diff --git a/Documentation/bpf/bpf_iterators.rst b/Documentation/bpf/bpf_iterators.rst index 07433915aa414d6369d2a189170fd6cf3d437b51..7f514cb6b0525ac8425f326ed315880cf6941e7f 100644 --- a/Documentation/bpf/bpf_iterators.rst +++ b/Documentation/bpf/bpf_iterators.rst @@ -86,7 +86,7 @@ following steps: The following are a few examples of selftest BPF iterator programs: * `bpf_iter_tcp4.c `_ -* `bpf_iter_task_vma.c `_ +* `bpf_iter_task_vmas.c `_ * `bpf_iter_task_file.c `_ Let us look at ``bpf_iter_task_file.c``, which runs in kernel space: diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst index 0d2647fb358d7ce1a4a85bd994d9b05e8ea0cec9..18920610ab7cea379f172f0b8684475eaf471df6 100644 --- a/Documentation/bpf/kfuncs.rst +++ b/Documentation/bpf/kfuncs.rst @@ -37,16 +37,14 @@ prototype in a header for the wrapper kfunc. An example is given below:: /* Disables missing prototype warnings */ - __diag_push(); - __diag_ignore_all("-Wmissing-prototypes", - "Global kfuncs as their definitions will be in BTF"); + __bpf_kfunc_start_defs(); __bpf_kfunc struct task_struct *bpf_find_get_task_by_vpid(pid_t nr) { return find_get_task_by_vpid(nr); } - __diag_pop(); + __bpf_kfunc_end_defs(); A wrapper kfunc is often needed when we need to annotate parameters of the kfunc. Otherwise one may directly make the kfunc visible to the BPF program by @@ -155,10 +153,10 @@ In addition to kfuncs' arguments, verifier may need more information about the type of kfunc(s) being registered with the BPF subsystem. To do so, we define flags on a set of kfuncs as follows:: - BTF_SET8_START(bpf_task_set) + BTF_KFUNCS_START(bpf_task_set) BTF_ID_FLAGS(func, bpf_get_task_pid, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_put_pid, KF_RELEASE) - BTF_SET8_END(bpf_task_set) + BTF_KFUNCS_END(bpf_task_set) This set encodes the BTF ID of each kfunc listed above, and encodes the flags along with it. Ofcourse, it is also allowed to specify no flags. @@ -325,10 +323,10 @@ Once the kfunc is prepared for use, the final step to making it visible is registering it with the BPF subsystem. Registration is done per BPF program type. An example is shown below:: - BTF_SET8_START(bpf_task_set) + BTF_KFUNCS_START(bpf_task_set) BTF_ID_FLAGS(func, bpf_get_task_pid, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_put_pid, KF_RELEASE) - BTF_SET8_END(bpf_task_set) + BTF_KFUNCS_END(bpf_task_set) static const struct btf_kfunc_id_set bpf_task_kfunc_set = { .owner = THIS_MODULE, diff --git a/Documentation/scheduler/index.rst b/Documentation/scheduler/index.rst index 3170747226f6da7f828223f6504704391fe47314..0b650bb550e647407607dc4486f8ba1320cbe5f0 100644 --- a/Documentation/scheduler/index.rst +++ b/Documentation/scheduler/index.rst @@ -19,6 +19,7 @@ Scheduler sched-nice-design sched-rt-group sched-stats + sched-ext sched-debug text_files diff --git a/Documentation/scheduler/sched-design-CFS.rst b/Documentation/scheduler/sched-design-CFS.rst index f68919800f05072912935d61fe760d95a278d979..6cffffe265006e8b71751649dc06e99852fb507e 100644 --- a/Documentation/scheduler/sched-design-CFS.rst +++ b/Documentation/scheduler/sched-design-CFS.rst @@ -180,7 +180,7 @@ This is the (partial) list of the hooks: compat_yield sysctl is turned on; in that case, it places the scheduling entity at the right-most end of the red-black tree. - - check_preempt_curr(...) + - wakeup_preempt(...) This function checks if a task that entered the runnable state should preempt the currently running task. @@ -189,10 +189,10 @@ This is the (partial) list of the hooks: This function chooses the most appropriate task eligible to run next. - - set_curr_task(...) + - set_next_task(...) - This function is called when a task changes its scheduling class or changes - its task group. + This function is called when a task changes its scheduling class, changes + its task group or is scheduled. - task_tick(...) diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst new file mode 100644 index 0000000000000000000000000000000000000000..a8ceaad63b6aa1685e455556a1c27083329094c0 --- /dev/null +++ b/Documentation/scheduler/sched-ext.rst @@ -0,0 +1,325 @@ +========================== +Extensible Scheduler Class +========================== + +sched_ext is a scheduler class whose behavior can be defined by a set of BPF +programs - the BPF scheduler. + +* sched_ext exports a full scheduling interface so that any scheduling + algorithm can be implemented on top. + +* The BPF scheduler can group CPUs however it sees fit and schedule them + together, as tasks aren't tied to specific CPUs at the time of wakeup. + +* The BPF scheduler can be turned on and off dynamically anytime. + +* The system integrity is maintained no matter what the BPF scheduler does. + The default scheduling behavior is restored anytime an error is detected, + a runnable task stalls, or on invoking the SysRq key sequence + :kbd:`SysRq-S`. + +* When the BPF scheduler triggers an error, debug information is dumped to + aid debugging. The debug dump is passed to and printed out by the + scheduler binary. The debug dump can also be accessed through the + `sched_ext_dump` tracepoint. The SysRq key sequence :kbd:`SysRq-D` + triggers a debug dump. This doesn't terminate the BPF scheduler and can + only be read through the tracepoint. + +Switching to and from sched_ext +=============================== + +``CONFIG_SCHED_CLASS_EXT`` is the config option to enable sched_ext and +``tools/sched_ext`` contains the example schedulers. The following config +options should be enabled to use sched_ext: + +.. code-block:: none + + CONFIG_BPF=y + CONFIG_SCHED_CLASS_EXT=y + CONFIG_BPF_SYSCALL=y + CONFIG_BPF_JIT=y + CONFIG_DEBUG_INFO_BTF=y + CONFIG_BPF_JIT_ALWAYS_ON=y + CONFIG_BPF_JIT_DEFAULT_ON=y + CONFIG_PAHOLE_HAS_SPLIT_BTF=y + CONFIG_PAHOLE_HAS_BTF_TAG=y + +sched_ext is used only when the BPF scheduler is loaded and running. + +If a task explicitly sets its scheduling policy to ``SCHED_EXT``, it will be +treated as ``SCHED_NORMAL`` and scheduled by CFS until the BPF scheduler is +loaded. + +When the BPF scheduler is loaded and ``SCX_OPS_SWITCH_PARTIAL`` is not set +in ``ops->flags``, all ``SCHED_NORMAL``, ``SCHED_BATCH``, ``SCHED_IDLE``, and +``SCHED_EXT`` tasks are scheduled by sched_ext. + +However, when the BPF scheduler is loaded and ``SCX_OPS_SWITCH_PARTIAL`` is +set in ``ops->flags``, only tasks with the ``SCHED_EXT`` policy are scheduled +by sched_ext, while tasks with ``SCHED_NORMAL``, ``SCHED_BATCH`` and +``SCHED_IDLE`` policies are scheduled by CFS. + +Terminating the sched_ext scheduler program, triggering :kbd:`SysRq-S`, or +detection of any internal error including stalled runnable tasks aborts the +BPF scheduler and reverts all tasks back to CFS. + +.. code-block:: none + + # make -j16 -C tools/sched_ext + # tools/sched_ext/build/bin/scx_simple + local=0 global=3 + local=5 global=24 + local=9 global=44 + local=13 global=56 + local=17 global=72 + ^CEXIT: BPF scheduler unregistered + +The current status of the BPF scheduler can be determined as follows: + +.. code-block:: none + + # cat /sys/kernel/sched_ext/state + enabled + # cat /sys/kernel/sched_ext/root/ops + simple + +You can check if any BPF scheduler has ever been loaded since boot by examining +this monotonically incrementing counter (a value of zero indicates that no BPF +scheduler has been loaded): + +.. code-block:: none + + # cat /sys/kernel/sched_ext/enable_seq + 1 + +``tools/sched_ext/scx_show_state.py`` is a drgn script which shows more +detailed information: + +.. code-block:: none + + # tools/sched_ext/scx_show_state.py + ops : simple + enabled : 1 + switching_all : 1 + switched_all : 1 + enable_state : enabled (2) + bypass_depth : 0 + nr_rejected : 0 + enable_seq : 1 + +If ``CONFIG_SCHED_DEBUG`` is set, whether a given task is on sched_ext can +be determined as follows: + +.. code-block:: none + + # grep ext /proc/self/sched + ext.enabled : 1 + +The Basics +========== + +Userspace can implement an arbitrary BPF scheduler by loading a set of BPF +programs that implement ``struct sched_ext_ops``. The only mandatory field +is ``ops.name`` which must be a valid BPF object name. All operations are +optional. The following modified excerpt is from +``tools/sched_ext/scx_simple.bpf.c`` showing a minimal global FIFO scheduler. + +.. code-block:: c + + /* + * Decide which CPU a task should be migrated to before being + * enqueued (either at wakeup, fork time, or exec time). If an + * idle core is found by the default ops.select_cpu() implementation, + * then insert the task directly into SCX_DSQ_LOCAL and skip the + * ops.enqueue() callback. + * + * Note that this implementation has exactly the same behavior as the + * default ops.select_cpu implementation. The behavior of the scheduler + * would be exactly same if the implementation just didn't define the + * simple_select_cpu() struct_ops prog. + */ + s32 BPF_STRUCT_OPS(simple_select_cpu, struct task_struct *p, + s32 prev_cpu, u64 wake_flags) + { + s32 cpu; + /* Need to initialize or the BPF verifier will reject the program */ + bool direct = false; + + cpu = scx_bpf_select_cpu_dfl(p, prev_cpu, wake_flags, &direct); + + if (direct) + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0); + + return cpu; + } + + /* + * Do a direct insertion of a task to the global DSQ. This ops.enqueue() + * callback will only be invoked if we failed to find a core to insert + * into in ops.select_cpu() above. + * + * Note that this implementation has exactly the same behavior as the + * default ops.enqueue implementation, which just dispatches the task + * to SCX_DSQ_GLOBAL. The behavior of the scheduler would be exactly same + * if the implementation just didn't define the simple_enqueue struct_ops + * prog. + */ + void BPF_STRUCT_OPS(simple_enqueue, struct task_struct *p, u64 enq_flags) + { + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + } + + s32 BPF_STRUCT_OPS_SLEEPABLE(simple_init) + { + /* + * By default, all SCHED_EXT, SCHED_OTHER, SCHED_IDLE, and + * SCHED_BATCH tasks should use sched_ext. + */ + return 0; + } + + void BPF_STRUCT_OPS(simple_exit, struct scx_exit_info *ei) + { + exit_type = ei->type; + } + + SEC(".struct_ops") + struct sched_ext_ops simple_ops = { + .select_cpu = (void *)simple_select_cpu, + .enqueue = (void *)simple_enqueue, + .init = (void *)simple_init, + .exit = (void *)simple_exit, + .name = "simple", + }; + +Dispatch Queues +--------------- + +To match the impedance between the scheduler core and the BPF scheduler, +sched_ext uses DSQs (dispatch queues) which can operate as both a FIFO and a +priority queue. By default, there is one global FIFO (``SCX_DSQ_GLOBAL``), +and one local dsq per CPU (``SCX_DSQ_LOCAL``). The BPF scheduler can manage +an arbitrary number of dsq's using ``scx_bpf_create_dsq()`` and +``scx_bpf_destroy_dsq()``. + +A CPU always executes a task from its local DSQ. A task is "inserted" into a +DSQ. A task in a non-local DSQ is "move"d into the target CPU's local DSQ. + +When a CPU is looking for the next task to run, if the local DSQ is not +empty, the first task is picked. Otherwise, the CPU tries to move a task +from the global DSQ. If that doesn't yield a runnable task either, +``ops.dispatch()`` is invoked. + +Scheduling Cycle +---------------- + +The following briefly shows how a waking task is scheduled and executed. + +1. When a task is waking up, ``ops.select_cpu()`` is the first operation + invoked. This serves two purposes. First, CPU selection optimization + hint. Second, waking up the selected CPU if idle. + + The CPU selected by ``ops.select_cpu()`` is an optimization hint and not + binding. The actual decision is made at the last step of scheduling. + However, there is a small performance gain if the CPU + ``ops.select_cpu()`` returns matches the CPU the task eventually runs on. + + A side-effect of selecting a CPU is waking it up from idle. While a BPF + scheduler can wake up any cpu using the ``scx_bpf_kick_cpu()`` helper, + using ``ops.select_cpu()`` judiciously can be simpler and more efficient. + + A task can be immediately inserted into a DSQ from ``ops.select_cpu()`` + by calling ``scx_bpf_dsq_insert()``. If the task is inserted into + ``SCX_DSQ_LOCAL`` from ``ops.select_cpu()``, it will be inserted into the + local DSQ of whichever CPU is returned from ``ops.select_cpu()``. + Additionally, inserting directly from ``ops.select_cpu()`` will cause the + ``ops.enqueue()`` callback to be skipped. + + Note that the scheduler core will ignore an invalid CPU selection, for + example, if it's outside the allowed cpumask of the task. + +2. Once the target CPU is selected, ``ops.enqueue()`` is invoked (unless the + task was inserted directly from ``ops.select_cpu()``). ``ops.enqueue()`` + can make one of the following decisions: + + * Immediately insert the task into either the global or a local DSQ by + calling ``scx_bpf_dsq_insert()`` with one of the following options: + ``SCX_DSQ_GLOBAL``, ``SCX_DSQ_LOCAL``, or ``SCX_DSQ_LOCAL_ON | cpu``. + + * Immediately insert the task into a custom DSQ by calling + ``scx_bpf_dsq_insert()`` with a DSQ ID which is smaller than 2^63. + + * Queue the task on the BPF side. + +3. When a CPU is ready to schedule, it first looks at its local DSQ. If + empty, it then looks at the global DSQ. If there still isn't a task to + run, ``ops.dispatch()`` is invoked which can use the following two + functions to populate the local DSQ. + + * ``scx_bpf_dsq_insert()`` inserts a task to a DSQ. Any target DSQ can be + used - ``SCX_DSQ_LOCAL``, ``SCX_DSQ_LOCAL_ON | cpu``, + ``SCX_DSQ_GLOBAL`` or a custom DSQ. While ``scx_bpf_dsq_insert()`` + currently can't be called with BPF locks held, this is being worked on + and will be supported. ``scx_bpf_dsq_insert()`` schedules insertion + rather than performing them immediately. There can be up to + ``ops.dispatch_max_batch`` pending tasks. + + * ``scx_bpf_move_to_local()`` moves a task from the specified non-local + DSQ to the dispatching DSQ. This function cannot be called with any BPF + locks held. ``scx_bpf_move_to_local()`` flushes the pending insertions + tasks before trying to move from the specified DSQ. + +4. After ``ops.dispatch()`` returns, if there are tasks in the local DSQ, + the CPU runs the first one. If empty, the following steps are taken: + + * Try to move from the global DSQ. If successful, run the task. + + * If ``ops.dispatch()`` has dispatched any tasks, retry #3. + + * If the previous task is an SCX task and still runnable, keep executing + it (see ``SCX_OPS_ENQ_LAST``). + + * Go idle. + +Note that the BPF scheduler can always choose to dispatch tasks immediately +in ``ops.enqueue()`` as illustrated in the above simple example. If only the +built-in DSQs are used, there is no need to implement ``ops.dispatch()`` as +a task is never queued on the BPF scheduler and both the local and global +DSQs are executed automatically. + +``scx_bpf_dsq_insert()`` inserts the task on the FIFO of the target DSQ. Use +``scx_bpf_dsq_insert_vtime()`` for the priority queue. Internal DSQs such as +``SCX_DSQ_LOCAL`` and ``SCX_DSQ_GLOBAL`` do not support priority-queue +dispatching, and must be dispatched to with ``scx_bpf_dsq_insert()``. See +the function documentation and usage in ``tools/sched_ext/scx_simple.bpf.c`` +for more information. + +Where to Look +============= + +* ``include/linux/sched/ext.h`` defines the core data structures, ops table + and constants. + +* ``kernel/sched/ext.c`` contains sched_ext core implementation and helpers. + The functions prefixed with ``scx_bpf_`` can be called from the BPF + scheduler. + +* ``tools/sched_ext/`` hosts example BPF scheduler implementations. + + * ``scx_simple[.bpf].c``: Minimal global FIFO scheduler example using a + custom DSQ. + + * ``scx_qmap[.bpf].c``: A multi-level FIFO scheduler supporting five + levels of priority implemented with ``BPF_MAP_TYPE_QUEUE``. + +ABI Instability +=============== + +The APIs provided by sched_ext to BPF schedulers programs have no stability +guarantees. This includes the ops table callbacks and constants defined in +``include/linux/sched/ext.h``, as well as the ``scx_bpf_`` kfuncs defined in +``kernel/sched/ext.c``. + +While we will attempt to provide a relatively stable API surface when +possible, they are subject to change without warning between kernel +versions. diff --git a/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst b/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst index 3076402406c48e3110a8e2f7bcb681a4d1864408..abc6709ec3b26a040b7b6bb6681f8fb9ec1cf7de 100644 --- a/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst +++ b/Documentation/translations/zh_CN/scheduler/sched-design-CFS.rst @@ -80,7 +80,7 @@ p->se.vruntime。一旦p->se.vruntime变得足够大，其它的任务将成为 CFS使用纳秒粒度的计时，不依赖于任何jiffies或HZ的细节。因此CFS并不像之前的调度器那样 有“时间片”的概念，也没有任何启发式的设计。唯一可调的参数（你需要打开CONFIG_SCHED_DEBUG）是： - /sys/kernel/debug/sched/min_granularity_ns + /sys/kernel/debug/sched/base_slice_ns 它可以用来将调度器从“桌面”模式（也就是低时延）调节为“服务器”（也就是高批处理）模式。 它的默认设置是适合桌面的工作负载。SCHED_BATCH也被CFS调度器模块处理。 @@ -147,7 +147,7 @@ array）。 这个函数的行为基本上是出队，紧接着入队，除非compat_yield sysctl被开启。在那种情况下， 它将调度实体放在红黑树的最右端。 - - check_preempt_curr(...) + - wakeup_preempt(...) 这个函数检查进入可运行状态的任务能否抢占当前正在运行的任务。 @@ -155,9 +155,9 @@ array）。 这个函数选择接下来最适合运行的任务。 - - set_curr_task(...) + - set_next_task(...) - 这个函数在任务改变调度类或改变任务组时被调用。 + 这个函数在任务改变调度类，改变任务组时，或者任务被调度时被调用。 - task_tick(...) diff --git a/MAINTAINERS b/MAINTAINERS index e6199cc299b1c36cc9b42d34365b4ea46037457c..40f9305fdd0fe055cec3c045e0bd40dc0d727b67 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19262,6 +19262,20 @@ F: include/linux/wait.h F: include/uapi/linux/sched.h F: kernel/sched/ +SCHEDULER - SCHED_EXT +R: Tejun Heo +R: David Vernet +R: Andrea Righi +R: Changwoo Min +L: linux-kernel@vger.kernel.org +S: Maintained +W: https://github.com/sched-ext/scx +T: git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git +F: include/linux/sched/ext.h +F: kernel/sched/ext* +F: tools/sched_ext/ +F: tools/testing/selftests/sched_ext + SCSI LIBSAS SUBSYSTEM R: John Garry R: Jason Yan diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index d4237341e76d7afa8104baa4d618334841d313b0..827f2c617d1377da2afae6f443718c6ad2d1dea2 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -97,6 +97,7 @@ CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set # CONFIG_PREEMPT_DYNAMIC is not set +CONFIG_SCHED_CLASS_EXT=y CONFIG_XCU_SCHEDULER=y CONFIG_XCU_VSTREAM=y CONFIG_XSCHED_NR_CUS=128 @@ -184,6 +185,7 @@ CONFIG_QOS_SCHED_MULTILEVEL=y CONFIG_FAIR_GROUP_SCHED=y CONFIG_CFS_BANDWIDTH=y CONFIG_RT_GROUP_SCHED=y +CONFIG_EXT_GROUP_SCHED=y CONFIG_QOS_SCHED_DYNAMIC_AFFINITY=y CONFIG_SCHED_SOFT_DOMAIN=y # CONFIG_SCHED_MM_CID is not set diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 8b957d2f60ebe2ad04b86359d03cc82c4ba0837f..461b47d7ea0185151534406d4f86d9300103df93 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1890,7 +1890,7 @@ static bool is_struct_ops_tramp(const struct bpf_tramp_links *fentry_links) * */ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, - struct bpf_tramp_links *tlinks, void *orig_call, + struct bpf_tramp_links *tlinks, void *func_addr, int nregs, u32 flags) { int i; @@ -1992,7 +1992,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, if (flags & BPF_TRAMP_F_IP_ARG) { /* save ip address of the traced function */ - emit_addr_mov_i64(A64_R(10), (const u64)orig_call, ctx); + emit_addr_mov_i64(A64_R(10), (const u64)func_addr, ctx); emit(A64_STR64I(A64_R(10), A64_SP, ip_off), ctx); } @@ -2105,18 +2105,10 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, return ctx->idx; } -int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, - void *image_end, const struct btf_func_model *m, - u32 flags, struct bpf_tramp_links *tlinks, - void *orig_call) +static int btf_func_model_nregs(const struct btf_func_model *m) { - int i, ret; int nregs = m->nr_args; - int max_insns = ((long)image_end - (long)image) / AARCH64_INSN_SIZE; - struct jit_ctx ctx = { - .image = NULL, - .idx = 0, - }; + int i; /* extra registers needed for struct argument */ for (i = 0; i < MAX_BPF_FUNC_ARGS; i++) { @@ -2125,22 +2117,49 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, nregs += (m->arg_size[i] + 7) / 8 - 1; } + return nregs; +} + +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr) +{ + struct jit_ctx ctx = { + .image = NULL, + .idx = 0, + }; + struct bpf_tramp_image im; + int nregs, ret; + + nregs = btf_func_model_nregs(m); /* the first 8 registers are used for arguments */ if (nregs > 8) return -ENOTSUPP; - ret = prepare_trampoline(&ctx, im, tlinks, orig_call, nregs, flags); + ret = prepare_trampoline(&ctx, &im, tlinks, func_addr, nregs, flags); if (ret < 0) return ret; - if (ret > max_insns) - return -EFBIG; + return ret < 0 ? ret : ret * AARCH64_INSN_SIZE; +} - ctx.image = image; - ctx.idx = 0; +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, + void *image_end, const struct btf_func_model *m, + u32 flags, struct bpf_tramp_links *tlinks, + void *func_addr) +{ + int ret, nregs; + struct jit_ctx ctx = { + .image = image, + .idx = 0, + }; + + nregs = btf_func_model_nregs(m); + /* the first 8 registers are used for arguments */ + if (nregs > 8) + return -ENOTSUPP; jit_fill_hole(image, (unsigned int)(image_end - image)); - ret = prepare_trampoline(&ctx, im, tlinks, orig_call, nregs, flags); + ret = prepare_trampoline(&ctx, im, tlinks, func_addr, nregs, flags); if (ret > 0 && validate_code(&ctx) < 0) ret = -EINVAL; diff --git a/arch/mips/dec/setup.c b/arch/mips/dec/setup.c index 6c3704f51d0de40fee5f851dcc76420bec39123b..87f0a1436bf9cc78bed11a708d49c20741ad51ea 100644 --- a/arch/mips/dec/setup.c +++ b/arch/mips/dec/setup.c @@ -756,7 +756,7 @@ void __init arch_init_irq(void) NULL)) pr_err("Failed to register fpu interrupt\n"); desc_fpu = irq_to_desc(irq_fpu); - fpu_kstat_irq = this_cpu_ptr(desc_fpu->kstat_irqs); + fpu_kstat_irq = this_cpu_ptr(&desc_fpu->kstat_irqs->cnt); } if (dec_interrupt[DEC_IRQ_CASCADE] >= 0) { if (request_irq(dec_interrupt[DEC_IRQ_CASCADE], no_action, diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index 2019c1f04bd037af0d346f4c4e03f42c769eb16f..adfe2ed31075d37b763962a72286ea2989d24008 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -344,7 +344,7 @@ static int smp_boot_one_cpu(int cpuid, struct task_struct *idle) struct irq_desc *desc = irq_to_desc(i); if (desc && desc->kstat_irqs) - *per_cpu_ptr(desc->kstat_irqs, cpuid) = 0; + *per_cpu_ptr(desc->kstat_irqs, cpuid) = (struct irqstat) { }; } #endif diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c index e165bfa842bfca8c27bb2676a1d098964db10584..c901256d3281684ff49d54792235ec70377bf997 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_xics.c +++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c @@ -837,7 +837,7 @@ static inline void this_cpu_inc_rm(unsigned int __percpu *addr) */ static void kvmppc_rm_handle_irq_desc(struct irq_desc *desc) { - this_cpu_inc_rm(desc->kstat_irqs); + this_cpu_inc_rm(&desc->kstat_irqs->cnt); __this_cpu_inc(kstat.irqs_sum); } diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 16eb4cd11cbd6717779645f8eb31a00258225db5..e9db9b183385ed2b7c2f2e84bd6dd8d419313c82 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -15,6 +15,8 @@ #define RV_FENTRY_NINSNS 2 #define RV_FENTRY_NBYTES (RV_FENTRY_NINSNS * 4) +/* imm that allows emit_imm to emit max count insns */ +#define RV_MAX_COUNT_IMM 0x7FFF7FF7FF7FF7FF #define RV_REG_TCC RV_REG_A6 #define RV_REG_TCC_SAVED RV_REG_S6 /* Store A6 in S6 if program do calls */ @@ -922,7 +924,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, orig_call += RV_FENTRY_NINSNS * 4; if (flags & BPF_TRAMP_F_CALL_ORIG) { - emit_imm(RV_REG_A0, (const s64)im, ctx); + emit_imm(RV_REG_A0, ctx->insns ? (const s64)im : RV_MAX_COUNT_IMM, ctx); ret = emit_call((const u64)__bpf_tramp_enter, true, ctx); if (ret) return ret; @@ -983,7 +985,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, if (flags & BPF_TRAMP_F_CALL_ORIG) { im->ip_epilogue = ctx->insns + ctx->ninsns; - emit_imm(RV_REG_A0, (const s64)im, ctx); + emit_imm(RV_REG_A0, ctx->insns ? (const s64)im : RV_MAX_COUNT_IMM, ctx); ret = emit_call((const u64)__bpf_tramp_exit, true, ctx); if (ret) goto out; @@ -1030,23 +1032,29 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, return ret; } -int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, - void *image_end, const struct btf_func_model *m, - u32 flags, struct bpf_tramp_links *tlinks, - void *func_addr) +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr) { - int ret; + struct bpf_tramp_image im; struct rv_jit_context ctx; + int ret; ctx.ninsns = 0; ctx.insns = NULL; ctx.ro_insns = NULL; - ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx); - if (ret < 0) - return ret; + ret = __arch_prepare_bpf_trampoline(&im, m, tlinks, func_addr, flags, &ctx); - if (ninsns_rvoff(ret) > (long)image_end - (long)image) - return -EFBIG; + return ret < 0 ? ret : ninsns_rvoff(ctx.ninsns); +} + +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, + void *image_end, const struct btf_func_model *m, + u32 flags, struct bpf_tramp_links *tlinks, + void *func_addr) +{ + int ret; + struct rv_jit_context ctx; + u32 size = image_end - image; ctx.ninsns = 0; /* @@ -1060,11 +1068,16 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, ctx.ro_insns = image; ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx); if (ret < 0) - return ret; + goto out; - bpf_flush_icache(ctx.insns, ctx.insns + ctx.ninsns); + if (WARN_ON(size < ninsns_rvoff(ctx.ninsns))) { + ret = -E2BIG; + goto out; + } - return ninsns_rvoff(ret); + bpf_flush_icache(image, image_end); +out: + return ret < 0 ? ret : size; } int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 05746e22fe79c517541032c447d1ce319f3f9229..8815d1e6451e5db2d94f6edccc727a6f3518765c 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -2500,6 +2500,21 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, return 0; } +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *orig_call) +{ + struct bpf_tramp_image im; + struct bpf_tramp_jit tjit; + int ret; + + memset(&tjit, 0, sizeof(tjit)); + + ret = __arch_prepare_bpf_trampoline(&im, &tjit, m, flags, + tlinks, orig_call); + + return ret < 0 ? ret : tjit.common.prg; +} + int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, @@ -2507,30 +2522,27 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, { struct bpf_tramp_jit tjit; int ret; - int i; - for (i = 0; i < 2; i++) { - if (i == 0) { - /* Compute offsets, check whether the code fits. */ - memset(&tjit, 0, sizeof(tjit)); - } else { - /* Generate the code. */ - tjit.common.prg = 0; - tjit.common.prg_buf = image; - } - ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags, - tlinks, func_addr); - if (ret < 0) - return ret; - if (tjit.common.prg > (char *)image_end - (char *)image) - /* - * Use the same error code as for exceeding - * BPF_MAX_TRAMP_LINKS. - */ - return -E2BIG; - } + /* Compute offsets, check whether the code fits. */ + memset(&tjit, 0, sizeof(tjit)); + ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags, + tlinks, func_addr); + + if (ret < 0) + return ret; + if (tjit.common.prg > (char *)image_end - (char *)image) + /* + * Use the same error code as for exceeding + * BPF_MAX_TRAMP_LINKS. + */ + return -E2BIG; + + tjit.common.prg = 0; + tjit.common.prg_buf = image; + ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags, + tlinks, func_addr); - return tjit.common.prg; + return ret < 0 ? ret : tjit.common.prg; } bool bpf_jit_supports_subprog_tailcalls(void) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index d61f04743aad0ebe1bf5b11936c2bdc07a5b2bb1..724636778ea501524f19c761eb7403067d702c27 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -2171,7 +2171,8 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_link *l, int stack_size, - int run_ctx_off, bool save_ret) + int run_ctx_off, bool save_ret, + void *image, void *rw_image) { u8 *prog = *pprog; u8 *jmp_insn; @@ -2199,7 +2200,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, else EMIT4(0x48, 0x8D, 0x75, -run_ctx_off); - if (emit_rsb_call(&prog, bpf_trampoline_enter(p), prog)) + if (emit_rsb_call(&prog, bpf_trampoline_enter(p), image + (prog - (u8 *)rw_image))) return -EINVAL; /* remember prog start time returned by __bpf_prog_enter */ emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); @@ -2223,7 +2224,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, (long) p->insnsi >> 32, (u32) (long) p->insnsi); /* call JITed bpf program or interpreter */ - if (emit_rsb_call(&prog, p->bpf_func, prog)) + if (emit_rsb_call(&prog, p->bpf_func, image + (prog - (u8 *)rw_image))) return -EINVAL; /* @@ -2250,7 +2251,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, EMIT3_off32(0x48, 0x8D, 0x95, -run_ctx_off); else EMIT4(0x48, 0x8D, 0x55, -run_ctx_off); - if (emit_rsb_call(&prog, bpf_trampoline_exit(p), prog)) + if (emit_rsb_call(&prog, bpf_trampoline_exit(p), image + (prog - (u8 *)rw_image))) return -EINVAL; *pprog = prog; @@ -2285,14 +2286,15 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_links *tl, int stack_size, - int run_ctx_off, bool save_ret) + int run_ctx_off, bool save_ret, + void *image, void *rw_image) { int i; u8 *prog = *pprog; for (i = 0; i < tl->nr_links; i++) { if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, - run_ctx_off, save_ret)) + run_ctx_off, save_ret, image, rw_image)) return -EINVAL; } *pprog = prog; @@ -2301,7 +2303,8 @@ static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_links *tl, int stack_size, - int run_ctx_off, u8 **branches) + int run_ctx_off, u8 **branches, + void *image, void *rw_image) { u8 *prog = *pprog; int i; @@ -2312,7 +2315,8 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, emit_mov_imm32(&prog, false, BPF_REG_0, 0); emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); for (i = 0; i < tl->nr_links; i++) { - if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, run_ctx_off, true)) + if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, run_ctx_off, true, + image, rw_image)) return -EINVAL; /* mod_ret prog stored return value into [rbp - 8]. Emit: @@ -2395,10 +2399,11 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, * add rsp, 8 // skip eth_type_trans's frame * ret // return to its caller */ -int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, - const struct btf_func_model *m, u32 flags, - struct bpf_tramp_links *tlinks, - void *func_addr) +static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_image, + void *rw_image_end, void *image, + const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, + void *func_addr) { int i, ret, nr_regs = m->nr_args, stack_size = 0; int regs_off, nregs_off, ip_off, run_ctx_off, arg_stack_off, rbx_off; @@ -2494,7 +2499,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i orig_call += X86_PATCH_SIZE; } - prog = image; + prog = rw_image; EMIT_ENDBR(); /* @@ -2536,7 +2541,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i if (flags & BPF_TRAMP_F_CALL_ORIG) { /* arg1: mov rdi, im */ emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im); - if (emit_rsb_call(&prog, __bpf_tramp_enter, prog)) { + if (emit_rsb_call(&prog, __bpf_tramp_enter, + image + (prog - (u8 *)rw_image))) { ret = -EINVAL; goto cleanup; } @@ -2544,7 +2550,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i if (fentry->nr_links) if (invoke_bpf(m, &prog, fentry, regs_off, run_ctx_off, - flags & BPF_TRAMP_F_RET_FENTRY_RET)) + flags & BPF_TRAMP_F_RET_FENTRY_RET, image, rw_image)) return -EINVAL; if (fmod_ret->nr_links) { @@ -2554,7 +2560,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i return -ENOMEM; if (invoke_bpf_mod_ret(m, &prog, fmod_ret, regs_off, - run_ctx_off, branches)) { + run_ctx_off, branches, image, rw_image)) { ret = -EINVAL; goto cleanup; } @@ -2575,14 +2581,14 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i EMIT2(0xff, 0xd3); /* call *rbx */ } else { /* call original function */ - if (emit_rsb_call(&prog, orig_call, prog)) { + if (emit_rsb_call(&prog, orig_call, image + (prog - (u8 *)rw_image))) { ret = -EINVAL; goto cleanup; } } /* remember return value in a stack for bpf prog to access */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); - im->ip_after_call = prog; + im->ip_after_call = image + (prog - (u8 *)rw_image); memcpy(prog, x86_nops[5], X86_PATCH_SIZE); prog += X86_PATCH_SIZE; } @@ -2598,12 +2604,13 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i * aligned address of do_fexit. */ for (i = 0; i < fmod_ret->nr_links; i++) - emit_cond_near_jump(&branches[i], prog, branches[i], - X86_JNE); + emit_cond_near_jump(&branches[i], image + (prog - (u8 *)rw_image), + image + (branches[i] - (u8 *)rw_image), X86_JNE); } if (fexit->nr_links) - if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off, false)) { + if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off, + false, image, rw_image)) { ret = -EINVAL; goto cleanup; } @@ -2616,10 +2623,10 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i * restored to R0. */ if (flags & BPF_TRAMP_F_CALL_ORIG) { - im->ip_epilogue = prog; + im->ip_epilogue = image + (prog - (u8 *)rw_image); /* arg1: mov rdi, im */ emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im); - if (emit_rsb_call(&prog, __bpf_tramp_exit, prog)) { + if (emit_rsb_call(&prog, __bpf_tramp_exit, image + (prog - (u8 *)rw_image))) { ret = -EINVAL; goto cleanup; } @@ -2638,19 +2645,90 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i if (flags & BPF_TRAMP_F_SKIP_FRAME) /* skip our return address and return to parent */ EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */ - emit_return(&prog, prog); + emit_return(&prog, image + (prog - (u8 *)rw_image)); /* Make sure the trampoline generation logic doesn't overflow */ - if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) { + if (WARN_ON_ONCE(prog > (u8 *)rw_image_end - BPF_INSN_SAFETY)) { ret = -EFAULT; goto cleanup; } - ret = prog - (u8 *)image; + ret = prog - (u8 *)rw_image + BPF_INSN_SAFETY; cleanup: kfree(branches); return ret; } +void *arch_alloc_bpf_trampoline(unsigned int size) +{ + return bpf_prog_pack_alloc(size, jit_fill_hole); +} + +void arch_free_bpf_trampoline(void *image, unsigned int size) +{ + bpf_prog_pack_free(image, size); +} + +void arch_protect_bpf_trampoline(void *image, unsigned int size) +{ +} + +void arch_unprotect_bpf_trampoline(void *image, unsigned int size) +{ +} + +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, + const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, + void *func_addr) +{ + void *rw_image, *tmp; + int ret; + u32 size = image_end - image; + + /* rw_image doesn't need to be in module memory range, so we can + * use kvmalloc. + */ + rw_image = kvmalloc(size, GFP_KERNEL); + if (!rw_image) + return -ENOMEM; + + ret = __arch_prepare_bpf_trampoline(im, rw_image, rw_image + size, image, m, + flags, tlinks, func_addr); + if (ret < 0) + goto out; + + tmp = bpf_arch_text_copy(image, rw_image, size); + if (IS_ERR(tmp)) + ret = PTR_ERR(tmp); +out: + kvfree(rw_image); + return ret; +} + +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr) +{ + struct bpf_tramp_image im; + void *image; + int ret; + + /* Allocate a temporary buffer for __arch_prepare_bpf_trampoline(). + * This will NOT cause fragmentation in direct map, as we do not + * call set_memory_*() on this buffer. + * + * We cannot use kvmalloc here, because we need image to be in + * module memory range. + */ + image = bpf_jit_alloc_exec(PAGE_SIZE); + if (!image) + return -ENOMEM; + + ret = __arch_prepare_bpf_trampoline(&im, image, image + PAGE_SIZE, image, + m, flags, tlinks, func_addr); + bpf_jit_free_exec(image); + return ret; +} + static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs, u8 *image, u8 *buf) { u8 *jg_reloc, *prog = *pprog; diff --git a/drivers/hid/bpf/hid_bpf_dispatch.c b/drivers/hid/bpf/hid_bpf_dispatch.c index 7903c8638e8173f2778fce729e7fa03a9a32dc91..c2ffa01585edc632d4023d960d38a7617502aa29 100644 --- a/drivers/hid/bpf/hid_bpf_dispatch.c +++ b/drivers/hid/bpf/hid_bpf_dispatch.c @@ -172,9 +172,9 @@ hid_bpf_get_data(struct hid_bpf_ctx *ctx, unsigned int offset, const size_t rdwr * The following set contains all functions we agree BPF programs * can use. */ -BTF_SET8_START(hid_bpf_kfunc_ids) +BTF_KFUNCS_START(hid_bpf_kfunc_ids) BTF_ID_FLAGS(func, hid_bpf_get_data, KF_RET_NULL) -BTF_SET8_END(hid_bpf_kfunc_ids) +BTF_KFUNCS_END(hid_bpf_kfunc_ids) static const struct btf_kfunc_id_set hid_bpf_kfunc_set = { .owner = THIS_MODULE, @@ -479,12 +479,12 @@ static const struct btf_kfunc_id_set hid_bpf_fmodret_set = { }; /* for syscall HID-BPF */ -BTF_SET8_START(hid_bpf_syscall_kfunc_ids) +BTF_KFUNCS_START(hid_bpf_syscall_kfunc_ids) BTF_ID_FLAGS(func, hid_bpf_attach_prog) BTF_ID_FLAGS(func, hid_bpf_allocate_context, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, hid_bpf_release_context, KF_RELEASE) BTF_ID_FLAGS(func, hid_bpf_hw_request) -BTF_SET8_END(hid_bpf_syscall_kfunc_ids) +BTF_KFUNCS_END(hid_bpf_syscall_kfunc_ids) static const struct btf_kfunc_id_set hid_bpf_syscall_kfunc_set = { .owner = THIS_MODULE, diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index 02c0a7b935b2e75706bd436fa3e784f1ddecd922..de447b3f061d73f3abb7e4d76c0da02586e11513 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -520,6 +520,7 @@ static const struct sysrq_key_op *sysrq_key_table[62] = { NULL, /* P */ NULL, /* Q */ NULL, /* R */ + /* S: May be registered by sched_ext for resetting */ NULL, /* S */ NULL, /* T */ NULL, /* U */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index f4888ae85f90b34ef0a237da75184c70347193d4..d010f6aeeacb9579ec7dd7298f37125a9d77287f 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -131,6 +131,7 @@ *(__dl_sched_class) \ *(__rt_sched_class) \ *(__fair_sched_class) \ + *(__ext_sched_class) \ *(__idle_sched_class) \ __sched_class_lowest = .; diff --git a/include/linux/bitops.h b/include/linux/bitops.h index f7f5a783da2aa8ad8f5de0a3a70ab3340e5963f6..e0cd09eb91cdca687742ea7e31be339b2b367321 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -21,6 +21,8 @@ #define BITS_TO_U32(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u32)) #define BITS_TO_BYTES(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) +#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_BYTE) + extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); extern unsigned int __sw_hweight32(unsigned int w); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c9f81962d9f95d31e4cbe43ef6681db0571ed1da..001dee769c6663c906efd5d747e3b5fa55c010f9 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1151,10 +1151,17 @@ struct bpf_tramp_run_ctx; * fexit = a set of program to run after original function */ struct bpf_tramp_image; -int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, - void *orig_call); + void *func_addr); +void *arch_alloc_bpf_trampoline(unsigned int size); +void arch_free_bpf_trampoline(void *image, unsigned int size); +void arch_protect_bpf_trampoline(void *image, unsigned int size); +void arch_unprotect_bpf_trampoline(void *image, unsigned int size); +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr); + u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start, @@ -1196,7 +1203,7 @@ struct bpf_tramp_image { struct work_struct work; }; - KABI_RESERVE(1) + KABI_USE(1, int size) KABI_RESERVE(2) KABI_RESERVE(3) KABI_RESERVE(4) @@ -1388,7 +1395,7 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to); /* Called only from JIT-enabled code, so there's no need for stubs. */ -void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym); +void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); @@ -1434,6 +1441,8 @@ static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog) struct bpf_func_info_aux { u16 linkage; bool unreliable; + KABI_FILL_HOLE(bool called : 1) + KABI_FILL_HOLE(bool verified : 1) }; enum bpf_jit_poke_reason { @@ -1463,6 +1472,7 @@ struct bpf_ctx_arg_aux { u32 offset; enum bpf_reg_type reg_type; u32 btf_id; + KABI_BROKEN_INSERT(struct btf *btf) // will affect struct bpf_iter_reg. }; struct btf_mod_pair { @@ -1763,12 +1773,10 @@ struct bpf_struct_ops { void (*unreg)(void *kdata); int (*update)(void *kdata, void *old_kdata); int (*validate)(void *kdata); - const struct btf_type *type; - const struct btf_type *value_type; + void *cfi_stubs; + struct module *owner; const char *name; struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; - u32 type_id; - u32 value_id; KABI_RESERVE(1) KABI_RESERVE(2) @@ -1776,10 +1784,58 @@ struct bpf_struct_ops { KABI_RESERVE(4) }; +/* Every member of a struct_ops type has an instance even a member is not + * an operator (function pointer). The "info" field will be assigned to + * prog->aux->ctx_arg_info of BPF struct_ops programs to provide the + * argument information required by the verifier to verify the program. + * + * btf_ctx_access() will lookup prog->aux->ctx_arg_info to find the + * corresponding entry for an given argument. + */ +struct bpf_struct_ops_arg_info { + struct bpf_ctx_arg_aux *info; + u32 cnt; +}; + +struct bpf_struct_ops_desc { + struct bpf_struct_ops *st_ops; + + const struct btf_type *type; + const struct btf_type *value_type; + u32 type_id; + u32 value_id; + + /* Collection of argument information for each member */ + struct bpf_struct_ops_arg_info *arg_info; +}; + +enum bpf_struct_ops_state { + BPF_STRUCT_OPS_STATE_INIT, + BPF_STRUCT_OPS_STATE_INUSE, + BPF_STRUCT_OPS_STATE_TOBEFREE, + BPF_STRUCT_OPS_STATE_READY, +}; + +struct bpf_struct_ops_common_value { + refcount_t refcnt; + enum bpf_struct_ops_state state; +}; + #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) +/* This macro helps developer to register a struct_ops type and generate + * type information correctly. Developers should use this macro to register + * a struct_ops type instead of calling __register_bpf_struct_ops() directly. + */ +#define register_bpf_struct_ops(st_ops, type) \ + ({ \ + struct bpf_struct_ops_##type { \ + struct bpf_struct_ops_common_value common; \ + struct type data ____cacheline_aligned_in_smp; \ + }; \ + BTF_TYPE_EMIT(struct bpf_struct_ops_##type); \ + __register_bpf_struct_ops(st_ops); \ + }) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) -const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id); -void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log); bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, @@ -1787,7 +1843,9 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, struct bpf_tramp_link *link, const struct btf_func_model *model, - void *image, void *image_end); + void **image, u32 *image_off, + bool allow_alloc); +void bpf_struct_ops_image_free(void *image); static inline bool bpf_try_module_get(const void *data, struct module *owner) { if (owner == BPF_MODULE_OWNER) @@ -1820,15 +1878,13 @@ struct bpf_dummy_ops { int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); #endif +int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, + struct btf *btf, + struct bpf_verifier_log *log); +void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map); +void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc); #else -static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) -{ - return NULL; -} -static inline void bpf_struct_ops_init(struct btf *btf, - struct bpf_verifier_log *log) -{ -} +#define register_bpf_struct_ops(st_ops, type) ({ (void *)(st_ops); 0; }) static inline bool bpf_try_module_get(const void *data, struct module *owner) { return try_module_get(owner); @@ -1847,6 +1903,13 @@ static inline int bpf_struct_ops_link_create(union bpf_attr *attr) { return -EOPNOTSUPP; } +static inline void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map) +{ +} + +static inline void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc) +{ +} #endif diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index bb1223b2130877d6fee6a2d58926647c354f6cb7..50ab9929b3d07d6b47df4d685a78b08a76c64212 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -25,6 +25,9 @@ struct bpf_mem_alloc { int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu); void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); +/* Check the allocation size for kmalloc equivalent allocator */ +int bpf_mem_alloc_check_size(bool percpu, size_t size); + /* kmalloc/kfree equivalent: */ void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size); void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b7ff22ed0fd7132c03902572749ffad4d68c3135..0b17e46d56cda6923a9e0ee78867bcbefe576750 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -473,19 +473,18 @@ struct bpf_verifier_state { KABI_RESERVE(4) }; -#define bpf_get_spilled_reg(slot, frame) \ +#define bpf_get_spilled_reg(slot, frame, mask) \ (((slot < frame->allocated_stack / BPF_REG_SIZE) && \ - (frame->stack[slot].slot_type[0] == STACK_SPILL)) \ + ((1 << frame->stack[slot].slot_type[0]) & (mask))) \ ? &frame->stack[slot].spilled_ptr : NULL) /* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */ -#define bpf_for_each_spilled_reg(iter, frame, reg) \ - for (iter = 0, reg = bpf_get_spilled_reg(iter, frame); \ +#define bpf_for_each_spilled_reg(iter, frame, reg, mask) \ + for (iter = 0, reg = bpf_get_spilled_reg(iter, frame, mask); \ iter < frame->allocated_stack / BPF_REG_SIZE; \ - iter++, reg = bpf_get_spilled_reg(iter, frame)) + iter++, reg = bpf_get_spilled_reg(iter, frame, mask)) -/* Invoke __expr over regsiters in __vst, setting __state and __reg */ -#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \ +#define bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, __mask, __expr) \ ({ \ struct bpf_verifier_state *___vstate = __vst; \ int ___i, ___j; \ @@ -497,7 +496,7 @@ struct bpf_verifier_state { __reg = &___regs[___j]; \ (void)(__expr); \ } \ - bpf_for_each_spilled_reg(___j, __state, __reg) { \ + bpf_for_each_spilled_reg(___j, __state, __reg, __mask) { \ if (!__reg) \ continue; \ (void)(__expr); \ @@ -505,6 +504,10 @@ struct bpf_verifier_state { } \ }) +/* Invoke __expr over regsiters in __vst, setting __state and __reg */ +#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \ + bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, 1 << STACK_SPILL, __expr) + /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; @@ -745,7 +748,8 @@ struct bpf_verifier_env { char tmp_str_buf[TMP_STR_BUF_LEN]; KABI_USE(1, struct bpf_jmp_history_entry *cur_hist_ent) - KABI_RESERVE(2) + /* The owner module of prog->aux->attach_btf */ + KABI_USE(2, struct module *attach_btf_mod) KABI_RESERVE(3) KABI_RESERVE(4) KABI_RESERVE(5) diff --git a/include/linux/btf.h b/include/linux/btf.h index 928113a80a95278e44161ed8a7c559716e237651..53f51447a5623577480127c6ec0a1e0ef24c4af2 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -74,6 +74,7 @@ #define KF_ITER_NEW (1 << 8) /* kfunc implements BPF iter constructor */ #define KF_ITER_NEXT (1 << 9) /* kfunc implements BPF iter next method */ #define KF_ITER_DESTROY (1 << 10) /* kfunc implements BPF iter destructor */ +#define KF_RCU_PROTECTED (1 << 11) /* kfunc should be protected by rcu cs when they are invoked */ /* * Tag marking a kernel function as a kfunc. This is meant to minimize the @@ -83,6 +84,15 @@ */ #define __bpf_kfunc __used noinline +#define __bpf_kfunc_start_defs() \ + __diag_push(); \ + __diag_ignore_all("-Wmissing-declarations", \ + "Global kfuncs as their definitions will be in BTF");\ + __diag_ignore_all("-Wmissing-prototypes", \ + "Global kfuncs as their definitions will be in BTF") + +#define __bpf_kfunc_end_defs() __diag_pop() + /* * Return the name of the passed struct, if exists, or halt the build if for * example the structure gets renamed. In this way, developers have to revisit @@ -125,6 +135,7 @@ struct btf_struct_metas { extern const struct file_operations btf_fops; +const char *btf_get_name(const struct btf *btf); void btf_get(struct btf *btf); void btf_put(struct btf *btf); int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_sz); @@ -331,6 +342,11 @@ static inline bool btf_type_is_scalar(const struct btf_type *t) return btf_type_is_int(t) || btf_type_is_enum(t); } +static inline bool btf_type_is_fwd(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_FWD; +} + static inline bool btf_type_is_typedef(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF; @@ -482,8 +498,26 @@ static inline void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func); } +bool btf_param_match_suffix(const struct btf *btf, + const struct btf_param *arg, + const char *suffix); +int btf_ctx_arg_offset(const struct btf *btf, const struct btf_type *func_proto, + u32 arg_no); + struct bpf_verifier_log; +#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) +struct bpf_struct_ops; +int __register_bpf_struct_ops(struct bpf_struct_ops *st_ops); +const struct bpf_struct_ops_desc *bpf_struct_ops_find_value(struct btf *btf, u32 value_id); +const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id); +#else +static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id) +{ + return NULL; +} +#endif + #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); @@ -507,6 +541,7 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type); bool btf_types_are_same(const struct btf *btf1, u32 id1, const struct btf *btf2, u32 id2); +int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -559,6 +594,10 @@ static inline bool btf_types_are_same(const struct btf *btf1, u32 id1, { return false; } +static inline int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx) +{ + return -EOPNOTSUPP; +} #endif static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t) diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index a9cb10b0e2e9bf45c33f4ad39e7a95d8d9b6b1b5..e24aabfe8ecc91fae3a814eccade54b366016bc1 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -8,6 +8,9 @@ struct btf_id_set { u32 ids[]; }; +/* This flag implies BTF_SET8 holds kfunc(s) */ +#define BTF_SET8_KFUNCS (1 << 0) + struct btf_id_set8 { u32 cnt; u32 flags; @@ -21,6 +24,7 @@ struct btf_id_set8 { #include /* for __PASTE */ #include /* for __maybe_unused */ +#include /* * Following macros help to define lists of BTF IDs placed @@ -183,17 +187,18 @@ extern struct btf_id_set name; * .word (1 << 3) | (1 << 1) | (1 << 2) * */ -#define __BTF_SET8_START(name, scope) \ +#define __BTF_SET8_START(name, scope, flags) \ +__BTF_ID_LIST(name, local) \ asm( \ ".pushsection " BTF_IDS_SECTION ",\"a\"; \n" \ "." #scope " __BTF_ID__set8__" #name "; \n" \ "__BTF_ID__set8__" #name ":; \n" \ -".zero 8 \n" \ +".zero 4 \n" \ +".long " __stringify(flags) "\n" \ ".popsection; \n"); #define BTF_SET8_START(name) \ -__BTF_ID_LIST(name, local) \ -__BTF_SET8_START(name, local) +__BTF_SET8_START(name, local, 0) #define BTF_SET8_END(name) \ asm( \ @@ -202,6 +207,12 @@ asm( \ ".popsection; \n"); \ extern struct btf_id_set8 name; +#define BTF_KFUNCS_START(name) \ +__BTF_SET8_START(name, local, BTF_SET8_KFUNCS) + +#define BTF_KFUNCS_END(name) \ +BTF_SET8_END(name) + #else #define BTF_ID_LIST(name) static u32 __maybe_unused name[64]; @@ -216,6 +227,8 @@ extern struct btf_id_set8 name; #define BTF_SET_END(name) #define BTF_SET8_START(name) static struct btf_id_set8 __maybe_unused name = { 0 }; #define BTF_SET8_END(name) +#define BTF_KFUNCS_START(name) static struct btf_id_set8 __maybe_unused name = { .flags = BTF_SET8_KFUNCS }; +#define BTF_KFUNCS_END(name) #endif /* CONFIG_DEBUG_INFO_BTF */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 794cf8953b7fd64b33bf2e57d769016957d04123..cd324445b4d50f336bbd0ef912df63fb52fa2ab5 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -30,8 +30,6 @@ struct kernel_clone_args; -#ifdef CONFIG_CGROUPS - /* * All weight knobs on the default hierarchy should use the following min, * default and max values. The default value is the logarithmic center of @@ -41,13 +39,13 @@ struct kernel_clone_args; #define CGROUP_WEIGHT_DFL 100 #define CGROUP_WEIGHT_MAX 10000 -/* walk only threadgroup leaders */ -#define CSS_TASK_ITER_PROCS (1U << 0) -/* walk all threaded css_sets in the domain */ -#define CSS_TASK_ITER_THREADED (1U << 1) +#ifdef CONFIG_CGROUPS -/* internal flags */ -#define CSS_TASK_ITER_SKIPPED (1U << 16) +enum { + CSS_TASK_ITER_PROCS = (1U << 0), /* walk only threadgroup leaders */ + CSS_TASK_ITER_THREADED = (1U << 1), /* walk all threaded css_sets in the domain */ + CSS_TASK_ITER_SKIPPED = (1U << 16), /* internal flags */ +}; /* a css_task_iter should be treated as an opaque object */ struct css_task_iter { diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index 64b8600eb8c0e4a2ea8a0b89aa659c32c45266a9..69cb6f739bea07d3188b7e98bf44d0f7eba1e0db 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -7,8 +7,9 @@ /* * DEFINE_FREE(name, type, free): * simple helper macro that defines the required wrapper for a __free() - * based cleanup function. @free is an expression using '_T' to access - * the variable. + * based cleanup function. @free is an expression using '_T' to access the + * variable. @free should typically include a NULL test before calling a + * function, see the example below. * * __free(name): * variable attribute to add a scoped based cleanup to the variable. @@ -17,6 +18,9 @@ * like a non-atomic xchg(var, NULL), such that the cleanup function will * be inhibited -- provided it sanely deals with a NULL value. * + * NOTE: this has __must_check semantics so that it is harder to accidentally + * leak the resource. + * * return_ptr(p): * returns p while inhibiting the __free(). * @@ -24,6 +28,8 @@ * * DEFINE_FREE(kfree, void *, if (_T) kfree(_T)) * + * void *alloc_obj(...) + * { * struct obj *p __free(kfree) = kmalloc(...); * if (!p) * return NULL; @@ -32,6 +38,24 @@ * return NULL; * * return_ptr(p); + * } + * + * NOTE: the DEFINE_FREE()'s @free expression includes a NULL test even though + * kfree() is fine to be called with a NULL value. This is on purpose. This way + * the compiler sees the end of our alloc_obj() function as: + * + * tmp = p; + * p = NULL; + * if (p) + * kfree(p); + * return tmp; + * + * And through the magic of value-propagation and dead-code-elimination, it + * eliminates the actual cleanup call and compiles into: + * + * return p; + * + * Without the NULL test it turns into a mess and the compiler can't help us. */ #define DEFINE_FREE(_name, _type, _free) \ @@ -39,8 +63,20 @@ #define __free(_name) __cleanup(__free_##_name) +#define __get_and_null(p, nullvalue) \ + ({ \ + __auto_type __ptr = &(p); \ + __auto_type __val = *__ptr; \ + *__ptr = nullvalue; \ + __val; \ + }) + +static inline __must_check +const volatile void * __must_check_fn(const volatile void *val) +{ return val; } + #define no_free_ptr(p) \ - ({ __auto_type __ptr = (p); (p) = NULL; __ptr; }) + ((typeof(p)) __must_check_fn((__force const volatile void *)__get_and_null(p, NULL))) #define return_ptr(p) return no_free_ptr(p) diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 4c26ede3b87d311283306c014b072c1ac233affa..ce7c7394b8313d647e836c439d2e59ba59ad4d00 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -990,15 +990,6 @@ static inline void reset_cpu_possible_mask(void) bitmap_zero(cpumask_bits(&__cpu_possible_mask), NR_CPUS); } -static inline void -set_cpu_possible(unsigned int cpu, bool possible) -{ - if (possible) - cpumask_set_cpu(cpu, &__cpu_possible_mask); - else - cpumask_clear_cpu(cpu, &__cpu_possible_mask); -} - static inline void set_cpu_enabled(unsigned int cpu, bool can_be_onlined) { @@ -1007,36 +998,16 @@ set_cpu_enabled(unsigned int cpu, bool can_be_onlined) else cpumask_clear_cpu(cpu, &__cpu_enabled_mask); } +#define assign_cpu(cpu, mask, val) \ + assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) -static inline void -set_cpu_present(unsigned int cpu, bool present) -{ - if (present) - cpumask_set_cpu(cpu, &__cpu_present_mask); - else - cpumask_clear_cpu(cpu, &__cpu_present_mask); -} +#define set_cpu_possible(cpu, possible) assign_cpu((cpu), &__cpu_possible_mask, (possible)) +#define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present)) +#define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active)) +#define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying)) void set_cpu_online(unsigned int cpu, bool online); -static inline void -set_cpu_active(unsigned int cpu, bool active) -{ - if (active) - cpumask_set_cpu(cpu, &__cpu_active_mask); - else - cpumask_clear_cpu(cpu, &__cpu_active_mask); -} - -static inline void -set_cpu_dying(unsigned int cpu, bool dying) -{ - if (dying) - cpumask_set_cpu(cpu, &__cpu_dying_mask); - else - cpumask_clear_cpu(cpu, &__cpu_dying_mask); -} - /** * to_cpumask - convert an NR_CPUS bitmap to a struct cpumask * * @bitmap: the bitmap diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 784efdba67037adc651d63d2b65b8ae08921b20e..3b1128cc5b1f36cd5cbc36fe860770142973ef2d 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -248,7 +248,6 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, scale_cpu = arch_scale_cpu_capacity(cpu); ref_freq = arch_scale_freq_ref(cpu); - max_util = map_util_perf(max_util); max_util = min(max_util, allowed_cpu_cap); freq = map_util_freq(max_util, ref_freq, scale_cpu); diff --git a/include/linux/file.h b/include/linux/file.h index 6e9099d2934368d2aa41ffc30f4e438f8d42531d..6541d0b15ce6a3d9eb8d756508d824f260b75962 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -94,6 +94,26 @@ extern void put_unused_fd(unsigned int fd); DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), get_unused_fd_flags(flags), unsigned flags) +/* + * take_fd() will take care to set @fd to -EBADF ensuring that + * CLASS(get_unused_fd) won't call put_unused_fd(). This makes it + * easier to rely on CLASS(get_unused_fd): + * + * struct file *f; + * + * CLASS(get_unused_fd, fd)(O_CLOEXEC); + * if (fd < 0) + * return fd; + * + * f = dentry_open(&path, O_RDONLY, current_cred()); + * if (IS_ERR(f)) + * return PTR_ERR(fd); + * + * fd_install(fd, f); + * return take_fd(fd); + */ +#define take_fd(fd) __get_and_null(fd, -EBADF) + extern void fd_install(unsigned int fd, struct file *file); extern int __receive_fd(struct file *file, int __user *ufd, diff --git a/include/linux/filter.h b/include/linux/filter.h index a7c0caa8b7ad5dea532f01d4fb74a3735cfd8a0c..8af847032cb14d438d0f7b01b80eee9c59799b95 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1035,7 +1035,7 @@ struct bpf_binary_header * bpf_jit_binary_pack_hdr(const struct bpf_prog *fp); void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns); -void bpf_prog_pack_free(struct bpf_binary_header *hdr); +void bpf_prog_pack_free(void *ptr, u32 size); static inline bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp) { diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index fea156ae551c8bc61346eec9d5bc7bb2b878efab..33409e3dcf6fbd4a52a7fe382a983f4f992d2b0b 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -17,6 +17,18 @@ struct irq_desc; struct irq_domain; struct pt_regs; +/** + * struct irqstat - interrupt statistics + * @cnt: real-time interrupt count + * @ref: snapshot of interrupt count + */ +struct irqstat { + unsigned int cnt; +#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT + unsigned int ref; +#endif +}; + /** * struct irq_desc - interrupt descriptor * @irq_common_data: per irq and chip data passed down to chip functions @@ -55,7 +67,8 @@ struct pt_regs; struct irq_desc { struct irq_common_data irq_common_data; struct irq_data irq_data; - unsigned int __percpu *kstat_irqs; + KABI_REPLACE(unsigned int __percpu *kstat_irqs, + struct irqstat __percpu *kstat_irqs) irq_flow_handler_t handle_irq; struct irqaction *action; /* IRQ action list */ unsigned int status_use_accessors; @@ -121,7 +134,7 @@ extern struct irq_desc irq_desc[NR_IRQS]; static inline unsigned int irq_desc_kstat_cpu(struct irq_desc *desc, unsigned int cpu) { - return desc->kstat_irqs ? *per_cpu_ptr(desc->kstat_irqs, cpu) : 0; + return desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0; } static inline struct irq_desc *irq_data_to_desc(struct irq_data *data) diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 9935f7ecbfb9e31a68a6c6d0748aea49e0171344..9c042c6384bb3dec72670815fbaaf4483ae4d221 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -79,6 +79,14 @@ static inline unsigned int kstat_cpu_softirqs_sum(int cpu) return sum; } +#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT +extern void kstat_snapshot_irqs(void); +extern unsigned int kstat_get_irq_since_snapshot(unsigned int irq); +#else +static inline void kstat_snapshot_irqs(void) { } +static inline unsigned int kstat_get_irq_since_snapshot(unsigned int irq) { return 0; } +#endif + /* * Number of interrupts per specific IRQ source, since bootup */ diff --git a/include/linux/sched.h b/include/linux/sched.h index bb23790fd2d39f7cb17cc72018dc774650875a62..3014da820ba667e806503ae5a6757cbdf3f53e94 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -77,6 +77,8 @@ struct task_delay_info; struct task_group; struct user_event_mm; +#include + /* * Task state bitmask. NOTE! These bits are also * encoded in fs/proc/array.c: get_task_state(). @@ -533,7 +535,7 @@ struct sched_statistics { u64 block_max; s64 sum_block_runtime; - u64 exec_max; + KABI_REPLACE(u64 exec_max, s64 exec_max) u64 slice_max; u64 nr_migrations_cold; @@ -1644,6 +1646,10 @@ struct task_struct { KABI_RESERVE(16) KABI_AUX_PTR(task_struct) +#if !defined(__GENKSYMS__) && defined(CONFIG_SCHED_CLASS_EXT) + KABI_BROKEN_INSERT(struct sched_ext_entity scx) +#endif + /* CPU-specific state of this task: */ struct thread_struct thread; diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h new file mode 100644 index 0000000000000000000000000000000000000000..1d70a9867fb12e2a88edf4766fa874628509dbaa --- /dev/null +++ b/include/linux/sched/ext.h @@ -0,0 +1,216 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst + * + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo + * Copyright (c) 2022 David Vernet + */ +#ifndef _LINUX_SCHED_EXT_H +#define _LINUX_SCHED_EXT_H + +#ifdef CONFIG_SCHED_CLASS_EXT + +#include +#include + +enum scx_public_consts { + SCX_OPS_NAME_LEN = 128, + + SCX_SLICE_DFL = 20 * 1000000, /* 20ms */ + SCX_SLICE_INF = U64_MAX, /* infinite, implies nohz */ +}; + +/* + * DSQ (dispatch queue) IDs are 64bit of the format: + * + * Bits: [63] [62 .. 