diff options
Diffstat (limited to 'tools/sched_ext/include/scx')
| -rw-r--r-- | tools/sched_ext/include/scx/common.bpf.h | 685 | ||||
| -rw-r--r-- | tools/sched_ext/include/scx/common.h | 82 | ||||
| -rw-r--r-- | tools/sched_ext/include/scx/compat.bpf.h | 238 | ||||
| -rw-r--r-- | tools/sched_ext/include/scx/compat.h | 199 | ||||
| -rw-r--r-- | tools/sched_ext/include/scx/enum_defs.autogen.h | 123 | ||||
| -rw-r--r-- | tools/sched_ext/include/scx/enums.autogen.bpf.h | 129 | ||||
| -rw-r--r-- | tools/sched_ext/include/scx/enums.autogen.h | 49 | ||||
| -rw-r--r-- | tools/sched_ext/include/scx/enums.bpf.h | 12 | ||||
| -rw-r--r-- | tools/sched_ext/include/scx/enums.h | 28 | ||||
| -rw-r--r-- | tools/sched_ext/include/scx/user_exit_info.h | 118 |
10 files changed, 1663 insertions, 0 deletions
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h new file mode 100644 index 000000000000..d4e21558e982 --- /dev/null +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -0,0 +1,685 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo <tj@kernel.org> + * Copyright (c) 2022 David Vernet <dvernet@meta.com> + */ +#ifndef __SCX_COMMON_BPF_H +#define __SCX_COMMON_BPF_H + +/* + * The generated kfunc prototypes in vmlinux.h are missing address space + * attributes which cause build failures. For now, suppress the generated + * prototypes. See https://github.com/sched-ext/scx/issues/1111. + */ +#define BPF_NO_KFUNC_PROTOTYPES + +#ifdef LSP +#define __bpf__ +#include "../vmlinux.h" +#else +#include "vmlinux.h" +#endif + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <asm-generic/errno.h> +#include "user_exit_info.h" +#include "enum_defs.autogen.h" + +#define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ +#define PF_KTHREAD 0x00200000 /* I am a kernel thread */ +#define PF_EXITING 0x00000004 +#define CLOCK_MONOTONIC 1 + +extern int LINUX_KERNEL_VERSION __kconfig; +extern const char CONFIG_CC_VERSION_TEXT[64] __kconfig __weak; +extern const char CONFIG_LOCALVERSION[64] __kconfig __weak; + +/* + * Earlier versions of clang/pahole lost upper 32bits in 64bit enums which can + * lead to really confusing misbehaviors. Let's trigger a build failure. + */ +static inline void ___vmlinux_h_sanity_check___(void) +{ + _Static_assert(SCX_DSQ_FLAG_BUILTIN, + "bpftool generated vmlinux.h is missing high bits for 64bit enums, upgrade clang and pahole"); +} + +s32 scx_bpf_create_dsq(u64 dsq_id, s32 node) __ksym; +s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool *is_idle) __ksym; +s32 scx_bpf_select_cpu_and(struct task_struct *p, s32 prev_cpu, u64 wake_flags, + const struct cpumask *cpus_allowed, u64 flags) __ksym __weak; +void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_flags) __ksym __weak; +void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym __weak; +u32 scx_bpf_dispatch_nr_slots(void) __ksym; +void scx_bpf_dispatch_cancel(void) __ksym; +bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym __weak; +void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym __weak; +void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym __weak; +bool scx_bpf_dsq_move(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak; +bool scx_bpf_dsq_move_vtime(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak; +u32 scx_bpf_reenqueue_local(void) __ksym; +void scx_bpf_kick_cpu(s32 cpu, u64 flags) __ksym; +s32 scx_bpf_dsq_nr_queued(u64 dsq_id) __ksym; +void scx_bpf_destroy_dsq(u64 dsq_id) __ksym; +int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, u64 flags) __ksym __weak; +struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *it) __ksym __weak; +void bpf_iter_scx_dsq_destroy(struct bpf_iter_scx_dsq *it) __ksym __weak; +void scx_bpf_exit_bstr(s64 exit_code, char *fmt, unsigned long long *data, u32 data__sz) __ksym __weak; +void scx_bpf_error_bstr(char *fmt, unsigned long long *data, u32 data_len) __ksym; +void scx_bpf_dump_bstr(char *fmt, unsigned long long *data, u32 data_len) __ksym __weak; +u32 scx_bpf_cpuperf_cap(s32 cpu) __ksym __weak; +u32 scx_bpf_cpuperf_cur(s32 cpu) __ksym __weak; +void scx_bpf_cpuperf_set(s32 cpu, u32 perf) __ksym __weak; +u32 scx_bpf_nr_node_ids(void) __ksym __weak; +u32 scx_bpf_nr_cpu_ids(void) __ksym __weak; +int scx_bpf_cpu_node(s32 cpu) __ksym __weak; +const struct cpumask *scx_bpf_get_possible_cpumask(void) __ksym __weak; +const struct cpumask *scx_bpf_get_online_cpumask(void) __ksym __weak; +void scx_bpf_put_cpumask(const struct cpumask *cpumask) __ksym __weak; +const struct cpumask *scx_bpf_get_idle_cpumask_node(int node) __ksym __weak; +const struct cpumask *scx_bpf_get_idle_cpumask(void) __ksym; +const struct cpumask *scx_bpf_get_idle_smtmask_node(int node) __ksym __weak; +const struct cpumask *scx_bpf_get_idle_smtmask(void) __ksym; +void scx_bpf_put_idle_cpumask(const struct cpumask *cpumask) __ksym; +bool scx_bpf_test_and_clear_cpu_idle(s32 cpu) __ksym; +s32 scx_bpf_pick_idle_cpu_node(const cpumask_t *cpus_allowed, int node, u64 flags) __ksym __weak; +s32 scx_bpf_pick_idle_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym; +s32 scx_bpf_pick_any_cpu_node(const cpumask_t *cpus_allowed, int node, u64 flags) __ksym __weak; +s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym; +bool scx_bpf_task_running(const struct task_struct *p) __ksym; +s32 scx_bpf_task_cpu(const struct task_struct *p) __ksym; +struct rq *scx_bpf_cpu_rq(s32 cpu) __ksym; +struct cgroup *scx_bpf_task_cgroup(struct task_struct *p) __ksym __weak; +u64 scx_bpf_now(void) __ksym __weak; +void scx_bpf_events(struct scx_event_stats *events, size_t events__sz) __ksym __weak; + +/* + * Use the following as @it__iter when calling scx_bpf_dsq_move[_vtime]() from + * within bpf_for_each() loops. + */ +#define BPF_FOR_EACH_ITER (&___it) + +#define scx_read_event(e, name) \ + (bpf_core_field_exists((e)->name) ? (e)->name : 0) + +static inline __attribute__((format(printf, 1, 2))) +void ___scx_bpf_bstr_format_checker(const char *fmt, ...) {} + +/* + * Helper macro for initializing the fmt and variadic argument inputs to both + * bstr exit kfuncs. Callers to this function should use ___fmt and ___param to + * refer to the initialized list of inputs to the bstr kfunc. + */ +#define scx_bpf_bstr_preamble(fmt, args...) \ + static char ___fmt[] = fmt; \ + /* \ + * Note that __param[] must have at least one \ + * element to keep the verifier happy. \ + */ \ + unsigned long long ___param[___bpf_narg(args) ?: 1] = {}; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") + +/* + * scx_bpf_exit() wraps the scx_bpf_exit_bstr() kfunc with variadic arguments + * instead of an array of u64. Using this macro will cause the scheduler to + * exit cleanly with the specified exit code being passed to user space. + */ +#define scx_bpf_exit(code, fmt, args...) \ +({ \ + scx_bpf_bstr_preamble(fmt, args) \ + scx_bpf_exit_bstr(code, ___fmt, ___param, sizeof(___param)); \ + ___scx_bpf_bstr_format_checker(fmt, ##args); \ +}) + +/* + * scx_bpf_error() wraps the scx_bpf_error_bstr() kfunc with variadic arguments + * instead of an array of u64. Invoking this macro will cause the scheduler to + * exit in an erroneous state, with diagnostic information being passed to the + * user. + */ +#define scx_bpf_error(fmt, args...) \ +({ \ + scx_bpf_bstr_preamble(fmt, args) \ + scx_bpf_error_bstr(___fmt, ___param, sizeof(___param)); \ + ___scx_bpf_bstr_format_checker(fmt, ##args); \ +}) + +/* + * scx_bpf_dump() wraps the scx_bpf_dump_bstr() kfunc with variadic arguments + * instead of an array of u64. To be used from ops.dump() and friends. + */ +#define scx_bpf_dump(fmt, args...) \ +({ \ + scx_bpf_bstr_preamble(fmt, args) \ + scx_bpf_dump_bstr(___fmt, ___param, sizeof(___param)); \ + ___scx_bpf_bstr_format_checker(fmt, ##args); \ +}) + +/* + * scx_bpf_dump_header() is a wrapper around scx_bpf_dump that adds a header + * of system information for debugging. + */ +#define scx_bpf_dump_header() \ +({ \ + scx_bpf_dump("kernel: %d.