6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tejun Heo tj@kernel.org

[ Upstream commit 0c2b8356e430229efef42b03bd765a2a7ecf73fd ]

There currently isn't a place to place SCX-internal types and accessors to be shared between ext.c and ext_idle.c. Create kernel/sched/ext_internal.h and move internal type and accessor definitions there. This trims ext.c a bit and makes future additions easier. Pure code reorganization. No functional changes.

Signed-off-by: Tejun Heo tj@kernel.org Acked-by: Andrea Righi arighi@nvidia.com Stable-dep-of: efeeaac9ae97 ("sched_ext: Sync error_irq_work before freeing scx_sched") Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/sched/build_policy.c | 1 + kernel/sched/ext.c | 1034 ---------------------------------- kernel/sched/ext.h | 23 - kernel/sched/ext_internal.h | 1061 +++++++++++++++++++++++++++++++++++ 4 files changed, 1062 insertions(+), 1057 deletions(-) create mode 100644 kernel/sched/ext_internal.h

diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c index c4a488e67aa7d..755883faf7518 100644 --- a/kernel/sched/build_policy.c +++ b/kernel/sched/build_policy.c @@ -58,6 +58,7 @@ #include "deadline.c"

#ifdef CONFIG_SCHED_CLASS_EXT +# include "ext_internal.h" # include "ext.c" # include "ext_idle.c" #endif diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 088ceff38c8a4..8ecde1abb4e28 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -9,1040 +9,6 @@ #include <linux/btf_ids.h> #include "ext_idle.h"