0] + * [ B] [ ID ] + * + * B: 1 for IDs for built-in DSQs, 0 for ops-created user DSQs + * ID: 63 bit ID + * + * Built-in IDs: + * + * Bits: [63] [62] [61..32] [31 .. 0] + * [ 1] [ L] [ R ] [ V ] + * + * 1: 1 for built-in DSQs. + * L: 1 for LOCAL_ON DSQ IDs, 0 for others + * V: For LOCAL_ON DSQ IDs, a CPU number. For others, a pre-defined value. + */ +enum scx_dsq_id_flags { + SCX_DSQ_FLAG_BUILTIN = 1LLU << 63, + SCX_DSQ_FLAG_LOCAL_ON = 1LLU << 62, + + SCX_DSQ_INVALID = SCX_DSQ_FLAG_BUILTIN | 0, + SCX_DSQ_GLOBAL = SCX_DSQ_FLAG_BUILTIN | 1, + SCX_DSQ_LOCAL = SCX_DSQ_FLAG_BUILTIN | 2, + SCX_DSQ_LOCAL_ON = SCX_DSQ_FLAG_BUILTIN | SCX_DSQ_FLAG_LOCAL_ON, + SCX_DSQ_LOCAL_CPU_MASK = 0xffffffffLLU, +}; + +/* + * A dispatch queue (DSQ) can be either a FIFO or p->scx.dsq_vtime ordered + * queue. A built-in DSQ is always a FIFO. The built-in local DSQs are used to + * buffer between the scheduler core and the BPF scheduler. See the + * documentation for more details. + */ +struct scx_dispatch_q { + raw_spinlock_t lock; + struct list_head list; /* tasks in dispatch order */ + struct rb_root priq; /* used to order by p->scx.dsq_vtime */ + u32 nr; + u32 seq; /* used by BPF iter */ + u64 id; + struct rhash_head hash_node; + struct llist_node free_node; + struct rcu_head rcu; +}; + +/* scx_entity.flags */ +enum scx_ent_flags { + SCX_TASK_QUEUED = 1 << 0, /* on ext runqueue */ + SCX_TASK_RESET_RUNNABLE_AT = 1 << 2, /* runnable_at should be reset */ + SCX_TASK_DEQD_FOR_SLEEP = 1 << 3, /* last dequeue was for SLEEP */ + + SCX_TASK_STATE_SHIFT = 8, /* bit 8 and 9 are used to carry scx_task_state */ + SCX_TASK_STATE_BITS = 2, + SCX_TASK_STATE_MASK = ((1 << SCX_TASK_STATE_BITS) - 1) << SCX_TASK_STATE_SHIFT, + + SCX_TASK_CURSOR = 1 << 31, /* iteration cursor, not a task */ +}; + +/* scx_entity.flags & SCX_TASK_STATE_MASK */ +enum scx_task_state { + SCX_TASK_NONE, /* ops.init_task() not called yet */ + SCX_TASK_INIT, /* ops.init_task() succeeded, but task can be cancelled */ + SCX_TASK_READY, /* fully initialized, but not in sched_ext */ + SCX_TASK_ENABLED, /* fully initialized and in sched_ext */ + + SCX_TASK_NR_STATES, +}; + +/* scx_entity.dsq_flags */ +enum scx_ent_dsq_flags { + SCX_TASK_DSQ_ON_PRIQ = 1 << 0, /* task is queued on the priority queue of a dsq */ +}; + +/* + * Mask bits for scx_entity.kf_mask. Not all kfuncs can be called from + * everywhere and the following bits track which kfunc sets are currently + * allowed for %current. This simple per-task tracking works because SCX ops + * nest in a limited way. BPF will likely implement a way to allow and disallow + * kfuncs depending on the calling context which will replace this manual + * mechanism. See scx_kf_allow(). + */ +enum scx_kf_mask { + SCX_KF_UNLOCKED = 0, /* sleepable and not rq locked */ + /* ENQUEUE and DISPATCH may be nested inside CPU_RELEASE */ + SCX_KF_CPU_RELEASE = 1 << 0, /* ops.cpu_release() */ + /* ops.dequeue (in REST) may be nested inside DISPATCH */ + SCX_KF_DISPATCH = 1 << 1, /* ops.dispatch() */ + SCX_KF_ENQUEUE = 1 << 2, /* ops.enqueue() and ops.select_cpu() */ + SCX_KF_SELECT_CPU = 1 << 3, /* ops.select_cpu() */ + SCX_KF_REST = 1 << 4, /* other rq-locked operations */ + + __SCX_KF_RQ_LOCKED = SCX_KF_CPU_RELEASE | SCX_KF_DISPATCH | + SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, + __SCX_KF_TERMINAL = SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, +}; + +enum scx_dsq_lnode_flags { + SCX_DSQ_LNODE_ITER_CURSOR = 1 << 0, + + /* high 16 bits can be for iter cursor flags */ + __SCX_DSQ_LNODE_PRIV_SHIFT = 16, +}; + +struct scx_dsq_list_node { + struct list_head node; + u32 flags; + u32 priv; /* can be used by iter cursor */ +}; + +/* + * The following is embedded in task_struct and contains all fields necessary + * for a task to be scheduled by SCX. + */ +struct sched_ext_entity { + struct scx_dispatch_q *dsq; + struct scx_dsq_list_node dsq_list; /* dispatch order */ + struct rb_node dsq_priq; /* p->scx.dsq_vtime order */ + u32 dsq_seq; + u32 dsq_flags; /* protected by DSQ lock */ + u32 flags; /* protected by rq lock */ + u32 weight; + s32 sticky_cpu; + s32 holding_cpu; + u32 kf_mask; /* see scx_kf_mask above */ + struct task_struct *kf_tasks[2]; /* see SCX_CALL_OP_TASK() */ + atomic_long_t ops_state; + + struct list_head runnable_node; /* rq->scx.runnable_list */ + unsigned long runnable_at; + +#ifdef CONFIG_SCHED_CORE + u64 core_sched_at; /* see scx_prio_less() */ +#endif + u64 ddsp_dsq_id; + u64 ddsp_enq_flags; + + /* BPF scheduler modifiable fields */ + + /* + * Runtime budget in nsecs. This is usually set through + * scx_bpf_dispatch() but can also be modified directly by the BPF + * scheduler. Automatically decreased by SCX as the task executes. On + * depletion, a scheduling event is triggered. + * + * This value is cleared to zero if the task is preempted by + * %SCX_KICK_PREEMPT and shouldn't be used to determine how long the + * task ran. Use p->se.sum_exec_runtime instead. + */ + u64 slice; + + /* + * Used to order tasks when dispatching to the vtime-ordered priority + * queue of a dsq. This is usually set through scx_bpf_dispatch_vtime() + * but can also be modified directly by the BPF scheduler. Modifying it + * while a task is queued on a dsq may mangle the ordering and is not + * recommended. + */ + u64 dsq_vtime; + + /* + * If set, reject future sched_setscheduler(2) calls updating the policy + * to %SCHED_EXT with -%EACCES. + * + * Can be set from ops.init_task() while the BPF scheduler is being + * loaded (!scx_init_task_args->fork). If set and the task's policy is + * already %SCHED_EXT, the task's policy is rejected and forcefully + * reverted to %SCHED_NORMAL. The number of such events are reported + * through /sys/kernel/debug/sched_ext::nr_rejected. Setting this flag + * during fork is not allowed. + */ + bool disallow; /* reject switching into SCX */ + + /* cold fields */ +#ifdef CONFIG_EXT_GROUP_SCHED + struct cgroup *cgrp_moving_from; +#endif + struct list_head tasks_node; +}; + +void sched_ext_free(struct task_struct *p); +void print_scx_info(const char *log_lvl, struct task_struct *p); +void scx_softlockup(u32 dur_s); + +#else /* !CONFIG_SCHED_CLASS_EXT */ + +static inline void sched_ext_free(struct task_struct *p) {} +static inline void print_scx_info(const char *log_lvl, struct task_struct *p) {} +static inline void scx_softlockup(u32 dur_s) {} + +#endif /* CONFIG_SCHED_CLASS_EXT */ +#endif /* _LINUX_SCHED_EXT_H */ diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index a23af225c8983903b103e18c52520acb13e89407..a4f5fd4774cedd567ebc26a68585abfe4494104d 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -61,7 +61,8 @@ extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); extern int sched_fork(unsigned long clone_flags, struct task_struct *p); -extern void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs); +extern int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs); +extern void sched_cancel_fork(struct task_struct *p); extern void sched_post_fork(struct task_struct *p); extern void sched_dead(struct task_struct *p); @@ -117,6 +118,11 @@ static inline struct task_struct *get_task_struct(struct task_struct *t) return t; } +static inline struct task_struct *tryget_task_struct(struct task_struct *t) +{ + return refcount_inc_not_zero(&t->usage) ? t : NULL; +} + extern void __put_task_struct(struct task_struct *t); extern void __put_task_struct_rcu_cb(struct rcu_head *rhp); diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 6d91ba4eb4f53e93df3ab2267fe71db1f8d7b4e8..59709a62394b09d52bf04ae926434c7e0e7461aa 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -776,7 +776,8 @@ struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name); void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, - u64 *probe_offset, u64 *probe_addr); + u64 *probe_offset, u64 *probe_addr, + unsigned long *missed); int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); #else @@ -816,7 +817,7 @@ static inline void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) static inline int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, - u64 *probe_addr) + u64 *probe_addr, unsigned long *missed) { return -EOPNOTSUPP; } @@ -891,6 +892,7 @@ extern void perf_kprobe_destroy(struct perf_event *event); extern int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, const char **symbol, u64 *probe_offset, u64 *probe_addr, + unsigned long *missed, bool perf_type_tracepoint); #endif #ifdef CONFIG_UPROBE_EVENTS diff --git a/include/trace/events/sched_ext.h b/include/trace/events/sched_ext.h new file mode 100644 index 0000000000000000000000000000000000000000..73e0f7cf2bfa55bef6a8880d850651b09fcd9d50 --- /dev/null +++ b/include/trace/events/sched_ext.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM sched_ext + +#if !defined(_TRACE_SCHED_EXT_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_SCHED_EXT_H + +#include + +TRACE_EVENT(sched_ext_dump, + + TP_PROTO(const char *line), + + TP_ARGS(line), + + TP_STRUCT__entry( + __string(line, line) + ), + + TP_fast_assign( + __assign_str(line, line); + ), + + TP_printk("%s", + __get_str(line) + ) +); + +#endif /* _TRACE_SCHED_EXT_H */ + +/* This part must be outside protection */ +#include diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 782d56c4ebcac55b66a39f0a7e26f7d5dca790ef..1e2de651cd690523c865e66314ceebeb47a3cba4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1335,6 +1335,9 @@ enum { /* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ BPF_F_PATH_FD = (1U << 14), + +/* Flag for value_type_btf_obj_fd, the fd is available */ + BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15), }; /* Flags for BPF_PROG_QUERY. */ @@ -1408,6 +1411,14 @@ union bpf_attr { * to using 5 hash functions). */ __u64 map_extra; + + /* fd pointing to a BTF + * type data for + * btf_vmlinux_value_type_id. + */ +#if !defined(__GENKSYMS__) + __s32 value_type_btf_obj_fd; +#endif }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -5122,6 +5133,8 @@ union bpf_attr { * **BPF_F_TIMER_ABS** * Start the timer in absolute expire value instead of the * default relative one. + * **BPF_F_TIMER_CPU_PIN** + * Timer will be pinned to the CPU of the caller. * * Return * 0 on success. @@ -6481,7 +6494,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; - __u32 :32; /* alignment pad */ + __u32 btf_vmlinux_id; __u64 map_extra; } __attribute__((aligned(8))); @@ -6565,20 +6578,35 @@ struct bpf_link_info { __aligned_u64 file_name; /* in/out */ __u32 name_len; __u32 offset; /* offset from file_name */ +#if !defined(__GENKSYMS__) + __u64 cookie; +#endif } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */ struct { __aligned_u64 func_name; /* in/out */ __u32 name_len; __u32 offset; /* offset from func_name */ __u64 addr; +#if !defined(__GENKSYMS__) + __u64 missed; + __u64 cookie; +#endif } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */ struct { __aligned_u64 tp_name; /* in/out */ __u32 name_len; +#if !defined(__GENKSYMS__) + __u32 :32; + __u64 cookie; +#endif } tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */ struct { __u64 config; __u32 type; +#if !defined(__GENKSYMS__) + __u32 :32; + __u64 cookie; +#endif } event; /* BPF_PERF_EVENT_EVENT */ struct { __u64:64; @@ -7346,9 +7374,11 @@ struct bpf_core_relo { * Flags to control bpf_timer_start() behaviour. * - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is * relative to current time. + * - BPF_F_TIMER_CPU_PIN: Timer will be pinned to the CPU of the caller. */ enum { BPF_F_TIMER_ABS = (1ULL << 0), + BPF_F_TIMER_CPU_PIN = (1ULL << 1), }; /* BPF numbers iterator state */ diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h index 3bac0a8ceab26ee78c37b425a76115aa21c20c06..359a14cc76a4038aeacef14b2915d5ce60d0cf44 100644 --- a/include/uapi/linux/sched.h +++ b/include/uapi/linux/sched.h @@ -118,6 +118,7 @@ struct clone_args { /* SCHED_ISO: reserved but not implemented yet */ #define SCHED_IDLE 5 #define SCHED_DEADLINE 6 +#define SCHED_EXT 7 /* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */ #define SCHED_RESET_ON_FORK 0x40000000 diff --git a/init/Kconfig b/init/Kconfig index 6c1f5079467f9b3910691098d42788110be55e52..165073211f355c0bd294346314d603707ac18d7b 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1129,9 +1129,13 @@ config QOS_SCHED_MULTILEVEL Expand the qos_level to [-2,2] to distinguish the tasks expected to be with extremely high or low priority level. +config GROUP_SCHED_WEIGHT + def_bool n + config FAIR_GROUP_SCHED bool "Group scheduling for SCHED_OTHER" depends on CGROUP_SCHED + select GROUP_SCHED_WEIGHT default CGROUP_SCHED config CFS_BANDWIDTH @@ -1156,6 +1160,12 @@ config RT_GROUP_SCHED realtime bandwidth for them. See Documentation/scheduler/sched-rt-group.rst for more information. +config EXT_GROUP_SCHED + bool + depends on SCHED_CLASS_EXT && CGROUP_SCHED + select GROUP_SCHED_WEIGHT + default y + endif #CGROUP_SCHED config QOS_SCHED_DYNAMIC_AFFINITY diff --git a/init/init_task.c b/init/init_task.c index 61a6345708c80d73f9670d9a5607353be1662dcf..59ef4d370ef6eda4c0bb55428894db4c6ad2b17b 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -111,6 +112,17 @@ struct task_struct init_task #endif #ifdef CONFIG_CGROUP_SCHED .sched_task_group = &root_task_group, +#endif +#ifdef CONFIG_SCHED_CLASS_EXT + .scx = { + .dsq_list.node = LIST_HEAD_INIT(init_task.scx.dsq_list.node), + .sticky_cpu = -1, + .holding_cpu = -1, + .runnable_node = LIST_HEAD_INIT(init_task.scx.runnable_node), + .runnable_at = INITIAL_JIFFIES, + .ddsp_dsq_id = SCX_DSQ_INVALID, + .slice = SCX_SLICE_DFL, + }, #endif .ptraced = LIST_HEAD_INIT(init_task.ptraced), .ptrace_entry = LIST_HEAD_INIT(init_task.ptrace_entry), diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index dc2a630f200a1665f8232a2983c38b82ac9c4b07..23034579d7721e3116031bc4b3e559068fac89d9 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -133,4 +133,29 @@ config SCHED_CORE which is the likely usage by Linux distributions, there should be no measurable impact on performance. - +config SCHED_CLASS_EXT + bool "Extensible Scheduling Class" + depends on BPF_SYSCALL && BPF_JIT && DEBUG_INFO_BTF + select STACKTRACE if STACKTRACE_SUPPORT + help + This option enables a new scheduler class sched_ext (SCX), which + allows scheduling policies to be implemented as BPF programs to + achieve the following: + + - Ease of experimentation and exploration: Enabling rapid + iteration of new scheduling policies. + - Customization: Building application-specific schedulers which + implement policies that are not applicable to general-purpose + schedulers. + - Rapid scheduler deployments: Non-disruptive swap outs of + scheduling policies in production environments. + + sched_ext leverages BPF struct_ops feature to define a structure + which exports function callbacks and flags to BPF programs that + wish to implement scheduling policies. The struct_ops structure + exported by sched_ext is struct sched_ext_ops, and is conceptually + similar to struct sched_class. + + For more information: + Documentation/scheduler/sched-ext.rst + https://github.com/sched-ext/scx diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 96856f130cbff8111fd31fa1007a9fade8dfd15d..0fae79164187094d77def3bdc9cd6e6cac99c733 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -782,9 +782,7 @@ struct bpf_iter_num_kern { int end; /* final value, exclusive */ } __aligned(8); -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "Global functions as their definitions will be in vmlinux BTF"); +__bpf_kfunc_start_defs(); __bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end) { @@ -793,8 +791,6 @@ __bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end) BUILD_BUG_ON(sizeof(struct bpf_iter_num_kern) != sizeof(struct bpf_iter_num)); BUILD_BUG_ON(__alignof__(struct bpf_iter_num_kern) != __alignof__(struct bpf_iter_num)); - BTF_TYPE_EMIT(struct btf_iter_num); - /* start == end is legit, it's an empty range and we'll just get NULL * on first (and any subsequent) bpf_iter_num_next() call */ @@ -845,4 +841,4 @@ __bpf_kfunc void bpf_iter_num_destroy(struct bpf_iter_num *it) s->cur = s->end = 0; } -__diag_pop(); +__bpf_kfunc_end_defs(); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index fdc3e8705a3cb838e82409f0c025b1e39ea4dfec..edcd3ffad912c4f6ad650c575149c9c8bf0a7ee9 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -13,26 +13,17 @@ #include #include -enum bpf_struct_ops_state { - BPF_STRUCT_OPS_STATE_INIT, - BPF_STRUCT_OPS_STATE_INUSE, - BPF_STRUCT_OPS_STATE_TOBEFREE, - BPF_STRUCT_OPS_STATE_READY, -}; - -#define BPF_STRUCT_OPS_COMMON_VALUE \ - refcount_t refcnt; \ - enum bpf_struct_ops_state state - struct bpf_struct_ops_value { - BPF_STRUCT_OPS_COMMON_VALUE; + struct bpf_struct_ops_common_value common; char data[] ____cacheline_aligned_in_smp; }; +#define MAX_TRAMP_IMAGE_PAGES 8 + struct bpf_struct_ops_map { struct bpf_map map; struct rcu_head rcu; - const struct bpf_struct_ops *st_ops; + const struct bpf_struct_ops_desc *st_ops_desc; /* protect map_update */ struct mutex lock; /* link has all the bpf_links that is populated @@ -40,12 +31,14 @@ struct bpf_struct_ops_map { * (in kvalue.data). */ struct bpf_link **links; - /* image is a page that has all the trampolines + u32 links_cnt; + u32 image_pages_cnt; + /* image_pages is an array of pages that has all the trampolines * that stores the func args before calling the bpf_prog. - * A PAGE_SIZE "image" is enough to store all trampoline for - * "links[]". */ - void *image; + void *image_pages[MAX_TRAMP_IMAGE_PAGES]; + /* The owner moduler's btf. */ + struct btf *btf; /* uvalue->data stores the kernel struct * (e.g. tcp_congestion_ops) that is more useful * to userspace than the kvalue. For example, @@ -70,35 +63,6 @@ static DEFINE_MUTEX(update_mutex); #define VALUE_PREFIX "bpf_struct_ops_" #define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1) -/* bpf_struct_ops_##_name (e.g. bpf_struct_ops_tcp_congestion_ops) is - * the map's value exposed to the userspace and its btf-type-id is - * stored at the map->btf_vmlinux_value_type_id. - * - */ -#define BPF_STRUCT_OPS_TYPE(_name) \ -extern struct bpf_struct_ops bpf_##_name; \ - \ -struct bpf_struct_ops_##_name { \ - BPF_STRUCT_OPS_COMMON_VALUE; \ - struct _name data ____cacheline_aligned_in_smp; \ -}; -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE - -enum { -#define BPF_STRUCT_OPS_TYPE(_name) BPF_STRUCT_OPS_TYPE_##_name, -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE - __NR_BPF_STRUCT_OPS_TYPE, -}; - -static struct bpf_struct_ops * const bpf_struct_ops[] = { -#define BPF_STRUCT_OPS_TYPE(_name) \ - [BPF_STRUCT_OPS_TYPE_##_name] = &bpf_##_name, -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE -}; - const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = { }; @@ -108,138 +72,368 @@ const struct bpf_prog_ops bpf_struct_ops_prog_ops = { #endif }; -static const struct btf_type *module_type; +BTF_ID_LIST(st_ops_ids) +BTF_ID(struct, module) +BTF_ID(struct, bpf_struct_ops_common_value) + +enum { + IDX_MODULE_ID, + IDX_ST_OPS_COMMON_VALUE_ID, +}; -void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) +extern struct btf *btf_vmlinux; + +static bool is_valid_value_type(struct btf *btf, s32 value_id, + const struct btf_type *type, + const char *value_name) { - s32 type_id, value_id, module_id; + const struct btf_type *common_value_type; const struct btf_member *member; - struct bpf_struct_ops *st_ops; - const struct btf_type *t; - char value_name[128]; - const char *mname; - u32 i, j; + const struct btf_type *vt, *mt; - /* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */ -#define BPF_STRUCT_OPS_TYPE(_name) BTF_TYPE_EMIT(struct bpf_struct_ops_##_name); -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE + vt = btf_type_by_id(btf, value_id); + if (btf_vlen(vt) != 2) { + pr_warn("The number of %s's members should be 2, but we get %d\n", + value_name, btf_vlen(vt)); + return false; + } + member = btf_type_member(vt); + mt = btf_type_by_id(btf, member->type); + common_value_type = btf_type_by_id(btf_vmlinux, + st_ops_ids[IDX_ST_OPS_COMMON_VALUE_ID]); + if (mt != common_value_type) { + pr_warn("The first member of %s should be bpf_struct_ops_common_value\n", + value_name); + return false; + } + member++; + mt = btf_type_by_id(btf, member->type); + if (mt != type) { + pr_warn("The second member of %s should be %s\n", + value_name, btf_name_by_offset(btf, type->name_off)); + return false; + } - module_id = btf_find_by_name_kind(btf, "module", BTF_KIND_STRUCT); - if (module_id < 0) { - pr_warn("Cannot find struct module in btf_vmlinux\n"); - return; + return true; +} + +static void *bpf_struct_ops_image_alloc(void) +{ + void *image; + int err; + + err = bpf_jit_charge_modmem(PAGE_SIZE); + if (err) + return ERR_PTR(err); + image = arch_alloc_bpf_trampoline(PAGE_SIZE); + if (!image) { + bpf_jit_uncharge_modmem(PAGE_SIZE); + return ERR_PTR(-ENOMEM); } - module_type = btf_type_by_id(btf, module_id); - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - st_ops = bpf_struct_ops[i]; + return image; +} - if (strlen(st_ops->name) + VALUE_PREFIX_LEN >= - sizeof(value_name)) { - pr_warn("struct_ops name %s is too long\n", - st_ops->name); - continue; - } - sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); +void bpf_struct_ops_image_free(void *image) +{ + if (image) { + arch_free_bpf_trampoline(image, PAGE_SIZE); + bpf_jit_uncharge_modmem(PAGE_SIZE); + } +} + +#define MAYBE_NULL_SUFFIX "__nullable" + +/* Prepare argument info for every nullable argument of a member of a + * struct_ops type. + * + * Initialize a struct bpf_struct_ops_arg_info according to type info of + * the arguments of a stub function. (Check kCFI for more information about + * stub functions.) + * + * Each member in the struct_ops type has a struct bpf_struct_ops_arg_info + * to provide an array of struct bpf_ctx_arg_aux, which in turn provides + * the information that used by the verifier to check the arguments of the + * BPF struct_ops program assigned to the member. Here, we only care about + * the arguments that are marked as __nullable. + * + * The array of struct bpf_ctx_arg_aux is eventually assigned to + * prog->aux->ctx_arg_info of BPF struct_ops programs and passed to the + * verifier. (See check_struct_ops_btf_id()) + * + * arg_info->info will be the list of struct bpf_ctx_arg_aux if success. If + * fails, it will be kept untouched. + */ +static int prepare_arg_info(struct btf *btf, + const char *st_ops_name, + const char *member_name, + const struct btf_type *func_proto, void *stub_func_addr, + struct bpf_struct_ops_arg_info *arg_info) +{ + const struct btf_type *stub_func_proto, *pointed_type; + const struct btf_param *stub_args, *args; + struct bpf_ctx_arg_aux *info, *info_buf; + u32 nargs, arg_no, info_cnt = 0; + char ksym[KSYM_SYMBOL_LEN]; + const char *stub_fname; + s32 stub_func_id; + u32 arg_btf_id; + int offset; + + stub_fname = kallsyms_lookup((unsigned long)stub_func_addr, NULL, NULL, NULL, ksym); + if (!stub_fname) { + pr_warn("Cannot find the stub function name for the %s in struct %s\n", + member_name, st_ops_name); + return -ENOENT; + } - value_id = btf_find_by_name_kind(btf, value_name, - BTF_KIND_STRUCT); - if (value_id < 0) { - pr_warn("Cannot find struct %s in btf_vmlinux\n", - value_name); + stub_func_id = btf_find_by_name_kind(btf, stub_fname, BTF_KIND_FUNC); + if (stub_func_id < 0) { + pr_warn("Cannot find the stub function %s in btf\n", stub_fname); + return -ENOENT; + } + + stub_func_proto = btf_type_by_id(btf, stub_func_id); + stub_func_proto = btf_type_by_id(btf, stub_func_proto->type); + + /* Check if the number of arguments of the stub function is the same + * as the number of arguments of the function pointer. + */ + nargs = btf_type_vlen(func_proto); + if (nargs != btf_type_vlen(stub_func_proto)) { + pr_warn("the number of arguments of the stub function %s does not match the number of arguments of the member %s of struct %s\n", + stub_fname, member_name, st_ops_name); + return -EINVAL; + } + + if (!nargs) + return 0; + + args = btf_params(func_proto); + stub_args = btf_params(stub_func_proto); + + info_buf = kcalloc(nargs, sizeof(*info_buf), GFP_KERNEL); + if (!info_buf) + return -ENOMEM; + + /* Prepare info for every nullable argument */ + info = info_buf; + for (arg_no = 0; arg_no < nargs; arg_no++) { + /* Skip arguments that is not suffixed with + * "__nullable". + */ + if (!btf_param_match_suffix(btf, &stub_args[arg_no], + MAYBE_NULL_SUFFIX)) continue; + + /* Should be a pointer to struct */ + pointed_type = btf_type_resolve_ptr(btf, + args[arg_no].type, + &arg_btf_id); + if (!pointed_type || + !btf_type_is_struct(pointed_type)) { + pr_warn("stub function %s has %s tagging to an unsupported type\n", + stub_fname, MAYBE_NULL_SUFFIX); + goto err_out; } - type_id = btf_find_by_name_kind(btf, st_ops->name, - BTF_KIND_STRUCT); - if (type_id < 0) { - pr_warn("Cannot find struct %s in btf_vmlinux\n", - st_ops->name); - continue; + offset = btf_ctx_arg_offset(btf, func_proto, arg_no); + if (offset < 0) { + pr_warn("stub function %s has an invalid trampoline ctx offset for arg#%u\n", + stub_fname, arg_no); + goto err_out; } - t = btf_type_by_id(btf, type_id); - if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { - pr_warn("Cannot support #%u members in struct %s\n", - btf_type_vlen(t), st_ops->name); - continue; + + if (args[arg_no].type != stub_args[arg_no].type) { + pr_warn("arg#%u type in stub function %s does not match with its original func_proto\n", + arg_no, stub_fname); + goto err_out; } - for_each_member(j, t, member) { - const struct btf_type *func_proto; + /* Fill the information of the new argument */ + info->reg_type = + PTR_TRUSTED | PTR_TO_BTF_ID | PTR_MAYBE_NULL; + info->btf_id = arg_btf_id; + info->btf = btf; + info->offset = offset; - mname = btf_name_by_offset(btf, member->name_off); - if (!*mname) { - pr_warn("anon member in struct %s is not supported\n", - st_ops->name); - break; - } + info++; + info_cnt++; + } - if (__btf_member_bitfield_size(t, member)) { - pr_warn("bit field member %s in struct %s is not supported\n", - mname, st_ops->name); - break; - } + if (info_cnt) { + arg_info->info = info_buf; + arg_info->cnt = info_cnt; + } else { + kfree(info_buf); + } - func_proto = btf_type_resolve_func_ptr(btf, - member->type, - NULL); - if (func_proto && - btf_distill_func_proto(log, btf, - func_proto, mname, - &st_ops->func_models[j])) { - pr_warn("Error in parsing func ptr %s in struct %s\n", - mname, st_ops->name); - break; - } - } + return 0; - if (j == btf_type_vlen(t)) { - if (st_ops->init(btf)) { - pr_warn("Error in init bpf_struct_ops %s\n", - st_ops->name); - } else { - st_ops->type_id = type_id; - st_ops->type = t; - st_ops->value_id = value_id; - st_ops->value_type = btf_type_by_id(btf, - value_id); - } - } - } +err_out: + kfree(info_buf); + + return -EINVAL; } -extern struct btf *btf_vmlinux; +/* Clean up the arg_info in a struct bpf_struct_ops_desc. */ +void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc) +{ + struct bpf_struct_ops_arg_info *arg_info; + int i; + + arg_info = st_ops_desc->arg_info; + for (i = 0; i < btf_type_vlen(st_ops_desc->type); i++) + kfree(arg_info[i].info); -static const struct bpf_struct_ops * -bpf_struct_ops_find_value(u32 value_id) + kfree(arg_info); +} + +static bool is_module_member(const struct btf *btf, u32 id) { - unsigned int i; + const struct btf_type *t; - if (!value_id || !btf_vmlinux) - return NULL; + t = btf_type_resolve_ptr(btf, id, NULL); + if (!t) + return false; - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i]->value_id == value_id) - return bpf_struct_ops[i]; - } + if (!__btf_type_is_struct(t) && !btf_type_is_fwd(t)) + return false; - return NULL; + return !strcmp(btf_name_by_offset(btf, t->name_off), "module"); } -const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) +int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff) { - unsigned int i; + void *func_ptr = *(void **)(st_ops->cfi_stubs + moff); - if (!type_id || !btf_vmlinux) - return NULL; + return func_ptr ? 0 : -ENOTSUPP; +} - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i]->type_id == type_id) - return bpf_struct_ops[i]; +int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, + struct btf *btf, + struct bpf_verifier_log *log) +{ + struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; + struct bpf_struct_ops_arg_info *arg_info; + const struct btf_member *member; + const struct btf_type *t; + s32 type_id, value_id; + char value_name[128]; + const char *mname; + int i, err; + + if (strlen(st_ops->name) + VALUE_PREFIX_LEN >= + sizeof(value_name)) { + pr_warn("struct_ops name %s is too long\n", + st_ops->name); + return -EINVAL; + } + sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); + + type_id = btf_find_by_name_kind(btf, st_ops->name, + BTF_KIND_STRUCT); + if (type_id < 0) { + pr_warn("Cannot find struct %s in %s\n", + st_ops->name, btf_get_name(btf)); + return -EINVAL; + } + t = btf_type_by_id(btf, type_id); + if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { + pr_warn("Cannot support #%u members in struct %s\n", + btf_type_vlen(t), st_ops->name); + return -EINVAL; } - return NULL; + value_id = btf_find_by_name_kind(btf, value_name, + BTF_KIND_STRUCT); + if (value_id < 0) { + pr_warn("Cannot find struct %s in %s\n", + value_name, btf_get_name(btf)); + return -EINVAL; + } + if (!is_valid_value_type(btf, value_id, t, value_name)) + return -EINVAL; + + arg_info = kcalloc(btf_type_vlen(t), sizeof(*arg_info), + GFP_KERNEL); + if (!arg_info) + return -ENOMEM; + + st_ops_desc->arg_info = arg_info; + st_ops_desc->type = t; + st_ops_desc->type_id = type_id; + st_ops_desc->value_id = value_id; + st_ops_desc->value_type = btf_type_by_id(btf, value_id); + + for_each_member(i, t, member) { + const struct btf_type *func_proto; + void **stub_func_addr; + u32 moff; + + moff = __btf_member_bit_offset(t, member) / 8; + mname = btf_name_by_offset(btf, member->name_off); + if (!*mname) { + pr_warn("anon member in struct %s is not supported\n", + st_ops->name); + err = -EOPNOTSUPP; + goto errout; + } + + if (__btf_member_bitfield_size(t, member)) { + pr_warn("bit field member %s in struct %s is not supported\n", + mname, st_ops->name); + err = -EOPNOTSUPP; + goto errout; + } + + if (!st_ops_ids[IDX_MODULE_ID] && is_module_member(btf, member->type)) { + pr_warn("'struct module' btf id not found. Is CONFIG_MODULES enabled? bpf_struct_ops '%s' needs module support.\n", + st_ops->name); + err = -EOPNOTSUPP; + goto errout; + } + + func_proto = btf_type_resolve_func_ptr(btf, + member->type, + NULL); + + /* The member is not a function pointer or + * the function pointer is not supported. + */ + if (!func_proto || bpf_struct_ops_supported(st_ops, moff)) + continue; + + if (btf_distill_func_proto(log, btf, + func_proto, mname, + &st_ops->func_models[i])) { + pr_warn("Error in parsing func ptr %s in struct %s\n", + mname, st_ops->name); + err = -EINVAL; + goto errout; + } + + stub_func_addr = *(void **)(st_ops->cfi_stubs + moff); + err = prepare_arg_info(btf, st_ops->name, mname, + func_proto, stub_func_addr, + arg_info + i); + if (err) + goto errout; + } + + if (st_ops->init(btf)) { + pr_warn("Error in init bpf_struct_ops %s\n", + st_ops->name); + err = -EINVAL; + goto errout; + } + + return 0; + +errout: + bpf_struct_ops_desc_release(st_ops_desc); + + return err; } static int bpf_struct_ops_map_get_next_key(struct bpf_map *map, void *key, @@ -265,7 +459,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, kvalue = &st_map->kvalue; /* Pair with smp_store_release() during map_update */ - state = smp_load_acquire(&kvalue->state); + state = smp_load_acquire(&kvalue->common.state); if (state == BPF_STRUCT_OPS_STATE_INIT) { memset(value, 0, map->value_size); return 0; @@ -276,7 +470,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, */ uvalue = value; memcpy(uvalue, st_map->uvalue, map->value_size); - uvalue->state = state; + uvalue->common.state = state; /* This value offers the user space a general estimate of how * many sockets are still utilizing this struct_ops for TCP @@ -284,7 +478,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, * should sufficiently meet our present goals. */ refcnt = atomic64_read(&map->refcnt) - atomic64_read(&map->usercnt); - refcount_set(&uvalue->refcnt, max_t(s64, refcnt, 0)); + refcount_set(&uvalue->common.refcnt, max_t(s64, refcnt, 0)); return 0; } @@ -296,10 +490,9 @@ static void *bpf_struct_ops_map_lookup_elem(struct bpf_map *map, void *key) static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) { - const struct btf_type *t = st_map->st_ops->type; u32 i; - for (i = 0; i < btf_type_vlen(t); i++) { + for (i = 0; i < st_map->links_cnt; i++) { if (st_map->links[i]) { bpf_link_put(st_map->links[i]); st_map->links[i] = NULL; @@ -307,7 +500,16 @@ static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) } } -static int check_zero_holes(const struct btf_type *t, void *data) +static void bpf_struct_ops_map_free_image(struct bpf_struct_ops_map *st_map) +{ + int i; + + for (i = 0; i < st_map->image_pages_cnt; i++) + bpf_struct_ops_image_free(st_map->image_pages[i]); + st_map->image_pages_cnt = 0; +} + +static int check_zero_holes(const struct btf *btf, const struct btf_type *t, void *data) { const struct btf_member *member; u32 i, moff, msize, prev_mend = 0; @@ -319,8 +521,8 @@ static int check_zero_holes(const struct btf_type *t, void *data) memchr_inv(data + prev_mend, 0, moff - prev_mend)) return -EINVAL; - mtype = btf_type_by_id(btf_vmlinux, member->type); - mtype = btf_resolve_size(btf_vmlinux, mtype, &msize); + mtype = btf_type_by_id(btf, member->type); + mtype = btf_resolve_size(btf, mtype, &msize); if (IS_ERR(mtype)) return PTR_ERR(mtype); prev_mend = moff + msize; @@ -352,9 +554,12 @@ const struct bpf_link_ops bpf_struct_ops_link_lops = { int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, struct bpf_tramp_link *link, const struct btf_func_model *model, - void *image, void *image_end) + void **_image, u32 *_image_off, + bool allow_alloc) { - u32 flags; + u32 flags, image_off = *_image_off; + void *image = *_image; + int size; tlinks[BPF_TRAMP_FENTRY].links[0] = link; tlinks[BPF_TRAMP_FENTRY].nr_links = 1; @@ -362,23 +567,51 @@ int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, * and it must be used alone. */ flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0; - return arch_prepare_bpf_trampoline(NULL, image, image_end, + + size = arch_bpf_trampoline_size(model, flags, tlinks, NULL); + if (size <= 0) + return size ? : -EFAULT; + + /* Allocate image buffer if necessary */ + if (!image || size > PAGE_SIZE - image_off) { + if (!allow_alloc) + return -E2BIG; + + image = bpf_struct_ops_image_alloc(); + if (IS_ERR(image)) + return PTR_ERR(image); + image_off = 0; + } + + size = arch_prepare_bpf_trampoline(NULL, image + image_off, + image + PAGE_SIZE, model, flags, tlinks, NULL); + if (size <= 0) { + if (image != *_image) + bpf_struct_ops_image_free(image); + return size ? : -EFAULT; + } + + *_image = image; + *_image_off = image_off + size; + return 0; } static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; - const struct bpf_struct_ops *st_ops = st_map->st_ops; + const struct bpf_struct_ops_desc *st_ops_desc = st_map->st_ops_desc; + const struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; struct bpf_struct_ops_value *uvalue, *kvalue; + const struct btf_type *module_type; const struct btf_member *member; - const struct btf_type *t = st_ops->type; + const struct btf_type *t = st_ops_desc->type; struct bpf_tramp_links *tlinks; void *udata, *kdata; int prog_fd, err; - void *image, *image_end; - u32 i; + u32 i, trampoline_start, image_off = 0; + void *cur_image = NULL, *image = NULL; if (flags) return -EINVAL; @@ -386,16 +619,16 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (*(u32 *)key != 0) return -E2BIG; - err = check_zero_holes(st_ops->value_type, value); + err = check_zero_holes(st_map->btf, st_ops_desc->value_type, value); if (err) return err; uvalue = value; - err = check_zero_holes(t, uvalue->data); + err = check_zero_holes(st_map->btf, t, uvalue->data); if (err) return err; - if (uvalue->state || refcount_read(&uvalue->refcnt)) + if (uvalue->common.state || refcount_read(&uvalue->common.refcnt)) return -EINVAL; tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL); @@ -407,7 +640,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, mutex_lock(&st_map->lock); - if (kvalue->state != BPF_STRUCT_OPS_STATE_INIT) { + if (kvalue->common.state != BPF_STRUCT_OPS_STATE_INIT) { err = -EBUSY; goto unlock; } @@ -416,9 +649,8 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, udata = &uvalue->data; kdata = &kvalue->data; - image = st_map->image; - image_end = st_map->image + PAGE_SIZE; + module_type = btf_type_by_id(btf_vmlinux, st_ops_ids[IDX_MODULE_ID]); for_each_member(i, t, member) { const struct btf_type *mtype, *ptype; struct bpf_prog *prog; @@ -426,7 +658,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, u32 moff; moff = __btf_member_bit_offset(t, member) / 8; - ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); + ptype = btf_type_resolve_ptr(st_map->btf, member->type, NULL); if (ptype == module_type) { if (*(void **)(udata + moff)) goto reset_unlock; @@ -451,8 +683,8 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (!ptype || !btf_type_is_func_proto(ptype)) { u32 msize; - mtype = btf_type_by_id(btf_vmlinux, member->type); - mtype = btf_resolve_size(btf_vmlinux, mtype, &msize); + mtype = btf_type_by_id(st_map->btf, member->type); + mtype = btf_resolve_size(st_map->btf, mtype, &msize); if (IS_ERR(mtype)) { err = PTR_ERR(mtype); goto reset_unlock; @@ -478,7 +710,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, } if (prog->type != BPF_PROG_TYPE_STRUCT_OPS || - prog->aux->attach_btf_id != st_ops->type_id || + prog->aux->attach_btf_id != st_ops_desc->type_id || prog->expected_attach_type != i) { bpf_prog_put(prog); err = -EINVAL; @@ -495,36 +727,46 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, &bpf_struct_ops_link_lops, prog); st_map->links[i] = &link->link; + trampoline_start = image_off; err = bpf_struct_ops_prepare_trampoline(tlinks, link, - &st_ops->func_models[i], - image, image_end); + &st_ops->func_models[i], + &image, &image_off, + st_map->image_pages_cnt < MAX_TRAMP_IMAGE_PAGES); + if (err) + goto reset_unlock; + + if (cur_image != image) { + st_map->image_pages[st_map->image_pages_cnt++] = image; + cur_image = image; + trampoline_start = 0; + } if (err < 0) goto reset_unlock; - *(void **)(kdata + moff) = image; - image += err; + *(void **)(kdata + moff) = image + trampoline_start; /* put prog_id to udata */ *(unsigned long *)(udata + moff) = prog->aux->id; } + if (st_ops->validate) { + err = st_ops->validate(kdata); + if (err) + goto reset_unlock; + } + for (i = 0; i < st_map->image_pages_cnt; i++) + arch_protect_bpf_trampoline(st_map->image_pages[i], PAGE_SIZE); + if (st_map->map.map_flags & BPF_F_LINK) { err = 0; - if (st_ops->validate) { - err = st_ops->validate(kdata); - if (err) - goto reset_unlock; - } - set_memory_rox((long)st_map->image, 1); /* Let bpf_link handle registration & unregistration. * * Pair with smp_load_acquire() during lookup_elem(). */ - smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_READY); + smp_store_release(&kvalue->common.state, BPF_STRUCT_OPS_STATE_READY); goto unlock; } - set_memory_rox((long)st_map->image, 1); err = st_ops->reg(kdata); if (likely(!err)) { /* This refcnt increment on the map here after @@ -538,7 +780,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, * It ensures the above udata updates (e.g. prog->aux->id) * can be seen once BPF_STRUCT_OPS_STATE_INUSE is set. */ - smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_INUSE); + smp_store_release(&kvalue->common.state, BPF_STRUCT_OPS_STATE_INUSE); goto unlock; } @@ -547,10 +789,9 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, * there was a race in registering the struct_ops (under the same name) to * a sub-system through different struct_ops's maps. */ - set_memory_nx((long)st_map->image, 1); - set_memory_rw((long)st_map->image, 1); reset_unlock: + bpf_struct_ops_map_free_image(st_map); bpf_struct_ops_map_put_progs(st_map); memset(uvalue, 0, map->value_size); memset(kvalue, 0, map->value_size); @@ -569,12 +810,12 @@ static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) if (st_map->map.map_flags & BPF_F_LINK) return -EOPNOTSUPP; - prev_state = cmpxchg(&st_map->kvalue.state, + prev_state = cmpxchg(&st_map->kvalue.common.state, BPF_STRUCT_OPS_STATE_INUSE, BPF_STRUCT_OPS_STATE_TOBEFREE); switch (prev_state) { case BPF_STRUCT_OPS_STATE_INUSE: - st_map->st_ops->unreg(&st_map->kvalue.data); + st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data); bpf_map_put(map); return 0; case BPF_STRUCT_OPS_STATE_TOBEFREE: @@ -591,6 +832,7 @@ static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key, struct seq_file *m) { + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; void *value; int err; @@ -600,7 +842,8 @@ static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key, err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); if (!err) { - btf_type_seq_show(btf_vmlinux, map->btf_vmlinux_value_type_id, + btf_type_seq_show(st_map->btf, + map->btf_vmlinux_value_type_id, value, m); seq_puts(m, "\n"); } @@ -615,13 +858,22 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map) if (st_map->links) bpf_struct_ops_map_put_progs(st_map); bpf_map_area_free(st_map->links); - bpf_jit_free_exec(st_map->image); + bpf_struct_ops_map_free_image(st_map); bpf_map_area_free(st_map->uvalue); bpf_map_area_free(st_map); } static void bpf_struct_ops_map_free(struct bpf_map *map) { + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + + /* st_ops->owner was acquired during map_alloc to implicitly holds + * the btf's refcnt. The acquire was only done when btf_is_module() + * st_map->btf cannot be NULL here. + */ + if (btf_is_module(st_map->btf)) + module_put(st_map->st_ops_desc->st_ops->owner); + /* The struct_ops's function may switch to another struct_ops. * * For example, bpf_tcp_cc_x->init() may switch to @@ -645,28 +897,61 @@ static void bpf_struct_ops_map_free(struct bpf_map *map) static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr) { if (attr->key_size != sizeof(unsigned int) || attr->max_entries != 1 || - (attr->map_flags & ~BPF_F_LINK) || !attr->btf_vmlinux_value_type_id) + (attr->map_flags & ~(BPF_F_LINK | BPF_F_VTYPE_BTF_OBJ_FD)) || + !attr->btf_vmlinux_value_type_id) return -EINVAL; return 0; } static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) { - const struct bpf_struct_ops *st_ops; + const struct bpf_struct_ops_desc *st_ops_desc; size_t st_map_size; struct bpf_struct_ops_map *st_map; const struct btf_type *t, *vt; + struct module *mod = NULL; struct bpf_map *map; + struct btf *btf; + int ret; + + if (attr->map_flags & BPF_F_VTYPE_BTF_OBJ_FD) { + /* The map holds btf for its whole life time. */ + btf = btf_get_by_fd(attr->value_type_btf_obj_fd); + if (IS_ERR(btf)) + return ERR_CAST(btf); + if (!btf_is_module(btf)) { + btf_put(btf); + return ERR_PTR(-EINVAL); + } - st_ops = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id); - if (!st_ops) - return ERR_PTR(-ENOTSUPP); + mod = btf_try_get_module(btf); + /* mod holds a refcnt to btf. We don't need an extra refcnt + * here. + */ + btf_put(btf); + if (!mod) + return ERR_PTR(-EINVAL); + } else { + btf = bpf_get_btf_vmlinux(); + if (IS_ERR(btf)) + return ERR_CAST(btf); + if (!btf) + return ERR_PTR(-ENOTSUPP); + } + + st_ops_desc = bpf_struct_ops_find_value(btf, attr->btf_vmlinux_value_type_id); + if (!st_ops_desc) { + ret = -ENOTSUPP; + goto errout; + } - vt = st_ops->value_type; - if (attr->value_size != vt->size) - return ERR_PTR(-EINVAL); + vt = st_ops_desc->value_type; + if (attr->value_size != vt->size) { + ret = -EINVAL; + goto errout; + } - t = st_ops->type; + t = st_ops_desc->type; st_map_size = sizeof(*st_map) + /* kvalue stores the @@ -675,34 +960,43 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) (vt->size - sizeof(struct bpf_struct_ops_value)); st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE); - if (!st_map) - return ERR_PTR(-ENOMEM); + if (!st_map) { + ret = -ENOMEM; + goto errout; + } - st_map->st_ops = st_ops; + st_map->st_ops_desc = st_ops_desc; map = &st_map->map; st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE); + st_map->links_cnt = btf_type_vlen(t); st_map->links = - bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *), + bpf_map_area_alloc(st_map->links_cnt * sizeof(struct bpf_links *), NUMA_NO_NODE); - st_map->image = bpf_jit_alloc_exec(PAGE_SIZE); - if (!st_map->uvalue || !st_map->links || !st_map->image) { - __bpf_struct_ops_map_free(map); - return ERR_PTR(-ENOMEM); + if (!st_map->uvalue || !st_map->links) { + ret = -ENOMEM; + goto errout_free; } + st_map->btf = btf; mutex_init(&st_map->lock); - set_vm_flush_reset_perms(st_map->image); bpf_map_init_from_attr(map, attr); return map; + +errout_free: + __bpf_struct_ops_map_free(map); +errout: + module_put(mod); + + return ERR_PTR(ret); } static u64 bpf_struct_ops_map_mem_usage(const struct bpf_map *map) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; - const struct bpf_struct_ops *st_ops = st_map->st_ops; - const struct btf_type *vt = st_ops->value_type; + const struct bpf_struct_ops_desc *st_ops_desc = st_map->st_ops_desc; + const struct btf_type *vt = st_ops_desc->value_type; u64 usage; usage = sizeof(*st_map) + @@ -761,7 +1055,7 @@ static bool bpf_struct_ops_valid_to_reg(struct bpf_map *map) return map->map_type == BPF_MAP_TYPE_STRUCT_OPS && map->map_flags & BPF_F_LINK && /* Pair with smp_store_release() during map_update */ - smp_load_acquire(&st_map->kvalue.state) == BPF_STRUCT_OPS_STATE_READY; + smp_load_acquire(&st_map->kvalue.common.state) == BPF_STRUCT_OPS_STATE_READY; } static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link) @@ -776,7 +1070,7 @@ static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link) /* st_link->map can be NULL if * bpf_struct_ops_link_create() fails to register. */ - st_map->st_ops->unreg(&st_map->kvalue.data); + st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data); bpf_map_put(&st_map->map); } kfree(st_link); @@ -823,7 +1117,7 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map if (!bpf_struct_ops_valid_to_reg(new_map)) return -EINVAL; - if (!st_map->st_ops->update) + if (!st_map->st_ops_desc->st_ops->update) return -EOPNOTSUPP; mutex_lock(&update_mutex); @@ -836,12 +1130,12 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map old_st_map = container_of(old_map, struct bpf_struct_ops_map, map); /* The new and old struct_ops must be the same type. */ - if (st_map->st_ops != old_st_map->st_ops) { + if (st_map->st_ops_desc != old_st_map->st_ops_desc) { err = -EINVAL; goto err_out; } - err = st_map->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data); + err = st_map->st_ops_desc->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data); if (err) goto err_out; @@ -892,7 +1186,7 @@ int bpf_struct_ops_link_create(union bpf_attr *attr) if (err) goto err_out; - err = st_map->st_ops->reg(st_map->kvalue.data); + err = st_map->st_ops_desc->st_ops->reg(st_map->kvalue.data); if (err) { bpf_link_cleanup(&link_primer); link = NULL; @@ -908,3 +1202,9 @@ int bpf_struct_ops_link_create(union bpf_attr *attr) return err; } +void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + + info->btf_vmlinux_id = btf_obj_id(st_map->btf); +} diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h deleted file mode 100644 index 5678a9ddf8178c2d222bb84c612097eb382f9139..0000000000000000000000000000000000000000 --- a/kernel/bpf/bpf_struct_ops_types.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* internal file - do not include directly */ - -#ifdef CONFIG_BPF_JIT -#ifdef CONFIG_NET -BPF_STRUCT_OPS_TYPE(bpf_dummy_ops) -#endif -#ifdef CONFIG_INET -#include -BPF_STRUCT_OPS_TYPE(tcp_congestion_ops) -#endif -#endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 7c888ee0ccc743c371fdfac2c6ea19c537d019ea..bad8cb7ecbe0b4495fbd1b89870d18d845ab3737 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -245,6 +246,12 @@ struct btf_id_dtor_kfunc_tab { struct btf_id_dtor_kfunc dtors[]; }; +struct btf_struct_ops_tab { + u32 cnt; + u32 capacity; + struct bpf_struct_ops_desc ops[]; +}; + struct btf { void *data; struct btf_type **types; @@ -262,6 +269,7 @@ struct btf { struct btf_kfunc_set_tab *kfunc_set_tab; struct btf_id_dtor_kfunc_tab *dtor_kfunc_tab; struct btf_struct_metas *struct_meta_tab; + struct btf_struct_ops_tab *struct_ops_tab; /* split BTF support */ struct btf *base_btf; @@ -492,11 +500,6 @@ bool btf_type_is_void(const struct btf_type *t) return t == &btf_void; } -static bool btf_type_is_fwd(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_FWD; -} - static bool btf_type_is_datasec(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; @@ -1692,11 +1695,27 @@ static void btf_free_struct_meta_tab(struct btf *btf) btf->struct_meta_tab = NULL; } +static void btf_free_struct_ops_tab(struct btf *btf) +{ + struct btf_struct_ops_tab *tab = btf->struct_ops_tab; + u32 i; + + if (!tab) + return; + + for (i = 0; i < tab->cnt; i++) + bpf_struct_ops_desc_release(&tab->ops[i]); + + kfree(tab); + btf->struct_ops_tab = NULL; +} + static void btf_free(struct btf *btf) { btf_free_struct_meta_tab(btf); btf_free_dtor_kfunc_tab(btf); btf_free_kfunc_set_tab(btf); + btf_free_struct_ops_tab(btf); kvfree(btf->types); kvfree(btf->resolved_sizes); kvfree(btf->resolved_ids); @@ -1711,6 +1730,11 @@ static void btf_free_rcu(struct rcu_head *rcu) btf_free(btf); } +const char *btf_get_name(const struct btf *btf) +{ + return btf->name; +} + void btf_get(struct btf *btf) { refcount_inc(&btf->refcnt); @@ -5771,8 +5795,6 @@ struct btf *btf_parse_vmlinux(void) /* btf_parse_vmlinux() runs under bpf_verifier_lock */ bpf_ctx_convert.t = btf_type_by_id(btf, bpf_ctx_convert_btf_id[0]); - bpf_struct_ops_init(btf, log); - refcount_set(&btf->refcnt, 1); err = btf_alloc_id(btf); @@ -6123,6 +6145,25 @@ static const struct bpf_raw_tp_null_args raw_tp_null_args[] = { /* snd_firewire_lib */ { "amdtp_packet", 0x100 }, }; +int btf_ctx_arg_offset(const struct btf *btf, const struct btf_type *func_proto, + u32 arg_no) +{ + const struct btf_param *args; + const struct btf_type *t; + int off = 0, i; + u32 sz; + + args = btf_params(func_proto); + for (i = 0; i < arg_no; i++) { + t = btf_type_by_id(btf, args[i].type); + t = btf_resolve_size(btf, t, &sz); + if (IS_ERR(t)) + return PTR_ERR(t); + off += roundup(sz, 8); + } + + return off; +} bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, @@ -6273,7 +6314,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, } info->reg_type = ctx_arg_info->reg_type; - info->btf = btf_vmlinux; + info->btf = ctx_arg_info->btf ? : btf_vmlinux; info->btf_id = ctx_arg_info->btf_id; return true; } @@ -6371,6 +6412,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, } return true; } +EXPORT_SYMBOL_GPL(btf_ctx_access); enum bpf_struct_walk_result { /* < 0 error */ @@ -7836,15 +7878,44 @@ BTF_ID_LIST_GLOBAL(btf_tracing_ids, MAX_BTF_TRACING_TYPE) BTF_TRACING_TYPE_xxx #undef BTF_TRACING_TYPE +/* Validate well-formedness of iter argument type. + * On success, return positive BTF ID of iter state's STRUCT type. + * On error, negative error is returned. + */ +int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx) +{ + const struct btf_param *arg; + const struct btf_type *t; + const char *name; + int btf_id; + + if (btf_type_vlen(func) <= arg_idx) + return -EINVAL; + + arg = &btf_params(func)[arg_idx]; + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!t || !btf_type_is_ptr(t)) + return -EINVAL; + t = btf_type_skip_modifiers(btf, t->type, &btf_id); + if (!t || !__btf_type_is_struct(t)) + return -EINVAL; + + name = btf_name_by_offset(btf, t->name_off); + if (!name || strncmp(name, ITER_PREFIX, sizeof(ITER_PREFIX) - 1)) + return -EINVAL; + + return btf_id; +} + static int btf_check_iter_kfuncs(struct btf *btf, const char *func_name, const struct btf_type *func, u32 func_flags) { u32 flags = func_flags & (KF_ITER_NEW | KF_ITER_NEXT | KF_ITER_DESTROY); - const char *name, *sfx, *iter_name; - const struct btf_param *arg; + const char *sfx, *iter_name; const struct btf_type *t; char exp_name[128]; u32 nr_args; + int btf_id; /* exactly one of KF_ITER_{NEW,NEXT,DESTROY} can be set */ if (!flags || (flags & (flags - 1))) @@ -7855,28 +7926,21 @@ static int btf_check_iter_kfuncs(struct btf *btf, const char *func_name, if (nr_args < 1) return -EINVAL; - arg = &btf_params(func)[0]; - t = btf_type_skip_modifiers(btf, arg->type, NULL); - if (!t || !btf_type_is_ptr(t)) - return -EINVAL; - t = btf_type_skip_modifiers(btf, t->type, NULL); - if (!t || !__btf_type_is_struct(t)) - return -EINVAL; - - name = btf_name_by_offset(btf, t->name_off); - if (!name || strncmp(name, ITER_PREFIX, sizeof(ITER_PREFIX) - 1)) - return -EINVAL; + btf_id = btf_check_iter_arg(btf, func, 0); + if (btf_id < 0) + return btf_id; /* sizeof(struct bpf_iter_) should be a multiple of 8 to * fit nicely in stack slots */ + t = btf_type_by_id(btf, btf_id); if (t->size == 0 || (t->size % 8)) return -EINVAL; /* validate bpf_iter__{new,next,destroy}(struct bpf_iter_ *) * naming pattern */ - iter_name = name + sizeof(ITER_PREFIX) - 1; + iter_name = btf_name_by_offset(btf, t->name_off) + sizeof(ITER_PREFIX) - 1; if (flags & KF_ITER_NEW) sfx = "new"; else if (flags & KF_ITER_NEXT) @@ -8193,6 +8257,14 @@ int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, { enum btf_kfunc_hook hook; + /* All kfuncs need to be tagged as such in BTF. + * WARN() for initcall registrations that do not check errors. + */ + if (!(kset->set->flags & BTF_SET8_KFUNCS)) { + WARN_ON(!kset->owner); + return -EINVAL; + } + hook = bpf_prog_type_to_kfunc_hook(prog_type); return __register_btf_kfunc_id_set(hook, kset); } @@ -8857,3 +8929,141 @@ bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, return !strncmp(reg_name, arg_name, cmp_len); } + +#ifdef CONFIG_BPF_JIT +static int +btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops, + struct bpf_verifier_log *log) +{ + struct btf_struct_ops_tab *tab, *new_tab; + int i, err; + + tab = btf->struct_ops_tab; + if (!tab) { + tab = kzalloc(offsetof(struct btf_struct_ops_tab, ops[4]), + GFP_KERNEL); + if (!tab) + return -ENOMEM; + tab->capacity = 4; + btf->struct_ops_tab = tab; + } + + for (i = 0; i < tab->cnt; i++) + if (tab->ops[i].st_ops == st_ops) + return -EEXIST; + + if (tab->cnt == tab->capacity) { + new_tab = krealloc(tab, + offsetof(struct btf_struct_ops_tab, + ops[tab->capacity * 2]), + GFP_KERNEL); + if (!new_tab) + return -ENOMEM; + tab = new_tab; + tab->capacity *= 2; + btf->struct_ops_tab = tab; + } + + tab->ops[btf->struct_ops_tab->cnt].st_ops = st_ops; + + err = bpf_struct_ops_desc_init(&tab->ops[btf->struct_ops_tab->cnt], btf, log); + if (err) + return err; + + btf->struct_ops_tab->cnt++; + + return 0; +} + +const struct bpf_struct_ops_desc * +bpf_struct_ops_find_value(struct btf *btf, u32 value_id) +{ + const struct bpf_struct_ops_desc *st_ops_list; + unsigned int i; + u32 cnt; + + if (!value_id) + return NULL; + if (!btf->struct_ops_tab) + return NULL; + + cnt = btf->struct_ops_tab->cnt; + st_ops_list = btf->struct_ops_tab->ops; + for (i = 0; i < cnt; i++) { + if (st_ops_list[i].value_id == value_id) + return &st_ops_list[i]; + } + + return NULL; +} + +const struct bpf_struct_ops_desc * +bpf_struct_ops_find(struct btf *btf, u32 type_id) +{ + const struct bpf_struct_ops_desc *st_ops_list; + unsigned int i; + u32 cnt; + + if (!type_id) + return NULL; + if (!btf->struct_ops_tab) + return NULL; + + cnt = btf->struct_ops_tab->cnt; + st_ops_list = btf->struct_ops_tab->ops; + for (i = 0; i < cnt; i++) { + if (st_ops_list[i].type_id == type_id) + return &st_ops_list[i]; + } + + return NULL; +} + +int __register_bpf_struct_ops(struct bpf_struct_ops *st_ops) +{ + struct bpf_verifier_log *log; + struct btf *btf; + int err = 0; + + btf = btf_get_module_btf(st_ops->owner); + if (!btf) + return check_btf_kconfigs(st_ops->owner, "struct_ops"); + if (IS_ERR(btf)) + return PTR_ERR(btf); + + log = kzalloc(sizeof(*log), GFP_KERNEL | __GFP_NOWARN); + if (!log) { + err = -ENOMEM; + goto errout; + } + + log->level = BPF_LOG_KERNEL; + + err = btf_add_struct_ops(btf, st_ops, log); + +errout: + kfree(log); + btf_put(btf); + + return err; +} +EXPORT_SYMBOL_GPL(__register_bpf_struct_ops); +#endif + +bool btf_param_match_suffix(const struct btf *btf, + const struct btf_param *arg, + const char *suffix) +{ + int suffix_len = strlen(suffix), len; + const char *param_name; + + /* In the future, this can be ported to use BTF tagging */ + param_name = btf_name_by_offset(btf, arg->name_off); + if (str_is_empty(param_name)) + return false; + len = strlen(param_name); + if (len <= suffix_len) + return false; + param_name += len - suffix_len; + return !strncmp(param_name, suffix, suffix_len); +} diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c index 810378f04fbcace6bed0b30394c2bc711f5f196d..f04a468cf6a72688121ced9e4ddcf0555b7758c5 100644 --- a/kernel/bpf/cgroup_iter.c +++ b/kernel/bpf/cgroup_iter.c @@ -282,7 +282,7 @@ static struct bpf_iter_reg bpf_cgroup_reg_info = { .