From a9e3760b0838299649c0d57cca44daaf40ba3c33 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 14 Sep 2026 22:12:34 -1000 Subject: sched_ext: Maintain an online cid mask in the scheduler arena Schedulers on the default cid mapping treat [0, nr_online_cids) as the online set and restart on hotplug. Schedulers that install their own mapping with scx_bpf_cid_override() have no way to learn which cids are online: the count no longer identifies members and the CPU-form cpumask is unusable from cid programs. This is an obvious hole in the cid API. Add scx_bpf_online_cmask(), a kernel-maintained cmask in the scheduler's arena, allocated alongside the per-CPU scratch masks and populated after the cid mapping is finalized and before ops.init(), for child schedulers too. The pointer stays valid through ops.exit() with no reference to take. It is the arena offset as a void pointer, the same form struct_ops arena arguments arrive in. The verifier types the void return as a scalar for the program's arena cast. The mask follows the SCX hotplug notifications: seeded from cpu_active_mask and updated before ops.cid_online/offline() runs, so it lags cpu_online_mask only inside a hotplug transition. Updates walk the scheduler list under the lock that also serializes unlinking. Reads are live, not atomic snapshots. Root initialization excludes hotplug. v2: Reworded the getter kerneldoc (Andrea Righi). Signed-off-by: Tejun Heo Reviewed-by: Andrea Righi --- lib/errseq.c | 208 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 208 insertions(+) create mode 100644 lib/errseq.c (limited to 'lib/errseq.c') diff --git a/lib/errseq.c b/lib/errseq.c new file mode 100644 index 000000000..13a2581c5 --- /dev/null +++ b/lib/errseq.c @@ -0,0 +1,208 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include + +/* + * An errseq_t is a way of recording errors in one place, and allowing any + * number of "subscribers" to tell whether it has changed since a previous + * point where it was sampled. + * + * It's implemented as an unsigned 32-bit value. The low order bits are + * designated to hold an error code (between 0 and -MAX_ERRNO). The upper bits + * are used as a counter. This is done with atomics instead of locking so that + * these functions can be called from any context. + * + * The general idea is for consumers to sample an errseq_t value. That value + * can later be used to tell whether any new errors have occurred since that + * sampling was done. + * + * Note that there is a risk of collisions if new errors are being recorded + * frequently, since we have so few bits to use as a counter. + * + * To mitigate this, one bit is used as a flag to tell whether the value has + * been sampled since a new value was recorded. That allows us to avoid bumping + * the counter if no one has sampled it since the last time an error was + * recorded. + * + * A new errseq_t should always be zeroed out. A errseq_t value of all zeroes + * is the special (but common) case where there has never been an error. An all + * zero value thus serves as the "epoch" if one wishes to know whether there + * has ever been an error set since it was first initialized. + */ + +/* The low bits are designated for error code (max of MAX_ERRNO) */ +#define ERRSEQ_SHIFT (ilog2(MAX_ERRNO) + 1) + +/* This bit is used as a flag to indicate whether the value has been seen */ +#define ERRSEQ_SEEN (1 << ERRSEQ_SHIFT) + +/* Leverage macro ERRSEQ_SEEN to define errno mask macro here */ +#define ERRNO_MASK (ERRSEQ_SEEN - 1) + +/* The lowest bit of the counter */ +#define ERRSEQ_CTR_INC (1 << (ERRSEQ_SHIFT + 1)) + +/** + * errseq_set - set a errseq_t for later reporting + * @eseq: errseq_t field that should be set + * @err: error to set (must be between -1 and -MAX_ERRNO) + * + * This function sets the error in @eseq, and increments the sequence counter + * if the last sequence was sampled at some point in the past. + * + * Any error set will always overwrite an existing error. + * + * Return: The previous value, primarily for debugging purposes. The + * return value should not be used as a previously sampled value in later + * calls as it will not have the SEEN flag set. + */ +errseq_t errseq_set(errseq_t *eseq, int err) +{ + errseq_t cur, old; + + + /* + * Ensure the error code