pos + iomi.len > i_size_read(iomi.inode)) + return -ENOTBLK; + if (IS_ENCRYPTED(iomi.inode)) + return -ENOTBLK; + + ret = kiocb_write_and_wait(iocb, iomi.len); + if (ret) + return ret; + + if (iocb->ki_flags & IOCB_NOWAIT) + iomi.flags |= IOMAP_NOWAIT; + + inode_dio_begin(iomi.inode); + ret = begin(iomi.inode, iomi.pos, iomi.len, iomi.flags, &iomi.iomap, + &iomi.srcmap); + if (ret) { + inode_dio_end(iomi.inode); + return ret; + } + + return __iomap_dio_read_simple(iocb, iter, &iomi); +} + #ifdef CONFIG_SWAP struct file; struct swap_info_struct; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index d20aa6f6863a..ac43b8b93f14 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -1704,6 +1704,7 @@ void iopf_free_group(struct iopf_group *group); int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt); void iopf_group_response(struct iopf_group *group, enum iommu_page_response_code status); +void iopf_group_dequeue(struct iopf_group *group); #else static inline int iopf_queue_add_device(struct iopf_queue *queue, struct device *dev) @@ -1749,5 +1750,9 @@ static inline void iopf_group_response(struct iopf_group *group, enum iommu_page_response_code status) { } + +static inline void iopf_group_dequeue(struct iopf_group *group) +{ +} #endif /* CONFIG_IOMMU_IOPF */ #endif /* __LINUX_IOMMU_H */ diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h index 1fabf0f5ea8e..0bb6c03481fa 100644 --- a/include/linux/irq-entry-common.h +++ b/include/linux/irq-entry-common.h @@ -49,9 +49,9 @@ * Defaults to an empty implementation. Can be replaced by architecture * specific code. * - * Invoked from syscall_enter_from_user_mode() in the non-instrumentable - * section. Use __always_inline so the compiler cannot push it out of line - * and make it instrumentable. + * Invoked from enter_from_user_mode() in the non-instrumentable section. Use + * __always_inline so the compiler cannot push it out of line and make it + * instrumentable. */ static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs); diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 8080db17c1b1..779d6023c5c2 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -146,7 +146,7 @@ extern struct irq_desc irq_desc[NR_IRQS]; static inline unsigned int irq_desc_kstat_cpu(struct irq_desc *desc, unsigned int cpu) { - return desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0; + return per_cpu(desc->kstat_irqs->cnt, cpu); } static inline struct irq_desc *irq_data_to_desc(struct irq_data *data) diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index b9c7b0ebf7b9..c95350a10987 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -71,7 +71,7 @@ * Additional babbling in: Documentation/staging/static-keys.rst */ -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/types.h> #include <linux/compiler.h> @@ -100,12 +100,12 @@ struct static_key { #endif /* CONFIG_JUMP_LABEL */ }; -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #ifdef CONFIG_JUMP_LABEL #include <asm/jump_label.h> -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #ifdef CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE struct jump_entry { @@ -180,7 +180,7 @@ static inline int jump_entry_size(struct jump_entry *entry) #endif #endif -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ enum jump_label_type { JUMP_LABEL_NOP = 0, @@ -524,6 +524,6 @@ extern bool ____wrong_branch_error(void); #define static_branch_enable_cpuslocked(x) static_key_enable_cpuslocked(&(x)->key) #define static_branch_disable_cpuslocked(x) static_key_disable_cpuslocked(&(x)->key) -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* _LINUX_JUMP_LABEL_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e5570a16cbb1..24414c79e59a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -72,7 +72,7 @@ extern int dynamic_might_resched(void); #ifdef CONFIG_DEBUG_ATOMIC_SLEEP extern void __might_resched(const char *file, int line, unsigned int offsets); extern void __might_sleep(const char *file, int line); -extern void __cant_sleep(const char *file, int line, int preempt_offset); +extern void __cant_sleep(const char *file, int line); extern void __cant_migrate(const char *file, int line); /** @@ -95,7 +95,7 @@ extern void __cant_migrate(const char *file, int line); * this macro will print a stack trace if it is executed with preemption enabled */ # define cant_sleep() \ - do { __cant_sleep(__FILE__, __LINE__, 0); } while (0) + do { __cant_sleep(__FILE__, __LINE__); } while (0) # define sched_annotate_sleep() (current->task_state_change = 0) /** diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 8a22bc9b8c6c..0af8ae4fdd08 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -13,7 +13,7 @@ #define IND_SOURCE (1 << IND_SOURCE_BIT) #define IND_FLAGS (IND_DESTINATION | IND_INDIRECTION | IND_DONE | IND_SOURCE) -#if !defined(__ASSEMBLY__) +#if !defined(__ASSEMBLER__) #include <linux/vmcore_info.h> #include <linux/crash_reserve.h> diff --git a/include/linux/libata.h b/include/linux/libata.h index 96e626d6a7ca..1827502b9cf2 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -425,7 +425,7 @@ enum { /* This should match the actual table size of * ata_eh_cmd_timeout_table in libata-eh.c. */ - ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 8, + ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 9, /* User visible DMA mask for DMA control. DO NOT renumber. */ ATA_DMA_MASK_ATA = (1 << 0), /* DMA on ATA Disk */ @@ -1153,6 +1153,9 @@ extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd, #endif extern enum scsi_qc_status ata_scsi_queuecmd(struct Scsi_Host *h, struct scsi_cmnd *cmd); +enum scsi_timeout_action ata_scsi_retry_deferred_qc(struct ata_port *ap, + struct scsi_cmnd *scmd); +enum scsi_timeout_action ata_scsi_eh_timed_out(struct scsi_cmnd *cmd); #if IS_REACHABLE(CONFIG_ATA) bool ata_scsi_dma_need_drain(struct request *rq); #else @@ -1464,6 +1467,7 @@ extern const struct attribute_group *ata_common_sdev_groups[]; .ioctl = ata_scsi_ioctl, \ ATA_SCSI_COMPAT_IOCTL \ .queuecommand = ata_scsi_queuecmd, \ + .eh_timed_out = ata_scsi_eh_timed_out, \ .dma_need_drain = ata_scsi_dma_need_drain, \ .this_id = ATA_SHT_THIS_ID, \ .emulated = ATA_SHT_EMULATED, \ diff --git a/include/linux/liveupdate.h b/include/linux/liveupdate.h index 88722e5caf02..63ea5417de84 100644 --- a/include/linux/liveupdate.h +++ b/include/linux/liveupdate.h @@ -173,7 +173,9 @@ struct liveupdate_flb_ops { * @lock: A mutex that protects all fields within this structure, providing * the synchronization service for the FLB's ops. * @finished: True once the FLB's finish() callback has run. - * @retrieved: True once the FLB's retrieve() callback has run. + * @retrieve_status: Status code indicating whether retrieve() has been + * attempted. 0 means not attempted, 1 means successful, + * and negative value means it failed with that error code. */ struct luo_flb_private_state { refcount_t count; @@ -181,7 +183,7 @@ struct luo_flb_private_state { void *obj; struct mutex lock; bool finished; - bool retrieved; + int retrieve_status; }; /* @@ -243,6 +245,7 @@ int liveupdate_flb_get_incoming(struct liveupdate_flb *flb, void **objp); void liveupdate_flb_put_incoming(struct liveupdate_flb *flb); int liveupdate_flb_get_outgoing(struct liveupdate_flb *flb, void **objp); +void liveupdate_flb_put_outgoing(struct liveupdate_flb *flb); #else /* CONFIG_LIVEUPDATE */ @@ -292,5 +295,9 @@ static inline int liveupdate_flb_get_outgoing(struct liveupdate_flb *flb, return -EOPNOTSUPP; } +static inline void liveupdate_flb_put_outgoing(struct liveupdate_flb *flb) +{ +} + #endif /* CONFIG_LIVEUPDATE */ #endif /* _LINUX_LIVEUPDATE_H */ diff --git a/include/linux/lockref.h b/include/linux/lockref.h index 6ded24cdb4a8..ddfb7d3b8cec 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -34,6 +34,8 @@ struct lockref { }; }; +#define __LOCKREF_DEAD_VAL -128 + /** * lockref_init - Initialize a lockref * @lockref: pointer to lockref structure @@ -55,9 +57,15 @@ void lockref_mark_dead(struct lockref *lockref); bool lockref_get_not_dead(struct lockref *lockref); /* Must be called under spinlock for reliable results */ -static inline bool __lockref_is_dead(const struct lockref *l) +static inline bool lockref_is_dead(const struct lockref *l) +{ + return (READ_ONCE(l->count) == __LOCKREF_DEAD_VAL); +} + +static inline bool lockref_is_dead_or_zero(const struct lockref *l) { - return ((int)l->count < 0); + int count = READ_ONCE(l->count); + return (count == __LOCKREF_DEAD_VAL || count == 0); } #endif /* __LINUX_LOCKREF_H */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e1f46a0016fc..8170bb8066a2 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -520,6 +520,22 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) return (memcg == root_mem_cgroup); } +/** + * mem_cgroup_shrink_is_root - is this a global or root-memcg shrink invocation? + * @sc: shrink_control describing the current shrinker call + * + * Returns true when @sc represents a global reclaim shrink (sc->memcg == NULL) + * or a root-memcg shrink, i.e. not a per-memcg iteration of + * shrink_slab_memcg(). Filesystems whose ->nr_cached_objects()/ + * ->free_cached_objects() implementations operate on filesystem-global state + * and do not honour sc->memcg can use this to early-return 0 in per-memcg + * contexts. + */ +static inline bool mem_cgroup_shrink_is_root(struct shrink_control *sc) +{ + return !sc->memcg || mem_cgroup_is_root(sc->memcg); +} + static inline bool obj_cgroup_is_root(const struct obj_cgroup *objcg) { return objcg->is_root; @@ -1071,6 +1087,11 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) return true; } +static inline bool mem_cgroup_shrink_is_root(struct shrink_control *sc) +{ + return true; +} + static inline bool obj_cgroup_is_root(const struct obj_cgroup *objcg) { return true; @@ -1472,6 +1493,31 @@ static inline void