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__cgroup, cgroup), - PTR_TO_BTF_ID_OR_NULL }, + PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED }, }, .seq_info = &cgroup_iter_seq_info, }; @@ -294,3 +294,66 @@ static int __init bpf_cgroup_iter_init(void) } late_initcall(bpf_cgroup_iter_init); + +struct bpf_iter_css { + __u64 __opaque[3]; +} __attribute__((aligned(8))); + +struct bpf_iter_css_kern { + struct cgroup_subsys_state *start; + struct cgroup_subsys_state *pos; + unsigned int flags; +} __attribute__((aligned(8))); + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_iter_css_new(struct bpf_iter_css *it, + struct cgroup_subsys_state *start, unsigned int flags) +{ + struct bpf_iter_css_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(struct bpf_iter_css_kern) > sizeof(struct bpf_iter_css)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_css_kern) != __alignof__(struct bpf_iter_css)); + + kit->start = NULL; + switch (flags) { + case BPF_CGROUP_ITER_DESCENDANTS_PRE: + case BPF_CGROUP_ITER_DESCENDANTS_POST: + case BPF_CGROUP_ITER_ANCESTORS_UP: + break; + default: + return -EINVAL; + } + + kit->start = start; + kit->pos = NULL; + kit->flags = flags; + return 0; +} + +__bpf_kfunc struct cgroup_subsys_state *bpf_iter_css_next(struct bpf_iter_css *it) +{ + struct bpf_iter_css_kern *kit = (void *)it; + + if (!kit->start) + return NULL; + + switch (kit->flags) { + case BPF_CGROUP_ITER_DESCENDANTS_PRE: + kit->pos = css_next_descendant_pre(kit->pos, kit->start); + break; + case BPF_CGROUP_ITER_DESCENDANTS_POST: + kit->pos = css_next_descendant_post(kit->pos, kit->start); + break; + case BPF_CGROUP_ITER_ANCESTORS_UP: + kit->pos = kit->pos ? kit->pos->parent : kit->start; + } + + return kit->pos; +} + +__bpf_kfunc void bpf_iter_css_destroy(struct bpf_iter_css *it) +{ +} + +__bpf_kfunc_end_defs(); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 17f0df3dae00a12f7fb52fdb712688366697b23e..4dca8a24adbb54677390ed1a24eb36e836f7d11d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -942,20 +942,20 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns) return ptr; } -void bpf_prog_pack_free(struct bpf_binary_header *hdr) +void bpf_prog_pack_free(void *ptr, u32 size) { struct bpf_prog_pack *pack = NULL, *tmp; unsigned int nbits; unsigned long pos; mutex_lock(&pack_mutex); - if (hdr->size > BPF_PROG_PACK_SIZE) { - bpf_jit_free_exec(hdr); + if (size > BPF_PROG_PACK_SIZE) { + bpf_jit_free_exec(ptr); goto out; } list_for_each_entry(tmp, &pack_list, list) { - if ((void *)hdr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > (void *)hdr) { + if (ptr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > ptr) { pack = tmp; break; } @@ -964,10 +964,10 @@ void bpf_prog_pack_free(struct bpf_binary_header *hdr) if (WARN_ONCE(!pack, "bpf_prog_pack bug\n")) goto out; - nbits = BPF_PROG_SIZE_TO_NBITS(hdr->size); - pos = ((unsigned long)hdr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT; + nbits = BPF_PROG_SIZE_TO_NBITS(size); + pos = ((unsigned long)ptr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT; - WARN_ONCE(bpf_arch_text_invalidate(hdr, hdr->size), + WARN_ONCE(bpf_arch_text_invalidate(ptr, size), "bpf_prog_pack bug: missing bpf_arch_text_invalidate?\n"); bitmap_clear(pack->bitmap, pos, nbits); @@ -1114,8 +1114,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr, *rw_header = kvmalloc(size, GFP_KERNEL); if (!*rw_header) { - bpf_arch_text_copy(&ro_header->size, &size, sizeof(size)); - bpf_prog_pack_free(ro_header); + bpf_prog_pack_free(ro_header, size); bpf_jit_uncharge_modmem(size); return NULL; } @@ -1146,7 +1145,7 @@ int bpf_jit_binary_pack_finalize(struct bpf_prog *prog, kvfree(rw_header); if (IS_ERR(ptr)) { - bpf_prog_pack_free(ro_header); + bpf_prog_pack_free(ro_header, ro_header->size); return PTR_ERR(ptr); } return 0; @@ -1167,7 +1166,7 @@ void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, { u32 size = ro_header->size; - bpf_prog_pack_free(ro_header); + bpf_prog_pack_free(ro_header, size); kvfree(rw_header); bpf_jit_uncharge_modmem(size); } diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c index 6983af8e093c4b0260f64d62d7c5d040e67e647f..7e5894110454d576cd4358d70fe90a7f0f114aae 100644 --- a/kernel/bpf/cpumask.c +++ b/kernel/bpf/cpumask.c @@ -34,9 +34,7 @@ static bool cpu_valid(u32 cpu) return cpu < nr_cpu_ids; } -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "Global kfuncs as their definitions will be in BTF"); +__bpf_kfunc_start_defs(); /** * bpf_cpumask_create() - Create a mutable BPF cpumask. @@ -407,9 +405,9 @@ __bpf_kfunc u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, return cpumask_any_and_distribute(src1, src2); } -__diag_pop(); +__bpf_kfunc_end_defs(); -BTF_SET8_START(cpumask_kfunc_btf_ids) +BTF_KFUNCS_START(cpumask_kfunc_btf_ids) BTF_ID_FLAGS(func, bpf_cpumask_create, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_cpumask_release, KF_RELEASE) BTF_ID_FLAGS(func, bpf_cpumask_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) @@ -434,7 +432,7 @@ BTF_ID_FLAGS(func, bpf_cpumask_full, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_copy, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_any_distribute, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_any_and_distribute, KF_RCU) -BTF_SET8_END(cpumask_kfunc_btf_ids) +BTF_KFUNCS_END(cpumask_kfunc_btf_ids) static const struct btf_kfunc_id_set cpumask_kfunc_set = { .owner = THIS_MODULE, diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c index fa3e9225aedc0a81ceedb7b5fc7345268538b29c..70fb82bf16370ed15c419cdb7a5b9ca0279660d5 100644 --- a/kernel/bpf/dispatcher.c +++ b/kernel/bpf/dispatcher.c @@ -150,14 +150,11 @@ void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, goto out; d->rw_image = bpf_jit_alloc_exec(PAGE_SIZE); if (!d->rw_image) { - u32 size = PAGE_SIZE; - - bpf_arch_text_copy(d->image, &size, sizeof(size)); - bpf_prog_pack_free((struct bpf_binary_header *)d->image); + bpf_prog_pack_free(d->image, PAGE_SIZE); d->image = NULL; goto out; } - bpf_image_ksym_add(d->image, &d->ksym); + bpf_image_ksym_add(d->image, PAGE_SIZE, &d->ksym); } prev_num_progs = d->num_progs; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index f40085f4de314a844b00600b9687874893f3d301..0b73d8548a2f5770b27a7c5eea3598821971babe 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1363,7 +1363,7 @@ BPF_CALL_3(bpf_timer_start, struct bpf_async_kern *, timer, u64, nsecs, u64, fla if (in_nmi()) return -EOPNOTSUPP; - if (flags > BPF_F_TIMER_ABS) + if (flags & ~(BPF_F_TIMER_ABS | BPF_F_TIMER_CPU_PIN)) return -EINVAL; __bpf_spin_lock_irqsave(&timer->lock); t = timer->timer; @@ -1377,6 +1377,9 @@ BPF_CALL_3(bpf_timer_start, struct bpf_async_kern *, timer, u64, nsecs, u64, fla else mode = HRTIMER_MODE_REL_SOFT; + if (flags & BPF_F_TIMER_CPU_PIN) + mode |= HRTIMER_MODE_PINNED; + hrtimer_start(&t->timer, ns_to_ktime(nsecs), mode); out: __bpf_spin_unlock_irqrestore(&timer->lock); @@ -2030,9 +2033,7 @@ void bpf_rb_root_free(const struct btf_field *field, void *rb_root, } } -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "Global functions as their definitions will be in vmlinux BTF"); +__bpf_kfunc_start_defs(); __bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign) { @@ -2612,9 +2613,159 @@ __bpf_kfunc void bpf_rcu_read_unlock(void) rcu_read_unlock(); } -__diag_pop(); +struct bpf_iter_bits { + __u64 __opaque[2]; +} __aligned(8); + +#define BITS_ITER_NR_WORDS_MAX 511 + +struct bpf_iter_bits_kern { + union { + __u64 *bits; + __u64 bits_copy; + }; + int nr_bits; + int bit; +} __aligned(8); + +/* On 64-bit hosts, unsigned long and u64 have the same size, so passing + * a u64 pointer and an unsigned long pointer to find_next_bit() will + * return the same result, as both point to the same 8-byte area. + * + * For 32-bit little-endian hosts, using a u64 pointer or unsigned long + * pointer also makes no difference. This is because the first iterated + * unsigned long is composed of bits 0-31 of the u64 and the second unsigned + * long is composed of bits 32-63 of the u64. + * + * However, for 32-bit big-endian hosts, this is not the case. The first + * iterated unsigned long will be bits 32-63 of the u64, so swap these two + * ulong values within the u64. + */ +static void swap_ulong_in_u64(u64 *bits, unsigned int nr) +{ +#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN) + unsigned int i; + + for (i = 0; i < nr; i++) + bits[i] = (bits[i] >> 32) | ((u64)(u32)bits[i] << 32); +#endif +} + +/** + * bpf_iter_bits_new() - Initialize a new bits iterator for a given memory area + * @it: The new bpf_iter_bits to be created + * @unsafe_ptr__ign: A pointer pointing to a memory area to be iterated over + * @nr_words: The size of the specified memory area, measured in 8-byte units. + * The maximum value of @nr_words is @BITS_ITER_NR_WORDS_MAX. This limit may be + * further reduced by the BPF memory allocator implementation. + * + * This function initializes a new bpf_iter_bits structure for iterating over + * a memory area which is specified by the @unsafe_ptr__ign and @nr_words. It + * copies the data of the memory area to the newly created bpf_iter_bits @it for + * subsequent iteration operations. + * + * On success, 0 is returned. On failure, ERR is returned. + */ +__bpf_kfunc int +bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_words) +{ + struct bpf_iter_bits_kern *kit = (void *)it; + u32 nr_bytes = nr_words * sizeof(u64); + u32 nr_bits = BYTES_TO_BITS(nr_bytes); + int err; + + BUILD_BUG_ON(sizeof(struct bpf_iter_bits_kern) != sizeof(struct bpf_iter_bits)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_bits_kern) != + __alignof__(struct bpf_iter_bits)); + + kit->nr_bits = 0; + kit->bits_copy = 0; + kit->bit = -1; + + if (!unsafe_ptr__ign || !nr_words) + return -EINVAL; + if (nr_words > BITS_ITER_NR_WORDS_MAX) + return -E2BIG; + + /* Optimization for u64 mask */ + if (nr_bits == 64) { + err = bpf_probe_read_kernel_common(&kit->bits_copy, nr_bytes, unsafe_ptr__ign); + if (err) + return -EFAULT; + + swap_ulong_in_u64(&kit->bits_copy, nr_words); + + kit->nr_bits = nr_bits; + return 0; + } + + if (bpf_mem_alloc_check_size(false, nr_bytes)) + return -E2BIG; + + /* Fallback to memalloc */ + kit->bits = bpf_mem_alloc(&bpf_global_ma, nr_bytes); + if (!kit->bits) + return -ENOMEM; + + err = bpf_probe_read_kernel_common(kit->bits, nr_bytes, unsafe_ptr__ign); + if (err) { + bpf_mem_free(&bpf_global_ma, kit->bits); + return err; + } + + swap_ulong_in_u64(kit->bits, nr_words); + + kit->nr_bits = nr_bits; + return 0; +} + +/** + * bpf_iter_bits_next() - Get the next bit in a bpf_iter_bits + * @it: The bpf_iter_bits to be checked + * + * This function returns a pointer to a number representing the value of the + * next bit in the bits. + * + * If there are no further bits available, it returns NULL. + */ +__bpf_kfunc int *bpf_iter_bits_next(struct bpf_iter_bits *it) +{ + struct bpf_iter_bits_kern *kit = (void *)it; + int bit = kit->bit, nr_bits = kit->nr_bits; + const void *bits; + + if (!nr_bits || bit >= nr_bits) + return NULL; + + bits = nr_bits == 64 ? &kit->bits_copy : kit->bits; + bit = find_next_bit(bits, nr_bits, bit + 1); + if (bit >= nr_bits) { + kit->bit = bit; + return NULL; + } + + kit->bit = bit; + return &kit->bit; +} + +/** + * bpf_iter_bits_destroy() - Destroy a bpf_iter_bits + * @it: The bpf_iter_bits to be destroyed + * + * Destroy the resource associated with the bpf_iter_bits. + */ +__bpf_kfunc void bpf_iter_bits_destroy(struct bpf_iter_bits *it) +{ + struct bpf_iter_bits_kern *kit = (void *)it; + + if (kit->nr_bits <= 64) + return; + bpf_mem_free(&bpf_global_ma, kit->bits); +} + +__bpf_kfunc_end_defs(); -BTF_SET8_START(generic_btf_ids) +BTF_KFUNCS_START(generic_btf_ids) #ifdef CONFIG_KEXEC_CORE BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE) #endif @@ -2642,7 +2793,7 @@ BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL) #ifdef CONFIG_BPF_RVI BTF_ID_FLAGS(func, bpf_current_level1_reaper, KF_ACQUIRE | KF_RET_NULL) #endif -BTF_SET8_END(generic_btf_ids) +BTF_KFUNCS_END(generic_btf_ids) static const struct btf_kfunc_id_set generic_kfunc_set = { .owner = THIS_MODULE, @@ -2658,7 +2809,7 @@ BTF_ID(struct, cgroup) BTF_ID(func, bpf_cgroup_release) #endif -BTF_SET8_START(common_btf_ids) +BTF_KFUNCS_START(common_btf_ids) BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx) BTF_ID_FLAGS(func, bpf_rdonly_cast) BTF_ID_FLAGS(func, bpf_rcu_read_lock) @@ -2668,12 +2819,29 @@ BTF_ID_FLAGS(func, bpf_dynptr_slice_rdwr, KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_num_new, KF_ITER_NEW) BTF_ID_FLAGS(func, bpf_iter_num_next, KF_ITER_NEXT | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY) +BTF_ID_FLAGS(func, bpf_iter_task_vma_new, KF_ITER_NEW | KF_RCU) +BTF_ID_FLAGS(func, bpf_iter_task_vma_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY) +#ifdef CONFIG_CGROUPS +BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY) +BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED) +BTF_ID_FLAGS(func, bpf_iter_css_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_css_destroy, KF_ITER_DESTROY) +#endif +BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED) +BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, bpf_dynptr_adjust) BTF_ID_FLAGS(func, bpf_dynptr_is_null) BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly) BTF_ID_FLAGS(func, bpf_dynptr_size) BTF_ID_FLAGS(func, bpf_dynptr_clone) -BTF_SET8_END(common_btf_ids) +BTF_ID_FLAGS(func, bpf_iter_bits_new, KF_ITER_NEW) +BTF_ID_FLAGS(func, bpf_iter_bits_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_bits_destroy, KF_ITER_DESTROY) +BTF_KFUNCS_END(common_btf_ids) static const struct btf_kfunc_id_set common_kfunc_set = { .owner = THIS_MODULE, diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c index 6fc9dae9edc81cad457b3e193ce671a3b0723aa8..9575314f40a69236267f4d52abe2b886e40441f2 100644 --- a/kernel/bpf/map_iter.c +++ b/kernel/bpf/map_iter.c @@ -193,9 +193,7 @@ static int __init bpf_map_iter_init(void) late_initcall(bpf_map_iter_init); -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "Global functions as their definitions will be in vmlinux BTF"); +__bpf_kfunc_start_defs(); __bpf_kfunc s64 bpf_map_sum_elem_count(const struct bpf_map *map) { @@ -213,11 +211,11 @@ __bpf_kfunc s64 bpf_map_sum_elem_count(const struct bpf_map *map) return ret; } -__diag_pop(); +__bpf_kfunc_end_defs(); -BTF_SET8_START(bpf_map_iter_kfunc_ids) +BTF_KFUNCS_START(bpf_map_iter_kfunc_ids) BTF_ID_FLAGS(func, bpf_map_sum_elem_count, KF_TRUSTED_ARGS) -BTF_SET8_END(bpf_map_iter_kfunc_ids) +BTF_KFUNCS_END(bpf_map_iter_kfunc_ids) static const struct btf_kfunc_id_set bpf_map_iter_kfunc_set = { .owner = THIS_MODULE, diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index 85f9501ff6e66ae89840077039eca59686e758f1..38fe720d0f87b28f972b59f8181bfec1e670a68f 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -35,6 +35,8 @@ */ #define LLIST_NODE_SZ sizeof(struct llist_node) +#define BPF_MEM_ALLOC_SIZE_MAX 4096 + /* similar to kmalloc, but sizeof == 8 bucket is gone */ static u8 size_index[24] __ro_after_init = { 3, /* 8 */ @@ -65,7 +67,7 @@ static u8 size_index[24] __ro_after_init = { static int bpf_mem_cache_idx(size_t size) { - if (!size || size > 4096) + if (!size || size > BPF_MEM_ALLOC_SIZE_MAX) return -1; if (size <= 192) @@ -930,3 +932,13 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags) return !ret ? NULL : ret + LLIST_NODE_SZ; } + +int bpf_mem_alloc_check_size(bool percpu, size_t size) +{ + /* The size of percpu allocation doesn't have LLIST_NODE_SZ overhead */ + if ((percpu && size > BPF_MEM_ALLOC_SIZE_MAX) || + (!percpu && size > BPF_MEM_ALLOC_SIZE_MAX - LLIST_NODE_SZ)) + return -E2BIG; + + return 0; +} diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 091234d93d2b269d3860f72800da529467bdca30..f2996fac05d52aa985bcb105dcb466a78725976f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1135,7 +1135,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return ret; } -#define BPF_MAP_CREATE_LAST_FIELD map_extra +#define BPF_MAP_CREATE_LAST_FIELD value_type_btf_obj_fd /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -3497,7 +3497,7 @@ static void bpf_perf_link_dealloc(struct bpf_link *link) static int bpf_perf_link_fill_common(const struct perf_event *event, char __user *uname, u32 ulen, u64 *probe_offset, u64 *probe_addr, - u32 *fd_type) + u32 *fd_type, unsigned long *missed) { const char *buf; u32 prog_id; @@ -3508,7 +3508,7 @@ static int bpf_perf_link_fill_common(const struct perf_event *event, return -EINVAL; err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf, - probe_offset, probe_addr); + probe_offset, probe_addr, missed); if (err) return err; if (!uname) @@ -3531,6 +3531,7 @@ static int bpf_perf_link_fill_common(const struct perf_event *event, static int bpf_perf_link_fill_kprobe(const struct perf_event *event, struct bpf_link_info *info) { + unsigned long missed; char __user *uname; u64 addr, offset; u32 ulen, type; @@ -3539,7 +3540,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event, uname = u64_to_user_ptr(info->perf_event.kprobe.func_name); ulen = info->perf_event.kprobe.name_len; err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr, - &type); + &type, &missed); if (err) return err; if (type == BPF_FD_TYPE_KRETPROBE) @@ -3548,9 +3549,11 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event, info->perf_event.type = BPF_PERF_EVENT_KPROBE; info->perf_event.kprobe.offset = offset; + info->perf_event.kprobe.missed = missed; if (!kallsyms_show_value(current_cred())) addr = 0; info->perf_event.kprobe.addr = addr; + info->perf_event.kprobe.cookie = event->bpf_cookie; return 0; } #endif @@ -3567,7 +3570,7 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event, uname = u64_to_user_ptr(info->perf_event.uprobe.file_name); ulen = info->perf_event.uprobe.name_len; err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr, - &type); + &type, NULL); if (err) return err; @@ -3576,6 +3579,7 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event, else info->perf_event.type = BPF_PERF_EVENT_UPROBE; info->perf_event.uprobe.offset = offset; + info->perf_event.uprobe.cookie = event->bpf_cookie; return 0; } #endif @@ -3603,7 +3607,8 @@ static int bpf_perf_link_fill_tracepoint(const struct perf_event *event, uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name); ulen = info->perf_event.tracepoint.name_len; info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT; - return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL); + info->perf_event.tracepoint.cookie = event->bpf_cookie; + return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL, NULL); } static int bpf_perf_link_fill_perf_event(const struct perf_event *event, @@ -3611,6 +3616,7 @@ static int bpf_perf_link_fill_perf_event(const struct perf_event *event, { info->perf_event.event.type = event->attr.type; info->perf_event.event.config = event->attr.config; + info->perf_event.event.cookie = event->bpf_cookie; info->perf_event.type = BPF_PERF_EVENT_EVENT; return 0; } @@ -4743,6 +4749,8 @@ static int bpf_map_get_info_by_fd(struct file *file, info.btf_value_type_id = map->btf_value_type_id; } info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) + bpf_map_struct_ops_info_fill(&info, map); if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_info_fill(&info, map); @@ -4976,7 +4984,7 @@ static int bpf_task_fd_query(const union bpf_attr *attr, err = bpf_get_perf_event_info(event, &prog_id, &fd_type, &buf, &probe_offset, - &probe_addr); + &probe_addr, NULL); if (!err) err = bpf_task_fd_query_copy(attr, uattr, prog_id, fd_type, buf, diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index f7ef58090c7d0b62e72aed2adf15a4e1209f7fa0..145c506899e4f2db7cfcf1f69a533564c031e93b 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -7,7 +7,9 @@ #include #include #include +#include #include +#include #include "mmap_unlock_work.h" static const char * const iter_task_type_names[] = { @@ -724,7 +726,7 @@ static struct bpf_iter_reg task_reg_info = { .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__task, task), - PTR_TO_BTF_ID_OR_NULL }, + PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED }, }, .seq_info = &task_seq_info, .fill_link_info = bpf_iter_fill_link_info, @@ -823,6 +825,244 @@ const struct bpf_func_proto bpf_find_vma_proto = { .arg5_type = ARG_ANYTHING, }; +struct bpf_iter_task_vma_kern_data { + struct task_struct *task; + struct mm_struct *mm; + struct mmap_unlock_irq_work *work; + struct vma_iterator vmi; +}; + +struct bpf_iter_task_vma { + /* opaque iterator state; having __u64 here allows to preserve correct + * alignment requirements in vmlinux.h, generated from BTF + */ + __u64 __opaque[1]; +} __attribute__((aligned(8))); + +/* Non-opaque version of bpf_iter_task_vma */ +struct bpf_iter_task_vma_kern { + struct bpf_iter_task_vma_kern_data *data; +} __attribute__((aligned(8))); + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it, + struct task_struct *task, u64 addr) +{ + struct bpf_iter_task_vma_kern *kit = (void *)it; + bool irq_work_busy = false; + int err; + + BUILD_BUG_ON(sizeof(struct bpf_iter_task_vma_kern) != sizeof(struct bpf_iter_task_vma)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_task_vma_kern) != __alignof__(struct bpf_iter_task_vma)); + + /* is_iter_reg_valid_uninit guarantees that kit hasn't been initialized + * before, so non-NULL kit->data doesn't point to previously + * bpf_mem_alloc'd bpf_iter_task_vma_kern_data + */ + kit->data = bpf_mem_alloc(&bpf_global_ma, sizeof(struct bpf_iter_task_vma_kern_data)); + if (!kit->data) + return -ENOMEM; + + kit->data->task = get_task_struct(task); + kit->data->mm = task->mm; + if (!kit->data->mm) { + err = -ENOENT; + goto err_cleanup_iter; + } + + /* kit->data->work == NULL is valid after bpf_mmap_unlock_get_irq_work */ + irq_work_busy = bpf_mmap_unlock_get_irq_work(&kit->data->work); + if (irq_work_busy || !mmap_read_trylock(kit->data->mm)) { + err = -EBUSY; + goto err_cleanup_iter; + } + + vma_iter_init(&kit->data->vmi, kit->data->mm, addr); + return 0; + +err_cleanup_iter: + if (kit->data->task) + put_task_struct(kit->data->task); + bpf_mem_free(&bpf_global_ma, kit->data); + /* NULL kit->data signals failed bpf_iter_task_vma initialization */ + kit->data = NULL; + return err; +} + +__bpf_kfunc struct vm_area_struct *bpf_iter_task_vma_next(struct bpf_iter_task_vma *it) +{ + struct bpf_iter_task_vma_kern *kit = (void *)it; + + if (!kit->data) /* bpf_iter_task_vma_new failed */ + return NULL; + return vma_next(&kit->data->vmi); +} + +__bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it) +{ + struct bpf_iter_task_vma_kern *kit = (void *)it; + + if (kit->data) { + bpf_mmap_unlock_mm(kit->data->work, kit->data->mm); + put_task_struct(kit->data->task); + bpf_mem_free(&bpf_global_ma, kit->data); + } +} + +__bpf_kfunc_end_defs(); + +#ifdef CONFIG_CGROUPS + +struct bpf_iter_css_task { + __u64 __opaque[1]; +} __attribute__((aligned(8))); + +struct bpf_iter_css_task_kern { + struct css_task_iter *css_it; +} __attribute__((aligned(8))); + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_iter_css_task_new(struct bpf_iter_css_task *it, + struct cgroup_subsys_state *css, unsigned int flags) +{ + struct bpf_iter_css_task_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(struct bpf_iter_css_task_kern) != sizeof(struct bpf_iter_css_task)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_css_task_kern) != + __alignof__(struct bpf_iter_css_task)); + kit->css_it = NULL; + switch (flags) { + case CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED: + case CSS_TASK_ITER_PROCS: + case 0: + break; + default: + return -EINVAL; + } + + kit->css_it = bpf_mem_alloc(&bpf_global_ma, sizeof(struct css_task_iter)); + if (!kit->css_it) + return -ENOMEM; + css_task_iter_start(css, flags, kit->css_it); + return 0; +} + +__bpf_kfunc struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it) +{ + struct bpf_iter_css_task_kern *kit = (void *)it; + + if (!kit->css_it) + return NULL; + return css_task_iter_next(kit->css_it); +} + +__bpf_kfunc void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it) +{ + struct bpf_iter_css_task_kern *kit = (void *)it; + + if (!kit->css_it) + return; + css_task_iter_end(kit->css_it); + bpf_mem_free(&bpf_global_ma, kit->css_it); +} + +__bpf_kfunc_end_defs(); + +#endif /* CONFIG_CGROUPS */ + +struct bpf_iter_task { + __u64 __opaque[3]; +} __attribute__((aligned(8))); + +struct bpf_iter_task_kern { + struct task_struct *task; + struct task_struct *pos; + unsigned int flags; +} __attribute__((aligned(8))); + +enum { + /* all process in the system */ + BPF_TASK_ITER_ALL_PROCS, + /* all threads in the system */ + BPF_TASK_ITER_ALL_THREADS, + /* all threads of a specific process */ + BPF_TASK_ITER_PROC_THREADS +}; + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it, + struct task_struct *task__nullable, unsigned int flags) +{ + struct bpf_iter_task_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(struct bpf_iter_task_kern) > sizeof(struct bpf_iter_task)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_task_kern) != + __alignof__(struct bpf_iter_task)); + + kit->task = kit->pos = NULL; + switch (flags) { + case BPF_TASK_ITER_ALL_THREADS: + case BPF_TASK_ITER_ALL_PROCS: + break; + case BPF_TASK_ITER_PROC_THREADS: + if (!task__nullable) + return -EINVAL; + break; + default: + return -EINVAL; + } + + if (flags == BPF_TASK_ITER_PROC_THREADS) + kit->task = task__nullable; + else + kit->task = &init_task; + kit->pos = kit->task; + kit->flags = flags; + return 0; +} + +__bpf_kfunc struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it) +{ + struct bpf_iter_task_kern *kit = (void *)it; + struct task_struct *pos; + unsigned int flags; + + flags = kit->flags; + pos = kit->pos; + + if (!pos) + return pos; + + if (flags == BPF_TASK_ITER_ALL_PROCS) + goto get_next_task; + + kit->pos = next_thread(kit->pos); + if (kit->pos == kit->task) { + if (flags == BPF_TASK_ITER_PROC_THREADS) { + kit->pos = NULL; + return pos; + } + } else + return pos; + +get_next_task: + kit->pos = next_task(kit->pos); + kit->task = kit->pos; + if (kit->pos == &init_task) + kit->pos = NULL; + + return pos; +} + +__bpf_kfunc void bpf_iter_task_destroy(struct bpf_iter_task *it) +{ +} + +__bpf_kfunc_end_defs(); + DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work); static void do_mmap_read_unlock(struct irq_work *entry) diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index bcf8e4bad210984102e010cf3a8485e20eae8fea..7db673c1ab7dd5010a2e81a6dfcf9fde926c8210 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -115,10 +115,10 @@ bool bpf_prog_has_trampoline(const struct bpf_prog *prog) (ptype == BPF_PROG_TYPE_LSM && eatype == BPF_LSM_MAC); } -void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym) +void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym) { ksym->start = (unsigned long) data; - ksym->end = ksym->start + PAGE_SIZE; + ksym->end = ksym->start + size; bpf_ksym_add(ksym); perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start, PAGE_SIZE, false, ksym->name); @@ -254,8 +254,8 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_a static void bpf_tramp_image_free(struct bpf_tramp_image *im) { bpf_image_ksym_del(&im->ksym); - bpf_jit_free_exec(im->image); - bpf_jit_uncharge_modmem(PAGE_SIZE); + arch_free_bpf_trampoline(im->image, im->size); + bpf_jit_uncharge_modmem(im->size); percpu_ref_exit(&im->pcref); kfree_rcu(im, rcu); } @@ -349,7 +349,7 @@ static void bpf_tramp_image_put(struct bpf_tramp_image *im) call_rcu_tasks_trace(&im->rcu, __bpf_tramp_image_put_rcu_tasks); } -static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key) +static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, int size) { struct bpf_tramp_image *im; struct bpf_ksym *ksym; @@ -360,15 +360,15 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key) if (!im) goto out; - err = bpf_jit_charge_modmem(PAGE_SIZE); + err = bpf_jit_charge_modmem(size); if (err) goto out_free_im; + im->size = size; err = -ENOMEM; - im->image = image = bpf_jit_alloc_exec(PAGE_SIZE); + im->image = image = arch_alloc_bpf_trampoline(size); if (!image) goto out_uncharge; - set_vm_flush_reset_perms(image); err = percpu_ref_init(&im->pcref, __bpf_tramp_image_release, 0, GFP_KERNEL); if (err) @@ -377,13 +377,13 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key) ksym = &im->ksym; INIT_LIST_HEAD_RCU(&ksym->lnode); snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", key); - bpf_image_ksym_add(image, ksym); + bpf_image_ksym_add(image, size, ksym); return im; out_free_image: - bpf_jit_free_exec(im->image); + arch_free_bpf_trampoline(im->image, im->size); out_uncharge: - bpf_jit_uncharge_modmem(PAGE_SIZE); + bpf_jit_uncharge_modmem(size); out_free_im: kfree(im); out: @@ -396,7 +396,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut struct bpf_tramp_links *tlinks; u32 orig_flags = tr->flags; bool ip_arg = false; - int err, total; + int err, total, size; tlinks = bpf_trampoline_get_progs(tr, &total, &ip_arg); if (IS_ERR(tlinks)) @@ -409,12 +409,6 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut goto out; } - im = bpf_tramp_image_alloc(tr->key); - if (IS_ERR(im)) { - err = PTR_ERR(im); - goto out; - } - /* clear all bits except SHARE_IPMODIFY and TAIL_CALL_CTX */ tr->flags &= (BPF_TRAMP_F_SHARE_IPMODIFY | BPF_TRAMP_F_TAIL_CALL_CTX); @@ -438,13 +432,31 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut tr->flags |= BPF_TRAMP_F_ORIG_STACK; #endif - err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE, + size = arch_bpf_trampoline_size(&tr->func.model, tr->flags, + tlinks, tr->func.addr); + if (size < 0) { + err = size; + goto out; + } + + if (size > PAGE_SIZE) { + err = -E2BIG; + goto out; + } + + im = bpf_tramp_image_alloc(tr->key, size); + if (IS_ERR(im)) { + err = PTR_ERR(im); + goto out; + } + + err = arch_prepare_bpf_trampoline(im, im->image, im->image + size, &tr->func.model, tr->flags, tlinks, tr->func.addr); if (err < 0) goto out_free; - set_memory_rox((long)im->image, 1); + arch_protect_bpf_trampoline(im->image, im->size); WARN_ON(tr->cur_image && total == 0); if (tr->cur_image) @@ -464,9 +476,8 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut tr->fops->func = NULL; tr->fops->trampoline = 0; - /* reset im->image memory attr for arch_prepare_bpf_trampoline */ - set_memory_nx((long)im->image, 1); - set_memory_rw((long)im->image, 1); + /* free im memory and reallocate later */ + bpf_tramp_image_free(im); goto again; } #endif @@ -1066,10 +1077,50 @@ bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog) } int __weak -arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, +arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, - void *orig_call) + void *func_addr) +{ + return -ENOTSUPP; +} + +void * __weak arch_alloc_bpf_trampoline(unsigned int size) +{ + void *image; + + if (WARN_ON_ONCE(size > PAGE_SIZE)) + return NULL; + image = bpf_jit_alloc_exec(PAGE_SIZE); + if (image) + set_vm_flush_reset_perms(image); + return image; +} + +void __weak arch_free_bpf_trampoline(void *image, unsigned int size) +{ + WARN_ON_ONCE(size > PAGE_SIZE); + /* bpf_jit_free_exec doesn't need "size", but + * bpf_prog_pack_free() needs it. + */ + bpf_jit_free_exec(image); +} + +void __weak arch_protect_bpf_trampoline(void *image, unsigned int size) +{ + WARN_ON_ONCE(size > PAGE_SIZE); + set_memory_rox((long)image, 1); +} + +void __weak arch_unprotect_bpf_trampoline(void *image, unsigned int size) +{ + WARN_ON_ONCE(size > PAGE_SIZE); + set_memory_nx((long)image, 1); + set_memory_rw((long)image, 1); +} + +int __weak arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr) { return -ENOTSUPP; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 26086c893dfb88da0db1119c8caa94263626ce30..5c24f719437f7df4bc9aca605dc262251c4338a3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -339,6 +339,11 @@ struct bpf_kfunc_call_arg_meta { struct btf *btf_vmlinux; +static const char *btf_type_name(const struct btf *btf, u32 id) +{ + return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); +} + static DEFINE_MUTEX(bpf_verifier_lock); static const struct bpf_line_info * @@ -502,6 +507,22 @@ static bool subprog_is_global(const struct bpf_verifier_env *env, int subprog) return aux && aux[subprog].linkage == BTF_FUNC_GLOBAL; } +static const char *subprog_name(const struct bpf_verifier_env *env, int subprog) +{ + struct bpf_func_info *info; + + if (!env->prog->aux->func_info) + return ""; + + info = &env->prog->aux->func_info[subprog]; + return btf_type_name(env->prog->aux->btf, info->type_id); +} + +static struct bpf_func_info_aux *subprog_aux(const struct bpf_verifier_env *env, int subprog) +{ + return &env->prog->aux->func_info_aux[subprog]; +} + static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK); @@ -747,11 +768,6 @@ static int iter_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg, return stack_slot_obj_get_spi(env, reg, "iter", nr_slots); } -static const char *btf_type_name(const struct btf *btf, u32 id) -{ - return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); -} - static const char *dynptr_type_str(enum bpf_dynptr_type type) { switch (type) { @@ -1190,7 +1206,12 @@ static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg static void __mark_reg_known_zero(struct bpf_reg_state *reg); +static bool in_rcu_cs(struct bpf_verifier_env *env); + +static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta); + static int mark_stack_slots_iter(struct bpf_verifier_env *env, + struct bpf_kfunc_call_arg_meta *meta, struct bpf_reg_state *reg, int insn_idx, struct btf *btf, u32 btf_id, int nr_slots) { @@ -1211,6 +1232,12 @@ static int mark_stack_slots_iter(struct bpf_verifier_env *env, __mark_reg_known_zero(st); st->type = PTR_TO_STACK; /* we don't have dedicated reg type */ + if (is_kfunc_rcu_protected(meta)) { + if (in_rcu_cs(env)) + st->type |= MEM_RCU; + else + st->type |= PTR_UNTRUSTED; + } st->live |= REG_LIVE_WRITTEN; st->ref_obj_id = i == 0 ? id : 0; st->iter.btf = btf; @@ -1285,7 +1312,7 @@ static bool is_iter_reg_valid_uninit(struct bpf_verifier_env *env, return true; } -static bool is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg, +static int is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg, struct btf *btf, u32 btf_id, int nr_slots) { struct bpf_func_state *state = func(env, reg); @@ -1293,26 +1320,28 @@ static bool is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_ spi = iter_get_spi(env, reg, nr_slots); if (spi < 0) - return false; + return -EINVAL; for (i = 0; i < nr_slots; i++) { struct bpf_stack_state *slot = &state->stack[spi - i]; struct bpf_reg_state *st = &slot->spilled_ptr; + if (st->type & PTR_UNTRUSTED) + return -EPROTO; /* only main (first) slot has ref_obj_id set */ if (i == 0 && !st->ref_obj_id) - return false; + return -EINVAL; if (i != 0 && st->ref_obj_id) - return false; + return -EINVAL; if (st->iter.btf != btf || st->iter.btf_id != btf_id) - return false; + return -EINVAL; for (j = 0; j < BPF_REG_SIZE; j++) if (slot->slot_type[j] != STACK_ITER) - return false; + return -EINVAL; } - return true; + return 0; } /* Check if given stack slot is "special": @@ -5393,6 +5422,11 @@ static int map_kptr_match_type(struct bpf_verifier_env *env, return -EINVAL; } +static bool in_sleepable(struct bpf_verifier_env *env) +{ + return env->prog->aux->sleepable; +} + /* The non-sleepable programs and sleepable programs with explicit bpf_rcu_read_lock() * can dereference RCU protected pointers and result is PTR_TRUSTED. */ @@ -5400,13 +5434,15 @@ static bool in_rcu_cs(struct bpf_verifier_env *env) { return env->cur_state->active_rcu_lock || env->cur_state->active_lock.ptr || - !env->prog->aux->sleepable; + !in_sleepable(env); } /* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */ BTF_SET_START(rcu_protected_types) BTF_ID(struct, prog_test_ref_kfunc) +#ifdef CONFIG_CGROUPS BTF_ID(struct, cgroup) +#endif BTF_ID(struct, bpf_cpumask) BTF_ID(struct, task_struct) BTF_SET_END(rcu_protected_types) @@ -7798,12 +7834,17 @@ static bool is_iter_destroy_kfunc(struct bpf_kfunc_call_arg_meta *meta) return meta->kfunc_flags & KF_ITER_DESTROY; } -static bool is_kfunc_arg_iter(struct bpf_kfunc_call_arg_meta *meta, int arg) +static bool is_kfunc_arg_iter(struct bpf_kfunc_call_arg_meta *meta, int arg_idx, + const struct btf_param *arg) { /* btf_check_iter_kfuncs() guarantees that first argument of any iter * kfunc is iter state pointer */ - return arg == 0 && is_iter_kfunc(meta); + if (is_iter_kfunc(meta)) + return arg_idx == 0; + + /* iter passed as an argument to a generic kfunc */ + return btf_param_match_suffix(meta->btf, arg, "__iter"); } static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_idx, @@ -7811,14 +7852,20 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; const struct btf_type *t; - const struct btf_param *arg; - int spi, err, i, nr_slots; - u32 btf_id; + int spi, err, i, nr_slots, btf_id; - /* btf_check_iter_kfuncs() ensures we don't need to validate anything here */ - arg = &btf_params(meta->func_proto)[0]; - t = btf_type_skip_modifiers(meta->btf, arg->type, NULL); /* PTR */ - t = btf_type_skip_modifiers(meta->btf, t->type, &btf_id); /* STRUCT */ + /* For iter_{new,next,destroy} functions, btf_check_iter_kfuncs() + * ensures struct convention, so we wouldn't need to do any BTF + * validation here. But given iter state can be passed as a parameter + * to any kfunc, if arg has "__iter" suffix, we need to be a bit more + * conservative here. + */ + btf_id = btf_check_iter_arg(meta->btf, meta->func_proto, regno - 1); + if (btf_id < 0) { + verbose(env, "expected valid iter pointer as arg #%d\n", regno); + return -EINVAL; + } + t = btf_type_by_id(meta->btf, btf_id); nr_slots = t->size / BPF_REG_SIZE; if (is_iter_new_kfunc(meta)) { @@ -7836,15 +7883,26 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id return err; } - err = mark_stack_slots_iter(env, reg, insn_idx, meta->btf, btf_id, nr_slots); + err = mark_stack_slots_iter(env, meta, reg, insn_idx, meta->btf, btf_id, nr_slots); if (err) return err; } else { - /* iter_next() or iter_destroy() expect initialized iter state*/ - if (!is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots)) { + /* iter_next() or iter_destroy(), as well as any kfunc + * accepting iter argument, expect initialized iter state + */ + err = is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots); + switch (err) { + case 0: + break; + case -EINVAL: verbose(env, "expected an initialized iter_%s as arg #%d\n", iter_type_str(meta->btf, btf_id), regno); - return -EINVAL; + return err; + case -EPROTO: + verbose(env, "expected an RCU CS when using %s\n", meta->func_name); + return err; + default: + return err; } spi = iter_get_spi(env, reg, nr_slots); @@ -9441,15 +9499,27 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (err == -EFAULT) return err; if (subprog_is_global(env, subprog)) { + const char *sub_name = subprog_name(env, subprog); + + /* Only global subprogs cannot be called with a lock held. */ + if (env->cur_state->active_lock.ptr) { + verbose(env, "global function calls are not allowed while holding a lock,\n" + "use static function instead\n"); + return -EINVAL; + } + if (err) { - verbose(env, "Caller passes invalid args into func#%d\n", subprog); + verbose(env, "Caller passes invalid args into func#%d ('%s')\n", + subprog, sub_name); return err; } - if (env->log.level & BPF_LOG_LEVEL) - verbose(env, "Func#%d is global and valid. Skipping.\n", subprog); + verbose(env, "Func#%d ('%s') is global and assumed valid.\n", + subprog, sub_name); if (env->subprog_info[subprog].changes_pkt_data) clear_all_pkt_pointers(env); + /* mark global subprog for verifying after main prog */ + subprog_aux(env, subprog)->called = true; clear_caller_saved_regs(env, caller->regs); /* All global functions return a 64-bit SCALAR_VALUE */ @@ -10095,7 +10165,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } - if (!env->prog->aux->sleepable && fn->might_sleep) { + if (!in_sleepable(env) && fn->might_sleep) { verbose(env, "helper call might sleep in a non-sleepable prog\n"); return -EINVAL; } @@ -10125,7 +10195,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } - if (env->prog->aux->sleepable && is_storage_get_function(func_id)) + if (in_sleepable(env) && is_storage_get_function(func_id)) env->insn_aux_data[insn_idx].storage_get_func_atomic = true; } @@ -10570,22 +10640,9 @@ static bool is_kfunc_rcu(struct bpf_kfunc_call_arg_meta *meta) return meta->kfunc_flags & KF_RCU; } -static bool __kfunc_param_match_suffix(const struct btf *btf, - const struct btf_param *arg, - const char *suffix) +static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta) { - int suffix_len = strlen(suffix), len; - const char *param_name; - - /* In the future, this can be ported to use BTF tagging */ - param_name = btf_name_by_offset(btf, arg->name_off); - if (str_is_empty(param_name)) - return false; - len = strlen(param_name); - if (len < suffix_len) - return false; - param_name += len - suffix_len; - return !strncmp(param_name, suffix, suffix_len); + return meta->kfunc_flags & KF_RCU_PROTECTED; } static bool is_kfunc_arg_mem_size(const struct btf *btf, @@ -10598,7 +10655,7 @@ static bool is_kfunc_arg_mem_size(const struct btf *btf, if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) return false; - return __kfunc_param_match_suffix(btf, arg, "__sz"); + return btf_param_match_suffix(btf, arg, "__sz"); } static bool is_kfunc_arg_const_mem_size(const struct btf *btf, @@ -10611,37 +10668,42 @@ static bool is_kfunc_arg_const_mem_size(const struct btf *btf, if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) return false; - return __kfunc_param_match_suffix(btf, arg, "__szk"); + return btf_param_match_suffix(btf, arg, "__szk"); } static bool is_kfunc_arg_optional(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__opt"); + return btf_param_match_suffix(btf, arg, "__opt"); } static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__k"); + return btf_param_match_suffix(btf, arg, "__k"); } static bool is_kfunc_arg_ignore(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__ign"); + return btf_param_match_suffix(btf, arg, "__ign"); } static bool is_kfunc_arg_alloc_obj(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__alloc"); + return btf_param_match_suffix(btf, arg, "__alloc"); } static bool is_kfunc_arg_uninit(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__uninit"); + return btf_param_match_suffix(btf, arg, "__uninit"); } static bool is_kfunc_arg_refcounted_kptr(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__refcounted_kptr"); + return btf_param_match_suffix(btf, arg, "__refcounted_kptr"); +} + +static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param *arg) +{ + return btf_param_match_suffix(btf, arg, "__nullable"); } static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, @@ -10786,6 +10848,7 @@ enum kfunc_ptr_arg_type { KF_ARG_PTR_TO_CALLBACK, KF_ARG_PTR_TO_RB_ROOT, KF_ARG_PTR_TO_RB_NODE, + KF_ARG_PTR_TO_NULL, }; enum special_kfunc_type { @@ -10808,6 +10871,7 @@ enum special_kfunc_type { KF_bpf_dynptr_slice, KF_bpf_dynptr_slice_rdwr, KF_bpf_dynptr_clone, + KF_bpf_iter_css_task_new, }; BTF_SET_START(special_kfunc_set) @@ -10828,6 +10892,9 @@ BTF_ID(func, bpf_dynptr_from_xdp) BTF_ID(func, bpf_dynptr_slice) BTF_ID(func, bpf_dynptr_slice_rdwr) BTF_ID(func, bpf_dynptr_clone) +#ifdef CONFIG_CGROUPS +BTF_ID(func, bpf_iter_css_task_new) +#endif BTF_SET_END(special_kfunc_set) BTF_ID_LIST(special_kfunc_list) @@ -10850,6 +10917,11 @@ BTF_ID(func, bpf_dynptr_from_xdp) BTF_ID(func, bpf_dynptr_slice) BTF_ID(func, bpf_dynptr_slice_rdwr) BTF_ID(func, bpf_dynptr_clone) +#ifdef CONFIG_CGROUPS +BTF_ID(func, bpf_iter_css_task_new) +#else +BTF_ID_UNUSED +#endif static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) { @@ -10903,7 +10975,7 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, if (is_kfunc_arg_dynptr(meta->btf, &args[argno])) return KF_ARG_PTR_TO_DYNPTR; - if (is_kfunc_arg_iter(meta, argno)) + if (is_kfunc_arg_iter(meta, argno, &args[argno])) return KF_ARG_PTR_TO_ITER; if (is_kfunc_arg_list_head(meta->btf, &args[argno])) @@ -10930,6 +11002,8 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, if (is_kfunc_arg_callback(env, meta->btf, &args[argno])) return KF_ARG_PTR_TO_CALLBACK; + if (is_kfunc_arg_nullable(meta->btf, &args[argno]) && register_is_null(reg)) + return KF_ARG_PTR_TO_NULL; if (argno + 1 < nargs && (is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1]) || @@ -11374,6 +11448,28 @@ static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env, &meta->arg_rbtree_root.field); } +/* + * css_task iter allowlist is needed to avoid dead locking on css_set_lock. + * LSM hooks and iters (both sleepable and non-sleepable) are safe. + * Any sleepable progs are also safe since bpf_check_attach_target() enforce + * them can only be attached to some specific hook points. + */ +static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env) +{ + enum bpf_prog_type prog_type = resolve_prog_type(env->prog); + + switch (prog_type) { + case BPF_PROG_TYPE_LSM: + return true; + case BPF_PROG_TYPE_TRACING: + if (env->prog->expected_attach_type == BPF_TRACE_ITER) + return true; + fallthrough; + default: + return env->prog->aux->sleepable; + } +} + static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta, int insn_idx) { @@ -11460,7 +11556,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ } if ((is_kfunc_trusted_args(meta) || is_kfunc_rcu(meta)) && - (register_is_null(reg) || type_may_be_null(reg->type))) { + (register_is_null(reg) || type_may_be_null(reg->type)) && + !is_kfunc_arg_nullable(meta->btf, &args[i])) { verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i); return -EACCES; } @@ -11485,6 +11582,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return kf_arg_type; switch (kf_arg_type) { + case KF_ARG_PTR_TO_NULL: + continue; case KF_ARG_PTR_TO_ALLOC_BTF_ID: case KF_ARG_PTR_TO_BTF_ID: if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta)) @@ -11615,6 +11714,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ break; } case KF_ARG_PTR_TO_ITER: + if (meta->func_id == special_kfunc_list[KF_bpf_iter_css_task_new]) { + if (!check_css_task_iter_allowlist(env)) { + verbose(env, "css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs\n"); + return -EINVAL; + } + } ret = process_iter_arg(env, regno, insn_idx, meta); if (ret < 0) return ret; @@ -11861,7 +11966,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } sleepable = is_kfunc_sleepable(&meta); - if (sleepable && !env->prog->aux->sleepable) { + if (sleepable && !in_sleepable(env)) { verbose(env, "program must be sleepable to call sleepable kfunc %s\n", func_name); return -EACCES; } @@ -11887,6 +11992,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (env->cur_state->active_rcu_lock) { struct bpf_func_state *state; struct bpf_reg_state *reg; + u32 clear_mask = (1 << STACK_SPILL) | (1 << STACK_ITER); if (in_rbtree_lock_required_cb(env) && (rcu_lock || rcu_unlock)) { verbose(env, "Calling bpf_rcu_read_{lock,unlock} in unnecessary rbtree callback\n"); @@ -11897,7 +12003,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, verbose(env, "nested rcu read lock (kernel function %s)\n", func_name); return -EINVAL; } else if (rcu_unlock) { - bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ + bpf_for_each_reg_in_vstate_mask(env->cur_state, state, reg, clear_mask, ({ if (reg->type & MEM_RCU) { reg->type &= ~(MEM_RCU | PTR_MAYBE_NULL); reg->type |= PTR_UNTRUSTED; @@ -17371,7 +17477,6 @@ static int do_check(struct bpf_verifier_env *env) if (env->cur_state->active_lock.ptr) { if ((insn->src_reg == BPF_REG_0 && insn->imm != BPF_FUNC_spin_unlock) || - (insn->src_reg == BPF_PSEUDO_CALL) || (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && (insn->off != 0 || !is_bpf_graph_api_kfunc(insn->imm)))) { verbose(env, "function calls are not allowed while holding a lock\n"); @@ -17413,15 +17518,12 @@ static int do_check(struct bpf_verifier_env *env) verbose(env, "BPF_EXIT uses reserved fields\n"); return -EINVAL; } - - if (env->cur_state->active_lock.ptr && - !in_rbtree_lock_required_cb(env)) { + if (env->cur_state->active_lock.ptr && !env->cur_state->curframe) { verbose(env, "bpf_spin_unlock is missing\n"); return -EINVAL; } - if (env->cur_state->active_rcu_lock && - !in_rbtree_lock_required_cb(env)) { + if (env->cur_state->active_rcu_lock && !env->cur_state->curframe) { verbose(env, "bpf_rcu_read_unlock is missing\n"); return -EINVAL; } @@ -19439,7 +19541,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) } if (is_storage_get_function(insn->imm)) { - if (!env->prog->aux->sleepable || + if (!in_sleepable(env) || env->insn_aux_data[i + delta].storage_get_func_atomic) insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_ATOMIC); else @@ -19947,8 +20049,11 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) return ret; } -/* Verify all global functions in a BPF program one by one based on their BTF. - * All global functions must pass verification. Otherwise the whole program is rejected. +/* Lazily verify all global functions based on their BTF, if they are called + * from main BPF program or any of subprograms transitively. + * BPF global subprogs called from dead code are not validated. + * All callable global functions must pass verification. + * Otherwise the whole program is rejected. * Consider: * int bar(int); * int foo(int f) @@ -19967,25 +20072,46 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) static int do_check_subprogs(struct bpf_verifier_env *env) { struct bpf_prog_aux *aux = env->prog->aux; - int i, ret; + struct bpf_func_info_aux *sub_aux; + int i, ret, new_cnt; if (!aux->func_info) return 0; +again: + new_cnt = 0; for (i = 1; i < env->subprog_cnt; i++) { - if (aux->func_info_aux[i].linkage != BTF_FUNC_GLOBAL) + if (!subprog_is_global(env, i)) continue; + + sub_aux = subprog_aux(env, i); + if (!sub_aux->called || sub_aux->verified) + continue; + env->insn_idx = env->subprog_info[i].start; WARN_ON_ONCE(env->insn_idx == 0); ret = do_check_common(env, i); if (ret) { return ret; } else if (env->log.level & BPF_LOG_LEVEL) { - verbose(env, - "Func#%d is safe for any args that match its prototype\n", - i); + verbose(env, "Func#%d ('%s') is safe for any args that match its prototype\n", + i, subprog_name(env, i)); } + + /* We verified new global subprog, it might have called some + * more global subprogs that we haven't verified yet, so we + * need to do another pass over subprogs to verify those. + */ + sub_aux->verified = true; + new_cnt++; } + + /* We can't loop forever as we verify at least one global subprog on + * each pass. + */ + if (new_cnt) + goto again; + return 0; } @@ -20028,10 +20154,12 @@ static void print_verification_stats(struct bpf_verifier_env *env) static int check_struct_ops_btf_id(struct bpf_verifier_env *env) { const struct btf_type *t, *func_proto; + const struct bpf_struct_ops_desc *st_ops_desc; const struct bpf_struct_ops *st_ops; const struct btf_member *member; struct bpf_prog *prog = env->prog; u32 btf_id, member_idx; + struct btf *btf; const char *mname; if (!prog->gpl_compatible) { @@ -20039,15 +20167,30 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) return -EINVAL; } + if (!prog->aux->attach_btf_id) + return -ENOTSUPP; + + btf = prog->aux->attach_btf; + if (btf_is_module(btf)) { + /* Make sure st_ops is valid through the lifetime of env */ + env->attach_btf_mod = btf_try_get_module(btf); + if (!env->attach_btf_mod) { + verbose(env, "struct_ops module %s is not found\n", + btf_get_name(btf)); + return -ENOTSUPP; + } + } + btf_id = prog->aux->attach_btf_id; - st_ops = bpf_struct_ops_find(btf_id); - if (!st_ops) { + st_ops_desc = bpf_struct_ops_find(btf, btf_id); + if (!st_ops_desc) { verbose(env, "attach_btf_id %u is not a supported struct\n", btf_id); return -ENOTSUPP; } + st_ops = st_ops_desc->st_ops; - t = st_ops->type; + t = st_ops_desc->type; member_idx = prog->expected_attach_type; if (member_idx >= btf_type_vlen(t)) { verbose(env, "attach to invalid member idx %u of struct %s\n", @@ -20056,8 +20199,8 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } member = &btf_type_member(t)[member_idx]; - mname = btf_name_by_offset(btf_vmlinux, member->name_off); - func_proto = btf_type_resolve_func_ptr(btf_vmlinux, member->type, + mname = btf_name_by_offset(btf, member->name_off); + func_proto = btf_type_resolve_func_ptr(btf, member->type, NULL); if (!func_proto) { verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n", @@ -20075,6 +20218,12 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } } + /* btf_ctx_access() used this to provide argument type info */ + prog->aux->ctx_arg_info = + st_ops_desc->arg_info[member_idx].info; + prog->aux->ctx_arg_info_size = + st_ops_desc->arg_info[member_idx].cnt; + prog->aux->attach_func_proto = func_proto; prog->aux->attach_func_name = mname; env->ops = st_ops->verifier_ops; @@ -20684,8 +20833,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (ret) goto skip_full_check; - ret = do_check_subprogs(env); - ret = ret ?: do_check_main(env); + ret = do_check_main(env); + ret = ret ?: do_check_subprogs(env); if (ret == 0 && bpf_prog_is_offloaded(env->prog->aux)) ret = bpf_prog_offload_finalize(env); @@ -20804,6 +20953,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 env->prog->expected_attach_type = 0; *prog = env->prog; + + module_put(env->attach_btf_mod); err_unlock: if (!is_priv) mutex_unlock(&bpf_verifier_lock); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 7df73d1d66289a841494e882ad8cbfce190e2620..5810f75c2383901e7c561787c7b73570cf7f4a57 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5079,9 +5079,11 @@ static void css_task_iter_advance(struct css_task_iter *it) void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it) { + unsigned long irqflags; + memset(it, 0, sizeof(*it)); - spin_lock_irq(&css_set_lock); + spin_lock_irqsave(&css_set_lock, irqflags); it->ss = css->ss; it->flags = flags; @@ -5095,7 +5097,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, css_task_iter_advance(it); - spin_unlock_irq(&css_set_lock); + spin_unlock_irqrestore(&css_set_lock, irqflags); } /** @@ -5108,12 +5110,14 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, */ struct task_struct *css_task_iter_next(struct css_task_iter *it) { + unsigned long irqflags; + if (it->cur_task) { put_task_struct(it->cur_task); it->cur_task = NULL; } - spin_lock_irq(&css_set_lock); + spin_lock_irqsave(&css_set_lock, irqflags); /* @it may be half-advanced by skips, finish advancing */ if (it->flags & CSS_TASK_ITER_SKIPPED) @@ -5126,7 +5130,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it) css_task_iter_advance(it); } - spin_unlock_irq(&css_set_lock); + spin_unlock_irqrestore(&css_set_lock, irqflags); return it->cur_task; } @@ -5139,11 +5143,13 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it) */ void css_task_iter_end(struct css_task_iter *it) { + unsigned long irqflags; + if (it->cur_cset) { - spin_lock_irq(&css_set_lock); + spin_lock_irqsave(&css_set_lock, irqflags); list_del(&it->iters_node); put_css_set_locked(it->cur_cset); - spin_unlock_irq(&css_set_lock); + spin_unlock_irqrestore(&css_set_lock, irqflags); } if (it->cur_dcset) diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 329c10c084a27446c7b2d1465eaaa0128ec8810a..c7c444c8e350240b462e017cdd5c1b1f7392ac7d 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -537,13 +537,13 @@ void cgroup_base_stat_cputime_show(struct seq_file *seq) } /* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */ -BTF_SET8_START(bpf_rstat_kfunc_ids) +BTF_KFUNCS_START(bpf_rstat_kfunc_ids) BTF_ID_FLAGS(func, cgroup_rstat_updated) BTF_ID_FLAGS(func, cgroup_rstat_flush, KF_SLEEPABLE) #if defined(CONFIG_BPF_RVI) && !defined(CONFIG_PREEMPT_RT) BTF_ID_FLAGS(func, cgroup_rstat_flush_atomic) #endif -BTF_SET8_END(bpf_rstat_kfunc_ids) +BTF_KFUNCS_END(bpf_rstat_kfunc_ids) static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = { .owner = THIS_MODULE, diff --git a/kernel/fork.c b/kernel/fork.c index f3c663602345ff0a1a640610250b9053ff6dfc13..5b4649261c9e83c82954629ad2270f8ebadc1d07 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -1026,6 +1027,7 @@ void __put_task_struct(struct task_struct *tsk) WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); + sched_ext_free(tsk); io_uring_free(tsk); cgroup_free(tsk); task_numa_free(tsk, true); @@ -2598,7 +2600,7 @@ __latent_entropy struct task_struct *copy_process( retval = perf_event_init_task(p, clone_flags); if (retval) - goto bad_fork_cleanup_policy; + goto bad_fork_sched_cancel_fork; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_perf; @@ -2730,7 +2732,9 @@ __latent_entropy struct task_struct *copy_process( * cgroup specific, it unconditionally needs to place the task on a * runqueue. */ - sched_cgroup_fork(p, args); + retval = sched_cgroup_fork(p, args); + if (retval) + goto bad_fork_cancel_cgroup; /* * From this point on we must avoid any synchronous user-space @@ -2776,13 +2780,13 @@ __latent_entropy struct task_struct *copy_process( /* Don't start children in a dying pid namespace */ if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) { retval = -ENOMEM; - goto bad_fork_cancel_cgroup; + goto bad_fork_core_free; } /* Let kill terminate clone/fork in the middle */ if (fatal_signal_pending(current)) { retval = -EINTR; - goto bad_fork_cancel_cgroup; + goto bad_fork_core_free; } /* No more failure paths after this point. */ @@ -2858,10 +2862,11 @@ __latent_entropy struct task_struct *copy_process( return p; -bad_fork_cancel_cgroup: +bad_fork_core_free: sched_core_free(p); spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); +bad_fork_cancel_cgroup: cgroup_cancel_fork(p, args); bad_fork_put_pidfd: if (clone_flags & CLONE_PIDFD) { @@ -2900,6 +2905,8 @@ __latent_entropy struct task_struct *copy_process( audit_free(p); bad_fork_cleanup_perf: perf_event_free_task(p); +bad_fork_sched_cancel_fork: + sched_cancel_fork(p); bad_fork_cleanup_policy: lockdep_free_task(p); #ifdef CONFIG_NUMA diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 8a65b0c34b5ac096794894c12b5168d7066fcbec..ce043726c78b63cf599c0c379b29c5ca67673750 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -108,6 +108,10 @@ config GENERIC_IRQ_MATRIX_ALLOCATOR config GENERIC_IRQ_RESERVATION_MODE bool +# Snapshot for interrupt statistics +config GENERIC_IRQ_STAT_SNAPSHOT + bool + # Support forced irq threading config IRQ_FORCED_THREADING bool diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 2340441d2a7227628e23f1dedca229ab19009052..196c6f11f26eeaf65fe9ca5d217195d95fe8f158 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -258,7 +258,7 @@ static inline void irq_state_set_masked(struct irq_desc *desc) static inline void __kstat_incr_irqs_this_cpu(struct irq_desc *desc) { - __this_cpu_inc(*desc->kstat_irqs); + __this_cpu_inc(desc->kstat_irqs->cnt); __this_cpu_inc(kstat.irqs_sum); } diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 29f4101585cf7c499f65944e955ce941579bc12d..1382073c3fe807e349e20a04948001ef537d8fc3 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -92,11 +92,23 @@ static void desc_smp_init(struct