%d.%d %s\ncc: %s\n", \ + LINUX_KERNEL_VERSION >> 16, \ + LINUX_KERNEL_VERSION >> 8 & 0xFF, \ + LINUX_KERNEL_VERSION & 0xFF, \ + CONFIG_LOCALVERSION, \ + CONFIG_CC_VERSION_TEXT); \ +}) + +#define BPF_STRUCT_OPS(name, args...) \ +SEC("struct_ops/"#name) \ +BPF_PROG(name, ##args) + +#define BPF_STRUCT_OPS_SLEEPABLE(name, args...) \ +SEC("struct_ops.s/"#name) \ +BPF_PROG(name, ##args) + +/** + * RESIZABLE_ARRAY - Generates annotations for an array that may be resized + * @elfsec: the data section of the BPF program in which to place the array + * @arr: the name of the array + * + * libbpf has an API for setting map value sizes. Since data sections (i.e. + * bss, data, rodata) themselves are maps, a data section can be resized. If + * a data section has an array as its last element, the BTF info for that + * array will be adjusted so that length of the array is extended to meet the + * new length of the data section. This macro annotates an array to have an + * element count of one with the assumption that this array can be resized + * within the userspace program. It also annotates the section specifier so + * this array exists in a custom sub data section which can be resized + * independently. + * + * See RESIZE_ARRAY() for the userspace convenience macro for resizing an + * array declared with RESIZABLE_ARRAY(). + */ +#define RESIZABLE_ARRAY(elfsec, arr) arr[1] SEC("."#elfsec"."#arr) + +/** + * MEMBER_VPTR - Obtain the verified pointer to a struct or array member + * @base: struct or array to index + * @member: dereferenced member (e.g. .field, [idx0][idx1], .field[idx0] ...) + * + * The verifier often gets confused by the instruction sequence the compiler + * generates for indexing struct fields or arrays. This macro forces the + * compiler to generate a code sequence which first calculates the byte offset, + * checks it against the struct or array size and add that byte offset to + * generate the pointer to the member to help the verifier. + * + * Ideally, we want to abort if the calculated offset is out-of-bounds. However, + * BPF currently doesn't support abort, so evaluate to %NULL instead. The caller + * must check for %NULL and take appropriate action to appease the verifier. To + * avoid confusing the verifier, it's best to check for %NULL and dereference + * immediately. + * + * vptr = MEMBER_VPTR(my_array, [i][j]); + * if (!vptr) + * return error; + * *vptr = new_value; + * + * sizeof(@base) should encompass the memory area to be accessed and thus can't + * be a pointer to the area. Use `MEMBER_VPTR(*ptr, .member)` instead of + * `MEMBER_VPTR(ptr, ->member)`. + */ +#define MEMBER_VPTR(base, member) (typeof((base) member) *) \ +({ \ + u64 __base = (u64)&(base); \ + u64 __addr = (u64)&((base) member) - __base; \ + _Static_assert(sizeof(base) >= sizeof((base) member), \ + "@base is smaller than @member, is @base a pointer?"); \ + asm volatile ( \ + "if %0 <= %[max] goto +2\n" \ + "%0 = 0\n" \ + "goto +1\n" \ + "%0 += %1\n" \ + : "+r"(__addr) \ + : "r"(__base), \ + [max]"i"(sizeof(base) - sizeof((base) member))); \ + __addr; \ +}) + +/** + * ARRAY_ELEM_PTR - Obtain the verified pointer to an array element + * @arr: array to index into + * @i: array index + * @n: number of elements in array + * + * Similar to MEMBER_VPTR() but is intended for use with arrays where the + * element count needs to be explicit. + * It can be used in cases where a global array is defined with an initial + * size but is intended to be be resized before loading the BPF program. + * Without this version of the macro, MEMBER_VPTR() will use the compile time + * size of the array to compute the max, which will result in rejection by + * the verifier. + */ +#define ARRAY_ELEM_PTR(arr, i, n) (typeof(arr[i]) *) \ +({ \ + u64 __base = (u64)arr; \ + u64 __addr = (u64)&(arr[i]) - __base; \ + asm volatile ( \ + "if %0 <= %[max] goto +2\n" \ + "%0 = 0\n" \ + "goto +1\n" \ + "%0 += %1\n" \ + : "+r"(__addr) \ + : "r"(__base), \ + [max]"r"(sizeof(arr[0]) * ((n) - 1))); \ + __addr; \ +}) + + +/* + * BPF declarations and helpers + */ + +/* list and rbtree */ +#define __contains(name, node) __attribute__((btf_decl_tag("contains:" #name ":" #node))) +#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8))) + +void *bpf_obj_new_impl(__u64 local_type_id, void *meta) __ksym; +void bpf_obj_drop_impl(void *kptr, void *meta) __ksym; + +#define bpf_obj_new(type) ((type *)bpf_obj_new_impl(bpf_core_type_id_local(type), NULL)) +#define bpf_obj_drop(kptr) bpf_obj_drop_impl(kptr, NULL) + +int bpf_list_push_front_impl(struct bpf_list_head *head, + struct bpf_list_node *node, + void *meta, __u64 off) __ksym; +#define bpf_list_push_front(head, node) bpf_list_push_front_impl(head, node, NULL, 0) + +int bpf_list_push_back_impl(struct bpf_list_head *head, + struct bpf_list_node *node, + void *meta, __u64 off) __ksym; +#define bpf_list_push_back(head, node) bpf_list_push_back_impl(head, node, NULL, 0) + +struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) __ksym; +struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) __ksym; +struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root, + struct bpf_rb_node *node) __ksym; +int bpf_rbtree_add_impl(struct bpf_rb_root *root, struct bpf_rb_node *node, + bool (less)(struct bpf_rb_node *a, const struct bpf_rb_node *b), + void *meta, __u64 off) __ksym; +#define bpf_rbtree_add(head, node, less) bpf_rbtree_add_impl(head, node, less, NULL, 0) + +struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root) __ksym; + +void *bpf_refcount_acquire_impl(void *kptr, void *meta) __ksym; +#define bpf_refcount_acquire(kptr) bpf_refcount_acquire_impl(kptr, NULL) + +/* task */ +struct task_struct *bpf_task_from_pid(s32 pid) __ksym; +struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym; +void bpf_task_release(struct task_struct *p) __ksym; + +/* cgroup */ +struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) __ksym; +void bpf_cgroup_release(struct cgroup *cgrp) __ksym; +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; + +/* css iteration */ +struct bpf_iter_css; +struct cgroup_subsys_state; +extern int bpf_iter_css_new(struct bpf_iter_css *it, + struct cgroup_subsys_state *start, + unsigned int flags) __weak __ksym; +extern struct cgroup_subsys_state * +bpf_iter_css_next(struct bpf_iter_css *it) __weak __ksym; +extern void bpf_iter_css_destroy(struct bpf_iter_css *it) __weak __ksym; + +/* cpumask */ +struct bpf_cpumask *bpf_cpumask_create(void) __ksym; +struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) __ksym; +void bpf_cpumask_release(struct bpf_cpumask *cpumask) __ksym; +u32 bpf_cpumask_first(const struct cpumask *cpumask) __ksym; +u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym; +void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym; +void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym; +bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask) __ksym; +bool bpf_cpumask_test_and_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym; +bool