lruvec_lock_irq(struct lruvec *lruvec) spin_lock_irq(&lruvec->lru_lock); } +static inline struct lruvec *lruvec_live_lock_irq(struct lruvec *lruvec) +{ +#ifdef CONFIG_MEMCG + struct pglist_data *pgdat = lruvec_pgdat(lruvec); + struct mem_cgroup *memcg = lruvec_memcg(lruvec); + + rcu_read_lock(); + + /* + * The memcg can be NULL when the memory controller is disabled. + * Otherwise, the caller keeps the memcg owning @lruvec alive. + */ + while (unlikely(memcg && css_is_dying(&memcg->css))) { + memcg = parent_mem_cgroup(memcg); + lruvec = mem_cgroup_lruvec(memcg, pgdat); + } + + spin_lock_irq(&lruvec->lru_lock); +#else + lruvec_lock_irq(lruvec); +#endif + + return lruvec; +} + static inline void lruvec_unlock(struct lruvec *lruvec) { spin_unlock(&lruvec->lru_lock); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 7c9d66729c60..06c58cb05779 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -289,7 +289,7 @@ static inline void __remove_memory(u64 start, u64 size) {} /* Default online_type (MMOP_*) when new memory blocks are added. */ extern enum mmop mhp_get_default_online_type(void); extern void mhp_set_default_online_type(enum mmop online_type); -extern void __ref free_area_init_core_hotplug(struct pglist_data *pgdat); +int __ref free_area_init_core_hotplug(struct pglist_data *pgdat); extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); extern int add_memory_resource(int nid, struct resource *resource, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 695c86ee6d7a..8f18a508320d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -12215,18 +12215,7 @@ struct mlx5_ifc_mcia_reg_bits { u8 reserved_at_60[0x20]; - u8 dword_0[0x20]; - u8 dword_1[0x20]; - u8 dword_2[0x20]; - u8 dword_3[0x20]; - u8 dword_4[0x20]; - u8 dword_5[0x20]; - u8 dword_6[0x20]; - u8 dword_7[0x20]; - u8 dword_8[0x20]; - u8 dword_9[0x20]; - u8 dword_10[0x20]; - u8 dword_11[0x20]; + u8 dwords[0x400]; }; struct mlx5_ifc_dcbx_param_bits { diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 04b8f61ece5d..6b5c2390cc30 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -621,6 +621,7 @@ static inline void mmap_read_unlock(struct mm_struct *mm) DEFINE_GUARD(mmap_read_lock, struct mm_struct *, mmap_read_lock(_T), mmap_read_unlock(_T)) +DEFINE_GUARD_COND(mmap_read_lock, _try, mmap_read_trylock(_T)) static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { diff --git a/include/linux/namei.h b/include/linux/namei.h index ebe6e29f7e93..86d657b24fc6 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -97,6 +97,9 @@ struct dentry *start_creating_dentry(struct dentry *parent, struct dentry *start_removing_dentry(struct dentry *parent, struct dentry *child); +struct file *vfs_lookup_open(struct path *parent, struct qstr *last, + int open_flag, umode_t mode); + /* end_creating - finish action started with start_creating * @child: dentry returned by start_creating() or vfs_mkdir() * diff --git a/include/linux/net.h b/include/linux/net.h index f268f395ce47..fdcf9956805c 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -285,6 +285,7 @@ int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags); struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname); struct socket *sockfd_lookup(int fd, int *err); struct socket *sock_from_file(struct file *file); +int sock_read_xattr(struct socket *sock, const char *name, void *value, size_t size); #define sockfd_put(sock) fput(sock->file) int net_ratelimit(void); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9981d637f8b5..8840b126979f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -300,9 +300,11 @@ struct hh_cache { * We could use other alignment values, but we must maintain the * relationship HH alignment <= LL alignment. */ -#define LL_RESERVED_SPACE(dev) \ - ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \ +#define LL_RESERVED_SPACE_EX(dev, hlen) \ + ((((hlen) + READ_ONCE((dev)->needed_headroom)) \ & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) +#define LL_RESERVED_SPACE(dev) \ + LL_RESERVED_SPACE_EX(dev, (dev)->hard_header_len) #define LL_RESERVED_SPACE_EXTRA(dev,extra) \ ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \ & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) @@ -3531,11 +3533,6 @@ static inline bool dev_validate_header(const struct net_device *dev, if (len < dev->min_header_len) return false; - if (capable(CAP_SYS_RAWIO)) { - memset(ll_header + len, 0, dev->hard_header_len - len); - return true; - } - if (dev->header_ops && dev->header_ops->validate) return dev->header_ops->validate(ll_header, len); diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index b98331572ad2..c46864cc6623 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -244,8 +244,8 @@ extern void ip_set_type_unregister(struct ip_set_type *set_type); /* A generic IP set */ struct ip_set { - /* For call_cru in destroy */ - struct rcu_head rcu; + /* for set destruction */ + struct rcu_work rwork; /* The name of the set */ char name[IPSET_MAXNAMELEN]; /* Lock protecting the set data */ @@ -273,7 +273,7 @@ struct ip_set { /* Number of elements (vs timeout) */ u32 elements; /* Size of the dynamic extensions (vs timeout) */ - size_t ext_size; + atomic64_t ext_size; /* Element data size */ size_t dsize; /* Offsets to extensions in elements */ diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index dbc614dfe0d5..aafa0c04f917 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -115,7 +115,7 @@ struct nf_nat_sip_hooks { unsigned int *datalen); void (*seq_adjust)(struct sk_buff *skb, - unsigned int protoff, s16 off); + unsigned int protoff, s32 off); unsigned int (*expect)(struct sk_buff *skb, unsigned int protoff, diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 1bc120d61c5b..f837a501008c 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -191,7 +191,6 @@ struct netfs_io_subrequest { #define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ #define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ #define NETFS_SREQ_MADE_PROGRESS 4 /* Set if we transferred at least some data */ -#define NETFS_SREQ_ONDEMAND 5 /* Set if it's from on-demand read mode */ #define NETFS_SREQ_BOUNDARY 6 /* Set if ends on hard boundary (eg. ceph object) */ #define NETFS_SREQ_HIT_EOF 7 /* Set if short due to EOF */ #define NETFS_SREQ_IN_PROGRESS 8 /* Unlocked when the subrequest completes */ @@ -255,6 +254,7 @@ struct netfs_io_request { unsigned long long cleaned_to; /* Position we've cleaned folios to */ unsigned long long abandon_to; /* Position to abandon folios to */ const struct folio *no_unlock_folio; /* Don't unlock this folio after read */ + gfp_t gfp; /* GFP flags to use */ unsigned int direct_bv_count; /* Number of elements in direct_bv[] */ unsigned int debug_id; unsigned int rsize; /* Maximum read size (0 for none) */ @@ -373,14 +373,6 @@ struct netfs_cache_ops { loff_t *_start, size_t *_len, size_t upper_len, loff_t i_size, bool no_space_allocated_yet); - /* Prepare an on-demand read operation, shortening it to a cached/uncached - * boundary as appropriate. - */ - enum netfs_io_source (*prepare_ondemand_read)(struct netfs_cache_resources *cres, - loff_t start, size_t *_len, - loff_t i_size, - unsigned long *_flags, ino_t ino); - /* Query the occupancy of the cache in a region, returning where the * next chunk of data starts and how long it is. */ diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index f3b13da78aac..6063fe5b7784 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -214,6 +214,12 @@ static inline int nvmem_layout_register(struct nvmem_layout *layout) static inline void nvmem_layout_unregister(struct nvmem_layout *layout) {} +static inline int nvmem_add_cells_from_dt(struct nvmem_device *nvmem, + struct device_node *np) +{ + return -EOPNOTSUPP; +} + #endif /* CONFIG_NVMEM */ #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 9a00e701454c..af2e68e496e5 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -7,7 +7,7 @@ #ifdef CONFIG_OBJTOOL -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #define UNWIND_HINT(type, sp_reg, sp_offset, signal) \ "987: \n\t" \ @@ -53,7 +53,7 @@ #define __ASM_BREF(label) label ## b -#else /* __ASSEMBLY__ */ +#else /* __ASSEMBLER__ */ /* * In asm, there are two kinds of code: normal C-type callable functions and @@ -102,11 +102,11 @@ #endif .endm -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #else /* !CONFIG_OBJTOOL */ -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #define UNWIND_HINT(type, sp_reg, sp_offset, signal) "\n\t" #define STACK_FRAME_NON_STANDARD(func) diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h index c6def4049b1a..c24e9ea39269 100644 --- a/include/linux/objtool_types.h +++ b/include/linux/objtool_types.h @@ -2,7 +2,7 @@ #ifndef _LINUX_OBJTOOL_TYPES_H #define _LINUX_OBJTOOL_TYPES_H -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/types.h> @@ -18,7 +18,7 @@ struct unwind_hint { u8 signal; }; -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ /* * UNWIND_HINT_TYPE_UNDEFINED: A blind spot in ORC coverage which can result in diff --git a/include/linux/page_reporting.h b/include/linux/page_reporting.h index 9d4ca5c218a0..272b1274efdc 100644 --- a/include/linux/page_reporting.h +++ b/include/linux/page_reporting.h @@ -5,7 +5,6 @@ #include <linux/mmzone.h> #include <linux/scatterlist.h> -/* This value should always be a power of 2, see page_reporting_cycle() */ #define PAGE_REPORTING_CAPACITY 32 #define PAGE_REPORTING_ORDER_UNSPECIFIED -1 @@ -22,6 +21,9 @@ struct page_reporting_dev_info { /* Minimal order of page reporting */ unsigned int order; + + /* Max pages per report batch; 0 (default) means PAGE_REPORTING_CAPACITY */ + unsigned int capacity; }; /* Tear-down and bring-up for page reporting devices */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 1c9d40e09107..2c17239aacea 