irq_desc *desc, int node, #endif } +static void free_masks(struct irq_desc *desc) +{ +#ifdef CONFIG_GENERIC_PENDING_IRQ + free_cpumask_var(desc->pending_mask); +#endif + free_cpumask_var(desc->irq_common_data.affinity); +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + free_cpumask_var(desc->irq_common_data.effective_affinity); +#endif +} + #else static inline int alloc_masks(struct irq_desc *desc, int node) { return 0; } static inline void desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { } +static inline void free_masks(struct irq_desc *desc) { } #endif static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node, @@ -122,7 +134,7 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node, desc->name = NULL; desc->owner = owner; for_each_possible_cpu(cpu) - *per_cpu_ptr(desc->kstat_irqs, cpu) = 0; + *per_cpu_ptr(desc->kstat_irqs, cpu) = (struct irqstat) { }; desc_smp_init(desc, node, affinity); } @@ -168,6 +180,39 @@ static void delete_irq_desc(unsigned int irq) mas_erase(&mas); } +#ifdef CONFIG_SPARSE_IRQ +static const struct kobj_type irq_kobj_type; +#endif + +static int init_desc(struct irq_desc *desc, int irq, int node, + unsigned int flags, + const struct cpumask *affinity, + struct module *owner) +{ + desc->kstat_irqs = alloc_percpu(struct irqstat); + if (!desc->kstat_irqs) + return -ENOMEM; + + if (alloc_masks(desc, node)) { + free_percpu(desc->kstat_irqs); + return -ENOMEM; + } + + raw_spin_lock_init(&desc->lock); + lockdep_set_class(&desc->lock, &irq_desc_lock_class); + mutex_init(&desc->request_mutex); + init_waitqueue_head(&desc->wait_for_threads); + desc_set_defaults(irq, desc, node, affinity, owner); + irqd_set(&desc->irq_data, flags); + irq_resend_init(desc); +#ifdef CONFIG_SPARSE_IRQ + kobject_init(&desc->kobj, &irq_kobj_type); + init_rcu_head(&desc->rcu); +#endif + + return 0; +} + #ifdef CONFIG_SPARSE_IRQ static void irq_kobj_release(struct kobject *kobj); @@ -387,21 +432,6 @@ struct irq_desc *irq_to_desc(unsigned int irq) EXPORT_SYMBOL_GPL(irq_to_desc); #endif -#ifdef CONFIG_SMP -static void free_masks(struct irq_desc *desc) -{ -#ifdef CONFIG_GENERIC_PENDING_IRQ - free_cpumask_var(desc->pending_mask); -#endif - free_cpumask_var(desc->irq_common_data.affinity); -#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK - free_cpumask_var(desc->irq_common_data.effective_affinity); -#endif -} -#else -static inline void free_masks(struct irq_desc *desc) { } -#endif - void irq_lock_sparse(void) { mutex_lock(&sparse_irq_lock); @@ -417,36 +447,19 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags, struct module *owner) { struct irq_desc *desc; + int ret; desc = kzalloc_node(sizeof(*desc), GFP_KERNEL, node); if (!desc) return NULL; - /* allocate based on nr_cpu_ids */ - desc->kstat_irqs = alloc_percpu(unsigned int); - if (!desc->kstat_irqs) - goto err_desc; - - if (alloc_masks(desc, node)) - goto err_kstat; - raw_spin_lock_init(&desc->lock); - lockdep_set_class(&desc->lock, &irq_desc_lock_class); - mutex_init(&desc->request_mutex); - init_rcu_head(&desc->rcu); - init_waitqueue_head(&desc->wait_for_threads); - - desc_set_defaults(irq, desc, node, affinity, owner); - irqd_set(&desc->irq_data, flags); - kobject_init(&desc->kobj, &irq_kobj_type); - irq_resend_init(desc); + ret = init_desc(desc, irq, node, flags, affinity, owner); + if (unlikely(ret)) { + kfree(desc); + return NULL; + } return desc; - -err_kstat: - free_percpu(desc->kstat_irqs); -err_desc: - kfree(desc); - return NULL; } static void irq_kobj_release(struct kobject *kobj) @@ -587,26 +600,29 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { int __init early_irq_init(void) { int count, i, node = first_online_node; - struct irq_desc *desc; + int ret; init_irq_default_affinity(); printk(KERN_INFO "NR_IRQS: %d\n", NR_IRQS); - desc = irq_desc; count = ARRAY_SIZE(irq_desc); for (i = 0; i < count; i++) { - desc[i].kstat_irqs = alloc_percpu(unsigned int); - alloc_masks(&desc[i], node); - raw_spin_lock_init(&desc[i].lock); - lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); - mutex_init(&desc[i].request_mutex); - init_waitqueue_head(&desc[i].wait_for_threads); - desc_set_defaults(i, &desc[i], node, NULL, NULL); - irq_resend_init(&desc[i]); + ret = init_desc(irq_desc + i, i, node, 0, NULL, NULL); + if (unlikely(ret)) + goto __free_desc_res; } + return arch_early_irq_init(); + +__free_desc_res: + while (--i >= 0) { + free_masks(irq_desc + i); + free_percpu(irq_desc[i].kstat_irqs); + } + + return ret; } struct irq_desc *irq_to_desc(unsigned int irq) @@ -956,8 +972,7 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) { struct irq_desc *desc = irq_to_desc(irq); - return desc && desc->kstat_irqs ? - *per_cpu_ptr(desc->kstat_irqs, cpu) : 0; + return desc && desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0; } static bool irq_is_nmi(struct irq_desc *desc) @@ -979,10 +994,35 @@ static unsigned int kstat_irqs(unsigned int irq) return data_race(desc->tot_count); for_each_possible_cpu(cpu) - sum += data_race(*per_cpu_ptr(desc->kstat_irqs, cpu)); + sum += data_race(per_cpu(desc->kstat_irqs->cnt, cpu)); return sum; } +#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT + +void kstat_snapshot_irqs(void) +{ + struct irq_desc *desc; + unsigned int irq; + + for_each_irq_desc(irq, desc) { + if (!desc->kstat_irqs) + continue; + this_cpu_write(desc->kstat_irqs->ref, this_cpu_read(desc->kstat_irqs->cnt)); + } +} + +unsigned int kstat_get_irq_since_snapshot(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (!desc || !desc->kstat_irqs) + return 0; + return this_cpu_read(desc->kstat_irqs->cnt) - this_cpu_read(desc->kstat_irqs->ref); +} + +#endif + /** * kstat_irqs_usr - Get the statistics for an interrupt from thread context * @irq: The interrupt number diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 2bb1769cf43233c9789af6840feade0d79a43bcf..cb2795df2361dbba727c6e2f77f2ee4bc7b7f800 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -500,7 +500,7 @@ int show_interrupts(struct seq_file *p, void *v) if (desc->kstat_irqs) { for_each_online_cpu(j) - any_count |= data_race(*per_cpu_ptr(desc->kstat_irqs, j)); + any_count |= data_race(per_cpu(desc->kstat_irqs->cnt, j)); } if ((!desc->action || irq_desc_is_chained(desc)) && !any_count) @@ -508,8 +508,7 @@ int show_interrupts(struct seq_file *p, void *v) seq_printf(p, "%*d: ", prec, i); for_each_online_cpu(j) - seq_printf(p, "%10u ", desc->kstat_irqs ? - *per_cpu_ptr(desc->kstat_irqs, j) : 0); + seq_printf(p, "%10u ", desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, j) : 0); raw_spin_lock_irqsave(&desc->lock, flags); if (desc->irq_data.chip) { diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c index e2c2d4e5735f084cc22d86beaac8ab9412eba1c5..0ecd3e62c13017c0f06be1173b077bba121b06f7 100644 --- a/kernel/sched/autogroup.c +++ b/kernel/sched/autogroup.c @@ -151,7 +151,7 @@ void sched_autogroup_exit_task(struct task_struct *p) * see this thread after that: we can no longer use signal->autogroup. * See the PF_EXITING check in task_wants_autogroup(). */ - sched_move_task(p); + sched_move_task(p, true); } static void @@ -183,7 +183,7 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag) * sched_autogroup_exit_task(). */ for_each_thread(p, t) - sched_move_task(t); + sched_move_task(t, true); unlock_task_sighand(p, &flags); autogroup_kref_put(prev); diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c index 6aff6482b1e7ba40f1f76c4b0c12bae3cf3adc4d..9901e1203c37927d29a323e4bef1c9f3c6a10ec8 100644 --- a/kernel/sched/build_policy.c +++ b/kernel/sched/build_policy.c @@ -16,18 +16,25 @@ #include #include #include +#include #include #include #include #include +#include #include +#include #include +#include +#include #include #include #include #include #include +#include +#include #include @@ -55,3 +62,9 @@ #ifdef CONFIG_SCHED_SOFT_DOMAIN #include "soft_domain.c" #endif +#ifdef CONFIG_SCHED_CLASS_EXT +# include "ext.c" +# include "ext_idle.c" +#endif + +#include "syscalls.c" diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d9afdd7e588ee1230a2348cc304d6c7826cb1a5e..b50746de64c7e84fae18ec6715a30576fbfefd9f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2,9 +2,10 @@ /* * kernel/sched/core.c * - * Core kernel scheduler code and related syscalls + * Core kernel CPU scheduler code * * Copyright (C) 1991-2002 Linus Torvalds + * Copyright (C) 1998-2024 Ingo Molnar, Red Hat */ #include #include @@ -99,6 +100,23 @@ #include +/* + * Fix kabi for 04746ed80bcf, + * and still keep EXPORT_SYMBOL them in core.c instead of syscalls.c + */ +extern void sched_set_fifo_low(struct task_struct *p); +EXPORT_SYMBOL_GPL(sched_set_fifo_low); +extern int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr); +EXPORT_SYMBOL_GPL(sched_setattr_nocheck); +extern int __sched yield_to(struct task_struct *p, bool preempt); +EXPORT_SYMBOL_GPL(yield_to); +extern void set_user_nice(struct task_struct *p, long nice); +EXPORT_SYMBOL(set_user_nice); +extern void sched_set_fifo(struct task_struct *p); +EXPORT_SYMBOL_GPL(sched_set_fifo); +extern void sched_set_normal(struct task_struct *p, int nice); +EXPORT_SYMBOL_GPL(sched_set_normal); + EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpu); EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpumask); @@ -184,7 +202,10 @@ static inline int __task_prio(const struct task_struct *p) if (p->sched_class == &idle_sched_class) return MAX_RT_PRIO + NICE_WIDTH; /* 140 */ - return MAX_RT_PRIO + MAX_NICE; /* 120, squash fair */ + if (task_on_scx(p)) + return MAX_RT_PRIO + MAX_NICE + 1; /* 120, squash ext */ + + return MAX_RT_PRIO + MAX_NICE; /* 119, squash fair */ } /* @@ -213,6 +234,11 @@ static inline bool prio_less(const struct task_struct *a, if (pa == MAX_RT_PRIO + MAX_NICE) /* fair */ return cfs_prio_less(a, b, in_fi); +#ifdef CONFIG_SCHED_CLASS_EXT + if (pa == MAX_RT_PRIO + MAX_NICE + 1) /* ext */ + return scx_prio_less(a, b, in_fi); +#endif + return false; } @@ -762,6 +788,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) void update_rq_clock(struct rq *rq) { s64 delta; + u64 clock; lockdep_assert_rq_held(rq); @@ -773,11 +800,14 @@ void update_rq_clock(struct rq *rq) SCHED_WARN_ON(rq->clock_update_flags & RQCF_UPDATED); rq->clock_update_flags |= RQCF_UPDATED; #endif + clock = sched_clock_cpu(cpu_of(rq)); + scx_rq_clock_update(rq, clock); - delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; + delta = clock - rq->clock; if (delta < 0) return; rq->clock += delta; + update_rq_clock_task(rq, delta); } @@ -1246,11 +1276,14 @@ bool sched_can_stop_tick(struct rq *rq) return true; /* - * If there are no DL,RR/FIFO tasks, there must only be CFS tasks left; - * if there's more than one we need the tick for involuntary - * preemption. + * If there are no DL,RR/FIFO tasks, there must only be CFS or SCX tasks + * left. For CFS, if there's more than one we need the tick for + * involuntary preemption. For SCX, ask. */ - if (rq->nr_running > 1) + if (scx_enabled() && !scx_can_stop_tick(rq)) + return false; + + if (rq->cfs.h_nr_running > 1) return false; /* @@ -1315,7 +1348,7 @@ int tg_nop(struct task_group *tg, void *data) } #endif -static void set_load_weight(struct task_struct *p, bool update_load) +void set_load_weight(struct task_struct *p, bool update_load) { int prio = p->static_prio - MAX_RT_PRIO; struct load_weight lw; @@ -1332,8 +1365,8 @@ static void set_load_weight(struct task_struct *p, bool update_load) * SCHED_OTHER tasks have to update their load when changing their * weight */ - if (update_load && p->sched_class == &fair_sched_class) - reweight_task(p, &lw); + if (update_load && p->sched_class->reweight_task) + p->sched_class->reweight_task(task_rq(p), p, &lw); else p->se.load = lw; } @@ -1372,7 +1405,7 @@ static unsigned int __maybe_unused sysctl_sched_uclamp_util_max = SCHED_CAPACITY * This knob will not override the system default sched_util_clamp_min defined * above. */ -static unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE; +unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE; /* All clamps are required to be less or equal than these values */ static struct uclamp_se uclamp_default[UCLAMP_CNT]; @@ -1397,32 +1430,6 @@ static struct uclamp_se uclamp_default[UCLAMP_CNT]; */ DEFINE_STATIC_KEY_FALSE(sched_uclamp_used); -/* Integer rounded range for each bucket */ -#define UCLAMP_BUCKET_DELTA DIV_ROUND_CLOSEST(SCHED_CAPACITY_SCALE, UCLAMP_BUCKETS) - -#define for_each_clamp_id(clamp_id) \ - for ((clamp_id) = 0; (clamp_id) < UCLAMP_CNT; (clamp_id)++) - -static inline unsigned int uclamp_bucket_id(unsigned int clamp_value) -{ - return min_t(unsigned int, clamp_value / UCLAMP_BUCKET_DELTA, UCLAMP_BUCKETS - 1); -} - -static inline unsigned int uclamp_none(enum uclamp_id clamp_id) -{ - if (clamp_id == UCLAMP_MIN) - return 0; - return SCHED_CAPACITY_SCALE; -} - -static inline void uclamp_se_set(struct uclamp_se *uc_se, - unsigned int value, bool user_defined) -{ - uc_se->value = value; - uc_se->bucket_id = uclamp_bucket_id(value); - uc_se->user_defined = user_defined; -} - static inline unsigned int uclamp_idle_value(struct rq *rq, enum uclamp_id clamp_id, unsigned int clamp_value) @@ -1490,16 +1497,12 @@ static void __uclamp_update_util_min_rt_default(struct task_struct *p) static void uclamp_update_util_min_rt_default(struct task_struct *p) { - struct rq_flags rf; - struct rq *rq; - if (!rt_task(p)) return; /* Protect updates to p->uclamp_* */ - rq = task_rq_lock(p, &rf); + guard(task_rq_lock)(p); __uclamp_update_util_min_rt_default(p); - task_rq_unlock(rq, p, &rf); } static inline struct uclamp_se @@ -1795,9 +1798,8 @@ static void uclamp_update_root_tg(void) uclamp_se_set(&tg->uclamp_req[UCLAMP_MAX], sysctl_sched_uclamp_util_max, false); - rcu_read_lock(); + guard(rcu)(); cpu_util_update_eff(&root_task_group.css); - rcu_read_unlock(); } #else static void uclamp_update_root_tg(void) { } @@ -1824,10 +1826,9 @@ static void uclamp_sync_util_min_rt_default(void) smp_mb__after_spinlock(); read_unlock(&tasklist_lock); - rcu_read_lock(); + guard(rcu)(); for_each_process_thread(g, p) uclamp_update_util_min_rt_default(p); - rcu_read_unlock(); } static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, @@ -1894,107 +1895,6 @@ static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, #endif #endif -static int uclamp_validate(struct task_struct *p, - const struct sched_attr *attr) -{ - int util_min = p->uclamp_req[UCLAMP_MIN].value; - int util_max = p->uclamp_req[UCLAMP_MAX].value; - - if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) { - util_min = attr->sched_util_min; - - if (util_min + 1 > SCHED_CAPACITY_SCALE + 1) - return -EINVAL; - } - - if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) { - util_max = attr->sched_util_max; - - if (util_max + 1 > SCHED_CAPACITY_SCALE + 1) - return -EINVAL; - } - - if (util_min != -1 && util_max != -1 && util_min > util_max) - return -EINVAL; - - /* - * We have valid uclamp attributes; make sure uclamp is enabled. - * - * We need to do that here, because enabling static branches is a - * blocking operation which obviously cannot be done while holding - * scheduler locks. - */ - static_branch_enable(&sched_uclamp_used); - - return 0; -} - -static bool uclamp_reset(const struct sched_attr *attr, - enum uclamp_id clamp_id, - struct uclamp_se *uc_se) -{ - /* Reset on sched class change for a non user-defined clamp value. */ - if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)) && - !uc_se->user_defined) - return true; - - /* Reset on sched_util_{min,max} == -1. */ - if (clamp_id == UCLAMP_MIN && - attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN && - attr->sched_util_min == -1) { - return true; - } - - if (clamp_id == UCLAMP_MAX && - attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX && - attr->sched_util_max == -1) { - return true; - } - - return false; -} - -static void __setscheduler_uclamp(struct task_struct *p, - const struct sched_attr *attr) -{ - enum uclamp_id clamp_id; - - for_each_clamp_id(clamp_id) { - struct uclamp_se *uc_se = &p->uclamp_req[clamp_id]; - unsigned int value; - - if (!uclamp_reset(attr, clamp_id, uc_se)) - continue; - - /* - * RT by default have a 100% boost value that could be modified - * at runtime. - */ - if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN)) - value = sysctl_sched_uclamp_util_min_rt_default; - else - value = uclamp_none(clamp_id); - - uclamp_se_set(uc_se, value, false); - - } - - if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP))) - return; - - if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN && - attr->sched_util_min != -1) { - uclamp_se_set(&p->uclamp_req[UCLAMP_MIN], - attr->sched_util_min, true); - } - - if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX && - attr->sched_util_max != -1) { - uclamp_se_set(&p->uclamp_req[UCLAMP_MAX], - attr->sched_util_max, true); - } -} - static void uclamp_fork(struct task_struct *p) { enum uclamp_id clamp_id; @@ -2062,13 +1962,6 @@ static void __init init_uclamp(void) #else /* CONFIG_UCLAMP_TASK */ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) { } static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) { } -static inline int uclamp_validate(struct task_struct *p, - const struct sched_attr *attr) -{ - return -EOPNOTSUPP; -} -static void __setscheduler_uclamp(struct task_struct *p, - const struct sched_attr *attr) { } static inline void uclamp_fork(struct task_struct *p) { } static inline void uclamp_post_fork(struct task_struct *p) { } static inline void init_uclamp(void) { } @@ -2098,7 +1991,7 @@ unsigned long get_wchan(struct task_struct *p) return ip; } -static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) +void enqueue_task(struct rq *rq, struct task_struct *p, int flags) { if (!(flags & ENQUEUE_NOCLOCK)) update_rq_clock(rq); @@ -2115,7 +2008,10 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) sched_core_enqueue(rq, p); } -static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) +/* + * Must only return false when DEQUEUE_SLEEP. + */ +inline bool dequeue_task(struct rq *rq, struct task_struct *p, int flags) { if (sched_core_enabled(rq)) sched_core_dequeue(rq, p, flags); @@ -2129,7 +2025,7 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) } uclamp_rq_dec(rq, p); - p->sched_class->dequeue_task(rq, p, flags); + return p->sched_class->dequeue_task(rq, p, flags); } void activate_task(struct rq *rq, struct task_struct *p, int flags) @@ -2151,52 +2047,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags) dequeue_task(rq, p, flags); } -static inline int __normal_prio(int policy, int rt_prio, int nice) -{ - int prio; - - if (dl_policy(policy)) - prio = MAX_DL_PRIO - 1; - else if (rt_policy(policy)) - prio = MAX_RT_PRIO - 1 - rt_prio; - else - prio = NICE_TO_PRIO(nice); - - return prio; -} - -/* - * Calculate the expected normal priority: i.e. priority - * without taking RT-inheritance into account. Might be - * boosted by interactivity modifiers. Changes upon fork, - * setprio syscalls, and whenever the interactivity - * estimator recalculates. - */ -static inline int normal_prio(struct task_struct *p) -{ - return __normal_prio(p->policy, p->rt_priority, PRIO_TO_NICE(p->static_prio)); -} - -/* - * Calculate the current priority, i.e. the priority - * taken into account by the scheduler. This value might - * be boosted by RT tasks, or might be boosted by - * interactivity modifiers. Will be RT if the task got - * RT-boosted. If not then it returns p->normal_prio. - */ -static int effective_prio(struct task_struct *p) -{ - p->normal_prio = normal_prio(p); - /* - * If we are RT tasks or we were boosted to RT priority, - * keep the priority unchanged. Otherwise, update priority - * to the normal priority: - */ - if (!rt_prio(p->prio)) - return p->normal_prio; - return p->prio; -} - /** * task_curr - is this task currently executing on a CPU? * @p: the task in question. @@ -2208,6 +2058,17 @@ inline int task_curr(const struct task_struct *p) return cpu_curr(task_cpu(p)) == p; } +/* + * ->switching_to() is called with the pi_lock and rq_lock held and must not + * mess with locking. + */ +void check_class_changing(struct rq *rq, struct task_struct *p, + const struct sched_class *prev_class) +{ + if (prev_class != p->sched_class && p->sched_class->switching_to) + p->sched_class->switching_to(rq, p); +} + /* * switched_from, switched_to and prio_changed must _NOT_ drop rq->lock, * use the balance_callback list if you want balancing. @@ -2215,9 +2076,9 @@ inline int task_curr(const struct task_struct *p) * this means any call to check_class_changed() must be followed by a call to * balance_callback(). */ -static inline void check_class_changed(struct rq *rq, struct task_struct *p, - const struct sched_class *prev_class, - int oldprio) +void check_class_changed(struct rq *rq, struct task_struct *p, + const struct sched_class *prev_class, + int oldprio) { if (prev_class != p->sched_class) { if (prev_class->switched_from) @@ -2228,10 +2089,10 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p, p->sched_class->prio_changed(rq, p, oldprio); } -void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) +void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags) { if (p->sched_class == rq->curr->sched_class) - rq->curr->sched_class->check_preempt_curr(rq, p, flags); + rq->curr->sched_class->wakeup_preempt(rq, p, flags); else if (sched_class_above(p->sched_class, rq->curr->sched_class)) resched_curr(rq); @@ -2260,20 +2121,13 @@ static __always_inline int task_state_match(struct task_struct *p, unsigned int state) { #ifdef CONFIG_PREEMPT_RT - int match; - /* * Serialize against current_save_and_set_rtlock_wait_state() and * current_restore_rtlock_saved_state(). */ - raw_spin_lock_irq(&p->pi_lock); - match = __task_state_match(p, state); - raw_spin_unlock_irq(&p->pi_lock); - - return match; -#else - return __task_state_match(p, state); + guard(raw_spinlock_irq)(&p->pi_lock); #endif + return __task_state_match(p, state); } /* @@ -2396,9 +2250,6 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state static void __do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx); -static int __set_cpus_allowed_ptr(struct task_struct *p, - struct affinity_context *ctx); - static void migrate_disable_switch(struct rq *rq, struct task_struct *p) { struct affinity_context ac = { @@ -2427,10 +2278,9 @@ void migrate_disable(void) return; } - preempt_disable(); + guard(preempt)(); this_rq()->nr_pinned++; p->migration_disabled = 1; - preempt_enable(); } EXPORT_SYMBOL_GPL(migrate_disable); @@ -2454,7 +2304,7 @@ void migrate_enable(void) * Ensure stop_task runs either before or after this, and that * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule(). */ - preempt_disable(); + guard(preempt)(); if (p->cpus_ptr != &p->cpus_mask) __set_cpus_allowed_ptr(p, &ac); /* @@ -2465,7 +2315,6 @@ void migrate_enable(void) barrier(); p->migration_disabled = 0; this_rq()->nr_pinned--; - preempt_enable(); } EXPORT_SYMBOL_GPL(migrate_enable); @@ -2481,7 +2330,7 @@ static inline bool rq_has_pinned_tasks(struct rq *rq) static inline bool is_cpu_allowed(struct task_struct *p, int cpu) { /* When not in the task's cpumask, no point in looking further. */ - if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + if (!task_allowed_on_cpu(p, cpu)) return false; /* migrate_disabled() must be allowed to finish. */ @@ -2490,7 +2339,7 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu) /* Non kernel threads are not allowed during either online or offline. */ if (!(p->flags & PF_KTHREAD)) - return cpu_active(cpu) && task_cpu_possible(cpu, p); + return cpu_active(cpu); /* KTHREAD_IS_PER_CPU is always allowed. */ if (kthread_is_per_cpu(p)) @@ -2544,7 +2393,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf, rq_lock(rq, rf); WARN_ON_ONCE(task_cpu(p) != new_cpu); activate_task(rq, p, 0); - check_preempt_curr(rq, p, 0); + wakeup_preempt(rq, p, 0); return rq; } @@ -2834,16 +2683,6 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu); } -static cpumask_t *alloc_user_cpus_ptr(int node) -{ - /* - * See do_set_cpus_allowed() above for the rcu_head usage. - */ - int size = max_t(int, cpumask_size(), sizeof(struct rcu_head)); - - return kmalloc_node(size, GFP_KERNEL, node); -} - int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node) { @@ -3212,8 +3051,7 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p, * task must not exit() & deallocate itself prematurely. The * call is not atomic; no spinlocks may be held. */ -static int __set_cpus_allowed_ptr(struct task_struct *p, - struct affinity_context *ctx) +int __set_cpus_allowed_ptr(struct task_struct *p, struct affinity_context *ctx) { struct rq_flags rf; struct rq *rq; @@ -3332,9 +3170,6 @@ void force_compatible_cpus_allowed_ptr(struct task_struct *p) free_cpumask_var(new_mask); } -static int -__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx); - /* * Restore the affinity of a task @p which was previously restricted by a * call to force_compatible_cpus_allowed_ptr(). @@ -3430,7 +3265,7 @@ static void __migrate_swap_task(struct task_struct *p, int cpu) deactivate_task(src_rq, p, 0); set_task_cpu(p, cpu); activate_task(dst_rq, p, 0); - check_preempt_curr(dst_rq, p, 0); + wakeup_preempt(dst_rq, p, 0); rq_unpin_lock(dst_rq, &drf); rq_unpin_lock(src_rq, &srf); @@ -3537,13 +3372,11 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p, */ void kick_process(struct task_struct *p) { - int cpu; + guard(preempt)(); + int cpu = task_cpu(p); - preempt_disable(); - cpu = task_cpu(p); if ((cpu != smp_processor_id()) && task_curr(p)) smp_send_reschedule(cpu); - preempt_enable(); } EXPORT_SYMBOL_GPL(kick_process); @@ -3644,14 +3477,16 @@ static int select_fallback_rq(int cpu, struct task_struct *p) * The caller (fork, wakeup) owns p->pi_lock, ->cpus_ptr is stable. */ static inline -int select_task_rq(struct task_struct *p, int cpu, int wake_flags) +int select_task_rq(struct task_struct *p, int cpu, int *wake_flags) { lockdep_assert_held(&p->pi_lock); - if (p->nr_cpus_allowed > 1 && !is_migration_disabled(p)) - cpu = p->sched_class->select_task_rq(p, cpu, wake_flags); - else + if (p->nr_cpus_allowed > 1 && !is_migration_disabled(p)) { + cpu = p->sched_class->select_task_rq(p, cpu, *wake_flags); + *wake_flags |= WF_RQ_SELECTED; + } else { cpu = cpumask_any(p->cpus_ptr); + } /* * In order not to call set_task_cpu() on a blocking task we need @@ -3716,12 +3551,6 @@ void sched_set_stop_task(int cpu, struct task_struct *stop) #else /* CONFIG_SMP */ -static inline int __set_cpus_allowed_ptr(struct task_struct *p, - struct affinity_context *ctx) -{ - return set_cpus_allowed_ptr(p, ctx->new_mask); -} - static inline void migrate_disable_switch(struct rq *rq, struct task_struct *p) { } static inline bool rq_has_pinned_tasks(struct rq *rq) @@ -3729,11 +3558,6 @@ static inline bool rq_has_pinned_tasks(struct rq *rq) return false; } -static inline cpumask_t *alloc_user_cpus_ptr(int node) -{ - return NULL; -} - #endif /* !CONFIG_SMP */ static void @@ -3796,6 +3620,8 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, rq->nr_uninterruptible--; #ifdef CONFIG_SMP + if (wake_flags & WF_RQ_SELECTED) + en_flags |= ENQUEUE_RQ_SELECTED; if (wake_flags & WF_MIGRATED) en_flags |= ENQUEUE_MIGRATED; else @@ -3806,7 +3632,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, } activate_task(rq, p, en_flags); - check_preempt_curr(rq, p, wake_flags); + wakeup_preempt(rq, p, wake_flags); ttwu_do_wakeup(p); @@ -3882,7 +3708,7 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags) * it should preempt the task that is current now. */ update_rq_clock(rq); - check_preempt_curr(rq, p, wake_flags); + wakeup_preempt(rq, p, wake_flags); } ttwu_do_wakeup(p); ret = 1; @@ -3996,6 +3822,10 @@ bool cpus_share_resources(int this_cpu, int that_cpu) static inline bool ttwu_queue_cond(struct task_struct *p, int cpu) { + /* See SCX_OPS_ALLOW_QUEUED_WAKEUP. */ + if (!scx_allow_ttwu_queue(p)) + return false; + /* * Do not complicate things with the async wake_list while the CPU is * in hotplug state. @@ -4239,6 +4069,8 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) guard(preempt)(); int cpu, success = 0; + wake_flags |= WF_TTWU; + if (p == current) { /* * We're waking current, this means 'p->on_rq' and 'task_cpu(p) @@ -4368,7 +4200,7 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) */ smp_cond_load_acquire(&p->on_cpu, !VAL); - cpu = select_task_rq(p, p->wake_cpu, wake_flags | WF_TTWU); + cpu = select_task_rq(p, p->wake_cpu, &wake_flags); if (task_cpu(p) != cpu) { if (p->in_iowait) { delayacct_blkio_end(p); @@ -4565,6 +4397,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->rt.on_rq = 0; p->rt.on_list = 0; +#ifdef CONFIG_SCHED_CLASS_EXT + init_scx_entity(&p->scx); +#endif + #ifdef CONFIG_PREEMPT_NOTIFIERS INIT_HLIST_HEAD(&p->preempt_notifiers); #endif @@ -4841,10 +4677,18 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) if (dl_prio(p->prio)) return -EAGAIN; - else if (rt_prio(p->prio)) + + scx_pre_fork(p); + + if (rt_prio(p->prio)) { p->sched_class = &rt_sched_class; - else +#ifdef CONFIG_SCHED_CLASS_EXT + } else if (task_should_scx(p->policy)) { + p->sched_class = &ext_sched_class; +#endif + } else { p->sched_class = &fair_sched_class; + } init_entity_runnable_average(&p->se); @@ -4864,7 +4708,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) return 0; } -void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs) +int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs) { unsigned long flags; struct task_group *tg_qos __maybe_unused = NULL; @@ -4899,11 +4743,19 @@ void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs) if (p->sched_class->task_fork) p->sched_class->task_fork(p); raw_spin_unlock_irqrestore(&p->pi_lock, flags); + + return scx_fork(p); +} + +void sched_cancel_fork(struct task_struct *p) +{ + scx_cancel_fork(p); } void sched_post_fork(struct task_struct *p) { uclamp_post_fork(p); + scx_post_fork(p); } unsigned long to_ratio(u64 period, u64 runtime) @@ -4933,6 +4785,7 @@ void wake_up_new_task(struct task_struct *p) { struct rq_flags rf; struct rq *rq; + int wake_flags = WF_FORK; raw_spin_lock_irqsave(&p->pi_lock, rf.flags); WRITE_ONCE(p->__state, TASK_RUNNING); @@ -4947,7 +4800,7 @@ void wake_up_new_task(struct task_struct *p) */ p->recent_used_cpu = task_cpu(p); rseq_migrate(p); - __set_task_cpu(p, select_task_rq(p, task_cpu(p), WF_FORK)); + __set_task_cpu(p, select_task_rq(p, task_cpu(p), &wake_flags)); #endif rq = __task_rq_lock(p, &rf); update_rq_clock(rq); @@ -4956,7 +4809,7 @@ void wake_up_new_task(struct task_struct *p) activate_task(rq, p, ENQUEUE_NOCLOCK); trace_sched_wakeup_new(p); ifs_task_waking(p); - check_preempt_curr(rq, p, WF_FORK); + wakeup_preempt(rq, p, wake_flags); #ifdef CONFIG_SMP if (p->sched_class->task_woken) { /* @@ -5152,7 +5005,7 @@ __splice_balance_callbacks(struct rq *rq, bool split) return head; } -static inline struct balance_callback *splice_balance_callbacks(struct rq *rq) +struct balance_callback *splice_balance_callbacks(struct rq *rq) { return __splice_balance_callbacks(rq, true); } @@ -5162,7 +5015,7 @@ static void __balance_callbacks(struct rq *rq) do_balance_callbacks(rq, __splice_balance_callbacks(rq, false)); } -static inline void balance_callbacks(struct rq *rq, struct balance_callback *head) +void balance_callbacks(struct rq *rq, struct balance_callback *head) { unsigned long flags; @@ -5179,15 +5032,6 @@ static inline void __balance_callbacks(struct rq *rq) { } -static inline struct balance_callback *splice_balance_callbacks(struct rq *rq) -{ - return NULL; -} - -static inline void balance_callbacks(struct rq *rq, struct balance_callback *head) -{ -} - #endif static inline void @@ -5744,6 +5588,7 @@ void scheduler_tick(void) calc_global_load_tick(rq); sched_core_tick(rq); task_tick_mm_cid(rq, curr); + scx_tick(rq); rq_unlock(rq, &rf); @@ -5756,8 +5601,10 @@ void scheduler_tick(void) wq_worker_tick(curr); #ifdef CONFIG_SMP - rq->idle_balance = idle_cpu(cpu); - trigger_load_balance(rq); + if (!scx_switched_all()) { + rq->idle_balance = idle_cpu(cpu); + trigger_load_balance(rq); + } #endif } @@ -6045,11 +5892,25 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt) schedstat_inc(this_rq()->sched_count); } -static void put_prev_task_balance(struct rq *rq, struct task_struct *prev, - struct rq_flags *rf) +static void prev_balance(struct rq *rq, struct task_struct *prev, + struct rq_flags *rf) { -#ifdef CONFIG_SMP + const struct sched_class *start_class = prev->sched_class; const struct sched_class *class; + +#ifdef CONFIG_SCHED_CLASS_EXT + /* + * SCX requires a balance() call before every pick_task() including when + * waking up from SCHED_IDLE. If @start_class is below SCX, start from + * SCX instead. Also, set a flag to detect missing balance() call. + */ + if (scx_enabled()) { + rq->scx.flags |= SCX_RQ_BAL_PENDING; + if (sched_class_above(&ext_sched_class, start_class)) + start_class = &ext_sched_class; + } +#endif + /* * We must do the balancing pass before put_prev_task(), such * that when we release the rq->lock the task is in the same @@ -6058,13 +5919,11 @@ static void put_prev_task_balance(struct rq *rq, struct task_struct *prev, * We can terminate the balance pass as soon as we know there is * a runnable task of @class priority or higher. */ - for_class_range(class, prev->sched_class, &idle_sched_class) { - if (class->balance(rq, prev, rf)) + for_active_class_range(class, start_class, &idle_sched_class) { + if (class->balance && class->balance(rq, prev, rf)) break; } -#endif - put_prev_task(rq, prev); } /* @@ -6076,6 +5935,9 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) const struct sched_class *class; struct task_struct *p; + if (scx_enabled()) + goto restart; + /* * Optimization: we know that if all tasks are in the fair class we can * call that function directly, but only if the @prev task wasn't of a @@ -6091,20 +5953,33 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) /* Assume the next prioritized class is idle_sched_class */ if (!p) { - put_prev_task(rq, prev); - p = pick_next_task_idle(rq); + p = pick_task_idle(rq); + put_prev_set_next_task(rq, prev, p); } return p; } restart: - put_prev_task_balance(rq, prev, rf); + prev_balance(rq, prev, rf); - for_each_class(class) { - p = class->pick_next_task(rq); - if (p) - return p; + for_each_active_class(class) { + if (class->pick_next_task) { + p = class->pick_next_task(rq, prev); + if (p) + return p; + } else { + p = class->pick_task(rq); + if (p) { + const struct sched_class *prev_class = prev->sched_class; + + put_prev_set_next_task(rq, prev, p); + + if (class != prev_class && prev_class->switch_class) + prev_class->switch_class(rq, p); + return p; + } + } } BUG(); /* The idle class should always have a runnable task. */ @@ -6134,7 +6009,7 @@ static inline struct task_struct *pick_task(struct rq *rq) const struct sched_class *class; struct task_struct *p; - for_each_class(class) { + for_each_active_class(class) { p = class->pick_task(rq); if (p) return p; @@ -6190,16 +6065,11 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) WRITE_ONCE(rq->core_sched_seq, rq->core->core_pick_seq); next = rq->core_pick; - if (next != prev) { - put_prev_task(rq, prev); - set_next_task(rq, next); - } - rq->core_pick = NULL; - goto out; + goto out_set_next; } - put_prev_task_balance(rq, prev, rf); + prev_balance(rq, prev, rf); smt_mask = cpu_smt_mask(cpu); need_sync = !!rq->core->core_cookie; @@ -6366,8 +6236,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } out_set_next: - set_next_task(rq, next); -out: + put_prev_set_next_task(rq, prev, next); if (rq->core->core_forceidle_count && next == rq->idle) queue_core_balance(rq); @@ -6452,8 +6321,9 @@ static void sched_core_balance(struct rq *rq) struct sched_domain *sd; int cpu = cpu_of(rq); - preempt_disable(); - rcu_read_lock(); + guard(preempt)(); + guard(rcu)(); + raw_spin_rq_unlock_irq(rq); for_each_domain(cpu, sd) { if (need_resched()) @@ -6463,8 +6333,6 @@ static void sched_core_balance(struct rq *rq) break; } raw_spin_rq_lock_irq(rq); - rcu_read_unlock(); - preempt_enable(); } static DEFINE_PER_CPU(struct balance_callback, core_balance_head); @@ -7107,35 +6975,51 @@ int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flag } EXPORT_SYMBOL(default_wake_function); -static void __setscheduler_prio(struct task_struct *p, int prio) +void __setscheduler_prio(struct task_struct *p, int prio) { if (dl_prio(prio)) p->sched_class = &dl_sched_class; else if (rt_prio(prio)) p->sched_class = &rt_sched_class; +#ifdef CONFIG_SCHED_CLASS_EXT + else if (task_should_scx(p->policy)) + p->sched_class = &ext_sched_class; +#endif else p->sched_class = &fair_sched_class; p->prio = prio; } -#ifdef CONFIG_RT_MUTEXES - -static inline int __rt_effective_prio(struct task_struct *pi_task, int prio) +/* + * Currently, __setscheduler_class is mainly picked for sched_ext, + * but the original patch comes from mainline, the commits are: + * + * 98442f0ccd82 ("sched: Fix delayed_dequeue vs switched_from_fair()"): + * it is for delayed_dequeue in EEVDF + * + * 5db91545ef81 + * ("sched: Pass correct scheduling policy to __setscheduler_class"): + * it is to adopt __setscheduler_class() in sched_ext. + */ +const struct sched_class *__setscheduler_class(int policy, int prio) { - if (pi_task) - prio = min(prio, pi_task->prio); + if (dl_prio(prio)) + return &dl_sched_class; - return prio; -} + if (rt_prio(prio)) + return &rt_sched_class; -static inline int rt_effective_prio(struct task_struct *p, int prio) -{ - struct task_struct *pi_task = rt_mutex_get_top_task(p); +#ifdef CONFIG_SCHED_CLASS_EXT + if (task_should_scx(policy)) + return &ext_sched_class; +#endif - return __rt_effective_prio(pi_task, prio); + return &fair_sched_class; } +#ifdef CONFIG_RT_MUTEXES + /* * rt_mutex_setprio - set the current priority of a task * @p: task to boost @@ -7247,6 +7131,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) } __setscheduler_prio(p, prio); + check_class_changing(rq, p, prev_class); if (queued) enqueue_task(rq, p, queue_flag); @@ -7264,1430 +7149,33 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) preempt_enable(); } -#else -static inline int rt_effective_prio(struct task_struct *p, int prio) -{ - return prio; -} #endif -void set_user_nice(struct task_struct *p, long nice) +#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) +int __sched __cond_resched(void) { - bool queued, running; - int old_prio; - struct rq_flags rf; - struct rq *rq; - - if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE) - return; + if (should_resched(0) && !irqs_disabled()) { + preempt_schedule_common(); + return 1; + } /* - * We have to be careful, if called from sys_setpriority(), - * the task might be in the middle of scheduling on another CPU. + * In preemptible kernels, ->rcu_read_lock_nesting tells the tick + * whether the current CPU is in an RCU read-side critical section, + * so the tick can report quiescent states even for CPUs looping + * in kernel context. In contrast, in non-preemptible kernels, + * RCU readers leave no in-memory hints, which means that CPU-bound + * processes executing in kernel context might never report an + * RCU quiescent state. Therefore, the following code causes + * cond_resched() to report a quiescent state, but only when RCU + * is in urgent need of one. */ - rq = task_rq_lock(p, &rf); - update_rq_clock(rq); - - /* - * The RT priorities are set via sched_setscheduler(), but we still - * allow the 'normal' nice value to be set - but as expected - * it won't have any effect on scheduling until the task is - * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR: - */ - if (task_has_dl_policy(p) || task_has_rt_policy(p)) { - p->static_prio = NICE_TO_PRIO(nice); - goto out_unlock; - } - queued = task_on_rq_queued(p); - running = task_current(rq, p); - if (queued) - dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK); - if (running) - put_prev_task(rq, p); - - p->static_prio = NICE_TO_PRIO(nice); - set_load_weight(p, true); - old_prio = p->prio; - p->prio = effective_prio(p); - - if (queued) - enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK); - if (running) - set_next_task(rq, p); - - /* - * If the task increased its priority or is running and - * lowered its priority, then reschedule its CPU: - */ - p->sched_class->prio_changed(rq, p, old_prio); - -out_unlock: - task_rq_unlock(rq, p, &rf); -} -EXPORT_SYMBOL(set_user_nice); - -/* - * is_nice_reduction - check if nice value is an actual reduction - * - * Similar to can_nice() but does not perform a capability check. - * - * @p: task - * @nice: nice value - */ -static bool is_nice_reduction(const struct task_struct *p, const int nice) -{ - /* Convert nice value [19,-20] to rlimit style value [1,40]: */ - int nice_rlim = nice_to_rlimit(nice); - - return (nice_rlim <= task_rlimit(p, RLIMIT_NICE)); -} - -/* - * can_nice - check if a task can reduce its nice value - * @p: task - * @nice: nice value - */ -int can_nice(const struct task_struct *p, const int nice) -{ - return is_nice_reduction(p, nice) || capable(CAP_SYS_NICE); -} - -#ifdef __ARCH_WANT_SYS_NICE - -/* - * sys_nice - change the priority of the current process. - * @increment: priority increment - * - * sys_setpriority is a more generic, but much slower function that - * does similar things. - */ -SYSCALL_DEFINE1(nice, int, increment) -{ - long nice, retval; - - /* - * Setpriority might change our priority at the same moment. - * We don't have to worry. Conceptually one call occurs first - * and we have a single winner. - */ - increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH); - nice = task_nice(current) + increment; - - nice = clamp_val(nice, MIN_NICE, MAX_NICE); - if (increment < 0 && !can_nice(current, nice)) - return -EPERM; - - retval = security_task_setnice(current, nice); - if (retval) - return retval; - - set_user_nice(current, nice); - return 0; -} - -#endif - -/** - * task_prio - return the priority value of a given task. - * @p: the task in question. - * - * Return: The priority value as seen by users in /proc. - * - * sched policy return value kernel prio user prio/nice - * - * normal, batch, idle [0 ... 39] [100 ... 139] 0/[-20 ... 19] - * fifo, rr [-2 ... -100] [98 ... 0] [1 ... 99] - * deadline -101 -1 0 - */ -int task_prio(const struct task_struct *p) -{ - return p->prio - MAX_RT_PRIO; -} - -/** - * idle_cpu - is a given CPU idle currently? - * @cpu: the processor in question. - * - * Return: 1 if the CPU is currently idle. 0 otherwise. - */ -int idle_cpu(int cpu) -{ - struct rq *rq = cpu_rq(cpu); - - if (rq->curr != rq->idle) - return 0; - - if (rq->nr_running) - return 0; - -#ifdef CONFIG_SMP - if (rq->ttwu_pending) - return 0; -#endif - - return 1; -} - -/** - * available_idle_cpu - is a given CPU idle for enqueuing work. - * @cpu: the CPU in question. - * - * Return: 1 if the CPU is currently idle. 0 otherwise. - */ -int available_idle_cpu(int cpu) -{ - if (!idle_cpu(cpu)) - return 0; - - if (vcpu_is_preempted(cpu)) - return 0; - - return 1; -} - -/** - * idle_task - return the idle task for a given CPU. - * @cpu: the processor in question. - * - * Return: The idle task for the CPU @cpu. - */ -struct task_struct *idle_task(int cpu) -{ - return cpu_rq(cpu)->idle; -} - -#ifdef CONFIG_SCHED_CORE -int sched_core_idle_cpu(int cpu) -{ - struct rq *rq = cpu_rq(cpu); - - if (sched_core_enabled(rq) && rq->curr == rq->idle) - return 1; - - return idle_cpu(cpu); -} - -#endif - -#ifdef CONFIG_SMP -/* - * This function computes an effective utilization for the given CPU, to be - * used for frequency selection given the linear relation: f = u * f_max. - * - * The scheduler tracks the following metrics: - * - * cpu_util_{cfs,rt,dl,irq}() - * cpu_bw_dl() - * - * Where the cfs,rt and dl util numbers are tracked with the same metric and - * synchronized windows and are thus directly comparable. - * - * The cfs,rt,dl utilization are the running times measured with rq->clock_task - * which excludes things like IRQ and steal-time. These latter are then accrued - * in the irq utilization. - * - * The DL bandwidth number otoh is not a measured metric but a value computed - * based on the task model parameters and gives the minimal utilization - * required to meet deadlines. - */ -unsigned long effective_cpu_util(int cpu, unsigned long util_cfs, - enum cpu_util_type type, - struct task_struct *p) -{ - unsigned long dl_util, util, irq, max; - struct rq *rq = cpu_rq(cpu); - - max = arch_scale_cpu_capacity(cpu); - - if (!uclamp_is_used() && - type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) { - return max; - } - - /* - * Early check to see if IRQ/steal time saturates the CPU, can be - * because of inaccuracies in how we track these -- see - * update_irq_load_avg(). - */ - irq = cpu_util_irq(rq); - if (unlikely(irq >= max)) - return max; - - /* - * Because the time spend on RT/DL tasks is visible as 'lost' time to - * CFS tasks and we use the same metric to track the effective - * utilization (PELT windows are synchronized) we can directly add them - * to obtain the CPU's actual utilization. - * - * CFS and RT utilization can be boosted or capped, depending on - * utilization clamp constraints requested by currently RUNNABLE - * tasks. - * When there are no CFS RUNNABLE tasks, clamps are released and - * frequency will be gracefully reduced with the utilization decay. - */ - util = util_cfs + cpu_util_rt(rq); - if (type == FREQUENCY_UTIL) - util = uclamp_rq_util_with(rq, util, p); - - dl_util = cpu_util_dl(rq); - - /* - * For frequency selection we do not make cpu_util_dl() a permanent part - * of this sum because we want to use cpu_bw_dl() later on, but we need - * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such - * that we select f_max when there is no idle time. - * - * NOTE: numerical errors or stop class might cause us to not quite hit - * saturation when we should -- something for later. - */ - if (util + dl_util >= max) - return max; - - /* - * OTOH, for energy computation we need the estimated running time, so - * include util_dl and ignore dl_bw. - */ - if (type == ENERGY_UTIL) - util += dl_util; - - /* - * There is still idle time; further improve the number by using the - * irq metric. Because IRQ/steal time is hidden from the task clock we - * need to scale the task numbers: - * - * max - irq - * U' = irq + --------- * U - * max - */ - util = scale_irq_capacity(util, irq, max); - util += irq; - - /* - * Bandwidth required by DEADLINE must always be granted while, for - * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism - * to gracefully reduce the frequency when no tasks show up for longer - * periods of time. - * - * Ideally we would like to set bw_dl as min/guaranteed freq and util + - * bw_dl as requested freq. However, cpufreq is not yet ready for such - * an interface. So, we only do the latter for now. - */ - if (type == FREQUENCY_UTIL) - util += cpu_bw_dl(rq); - - return min(max, util); -} - -unsigned long sched_cpu_util(int cpu) -{ - return effective_cpu_util(cpu, cpu_util_cfs(cpu), ENERGY_UTIL, NULL); -} -#endif /* CONFIG_SMP */ - -/** - * find_process_by_pid - find a process with a matching PID value. - * @pid: the pid in question. - * - * The task of @pid, if found. %NULL otherwise. - */ -static struct task_struct *find_process_by_pid(pid_t pid) -{ - return pid ? find_task_by_vpid(pid) : current; -} - -/* - * sched_setparam() passes in -1 for its policy, to let the functions - * it calls know not to change it. - */ -#define SETPARAM_POLICY -1 - -static void __setscheduler_params(struct task_struct *p, - const struct sched_attr *attr) -{ - int policy = attr->sched_policy; - - if (policy == SETPARAM_POLICY) - policy = p->policy; - - p->policy = policy; - - if (dl_policy(policy)) - __setparam_dl(p, attr); - else if (fair_policy(policy)) - p->static_prio = NICE_TO_PRIO(attr->sched_nice); - - /* rt-policy tasks do not have a timerslack */ - if (task_is_realtime(p)) { - p->timer_slack_ns = 0; - } else if (p->timer_slack_ns == 0) { - /* when switching back to non-rt policy, restore timerslack */ - p->timer_slack_ns = p->default_timer_slack_ns; - } - - /* - * __sched_setscheduler() ensures attr->sched_priority == 0 when - * !rt_policy. Always setting this ensures that things like - * getparam()/getattr() don't report silly values for !rt tasks. - */ - p->rt_priority = attr->sched_priority; - p->normal_prio = normal_prio(p); - set_load_weight(p, true); -} - -/* - * Check the target process has a UID that matches the current process's: - */ -static bool check_same_owner(struct task_struct *p) -{ - const struct cred *cred = current_cred(), *pcred; - bool match; - - rcu_read_lock(); - pcred = __task_cred(p); - match = (uid_eq(cred->euid, pcred->euid) || - uid_eq(cred->euid, pcred->uid)); - rcu_read_unlock(); - return match; -} - -/* - * Allow unprivileged RT tasks to decrease priority. - * Only issue a capable test if needed and only once to avoid an audit - * event on permitted non-privileged operations: - */ -static int user_check_sched_setscheduler(struct task_struct *p, - const struct sched_attr *attr, - int policy, int reset_on_fork) -{ - if (fair_policy(policy)) { - if (attr->sched_nice < task_nice(p) && - !is_nice_reduction(p, attr->sched_nice)) - goto req_priv; - } - - if (rt_policy(policy)) { - unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); - - /* Can't set/change the rt policy: */ - if (policy != p->policy && !rlim_rtprio) - goto req_priv; - - /* Can't increase priority: */ - if (attr->sched_priority > p->rt_priority && - attr->sched_priority > rlim_rtprio) - goto req_priv; - } - - /* - * Can't set/change SCHED_DEADLINE policy at all for now - * (safest behavior); in the future we would like to allow - * unprivileged DL tasks to increase their relative deadline - * or reduce their runtime (both ways reducing utilization) - */ - if (dl_policy(policy)) - goto req_priv; - - /* - * Treat SCHED_IDLE as nice 20. Only allow a switch to - * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. - */ - if (task_has_idle_policy(p) && !idle_policy(policy)) { - if (!is_nice_reduction(p, task_nice(p))) - goto req_priv; - } - - /* Can't change other user's priorities: */ - if (!check_same_owner(p)) - goto req_priv; - - /* Normal users shall not reset the sched_reset_on_fork flag: */ - if (p->sched_reset_on_fork && !reset_on_fork) - goto req_priv; - - return 0; - -req_priv: - if (!capable(CAP_SYS_NICE)) - return -EPERM; - - return 0; -} - -static int __sched_setscheduler(struct task_struct *p, - const struct sched_attr *attr, - bool user, bool pi) -{ - int oldpolicy = -1, policy = attr->sched_policy; - int retval, oldprio, newprio, queued, running; - const struct sched_class *prev_class; - struct balance_callback *head; - struct rq_flags rf; - int reset_on_fork; - int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; - struct rq *rq; - bool cpuset_locked = false; - - /* The pi code expects interrupts enabled */ - BUG_ON(pi && in_interrupt()); -recheck: - /* Double check policy once rq lock held: */ - if (policy < 0) { - reset_on_fork = p->sched_reset_on_fork; - policy = oldpolicy = p->policy; - } else { - reset_on_fork = !!(attr->sched_flags & SCHED_FLAG_RESET_ON_FORK); - - if (!valid_policy(policy)) - return -EINVAL; - } - - if (attr->sched_flags & ~(SCHED_FLAG_ALL | SCHED_FLAG_SUGOV)) - return -EINVAL; - - /* - * Valid priorities for SCHED_FIFO and SCHED_RR are - * 1..MAX_RT_PRIO-1, valid priority for SCHED_NORMAL, - * SCHED_BATCH and SCHED_IDLE is 0. - */ - if (attr->sched_priority > MAX_RT_PRIO-1) - return -EINVAL; - if ((dl_policy(policy) && !__checkparam_dl(attr)) || - (rt_policy(policy) != (attr->sched_priority != 0))) - return -EINVAL; - - if (user) { - retval = user_check_sched_setscheduler(p, attr, policy, reset_on_fork); - if (retval) - return retval; - - if (attr->sched_flags & SCHED_FLAG_SUGOV) - return -EINVAL; - - retval = security_task_setscheduler(p); - if (retval) - return retval; - } - - /* Update task specific "requested" clamps */ - if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) { - retval = uclamp_validate(p, attr); - if (retval) - return retval; - } - - /* - * SCHED_DEADLINE bandwidth accounting relies on stable cpusets - * information. - */ - if (dl_policy(policy) || dl_policy(p->policy)) { - cpuset_locked = true; - cpuset_lock(); - } - - /* - * Make sure no PI-waiters arrive (or leave) while we are - * changing the priority of the task: - * - * To be able to change p->policy safely, the appropriate - * runqueue lock must be held. - */ - rq = task_rq_lock(p, &rf); - update_rq_clock(rq); - - /* - * Changing the policy of the stop threads its a very bad idea: - */ - if (p == rq->stop) { - retval = -EINVAL; - goto unlock; - } - - /* - * If not changing anything there's no need to proceed further, - * but store a possible modification of reset_on_fork. - */ - if (unlikely(policy == p->policy)) { - if (fair_policy(policy) && attr->sched_nice != task_nice(p)) - goto change; - if (rt_policy(policy) && attr->sched_priority != p->rt_priority) - goto change; - if (dl_policy(policy) && dl_param_changed(p, attr)) - goto change; - if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) - goto change; - - p->sched_reset_on_fork = reset_on_fork; - retval = 0; - goto unlock; - } -change: - -#ifdef CONFIG_QOS_SCHED - /* - * If the scheduling policy of an offline task is set to a policy - * other than SCHED_IDLE, the online task preemption and cpu resource - * isolation will be invalid, so return -EINVAL in this case. - */ - if (unlikely(is_offline_level(task_group(p)->qos_level) && !idle_policy(policy))) { - retval = -EINVAL; - goto unlock; - } -#endif - - if (user) { -#ifdef CONFIG_RT_GROUP_SCHED - /* - * Do not allow realtime tasks into groups that have no runtime - * assigned. - */ - if (rt_bandwidth_enabled() && rt_policy(policy) && - task_group(p)->rt_bandwidth.rt_runtime == 0 && - !task_group_is_autogroup(task_group(p))) { - retval = -EPERM; - goto unlock; - } -#endif -#ifdef CONFIG_SMP - if (dl_bandwidth_enabled() && dl_policy(policy) && - !