bpf_cpumask_test_and_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym; +void bpf_cpumask_setall(struct bpf_cpumask *cpumask) __ksym; +void bpf_cpumask_clear(struct bpf_cpumask *cpumask) __ksym; +bool bpf_cpumask_and(struct bpf_cpumask *dst, const struct cpumask *src1, + const struct cpumask *src2) __ksym; +void bpf_cpumask_or(struct bpf_cpumask *dst, const struct cpumask *src1, + const struct cpumask *src2) __ksym; +void bpf_cpumask_xor(struct bpf_cpumask *dst, const struct cpumask *src1, + const struct cpumask *src2) __ksym; +bool bpf_cpumask_equal(const struct cpumask *src1, const struct cpumask *src2) __ksym; +bool bpf_cpumask_intersects(const struct cpumask *src1, const struct cpumask *src2) __ksym; +bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2) __ksym; +bool bpf_cpumask_empty(const struct cpumask *cpumask) __ksym; +bool bpf_cpumask_full(const struct cpumask *cpumask) __ksym; +void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym; +u32 bpf_cpumask_any_distribute(const struct cpumask *cpumask) __ksym; +u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, + const struct cpumask *src2) __ksym; +u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym; + +int bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_words) __ksym; +int *bpf_iter_bits_next(struct bpf_iter_bits *it) __ksym; +void bpf_iter_bits_destroy(struct bpf_iter_bits *it) __ksym; + +#define def_iter_struct(name) \ +struct bpf_iter_##name { \ + struct bpf_iter_bits it; \ + const struct cpumask *bitmap; \ +}; + +#define def_iter_new(name) \ +static inline int bpf_iter_##name##_new( \ + struct bpf_iter_##name *it, const u64 *unsafe_ptr__ign, u32 nr_words) \ +{ \ + it->bitmap = scx_bpf_get_##name##_cpumask(); \ + return bpf_iter_bits_new(&it->it, (const u64 *)it->bitmap, \ + sizeof(struct cpumask) / 8); \ +} + +#define def_iter_next(name) \ +static inline int *bpf_iter_##name##_next(struct bpf_iter_##name *it) { \ + return bpf_iter_bits_next(&it->it); \ +} + +#define def_iter_destroy(name) \ +static inline void bpf_iter_##name##_destroy(struct bpf_iter_##name *it) { \ + scx_bpf_put_cpumask(it->bitmap); \ + bpf_iter_bits_destroy(&it->it); \ +} +#define def_for_each_cpu(cpu, name) for_each_##name##_cpu(cpu) + +/// Provides iterator for possible and online cpus. +/// +/// # Example +/// +/// ``` +/// static inline void example_use() { +/// int *cpu; +/// +/// for_each_possible_cpu(cpu){ +/// bpf_printk("CPU %d is possible", *cpu); +/// } +/// +/// for_each_online_cpu(cpu){ +/// bpf_printk("CPU %d is online", *cpu); +/// } +/// } +/// ``` +def_iter_struct(possible); +def_iter_new(possible); +def_iter_next(possible); +def_iter_destroy(possible); +#define for_each_possible_cpu(cpu) bpf_for_each(possible, cpu, NULL, 0) + +def_iter_struct(online); +def_iter_new(online); +def_iter_next(online); +def_iter_destroy(online); +#define for_each_online_cpu(cpu) bpf_for_each(online, cpu, NULL, 0) + +/* + * Access a cpumask in read-only mode (typically to check bits). + */ +static __always_inline const struct cpumask *cast_mask(struct bpf_cpumask *mask) +{ + return (const struct cpumask *)mask; +} + +/* + * Return true if task @p cannot migrate to a different CPU, false + * otherwise. + */ +static inline bool is_migration_disabled(const struct task_struct *p) +{ + if (bpf_core_field_exists(p->migration_disabled)) + return p->migration_disabled; + return false; +} + +/* rcu */ +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +/* + * Time helpers, most of which are from jiffies.h. + */ + +/** + * time_delta - Calculate the delta between new and old time stamp + * @after: first comparable as u64 + * @before: second comparable as u64 + * + * Return: the time difference, which is >= 0 + */ +static inline s64 time_delta(u64 after, u64 before) +{ + return (s64)(after - before) > 0 ? (s64)(after - before) : 0; +} + +/** + * time_after - returns true if the time a is after time b. + * @a: first comparable as u64 + * @b: second comparable as u64 + * + * Do this with "<0" and ">=0" to only test the sign of the result. A + * good compiler would generate better code (and a really good compiler + * wouldn't care). Gcc is currently neither. + * + * Return: %true is time a is after time b, otherwise %false. + */ +static inline bool time_after(u64 a, u64 b) +{ + return (s64)(b - a) < 0; +} + +/** + * time_before - returns true if the time a is before time b. + * @a: first comparable as u64 + * @b: second comparable as u64 + * + * Return: %true is time a is before time b, otherwise %false. + */ +static inline bool time_before(u64 a, u64 b) +{ + return time_after(b, a); +} + +/** + * time_after_eq - returns true if the time a is after or the same as time b. + * @a: first comparable as u64 + * @b: second comparable as u64 + * + * Return: %true is time a is after or the same as time b, otherwise %false. + */ +static inline bool time_after_eq(u64 a, u64 b) +{ + return (s64)(a - b) >= 0; +} + +/** + * time_before_eq - returns true if the time a is before or the same as time b. + * @a: first comparable as u64 + * @b: second comparable as u64 + * + * Return: %true is time a is before or the same as time b, otherwise %false. + */ +static inline bool time_before_eq(u64 a, u64 b) +{ + return time_after_eq(b, a); +} + +/** + * time_in_range - Calculate whether a is in the range of [b, c]. + * @a: time to test + * @b: beginning of the range + * @c: end of the range + * + * Return: %true is time a is in the range [b, c], otherwise %false. + */ +static inline bool time_in_range(u64 a, u64 b, u64 c) +{ + return time_after_eq(a, b) && time_before_eq(a, c); +} + +/** + * time_in_range_open - Calculate whether a is in the range of [b, c). + * @a: time to test + * @b: beginning of the range + * @c: end of the range + * + * Return: %true is time a is in the range [b, c), otherwise %false. + */ +static inline bool time_in_range_open(u64 a, u64 b, u64 c) +{ + return time_after_eq(a, b) && time_before(a, c); +} + + +/* + * Other helpers + */ + +/* useful compiler attributes */ +#define likely(x) __builtin_expect(!!(x), 1) +#define unlikely(x) __builtin_expect(!!(x), 0) +#define __maybe_unused __attribute__((__unused__)) + +/* + * READ/WRITE_ONCE() are from kernel (include/asm-generic/rwonce.h). They + * prevent compiler from caching, redoing or reordering reads or writes. + */ +typedef __u8 __attribute__((__may_alias__)) __u8_alias_t; +typedef __u16 __attribute__((__may_alias__)) __u16_alias_t; +typedef __u32 __attribute__((__may_alias__)) __u32_alias_t; +typedef __u64 __attribute__((__may_alias__)) __u64_alias_t; + +static __always_inline void __read_once_size(const volatile void *p, void *res, int size) +{ + switch (size) { + case 1: *(__u8_alias_t *) res = *(volatile __u8_alias_t *) p; break; + case 2: *(__u16_alias_t *) res = *(volatile __u16_alias_t *) p; break; + case 4: *(__u32_alias_t *) res = *(volatile __u32_alias_t *) p; break; + case 8: *(__u64_alias_t *) res = *(volatile __u64_alias_t *) p; break; + default: + barrier(); + __builtin_memcpy((void *)res, (const void *)p, size); + barrier(); + } +} + +static __always_inline void __write_once_size(volatile void *p, void *res, int size) +{ + switch (size) { + case 1: *(volatile __u8_alias_t *) p = *(__u8_alias_t *) res; break; + case 2: *(volatile __u16_alias_t *) p = *(__u16_alias_t *) res; break; + case 4: *(volatile __u32_alias_t *) p = *(__u32_alias_t *) res; break; + case 8: *(volatile __u64_alias_t *) p = *(__u64_alias_t *) res; break; + default: + barrier(); + __builtin_memcpy((void *)p, (const void *)res, size); + barrier(); + } +} + +/* + * __unqual_typeof(x) - Declare an unqualified scalar type, leaving + * non-scalar types unchanged, + * + * Prefer C11 _Generic for better compile-times and simpler code. Note: 'char' + * is not type-compatible with 'signed char', and we define a separate case. + * + * This is copied verbatim from kernel's include/linux/compiler_types.h, but + * with default expression (for pointers) changed from (x) to (typeof(x)0). + * + * This is because LLVM has a bug where for lvalue (x), it does not get rid of + * an extra address_space qualifier, but does in case of rvalue (typeof(x)0). + * Hence, for pointers, we need to create an rvalue expression to get the + * desired type. See https://github.com/llvm/llvm-project/issues/53400. + */ +#define __scalar_type_to_expr_cases(type) \ + unsigned type : (unsigned type)0, signed type : (signed type)0 + +#define __unqual_typeof(x) \ + typeof(_Generic((x), \ + char: (char)0, \ + __scalar_type_to_expr_cases(char), \ + __scalar_type_to_expr_cases(short), \ + __scalar_type_to_expr_cases(int), \ + __scalar_type_to_expr_cases(long), \ + __scalar_type_to_expr_cases(long long), \ + default: (typeof(x))0)) + +#define READ_ONCE(x) \ +({ \ + union { __unqual_typeof(x) __val; char __c[1]; } __u = \ + { .__c = { 0 } }; \ + __read_once_size((__unqual_typeof(x) *)&(x), __u.__c, sizeof(x)); \ + __u.__val; \ +}) + +#define WRITE_ONCE(x, val) \ +({ \ + union { __unqual_typeof(x) __val; char __c[1]; } __u = \ + { .__val = (val) }; \ + __write_once_size((__unqual_typeof(x) *)&(x), __u.__c, sizeof(x)); \ + __u.__val; \ +}) + +/* + * log2_u32 - Compute the base 2 logarithm of a 32-bit exponential value. + * @v: The value for which we're computing the base 2 logarithm. + */ +static inline u32 log2_u32(u32 v) +{ + u32 r; + u32 shift; + + r = (v > 0xFFFF) << 4; v >>= r; + shift = (v > 0xFF) << 3; v >>= shift; r |= shift; + shift = (v > 0xF) << 2; v >>= shift; r |= shift; + shift = (v > 0x3) << 1; v >>= shift; r |= shift; + r |= (v >> 1); + return r; +} + +/* + * log2_u64 - Compute the base 2 logarithm of a 64-bit exponential value. + * @v: The value for which we're computing the base 2 logarithm. + */ +static inline u32 log2_u64(u64 v) +{ + u32 hi = v >> 32; + if (hi) + return log2_u32(hi) + 32 + 1; + else + return log2_u32(v) + 1; +} + +/* + * Return a value proportionally scaled to the task's weight. + */ +static inline u64 scale_by_task_weight(const struct task_struct *p, u64 value) +{ + return (value * p->scx.weight) / 100; +} + +/* + * Return a value inversely proportional to the task's weight. + */ +static inline u64 scale_by_task_weight_inverse(const struct task_struct *p, u64 value) +{ + return value * 100 / p->scx.weight; +} + + +#include "compat.bpf.h" +#include "enums.bpf.h" + +#endif /* __SCX_COMMON_BPF_H */ diff --git a/tools/sched_ext/include/scx/common.h b/tools/sched_ext/include/scx/common.h new file mode 100644 index 000000000000..1dc76bd84296 --- /dev/null +++ b/tools/sched_ext/include/scx/common.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 Tejun Heo <tj@kernel.org> + * Copyright (c) 2023 David Vernet <dvernet@meta.com> + */ +#ifndef __SCHED_EXT_COMMON_H +#define __SCHED_EXT_COMMON_H + +#ifdef __KERNEL__ +#error "Should not be included by BPF programs" +#endif + +#include <stdarg.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdint.h> +#include <errno.h> +#include "enum_defs.autogen.h" + +typedef uint8_t u8; +typedef uint16_t u16; +typedef uint32_t u32; +typedef uint64_t u64; +typedef int8_t s8; +typedef int16_t s16; +typedef int32_t s32; +typedef int64_t s64; + +#define SCX_BUG(__fmt, ...) \ + do { \ + fprintf(stderr, "[SCX_BUG] %s:%d", __FILE__, __LINE__); \ + if (errno) \ + fprintf(stderr, " (%s)\n", strerror(errno)); \ + else \ + fprintf(stderr, "\n"); \ + fprintf(stderr, __fmt __VA_OPT__(,) __VA_ARGS__); \ + fprintf(stderr, "\n"); \ + \ + exit(EXIT_FAILURE); \ + } while (0) + +#define SCX_BUG_ON(__cond, __fmt, ...) \ + do { \ + if (__cond) \ + SCX_BUG((__fmt) __VA_OPT__(,) __VA_ARGS__); \ + } while (0) + +/** + * RESIZE_ARRAY - Convenience macro for resizing a BPF array + * @__skel: the skeleton containing the array + * @elfsec: the data section of the BPF program in which the array exists + * @arr: the name of the array + * @n: the desired array element count + * + * For BPF arrays declared with RESIZABLE_ARRAY(), this macro performs two + * operations. It resizes the map which corresponds to the custom data + * section that contains the target array. As a side effect, the BTF info for + * the array is adjusted so that the array length is sized to cover the new + * data section size. The second operation is reassigning the skeleton pointer + * for that custom data section so that it points to the newly memory mapped + * region. + */ +#define RESIZE_ARRAY(__skel, elfsec, arr, n) \ + do { \ + size_t __sz; \ + bpf_map__set_value_size((__skel)->maps.elfsec##_##arr, \ + sizeof((__skel)->elfsec##_##arr->arr[0]) * (n)); \ + (__skel)->elfsec##_##arr = \ + bpf_map__initial_value((__skel)->maps.elfsec##_##arr, &__sz); \ + } while (0) + +#include "user_exit_info.h" +#include "compat.h" +#include "enums.h" + +/* not available when building kernel tools/sched_ext */ +#if __has_include(<lib/sdt_task.h>) +#include <lib/sdt_task.h> +#endif + +#endif /* __SCHED_EXT_COMMON_H */ diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h new file mode 100644 index 000000000000..9252e1a00556 --- /dev/null +++ b/tools/sched_ext/include/scx/compat.bpf.h @@ -0,0 +1,238 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 Tejun Heo <tj@kernel.org> + * Copyright (c) 2024 David Vernet <dvernet@meta.com> + */ +#ifndef __SCX_COMPAT_BPF_H +#define __SCX_COMPAT_BPF_H + +#define __COMPAT_ENUM_OR_ZERO(__type, __ent) \ +({ \ + __type __ret = 0; \ + if (bpf_core_enum_value_exists(__type, __ent)) \ + __ret = __ent; \ + __ret; \ +}) + +/* v6.12: 819513666966 ("sched_ext: Add cgroup support") */ +#define __COMPAT_scx_bpf_task_cgroup(p) \ + (bpf_ksym_exists(scx_bpf_task_cgroup) ? \ + scx_bpf_task_cgroup((p)) : NULL) + +/* + * v6.13: The verb `dispatch` was too overloaded and confusing. kfuncs are + * renamed to unload the verb. + * + * Build error is triggered if old names are used. New binaries work with both + * new and old names. The compat macros will be removed on v6.15 release. + * + * scx_bpf_dispatch_from_dsq() and friends were added during v6.12 by + * 4c30f5ce4f7a ("sched_ext: Implement scx_bpf_dispatch[_vtime]_from_dsq()"). + * Preserve __COMPAT macros until v6.15. + */ +void scx_bpf_dispatch___compat(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_flags) __ksym __weak; +void scx_bpf_dispatch_vtime___compat(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym __weak; +bool scx_bpf_consume___compat(u64 dsq_id) __ksym __weak; +void scx_bpf_dispatch_from_dsq_set_slice___compat(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym __weak; +void scx_bpf_dispatch_from_dsq_set_vtime___compat(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym __weak; +bool scx_bpf_dispatch_from_dsq___compat(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak; +bool scx_bpf_dispatch_vtime_from_dsq___compat(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak; + +#define scx_bpf_dsq_insert(p, dsq_id, slice, enq_flags) \ + (bpf_ksym_exists(scx_bpf_dsq_insert) ? \ + scx_bpf_dsq_insert((p), (dsq_id), (slice), (enq_flags)) : \ + scx_bpf_dispatch___compat((p), (dsq_id), (slice), (enq_flags))) + +#define