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2640,6 +2640,8 @@ #define PCI_VENDOR_ID_SUNIX 0x1fd4 #define PCI_DEVICE_ID_SUNIX_1999 0x1999 +#define PCI_VENDOR_ID_PICOHEART 0x20fa + #define PCI_VENDOR_ID_HINT 0x3388 #define PCI_DEVICE_ID_HINT_VXPROII_IDE 0x8013 diff --git a/include/linux/pcie-dwc.h b/include/linux/pcie-dwc.h index 8ff778e7aec0..d3cd701a58e3 100644 --- a/include/linux/pcie-dwc.h +++ b/include/linux/pcie-dwc.h @@ -26,6 +26,8 @@ static const struct dwc_pcie_vsec_id dwc_pcie_rasdes_vsec_ids[] = { .vsec_id = 0x02, .vsec_rev = 0x4 }, { .vendor_id = PCI_VENDOR_ID_AMPERE, .vsec_id = 0x02, .vsec_rev = 0x4 }, + { .vendor_id = PCI_VENDOR_ID_PICOHEART, + .vsec_id = 0x02, .vsec_rev = 0x4 }, { .vendor_id = PCI_VENDOR_ID_QCOM, .vsec_id = 0x02, .vsec_rev = 0x4 }, { .vendor_id = PCI_VENDOR_ID_ROCKCHIP, diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 52b37f7bdbf9..02d2c7f45b52 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -119,7 +119,7 @@ struct arm_pmu { /* PMUv3 only */ int pmuver; - bool has_smt; + bool avoid_pmccntr; u64 reg_pmmir; u64 reg_brbidr; #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 7f6a92ac9704..6402930282e5 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -14,6 +14,9 @@ #define PIPE_BUF_FLAG_LOSS 0x40 /* Message loss happened after this buffer */ #endif +#define PIPE_PREALLOC_MAX 8 /* max pages in prealloc pool */ +#define PIPE_PREALLOC_KEEP 2 /* keep at least this many after trim */ + /** * struct pipe_buffer - a linux kernel pipe buffer * @page: the page containing the data for the pipe buffer @@ -59,6 +62,21 @@ union pipe_index { }; /** + * struct anon_pipe_prealloc - per-pipe page preallocation pool + * @pages: array of cached pages (pool) + * @count: number of pages currently in the pool + * + * Each pipe keeps a small bounded pool of preallocated pages to reduce + * allocation overhead during writes. The pool is bounded at PIPE_PREALLOC_MAX + * and trimmed down to PIPE_PREALLOC_KEEP after a write completes. + */ +struct anon_pipe_prealloc { + struct page *pages[PIPE_PREALLOC_MAX]; + + unsigned int __data_racy count; +}; + +/** * struct pipe_inode_info - a linux kernel pipe * @mutex: mutex protecting the whole thing * @rd_wait: reader wait point in case of empty pipe @@ -68,13 +86,13 @@ union pipe_index { * @max_usage: The maximum number of slots that may be used in the ring * @ring_size: total number of buffers (should be a power of 2) * @nr_accounted: The amount this pipe accounts for in user->pipe_bufs - * @tmp_page: cached released page + * @prealloc: per-pipe page preallocation pool * @readers: number of current readers of this pipe * @writers: number of current writers of this pipe * @files: number of struct file referring this pipe (protected by ->i_lock) * @r_counter: reader counter * @w_counter: writer counter - * @poll_usage: is this pipe used for epoll, which has crazy wakeups? + * @pseudo_edgetrigger: has an EPOLLET consumer, enable per-write wakeups * @fasync_readers: reader side fasync * @fasync_writers: writer side fasync * @bufs: the circular array of pipe buffers @@ -95,11 +113,11 @@ struct pipe_inode_info { unsigned int files; unsigned int r_counter; unsigned int w_counter; - bool poll_usage; + bool pseudo_edgetrigger; #ifdef CONFIG_WATCH_QUEUE bool note_loss; #endif - struct page *tmp_page[2]; + struct anon_pipe_prealloc prealloc; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; struct pipe_buffer *bufs; diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 4d3dbcef379e..9a1a0c61361c 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -37,7 +37,7 @@ static inline int clockid_to_fd(const clockid_t clk) return ~(clk >> 3); } -static inline bool clockid_aux_valid(clockid_t id) +static inline bool clockid_is_aux_clock(clockid_t id) { return IS_ENABLED(CONFIG_POSIX_AUX_CLOCKS) && id >= CLOCK_AUX && id <= CLOCK_AUX_LAST; } @@ -47,7 +47,7 @@ static inline bool clockid_aux_valid(clockid_t id) #include <linux/signal_types.h> /** - * cpu_timer - Posix CPU timer representation for k_itimer + * struct cpu_timer - Posix CPU timer representation for k_itimer * @node: timerqueue node to queue in the task/sig * @head: timerqueue head on which this timer is queued * @pid: Pointer to target task PID @@ -174,6 +174,7 @@ static inline void posix_cputimers_init_work(void) { } * @it_sigqueue_seq: The sequence count at the point where the signal was queued * @it_sigev_notify: The notify word of sigevent struct for signal delivery * @it_interval: The interval for periodic timers + * @it_pid_type: The type of the PID * @it_signal: Pointer to the creators signal struct * @it_pid: The pid of the process/task targeted by the signal * @it_process: The task to wakeup on clock_nanosleep (CPU timers) diff --git a/include/linux/posix-timers_types.h b/include/linux/posix-timers_types.h index a4712c1008c9..b40cf352e01d 100644 --- a/include/linux/posix-timers_types.h +++ b/include/linux/posix-timers_types.h @@ -34,7 +34,7 @@ #ifdef CONFIG_POSIX_TIMERS /** - * posix_cputimer_base - Container per posix CPU clock + * struct posix_cputimer_base - Container per posix CPU clock * @nextevt: Earliest-expiration cache * @tqhead: timerqueue head for cpu_timers */ @@ -44,7 +44,7 @@ struct posix_cputimer_base { }; /** - * posix_cputimers - Container for posix CPU timer related data + * struct posix_cputimers - Container for posix CPU timer related data * @bases: Base container for posix CPU clocks * @timers_active: Timers are queued. * @expiry_active: Timer expiry is active. Used for @@ -60,7 +60,7 @@ struct posix_cputimers { }; /** - * posix_cputimers_work - Container for task work based posix CPU timer expiry + * struct posix_cputimers_work - Container for task work based posix CPU timer expiry * @work: The task work to be scheduled * @mutex: Mutex held around expiry in context of this task work * @scheduled: @work has been scheduled already, no further processing diff --git a/include/linux/preempt.h b/include/linux/preempt.h index d964f965c8ff..8299657f0f86 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -17,6 +17,9 @@ * * - bits 0-7 are the preemption count (max preemption depth: 256) * - bits 8-15 are the softirq count (max # of softirqs: 256) + * - bits 16-23 are the hardirq disable count (max # of hardirq disable: 256) + * - bits 24-27 are the hardirq count (max # of hardirqs: 16) + * - bit 28 is the NMI flag (no nesting count, tracked separately) * * The hardirq count could in theory be the same as the number of * interrupts in the system, but we run all interrupt handlers with @@ -24,31 +27,56 @@ * there are a few palaeontologic drivers which reenable interrupts in * the handler, so we need more than one bit here. * + * NMI nesting depth is tracked in a separate per-CPU variable + * (nmi_nesting) to save bits in preempt_count. + * * PREEMPT_MASK: 0x000000ff * SOFTIRQ_MASK: 0x0000ff00 - * HARDIRQ_MASK: 0x000f0000 - * NMI_MASK: 0x00f00000 + * HARDIRQ_DISABLE_MASK: 0x00ff0000 + * HARDIRQ_MASK: 0x0f000000 + * + * When HAS_SEPARATE_PREEMPT_RESCHED_BITS=y, PREEMPT_NEED_RESCHED is put in a + * separate word and that allows 64bit load-store architectures to 'set' + * PREEMPT_NEED_RESCHED without messing up the otherwise symmetric + * modifications used on preempt_count and still load the whole thing + * (single-copy) atomically, without having to resort to full atomic + * operations. + * + * Because of the above, NMI_MASK bits are different depending on + * HAS_SEPARATE_PREEMPT_RESCHED_BITS: + * + * - HAS_SEPARATE_PREEMPT_RESCHED_BITS=n: + * + * NMI_MASK: 0x10000000 * PREEMPT_NEED_RESCHED: 0x80000000 + * + * - HAS_SEPARATE_PREEMPT_RESCHED_BITS=y: + * NMI_MASK: 0xf0000000 + * (PREEMPT_NEED_RESCHED is in a different word) */ #define PREEMPT_BITS 8 #define SOFTIRQ_BITS 8 +#define HARDIRQ_DISABLE_BITS 8 #define HARDIRQ_BITS 4 -#define NMI_BITS 4 +#define NMI_BITS (1 + 3*IS_ENABLED(CONFIG_HAS_SEPARATE_PREEMPT_RESCHED_BITS)) #define PREEMPT_SHIFT 0 #define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) -#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) +#define HARDIRQ_DISABLE_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) +#define HARDIRQ_SHIFT (HARDIRQ_DISABLE_SHIFT + HARDIRQ_DISABLE_BITS) #define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS) #define __IRQ_MASK(x) ((1UL << (x))-1) #define PREEMPT_MASK (__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT) #define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) +#define HARDIRQ_DISABLE_MASK (__IRQ_MASK(HARDIRQ_DISABLE_BITS) << HARDIRQ_DISABLE_SHIFT) #define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) #define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT) #define PREEMPT_OFFSET (1UL << PREEMPT_SHIFT) #define SOFTIRQ_OFFSET (1UL << SOFTIRQ_SHIFT) +#define HARDIRQ_DISABLE_OFFSET (1UL << HARDIRQ_DISABLE_SHIFT) #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) #define NMI_OFFSET (1UL << NMI_SHIFT) @@ -105,8 +133,8 @@ static __always_inline unsigned char interrupt_context_level(void) * preempt_count() is commonly implemented with READ_ONCE(). */ -#define nmi_count() (preempt_count() & NMI_MASK) -#define hardirq_count() (preempt_count() & HARDIRQ_MASK) +#define nmi_count() (preempt_count() & NMI_MASK) +#define hardirq_count() (preempt_count() & HARDIRQ_MASK) #ifdef CONFIG_PREEMPT_RT # define softirq_count() (current->softirq_disable_cnt & SOFTIRQ_MASK) # define irq_count() ((preempt_count() & (NMI_MASK | HARDIRQ_MASK)) | softirq_count()) @@ -140,6 +168,10 @@ static __always_inline unsigned char interrupt_context_level(void) #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) +#define hardirq_disable_count() ((preempt_count() & HARDIRQ_DISABLE_MASK) >> HARDIRQ_DISABLE_SHIFT) +#define hardirq_disable_enter() __preempt_count_add_return(HARDIRQ_DISABLE_OFFSET) +#define hardirq_disable_exit() __preempt_count_sub_return(HARDIRQ_DISABLE_OFFSET) + /* * The