(attr->sched_flags & SCHED_FLAG_SUGOV)) { - cpumask_t *span = rq->rd->span; - - /* - * Don't allow tasks with an affinity mask smaller than - * the entire root_domain to become SCHED_DEADLINE. We - * will also fail if there's no bandwidth available. - */ - if (!cpumask_subset(span, p->cpus_ptr) || - rq->rd->dl_bw.bw == 0) { - retval = -EPERM; - goto unlock; - } - } -#endif - } - - /* Re-check policy now with rq lock held: */ - if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { - policy = oldpolicy = -1; - task_rq_unlock(rq, p, &rf); - if (cpuset_locked) - cpuset_unlock(); - goto recheck; - } - - /* - * If setscheduling to SCHED_DEADLINE (or changing the parameters - * of a SCHED_DEADLINE task) we need to check if enough bandwidth - * is available. - */ - if ((dl_policy(policy) || dl_task(p)) && sched_dl_overflow(p, policy, attr)) { - retval = -EBUSY; - goto unlock; - } - - p->sched_reset_on_fork = reset_on_fork; - oldprio = p->prio; - - newprio = __normal_prio(policy, attr->sched_priority, attr->sched_nice); - if (pi) { - /* - * Take priority boosted tasks into account. If the new - * effective priority is unchanged, we just store the new - * normal parameters and do not touch the scheduler class and - * the runqueue. This will be done when the task deboost - * itself. - */ - newprio = rt_effective_prio(p, newprio); - if (newprio == oldprio) - queue_flags &= ~DEQUEUE_MOVE; - } - - queued = task_on_rq_queued(p); - running = task_current(rq, p); - if (queued) - dequeue_task(rq, p, queue_flags); - if (running) - put_prev_task(rq, p); - - prev_class = p->sched_class; - - if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) { - __setscheduler_params(p, attr); - __setscheduler_prio(p, newprio); - } - __setscheduler_uclamp(p, attr); - - if (queued) { - /* - * We enqueue to tail when the priority of a task is - * increased (user space view). - */ - if (oldprio < p->prio) - queue_flags |= ENQUEUE_HEAD; - - enqueue_task(rq, p, queue_flags); - } - if (running) - set_next_task(rq, p); - - check_class_changed(rq, p, prev_class, oldprio); - - /* Avoid rq from going away on us: */ - preempt_disable(); - head = splice_balance_callbacks(rq); - task_rq_unlock(rq, p, &rf); - - if (pi) { - if (cpuset_locked) - cpuset_unlock(); - rt_mutex_adjust_pi(p); - } - - /* Run balance callbacks after we've adjusted the PI chain: */ - balance_callbacks(rq, head); - preempt_enable(); - - return 0; - -unlock: - task_rq_unlock(rq, p, &rf); - if (cpuset_locked) - cpuset_unlock(); - return retval; -} - -static int _sched_setscheduler(struct task_struct *p, int policy, - const struct sched_param *param, bool check) -{ - struct sched_attr attr = { - .sched_policy = policy, - .sched_priority = param->sched_priority, - .sched_nice = PRIO_TO_NICE(p->static_prio), - }; - - /* Fixup the legacy SCHED_RESET_ON_FORK hack. */ - if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) { - attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; - policy &= ~SCHED_RESET_ON_FORK; - attr.sched_policy = policy; - } - - return __sched_setscheduler(p, &attr, check, true); -} -/** - * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. - * @p: the task in question. - * @policy: new policy. - * @param: structure containing the new RT priority. - * - * Use sched_set_fifo(), read its comment. - * - * Return: 0 on success. An error code otherwise. - * - * NOTE that the task may be already dead. - */ -int sched_setscheduler(struct task_struct *p, int policy, - const struct sched_param *param) -{ - return _sched_setscheduler(p, policy, param, true); -} - -int sched_setattr(struct task_struct *p, const struct sched_attr *attr) -{ - return __sched_setscheduler(p, attr, true, true); -} - -int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr) -{ - return __sched_setscheduler(p, attr, false, true); -} -EXPORT_SYMBOL_GPL(sched_setattr_nocheck); - -/** - * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. - * @p: the task in question. - * @policy: new policy. - * @param: structure containing the new RT priority. - * - * Just like sched_setscheduler, only don't bother checking if the - * current context has permission. For example, this is needed in - * stop_machine(): we create temporary high priority worker threads, - * but our caller might not have that capability. - * - * Return: 0 on success. An error code otherwise. - */ -int sched_setscheduler_nocheck(struct task_struct *p, int policy, - const struct sched_param *param) -{ - return _sched_setscheduler(p, policy, param, false); -} - -/* - * SCHED_FIFO is a broken scheduler model; that is, it is fundamentally - * incapable of resource management, which is the one thing an OS really should - * be doing. - * - * This is of course the reason it is limited to privileged users only. - * - * Worse still; it is fundamentally impossible to compose static priority - * workloads. You cannot take two correctly working static prio workloads - * and smash them together and still expect them to work. - * - * For this reason 'all' FIFO tasks the kernel creates are basically at: - * - * MAX_RT_PRIO / 2 - * - * The administrator _MUST_ configure the system, the kernel simply doesn't - * know enough information to make a sensible choice. - */ -void sched_set_fifo(struct task_struct *p) -{ - struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 }; - WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0); -} -EXPORT_SYMBOL_GPL(sched_set_fifo); - -/* - * For when you don't much care about FIFO, but want to be above SCHED_NORMAL. - */ -void sched_set_fifo_low(struct task_struct *p) -{ - struct sched_param sp = { .sched_priority = 1 }; - WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0); -} -EXPORT_SYMBOL_GPL(sched_set_fifo_low); - -void sched_set_normal(struct task_struct *p, int nice) -{ - struct sched_attr attr = { - .sched_policy = SCHED_NORMAL, - .sched_nice = nice, - }; - WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0); -} -EXPORT_SYMBOL_GPL(sched_set_normal); - -static int -do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) -{ - struct sched_param lparam; - struct task_struct *p; - int retval; - - if (!param || pid < 0) - return -EINVAL; - if (copy_from_user(&lparam, param, sizeof(struct sched_param))) - return -EFAULT; - - rcu_read_lock(); - retval = -ESRCH; - p = find_process_by_pid(pid); - if (likely(p)) - get_task_struct(p); - rcu_read_unlock(); - - if (likely(p)) { - retval = sched_setscheduler(p, policy, &lparam); - put_task_struct(p); - } - - return retval; -} - -/* - * Mimics kernel/events/core.c perf_copy_attr(). - */ -static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *attr) -{ - u32 size; - int ret; - - /* Zero the full structure, so that a short copy will be nice: */ - memset(attr, 0, sizeof(*attr)); - - ret = get_user(size, &uattr->size); - if (ret) - return ret; - - /* ABI compatibility quirk: */ - if (!size) - size = SCHED_ATTR_SIZE_VER0; - if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE) - goto err_size; - - ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size); - if (ret) { - if (ret == -E2BIG) - goto err_size; - return ret; - } - - if ((attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) && - size < SCHED_ATTR_SIZE_VER1) - return -EINVAL; - - /* - * XXX: Do we want to be lenient like existing syscalls; or do we want - * to be strict and return an error on out-of-bounds values? - */ - attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE); - - return 0; - -err_size: - put_user(sizeof(*attr), &uattr->size); - return -E2BIG; -} - -static void get_params(struct task_struct *p, struct sched_attr *attr) -{ - if (task_has_dl_policy(p)) - __getparam_dl(p, attr); - else if (task_has_rt_policy(p)) - attr->sched_priority = p->rt_priority; - else - attr->sched_nice = task_nice(p); -} - -/** - * sys_sched_setscheduler - set/change the scheduler policy and RT priority - * @pid: the pid in question. - * @policy: new policy. - * @param: structure containing the new RT priority. - * - * Return: 0 on success. An error code otherwise. - */ -SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param) -{ - if (policy < 0) - return -EINVAL; - - return do_sched_setscheduler(pid, policy, param); -} - -/** - * sys_sched_setparam - set/change the RT priority of a thread - * @pid: the pid in question. - * @param: structure containing the new RT priority. - * - * Return: 0 on success. An error code otherwise. - */ -SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) -{ - return do_sched_setscheduler(pid, SETPARAM_POLICY, param); -} - -/** - * sys_sched_setattr - same as above, but with extended sched_attr - * @pid: the pid in question. - * @uattr: structure containing the extended parameters. - * @flags: for future extension. - */ -SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, - unsigned int, flags) -{ - struct sched_attr attr; - struct task_struct *p; - int retval; - - if (!uattr || pid < 0 || flags) - return -EINVAL; - - retval = sched_copy_attr(uattr, &attr); - if (retval) - return retval; - - if ((int)attr.sched_policy < 0) - return -EINVAL; - if (attr.sched_flags & SCHED_FLAG_KEEP_POLICY) - attr.sched_policy = SETPARAM_POLICY; - - rcu_read_lock(); - retval = -ESRCH; - p = find_process_by_pid(pid); - if (likely(p)) - get_task_struct(p); - rcu_read_unlock(); - - if (likely(p)) { - if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS) - get_params(p, &attr); - retval = sched_setattr(p, &attr); - put_task_struct(p); - } - - return retval; -} - -/** - * sys_sched_getscheduler - get the policy (scheduling class) of a thread - * @pid: the pid in question. - * - * Return: On success, the policy of the thread. Otherwise, a negative error - * code. - */ -SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) -{ - struct task_struct *p; - int retval; - - if (pid < 0) - return -EINVAL; - - retval = -ESRCH; - rcu_read_lock(); - p = find_process_by_pid(pid); - if (p) { - retval = security_task_getscheduler(p); - if (!retval) - retval = p->policy - | (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0); - } - rcu_read_unlock(); - return retval; -} - -/** - * sys_sched_getparam - get the RT priority of a thread - * @pid: the pid in question. - * @param: structure containing the RT priority. - * - * Return: On success, 0 and the RT priority is in @param. Otherwise, an error - * code. - */ -SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) -{ - struct sched_param lp = { .sched_priority = 0 }; - struct task_struct *p; - int retval; - - if (!param || pid < 0) - return -EINVAL; - - rcu_read_lock(); - p = find_process_by_pid(pid); - retval = -ESRCH; - if (!p) - goto out_unlock; - - retval = security_task_getscheduler(p); - if (retval) - goto out_unlock; - - if (task_has_rt_policy(p)) - lp.sched_priority = p->rt_priority; - rcu_read_unlock(); - - /* - * This one might sleep, we cannot do it with a spinlock held ... - */ - retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0; - - return retval; - -out_unlock: - rcu_read_unlock(); - return retval; -} - -/* - * Copy the kernel size attribute structure (which might be larger - * than what user-space knows about) to user-space. - * - * Note that all cases are valid: user-space buffer can be larger or - * smaller than the kernel-space buffer. The usual case is that both - * have the same size. - */ -static int -sched_attr_copy_to_user(struct sched_attr __user *uattr, - struct sched_attr *kattr, - unsigned int usize) -{ - unsigned int ksize = sizeof(*kattr); - - if (!access_ok(uattr, usize)) - return -EFAULT; - - /* - * sched_getattr() ABI forwards and backwards compatibility: - * - * If usize == ksize then we just copy everything to user-space and all is good. - * - * If usize < ksize then we only copy as much as user-space has space for, - * this keeps ABI compatibility as well. We skip the rest. - * - * If usize > ksize then user-space is using a newer version of the ABI, - * which part the kernel doesn't know about. Just ignore it - tooling can - * detect the kernel's knowledge of attributes from the attr->size value - * which is set to ksize in this case. - */ - kattr->size = min(usize, ksize); - - if (copy_to_user(uattr, kattr, kattr->size)) - return -EFAULT; - - return 0; -} - -/** - * sys_sched_getattr - similar to sched_getparam, but with sched_attr - * @pid: the pid in question. - * @uattr: structure containing the extended parameters. - * @usize: sizeof(attr) for fwd/bwd comp. - * @flags: for future extension. - */ -SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, - unsigned int, usize, unsigned int, flags) -{ - struct sched_attr kattr = { }; - struct task_struct *p; - int retval; - - if (!uattr || pid < 0 || usize > PAGE_SIZE || - usize < SCHED_ATTR_SIZE_VER0 || flags) - return -EINVAL; - - rcu_read_lock(); - p = find_process_by_pid(pid); - retval = -ESRCH; - if (!p) - goto out_unlock; - - retval = security_task_getscheduler(p); - if (retval) - goto out_unlock; - - kattr.sched_policy = p->policy; - if (p->sched_reset_on_fork) - kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; - get_params(p, &kattr); - kattr.sched_flags &= SCHED_FLAG_ALL; - -#ifdef CONFIG_UCLAMP_TASK - /* - * This could race with another potential updater, but this is fine - * because it'll correctly read the old or the new value. We don't need - * to guarantee who wins the race as long as it doesn't return garbage. - */ - kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value; - kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value; -#endif - - rcu_read_unlock(); - - return sched_attr_copy_to_user(uattr, &kattr, usize); - -out_unlock: - rcu_read_unlock(); - return retval; -} - -#ifdef CONFIG_SMP -int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask) -{ - int ret = 0; - - /* - * If the task isn't a deadline task or admission control is - * disabled then we don't care about affinity changes. - */ - if (!task_has_dl_policy(p) || !dl_bandwidth_enabled()) - return 0; - - /* - * Since bandwidth control happens on root_domain basis, - * if admission test is enabled, we only admit -deadline - * tasks allowed to run on all the CPUs in the task's - * root_domain. - */ - rcu_read_lock(); - if (!cpumask_subset(task_rq(p)->rd->span, mask)) - ret = -EBUSY; - rcu_read_unlock(); - return ret; -} -#endif - -static int -__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx) -{ - int retval; - cpumask_var_t cpus_allowed, new_mask; - - if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) - return -ENOMEM; - - if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) { - retval = -ENOMEM; - goto out_free_cpus_allowed; - } - - cpuset_cpus_allowed(p, cpus_allowed); - cpumask_and(new_mask, ctx->new_mask, cpus_allowed); - - ctx->new_mask = new_mask; - ctx->flags |= SCA_CHECK; - - retval = dl_task_check_affinity(p, new_mask); - if (retval) - goto out_free_new_mask; - - retval = __set_cpus_allowed_ptr(p, ctx); - if (retval) - goto out_free_new_mask; - - cpuset_cpus_allowed(p, cpus_allowed); - if (!cpumask_subset(new_mask, cpus_allowed)) { - /* - * We must have raced with a concurrent cpuset update. - * Just reset the cpumask to the cpuset's cpus_allowed. - */ - cpumask_copy(new_mask, cpus_allowed); - - /* - * If SCA_USER is set, a 2nd call to __set_cpus_allowed_ptr() - * will restore the previous user_cpus_ptr value. - * - * In the unlikely event a previous user_cpus_ptr exists, - * we need to further restrict the mask to what is allowed - * by that old user_cpus_ptr. - */ - if (unlikely((ctx->flags & SCA_USER) && ctx->user_mask)) { - bool empty = !cpumask_and(new_mask, new_mask, - ctx->user_mask); - - if (empty) - cpumask_copy(new_mask, cpus_allowed); - } - __set_cpus_allowed_ptr(p, ctx); - retval = -EINVAL; - } - -out_free_new_mask: - free_cpumask_var(new_mask); -out_free_cpus_allowed: - free_cpumask_var(cpus_allowed); - return retval; -} - -long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) -{ - struct affinity_context ac; - struct cpumask *user_mask; - struct task_struct *p; - int retval; - - rcu_read_lock(); - - p = find_process_by_pid(pid); - if (!p) { - rcu_read_unlock(); - return -ESRCH; - } - - /* Prevent p going away */ - get_task_struct(p); - rcu_read_unlock(); - - if (p->flags & PF_NO_SETAFFINITY) { - retval = -EINVAL; - goto out_put_task; - } - - if (!check_same_owner(p)) { - rcu_read_lock(); - if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { - rcu_read_unlock(); - retval = -EPERM; - goto out_put_task; - } - rcu_read_unlock(); - } - - retval = security_task_setscheduler(p); - if (retval) - goto out_put_task; - - /* - * With non-SMP configs, user_cpus_ptr/user_mask isn't used and - * alloc_user_cpus_ptr() returns NULL. - */ - user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE); - if (user_mask) { - cpumask_copy(user_mask, in_mask); - } else if (IS_ENABLED(CONFIG_SMP)) { - retval = -ENOMEM; - goto out_put_task; - } - - ac = (struct affinity_context){ - .new_mask = in_mask, - .user_mask = user_mask, - .flags = SCA_USER, - }; - - retval = __sched_setaffinity(p, &ac); - kfree(ac.user_mask); - -out_put_task: - put_task_struct(p); - return retval; -} - -static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, - struct cpumask *new_mask) -{ - if (len < cpumask_size()) - cpumask_clear(new_mask); - else if (len > cpumask_size()) - len = cpumask_size(); - - return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0; -} - -/** - * sys_sched_setaffinity - set the CPU affinity of a process - * @pid: pid of the process - * @len: length in bytes of the bitmask pointed to by user_mask_ptr - * @user_mask_ptr: user-space pointer to the new CPU mask - * - * Return: 0 on success. An error code otherwise. - */ -SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, - unsigned long __user *, user_mask_ptr) -{ - cpumask_var_t new_mask; - int retval; - - if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) - return -ENOMEM; - - retval = get_user_cpu_mask(user_mask_ptr, len, new_mask); - if (retval == 0) - retval = sched_setaffinity(pid, new_mask); - free_cpumask_var(new_mask); - return retval; -} - -long sched_getaffinity(pid_t pid, struct cpumask *mask) -{ - struct task_struct *p; - unsigned long flags; - int retval; - - rcu_read_lock(); - - retval = -ESRCH; - p = find_process_by_pid(pid); - if (!p) - goto out_unlock; - - retval = security_task_getscheduler(p); - if (retval) - goto out_unlock; - - raw_spin_lock_irqsave(&p->pi_lock, flags); - cpumask_and(mask, &p->cpus_mask, cpu_active_mask); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); - -out_unlock: - rcu_read_unlock(); - - return retval; -} - -/** - * sys_sched_getaffinity - get the CPU affinity of a process - * @pid: pid of the process - * @len: length in bytes of the bitmask pointed to by user_mask_ptr - * @user_mask_ptr: user-space pointer to hold the current CPU mask - * - * Return: size of CPU mask copied to user_mask_ptr on success. An - * error code otherwise. - */ -SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, - unsigned long __user *, user_mask_ptr) -{ - int ret; - cpumask_var_t mask; - - if ((len * BITS_PER_BYTE) < nr_cpu_ids) - return -EINVAL; - if (len & (sizeof(unsigned long)-1)) - return -EINVAL; - - if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) - return -ENOMEM; - - ret = sched_getaffinity(pid, mask); - if (ret == 0) { - unsigned int retlen = min(len, cpumask_size()); - - if (copy_to_user(user_mask_ptr, cpumask_bits(mask), retlen)) - ret = -EFAULT; - else - ret = retlen; - } - free_cpumask_var(mask); - - return ret; -} - -static void do_sched_yield(void) -{ - struct rq_flags rf; - struct rq *rq; - - rq = this_rq_lock_irq(&rf); - - schedstat_inc(rq->yld_count); - current->sched_class->yield_task(rq); - - preempt_disable(); - rq_unlock_irq(rq, &rf); - sched_preempt_enable_no_resched(); - - schedule(); -} - -/** - * sys_sched_yield - yield the current processor to other threads. - * - * This function yields the current CPU to other tasks. If there are no - * other threads running on this CPU then this function will return. - * - * Return: 0. - */ -SYSCALL_DEFINE0(sched_yield) -{ - do_sched_yield(); - return 0; -} - -#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) -int __sched __cond_resched(void) -{ - if (should_resched(0) && !irqs_disabled()) { - preempt_schedule_common(); - return 1; - } - /* - * In preemptible kernels, ->rcu_read_lock_nesting tells the tick - * whether the current CPU is in an RCU read-side critical section, - * so the tick can report quiescent states even for CPUs looping - * in kernel context. In contrast, in non-preemptible kernels, - * RCU readers leave no in-memory hints, which means that CPU-bound - * processes executing in kernel context might never report an - * RCU quiescent state. Therefore, the following code causes - * cond_resched() to report a quiescent state, but only when RCU - * is in urgent need of one. - */ -#ifndef CONFIG_PREEMPT_RCU - rcu_all_qs(); -#endif - return 0; -} -EXPORT_SYMBOL(__cond_resched); -#endif +#ifndef CONFIG_PREEMPT_RCU + rcu_all_qs(); +#endif + return 0; +} +EXPORT_SYMBOL(__cond_resched); +#endif #ifdef CONFIG_PREEMPT_DYNAMIC #if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) @@ -8991,109 +7479,6 @@ static inline void preempt_dynamic_init(void) { } #endif /* #ifdef CONFIG_PREEMPT_DYNAMIC */ -/** - * yield - yield the current processor to other threads. - * - * Do not ever use this function, there's a 99% chance you're doing it wrong. - * - * The scheduler is at all times free to pick the calling task as the most - * eligible task to run, if removing the yield() call from your code breaks - * it, it's already broken. - * - * Typical broken usage is: - * - * while (!event) - * yield(); - * - * where one assumes that yield() will let 'the other' process run that will - * make event true. If the current task is a SCHED_FIFO task that will never - * happen. Never use yield() as a progress guarantee!! - * - * If you want to use yield() to wait for something, use wait_event(). - * If you want to use yield() to be 'nice' for others, use cond_resched(). - * If you still want to use yield(), do not! - */ -void __sched yield(void) -{ - set_current_state(TASK_RUNNING); - do_sched_yield(); -} -EXPORT_SYMBOL(yield); - -/** - * yield_to - yield the current processor to another thread in - * your thread group, or accelerate that thread toward the - * processor it's on. - * @p: target task - * @preempt: whether task preemption is allowed or not - * - * It's the caller's job to ensure that the target task struct - * can't go away on us before we can do any checks. - * - * Return: - * true (>0) if we indeed boosted the target task. - * false (0) if we failed to boost the target. - * -ESRCH if there's no task to yield to. - */ -int __sched yield_to(struct task_struct *p, bool preempt) -{ - struct task_struct *curr = current; - struct rq *rq, *p_rq; - unsigned long flags; - int yielded = 0; - - raw_spin_lock_irqsave(&p->pi_lock, flags); - rq = this_rq(); - -again: - p_rq = task_rq(p); - /* - * If we're the only runnable task on the rq and target rq also - * has only one task, there's absolutely no point in yielding. - */ - if (rq->nr_running == 1 && p_rq->nr_running == 1) { - yielded = -ESRCH; - goto out_irq; - } - - double_rq_lock(rq, p_rq); - if (task_rq(p) != p_rq) { - double_rq_unlock(rq, p_rq); - goto again; - } - - if (!curr->sched_class->yield_to_task) - goto out_unlock; - - if (curr->sched_class != p->sched_class) - goto out_unlock; - - if (task_on_cpu(p_rq, p) || !task_is_running(p)) - goto out_unlock; - - yielded = curr->sched_class->yield_to_task(rq, p); - if (yielded) { - schedstat_inc(rq->yld_count); - /* - * Make p's CPU reschedule; pick_next_entity takes care of - * fairness. - */ - if (preempt && rq != p_rq) - resched_curr(p_rq); - } - -out_unlock: - double_rq_unlock(rq, p_rq); -out_irq: - raw_spin_unlock_irqrestore(&p->pi_lock, flags); - - if (yielded > 0) - schedule(); - - return yielded; -} -EXPORT_SYMBOL_GPL(yield_to); - int io_schedule_prepare(void) { int old_iowait = current->in_iowait; @@ -9135,131 +7520,6 @@ void __sched io_schedule(void) } EXPORT_SYMBOL(io_schedule); -/** - * sys_sched_get_priority_max - return maximum RT priority. - * @policy: scheduling class. - * - * Return: On success, this syscall returns the maximum - * rt_priority that can be used by a given scheduling class. - * On failure, a negative error code is returned. - */ -SYSCALL_DEFINE1(sched_get_priority_max, int, policy) -{ - int ret = -EINVAL; - - switch (policy) { - case SCHED_FIFO: - case SCHED_RR: - ret = MAX_RT_PRIO-1; - break; - case SCHED_DEADLINE: - case SCHED_NORMAL: - case SCHED_BATCH: - case SCHED_IDLE: - ret = 0; - break; - } - return ret; -} - -/** - * sys_sched_get_priority_min - return minimum RT priority. - * @policy: scheduling class. - * - * Return: On success, this syscall returns the minimum - * rt_priority that can be used by a given scheduling class. - * On failure, a negative error code is returned. - */ -SYSCALL_DEFINE1(sched_get_priority_min, int, policy) -{ - int ret = -EINVAL; - - switch (policy) { - case SCHED_FIFO: - case SCHED_RR: - ret = 1; - break; - case SCHED_DEADLINE: - case SCHED_NORMAL: - case SCHED_BATCH: - case SCHED_IDLE: - ret = 0; - } - return ret; -} - -static int sched_rr_get_interval(pid_t pid, struct timespec64 *t) -{ - struct task_struct *p; - unsigned int time_slice; - struct rq_flags rf; - struct rq *rq; - int retval; - - if (pid < 0) - return -EINVAL; - - retval = -ESRCH; - rcu_read_lock(); - p = find_process_by_pid(pid); - if (!p) - goto out_unlock; - - retval = security_task_getscheduler(p); - if (retval) - goto out_unlock; - - rq = task_rq_lock(p, &rf); - time_slice = 0; - if (p->sched_class->get_rr_interval) - time_slice = p->sched_class->get_rr_interval(rq, p); - task_rq_unlock(rq, p, &rf); - - rcu_read_unlock(); - jiffies_to_timespec64(time_slice, t); - return 0; - -out_unlock: - rcu_read_unlock(); - return retval; -} - -/** - * sys_sched_rr_get_interval - return the default timeslice of a process. - * @pid: pid of the process. - * @interval: userspace pointer to the timeslice value. - * - * this syscall writes the default timeslice value of a given process - * into the user-space timespec buffer. A value of '0' means infinity. - * - * Return: On success, 0 and the timeslice is in @interval. Otherwise, - * an error code. - */ -SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, - struct __kernel_timespec __user *, interval) -{ - struct timespec64 t; - int retval = sched_rr_get_interval(pid, &t); - - if (retval == 0) - retval = put_timespec64(&t, interval); - - return retval; -} - -#ifdef CONFIG_COMPAT_32BIT_TIME -SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid, - struct old_timespec32 __user *, interval) -{ - struct timespec64 t; - int retval = sched_rr_get_interval(pid, &t); - - if (retval == 0) - retval = put_old_timespec32(&t, interval); - return retval; -} -#endif - void sched_show_task(struct task_struct *p) { unsigned long free = 0; @@ -9286,6 +7546,7 @@ void sched_show_task(struct task_struct *p) print_worker_info(KERN_INFO, p); print_stop_info(KERN_INFO, p); + print_scx_info(KERN_INFO, p); show_stack(p, NULL, KERN_INFO); put_task_stack(p); } @@ -9790,6 +8051,8 @@ int sched_cpu_activate(unsigned int cpu) cpuset_cpu_active(); } + scx_rq_activate(rq); + /* * Put the rq online, if not already. This happens: * @@ -9850,6 +8113,8 @@ int sched_cpu_deactivate(unsigned int cpu) } rq_unlock_irqrestore(rq, &rf); + scx_rq_deactivate(rq); + /* * When going down, decrement the number of cores with SMT present. */ @@ -10048,11 +8313,15 @@ void __init sched_init(void) int i; /* Make sure the linker didn't screw up */ - BUG_ON(&idle_sched_class != &fair_sched_class + 1 || - &fair_sched_class != &rt_sched_class + 1 || - &rt_sched_class != &dl_sched_class + 1); #ifdef CONFIG_SMP - BUG_ON(&dl_sched_class != &stop_sched_class + 1); + BUG_ON(!sched_class_above(&stop_sched_class, &dl_sched_class)); +#endif + BUG_ON(!sched_class_above(&dl_sched_class, &rt_sched_class)); + BUG_ON(!sched_class_above(&rt_sched_class, &fair_sched_class)); + BUG_ON(!sched_class_above(&fair_sched_class, &idle_sched_class)); +#ifdef CONFIG_SCHED_CLASS_EXT + BUG_ON(!sched_class_above(&fair_sched_class, &ext_sched_class)); + BUG_ON(!sched_class_above(&ext_sched_class, &idle_sched_class)); #endif wait_bit_init(); @@ -10076,6 +8345,9 @@ void __init sched_init(void) root_task_group.shares = ROOT_TASK_GROUP_LOAD; init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL); #endif /* CONFIG_FAIR_GROUP_SCHED */ +#ifdef CONFIG_EXT_GROUP_SCHED + scx_tg_init(&root_task_group); +#endif /* CONFIG_EXT_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED root_task_group.rt_se = (struct sched_rt_entity **)ptr; ptr += nr_cpu_ids * sizeof(void **); @@ -10237,6 +8509,7 @@ void __init sched_init(void) balance_push_set(smp_processor_id(), false); #endif init_sched_fair_class(); + init_sched_ext_class(); psi_init(); @@ -10622,6 +8895,7 @@ struct task_group *sched_create_group(struct task_group *parent) tg_init_tag(tg, parent); #endif + scx_tg_init(tg); alloc_uclamp_sched_group(tg, parent); return tg; @@ -10732,22 +9006,23 @@ static void sched_change_group(struct task_struct *tsk, struct task_group *group * now. This function just updates tsk->se.cfs_rq and tsk->se.parent to reflect * its new group. */ -void sched_move_task(struct task_struct *tsk) +void sched_move_task(struct task_struct *tsk, bool for_autogroup) { int queued, running, queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; struct task_group *group; - struct rq_flags rf; struct rq *rq; - rq = task_rq_lock(tsk, &rf); + CLASS(task_rq_lock, rq_guard)(tsk); + rq = rq_guard.rq; + /* * Esp. with SCHED_AUTOGROUP enabled it is possible to get superfluous * group changes. */ group = sched_get_task_group(tsk); if (group == tsk->sched_task_group) - goto unlock; + return; update_rq_clock(rq); @@ -10760,6 +9035,8 @@ void sched_move_task(struct task_struct *tsk) put_prev_task(rq, tsk); sched_change_group(tsk, group); + if (!for_autogroup) + scx_cgroup_move_task(tsk); if (queued) enqueue_task(rq, tsk, queue_flags); @@ -10772,14 +9049,6 @@ void sched_move_task(struct task_struct *tsk) */ resched_curr(rq); } - -unlock: - task_rq_unlock(rq, tsk, &rf); -} - -static inline struct task_group *css_tg(struct cgroup_subsys_state *css) -{ - return css ? container_of(css, struct task_group, css) : NULL; } static struct cgroup_subsys_state * @@ -10805,17 +9074,20 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) { struct task_group *tg = css_tg(css); struct task_group *parent = css_tg(css->parent); + int ret; + + ret = scx_tg_online(tg); + if (ret) + return ret; if (parent) sched_online_group(tg, parent); #ifdef CONFIG_UCLAMP_TASK_GROUP /* Propagate the effective uclamp value for the new group */ - mutex_lock(&uclamp_mutex); - rcu_read_lock(); + guard(mutex)(&uclamp_mutex); + guard(rcu)(); cpu_util_update_eff(css); - rcu_read_unlock(); - mutex_unlock(&uclamp_mutex); #endif return 0; @@ -10827,6 +9099,7 @@ static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css) offline_auto_affinity(tg); offline_soft_domain(tg); + scx_tg_offline(tg); } static void cpu_cgroup_css_released(struct cgroup_subsys_state *css) @@ -10846,9 +9119,9 @@ static void cpu_cgroup_css_free(struct cgroup_subsys_state *css) sched_unregister_group(tg); } -#ifdef CONFIG_RT_GROUP_SCHED static int cpu_cgroup_can_attach(struct cgroup_taskset *tset) { +#ifdef CONFIG_RT_GROUP_SCHED struct task_struct *task; struct cgroup_subsys_state *css; @@ -10856,9 +9129,9 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset) if (!sched_rt_can_attach(css_tg(css), task)) return -EINVAL; } - return 0; -} #endif + return scx_cgroup_can_attach(tset); +} static void cpu_cgroup_attach(struct cgroup_taskset *tset) { @@ -10866,7 +9139,14 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset) struct cgroup_subsys_state *css; cgroup_taskset_for_each(task, css, tset) - sched_move_task(task); + sched_move_task(task, false); + + scx_cgroup_finish_attach(); +} + +static void cpu_cgroup_cancel_attach(struct cgroup_taskset *tset) +{ + scx_cgroup_cancel_attach(tset); } #ifdef CONFIG_UCLAMP_TASK_GROUP @@ -10974,8 +9254,8 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf, static_branch_enable(&sched_uclamp_used); - mutex_lock(&uclamp_mutex); - rcu_read_lock(); + guard(mutex)(&uclamp_mutex); + guard(rcu)(); tg = css_tg(of_css(of)); if (tg->uclamp_req[clamp_id].value != req.util) @@ -10990,9 +9270,6 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf, /* Update effective clamps to track the most restrictive value */ cpu_util_update_eff(of_css(of)); - rcu_read_unlock(); - mutex_unlock(&uclamp_mutex); - return nbytes; } @@ -11018,10 +9295,10 @@ static inline void cpu_uclamp_print(struct seq_file *sf, u64 percent; u32 rem; - rcu_read_lock(); - tg = css_tg(seq_css(sf)); - util_clamp = tg->uclamp_req[clamp_id].value; - rcu_read_unlock(); + scoped_guard (rcu) { + tg = css_tg(seq_css(sf)); + util_clamp = tg->uclamp_req[clamp_id].value; + } if (util_clamp == SCHED_CAPACITY_SCALE) { seq_puts(sf, "max\n"); @@ -11046,22 +9323,36 @@ static int cpu_uclamp_max_show(struct seq_file *sf, void *v) } #endif /* CONFIG_UCLAMP_TASK_GROUP */ +#ifdef CONFIG_GROUP_SCHED_WEIGHT +static unsigned long tg_weight(struct task_group *tg) +{ #ifdef CONFIG_FAIR_GROUP_SCHED + return scale_load_down(tg->shares); +#else + return sched_weight_from_cgroup(tg->scx_weight); +#endif +} + static int cpu_shares_write_u64(struct cgroup_subsys_state *css, struct cftype *cftype, u64 shareval) { + int ret; + if (shareval > scale_load_down(ULONG_MAX)) shareval = MAX_SHARES; - return sched_group_set_shares(css_tg(css), scale_load(shareval)); + ret = sched_group_set_shares(css_tg(css), scale_load(shareval)); + if (!ret) + scx_group_set_weight(css_tg(css), + sched_weight_to_cgroup(shareval)); + return ret; } static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { - struct task_group *tg = css_tg(css); - - return (u64) scale_load_down(tg->shares); + return tg_weight(css_tg(css)); } +#endif /* CONFIG_GROUP_SCHED_WEIGHT */ #ifdef CONFIG_CFS_BANDWIDTH static DEFINE_MUTEX(cfs_constraints_mutex); @@ -11351,7 +9642,6 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data) static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota) { - int ret; struct cfs_schedulable_data data = { .tg = tg, .period = period, @@ -11363,11 +9653,8 @@ static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota) do_div(data.quota, NSEC_PER_USEC); } - rcu_read_lock(); - ret = walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data); - rcu_read_unlock(); - - return ret; + guard(rcu)(); + return walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data); } static int cpu_cfs_stat_show(struct seq_file *sf, void *v) @@ -11419,7 +9706,6 @@ static int cpu_cfs_local_stat_show(struct seq_file *sf, void *v) return 0; } #endif /* CONFIG_CFS_BANDWIDTH */ -#endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED static int cpu_rt_runtime_write(struct cgroup_subsys_state *css, @@ -11447,7 +9733,7 @@ static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css, } #endif /* CONFIG_RT_GROUP_SCHED */ -#ifdef CONFIG_FAIR_GROUP_SCHED +#ifdef CONFIG_GROUP_SCHED_WEIGHT static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) { @@ -11457,7 +9743,12 @@ static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css, static int cpu_idle_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, s64 idle) { - return sched_group_set_idle(css_tg(css), idle); + int ret; + + ret = sched_group_set_idle(css_tg(css), idle); + if (!ret) + scx_group_set_idle(css_tg(css), idle); + return ret; } #endif @@ -11849,7 +10140,7 @@ static int soft_domain_cpu_list_seq_show(struct seq_file *sf, void *v) #endif static struct cftype cpu_legacy_files[] = { -#ifdef CONFIG_FAIR_GROUP_SCHED +#ifdef CONFIG_GROUP_SCHED_WEIGHT { .name = "shares", .read_u64 = cpu_shares_read_u64, @@ -12026,38 +10317,35 @@ static int cpu_local_stat_show(struct seq_file *sf, return 0; } -#ifdef CONFIG_FAIR_GROUP_SCHED +#ifdef CONFIG_GROUP_SCHED_WEIGHT + static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { - struct task_group *tg = css_tg(css); - u64 weight = scale_load_down(tg->shares); - - return DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024); + return sched_weight_to_cgroup(tg_weight(css_tg(css))); } static int cpu_weight_write_u64(struct cgroup_subsys_state *css, - struct cftype *cft, u64 weight) + struct cftype *cft, u64 cgrp_weight) { - /* - * cgroup weight knobs should use the common MIN, DFL and MAX - * values which are 1, 100 and 10000 respectively. While it loses - * a bit of range on both ends, it maps pretty well onto the shares - * value used by scheduler and the round-trip conversions preserve - * the original value over the entire range. - */ - if (weight < CGROUP_WEIGHT_MIN || weight > CGROUP_WEIGHT_MAX) + unsigned long weight; + int ret; + + if (cgrp_weight < CGROUP_WEIGHT_MIN || cgrp_weight > CGROUP_WEIGHT_MAX) return -ERANGE; - weight = DIV_ROUND_CLOSEST_ULL(weight * 1024, CGROUP_WEIGHT_DFL); + weight = sched_weight_from_cgroup(cgrp_weight); - return sched_group_set_shares(css_tg(css), scale_load(weight)); + ret = sched_group_set_shares(css_tg(css), scale_load(weight)); + if (!ret) + scx_group_set_weight(css_tg(css), cgrp_weight); + return ret; } static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) { - unsigned long weight = scale_load_down(css_tg(css)->shares); + unsigned long weight = tg_weight(css_tg(css)); int last_delta = INT_MAX; int prio, delta; @@ -12076,7 +10364,7 @@ static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, s64 nice) { unsigned long weight; - int idx; + int idx, ret; if (nice < MIN_NICE || nice > MAX_NICE) return -ERANGE; @@ -12085,9 +10373,13 @@ static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css, idx = array_index_nospec(idx, 40); weight = sched_prio_to_weight[idx]; - return sched_group_set_shares(css_tg(css), scale_load(weight)); + ret = sched_group_set_shares(css_tg(css), scale_load(weight)); + if (!ret) + scx_group_set_weight(css_tg(css), + sched_weight_to_cgroup(weight)); + return ret; } -#endif +#endif /* CONFIG_GROUP_SCHED_WEIGHT */ static void __maybe_unused cpu_period_quota_print(struct seq_file *sf, long period, long quota) @@ -12245,7 +10537,7 @@ static ssize_t cpu_max_write(struct kernfs_open_file *of, #endif static struct cftype cpu_files[] = { -#ifdef CONFIG_FAIR_GROUP_SCHED +#ifdef CONFIG_GROUP_SCHED_WEIGHT { .name = "weight", .flags = CFTYPE_NOT_ON_ROOT, @@ -12312,10 +10604,9 @@ struct cgroup_subsys cpu_cgrp_subsys = { .css_free = cpu_cgroup_css_free, .css_extra_stat_show = cpu_extra_stat_show, .css_local_stat_show = cpu_local_stat_show, -#ifdef CONFIG_RT_GROUP_SCHED .can_attach = cpu_cgroup_can_attach, -#endif .attach = cpu_cgroup_attach, + .cancel_attach = cpu_cgroup_cancel_attach, .legacy_cftypes = cpu_legacy_files, .dfl_cftypes = cpu_files, .early_init = true, @@ -12533,14 +10824,12 @@ int __sched_mm_cid_migrate_from_fetch_cid(struct rq *src_rq, * are not the last task to be migrated from this cpu for this mm, so * there is no need to move src_cid to the destination cpu. */ - rcu_read_lock(); + guard(rcu)(); src_task = rcu_dereference(src_rq->curr); if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) { - rcu_read_unlock(); t->last_mm_cid = -1; return -1; } - rcu_read_unlock(); return src_cid; } @@ -12584,18 +10873,17 @@ int __sched_mm_cid_migrate_from_try_steal_cid(struct rq *src_rq, * the lazy-put flag, this task will be responsible for transitioning * from lazy-put flag set to MM_CID_UNSET. */ - rcu_read_lock(); - src_task = rcu_dereference(src_rq->curr); - if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) { - rcu_read_unlock(); - /* - * We observed an active task for this mm, there is therefore - * no point in moving this cid to the destination cpu. - */ - t->last_mm_cid = -1; - return -1; + scoped_guard (rcu) { + src_task = rcu_dereference(src_rq->curr); + if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) { + /* + * We observed an active task for this mm, there is therefore + * no point in moving this cid to the destination cpu. + */ + t->last_mm_cid = -1; + return -1; + } } - rcu_read_unlock(); /* * The src_cid is unused, so it can be unset. @@ -12668,7 +10956,6 @@ static void sched_mm_cid_remote_clear(struct mm_struct *mm, struct mm_cid *pcpu_ { struct rq *rq = cpu_rq(cpu); struct task_struct *t; - unsigned long flags; int cid, lazy_cid; cid = READ_ONCE(pcpu_cid->cid); @@ -12703,23 +10990,21 @@ static void sched_mm_cid_remote_clear(struct mm_struct *mm, struct mm_cid *pcpu_ * the lazy-put flag, that task will be responsible for transitioning * from lazy-put flag set to MM_CID_UNSET. */ - rcu_read_lock(); - t = rcu_dereference(rq->curr); - if (READ_ONCE(t->mm_cid_active) && t->mm == mm) { - rcu_read_unlock(); - return; + scoped_guard (rcu) { + t = rcu_dereference(rq->curr); + if (READ_ONCE(t->mm_cid_active) && t->mm == mm) + return; } - rcu_read_unlock(); /* * The cid is unused, so it can be unset. * Disable interrupts to keep the window of cid ownership without rq * lock small. */ - local_irq_save(flags); - if (try_cmpxchg(&pcpu_cid->cid, &lazy_cid, MM_CID_UNSET)) - __mm_cid_put(mm, cid); - local_irq_restore(flags); + scoped_guard (irqsave) { + if (try_cmpxchg(&pcpu_cid->cid, &lazy_cid, MM_CID_UNSET)) + __mm_cid_put(mm, cid); + } } static void sched_mm_cid_remote_clear_old(struct mm_struct *mm, int cpu) @@ -12741,14 +11026,13 @@ static void sched_mm_cid_remote_clear_old(struct mm_struct *mm, int cpu) * snapshot associated with this cid if an active task using the mm is * observed on this rq. */ - rcu_read_lock(); - curr = rcu_dereference(rq->curr); - if (READ_ONCE(curr->mm_cid_active) && curr->mm == mm) { - WRITE_ONCE(pcpu_cid->time, rq_clock); - rcu_read_unlock(); - return; + scoped_guard (rcu) { + curr = rcu_dereference(rq->curr); + if (READ_ONCE(curr->mm_cid_active) && curr->mm == mm) { + WRITE_ONCE(pcpu_cid->time, rq_clock); + return; + } } - rcu_read_unlock(); if (rq_clock < pcpu_cid->time + SCHED_MM_CID_PERIOD_NS) return; @@ -12844,7 +11128,6 @@ void task_tick_mm_cid(struct rq *rq, struct task_struct *curr) void sched_mm_cid_exit_signals(struct task_struct *t) { struct mm_struct *mm = t->mm; - struct rq_flags rf; struct rq *rq; if (!mm) @@ -12852,7 +11135,7 @@ void sched_mm_cid_exit_signals(struct task_struct *t) preempt_disable(); rq = this_rq(); - rq_lock_irqsave(rq, &rf); + guard(rq_lock_irqsave)(rq); preempt_enable_no_resched(); /* holding spinlock */ WRITE_ONCE(t->mm_cid_active, 0); /* @@ -12862,13 +11145,11 @@ void sched_mm_cid_exit_signals(struct task_struct *t) smp_mb(); mm_cid_put(mm); t->last_mm_cid = t->mm_cid = -1; - rq_unlock_irqrestore(rq, &rf); } void sched_mm_cid_before_execve(struct task_struct *t) { struct mm_struct *mm = t->mm; - struct rq_flags rf; struct rq *rq; if (!mm) @@ -12876,7 +11157,7 @@ void sched_mm_cid_before_execve(struct task_struct *t) preempt_disable(); rq = this_rq(); - rq_lock_irqsave(rq, &rf); + guard(rq_lock_irqsave)(rq); preempt_enable_no_resched(); /* holding spinlock */ WRITE_ONCE(t->mm_cid_active, 0); /* @@ -12886,13 +11167,11 @@ void sched_mm_cid_before_execve(struct task_struct *t) smp_mb(); mm_cid_put(mm); t->last_mm_cid = t->mm_cid = -1; - rq_unlock_irqrestore(rq, &rf); } void sched_mm_cid_after_execve(struct task_struct *t) { struct mm_struct *mm = t->mm; - struct rq_flags rf; struct rq *rq; if (!mm) @@ -12900,16 +11179,16 @@ void sched_mm_cid_after_execve(struct task_struct *t) preempt_disable(); rq = this_rq(); - rq_lock_irqsave(rq, &rf); - preempt_enable_no_resched(); /* holding spinlock */ - WRITE_ONCE(t->mm_cid_active, 1); - /* - * Store t->mm_cid_active before loading per-mm/cpu cid. - * Matches barrier in sched_mm_cid_remote_clear_old(). - */ - smp_mb(); - t->last_mm_cid = t->mm_cid = mm_cid_get(rq, mm); - rq_unlock_irqrestore(rq, &rf); + scoped_guard (rq_lock_irqsave, rq) { + preempt_enable_no_resched(); /* holding spinlock */ + WRITE_ONCE(t->mm_cid_active, 1); + /* + * Store t->mm_cid_active before loading per-mm/cpu cid. + * Matches barrier in sched_mm_cid_remote_clear_old(). + */ + smp_mb(); + t->last_mm_cid = t->mm_cid = mm_cid_get(rq, mm); + } rseq_set_notify_resume(t); } @@ -12919,3 +11198,38 @@ void sched_mm_cid_fork(struct task_struct *t) t->mm_cid_active = 1; } #endif + +#ifdef CONFIG_SCHED_CLASS_EXT +void sched_deq_and_put_task(struct task_struct *p, int queue_flags, + struct sched_enq_and_set_ctx *ctx) +{ + struct rq *rq = task_rq(p); + + lockdep_assert_rq_held(rq); + + *ctx = (struct sched_enq_and_set_ctx){ + .p = p, + .queue_flags = queue_flags, + .queued = task_on_rq_queued(p), + .running = task_current(rq, p), + }; + + update_rq_clock(rq); + if (ctx->queued) + dequeue_task(rq, p, queue_flags | DEQUEUE_NOCLOCK); + if (ctx->running) + put_prev_task(rq, p); +} + +void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx) +{ + struct rq *rq = task_rq(ctx->p); + + lockdep_assert_rq_held(rq); + + if (ctx->queued) + enqueue_task(rq, ctx->p, ctx->queue_flags | ENQUEUE_NOCLOCK); + if (ctx->running) + set_next_task(rq, ctx->p); +} +#endif /* CONFIG_SCHED_CLASS_EXT */ diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 30750c4463e285f87a5e0dc6912b5250fd3543c4..17b3517029b1c800caf2d11d15cfb31b4ea058e0 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -47,7 +47,7 @@ struct sugov_cpu { u64 last_update; unsigned long util; - unsigned long bw_dl; + unsigned long bw_min; /* The field below is for single-CPU policies only: */ #ifdef CONFIG_NO_HZ_COMMON @@ -145,7 +145,11 @@ unsigned long get_capacity_ref_freq(struct cpufreq_policy *policy) if (arch_scale_freq_invariant()) return policy->cpuinfo.max_freq; - return policy->cur; + /* + * Apply a 25% margin so that we select a higher frequency than + * the current one before the CPU is fully busy: + */ + return policy->cur + (policy->cur >> 2); } /** @@ -177,7 +181,6 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, unsigned int freq; freq = get_capacity_ref_freq(policy); - util = map_util_perf(util); freq = map_util_freq(util, freq, max); if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update) @@ -187,14 +190,32 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, return cpufreq_driver_resolve_freq(policy, freq); } +unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual, + unsigned long min, + unsigned long max) +{ + /* Add dvfs headroom to actual utilization */ + actual = map_util_perf(actual); + /* Actually we don't need to target the max performance */ + if (actual < max) + max = actual; + + /* + * Ensure at least minimum performance while providing more compute + * capacity when possible. + */ + return max(min, max); +} + static void sugov_get_util(struct sugov_cpu *sg_cpu) { - unsigned long util = cpu_util_cfs_boost(sg_cpu->cpu); - struct rq *rq = cpu_rq(sg_cpu->cpu); + unsigned long min, max, util = scx_cpuperf_target(sg_cpu->cpu); - sg_cpu->bw_dl = cpu_bw_dl(rq); - sg_cpu->util = effective_cpu_util(sg_cpu->cpu, util, - FREQUENCY_UTIL, NULL); + if (!scx_switched_all()) + util += cpu_util_cfs_boost(sg_cpu->cpu); + util = effective_cpu_util(sg_cpu->cpu, util, &min, &max); + sg_cpu->bw_min = min; + sg_cpu->util = sugov_effective_cpu_perf(sg_cpu->cpu, util, min, max); } /** @@ -322,16 +343,35 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time, } #ifdef CONFIG_NO_HZ_COMMON -static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) +static bool sugov_hold_freq(struct sugov_cpu *sg_cpu) { - unsigned long idle_calls = tick_nohz_get_idle_calls_cpu(sg_cpu->cpu); - bool ret = idle_calls == sg_cpu->saved_idle_calls; + unsigned long idle_calls; + bool ret; + + /* + * The heuristics in this function is for the fair class. For SCX, the + * performance target comes directly from the BPF scheduler. Let's just + * follow it. + */ + if (scx_switched_all()) + return false; + + /* if capped by uclamp_max, always update to be in compliance */ + if (uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu))) + return false; + + /* + * Maintain the frequency if the CPU has not been idle recently, as + * reduction is likely to be premature. + */ + idle_calls = tick_nohz_get_idle_calls_cpu(sg_cpu->cpu); + ret = idle_calls == sg_cpu->saved_idle_calls; sg_cpu->saved_idle_calls = idle_calls; return ret; } #else -static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; } +static inline bool sugov_hold_freq(struct sugov_cpu *sg_cpu) { return false; } #endif /* CONFIG_NO_HZ_COMMON */ /* @@ -340,7 +380,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; } */ static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu) { - if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl) + if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min) sg_cpu->sg_policy->limits_changed = true; } @@ -377,14 +417,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time, return; next_f = get_next_freq(sg_policy, sg_cpu->util, max_cap); - /* - * Do not reduce the frequency if the CPU has not been idle - * recently, as the reduction is likely to be premature then. - * - * Except when the rq is capped by uclamp_max. - */ - if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) && - sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq && + + if (sugov_hold_freq(sg_cpu) && next_f < sg_policy->next_freq && !sg_policy->need_freq_update) { next_f = sg_policy->next_freq; @@ -431,18 +465,11 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time, if (!sugov_update_single_common(sg_cpu, time, max_cap, flags)) return; - /* - * Do not reduce the target performance level if the CPU has not been - * idle recently, as the reduction is likely to be premature then. - * - * Except when the rq is capped by uclamp_max. - */ - if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) && - sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util) + if (sugov_hold_freq(sg_cpu) && sg_cpu->util < prev_util) sg_cpu->util = prev_util; - cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl), - map_util_perf(sg_cpu->util), max_cap); + cpufreq_driver_adjust_perf(sg_cpu->cpu, sg_cpu->bw_min, + sg_cpu->util, max_cap); sg_cpu->sg_policy->last_freq_update_time = time; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 1122f2a5ff2e33b7d7cc4abba792880de03e3de6..17ae7fbcb4fe1eb200dbc0419a4f9de4f4cc979f 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -389,12 +389,12 @@ static void dl_change_utilization(struct task_struct *p, u64 new_bw) * up, and checks if the task is still in the "ACTIVE non contending" * state or not (in the second case, it updates running_bw). */ -static void task_non_contending(struct task_struct *p) +static void task_non_contending(struct sched_dl_entity *dl_se) { - struct sched_dl_entity *dl_se = &p->dl; struct hrtimer *timer = &dl_se->inactive_timer; struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); + struct task_struct *p = dl_task_of(dl_se); s64 zerolag_time; /* @@ -426,13 +426,14 @@ static void task_non_contending(struct task_struct *p) if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) { if (dl_task(p)) sub_running_bw(dl_se, dl_rq); + if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) { struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); if (READ_ONCE(p->__state) == TASK_DEAD) - sub_rq_bw(&p->dl, &rq->dl); + sub_rq_bw(dl_se, &rq->dl); raw_spin_lock(&dl_b->lock); - __dl_sub(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p))); + __dl_sub(dl_b, dl_se->dl_bw, dl_bw_cpus(task_cpu(p))); raw_spin_unlock(&dl_b->lock); __dl_clear_params(p); } @@ -763,7 +764,7 @@ static inline void deadline_queue_pull_task(struct rq *rq) static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags); static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags); -static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p, int flags); +static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p, int flags); static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se, struct rq *rq) @@ -1175,7 +1176,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) enqueue_task_dl(rq, p, ENQUEUE_REPLENISH); if (dl_task(rq->curr)) - check_preempt_curr_dl(rq, p, 0); + wakeup_preempt_dl(rq, p, 0); else resched_curr(rq); @@ -1299,9 +1300,8 @@ static void update_curr_dl(struct rq *rq) { struct task_struct *curr = rq->curr; struct sched_dl_entity *dl_se = &curr->dl; - u64 delta_exec, scaled_delta_exec; + s64 delta_exec, scaled_delta_exec; int cpu = cpu_of(rq); - u64 now; if (!dl_task(curr) || !on_dl_rq(dl_se)) return; @@ -1314,21 +1314,13 @@ static void update_curr_dl(struct rq *rq) * natural solution, but the full ramifications of this * approach need further study. */ - now = rq_clock_task(rq); - delta_exec = now - curr->se.exec_start; - if (unlikely((s64)delta_exec <= 0)) { + delta_exec = update_curr_common(rq); + if (unlikely(delta_exec <= 0)) { if (unlikely(dl_se->dl_yielded)) goto throttle; return; } - schedstat_set(curr->stats.exec_max, - max(curr->stats.exec_max, delta_exec)); - - trace_sched_stat_runtime(curr, delta_exec, 0); - - update_current_exec_runtime(curr, now, delta_exec); - if (dl_entity_is_special(dl_se)) return; @@ -1634,6 +1626,41 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags) update_stats_enqueue_dl(dl_rq_of_se(dl_se), dl_se, flags); + /* + * Check if a constrained deadline task was activated + * after the deadline but before the next period. + * If that is the case, the task will be throttled and + * the replenishment timer will be set to the next period. + */ + if (!dl_se->dl_throttled && !dl_is_implicit(dl_se)) + dl_check_constrained_dl(dl_se); + + if (flags & (ENQUEUE_RESTORE|ENQUEUE_MIGRATING)) { + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + + add_rq_bw(dl_se, dl_rq); + add_running_bw(dl_se, dl_rq); + } + + /* + * If p is throttled, we do not enqueue it. In fact, if it exhausted + * its budget it needs a replenishment and, since it now is on + * its rq, the bandwidth timer callback (which clearly has not + * run yet) will take care of this. + * However, the active utilization does not depend on the fact + * that the task is on the runqueue or not (but depends on the + * task's state - in GRUB parlance, "inactive" vs "active contending"). + * In other words, even if a task is throttled its utilization must + * be counted in the active utilization; hence, we need to call + * add_running_bw(). + */ + if (dl_se->dl_throttled && !(flags & ENQUEUE_REPLENISH)) { + if (flags & ENQUEUE_WAKEUP) + task_contending(dl_se, flags); + + return; + } + /* * If this is a wakeup or a new instance, the scheduling * parameters of the task might need updating. Otherwise, @@ -1654,9 +1681,28 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags) __enqueue_dl_entity(dl_se); } -static void dequeue_dl_entity(struct sched_dl_entity *dl_se) +static void dequeue_dl_entity(struct sched_dl_entity *dl_se, int flags) { __dequeue_dl_entity(dl_se); + + if (flags & (DEQUEUE_SAVE|DEQUEUE_MIGRATING)) { + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + + sub_running_bw(dl_se, dl_rq); + sub_rq_bw(dl_se, dl_rq); + } + + /* + * This check allows to start the inactive timer (or to immediately + * decrease the active utilization, if needed) in two cases: + * when the task blocks and when it is terminating + * (p->state == TASK_DEAD). We can handle the two cases in the same + * way, because from GRUB's point of view the same thing is happening + * (the task moves from "active contending" to "active non contending" + * or "inactive") + */ + if (flags & DEQUEUE_SLEEP) + task_non_contending(dl_se); } static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) @@ -1705,76 +1751,37 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) return; } - /* - * Check if a constrained deadline task was activated - * after the deadline but before the next period. - * If that is the case, the task will be throttled and - * the replenishment timer will be set to the next period. - */ - if (!p->dl.dl_throttled && !dl_is_implicit(&p->dl)) - dl_check_constrained_dl(&p->dl); - - if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & ENQUEUE_RESTORE) { - add_rq_bw(&p->dl, &rq->dl); - add_running_bw(&p->dl, &rq->dl); - } - - /* - * If p is throttled, we do not enqueue it. In fact, if it exhausted - * its budget it needs a replenishment and, since it now is on - * its rq, the bandwidth timer callback (which clearly has not - * run yet) will take care of this. - * However, the active utilization does not depend on the fact - * that the task is on the runqueue or not (but depends on the - * task's state - in GRUB parlance, "inactive" vs "active contending"). - * In other words, even if a task is throttled its utilization must - * be counted in the active utilization; hence, we need to call - * add_running_bw(). - */ - if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) { - if (flags & ENQUEUE_WAKEUP) - task_contending(&p->dl, flags); - - return; - } - check_schedstat_required(); update_stats_wait_start_dl(dl_rq_of_se(&p->dl), &p->dl); + if (p->on_rq == TASK_ON_RQ_MIGRATING) + flags |= ENQUEUE_MIGRATING; + enqueue_dl_entity(&p->dl, flags); - if (!task_current(rq, p) && p->nr_cpus_allowed > 1) + if (!task_current(rq, p) && !p->dl.dl_throttled && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); } static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) { update_stats_dequeue_dl(&rq->dl, &p->dl, flags); - dequeue_dl_entity(&p->dl); - dequeue_pushable_dl_task(rq, p); + dequeue_dl_entity(&p->dl, flags); + + if (!p->dl.dl_throttled) + dequeue_pushable_dl_task(rq, p); } -static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) +static bool dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) { update_curr_dl(rq); - __dequeue_task_dl(rq, p, flags); - if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & DEQUEUE_SAVE) { - sub_running_bw(&p->dl, &rq->dl); - sub_rq_bw(&p->dl, &rq->dl); - } + if (p->on_rq == TASK_ON_RQ_MIGRATING) + flags |= DEQUEUE_MIGRATING; - /* - * This check allows to start the inactive timer (or to immediately - * decrease the active utilization, if needed) in two cases: - * when the task blocks and when it is terminating - * (p->state == TASK_DEAD). We can handle the two cases in the same - * way, because from GRUB's point of view the same thing is happening - * (the task moves from "active contending" to "active non contending" - * or "inactive") - */ - if (flags & DEQUEUE_SLEEP) - task_non_contending(p); + __dequeue_task_dl(rq, p, flags); + + return true; } /* @@ -1944,7 +1951,7 @@ static int balance_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf) * Only called when both the current and waking task are -deadline * tasks. */ -static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p, +static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p, int flags) { if (dl_entity_preempt(&p->dl, &rq->curr->dl)) { @@ -2024,18 +2031,7 @@ static struct task_struct *pick_task_dl(struct rq *rq) return p; } -static struct task_struct *pick_next_task_dl(struct rq *rq) -{ - struct task_struct *p; - - p = pick_task_dl(rq); - if (p) - set_next_task_dl(rq, p, true); - - return p; -} - -static void put_prev_task_dl(struct rq *rq, struct task_struct *p) +static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct task_struct *next) { struct sched_dl_entity *dl_se = &p->dl; struct dl_rq *dl_rq = &rq->dl; @@ -2592,7 +2588,7 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) * will reset the task parameters. */ if (task_on_rq_queued(p) && p->dl.dl_runtime) - task_non_contending(p); + task_non_contending(&p->dl); /* * In case a task is setscheduled out from SCHED_DEADLINE we need to @@ -2659,7 +2655,7 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) deadline_queue_push_tasks(rq); #endif if (dl_task(rq->curr)) - check_preempt_curr_dl(rq, p, 0); + wakeup_preempt_dl(rq, p, 0); else resched_curr(rq); } else { @@ -2728,15 +2724,14 @@ DEFINE_SCHED_CLASS(dl) = { .dequeue_task = dequeue_task_dl, .yield_task = yield_task_dl, - .check_preempt_curr = check_preempt_curr_dl, + .wakeup_preempt = wakeup_preempt_dl, - .pick_next_task = pick_next_task_dl, + .pick_task = pick_task_dl, .put_prev_task = put_prev_task_dl, .set_next_task = set_next_task_dl, #ifdef CONFIG_SMP .balance = balance_dl, - .pick_task = pick_task_dl, .select_task_rq = select_task_rq_dl, .migrate_task_rq = migrate_task_rq_dl, .set_cpus_allowed = set_cpus_allowed_dl, diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 10a19e51e9b8236a9432e9de0bdbb399466e294a..b084af523ce7ac5c2499cac158bf19628c6ec13f 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -1151,6 +1151,9 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, } else if (fair_policy(p->policy)) { P(se.slice); } +#ifdef CONFIG_SCHED_CLASS_EXT + __PS("ext.enabled", task_on_scx(p)); +#endif #undef PN_SCHEDSTAT #undef P_SCHEDSTAT diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c new file mode 100644 index 0000000000000000000000000000000000000000..77eb18030fe33ddcb7bddc72dfb7d259c9ff49a3 --- /dev/null +++ b/kernel/sched/ext.c @@ -0,0 +1,7242 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst + * + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo + * Copyright (c) 2022 David Vernet + */ +#include +#include +#include +#include +#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_OPS_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_ops_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, + + /* + * CPU cgroup support flags + */ + SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* cpu.weight */ + + 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_HAS_CGROUP_WEIGHT, +}; + +/* 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; +}; + +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 + * + * 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? + * + * 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_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 @tg's weight to @weight. + */ + void (*cgroup_set_weight)(struct cgroup *cgrp, u32 weight); +#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]; +}; + +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), +}; + +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 + * bpf_scx_reenqueue_local() kfunc. If bpf_scx_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 */ +}; + +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_ops_enable_state { + SCX_OPS_ENABLING, + SCX_OPS_ENABLED, + SCX_OPS_DISABLING, + SCX_OPS_DISABLED, +}; + +static const char *scx_ops_enable_state_str[] = { + [SCX_OPS_ENABLING] = "enabling", + [SCX_OPS_ENABLED] = "enabled", + [SCX_OPS_DISABLING] = "disabling", + [SCX_OPS_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) + +/* + * During exit, a task may schedule after losing its PIDs. When disabling the + * BPF scheduler, we need to be able to iterate tasks in every state to + * guarantee system safety. Maintain a dedicated task list which contains every + * task between its fork and eventual free. + */ +static DEFINE_SPINLOCK(scx_tasks_lock); +static LIST_HEAD(scx_tasks); + +/* ops enable/disable */ +static struct kthread_worker *scx_ops_helper; +static DEFINE_MUTEX(scx_ops_enable_mutex); +DEFINE_STATIC_KEY_FALSE(__scx_ops_enabled); +DEFINE_STATIC_PERCPU_RWSEM(scx_fork_rwsem); +static atomic_t scx_ops_enable_state_var = ATOMIC_INIT(SCX_OPS_DISABLED); +static unsigned long scx_in_softlockup; +static atomic_t scx_ops_breather_depth = ATOMIC_INIT(0); +static int scx_ops_bypass_depth; +static bool scx_ops_init_task_enabled; +static bool scx_switching_all; +DEFINE_STATIC_KEY_FALSE(__scx_switched_all); + +static struct sched_ext_ops scx_ops; +static bool scx_warned_zero_slice; + +DEFINE_STATIC_KEY_FALSE(scx_ops_allow_queued_wakeup); +static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_last); +static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_exiting); +static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_migration_disabled); +static DEFINE_STATIC_KEY_FALSE(scx_ops_cpu_preempt); + +static struct static_key_false scx_has_op[SCX_OPI_END] = + { [0 ... SCX_OPI_END-1] = STATIC_KEY_FALSE_INIT }; + +static atomic_t scx_exit_kind = ATOMIC_INIT(SCX_EXIT_DONE); +static struct scx_exit_info *scx_exit_info; + +static atomic_long_t scx_nr_rejected = ATOMIC_LONG_INIT(0); +static atomic_long_t scx_hotplug_seq = ATOMIC_LONG_INIT(0); + +/* + * A monotically increasing sequence number that is incremented every time a + * scheduler is enabled. This can be used by to check if any custom sched_ext + * scheduler has ever been used in the system. + */ +static atomic_long_t scx_enable_seq = ATOMIC_LONG_INIT(0); + +/* + * The maximum amount of time in jiffies that a task may be runnable without + * being scheduled on a CPU. If this timeout is exceeded, it will trigger + * scx_ops_error(). + */ +static unsigned long scx_watchdog_timeout; + +/* + * The last time the delayed work was run. This delayed work relies on + * ksoftirqd being able to run to service timer interrupts, so it's possible + * that this work itself could get wedged. To account for this, we check that + * it's not stalled in the timer tick, and trigger an error if it is. + */ +static unsigned long scx_watchdog_timestamp = INITIAL_JIFFIES; + +static struct delayed_work scx_watchdog_work; + +/* for %SCX_KICK_WAIT */ +static unsigned long __percpu *scx_kick_cpus_pnt_seqs; + +/* + * Direct dispatch marker. + * + * Non-NULL values are used for direct dispatch from enqueue path. A valid + * pointer points to the task currently being enqueued. An ERR_PTR value is used + * to indicate that direct dispatch has already happened. + */ +static DEFINE_PER_CPU(struct task_struct *, direct_dispatch_task); + +/* + * 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. + */ +static struct scx_dispatch_q **global_dsqs; + +static const struct rhashtable_params dsq_hash_params = { + .key_len = sizeof_field(struct scx_dispatch_q, id), + .key_offset = offsetof(struct scx_dispatch_q, id), + .head_offset = offsetof(struct scx_dispatch_q, hash_node), +}; + +static struct rhashtable dsq_hash; +static LLIST_HEAD(dsqs_to_free); + +/* dispatch buf */ +struct scx_dsp_buf_ent { + struct task_struct *task; + unsigned long qseq; + u64 dsq_id; + u64 enq_flags; +}; + +static u32 scx_dsp_max_batch; + +struct scx_dsp_ctx { + struct rq *rq; + u32 cursor; + u32 nr_tasks; + struct scx_dsp_buf_ent buf[]; +}; + +static struct scx_dsp_ctx __percpu *scx_dsp_ctx; + +/* string formatting from BPF */ +struct scx_bstr_buf { + u64 data[MAX_BPRINTF_VARARGS]; + char line[SCX_EXIT_MSG_LEN]; +}; + +static DEFINE_RAW_SPINLOCK(scx_exit_bstr_buf_lock); +static struct scx_bstr_buf scx_exit_bstr_buf; + +/* ops debug dump */ +struct scx_dump_data { + s32 cpu; + bool first; + s32 cursor; + struct seq_buf *s; + const char *prefix; + struct scx_bstr_buf buf; +}; + +static struct scx_dump_data scx_dump_data = { + .cpu = -1, +}; + +/* /sys/kernel/sched_ext interface */ +static struct kset *scx_kset; +static struct kobject *scx_root_kobj; + +#define CREATE_TRACE_POINTS +#include + +static void process_ddsp_deferred_locals(struct rq *rq); +static void scx_bpf_kick_cpu(s32 cpu, u64 flags); +static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind, + s64 exit_code, + const char *fmt, ...); + +#define scx_ops_error_kind(err, fmt, args...) \ + scx_ops_exit_kind((err), 0, fmt, ##args) + +#define scx_ops_exit(code, fmt, args...) \ + scx_ops_exit_kind(SCX_EXIT_UNREG_KERN, (code), fmt, ##args) + +#define scx_ops_error(fmt, args...) \ + scx_ops_error_kind(SCX_EXIT_ERROR, fmt, ##args) + +#define SCX_HAS_OP(op) static_branch_likely(&scx_has_op[SCX_OP_IDX(op)]) + +static long jiffies_delta_msecs(unsigned long at, unsigned long now) +{ + if (time_after(at, now)) + return jiffies_to_msecs(at - now); + else + return -(long)jiffies_to_msecs(now - at); +} + +/* if the highest set bit is N, return a mask with bits [N+1, 31] set */ +static u32 higher_bits(u32 flags) +{ + return ~((1 << fls(flags)) - 1); +} + +/* return the mask with only the highest bit set */ +static u32 highest_bit(u32 flags) +{ + int bit = fls(flags); + return ((u64)1 << bit) >> 1; +} + +static bool u32_before(u32 a, u32 b) +{ + return (s32)(a - b) < 0; +} + +static struct scx_dispatch_q *find_global_dsq(struct task_struct *p) +{ + return global_dsqs[cpu_to_node(task_cpu(p))]; +} + +static struct scx_dispatch_q *find_user_dsq(u64 dsq_id) +{ + return rhashtable_lookup_fast(&dsq_hash, &dsq_id, dsq_hash_params); +} + +/* + * scx_kf_mask enforcement. Some kfuncs can only be called from specific SCX + * ops. When invoking SCX ops, SCX_CALL_OP[_RET]() should be used to indicate + * the allowed kfuncs and those kfuncs should use scx_kf_allowed() to check + * whether it's running from an allowed context. + * + * @mask is constant, always inline to cull the mask calculations. + */ +static __always_inline void scx_kf_allow(u32 mask) +{ + /* nesting is allowed only in increasing scx_kf_mask order */ + WARN_ONCE((mask | higher_bits(mask)) & current->scx.kf_mask, + "invalid nesting current->scx.kf_mask=0x%x mask=0x%x\n", + current->scx.kf_mask, mask); + current->scx.kf_mask |= mask; + barrier(); +} + +static void scx_kf_disallow(u32 mask) +{ + barrier(); + current->scx.kf_mask &= ~mask; +} + +/* + * Track the rq currently locked. + * + * This allows kfuncs to safely operate on rq from any scx ops callback, + * knowing which rq is already locked. + */ +DEFINE_PER_CPU(struct rq *, scx_locked_rq_state); + +static inline void update_locked_rq(struct rq *rq) +{ + /* + * Check whether @rq is actually locked. This can help expose bugs + * or incorrect assumptions about the context in which a kfunc or + * callback is executed. + */ + if (rq) + lockdep_assert_rq_held(rq); + __this_cpu_write(scx_locked_rq_state, rq); +} + +#define SCX_CALL_OP(mask, op, rq, args...) \ +do { \ + if (rq) \ + update_locked_rq(rq); \ + if (mask) { \ + scx_kf_allow(mask); \ + scx_ops.op(args); \ + scx_kf_disallow(mask); \ + } else { \ + scx_ops.op(args); \ + } \ + if (rq) \ + update_locked_rq(NULL); \ +} while (0) + +#define SCX_CALL_OP_RET(mask, op, rq, args...) \ +({ \ + __typeof__(scx_ops.op(args)) __ret; \ + \ + if (rq) \ + update_locked_rq(rq); \ + if (mask) { \ + scx_kf_allow(mask); \ + __ret = scx_ops.op(args); \ + scx_kf_disallow(mask); \ + } else { \ + __ret = scx_ops.op(args); \ + } \ + if (rq) \ + update_locked_rq(NULL); \ + __ret; \ +}) + +/* + * Some kfuncs are allowed only on the tasks that are subjects of the + * in-progress scx_ops operation for, e.g., locking guarantees. To enforce such + * restrictions, the following SCX_CALL_OP_*() variants should be used when + * invoking scx_ops operations that take task arguments. These can only be used + * for non-nesting operations due to the way the tasks are tracked. + * + * kfuncs which can only operate on such tasks can in turn use + * scx_kf_allowed_on_arg_tasks() to test whether the invocation is allowed on + * the specific task. + */ +#define SCX_CALL_OP_TASK(mask, op, rq, task, args...) \ +do { \ + BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \ + current->scx.kf_tasks[0] = task; \ + SCX_CALL_OP(mask, op, rq, task, ##args); \ + current->scx.kf_tasks[0] = NULL; \ +} while (0) + +#define SCX_CALL_OP_TASK_RET(mask, op, rq, task, args...) \ +({ \ + __typeof__(scx_ops.op(task, ##args)) __ret; \ + BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \ + current->scx.kf_tasks[0] = task; \ + __ret = SCX_CALL_OP_RET(mask, op, rq, task, ##args); \ + current->scx.kf_tasks[0] = NULL; \ + __ret; \ +}) + +#define SCX_CALL_OP_2TASKS_RET(mask, op, rq, task0, task1, args...) \ +({ \ + __typeof__(scx_ops.op(task0, task1, ##args)) __ret; \ + BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \ + current->scx.kf_tasks[0] = task0; \ + current->scx.kf_tasks[1] = task1; \ + __ret = SCX_CALL_OP_RET(mask, op, rq, task0, task1, ##args); \ + current->scx.kf_tasks[0] = NULL; \ + current->scx.kf_tasks[1] = NULL; \ + __ret; \ +}) + +/* @mask is constant, always inline to cull unnecessary branches */ +static __always_inline bool scx_kf_allowed(u32 mask) +{ + if (unlikely(!