-#define SCX_OP_IDX(op) (offsetof(struct sched_ext_ops, op) / sizeof(void (*)(void))) - -enum scx_consts { - SCX_DSP_DFL_MAX_BATCH = 32, - SCX_DSP_MAX_LOOPS = 32, - SCX_WATCHDOG_MAX_TIMEOUT = 30 * HZ, - - SCX_EXIT_BT_LEN = 64, - SCX_EXIT_MSG_LEN = 1024, - SCX_EXIT_DUMP_DFL_LEN = 32768, - - SCX_CPUPERF_ONE = SCHED_CAPACITY_SCALE, - - /* - * Iterating all tasks may take a while. Periodically drop - * scx_tasks_lock to avoid causing e.g. CSD and RCU stalls. - */ - SCX_TASK_ITER_BATCH = 32, -}; - -enum scx_exit_kind { - SCX_EXIT_NONE, - SCX_EXIT_DONE, - - SCX_EXIT_UNREG = 64, /* user-space initiated unregistration */ - SCX_EXIT_UNREG_BPF, /* BPF-initiated unregistration */ - SCX_EXIT_UNREG_KERN, /* kernel-initiated unregistration */ - SCX_EXIT_SYSRQ, /* requested by 'S' sysrq */ - - SCX_EXIT_ERROR = 1024, /* runtime error, error msg contains details */ - SCX_EXIT_ERROR_BPF, /* ERROR but triggered through scx_bpf_error() */ - SCX_EXIT_ERROR_STALL, /* watchdog detected stalled runnable tasks */ -}; - -/* - * An exit code can be specified when exiting with scx_bpf_exit() or scx_exit(), - * corresponding to exit_kind UNREG_BPF and UNREG_KERN respectively. The codes - * are 64bit of the format: - * - * Bits: [63 .. 48 47 .. 32 31 .. 0] - * [ SYS ACT ] [ SYS RSN ] [ USR ] - * - * SYS ACT: System-defined exit actions - * SYS RSN: System-defined exit reasons - * USR : User-defined exit codes and reasons - * - * Using the above, users may communicate intention and context by ORing system - * actions and/or system reasons with a user-defined exit code. - */ -enum scx_exit_code { - /* Reasons */ - SCX_ECODE_RSN_HOTPLUG = 1LLU << 32, - - /* Actions */ - SCX_ECODE_ACT_RESTART = 1LLU << 48, -}; - -/* - * scx_exit_info is passed to ops.exit() to describe why the BPF scheduler is - * being disabled. - */ -struct scx_exit_info { - /* %SCX_EXIT_* - broad category of the exit reason */ - enum scx_exit_kind kind; - - /* exit code if gracefully exiting */ - s64 exit_code; - - /* textual representation of the above */ - const char *reason; - - /* backtrace if exiting due to an error */ - unsigned long *bt; - u32 bt_len; - - /* informational message */ - char *msg; - - /* debug dump */ - char *dump; -}; - -/* sched_ext_ops.flags */ -enum scx_ops_flags { - /* - * Keep built-in idle tracking even if ops.update_idle() is implemented. - */ - SCX_OPS_KEEP_BUILTIN_IDLE = 1LLU << 0, - - /* - * By default, if there are no other task to run on the CPU, ext core - * keeps running the current task even after its slice expires. If this - * flag is specified, such tasks are passed to ops.enqueue() with - * %SCX_ENQ_LAST. See the comment above %SCX_ENQ_LAST for more info. - */ - SCX_OPS_ENQ_LAST = 1LLU << 1, - - /* - * An exiting task may schedule after PF_EXITING is set. In such cases, - * bpf_task_from_pid() may not be able to find the task and if the BPF - * scheduler depends on pid lookup for dispatching, the task will be - * lost leading to various issues including RCU grace period stalls. - * - * To mask this problem, by default, unhashed tasks are automatically - * dispatched to the local DSQ on enqueue. If the BPF scheduler doesn't - * depend on pid lookups and wants to handle these tasks directly, the - * following flag can be used. - */ - SCX_OPS_ENQ_EXITING = 1LLU << 2, - - /* - * If set, only tasks with policy set to SCHED_EXT are attached to - * sched_ext. If clear, SCHED_NORMAL tasks are also included. - */ - SCX_OPS_SWITCH_PARTIAL = 1LLU << 3, - - /* - * A migration disabled task can only execute on its current CPU. By - * default, such tasks are automatically put on the CPU's local DSQ with - * the default slice on enqueue. If this ops flag is set, they also go - * through ops.enqueue(). - * - * A migration disabled task never invokes ops.select_cpu() as it can - * only select the current CPU. Also, p->cpus_ptr will only contain its - * current CPU while p->nr_cpus_allowed keeps tracking p->user_cpus_ptr - * and thus may disagree with cpumask_weight(p->cpus_ptr). - */ - SCX_OPS_ENQ_MIGRATION_DISABLED = 1LLU << 4, - - /* - * Queued wakeup (ttwu_queue) is a wakeup optimization that invokes - * ops.enqueue() on the ops.select_cpu() selected or the wakee's - * previous CPU via IPI (inter-processor interrupt) to reduce cacheline - * transfers. When this optimization is enabled, ops.select_cpu() is - * skipped in some cases (when racing against the wakee switching out). - * As the BPF scheduler may depend on ops.select_cpu() being invoked - * during wakeups, queued wakeup is disabled by default. - * - * If this ops flag is set, queued wakeup optimization is enabled and - * the BPF scheduler must be able to handle ops.enqueue() invoked on the - * wakee's CPU without preceding ops.select_cpu() even for tasks which - * may be executed on multiple CPUs. - */ - SCX_OPS_ALLOW_QUEUED_WAKEUP = 1LLU << 5, - - /* - * If set, enable per-node idle cpumasks. If clear, use a single global - * flat idle cpumask. - */ - SCX_OPS_BUILTIN_IDLE_PER_NODE = 1LLU << 6, - - /* - * CPU cgroup support flags - */ - SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* DEPRECATED, will be removed on 6.18 */ - - SCX_OPS_ALL_FLAGS = SCX_OPS_KEEP_BUILTIN_IDLE | - SCX_OPS_ENQ_LAST | - SCX_OPS_ENQ_EXITING | - SCX_OPS_ENQ_MIGRATION_DISABLED | - SCX_OPS_ALLOW_QUEUED_WAKEUP | - SCX_OPS_SWITCH_PARTIAL | - SCX_OPS_BUILTIN_IDLE_PER_NODE | - SCX_OPS_HAS_CGROUP_WEIGHT, - - /* high 8 bits are internal, don't include in SCX_OPS_ALL_FLAGS */ - __SCX_OPS_INTERNAL_MASK = 0xffLLU << 56, - - SCX_OPS_HAS_CPU_PREEMPT = 1LLU << 56, -}; - -/* argument container for ops.init_task() */ -struct scx_init_task_args { - /* - * Set if ops.init_task() is being invoked on the fork path, as opposed - * to the scheduler transition path. - */ - bool fork; -#ifdef CONFIG_EXT_GROUP_SCHED - /* the cgroup the task is joining */ - struct cgroup *cgroup; -#endif -}; - -/* argument container for ops.exit_task() */ -struct scx_exit_task_args { - /* Whether the task exited before running on sched_ext. */ - bool cancelled; -}; - -/* argument container for ops->cgroup_init() */ -struct scx_cgroup_init_args { - /* the weight of the cgroup [1..10000] */ - u32 weight; - - /* bandwidth control parameters from cpu.max and cpu.max.burst */ - u64 bw_period_us; - u64 bw_quota_us; - u64 bw_burst_us; -}; - -enum scx_cpu_preempt_reason { - /* next task is being scheduled by &sched_class_rt */ - SCX_CPU_PREEMPT_RT, - /* next task is being scheduled by &sched_class_dl */ - SCX_CPU_PREEMPT_DL, - /* next task is being scheduled by &sched_class_stop */ - SCX_CPU_PREEMPT_STOP, - /* unknown reason for SCX being preempted */ - SCX_CPU_PREEMPT_UNKNOWN, -}; - -/* - * Argument container for ops->cpu_acquire(). Currently empty, but may be - * expanded in the future. - */ -struct scx_cpu_acquire_args {}; - -/* argument container for ops->cpu_release() */ -struct scx_cpu_release_args { - /* the reason the CPU was preempted */ - enum scx_cpu_preempt_reason reason; - - /* the task that's going to be scheduled on the CPU */ - struct task_struct *task; -}; - -/* - * Informational context provided to dump operations. - */ -struct scx_dump_ctx { - enum scx_exit_kind kind; - s64 exit_code; - const char *reason; - u64 at_ns; - u64 at_jiffies; -}; - -/** - * struct sched_ext_ops - Operation table for BPF scheduler implementation - * - * A BPF scheduler can implement an arbitrary scheduling policy by - * implementing and loading operations in this table. Note that a userland - * scheduling policy can also be implemented using the BPF scheduler - * as a shim layer. - */ -struct sched_ext_ops { - /** - * @select_cpu: Pick the target CPU for a task which is being woken up - * @p: task being woken up - * @prev_cpu: the cpu @p was on before sleeping - * @wake_flags: SCX_WAKE_* - * - * Decision made here isn't final. @p may be moved to any CPU while it - * is getting dispatched for execution later. However, as @p is not on - * the rq at this point, getting the eventual execution CPU right here - * saves a small bit of overhead down the line. - * - * If an idle CPU is returned, the CPU is kicked and will try to - * dispatch. While an explicit custom mechanism can be added, - * select_cpu() serves as the default way to wake up idle CPUs. - * - * @p may be inserted into a DSQ directly by calling - * scx_bpf_dsq_insert(). If so, the ops.enqueue() will be skipped. - * Directly inserting into %SCX_DSQ_LOCAL will put @p in the local DSQ - * of the CPU returned by this operation. - * - * Note that select_cpu() is never called for tasks that can only run - * on a single CPU or tasks with migration disabled, as they don't have - * the option to select a different CPU. See select_task_rq() for - * details. - */ - s32 (*select_cpu)(struct task_struct *p, s32 prev_cpu, u64 wake_flags); - - /** - * @enqueue: Enqueue a task on the BPF scheduler - * @p: task being enqueued - * @enq_flags: %SCX_ENQ_* - * - * @p is ready to run. Insert directly into a DSQ by calling - * scx_bpf_dsq_insert() or enqueue on the BPF scheduler. If not directly - * inserted, the bpf scheduler owns @p and if it fails to dispatch @p, - * the task will stall. - * - * If @p was inserted into a DSQ from ops.select_cpu(), this callback is - * skipped. - */ - void (*enqueue)(struct task_struct *p, u64 enq_flags); - - /** - * @dequeue: Remove a task from the BPF scheduler - * @p: task being dequeued - * @deq_flags: %SCX_DEQ_* - * - * Remove @p from the BPF scheduler. This is usually called to isolate - * the task while updating its scheduling properties (e.g. priority). - * - * The ext core keeps track of whether the BPF side owns a given task or - * not and can gracefully ignore spurious dispatches from BPF side, - * which makes it safe to not implement this method. However, depending - * on the scheduling logic, this can lead to confusing behaviors - e.g. - * scheduling position not being updated across a priority change. - */ - void (*dequeue)(struct task_struct *p, u64 deq_flags); - - /** - * @dispatch: Dispatch tasks from the BPF scheduler and/or user DSQs - * @cpu: CPU to dispatch tasks for - * @prev: previous task being switched out - * - * Called when a CPU's local dsq is empty. The operation should dispatch - * one or more tasks from the BPF scheduler into the DSQs using - * scx_bpf_dsq_insert() and/or move from user DSQs into the local DSQ - * using scx_bpf_dsq_move_to_local(). - * - * The maximum number of times scx_bpf_dsq_insert() can be called - * without an intervening scx_bpf_dsq_move_to_local() is specified by - * ops.dispatch_max_batch. See the comments on top of the two functions - * for more details. - * - * When not %NULL, @prev is an SCX task with its slice depleted. If - * @prev is still runnable as indicated by set %SCX_TASK_QUEUED in - * @prev->scx.flags, it is not enqueued yet and will be enqueued after - * ops.dispatch() returns. To keep executing @prev, return without - * dispatching or moving any tasks. Also see %SCX_OPS_ENQ_LAST. - */ - void (*dispatch)(s32 cpu, struct task_struct *prev); - - /** - * @tick: Periodic tick - * @p: task running currently - * - * This operation is called every 1/HZ seconds on CPUs which are - * executing an SCX task. Setting @p->scx.slice to 0 will trigger an - * immediate dispatch cycle on the CPU. - */ - void (*tick)(struct task_struct *p); - - /** - * @runnable: A task is becoming runnable on its associated CPU - * @p: task becoming runnable - * @enq_flags: %SCX_ENQ_* - * - * This and the following three functions can be used to track a task's - * execution state transitions. A task becomes ->runnable() on a CPU, - * and then goes through one or more ->running() and ->stopping() pairs - * as it runs on the CPU, and eventually becomes ->quiescent() when it's - * done running on the CPU. - * - * @p is becoming runnable on the CPU because it's - * - * - waking up (%SCX_ENQ_WAKEUP) - * - being moved from another CPU - * - being restored after temporarily taken off the queue for an - * attribute change. - * - * This and ->enqueue() are related but not coupled. This operation - * notifies @p's state transition and may not be followed by ->enqueue() - * e.g. when @p is being dispatched to a remote CPU, or when @p is - * being enqueued on a CPU experiencing a hotplug event. Likewise, a - * task may be ->enqueue()'d without being preceded by this operation - * e.g. after exhausting its slice. - */ - void (*runnable)(struct task_struct *p, u64 enq_flags); - - /** - * @running: A task is starting to run on its associated CPU - * @p: task starting to run - * - * Note that this callback may be called from a CPU other than the - * one the task is going to run on. This can happen when a task - * property is changed (i.e., affinity), since scx_next_task_scx(), - * which triggers this callback, may run on a CPU different from - * the task's assigned CPU. - * - * Therefore, always use scx_bpf_task_cpu(@p) to determine the - * target CPU the task is going to use. - * - * See ->runnable() for explanation on the task state notifiers. - */ - void (*running)(struct task_struct *p); - - /** - * @stopping: A task is stopping execution - * @p: task stopping to run - * @runnable: is task @p still runnable? - * - * Note that this callback may be called from a CPU other than the - * one the task was running on. This can happen when a task - * property is changed (i.e., affinity), since dequeue_task_scx(), - * which triggers this callback, may run on a CPU different from - * the task's assigned CPU. - * - * Therefore, always use scx_bpf_task_cpu(@p) to retrieve the CPU - * the task was running on. - * - * See ->runnable() for explanation on the task state notifiers. If - * !@runnable, ->quiescent() will be invoked after this operation - * returns. - */ - void (*stopping)(struct task_struct *p, bool runnable); - - /** - * @quiescent: A task is becoming not runnable on its associated CPU - * @p: task becoming not runnable - * @deq_flags: %SCX_DEQ_* - * - * See ->runnable() for explanation on the task state notifiers. - * - * @p is becoming quiescent on the CPU because it's - * - * - sleeping (%SCX_DEQ_SLEEP) - * - being moved to another CPU - * - being temporarily taken off the queue for an attribute change - * (%SCX_DEQ_SAVE) - * - * This and ->dequeue() are related but not coupled. This operation - * notifies @p's state transition and may not be preceded by ->dequeue() - * e.g. when @p is being dispatched to a remote CPU. - */ - void (*quiescent)(struct task_struct *p, u64 deq_flags); - - /** - * @yield: Yield CPU - * @from: yielding task - * @to: optional yield target task - * - * If @to is NULL, @from is yielding the CPU to other runnable tasks. - * The BPF scheduler should ensure that other available tasks are - * dispatched before the yielding task. Return value is ignored in this - * case. - * - * If @to is not-NULL, @from wants to yield the CPU to @to. If the bpf - * scheduler can implement the request, return %true; otherwise, %false. - */ - bool (*yield)(struct task_struct *from, struct task_struct *to); - - /** - * @core_sched_before: Task ordering for core-sched - * @a: task A - * @b: task B - * - * Used by core-sched to determine the ordering between two tasks. See - * Documentation/admin-guide/hw-vuln/core-scheduling.rst for details on - * core-sched. - * - * Both @a and @b are runnable and may or may not currently be queued on - * the BPF scheduler. Should return %true if @a should run before @b. - * %false if there's no required ordering or @b should run before @a. - * - * If not specified, the default is ordering them according to when they - * became runnable. - */ - bool (*core_sched_before)(struct task_struct *a, struct task_struct *b); - - /** - * @set_weight: Set task weight - * @p: task to set weight for - * @weight: new weight [1..10000] - * - * Update @p's weight to @weight. - */ - void (*set_weight)(struct task_struct *p, u32 weight); - - /** - * @set_cpumask: Set CPU affinity - * @p: task to set CPU affinity for - * @cpumask: cpumask of cpus that @p can run on - * - * Update @p's CPU affinity to @cpumask. - */ - void (*set_cpumask)(struct task_struct *p, - const struct cpumask *cpumask); - - /** - * @update_idle: Update the idle state of a CPU - * @cpu: CPU to update the idle state for - * @idle: whether entering or exiting the idle state - * - * This operation is called when @rq's CPU goes or leaves the idle - * state. By default, implementing this operation disables the built-in - * idle CPU tracking and the following helpers become unavailable: - * - * - scx_bpf_select_cpu_dfl() - * - scx_bpf_select_cpu_and() - * - scx_bpf_test_and_clear_cpu_idle() - * - scx_bpf_pick_idle_cpu() - * - * The user also must implement ops.select_cpu() as the default - * implementation relies on scx_bpf_select_cpu_dfl(). - * - * Specify the %SCX_OPS_KEEP_BUILTIN_IDLE flag to keep the built-in idle - * tracking. - */ - void (*update_idle)(s32 cpu, bool idle); - - /** - * @cpu_acquire: A CPU is becoming available to the BPF scheduler - * @cpu: The CPU being acquired by the BPF