preempt_count offset after preempt_disable(); */ diff --git a/include/linux/psi.h b/include/linux/psi.h index e0745873e3f2..7966e3ac03b9 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -25,7 +25,9 @@ void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, enum psi_res res, struct file *file, - struct kernfs_open_file *of); + struct kernfs_open_file *of, + bool *need_rtpoll_worker); +int psi_trigger_create_rtpoll_worker(struct psi_group *group); void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index c95e891903f0..d2c3629bbe45 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -98,29 +98,13 @@ static inline bool ptr_ring_full_bh(struct ptr_ring *r) /* Note: callers invoking this in a loop must use a compiler barrier, * for example cpu_relax(). Callers must hold producer_lock. - */ -static inline int __ptr_ring_check_produce(struct ptr_ring *r) -{ - if (unlikely(!r->size)) - return -EINVAL; - - if (data_race(r->queue[r->producer])) - return -ENOSPC; - - return 0; -} - -/* Note: callers invoking this in a loop must use a compiler barrier, - * for example cpu_relax(). Callers must hold producer_lock. * Callers are responsible for making sure pointer that is being queued * points to a valid data. */ static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr) { - int p = __ptr_ring_check_produce(r); - - if (p) - return p; + if (unlikely(!r->size) || data_race(r->queue[r->producer])) + return -ENOSPC; /* Make sure the pointer we are storing points to a valid data. */ /* Pairs with the dependency ordering in __ptr_ring_consume. */ diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index ef314f7a9ecc..2839d5c8eaa0 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -405,13 +405,13 @@ extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oa /* * ptrace report for syscall entry and exit looks identical. */ -static inline int ptrace_report_syscall(unsigned long message) +static inline bool ptrace_report_syscall(unsigned long message) { int ptrace = current->ptrace; int signr; if (!(ptrace & PT_PTRACED)) - return 0; + return true; signr = ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0), message); @@ -424,11 +424,11 @@ static inline int ptrace_report_syscall(unsigned long message) if (signr) send_sig(signr, current, 1); - return fatal_signal_pending(current); + return !fatal_signal_pending(current); } /** - * ptrace_report_syscall_entry - task is about to attempt a system call + * ptrace_report_syscall_permit_entry - task is about to attempt a system call * @regs: user register state of current task * * This will be called if %SYSCALL_WORK_SYSCALL_TRACE or @@ -438,7 +438,7 @@ static inline int ptrace_report_syscall(unsigned long message) * call number and arguments to be tried. It is safe to block here, * preventing the system call from beginning. * - * Returns zero normally, or nonzero if the calling arch code should abort + * Returns True normally, or False if the calling architecture code should abort * the system call. That must prevent normal entry so no system call is * made. If @task ever returns to user mode after this, its register state * is unspecified, but should be something harmless like an %ENOSYS error @@ -447,8 +447,7 @@ static inline int ptrace_report_syscall(unsigned long message) * * Called without locks, just after entering kernel mode. */ -static inline __must_check int ptrace_report_syscall_entry( - struct pt_regs *regs) +static inline __must_check bool ptrace_report_syscall_permit_entry(struct pt_regs *regs) { return ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_ENTRY); } diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index 024fc20e7762..d8b939f50bba 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -77,8 +77,27 @@ static __always_inline u32 get_kstack_offset(void) } \ } while (0) +/** + * add_random_kstack_offset_irqsoff - Increase stack utilization by a random offset. + * + * This should be used in the syscall entry path after user registers have been + * stored to the stack. Interrupts must be still disabled. + */ +#define add_random_kstack_offset_irqsoff() \ +do { \ + lockdep_assert_irqs_disabled(); \ + if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ + &randomize_kstack_offset)) { \ + u32 offset = prandom_u32_state(raw_cpu_ptr(&kstack_rnd_state)); \ + u8 *ptr = __kstack_alloca(KSTACK_OFFSET_MAX(offset)); \ + /* Keep allocation even after "ptr" loses scope. */ \ + asm volatile("" :: "r"(ptr) : "memory"); \ + } \ +} while (0) + #else /* CONFIG_RANDOMIZE_KSTACK_OFFSET */ #define add_random_kstack_offset() do { } while (0) +#define add_random_kstack_offset_irqsoff() do { } while (0) #endif /* CONFIG_RANDOMIZE_KSTACK_OFFSET */ #endif diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 73ff522448a0..dd09c2ce9a0f 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -54,11 +54,11 @@ enum resctrl_res_level { RDT_RESOURCE_MBA, RDT_RESOURCE_SMBA, RDT_RESOURCE_PERF_PKG, - - /* Must be the last */ - RDT_NUM_RESOURCES, + RDT_RESOURCE_LAST = RDT_RESOURCE_PERF_PKG }; +#define RDT_NUM_RESOURCES (RDT_RESOURCE_LAST + 1) + /** * enum resctrl_conf_type - The type of configuration. * @CDP_NONE: No prioritisation, both code and data are controlled or monitored. @@ -69,9 +69,10 @@ enum resctrl_conf_type { CDP_NONE, CDP_CODE, CDP_DATA, + CDP_LAST = CDP_DATA }; -#define CDP_NUM_TYPES (CDP_DATA + 1) +#define CDP_NUM_TYPES (CDP_LAST + 1) /* * struct pseudo_lock_region - pseudo-lock region information @@ -323,7 +324,7 @@ struct resctrl_mon { * @cdp_capable: Is the CDP feature available on this resource */ struct rdt_resource { - int rid; + enum resctrl_res_level rid; bool alloc_capable; bool mon_capable; enum resctrl_scope ctrl_scope; diff --git a/include/linux/rolling_buffer.h b/include/linux/rolling_buffer.h index ac15b1ffdd83..9e5dad29669c 100644 --- a/include/linux/rolling_buffer.h +++ b/include/linux/rolling_buffer.h @@ -43,13 +43,13 @@ struct rolling_buffer_snapshot { #define ROLLBUF_MARK_2 BIT(1) int rolling_buffer_init(struct rolling_buffer *roll, unsigned int rreq_id, - unsigned int direction); -int rolling_buffer_make_space(struct rolling_buffer *roll); + unsigned int direction, gfp_t gfp); +int rolling_buffer_make_space(struct rolling_buffer *roll, gfp_t gfp); ssize_t rolling_buffer_load_from_ra(struct rolling_buffer *roll, struct readahead_control *ractl, struct folio_batch *put_batch); ssize_t rolling_buffer_append(struct rolling_buffer *roll, struct folio *folio, - unsigned int flags); + unsigned int flags, gfp_t gfp); struct folio_queue *rolling_buffer_delete_spent(struct rolling_buffer *roll); void rolling_buffer_clear(struct rolling_buffer *roll); diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h index ed9da6e41a2a..31ce349ed42c 100644 --- a/include/linux/rseq_entry.h +++ b/include/linux/rseq_entry.h @@ -233,6 +233,7 @@ efault: static __always_inline bool rseq_grant_slice_extension(unsigned long ti_work, unsigned long mask) { if (unlikely(__rseq_grant_slice_extension(ti_work & mask))) { + guard(irq)(); hrtimer_rearm_deferred_tif(ti_work); return true; } diff --git a/include/linux/sched.h b/include/linux/sched.h index 373bcc0598d1..193a4a4dcc27 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -550,7 +550,6 @@ struct sched_statistics { s64 exec_max; u64 slice_max; - u64 nr_migrations_cold; u64 nr_failed_migrations_affine; u64 nr_failed_migrations_running; u64 nr_failed_migrations_hot; @@ -563,8 +562,6 @@ struct sched_statistics { u64 nr_wakeups_remote; u64 nr_wakeups_affine; u64 nr_wakeups_affine_attempts; - u64 nr_wakeups_passive; - u64 nr_wakeups_idle; #ifdef CONFIG_SCHED_CORE u64 core_forceidle_sum; @@ -575,6 +572,7 @@ struct sched_statistics { struct sched_entity { /* For load-balancing: */ struct load_weight load; + struct load_weight h_load; struct rb_node run_node; u64 deadline; u64 min_vruntime; @@ -823,6 +821,17 @@ struct kmap_ctrl { #endif }; +#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPTION) +struct task_ipi_mask { + union { + cpumask_t *ipi_mask_ptr; + unsigned long ipi_mask_val; + }; +}; +#else +struct task_ipi_mask { }; +#endif + struct task_struct { #ifdef CONFIG_THREAD_INFO_IN_TASK /* @@ -1191,6 +1200,7 @@ struct task_struct { unsigned long last_switch_time; #endif /* Filesystem information: */ + struct fs_struct *real_fs; struct fs_struct *fs; /* Open file information: */ @@ -1359,6 +1369,7 @@ struct task_struct { struct list_head perf_event_list; struct perf_ctx_data __rcu *perf_ctx_data; #endif + struct task_ipi_mask __private ipi_mask; #ifdef CONFIG_DEBUG_PREEMPT unsigned long preempt_disable_ip; #endif diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 20b2343aa344..87e353f7e011 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -244,11 +244,11 @@ struct sched_ext_entity { * to %SCHED_EXT with -%EACCES. * * Can be set from ops.init_task() while the BPF scheduler is being - * loaded (!scx_init_task_args->fork). If set and the task's policy is - * already %SCHED_EXT, the task's policy is rejected and forcefully - * reverted to %SCHED_NORMAL. The number of such events are reported - * through /sys/kernel/debug/sched_ext::nr_rejected. Setting this flag - * during fork is not allowed. + * loaded. If set and the task's policy is already %SCHED_EXT, the + * task's policy is rejected and forcefully reverted to %SCHED_NORMAL. + * The number of such events are reported through + * /sys/kernel/sched_ext/nr_rejected. Setting this flag from any other + * ops.init_task() invocation, such as during fork, fails the scheduler. */ bool disallow; /* reject switching into SCX */ diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index 42839cfa2778..dc3ec2452ee1 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -146,8 +146,7 @@ SD_FLAG(SD_ASYM_PACKING, SDF_NEEDS_GROUPS) /* * Prefer to place