Re: [patch 02/12] rseq: Add fields and constants for time slice extension

[Mathieu Desnoyers]

On 2025-09-11 11:41, Mathieu Desnoyers wrote:
> On 2025-09-08 18:59, Thomas Gleixner wrote:
[...]

> > +
> > +The kernel enforces flag consistency and terminates the thread with 
> > SIGSEGV
> > +if it detects a violation.
> > --- a/include/linux/rseq_types.h
> > +++ b/include/linux/rseq_types.h
> > @@ -71,12 +71,35 @@ struct rseq_ids {
> >   };
> >   /**
> > + * union rseq_slice_state - Status information for rseq time slice 
> > extension
> > + * @state:    Compound to access the overall state
> > + * @enabled:    Time slice extension is enabled for the task
> > + * @granted:    Time slice extension was granted to the task
> > + */
> > +union rseq_slice_state {
> > +    u16            state;
> > +    struct {
> > +        u8        enabled;
> > +        u8        granted;
> > +    };
> > +};
> > +
> > +/**
> > + * struct rseq_slice - Status information for rseq time slice extension
> > + * @state:    Time slice extension state
> > + */
> > +struct rseq_slice {
> > +    union rseq_slice_state    state;
> > +};
> > +
> > +/**
> >    * struct rseq_data - Storage for all rseq related data
> >    * @usrptr:    Pointer to the registered user space RSEQ memory
> >    * @len:    Length of the RSEQ region
> >    * @sig:    Signature of critial section abort IPs
> >    * @event:    Storage for event management
> >    * @ids:    Storage for cached CPU ID and MM CID
> > + * @slice:    Storage for time slice extension data
> >    */
> >   struct rseq_data {
> >       struct rseq __user        *usrptr;
> > @@ -84,6 +107,9 @@ struct rseq_data {
> >       u32                sig;
> >       struct rseq_event        event;
> >       struct rseq_ids            ids;
> > +#ifdef CONFIG_RSEQ_SLICE_EXTENSION
> > +    struct rseq_slice        slice;
> > +#endif

Note: we could move this #ifdef to surround the definition
of both union rseq_slice_state and struct rseq_slice,
and emit an empty structure in the #else case rather than
do the ifdef here.

Thanks,

Mathieu

> >   };
> >   #else /* CONFIG_RSEQ */
> > --- a/include/uapi/linux/rseq.h
> > +++ b/include/uapi/linux/rseq.h
> > @@ -23,9 +23,15 @@ enum rseq_flags {
> >   };
> >   enum rseq_cs_flags_bit {
> > +    /* Historical and unsupported bits */
> >       RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT    = 0,
> >       RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT    = 1,
> >       RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT    = 2,
> > +    /* (3) Intentional gap to put new bits into a seperate byte */
> > +
> > +    /* User read only feature flags */
> > +    RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE_BIT    = 4,
> > +    RSEQ_CS_FLAG_SLICE_EXT_ENABLED_BIT    = 5,
> >   };
> >   enum rseq_cs_flags {
> > @@ -35,6 +41,22 @@ enum rseq_cs_flags {
> >           (1U << RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT),
> >       RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE    =
> >           (1U << RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT),
> > +
> > +    RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE    =
> > +        (1U << RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE_BIT),
> > +    RSEQ_CS_FLAG_SLICE_EXT_ENABLED        =
> > +        (1U << RSEQ_CS_FLAG_SLICE_EXT_ENABLED_BIT),
> > +};
> > +
> > +enum rseq_slice_bits {
> > +    /* Time slice extension ABI bits */
> > +    RSEQ_SLICE_EXT_REQUEST_BIT        = 0,
> > +    RSEQ_SLICE_EXT_GRANTED_BIT        = 1,
> > +};
> > +
> > +enum rseq_slice_masks {
> > +    RSEQ_SLICE_EXT_REQUEST    = (1U << RSEQ_SLICE_EXT_REQUEST_BIT),
> > +    RSEQ_SLICE_EXT_GRANTED    = (1U << RSEQ_SLICE_EXT_GRANTED_BIT),
> >   };
> >   /*
> > @@ -142,6 +164,12 @@ struct rseq {
> >       __u32 mm_cid;
> >       /*
> > +     * Time slice extension control word. CPU local atomic updates from
> > +     * kernel and user space.
> > +     */
> > +    __u32 slice_ctrl;
> > +
> > +    /*
> >        * Flexible array member at end of structure, after last feature 
> > field.
> >        */
> >       char end[];
> > --- a/init/Kconfig
> > +++ b/init/Kconfig
> > @@ -1908,6 +1908,18 @@ config RSEQ_DEBUG_DEFAULT_ENABLE
> >         If unsure, say N.
> > +config RSEQ_SLICE_EXTENSION
> > +    bool "Enable rseq based time slice extension mechanism"
> > +    depends on RSEQ && HIGH_RES_TIMERS && GENERIC_ENTRY && 
> > HAVE_GENERIC_TIF_BITS
> > +    help
> > +          Allows userspace to request a limited time slice extension 
> > when
> > +      returning from an interrupt to user space via the RSEQ shared
> > +      data ABI. If granted, that allows to complete a critical section,
> > +      so that other threads are not stuck on a conflicted resource,
> > +      while the task is scheduled out.
> > +
> > +      If unsure, say N.
> > +
> >   config DEBUG_RSEQ
> >       default n
> >       bool "Enable debugging of rseq() system call" if EXPERT
> > --- a/kernel/rseq.c
> > +++ b/kernel/rseq.c
> > @@ -387,6 +387,8 @@ static bool rseq_reset_ids(void)
> >    */
> >   SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, 
> > int, flags, u32, sig)
> >   {
> > +    u32 rseqfl = 0;
> > +
> >       if (flags & RSEQ_FLAG_UNREGISTER) {
> >           if (flags & ~RSEQ_FLAG_UNREGISTER)
> >               return -EINVAL;
> > @@ -448,6 +450,12 @@ SYSCALL_DEFINE4(rseq, struct rseq __user
> >       if (put_user_masked_u64(0UL, &rseq->rseq_cs))
> >           return -EFAULT;
> > +    if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION))
> > +        rseqfl |= RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE;
> > +
> > +    if (put_user_masked_u32(rseqfl, &rseq->flags))
> > +        return -EFAULT;
> > +
> >       /*
> >        * Activate the registration by setting the rseq area address, 
> > length
> >        * and signature in the task struct.


--
Mathieu Desnoyers
EfficiOS Inc.
https://www.efficios.com