diff options
Diffstat (limited to 'include/linux')
26 files changed, 364 insertions, 130 deletions
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 50b47eba7d01..e7195750d21b 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -105,6 +105,12 @@ ARM_SMCCC_SMC_32, \ 0, 0x3fff) +/* C1-Pro erratum 4193714: SME DVMSync early acknowledgement */ +#define ARM_SMCCC_CPU_WORKAROUND_4193714 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_CPU, 0x10) + #define ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_32, \ diff --git a/include/linux/bio.h b/include/linux/bio.h index 97d747320b35..dc17780d6c1e 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -475,7 +475,8 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); -int bio_iov_iter_bounce(struct bio *bio, struct iov_iter *iter, size_t maxlen); +int bio_iov_iter_bounce(struct bio *bio, struct iov_iter *iter, size_t maxlen, + size_t minsize); void bio_iov_iter_unbounce(struct bio *bio, bool is_error, bool mark_dirty); extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b4b703c90ca9..01e203964892 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -3725,6 +3725,7 @@ extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; +extern const struct bpf_func_proto bpf_sk_setsockopt_nodelay_proto; extern const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_find_vma_proto; diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index f42563739d2e..50a784da7a81 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -611,8 +611,8 @@ struct cgroup { /* used to wait for offlining of csses */ wait_queue_head_t offline_waitq; - /* used by cgroup_rmdir() to wait for dying tasks to leave */ - wait_queue_head_t dying_populated_waitq; + /* defers killing csses after removal until cgroup is depopulated */ + struct work_struct finish_destroy_work; /* used to schedule release agent */ struct work_struct release_agent_work; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index e52160e85af4..f6d037a30fd8 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -53,6 +53,7 @@ struct kernel_clone_args; enum css_task_iter_flags { CSS_TASK_ITER_PROCS = (1U << 0), /* walk only threadgroup leaders */ CSS_TASK_ITER_THREADED = (1U << 1), /* walk all threaded css_sets in the domain */ + CSS_TASK_ITER_WITH_DEAD = (1U << 2), /* include exiting tasks */ CSS_TASK_ITER_SKIPPED = (1U << 16), /* internal flags */ }; diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index 0a3bcd1718f3..be1b38c981d4 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -94,6 +94,7 @@ int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num); int register_fprobe_syms(struct fprobe *fp, const char **syms, int num); int unregister_fprobe(struct fprobe *fp); +int unregister_fprobe_async(struct fprobe *fp); bool fprobe_is_registered(struct fprobe *fp); int fprobe_count_ips_from_filter(const char *filter, const char *notfilter); #else @@ -113,6 +114,10 @@ static inline int unregister_fprobe(struct fprobe *fp) { return -EOPNOTSUPP; } +static inline int unregister_fprobe_async(struct fprobe *fp) +{ + return -EOPNOTSUPP; +} static inline bool fprobe_is_registered(struct fprobe *fp) { return false; diff --git a/include/linux/hid.h b/include/linux/hid.h index 442a80d79e89..bfb9859f391e 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -1030,6 +1030,8 @@ struct hid_field *hid_find_field(struct hid_device *hdev, unsigned int report_ty int hid_set_field(struct hid_field *, unsigned, __s32); int hid_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size, int interrupt); +int hid_safe_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data, + size_t bufsize, u32 size, int interrupt); struct hid_field *hidinput_get_led_field(struct hid_device *hid); unsigned int hidinput_count_leds(struct hid_device *hid); __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code); @@ -1298,8 +1300,8 @@ static inline u32 hid_report_len(struct hid_report *report) return DIV_ROUND_UP(report->size, 8) + (report->id > 0); } -int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size, - int interrupt); +int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *data, + size_t bufsize, u32 size, int interrupt); /* HID quirks API */ unsigned long hid_lookup_quirk(const struct hid_device *hdev); diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h