tasks in a sibling domain * - * Set up until domains start spanning NUMA nodes. Close to being a SHARED_CHILD - * flag, but cleared below domains with SD_ASYM_CPUCAPACITY. + * Set up until domains start spanning NUMA nodes. * * NEEDS_GROUPS: Load balancing flag. */ diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 41ed884cffc9..e0c1ca8c6a18 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -31,6 +31,7 @@ struct kernel_clone_args { u32 io_thread:1; u32 user_worker:1; u32 no_files:1; + u32 umh:1; unsigned long stack; unsigned long stack_size; unsigned long tls; diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 9b959972bf4a..fcb3eb9825e5 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -22,14 +22,14 @@ #include <linux/atomic.h> #include <asm/seccomp.h> -extern int __secure_computing(void); +extern bool __seccomp_permit_syscall(void); #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER -static inline int secure_computing(void) +static __always_inline bool seccomp_permit_syscall(void) { if (unlikely(test_syscall_work(SECCOMP))) - return __secure_computing(); - return 0; + return __seccomp_permit_syscall(); + return true; } #else extern void secure_computing_strict(int this_syscall); @@ -50,11 +50,11 @@ static inline int seccomp_mode(struct seccomp *s) struct seccomp_data; #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER -static inline int secure_computing(void) { return 0; } +static inline bool seccomp_permit_syscall(void) { return true; } #else static inline void secure_computing_strict(int this_syscall) { return; } #endif -static inline int __secure_computing(void) { return 0; } +static inline bool __seccomp_permit_syscall(void) { return true; } static inline long prctl_get_seccomp(void) { diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 2fb266ea69fa..dc0e8c62d9e0 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -104,7 +104,7 @@ static inline void seq_setwidth(struct seq_file *m, size_t size) } void seq_pad(struct seq_file *m, char c); -char *mangle_path(char *s, const char *p, const char *esc); +char *seq_mangle_path(char *s, const char *p, const char *esc); int seq_open(struct file *, const struct seq_operations *); ssize_t seq_read(struct file *, char __user *, size_t, loff_t *); ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter); diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index a8553401b1c9..d5e35f24738d 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -551,20 +551,6 @@ static inline void psock_progs_drop(struct sk_psock_progs *progs) psock_set_prog(&progs->skb_verdict, NULL); } -/* for tcp only, sk is locked */ -static inline ssize_t sk_psock_msg_inq(struct sock *sk) -{ - struct sk_psock *psock; - ssize_t inq = 0; - - psock = sk_psock_get(sk); - if (likely(psock)) { - inq = sk_psock_get_msg_len_nolock(psock); - sk_psock_put(sk, psock); - } - return inq; -} - /* for udp only, sk is not locked */ static inline ssize_t sk_msg_first_len(struct sock *sk) { diff --git a/include/linux/slab.h b/include/linux/slab.h index 51f03f18c9a7..32c9f8ed7ae2 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -58,10 +58,13 @@ enum _slab_flag_bits { #endif _SLAB_OBJECT_POISON, _SLAB_CMPXCHG_DOUBLE, +#ifdef CONFIG_SLAB_OBJ_EXT _SLAB_NO_OBJ_EXT, -#if defined(CONFIG_SLAB_OBJ_EXT) && defined(CONFIG_64BIT) +#ifdef CONFIG_64BIT _SLAB_OBJ_EXT_IN_OBJ, #endif +#endif + _SLAB_NO_SHEAVES, _SLAB_FLAGS_LAST_BIT }; @@ -239,8 +242,14 @@ enum _slab_flag_bits { #endif #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ -/* Slab created using create_boot_cache */ +/* Slab caches without obj_exts array */ +#ifdef CONFIG_SLAB_OBJ_EXT #define SLAB_NO_OBJ_EXT __SLAB_FLAG_BIT(_SLAB_NO_OBJ_EXT) +#else +#define SLAB_NO_OBJ_EXT __SLAB_FLAG_UNUSED +#endif + +#define SLAB_NO_SHEAVES __SLAB_FLAG_BIT(_SLAB_NO_SHEAVES) #if defined(CONFIG_SLAB_OBJ_EXT) && defined(CONFIG_64BIT) #define SLAB_OBJ_EXT_IN_OBJ __SLAB_FLAG_BIT(_SLAB_OBJ_EXT_IN_OBJ) @@ -505,8 +514,12 @@ typedef struct { unsigned long v; } kmalloc_token_t; extern unsigned long random_kmalloc_seed; #define __kmalloc_token(...) ((kmalloc_token_t){ .v = _CODE_LOCATION_ }) #elif defined(CONFIG_KMALLOC_PARTITION_TYPED) +#ifdef __CHECKER__ +#define __kmalloc_token(...) ((kmalloc_token_t){ .v = 0 }) +#else /* !__CHECKER__ */ #define __kmalloc_token(...) ((kmalloc_token_t){ .v = __builtin_infer_alloc_token(__VA_ARGS__) }) -#endif +#endif /* __CHECKER__ */ +#endif /* CONFIG_KMALLOC_PARTITION_TYPED */ #define DECL_TOKEN_PARAM(_token) , kmalloc_token_t (_token) #define _PASS_TOKEN_PARAM(_token) , (_token) #define PASS_TOKEN_PARAM(_token) (_token) @@ -700,6 +713,9 @@ enum kmalloc_cache_type { #ifndef CONFIG_MEMCG KMALLOC_CGROUP = KMALLOC_NORMAL, #endif +#ifndef CONFIG_SLAB_OBJ_EXT + KMALLOC_NO_OBJ_EXT = KMALLOC_NORMAL, +#endif KMALLOC_PARTITION_START = KMALLOC_NORMAL, KMALLOC_PARTITION_END = KMALLOC_PARTITION_START + KMALLOC_PARTITION_CACHES_NR, #ifdef CONFIG_SLUB_TINY @@ -713,6 +729,9 @@ enum kmalloc_cache_type { #ifdef CONFIG_MEMCG KMALLOC_CGROUP, #endif +#ifdef CONFIG_SLAB_OBJ_EXT + KMALLOC_NO_OBJ_EXT, +#endif NR_KMALLOC_TYPES }; diff --git a/include/linux/smp.h b/include/linux/smp.h index 6925d15ccaa7..2dfa7390717a 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -47,8 +47,7 @@ extern void __smp_call_single_queue(int cpu, struct llist_node *node); /* total number of cpus in this system (may exceed NR_CPUS) */ extern unsigned int total_cpus; -int smp_call_function_single(int cpuid, smp_call_func_t func, void *info, - int wait); +int smp_call_function_single(int cpuid, smp_call_func_t func, void *info, bool wait); void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait, const struct cpumask *mask); @@ -239,6 +238,18 @@ static inline int get_boot_cpu_id(void) #endif /* !SMP */ +#if defined(CONFIG_PREEMPTION) && defined(CONFIG_SMP) +int smp_task_ipi_mask_alloc(struct task_struct *task); +void smp_task_ipi_mask_free(struct task_struct *task); +#else +static inline int smp_task_ipi_mask_alloc(struct task_struct *task) +{ + return 0; +} + +static inline void smp_task_ipi_mask_free(struct task_struct *task) { } +#endif + /* * raw_smp_processor_id() - get the current (unstable) CPU id * diff --git a/include/linux/soc/qcom/geni-se.h b/include/linux/soc/qcom/geni-se.h index c5e6ab85df09..0991ef7ec092 100644 --- a/include/linux/soc/qcom/geni-se.h +++ b/include/linux/soc/qcom/geni-se.h @@ -124,6 +124,7 @@ struct geni_se { #define SE_DMA_RX_FSM_RST 0xd58 #define SE_HW_PARAM_0 0xe24 #define SE_HW_PARAM_1 0xe28 +#define SE_HW_PARAM_2 0xe2c /* GENI_FORCE_DEFAULT_REG fields */ #define FORCE_DEFAULT BIT(0) @@ -291,6 +292,9 @@ struct geni_se { #define RX_FIFO_DEPTH_MSK GENMASK(21, 16) #define RX_FIFO_DEPTH_SHFT 16 +/* SE_HW_PARAM_2 fields */ +#define PROG_RAM_DEPTH_MSK GENMASK(10, 0) + #define HW_VER_MAJOR_MASK GENMASK(31, 28) #define HW_VER_MAJOR_SHFT 28 #define HW_VER_MINOR_MASK GENMASK(27, 16) diff --git a/include/linux/soc/qcom/smem.h b/include/linux/soc/qcom/smem.h index f946e3beca21..3249cbd2016b 100644 --- a/include/linux/soc/qcom/smem.h +++ b/include/linux/soc/qcom/smem.h @@ -17,4 +17,6 @@ int qcom_smem_get_feature_code(u32 *code); int qcom_smem_bust_hwspin_lock_by_host(unsigned int host); +int qcom_smem_dram_get_hbb(void); + #endif diff --git a/include/linux/soc/qcom/ubwc.h b/include/linux/soc/qcom/ubwc.h index 83d2c2a7116c..f3a70360b177 100644 --- a/include/linux/soc/qcom/ubwc.h +++ b/include/linux/soc/qcom/ubwc.h @@ -8,25 +8,12 @@ #define __QCOM_UBWC_H__ #include <linux/bits.h> +#include <linux/err.h> #include <linux/printk.h> #include <linux/types.h> struct qcom_ubwc_cfg_data { u32 ubwc_enc_version; - /* Can be read from MDSS_BASE + 0x58 */ - u32 ubwc_dec_version; - - /** - * @ubwc_swizzle: Whether to enable level 1, 2 & 3 bank swizzling. - * - * UBWC 1.0 always enables all three levels. - * UBWC 2.0 removes level 1 bank swizzling, leaving levels 2 & 3. - * UBWC 4.0 adds the optional ability to disable levels 2 & 3. - */ - u32 ubwc_swizzle; -#define UBWC_SWIZZLE_ENABLE_LVL1 BIT(0) -#define UBWC_SWIZZLE_ENABLE_LVL2 BIT(1) -#define UBWC_SWIZZLE_ENABLE_LVL3 BIT(2) /** * @highest_bank_bit: Highest Bank Bit @@ -35,16 +22,10 @@ struct qcom_ubwc_cfg_data { * DDR bank. This should ideally use DRAM type detection. */ int highest_bank_bit; - bool ubwc_bank_spread; - /** - * @macrotile_mode: Macrotile Mode - * - * Whether to use 4-channel macrotiling mode or the newer - * 8-channel macrotiling mode introduced in UBWC 3.1. 0 is - * 4-channel and 1 is 8-channel. - */ - bool macrotile_mode; + unsigned int flags; +#define UBWC_FLAG_DISABLE_SWIZZLE_LVL2 BIT(0) +#define UBWC_FLAG_DISABLE_SWIZZLE_LVL3 BIT(1) }; #define UBWC_1_0 0x10000000 @@ -67,37 +48,62 @@ static inline const struct qcom_ubwc_cfg_data *qcom_ubwc_config_get_data(void) static inline bool qcom_ubwc_get_ubwc_mode(const struct qcom_ubwc_cfg_data *cfg) { - bool ret = cfg->ubwc_enc_version == UBWC_1_0; - - if (ret && !