scx_bpf_dsq_insert_vtime(p, dsq_id, slice, vtime, enq_flags) \ + (bpf_ksym_exists(scx_bpf_dsq_insert_vtime) ? \ + scx_bpf_dsq_insert_vtime((p), (dsq_id), (slice), (vtime), (enq_flags)) : \ + scx_bpf_dispatch_vtime___compat((p), (dsq_id), (slice), (vtime), (enq_flags))) + +#define scx_bpf_dsq_move_to_local(dsq_id) \ + (bpf_ksym_exists(scx_bpf_dsq_move_to_local) ? \ + scx_bpf_dsq_move_to_local((dsq_id)) : \ + scx_bpf_consume___compat((dsq_id))) + +#define __COMPAT_scx_bpf_dsq_move_set_slice(it__iter, slice) \ + (bpf_ksym_exists(scx_bpf_dsq_move_set_slice) ? \ + scx_bpf_dsq_move_set_slice((it__iter), (slice)) : \ + (bpf_ksym_exists(scx_bpf_dispatch_from_dsq_set_slice___compat) ? \ + scx_bpf_dispatch_from_dsq_set_slice___compat((it__iter), (slice)) : \ + (void)0)) + +#define __COMPAT_scx_bpf_dsq_move_set_vtime(it__iter, vtime) \ + (bpf_ksym_exists(scx_bpf_dsq_move_set_vtime) ? \ + scx_bpf_dsq_move_set_vtime((it__iter), (vtime)) : \ + (bpf_ksym_exists(scx_bpf_dispatch_from_dsq_set_vtime___compat) ? \ + scx_bpf_dispatch_from_dsq_set_vtime___compat((it__iter), (vtime)) : \ + (void) 0)) + +#define __COMPAT_scx_bpf_dsq_move(it__iter, p, dsq_id, enq_flags) \ + (bpf_ksym_exists(scx_bpf_dsq_move) ? \ + scx_bpf_dsq_move((it__iter), (p), (dsq_id), (enq_flags)) : \ + (bpf_ksym_exists(scx_bpf_dispatch_from_dsq___compat) ? \ + scx_bpf_dispatch_from_dsq___compat((it__iter), (p), (dsq_id), (enq_flags)) : \ + false)) + +#define __COMPAT_scx_bpf_dsq_move_vtime(it__iter, p, dsq_id, enq_flags) \ + (bpf_ksym_exists(scx_bpf_dsq_move_vtime) ? \ + scx_bpf_dsq_move_vtime((it__iter), (p), (dsq_id), (enq_flags)) : \ + (bpf_ksym_exists(scx_bpf_dispatch_vtime_from_dsq___compat) ? \ + scx_bpf_dispatch_vtime_from_dsq___compat((it__iter), (p), (dsq_id), (enq_flags)) : \ + false)) + +#define scx_bpf_dispatch(p, dsq_id, slice, enq_flags) \ + _Static_assert(false, "scx_bpf_dispatch() renamed to scx_bpf_dsq_insert()") + +#define scx_bpf_dispatch_vtime(p, dsq_id, slice, vtime, enq_flags) \ + _Static_assert(false, "scx_bpf_dispatch_vtime() renamed to scx_bpf_dsq_insert_vtime()") + +#define scx_bpf_consume(dsq_id) ({ \ + _Static_assert(false, "scx_bpf_consume() renamed to scx_bpf_dsq_move_to_local()"); \ + false; \ +}) + +#define scx_bpf_dispatch_from_dsq_set_slice(it__iter, slice) \ + _Static_assert(false, "scx_bpf_dispatch_from_dsq_set_slice() renamed to scx_bpf_dsq_move_set_slice()") + +#define scx_bpf_dispatch_from_dsq_set_vtime(it__iter, vtime) \ + _Static_assert(false, "scx_bpf_dispatch_from_dsq_set_vtime() renamed to scx_bpf_dsq_move_set_vtime()") + +#define scx_bpf_dispatch_from_dsq(it__iter, p, dsq_id, enq_flags) ({ \ + _Static_assert(false, "scx_bpf_dispatch_from_dsq() renamed to scx_bpf_dsq_move()"); \ + false; \ +}) + +#define scx_bpf_dispatch_vtime_from_dsq(it__iter, p, dsq_id, enq_flags) ({ \ + _Static_assert(false, "scx_bpf_dispatch_vtime_from_dsq() renamed to scx_bpf_dsq_move_vtime()"); \ + false; \ +}) + +#define __COMPAT_scx_bpf_dispatch_from_dsq_set_slice(it__iter, slice) \ + _Static_assert(false, "__COMPAT_scx_bpf_dispatch_from_dsq_set_slice() renamed to __COMPAT_scx_bpf_dsq_move_set_slice()") + +#define __COMPAT_scx_bpf_dispatch_from_dsq_set_vtime(it__iter, vtime) \ + _Static_assert(false, "__COMPAT_scx_bpf_dispatch_from_dsq_set_vtime() renamed to __COMPAT_scx_bpf_dsq_move_set_vtime()") + +#define __COMPAT_scx_bpf_dispatch_from_dsq(it__iter, p, dsq_id, enq_flags) ({ \ + _Static_assert(false, "__COMPAT_scx_bpf_dispatch_from_dsq() renamed to __COMPAT_scx_bpf_dsq_move()"); \ + false; \ +}) + +#define __COMPAT_scx_bpf_dispatch_vtime_from_dsq(it__iter, p, dsq_id, enq_flags) ({ \ + _Static_assert(false, "__COMPAT_scx_bpf_dispatch_vtime_from_dsq() renamed to __COMPAT_scx_bpf_dsq_move_vtime()"); \ + false; \ +}) + +/** + * __COMPAT_is_enq_cpu_selected - Test if SCX_ENQ_CPU_SELECTED is on + * in a compatible way. We will preserve this __COMPAT helper until v6.16. + * + * @enq_flags: enqueue flags from ops.enqueue() + * + * Return: True if SCX_ENQ_CPU_SELECTED is turned on in @enq_flags + */ +static inline bool __COMPAT_is_enq_cpu_selected(u64 enq_flags) +{ +#ifdef HAVE_SCX_ENQ_CPU_SELECTED + /* + * This is the case that a BPF code compiled against vmlinux.h + * where the enum SCX_ENQ_CPU_SELECTED exists. + */ + + /* + * We should temporarily suspend the macro expansion of + * 'SCX_ENQ_CPU_SELECTED'. This avoids 'SCX_ENQ_CPU_SELECTED' being + * rewritten to '__SCX_ENQ_CPU_SELECTED' when 'SCX_ENQ_CPU_SELECTED' + * is defined in 'scripts/gen_enums.py'. + */ +#pragma push_macro("SCX_ENQ_CPU_SELECTED") +#undef SCX_ENQ_CPU_SELECTED + u64 flag; + + /* + * When the kernel did not have SCX_ENQ_CPU_SELECTED, + * select_task_rq_scx() has never been skipped. Thus, this case + * should be considered that the CPU has already been selected. + */ + if (!bpf_core_enum_value_exists(enum scx_enq_flags, + SCX_ENQ_CPU_SELECTED)) + return true; + + flag = bpf_core_enum_value(enum scx_enq_flags, SCX_ENQ_CPU_SELECTED); + return enq_flags & flag; + + /* + * Once done, resume the macro expansion of 'SCX_ENQ_CPU_SELECTED'. + */ +#pragma pop_macro("SCX_ENQ_CPU_SELECTED") +#else + /* + * This is the case that a BPF code compiled against vmlinux.h + * where the enum SCX_ENQ_CPU_SELECTED does NOT exist. + */ + return true; +#endif /* HAVE_SCX_ENQ_CPU_SELECTED */ +} + + +#define scx_bpf_now() \ + (bpf_ksym_exists(scx_bpf_now) ? \ + scx_bpf_now() : \ + bpf_ktime_get_ns()) + +/* + * v6.15: Introduce event counters. + * + * Preserve the following macro until v6.17. + */ +#define __COMPAT_scx_bpf_events(events, size) \ + (bpf_ksym_exists(scx_bpf_events) ? \ + scx_bpf_events(events, size) : ({})) + +/* + * v6.15: Introduce NUMA-aware kfuncs to operate with per-node idle + * cpumasks. + * + * Preserve the following __COMPAT_scx_*_node macros until v6.17. + */ +#define __COMPAT_scx_bpf_nr_node_ids() \ + (bpf_ksym_exists(scx_bpf_nr_node_ids) ? \ + scx_bpf_nr_node_ids() : 1U) + +#define __COMPAT_scx_bpf_cpu_node(cpu) \ + (bpf_ksym_exists(scx_bpf_cpu_node) ? \ + scx_bpf_cpu_node(cpu) : 0) + +#define __COMPAT_scx_bpf_get_idle_cpumask_node(node) \ + (bpf_ksym_exists(scx_bpf_get_idle_cpumask_node) ? \ + scx_bpf_get_idle_cpumask_node(node) : \ + scx_bpf_get_idle_cpumask()) \ + +#define __COMPAT_scx_bpf_get_idle_smtmask_node(node) \ + (bpf_ksym_exists(scx_bpf_get_idle_smtmask_node) ? \ + scx_bpf_get_idle_smtmask_node(node) : \ + scx_bpf_get_idle_smtmask()) + +#define __COMPAT_scx_bpf_pick_idle_cpu_node(cpus_allowed, node, flags) \ + (bpf_ksym_exists(scx_bpf_pick_idle_cpu_node) ? \ + scx_bpf_pick_idle_cpu_node(cpus_allowed, node, flags) : \ + scx_bpf_pick_idle_cpu(cpus_allowed, flags)) + +#define __COMPAT_scx_bpf_pick_any_cpu_node(cpus_allowed, node, flags) \ + (bpf_ksym_exists(scx_bpf_pick_any_cpu_node) ? \ + scx_bpf_pick_any_cpu_node(cpus_allowed, node, flags) : \ + scx_bpf_pick_any_cpu(cpus_allowed, flags)) + +/* + * Define sched_ext_ops. This may be expanded to define multiple variants for + * backward compatibility. See compat.h::SCX_OPS_LOAD/ATTACH(). + */ +#define SCX_OPS_DEFINE(__name, ...) \ + SEC(".struct_ops.link") \ + struct sched_ext_ops __name = { \ + __VA_ARGS__, \ + }; + +#endif /* __SCX_COMPAT_BPF_H */ diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h new file mode 100644 index 000000000000..35c67c5174ac --- /dev/null +++ b/tools/sched_ext/include/scx/compat.h @@ -0,0 +1,199 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 Tejun Heo <tj@kernel.org> + * Copyright (c) 2024 David Vernet <dvernet@meta.com> + */ +#ifndef __SCX_COMPAT_H +#define __SCX_COMPAT_H + +#include <bpf/btf.h> +#include <fcntl.h> +#include <stdlib.h> +#include <unistd.h> + +struct btf *__COMPAT_vmlinux_btf __attribute__((weak)); + +static inline void __COMPAT_load_vmlinux_btf(void) +{ + if (!