scheduler. - * @args: Acquire arguments, see the struct definition. - * - * A CPU that was previously released from the BPF scheduler is now once - * again under its control. - */ - void (*cpu_acquire)(s32 cpu, struct scx_cpu_acquire_args *args); - - /** - * @cpu_release: A CPU is taken away from the BPF scheduler - * @cpu: The CPU being released by the BPF scheduler. - * @args: Release arguments, see the struct definition. - * - * The specified CPU is no longer under the control of the BPF - * scheduler. This could be because it was preempted by a higher - * priority sched_class, though there may be other reasons as well. The - * caller should consult @args->reason to determine the cause. - */ - void (*cpu_release)(s32 cpu, struct scx_cpu_release_args *args); - - /** - * @init_task: Initialize a task to run in a BPF scheduler - * @p: task to initialize for BPF scheduling - * @args: init arguments, see the struct definition - * - * Either we're loading a BPF scheduler or a new task is being forked. - * Initialize @p for BPF scheduling. This operation may block and can - * be used for allocations, and is called exactly once for a task. - * - * Return 0 for success, -errno for failure. An error return while - * loading will abort loading of the BPF scheduler. During a fork, it - * will abort that specific fork. - */ - s32 (*init_task)(struct task_struct *p, struct scx_init_task_args *args); - - /** - * @exit_task: Exit a previously-running task from the system - * @p: task to exit - * @args: exit arguments, see the struct definition - * - * @p is exiting or the BPF scheduler is being unloaded. Perform any - * necessary cleanup for @p. - */ - void (*exit_task)(struct task_struct *p, struct scx_exit_task_args *args); - - /** - * @enable: Enable BPF scheduling for a task - * @p: task to enable BPF scheduling for - * - * Enable @p for BPF scheduling. enable() is called on @p any time it - * enters SCX, and is always paired with a matching disable(). - */ - void (*enable)(struct task_struct *p); - - /** - * @disable: Disable BPF scheduling for a task - * @p: task to disable BPF scheduling for - * - * @p is exiting, leaving SCX or the BPF scheduler is being unloaded. - * Disable BPF scheduling for @p. A disable() call is always matched - * with a prior enable() call. - */ - void (*disable)(struct task_struct *p); - - /** - * @dump: Dump BPF scheduler state on error - * @ctx: debug dump context - * - * Use scx_bpf_dump() to generate BPF scheduler specific debug dump. - */ - void (*dump)(struct scx_dump_ctx *ctx); - - /** - * @dump_cpu: Dump BPF scheduler state for a CPU on error - * @ctx: debug dump context - * @cpu: CPU to generate debug dump for - * @idle: @cpu is currently idle without any runnable tasks - * - * Use scx_bpf_dump() to generate BPF scheduler specific debug dump for - * @cpu. If @idle is %true and this operation doesn't produce any - * output, @cpu is skipped for dump. - */ - void (*dump_cpu)(struct scx_dump_ctx *ctx, s32 cpu, bool idle); - - /** - * @dump_task: Dump BPF scheduler state for a runnable task on error - * @ctx: debug dump context - * @p: runnable task to generate debug dump for - * - * Use scx_bpf_dump() to generate BPF scheduler specific debug dump for - * @p. - */ - void (*dump_task)(struct scx_dump_ctx *ctx, struct task_struct *p); - -#ifdef CONFIG_EXT_GROUP_SCHED - /** - * @cgroup_init: Initialize a cgroup - * @cgrp: cgroup being initialized - * @args: init arguments, see the struct definition - * - * Either the BPF scheduler is being loaded or @cgrp created, initialize - * @cgrp for sched_ext. This operation may block. - * - * Return 0 for success, -errno for failure. An error return while - * loading will abort loading of the BPF scheduler. During cgroup - * creation, it will abort the specific cgroup creation. - */ - s32 (*cgroup_init)(struct cgroup *cgrp, - struct scx_cgroup_init_args *args); - - /** - * @cgroup_exit: Exit a cgroup - * @cgrp: cgroup being exited - * - * Either the BPF scheduler is being unloaded or @cgrp destroyed, exit - * @cgrp for sched_ext. This operation my block. - */ - void (*cgroup_exit)(struct cgroup *cgrp); - - /** - * @cgroup_prep_move: Prepare a task to be moved to a different cgroup - * @p: task being moved - * @from: cgroup @p is being moved from - * @to: cgroup @p is being moved to - * - * Prepare @p for move from cgroup @from to @to. This operation may - * block and can be used for allocations. - * - * Return 0 for success, -errno for failure. An error return aborts the - * migration. - */ - s32 (*cgroup_prep_move)(struct task_struct *p, - struct cgroup *from, struct cgroup *to); - - /** - * @cgroup_move: Commit cgroup move - * @p: task being moved - * @from: cgroup @p is being moved from - * @to: cgroup @p is being moved to - * - * Commit the move. @p is dequeued during this operation. - */ - void (*cgroup_move)(struct task_struct *p, - struct cgroup *from, struct cgroup *to); - - /** - * @cgroup_cancel_move: Cancel cgroup move - * @p: task whose cgroup move is being canceled - * @from: cgroup @p was being moved from - * @to: cgroup @p was being moved to - * - * @p was cgroup_prep_move()'d but failed before reaching cgroup_move(). - * Undo the preparation. - */ - void (*cgroup_cancel_move)(struct task_struct *p, - struct cgroup *from, struct cgroup *to); - - /** - * @cgroup_set_weight: A cgroup's weight is being changed - * @cgrp: cgroup whose weight is being updated - * @weight: new weight [1..10000] - * - * Update @cgrp's weight to @weight. - */ - void (*cgroup_set_weight)(struct cgroup *cgrp, u32 weight); - - /** - * @cgroup_set_bandwidth: A cgroup's bandwidth is being changed - * @cgrp: cgroup whose bandwidth is being updated - * @period_us: bandwidth control period - * @quota_us: bandwidth control quota - * @burst_us: bandwidth control burst - * - * Update @cgrp's bandwidth control parameters. This is from the cpu.max - * cgroup interface. - * - * @quota_us / @period_us determines the CPU bandwidth @cgrp is entitled - * to. For example, if @period_us is 1_000_000 and @quota_us is - * 2_500_000. @cgrp is entitled to 2.5 CPUs. @burst_us can be - * interpreted in the same fashion and specifies how much @cgrp can - * burst temporarily. The specific control mechanism and thus the - * interpretation of @period_us and burstiness is upto to the BPF - * scheduler. - */ - void (*cgroup_set_bandwidth)(struct cgroup *cgrp, - u64 period_us, u64 quota_us, u64 burst_us); - -#endif /* CONFIG_EXT_GROUP_SCHED */ - - /* - * All online ops must come before ops.cpu_online(). - */ - - /** - * @cpu_online: A CPU became online - * @cpu: CPU which just came up - * - * @cpu just came online. @cpu will not call ops.enqueue() or - * ops.dispatch(), nor run tasks associated with other CPUs beforehand. - */ - void (*cpu_online)(s32 cpu); - - /** - * @cpu_offline: A CPU is going offline - * @cpu: CPU which is going offline - * - * @cpu is going offline. @cpu will not call ops.enqueue() or - * ops.dispatch(), nor run tasks associated with other CPUs afterwards. - */ - void (*cpu_offline)(s32 cpu); - - /* - * All CPU hotplug ops must come before ops.init(). - */ - - /** - * @init: Initialize the BPF scheduler - */ - s32 (*init)(void); - - /** - * @exit: Clean up after the BPF scheduler - * @info: Exit info - * - * ops.exit() is also called on ops.init() failure, which is a bit - * unusual. This is to allow rich reporting through @info on how - * ops.init() failed. - */ - void (*exit)(struct scx_exit_info *info); - - /** - * @dispatch_max_batch: Max nr of tasks that dispatch() can dispatch - */ - u32 dispatch_max_batch; - - /** - * @flags: %SCX_OPS_* flags - */ - u64 flags; - - /** - * @timeout_ms: The maximum amount of time, in milliseconds, that a - * runnable task should be able to wait before being scheduled. The - * maximum timeout may not exceed the default timeout of 30 seconds. - * - * Defaults to the maximum allowed timeout value of 30 seconds. - */ - u32 timeout_ms; - - /** - * @exit_dump_len: scx_exit_info.dump buffer length. If 0, the default - * value of 32768 is used. - */ - u32 exit_dump_len; - - /** - * @hotplug_seq: A sequence number that may be set by the scheduler to - * detect when a hotplug event has occurred during the loading process. - * If 0, no detection occurs. Otherwise, the scheduler will fail to - * load if the sequence number does not match @scx_hotplug_seq on the - * enable path. - */ - u64 hotplug_seq; - - /** - * @name: BPF scheduler's name - * - * Must be a non-zero valid BPF object name including only isalnum(), - * '_' and '.' chars. Shows up in kernel.sched_ext_ops sysctl while the - * BPF scheduler is enabled. - */ - char name[SCX_OPS_NAME_LEN]; - - /* internal use only, must be NULL */ - void *priv; -}; - -enum scx_opi { - SCX_OPI_BEGIN = 0, - SCX_OPI_NORMAL_BEGIN = 0, - SCX_OPI_NORMAL_END = SCX_OP_IDX(cpu_online), - SCX_OPI_CPU_HOTPLUG_BEGIN = SCX_OP_IDX(cpu_online), - SCX_OPI_CPU_HOTPLUG_END = SCX_OP_IDX(init), - SCX_OPI_END = SCX_OP_IDX(init), -}; - -/* - * Collection of event counters. Event types are placed in descending order. - */ -struct scx_event_stats { - /* - * If ops.select_cpu() returns a CPU which can't be used by the task, - * the core scheduler code silently picks a fallback CPU. - */ - s64 SCX_EV_SELECT_CPU_FALLBACK; - - /* - * When dispatching to a local DSQ, the CPU may have gone offline in - * the meantime. In this case, the task is bounced to the global DSQ. - */ - s64 SCX_EV_DISPATCH_LOCAL_DSQ_OFFLINE; - - /* - * If SCX_OPS_ENQ_LAST is not set, the number of times that a task - * continued to run because there were no other tasks on the CPU. - */ - s64 SCX_EV_DISPATCH_KEEP_LAST; - - /* - * If SCX_OPS_ENQ_EXITING is not set, the number of times that a task - * is dispatched to a local DSQ when exiting. - */ - s64 SCX_EV_ENQ_SKIP_EXITING; - - /* - * If SCX_OPS_ENQ_MIGRATION_DISABLED is not set, the number of times a - * migration disabled task skips ops.enqueue() and is dispatched to its - * local DSQ. - */ - s64 SCX_EV_ENQ_SKIP_MIGRATION_DISABLED; - - /* - * Total number of times a task's time slice was refilled with the - * default value (SCX_SLICE_DFL). - */ - s64 SCX_EV_REFILL_SLICE_DFL; - - /* - * The total duration of bypass modes in nanoseconds. - */ - s64 SCX_EV_BYPASS_DURATION; - - /* - * The number of tasks dispatched in the bypassing mode. - */ - s64 SCX_EV_BYPASS_DISPATCH; - - /* - * The number of times the bypassing mode has been activated. - */ - s64 SCX_EV_BYPASS_ACTIVATE; -}; - -struct scx_sched { - struct sched_ext_ops ops; - DECLARE_BITMAP(has_op, SCX_OPI_END); - - /* - * Dispatch queues. - * - * The global DSQ (%SCX_DSQ_GLOBAL) is split per-node for scalability. - * This is to avoid live-locking in bypass mode where all tasks are - * dispatched to %SCX_DSQ_GLOBAL and all CPUs consume from it. If - * per-node split isn't sufficient, it can be further split. - */ - struct rhashtable dsq_hash; - struct scx_dispatch_q **global_dsqs; - - /* - * The event counters are in a per-CPU variable to minimize the - * accounting overhead. A system-wide view on the event counter is - * constructed when requested by scx_bpf_events(). - */ - struct scx_event_stats __percpu *event_stats_cpu; - - bool warned_zero_slice; - - atomic_t exit_kind; - struct scx_exit_info *exit_info; - - struct kobject kobj; - - struct kthread_worker *helper; - struct irq_work error_irq_work; - struct kthread_work disable_work; - struct rcu_work rcu_work; -}; - -enum scx_wake_flags { - /* expose select WF_* flags as enums */ - SCX_WAKE_FORK = WF_FORK, - SCX_WAKE_TTWU = WF_TTWU, - SCX_WAKE_SYNC = WF_SYNC, -}; - -enum scx_enq_flags { - /* expose select ENQUEUE_* flags as enums */ - SCX_ENQ_WAKEUP = ENQUEUE_WAKEUP, - SCX_ENQ_HEAD = ENQUEUE_HEAD, - SCX_ENQ_CPU_SELECTED = ENQUEUE_RQ_SELECTED, - - /* high 32bits are SCX specific */ - - /* - * Set the following to trigger preemption when calling - * scx_bpf_dsq_insert() with a local dsq as the target. The slice of the - * current task is cleared to zero and the CPU is kicked into the - * scheduling path. Implies %SCX_ENQ_HEAD. - */ - SCX_ENQ_PREEMPT = 1LLU << 32, - - /* - * The task being enqueued was previously enqueued on the current CPU's - * %SCX_DSQ_LOCAL, but was removed from it in a call to the - * scx_bpf_reenqueue_local() kfunc. If scx_bpf_reenqueue_local() was - * invoked in a ->cpu_release() callback, and the task is again - * dispatched back to %SCX_LOCAL_DSQ by this current ->enqueue(), the - * task will not be scheduled on the CPU until at least the next invocation - * of the ->cpu_acquire() callback. - */ - SCX_ENQ_REENQ = 1LLU << 40, - - /* - * The task being enqueued is the only task available for the cpu. By - * default, ext core keeps executing such tasks but when - * %SCX_OPS_ENQ_LAST is specified, they're ops.enqueue()'d with the - * %SCX_ENQ_LAST flag set. - * - * The BPF scheduler is responsible for triggering a follow-up - * scheduling event. Otherwise, Execution may stall. - */ - SCX_ENQ_LAST = 1LLU << 41, - - /* high 8 bits are internal */ - __SCX_ENQ_INTERNAL_MASK = 0xffLLU << 56, - - SCX_ENQ_CLEAR_OPSS = 1LLU << 56, - SCX_ENQ_DSQ_PRIQ = 1LLU << 57, -}; - -enum scx_deq_flags { - /* expose select DEQUEUE_* flags as enums */ - SCX_DEQ_SLEEP = DEQUEUE_SLEEP, - - /* high 32bits are SCX specific */ - - /* - * The generic core-sched layer decided to execute the task even though - * it hasn't been dispatched yet. Dequeue from the BPF side. - */ - SCX_DEQ_CORE_SCHED_EXEC = 1LLU << 32, -}; - -enum scx_pick_idle_cpu_flags { - SCX_PICK_IDLE_CORE = 1LLU << 0, /* pick a CPU whose SMT siblings are also idle */ - SCX_PICK_IDLE_IN_NODE = 1LLU << 1, /* pick a CPU in the same target NUMA node */ -}; - -enum scx_kick_flags { - /* - * Kick the target CPU if idle. Guarantees that the target CPU goes - * through at least one full scheduling cycle before going idle. If the - * target CPU can be determined to be currently not idle and going to go - * through a scheduling cycle before going idle, noop. - */ - SCX_KICK_IDLE = 1LLU << 0, - - /* - * Preempt the current task and execute the dispatch path. If the - * current task of the target CPU is an SCX task, its ->scx.slice is - * cleared to zero before the scheduling path is invoked so that the - * task expires and the dispatch path is invoked. - */ - SCX_KICK_PREEMPT = 1LLU << 1, - - /* - * Wait for the CPU to be rescheduled. The scx_bpf_kick_cpu() call will - * return after the target CPU finishes picking the next task. - */ - SCX_KICK_WAIT = 1LLU << 2, -}; - -enum scx_tg_flags { - SCX_TG_ONLINE = 1U << 0, - SCX_TG_INITED = 1U << 1, -}; - -enum scx_enable_state { - SCX_ENABLING, - SCX_ENABLED, - SCX_DISABLING, - SCX_DISABLED, -}; - -static const char *scx_enable_state_str[] = { - [SCX_ENABLING] = "enabling", - [SCX_ENABLED] = "enabled", - [SCX_DISABLING] = "disabling", - [SCX_DISABLED] = "disabled", -}; - -/* - * sched_ext_entity->ops_state - * - * Used to track the task ownership between the SCX core and the BPF scheduler. - * State transitions look as follows: - * - * NONE -> QUEUEING -> QUEUED -> DISPATCHING - * ^ | | - * | v v - * -------------------------------/ - * - * QUEUEING and DISPATCHING states can be waited upon. See wait_ops_state() call - * sites for explanations on the conditions being waited upon and why they are - * safe. Transitions out of them into NONE or QUEUED must store_release and the - * waiters should load_acquire. - * - * Tracking scx_ops_state enables sched_ext core to reliably determine whether - * any given task can be dispatched by the BPF scheduler at all times and thus - * relaxes the requirements on the BPF scheduler. This allows the BPF scheduler - * to try to dispatch any task anytime regardless of its state as the SCX core - * can safely reject invalid dispatches. - */ -enum scx_ops_state { - SCX_OPSS_NONE, /* owned by the SCX core */ - SCX_OPSS_QUEUEING, /* in transit to the BPF scheduler */ - SCX_OPSS_QUEUED, /* owned by the BPF scheduler */ - SCX_OPSS_DISPATCHING, /* in transit back to the SCX core */ - - /* - * QSEQ brands each QUEUED instance so that, when dispatch races - * dequeue/requeue, the dispatcher can tell whether it still has a claim - * on the task being dispatched. - * - * As some 32bit archs can't do 64bit store_release/load_acquire, - * p->scx.ops_state is atomic_long_t which leaves 30 bits for QSEQ on - * 32bit machines. The dispatch race window QSEQ protects is very narrow - * and runs with IRQ disabled. 30 bits should be sufficient. - */ - SCX_OPSS_QSEQ_SHIFT = 2, -}; - -/* Use macros to ensure that the type is unsigned long for the masks */ -#define SCX_OPSS_STATE_MASK ((1LU << SCX_OPSS_QSEQ_SHIFT) - 1) -#define SCX_OPSS_QSEQ_MASK (~SCX_OPSS_STATE_MASK) - /* * NOTE: sched_ext is in the process of growing multiple scheduler support and * scx_root usage is in a transitional state. Naked dereferences are safe if the diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index 292bb41a242ec..33858607bc97f 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -8,29 +8,6 @@ */ #ifdef CONFIG_SCHED_CLASS_EXT