actually fits where we want it to go. If it + * doesn't then just throw a warning and don't record anything. We + * also don't accept zero here as that would effectively clear a + * previous error. + */ + old = READ_ONCE(*eseq); + + if (WARN(unlikely(err == 0 || (unsigned int)-err > MAX_ERRNO), + "err = %d\n", err)) + return old; + + for (;;) { + errseq_t new; + + /* Clear out error bits and set new error */ + new = (old & ~(ERRNO_MASK | ERRSEQ_SEEN)) | -err; + + /* Only increment if someone has looked at it */ + if (old & ERRSEQ_SEEN) + new += ERRSEQ_CTR_INC; + + /* If there would be no change, then call it done */ + if (new == old) { + cur = new; + break; + } + + /* Try to swap the new value into place */ + cur = cmpxchg(eseq, old, new); + + /* + * Call it success if we did the swap or someone else beat us + * to it for the same value. + */ + if (likely(cur == old || cur == new)) + break; + + /* Raced with an update, try again */ + old = cur; + } + return cur; +} +EXPORT_SYMBOL(errseq_set); + +/** + * errseq_sample() - Grab current errseq_t value. + * @eseq: Pointer to errseq_t to be sampled. + * + * This function allows callers to initialise their errseq_t variable. + * If the error has been "seen", new callers will not see an old error. + * If there is an unseen error in @eseq, the caller of this function will + * see it the next time it checks for an error. + * + * Context: Any context. + * Return: The current errseq value. + */ +errseq_t errseq_sample(errseq_t *eseq) +{ + errseq_t old = READ_ONCE(*eseq); + + /* If nobody has seen this error yet, then we can be the first. */ + if (!(old & ERRSEQ_SEEN)) + old = 0; + return old; +} +EXPORT_SYMBOL(errseq_sample); + +/** + * errseq_check() - Has an error occurred since a particular sample point? + * @eseq: Pointer to errseq_t value to be checked. + * @since: Previously-sampled errseq_t from which to check. + * + * Grab the value that eseq points to, and see if it has changed @since + * the given value was sampled. The @since value is not advanced, so there + * is no need to mark the value as seen. + * + * Return: The latest error set in the errseq_t or 0 if it hasn't changed. + */ +int errseq_check(errseq_t *eseq, errseq_t since) +{ + errseq_t cur = READ_ONCE(*eseq); + + if (likely(cur == since)) + return 0; + return -(cur & ERRNO_MASK); +} +EXPORT_SYMBOL(errseq_check); + +/** + * errseq_check_and_advance() - Check an errseq_t and advance to current value. + * @eseq: Pointer to value being checked and reported. + * @since: Pointer to previously-sampled errseq_t to check against and advance. + * + * Grab the eseq value, and see whether it matches the value that @since + * points to. If it does, then just return 0. + * + * If it doesn't, then the value has changed. Set the "seen" flag, and try to + * swap it into place as the new eseq value. Then, set that value as the new + * "since" value, and return whatever the error portion is set to. + * + * Note that no locking is provided here for concurrent updates to the "since" + * value. The caller must provide that if necessary. Because of this, callers + * may want to do a lockless errseq_check before taking the lock and calling + * this. + * + * Return: Negative errno if one has been stored, or 0 if no new error has + * occurred. + */ +int errseq_check_and_advance(errseq_t *eseq, errseq_t *since) +{ + int err = 0; + errseq_t old, new; + + /* + * Most callers will want to use the inline wrapper to check this, + * so that the common case of no error is handled without needing + * to take the lock that protects the "since" value. + */ + old = READ_ONCE(*eseq); + if (old != *since) { + /* + * Set the flag and try to swap it into place if it has + * changed. + * + * We don't care about the outcome of the swap here. If the + * swap doesn't occur, then it has either been updated by a + * writer who is altering the value in some way (updating + * counter or resetting the error), or another reader who is + * just setting the "seen" flag. Either outcome is OK, and we + * can advance "since" and return an error based on what we + * have. + */ + new = old | ERRSEQ_SEEN; + if (new != old) + cmpxchg(eseq, old, new); + *since = new; + err = -(new & ERRNO_MASK); + } + return err; +} +EXPORT_SYMBOL(errseq_check_and_advance); -- cgit v1.3.1