__COMPAT_vmlinux_btf) { + __COMPAT_vmlinux_btf = btf__load_vmlinux_btf(); + SCX_BUG_ON(!__COMPAT_vmlinux_btf, "btf__load_vmlinux_btf()"); + } +} + +static inline bool __COMPAT_read_enum(const char *type, const char *name, u64 *v) +{ + const struct btf_type *t; + const char *n; + s32 tid; + int i; + + __COMPAT_load_vmlinux_btf(); + + tid = btf__find_by_name(__COMPAT_vmlinux_btf, type); + if (tid < 0) + return false; + + t = btf__type_by_id(__COMPAT_vmlinux_btf, tid); + SCX_BUG_ON(!t, "btf__type_by_id(%d)", tid); + + if (btf_is_enum(t)) { + struct btf_enum *e = btf_enum(t); + + for (i = 0; i < BTF_INFO_VLEN(t->info); i++) { + n = btf__name_by_offset(__COMPAT_vmlinux_btf, e[i].name_off); + SCX_BUG_ON(!n, "btf__name_by_offset()"); + if (!strcmp(n, name)) { + *v = e[i].val; + return true; + } + } + } else if (btf_is_enum64(t)) { + struct btf_enum64 *e = btf_enum64(t); + + for (i = 0; i < BTF_INFO_VLEN(t->info); i++) { + n = btf__name_by_offset(__COMPAT_vmlinux_btf, e[i].name_off); + SCX_BUG_ON(!n, "btf__name_by_offset()"); + if (!strcmp(n, name)) { + *v = btf_enum64_value(&e[i]); + return true; + } + } + } + + return false; +} + +#define __COMPAT_ENUM_OR_ZERO(__type, __ent) \ +({ \ + u64 __val = 0; \ + __COMPAT_read_enum(__type, __ent, &__val); \ + __val; \ +}) + +static inline bool __COMPAT_has_ksym(const char *ksym) +{ + __COMPAT_load_vmlinux_btf(); + return btf__find_by_name(__COMPAT_vmlinux_btf, ksym) >= 0; +} + +static inline bool __COMPAT_struct_has_field(const char *type, const char *field) +{ + const struct btf_type *t; + const struct btf_member *m; + const char *n; + s32 tid; + int i; + + __COMPAT_load_vmlinux_btf(); + tid = btf__find_by_name_kind(__COMPAT_vmlinux_btf, type, BTF_KIND_STRUCT); + if (tid < 0) + return false; + + t = btf__type_by_id(__COMPAT_vmlinux_btf, tid); + SCX_BUG_ON(!t, "btf__type_by_id(%d)", tid); + + m = btf_members(t); + + for (i = 0; i < BTF_INFO_VLEN(t->info); i++) { + n = btf__name_by_offset(__COMPAT_vmlinux_btf, m[i].name_off); + SCX_BUG_ON(!n, "btf__name_by_offset()"); + if (!strcmp(n, field)) + return true; + } + + return false; +} + +#define SCX_OPS_FLAG(name) __COMPAT_ENUM_OR_ZERO("scx_ops_flags", #name) + +#define SCX_OPS_KEEP_BUILTIN_IDLE SCX_OPS_FLAG(SCX_OPS_KEEP_BUILTIN_IDLE) +#define SCX_OPS_ENQ_LAST SCX_OPS_FLAG(SCX_OPS_ENQ_LAST) +#define SCX_OPS_ENQ_EXITING SCX_OPS_FLAG(SCX_OPS_ENQ_EXITING) +#define SCX_OPS_SWITCH_PARTIAL SCX_OPS_FLAG(SCX_OPS_SWITCH_PARTIAL) +#define SCX_OPS_ENQ_MIGRATION_DISABLED SCX_OPS_FLAG(SCX_OPS_ENQ_MIGRATION_DISABLED) +#define SCX_OPS_ALLOW_QUEUED_WAKEUP SCX_OPS_FLAG(SCX_OPS_ALLOW_QUEUED_WAKEUP) +#define SCX_OPS_BUILTIN_IDLE_PER_NODE SCX_OPS_FLAG(SCX_OPS_BUILTIN_IDLE_PER_NODE) + +#define SCX_PICK_IDLE_FLAG(name) __COMPAT_ENUM_OR_ZERO("scx_pick_idle_cpu_flags", #name) + +#define SCX_PICK_IDLE_CORE SCX_PICK_IDLE_FLAG(SCX_PICK_IDLE_CORE) +#define SCX_PICK_IDLE_IN_NODE SCX_PICK_IDLE_FLAG(SCX_PICK_IDLE_IN_NODE) + +static inline long scx_hotplug_seq(void) +{ + int fd; + char buf[32]; + ssize_t len; + long val; + + fd = open("/sys/kernel/sched_ext/hotplug_seq", O_RDONLY); + if (fd < 0) + return -ENOENT; + + len = read(fd, buf, sizeof(buf) - 1); + SCX_BUG_ON(len <= 0, "read failed (%ld)", len); + buf[len] = 0; + close(fd); + + val = strtoul(buf, NULL, 10); + SCX_BUG_ON(val < 0, "invalid num hotplug events: %lu", val); + + return val; +} + +/* + * struct sched_ext_ops can change over time. If compat.bpf.h::SCX_OPS_DEFINE() + * is used to define ops and compat.h::SCX_OPS_LOAD/ATTACH() are used to load + * and attach it, backward compatibility is automatically maintained where + * reasonable. + * + * ec7e3b0463e1 ("implement-ops") in https://github.com/sched-ext/sched_ext is + * the current minimum required kernel version. + */ +#define SCX_OPS_OPEN(__ops_name, __scx_name) ({ \ + struct __scx_name *__skel; \ + \ + SCX_BUG_ON(!__COMPAT_struct_has_field("sched_ext_ops", "dump"), \ + "sched_ext_ops.dump() missing, kernel too old?"); \ + \ + __skel = __scx_name##__open(); \ + SCX_BUG_ON(!__skel, "Could not open " #__scx_name); \ + __skel->struct_ops.__ops_name->hotplug_seq = scx_hotplug_seq(); \ + SCX_ENUM_INIT(__skel); \ + __skel; \ +}) + +#define SCX_OPS_LOAD(__skel, __ops_name, __scx_name, __uei_name) ({ \ + UEI_SET_SIZE(__skel, __ops_name, __uei_name); \ + SCX_BUG_ON(__scx_name##__load((__skel)), "Failed to load skel"); \ +}) + +/* + * New versions of bpftool now emit additional link placeholders for BPF maps, + * and set up BPF skeleton in such a way that libbpf will auto-attach BPF maps + * automatically, assumming libbpf is recent enough (v1.5+). Old libbpf will do + * nothing with those links and won't attempt to auto-attach maps. + * + * To maintain compatibility with older libbpf while avoiding trying to attach + * twice, disable the autoattach feature on newer libbpf. + */ +#if LIBBPF_MAJOR_VERSION > 1 || \ + (LIBBPF_MAJOR_VERSION == 1 && LIBBPF_MINOR_VERSION >= 5) +#define __SCX_OPS_DISABLE_AUTOATTACH(__skel, __ops_name) \ + bpf_map__set_autoattach((__skel)->maps.__ops_name, false) +#else +#define __SCX_OPS_DISABLE_AUTOATTACH(__skel, __ops_name) do {} while (0) +#endif + +#define SCX_OPS_ATTACH(__skel, __ops_name, __scx_name) ({ \ + struct bpf_link *__link; \ + __SCX_OPS_DISABLE_AUTOATTACH(__skel, __ops_name); \ + SCX_BUG_ON(__scx_name##__attach((__skel)), "Failed to attach skel"); \ + __link = bpf_map__attach_struct_ops((__skel)->maps.__ops_name); \ + SCX_BUG_ON(!__link, "Failed to attach struct_ops"); \ + __link; \ +}) + +#endif /* __SCX_COMPAT_H */ diff --git a/tools/sched_ext/include/scx/enum_defs.autogen.h b/tools/sched_ext/include/scx/enum_defs.autogen.h new file mode 100644 index 000000000000..c2c33df9292c --- /dev/null +++ b/tools/sched_ext/include/scx/enum_defs.autogen.h @@ -0,0 +1,123 @@ +/* + * WARNING: This file is autogenerated from gen_enum_defs.py [1]. + * + * [1] https://github.com/sched-ext/scx/blob/main/scripts/gen_enum_defs.py + */ + +#ifndef __ENUM_DEFS_AUTOGEN_H__ +#define __ENUM_DEFS_AUTOGEN_H__ + +#define HAVE_SCX_DSP_DFL_MAX_BATCH +#define HAVE_SCX_DSP_MAX_LOOPS +#define HAVE_SCX_WATCHDOG_MAX_TIMEOUT +#define HAVE_SCX_EXIT_BT_LEN +#define HAVE_SCX_EXIT_MSG_LEN +#define HAVE_SCX_EXIT_DUMP_DFL_LEN +#define HAVE_SCX_CPUPERF_ONE +#define HAVE_SCX_OPS_TASK_ITER_BATCH +#define HAVE_SCX_CPU_PREEMPT_RT +#define HAVE_SCX_CPU_PREEMPT_DL +#define HAVE_SCX_CPU_PREEMPT_STOP +#define HAVE_SCX_CPU_PREEMPT_UNKNOWN +#define HAVE_SCX_DEQ_SLEEP +#define HAVE_SCX_DEQ_CORE_SCHED_EXEC +#define HAVE_SCX_DSQ_FLAG_BUILTIN +#define HAVE_SCX_DSQ_FLAG_LOCAL_ON +#define HAVE_SCX_DSQ_INVALID +#define HAVE_SCX_DSQ_GLOBAL +#define HAVE_SCX_DSQ_LOCAL +#define HAVE_SCX_DSQ_LOCAL_ON +#define HAVE_SCX_DSQ_LOCAL_CPU_MASK +#define HAVE_SCX_DSQ_ITER_REV +#define HAVE___SCX_DSQ_ITER_HAS_SLICE +#define HAVE___SCX_DSQ_ITER_HAS_VTIME +#define HAVE___SCX_DSQ_ITER_USER_FLAGS +#define HAVE___SCX_DSQ_ITER_ALL_FLAGS +#define HAVE_SCX_DSQ_LNODE_ITER_CURSOR +#define HAVE___SCX_DSQ_LNODE_PRIV_SHIFT +#define HAVE_SCX_ENQ_WAKEUP +#define HAVE_SCX_ENQ_HEAD +#define HAVE_SCX_ENQ_CPU_SELECTED +#define HAVE_SCX_ENQ_PREEMPT +#define HAVE_SCX_ENQ_REENQ +#define HAVE_SCX_ENQ_LAST +#define HAVE___SCX_ENQ_INTERNAL_MASK +#define