-static inline bool scx_kf_allowed_if_unlocked(void) -{ - return !current->scx.kf_mask; -} - -static inline bool scx_rq_bypassing(struct rq *rq) -{ - return unlikely(rq->scx.flags & SCX_RQ_BYPASSING); -} - -DECLARE_STATIC_KEY_FALSE(scx_ops_allow_queued_wakeup); - -DECLARE_PER_CPU(struct rq *, scx_locked_rq_state); - -/* - * Return the rq currently locked from an scx callback, or NULL if no rq is - * locked. - */ -static inline struct rq *scx_locked_rq(void) -{ - return __this_cpu_read(scx_locked_rq_state); -} - void scx_tick(struct rq *rq); void init_scx_entity(struct sched_ext_entity *scx); void scx_pre_fork(struct task_struct *p); diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h new file mode 100644 index 0000000000000..76690ede8700f --- /dev/null +++ b/kernel/sched/ext_internal.h @@ -0,0 +1,1061 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst + * + * Copyright (c) 2025 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2025 Tejun Heo tj@kernel.org + */ +#define SCX_OP_IDX(op) (offsetof(struct sched_ext_ops, op) / sizeof(void (*)(void))) + +enum scx_consts { + SCX_DSP_DFL_MAX_BATCH = 32, + SCX_DSP_MAX_LOOPS = 32, + SCX_WATCHDOG_MAX_TIMEOUT = 30 * HZ, + + SCX_EXIT_BT_LEN = 64, + SCX_EXIT_MSG_LEN = 1024, + SCX_EXIT_DUMP_DFL_LEN = 32768, + + SCX_CPUPERF_ONE = SCHED_CAPACITY_SCALE, + + /* + * Iterating all tasks may take a while. Periodically drop + * scx_tasks_lock to avoid causing e.g. CSD and RCU stalls. + */ + SCX_TASK_ITER_BATCH = 32, +}; + +enum scx_exit_kind { + SCX_EXIT_NONE, + SCX_EXIT_DONE, + + SCX_EXIT_UNREG = 64, /* user-space initiated unregistration */ + SCX_EXIT_UNREG_BPF, /* BPF-initiated unregistration */ + SCX_EXIT_UNREG_KERN, /* kernel-initiated unregistration */ + SCX_EXIT_SYSRQ, /* requested by 'S' sysrq */ + + SCX_EXIT_ERROR = 1024, /* runtime error, error msg contains details */ + SCX_EXIT_ERROR_BPF, /* ERROR but triggered through scx_bpf_error() */ + SCX_EXIT_ERROR_STALL, /* watchdog detected stalled runnable tasks */ +}; + +/* + * An exit code can be specified when exiting with scx_bpf_exit() or scx_exit(), + * corresponding to exit_kind UNREG_BPF and UNREG_KERN respectively. The codes + * are 64bit of the format: + * + * Bits: [63 .. 48 47 .. 32 31 .. 0] + * [ SYS ACT ] [ SYS RSN ] [ USR ] + * + * SYS ACT: System-defined exit actions + * SYS RSN: System-defined exit reasons + * USR : User-defined exit codes and reasons + * + * Using the above, users may communicate intention and context by ORing system + * actions and/or system reasons with a user-defined exit code. + */ +enum scx_exit_code { + /* Reasons */ + SCX_ECODE_RSN_HOTPLUG = 1LLU << 32, + + /* Actions */ + SCX_ECODE_ACT_RESTART = 1LLU << 48, +}; + +/* + * scx_exit_info is passed to ops.exit() to describe why the BPF scheduler is + * being disabled. + */ +struct scx_exit_info { + /* %SCX_EXIT_* - broad category of the exit reason */ + enum scx_exit_kind kind; + + /* exit code if gracefully exiting */ + s64 exit_code; + + /* textual representation of the above */ + const char *reason; + + /* backtrace if exiting due to an error */ + unsigned long *bt; + u32 bt_len; + + /* informational message */ + char *msg; + + /* debug dump */ + char *dump; +}; + +/* sched_ext_ops.flags */ +enum scx_ops_flags { + /* + * Keep built-in idle tracking even if ops.update_idle() is implemented. + */ + SCX_OPS_KEEP_BUILTIN_IDLE = 1LLU << 0, + + /* + * By default, if there are no other task to run on the CPU, ext core + * keeps running the current task even after its slice expires. If this + * flag is specified, such tasks are passed to ops.enqueue() with + * %SCX_ENQ_LAST. See the comment above %SCX_ENQ_LAST for more info. + */ + SCX_OPS_ENQ_LAST = 1LLU << 1, + + /* + * An exiting task may schedule after PF_EXITING is set. In such cases, + * bpf_task_from_pid() may not be able to find the task and if the BPF + * scheduler depends on pid lookup for dispatching, the task will be + * lost leading to various issues including RCU grace period stalls. + * + * To mask this problem, by default, unhashed tasks are automatically + * dispatched to the local DSQ on enqueue. If the BPF scheduler doesn't + * depend on pid lookups and wants to handle these tasks directly, the + * following flag can be used. + */ + SCX_OPS_ENQ_EXITING = 1LLU << 2, + + /* + * If set, only tasks with policy set to SCHED_EXT are attached to + * sched_ext. If clear, SCHED_NORMAL tasks are also included. + */ + SCX_OPS_SWITCH_PARTIAL = 1LLU << 3, + + /* + * A migration disabled task can only execute on its current CPU. By + * default, such tasks are automatically put on the CPU's local DSQ with + * the default slice on enqueue. If this ops flag is set, they also go + * through ops.enqueue(). + * + * A migration disabled task never invokes ops.select_cpu() as it can + * only select the current CPU. Also, p->cpus_ptr will only contain its + * current CPU while p->nr_cpus_allowed keeps tracking p->user_cpus_ptr + * and thus may disagree with cpumask_weight(p->cpus_ptr). + */ + SCX_OPS_ENQ_MIGRATION_DISABLED = 1LLU << 4, + + /* + * Queued wakeup (ttwu_queue) is a wakeup optimization that invokes + * ops.enqueue() on the ops.select_cpu() selected or the wakee's + * previous CPU via IPI (inter-processor interrupt) to reduce cacheline + * transfers. When this optimization is enabled, ops.select_cpu() is + * skipped in some cases (when racing against the wakee switching out). + * As the BPF scheduler may depend on ops.select_cpu() being invoked + * during wakeups, queued wakeup is disabled by default. + * + * If this ops flag is set, queued wakeup optimization is enabled and + * the BPF scheduler must be able to handle ops.enqueue() invoked on the + * wakee's CPU without preceding ops.select_cpu() even for tasks which + * may be executed on multiple CPUs. + */ + SCX_OPS_ALLOW_QUEUED_WAKEUP = 1LLU << 5, + + /* + * If set, enable per-node idle cpumasks. If clear, use a single global + * flat idle cpumask. + */ + SCX_OPS_BUILTIN_IDLE_PER_NODE = 1LLU << 6, + + /* + * CPU cgroup support flags + */ + SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* DEPRECATED, will be removed on 6.18 */ + + SCX_OPS_ALL_FLAGS = SCX_OPS_KEEP_BUILTIN_IDLE | + SCX_OPS_ENQ_LAST | + SCX_OPS_ENQ_EXITING | + SCX_OPS_ENQ_MIGRATION_DISABLED | + SCX_OPS_ALLOW_QUEUED_WAKEUP | + SCX_OPS_SWITCH_PARTIAL | + SCX_OPS_BUILTIN_IDLE_PER_NODE | + SCX_OPS_HAS_CGROUP_WEIGHT, + + /* high 8 bits are internal, don't include in SCX_OPS_ALL_FLAGS */ + __SCX_OPS_INTERNAL_MASK = 0xffLLU << 56, + + SCX_OPS_HAS_CPU_PREEMPT = 1LLU << 56, +}; + +/* argument container for ops.init_task() */ +struct scx_init_task_args { + /* + * Set if ops.init_task() is being invoked on the fork path, as opposed + * to the scheduler transition path. + */ + bool fork; +#ifdef CONFIG_EXT_GROUP_SCHED + /* the cgroup the task is joining */ + struct cgroup *cgroup; +#endif +}; + +/* argument container for ops.exit_task() */ +struct scx_exit_task_args { + /* Whether the task exited before running on sched_ext. */ + bool cancelled; +}; + +/* argument container for ops->cgroup_init() */ +struct scx_cgroup_init_args { + /* the weight of the cgroup [1..10000] */ + u32 weight; + + /* bandwidth control parameters from cpu.max and cpu.max.burst */ + u64 bw_period_us; + u64 bw_quota_us; + u64 bw_burst_us; +}; + +enum scx_cpu_preempt_reason { + /* next task is being scheduled by &sched_class_rt */ + SCX_CPU_PREEMPT_RT, + /* next task is being scheduled by &sched_class_dl */ + SCX_CPU_PREEMPT_DL, + /* next task is being scheduled by &sched_class_stop */ + SCX_CPU_PREEMPT_STOP, + /* unknown reason for SCX being preempted */ + SCX_CPU_PREEMPT_UNKNOWN, +}; + +/* + * Argument container for ops->cpu_acquire(). Currently empty, but may be + * expanded in the future. + */ +struct scx_cpu_acquire_args {}; + +/* argument container for ops->cpu_release() */ +struct scx_cpu_release_args { + /* the reason the CPU was preempted */ + enum scx_cpu_preempt_reason reason; + + /* the task that's going to be scheduled on the CPU */ + struct task_struct *task; +}; + +/* + * Informational context provided to dump operations. + */ +struct scx_dump_ctx { + enum scx_exit_kind kind; + s64 exit_code; + const char *reason; + u64 at_ns; + u64 at_jiffies; +}; + +/** + * struct sched_ext_ops - Operation table for BPF scheduler implementation + * + * A BPF scheduler can implement an arbitrary scheduling policy by + * implementing and loading operations in this table. Note that a userland + * scheduling policy can also be implemented using the BPF scheduler + * as a shim layer. + */ +struct sched_ext_ops { + /** + * @select_cpu: Pick the target CPU for a task which is being woken up + * @p: task being woken up + * @prev_cpu: the cpu @p was on before sleeping + * @wake_flags: SCX_WAKE_* + * + * Decision made here isn't final. @p may be moved to any CPU while it + * is getting dispatched for execution later. However, as @p is not on + * the rq at this point, getting the eventual execution CPU right here + * saves a small bit of overhead down the line. + * + * If an idle CPU is returned, the CPU is kicked and will try to + * dispatch. While an explicit custom mechanism can be added, + * select_cpu() serves as the default way to wake up idle CPUs. + * + * @p may be inserted into a DSQ directly by calling + * scx_bpf_dsq_insert(). If so, the ops.enqueue() will be skipped. + * Directly inserting into %SCX_DSQ_LOCAL will put @p in the local DSQ + * of the CPU returned by this operation. + * + * Note that select_cpu() is never called for tasks that can only run + * on a single CPU or tasks with migration disabled, as they don't have + * the option to select a different CPU. See select_task_rq() for + * details. + */ + s32 (*select_cpu)(struct task_struct *p, s32 prev_cpu, u64 wake_flags); + + /** + * @enqueue: Enqueue a task on the BPF scheduler + * @p: task being enqueued + * @enq_flags: %SCX_ENQ_* + * + * @p is ready to run. Insert directly into a DSQ by calling + * scx_bpf_dsq_insert() or enqueue on the BPF scheduler. If not directly + * inserted, the bpf scheduler owns @p and if it fails to dispatch @p, + * the task will stall. + * + * If @p was inserted into a DSQ from ops.select_cpu(), this callback is + * skipped. + */ + void (*enqueue)(struct task_struct *p, u64 enq_flags); + + /** + * @dequeue: Remove a task from the BPF scheduler + * @p: task being dequeued + * @deq_flags: %SCX_DEQ_* + * + * Remove @p from the BPF scheduler. This is usually called to isolate + * the task while updating its scheduling properties (e.g. priority). + * + * The ext core keeps track of whether the BPF side owns a given task or + * not and can gracefully ignore spurious dispatches from BPF side, + * which makes it safe to not implement this method. However, depending + * on the scheduling logic, this can lead to confusing behaviors - e.g. + * scheduling position not being updated across a priority change. + */ + void (*dequeue)(struct task_struct *p, u64 deq_flags); + + /** + * @dispatch: Dispatch tasks from the BPF scheduler and/or user DSQs + * @cpu: CPU to dispatch tasks for + * @prev: previous task being switched out + * + * Called when a CPU's local dsq is empty. The operation should dispatch + * one or more tasks from the BPF scheduler into the DSQs using + * scx_bpf_dsq_insert() and/or move from user DSQs into the local DSQ + * using scx_bpf_dsq_move_to_local(). + * + * The maximum number of times scx_bpf_dsq_insert() can be called + * without an intervening scx_bpf_dsq_move_to_local() is specified by + * ops.dispatch_max_batch. See the comments on top of the two functions + * for more details. + * + * When not %NULL, @prev is an SCX task with its slice depleted. If + * @prev is still runnable as indicated by set %SCX_TASK_QUEUED in + * @prev->scx.flags, it is not enqueued yet and will be enqueued after + * ops.dispatch() returns. To keep executing @prev, return without + * dispatching or moving any tasks. Also see %SCX_OPS_ENQ_LAST. + */ + void (*dispatch)(s32 cpu, struct task_struct *prev); + + /** + * @tick: Periodic tick + * @p: task running currently + * + * This operation is called every 1/HZ seconds on CPUs which are + * executing an SCX task. Setting @p->scx.slice to 0 will trigger an + * immediate dispatch cycle on the CPU. + */ + void (*tick)(struct task_struct *p); + + /** + * @runnable: A task is becoming runnable on its associated CPU + * @p: task becoming runnable + * @enq_flags: %SCX_ENQ_* + * + * This and the following three functions can be used to track a task's + * execution state transitions. A task becomes ->runnable() on a CPU, + * and then goes through one or more ->running() and ->stopping() pairs + * as it runs on the CPU, and eventually becomes ->quiescent() when it's + * done running on the CPU. + * + * @p is becoming runnable on the CPU because it's + * + * - waking up (%SCX_ENQ_WAKEUP) + * - being moved from another CPU + * - being restored after temporarily taken off the queue for an + * attribute change. + * + * This and ->enqueue() are related but not coupled. This operation + * notifies @p's state transition and may not be followed by ->enqueue() + * e.g. when @p is being dispatched to a remote CPU, or when @p is + * being enqueued on a CPU experiencing a hotplug event. Likewise, a + * task may be ->enqueue()'d without being preceded by this operation + * e.g. after exhausting its slice. + */ + void (*runnable)(struct task_struct *p, u64 enq_flags); + + /** + * @running: A task is starting to run on its associated CPU + * @p: task starting to run + * + * Note that this callback may be called from a CPU other than the + * one the task is going to run on. This can happen when a task + * property is changed (i.e., affinity), since scx_next_task_scx(), + * which triggers this callback, may run on a CPU different from + * the task's assigned CPU. + * + * Therefore, always use scx_bpf_task_cpu(@p) to determine the + * target CPU the task is going to use. + * + * See ->runnable() for explanation on the task state notifiers. + */ + void (*running)(struct task_struct *p); + + /** + * @stopping: A task is stopping execution + * @p: task stopping to run + * @runnable: is task @p still runnable? + * + * Note that this callback may be called from a CPU other than the + * one the task was running on. This can happen when a task + * property is changed (i.e., affinity), since dequeue_task_scx(), + * which triggers this callback, may run on a CPU different from + * the task's assigned CPU. + * + * Therefore, always use scx_bpf_task_cpu(@p) to retrieve the CPU + * the task was running on. + * + * See ->runnable() for explanation on the task state notifiers. If + * !@runnable, ->quiescent() will be invoked after this operation + * returns. + */ + void (*stopping)(struct task_struct *p, bool runnable); + + /** + * @quiescent: A task is becoming not runnable on its associated CPU + * @p: task becoming not runnable + * @deq_flags: %SCX_DEQ_* + * + * See ->runnable() for explanation on the task state notifiers. + * + * @p is becoming quiescent on the CPU because it's + * + * - sleeping (%SCX_DEQ_SLEEP) + * - being moved to another CPU + * - being temporarily taken off the queue for an attribute change + * (%SCX_DEQ_SAVE) + * + * This and ->dequeue() are related but not coupled. This operation + * notifies @p's state transition and may not be preceded by ->dequeue() + * e.g. when @p is being dispatched to a remote CPU. + */ + void (*quiescent)(struct task_struct *p, u64 deq_flags); + + /** + * @yield: Yield CPU + * @from: yielding task + * @to: optional yield target task + * + * If @to is NULL, @from is yielding the CPU to other runnable tasks. + * The BPF scheduler should ensure that other available tasks are + * dispatched before the yielding task. Return value is ignored in this + * case. + * + * If @to is not-NULL, @from wants to yield the CPU to @to. If the bpf + * scheduler can implement the request, return %true; otherwise, %false. + */ + bool (*yield)(struct task_struct *from, struct task_struct *to); + + /** + * @core_sched_before: Task ordering for core-sched + * @a: task A + * @b: task B + * + * Used by core-sched to determine the ordering between two tasks. See + * Documentation/admin-guide/hw-vuln/core-scheduling.rst for details on + * core-sched. + * + * Both @a and @b are runnable and may or may not currently be queued on + * the BPF scheduler. Should return %true if @a should run before @b. + * %false if there's no required ordering or @b should run before @a. + * + * If not specified, the default is ordering them according to when they + * became runnable. + */ + bool (*core_sched_before)(struct task_struct *a, struct task_struct *b); + + /** + * @set_weight: Set task weight + * @p: task to set weight for + * @weight: new weight [1..10000] + * + * Update @p's weight to @weight. + */ + void (*set_weight)(struct task_struct *p, u32 weight); + + /** + * @set_cpumask: Set CPU affinity + * @p: task to set CPU affinity for + * @cpumask: cpumask of cpus that @p can run on + * + * Update @p's CPU affinity to @cpumask. + */ + void (*set_cpumask)(struct task_struct *p, + const struct cpumask *cpumask); + + /** + * @update_idle: Update the idle state of a CPU + * @cpu: CPU to update the idle state for + * @idle: whether entering or exiting the idle state + * + * This operation is called when @rq's CPU goes or leaves the idle + * state. By default, implementing this operation disables the built-in + * idle CPU tracking and the following helpers become unavailable: + * + * - scx_bpf_select_cpu_dfl() + * - scx_bpf_select_cpu_and() + * - scx_bpf_test_and_clear_cpu_idle() + * - scx_bpf_pick_idle_cpu() + * + * The