(current->scx.kf_mask & mask))) { + scx_ops_error("kfunc with mask 0x%x called from an operation only allowing 0x%x", + mask, current->scx.kf_mask); + return false; + } + + /* + * Enforce nesting boundaries. e.g. A kfunc which can be called from + * DISPATCH must not be called if we're running DEQUEUE which is nested + * inside ops.dispatch(). We don't need to check boundaries for any + * blocking kfuncs as the verifier ensures they're only called from + * sleepable progs. + */ + if (unlikely(highest_bit(mask) == SCX_KF_CPU_RELEASE && + (current->scx.kf_mask & higher_bits(SCX_KF_CPU_RELEASE)))) { + scx_ops_error("cpu_release kfunc called from a nested operation"); + return false; + } + + if (unlikely(highest_bit(mask) == SCX_KF_DISPATCH && + (current->scx.kf_mask & higher_bits(SCX_KF_DISPATCH)))) { + scx_ops_error("dispatch kfunc called from a nested operation"); + return false; + } + + return true; +} + +/* see SCX_CALL_OP_TASK() */ +static __always_inline bool scx_kf_allowed_on_arg_tasks(u32 mask, + struct task_struct *p) +{ + if (!scx_kf_allowed(mask)) + return false; + + if (unlikely((p != current->scx.kf_tasks[0] && + p != current->scx.kf_tasks[1]))) { + scx_ops_error("called on a task not being operated on"); + return false; + } + + return true; +} + +/** + * nldsq_next_task - Iterate to the next task in a non-local DSQ + * @dsq: user dsq being iterated + * @cur: current position, %NULL to start iteration + * @rev: walk backwards + * + * Returns %NULL when iteration is finished. + */ +static struct task_struct *nldsq_next_task(struct scx_dispatch_q *dsq, + struct task_struct *cur, bool rev) +{ + struct list_head *list_node; + struct scx_dsq_list_node *dsq_lnode; + + lockdep_assert_held(&dsq->lock); + + if (cur) + list_node = &cur->scx.dsq_list.node; + else + list_node = &dsq->list; + + /* find the next task, need to skip BPF iteration cursors */ + do { + if (rev) + list_node = list_node->prev; + else + list_node = list_node->next; + + if (list_node == &dsq->list) + return NULL; + + dsq_lnode = container_of(list_node, struct scx_dsq_list_node, + node); + } while (dsq_lnode->flags & SCX_DSQ_LNODE_ITER_CURSOR); + + return container_of(dsq_lnode, struct task_struct, scx.dsq_list); +} + +#define nldsq_for_each_task(p, dsq) \ + for ((p) = nldsq_next_task((dsq), NULL, false); (p); \ + (p) = nldsq_next_task((dsq), (p), false)) + + +/* + * BPF DSQ iterator. Tasks in a non-local DSQ can be iterated in [reverse] + * dispatch order. BPF-visible iterator is opaque and larger to allow future + * changes without breaking backward compatibility. Can be used with + * bpf_for_each(). See bpf_iter_scx_dsq_*(). + */ +enum scx_dsq_iter_flags { + /* iterate in the reverse dispatch order */ + SCX_DSQ_ITER_REV = 1U << 16, + + __SCX_DSQ_ITER_HAS_SLICE = 1U << 30, + __SCX_DSQ_ITER_HAS_VTIME = 1U << 31, + + __SCX_DSQ_ITER_USER_FLAGS = SCX_DSQ_ITER_REV, + __SCX_DSQ_ITER_ALL_FLAGS = __SCX_DSQ_ITER_USER_FLAGS | + __SCX_DSQ_ITER_HAS_SLICE | + __SCX_DSQ_ITER_HAS_VTIME, +}; + +struct bpf_iter_scx_dsq_kern { + struct scx_dsq_list_node cursor; + struct scx_dispatch_q *dsq; + u64 slice; + u64 vtime; +} __attribute__((aligned(8))); + +struct bpf_iter_scx_dsq { + u64 __opaque[6]; +} __attribute__((aligned(8))); + + +/* + * SCX task iterator. + */ +struct scx_task_iter { + struct sched_ext_entity cursor; + struct task_struct *locked; + struct rq *rq; + struct rq_flags rf; + u32 cnt; +}; + +/** + * scx_task_iter_start - Lock scx_tasks_lock and start a task iteration + * @iter: iterator to init + * + * Initialize @iter and return with scx_tasks_lock held. Once initialized, @iter + * must eventually be stopped with scx_task_iter_stop(). + * + * scx_tasks_lock and the rq lock may be released using scx_task_iter_unlock() + * between this and the first next() call or between any two next() calls. If + * the locks are released between two next() calls, the caller is responsible + * for ensuring that the task being iterated remains accessible either through + * RCU read lock or obtaining a reference count. + * + * All tasks which existed when the iteration started are guaranteed to be + * visited as long as they still exist. + */ +static void scx_task_iter_start(struct scx_task_iter *iter) +{ + BUILD_BUG_ON(__SCX_DSQ_ITER_ALL_FLAGS & + ((1U << __SCX_DSQ_LNODE_PRIV_SHIFT) - 1)); + + spin_lock_irq(&scx_tasks_lock); + + iter->cursor = (struct sched_ext_entity){ .flags = SCX_TASK_CURSOR }; + list_add(&iter->cursor.tasks_node, &scx_tasks); + iter->locked = NULL; + iter->cnt = 0; +} + +static void __scx_task_iter_rq_unlock(struct scx_task_iter *iter) +{ + if (iter->locked) { + task_rq_unlock(iter->rq, iter->locked, &iter->rf); + iter->locked = NULL; + } +} + +/** + * scx_task_iter_unlock - Unlock rq and scx_tasks_lock held by a task iterator + * @iter: iterator to unlock + * + * If @iter is in the middle of a locked iteration, it may be locking the rq of + * the task currently being visited in addition to scx_tasks_lock. Unlock both. + * This function can be safely called anytime during an iteration. + */ +static void scx_task_iter_unlock(struct scx_task_iter *iter) +{ + __scx_task_iter_rq_unlock(iter); + spin_unlock_irq(&scx_tasks_lock); +} + +/** + * scx_task_iter_relock - Lock scx_tasks_lock released by scx_task_iter_unlock() + * @iter: iterator to re-lock + * + * Re-lock scx_tasks_lock unlocked by scx_task_iter_unlock(). Note that it + * doesn't re-lock the rq lock. Must be called before other iterator operations. + */ +static void scx_task_iter_relock(struct scx_task_iter *iter) +{ + spin_lock_irq(&scx_tasks_lock); +} + +/** + * scx_task_iter_stop - Stop a task iteration and unlock scx_tasks_lock + * @iter: iterator to exit + * + * Exit a previously initialized @iter. Must be called with scx_tasks_lock held + * which is released on return. If the iterator holds a task's rq lock, that rq + * lock is also released. See scx_task_iter_start() for details. + */ +static void scx_task_iter_stop(struct scx_task_iter *iter) +{ + list_del_init(&iter->cursor.tasks_node); + scx_task_iter_unlock(iter); +} + +/** + * scx_task_iter_next - Next task + * @iter: iterator to walk + * + * Visit the next task. See scx_task_iter_start() for details. Locks are dropped + * and re-acquired every %SCX_OPS_TASK_ITER_BATCH iterations to avoid causing + * stalls by holding scx_tasks_lock for too long. + */ +static struct task_struct *scx_task_iter_next(struct scx_task_iter *iter) +{ + struct list_head *cursor = &iter->cursor.tasks_node; + struct sched_ext_entity *pos; + + if (!(++iter->cnt % SCX_OPS_TASK_ITER_BATCH)) { + scx_task_iter_unlock(iter); + cond_resched(); + scx_task_iter_relock(iter); + } + + list_for_each_entry(pos, cursor, tasks_node) { + if (&pos->tasks_node == &scx_tasks) + return NULL; + if (!(pos->flags & SCX_TASK_CURSOR)) { + list_move(cursor, &pos->tasks_node); + return container_of(pos, struct task_struct, scx); + } + } + + /* can't happen, should always terminate at scx_tasks above */ + BUG(); +} + +/** + * scx_task_iter_next_locked - Next non-idle task with its rq locked + * @iter: iterator to walk + * + * Visit the non-idle task with its rq lock held. Allows callers to specify + * whether they would like to filter out dead tasks. See scx_task_iter_start() + * for details. + */ +static struct task_struct *scx_task_iter_next_locked(struct scx_task_iter *iter) +{ + struct task_struct *p; + + __scx_task_iter_rq_unlock(iter); + + while ((p = scx_task_iter_next(iter))) { + /* + * scx_task_iter is used to prepare and move tasks into SCX + * while loading the BPF scheduler and vice-versa while + * unloading. The init_tasks ("swappers") should be excluded + * from the iteration because: + * + * - It's unsafe to use __setschduler_prio() on an init_task to + * determine the sched_class to use as it won't preserve its + * idle_sched_class. + * + * - ops.init/exit_task() can easily be confused if called with + * init_tasks as they, e.g., share PID 0. + * + * As init_tasks are never scheduled through SCX, they can be + * skipped safely. Note that is_idle_task() which tests %PF_IDLE + * doesn't work here: + * + * - %PF_IDLE may not be set for an init_task whose CPU hasn't + * yet been onlined. + * + * - %PF_IDLE can be set on tasks that are not init_tasks. See + * play_idle_precise() used by CONFIG_IDLE_INJECT. + * + * Test for idle_sched_class as only init_tasks are on it. + */ + if (p->sched_class != &idle_sched_class) + break; + } + if (!p) + return NULL; + + iter->rq = task_rq_lock(p, &iter->rf); + iter->locked = p; + + return p; +} + +static enum scx_ops_enable_state scx_ops_enable_state(void) +{ + return atomic_read(&scx_ops_enable_state_var); +} + +static enum scx_ops_enable_state +scx_ops_set_enable_state(enum scx_ops_enable_state to) +{ + return atomic_xchg(&scx_ops_enable_state_var, to); +} + +static bool scx_ops_tryset_enable_state(enum scx_ops_enable_state to, + enum scx_ops_enable_state from) +{ + int from_v = from; + + return atomic_try_cmpxchg(&scx_ops_enable_state_var, &from_v, to); +} + +static bool scx_rq_bypassing(struct rq *rq) +{ + return unlikely(rq->scx.flags & SCX_RQ_BYPASSING); +} + +/** + * wait_ops_state - Busy-wait the specified ops state to end + * @p: target task + * @opss: state to wait the end of + * + * Busy-wait for @p to transition out of @opss. This can only be used when the + * state part of @opss is %SCX_QUEUEING or %SCX_DISPATCHING. This function also + * has load_acquire semantics to ensure that the caller can see the updates made + * in the enqueueing and dispatching paths. + */ +static void wait_ops_state(struct task_struct *p, unsigned long opss) +{ + do { + cpu_relax(); + } while (atomic_long_read_acquire(&p->scx.ops_state) == opss); +} + +/** + * ops_cpu_valid - Verify a cpu number + * @cpu: cpu number which came from a BPF ops + * @where: extra information reported on error + * + * @cpu is a cpu number which came from the BPF scheduler and can be any value. + * Verify that it is in range and one of the possible cpus. If invalid, trigger + * an ops error. + */ +static bool ops_cpu_valid(s32 cpu, const char *where) +{ + if (likely(cpu >= 0 && cpu < nr_cpu_ids && cpu_possible(cpu))) { + return true; + } else { + scx_ops_error("invalid CPU %d%s%s", cpu, + where ? " " : "", where ?: ""); + return false; + } +} + +/** + * ops_sanitize_err - Sanitize a -errno value + * @ops_name: operation to blame on failure + * @err: -errno value to sanitize + * + * Verify @err is a valid -errno. If not, trigger scx_ops_error() and return + * -%EPROTO. This is necessary because returning a rogue -errno up the chain can + * cause misbehaviors. For an example, a large negative return from + * ops.init_task() triggers an oops when passed up the call chain because the + * value fails IS_ERR() test after being encoded with ERR_PTR() and then is + * handled as a pointer. + */ +static int ops_sanitize_err(const char *ops_name, s32 err) +{ + if (err < 0 && err >= -MAX_ERRNO) + return err; + + scx_ops_error("ops.%s() returned an invalid errno %d", ops_name, err); + return -EPROTO; +} + +static void run_deferred(struct rq *rq) +{ + process_ddsp_deferred_locals(rq); +} + +#ifdef CONFIG_SMP +static void deferred_bal_cb_workfn(struct rq *rq) +{ + run_deferred(rq); +} +#endif + +static void deferred_irq_workfn(struct irq_work *irq_work) +{ + struct rq *rq = container_of(irq_work, struct rq, scx.deferred_irq_work); + + raw_spin_rq_lock(rq); + run_deferred(rq); + raw_spin_rq_unlock(rq); +} + +/** + * schedule_deferred - Schedule execution of deferred actions on an rq + * @rq: target rq + * + * Schedule execution of deferred actions on @rq. Must be called with @rq + * locked. Deferred actions are executed with @rq locked but unpinned, and thus + * can unlock @rq to e.g. migrate tasks to other rqs. + */ +static void schedule_deferred(struct rq *rq) +{ + lockdep_assert_rq_held(rq); + +#ifdef CONFIG_SMP + /* + * If in the middle of waking up a task, task_woken_scx() will be called + * afterwards which will then run the deferred actions, no need to + * schedule anything. + */ + if (rq->scx.flags & SCX_RQ_IN_WAKEUP) + return; + + /* + * If in balance, the balance callbacks will be called before rq lock is + * released. Schedule one. + */ + if (rq->scx.flags & SCX_RQ_IN_BALANCE) { + queue_balance_callback(rq, &rq->scx.deferred_bal_cb, + deferred_bal_cb_workfn); + return; + } +#endif + /* + * No scheduler hooks available. Queue an irq work. They are executed on + * IRQ re-enable which may take a bit longer than the scheduler hooks. + * The above WAKEUP and BALANCE paths should cover most of the cases and + * the time to IRQ re-enable shouldn't be long. + */ + irq_work_queue(&rq->scx.deferred_irq_work); +} + +/** + * touch_core_sched - Update timestamp used for core-sched task ordering + * @rq: rq to read clock from, must be locked + * @p: task to update the timestamp for + * + * Update @p->scx.core_sched_at timestamp. This is used by scx_prio_less() to + * implement global or local-DSQ FIFO ordering for core-sched. Should be called + * when a task becomes runnable and its turn on the CPU ends (e.g. slice + * exhaustion). + */ +static void touch_core_sched(struct rq *rq, struct task_struct *p) +{ + lockdep_assert_rq_held(rq); + +#ifdef CONFIG_SCHED_CORE + /* + * It's okay to update the timestamp spuriously. Use + * sched_core_disabled() which is cheaper than enabled(). + * + * As this is used to determine ordering between tasks of sibling CPUs, + * it may be better to use per-core dispatch sequence instead. + */ + if (!sched_core_disabled()) + p->scx.core_sched_at = sched_clock_cpu(cpu_of(rq)); +#endif +} + +/** + * touch_core_sched_dispatch - Update core-sched timestamp on dispatch + * @rq: rq to read clock from, must be locked + * @p: task being dispatched + * + * If the BPF scheduler implements custom core-sched ordering via + * ops.core_sched_before(), @p->scx.core_sched_at is used to implement FIFO + * ordering within each local DSQ. This function is called from dispatch paths + * and updates @p->scx.core_sched_at if custom core-sched ordering is in effect. + */ +static void touch_core_sched_dispatch(struct rq *rq, struct task_struct *p) +{ + lockdep_assert_rq_held(rq); + +#ifdef CONFIG_SCHED_CORE + if (SCX_HAS_OP(core_sched_before)) + touch_core_sched(rq, p); +#endif +} + +static void update_curr_scx(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + s64 delta_exec; + + delta_exec = update_curr_common(rq); + if (unlikely(delta_exec <= 0)) + return; + + if (curr->scx.slice != SCX_SLICE_INF) { + curr->scx.slice -= min_t(u64, curr->scx.slice, delta_exec); + if (!curr->scx.slice) + touch_core_sched(rq, curr); + } +} + +static bool scx_dsq_priq_less(struct rb_node *node_a, + const struct rb_node *node_b) +{ + const struct task_struct *a = + container_of(node_a, struct task_struct, scx.dsq_priq); + const struct task_struct *b = + container_of(node_b, struct task_struct, scx.dsq_priq); + + return time_before64(a->scx.dsq_vtime, b->scx.dsq_vtime); +} + +static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta) +{ + /* scx_bpf_dsq_nr_queued() reads ->nr without locking, use WRITE_ONCE() */ + WRITE_ONCE(dsq->nr, dsq->nr + delta); +} + +static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, + u64 enq_flags) +{ + bool is_local = dsq->id == SCX_DSQ_LOCAL; + + WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_list.node)); + WARN_ON_ONCE((p->scx.dsq_flags & SCX_TASK_DSQ_ON_PRIQ) || + !RB_EMPTY_NODE(&p->scx.dsq_priq)); + + if (!is_local) { + raw_spin_lock(&dsq->lock); + if (unlikely(dsq->id == SCX_DSQ_INVALID)) { + scx_ops_error("attempting to dispatch to a destroyed dsq"); + /* fall back to the global dsq */ + raw_spin_unlock(&dsq->lock); + dsq = find_global_dsq(p); + raw_spin_lock(&dsq->lock); + } + } + + if (unlikely((dsq->id & SCX_DSQ_FLAG_BUILTIN) && + (enq_flags & SCX_ENQ_DSQ_PRIQ))) { + /* + * SCX_DSQ_LOCAL and SCX_DSQ_GLOBAL DSQs always consume from + * their FIFO queues. To avoid confusion and accidentally + * starving vtime-dispatched tasks by FIFO-dispatched tasks, we + * disallow any internal DSQ from doing vtime ordering of + * tasks. + */ + scx_ops_error("cannot use vtime ordering for built-in DSQs"); + enq_flags &= ~SCX_ENQ_DSQ_PRIQ; + } + + if (enq_flags & SCX_ENQ_DSQ_PRIQ) { + struct rb_node *rbp; + + /* + * A PRIQ DSQ shouldn't be using FIFO enqueueing. As tasks are + * linked to both the rbtree and list on PRIQs, this can only be + * tested easily when adding the first task. + */ + if (unlikely(RB_EMPTY_ROOT(&dsq->priq) && + nldsq_next_task(dsq, NULL, false))) + scx_ops_error("DSQ ID 0x%016llx already had FIFO-enqueued tasks", + dsq->id); + + p->scx.dsq_flags |= SCX_TASK_DSQ_ON_PRIQ; + rb_add(&p->scx.dsq_priq, &dsq->priq, scx_dsq_priq_less); + + /* + * Find the previous task and insert after it on the list so + * that @dsq->list is vtime ordered. + */ + rbp = rb_prev(&p->scx.dsq_priq); + if (rbp) { + struct task_struct *prev = + container_of(rbp, struct task_struct, + scx.dsq_priq); + list_add(&p->scx.dsq_list.node, &prev->scx.dsq_list.node); + } else { + list_add(&p->scx.dsq_list.node, &dsq->list); + } + } else { + /* a FIFO DSQ shouldn't be using PRIQ enqueuing */ + if (unlikely(!RB_EMPTY_ROOT(&dsq->priq))) + scx_ops_error("DSQ ID 0x%016llx already had PRIQ-enqueued tasks", + dsq->id); + + if (enq_flags & (SCX_ENQ_HEAD | SCX_ENQ_PREEMPT)) + list_add(&p->scx.dsq_list.node, &dsq->list); + else + list_add_tail(&p->scx.dsq_list.node, &dsq->list); + } + + /* seq records the order tasks are queued, used by BPF DSQ iterator */ + dsq->seq++; + p->scx.dsq_seq = dsq->seq; + + dsq_mod_nr(dsq, 1); + p->scx.dsq = dsq; + + /* + * scx.ddsp_dsq_id and scx.ddsp_enq_flags are only relevant on the + * direct dispatch path, but we clear them here because the direct + * dispatch verdict may be overridden on the enqueue path during e.g. + * bypass. + */ + p->scx.ddsp_dsq_id = SCX_DSQ_INVALID; + p->scx.ddsp_enq_flags = 0; + + /* + * We're transitioning out of QUEUEING or DISPATCHING. store_release to + * match waiters' load_acquire. + */ + if (enq_flags & SCX_ENQ_CLEAR_OPSS) + atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE); + + if (is_local) { + struct rq *rq = container_of(dsq, struct rq, scx.local_dsq); + bool preempt = false; + + if ((enq_flags & SCX_ENQ_PREEMPT) && p != rq->curr && + rq->curr->sched_class == &ext_sched_class) { + rq->curr->scx.slice = 0; + preempt = true; + } + + if (preempt || sched_class_above(&ext_sched_class, + rq->curr->sched_class)) + resched_curr(rq); + } else { + raw_spin_unlock(&dsq->lock); + } +} + +static void task_unlink_from_dsq(struct task_struct *p, + struct scx_dispatch_q *dsq) +{ + WARN_ON_ONCE(list_empty(&p->scx.dsq_list.node)); + + if (p->scx.dsq_flags & SCX_TASK_DSQ_ON_PRIQ) { + rb_erase(&p->scx.dsq_priq, &dsq->priq); + RB_CLEAR_NODE(&p->scx.dsq_priq); + p->scx.dsq_flags &= ~SCX_TASK_DSQ_ON_PRIQ; + } + + list_del_init(&p->scx.dsq_list.node); + dsq_mod_nr(dsq, -1); +} + +static bool task_linked_on_dsq(struct task_struct *p) +{ + return !list_empty(&p->scx.dsq_list.node); +} + +static void dispatch_dequeue(struct rq *rq, struct task_struct *p) +{ + struct scx_dispatch_q *dsq = p->scx.dsq; + bool is_local = dsq == &rq->scx.local_dsq; + + if (!dsq) { + /* + * If !dsq && on-list, @p is on @rq's ddsp_deferred_locals. + * Unlinking is all that's needed to cancel. + */ + if (unlikely(!list_empty(&p->scx.dsq_list.node))) + list_del_init(&p->scx.dsq_list.node); + + /* + * When dispatching directly from the BPF scheduler to a local + * DSQ, the task isn't associated with any DSQ but + * @p->scx.holding_cpu may be set under the protection of + * %SCX_OPSS_DISPATCHING. + */ + if (p->scx.holding_cpu >= 0) + p->scx.holding_cpu = -1; + + return; + } + + if (!is_local) + raw_spin_lock(&dsq->lock); + + /* + * Now that we hold @dsq->lock, @p->holding_cpu and @p->scx.dsq_* can't + * change underneath us. + */ + if (p->scx.holding_cpu < 0) { + /* @p must still be on @dsq, dequeue */ + task_unlink_from_dsq(p, dsq); + } else { + /* + * We're racing against dispatch_to_local_dsq() which already + * removed @p from @dsq and set @p->scx.holding_cpu. Clear the + * holding_cpu which tells dispatch_to_local_dsq() that it lost + * the race. + */ + WARN_ON_ONCE(task_linked_on_dsq(p)); + p->scx.holding_cpu = -1; + } + p->scx.dsq = NULL; + + if (!is_local) + raw_spin_unlock(&dsq->lock); +} + +static struct scx_dispatch_q *find_dsq_for_dispatch(struct rq *rq, u64 dsq_id, + struct task_struct *p) +{ + struct scx_dispatch_q *dsq; + + if (dsq_id == SCX_DSQ_LOCAL) + return &rq->scx.local_dsq; + + if ((dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON) { + s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK; + + if (!ops_cpu_valid(cpu, "in SCX_DSQ_LOCAL_ON dispatch verdict")) + return find_global_dsq(p); + + return &cpu_rq(cpu)->scx.local_dsq; + } + + if (dsq_id == SCX_DSQ_GLOBAL) + dsq = find_global_dsq(p); + else + dsq = find_user_dsq(dsq_id); + + if (unlikely(!dsq)) { + scx_ops_error("non-existent DSQ 0x%llx for %s[%d]", + dsq_id, p->comm, p->pid); + return find_global_dsq(p); + } + + return dsq; +} + +static void mark_direct_dispatch(struct task_struct *ddsp_task, + struct task_struct *p, u64 dsq_id, + u64 enq_flags) +{ + /* + * Mark that dispatch already happened from ops.select_cpu() or + * ops.enqueue() by spoiling direct_dispatch_task with a non-NULL value + * which can never match a valid task pointer. + */ + __this_cpu_write(direct_dispatch_task, ERR_PTR(-ESRCH)); + + /* @p must match the task on the enqueue path */ + if (unlikely(p != ddsp_task)) { + if (IS_ERR(ddsp_task)) + scx_ops_error("%s[%d] already direct-dispatched", + p->comm, p->pid); + else + scx_ops_error("scheduling for %s[%d] but trying to direct-dispatch %s[%d]", + ddsp_task->comm, ddsp_task->pid, + p->comm, p->pid); + return; + } + + WARN_ON_ONCE(p->scx.ddsp_dsq_id != SCX_DSQ_INVALID); + WARN_ON_ONCE(p->scx.ddsp_enq_flags); + + p->scx.ddsp_dsq_id = dsq_id; + p->scx.ddsp_enq_flags = enq_flags; +} + +static void direct_dispatch(struct task_struct *p, u64 enq_flags) +{ + struct rq *rq = task_rq(p); + struct scx_dispatch_q *dsq = + find_dsq_for_dispatch(rq, p->scx.ddsp_dsq_id, p); + + touch_core_sched_dispatch(rq, p); + + p->scx.ddsp_enq_flags |= enq_flags; + + /* + * We are in the enqueue path with @rq locked and pinned, and thus can't + * double lock a remote rq and enqueue to its local DSQ. For + * DSQ_LOCAL_ON verdicts targeting the local DSQ of a remote CPU, defer + * the enqueue so that it's executed when @rq can be unlocked. + */ + if (dsq->id == SCX_DSQ_LOCAL && dsq != &rq->scx.local_dsq) { + unsigned long opss; + + opss = atomic_long_read(&p->scx.ops_state) & SCX_OPSS_STATE_MASK; + + switch (opss & SCX_OPSS_STATE_MASK) { + case SCX_OPSS_NONE: + break; + case SCX_OPSS_QUEUEING: + /* + * As @p was never passed to the BPF side, _release is + * not strictly necessary. Still do it for consistency. + */ + atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE); + break; + default: + WARN_ONCE(true, "sched_ext: %s[%d] has invalid ops state 0x%lx in direct_dispatch()", + p->comm, p->pid, opss); + atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE); + break; + } + + WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_list.node)); + list_add_tail(&p->scx.dsq_list.node, + &rq->scx.ddsp_deferred_locals); + schedule_deferred(rq); + return; + } + + dispatch_enqueue(dsq, p, p->scx.ddsp_enq_flags | SCX_ENQ_CLEAR_OPSS); +} + +static bool scx_rq_online(struct rq *rq) +{ + /* + * Test both cpu_active() and %SCX_RQ_ONLINE. %SCX_RQ_ONLINE indicates + * the online state as seen from the BPF scheduler. cpu_active() test + * guarantees that, if this function returns %true, %SCX_RQ_ONLINE will + * stay set until the current scheduling operation is complete even if + * we aren't locking @rq. + */ + return likely((rq->scx.flags & SCX_RQ_ONLINE) && cpu_active(cpu_of(rq))); +} + +static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags, + int sticky_cpu) +{ + struct task_struct **ddsp_taskp; + unsigned long qseq; + + WARN_ON_ONCE(!(p->scx.flags & SCX_TASK_QUEUED)); + + /* rq migration */ + if (sticky_cpu == cpu_of(rq)) + goto local_norefill; + + /* + * If !scx_rq_online(), we already told the BPF scheduler that the CPU + * is offline and are just running the hotplug path. Don't bother the + * BPF scheduler. + */ + if (!scx_rq_online(rq)) + goto local; + + if (scx_rq_bypassing(rq)) + goto global; + + if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID) + goto direct; + + /* see %SCX_OPS_ENQ_EXITING */ + if (!static_branch_unlikely(&scx_ops_enq_exiting) && + unlikely(p->flags & PF_EXITING)) + goto local; + + /* see %SCX_OPS_ENQ_MIGRATION_DISABLED */ + if (!static_branch_unlikely(&scx_ops_enq_migration_disabled) && + is_migration_disabled(p)) + goto local; + + if (!SCX_HAS_OP(enqueue)) + goto global; + + /* DSQ bypass didn't trigger, enqueue on the BPF scheduler */ + qseq = rq->scx.ops_qseq++ << SCX_OPSS_QSEQ_SHIFT; + + WARN_ON_ONCE(atomic_long_read(&p->scx.ops_state) != SCX_OPSS_NONE); + atomic_long_set(&p->scx.ops_state, SCX_OPSS_QUEUEING | qseq); + + ddsp_taskp = this_cpu_ptr(&direct_dispatch_task); + WARN_ON_ONCE(*ddsp_taskp); + *ddsp_taskp = p; + + SCX_CALL_OP_TASK(SCX_KF_ENQUEUE, enqueue, rq, p, enq_flags); + + *ddsp_taskp = NULL; + if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID) + goto direct; + + /* + * If not directly dispatched, QUEUEING isn't clear yet and dispatch or + * dequeue may be waiting. The store_release matches their load_acquire. + */ + atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_QUEUED | qseq); + return; + +direct: + direct_dispatch(p, enq_flags); + return; + +local: + /* + * For task-ordering, slice refill must be treated as implying the end + * of the current slice. Otherwise, the longer @p stays on the CPU, the + * higher priority it becomes from scx_prio_less()'s POV. + */ + touch_core_sched(rq, p); + p->scx.slice = SCX_SLICE_DFL; +local_norefill: + dispatch_enqueue(&rq->scx.local_dsq, p, enq_flags); + return; + +global: + touch_core_sched(rq, p); /* see the comment in local: */ + p->scx.slice = SCX_SLICE_DFL; + dispatch_enqueue(find_global_dsq(p), p, enq_flags); +} + +static bool task_runnable(const struct task_struct *p) +{ + return !list_empty(&p->scx.runnable_node); +} + +static void set_task_runnable(struct rq *rq, struct task_struct *p) +{ + lockdep_assert_rq_held(rq); + + if (p->scx.flags & SCX_TASK_RESET_RUNNABLE_AT) { + p->scx.runnable_at = jiffies; + p->scx.flags &= ~SCX_TASK_RESET_RUNNABLE_AT; + } + + /* + * list_add_tail() must be used. scx_ops_bypass() depends on tasks being + * appended to the runnable_list. + */ + list_add_tail(&p->scx.runnable_node, &rq->scx.runnable_list); +} + +static void clr_task_runnable(struct task_struct *p, bool reset_runnable_at) +{ + list_del_init(&p->scx.runnable_node); + if (reset_runnable_at) + p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT; +} + +static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags) +{ + int sticky_cpu = p->scx.sticky_cpu; + + if (enq_flags & ENQUEUE_WAKEUP) + rq->scx.flags |= SCX_RQ_IN_WAKEUP; + + enq_flags |= rq->scx.extra_enq_flags; + + if (sticky_cpu >= 0) + p->scx.sticky_cpu = -1; + + /* + * Restoring a running task will be immediately followed by + * set_next_task_scx() which expects the task to not be on the BPF + * scheduler as tasks can only start running through local DSQs. Force + * direct-dispatch into the local DSQ by setting the sticky_cpu. + */ + if (unlikely(enq_flags & ENQUEUE_RESTORE) && task_current(rq, p)) + sticky_cpu = cpu_of(rq); + + if (p->scx.flags & SCX_TASK_QUEUED) { + WARN_ON_ONCE(!task_runnable(p)); + goto out; + } + + set_task_runnable(rq, p); + p->scx.flags |= SCX_TASK_QUEUED; + rq->scx.nr_running++; + add_nr_running(rq, 1); + + if (SCX_HAS_OP(runnable) && !task_on_rq_migrating(p)) + SCX_CALL_OP_TASK(SCX_KF_REST, runnable, rq, p, enq_flags); + + if (enq_flags & SCX_ENQ_WAKEUP) + touch_core_sched(rq, p); + + do_enqueue_task(rq, p, enq_flags, sticky_cpu); +out: + rq->scx.flags &= ~SCX_RQ_IN_WAKEUP; +} + +static void ops_dequeue(struct rq *rq, struct task_struct *p, u64 deq_flags) +{ + unsigned long opss; + + /* dequeue is always temporary, don't reset runnable_at */ + clr_task_runnable(p, false); + + /* acquire ensures that we see the preceding updates on QUEUED */ + opss = atomic_long_read_acquire(&p->scx.ops_state); + + switch (opss & SCX_OPSS_STATE_MASK) { + case SCX_OPSS_NONE: + break; + case SCX_OPSS_QUEUEING: + /* + * QUEUEING is started and finished while holding @p's rq lock. + * As we're holding the rq lock now, we shouldn't see QUEUEING. + */ + BUG(); + case SCX_OPSS_QUEUED: + if (SCX_HAS_OP(dequeue)) + SCX_CALL_OP_TASK(SCX_KF_REST, dequeue, rq, p, deq_flags); + + if (atomic_long_try_cmpxchg(&p->scx.ops_state, &opss, + SCX_OPSS_NONE)) + break; + fallthrough; + case SCX_OPSS_DISPATCHING: + /* + * If @p is being dispatched from the BPF scheduler to a DSQ, + * wait for the transfer to complete so that @p doesn't get + * added to its DSQ after dequeueing is complete. + * + * As we're waiting on DISPATCHING with the rq locked, the + * dispatching side shouldn't try to lock the rq while + * DISPATCHING is set. See dispatch_to_local_dsq(). + * + * DISPATCHING shouldn't have qseq set and control can reach + * here with NONE @opss from the above QUEUED case block. + * Explicitly wait on %SCX_OPSS_DISPATCHING instead of @opss. + */ + wait_ops_state(p, SCX_OPSS_DISPATCHING); + BUG_ON(atomic_long_read(&p->scx.ops_state) != SCX_OPSS_NONE); + break; + } +} + +static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags) +{ + if (!(p->scx.flags & SCX_TASK_QUEUED)) { + WARN_ON_ONCE(task_runnable(p)); + return true; + } + + ops_dequeue(rq, p, deq_flags); + + /* + * A currently running task which is going off @rq first gets dequeued + * and then stops running. As we want running <-> stopping transitions + * to be contained within runnable <-> quiescent transitions, trigger + * ->stopping() early here instead of in put_prev_task_scx(). + * + * @p may go through multiple stopping <-> running transitions between + * here and put_prev_task_scx() if task attribute changes occur while + * balance_scx() leaves @rq unlocked. However, they don't contain any + * information meaningful to the BPF scheduler and can be suppressed by + * skipping the callbacks if the task is !QUEUED. + */ + if (SCX_HAS_OP(stopping) && task_current(rq, p)) { + update_curr_scx(rq); + SCX_CALL_OP_TASK(SCX_KF_REST, stopping, rq, p, false); + } + + if (SCX_HAS_OP(quiescent) && !task_on_rq_migrating(p)) + SCX_CALL_OP_TASK(SCX_KF_REST, quiescent, rq, p, deq_flags); + + if (deq_flags & SCX_DEQ_SLEEP) + p->scx.flags |= SCX_TASK_DEQD_FOR_SLEEP; + else + p->scx.flags &= ~SCX_TASK_DEQD_FOR_SLEEP; + + p->scx.flags &= ~SCX_TASK_QUEUED; + rq->scx.nr_running--; + sub_nr_running(rq, 1); + + dispatch_dequeue(rq, p); + return true; +} + +static void yield_task_scx(struct rq *rq) +{ + struct task_struct *p = rq->curr; + + if (SCX_HAS_OP(yield)) + SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, rq, p, NULL); + else + p->scx.slice = 0; +} + +static bool yield_to_task_scx(struct rq *rq, struct task_struct *to) +{ + struct task_struct *from = rq->curr; + + if (SCX_HAS_OP(yield)) + return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, rq, from, to); + else + return false; +} + +static void move_local_task_to_local_dsq(struct task_struct *p, u64 enq_flags, + struct scx_dispatch_q *src_dsq, + struct rq *dst_rq) +{ + struct scx_dispatch_q *dst_dsq = &dst_rq->scx.local_dsq; + + /* @dsq is locked and @p is on @dst_rq */ + lockdep_assert_held(&src_dsq->lock); + lockdep_assert_rq_held(dst_rq); + + WARN_ON_ONCE(p->scx.holding_cpu >= 0); + + if (enq_flags & (SCX_ENQ_HEAD | SCX_ENQ_PREEMPT)) + list_add(&p->scx.dsq_list.node, &dst_dsq->list); + else + list_add_tail(&p->scx.dsq_list.node, &dst_dsq->list); + + dsq_mod_nr(dst_dsq, 1); + p->scx.dsq = dst_dsq; +} + +#ifdef CONFIG_SMP +/** + * move_remote_task_to_local_dsq - Move a task from a foreign rq to a local DSQ + * @p: task to move + * @enq_flags: %SCX_ENQ_* + * @src_rq: rq to move the task from, locked on entry, released on return + * @dst_rq: rq to move the task into, locked on return + * + * Move @p which is currently on @src_rq to @dst_rq's local DSQ. + */ +static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags, + struct rq *src_rq, struct rq *dst_rq) +{ + lockdep_assert_rq_held(src_rq); + + /* the following marks @p MIGRATING which excludes dequeue */ + deactivate_task(src_rq, p, 0); + set_task_cpu(p, cpu_of(dst_rq)); + p->scx.sticky_cpu = cpu_of(dst_rq); + + raw_spin_rq_unlock(src_rq); + raw_spin_rq_lock(dst_rq); + + /* + * We want to pass scx-specific enq_flags but activate_task() will + * truncate the upper 32 bit. As we own @rq, we can pass them through + * @rq->scx.extra_enq_flags instead. + */ + WARN_ON_ONCE(!cpumask_test_cpu(cpu_of(dst_rq), p->cpus_ptr)); + WARN_ON_ONCE(dst_rq->scx.extra_enq_flags); + dst_rq->scx.extra_enq_flags = enq_flags; + activate_task(dst_rq, p, 0); + dst_rq->scx.extra_enq_flags = 0; +} + +/* + * Similar to kernel/sched/core.c::is_cpu_allowed(). However, there are two + * differences: + * + * - is_cpu_allowed() asks "Can this task run on this CPU?" while + * task_can_run_on_remote_rq() asks "Can the BPF scheduler migrate the task to + * this CPU?". + * + * While migration is disabled, is_cpu_allowed() has to say "yes" as the task + * must be allowed to finish on the CPU that it's currently on regardless of + * the CPU state. However, task_can_run_on_remote_rq() must say "no" as the + * BPF scheduler shouldn't attempt to migrate a task which has migration + * disabled. + * + * - The BPF scheduler is bypassed while the rq is offline and we can always say + * no to the BPF scheduler initiated migrations while offline. + * + * The caller must ensure that @p and @rq are on different CPUs. + */ +static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq, + bool trigger_error) +{ + int cpu = cpu_of(rq); + + SCHED_WARN_ON(task_cpu(p) == cpu); + + /* + * If @p has migration disabled, @p->cpus_ptr is updated to contain only + * the pinned CPU in migrate_disable_switch() while @p is being switched + * out. However, put_prev_task_scx() is called before @p->cpus_ptr is + * updated and thus another CPU may see @p on a DSQ inbetween leading to + * @p passing the below task_allowed_on_cpu() check while migration is + * disabled. + * + * Test the migration disabled state first as the race window is narrow + * and the BPF scheduler failing to check migration disabled state can + * easily be masked if task_allowed_on_cpu() is done first. + */ + if (unlikely(is_migration_disabled(p))) { + if (trigger_error) + scx_ops_error("SCX_DSQ_LOCAL[_ON] cannot move migration disabled %s[%d] from CPU %d to %d", + p->comm, p->pid, task_cpu(p), cpu); + return false; + } + + /* + * We don't require the BPF scheduler to avoid dispatching to offline + * CPUs mostly for convenience but also because CPUs can go offline + * between scx_bpf_dsq_insert() calls and here. Trigger error iff the + * picked CPU is outside the allowed mask. + */ + if (!task_allowed_on_cpu(p, cpu)) { + if (trigger_error) + scx_ops_error("SCX_DSQ_LOCAL[_ON] target CPU %d not allowed for %s[%d]", + cpu, p->comm, p->pid); + return false; + } + + if (!scx_rq_online(rq)) + return false; + + return true; +} + +/** + * unlink_dsq_and_lock_src_rq() - Unlink task from its DSQ and lock its task_rq + * @p: target task + * @dsq: locked DSQ @p is currently on + * @src_rq: rq @p is currently on, stable with @dsq locked + * + * Called with @dsq locked but no rq's locked. We want to move @p to a different + * DSQ, including any local DSQ, but are not locking @src_rq. Locking @src_rq is + * required when transferring into a local DSQ. Even when transferring into a + * non-local DSQ, it's better to use the same mechanism to protect against + * dequeues and maintain the invariant that @p->scx.dsq can only change while + * @src_rq is locked, which e.g. scx_dump_task() depends on. + * + * We want to grab @src_rq but that can deadlock if we try while locking @dsq, + * so we want to unlink @p from @dsq, drop its lock and then lock @src_rq. As + * this may race with dequeue, which can't drop the rq lock or fail, do a little + * dancing from our side. + * + * @p->scx.holding_cpu is set to this CPU before @dsq is unlocked. If @p gets + * dequeued after we unlock @dsq but before locking @src_rq, the holding_cpu + * would be cleared to -1. While other cpus may have updated it to different + * values afterwards, as this operation can't be preempted or recurse, the + * holding_cpu can never become this CPU again before we're done. Thus, we can + * tell whether we lost to dequeue by testing whether the holding_cpu still + * points to this CPU. See dispatch_dequeue() for the counterpart. + * + * On return, @dsq is unlocked and @src_rq is locked. Returns %true if @p is + * still valid. %false if lost to dequeue. + */ +static bool unlink_dsq_and_lock_src_rq(struct task_struct *p, + struct scx_dispatch_q *dsq, + struct rq *src_rq) +{ + s32 cpu = raw_smp_processor_id(); + + lockdep_assert_held(&dsq->lock); + + WARN_ON_ONCE(p->scx.holding_cpu >= 0); + task_unlink_from_dsq(p, dsq); + p->scx.holding_cpu = cpu; + + raw_spin_unlock(&dsq->lock); + raw_spin_rq_lock(src_rq); + + /* task_rq couldn't have changed if we're still the holding cpu */ + return likely(p->scx.holding_cpu == cpu) && + !WARN_ON_ONCE(src_rq != task_rq(p)); +} + +static bool consume_remote_task(struct rq *this_rq, struct task_struct *p, + struct scx_dispatch_q *dsq, struct rq *src_rq) +{ + raw_spin_rq_unlock(this_rq); + + if (unlink_dsq_and_lock_src_rq(p, dsq, src_rq)) { + move_remote_task_to_local_dsq(p, 0, src_rq, this_rq); + return true; + } else { + raw_spin_rq_unlock(src_rq); + raw_spin_rq_lock(this_rq); + return false; + } +} +#else /* CONFIG_SMP */ +static inline void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags, struct rq *src_rq, struct rq *dst_rq) { WARN_ON_ONCE(1); } +static inline bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq, bool trigger_error) { return false; } +static inline bool consume_remote_task(struct rq *this_rq, struct task_struct *p, struct scx_dispatch_q *dsq, struct rq *task_rq) { return false; } +#endif /* CONFIG_SMP */ + +/** + * move_task_between_dsqs() - Move a task from one DSQ to another + * @p: target task + * @enq_flags: %SCX_ENQ_* + * @src_dsq: DSQ @p is currently on, must not be a local DSQ + * @dst_dsq: DSQ @p is being moved to, can be any DSQ + * + * Must be called with @p's task_rq and @src_dsq locked. If @dst_dsq is a local + * DSQ and @p is on a different CPU, @p will be migrated and thus its task_rq + * will change. As @p's task_rq is locked, this function doesn't need to use the + * holding_cpu mechanism. + * + * On return, @src_dsq is unlocked and only @p's new task_rq, which is the + * return value, is locked. + */ +static struct rq *move_task_between_dsqs(struct task_struct *p, u64 enq_flags, + struct scx_dispatch_q *src_dsq, + struct scx_dispatch_q *dst_dsq) +{ + struct rq *src_rq = task_rq(p), *dst_rq; + + BUG_ON(src_dsq->id == SCX_DSQ_LOCAL); + lockdep_assert_held(&src_dsq->lock); + lockdep_assert_rq_held(src_rq); + + if (dst_dsq->id == SCX_DSQ_LOCAL) { + dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq); + if (src_rq != dst_rq && + unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) { + dst_dsq = find_global_dsq(p); + dst_rq = src_rq; + } + } else { + /* no need to migrate if destination is a non-local DSQ */ + dst_rq = src_rq; + } + + /* + * Move @p into $dst_dsq. If $dst_dsq is the local DSQ of a different + * CPU, @p will be migrated. + */ + if (dst_dsq->id == SCX_DSQ_LOCAL) { + /* @p is going from a non-local DSQ to a local DSQ */ + if (src_rq == dst_rq) { + task_unlink_from_dsq(p, src_dsq); + move_local_task_to_local_dsq(p, enq_flags, + src_dsq, dst_rq); + raw_spin_unlock(&src_dsq->lock); + } else { + raw_spin_unlock(&src_dsq->lock); + move_remote_task_to_local_dsq(p, enq_flags, + src_rq, dst_rq); + } + } else { + /* + * @p is going from a non-local DSQ to a non-local DSQ. As + * $src_dsq is already locked, do an abbreviated dequeue. + */ + task_unlink_from_dsq(p, src_dsq); + p->scx.dsq = NULL; + raw_spin_unlock(&src_dsq->lock); + + dispatch_enqueue(dst_dsq, p, enq_flags); + } + + return dst_rq; +} + +/* + * A poorly behaving BPF scheduler can live-lock the system by e.g. incessantly + * banging on the same DSQ on a large NUMA system to the point where switching + * to the bypass mode can take a long time. Inject artificial delays while the + * bypass mode is switching to guarantee timely completion. + */ +static void scx_ops_breather(struct rq *rq) +{ + u64 until; + + lockdep_assert_rq_held(rq); + + if (likely(!atomic_read(&scx_ops_breather_depth))) + return; + + raw_spin_rq_unlock(rq); + + until = ktime_get_ns() + NSEC_PER_MSEC; + + do { + int cnt = 1024; + while (atomic_read(&scx_ops_breather_depth) && --cnt) + cpu_relax(); + } while (atomic_read(&scx_ops_breather_depth) && + time_before64(ktime_get_ns(), until)); + + raw_spin_rq_lock(rq); +} + +static bool consume_dispatch_q(struct rq *rq, struct scx_dispatch_q *dsq) +{ + struct task_struct *p; +retry: + /* + * This retry loop can repeatedly race against scx_ops_bypass() + * dequeueing tasks from @dsq trying to put the system into the bypass + * mode. On some multi-socket machines (e.g. 2x Intel 8480c), this can + * live-lock the machine into soft lockups. Give a breather. + */ + scx_ops_breather(rq); + + /* + * The caller can't expect to successfully consume a task if the task's + * addition to @dsq isn't guaranteed to be visible somehow. Test + * @dsq->list without locking and skip if it seems empty. + */ + if (list_empty(&dsq->list)) + return false; + + raw_spin_lock(&dsq->lock); + + nldsq_for_each_task(p, dsq) { + struct rq *task_rq = task_rq(p); + + if (rq == task_rq) { + task_unlink_from_dsq(p, dsq); + move_local_task_to_local_dsq(p, 0, dsq, rq); + raw_spin_unlock(&dsq->lock); + return true; + } + + if (task_can_run_on_remote_rq(p, rq, false)) { + if (likely(consume_remote_task(rq, p, dsq, task_rq))) + return true; + goto retry; + } + } + + raw_spin_unlock(&dsq->lock); + return false; +} + +static bool consume_global_dsq(struct rq *rq) +{ + int node = cpu_to_node(cpu_of(rq)); + + return consume_dispatch_q(rq, global_dsqs[node]); +} + +/** + * dispatch_to_local_dsq - Dispatch a task to a local dsq + * @rq: current rq which is locked + * @dst_dsq: destination DSQ + * @p: task to dispatch + * @enq_flags: %SCX_ENQ_* + * + * We're holding @rq lock and want to dispatch @p to @dst_dsq which is a local + * DSQ. This function performs all the synchronization dancing needed because + * local DSQs are protected with rq locks. + * + * The caller must have exclusive ownership of @p (e.g. through + * %SCX_OPSS_DISPATCHING). + */ +static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, + struct task_struct *p, u64 enq_flags) +{ + struct rq *src_rq = task_rq(p); + struct rq *dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq); +#ifdef CONFIG_SMP + struct rq *locked_rq = rq; +#endif + + /* + * We're synchronized against dequeue through DISPATCHING. As @p can't + * be dequeued, its task_rq and cpus_allowed are stable too. + * + * If dispatching to @rq that @p is already on, no lock dancing needed. + */ + if (rq == src_rq && rq == dst_rq) { + dispatch_enqueue(dst_dsq, p, enq_flags | SCX_ENQ_CLEAR_OPSS); + return; + } + +#ifdef CONFIG_SMP + if (src_rq != dst_rq && + unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) { + dispatch_enqueue(find_global_dsq(p), p, + enq_flags | SCX_ENQ_CLEAR_OPSS); + return; + } + + /* + * @p is on a possibly remote @src_rq which we need to lock to move the + * task. If dequeue is in progress, it'd be locking @src_rq and waiting + * on DISPATCHING, so we can't grab @src_rq lock while holding + * DISPATCHING. + * + * As DISPATCHING guarantees that @p is wholly ours, we can pretend that + * we're moving from a DSQ and use the same mechanism - mark the task + * under transfer with holding_cpu, release DISPATCHING and then follow + * the same protocol. See unlink_dsq_and_lock_src_rq(). + */ + p->scx.holding_cpu = raw_smp_processor_id(); + + /* store_release ensures that dequeue sees the above */ + atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE); + + /* switch to @src_rq lock */ + if (locked_rq != src_rq) { + raw_spin_rq_unlock(locked_rq); + locked_rq = src_rq; + raw_spin_rq_lock(src_rq); + } + + /* task_rq couldn't have changed if we're still the holding cpu */ + if (likely(p->scx.holding_cpu == raw_smp_processor_id()) && + !WARN_ON_ONCE(src_rq != task_rq(p))) { + /* + * If @p is staying on the same rq, there's no need to go + * through the full deactivate/activate cycle. Optimize by + * abbreviating move_remote_task_to_local_dsq(). + */ + if (src_rq == dst_rq) { + p->scx.holding_cpu = -1; + dispatch_enqueue(&dst_rq->scx.local_dsq, p, enq_flags); + } else { + move_remote_task_to_local_dsq(p, enq_flags, + src_rq, dst_rq); + /* task has been moved to dst_rq, which is now locked */ + locked_rq = dst_rq; + } + + /* if the destination CPU is idle, wake it up */ + if (sched_class_above(p->sched_class, dst_rq->curr->sched_class)) + resched_curr(dst_rq); + } + + /* switch back to @rq lock */ + if (locked_rq != rq) { + raw_spin_rq_unlock(locked_rq); + raw_spin_rq_lock(rq); + } +#else /* CONFIG_SMP */ + BUG(); /* control can not reach here on UP */ +#endif /* CONFIG_SMP */ +} + +/** + * finish_dispatch - Asynchronously finish dispatching a task + * @rq: current rq which is locked + * @p: task to finish dispatching + * @qseq_at_dispatch: qseq when @p started getting dispatched + * @dsq_id: destination DSQ ID + * @enq_flags: %SCX_ENQ_* + * + * Dispatching to local DSQs may need to wait for queueing to complete or + * require rq lock dancing. As we don't wanna do either while inside + * ops.dispatch() to avoid locking order inversion, we split dispatching into + * two parts. scx_bpf_dsq_insert() which is called by ops.dispatch() records the + * task and its qseq. Once ops.dispatch() returns, this function is called to + * finish up. + * + * There is no guarantee that @p is still valid for dispatching or even that it + * was valid in the first place. Make sure that the task is still owned by the + * BPF scheduler and claim the ownership before dispatching. + */ +static void finish_dispatch(struct rq *rq, struct task_struct *p, + unsigned long qseq_at_dispatch, + u64 dsq_id, u64 enq_flags) +{ + struct scx_dispatch_q *dsq; + unsigned long opss; + + touch_core_sched_dispatch(rq, p); +retry: + /* + * No need for _acquire here. @p is accessed only after a successful + * try_cmpxchg to DISPATCHING. + */ + opss = atomic_long_read(&p->scx.ops_state); + + switch (opss & SCX_OPSS_STATE_MASK) { + case SCX_OPSS_DISPATCHING: + case SCX_OPSS_NONE: + /* someone else already got to it */ + return; + case SCX_OPSS_QUEUED: + /* + * If qseq doesn't match, @p has gone through at least one + * dispatch/dequeue and re-enqueue cycle between + * scx_bpf_dsq_insert() and here and we have no claim on it. + */ + if ((opss & SCX_OPSS_QSEQ_MASK) != qseq_at_dispatch) + return; + + /* + * While we know @p is accessible, we don't yet have a claim on + * it - the BPF scheduler is allowed to dispatch tasks + * spuriously and there can be a racing dequeue attempt. Let's + * claim @p by atomically transitioning it from QUEUED to + * DISPATCHING. + */ + if (likely(atomic_long_try_cmpxchg(&p->scx.ops_state, &opss, + SCX_OPSS_DISPATCHING))) + break; + goto retry; + case SCX_OPSS_QUEUEING: + /* + * do_enqueue_task() is in the process of transferring the task + * to the BPF scheduler while holding @p's rq lock. As we aren't + * holding any kernel or BPF resource that the enqueue path may + * depend upon, it's safe to wait. + */ + wait_ops_state(p, opss); + goto retry; + } + + BUG_ON(!(p->scx.flags & SCX_TASK_QUEUED)); + + dsq = find_dsq_for_dispatch(this_rq(), dsq_id, p); + + if (dsq->id == SCX_DSQ_LOCAL) + dispatch_to_local_dsq(rq, dsq, p, enq_flags); + else + dispatch_enqueue(dsq, p, enq_flags | SCX_ENQ_CLEAR_OPSS); +} + +static void flush_dispatch_buf(struct rq *rq) +{ + struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx); + u32 u; + + for (u = 0; u < dspc->cursor; u++) { + struct scx_dsp_buf_ent *ent = &dspc->buf[u]; + + finish_dispatch(rq, ent->task, ent->qseq, ent->dsq_id, + ent->enq_flags); + } + + dspc->nr_tasks += dspc->cursor; + dspc->cursor = 0; +} + +static int balance_one(struct rq *rq, struct task_struct *prev) +{ + struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx); + bool prev_on_scx = prev->sched_class == &ext_sched_class; + bool prev_on_rq = prev->scx.flags & SCX_TASK_QUEUED; + int nr_loops = SCX_DSP_MAX_LOOPS; + + lockdep_assert_rq_held(rq); + rq->scx.flags |= SCX_RQ_IN_BALANCE; + rq->scx.flags &= ~(SCX_RQ_BAL_PENDING | SCX_RQ_BAL_KEEP); + + if (static_branch_unlikely(&scx_ops_cpu_preempt) && + unlikely(rq->scx.cpu_released)) { + /* + * If the previous sched_class for the current CPU was not SCX, + * notify the BPF scheduler that it again has control of the + * core. This callback complements ->cpu_release(), which is + * emitted in switch_class(). + */ + if (SCX_HAS_OP(cpu_acquire)) + SCX_CALL_OP(SCX_KF_REST, cpu_acquire, rq, cpu_of(rq), NULL); + rq->scx.cpu_released = false; + } + + if (prev_on_scx) { + update_curr_scx(rq); + + /* + * If @prev is runnable & has slice left, it has priority and + * fetching more just increases latency for the fetched tasks. + * Tell pick_task_scx() to keep running @prev. If the BPF + * scheduler wants to handle this explicitly, it should + * implement ->cpu_release(). + * + * See scx_ops_disable_workfn() for the explanation on the + * bypassing test. + */ + if (prev_on_rq && prev->scx.slice && !scx_rq_bypassing(rq)) { + rq->scx.flags |= SCX_RQ_BAL_KEEP; + goto has_tasks; + } + } + + /* if there already are tasks to run, nothing to do */ + if (rq->scx.local_dsq.nr) + goto has_tasks; + + if (consume_global_dsq(rq)) + goto has_tasks; + + if (!SCX_HAS_OP(dispatch) || scx_rq_bypassing(rq) || !scx_rq_online(rq)) + goto no_tasks; + + dspc->rq = rq; + + /* + * The dispatch loop. Because flush_dispatch_buf() may drop the rq lock, + * the local DSQ might still end up empty after a successful + * ops.dispatch(). If the local DSQ is empty even after ops.dispatch() + * produced some tasks, retry. The BPF scheduler may depend on this + * looping behavior to simplify its implementation. + */ + do { + dspc->nr_tasks = 0; + + SCX_CALL_OP(SCX_KF_DISPATCH, dispatch, rq, cpu_of(rq), + prev_on_scx ? prev : NULL); + + flush_dispatch_buf(rq); + + if (prev_on_rq && prev->scx.slice) { + rq->scx.flags |= SCX_RQ_BAL_KEEP; + goto has_tasks; + } + if (rq->scx.local_dsq.nr) + goto has_tasks; + if (consume_global_dsq(rq)) + goto has_tasks; + + /* + * ops.dispatch() can trap us in this loop by repeatedly + * dispatching ineligible tasks. Break out once in a while to + * allow the watchdog to run. As IRQ can't be enabled in + * balance(), we want to complete this scheduling cycle and then + * start a new one. IOW, we want to call resched_curr() on the + * next, most likely idle, task, not the current one. Use + * scx_bpf_kick_cpu() for deferred kicking. + */ + if (unlikely(!