index a2e47dbcf82c..19fffa4574a4 100644 --- a/include/linux/hid_bpf.h +++ b/include/linux/hid_bpf.h @@ -72,8 +72,8 @@ struct hid_ops { int (*hid_hw_output_report)(struct hid_device *hdev, __u8 *buf, size_t len, u64 source, bool from_bpf); int (*hid_input_report)(struct hid_device *hid, enum hid_report_type type, - u8 *data, u32 size, int interrupt, u64 source, bool from_bpf, - bool lock_already_taken); + u8 *data, size_t bufsize, u32 size, int interrupt, u64 source, + bool from_bpf, bool lock_already_taken); struct module *owner; const struct bus_type *bus_type; }; @@ -200,7 +200,8 @@ struct hid_bpf { #ifdef CONFIG_HID_BPF u8 *dispatch_hid_bpf_device_event(struct hid_device *hid, enum hid_report_type type, u8 *data, - u32 *size, int interrupt, u64 source, bool from_bpf); + size_t *buf_size, u32 *size, int interrupt, u64 source, + bool from_bpf); int dispatch_hid_bpf_raw_requests(struct hid_device *hdev, unsigned char reportnum, __u8 *buf, u32 size, enum hid_report_type rtype, @@ -215,8 +216,11 @@ int hid_bpf_device_init(struct hid_device *hid); const u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, const u8 *rdesc, unsigned int *size); #else /* CONFIG_HID_BPF */ static inline u8 *dispatch_hid_bpf_device_event(struct hid_device *hid, enum hid_report_type type, - u8 *data, u32 *size, int interrupt, - u64 source, bool from_bpf) { return data; } + u8 *data, size_t *buf_size, u32 *size, + int interrupt, u64 source, bool from_bpf) +{ + return data; +} static inline int dispatch_hid_bpf_raw_requests(struct hid_device *hdev, unsigned char reportnum, u8 *buf, u32 size, enum hid_report_type rtype, diff --git a/include/linux/intel_tpmi.h b/include/linux/intel_tpmi.h index 94c06bf214fb..15f02422e9ca 100644 --- a/include/linux/intel_tpmi.h +++ b/include/linux/intel_tpmi.h @@ -28,6 +28,12 @@ enum intel_tpmi_id { TPMI_INFO_ID = 0x81, /* Special ID for PCI BDF and Package ID information */ }; +#define TPMI_CORE_INIT 0 +#define TPMI_CORE_EXIT 1 + +int tpmi_register_notifier(struct notifier_block *nb); +int tpmi_unregister_notifier(struct notifier_block *nb); + struct oobmsm_plat_info *tpmi_get_platform_data(struct auxiliary_device *auxdev); struct resource *tpmi_get_resource_at_index(struct auxiliary_device *auxdev, int index); int tpmi_get_resource_count(struct auxiliary_device *auxdev); diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h index 167fba7dbf04..1fabf0f5ea8e 100644 --- a/include/linux/irq-entry-common.h +++ b/include/linux/irq-entry-common.h @@ -218,14 +218,6 @@ static __always_inline void __exit_to_user_mode_validate(void) lockdep_sys_exit(); } -/* Temporary workaround to keep ARM64 alive */ -static __always_inline void exit_to_user_mode_prepare_legacy(struct pt_regs *regs) -{ - __exit_to_user_mode_prepare(regs, EXIT_TO_USER_MODE_WORK); - rseq_exit_to_user_mode_legacy(); - __exit_to_user_mode_validate(); -} - /** * syscall_exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required * @regs: Pointer to pt_regs on entry stack diff --git a/include/linux/irqchip/arm-gic-v5.h b/include/linux/irqchip/arm-gic-v5.h index 40d2fce68294..f78787e654f4 100644 --- a/include/linux/irqchip/arm-gic-v5.h +++ b/include/linux/irqchip/arm-gic-v5.h @@ -425,9 +425,6 @@ struct gicv5_its_itt_cfg { void gicv5_init_lpis(u32 max); void gicv5_deinit_lpis(void); -int gicv5_alloc_lpi(void); -void gicv5_free_lpi(u32 lpi); - void __init gicv5_its_of_probe(struct device_node *parent); void __init gicv5_its_acpi_probe(void); #endif diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 77c778d84d4c..5a1c5c336fa4 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -146,6 +146,9 @@ struct xt_match { /* Called when user tries to insert an entry of this type. */ int (*checkentry)(const struct xt_mtchk_param *); + /* Called to validate hooks based on the match configuration. */ + int (*check_hooks)(const struct xt_mtchk_param *); + /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_mtdtor_param *); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT @@ -187,6 +190,9 @@ struct xt_target { /* Should return 0 on success or an error code otherwise (-Exxxx). */ int (*checkentry)(const struct xt_tgchk_param *); + /* Called to validate hooks based on the target configuration. */ + int (*check_hooks)(const struct xt_tgchk_param *); + /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_tgdtor_param *); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT @@ -279,8 +285,10 @@ bool xt_find_jump_offset(const unsigned int *offsets, int xt_check_proc_name(const char *name, unsigned int size); +int xt_check_hooks_match(struct xt_mtchk_param *par); int xt_check_match(struct xt_mtchk_param *, unsigned int size, u16 proto, bool inv_proto); +int xt_check_hooks_target(struct xt_tgchk_param *par); int xt_check_target(struct xt_tgchk_param *, unsigned int size, u16 proto, bool inv_proto); @@ -297,9 +305,11 @@ struct xt_counters *xt_counters_alloc(unsigned int counters); struct xt_table *xt_register_table(struct net *net, const struct xt_table *table, + const struct nf_hook_ops *template_ops, struct xt_table_info *bootstrap, struct xt_table_info *newinfo); -void *xt_unregister_table(struct xt_table *table); +void xt_unregister_table_pre_exit(struct net *net, u8 af, const char *name); +struct xt_table *xt_unregister_table_exit(struct net *net, u8 af, const char *name); struct xt_table_info *xt_replace_table(struct xt_table *table, unsigned int num_counters, diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index a40aaf645fa4..05631a25e622 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -53,7 +53,6 @@ int arpt_register_table(struct net *net, const struct xt_table *table, const struct arpt_replace *repl, const struct nf_hook_ops *ops); void arpt_unregister_table(struct net *net, const char *name); -void arpt_unregister_table_pre_exit(struct net *net, const char *name); extern unsigned int arpt_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 132b0e4a6d4d..13593391d605 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -26,7 +26,6 @@ int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, const struct nf_hook_ops *ops); -void ipt_unregister_table_pre_exit(struct net *net, const char *name); void ipt_unregister_table_exit(struct net *net, const char *name); /* Standard entry. */ diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 8b8885a73c76..c6d5b927830d 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -27,7 +27,6 @@ extern void *ip6t_alloc_initial_table(const struct xt_table *); int ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl, const struct nf_hook_ops *ops); -void ip6t_unregister_table_pre_exit(struct net *net, const char *name); void ip6t_unregister_table_exit(struct net *net, const char *name); extern unsigned int ip6t_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); diff --git a/include/linux/rseq.h b/include/linux/rseq.h index b9d62fc2140d..7ef79b25e714 100644 --- a/include/linux/rseq.h +++ b/include/linux/rseq.h @@ -9,6 +9,11 @@ void __rseq_handle_slowpath(struct pt_regs *regs); +static __always_inline bool rseq_v2(struct task_struct *t) +{ + return IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY) && likely(t->rseq.event.has_rseq > 1); +} + /* Invoked from resume_user_mode_work() */ static inline void rseq_handle_slowpath(struct pt_regs *regs) { @@ -16,8 +21,7 @@ static inline void rseq_handle_slowpath(struct pt_regs *regs) if (current->rseq.event.slowpath) __rseq_handle_slowpath(regs); } else { - /* '&' is intentional to spare one conditional branch */ - if (current->rseq.event.sched_switch & current->rseq.event.has_rseq) + if (current->rseq.event.sched_switch && current->rseq.event.has_rseq) __rseq_handle_slowpath(regs); } } @@ -30,9 +34,9 @@ void __rseq_signal_deliver(int sig, struct pt_regs *regs); */ static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { - if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { - /* '&' is intentional to spare one conditional branch */ - if (current->rseq.event.has_rseq & current->rseq.event.user_irq) + if (rseq_v2(current)) { + /* has_rseq is implied in rseq_v2() */ + if (current->rseq.event.user_irq) __rseq_signal_deliver(ksig->sig, regs); } else { if (current->rseq.event.has_rseq) @@ -50,15 +54,22 @@ static __always_inline void rseq_sched_switch_event(struct task_struct *t) { struct rseq_event *ev = &t->rseq.event; - if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { + /* + * Only apply the user_irq optimization for RSEQ ABI V2 registrations. + * Legacy users like TCMalloc rely on the original ABI V1 behaviour + * which updates IDs on every