user also must implement ops.select_cpu() as the default + * implementation relies on scx_bpf_select_cpu_dfl(). + * + * Specify the %SCX_OPS_KEEP_BUILTIN_IDLE flag to keep the built-in idle + * tracking. + */ + void (*update_idle)(s32 cpu, bool idle); + + /** + * @cpu_acquire: A CPU is becoming available to the BPF scheduler + * @cpu: The CPU being acquired by the BPF scheduler. + * @args: Acquire arguments, see the struct definition. + * + * A CPU that was previously released from the BPF scheduler is now once + * again under its control. + */ + void (*cpu_acquire)(s32 cpu, struct scx_cpu_acquire_args *args); + + /** + * @cpu_release: A CPU is taken away from the BPF scheduler + * @cpu: The CPU being released by the BPF scheduler. + * @args: Release arguments, see the struct definition. + * + * The specified CPU is no longer under the control of the BPF + * scheduler. This could be because it was preempted by a higher + * priority sched_class, though there may be other reasons as well. The + * caller should consult @args->reason to determine the cause. + */ + void (*cpu_release)(s32 cpu, struct scx_cpu_release_args *args); + + /** + * @init_task: Initialize a task to run in a BPF scheduler + * @p: task to initialize for BPF scheduling + * @args: init arguments, see the struct definition + * + * Either we're loading a BPF scheduler or a new task is being forked. + * Initialize @p for BPF scheduling. This operation may block and can + * be used for allocations, and is called exactly once for a task. + * + * Return 0 for success, -errno for failure. An error return while + * loading will abort loading of the BPF scheduler. During a fork, it + * will abort that specific fork. + */ + s32 (*init_task)(struct task_struct *p, struct scx_init_task_args *args); + + /** + * @exit_task: Exit a previously-running task from the system + * @p: task to exit + * @args: exit arguments, see the struct definition + * + * @p is exiting or the BPF scheduler is being unloaded. Perform any + * necessary cleanup for @p. + */ + void (*exit_task)(struct task_struct *p, struct scx_exit_task_args *args); + + /** + * @enable: Enable BPF scheduling for a task + * @p: task to enable BPF scheduling for + * + * Enable @p for BPF scheduling. enable() is called on @p any time it + * enters SCX, and is always paired with a matching disable(). + */ + void (*enable)(struct task_struct *p); + + /** + * @disable: Disable BPF scheduling for a task + * @p: task to disable BPF scheduling for + * + * @p is exiting, leaving SCX or the BPF scheduler is being unloaded. + * Disable BPF scheduling for @p. A disable() call is always matched + * with a prior enable() call. + */ + void (*disable)(struct task_struct *p); + + /** + * @dump: Dump BPF scheduler state on error + * @ctx: debug dump context + * + * Use scx_bpf_dump() to generate BPF scheduler specific debug dump. + */ + void (*dump)(struct scx_dump_ctx *ctx); + + /** + * @dump_cpu: Dump BPF scheduler state for a CPU on error + * @ctx: debug dump context + * @cpu: CPU to generate debug dump for + * @idle: @cpu is currently idle without any runnable tasks + * + * Use scx_bpf_dump() to generate BPF scheduler specific debug dump for + * @cpu. If @idle is %true and this operation doesn't produce any + * output, @cpu is skipped for dump. + */ + void (*dump_cpu)(struct scx_dump_ctx *ctx, s32 cpu, bool idle); + + /** + * @dump_task: Dump BPF scheduler state for a runnable task on error + * @ctx: debug dump context + * @p: runnable task to generate debug dump for + * + * Use scx_bpf_dump() to generate BPF scheduler specific debug dump for + * @p. + */ + void (*dump_task)(struct scx_dump_ctx *ctx, struct task_struct *p); + +#ifdef CONFIG_EXT_GROUP_SCHED + /** + * @cgroup_init: Initialize a cgroup + * @cgrp: cgroup being initialized + * @args: init arguments, see the struct definition + * + * Either the BPF scheduler is being loaded or @cgrp created, initialize + * @cgrp for sched_ext. This operation may block. + * + * Return 0 for success, -errno for failure. An error return while + * loading will abort loading of the BPF scheduler. During cgroup + * creation, it will abort the specific cgroup creation. + */ + s32 (*cgroup_init)(struct cgroup *cgrp, + struct scx_cgroup_init_args *args); + + /** + * @cgroup_exit: Exit a cgroup + * @cgrp: cgroup being exited + * + * Either the BPF scheduler is being unloaded or @cgrp destroyed, exit + * @cgrp for sched_ext. This operation my block. + */ + void (*cgroup_exit)(struct cgroup *cgrp); + + /** + * @cgroup_prep_move: Prepare a task to be moved to a different cgroup + * @p: task being moved + * @from: cgroup @p is being moved from + * @to: cgroup @p is being moved to + * + * Prepare @p for move from cgroup @from to @to. This operation may + * block and can be used for allocations. + * + * Return 0 for success, -errno for failure. An error return aborts the + * migration. + */ + s32 (*cgroup_prep_move)(struct task_struct *p, + struct cgroup *from, struct cgroup *to); + + /** + * @cgroup_move: Commit cgroup move + * @p: task being moved + * @from: cgroup @p is being moved from + * @to: cgroup @p is being moved to + * + * Commit the move. @p is dequeued during this operation. + */ + void (*cgroup_move)(struct task_struct *p, + struct cgroup *from, struct cgroup *to); + + /** + * @cgroup_cancel_move: Cancel cgroup move + * @p: task whose cgroup move is being canceled + * @from: cgroup @p was being moved from + * @to: cgroup @p was being moved to + * + * @p was cgroup_prep_move()'d but failed before reaching cgroup_move(). + * Undo the preparation. + */ + void (*cgroup_cancel_move)(struct task_struct *p, + struct cgroup *from, struct cgroup *to); + + /** + * @cgroup_set_weight: A cgroup's weight is being changed + * @cgrp: cgroup whose weight is being updated + * @weight: new weight [1..10000] + * + * Update @cgrp's weight to @weight. + */ + void (*cgroup_set_weight)(struct cgroup *cgrp, u32 weight); + + /** + * @cgroup_set_bandwidth: A cgroup's bandwidth is being changed + * @cgrp: cgroup whose bandwidth is being updated + * @period_us: bandwidth control period + * @quota_us: bandwidth control quota + * @burst_us: bandwidth control burst + * + * Update @cgrp's bandwidth control parameters. This is from the cpu.max + * cgroup interface. + * + * @quota_us / @period_us determines the CPU bandwidth @cgrp is entitled + * to. For example, if @period_us is 1_000_000 and @quota_us is + * 2_500_000. @cgrp is entitled to 2.5 CPUs. @burst_us can be + * interpreted in the same fashion and specifies how much @cgrp can + * burst temporarily. The specific control mechanism and thus the + * interpretation of @period_us and burstiness is upto to the BPF + * scheduler. + */ + void (*cgroup_set_bandwidth)(struct cgroup *cgrp, + u64 period_us, u64 quota_us, u64 burst_us); + +#endif /* CONFIG_EXT_GROUP_SCHED */ + + /* + * All online ops must come before ops.cpu_online(). + */ + + /** + * @cpu_online: A CPU became online + * @cpu: CPU which just came up + * + * @cpu just came online. @cpu will not call ops.enqueue() or + * ops.dispatch(), nor run tasks associated with other CPUs beforehand. + */ + void (*cpu_online)(s32 cpu); + + /** + * @cpu_offline: A CPU is going offline + * @cpu: CPU which is going offline + * + * @cpu is going offline. @cpu will not call ops.enqueue() or + * ops.dispatch(), nor run tasks associated with other CPUs afterwards. + */ + void (*cpu_offline)(s32 cpu); + + /* + * All CPU hotplug ops must come before ops.init(). + */ + + /** + * @init: Initialize the BPF scheduler + */ + s32 (*init)(void); + + /** + * @exit: Clean up after the BPF scheduler + * @info: Exit info + * + * ops.exit() is also called on ops.init() failure, which is a bit + * unusual. This is to allow rich reporting through @info on how + * ops.init() failed. + */ + void (*exit)(struct scx_exit_info *info); + + /** + * @dispatch_max_batch: Max nr of tasks that dispatch() can dispatch + */ + u32 dispatch_max_batch; + + /** + * @flags: %SCX_OPS_* flags + */ + u64 flags; + + /** + * @timeout_ms: The maximum amount of time, in milliseconds, that a + * runnable task should be able to wait before being scheduled. The + * maximum timeout may not exceed the default timeout of 30 seconds. + * + * Defaults to the maximum allowed timeout value of 30 seconds. + */ + u32 timeout_ms; + + /** + * @exit_dump_len: scx_exit_info.dump buffer length. If 0, the default + * value of 32768 is used. + */ + u32 exit_dump_len; + + /** + * @hotplug_seq: A sequence number that may be set by the scheduler to + * detect when a hotplug event has occurred during the loading process. + * If 0, no detection occurs. Otherwise, the scheduler will fail to + * load if the sequence number does not match @scx_hotplug_seq on the + * enable path. + */ + u64 hotplug_seq; + + /** + * @name: BPF scheduler's name + * + * Must be a non-zero valid BPF object name including only isalnum(), + * '_' and '.' chars. Shows up in kernel.sched_ext_ops sysctl while the + * BPF scheduler is enabled. + */ + char name[SCX_OPS_NAME_LEN]; + + /* internal use only, must be NULL */ + void *priv; +}; + +enum scx_opi { + SCX_OPI_BEGIN = 0, + SCX_OPI_NORMAL_BEGIN = 0, + SCX_OPI_NORMAL_END = SCX_OP_IDX(cpu_online), + SCX_OPI_CPU_HOTPLUG_BEGIN = SCX_OP_IDX(cpu_online), + SCX_OPI_CPU_HOTPLUG_END = SCX_OP_IDX(init), + SCX_OPI_END = SCX_OP_IDX(init), +}; + +/* + * Collection of event counters. Event types are placed in descending order. + */ +struct scx_event_stats { + /* + * If ops.select_cpu() returns a CPU which can't be used by the task, + * the core scheduler code silently picks a fallback CPU. + */ + s64 SCX_EV_SELECT_CPU_FALLBACK; + + /* + * When dispatching to a local DSQ, the CPU may have gone offline in + * the meantime. In this case, the task is bounced to the global DSQ. + */ + s64 SCX_EV_DISPATCH_LOCAL_DSQ_OFFLINE; + + /* + * If SCX_OPS_ENQ_LAST is not set, the number of times that a task + * continued to run because there were no other tasks on the CPU. + */ + s64 SCX_EV_DISPATCH_KEEP_LAST; + + /* + * If SCX_OPS_ENQ_EXITING is not set, the number of times that a task + * is dispatched to a local DSQ when exiting. + */ + s64 SCX_EV_ENQ_SKIP_EXITING; + + /* + * If SCX_OPS_ENQ_MIGRATION_DISABLED is not set, the number of times a + * migration disabled task skips ops.enqueue() and is dispatched to its + * local DSQ. + */ + s64 SCX_EV_ENQ_SKIP_MIGRATION_DISABLED; + + /* + * Total number of times a task's time slice was refilled with the + * default value (SCX_SLICE_DFL). + */ + s64 SCX_EV_REFILL_SLICE_DFL; + + /* + * The total duration of bypass modes in nanoseconds. + */ + s64 SCX_EV_BYPASS_DURATION; + + /* + * The number of tasks dispatched in the bypassing mode. + */ + s64 SCX_EV_BYPASS_DISPATCH; + + /* + * The number of times the bypassing mode has been activated. + */ + s64 SCX_EV_BYPASS_ACTIVATE; +}; + +struct scx_sched { + struct sched_ext_ops ops; + DECLARE_BITMAP(has_op, SCX_OPI_END); + + /* + * Dispatch queues. + * + * The global DSQ (%SCX_DSQ_GLOBAL) is split per-node for scalability. + * This is to avoid live-locking in bypass mode where all tasks are + * dispatched to %SCX_DSQ_GLOBAL and all CPUs consume from it. If + * per-node split isn't sufficient, it can be further split. + */ + struct rhashtable dsq_hash; + struct scx_dispatch_q **global_dsqs; + + /* + * The event counters are in a per-CPU variable to minimize the + * accounting overhead. A system-wide view on the event counter is + * constructed when requested by scx_bpf_events(). + */ + struct scx_event_stats __percpu *event_stats_cpu; + + bool warned_zero_slice; + + atomic_t exit_kind; + struct scx_exit_info *exit_info; + + struct kobject kobj; + + struct kthread_worker *helper; + struct irq_work error_irq_work; + struct kthread_work disable_work; + struct rcu_work rcu_work; +}; + +enum scx_wake_flags { + /* expose select WF_* flags as enums */ + SCX_WAKE_FORK = WF_FORK, + SCX_WAKE_TTWU = WF_TTWU, + SCX_WAKE_SYNC = WF_SYNC, +}; + +enum scx_enq_flags { + /* expose select ENQUEUE_* flags as enums */ + SCX_ENQ_WAKEUP = ENQUEUE_WAKEUP, + SCX_ENQ_HEAD = ENQUEUE_HEAD, + SCX_ENQ_CPU_SELECTED = ENQUEUE_RQ_SELECTED, + + /* high 32bits are SCX specific */ + + /* + * Set the following to trigger preemption when calling + * scx_bpf_dsq_insert() with a local dsq as the target. The slice of the + * current task is cleared to zero and the CPU is kicked into the + * scheduling path. Implies %SCX_ENQ_HEAD. + */ + SCX_ENQ_PREEMPT = 1LLU << 32, + + /* + * The task being enqueued was previously enqueued on the current CPU's + * %SCX_DSQ_LOCAL, but was removed from it in a call to the + * scx_bpf_reenqueue_local() kfunc. If scx_bpf_reenqueue_local() was + * invoked in a ->cpu_release() callback, and the task is again + * dispatched back to %SCX_LOCAL_DSQ by this current ->enqueue(), the + * task will not be scheduled on the CPU until at least the next invocation + * of the ->cpu_acquire() callback. + */ + SCX_ENQ_REENQ = 1LLU << 40, + + /* + * The task being enqueued is the only task available for the cpu. By + * default, ext core keeps executing such tasks but when + * %SCX_OPS_ENQ_LAST is specified, they're ops.enqueue()'d with the + * %SCX_ENQ_LAST flag set. + * + * The BPF scheduler is responsible for triggering a follow-up + * scheduling event. Otherwise, Execution may stall. + */ + SCX_ENQ_LAST = 1LLU << 41, + + /* high 8 bits are internal */ + __SCX_ENQ_INTERNAL_MASK = 0xffLLU << 56, + + SCX_ENQ_CLEAR_OPSS = 1LLU << 56, + SCX_ENQ_DSQ_PRIQ = 1LLU << 57, +}; + +enum scx_deq_flags { + /* expose select DEQUEUE_* flags as enums */ + SCX_DEQ_SLEEP = DEQUEUE_SLEEP, + + /* high 32bits are SCX specific */ + + /* + * The generic core-sched layer decided to execute the task even though + * it hasn't been dispatched yet. Dequeue from the BPF side. + */ + SCX_DEQ_CORE_SCHED_EXEC = 1LLU << 32, +}; + +enum scx_pick_idle_cpu_flags { + SCX_PICK_IDLE_CORE = 1LLU << 0, /* pick a CPU whose SMT siblings are also idle */ + SCX_PICK_IDLE_IN_NODE = 1LLU << 1, /* pick a CPU in the same target NUMA node */ +}; + +enum scx_kick_flags { + /* + * Kick the target CPU if idle. Guarantees that the target CPU goes + * through at least one full scheduling cycle before going idle. If the + * target CPU can be determined to be currently not idle and going to go + * through a scheduling cycle before going idle, noop. + */ + SCX_KICK_IDLE = 1LLU << 0, + + /* + * Preempt the current task and execute the dispatch path. If the + * current task of the target CPU is an SCX task, its ->scx.slice is + * cleared to zero before the scheduling path is invoked so that the + * task expires and the dispatch path is invoked. + */ + SCX_KICK_PREEMPT = 1LLU << 1, + + /* + * Wait for the CPU to be rescheduled. The scx_bpf_kick_cpu() call will + * return after the target CPU finishes picking the next task. + */ + SCX_KICK_WAIT = 1LLU << 2, +}; + +enum scx_tg_flags { + SCX_TG_ONLINE = 1U << 0, + SCX_TG_INITED = 1U << 1, +}; + +enum scx_enable_state { + SCX_ENABLING, + SCX_ENABLED, + SCX_DISABLING, + SCX_DISABLED, +}; + +static const char *scx_enable_state_str[] = { + [SCX_ENABLING] = "enabling", + [SCX_ENABLED] = "enabled", + [SCX_DISABLING] = "disabling", + [SCX_DISABLED] = "disabled", +}; + +/* + * sched_ext_entity->ops_state + * + * Used to track the task ownership between the SCX core and the BPF scheduler. + * State transitions look as follows: + * + * NONE -> QUEUEING -> QUEUED -> DISPATCHING + * ^ | | + * | v v + * -------------------------------/ + * + * QUEUEING and DISPATCHING states can be waited upon. See wait_ops_state() call + * sites for explanations on the conditions being waited upon and why they are + * safe. Transitions out of them into NONE or QUEUED must store_release and the + * waiters should load_acquire. + * + * Tracking scx_ops_state enables sched_ext core to reliably determine whether + * any given task can be dispatched by the BPF scheduler at all times and thus + * relaxes the requirements on the BPF scheduler. This allows the BPF scheduler + * to try to dispatch any task anytime regardless of its state as the SCX core + * can safely reject invalid dispatches. + */ +enum scx_ops_state { + SCX_OPSS_NONE, /* owned by the SCX core */ + SCX_OPSS_QUEUEING, /* in transit to the BPF scheduler */ + SCX_OPSS_QUEUED, /* owned by the BPF scheduler */ + SCX_OPSS_DISPATCHING, /* in transit back to the SCX core */ + + /* + * QSEQ brands each QUEUED instance so that, when dispatch races + * dequeue/requeue, the dispatcher can tell whether it still has a claim + * on the task being dispatched. + * + * As some 32bit archs can't do 64bit store_release/load_acquire, + * p->scx.ops_state is atomic_long_t which leaves 30 bits for QSEQ on + * 32bit machines. The dispatch race window QSEQ protects is very narrow + * and runs with IRQ disabled. 30 bits should be sufficient. + */ + SCX_OPSS_QSEQ_SHIFT = 2, +}; + +/* Use macros to ensure that the type is unsigned long for the masks */ +#define SCX_OPSS_STATE_MASK ((1LU << SCX_OPSS_QSEQ_SHIFT) - 1) +#define SCX_OPSS_QSEQ_MASK (~SCX_OPSS_STATE_MASK) + +DECLARE_PER_CPU(struct rq *, scx_locked_rq_state); + +/* + * Return the rq currently locked from an scx callback, or NULL if no rq is + * locked. + */ +static inline struct rq *scx_locked_rq(void) +{ + return __this_cpu_read(scx_locked_rq_state); +} + +static inline bool scx_kf_allowed_if_unlocked(void) +{ + return !current->scx.kf_mask; +} + +static inline bool scx_rq_bypassing(struct rq *rq) +{ + return unlikely(rq->scx.flags & SCX_RQ_BYPASSING); +}