(cfg->ubwc_swizzle & UBWC_SWIZZLE_ENABLE_LVL1)) - pr_err("UBWC config discrepancy - level 1 swizzling disabled on UBWC 1.0\n"); - - return ret; + return cfg->ubwc_enc_version == UBWC_1_0; } -/* - * This is the best guess, based on the MDSS driver, which worked so far. - */ static inline bool qcom_ubwc_min_acc_length_64b(const struct qcom_ubwc_cfg_data *cfg) { - return cfg->ubwc_enc_version == UBWC_1_0 && - (cfg->ubwc_dec_version == UBWC_2_0 || - cfg->ubwc_dec_version == UBWC_3_0); + return cfg->ubwc_enc_version == UBWC_1_0; } +/* + * @qcom_ubwc_macrotile_mode: whether to use 4-channel or 8-channel macrotiling + * + * The 8-channel macrotiling mode was introduced in UBWC 3.1. + * + * Returns: false for the 4-channel and true for 8-channel. + */ static inline bool qcom_ubwc_macrotile_mode(const struct qcom_ubwc_cfg_data *cfg) { - return cfg->macrotile_mode; + return cfg->ubwc_enc_version >= UBWC_3_1; } static inline bool qcom_ubwc_bank_spread(const struct qcom_ubwc_cfg_data *cfg) { - return cfg->ubwc_bank_spread; + return true; } +#define UBWC_SWIZZLE_ENABLE_LVL1 BIT(0) +#define UBWC_SWIZZLE_ENABLE_LVL2 BIT(1) +#define UBWC_SWIZZLE_ENABLE_LVL3 BIT(2) + +/** + * @qcom_ubwc_swizzle: Whether to enable level 1, 2 & 3 bank swizzling. + * + * UBWC 1.0 always enables all three levels. + * UBWC 2.0 removes level 1 bank swizzling, leaving levels 2 & 3. + * UBWC 4.0 adds the optional ability to disable levels 2 & 3. + */ static inline u32 qcom_ubwc_swizzle(const struct qcom_ubwc_cfg_data *cfg) { - return cfg->ubwc_swizzle; + if (cfg->ubwc_enc_version == 0) + return 0; + + if (cfg->ubwc_enc_version == UBWC_1_0) + return UBWC_SWIZZLE_ENABLE_LVL1 | + UBWC_SWIZZLE_ENABLE_LVL2 | + UBWC_SWIZZLE_ENABLE_LVL3; + + u32 ubwc_swizzle = UBWC_SWIZZLE_ENABLE_LVL2 | + UBWC_SWIZZLE_ENABLE_LVL3; + + if (cfg->flags & UBWC_FLAG_DISABLE_SWIZZLE_LVL2) + ubwc_swizzle &= ~UBWC_SWIZZLE_ENABLE_LVL2; + + if (cfg->flags & UBWC_FLAG_DISABLE_SWIZZLE_LVL3) + ubwc_swizzle &= ~UBWC_SWIZZLE_ENABLE_LVL3; + + return ubwc_swizzle; } static inline u32 qcom_ubwc_version_tag(const struct qcom_ubwc_cfg_data *cfg) diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 241277cd34cf..799a8f7d2741 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -57,6 +57,7 @@ #include <linux/linkage.h> #include <linux/compiler.h> #include <linux/irqflags.h> +#include <linux/interrupt_rc.h> #include <linux/thread_info.h> #include <linux/stringify.h> #include <linux/bottom_half.h> @@ -273,9 +274,11 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) #endif #define raw_spin_lock_irq(lock) _raw_spin_lock_irq(lock) +#define raw_spin_lock_irq_disable(lock) _raw_spin_lock_irq_disable(lock) #define raw_spin_lock_bh(lock) _raw_spin_lock_bh(lock) #define raw_spin_unlock(lock) _raw_spin_unlock(lock) #define raw_spin_unlock_irq(lock) _raw_spin_unlock_irq(lock) +#define raw_spin_unlock_irq_enable(lock) _raw_spin_unlock_irq_enable(lock) #define raw_spin_unlock_irqrestore(lock, flags) \ do { \ @@ -290,6 +293,8 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) #define raw_spin_trylock_irqsave(lock, flags) _raw_spin_trylock_irqsave(lock, &(flags)) +#define raw_spin_trylock_irq_disable(lock) _raw_spin_trylock_irq_disable(lock) + #ifndef CONFIG_PREEMPT_RT /* Include rwlock functions for !RT */ #include <linux/rwlock.h> @@ -372,6 +377,12 @@ static __always_inline void spin_lock_irq(spinlock_t *lock) raw_spin_lock_irq(&lock->rlock); } +static __always_inline void spin_lock_irq_disable(spinlock_t *lock) + __acquires(lock) __no_context_analysis +{ + raw_spin_lock_irq_disable(&lock->rlock); +} + #define spin_lock_irqsave(lock, flags) \ do { \ raw_spin_lock_irqsave(spinlock_check(lock), flags); \ @@ -402,6 +413,12 @@ static __always_inline void spin_unlock_irq(spinlock_t *lock) raw_spin_unlock_irq(&lock->rlock); } +static __always_inline void spin_unlock_irq_enable(spinlock_t *lock) + __releases(lock) __no_context_analysis +{ + raw_spin_unlock_irq_enable(&lock->rlock); +} + static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) __releases(lock) __no_context_analysis { @@ -427,6 +444,12 @@ static __always_inline bool _spin_trylock_irqsave(spinlock_t *lock, unsigned lon } #define spin_trylock_irqsave(lock, flags) _spin_trylock_irqsave(lock, &(flags)) +static __always_inline int spin_trylock_irq_disable(spinlock_t *lock) + __cond_acquires(true, lock) __no_context_analysis +{ + return raw_spin_trylock_irq_disable(&lock->rlock); +} + /** * spin_is_locked() - Check whether a spinlock is locked. * @lock: Pointer to the spinlock. @@ -549,12 +572,12 @@ DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_nested, __acquires(_T), __releases(*(raw #define class_raw_spinlock_nested_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_nested, _T) DEFINE_LOCK_GUARD_1(raw_spinlock_irq, raw_spinlock_t, - raw_spin_lock_irq(_T->lock), - raw_spin_unlock_irq(_T->lock)) + raw_spin_lock_irq_disable(_T->lock), + raw_spin_unlock_irq_enable(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_irq, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_irq_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_irq, _T) -DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irq, _try, raw_spin_trylock_irq(_T->lock)) +DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irq, _try, raw_spin_trylock_irq_disable(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_irq_try, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_irq_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_irq_try, _T) @@ -569,14 +592,13 @@ DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_bh_try, __acquires(_T), __releases(*(raw #define class_raw_spinlock_bh_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_bh_try, _T) DEFINE_LOCK_GUARD_1(raw_spinlock_irqsave, raw_spinlock_t, - raw_spin_lock_irqsave(_T->lock, _T->flags), - raw_spin_unlock_irqrestore(_T->lock, _T->flags), - unsigned long flags) + raw_spin_lock_irq_disable(_T->lock), + raw_spin_unlock_irq_enable(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_irqsave, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_irqsave_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_irqsave, _T) DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irqsave, _try, - raw_spin_trylock_irqsave(_T->lock, _T->flags)) + raw_spin_trylock_irq_disable(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(raw_spinlock_irqsave_try, __acquires(_T), __releases(*(raw_spinlock_t **)_T)) #define class_raw_spinlock_irqsave_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(raw_spinlock_irqsave_try, _T) @@ -595,13 +617,13 @@ DECLARE_LOCK_GUARD_1_ATTRS(spinlock_try, __acquires(_T), __releases(*(spinlock_t #define class_spinlock_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_try, _T) DEFINE_LOCK_GUARD_1(spinlock_irq, spinlock_t, - spin_lock_irq(_T->lock), - spin_unlock_irq(_T->lock)) + spin_lock_irq_disable(_T->lock), + spin_unlock_irq_enable(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(spinlock_irq, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_irq_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_irq, _T) DEFINE_LOCK_GUARD_1_COND(spinlock_irq, _try, - spin_trylock_irq(_T->lock)) + spin_trylock_irq_disable(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(spinlock_irq_try, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_irq_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_irq_try, _T) @@ -617,14 +639,13 @@ DECLARE_LOCK_GUARD_1_ATTRS(spinlock_bh_try, __acquires(_T), __releases(*(spinloc #define class_spinlock_bh_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_bh_try, _T) DEFINE_LOCK_GUARD_1(spinlock_irqsave, spinlock_t, - spin_lock_irqsave(_T->lock, _T->flags), - spin_unlock_irqrestore(_T->lock, _T->flags), - unsigned long flags) + spin_lock_irq_disable(_T->lock), + spin_unlock_irq_enable(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(spinlock_irqsave, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_irqsave_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_irqsave, _T) DEFINE_LOCK_GUARD_1_COND(spinlock_irqsave, _try, - spin_trylock_irqsave(_T->lock, _T->flags)) + spin_trylock_irq_disable(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(spinlock_irqsave_try, __acquires(_T), __releases(*(spinlock_t **)_T)) #define class_spinlock_irqsave_try_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(spinlock_irqsave_try, _T) diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index bda5e7a390cd..90909d933dab 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -28,6 +28,8 @@ _raw_spin_lock_nest_lock(raw_spinlock_t *lock, struct lockdep_map *map) void __lockfunc _raw_spin_lock_bh(raw_spinlock_t *lock) __acquires(lock); void __lockfunc _raw_spin_lock_irq(raw_spinlock_t *lock) __acquires(lock); +void __lockfunc _raw_spin_lock_irq_disable(raw_spinlock_t *lock) + __acquires(lock); unsigned long __lockfunc _raw_spin_lock_irqsave(raw_spinlock_t *lock) __acquires(lock); @@ -39,6 +41,7 @@ int __lockfunc _raw_spin_trylock_bh(raw_spinlock_t *lock) __cond_acquires(true, void __lockfunc _raw_spin_unlock(raw_spinlock_t *lock) __releases(lock); void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock) __releases(lock); void __lockfunc _raw_spin_unlock_irq(raw_spinlock_t *lock) __releases(lock); +void __lockfunc _raw_spin_unlock_irq_enable(raw_spinlock_t *lock) __releases(lock); void __lockfunc _raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags) __releases(lock); @@ -55,6 +58,11 @@ _raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags) #define _raw_spin_lock_irq(lock) __raw_spin_lock_irq(lock) #endif +/* Use the same config as spin_lock_irq() temporarily. */ +#ifdef CONFIG_INLINE_SPIN_LOCK_IRQ +#define _raw_spin_lock_irq_disable(lock) __raw_spin_lock_irq_disable(lock) +#endif + #ifdef CONFIG_INLINE_SPIN_LOCK_IRQSAVE #define _raw_spin_lock_irqsave(lock) __raw_spin_lock_irqsave(lock) #endif @@ -79,6 +87,11 @@ _raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags) #define _raw_spin_unlock_irq(lock) __raw_spin_unlock_irq(lock) #endif +/* Use the same config as spin_unlock_irq() temporarily. */ +#ifdef CONFIG_INLINE_SPIN_UNLOCK_IRQ +#define _raw_spin_unlock_irq_enable(lock) __raw_spin_unlock_irq_enable(lock) +#endif + #ifdef CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE #define _raw_spin_unlock_irqrestore(lock, flags) __raw_spin_unlock_irqrestore(lock, flags) #endif @@ -105,6 +118,16 @@ static __always_inline bool _raw_spin_trylock_irq(raw_spinlock_t *lock) return false; } +static __always_inline bool _raw_spin_trylock_irq_disable(raw_spinlock_t *lock) + __cond_acquires(true, lock) +{ + local_interrupt_disable(); + if (_raw_spin_trylock(lock)) + return true; + local_interrupt_enable(); + return false; +} + static __always_inline bool _raw_spin_trylock_irqsave(raw_spinlock_t *lock, unsigned long *flags) __cond_acquires(true, lock) { @@ -143,6 +166,15 @@ static inline void __raw_spin_lock_irq(raw_spinlock_t *lock) LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock); } +static inline void __raw_spin_lock_irq_disable(raw_spinlock_t *lock) + __acquires(lock) __no_context_analysis +{ + local_interrupt_disable(); + preempt_disable(); + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); + LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock); +} + static inline void __raw_spin_lock_bh(raw_spinlock_t *lock) __acquires(lock) __no_context_analysis { @@ -188,6 +220,15 @@ static inline void __raw_spin_unlock_irq(raw_spinlock_t *lock) preempt_enable(); } +static inline void __raw_spin_unlock_irq_enable(raw_spinlock_t *lock) + __releases(lock) +{ + spin_release(&lock->dep_map, _RET_IP_); + do_raw_spin_unlock(lock); + local_interrupt_enable(); + preempt_enable(); +} + static inline void __raw_spin_unlock_bh(raw_spinlock_t *lock) __releases(lock) { diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h index a9d5c7c66e03..d03d3065ee04 100644 --- a/include/linux/spinlock_api_up.h +++ b/include/linux/spinlock_api_up.h @@ -42,6 +42,9 @@ #define __LOCK_IRQSAVE(lock, flags, ...) \ do { local_irq_save(flags); __LOCK(lock, ##__VA_ARGS__); } while (0) +#define __LOCK_IRQ_DISABLE(lock, ...) \ + do { local_interrupt_disable(); __LOCK(lock, ##__VA_ARGS__); } while (0) + #define ___UNLOCK_(lock) \ do { __release(lock); (void)(lock); } while (0) @@ -61,6 +64,9 @@ #define __UNLOCK_IRQRESTORE(lock, flags, ...) \ do { local_irq_restore(flags); __UNLOCK(lock, ##__VA_ARGS__); } while (0) +#define __UNLOCK_IRQ_ENABLE(lock, ...) \ + do { __UNLOCK(lock, ##__VA_ARGS__); local_interrupt_enable(); } while (0) + #define _raw_spin_lock(lock) __LOCK(lock) #define _raw_spin_lock_nested(lock, subclass) __LOCK(lock) #define _raw_read_lock(lock) __LOCK(lock, shared) @@ -70,6 +76,7 @@ #define _raw_read_lock_bh(lock) __LOCK_BH(lock, shared) #define _raw_write_lock_bh(lock) __LOCK_BH(lock) #define _raw_spin_lock_irq(lock) __LOCK_IRQ(lock) +#define _raw_spin_lock_irq_disable(lock) __LOCK_IRQ_DISABLE(lock) #define _raw_read_lock_irq(lock) __LOCK_IRQ(lock, shared) #define _raw_write_lock_irq(lock) __LOCK_IRQ(lock) #define _raw_spin_lock_irqsave(lock, flags) __LOCK_IRQSAVE(lock, flags) @@ -97,6 +104,13 @@ static __always_inline int _raw_spin_trylock_irq(raw_spinlock_t *lock) return 1; } +static __always_inline int _raw_spin_trylock_irq_disable(raw_spinlock_t *lock) + __cond_acquires(true, lock) +{ + __LOCK_IRQ_DISABLE(lock); + return 1; +} + static __always_inline int _raw_spin_trylock_irqsave(raw_spinlock_t *lock, unsigned long *flags) __cond_acquires(true, lock) { @@ -132,6 +146,7 @@ static __always_inline int _raw_write_trylock_irqsave(rwlock_t *lock, unsigned l #define _raw_write_unlock_bh(lock) __UNLOCK_BH(lock) #define _raw_read_unlock_bh(lock) __UNLOCK_BH(lock, shared) #define _raw_spin_unlock_irq(lock) __UNLOCK_IRQ(lock) +#define _raw_spin_unlock_irq_enable(lock) __UNLOCK_IRQ_ENABLE(lock) #define _raw_read_unlock_irq(lock) __UNLOCK_IRQ(lock, shared) #define _raw_write_unlock_irq(lock) __UNLOCK_IRQ(lock) #define _raw_spin_unlock_irqrestore(lock, flags) \ diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h index 373618a4243c..560d06384e0c 100644 --- a/include/linux/spinlock_rt.h +++ b/include/linux/spinlock_rt.h @@ -96,6 +96,12 @@ static __always_inline void spin_lock_irq(spinlock_t *lock) rt_spin_lock(lock); } +static __always_inline void spin_lock_irq_disable(spinlock_t *lock) + __acquires(lock) +{ + rt_spin_lock(lock); +} + #define spin_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ @@ -122,6 +128,12 @@ static __always_inline void spin_unlock_irq(spinlock_t *lock) rt_spin_unlock(lock); } +static __always_inline void spin_unlock_irq_enable(spinlock_t *lock) + __releases(lock) +{ + rt_spin_unlock(lock); +} + static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) __releases(lock) @@ -131,6 +143,12 @@ static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, #define spin_trylock(lock) rt_spin_trylock(lock) +static __always_inline int spin_trylock_irq_disable(spinlock_t *lock) + __cond_acquires(true, lock) +{ + return rt_spin_trylock(lock); +} + #define spin_trylock_bh(lock) rt_spin_trylock_bh(lock) #define spin_trylock_irq(lock) rt_spin_trylock(lock) diff --git a/include/linux/srcu.h b/include/linux/srcu.h index a54ce9e808b9..72c86d3b23f2 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -638,4 +638,11 @@ DEFINE_LOCK_GUARD_1(srcu_fast_notrace, struct srcu_struct, DECLARE_LOCK_GUARD_1_ATTRS(srcu_fast_notrace, __acquires_shared(_T), __releases_shared(*(struct srcu_struct **)_T)) #define class_srcu_fast_notrace_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(srcu_fast_notrace, _T) +DEFINE_LOCK_GUARD_1(srcu_fast_updown, struct srcu_struct, + _T->scp = srcu_read_lock_fast_updown(_T->lock), + srcu_read_unlock_fast_updown(_T->lock, _T->scp), + struct srcu_ctr __percpu *scp) +DECLARE_LOCK_GUARD_1_ATTRS(srcu_fast_updown, __acquires_shared(_T), __releases_shared(*(struct srcu_struct **)_T)) +#define class_srcu_fast_updown_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(srcu_fast_updown, _T) + #endif diff --git a/include/linux/stat.h b/include/linux/stat.h index e3d00e7bb26d..9c5709132862 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -41,8 +41,8 @@ struct kstat { u64 ino; dev_t dev; dev_t rdev; - kuid_t uid; - kgid_t gid; + kuid_t uid; /* This is logically a vfsuid_t. */ + kgid_t gid; /* This is logically a vfsgid_t. */ loff_t size; struct timespec64 atime; struct timespec64 mtime; diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h index cfb6ddeb292b..ac55bc966a56 100644 --- a/include/linux/static_call_types.h +++ b/include/linux/static_call_types.h @@ -25,7 +25,7 @@ #define STATIC_CALL_SITE_INIT 2UL /* init section */ #define STATIC_CALL_SITE_FLAGS 3UL -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ /* * The static call site table needs to be created by external tooling (objtool @@ -102,6 +102,6 @@ struct static_call_key { #endif /* CONFIG_HAVE_STATIC_CALL */ -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* _STATIC_CALL_TYPES_H */ diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 01011113d226..84e7fb627ba4 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -2,6 +2,7 @@ #ifndef _LINUX_STOP_MACHINE #define _LINUX_STOP_MACHINE +#include <linux/bug.h> #include <linux/cpu.h> #include <linux/cpumask_types.h> #include <linux/smp.h> @@ -31,7 +32,7 @@ struct cpu_stop_work { int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg); int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg); -bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, +void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf); void stop_machine_park(int cpu); void stop_machine_unpark(int cpu); @@ -68,19 +69,17 @@ static void stop_one_cpu_nowait_workfn(struct work_struct *work) preempt_enable(); } -static inline bool stop_one_cpu_nowait(unsigned int cpu, +static inline void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf) { - if (cpu == smp_processor_id()) { - INIT_WORK(&work_buf->work, stop_one_cpu_nowait_workfn); - work_buf->fn = fn; - work_buf->arg = arg; - schedule_work(&work_buf->work); - return true; - } - - return false; + if (WARN_ON_ONCE(cpu != smp_processor_id())) + return; + + INIT_WORK(&work_buf->work, stop_one_cpu_nowait_workfn); + work_buf->fn = fn; + work_buf->arg = arg; + schedule_work(&work_buf->work); } static inline void print_stop_info(const char *log_lvl, struct task_struct *task) { } diff --git a/include/linux/syscall_user_dispatch.h b/include/linux/syscall_user_dispatch.h index 3858a6ffdd5c..3dd30f4b2799 100644 --- a/include/linux/syscall_user_dispatch.h +++ b/include/linux/syscall_user_dispatch.h @@ -6,9 +6,23 @@ #define _SYSCALL_USER_DISPATCH_H #include <linux/thread_info.h> +#include <linux/sched.h> #include <linux/syscall_user_dispatch_types.h> -#ifdef CONFIG_GENERIC_ENTRY +struct pt_regs; + +#ifdef CONFIG_SYSCALL_USER_DISPATCH + +bool syscall_user_dispatch(struct pt_regs *regs); + +static __always_inline bool syscall_user_dispatch_clear_on_dispatch(void) +{ + if (likely(!current->syscall_dispatch.on_dispatch)) + return false; + + current->syscall_dispatch.on_dispatch = false; + return true; +} int set_syscall_user_dispatch(unsigned long mode, unsigned long offset, unsigned long len, char __user *selector); @@ -24,6 +38,16 @@ int syscall_user_dispatch_set_config(struct task_struct *task, unsigned long siz #else +static __always_inline bool syscall_user_dispatch(struct pt_regs *regs) +{ + return false; +} + +static __always_inline bool syscall_user_dispatch_clear_on_dispatch(void) +{ + return false; +} + static inline int set_syscall_user_dispatch(unsigned long mode, unsigned long offset, unsigned long len, char __user *selector) { @@ -46,6 +70,6 @@ static inline int syscall_user_dispatch_set_config(struct task_struct *task, return -EINVAL; } -#endif /* CONFIG_GENERIC_ENTRY */ +#endif /* CONFIG_SYSCALL_USER_DISPATCH */ #endif /* _SYSCALL_USER_DISPATCH_H */ diff --git a/include/linux/syscall_user_dispatch_types.h b/include/linux/syscall_user_dispatch_types.h index 3be36b06c7d7..c0bdd4f760d3 100644 --- a/include/linux/syscall_user_dispatch_types.h +++ b/include/linux/syscall_user_dispatch_types.h @@ -4,7 +4,7 @@ #include <linux/types.h> -#ifdef CONFIG_GENERIC_ENTRY +#ifdef CONFIG_SYSCALL_USER_DISPATCH struct syscall_user_dispatch { char __user *selector; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 874d9067a43b..8413b624ad47 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -457,6 +457,7 @@ asmlinkage long sys_faccessat2(int dfd, const char __user *filename, int mode, asmlinkage long sys_chdir(const char __user *filename); asmlinkage