HAVE_SCX_ENQ_CLEAR_OPSS +#define HAVE_SCX_ENQ_DSQ_PRIQ +#define HAVE_SCX_TASK_DSQ_ON_PRIQ +#define HAVE_SCX_TASK_QUEUED +#define HAVE_SCX_TASK_RESET_RUNNABLE_AT +#define HAVE_SCX_TASK_DEQD_FOR_SLEEP +#define HAVE_SCX_TASK_STATE_SHIFT +#define HAVE_SCX_TASK_STATE_BITS +#define HAVE_SCX_TASK_STATE_MASK +#define HAVE_SCX_TASK_CURSOR +#define HAVE_SCX_ECODE_RSN_HOTPLUG +#define HAVE_SCX_ECODE_ACT_RESTART +#define HAVE_SCX_EXIT_NONE +#define HAVE_SCX_EXIT_DONE +#define HAVE_SCX_EXIT_UNREG +#define HAVE_SCX_EXIT_UNREG_BPF +#define HAVE_SCX_EXIT_UNREG_KERN +#define HAVE_SCX_EXIT_SYSRQ +#define HAVE_SCX_EXIT_ERROR +#define HAVE_SCX_EXIT_ERROR_BPF +#define HAVE_SCX_EXIT_ERROR_STALL +#define HAVE_SCX_KF_UNLOCKED +#define HAVE_SCX_KF_CPU_RELEASE +#define HAVE_SCX_KF_DISPATCH +#define HAVE_SCX_KF_ENQUEUE +#define HAVE_SCX_KF_SELECT_CPU +#define HAVE_SCX_KF_REST +#define HAVE___SCX_KF_RQ_LOCKED +#define HAVE___SCX_KF_TERMINAL +#define HAVE_SCX_KICK_IDLE +#define HAVE_SCX_KICK_PREEMPT +#define HAVE_SCX_KICK_WAIT +#define HAVE_SCX_OPI_BEGIN +#define HAVE_SCX_OPI_NORMAL_BEGIN +#define HAVE_SCX_OPI_NORMAL_END +#define HAVE_SCX_OPI_CPU_HOTPLUG_BEGIN +#define HAVE_SCX_OPI_CPU_HOTPLUG_END +#define HAVE_SCX_OPI_END +#define HAVE_SCX_OPS_ENABLING +#define HAVE_SCX_OPS_ENABLED +#define HAVE_SCX_OPS_DISABLING +#define HAVE_SCX_OPS_DISABLED +#define HAVE_SCX_OPS_KEEP_BUILTIN_IDLE +#define HAVE_SCX_OPS_ENQ_LAST +#define HAVE_SCX_OPS_ENQ_EXITING +#define HAVE_SCX_OPS_SWITCH_PARTIAL +#define HAVE_SCX_OPS_ENQ_MIGRATION_DISABLED +#define HAVE_SCX_OPS_ALLOW_QUEUED_WAKEUP +#define HAVE_SCX_OPS_HAS_CGROUP_WEIGHT +#define HAVE_SCX_OPS_ALL_FLAGS +#define HAVE_SCX_OPSS_NONE +#define HAVE_SCX_OPSS_QUEUEING +#define HAVE_SCX_OPSS_QUEUED +#define HAVE_SCX_OPSS_DISPATCHING +#define HAVE_SCX_OPSS_QSEQ_SHIFT +#define HAVE_SCX_PICK_IDLE_CORE +#define HAVE_SCX_OPS_NAME_LEN +#define HAVE_SCX_SLICE_DFL +#define HAVE_SCX_SLICE_INF +#define HAVE_SCX_RQ_ONLINE +#define HAVE_SCX_RQ_CAN_STOP_TICK +#define HAVE_SCX_RQ_BAL_PENDING +#define HAVE_SCX_RQ_BAL_KEEP +#define HAVE_SCX_RQ_BYPASSING +#define HAVE_SCX_RQ_CLK_VALID +#define HAVE_SCX_RQ_IN_WAKEUP +#define HAVE_SCX_RQ_IN_BALANCE +#define HAVE_SCX_TASK_NONE +#define HAVE_SCX_TASK_INIT +#define HAVE_SCX_TASK_READY +#define HAVE_SCX_TASK_ENABLED +#define HAVE_SCX_TASK_NR_STATES +#define HAVE_SCX_TG_ONLINE +#define HAVE_SCX_TG_INITED +#define HAVE_SCX_WAKE_FORK +#define HAVE_SCX_WAKE_TTWU +#define HAVE_SCX_WAKE_SYNC + +#endif /* __ENUM_DEFS_AUTOGEN_H__ */ diff --git a/tools/sched_ext/include/scx/enums.autogen.bpf.h b/tools/sched_ext/include/scx/enums.autogen.bpf.h new file mode 100644 index 000000000000..2f8002bcc19a --- /dev/null +++ b/tools/sched_ext/include/scx/enums.autogen.bpf.h @@ -0,0 +1,129 @@ +/* + * WARNING: This file is autogenerated from scripts/gen_enums.py. If you would + * like to access an enum that is currently missing, add it to the script + * and run it from the root directory to update this file. + */ + +const volatile u64 __SCX_OPS_NAME_LEN __weak; +#define SCX_OPS_NAME_LEN __SCX_OPS_NAME_LEN + +const volatile u64 __SCX_SLICE_DFL __weak; +#define SCX_SLICE_DFL __SCX_SLICE_DFL + +const volatile u64 __SCX_SLICE_INF __weak; +#define SCX_SLICE_INF __SCX_SLICE_INF + +const volatile u64 __SCX_RQ_ONLINE __weak; +#define SCX_RQ_ONLINE __SCX_RQ_ONLINE + +const volatile u64 __SCX_RQ_CAN_STOP_TICK __weak; +#define SCX_RQ_CAN_STOP_TICK __SCX_RQ_CAN_STOP_TICK + +const volatile u64 __SCX_RQ_BAL_PENDING __weak; +#define SCX_RQ_BAL_PENDING __SCX_RQ_BAL_PENDING + +const volatile u64 __SCX_RQ_BAL_KEEP __weak; +#define SCX_RQ_BAL_KEEP __SCX_RQ_BAL_KEEP + +const volatile u64 __SCX_RQ_BYPASSING __weak; +#define SCX_RQ_BYPASSING __SCX_RQ_BYPASSING + +const volatile u64 __SCX_RQ_CLK_VALID __weak; +#define SCX_RQ_CLK_VALID __SCX_RQ_CLK_VALID + +const volatile u64 __SCX_RQ_IN_WAKEUP __weak; +#define SCX_RQ_IN_WAKEUP __SCX_RQ_IN_WAKEUP + +const volatile u64 __SCX_RQ_IN_BALANCE __weak; +#define SCX_RQ_IN_BALANCE __SCX_RQ_IN_BALANCE + +const volatile u64 __SCX_DSQ_FLAG_BUILTIN __weak; +#define SCX_DSQ_FLAG_BUILTIN __SCX_DSQ_FLAG_BUILTIN + +const volatile u64 __SCX_DSQ_FLAG_LOCAL_ON __weak; +#define SCX_DSQ_FLAG_LOCAL_ON __SCX_DSQ_FLAG_LOCAL_ON + +const volatile u64 __SCX_DSQ_INVALID __weak; +#define SCX_DSQ_INVALID __SCX_DSQ_INVALID + +const volatile u64 __SCX_DSQ_GLOBAL __weak; +#define SCX_DSQ_GLOBAL __SCX_DSQ_GLOBAL + +const volatile u64 __SCX_DSQ_LOCAL __weak; +#define SCX_DSQ_LOCAL __SCX_DSQ_LOCAL + +const volatile u64 __SCX_DSQ_LOCAL_ON __weak; +#define SCX_DSQ_LOCAL_ON __SCX_DSQ_LOCAL_ON + +const volatile u64 __SCX_DSQ_LOCAL_CPU_MASK __weak; +#define SCX_DSQ_LOCAL_CPU_MASK __SCX_DSQ_LOCAL_CPU_MASK + +const volatile u64 __SCX_TASK_QUEUED __weak; +#define SCX_TASK_QUEUED __SCX_TASK_QUEUED + +const volatile u64 __SCX_TASK_RESET_RUNNABLE_AT __weak; +#define SCX_TASK_RESET_RUNNABLE_AT __SCX_TASK_RESET_RUNNABLE_AT + +const volatile u64 __SCX_TASK_DEQD_FOR_SLEEP __weak; +#define SCX_TASK_DEQD_FOR_SLEEP __SCX_TASK_DEQD_FOR_SLEEP + +const volatile u64 __SCX_TASK_STATE_SHIFT __weak; +#define SCX_TASK_STATE_SHIFT __SCX_TASK_STATE_SHIFT + +const volatile u64 __SCX_TASK_STATE_BITS __weak; +#define SCX_TASK_STATE_BITS __SCX_TASK_STATE_BITS + +const volatile u64 __SCX_TASK_STATE_MASK __weak; +#define SCX_TASK_STATE_MASK __SCX_TASK_STATE_MASK + +const volatile u64 __SCX_TASK_CURSOR __weak; +#define SCX_TASK_CURSOR __SCX_TASK_CURSOR + +const volatile u64 __SCX_TASK_NONE __weak; +#define SCX_TASK_NONE __SCX_TASK_NONE + +const volatile u64 __SCX_TASK_INIT __weak; +#define SCX_TASK_INIT __SCX_TASK_INIT + +const volatile u64 __SCX_TASK_READY __weak; +#define SCX_TASK_READY __SCX_TASK_READY + +const volatile u64 __SCX_TASK_ENABLED __weak; +#define SCX_TASK_ENABLED __SCX_TASK_ENABLED + +const volatile u64 __SCX_TASK_NR_STATES __weak; +#define SCX_TASK_NR_STATES __SCX_TASK_NR_STATES + +const volatile u64 __SCX_TASK_DSQ_ON_PRIQ __weak; +#define SCX_TASK_DSQ_ON_PRIQ __SCX_TASK_DSQ_ON_PRIQ + +const volatile u64 __SCX_KICK_IDLE __weak; +#define SCX_KICK_IDLE __SCX_KICK_IDLE + +const volatile u64 __SCX_KICK_PREEMPT __weak; +#define SCX_KICK_PREEMPT __SCX_KICK_PREEMPT + +const volatile u64 __SCX_KICK_WAIT __weak; +#define SCX_KICK_WAIT __SCX_KICK_WAIT + +const volatile u64 __SCX_ENQ_WAKEUP __weak; +#define SCX_ENQ_WAKEUP __SCX_ENQ_WAKEUP + +const volatile u64 __SCX_ENQ_HEAD __weak; +#define SCX_ENQ_HEAD __SCX_ENQ_HEAD + +const volatile u64 __SCX_ENQ_PREEMPT __weak; +#define SCX_ENQ_PREEMPT __SCX_ENQ_PREEMPT + +const volatile u64 __SCX_ENQ_REENQ __weak; +#define SCX_ENQ_REENQ __SCX_ENQ_REENQ + +const volatile u64 __SCX_ENQ_LAST __weak; +#define SCX_ENQ_LAST __SCX_ENQ_LAST + +const volatile u64 __SCX_ENQ_CLEAR_OPSS __weak; +#define SCX_ENQ_CLEAR_OPSS __SCX_ENQ_CLEAR_OPSS + +const volatile u64 __SCX_ENQ_DSQ_PRIQ __weak; +#define SCX_ENQ_DSQ_PRIQ __SCX_ENQ_DSQ_PRIQ + diff --git a/tools/sched_ext/include/scx/enums.autogen.h b/tools/sched_ext/include/scx/enums.autogen.h new file mode 100644 index 000000000000..fedec938584b --- /dev/null +++ b/tools/sched_ext/include/scx/enums.autogen.h @@ -0,0 +1,49 @@ +/* + * WARNING: This file is autogenerated from scripts/gen_enums.py. If you would + * like to access an enum that is currently missing, add it to the script + * and run it from the root directory to update this file. + */ + +#define SCX_ENUM_INIT(skel) do { \ + SCX_ENUM_SET(skel, scx_public_consts, SCX_OPS_NAME_LEN); \ + SCX_ENUM_SET(skel, scx_public_consts, SCX_SLICE_DFL); \ + SCX_ENUM_SET(skel, scx_public_consts, SCX_SLICE_INF); \ + SCX_ENUM_SET(skel, scx_rq_flags, SCX_RQ_ONLINE); \ + SCX_ENUM_SET(skel, scx_rq_flags, SCX_RQ_CAN_STOP_TICK); \ + SCX_ENUM_SET(skel, scx_rq_flags, SCX_RQ_BAL_PENDING); \ + SCX_ENUM_SET(skel, scx_rq_flags, SCX_RQ_BAL_KEEP); \ + SCX_ENUM_SET(skel, scx_rq_flags, SCX_RQ_BYPASSING); \ + SCX_ENUM_SET(skel, scx_rq_flags, SCX_RQ_CLK_VALID); \ + SCX_ENUM_SET(skel, scx_rq_flags, SCX_RQ_IN_WAKEUP); \ + SCX_ENUM_SET(skel, scx_rq_flags, SCX_RQ_IN_BALANCE); \ + SCX_ENUM_SET(skel, scx_dsq_id_flags, SCX_DSQ_FLAG_BUILTIN); \ + SCX_ENUM_SET(skel, scx_dsq_id_flags, SCX_DSQ_FLAG_LOCAL_ON); \ + SCX_ENUM_SET(skel, scx_dsq_id_flags, SCX_DSQ_INVALID); \ + SCX_ENUM_SET(skel, scx_dsq_id_flags, SCX_DSQ_GLOBAL); \ + SCX_ENUM_SET(skel, scx_dsq_id_flags, SCX_DSQ_LOCAL); \ + SCX_ENUM_SET(skel, scx_dsq_id_flags, SCX_DSQ_LOCAL_ON); \ + SCX_ENUM_SET(skel, scx_dsq_id_flags, SCX_DSQ_LOCAL_CPU_MASK); \ + SCX_ENUM_SET(skel, scx_ent_flags, SCX_TASK_QUEUED); \ + SCX_ENUM_SET(skel, scx_ent_flags, SCX_TASK_RESET_RUNNABLE_AT); \ + SCX_ENUM_SET(skel, scx_ent_flags, SCX_TASK_DEQD_FOR_SLEEP); \ + SCX_ENUM_SET(skel, scx_ent_flags, SCX_TASK_STATE_SHIFT); \ + SCX_ENUM_SET(skel, scx_ent_flags, SCX_TASK_STATE_BITS); \ + SCX_ENUM_SET(skel, scx_ent_flags, SCX_TASK_STATE_MASK); \ + SCX_ENUM_SET(skel, scx_ent_flags, SCX_TASK_CURSOR); \ + SCX_ENUM_SET(skel, scx_task_state, SCX_TASK_NONE); \ + SCX_ENUM_SET(skel, scx_task_state, SCX_TASK_INIT); \ + SCX_ENUM_SET(skel, scx_task_state, SCX_TASK_READY); \ + SCX_ENUM_SET(skel, scx_task_state, SCX_TASK_ENABLED); \ + SCX_ENUM_SET(skel, scx_task_state, SCX_TASK_NR_STATES); \ + SCX_ENUM_SET(skel, scx_ent_dsq_flags, SCX_TASK_DSQ_ON_PRIQ); \ + SCX_ENUM_SET(skel, scx_kick_flags, SCX_KICK_IDLE); \ + SCX_ENUM_SET(skel, scx_kick_flags, SCX_KICK_PREEMPT); \ + SCX_ENUM_SET(skel, scx_kick_flags, SCX_KICK_WAIT); \ + SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_WAKEUP); \ + SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_HEAD); \ + SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_PREEMPT); \ + SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_REENQ); \ + SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_LAST); \ + SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_CLEAR_OPSS); \ + SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_DSQ_PRIQ); \ +} while (0) diff --git a/tools/sched_ext/include/scx/enums.bpf.h b/tools/sched_ext/include/scx/enums.bpf.h new file mode 100644 index 000000000000..af704c5d6334 --- /dev/null +++ b/tools/sched_ext/include/scx/enums.bpf.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Convenience macros for getting/setting struct scx_enums instances. + * + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + */ +#ifndef __SCX_ENUMS_BPF_H +#define __SCX_ENUMS_BPF_H + +#include "enums.autogen.bpf.h" + +#endif /* __SCX_ENUMS_BPF_H */ diff --git a/tools/sched_ext/include/scx/enums.h b/tools/sched_ext/include/scx/enums.h new file mode 100644 index 000000000000..8e7c91575f0b --- /dev/null +++ b/tools/sched_ext/include/scx/enums.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Define struct scx_enums that stores the load-time values of enums + * used by the BPF program. + * + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + */ + +#ifndef __SCX_ENUMS_H +#define __SCX_ENUMS_H + +static inline void __ENUM_set(u64 *val, char *type, char *name) +{ + bool res; + + res = __COMPAT_read_enum(type, name, val); + if (!res) + *val = 0; +} + +#define SCX_ENUM_SET(skel, type, name) do { \ + __ENUM_set(&skel->rodata->__##name, #type, #name); \ + } while (0) + + +#include "enums.autogen.h" + +#endif /* __SCX_ENUMS_H */ diff --git a/tools/sched_ext/include/scx/user_exit_info.h b/tools/sched_ext/include/scx/user_exit_info.h new file mode 100644 index 000000000000..66f856640ee7 --- /dev/null +++ b/tools/sched_ext/include/scx/user_exit_info.h @@ -0,0 +1,118 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Define struct user_exit_info which is shared between BPF and userspace parts + * to communicate exit status and other information. + * + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo <tj@kernel.org> + * Copyright (c) 2022 David Vernet <dvernet@meta.com> + */ +#ifndef __USER_EXIT_INFO_H +#define __USER_EXIT_INFO_H + +#ifdef LSP +#define __bpf__ +#include "../vmlinux.h" +#endif + +enum uei_sizes { + UEI_REASON_LEN = 128, + UEI_MSG_LEN = 1024, + UEI_DUMP_DFL_LEN = 32768, +}; + +struct user_exit_info { + int kind; + s64 exit_code; + char reason[UEI_REASON_LEN]; + char msg[UEI_MSG_LEN]; +}; + +#ifdef __bpf__ + +#ifndef LSP +#include "vmlinux.h" +#endif +#include <bpf/bpf_core_read.h> + +#define UEI_DEFINE(__name) \ + char RESIZABLE_ARRAY(data, __name##_dump); \ + const volatile u32 __name##_dump_len; \ + struct user_exit_info __name SEC(".data") + +#define UEI_RECORD(__uei_name, __ei) ({ \ + bpf_probe_read_kernel_str(__uei_name.reason, \ + sizeof(__uei_name.reason), (__ei)->reason); \ + bpf_probe_read_kernel_str(__uei_name.msg, \ + sizeof(__uei_name.msg), (__ei)->msg); \ + bpf_probe_read_kernel_str(__uei_name##_dump, \ + __uei_name##_dump_len, (__ei)->dump); \ + if (bpf_core_field_exists((__ei)->exit_code)) \ + __uei_name.exit_code = (__ei)->exit_code; \ + /* use __sync to force memory barrier */ \ + __sync_val_compare_and_swap(&__uei_name.kind, __uei_name.kind, \ + (__ei)->kind); \ +}) + +#else /* !__bpf__ */ + +#include <stdio.h> +#include <stdbool.h> + +/* no need to call the following explicitly if SCX_OPS_LOAD() is used */ +#define UEI_SET_SIZE(__skel, __ops_name, __uei_name) ({ \ + u32 __len = (__skel)->struct_ops.__ops_name->exit_dump_len ?: UEI_DUMP_DFL_LEN; \ + (__skel)->rodata->__uei_name##_dump_len = __len; \ + RESIZE_ARRAY((__skel), data, __uei_name##_dump, __len); \ +}) + +#define UEI_EXITED(__skel, __uei_name) ({ \ + /* use __sync to force memory barrier */ \ + __sync_val_compare_and_swap(&(__skel)->data->__uei_name.kind, -1, -1); \ +}) + +#define UEI_REPORT(__skel, __uei_name) ({ \ + struct user_exit_info *__uei = &(__skel)->data->__uei_name; \ + char *__uei_dump = (__skel)->data_##__uei_name##_dump->__uei_name##_dump; \ + if (__uei_dump[0] != '\0') { \ + fputs("\nDEBUG DUMP\n", stderr); \ + fputs("================================================================================\n\n", stderr); \ + fputs(__uei_dump, stderr); \ + fputs("\n================================================================================\n\n", stderr); \ + } \ + fprintf(stderr, "EXIT: %s", __uei->reason); \ + if (__uei->msg[0] != '\0') \ + fprintf(stderr, " (%s)", __uei->msg); \ + fputs("\n", stderr); \ + __uei->exit_code; \ +}) + +/* + * We can't import vmlinux.h while compiling user C code. Let's duplicate + * scx_exit_code definition. + */ +enum scx_exit_code { + /* Reasons */ + SCX_ECODE_RSN_HOTPLUG = 1LLU << 32, + + /* Actions */ + SCX_ECODE_ACT_RESTART = 1LLU << 48, +}; + +enum uei_ecode_mask { + UEI_ECODE_USER_MASK = ((1LLU << 32) - 1), + UEI_ECODE_SYS_RSN_MASK = ((1LLU << 16) - 1) << 32, + UEI_ECODE_SYS_ACT_MASK = ((1LLU << 16) - 1) << 48, +}; + +/* + * These macro interpret the ecode returned from UEI_REPORT(). + */ +#define UEI_ECODE_USER(__ecode) ((__ecode) & UEI_ECODE_USER_MASK) +#define UEI_ECODE_SYS_RSN(__ecode) ((__ecode) & UEI_ECODE_SYS_RSN_MASK) +#define UEI_ECODE_SYS_ACT(__ecode) ((__ecode) & UEI_ECODE_SYS_ACT_MASK) + +#define UEI_ECODE_RESTART(__ecode) (UEI_ECODE_SYS_ACT((__ecode)) == SCX_ECODE_ACT_RESTART) + +#endif /* __bpf__ */ +#endif /* __USER_EXIT_INFO_H */ |