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tejun Heo tj@kernel.org

[ Upstream commit efeeaac9ae9763f9c953e69633c86bc3031e39b5 ]

By the time scx_sched_free_rcu_work() runs, the scx_sched is no longer reachable. However, a previously queued error_irq_work may still be pending or running. Ensure it completes before proceeding with teardown.

Fixes: bff3b5aec1b7 ("sched_ext: Move disable machinery into scx_sched") Acked-by: Andrea Righi arighi@nvidia.com Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/sched/ext.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 46029050b170f..f89894476e51f 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -3537,7 +3537,9 @@ static void scx_sched_free_rcu_work(struct work_struct *work) struct scx_dispatch_q *dsq; int node;

+ irq_work_sync(&sch->error_irq_work); kthread_stop(sch->helper->task); + free_percpu(sch->pcpu);

for_each_node_state(node, N_POSSIBLE)

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Kaplan david.kaplan@amd.com

[ Upstream commit 930f2361fe542a00de9ce6070b1b6edb976f1165 ]

On Intel CPUs, the default retbleed mitigation is IBRS/eIBRS but this requires that a similar spectre_v2 mitigation is applied. If the user selects a different spectre_v2 mitigation (like spectre_v2=retpoline) a warning is printed but sysfs will still report 'Mitigation: IBRS' or 'Mitigation: Enhanced IBRS'. This is incorrect because retbleed is not mitigated, and IBRS is not actually set.

Fix this by choosing RETBLEED_MITIGATION_NONE in this scenario so the kernel correctly reports the system as vulnerable to retbleed.

Signed-off-by: David Kaplan david.kaplan@amd.com Signed-off-by: Borislav Petkov (AMD) bp@alien8.de Link: https://lore.kernel.org/20250915134706.3201818-1-david.kaplan@amd.com Stable-dep-of: 204ced4108f5 ("x86/bugs: Qualify RETBLEED_INTEL_MSG") Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/cpu/bugs.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 36dcfc5105be9..bf79ff6a1f662 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1460,8 +1460,10 @@ static void __init retbleed_update_mitigation(void) retbleed_mitigation = RETBLEED_MITIGATION_EIBRS; break; default: - if (retbleed_mitigation != RETBLEED_MITIGATION_STUFF) + if (retbleed_mitigation != RETBLEED_MITIGATION_STUFF) { pr_err(RETBLEED_INTEL_MSG); + retbleed_mitigation = RETBLEED_MITIGATION_NONE; + } } }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Charles Keepax ckeepax@opensource.cirrus.com

[ Upstream commit 5d7e45dd670e42df4836afeaa9baf9d41ca4b434 ]

The locking was changed from a buslock to a plain lock, but the patch description states there was no functional change. Assuming this was accidental so reverting to using the buslock.

Fixes: 5cd05f3e2315 ("genirq/chip: Rework irq_set_handler() variants") Signed-off-by: Charles Keepax ckeepax@opensource.cirrus.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Link: https://patch.msgid.link/20251023154901.1333755-2-ckeepax@opensource.cirrus.... Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/irq/chip.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 3ffa0d80ddd19..d1917b28761a3 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1030,7 +1030,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, void __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, const char *name) { - scoped_irqdesc_get_and_lock(irq, 0) + scoped_irqdesc_get_and_buslock(irq, 0) __irq_do_set_handler(scoped_irqdesc, handle, is_chained, name); } EXPORT_SYMBOL_GPL(__irq_set_handler);

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Charles Keepax ckeepax@opensource.cirrus.com

[ Upstream commit ef3330b99c01bda53f2a189b58bed8f6b7397f28 ]

The locking was changed from a buslock to a plain lock, but the patch description states there was no functional change. Assuming this was accidental so reverting to using the buslock.

Fixes: bddd10c55407 ("genirq/manage: Rework enable_irq()") Signed-off-by: Charles Keepax ckeepax@opensource.cirrus.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Link: https://patch.msgid.link/20251023154901.1333755-4-ckeepax@opensource.cirrus.... Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/irq/manage.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 7d68fb5dc2428..400856abf6721 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -789,7 +789,7 @@ void __enable_irq(struct irq_desc *desc) */ void enable_irq(unsigned int irq) { - scoped_irqdesc_get_and_lock(irq, IRQ_GET_DESC_CHECK_GLOBAL) { + scoped_irqdesc_get_and_buslock(irq, IRQ_GET_DESC_CHECK_GLOBAL) { struct irq_desc *desc = scoped_irqdesc;

if (WARN(!desc->irq_data.chip, "enable_irq before setup/request_irq: irq %u\n", irq))

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kyle Manna kyle@kylemanna.com

[ Upstream commit 71b69f817e91b588030d7d47ddbdc4857a92eb4e ]

Host Device IDs (DID0) correspond to: * Intel Core i7-12700K * Intel Core i5-12600K

See documentation: * 12th Generation Intel® Core™ Processors Datasheet * Volume 1 of 2, Doc. No.: 655258, Rev.: 011 * https://edc.intel.com/output/DownloadPdfDocument?id=8297 (PDF)

Signed-off-by: Kyle Manna kyle@kylemanna.com Signed-off-by: Tony Luck tony.luck@intel.com Reviewed-by: Qiuxu Zhuo qiuxu.zhuo@intel.com Link: https://lore.kernel.org/r/20250819161739.3241152-1-kyle@kylemanna.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/edac/ie31200_edac.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/edac/ie31200_edac.c b/drivers/edac/ie31200_edac.c index 5c1fa1c0d12e3..5a080ab65476d 100644 --- a/drivers/edac/ie31200_edac.c +++ b/drivers/edac/ie31200_edac.c @@ -99,6 +99,8 @@

/* Alder Lake-S */ #define PCI_DEVICE_ID_INTEL_IE31200_ADL_S_1 0x4660 +#define PCI_DEVICE_ID_INTEL_IE31200_ADL_S_2 0x4668 /* 8P+4E, e.g. i7-12700K */ +#define PCI_DEVICE_ID_INTEL_IE31200_ADL_S_3 0x4648 /* 6P+4E, e.g. i5-12600K */

/* Bartlett Lake-S */ #define PCI_DEVICE_ID_INTEL_IE31200_BTL_S_1 0x4639 @@ -761,6 +763,8 @@ static const struct pci_device_id ie31200_pci_tbl[] = { { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IE31200_RPL_S_6), (kernel_ulong_t)&rpl_s_cfg}, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IE31200_RPL_HX_1), (kernel_ulong_t)&rpl_s_cfg}, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IE31200_ADL_S_1), (kernel_ulong_t)&rpl_s_cfg}, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IE31200_ADL_S_2), (kernel_ulong_t)&rpl_s_cfg}, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IE31200_ADL_S_3), (kernel_ulong_t)&rpl_s_cfg}, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IE31200_BTL_S_1), (kernel_ulong_t)&rpl_s_cfg}, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IE31200_BTL_S_2), (kernel_ulong_t)&rpl_s_cfg}, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IE31200_BTL_S_3), (kernel_ulong_t)&rpl_s_cfg},

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Steven Rostedt rostedt@goodmis.org

[ Upstream commit 90942f9fac05702065ff82ed0bade0d08168d4ea ]

To determine if a task is a kernel thread or not, it is more reliable to use (current->flags & (PF_KTHREAD|PF_USER_WORKERi)) than to rely on current->mm being NULL. That is because some kernel tasks (io_uring helpers) may have a mm field.

Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lore.kernel.org/r/20250820180428.592367294@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/events/callchain.c | 6 +++--- kernel/events/core.c | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 6c83ad674d010..decff7266cfbd 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -242,10 +242,10 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,

if (user) { if (!user_mode(regs)) { - if (current->mm) - regs = task_pt_regs(current); - else + if (current->flags & (PF_KTHREAD | PF_USER_WORKER)) regs = NULL; + else + regs = task_pt_regs(current); }

if (regs) { diff --git a/kernel/events/core.c b/kernel/events/core.c index 6e9427c4aaff7..a3dc79ec6f879 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7440,7 +7440,7 @@ static void perf_sample_regs_user(struct perf_regs *regs_user, if (user_mode(regs)) { regs_user->abi = perf_reg_abi(current); regs_user->regs = regs; - } else if (!(current->flags & PF_KTHREAD)) { + } else if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER))) { perf_get_regs_user(regs_user, regs); } else { regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE; @@ -8080,7 +8080,7 @@ static u64 perf_virt_to_phys(u64 virt) * Try IRQ-safe get_user_page_fast_only first. * If failed, leave phys_addr as 0. */ - if (current->mm != NULL) { + if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER))) { struct page *p;

pagefault_disable();

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Josh Poimboeuf jpoimboe@kernel.org

[ Upstream commit 16ed389227651330879e17bd83d43bd234006722 ]

If the task is not a user thread, there's no user stack to unwind.

Signed-off-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lore.kernel.org/r/20250820180428.930791978@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/events/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c index a3dc79ec6f879..c0e938d28758f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8192,7 +8192,8 @@ struct perf_callchain_entry * perf_callchain(struct perf_event *event, struct pt_regs *regs) { bool kernel = !event->attr.exclude_callchain_kernel; - bool user = !event->attr.exclude_callchain_user; + bool user = !event->attr.exclude_callchain_user && + !(current->flags & (PF_KTHREAD | PF_USER_WORKER)); /* Disallow cross-task user callchains. */ bool crosstask = event->ctx->task && event->ctx->task != current; const u32 max_stack = event->attr.sample_max_stack;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jiri Olsa jolsa@kernel.org

[ Upstream commit 89d1d8434d246c96309a6068dfcf9e36dc61227b ]

Adding uprobe as another exception to the seccomp filter alongside with the uretprobe syscall.

Same as the uretprobe the uprobe syscall is installed by kernel as replacement for the breakpoint exception and is limited to x86_64 arch and isn't expected to ever be supported in i386.

Signed-off-by: Jiri Olsa jolsa@kernel.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Kees Cook kees@kernel.org Link: https://lore.kernel.org/r/20250720112133.244369-21-jolsa@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/seccomp.c | 32 +++++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 7 deletions(-)

diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 3bbfba30a777a..25f62867a16d9 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -741,6 +741,26 @@ seccomp_prepare_user_filter(const char __user *user_filter) }

#ifdef SECCOMP_ARCH_NATIVE +static bool seccomp_uprobe_exception(struct seccomp_data *sd) +{ +#if defined __NR_uretprobe || defined __NR_uprobe +#ifdef SECCOMP_ARCH_COMPAT + if (sd->arch == SECCOMP_ARCH_NATIVE) +#endif + { +#ifdef __NR_uretprobe + if (sd->nr == __NR_uretprobe) + return true; +#endif +#ifdef __NR_uprobe + if (sd->nr == __NR_uprobe) + return true; +#endif + } +#endif + return false; +} + /** * seccomp_is_const_allow - check if filter is constant allow with given data * @fprog: The BPF programs @@ -758,13 +778,8 @@ static bool seccomp_is_const_allow(struct sock_fprog_kern *fprog, return false;

/* Our single exception to filtering. */ -#ifdef __NR_uretprobe -#ifdef SECCOMP_ARCH_COMPAT - if (sd->arch == SECCOMP_ARCH_NATIVE) -#endif - if (sd->nr == __NR_uretprobe) - return true; -#endif + if (seccomp_uprobe_exception(sd)) + return true;

for (pc = 0; pc < fprog->len; pc++) { struct sock_filter *insn = &fprog->filter[pc]; @@ -1042,6 +1057,9 @@ static const int mode1_syscalls[] = { __NR_seccomp_read, __NR_seccomp_write, __NR_seccomp_exit, __NR_seccomp_sigreturn, #ifdef __NR_uretprobe __NR_uretprobe, +#endif +#ifdef __NR_uprobe + __NR_uprobe, #endif -1, /* negative terminated */ };

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Kaplan david.kaplan@amd.com

[ Upstream commit 5799d5d8a6c877f03ad5b5a640977053be45059a ]

Use attack vector controls to select whether VMSCAPE requires mitigation, similar to other bugs.

Signed-off-by: David Kaplan david.kaplan@amd.com Signed-off-by: Borislav Petkov (AMD) bp@alien8.de Signed-off-by: Sasha Levin sashal@kernel.org --- .../admin-guide/hw-vuln/attack_vector_controls.rst | 1 + arch/x86/kernel/cpu/bugs.c | 14 ++++++++++---- 2 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst b/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst index 5964901d66e31..d0bdbd81dcf9f 100644 --- a/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst +++ b/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst @@ -218,6 +218,7 @@ SRSO X X X X SSB X TAA X X X X * (Note 2) TSA X X X X +VMSCAPE X =============== ============== ============ ============= ============== ============ ========

Notes: diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 9750ce448e626..c6bb8e76eb984 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -434,6 +434,9 @@ static bool __init should_mitigate_vuln(unsigned int bug) case X86_BUG_SPEC_STORE_BYPASS: return cpu_attack_vector_mitigated(CPU_MITIGATE_USER_USER);

+ case X86_BUG_VMSCAPE: + return cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_HOST); + default: WARN(1, "Unknown bug %x\n", bug); return false; @@ -3308,15 +3311,18 @@ early_param("vmscape", vmscape_parse_cmdline);

static void __init vmscape_select_mitigation(void) { - if (cpu_mitigations_off() || - !boot_cpu_has_bug(X86_BUG_VMSCAPE) || + if (!boot_cpu_has_bug(X86_BUG_VMSCAPE) || !boot_cpu_has(X86_FEATURE_IBPB)) { vmscape_mitigation = VMSCAPE_MITIGATION_NONE; return; }

- if (vmscape_mitigation == VMSCAPE_MITIGATION_AUTO) - vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER; + if (vmscape_mitigation == VMSCAPE_MITIGATION_AUTO) { + if (should_mitigate_vuln(X86_BUG_VMSCAPE)) + vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER; + else + vmscape_mitigation = VMSCAPE_MITIGATION_NONE; + } }

static void __init vmscape_update_mitigation(void)

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Kaplan david.kaplan@amd.com

[ Upstream commit d1cc1baef67ac6c09b74629ca053bf3fb812f7dc ]

The LFENCE retpoline mitigation is not secure but the kernel prints inconsistent messages about this fact. The dmesg log says 'Mitigation: LFENCE', implying the system is mitigated. But sysfs reports 'Vulnerable: LFENCE' implying the system (correctly) is not mitigated.

Fix this by printing a consistent 'Vulnerable: LFENCE' string everywhere when this mitigation is selected.

Signed-off-by: David Kaplan david.kaplan@amd.com Signed-off-by: Borislav Petkov (AMD) bp@alien8.de Link: https://lore.kernel.org/20250915134706.3201818-1-david.kaplan@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/cpu/bugs.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index c6bb8e76eb984..26ece97011fd7 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2052,7 +2052,7 @@ static void __init spectre_v2_user_apply_mitigation(void) static const char * const spectre_v2_strings[] = { [SPECTRE_V2_NONE] = "Vulnerable", [SPECTRE_V2_RETPOLINE] = "Mitigation: Retpolines", - [SPECTRE_V2_LFENCE] = "Mitigation: LFENCE", + [SPECTRE_V2_LFENCE] = "Vulnerable: LFENCE", [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced / Automatic IBRS", [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced / Automatic IBRS + LFENCE", [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced / Automatic IBRS + Retpolines", @@ -3636,9 +3636,6 @@ static const char *spectre_bhi_state(void)

static ssize_t spectre_v2_show_state(char *buf) { - if (spectre_v2_enabled == SPECTRE_V2_LFENCE) - return sysfs_emit(buf, "Vulnerable: LFENCE\n"); - if (spectre_v2_enabled == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) return sysfs_emit(buf, "Vulnerable: eIBRS with unprivileged eBPF\n");

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chen Ridong chenridong@huawei.com

[ Upstream commit 59d5de3655698679ad8fd2cc82228de4679c4263 ]

A previous patch fixed a bug where new_prs should be assigned before checking housekeeping conflicts. This patch addresses another potential issue: the nocpu error check currently uses the xcpus which is not updated. Although no issue has been observed so far, the check should be performed using the new effective exclusive cpus.

The comment has been removed because the function returns an error if nocpu checking fails, which is unrelated to the parent.

Signed-off-by: Chen Ridong chenridong@huawei.com Reviewed-by: Waiman Long longman@redhat.com Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/cgroup/cpuset.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index fef93032fe7e4..fd890b34a8403 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1728,11 +1728,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd, if (prstate_housekeeping_conflict(new_prs, xcpus)) return PERR_HKEEPING;

- /* - * A parent can be left with no CPU as long as there is no - * task directly associated with the parent partition. - */ - if (nocpu) + if (tasks_nocpu_error(parent, cs, xcpus)) return PERR_NOCPUS;

/*

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Filipe Manana fdmanana@suse.com

[ Upstream commit e6dd405b6671b9753b98d8bdf76f8f0ed36c11cd ]

In the process_one_buffer() log tree walk callback we return errors to the log tree walk caller and then the caller aborts the transaction, if we have one, or turns the fs into error state if we don't have one. While this reduces code it makes it harder to figure out where exactly an error came from. So add the transaction aborts after every failure inside the process_one_buffer() callback, so that it helps figuring out why failures happen.

Reviewed-by: Boris Burkov boris@bur.io Reviewed-by: Qu Wenruo wqu@suse.com Signed-off-by: Filipe Manana fdmanana@suse.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/tree-log.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 6d92326a1a0c7..50ed84cb68a69 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -347,6 +347,7 @@ static int process_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, struct walk_control *wc, u64 gen, int level) { + struct btrfs_trans_handle *trans = wc->trans; struct btrfs_fs_info *fs_info = log->fs_info; int ret = 0;

@@ -361,18 +362,29 @@ static int process_one_buffer(struct btrfs_root *log, };

ret = btrfs_read_extent_buffer(eb, &check); - if (ret) + if (ret) { + if (trans) + btrfs_abort_transaction(trans, ret); + else + btrfs_handle_fs_error(fs_info, ret, NULL); return ret; + } }

if (wc->pin) { - ret = btrfs_pin_extent_for_log_replay(wc->trans, eb); - if (ret) + ASSERT(trans != NULL); + ret = btrfs_pin_extent_for_log_replay(trans, eb); + if (ret) { + btrfs_abort_transaction(trans, ret); return ret; + }

if (btrfs_buffer_uptodate(eb, gen, 0) && - btrfs_header_level(eb) == 0) + btrfs_header_level(eb) == 0) { ret = btrfs_exclude_logged_extents(eb); + if (ret) + btrfs_abort_transaction(trans, ret); + } } return ret; }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Naohiro Aota naohiro.aota@wdc.com

[ Upstream commit 0d703963d297964451783e1a0688ebdf74cd6151 ]

The hint block group selection in the extent allocator is wrong in the first place, as it can select the dedicated data relocation block group for the normal data allocation.

Since we separated the normal data space_info and the data relocation space_info, we can easily identify a block group is for data relocation or not. Do not choose it for the normal data allocation.

Reviewed-by: Johannes Thumshirn johannes.thumshirn@wdc.com Signed-off-by: Naohiro Aota naohiro.aota@wdc.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/extent-tree.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 97d517cdf2df7..682d21a73a67a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4297,7 +4297,8 @@ static int prepare_allocation_clustered(struct btrfs_fs_info *fs_info, }

static int prepare_allocation_zoned(struct btrfs_fs_info *fs_info, - struct find_free_extent_ctl *ffe_ctl) + struct find_free_extent_ctl *ffe_ctl, + struct btrfs_space_info *space_info) { if (ffe_ctl->for_treelog) { spin_lock(&fs_info->treelog_bg_lock); @@ -4321,6 +4322,7 @@ static int prepare_allocation_zoned(struct btrfs_fs_info *fs_info, u64 avail = block_group->zone_capacity - block_group->alloc_offset;

if (block_group_bits(block_group, ffe_ctl->flags) && + block_group->space_info == space_info && avail >= ffe_ctl->num_bytes) { ffe_ctl->hint_byte = block_group->start; break; @@ -4342,7 +4344,7 @@ static int prepare_allocation(struct btrfs_fs_info *fs_info, return prepare_allocation_clustered(fs_info, ffe_ctl, space_info, ins); case BTRFS_EXTENT_ALLOC_ZONED: - return prepare_allocation_zoned(fs_info, ffe_ctl); + return prepare_allocation_zoned(fs_info, ffe_ctl, space_info); default: BUG(); }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Filipe Manana fdmanana@suse.com

[ Upstream commit 2f5b8095ea47b142c56c09755a8b1e14145a2d30 ]

Currently we have this odd behaviour:

1) At btrfs_replay_log() we drop the reference of the log root tree if the call to btrfs_recover_log_trees() failed;

2) But if the call to btrfs_recover_log_trees() did not fail, we don't drop the reference in btrfs_replay_log() - we expect that btrfs_recover_log_trees() does it in case it returns success.

