diff --git a/include/linux/rseq.h b/include/linux/rseq.h index f446909551df..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); } @@ -161,6 +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..934db41ec782 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; @@ -230,6 +244,7 @@ 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); @@ -517,11 +532,9 @@ bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids, 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); @@ -612,6 +625,14 @@ 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 +644,9 @@ 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); diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h index 0b42045988db..a469c1870849 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 diff --git a/kernel/rseq.c b/kernel/rseq.c index 586f58f652c6..aa25753ea135 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -253,11 +253,14 @@ efault: static void rseq_slowpath_update_usr(struct pt_regs *regs) { /* - * Preserve rseq state and user_irq state. The generic entry code - * clears user_irq on the way out, the non-generic entry - * architectures are not having user_irq. + * Preserve has_rseq and user_irq state. The generic entry code clears + * user_irq on the way out, the non-generic entry architectures are not + * setting user_irq. */ - const struct rseq_event evt_mask = { .has_rseq = true, .user_irq = true, }; + const struct rseq_event evt_mask = { + .has_rseq = RSEQ_HAS_RSEQ_VERSION_MASK, + .user_irq = true, + }; struct task_struct *t = current; struct rseq_ids ids; u32 node_id; @@ -330,8 +333,9 @@ void __rseq_handle_slowpath(struct pt_regs *regs) void __rseq_signal_deliver(int sig, struct pt_regs *regs) { rseq_stat_inc(rseq_stats.signal); + /* - * Don't update IDs, they are handled on exit to user if + * Don't update IDs yet, they are handled on exit to user if * necessary. The important thing is to abort a critical section of * the interrupted context as after this point the instruction * pointer in @regs points to the signal handler. @@ -344,6 +348,13 @@ void __rseq_signal_deliver(int sig, struct pt_regs *regs) current->rseq.event.error = 0; force_sigsegv(sig); } + + /* + * In legacy mode, force the update of IDs before returning to user + * space to stay compatible. + */ + if (!rseq_v2(current)) + rseq_force_update(); } /* @@ -408,6 +419,7 @@ efault: SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig) { u32 rseqfl = 0; + u8 version = 1; if (flags & RSEQ_FLAG_UNREGISTER) { if (flags & ~RSEQ_FLAG_UNREGISTER) @@ -461,7 +473,11 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32 if (!access_ok(rseq, rseq_len)) return -EFAULT; - if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION)) { + /* + * The version check effectivly disables time slice extensions until the + * RSEQ ABI V2 registration are implemented. + */ + if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION) && version > 1) { if (rseq_slice_extension_enabled()) { rseqfl |= RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE; if (flags & RSEQ_FLAG_SLICE_EXT_DEFAULT_ON) @@ -484,7 +500,15 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32 unsafe_put_user(RSEQ_CPU_ID_UNINITIALIZED, &rseq->cpu_id, efault); unsafe_put_user(0U, &rseq->node_id, efault); unsafe_put_user(0U, &rseq->mm_cid, efault); - unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); + + /* + * All fields past mm_cid are only valid for non-legacy v2 + * registrations. + */ + if (version > 1) { + if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION)) + unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); + } } /* @@ -712,6 +736,8 @@ int rseq_slice_extension_prctl(unsigned long arg2, unsigned long arg3) return -ENOTSUPP; if (!current->rseq.usrptr) return -ENXIO; + if (!rseq_v2(current)) + return -ENOTSUPP; /* No change? */ if (enable == !!current->rseq.slice.state.enabled) diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 623445603725..226a6329f3e9 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -199,7 +199,16 @@ static void ipi_rseq(void *info) * is negligible. */ smp_mb(); - rseq_sched_switch_event(current); + /* + * Legacy mode requires that IDs are written and the critical section is + * evaluated. V2 optimized mode handles the critical section and IDs are + * only updated if they change as a consequence of preemption after + * return from this IPI. + */ + if (rseq_v2(current)) + rseq_sched_switch_event(current); + else + rseq_force_update(); } static void ipi_sync_rq_state(void *info)