context swtich. + */ + if (rseq_v2(t)) { /* - * Avoid a boat load of conditionals by using simple logic - * to determine whether NOTIFY_RESUME needs to be raised. + * Avoid a boat load of conditionals by using simple logic to + * determine whether TIF_NOTIFY_RESUME or TIF_RSEQ needs to be + * raised. * - * It's required when the CPU or MM CID has changed or - * the entry was from user space. + * It's required when the CPU or MM CID has changed or the entry + * was via interrupt from user space. ev->has_rseq does not have + * to be evaluated here because rseq_v2() implies has_rseq. */ - bool raise = (ev->user_irq | ev->ids_changed) & ev->has_rseq; + bool raise = ev->user_irq | ev->ids_changed; if (raise) { ev->sched_switch = true; @@ -66,6 +77,7 @@ static __always_inline void rseq_sched_switch_event(struct task_struct *t) } } else { if (ev->has_rseq) { + t->rseq.event.ids_changed = true; t->rseq.event.sched_switch = true; rseq_raise_notify_resume(t); } @@ -119,6 +131,8 @@ static inline void rseq_virt_userspace_exit(void) static inline void rseq_reset(struct task_struct *t) { + /* Protect against preemption and membarrier IPI */ + guard(irqsave)(); memset(&t->rseq, 0, sizeof(t->rseq)); t->rseq.ids.cpu_id = RSEQ_CPU_ID_UNINITIALIZED; } @@ -159,6 +173,7 @@ static inline unsigned int rseq_alloc_align(void) } #else /* CONFIG_RSEQ */ +static inline bool rseq_v2(struct task_struct *t) { return false; } static inline void rseq_handle_slowpath(struct pt_regs *regs) { } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { } static inline void rseq_sched_switch_event(struct task_struct *t) { } diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h index f11ebd34f8b9..63bc72086e75 100644 --- a/include/linux/rseq_entry.h +++ b/include/linux/rseq_entry.h @@ -111,6 +111,20 @@ static __always_inline void rseq_slice_clear_grant(struct task_struct *t) t->rseq.slice.state.granted = false; } +/* + * Open coded, so it can be invoked within a user access region. + * + * This clears the user space state of the time slice extensions field only when + * the task has registered the optimized RSEQ_ABI V2. Some legacy registrations, + * e.g. TCMalloc, have conflicting non-ABI fields in struct RSEQ, which would be + * overwritten by an unconditional write. + */ +#define rseq_slice_clear_user(rseq, efault) \ +do { \ + if (rseq_slice_extension_enabled()) \ + unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); \ +} while (0) + static __always_inline bool __rseq_grant_slice_extension(bool work_pending) { struct task_struct *curr = current; @@ -230,10 +244,10 @@ static __always_inline bool rseq_slice_extension_enabled(void) { return false; } static __always_inline bool rseq_arm_slice_extension_timer(void) { return false; } static __always_inline void rseq_slice_clear_grant(struct task_struct *t) { } static __always_inline bool rseq_grant_slice_extension(unsigned long ti_work, unsigned long mask) { return false; } +#define rseq_slice_clear_user(rseq, efault) do { } while (0) #endif /* !CONFIG_RSEQ_SLICE_EXTENSION */ bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr); -bool rseq_debug_validate_ids(struct task_struct *t); static __always_inline void rseq_note_user_irq_entry(void) { @@ -353,43 +367,6 @@ efault: return false; } -/* - * On debug kernels validate that user space did not mess with it if the - * debug branch is enabled. - */ -bool rseq_debug_validate_ids(struct task_struct *t) -{ - struct rseq __user *rseq = t->rseq.usrptr; - u32 cpu_id, uval, node_id; - - /* - * On the first exit after registering the rseq region CPU ID is - * RSEQ_CPU_ID_UNINITIALIZED and node_id in user space is 0! - */ - node_id = t->rseq.ids.cpu_id != RSEQ_CPU_ID_UNINITIALIZED ? - cpu_to_node(t->rseq.ids.cpu_id) : 0; - - scoped_user_read_access(rseq, efault) { - unsafe_get_user(cpu_id, &rseq->cpu_id_start, efault); - if (cpu_id != t->rseq.ids.cpu_id) - goto die; - unsafe_get_user(uval, &rseq->cpu_id, efault); - if (uval != cpu_id) - goto die; - unsafe_get_user(uval, &rseq->node_id, efault); - if (uval != node_id) - goto die; - unsafe_get_user(uval, &rseq->mm_cid, efault); - if (uval != t->rseq.ids.mm_cid) - goto die; - } - return true; -die: - t->rseq.event.fatal = true; -efault: - return false; -} - #endif /* RSEQ_BUILD_SLOW_PATH */ /* @@ -499,37 +476,50 @@ efault: * faults in task context are fatal too. */ static rseq_inline -bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids, - u32 node_id, u64 *csaddr) +bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids, u64 *csaddr) { struct rseq __user *rseq = t->rseq.usrptr; - if (static_branch_unlikely(&rseq_debug_enabled)) { - if (!rseq_debug_validate_ids(t)) - return false; - } - scoped_user_rw_access(rseq, efault) { + /* Validate the R/O fields for debug and optimized mode */ + if (static_branch_unlikely(&rseq_debug_enabled) || rseq_v2(t)) { + u32 cpu_id, uval; + + unsafe_get_user(cpu_id, &rseq->cpu_id_start, efault); + if (cpu_id != t->rseq.ids.cpu_id) + goto die; + unsafe_get_user(uval, &rseq->cpu_id, efault); + if (uval != cpu_id) + goto die; + unsafe_get_user(uval, &rseq->node_id, efault); + if (uval != t->rseq.ids.node_id) + goto die; + unsafe_get_user(uval, &rseq->mm_cid, efault); + if (uval != t->rseq.ids.mm_cid) + goto die; + } + unsafe_put_user(ids->cpu_id, &rseq->cpu_id_start, efault); unsafe_put_user(ids->cpu_id, &rseq->cpu_id, efault); - unsafe_put_user(node_id, &rseq->node_id, efault); + unsafe_put_user(ids->node_id, &rseq->node_id, efault); unsafe_put_user(ids->mm_cid, &rseq->mm_cid, efault); if (csaddr) unsafe_get_user(*csaddr, &rseq->rseq_cs, efault); - /* Open coded, so it's in the same user access region */ - if (rseq_slice_extension_enabled()) { - /* Unconditionally clear it, no point in conditionals */ - unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); - } + /* RSEQ ABI V2 only operations */ + if (rseq_v2(t)) + rseq_slice_clear_user(rseq, efault); } rseq_slice_clear_grant(t); /* Cache the new values */ - t->rseq.ids.cpu_cid = ids->cpu_cid; + t->rseq.ids = *ids; rseq_stat_inc(rseq_stats.ids); rseq_trace_update(t, ids); return true; + +die: + t->rseq.event.fatal = true; efault: return false; } @@ -539,11 +529,11 @@ efault: * is in a critical section. */ static rseq_inline bool rseq_update_usr(struct task_struct *t, struct pt_regs *regs, - struct rseq_ids *ids, u32 node_id) + struct rseq_ids *ids) { u64 csaddr; - if (!rseq_set_ids_get_csaddr(t, ids, node_id, &csaddr)) + if (!rseq_set_ids_get_csaddr(t, ids, &csaddr)) return false; /* @@ -612,6 +602,14 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t * interrupts disabled */ guard(pagefault)(); + /* + * This optimization is only valid when the task registered for the + * optimized RSEQ_ABI_V2 variant. Some legacy users rely on the original + * RSEQ implementation behaviour which unconditionally updated the IDs. + * rseq_sched_switch_event() ensures that legacy registrations always + * have both sched_switch and ids_changed set, which is compatible with + * the historical TIF_NOTIFY_RESUME behaviour. + */ if (likely(!t->rseq.event.ids_changed)) { struct rseq __user *rseq = t->rseq.usrptr; /* @@ -623,11 +621,9 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t scoped_user_rw_access(rseq, efault) { unsafe_get_user(csaddr, &rseq->rseq_cs, efault); - /* Open coded, so it's in the same user access region */ - if (rseq_slice_extension_enabled()) { - /* Unconditionally clear it, no point in conditionals */ - unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); - } + /* RSEQ ABI V2 only operations */ + if (rseq_v2(t)) + rseq_slice_clear_user(rseq, efault); } rseq_slice_clear_grant(t); @@ -640,12 +636,12 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t } struct rseq_ids ids = { - .cpu_id = task_cpu(t), - .mm_cid = task_mm_cid(t), + .cpu_id = task_cpu(t), + .mm_cid = task_mm_cid(t), + .node_id = cpu_to_node(ids.cpu_id), }; - u32 node_id = cpu_to_node(ids.cpu_id); - return rseq_update_usr(t, regs, &ids, node_id); + return rseq_update_usr(t, regs, &ids); efault: return false; } @@ -753,24 +749,6 @@ static __always_inline void rseq_irqentry_exit_to_user_mode(void) ev->events = 0; } -/* Required to keep ARM64 working */ -static __always_inline void rseq_exit_to_user_mode_legacy(void) -{ - struct rseq_event *ev = ¤t->rseq.event; - - rseq_stat_inc(rseq_stats.exit); - - if (static_branch_unlikely(&rseq_debug_enabled)) - WARN_ON_ONCE(ev->sched_switch); - - /* - * Ensure that event (especially user_irq) is cleared when the - * interrupt did not result in a schedule and therefore the - * rseq processing did not clear it. - */ - ev->events = 0; -} - void __rseq_debug_syscall_return(struct pt_regs *regs); static __always_inline void rseq_debug_syscall_return(struct pt_regs *regs) @@ -786,7 +764,6 @@ static inline bool rseq_exit_to_user_mode_restart(struct pt_regs *regs, unsigned } static inline void rseq_syscall_exit_to_user_mode(void) { } static inline void rseq_irqentry_exit_to_user_mode(void) { } -static inline void rseq_exit_to_user_mode_legacy(void) { } static inline void rseq_debug_syscall_return(struct pt_regs *regs) { } static inline bool rseq_grant_slice_extension(unsigned long ti_work, unsigned long mask) { return false; } #endif /* !CONFIG_RSEQ */ diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h index 0b42045988db..85739a63e85e 100644 --- a/include/linux/rseq_types.h +++ b/include/linux/rseq_types.h @@ -9,6 +9,12 @@ #ifdef CONFIG_RSEQ struct rseq; +/* + * rseq_event::has_rseq contains the ABI version number so preserving it + * in AND operations requires a mask. + */ +#define RSEQ_HAS_RSEQ_VERSION_MASK 0xff + /** * struct rseq_event - Storage for rseq related event management * @all: Compound to initialize and clear the data efficiently @@ -17,7 +23,8 @@ struct rseq; * exit to user * @ids_changed: Indicator that IDs need to be updated * @user_irq: True on interrupt entry from user mode - * @has_rseq: True if the task has a rseq pointer installed + * @has_rseq: Greater than 0 if the task has a rseq pointer installed. + * Contains the RSEQ version number * @error: Compound error code for the slow path to analyze * @fatal: User space data corrupted or invalid * @slowpath: Indicator that slow path processing via TIF_NOTIFY_RESUME @@ -59,8 +66,9 @@ struct rseq_event { * compiler emit a single compare on 64-bit * @cpu_id: The CPU ID which was written last to user space * @mm_cid: The MM CID which was written last to user space + * @node_id: The node ID which was written last to user space * - * @cpu_id and @mm_cid are updated when the data is written to user space. + * @cpu_id, @mm_cid and @node_id are updated when the data is written to user space. */ struct rseq_ids { union { @@ -70,6 +78,7 @@ struct rseq_ids { u32 mm_cid; }; }; + u32 node_id; }; /** diff --git a/include/linux/sched.h b/include/linux/sched.h index 368c7b4d7cb5..ee06cba5c6f5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1002,6 +1002,9 @@ struct task_struct { unsigned sched_rt_mutex:1; #endif + /* Save user-dumpable when mm goes away */ + unsigned user_dumpable:1; + /* Bit to tell TOMOYO we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 1198138cb839..273538200a44 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -33,6 +33,15 @@ struct root_domain; extern void dl_add_task_root_domain(struct task_struct *p); extern void dl_clear_root_domain(struct root_domain *rd); extern void dl_clear_root_domain_cpu(int cpu); +/* + * Return whether moving DL task @p to @new_mask requires moving DL + * bandwidth accounting between root domains. This helper is specific to + * DL bandwidth move accounting semantics and is shared by + * cpuset_can_attach() and set_cpus_allowed_dl() so both paths use the + * same source root-domain test. + */ +extern bool dl_task_needs_bw_move(struct task_struct *p, + const struct cpumask *new_mask); extern u64 dl_cookie; extern bool dl_bw_visited(int cpu, u64 cookie); diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 1a3af2ea2a79..2129e18ada58 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -103,21 +103,25 @@ enum scx_ent_flags { SCX_TASK_IMMED = 1 << 5, /* task is on local DSQ with %SCX_ENQ_IMMED */ /* - * Bits 8 and 9 are used to carry task state: + * Bits 8 to 10 are used to carry task state: * * NONE ops.init_task() not called yet + * INIT_BEGIN ops.init_task() in flight; see sched_ext_dead() * INIT ops.init_task() succeeded, but task can be cancelled * READY fully initialized, but not in sched_ext * ENABLED fully initialized and in sched_ext + * DEAD terminal state set by sched_ext_dead() */ - SCX_TASK_STATE_SHIFT = 8, /* bits 8 and 9 are used to carry task state */ - SCX_TASK_STATE_BITS = 2, + SCX_TASK_STATE_SHIFT = 8, + SCX_TASK_STATE_BITS = 3, SCX_TASK_STATE_MASK = ((1 << SCX_TASK_STATE_BITS) - 1) << SCX_TASK_STATE_SHIFT, SCX_TASK_NONE = 0 << SCX_TASK_STATE_SHIFT, - SCX_TASK_INIT = 1 << SCX_TASK_STATE_SHIFT, - SCX_TASK_READY = 2 << SCX_TASK_STATE_SHIFT, - SCX_TASK_ENABLED = 3 << SCX_TASK_STATE_SHIFT, + SCX_TASK_INIT_BEGIN = 1 << SCX_TASK_STATE_SHIFT, + SCX_TASK_INIT = 2 << SCX_TASK_STATE_SHIFT, + SCX_TASK_READY = 3 << SCX_TASK_STATE_SHIFT, + SCX_TASK_ENABLED = 4 << SCX_TASK_STATE_SHIFT, + SCX_TASK_DEAD = 5 << SCX_TASK_STATE_SHIFT, /* * Bits 12 and 13 are used to carry reenqueue reason. In addition to diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index dc3975ff1b2e..cf0fd03dd7a2 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -21,6 +21,11 @@ enum hk_type { HK_TYPE_MAX, /* + * HK_TYPE_KTHREAD is now an alias of HK_TYPE_DOMAIN + */ + HK_TYPE_KTHREAD = HK_TYPE_DOMAIN, + + /* * The following housekeeping types are only set by the nohz_full * boot commandline option. So they can share the same value. */ @@ -29,7 +34,6 @@ enum hk_type { HK_TYPE_RCU = HK_TYPE_KERNEL_NOISE, HK_TYPE_MISC = HK_TYPE_KERNEL_NOISE, HK_TYPE_WQ = HK_TYPE_KERNEL_NOISE, - HK_TYPE_KTHREAD = HK_TYPE_KERNEL_NOISE }; #ifdef CONFIG_CPU_ISOLATION diff --git a/include/linux/slab.h b/include/linux/slab.h index 15a60b501b95..2b5ab488e96b 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -1234,6 +1234,9 @@ void *kvrealloc_node_align_noprof(const void *p, size_t size, unsigned long alig extern void kvfree(const void *addr); DEFINE_FREE(kvfree, void *, if (!IS_ERR_OR_NULL(_T)) kvfree(_T)) +extern void kvfree_atomic(const void *addr); +DEFINE_FREE(kvfree_atomic, void *, if (!IS_ERR_OR_NULL(_T)) kvfree_atomic(_T)) + extern void kvfree_sensitive(const void *addr, size_t len); unsigned int kmem_cache_size(struct kmem_cache *s); diff --git a/include/linux/smbdirect.h b/include/linux/smbdirect.h new file mode 100644 index 000000000000..97f5ba730fa7 --- /dev/null +++ b/include/linux/smbdirect.h @@ -0,0 +1,186 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2025, Stefan Metzmacher + */ + +#ifndef __LINUX_SMBDIRECT_H__ +#define __LINUX_SMBDIRECT_H__ + +#include <linux/types.h> + +/* SMB-DIRECT buffer descriptor V1 structure [MS-SMBD] 2.2.3.1 */ +struct smbdirect_buffer_descriptor_v1 { + __le64 offset; + __le32 token; + __le32 length; +} __packed; + +/* + * Connection parameters mostly from [MS-SMBD] 3.1.1.1 + * + * These are setup and negotiated at the beginning of a + * connection and remain constant unless explicitly changed. + * + * Some values are important for the upper layer. + */ +struct smbdirect_socket_parameters { + __u64 flags; +#define SMBDIRECT_FLAG_PORT_RANGE_ONLY_IB ((__u64)0x1) +#define SMBDIRECT_FLAG_PORT_RANGE_ONLY_IW ((__u64)0x2) + __u32 resolve_addr_timeout_msec; + __u32 resolve_route_timeout_msec; + __u32 rdma_connect_timeout_msec; + __u32 negotiate_timeout_msec; + __u16 initiator_depth; /* limited to U8_MAX */ + __u16 responder_resources; /* limited to U8_MAX */ + __u16 recv_credit_max; + __u16 send_credit_target; + __u32 max_send_size; + __u32 max_fragmented_send_size; + __u32 max_recv_size; + __u32 max_fragmented_recv_size; + __u32 max_read_write_size; + __u32 max_frmr_depth; + __u32 keepalive_interval_msec; + __u32 keepalive_timeout_msec; +} __packed; + +#define SMBDIRECT_FLAG_PORT_RANGE_MASK ( \ + SMBDIRECT_FLAG_PORT_RANGE_ONLY_IB | \ + SMBDIRECT_FLAG_PORT_RANGE_ONLY_IW) + +struct smbdirect_socket; +struct smbdirect_send_batch; +struct smbdirect_mr_io; + +#include <rdma/rw.h> + +u8 smbdirect_netdev_rdma_capable_node_type(struct net_device *netdev); + +bool smbdirect_frwr_is_supported(const struct ib_device_attr *attrs); + +int smbdirect_socket_create_kern(struct net *net, struct smbdirect_socket **_sc); + +int smbdirect_socket_create_accepting(struct rdma_cm_id *id, struct smbdirect_socket **_sc); + +int smbdirect_socket_set_initial_parameters(struct smbdirect_socket *sc, + const struct smbdirect_socket_parameters *sp); + +const struct smbdirect_socket_parameters * +smbdirect_socket_get_current_parameters(struct smbdirect_socket *sc); + +int smbdirect_socket_set_kernel_settings(struct smbdirect_socket *sc, + enum ib_poll_context poll_ctx, + gfp_t gfp_mask); + +#define SMBDIRECT_LOG_ERR 0x0 +#define SMBDIRECT_LOG_INFO 0x1 + +#define SMBDIRECT_LOG_OUTGOING 0x1 +#define SMBDIRECT_LOG_INCOMING 0x2 +#define SMBDIRECT_LOG_READ 0x4 +#define SMBDIRECT_LOG_WRITE 0x8 +#define SMBDIRECT_LOG_RDMA_SEND 0x10 +#define SMBDIRECT_LOG_RDMA_RECV 0x20 +#define