long sys_fchdir(unsigned int fd); asmlinkage long sys_chroot(const char __user *filename); +asmlinkage long sys_fchroot(int fd, unsigned int flags); asmlinkage long sys_fchmod(unsigned int fd, umode_t mode); asmlinkage long sys_fchmodat(int dfd, const char __user *filename, umode_t mode); diff --git a/include/linux/tick.h b/include/linux/tick.h index 1cf4651f09ad..47750ccd1314 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -7,6 +7,8 @@ #include <linux/clockchips.h> #include <linux/irqflags.h> +#include <linux/jiffies.h> +#include <linux/ktime.h> #include <linux/percpu.h> #include <linux/context_tracking_state.h> #include <linux/cpumask.h> diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 4486dfd5d0de..fe077d97b5f8 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -84,8 +84,6 @@ struct tk_read_base { * @cycle_interval: Number of clock cycles in one NTP interval * @xtime_interval: Number of clock shifted nano seconds in one NTP * interval. - * @xtime_remainder: Shifted nano seconds left over when rounding - * @cycle_interval * @raw_interval: Shifted raw nano seconds accumulated per NTP interval. * @next_leap_ktime: CLOCK_MONOTONIC time value of a pending leap-second * @ntp_tick: The ntp_tick_length() value currently being @@ -99,6 +97,10 @@ struct tk_read_base { * @ntp_error_shift: Shift conversion between clock shifted nano seconds and * ntp shifted nano seconds. * @ntp_err_mult: Multiplication factor for scaled math conversion + * @cs_tick_adj: Per-second adjustment handed to NTP via ntp_clear() + * accounting for the difference between the nominal + * NTP interval and the real time taken by the + * clocksource's integer @cycle_interval (upscaled). * @skip_second_overflow: Flag used to avoid updating NTP twice with same second * @tai_offset: The current UTC to TAI offset in seconds * @@ -167,7 +169,7 @@ struct timekeeper { u32 cs_ns_to_cyc_mult; u32 cs_ns_to_cyc_shift; u64 cs_ns_to_cyc_maxns; - unsigned int clock_was_set_seq; + u32 clock_was_set_seq; u8 cs_was_changed_seq; u8 clock_valid; @@ -178,7 +180,6 @@ struct timekeeper { u64 cycle_interval; u64 xtime_interval; - s64 xtime_remainder; u64 raw_interval; ktime_t next_leap_ktime; @@ -186,29 +187,10 @@ struct timekeeper { s64 ntp_error; u32 ntp_error_shift; u32 ntp_err_mult; + s64 cs_tick_adj; u32 skip_second_overflow; + s64 skew_delta; s32 tai_offset; }; -#ifdef CONFIG_GENERIC_GETTIMEOFDAY - -extern void update_vsyscall(struct timekeeper *tk); -extern void update_vsyscall_tz(void); - -#else - -static inline void update_vsyscall(struct timekeeper *tk) -{ -} -static inline void update_vsyscall_tz(void) -{ -} -#endif - -#if defined(CONFIG_GENERIC_GETTIMEOFDAY) && defined(CONFIG_POSIX_AUX_CLOCKS) -extern void vdso_time_update_aux(struct timekeeper *tk); -#else -static inline void vdso_time_update_aux(struct timekeeper *tk) { } -#endif - #endif /* _LINUX_TIMEKEEPER_INTERNAL_H */ diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 984a866d293b..efa9442aaeef 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -44,7 +44,6 @@ extern void ktime_get_ts64(struct timespec64 *ts); extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); -extern void ktime_get_clock_ts64(clockid_t id, struct timespec64 *ts); /* Multigrain timestamp interfaces */ extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts); @@ -268,15 +267,18 @@ extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); * Auxiliary clock interfaces */ #ifdef CONFIG_POSIX_AUX_CLOCKS -extern bool ktime_get_aux(clockid_t id, ktime_t *kt); -extern bool ktime_get_aux_ts64(clockid_t id, struct timespec64 *kt); +extern bool __must_check ktime_get_aux(clockid_t id, ktime_t *kt); +extern bool __must_check ktime_get_aux_ts64(clockid_t id, struct timespec64 *kt); #else -static inline bool ktime_get_aux(clockid_t id, ktime_t *kt) { return false; } -static inline bool ktime_get_aux_ts64(clockid_t id, struct timespec64 *kt) { return false; } +static inline bool __must_check ktime_get_aux(clockid_t id, ktime_t *kt) { return false; } +static inline bool __must_check ktime_get_aux_ts64(clockid_t id, struct timespec64 *kt) +{ + return false; +} #endif /** - * struct system_time_snapshot - Simultaneous time capture of CLOCK_MONOTONIC_RAW, + * struct system_time_snapshot - Simultaneous time capture of monotonic raw time, * a selected CLOCK_* and the clocksource counter value * @cycles: Clocksource counter value to produce the system times * @hw_cycles: For derived clocksources, the hardware counter value from @@ -289,6 +291,10 @@ static inline bool ktime_get_aux_ts64(clockid_t id, struct timespec64 *kt) { ret * @clock_was_set_seq: The sequence number of clock-was-set events * @cs_was_changed_seq: The sequence number of clocksource change events * @valid: True if the snapshot is valid + * + * @monoraw is CLOCK_MONOTONIC_RAW for system time CLOCK ids. For CLOCK_AUX$N + * clock ids it's the monotonic raw time related to the AUX clock, which is + * CLOCK_MONOTONIC_RAW plus a AUX clock specific offset. */ struct system_time_snapshot { u64 cycles; @@ -297,7 +303,7 @@ struct system_time_snapshot { ktime_t monoraw; enum clocksource_ids cs_id; enum clocksource_ids hw_csid; - unsigned int clock_was_set_seq; + u32 clock_was_set_seq; u8 cs_was_changed_seq; u8 valid; }; @@ -326,6 +332,10 @@ struct system_counterval_t { * @sys_counter: Clocksource counter value simultaneous with device time * @sys_systime: System time for @clock_id * @sys_monoraw: Monotonic raw simultaneous with device time + * + * @sys_monoraw is CLOCK_MONOTONIC_RAW for system time CLOCK ids. For + * CLOCK_AUX$N clock ids it's the monotonic raw time related to the AUX clock, + * which is CLOCK_MONOTONIC_RAW plus a AUX clock specific offset. */ struct system_device_crosststamp { clockid_t clock_id; diff --git a/include/linux/timex.h b/include/linux/timex.h index 4ee32eff3f22..7014ccc638fc 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -156,8 +156,6 @@ extern int do_clock_adjtime(const clockid_t which_clock, struct __kernel_timex * extern void hardpps(const struct timespec64 *, const struct timespec64 *); -int read_current_timer(unsigned long *timer_val); - /* The clock frequency of the i8253/i8254 PIT */ #define PIT_TICK_RATE 1193182ul diff --git a/include/linux/types.h b/include/linux/types.h index 93166b0b0617..bc5dda2a3d86 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -163,6 +163,8 @@ typedef u32 dma_addr_t; typedef unsigned int __bitwise gfp_t; typedef unsigned int __bitwise slab_flags_t; typedef unsigned int __bitwise fmode_t; +typedef unsigned int __bitwise blk_mode_t; +typedef unsigned int __bitwise fop_flags_t; #ifdef CONFIG_PHYS_ADDR_T_64BIT typedef u64 phys_addr_t; diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index f548fea2adec..d34dbc0fbbfe 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -25,6 +25,7 @@ struct mm_struct; struct inode; struct notifier_block; struct page; +struct srcu_ctr; /* * Allowed return values from uprobe consumer's handler callback @@ -106,7 +107,7 @@ enum hprobe_state { * underlying uprobe is not guaranteed anymore. __UPROBE_DEAD is just an * internal marker and is handled transparently by hprobe_fetch() helper. * - * When uprobe is SRCU-protected, we also record srcu_idx value, necessary for + * When uprobe is SRCU-protected, we also record srcu_scp value, necessary for * SRCU unlocking. * * See hprobe_expire() and hprobe_fetch() for details of race-free uprobe @@ -115,7 +116,7 @@ enum hprobe_state { */ struct hprobe { enum hprobe_state state; - int srcu_idx; + struct srcu_ctr __percpu *srcu_scp; struct uprobe *uprobe; }; @@ -186,9 +187,6 @@ struct xol_area; struct uprobes_state { struct xol_area *xol_area; -#ifdef CONFIG_X86_64 - struct hlist_head head_tramps; -#endif }; typedef int (*uprobe_write_verify_t)(struct page *page, unsigned long vaddr, @@ -238,8 +236,6 @@ extern void uprobe_handle_trampoline(struct pt_regs *regs); extern void *arch_uretprobe_trampoline(unsigned long *psize); extern unsigned long uprobe_get_trampoline_vaddr(void); extern void uprobe_copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len); -extern void arch_uprobe_clear_state(struct mm_struct *mm); -extern void arch_uprobe_init_state(struct mm_struct *mm); extern void handle_syscall_uprobe(struct pt_regs *regs, unsigned long bp_vaddr); extern void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr); extern unsigned long arch_uprobe_get_xol_area(void); diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index b3cc7beab4a3..a4043b33c2c2 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -81,4 +81,7 @@ /* Device claims zero configurations, forcing to 1 */ #define USB_QUIRK_FORCE_ONE_CONFIG BIT(18) +/* Use a 255 bytes config descriptor request mirroring windows behavior */ +#define USB_QUIRK_WINDOWS_CONFIG_REQ_SIZE BIT(19) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 9c3be157397e..e38d9e60569f 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -58,6 +58,9 @@ enum ucount_type { UCOUNT_FANOTIFY_GROUPS, UCOUNT_FANOTIFY_MARKS, #endif +#if IS_ENABLED(CONFIG_BINFMT_MISC) + UCOUNT_BINFMT_MISC_INTERPRETERS, +#endif UCOUNT_COUNTS, }; diff --git a/include/linux/vdso_datastore.h b/include/linux/vdso_datastore.h index 3dfba9502d78..13b01baf3497 100644 --- a/include/linux/vdso_datastore.h +++ b/include/linux/vdso_datastore.h @@ -7,10 +7,10 @@ extern const struct vm_special_mapping vdso_vvar_mapping; struct vm_area_struct *vdso_install_vvar_mapping(struct mm_struct *mm, unsigned long addr); -#ifdef CONFIG_HAVE_GENERIC_VDSO +#ifdef CONFIG_VDSO_DATASTORE void __init vdso_setup_data_pages(void); -#else /* !CONFIG_HAVE_GENERIC_VDSO */ +#else /* !CONFIG_VDSO_DATASTORE */ static inline void vdso_setup_data_pages(void) { } -#endif /* CONFIG_HAVE_GENERIC_VDSO */ +#endif /* CONFIG_VDSO_DATASTORE */ #endif /* _LINUX_VDSO_DATASTORE_H */ |