Let's simplify this and make btrfs_replay_log() always drop the reference on the log root tree, not only this simplifies code as it's what makes sense since it's btrfs_replay_log() who grabbed the reference in the first place.

Signed-off-by: Filipe Manana fdmanana@suse.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/disk-io.c | 2 +- fs/btrfs/tree-log.c | 1 - 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 70fc4e7cc5a0e..0b02e36b30558 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2087,10 +2087,10 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,

/* returns with log_tree_root freed on success */ ret = btrfs_recover_log_trees(log_tree_root); + btrfs_put_root(log_tree_root); if (ret) { btrfs_handle_fs_error(fs_info, ret, "Failed to recover log tree"); - btrfs_put_root(log_tree_root); return ret; }

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 50ed84cb68a69..518cd74191e77 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -7469,7 +7469,6 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree)

log_root_tree->log_root = NULL; clear_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags); - btrfs_put_root(log_root_tree);

return 0; error:

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Filipe Manana fdmanana@suse.com

[ Upstream commit 5a0565cad3ef7cbf4cf43d1dd1e849b156205292 ]

If we fail to update the inode at link_to_fixup_dir(), we don't abort the transaction and propagate the error up the call chain, which makes it hard to pinpoint the error to the inode update. So abort the transaction if the inode update call fails, so that if it happens we known immediately.

Signed-off-by: Filipe Manana fdmanana@suse.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/tree-log.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 4f92aa15d9b1d..165d2ee500ca3 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1796,6 +1796,8 @@ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans, else inc_nlink(vfs_inode); ret = btrfs_update_inode(trans, inode); + if (ret) + btrfs_abort_transaction(trans, ret); } else if (ret == -EEXIST) { ret = 0; }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Filipe Manana fdmanana@suse.com

[ Upstream commit 45c222468d33202c07c41c113301a4b9c8451b8f ]

After setting the BTRFS_ROOT_FORCE_COW flag on the root we are doing a full write barrier, smp_wmb(), but we don't need to, all we need is a smp_mb__after_atomic(). The use of the smp_wmb() is from the old days when we didn't use a bit and used instead an int field in the root to signal if cow is forced. After the int field was changed to a bit in the root's state (flags field), we forgot to update the memory barrier in create_pending_snapshot() to smp_mb__after_atomic(), but we did the change in commit_fs_roots() after clearing BTRFS_ROOT_FORCE_COW. That happened in commit 27cdeb7096b8 ("Btrfs: use bitfield instead of integer data type for the some variants in btrfs_root"). On the reader side, in should_cow_block(), we also use the counterpart smp_mb__before_atomic() which generates further confusion.

So change the smp_wmb() to smp_mb__after_atomic(). In fact we don't even need any barrier at all since create_pending_snapshot() is called in the critical section of a transaction commit and therefore no one can concurrently join/attach the transaction, or start a new one, until the transaction is unblocked. By the time someone starts a new transaction and enters should_cow_block(), a lot of implicit memory barriers already took place by having acquired several locks such as fs_info->trans_lock and extent buffer locks on the root node at least. Nevertlheless, for consistency use smp_mb__after_atomic() after setting the force cow bit in create_pending_snapshot().

Signed-off-by: Filipe Manana fdmanana@suse.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/transaction.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index c5c0d9cf1a808..a4e486a600bed 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1806,7 +1806,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, } /* see comments in should_cow_block() */ set_bit(BTRFS_ROOT_FORCE_COW, &root->state); - smp_wmb(); + smp_mb__after_atomic();

btrfs_set_root_node(new_root_item, tmp); /* record when the snapshot was created in key.offset */

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Menglong Dong menglong8.dong@gmail.com

[ Upstream commit 35561bab768977c9e05f1f1a9bc00134c85f3e28 ]

The include/generated/asm-offsets.h is generated in Kbuild during compiling from arch/SRCARCH/kernel/asm-offsets.c. When we want to generate another similar offset header file, circular dependency can happen.

For example, we want to generate a offset file include/generated/test.h, which is included in include/sched/sched.h. If we generate asm-offsets.h first, it will fail, as include/sched/sched.h is included in asm-offsets.c and include/generated/test.h doesn't exist; If we generate test.h first, it can't success neither, as include/generated/asm-offsets.h is included by it.

In x86_64, the macro COMPILE_OFFSETS is used to avoid such circular dependency. We can generate asm-offsets.h first, and if the COMPILE_OFFSETS is defined, we don't include the "generated/test.h".

And we define the macro COMPILE_OFFSETS for all the asm-offsets.c for this purpose.

Signed-off-by: Menglong Dong dongml2@chinatelecom.cn Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/alpha/kernel/asm-offsets.c | 1 + arch/arc/kernel/asm-offsets.c | 1 + arch/arm/kernel/asm-offsets.c | 2 ++ arch/arm64/kernel/asm-offsets.c | 1 + arch/csky/kernel/asm-offsets.c | 1 + arch/hexagon/kernel/asm-offsets.c | 1 + arch/loongarch/kernel/asm-offsets.c | 2 ++ arch/m68k/kernel/asm-offsets.c | 1 + arch/microblaze/kernel/asm-offsets.c | 1 + arch/mips/kernel/asm-offsets.c | 2 ++ arch/nios2/kernel/asm-offsets.c | 1 + arch/openrisc/kernel/asm-offsets.c | 1 + arch/parisc/kernel/asm-offsets.c | 1 + arch/powerpc/kernel/asm-offsets.c | 1 + arch/riscv/kernel/asm-offsets.c | 1 + arch/s390/kernel/asm-offsets.c | 1 + arch/sh/kernel/asm-offsets.c | 1 + arch/sparc/kernel/asm-offsets.c | 1 + arch/um/kernel/asm-offsets.c | 2 ++ arch/xtensa/kernel/asm-offsets.c | 1 + 20 files changed, 24 insertions(+)

diff --git a/arch/alpha/kernel/asm-offsets.c b/arch/alpha/kernel/asm-offsets.c index e9dad60b147f3..1ebb058904992 100644 --- a/arch/alpha/kernel/asm-offsets.c +++ b/arch/alpha/kernel/asm-offsets.c @@ -4,6 +4,7 @@ * This code generates raw asm output which is post-processed to extract * and format the required data. */ +#define COMPILE_OFFSETS

#include <linux/types.h> #include <linux/stddef.h> diff --git a/arch/arc/kernel/asm-offsets.c b/arch/arc/kernel/asm-offsets.c index f77deb7991757..2978da85fcb65 100644 --- a/arch/arc/kernel/asm-offsets.c +++ b/arch/arc/kernel/asm-offsets.c @@ -2,6 +2,7 @@ /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) */ +#define COMPILE_OFFSETS

#include <linux/sched.h> #include <linux/mm.h> diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index 123f4a8ef4466..2101938d27fcb 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -7,6 +7,8 @@ * This code generates raw asm output which is post-processed to extract * and format the required data. */ +#define COMPILE_OFFSETS + #include <linux/compiler.h> #include <linux/sched.h> #include <linux/mm.h> diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 30d4bbe68661f..b6367ff3a49ca 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -6,6 +6,7 @@ * 2001-2002 Keith Owens * Copyright (C) 2012 ARM Ltd. */ +#define COMPILE_OFFSETS

#include <linux/arm_sdei.h> #include <linux/sched.h> diff --git a/arch/csky/kernel/asm-offsets.c b/arch/csky/kernel/asm-offsets.c index d1e9035794733..5525c8e7e1d9e 100644 --- a/arch/csky/kernel/asm-offsets.c +++ b/arch/csky/kernel/asm-offsets.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. +#define COMPILE_OFFSETS

#include <linux/sched.h> #include <linux/kernel_stat.h> diff --git a/arch/hexagon/kernel/asm-offsets.c b/arch/hexagon/kernel/asm-offsets.c index 03a7063f94561..50eea9fa6f137 100644 --- a/arch/hexagon/kernel/asm-offsets.c +++ b/arch/hexagon/kernel/asm-offsets.c @@ -8,6 +8,7 @@ * * Copyright (c) 2010-2012, The Linux Foundation. All rights reserved. */ +#define COMPILE_OFFSETS

#include <linux/compat.h> #include <linux/types.h> diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c index db1e4bb26b6a0..3017c71576009 100644 --- a/arch/loongarch/kernel/asm-offsets.c +++ b/arch/loongarch/kernel/asm-offsets.c @@ -4,6 +4,8 @@ * * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ +#define COMPILE_OFFSETS + #include <linux/types.h> #include <linux/sched.h> #include <linux/mm.h> diff --git a/arch/m68k/kernel/asm-offsets.c b/arch/m68k/kernel/asm-offsets.c index 906d732305374..67a1990f9d748 100644 --- a/arch/m68k/kernel/asm-offsets.c +++ b/arch/m68k/kernel/asm-offsets.c @@ -9,6 +9,7 @@ * #defines from the assembly-language output. */

+#define COMPILE_OFFSETS #define ASM_OFFSETS_C

#include <linux/stddef.h> diff --git a/arch/microblaze/kernel/asm-offsets.c b/arch/microblaze/kernel/asm-offsets.c index 104c3ac5f30c8..b4b67d58e7f6a 100644 --- a/arch/microblaze/kernel/asm-offsets.c +++ b/arch/microblaze/kernel/asm-offsets.c @@ -7,6 +7,7 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. */ +#define COMPILE_OFFSETS

#include <linux/init.h> #include <linux/stddef.h> diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index 1e29efcba46e5..5debd9a3854a9 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -9,6 +9,8 @@ * Kevin Kissell, kevink@mips.com and Carsten Langgaard, carstenl@mips.com * Copyright (C) 2000 MIPS Technologies, Inc. */ +#define COMPILE_OFFSETS + #include <linux/compat.h> #include <linux/types.h> #include <linux/sched.h> diff --git a/arch/nios2/kernel/asm-offsets.c b/arch/nios2/kernel/asm-offsets.c index e3d9b7b6fb48a..88190b503ce5d 100644 --- a/arch/nios2/kernel/asm-offsets.c +++ b/arch/nios2/kernel/asm-offsets.c @@ -2,6 +2,7 @@ /* * Copyright (C) 2011 Tobias Klauser tklauser@distanz.ch */ +#define COMPILE_OFFSETS

#include <linux/stddef.h> #include <linux/sched.h> diff --git a/arch/openrisc/kernel/asm-offsets.c b/arch/openrisc/kernel/asm-offsets.c index 710651d5aaae1..3cc826f2216b1 100644 --- a/arch/openrisc/kernel/asm-offsets.c +++ b/arch/openrisc/kernel/asm-offsets.c @@ -18,6 +18,7 @@ * compile this file to assembler, and then extract the * #defines from the assembly-language output. */ +#define COMPILE_OFFSETS

#include <linux/signal.h> #include <linux/sched.h> diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c index 757816a7bd4b2..9abfe65492c65 100644 --- a/arch/parisc/kernel/asm-offsets.c +++ b/arch/parisc/kernel/asm-offsets.c @@ -13,6 +13,7 @@ * Copyright (C) 2002 Randolph Chung <tausq with parisc-linux.org> * Copyright (C) 2003 James Bottomley <jejb at parisc-linux.org> */ +#define COMPILE_OFFSETS

#include <linux/types.h> #include <linux/sched.h> diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index b3048f6d3822c..a4bc80b30410a 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -8,6 +8,7 @@ * compile this file to assembler, and then extract the * #defines from the assembly-language output. */ +#define COMPILE_OFFSETS

#include <linux/compat.h> #include <linux/signal.h> diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index 6e8c0d6feae9e..7d42d3b8a32a7 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -3,6 +3,7 @@ * Copyright (C) 2012 Regents of the University of California * Copyright (C) 2017 SiFive */ +#define COMPILE_OFFSETS

#include <linux/kbuild.h> #include <linux/mm.h> diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 95ecad9c7d7d2..a8915663e917f 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -4,6 +4,7 @@ * This code generates raw asm output which is post-processed to extract * and format the required data. */ +#define COMPILE_OFFSETS

#include <linux/kbuild.h> #include <linux/sched.h> diff --git a/arch/sh/kernel/asm-offsets.c b/arch/sh/kernel/asm-offsets.c index a0322e8328456..429b6a7631468 100644 --- a/arch/sh/kernel/asm-offsets.c +++ b/arch/sh/kernel/asm-offsets.c @@ -8,6 +8,7 @@ * compile this file to assembler, and then extract the * #defines from the assembly-language output. */ +#define COMPILE_OFFSETS

#include <linux/stddef.h> #include <linux/types.h> diff --git a/arch/sparc/kernel/asm-offsets.c b/arch/sparc/kernel/asm-offsets.c index 3d9b9855dce91..6e660bde48dd8 100644 --- a/arch/sparc/kernel/asm-offsets.c +++ b/arch/sparc/kernel/asm-offsets.c @@ -10,6 +10,7 @@ * * On sparc, thread_info data is static and TI_XXX offsets are computed by hand. */ +#define COMPILE_OFFSETS

#include <linux/sched.h> #include <linux/mm_types.h> diff --git a/arch/um/kernel/asm-offsets.c b/arch/um/kernel/asm-offsets.c index 1fb12235ab9c8..a69873aa697f4 100644 --- a/arch/um/kernel/asm-offsets.c +++ b/arch/um/kernel/asm-offsets.c @@ -1 +1,3 @@ +#define COMPILE_OFFSETS + #include <sysdep/kernel-offsets.h> diff --git a/arch/xtensa/kernel/asm-offsets.c b/arch/xtensa/kernel/asm-offsets.c index da38de20ae598..cfbced95e944a 100644 --- a/arch/xtensa/kernel/asm-offsets.c +++ b/arch/xtensa/kernel/asm-offsets.c @@ -11,6 +11,7 @@ * * Chris Zankel chris@zankel.net */ +#define COMPILE_OFFSETS

#include <asm/processor.h> #include <asm/coprocessor.h>