--nr_loops)) { + scx_bpf_kick_cpu(cpu_of(rq), 0); + break; + } + } while (dspc->nr_tasks); + +no_tasks: + /* + * Didn't find another task to run. Keep running @prev unless + * %SCX_OPS_ENQ_LAST is in effect. + */ + if (prev_on_rq && (!static_branch_unlikely(&scx_ops_enq_last) || + scx_rq_bypassing(rq))) { + rq->scx.flags |= SCX_RQ_BAL_KEEP; + goto has_tasks; + } + rq->scx.flags &= ~SCX_RQ_IN_BALANCE; + return false; + +has_tasks: + rq->scx.flags &= ~SCX_RQ_IN_BALANCE; + return true; +} + +static int balance_scx(struct rq *rq, struct task_struct *prev, + struct rq_flags *rf) +{ + int ret; + + rq_unpin_lock(rq, rf); + + ret = balance_one(rq, prev); + +#ifdef CONFIG_SCHED_SMT + /* + * When core-sched is enabled, this ops.balance() call will be followed + * by pick_task_scx() on this CPU and the SMT siblings. Balance the + * siblings too. + */ + if (sched_core_enabled(rq)) { + const struct cpumask *smt_mask = cpu_smt_mask(cpu_of(rq)); + int scpu; + + for_each_cpu_andnot(scpu, smt_mask, cpumask_of(cpu_of(rq))) { + struct rq *srq = cpu_rq(scpu); + struct task_struct *sprev = srq->curr; + + WARN_ON_ONCE(__rq_lockp(rq) != __rq_lockp(srq)); + update_rq_clock(srq); + balance_one(srq, sprev); + } + } +#endif + rq_repin_lock(rq, rf); + + return ret; +} + +static void process_ddsp_deferred_locals(struct rq *rq) +{ + struct task_struct *p; + + lockdep_assert_rq_held(rq); + + /* + * Now that @rq can be unlocked, execute the deferred enqueueing of + * tasks directly dispatched to the local DSQs of other CPUs. See + * direct_dispatch(). Keep popping from the head instead of using + * list_for_each_entry_safe() as dispatch_local_dsq() may unlock @rq + * temporarily. + */ + while ((p = list_first_entry_or_null(&rq->scx.ddsp_deferred_locals, + struct task_struct, scx.dsq_list.node))) { + struct scx_dispatch_q *dsq; + + list_del_init(&p->scx.dsq_list.node); + + dsq = find_dsq_for_dispatch(rq, p->scx.ddsp_dsq_id, p); + if (!WARN_ON_ONCE(dsq->id != SCX_DSQ_LOCAL)) + dispatch_to_local_dsq(rq, dsq, p, p->scx.ddsp_enq_flags); + } +} + +static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first) +{ + if (p->scx.flags & SCX_TASK_QUEUED) { + /* + * Core-sched might decide to execute @p before it is + * dispatched. Call ops_dequeue() to notify the BPF scheduler. + */ + ops_dequeue(rq, p, SCX_DEQ_CORE_SCHED_EXEC); + dispatch_dequeue(rq, p); + } + + p->se.exec_start = rq_clock_task(rq); + + /* see dequeue_task_scx() on why we skip when !QUEUED */ + if (SCX_HAS_OP(running) && (p->scx.flags & SCX_TASK_QUEUED)) + SCX_CALL_OP_TASK(SCX_KF_REST, running, rq, p); + + clr_task_runnable(p, true); + + /* + * @p is getting newly scheduled or got kicked after someone updated its + * slice. Refresh whether tick can be stopped. See scx_can_stop_tick(). + */ + if ((p->scx.slice == SCX_SLICE_INF) != + (bool)(rq->scx.flags & SCX_RQ_CAN_STOP_TICK)) { + if (p->scx.slice == SCX_SLICE_INF) + rq->scx.flags |= SCX_RQ_CAN_STOP_TICK; + else + rq->scx.flags &= ~SCX_RQ_CAN_STOP_TICK; + + sched_update_tick_dependency(rq); + + /* + * For now, let's refresh the load_avgs just when transitioning + * in and out of nohz. In the future, we might want to add a + * mechanism which calls the following periodically on + * tick-stopped CPUs. + */ + update_other_load_avgs(rq); + } +} + +static enum scx_cpu_preempt_reason +preempt_reason_from_class(const struct sched_class *class) +{ +#ifdef CONFIG_SMP + if (class == &stop_sched_class) + return SCX_CPU_PREEMPT_STOP; +#endif + if (class == &dl_sched_class) + return SCX_CPU_PREEMPT_DL; + if (class == &rt_sched_class) + return SCX_CPU_PREEMPT_RT; + return SCX_CPU_PREEMPT_UNKNOWN; +} + +static void switch_class(struct rq *rq, struct task_struct *next) +{ + const struct sched_class *next_class = next->sched_class; + +#ifdef CONFIG_SMP + /* + * Pairs with the smp_load_acquire() issued by a CPU in + * kick_cpus_irq_workfn() who is waiting for this CPU to perform a + * resched. + */ + smp_store_release(&rq->scx.pnt_seq, rq->scx.pnt_seq + 1); +#endif + if (!static_branch_unlikely(&scx_ops_cpu_preempt)) + return; + + /* + * The callback is conceptually meant to convey that the CPU is no + * longer under the control of SCX. Therefore, don't invoke the callback + * if the next class is below SCX (in which case the BPF scheduler has + * actively decided not to schedule any tasks on the CPU). + */ + if (sched_class_above(&ext_sched_class, next_class)) + return; + + /* + * At this point we know that SCX was preempted by a higher priority + * sched_class, so invoke the ->cpu_release() callback if we have not + * done so already. We only send the callback once between SCX being + * preempted, and it regaining control of the CPU. + * + * ->cpu_release() complements ->cpu_acquire(), which is emitted the + * next time that balance_scx() is invoked. + */ + if (!rq->scx.cpu_released) { + if (SCX_HAS_OP(cpu_release)) { + struct scx_cpu_release_args args = { + .reason = preempt_reason_from_class(next_class), + .task = next, + }; + + SCX_CALL_OP(SCX_KF_CPU_RELEASE, cpu_release, rq, cpu_of(rq), &args); + } + rq->scx.cpu_released = true; + } +} + +static void put_prev_task_scx(struct rq *rq, struct task_struct *p, + struct task_struct *next) +{ + update_curr_scx(rq); + + /* see dequeue_task_scx() on why we skip when !QUEUED */ + if (SCX_HAS_OP(stopping) && (p->scx.flags & SCX_TASK_QUEUED)) + SCX_CALL_OP_TASK(SCX_KF_REST, stopping, rq, p, true); + + if (p->scx.flags & SCX_TASK_QUEUED) { + set_task_runnable(rq, p); + + /* + * If @p has slice left and is being put, @p is getting + * preempted by a higher priority scheduler class or core-sched + * forcing a different task. Leave it at the head of the local + * DSQ. + */ + if (p->scx.slice && !scx_rq_bypassing(rq)) { + dispatch_enqueue(&rq->scx.local_dsq, p, SCX_ENQ_HEAD); + goto switch_class; + } + + /* + * If @p is runnable but we're about to enter a lower + * sched_class, %SCX_OPS_ENQ_LAST must be set. Tell + * ops.enqueue() that @p is the only one available for this cpu, + * which should trigger an explicit follow-up scheduling event. + */ + if (sched_class_above(&ext_sched_class, next->sched_class)) { + WARN_ON_ONCE(!static_branch_unlikely(&scx_ops_enq_last)); + do_enqueue_task(rq, p, SCX_ENQ_LAST, -1); + } else { + do_enqueue_task(rq, p, 0, -1); + } + } + +switch_class: + if (next && next->sched_class != &ext_sched_class) + switch_class(rq, next); +} + +static struct task_struct *first_local_task(struct rq *rq) +{ + return list_first_entry_or_null(&rq->scx.local_dsq.list, + struct task_struct, scx.dsq_list.node); +} + +static struct task_struct *pick_task_scx(struct rq *rq) +{ + struct task_struct *prev = rq->curr; + struct task_struct *p; + bool keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP; + bool kick_idle = false; + + /* + * WORKAROUND: + * + * %SCX_RQ_BAL_KEEP should be set iff $prev is on SCX as it must just + * have gone through balance_scx(). Unfortunately, there currently is a + * bug where fair could say yes on balance() but no on pick_task(), + * which then ends up calling pick_task_scx() without preceding + * balance_scx(). + * + * Keep running @prev if possible and avoid stalling from entering idle + * without balancing. + * + * Once fair is fixed, remove the workaround and trigger WARN_ON_ONCE() + * if pick_task_scx() is called without preceding balance_scx(). + */ + if (unlikely(rq->scx.flags & SCX_RQ_BAL_PENDING)) { + if (prev->scx.flags & SCX_TASK_QUEUED) { + keep_prev = true; + } else { + keep_prev = false; + kick_idle = true; + } + } else if (unlikely(keep_prev && + prev->sched_class != &ext_sched_class)) { + /* + * Can happen while enabling as SCX_RQ_BAL_PENDING assertion is + * conditional on scx_enabled() and may have been skipped. + */ + WARN_ON_ONCE(scx_ops_enable_state() == SCX_OPS_ENABLED); + keep_prev = false; + } + + /* + * If balance_scx() is telling us to keep running @prev, replenish slice + * if necessary and keep running @prev. Otherwise, pop the first one + * from the local DSQ. + */ + if (keep_prev) { + p = prev; + if (!p->scx.slice) + p->scx.slice = SCX_SLICE_DFL; + } else { + p = first_local_task(rq); + if (!p) { + if (kick_idle) + scx_bpf_kick_cpu(cpu_of(rq), SCX_KICK_IDLE); + return NULL; + } + + if (unlikely(!p->scx.slice)) { + if (!scx_rq_bypassing(rq) && !scx_warned_zero_slice) { + printk_deferred(KERN_WARNING "sched_ext: %s[%d] has zero slice in %s()\n", + p->comm, p->pid, __func__); + scx_warned_zero_slice = true; + } + p->scx.slice = SCX_SLICE_DFL; + } + } + + return p; +} + +#ifdef CONFIG_SCHED_CORE +/** + * scx_prio_less - Task ordering for core-sched + * @a: task A + * @b: task B + * @in_fi: in forced idle state + * + * Core-sched is implemented as an additional scheduling layer on top of the + * usual sched_class'es and needs to find out the expected task ordering. For + * SCX, core-sched calls this function to interrogate the task ordering. + * + * Unless overridden by ops.core_sched_before(), @p->scx.core_sched_at is used + * to implement the default task ordering. The older the timestamp, the higher + * priority the task - the global FIFO ordering matching the default scheduling + * behavior. + * + * When ops.core_sched_before() is enabled, @p->scx.core_sched_at is used to + * implement FIFO ordering within each local DSQ. See pick_task_scx(). + */ +bool scx_prio_less(const struct task_struct *a, const struct task_struct *b, + bool in_fi) +{ + /* + * The const qualifiers are dropped from task_struct pointers when + * calling ops.core_sched_before(). Accesses are controlled by the + * verifier. + */ + if (SCX_HAS_OP(core_sched_before) && !scx_rq_bypassing(task_rq(a))) + return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, core_sched_before, NULL, + (struct task_struct *)a, + (struct task_struct *)b); + else + return time_after64(a->scx.core_sched_at, b->scx.core_sched_at); +} +#endif /* CONFIG_SCHED_CORE */ + +#ifdef CONFIG_SMP + +static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flags) +{ + /* + * sched_exec() calls with %WF_EXEC when @p is about to exec(2) as it + * can be a good migration opportunity with low cache and memory + * footprint. Returning a CPU different than @prev_cpu triggers + * immediate rq migration. However, for SCX, as the current rq + * association doesn't dictate where the task is going to run, this + * doesn't fit well. If necessary, we can later add a dedicated method + * which can decide to preempt self to force it through the regular + * scheduling path. + */ + if (unlikely(wake_flags & WF_EXEC)) + return prev_cpu; + + if (SCX_HAS_OP(select_cpu) && !scx_rq_bypassing(task_rq(p))) { + s32 cpu; + struct task_struct **ddsp_taskp; + + ddsp_taskp = this_cpu_ptr(&direct_dispatch_task); + WARN_ON_ONCE(*ddsp_taskp); + *ddsp_taskp = p; + + cpu = SCX_CALL_OP_TASK_RET(SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU, + select_cpu, NULL, p, prev_cpu, wake_flags); + *ddsp_taskp = NULL; + if (ops_cpu_valid(cpu, "from ops.select_cpu()")) + return cpu; + else + return prev_cpu; + } else { + bool found; + s32 cpu; + + cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, &found); + if (found) { + p->scx.slice = SCX_SLICE_DFL; + p->scx.ddsp_dsq_id = SCX_DSQ_LOCAL; + } + return cpu; + } +} + +static void task_woken_scx(struct rq *rq, struct task_struct *p) +{ + run_deferred(rq); +} + +static void set_cpus_allowed_scx(struct task_struct *p, + struct affinity_context *ac) +{ + set_cpus_allowed_common(p, ac); + + /* + * The effective cpumask is stored in @p->cpus_ptr which may temporarily + * differ from the configured one in @p->cpus_mask. Always tell the bpf + * scheduler the effective one. + * + * Fine-grained memory write control is enforced by BPF making the const + * designation pointless. Cast it away when calling the operation. + */ + if (SCX_HAS_OP(set_cpumask)) + SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, NULL, + p, (struct cpumask *)p->cpus_ptr); +} + +static void handle_hotplug(struct rq *rq, bool online) +{ + int cpu = cpu_of(rq); + + atomic_long_inc(&scx_hotplug_seq); + + if (scx_enabled()) + scx_idle_update_selcpu_topology(); + + if (online && SCX_HAS_OP(cpu_online)) + SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, NULL, cpu); + else if (!online && SCX_HAS_OP(cpu_offline)) + SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, NULL, cpu); + else + scx_ops_exit(SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG, + "cpu %d going %s, exiting scheduler", cpu, + online ? "online" : "offline"); +} + +void scx_rq_activate(struct rq *rq) +{ + handle_hotplug(rq, true); +} + +void scx_rq_deactivate(struct rq *rq) +{ + handle_hotplug(rq, false); +} + +static void rq_online_scx(struct rq *rq) +{ + rq->scx.flags |= SCX_RQ_ONLINE; +} + +static void rq_offline_scx(struct rq *rq) +{ + rq->scx.flags &= ~SCX_RQ_ONLINE; +} + +#endif /* CONFIG_SMP */ + +static bool check_rq_for_timeouts(struct rq *rq) +{ + struct task_struct *p; + struct rq_flags rf; + bool timed_out = false; + + rq_lock_irqsave(rq, &rf); + list_for_each_entry(p, &rq->scx.runnable_list, scx.runnable_node) { + unsigned long last_runnable = p->scx.runnable_at; + + if (unlikely(time_after(jiffies, + last_runnable + scx_watchdog_timeout))) { + u32 dur_ms = jiffies_to_msecs(jiffies - last_runnable); + + scx_ops_error_kind(SCX_EXIT_ERROR_STALL, + "%s[%d] failed to run for %u.%03us", + p->comm, p->pid, + dur_ms / 1000, dur_ms % 1000); + timed_out = true; + break; + } + } + rq_unlock_irqrestore(rq, &rf); + + return timed_out; +} + +static void scx_watchdog_workfn(struct work_struct *work) +{ + int cpu; + + WRITE_ONCE(scx_watchdog_timestamp, jiffies); + + for_each_online_cpu(cpu) { + if (unlikely(check_rq_for_timeouts(cpu_rq(cpu)))) + break; + + cond_resched(); + } + queue_delayed_work(system_unbound_wq, to_delayed_work(work), + scx_watchdog_timeout / 2); +} + +void scx_tick(struct rq *rq) +{ + unsigned long last_check; + + if (!scx_enabled()) + return; + + last_check = READ_ONCE(scx_watchdog_timestamp); + if (unlikely(time_after(jiffies, + last_check + READ_ONCE(scx_watchdog_timeout)))) { + u32 dur_ms = jiffies_to_msecs(jiffies - last_check); + + scx_ops_error_kind(SCX_EXIT_ERROR_STALL, + "watchdog failed to check in for %u.%03us", + dur_ms / 1000, dur_ms % 1000); + } + + update_other_load_avgs(rq); +} + +static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued) +{ + update_curr_scx(rq); + + /* + * While disabling, always resched and refresh core-sched timestamp as + * we can't trust the slice management or ops.core_sched_before(). + */ + if (scx_rq_bypassing(rq)) { + curr->scx.slice = 0; + touch_core_sched(rq, curr); + } else if (SCX_HAS_OP(tick)) { + SCX_CALL_OP_TASK(SCX_KF_REST, tick, rq, curr); + } + + if (!curr->scx.slice) + resched_curr(rq); +} + +#ifdef CONFIG_EXT_GROUP_SCHED +static struct cgroup *tg_cgrp(struct task_group *tg) +{ + /* + * If CGROUP_SCHED is disabled, @tg is NULL. If @tg is an autogroup, + * @tg->css.cgroup is NULL. In both cases, @tg can be treated as the + * root cgroup. + */ + if (tg && tg->css.cgroup) + return tg->css.cgroup; + else + return &cgrp_dfl_root.cgrp; +} + +#define SCX_INIT_TASK_ARGS_CGROUP(tg) .cgroup = tg_cgrp(tg), + +#else /* CONFIG_EXT_GROUP_SCHED */ + +#define SCX_INIT_TASK_ARGS_CGROUP(tg) + +#endif /* CONFIG_EXT_GROUP_SCHED */ + +static enum scx_task_state scx_get_task_state(const struct task_struct *p) +{ + return (p->scx.flags & SCX_TASK_STATE_MASK) >> SCX_TASK_STATE_SHIFT; +} + +static void scx_set_task_state(struct task_struct *p, enum scx_task_state state) +{ + enum scx_task_state prev_state = scx_get_task_state(p); + bool warn = false; + + BUILD_BUG_ON(SCX_TASK_NR_STATES > (1 << SCX_TASK_STATE_BITS)); + + switch (state) { + case SCX_TASK_NONE: + break; + case SCX_TASK_INIT: + warn = prev_state != SCX_TASK_NONE; + break; + case SCX_TASK_READY: + warn = prev_state == SCX_TASK_NONE; + break; + case SCX_TASK_ENABLED: + warn = prev_state != SCX_TASK_READY; + break; + default: + warn = true; + return; + } + + WARN_ONCE(warn, "sched_ext: Invalid task state transition %d -> %d for %s[%d]", + prev_state, state, p->comm, p->pid); + + p->scx.flags &= ~SCX_TASK_STATE_MASK; + p->scx.flags |= state << SCX_TASK_STATE_SHIFT; +} + +static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool fork) +{ + int ret; + + p->scx.disallow = false; + + if (SCX_HAS_OP(init_task)) { + struct scx_init_task_args args = { + SCX_INIT_TASK_ARGS_CGROUP(tg) + .fork = fork, + }; + + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init_task, NULL, p, &args); + if (unlikely(ret)) { + ret = ops_sanitize_err("init_task", ret); + return ret; + } + } + + scx_set_task_state(p, SCX_TASK_INIT); + + if (p->scx.disallow) { + if (!fork) { + struct rq *rq; + struct rq_flags rf; + + rq = task_rq_lock(p, &rf); + + /* + * We're in the load path and @p->policy will be applied + * right after. Reverting @p->policy here and rejecting + * %SCHED_EXT transitions from scx_check_setscheduler() + * guarantees that if ops.init_task() sets @p->disallow, + * @p can never be in SCX. + */ + if (p->policy == SCHED_EXT) { + p->policy = SCHED_NORMAL; + atomic_long_inc(&scx_nr_rejected); + } + + task_rq_unlock(rq, p, &rf); + } else if (p->policy == SCHED_EXT) { + scx_ops_error("ops.init_task() set task->scx.disallow for %s[%d] during fork", + p->comm, p->pid); + } + } + + p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT; + return 0; +} + +static void scx_ops_enable_task(struct task_struct *p) +{ + struct rq *rq = task_rq(p); + u32 weight; + + lockdep_assert_rq_held(rq); + + /* + * Set the weight before calling ops.enable() so that the scheduler + * doesn't see a stale value if they inspect the task struct. + */ + if (task_has_idle_policy(p)) + weight = WEIGHT_IDLEPRIO; + else + weight = sched_prio_to_weight[p->static_prio - MAX_RT_PRIO]; + + p->scx.weight = sched_weight_to_cgroup(weight); + + if (SCX_HAS_OP(enable)) + SCX_CALL_OP_TASK(SCX_KF_REST, enable, rq, p); + scx_set_task_state(p, SCX_TASK_ENABLED); + + if (SCX_HAS_OP(set_weight)) + SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, rq, p, p->scx.weight); +} + +static void scx_ops_disable_task(struct task_struct *p) +{ + struct rq *rq = task_rq(p); + + lockdep_assert_rq_held(rq); + WARN_ON_ONCE(scx_get_task_state(p) != SCX_TASK_ENABLED); + + if (SCX_HAS_OP(disable)) + SCX_CALL_OP_TASK(SCX_KF_REST, disable, rq, p); + scx_set_task_state(p, SCX_TASK_READY); +} + +static void scx_ops_exit_task(struct task_struct *p) +{ + struct scx_exit_task_args args = { + .cancelled = false, + }; + + lockdep_assert_rq_held(task_rq(p)); + + switch (scx_get_task_state(p)) { + case SCX_TASK_NONE: + return; + case SCX_TASK_INIT: + args.cancelled = true; + break; + case SCX_TASK_READY: + break; + case SCX_TASK_ENABLED: + scx_ops_disable_task(p); + break; + default: + WARN_ON_ONCE(true); + return; + } + + if (SCX_HAS_OP(exit_task)) + SCX_CALL_OP_TASK(SCX_KF_REST, exit_task, task_rq(p), p, &args); + scx_set_task_state(p, SCX_TASK_NONE); +} + +void init_scx_entity(struct sched_ext_entity *scx) +{ + memset(scx, 0, sizeof(*scx)); + INIT_LIST_HEAD(&scx->dsq_list.node); + RB_CLEAR_NODE(&scx->dsq_priq); + scx->sticky_cpu = -1; + scx->holding_cpu = -1; + INIT_LIST_HEAD(&scx->runnable_node); + scx->runnable_at = jiffies; + scx->ddsp_dsq_id = SCX_DSQ_INVALID; + scx->slice = SCX_SLICE_DFL; +} + +void scx_pre_fork(struct task_struct *p) +{ + /* + * BPF scheduler enable/disable paths want to be able to iterate and + * update all tasks which can become complex when racing forks. As + * enable/disable are very cold paths, let's use a percpu_rwsem to + * exclude forks. + */ + percpu_down_read(&scx_fork_rwsem); +} + +int scx_fork(struct task_struct *p) +{ + percpu_rwsem_assert_held(&scx_fork_rwsem); + + if (scx_ops_init_task_enabled) + return scx_ops_init_task(p, task_group(p), true); + else + return 0; +} + +void scx_post_fork(struct task_struct *p) +{ + if (scx_ops_init_task_enabled) { + scx_set_task_state(p, SCX_TASK_READY); + + /* + * Enable the task immediately if it's running on sched_ext. + * Otherwise, it'll be enabled in switching_to_scx() if and + * when it's ever configured to run with a SCHED_EXT policy. + */ + if (p->sched_class == &ext_sched_class) { + struct rq_flags rf; + struct rq *rq; + + rq = task_rq_lock(p, &rf); + scx_ops_enable_task(p); + task_rq_unlock(rq, p, &rf); + } + } + + spin_lock_irq(&scx_tasks_lock); + list_add_tail(&p->scx.tasks_node, &scx_tasks); + spin_unlock_irq(&scx_tasks_lock); + + percpu_up_read(&scx_fork_rwsem); +} + +void scx_cancel_fork(struct task_struct *p) +{ + if (scx_enabled()) { + struct rq *rq; + struct rq_flags rf; + + rq = task_rq_lock(p, &rf); + WARN_ON_ONCE(scx_get_task_state(p) >= SCX_TASK_READY); + scx_ops_exit_task(p); + task_rq_unlock(rq, p, &rf); + } + + percpu_up_read(&scx_fork_rwsem); +} + +void sched_ext_free(struct task_struct *p) +{ + unsigned long flags; + + spin_lock_irqsave(&scx_tasks_lock, flags); + list_del_init(&p->scx.tasks_node); + spin_unlock_irqrestore(&scx_tasks_lock, flags); + + /* + * @p is off scx_tasks and wholly ours. scx_ops_enable()'s READY -> + * ENABLED transitions can't race us. Disable ops for @p. + */ + if (scx_get_task_state(p) != SCX_TASK_NONE) { + struct rq_flags rf; + struct rq *rq; + + rq = task_rq_lock(p, &rf); + scx_ops_exit_task(p); + task_rq_unlock(rq, p, &rf); + } +} + +static void reweight_task_scx(struct rq *rq, struct task_struct *p, const struct load_weight *lw) +{ + lockdep_assert_rq_held(task_rq(p)); + + p->scx.weight = sched_weight_to_cgroup(scale_load_down(lw->weight)); + if (SCX_HAS_OP(set_weight)) + SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, rq, p, p->scx.weight); +} + +static void prio_changed_scx(struct rq *rq, struct task_struct *p, int oldprio) +{ +} + +static void switching_to_scx(struct rq *rq, struct task_struct *p) +{ + scx_ops_enable_task(p); + + /* + * set_cpus_allowed_scx() is not called while @p is associated with a + * different scheduler class. Keep the BPF scheduler up-to-date. + */ + if (SCX_HAS_OP(set_cpumask)) + SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, rq, + p, (struct cpumask *)p->cpus_ptr); +} + +static void switched_from_scx(struct rq *rq, struct task_struct *p) +{ + scx_ops_disable_task(p); +} + +static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p,int wake_flags) {} +static void switched_to_scx(struct rq *rq, struct task_struct *p) {} + +int scx_check_setscheduler(struct task_struct *p, int policy) +{ + lockdep_assert_rq_held(task_rq(p)); + + /* if disallow, reject transitioning into SCX */ + if (scx_enabled() && READ_ONCE(p->scx.disallow) && + p->policy != policy && policy == SCHED_EXT) + return -EACCES; + + return 0; +} + +#ifdef CONFIG_NO_HZ_FULL +bool scx_can_stop_tick(struct rq *rq) +{ + struct task_struct *p = rq->curr; + + if (scx_rq_bypassing(rq)) + return false; + + if (p->sched_class != &ext_sched_class) + return true; + + /* + * @rq can dispatch from different DSQs, so we can't tell whether it + * needs the tick or not by looking at nr_running. Allow stopping ticks + * iff the BPF scheduler indicated so. See set_next_task_scx(). + */ + return rq->scx.flags & SCX_RQ_CAN_STOP_TICK; +} +#endif + +#ifdef CONFIG_EXT_GROUP_SCHED + +DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem); +static bool scx_cgroup_enabled; +static bool cgroup_warned_missing_weight; +static bool cgroup_warned_missing_idle; + +static void scx_cgroup_warn_missing_weight(struct task_group *tg) +{ + if (scx_ops_enable_state() == SCX_OPS_DISABLED || + cgroup_warned_missing_weight) + return; + + if ((scx_ops.flags & SCX_OPS_HAS_CGROUP_WEIGHT) || !tg->css.parent) + return; + + pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.weight\n", + scx_ops.name); + cgroup_warned_missing_weight = true; +} + +static void scx_cgroup_warn_missing_idle(struct task_group *tg) +{ + if (!scx_cgroup_enabled || cgroup_warned_missing_idle) + return; + + if (!tg->idle) + return; + + pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.idle\n", + scx_ops.name); + cgroup_warned_missing_idle = true; +} + +void scx_tg_init(struct task_group *tg) +{ + tg->scx_weight = CGROUP_WEIGHT_DFL; +} + +int scx_tg_online(struct task_group *tg) +{ + int ret = 0; + + WARN_ON_ONCE(tg->scx_flags & (SCX_TG_ONLINE | SCX_TG_INITED)); + + percpu_down_read(&scx_cgroup_rwsem); + + scx_cgroup_warn_missing_weight(tg); + + if (scx_cgroup_enabled) { + if (SCX_HAS_OP(cgroup_init)) { + struct scx_cgroup_init_args args = + { .weight = tg->scx_weight }; + + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, NULL, + tg->css.cgroup, &args); + if (ret) + ret = ops_sanitize_err("cgroup_init", ret); + } + if (ret == 0) + tg->scx_flags |= SCX_TG_ONLINE | SCX_TG_INITED; + } else { + tg->scx_flags |= SCX_TG_ONLINE; + } + + percpu_up_read(&scx_cgroup_rwsem); + return ret; +} + +void scx_tg_offline(struct task_group *tg) +{ + WARN_ON_ONCE(!(tg->scx_flags & SCX_TG_ONLINE)); + + percpu_down_read(&scx_cgroup_rwsem); + + if (SCX_HAS_OP(cgroup_exit) && (tg->scx_flags & SCX_TG_INITED)) + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, NULL, tg->css.cgroup); + tg->scx_flags &= ~(SCX_TG_ONLINE | SCX_TG_INITED); + + percpu_up_read(&scx_cgroup_rwsem); +} + +int scx_cgroup_can_attach(struct cgroup_taskset *tset) +{ + struct cgroup_subsys_state *css; + struct task_struct *p; + int ret; + + /* released in scx_finish/cancel_attach() */ + percpu_down_read(&scx_cgroup_rwsem); + + if (!scx_cgroup_enabled) + return 0; + + cgroup_taskset_for_each(p, css, tset) { + struct cgroup *from = tg_cgrp(task_group(p)); + struct cgroup *to = tg_cgrp(css_tg(css)); + + WARN_ON_ONCE(p->scx.cgrp_moving_from); + + /* + * sched_move_task() omits identity migrations. Let's match the + * behavior so that ops.cgroup_prep_move() and ops.cgroup_move() + * always match one-to-one. + */ + if (from == to) + continue; + + if (SCX_HAS_OP(cgroup_prep_move)) { + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_prep_move, NULL, + p, from, css->cgroup); + if (ret) + goto err; + } + + p->scx.cgrp_moving_from = from; + } + + return 0; + +err: + cgroup_taskset_for_each(p, css, tset) { + if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from) + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, NULL, + p, p->scx.cgrp_moving_from, css->cgroup); + p->scx.cgrp_moving_from = NULL; + } + + percpu_up_read(&scx_cgroup_rwsem); + return ops_sanitize_err("cgroup_prep_move", ret); +} + +void scx_cgroup_move_task(struct task_struct *p) +{ + if (!scx_cgroup_enabled) + return; + + /* + * @p must have ops.cgroup_prep_move() called on it and thus + * cgrp_moving_from set. + */ + if (SCX_HAS_OP(cgroup_move) && !WARN_ON_ONCE(!p->scx.cgrp_moving_from)) + SCX_CALL_OP_TASK(SCX_KF_UNLOCKED, cgroup_move, NULL, + p, p->scx.cgrp_moving_from, tg_cgrp(task_group(p))); + p->scx.cgrp_moving_from = NULL; +} + +void scx_cgroup_finish_attach(void) +{ + percpu_up_read(&scx_cgroup_rwsem); +} + +void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) +{ + struct cgroup_subsys_state *css; + struct task_struct *p; + + if (!scx_cgroup_enabled) + goto out_unlock; + + cgroup_taskset_for_each(p, css, tset) { + if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from) + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, NULL, + p, p->scx.cgrp_moving_from, css->cgroup); + p->scx.cgrp_moving_from = NULL; + } +out_unlock: + percpu_up_read(&scx_cgroup_rwsem); +} + +void scx_group_set_weight(struct task_group *tg, unsigned long weight) +{ + percpu_down_read(&scx_cgroup_rwsem); + + if (scx_cgroup_enabled && SCX_HAS_OP(cgroup_set_weight) && + tg->scx_weight != weight) + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight, NULL, + tg_cgrp(tg), weight); + + tg->scx_weight = weight; + + percpu_up_read(&scx_cgroup_rwsem); +} + +void scx_group_set_idle(struct task_group *tg, bool idle) +{ + percpu_down_read(&scx_cgroup_rwsem); + scx_cgroup_warn_missing_idle(tg); + percpu_up_read(&scx_cgroup_rwsem); +} + +static void scx_cgroup_lock(void) +{ + percpu_down_write(&scx_cgroup_rwsem); +} + +static void scx_cgroup_unlock(void) +{ + percpu_up_write(&scx_cgroup_rwsem); +} + +#else /* CONFIG_EXT_GROUP_SCHED */ + +static inline void scx_cgroup_lock(void) {} +static inline void scx_cgroup_unlock(void) {} + +#endif /* CONFIG_EXT_GROUP_SCHED */ + +/* + * Omitted operations: + * + * - wakeup_preempt: NOOP as it isn't useful in the wakeup path because the task + * isn't tied to the CPU at that point. Preemption is implemented by resetting + * the victim task's slice to 0 and triggering reschedule on the target CPU. + * + * - migrate_task_rq: Unnecessary as task to cpu mapping is transient. + * + * - task_fork/dead: We need fork/dead notifications for all tasks regardless of + * their current sched_class. Call them directly from sched core instead. + */ +DEFINE_SCHED_CLASS(ext) = { + .enqueue_task = enqueue_task_scx, + .dequeue_task = dequeue_task_scx, + .yield_task = yield_task_scx, + .yield_to_task = yield_to_task_scx, + + .wakeup_preempt = wakeup_preempt_scx, + + .balance = balance_scx, + .pick_task = pick_task_scx, + + .put_prev_task = put_prev_task_scx, + .set_next_task = set_next_task_scx, + +#ifdef CONFIG_SMP + .select_task_rq = select_task_rq_scx, + .task_woken = task_woken_scx, + .set_cpus_allowed = set_cpus_allowed_scx, + + .rq_online = rq_online_scx, + .rq_offline = rq_offline_scx, +#endif + + .task_tick = task_tick_scx, + + .switching_to = switching_to_scx, + .switched_from = switched_from_scx, + .switched_to = switched_to_scx, + .reweight_task = reweight_task_scx, + .prio_changed = prio_changed_scx, + + .update_curr = update_curr_scx, + +#ifdef CONFIG_UCLAMP_TASK + .uclamp_enabled = 1, +#endif +}; + +static void init_dsq(struct scx_dispatch_q *dsq, u64 dsq_id) +{ + memset(dsq, 0, sizeof(*dsq)); + + raw_spin_lock_init(&dsq->lock); + INIT_LIST_HEAD(&dsq->list); + dsq->id = dsq_id; +} + +static struct scx_dispatch_q *create_dsq(u64 dsq_id, int node) +{ + struct scx_dispatch_q *dsq; + int ret; + + if (dsq_id & SCX_DSQ_FLAG_BUILTIN) + return ERR_PTR(-EINVAL); + + dsq = kmalloc_node(sizeof(*dsq), GFP_KERNEL, node); + if (!dsq) + return ERR_PTR(-ENOMEM); + + init_dsq(dsq, dsq_id); + + ret = rhashtable_lookup_insert_fast(&dsq_hash, &dsq->hash_node, + dsq_hash_params); + if (ret) { + kfree(dsq); + return ERR_PTR(ret); + } + return dsq; +} + +static void free_dsq_irq_workfn(struct irq_work *irq_work) +{ + struct llist_node *to_free = llist_del_all(&dsqs_to_free); + struct scx_dispatch_q *dsq, *tmp_dsq; + + llist_for_each_entry_safe(dsq, tmp_dsq, to_free, free_node) + kfree_rcu(dsq, rcu); +} + +static DEFINE_IRQ_WORK(free_dsq_irq_work, free_dsq_irq_workfn); + +static void destroy_dsq(u64 dsq_id) +{ + struct scx_dispatch_q *dsq; + unsigned long flags; + + rcu_read_lock(); + + dsq = find_user_dsq(dsq_id); + if (!dsq) + goto out_unlock_rcu; + + raw_spin_lock_irqsave(&dsq->lock, flags); + + if (dsq->nr) { + scx_ops_error("attempting to destroy in-use dsq 0x%016llx (nr=%u)", + dsq->id, dsq->nr); + goto out_unlock_dsq; + } + + if (rhashtable_remove_fast(&dsq_hash, &dsq->hash_node, dsq_hash_params)) + goto out_unlock_dsq; + + /* + * Mark dead by invalidating ->id to prevent dispatch_enqueue() from + * queueing more tasks. As this function can be called from anywhere, + * freeing is bounced through an irq work to avoid nesting RCU + * operations inside scheduler locks. + */ + dsq->id = SCX_DSQ_INVALID; + llist_add(&dsq->free_node, &dsqs_to_free); + irq_work_queue(&free_dsq_irq_work); + +out_unlock_dsq: + raw_spin_unlock_irqrestore(&dsq->lock, flags); +out_unlock_rcu: + rcu_read_unlock(); +} + +#ifdef CONFIG_EXT_GROUP_SCHED +static void scx_cgroup_exit(void) +{ + struct cgroup_subsys_state *css; + + percpu_rwsem_assert_held(&scx_cgroup_rwsem); + + scx_cgroup_enabled = false; + + /* + * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk + * cgroups and exit all the inited ones, all online cgroups are exited. + */ + rcu_read_lock(); + css_for_each_descendant_post(css, &root_task_group.css) { + struct task_group *tg = css_tg(css); + + if (!(tg->scx_flags & SCX_TG_INITED)) + continue; + tg->scx_flags &= ~SCX_TG_INITED; + + if (!scx_ops.cgroup_exit) + continue; + + if (WARN_ON_ONCE(!css_tryget(css))) + continue; + rcu_read_unlock(); + + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, NULL, css->cgroup); + + rcu_read_lock(); + css_put(css); + } + rcu_read_unlock(); +} + +static int scx_cgroup_init(void) +{ + struct cgroup_subsys_state *css; + int ret; + + percpu_rwsem_assert_held(&scx_cgroup_rwsem); + + cgroup_warned_missing_weight = false; + cgroup_warned_missing_idle = false; + + /* + * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk + * cgroups and init, all online cgroups are initialized. + */ + rcu_read_lock(); + css_for_each_descendant_pre(css, &root_task_group.css) { + struct task_group *tg = css_tg(css); + struct scx_cgroup_init_args args = { .weight = tg->scx_weight }; + + scx_cgroup_warn_missing_weight(tg); + scx_cgroup_warn_missing_idle(tg); + + if ((tg->scx_flags & + (SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE) + continue; + + if (!scx_ops.cgroup_init) { + tg->scx_flags |= SCX_TG_INITED; + continue; + } + + if (WARN_ON_ONCE(!css_tryget(css))) + continue; + rcu_read_unlock(); + + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, NULL, + css->cgroup, &args); + if (ret) { + css_put(css); + scx_ops_error("ops.cgroup_init() failed (%d)", ret); + return ret; + } + tg->scx_flags |= SCX_TG_INITED; + + rcu_read_lock(); + css_put(css); + } + rcu_read_unlock(); + + WARN_ON_ONCE(scx_cgroup_enabled); + scx_cgroup_enabled = true; + + return 0; +} + +#else +static void scx_cgroup_exit(void) {} +static int scx_cgroup_init(void) { return 0; } +#endif + + +/******************************************************************************** + * Sysfs interface and ops enable/disable. + */ + +#define SCX_ATTR(_name) \ + static struct kobj_attribute scx_attr_##_name = { \ + .attr = { .name = __stringify(_name), .mode = 0444 }, \ + .show = scx_attr_##_name##_show, \ + } + +static ssize_t scx_attr_state_show(struct kobject *kobj, + struct kobj_attribute *ka, char *buf) +{ + return sysfs_emit(buf, "%s\n", + scx_ops_enable_state_str[scx_ops_enable_state()]); +} +SCX_ATTR(state); + +static ssize_t scx_attr_switch_all_show(struct kobject *kobj, + struct kobj_attribute *ka, char *buf) +{ + return sysfs_emit(buf, "%d\n", READ_ONCE(scx_switching_all)); +} +SCX_ATTR(switch_all); + +static ssize_t scx_attr_nr_rejected_show(struct kobject *kobj, + struct kobj_attribute *ka, char *buf) +{ + return sysfs_emit(buf, "%ld\n", atomic_long_read(&scx_nr_rejected)); +} +SCX_ATTR(nr_rejected); + +static ssize_t scx_attr_hotplug_seq_show(struct kobject *kobj, + struct kobj_attribute *ka, char *buf) +{ + return sysfs_emit(buf, "%ld\n", atomic_long_read(&scx_hotplug_seq)); +} +SCX_ATTR(hotplug_seq); + +static ssize_t scx_attr_enable_seq_show(struct kobject *kobj, + struct kobj_attribute *ka, char *buf) +{ + return sysfs_emit(buf, "%ld\n", atomic_long_read(&scx_enable_seq)); +} +SCX_ATTR(enable_seq); + +static struct attribute *scx_global_attrs[] = { + &scx_attr_state.attr, + &scx_attr_switch_all.attr, + &scx_attr_nr_rejected.attr, + &scx_attr_hotplug_seq.attr, + &scx_attr_enable_seq.attr, + NULL, +}; + +static const struct attribute_group scx_global_attr_group = { + .attrs = scx_global_attrs, +}; + +static void scx_kobj_release(struct kobject *kobj) +{ + kfree(kobj); +} + +static ssize_t scx_attr_ops_show(struct kobject *kobj, + struct kobj_attribute *ka, char *buf) +{ + return sysfs_emit(buf, "%s\n", scx_ops.name); +} +SCX_ATTR(ops); + +static struct attribute *scx_sched_attrs[] = { + &scx_attr_ops.attr, + NULL, +}; +ATTRIBUTE_GROUPS(scx_sched); + +static const struct kobj_type scx_ktype = { + .release = scx_kobj_release, + .sysfs_ops = &kobj_sysfs_ops, + .default_groups = scx_sched_groups, +}; + +static int scx_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) +{ + return add_uevent_var(env, "SCXOPS=%s", scx_ops.name); +} + +static const struct kset_uevent_ops scx_uevent_ops = { + .uevent = scx_uevent, +}; + +/* + * Used by sched_fork() and __setscheduler_prio() to pick the matching + * sched_class. dl/rt are already handled. + */ +bool task_should_scx(int policy) +{ + if (!scx_enabled() || + unlikely(scx_ops_enable_state() == SCX_OPS_DISABLING)) + return false; + if (READ_ONCE(scx_switching_all)) + return true; + return policy == SCHED_EXT; +} + +/** + * scx_softlockup - sched_ext softlockup handler + * @dur_s: number of seconds of CPU stuck due to soft lockup + * + * On some multi-socket setups (e.g. 2x Intel 8480c), the BPF scheduler can + * live-lock the system by making many CPUs target the same DSQ to the point + * where soft-lockup detection triggers. This function is called from + * soft-lockup watchdog when the triggering point is close and tries to unjam + * the system by enabling the breather and aborting the BPF scheduler. + */ +void scx_softlockup(u32 dur_s) +{ + switch (scx_ops_enable_state()) { + case SCX_OPS_ENABLING: + case SCX_OPS_ENABLED: + break; + default: + return; + } + + /* allow only one instance, cleared at the end of scx_ops_bypass() */ + if (test_and_set_bit(0, &scx_in_softlockup)) + return; + + printk_deferred(KERN_ERR "sched_ext: Soft lockup - CPU%d stuck for %us, disabling \"%s\"\n", + smp_processor_id(), dur_s, scx_ops.name); + + /* + * Some CPUs may be trapped in the dispatch paths. Enable breather + * immediately; otherwise, we might even be able to get to + * scx_ops_bypass(). + */ + atomic_inc(&scx_ops_breather_depth); + + scx_ops_error("soft lockup - CPU#%d stuck for %us", + smp_processor_id(), dur_s); +} + +static void scx_clear_softlockup(void) +{ + if (test_and_clear_bit(0, &scx_in_softlockup)) + atomic_dec(&scx_ops_breather_depth); +} + +/** + * scx_ops_bypass - [Un]bypass scx_ops and guarantee forward progress + * @bypass: true for bypass, false for unbypass + * + * Bypassing guarantees that all runnable tasks make forward progress without + * trusting the BPF scheduler. We can't grab any mutexes or rwsems as they might + * be held by tasks that the BPF scheduler is forgetting to run, which + * unfortunately also excludes toggling the static branches. + * + * Let's work around by overriding a couple ops and modifying behaviors based on + * the DISABLING state and then cycling the queued tasks through dequeue/enqueue + * to force global FIFO scheduling. + * + * - ops.select_cpu() is ignored and the default select_cpu() is used. + * + * - ops.enqueue() is ignored and tasks are queued in simple global FIFO order. + * %SCX_OPS_ENQ_LAST is also ignored. + * + * - ops.dispatch() is ignored. + * + * - balance_scx() does not set %SCX_RQ_BAL_KEEP on non-zero slice as slice + * can't be trusted. Whenever a tick triggers, the running task is rotated to + * the tail of the queue with core_sched_at touched. + * + * - pick_next_task() suppresses zero slice warning. + * + * - scx_bpf_kick_cpu() is disabled to avoid irq_work malfunction during PM + * operations. + * + * - scx_prio_less() reverts to the default core_sched_at order. + */ +static void scx_ops_bypass(bool bypass) +{ + static DEFINE_RAW_SPINLOCK(bypass_lock); + int cpu; + unsigned long flags; + + raw_spin_lock_irqsave(&bypass_lock, flags); + if (bypass) { + scx_ops_bypass_depth++; + WARN_ON_ONCE(scx_ops_bypass_depth <= 0); + if (scx_ops_bypass_depth != 1) + goto unlock; + } else { + scx_ops_bypass_depth--; + WARN_ON_ONCE(scx_ops_bypass_depth < 0); + if (scx_ops_bypass_depth != 0) + goto unlock; + } + + atomic_inc(&scx_ops_breather_depth); + + /* + * No task property is changing. We just need to make sure all currently + * queued tasks are re-queued according to the new scx_rq_bypassing() + * state. As an optimization, walk each rq's runnable_list instead of + * the scx_tasks list. + * + * This function can't trust the scheduler and thus can't use + * cpus_read_lock(). Walk all possible CPUs instead of online. + */ + for_each_possible_cpu(cpu) { + struct rq *rq = cpu_rq(cpu); + struct task_struct *p, *n; + + raw_spin_rq_lock(rq); + + if (bypass) { + WARN_ON_ONCE(rq->scx.flags & SCX_RQ_BYPASSING); + rq->scx.flags |= SCX_RQ_BYPASSING; + } else { + WARN_ON_ONCE(!(rq->scx.flags & SCX_RQ_BYPASSING)); + rq->scx.flags &= ~SCX_RQ_BYPASSING; + } + + /* + * We need to guarantee that no tasks are on the BPF scheduler + * while bypassing. Either we see enabled or the enable path + * sees scx_rq_bypassing() before moving tasks to SCX. + */ + if (!scx_enabled()) { + raw_spin_rq_unlock(rq); + continue; + } + + /* + * The use of list_for_each_entry_safe_reverse() is required + * because each task is going to be removed from and added back + * to the runnable_list during iteration. Because they're added + * to the tail of the list, safe reverse iteration can still + * visit all nodes. + */ + list_for_each_entry_safe_reverse(p, n, &rq->scx.runnable_list, + scx.runnable_node) { + struct sched_enq_and_set_ctx ctx; + + /* cycling deq/enq is enough, see the function comment */ + sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx); + sched_enq_and_set_task(&ctx); + } + + /* resched to restore ticks and idle state */ + if (cpu_online(cpu) || cpu == smp_processor_id()) + resched_curr(rq); + + raw_spin_rq_unlock(rq); + } + + atomic_dec(&scx_ops_breather_depth); +unlock: + raw_spin_unlock_irqrestore(&bypass_lock, flags); + scx_clear_softlockup(); +} + +static void free_exit_info(struct scx_exit_info *ei) +{ + kvfree(ei->dump); + kfree(ei->msg); + kfree(ei->bt); + kfree(ei); +} + +static struct scx_exit_info *alloc_exit_info(size_t exit_dump_len) +{ + struct scx_exit_info *ei; + + ei = kzalloc(sizeof(*ei), GFP_KERNEL); + if (!ei) + return NULL; + + ei->bt = kcalloc(SCX_EXIT_BT_LEN, sizeof(ei->bt[0]), GFP_KERNEL); + ei->msg = kzalloc(SCX_EXIT_MSG_LEN, GFP_KERNEL); + ei->dump = kvzalloc(exit_dump_len, GFP_KERNEL); + + if (!ei->bt || !ei->msg || !ei->dump) { + free_exit_info(ei); + return NULL; + } + + return ei; +} + +static const char *scx_exit_reason(enum scx_exit_kind kind) +{ + switch (kind) { + case SCX_EXIT_UNREG: + return "unregistered from user space"; + case SCX_EXIT_UNREG_BPF: + return "unregistered from BPF"; + case SCX_EXIT_UNREG_KERN: + return "unregistered from the main kernel"; + case SCX_EXIT_SYSRQ: + return "disabled by sysrq-S"; + case SCX_EXIT_ERROR: + return "runtime error"; + case SCX_EXIT_ERROR_BPF: + return "scx_bpf_error"; + case SCX_EXIT_ERROR_STALL: + return "runnable task stall"; + default: + return ""; + } +} + +static void scx_ops_disable_workfn(struct kthread_work *work) +{ + struct scx_exit_info *ei = scx_exit_info; + struct scx_task_iter sti; + struct task_struct *p; + struct rhashtable_iter rht_iter; + struct scx_dispatch_q *dsq; + int i, kind, cpu; + + kind = atomic_read(&scx_exit_kind); + while (true) { + /* + * NONE indicates that a new scx_ops has been registered since + * disable was scheduled - don't kill the new ops. DONE + * indicates that the ops has already been disabled. + */ + if (kind == SCX_EXIT_NONE || kind == SCX_EXIT_DONE) + return; + if (atomic_try_cmpxchg(&scx_exit_kind, &kind, SCX_EXIT_DONE)) + break; + } + ei->kind = kind; + ei->reason = scx_exit_reason(ei->kind); + + /* guarantee forward progress by bypassing scx_ops */ + scx_ops_bypass(true); + + switch (scx_ops_set_enable_state(SCX_OPS_DISABLING)) { + case SCX_OPS_DISABLING: + WARN_ONCE(true, "sched_ext: duplicate disabling instance?"); + break; + case SCX_OPS_DISABLED: + pr_warn("sched_ext: ops error detected without ops (%s)\n", + scx_exit_info->msg); + WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_DISABLED) != + SCX_OPS_DISABLING); + goto done; + default: + break; + } + + /* + * Here, every runnable task is guaranteed to make forward progress and + * we can safely use blocking synchronization constructs. Actually + * disable ops. + */ + mutex_lock(&scx_ops_enable_mutex); + + static_branch_disable(&__scx_switched_all); + WRITE_ONCE(scx_switching_all, false); + + /* + * Shut down cgroup support before tasks so that the cgroup attach path + * doesn't race against scx_ops_exit_task(). + */ + scx_cgroup_lock(); + scx_cgroup_exit(); + scx_cgroup_unlock(); + + /* + * The BPF scheduler is going away. All tasks including %TASK_DEAD ones + * must be switched out and exited synchronously. + */ + percpu_down_write(&scx_fork_rwsem); + + scx_ops_init_task_enabled = false; + + scx_task_iter_start(&sti); + while ((p = scx_task_iter_next_locked(&sti))) { + const struct sched_class *old_class = p->sched_class; + struct sched_enq_and_set_ctx ctx; + + sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx); + + /* + * pick from mainline + * 98442f0ccd82 ("sched: Fix delayed_dequeue vs switched_from_fair()") + * 5db91545ef81 ("sched: Pass correct scheduling policy to + * __setscheduler_class") + */ + p->sched_class = __setscheduler_class(p->policy, p->prio); + check_class_changing(task_rq(p), p, old_class); + + sched_enq_and_set_task(&ctx); + + check_class_changed(task_rq(p), p, old_class, p->prio); + scx_ops_exit_task(p); + } + scx_task_iter_stop(&sti); + percpu_up_write(&scx_fork_rwsem); + + /* + * Invalidate all the rq clocks to prevent getting outdated + * rq clocks from a previous scx scheduler. + */ + for_each_possible_cpu(cpu) { + struct rq *rq = cpu_rq(cpu); + scx_rq_clock_invalidate(rq); + } + + /* no task is on scx, turn off all the switches and flush in-progress calls */ + static_branch_disable(&__scx_ops_enabled); + for (i = SCX_OPI_BEGIN; i < SCX_OPI_END; i++) + static_branch_disable(&scx_has_op[i]); + static_branch_disable(&scx_ops_allow_queued_wakeup); + static_branch_disable(&scx_ops_enq_last); + static_branch_disable(&scx_ops_enq_exiting); + static_branch_disable(&scx_ops_enq_migration_disabled); + static_branch_disable(&scx_ops_cpu_preempt); + static_branch_disable(&scx_builtin_idle_enabled); + synchronize_rcu(); + + if (ei->kind >= SCX_EXIT_ERROR) { + pr_err("sched_ext: BPF scheduler \"%s\" disabled (%s)\n", + scx_ops.name, ei->reason); + + if (ei->msg[0] != '\0') + pr_err("sched_ext: %s: %s\n", scx_ops.name, ei->msg); +#ifdef CONFIG_STACKTRACE + stack_trace_print(ei->bt, ei->bt_len, 2); +#endif + } else { + pr_info("sched_ext: BPF scheduler \"%s\" disabled (%s)\n", + scx_ops.name, ei->reason); + } + + if (scx_ops.exit) + SCX_CALL_OP(SCX_KF_UNLOCKED, exit, NULL, ei); + + cancel_delayed_work_sync(&scx_watchdog_work); + + /* + * Delete the kobject from the hierarchy eagerly in addition to just + * dropping a reference. Otherwise, if the object is deleted + * asynchronously, sysfs could observe an object of the same name still + * in the hierarchy when another scheduler is loaded. + */ + kobject_del(scx_root_kobj); + kobject_put(scx_root_kobj); + scx_root_kobj = NULL; + + memset(&scx_ops, 0, sizeof(scx_ops)); + + rhashtable_walk_enter(&dsq_hash, &rht_iter); + do { + rhashtable_walk_start(&rht_iter); + + while ((dsq = rhashtable_walk_next(&rht_iter)) && !IS_ERR(dsq)) + destroy_dsq(dsq->id); + + rhashtable_walk_stop(&rht_iter); + } while (dsq == ERR_PTR(-EAGAIN)); + rhashtable_walk_exit(&rht_iter); + + free_percpu(scx_dsp_ctx); + scx_dsp_ctx = NULL; + scx_dsp_max_batch = 0; + + free_exit_info(scx_exit_info); + scx_exit_info = NULL; + + mutex_unlock(&scx_ops_enable_mutex); + + WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_DISABLED) != + SCX_OPS_DISABLING); +done: + scx_ops_bypass(false); +} + +static DEFINE_KTHREAD_WORK(scx_ops_disable_work, scx_ops_disable_workfn); + +static void schedule_scx_ops_disable_work(void) +{ + struct kthread_worker *helper = READ_ONCE(scx_ops_helper); + + /* + * We may be called spuriously before the first bpf_sched_ext_reg(). If + * scx_ops_helper isn't set up yet, there's nothing to do. + */ + if (helper) + kthread_queue_work(helper, &scx_ops_disable_work); +} + +static void scx_ops_disable(enum scx_exit_kind kind) +{ + int none = SCX_EXIT_NONE; + + if (WARN_ON_ONCE(kind == SCX_EXIT_NONE || kind == SCX_EXIT_DONE)) + kind = SCX_EXIT_ERROR; + + atomic_try_cmpxchg(&scx_exit_kind, &none, kind); + + schedule_scx_ops_disable_work(); +} + +static void dump_newline(struct seq_buf *s) +{ + trace_sched_ext_dump(""); + + /* @s may be zero sized and seq_buf triggers WARN if so */ + if (s->size) + seq_buf_putc(s, '\n'); +} + +static __printf(2, 3) void dump_line(struct seq_buf *s, const char *fmt, ...) +{ + va_list args; + +#ifdef CONFIG_TRACEPOINTS + if (trace_sched_ext_dump_enabled()) { + /* protected by scx_dump_state()::dump_lock */ + static char line_buf[SCX_EXIT_MSG_LEN]; + + va_start(args, fmt); + vscnprintf(line_buf, sizeof(line_buf), fmt, args); + va_end(args); + + trace_sched_ext_dump(line_buf); + } +#endif + /* @s may be zero sized and seq_buf triggers WARN if so */ + if (s->size) { + va_start(args, fmt); + seq_buf_vprintf(s, fmt, args); + va_end(args); + + seq_buf_putc(s, '\n'); + } +} + +static void dump_stack_trace(struct seq_buf *s, const char *prefix, + const unsigned long *bt, unsigned int len) +{ + unsigned int i; + + for (i = 0; i < len; i++) + dump_line(s, "%s%pS", prefix, (void *)bt[i]); +} + +static void ops_dump_init(struct seq_buf *s, const char *prefix) +{ + struct scx_dump_data *dd = &scx_dump_data; + + lockdep_assert_irqs_disabled(); + + dd->cpu = smp_processor_id(); /* allow scx_bpf_dump() */ + dd->first = true; + dd->cursor = 0; + dd->s = s; + dd->prefix = prefix; +} + +static void ops_dump_flush(void) +{ + struct scx_dump_data *dd = &scx_dump_data; + char *line = dd->buf.line; + + if (!dd->cursor) + return; + + /* + * There's something to flush and this is the first line. Insert a blank + * line to distinguish ops dump. + */ + if (dd->first) { + dump_newline(dd->s); + dd->first = false; + } + + /* + * There may be multiple lines in $line. Scan and emit each line + * separately. + */ + while (true) { + char *end = line; + char c; + + while (*end != '\n' && *end != '\0') + end++; + + /* + * If $line overflowed, it may not have newline at the end. + * Always emit with a newline. + */ + c = *end; + *end = '\0'; + dump_line(dd->s, "%s%s", dd->prefix, line); + if (c == '\0') + break; + + /* move to the next line */ + end++; + if (*end == '\0') + break; + line = end; + } + + dd->cursor = 0; +} + +static void ops_dump_exit(void) +{ + ops_dump_flush(); + scx_dump_data.cpu = -1; +} + +static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx, + struct task_struct *p, char marker) +{ + static unsigned long bt[SCX_EXIT_BT_LEN]; + char dsq_id_buf[19] = "(n/a)"; + unsigned long ops_state = atomic_long_read(&p->scx.ops_state); + unsigned int bt_len = 0; + + if (p->scx.dsq) + scnprintf(dsq_id_buf, sizeof(dsq_id_buf), "0x%llx", + (unsigned long long)p->scx.dsq->id); + + dump_newline(s); + dump_line(s, " %c%c %s[%d] %+ldms", + marker, task_state_to_char(p), p->comm, p->pid, + jiffies_delta_msecs(p->scx.runnable_at, dctx->at_jiffies)); + dump_line(s, " scx_state/flags=%u/0x%x dsq_flags=0x%x ops_state/qseq=%lu/%lu", + scx_get_task_state(p), p->scx.flags & ~SCX_TASK_STATE_MASK, + p->scx.dsq_flags, ops_state & SCX_OPSS_STATE_MASK, + ops_state >> SCX_OPSS_QSEQ_SHIFT); + dump_line(s, " sticky/holding_cpu=%d/%d dsq_id=%s", + p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf); + dump_line(s, " dsq_vtime=%llu slice=%llu weight=%u", + p->scx.dsq_vtime, p->scx.slice, p->scx.weight); + dump_line(s, " cpus=%*pb", cpumask_pr_args(p->cpus_ptr)); + + if (SCX_HAS_OP(dump_task)) { + ops_dump_init(s, " "); + SCX_CALL_OP(SCX_KF_REST, dump_task, NULL, dctx, p); + ops_dump_exit(); + } + +#ifdef CONFIG_STACKTRACE + bt_len = stack_trace_save_tsk(p, bt, SCX_EXIT_BT_LEN, 1); +#endif + if (bt_len) { + dump_newline(s); + dump_stack_trace(s, " ", bt, bt_len); + } +} + +static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) +{ + static DEFINE_SPINLOCK(dump_lock); + static const char trunc_marker[] = "\n\n~~~~ TRUNCATED ~~~~\n"; + struct scx_dump_ctx dctx = { + .kind = ei->kind, + .exit_code = ei->exit_code, + .reason = ei->reason, + .at_ns = ktime_get_ns(), + .at_jiffies = jiffies, + }; + struct seq_buf s; + unsigned long flags; + char *buf; + int cpu; + + spin_lock_irqsave(&dump_lock, flags); + + seq_buf_init(&s, ei->dump, dump_len); + + if (ei->kind == SCX_EXIT_NONE) { + dump_line(&s, "Debug dump triggered by %s", ei->reason); + } else { + dump_line(&s, "%s[%d] triggered exit kind %d:", + current->comm, current->pid, ei->kind); + dump_line(&s, " %s (%s)", ei->reason, ei->msg); + dump_newline(&s); + dump_line(&s, "Backtrace:"); + dump_stack_trace(&s, " ", ei->bt, ei->bt_len); + } + + if (SCX_HAS_OP(dump)) { + ops_dump_init(&s, ""); + SCX_CALL_OP(SCX_KF_UNLOCKED, dump, NULL, &dctx); + ops_dump_exit(); + } + + dump_newline(&s); + dump_line(&s, "CPU states"); + dump_line(&s, "----------"); + + for_each_possible_cpu(cpu) { + struct rq *rq = cpu_rq(cpu); + struct rq_flags rf; + struct task_struct *p; + struct seq_buf ns; + size_t avail, used; + bool idle; + + rq_lock(rq, &rf); + + idle = list_empty(&rq->scx.runnable_list) && + rq->curr->sched_class == &idle_sched_class; + + if (idle && !SCX_HAS_OP(dump_cpu)) + goto next; + + /* + * We don't yet know whether ops.dump_cpu() will produce output + * and we may want to skip the default CPU dump if it doesn't. + * Use a nested seq_buf to generate the standard dump so that we + * can decide whether to commit later. + */ + avail = seq_buf_get_buf(&s, &buf); + seq_buf_init(&ns, buf, avail); + + dump_newline(&ns); + dump_line(&ns, "CPU %-4d: nr_run=%u flags=0x%x cpu_rel=%d ops_qseq=%lu pnt_seq=%lu", + cpu, rq->scx.nr_running, rq->scx.flags, + rq->scx.cpu_released, rq->scx.ops_qseq, + rq->scx.pnt_seq); + dump_line(&ns, " curr=%s[%d] class=%ps", + rq->curr->comm, rq->curr->pid, + rq->curr->sched_class); + if (!cpumask_empty(rq->scx.cpus_to_kick)) + dump_line(&ns, " cpus_to_kick : %*pb", + cpumask_pr_args(rq->scx.cpus_to_kick)); + if (!cpumask_empty(rq->scx.cpus_to_kick_if_idle)) + dump_line(&ns, " idle_to_kick : %*pb", + cpumask_pr_args(rq->scx.cpus_to_kick_if_idle)); + if (!cpumask_empty(rq->scx.cpus_to_preempt)) + dump_line(&ns, " cpus_to_preempt: %*pb", + cpumask_pr_args(rq->scx.cpus_to_preempt)); + if (!cpumask_empty(rq->scx.cpus_to_wait)) + dump_line(&ns, " cpus_to_wait : %*pb", + cpumask_pr_args(rq->scx.cpus_to_wait)); + + used = seq_buf_used(&ns); + if (SCX_HAS_OP(dump_cpu)) { + ops_dump_init(&ns, " "); + SCX_CALL_OP(SCX_KF_REST, dump_cpu, NULL, &dctx, cpu, idle); + ops_dump_exit(); + } + + /* + * If idle && nothing generated by ops.dump_cpu(), there's + * nothing interesting. Skip. + */ + if (idle && used == seq_buf_used(&ns)) + goto next; + + /* + * $s may already have overflowed when $ns was created. If so, + * calling commit on it will trigger BUG. + */ + if (avail) { + seq_buf_commit(&s, seq_buf_used(&ns)); + if (seq_buf_has_overflowed(&ns)) + seq_buf_set_overflow(&s); + } + + if (rq->curr->sched_class == &ext_sched_class) + scx_dump_task(&s, &dctx, rq->curr, '*'); + + list_for_each_entry(p, &rq->scx.runnable_list, scx.runnable_node) + scx_dump_task(&s, &dctx, p, ' '); + next: + rq_unlock(rq, &rf); + } + + if (seq_buf_has_overflowed(&s) && dump_len >= sizeof(trunc_marker)) + memcpy(ei->dump + dump_len - sizeof(trunc_marker), + trunc_marker, sizeof(trunc_marker)); + + spin_unlock_irqrestore(&dump_lock, flags); +} + +static void scx_ops_error_irq_workfn(struct irq_work *irq_work) +{ + struct scx_exit_info *ei = scx_exit_info; + + if (ei->kind >= SCX_EXIT_ERROR) + scx_dump_state(ei, scx_ops.exit_dump_len); + + schedule_scx_ops_disable_work(); +} + +static DEFINE_IRQ_WORK(scx_ops_error_irq_work, scx_ops_error_irq_workfn); + +static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind, + s64 exit_code, + const char *fmt, ...) +{ + struct scx_exit_info *ei = scx_exit_info; + int none = SCX_EXIT_NONE; + va_list args; + + if (!atomic_try_cmpxchg(&scx_exit_kind, &none, kind)) + return; + + ei->exit_code = exit_code; +#ifdef CONFIG_STACKTRACE + if (kind >= SCX_EXIT_ERROR) + ei->bt_len = stack_trace_save(ei->bt, SCX_EXIT_BT_LEN, 1); +#endif + va_start(args, fmt); + vscnprintf(ei->msg, SCX_EXIT_MSG_LEN, fmt, args); + va_end(args); + + /* + * Set ei->kind and ->reason for scx_dump_state(). They'll be set again + * in scx_ops_disable_workfn(). + */ + ei->kind = kind; + ei->reason = scx_exit_reason(ei->kind); + + irq_work_queue(&scx_ops_error_irq_work); +} + +static struct kthread_worker *scx_create_rt_helper(const char *name) +{ + struct kthread_worker *helper; + + helper = kthread_create_worker(0, name); + if (helper) + sched_set_fifo(helper->task); + return helper; +} + +static void check_hotplug_seq(const struct sched_ext_ops *ops) +{ + unsigned long long global_hotplug_seq; + + /* + * If a hotplug event has occurred between when a scheduler was + * initialized, and when we were able to attach, exit and notify user + * space about it. + */ + if (ops->hotplug_seq) { + global_hotplug_seq = atomic_long_read(&scx_hotplug_seq); + if (ops->hotplug_seq != global_hotplug_seq) { + scx_ops_exit(SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG, + "expected hotplug seq %llu did not match actual %llu", + ops->hotplug_seq, global_hotplug_seq); + } + } +} + +static int validate_ops(const struct sched_ext_ops *ops) +{ + /* + * It doesn't make sense to specify the SCX_OPS_ENQ_LAST flag if the + * ops.enqueue() callback isn't implemented. + */ + if ((ops->flags & SCX_OPS_ENQ_LAST) && !ops->enqueue) { + scx_ops_error("SCX_OPS_ENQ_LAST requires ops.enqueue() to be implemented"); + return -EINVAL; + } + + return 0; +} + +static int scx_ops_enable(struct sched_ext_ops *ops) +{ + struct scx_task_iter sti; + struct task_struct *p; + unsigned long timeout; + int i, cpu, node, ret; + + if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN), + cpu_possible_mask)) { + pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n"); + return -EINVAL; + } + + mutex_lock(&scx_ops_enable_mutex); + + if (!scx_ops_helper) { + WRITE_ONCE(scx_ops_helper, + scx_create_rt_helper("sched_ext_ops_helper")); + if (!scx_ops_helper) { + ret = -ENOMEM; + goto err_unlock; + } + } + + if (!global_dsqs) { + struct scx_dispatch_q **dsqs; + + dsqs = kcalloc(nr_node_ids, sizeof(dsqs[0]), GFP_KERNEL); + if (!dsqs) { + ret = -ENOMEM; + goto err_unlock; + } + + for_each_node_state(node, N_POSSIBLE) { + struct scx_dispatch_q *dsq; + + dsq = kzalloc_node(sizeof(*dsq), GFP_KERNEL, node); + if (!dsq) { + for_each_node_state(node, N_POSSIBLE) + kfree(dsqs[node]); + kfree(dsqs); + ret = -ENOMEM; + goto err_unlock; + } + + init_dsq(dsq, SCX_DSQ_GLOBAL); + dsqs[node] = dsq; + } + + global_dsqs = dsqs; + } + + if (scx_ops_enable_state() != SCX_OPS_DISABLED) { + ret = -EBUSY; + goto err_unlock; + } + + scx_root_kobj = kzalloc(sizeof(*scx_root_kobj), GFP_KERNEL); + if (!scx_root_kobj) { + ret = -ENOMEM; + goto err_unlock; + } + + scx_root_kobj->kset = scx_kset; + ret = kobject_init_and_add(scx_root_kobj, &scx_ktype, NULL, "root"); + if (ret < 0) + goto err; + + scx_exit_info = alloc_exit_info(ops->exit_dump_len); + if (!scx_exit_info) { + ret = -ENOMEM; + goto err_del; + } + + /* + * Set scx_ops, transition to ENABLING and clear exit info to arm the + * disable path. Failure triggers full disabling from here on. + */ + scx_ops = *ops; + + WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_ENABLING) != + SCX_OPS_DISABLED); + + atomic_set(&scx_exit_kind, SCX_EXIT_NONE); + scx_warned_zero_slice = false; + + atomic_long_set(&scx_nr_rejected, 0); + + for_each_possible_cpu(cpu) + cpu_rq(cpu)->scx.cpuperf_target = SCX_CPUPERF_ONE; + + /* + * Keep CPUs stable during enable so that the BPF scheduler can track + * online CPUs by watching ->on/offline_cpu() after ->init(). + */ + cpus_read_lock(); + + if (scx_ops.init) { + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init, NULL); + if (ret) { + ret = ops_sanitize_err("init", ret); + cpus_read_unlock(); + scx_ops_error("ops.init() failed (%d)", ret); + goto err_disable; + } + } + + for (i = SCX_OPI_CPU_HOTPLUG_BEGIN; i < SCX_OPI_CPU_HOTPLUG_END; i++) + if (((void (**)(void))ops)[i]) + static_branch_enable_cpuslocked(&scx_has_op[i]); + + check_hotplug_seq(ops); + scx_idle_update_selcpu_topology(); + + cpus_read_unlock(); + + ret = validate_ops(ops); + if (ret) + goto err_disable; + + WARN_ON_ONCE(scx_dsp_ctx); + scx_dsp_max_batch = ops->dispatch_max_batch ?: SCX_DSP_DFL_MAX_BATCH; + scx_dsp_ctx = __alloc_percpu(struct_size_t(struct scx_dsp_ctx, buf, + scx_dsp_max_batch), + __alignof__(struct scx_dsp_ctx)); + if (!scx_dsp_ctx) { + ret = -ENOMEM; + goto err_disable; + } + + if (ops->timeout_ms) + timeout = msecs_to_jiffies(ops->timeout_ms); + else + timeout = SCX_WATCHDOG_MAX_TIMEOUT; + + WRITE_ONCE(scx_watchdog_timeout, timeout); + WRITE_ONCE(scx_watchdog_timestamp, jiffies); + queue_delayed_work(system_unbound_wq, &scx_watchdog_work, + scx_watchdog_timeout / 2); + + /* + * Once __scx_ops_enabled is set, %current can be switched to SCX + * anytime. This can lead to stalls as some BPF schedulers (e.g. + * userspace scheduling) may not function correctly before all tasks are + * switched. Init in bypass mode to guarantee forward progress. + */ + scx_ops_bypass(true); + + for (i = SCX_OPI_NORMAL_BEGIN; i < SCX_OPI_NORMAL_END; i++) + if (((void (**)(void))ops)[i]) + static_branch_enable(&scx_has_op[i]); + + if (ops->flags & SCX_OPS_ALLOW_QUEUED_WAKEUP) + static_branch_enable(&scx_ops_allow_queued_wakeup); + if (ops->flags & SCX_OPS_ENQ_LAST) + static_branch_enable(&scx_ops_enq_last); + if (ops->flags & SCX_OPS_ENQ_EXITING) + static_branch_enable(&scx_ops_enq_exiting); + if (ops->flags & SCX_OPS_ENQ_MIGRATION_DISABLED) + static_branch_enable(&scx_ops_enq_migration_disabled); + if (scx_ops.cpu_acquire || scx_ops.cpu_release) + static_branch_enable(&scx_ops_cpu_preempt); + + if (!ops->update_idle || (ops->flags & SCX_OPS_KEEP_BUILTIN_IDLE)) { + scx_idle_reset_masks(); + static_branch_enable(&scx_builtin_idle_enabled); + } else { + static_branch_disable(&scx_builtin_idle_enabled); + } + + /* + * Lock out forks, cgroup on/offlining and moves before opening the + * floodgate so that they don't wander into the operations prematurely. + */ + percpu_down_write(&scx_fork_rwsem); + + WARN_ON_ONCE(scx_ops_init_task_enabled); + scx_ops_init_task_enabled = true; + + /* + * Enable ops for every task. Fork is excluded by scx_fork_rwsem + * preventing new tasks from being added. No need to exclude tasks + * leaving as sched_ext_free() can handle both prepped and enabled + * tasks. Prep all tasks first and then enable them with preemption + * disabled. + * + * All cgroups should be initialized before scx_ops_init_task() so that + * the BPF scheduler can reliably track each task's cgroup membership + * from scx_ops_init_task(). Lock out cgroup on/offlining and task + * migrations while tasks are being initialized so that + * scx_cgroup_can_attach() never sees uninitialized tasks. + */ + scx_cgroup_lock(); + ret = scx_cgroup_init(); + if (ret) + goto err_disable_unlock_all; + + scx_task_iter_start(&sti); + while ((p = scx_task_iter_next_locked(&sti))) { + /* + * @p may already be dead, have lost all its usages counts and + * be waiting for RCU grace period before being freed. @p can't + * be initialized for SCX in such cases and should be ignored. + */ + if (!tryget_task_struct(p)) + continue; + + scx_task_iter_unlock(&sti); + + ret = scx_ops_init_task(p, task_group(p), false); + if (ret) { + put_task_struct(p); + scx_task_iter_relock(&sti); + scx_task_iter_stop(&sti); + scx_ops_error("ops.init_task() failed (%d) for %s[%d]", + ret, p->comm, p->pid); + goto err_disable_unlock_all; + } + + scx_set_task_state(p, SCX_TASK_READY); + + put_task_struct(p); + scx_task_iter_relock(&sti); + } + scx_task_iter_stop(&sti); + scx_cgroup_unlock(); + percpu_up_write(&scx_fork_rwsem); + + /* + * All tasks are READY. It's safe to turn on scx_enabled() and switch + * all eligible tasks. + */ + WRITE_ONCE(scx_switching_all, !