SMBDIRECT_LOG_KEEP_ALIVE 0x40 +#define SMBDIRECT_LOG_RDMA_EVENT 0x80 +#define SMBDIRECT_LOG_RDMA_MR 0x100 +#define SMBDIRECT_LOG_RDMA_RW 0x200 +#define SMBDIRECT_LOG_NEGOTIATE 0x400 +void smbdirect_socket_set_logging(struct smbdirect_socket *sc, + void *private_ptr, + bool (*needed)(struct smbdirect_socket *sc, + void *private_ptr, + unsigned int lvl, + unsigned int cls), + void (*vaprintf)(struct smbdirect_socket *sc, + const char *func, + unsigned int line, + void *private_ptr, + unsigned int lvl, + unsigned int cls, + struct va_format *vaf)); + +bool smbdirect_connection_is_connected(struct smbdirect_socket *sc); + +int smbdirect_connection_wait_for_connected(struct smbdirect_socket *sc); + +int smbdirect_socket_bind(struct smbdirect_socket *sc, struct sockaddr *addr); + +void smbdirect_socket_shutdown(struct smbdirect_socket *sc); + +void smbdirect_socket_release(struct smbdirect_socket *sc); + +int smbdirect_connection_send_batch_flush(struct smbdirect_socket *sc, + struct smbdirect_send_batch *batch, + bool is_last); + +/* + * This is only temporary and only needed + * as long as the client still requires + * to use smbdirect_connection_send_single_iter() + */ +struct smbdirect_send_batch_storage { + union { + struct list_head __msg_list; + __aligned_u64 __space[5]; + }; +}; + +struct smbdirect_send_batch * +smbdirect_init_send_batch_storage(struct smbdirect_send_batch_storage *storage, + bool need_invalidate_rkey, + unsigned int remote_key); + +int smbdirect_connection_send_single_iter(struct smbdirect_socket *sc, + struct smbdirect_send_batch *batch, + struct iov_iter *iter, + unsigned int flags, + u32 remaining_data_length); + +int smbdirect_connection_send_wait_zero_pending(struct smbdirect_socket *sc); + +int smbdirect_connection_send_iter(struct smbdirect_socket *sc, + struct iov_iter *iter, + unsigned int flags, + bool need_invalidate, + unsigned int remote_key); + +int smbdirect_connection_recvmsg(struct smbdirect_socket *sc, + struct msghdr *msg, + unsigned int flags); + +int smbdirect_connect(struct smbdirect_socket *sc, + const struct sockaddr *dst); + +int smbdirect_connect_sync(struct smbdirect_socket *sc, + const struct sockaddr *dst); + +int smbdirect_socket_listen(struct smbdirect_socket *sc, int backlog); + +struct smbdirect_socket *smbdirect_socket_accept(struct smbdirect_socket *lsc, + long timeo, + struct proto_accept_arg *arg); + +int smbdirect_connection_rdma_xmit(struct smbdirect_socket *sc, + void *buf, size_t buf_len, + struct smbdirect_buffer_descriptor_v1 *desc, + size_t desc_len, + bool is_read); + +struct smbdirect_mr_io * +smbdirect_connection_register_mr_io(struct smbdirect_socket *sc, + struct iov_iter *iter, + bool writing, + bool need_invalidate); + +void smbdirect_mr_io_fill_buffer_descriptor(struct smbdirect_mr_io *mr, + struct smbdirect_buffer_descriptor_v1 *v1); + +void smbdirect_connection_deregister_mr_io(struct smbdirect_mr_io *mr); + +void smbdirect_connection_legacy_debug_proc_show(struct smbdirect_socket *sc, + unsigned int rdma_readwrite_threshold, + struct seq_file *m); + +#endif /* __LINUX_SMBDIRECT_H__ */ diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 2ebba746c18f..89165b769e5c 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -21,7 +21,7 @@ #define VFIO_PCI_CORE_H #define VFIO_PCI_OFFSET_SHIFT 40 -#define VFIO_PCI_OFFSET_TO_INDEX(off) (off >> VFIO_PCI_OFFSET_SHIFT) +#define VFIO_PCI_OFFSET_TO_INDEX(off) ((u64)(off) >> VFIO_PCI_OFFSET_SHIFT) #define VFIO_PCI_INDEX_TO_OFFSET(index) ((u64)(index) << VFIO_PCI_OFFSET_SHIFT) #define VFIO_PCI_OFFSET_MASK (((u64)(1) << VFIO_PCI_OFFSET_SHIFT) - 1) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index ab6cb70ca1a5..6177624539b3 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -534,8 +534,10 @@ alloc_workqueue_noprof(const char *fmt, unsigned int flags, int max_active, ...) * Pointer to the allocated workqueue on success, %NULL on failure. */ __printf(2, 5) struct workqueue_struct * -devm_alloc_workqueue(struct device *dev, const char *fmt, unsigned int flags, - int max_active, ...); +devm_alloc_workqueue_noprof(struct device *dev, const char *fmt, + unsigned int flags, int max_active, ...); +#define devm_alloc_workqueue(...) \ + alloc_hooks(devm_alloc_workqueue_noprof(__VA_ARGS__)) #ifdef CONFIG_LOCKDEP /** |