(ops->flags & SCX_OPS_SWITCH_PARTIAL)); + static_branch_enable(&__scx_ops_enabled); + + /* + * We're fully committed and can't fail. The task READY -> ENABLED + * transitions here are synchronized against sched_ext_free() through + * scx_tasks_lock. + */ + percpu_down_write(&scx_fork_rwsem); + scx_task_iter_start(&sti); + while ((p = scx_task_iter_next_locked(&sti))) { + const struct sched_class *old_class = p->sched_class; + struct sched_enq_and_set_ctx ctx; + + if (!tryget_task_struct(p)) + continue; + + sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx); + + p->scx.slice = SCX_SLICE_DFL; + + /* + * pick from mainline + * 98442f0ccd82 ("sched: Fix delayed_dequeue vs switched_from_fair()") + * 5db91545ef81 ("sched: Pass correct scheduling policy to + * __setscheduler_class") + */ + p->sched_class = __setscheduler_class(p->policy, p->prio); + check_class_changing(task_rq(p), p, old_class); + + sched_enq_and_set_task(&ctx); + + check_class_changed(task_rq(p), p, old_class, p->prio); + put_task_struct(p); + } + scx_task_iter_stop(&sti); + percpu_up_write(&scx_fork_rwsem); + + scx_ops_bypass(false); + + if (!scx_ops_tryset_enable_state(SCX_OPS_ENABLED, SCX_OPS_ENABLING)) { + WARN_ON_ONCE(atomic_read(&scx_exit_kind) == SCX_EXIT_NONE); + goto err_disable; + } + + if (!(ops->flags & SCX_OPS_SWITCH_PARTIAL)) + static_branch_enable(&__scx_switched_all); + + pr_info("sched_ext: BPF scheduler \"%s\" enabled%s\n", + scx_ops.name, scx_switched_all() ? "" : " (partial)"); + kobject_uevent(scx_root_kobj, KOBJ_ADD); + mutex_unlock(&scx_ops_enable_mutex); + + atomic_long_inc(&scx_enable_seq); + + return 0; + +err_del: + kobject_del(scx_root_kobj); +err: + kobject_put(scx_root_kobj); + scx_root_kobj = NULL; + if (scx_exit_info) { + free_exit_info(scx_exit_info); + scx_exit_info = NULL; + } +err_unlock: + mutex_unlock(&scx_ops_enable_mutex); + return ret; + +err_disable_unlock_all: + scx_cgroup_unlock(); + percpu_up_write(&scx_fork_rwsem); + scx_ops_bypass(false); +err_disable: + mutex_unlock(&scx_ops_enable_mutex); + /* + * Returning an error code here would not pass all the error information + * to userspace. Record errno using scx_ops_error() for cases + * scx_ops_error() wasn't already invoked and exit indicating success so + * that the error is notified through ops.exit() with all the details. + * + * Flush scx_ops_disable_work to ensure that error is reported before + * init completion. + */ + scx_ops_error("scx_ops_enable() failed (%d)", ret); + kthread_flush_work(&scx_ops_disable_work); + return 0; +} + + +/******************************************************************************** + * bpf_struct_ops plumbing. + */ +#include +#include +#include + +static const struct btf_type *task_struct_type; + +static bool bpf_scx_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (type != BPF_READ) + return false; + if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) + return false; + if (off % size != 0) + return false; + + return btf_ctx_access(off, size, type, prog, info); +} + +static int bpf_scx_btf_struct_access(struct bpf_verifier_log *log, + const struct bpf_reg_state *reg, int off, + int size) +{ + const struct btf_type *t; + + t = btf_type_by_id(reg->btf, reg->btf_id); + if (t == task_struct_type) { + if (off >= offsetof(struct task_struct, scx.slice) && + off + size <= offsetofend(struct task_struct, scx.slice)) + return SCALAR_VALUE; + if (off >= offsetof(struct task_struct, scx.dsq_vtime) && + off + size <= offsetofend(struct task_struct, scx.dsq_vtime)) + return SCALAR_VALUE; + if (off >= offsetof(struct task_struct, scx.disallow) && + off + size <= offsetofend(struct task_struct, scx.disallow)) + return SCALAR_VALUE; + } + + return -EACCES; +} + +static const struct bpf_func_proto * +bpf_scx_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_task_storage_get: + return &bpf_task_storage_get_proto; + case BPF_FUNC_task_storage_delete: + return &bpf_task_storage_delete_proto; + default: + return bpf_base_func_proto(func_id); + } +} + +static const struct bpf_verifier_ops bpf_scx_verifier_ops = { + .get_func_proto = bpf_scx_get_func_proto, + .is_valid_access = bpf_scx_is_valid_access, + .btf_struct_access = bpf_scx_btf_struct_access, +}; + +static int bpf_scx_init_member(const struct btf_type *t, + const struct btf_member *member, + void *kdata, const void *udata) +{ + const struct sched_ext_ops *uops = udata; + struct sched_ext_ops *ops = kdata; + u32 moff = __btf_member_bit_offset(t, member) / 8; + int ret; + + switch (moff) { + case offsetof(struct sched_ext_ops, dispatch_max_batch): + if (*(u32 *)(udata + moff) > INT_MAX) + return -E2BIG; + ops->dispatch_max_batch = *(u32 *)(udata + moff); + return 1; + case offsetof(struct sched_ext_ops, flags): + if (*(u64 *)(udata + moff) & ~SCX_OPS_ALL_FLAGS) + return -EINVAL; + ops->flags = *(u64 *)(udata + moff); + return 1; + case offsetof(struct sched_ext_ops, name): + ret = bpf_obj_name_cpy(ops->name, uops->name, + sizeof(ops->name)); + if (ret < 0) + return ret; + if (ret == 0) + return -EINVAL; + return 1; + case offsetof(struct sched_ext_ops, timeout_ms): + if (msecs_to_jiffies(*(u32 *)(udata + moff)) > + SCX_WATCHDOG_MAX_TIMEOUT) + return -E2BIG; + ops->timeout_ms = *(u32 *)(udata + moff); + return 1; + case offsetof(struct sched_ext_ops, exit_dump_len): + ops->exit_dump_len = + *(u32 *)(udata + moff) ?: SCX_EXIT_DUMP_DFL_LEN; + return 1; + case offsetof(struct sched_ext_ops, hotplug_seq): + ops->hotplug_seq = *(u64 *)(udata + moff); + return 1; + } + + return 0; +} + +static int bpf_scx_check_member(const struct btf_type *t, + const struct btf_member *member, + const struct bpf_prog *prog) +{ + u32 moff = __btf_member_bit_offset(t, member) / 8; + + switch (moff) { + case offsetof(struct sched_ext_ops, init_task): +#ifdef CONFIG_EXT_GROUP_SCHED + case offsetof(struct sched_ext_ops, cgroup_init): + case offsetof(struct sched_ext_ops, cgroup_exit): + case offsetof(struct sched_ext_ops, cgroup_prep_move): +#endif + case offsetof(struct sched_ext_ops, cpu_online): + case offsetof(struct sched_ext_ops, cpu_offline): + case offsetof(struct sched_ext_ops, init): + case offsetof(struct sched_ext_ops, exit): + break; + default: + if (prog->aux->sleepable) + return -EINVAL; + } + + return 0; +} + +static int bpf_scx_reg(void *kdata) +{ + return scx_ops_enable(kdata); +} + +static void bpf_scx_unreg(void *kdata) +{ + scx_ops_disable(SCX_EXIT_UNREG); + kthread_flush_work(&scx_ops_disable_work); +} + +static int bpf_scx_init(struct btf *btf) +{ + task_struct_type = btf_type_by_id(btf, btf_tracing_ids[BTF_TRACING_TYPE_TASK]); + + return 0; +} + +static int bpf_scx_update(void *kdata, void *old_kdata) +{ + /* + * sched_ext does not support updating the actively-loaded BPF + * scheduler, as registering a BPF scheduler can always fail if the + * scheduler returns an error code for e.g. ops.init(), ops.init_task(), + * etc. Similarly, we can always race with unregistration happening + * elsewhere, such as with sysrq. + */ + return -EOPNOTSUPP; +} + +static int bpf_scx_validate(void *kdata) +{ + return 0; +} + +static s32 sched_ext_ops__select_cpu(struct task_struct *p, s32 prev_cpu, u64 wake_flags) { return -EINVAL; } +static void sched_ext_ops__enqueue(struct task_struct *p, u64 enq_flags) {} +static void sched_ext_ops__dequeue(struct task_struct *p, u64 enq_flags) {} +static void sched_ext_ops__dispatch(s32 prev_cpu, struct task_struct *prev__nullable) {} +static void sched_ext_ops__tick(struct task_struct *p) {} +static void sched_ext_ops__runnable(struct task_struct *p, u64 enq_flags) {} +static void sched_ext_ops__running(struct task_struct *p) {} +static void sched_ext_ops__stopping(struct task_struct *p, bool runnable) {} +static void sched_ext_ops__quiescent(struct task_struct *p, u64 deq_flags) {} +static bool sched_ext_ops__yield(struct task_struct *from, struct task_struct *to__nullable) { return false; } +static bool sched_ext_ops__core_sched_before(struct task_struct *a, struct task_struct *b) { return false; } +static void sched_ext_ops__set_weight(struct task_struct *p, u32 weight) {} +static void sched_ext_ops__set_cpumask(struct task_struct *p, const struct cpumask *mask) {} +static void sched_ext_ops__update_idle(s32 cpu, bool idle) {} +static void sched_ext_ops__cpu_acquire(s32 cpu, struct scx_cpu_acquire_args *args) {} +static void sched_ext_ops__cpu_release(s32 cpu, struct scx_cpu_release_args *args) {} +static s32 sched_ext_ops__init_task(struct task_struct *p, struct scx_init_task_args *args) { return -EINVAL; } +static void sched_ext_ops__exit_task(struct task_struct *p, struct scx_exit_task_args *args) {} +static void sched_ext_ops__enable(struct task_struct *p) {} +static void sched_ext_ops__disable(struct task_struct *p) {} +#ifdef CONFIG_EXT_GROUP_SCHED +static s32 sched_ext_ops__cgroup_init(struct cgroup *cgrp, struct scx_cgroup_init_args *args) { return -EINVAL; } +static void sched_ext_ops__cgroup_exit(struct cgroup *cgrp) {} +static s32 sched_ext_ops__cgroup_prep_move(struct task_struct *p, struct cgroup *from, struct cgroup *to) { return -EINVAL; } +static void sched_ext_ops__cgroup_move(struct task_struct *p, struct cgroup *from, struct cgroup *to) {} +static void sched_ext_ops__cgroup_cancel_move(struct task_struct *p, struct cgroup *from, struct cgroup *to) {} +static void sched_ext_ops__cgroup_set_weight(struct cgroup *cgrp, u32 weight) {} +#endif +static void sched_ext_ops__cpu_online(s32 cpu) {} +static void sched_ext_ops__cpu_offline(s32 cpu) {} +static s32 sched_ext_ops__init(void) { return -EINVAL; } +static void sched_ext_ops__exit(struct scx_exit_info *info) {} +static void sched_ext_ops__dump(struct scx_dump_ctx *ctx) {} +static void sched_ext_ops__dump_cpu(struct scx_dump_ctx *ctx, s32 cpu, bool idle) {} +static void sched_ext_ops__dump_task(struct scx_dump_ctx *ctx, struct task_struct *p) {} + +static struct sched_ext_ops __bpf_ops_sched_ext_ops = { + .select_cpu = sched_ext_ops__select_cpu, + .enqueue = sched_ext_ops__enqueue, + .dequeue = sched_ext_ops__dequeue, + .dispatch = sched_ext_ops__dispatch, + .tick = sched_ext_ops__tick, + .runnable = sched_ext_ops__runnable, + .running = sched_ext_ops__running, + .stopping = sched_ext_ops__stopping, + .quiescent = sched_ext_ops__quiescent, + .yield = sched_ext_ops__yield, + .core_sched_before = sched_ext_ops__core_sched_before, + .set_weight = sched_ext_ops__set_weight, + .set_cpumask = sched_ext_ops__set_cpumask, + .update_idle = sched_ext_ops__update_idle, + .cpu_acquire = sched_ext_ops__cpu_acquire, + .cpu_release = sched_ext_ops__cpu_release, + .init_task = sched_ext_ops__init_task, + .exit_task = sched_ext_ops__exit_task, + .enable = sched_ext_ops__enable, + .disable = sched_ext_ops__disable, +#ifdef CONFIG_EXT_GROUP_SCHED + .cgroup_init = sched_ext_ops__cgroup_init, + .cgroup_exit = sched_ext_ops__cgroup_exit, + .cgroup_prep_move = sched_ext_ops__cgroup_prep_move, + .cgroup_move = sched_ext_ops__cgroup_move, + .cgroup_cancel_move = sched_ext_ops__cgroup_cancel_move, + .cgroup_set_weight = sched_ext_ops__cgroup_set_weight, +#endif + .cpu_online = sched_ext_ops__cpu_online, + .cpu_offline = sched_ext_ops__cpu_offline, + .init = sched_ext_ops__init, + .exit = sched_ext_ops__exit, + .dump = sched_ext_ops__dump, + .dump_cpu = sched_ext_ops__dump_cpu, + .dump_task = sched_ext_ops__dump_task, +}; + +static struct bpf_struct_ops bpf_sched_ext_ops = { + .verifier_ops = &bpf_scx_verifier_ops, + .reg = bpf_scx_reg, + .unreg = bpf_scx_unreg, + .check_member = bpf_scx_check_member, + .init_member = bpf_scx_init_member, + .init = bpf_scx_init, + .update = bpf_scx_update, + .validate = bpf_scx_validate, + .name = "sched_ext_ops", + .owner = THIS_MODULE, + .cfi_stubs = &__bpf_ops_sched_ext_ops +}; + + +/******************************************************************************** + * System integration and init. + */ + +static void sysrq_handle_sched_ext_reset(u8 key) +{ + if (scx_ops_helper) + scx_ops_disable(SCX_EXIT_SYSRQ); + else + pr_info("sched_ext: BPF scheduler not yet used\n"); +} + +static const struct sysrq_key_op sysrq_sched_ext_reset_op = { + .handler = sysrq_handle_sched_ext_reset, + .help_msg = "reset-sched-ext(S)", + .action_msg = "Disable sched_ext and revert all tasks to CFS", + .enable_mask = SYSRQ_ENABLE_RTNICE, +}; + +static void sysrq_handle_sched_ext_dump(u8 key) +{ + struct scx_exit_info ei = { .kind = SCX_EXIT_NONE, .reason = "SysRq-D" }; + + if (scx_enabled()) + scx_dump_state(&ei, 0); +} + +static const struct sysrq_key_op sysrq_sched_ext_dump_op = { + .handler = sysrq_handle_sched_ext_dump, + .help_msg = "dump-sched-ext(D)", + .action_msg = "Trigger sched_ext debug dump", + .enable_mask = SYSRQ_ENABLE_RTNICE, +}; + +static bool can_skip_idle_kick(struct rq *rq) +{ + lockdep_assert_rq_held(rq); + + /* + * We can skip idle kicking if @rq is going to go through at least one + * full SCX scheduling cycle before going idle. Just checking whether + * curr is not idle is insufficient because we could be racing + * balance_one() trying to pull the next task from a remote rq, which + * may fail, and @rq may become idle afterwards. + * + * The race window is small and we don't and can't guarantee that @rq is + * only kicked while idle anyway. Skip only when sure. + */ + return !is_idle_task(rq->curr) && !(rq->scx.flags & SCX_RQ_IN_BALANCE); +} + +static bool kick_one_cpu(s32 cpu, struct rq *this_rq, unsigned long *pseqs) +{ + struct rq *rq = cpu_rq(cpu); + struct scx_rq *this_scx = &this_rq->scx; + bool should_wait = false; + unsigned long flags; + + raw_spin_rq_lock_irqsave(rq, flags); + + /* + * During CPU hotplug, a CPU may depend on kicking itself to make + * forward progress. Allow kicking self regardless of online state. + */ + if (cpu_online(cpu) || cpu == cpu_of(this_rq)) { + if (cpumask_test_cpu(cpu, this_scx->cpus_to_preempt)) { + if (rq->curr->sched_class == &ext_sched_class) + rq->curr->scx.slice = 0; + cpumask_clear_cpu(cpu, this_scx->cpus_to_preempt); + } + + if (cpumask_test_cpu(cpu, this_scx->cpus_to_wait)) { + pseqs[cpu] = rq->scx.pnt_seq; + should_wait = true; + } + + resched_curr(rq); + } else { + cpumask_clear_cpu(cpu, this_scx->cpus_to_preempt); + cpumask_clear_cpu(cpu, this_scx->cpus_to_wait); + } + + raw_spin_rq_unlock_irqrestore(rq, flags); + + return should_wait; +} + +static void kick_one_cpu_if_idle(s32 cpu, struct rq *this_rq) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + raw_spin_rq_lock_irqsave(rq, flags); + + if (!can_skip_idle_kick(rq) && + (cpu_online(cpu) || cpu == cpu_of(this_rq))) + resched_curr(rq); + + raw_spin_rq_unlock_irqrestore(rq, flags); +} + +static void kick_cpus_irq_workfn(struct irq_work *irq_work) +{ + struct rq *this_rq = this_rq(); + struct scx_rq *this_scx = &this_rq->scx; + unsigned long *pseqs = this_cpu_ptr(scx_kick_cpus_pnt_seqs); + bool should_wait = false; + s32 cpu; + + for_each_cpu(cpu, this_scx->cpus_to_kick) { + should_wait |= kick_one_cpu(cpu, this_rq, pseqs); + cpumask_clear_cpu(cpu, this_scx->cpus_to_kick); + cpumask_clear_cpu(cpu, this_scx->cpus_to_kick_if_idle); + } + + for_each_cpu(cpu, this_scx->cpus_to_kick_if_idle) { + kick_one_cpu_if_idle(cpu, this_rq); + cpumask_clear_cpu(cpu, this_scx->cpus_to_kick_if_idle); + } + + if (!should_wait) + return; + + for_each_cpu(cpu, this_scx->cpus_to_wait) { + unsigned long *wait_pnt_seq = &cpu_rq(cpu)->scx.pnt_seq; + + if (cpu != cpu_of(this_rq)) { + /* + * Pairs with smp_store_release() issued by this CPU in + * switch_class() on the resched path. + * + * We busy-wait here to guarantee that no other task can + * be scheduled on our core before the target CPU has + * entered the resched path. + */ + while (smp_load_acquire(wait_pnt_seq) == pseqs[cpu]) + cpu_relax(); + } + + cpumask_clear_cpu(cpu, this_scx->cpus_to_wait); + } +} + +/** + * print_scx_info - print out sched_ext scheduler state + * @log_lvl: the log level to use when printing + * @p: target task + * + * If a sched_ext scheduler is enabled, print the name and state of the + * scheduler. If @p is on sched_ext, print further information about the task. + * + * This function can be safely called on any task as long as the task_struct + * itself is accessible. While safe, this function isn't synchronized and may + * print out mixups or garbages of limited length. + */ +void print_scx_info(const char *log_lvl, struct task_struct *p) +{ + enum scx_ops_enable_state state = scx_ops_enable_state(); + const char *all = READ_ONCE(scx_switching_all) ? "+all" : ""; + char runnable_at_buf[22] = "?"; + struct sched_class *class; + unsigned long runnable_at; + + if (state == SCX_OPS_DISABLED) + return; + + /* + * Carefully check if the task was running on sched_ext, and then + * carefully copy the time it's been runnable, and its state. + */ + if (copy_from_kernel_nofault(&class, &p->sched_class, sizeof(class)) || + class != &ext_sched_class) { + printk("%sSched_ext: %s (%s%s)", log_lvl, scx_ops.name, + scx_ops_enable_state_str[state], all); + return; + } + + if (!copy_from_kernel_nofault(&runnable_at, &p->scx.runnable_at, + sizeof(runnable_at))) + scnprintf(runnable_at_buf, sizeof(runnable_at_buf), "%+ldms", + jiffies_delta_msecs(runnable_at, jiffies)); + + /* print everything onto one line to conserve console space */ + printk("%sSched_ext: %s (%s%s), task: runnable_at=%s", + log_lvl, scx_ops.name, scx_ops_enable_state_str[state], all, + runnable_at_buf); +} + +static int scx_pm_handler(struct notifier_block *nb, unsigned long event, void *ptr) +{ + /* + * SCX schedulers often have userspace components which are sometimes + * involved in critial scheduling paths. PM operations involve freezing + * userspace which can lead to scheduling misbehaviors including stalls. + * Let's bypass while PM operations are in progress. + */ + switch (event) { + case PM_HIBERNATION_PREPARE: + case PM_SUSPEND_PREPARE: + case PM_RESTORE_PREPARE: + scx_ops_bypass(true); + break; + case PM_POST_HIBERNATION: + case PM_POST_SUSPEND: + case PM_POST_RESTORE: + scx_ops_bypass(false); + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block scx_pm_notifier = { + .notifier_call = scx_pm_handler, +}; + +void __init init_sched_ext_class(void) +{ + s32 cpu, v; + + /* + * The following is to prevent the compiler from optimizing out the enum + * definitions so that BPF scheduler implementations can use them + * through the generated vmlinux.h. + */ + WRITE_ONCE(v, SCX_ENQ_WAKEUP | SCX_DEQ_SLEEP | SCX_KICK_PREEMPT | + SCX_TG_ONLINE); + + BUG_ON(rhashtable_init(&dsq_hash, &dsq_hash_params)); + scx_idle_init_masks(); + + scx_kick_cpus_pnt_seqs = + __alloc_percpu(sizeof(scx_kick_cpus_pnt_seqs[0]) * nr_cpu_ids, + __alignof__(scx_kick_cpus_pnt_seqs[0])); + BUG_ON(!scx_kick_cpus_pnt_seqs); + + for_each_possible_cpu(cpu) { + struct rq *rq = cpu_rq(cpu); + + init_dsq(&rq->scx.local_dsq, SCX_DSQ_LOCAL); + INIT_LIST_HEAD(&rq->scx.runnable_list); + INIT_LIST_HEAD(&rq->scx.ddsp_deferred_locals); + + BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_kick, GFP_KERNEL)); + BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_kick_if_idle, GFP_KERNEL)); + BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_preempt, GFP_KERNEL)); + BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_wait, GFP_KERNEL)); + init_irq_work(&rq->scx.deferred_irq_work, deferred_irq_workfn); + init_irq_work(&rq->scx.kick_cpus_irq_work, kick_cpus_irq_workfn); + + if (cpu_online(cpu)) + cpu_rq(cpu)->scx.flags |= SCX_RQ_ONLINE; + } + + register_sysrq_key('S', &sysrq_sched_ext_reset_op); + register_sysrq_key('D', &sysrq_sched_ext_dump_op); + INIT_DELAYED_WORK(&scx_watchdog_work, scx_watchdog_workfn); +} + + +/******************************************************************************** + * Helpers that can be called from the BPF scheduler. + */ +static bool scx_dsq_insert_preamble(struct task_struct *p, u64 enq_flags) +{ + if (!scx_kf_allowed(SCX_KF_ENQUEUE | SCX_KF_DISPATCH)) + return false; + + lockdep_assert_irqs_disabled(); + + if (unlikely(!p)) { + scx_ops_error("called with NULL task"); + return false; + } + + if (unlikely(enq_flags & __SCX_ENQ_INTERNAL_MASK)) { + scx_ops_error("invalid enq_flags 0x%llx", enq_flags); + return false; + } + + return true; +} + +static void scx_dsq_insert_commit(struct task_struct *p, u64 dsq_id, + u64 enq_flags) +{ + struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx); + struct task_struct *ddsp_task; + + ddsp_task = __this_cpu_read(direct_dispatch_task); + if (ddsp_task) { + mark_direct_dispatch(ddsp_task, p, dsq_id, enq_flags); + return; + } + + if (unlikely(dspc->cursor >= scx_dsp_max_batch)) { + scx_ops_error("dispatch buffer overflow"); + return; + } + + dspc->buf[dspc->cursor++] = (struct scx_dsp_buf_ent){ + .task = p, + .qseq = atomic_long_read(&p->scx.ops_state) & SCX_OPSS_QSEQ_MASK, + .dsq_id = dsq_id, + .enq_flags = enq_flags, + }; +} + +__bpf_kfunc_start_defs(); + +/** + * scx_bpf_dsq_insert - Insert a task into the FIFO queue of a DSQ + * @p: task_struct to insert + * @dsq_id: DSQ to insert into + * @slice: duration @p can run for in nsecs, 0 to keep the current value + * @enq_flags: SCX_ENQ_* + * + * Insert @p into the FIFO queue of the DSQ identified by @dsq_id. It is safe to + * call this function spuriously. Can be called from ops.enqueue(), + * ops.select_cpu(), and ops.dispatch(). + * + * When called from ops.select_cpu() or ops.enqueue(), it's for direct dispatch + * and @p must match the task being enqueued. + * + * When called from ops.select_cpu(), @enq_flags and @dsp_id are stored, and @p + * will be directly inserted into the corresponding dispatch queue after + * ops.select_cpu() returns. If @p is inserted into SCX_DSQ_LOCAL, it will be + * inserted into the local DSQ of the CPU returned by ops.select_cpu(). + * @enq_flags are OR'd with the enqueue flags on the enqueue path before the + * task is inserted. + * + * When called from ops.dispatch(), there are no restrictions on @p or @dsq_id + * and this function can be called upto ops.dispatch_max_batch times to insert + * multiple tasks. scx_bpf_dispatch_nr_slots() returns the number of the + * remaining slots. scx_bpf_consume() flushes the batch and resets the counter. + * + * This function doesn't have any locking restrictions and may be called under + * BPF locks (in the future when BPF introduces more flexible locking). + * + * @p is allowed to run for @slice. The scheduling path is triggered on slice + * exhaustion. If zero, the current residual slice is maintained. If + * %SCX_SLICE_INF, @p never expires and the BPF scheduler must kick the CPU with + * scx_bpf_kick_cpu() to trigger scheduling. + */ +__bpf_kfunc void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id, u64 slice, + u64 enq_flags) +{ + if (!scx_dsq_insert_preamble(p, enq_flags)) + return; + + if (slice) + p->scx.slice = slice; + else + p->scx.slice = p->scx.slice ?: 1; + + scx_dsq_insert_commit(p, dsq_id, enq_flags); +} + +/* for backward compatibility, will be removed in v6.15 */ +__bpf_kfunc void scx_bpf_dispatch(struct task_struct *p, u64 dsq_id, u64 slice, + u64 enq_flags) +{ + printk_deferred_once(KERN_WARNING "sched_ext: scx_bpf_dispatch() renamed to scx_bpf_dsq_insert()"); + scx_bpf_dsq_insert(p, dsq_id, slice, enq_flags); +} + +/** + * scx_bpf_dsq_insert_vtime - Insert a task into the vtime priority queue of a DSQ + * @p: task_struct to insert + * @dsq_id: DSQ to insert into + * @slice: duration @p can run for in nsecs, 0 to keep the current value + * @vtime: @p's ordering inside the vtime-sorted queue of the target DSQ + * @enq_flags: SCX_ENQ_* + * + * Insert @p into the vtime priority queue of the DSQ identified by @dsq_id. + * Tasks queued into the priority queue are ordered by @vtime. All other aspects + * are identical to scx_bpf_dsq_insert(). + * + * @vtime ordering is according to time_before64() which considers wrapping. A + * numerically larger vtime may indicate an earlier position in the ordering and + * vice-versa. + * + * A DSQ can only be used as a FIFO or priority queue at any given time and this + * function must not be called on a DSQ which already has one or more FIFO tasks + * queued and vice-versa. Also, the built-in DSQs (SCX_DSQ_LOCAL and + * SCX_DSQ_GLOBAL) cannot be used as priority queues. + */ +__bpf_kfunc void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id, + u64 slice, u64 vtime, u64 enq_flags) +{ + if (!scx_dsq_insert_preamble(p, enq_flags)) + return; + + if (slice) + p->scx.slice = slice; + else + p->scx.slice = p->scx.slice ?: 1; + + p->scx.dsq_vtime = vtime; + + scx_dsq_insert_commit(p, dsq_id, enq_flags | SCX_ENQ_DSQ_PRIQ); +} + +/* for backward compatibility, will be removed in v6.15 */ +__bpf_kfunc void scx_bpf_dispatch_vtime(struct task_struct *p, u64 dsq_id, + u64 slice, u64 vtime, u64 enq_flags) +{ + printk_deferred_once(KERN_WARNING "sched_ext: scx_bpf_dispatch_vtime() renamed to scx_bpf_dsq_insert_vtime()"); + scx_bpf_dsq_insert_vtime(p, dsq_id, slice, vtime, enq_flags); +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(scx_kfunc_ids_enqueue_dispatch) +BTF_ID_FLAGS(func, scx_bpf_dsq_insert, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_dsq_insert_vtime, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_dispatch, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_dispatch_vtime, KF_RCU) +BTF_KFUNCS_END(scx_kfunc_ids_enqueue_dispatch) + +static const struct btf_kfunc_id_set scx_kfunc_set_enqueue_dispatch = { + .owner = THIS_MODULE, + .set = &scx_kfunc_ids_enqueue_dispatch, +}; + +static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit, + struct task_struct *p, u64 dsq_id, u64 enq_flags) +{ + struct scx_dispatch_q *src_dsq = kit->dsq, *dst_dsq; + struct rq *this_rq, *src_rq, *locked_rq; + bool dispatched = false; + bool in_balance; + unsigned long flags; + + if (!scx_kf_allowed_if_unlocked() && !scx_kf_allowed(SCX_KF_DISPATCH)) + return false; + + /* + * Can be called from either ops.dispatch() locking this_rq() or any + * context where no rq lock is held. If latter, lock @p's task_rq which + * we'll likely need anyway. + */ + src_rq = task_rq(p); + + local_irq_save(flags); + this_rq = this_rq(); + in_balance = this_rq->scx.flags & SCX_RQ_IN_BALANCE; + + if (in_balance) { + if (this_rq != src_rq) { + raw_spin_rq_unlock(this_rq); + raw_spin_rq_lock(src_rq); + } + } else { + raw_spin_rq_lock(src_rq); + } + + /* + * If the BPF scheduler keeps calling this function repeatedly, it can + * cause similar live-lock conditions as consume_dispatch_q(). Insert a + * breather if necessary. + */ + scx_ops_breather(src_rq); + + locked_rq = src_rq; + raw_spin_lock(&src_dsq->lock); + + /* + * Did someone else get to it? @p could have already left $src_dsq, got + * re-enqueud, or be in the process of being consumed by someone else. + */ + if (unlikely(p->scx.dsq != src_dsq || + u32_before(kit->cursor.priv, p->scx.dsq_seq) || + p->scx.holding_cpu >= 0) || + WARN_ON_ONCE(src_rq != task_rq(p))) { + raw_spin_unlock(&src_dsq->lock); + goto out; + } + + /* @p is still on $src_dsq and stable, determine the destination */ + dst_dsq = find_dsq_for_dispatch(this_rq, dsq_id, p); + + /* + * Apply vtime and slice updates before moving so that the new time is + * visible before inserting into $dst_dsq. @p is still on $src_dsq but + * this is safe as we're locking it. + */ + if (kit->cursor.flags & __SCX_DSQ_ITER_HAS_VTIME) + p->scx.dsq_vtime = kit->vtime; + if (kit->cursor.flags & __SCX_DSQ_ITER_HAS_SLICE) + p->scx.slice = kit->slice; + + /* execute move */ + locked_rq = move_task_between_dsqs(p, enq_flags, src_dsq, dst_dsq); + dispatched = true; +out: + if (in_balance) { + if (this_rq != locked_rq) { + raw_spin_rq_unlock(locked_rq); + raw_spin_rq_lock(this_rq); + } + } else { + raw_spin_rq_unlock_irqrestore(locked_rq, flags); + } + + kit->cursor.flags &= ~(__SCX_DSQ_ITER_HAS_SLICE | + __SCX_DSQ_ITER_HAS_VTIME); + return dispatched; +} + +__bpf_kfunc_start_defs(); + +/** + * scx_bpf_dispatch_nr_slots - Return the number of remaining dispatch slots + * + * Can only be called from ops.dispatch(). + */ +__bpf_kfunc u32 scx_bpf_dispatch_nr_slots(void) +{ + if (!scx_kf_allowed(SCX_KF_DISPATCH)) + return 0; + + return scx_dsp_max_batch - __this_cpu_read(scx_dsp_ctx->cursor); +} + +/** + * scx_bpf_dispatch_cancel - Cancel the latest dispatch + * + * Cancel the latest dispatch. Can be called multiple times to cancel further + * dispatches. Can only be called from ops.dispatch(). + */ +__bpf_kfunc void scx_bpf_dispatch_cancel(void) +{ + struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx); + + if (!scx_kf_allowed(SCX_KF_DISPATCH)) + return; + + if (dspc->cursor > 0) + dspc->cursor--; + else + scx_ops_error("dispatch buffer underflow"); +} + +/** + * scx_bpf_dsq_move_to_local - move a task from a DSQ to the current CPU's local DSQ + * @dsq_id: DSQ to move task from + * + * Move a task from the non-local DSQ identified by @dsq_id to the current CPU's + * local DSQ for execution. Can only be called from ops.dispatch(). + * + * This function flushes the in-flight dispatches from scx_bpf_dsq_insert() + * before trying to move from the specified DSQ. It may also grab rq locks and + * thus can't be called under any BPF locks. + * + * Returns %true if a task has been moved, %false if there isn't any task to + * move. + */ +__bpf_kfunc bool scx_bpf_dsq_move_to_local(u64 dsq_id) +{ + struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx); + struct scx_dispatch_q *dsq; + + if (!scx_kf_allowed(SCX_KF_DISPATCH)) + return false; + + flush_dispatch_buf(dspc->rq); + + dsq = find_user_dsq(dsq_id); + if (unlikely(!dsq)) { + scx_ops_error("invalid DSQ ID 0x%016llx", dsq_id); + return false; + } + + if (consume_dispatch_q(dspc->rq, dsq)) { + /* + * A successfully consumed task can be dequeued before it starts + * running while the CPU is trying to migrate other dispatched + * tasks. Bump nr_tasks to tell balance_scx() to retry on empty + * local DSQ. + */ + dspc->nr_tasks++; + return true; + } else { + return false; + } +} + +/* for backward compatibility, will be removed in v6.15 */ +__bpf_kfunc bool scx_bpf_consume(u64 dsq_id) +{ + printk_deferred_once(KERN_WARNING "sched_ext: scx_bpf_consume() renamed to scx_bpf_dsq_move_to_local()"); + return scx_bpf_dsq_move_to_local(dsq_id); +} + +/** + * scx_bpf_dsq_move_set_slice - Override slice when moving between DSQs + * @it__iter: DSQ iterator in progress + * @slice: duration the moved task can run for in nsecs + * + * Override the slice of the next task that will be moved from @it__iter using + * scx_bpf_dsq_move[_vtime](). If this function is not called, the previous + * slice duration is kept. + */ +__bpf_kfunc void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, + u64 slice) +{ + struct bpf_iter_scx_dsq_kern *kit = (void *)it__iter; + + kit->slice = slice; + kit->cursor.flags |= __SCX_DSQ_ITER_HAS_SLICE; +} + +/* for backward compatibility, will be removed in v6.15 */ +__bpf_kfunc void scx_bpf_dispatch_from_dsq_set_slice( + struct bpf_iter_scx_dsq *it__iter, u64 slice) +{ + printk_deferred_once(KERN_WARNING "sched_ext: scx_bpf_dispatch_from_dsq_set_slice() renamed to scx_bpf_dsq_move_set_slice()"); + scx_bpf_dsq_move_set_slice(it__iter, slice); +} + +/** + * scx_bpf_dsq_move_set_vtime - Override vtime when moving between DSQs + * @it__iter: DSQ iterator in progress + * @vtime: task's ordering inside the vtime-sorted queue of the target DSQ + * + * Override the vtime of the next task that will be moved from @it__iter using + * scx_bpf_dsq_move_vtime(). If this function is not called, the previous slice + * vtime is kept. If scx_bpf_dsq_move() is used to dispatch the next task, the + * override is ignored and cleared. + */ +__bpf_kfunc void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, + u64 vtime) +{ + struct bpf_iter_scx_dsq_kern *kit = (void *)it__iter; + + kit->vtime = vtime; + kit->cursor.flags |= __SCX_DSQ_ITER_HAS_VTIME; +} + +/* for backward compatibility, will be removed in v6.15 */ +__bpf_kfunc void scx_bpf_dispatch_from_dsq_set_vtime( + struct bpf_iter_scx_dsq *it__iter, u64 vtime) +{ + printk_deferred_once(KERN_WARNING "sched_ext: scx_bpf_dispatch_from_dsq_set_vtime() renamed to scx_bpf_dsq_move_set_vtime()"); + scx_bpf_dsq_move_set_vtime(it__iter, vtime); +} + +/** + * scx_bpf_dsq_move - Move a task from DSQ iteration to a DSQ + * @it__iter: DSQ iterator in progress + * @p: task to transfer + * @dsq_id: DSQ to move @p to + * @enq_flags: SCX_ENQ_* + * + * Transfer @p which is on the DSQ currently iterated by @it__iter to the DSQ + * specified by @dsq_id. All DSQs - local DSQs, global DSQ and user DSQs - can + * be the destination. + * + * For the transfer to be successful, @p must still be on the DSQ and have been + * queued before the DSQ iteration started. This function doesn't care whether + * @p was obtained from the DSQ iteration. @p just has to be on the DSQ and have + * been queued before the iteration started. + * + * @p's slice is kept by default. Use scx_bpf_dsq_move_set_slice() to update. + * + * Can be called from ops.dispatch() or any BPF context which doesn't hold a rq + * lock (e.g. BPF timers or SYSCALL programs). + * + * Returns %true if @p has been consumed, %false if @p had already been consumed + * or dequeued. + */ +__bpf_kfunc bool scx_bpf_dsq_move(struct bpf_iter_scx_dsq *it__iter, + struct task_struct *p, u64 dsq_id, + u64 enq_flags) +{ + return scx_dsq_move((struct bpf_iter_scx_dsq_kern *)it__iter, + p, dsq_id, enq_flags); +} + +/* for backward compatibility, will be removed in v6.15 */ +__bpf_kfunc bool scx_bpf_dispatch_from_dsq(struct bpf_iter_scx_dsq *it__iter, + struct task_struct *p, u64 dsq_id, + u64 enq_flags) +{ + printk_deferred_once(KERN_WARNING "sched_ext: scx_bpf_dispatch_from_dsq() renamed to scx_bpf_dsq_move()"); + return scx_bpf_dsq_move(it__iter, p, dsq_id, enq_flags); +} + +/** + * scx_bpf_dsq_move_vtime - Move a task from DSQ iteration to a PRIQ DSQ + * @it__iter: DSQ iterator in progress + * @p: task to transfer + * @dsq_id: DSQ to move @p to + * @enq_flags: SCX_ENQ_* + * + * Transfer @p which is on the DSQ currently iterated by @it__iter to the + * priority queue of the DSQ specified by @dsq_id. The destination must be a + * user DSQ as only user DSQs support priority queue. + * + * @p's slice and vtime are kept by default. Use scx_bpf_dsq_move_set_slice() + * and scx_bpf_dsq_move_set_vtime() to update. + * + * All other aspects are identical to scx_bpf_dsq_move(). See + * scx_bpf_dsq_insert_vtime() for more information on @vtime. + */ +__bpf_kfunc bool scx_bpf_dsq_move_vtime(struct bpf_iter_scx_dsq *it__iter, + struct task_struct *p, u64 dsq_id, + u64 enq_flags) +{ + return scx_dsq_move((struct bpf_iter_scx_dsq_kern *)it__iter, + p, dsq_id, enq_flags | SCX_ENQ_DSQ_PRIQ); +} + +/* for backward compatibility, will be removed in v6.15 */ +__bpf_kfunc bool scx_bpf_dispatch_vtime_from_dsq(struct bpf_iter_scx_dsq *it__iter, + struct task_struct *p, u64 dsq_id, + u64 enq_flags) +{ + printk_deferred_once(KERN_WARNING "sched_ext: scx_bpf_dispatch_from_dsq_vtime() renamed to scx_bpf_dsq_move_vtime()"); + return scx_bpf_dsq_move_vtime(it__iter, p, dsq_id, enq_flags); +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(scx_kfunc_ids_dispatch) +BTF_ID_FLAGS(func, scx_bpf_dispatch_nr_slots) +BTF_ID_FLAGS(func, scx_bpf_dispatch_cancel) +BTF_ID_FLAGS(func, scx_bpf_dsq_move_to_local) +BTF_ID_FLAGS(func, scx_bpf_consume) +BTF_ID_FLAGS(func, scx_bpf_dsq_move_set_slice) +BTF_ID_FLAGS(func, scx_bpf_dsq_move_set_vtime) +BTF_ID_FLAGS(func, scx_bpf_dsq_move, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_dsq_move_vtime, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq_set_slice) +BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq_set_vtime) +BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_dispatch_vtime_from_dsq, KF_RCU) +BTF_KFUNCS_END(scx_kfunc_ids_dispatch) + +static const struct btf_kfunc_id_set scx_kfunc_set_dispatch = { + .owner = THIS_MODULE, + .set = &scx_kfunc_ids_dispatch, +}; + +__bpf_kfunc_start_defs(); + +/** + * scx_bpf_reenqueue_local - Re-enqueue tasks on a local DSQ + * + * Iterate over all of the tasks currently enqueued on the local DSQ of the + * caller's CPU, and re-enqueue them in the BPF scheduler. Returns the number of + * processed tasks. Can only be called from ops.cpu_release(). + */ +__bpf_kfunc u32 scx_bpf_reenqueue_local(void) +{ + LIST_HEAD(tasks); + u32 nr_enqueued = 0; + struct rq *rq; + struct task_struct *p, *n; + + if (!scx_kf_allowed(SCX_KF_CPU_RELEASE)) + return 0; + + rq = cpu_rq(smp_processor_id()); + lockdep_assert_rq_held(rq); + + /* + * The BPF scheduler may choose to dispatch tasks back to + * @rq->scx.local_dsq. Move all candidate tasks off to a private list + * first to avoid processing the same tasks repeatedly. + */ + list_for_each_entry_safe(p, n, &rq->scx.local_dsq.list, + scx.dsq_list.node) { + /* + * If @p is being migrated, @p's current CPU may not agree with + * its allowed CPUs and the migration_cpu_stop is about to + * deactivate and re-activate @p anyway. Skip re-enqueueing. + * + * While racing sched property changes may also dequeue and + * re-enqueue a migrating task while its current CPU and allowed + * CPUs disagree, they use %ENQUEUE_RESTORE which is bypassed to + * the current local DSQ for running tasks and thus are not + * visible to the BPF scheduler. + */ + if (p->migration_pending) + continue; + + dispatch_dequeue(rq, p); + list_add_tail(&p->scx.dsq_list.node, &tasks); + } + + list_for_each_entry_safe(p, n, &tasks, scx.dsq_list.node) { + list_del_init(&p->scx.dsq_list.node); + do_enqueue_task(rq, p, SCX_ENQ_REENQ, -1); + nr_enqueued++; + } + + return nr_enqueued; +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(scx_kfunc_ids_cpu_release) +BTF_ID_FLAGS(func, scx_bpf_reenqueue_local) +BTF_KFUNCS_END(scx_kfunc_ids_cpu_release) + +static const struct btf_kfunc_id_set scx_kfunc_set_cpu_release = { + .owner = THIS_MODULE, + .set = &scx_kfunc_ids_cpu_release, +}; + +__bpf_kfunc_start_defs(); + +/** + * scx_bpf_create_dsq - Create a custom DSQ + * @dsq_id: DSQ to create + * @node: NUMA node to allocate from + * + * Create a custom DSQ identified by @dsq_id. Can be called from any sleepable + * scx callback, and any BPF_PROG_TYPE_SYSCALL prog. + */ +__bpf_kfunc s32 scx_bpf_create_dsq(u64 dsq_id, s32 node) +{ + if (unlikely(node >= (int)nr_node_ids || + (node < 0 && node != NUMA_NO_NODE))) + return -EINVAL; + return PTR_ERR_OR_ZERO(create_dsq(dsq_id, node)); +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(scx_kfunc_ids_unlocked) +BTF_ID_FLAGS(func, scx_bpf_create_dsq, KF_SLEEPABLE) +BTF_ID_FLAGS(func, scx_bpf_dsq_move_set_slice) +BTF_ID_FLAGS(func, scx_bpf_dsq_move_set_vtime) +BTF_ID_FLAGS(func, scx_bpf_dsq_move, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_dsq_move_vtime, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq_set_slice) +BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq_set_vtime) +BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_dispatch_vtime_from_dsq, KF_RCU) +BTF_KFUNCS_END(scx_kfunc_ids_unlocked) + +static const struct btf_kfunc_id_set scx_kfunc_set_unlocked = { + .owner = THIS_MODULE, + .set = &scx_kfunc_ids_unlocked, +}; + +__bpf_kfunc_start_defs(); + +/** + * scx_bpf_kick_cpu - Trigger reschedule on a CPU + * @cpu: cpu to kick + * @flags: %SCX_KICK_* flags + * + * Kick @cpu into rescheduling. This can be used to wake up an idle CPU or + * trigger rescheduling on a busy CPU. This can be called from any online + * scx_ops operation and the actual kicking is performed asynchronously through + * an irq work. + */ +__bpf_kfunc void scx_bpf_kick_cpu(s32 cpu, u64 flags) +{ + struct rq *this_rq; + unsigned long irq_flags; + + if (!ops_cpu_valid(cpu, NULL)) + return; + + local_irq_save(irq_flags); + + this_rq = this_rq(); + + /* + * While bypassing for PM ops, IRQ handling may not be online which can + * lead to irq_work_queue() malfunction such as infinite busy wait for + * IRQ status update. Suppress kicking. + */ + if (scx_rq_bypassing(this_rq)) + goto out; + + /* + * Actual kicking is bounced to kick_cpus_irq_workfn() to avoid nesting + * rq locks. We can probably be smarter and avoid bouncing if called + * from ops which don't hold a rq lock. + */ + if (flags & SCX_KICK_IDLE) { + struct rq *target_rq = cpu_rq(cpu); + + if (unlikely(flags & (SCX_KICK_PREEMPT | SCX_KICK_WAIT))) + scx_ops_error("PREEMPT/WAIT cannot be used with SCX_KICK_IDLE"); + + if (raw_spin_rq_trylock(target_rq)) { + if (can_skip_idle_kick(target_rq)) { + raw_spin_rq_unlock(target_rq); + goto out; + } + raw_spin_rq_unlock(target_rq); + } + cpumask_set_cpu(cpu, this_rq->scx.cpus_to_kick_if_idle); + } else { + cpumask_set_cpu(cpu, this_rq->scx.cpus_to_kick); + + if (flags & SCX_KICK_PREEMPT) + cpumask_set_cpu(cpu, this_rq->scx.cpus_to_preempt); + if (flags & SCX_KICK_WAIT) + cpumask_set_cpu(cpu, this_rq->scx.cpus_to_wait); + } + + irq_work_queue(&this_rq->scx.kick_cpus_irq_work); +out: + local_irq_restore(irq_flags); +} + +/** + * scx_bpf_dsq_nr_queued - Return the number of queued tasks + * @dsq_id: id of the DSQ + * + * Return the number of tasks in the DSQ matching @dsq_id. If not found, + * -%ENOENT is returned. + */ +__bpf_kfunc s32 scx_bpf_dsq_nr_queued(u64 dsq_id) +{ + struct scx_dispatch_q *dsq; + s32 ret; + + preempt_disable(); + + if (dsq_id == SCX_DSQ_LOCAL) { + ret = READ_ONCE(this_rq()->scx.local_dsq.nr); + goto out; + } else if ((dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON) { + s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK; + + if (ops_cpu_valid(cpu, NULL)) { + ret = READ_ONCE(cpu_rq(cpu)->scx.local_dsq.nr); + goto out; + } + } else { + dsq = find_user_dsq(dsq_id); + if (dsq) { + ret = READ_ONCE(dsq->nr); + goto out; + } + } + ret = -ENOENT; +out: + preempt_enable(); + return ret; +} + +/** + * scx_bpf_destroy_dsq - Destroy a custom DSQ + * @dsq_id: DSQ to destroy + * + * Destroy the custom DSQ identified by @dsq_id. Only DSQs created with + * scx_bpf_create_dsq() can be destroyed. The caller must ensure that the DSQ is + * empty and no further tasks are dispatched to it. Ignored if called on a DSQ + * which doesn't exist. Can be called from any online scx_ops operations. + */ +__bpf_kfunc void scx_bpf_destroy_dsq(u64 dsq_id) +{ + destroy_dsq(dsq_id); +} + +/** + * bpf_iter_scx_dsq_new - Create a DSQ iterator + * @it: iterator to initialize + * @dsq_id: DSQ to iterate + * @flags: %SCX_DSQ_ITER_* + * + * Initialize BPF iterator @it which can be used with bpf_for_each() to walk + * tasks in the DSQ specified by @dsq_id. Iteration using @it only includes + * tasks which are already queued when this function is invoked. + */ +__bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, + u64 flags) +{ + struct bpf_iter_scx_dsq_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(struct bpf_iter_scx_dsq_kern) > + sizeof(struct bpf_iter_scx_dsq)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_scx_dsq_kern) != + __alignof__(struct bpf_iter_scx_dsq)); + + /* + * next() and destroy() will be called regardless of the return value. + * Always clear $kit->dsq. + */ + kit->dsq = NULL; + + if (flags & ~__SCX_DSQ_ITER_USER_FLAGS) + return -EINVAL; + + kit->dsq = find_user_dsq(dsq_id); + if (!kit->dsq) + return -ENOENT; + + INIT_LIST_HEAD(&kit->cursor.node); + kit->cursor.flags = SCX_DSQ_LNODE_ITER_CURSOR | flags; + kit->cursor.priv = READ_ONCE(kit->dsq->seq); + + return 0; +} + +/** + * bpf_iter_scx_dsq_next - Progress a DSQ iterator + * @it: iterator to progress + * + * Return the next task. See bpf_iter_scx_dsq_new(). + */ +__bpf_kfunc struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *it) +{ + struct bpf_iter_scx_dsq_kern *kit = (void *)it; + bool rev = kit->cursor.flags & SCX_DSQ_ITER_REV; + struct task_struct *p; + unsigned long flags; + + if (!kit->dsq) + return NULL; + + raw_spin_lock_irqsave(&kit->dsq->lock, flags); + + if (list_empty(&kit->cursor.node)) + p = NULL; + else + p = container_of(&kit->cursor, struct task_struct, scx.dsq_list); + + /* + * Only tasks which were queued before the iteration started are + * visible. This bounds BPF iterations and guarantees that vtime never + * jumps in the other direction while iterating. + */ + do { + p = nldsq_next_task(kit->dsq, p, rev); + } while (p && unlikely(u32_before(kit->cursor.priv, p->scx.dsq_seq))); + + if (p) { + if (rev) + list_move_tail(&kit->cursor.node, &p->scx.dsq_list.node); + else + list_move(&kit->cursor.node, &p->scx.dsq_list.node); + } else { + list_del_init(&kit->cursor.node); + } + + raw_spin_unlock_irqrestore(&kit->dsq->lock, flags); + + return p; +} + +/** + * bpf_iter_scx_dsq_destroy - Destroy a DSQ iterator + * @it: iterator to destroy + * + * Undo scx_iter_scx_dsq_new(). + */ +__bpf_kfunc void bpf_iter_scx_dsq_destroy(struct bpf_iter_scx_dsq *it) +{ + struct bpf_iter_scx_dsq_kern *kit = (void *)it; + + if (!kit->dsq) + return; + + if (!list_empty(&kit->cursor.node)) { + unsigned long flags; + + raw_spin_lock_irqsave(&kit->dsq->lock, flags); + list_del_init(&kit->cursor.node); + raw_spin_unlock_irqrestore(&kit->dsq->lock, flags); + } + kit->dsq = NULL; +} + +__bpf_kfunc_end_defs(); + +static s32 __bstr_format(u64 *data_buf, char *line_buf, size_t line_size, + char *fmt, unsigned long long *data, u32 data__sz) +{ + struct bpf_bprintf_data bprintf_data = { .get_bin_args = true }; + s32 ret; + + if (data__sz % 8 || data__sz > MAX_BPRINTF_VARARGS * 8 || + (data__sz && !data)) { + scx_ops_error("invalid data=%p and data__sz=%u", + (void *)data, data__sz); + return -EINVAL; + } + + ret = copy_from_kernel_nofault(data_buf, data, data__sz); + if (ret < 0) { + scx_ops_error("failed to read data fields (%d)", ret); + return ret; + } + + ret = bpf_bprintf_prepare(fmt, UINT_MAX, data_buf, data__sz / 8, + &bprintf_data); + if (ret < 0) { + scx_ops_error("format preparation failed (%d)", ret); + return ret; + } + + ret = bstr_printf(line_buf, line_size, fmt, + bprintf_data.bin_args); + bpf_bprintf_cleanup(&bprintf_data); + if (ret < 0) { + scx_ops_error("(\"%s\", %p, %u) failed to format", + fmt, data, data__sz); + return ret; + } + + return ret; +} + +static s32 bstr_format(struct scx_bstr_buf *buf, + char *fmt, unsigned long long *data, u32 data__sz) +{ + return __bstr_format(buf->data, buf->line, sizeof(buf->line), + fmt, data, data__sz); +} + +__bpf_kfunc_start_defs(); + +/** + * scx_bpf_exit_bstr - Gracefully exit the BPF scheduler. + * @exit_code: Exit value to pass to user space via struct scx_exit_info. + * @fmt: error message format string + * @data: format string parameters packaged using ___bpf_fill() macro + * @data__sz: @data len, must end in '__sz' for the verifier + * + * Indicate that the BPF scheduler wants to exit gracefully, and initiate ops + * disabling. + */ +__bpf_kfunc void scx_bpf_exit_bstr(s64 exit_code, char *fmt, + unsigned long long *data, u32 data__sz) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&scx_exit_bstr_buf_lock, flags); + if (bstr_format(&scx_exit_bstr_buf, fmt, data, data__sz) >= 0) + scx_ops_exit_kind(SCX_EXIT_UNREG_BPF, exit_code, "%s", + scx_exit_bstr_buf.line); + raw_spin_unlock_irqrestore(&scx_exit_bstr_buf_lock, flags); +} + +/** + * scx_bpf_error_bstr - Indicate fatal error + * @fmt: error message format string + * @data: format string parameters packaged using ___bpf_fill() macro + * @data__sz: @data len, must end in '__sz' for the verifier + * + * Indicate that the BPF scheduler encountered a fatal error and initiate ops + * disabling. + */ +__bpf_kfunc void scx_bpf_error_bstr(char *fmt, unsigned long long *data, + u32 data__sz) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&scx_exit_bstr_buf_lock, flags); + if (bstr_format(&scx_exit_bstr_buf, fmt, data, data__sz) >= 0) + scx_ops_exit_kind(SCX_EXIT_ERROR_BPF, 0, "%s", + scx_exit_bstr_buf.line); + raw_spin_unlock_irqrestore(&scx_exit_bstr_buf_lock, flags); +} + +/** + * scx_bpf_dump_bstr - Generate extra debug dump specific to the BPF scheduler + * @fmt: format string + * @data: format string parameters packaged using ___bpf_fill() macro + * @data__sz: @data len, must end in '__sz' for the verifier + * + * To be called through scx_bpf_dump() helper from ops.dump(), dump_cpu() and + * dump_task() to generate extra debug dump specific to the BPF scheduler. + * + * The extra dump may be multiple lines. A single line may be split over + * multiple calls. The last line is automatically terminated. + */ +__bpf_kfunc void scx_bpf_dump_bstr(char *fmt, unsigned long long *data, + u32 data__sz) +{ + struct scx_dump_data *dd = &scx_dump_data; + struct scx_bstr_buf *buf = &dd->buf; + s32 ret; + + if (raw_smp_processor_id() != dd->cpu) { + scx_ops_error("scx_bpf_dump() must only be called from ops.dump() and friends"); + return; + } + + /* append the formatted string to the line buf */ + ret = __bstr_format(buf->data, buf->line + dd->cursor, + sizeof(buf->line) - dd->cursor, fmt, data, data__sz); + if (ret < 0) { + dump_line(dd->s, "%s[!] (\"%s\", %p, %u) failed to format (%d)", + dd->prefix, fmt, data, data__sz, ret); + return; + } + + dd->cursor += ret; + dd->cursor = min_t(s32, dd->cursor, sizeof(buf->line)); + + if (!dd->cursor) + return; + + /* + * If the line buf overflowed or ends in a newline, flush it into the + * dump. This is to allow the caller to generate a single line over + * multiple calls. As ops_dump_flush() can also handle multiple lines in + * the line buf, the only case which can lead to an unexpected + * truncation is when the caller keeps generating newlines in the middle + * instead of the end consecutively. Don't do that. + */ + if (dd->cursor >= sizeof(buf->line) || buf->line[dd->cursor - 1] == '\n') + ops_dump_flush(); +} + +/** + * scx_bpf_cpuperf_cap - Query the maximum relative capacity of a CPU + * @cpu: CPU of interest + * + * Return the maximum relative capacity of @cpu in relation to the most + * performant CPU in the system. The return value is in the range [1, + * %SCX_CPUPERF_ONE]. See scx_bpf_cpuperf_cur(). + */ +__bpf_kfunc u32 scx_bpf_cpuperf_cap(s32 cpu) +{ + if (ops_cpu_valid(cpu, NULL)) + return arch_scale_cpu_capacity(cpu); + else + return SCX_CPUPERF_ONE; +} + +/** + * scx_bpf_cpuperf_cur - Query the current relative performance of a CPU + * @cpu: CPU of interest + * + * Return the current relative performance of @cpu in relation to its maximum. + * The return value is in the range [1, %SCX_CPUPERF_ONE]. + * + * The current performance level of a CPU in relation to the maximum performance + * available in the system can be calculated as follows: + * + * scx_bpf_cpuperf_cap() * scx_bpf_cpuperf_cur() / %SCX_CPUPERF_ONE + * + * The result is in the range [1, %SCX_CPUPERF_ONE]. + */ +__bpf_kfunc u32 scx_bpf_cpuperf_cur(s32 cpu) +{ + if (ops_cpu_valid(cpu, NULL)) + return arch_scale_freq_capacity(cpu); + else + return SCX_CPUPERF_ONE; +} + +/** + * scx_bpf_cpuperf_set - Set the relative performance target of a CPU + * @cpu: CPU of interest + * @perf: target performance level [0, %SCX_CPUPERF_ONE] + * + * Set the target performance level of @cpu to @perf. @perf is in linear + * relative scale between 0 and %SCX_CPUPERF_ONE. This determines how the + * schedutil cpufreq governor chooses the target frequency. + * + * The actual performance level chosen, CPU grouping, and the overhead and + * latency of the operations are dependent on the hardware and cpufreq driver in + * use. Consult hardware and cpufreq documentation for more information. The + * current performance level can be monitored using scx_bpf_cpuperf_cur(). + */ +__bpf_kfunc void scx_bpf_cpuperf_set(s32 cpu, u32 perf) +{ + if (unlikely(perf > SCX_CPUPERF_ONE)) { + scx_ops_error("Invalid cpuperf target %u for CPU %d", perf, cpu); + return; + } + + if (ops_cpu_valid(cpu, NULL)) { + struct rq *rq = cpu_rq(cpu), *locked_rq = scx_locked_rq(); + struct rq_flags rf; + + /* + * When called with an rq lock held, restrict the operation + * to the corresponding CPU to prevent ABBA deadlocks. + */ + if (locked_rq && rq != locked_rq) { + scx_ops_error("Invalid target CPU %d", cpu); + return; + } + + /* + * If no rq lock is held, allow to operate on any CPU by + * acquiring the corresponding rq lock. + */ + if (!locked_rq) { + rq_lock_irqsave(rq, &rf); + update_rq_clock(rq); + } + + rq->scx.cpuperf_target = perf; + cpufreq_update_util(rq, 0); + + if (!locked_rq) + rq_unlock_irqrestore(rq, &rf); + } +} + +/** + * scx_bpf_nr_cpu_ids - Return the number of possible CPU IDs + * + * All valid CPU IDs in the system are smaller than the returned value. + */ +__bpf_kfunc u32 scx_bpf_nr_cpu_ids(void) +{ + return nr_cpu_ids; +} + +/** + * scx_bpf_get_possible_cpumask - Get a referenced kptr to cpu_possible_mask + */ +__bpf_kfunc const struct cpumask *scx_bpf_get_possible_cpumask(void) +{ + return cpu_possible_mask; +} + +/** + * scx_bpf_get_online_cpumask - Get a referenced kptr to cpu_online_mask + */ +__bpf_kfunc const struct cpumask *scx_bpf_get_online_cpumask(void) +{ + return cpu_online_mask; +} + +/** + * scx_bpf_put_cpumask - Release a possible/online cpumask + * @cpumask: cpumask to release + */ +__bpf_kfunc void scx_bpf_put_cpumask(const struct cpumask *cpumask) +{ + /* + * Empty function body because we aren't actually acquiring or releasing + * a reference to a global cpumask, which is read-only in the caller and + * is never released. The acquire / release semantics here are just used + * to make the cpumask is a trusted pointer in the caller. + */ +} + +/** + * scx_bpf_task_running - Is task currently running? + * @p: task of interest + */ +__bpf_kfunc bool scx_bpf_task_running(const struct task_struct *p) +{ + return task_rq(p)->curr == p; +} + +/** + * scx_bpf_task_cpu - CPU a task is currently associated with + * @p: task of interest + */ +__bpf_kfunc s32 scx_bpf_task_cpu(const struct task_struct *p) +{ + return task_cpu(p); +} + +/** + * scx_bpf_cpu_rq - Fetch the rq of a CPU + * @cpu: CPU of the rq + */ +__bpf_kfunc struct rq *scx_bpf_cpu_rq(s32 cpu) +{ + if (!ops_cpu_valid(cpu, NULL)) + return NULL; + + return cpu_rq(cpu); +} + +/** + * scx_bpf_task_cgroup - Return the sched cgroup of a task + * @p: task of interest + * + * @p->sched_task_group->css.cgroup represents the cgroup @p is associated with + * from the scheduler's POV. SCX operations should use this function to + * determine @p's current cgroup as, unlike following @p->cgroups, + * @p->sched_task_group is protected by @p's rq lock and thus atomic w.r.t. all + * rq-locked operations. Can be called on the parameter tasks of rq-locked + * operations. The restriction guarantees that @p's rq is locked by the caller. + */ +#ifdef CONFIG_CGROUP_SCHED +__bpf_kfunc struct cgroup *scx_bpf_task_cgroup(struct task_struct *p) +{ + struct task_group *tg = p->sched_task_group; + struct cgroup *cgrp = &cgrp_dfl_root.cgrp; + + if (!scx_kf_allowed_on_arg_tasks(__SCX_KF_RQ_LOCKED, p)) + goto out; + + cgrp = tg_cgrp(tg); + +out: + cgroup_get(cgrp); + return cgrp; +} +#endif + +/** + * scx_bpf_now - Returns a high-performance monotonically non-decreasing + * clock for the current CPU. The clock returned is in nanoseconds. + * + * It provides the following properties: + * + * 1) High performance: Many BPF schedulers call bpf_ktime_get_ns() frequently + * to account for execution time and track tasks' runtime properties. + * Unfortunately, in some hardware platforms, bpf_ktime_get_ns() -- which + * eventually reads a hardware timestamp counter -- is neither performant nor + * scalable. scx_bpf_now() aims to provide a high-performance clock by + * using the rq clock in the scheduler core whenever possible. + * + * 2) High enough resolution for the BPF scheduler use cases: In most BPF + * scheduler use cases, the required clock resolution is lower than the most + * accurate hardware clock (e.g., rdtsc in x86). scx_bpf_now() basically + * uses the rq clock in the scheduler core whenever it is valid. It considers + * that the rq clock is valid from the time the rq clock is updated + * (update_rq_clock) until the rq is unlocked (rq_unpin_lock). + * + * 3) Monotonically non-decreasing clock for the same CPU: scx_bpf_now() + * guarantees the clock never goes backward when comparing them in the same + * CPU. On the other hand, when comparing clocks in different CPUs, there + * is no such guarantee -- the clock can go backward. It provides a + * monotonically *non-decreasing* clock so that it would provide the same + * clock values in two different scx_bpf_now() calls in the same CPU + * during the same period of when the rq clock is valid. + */ +__bpf_kfunc u64 scx_bpf_now(void) +{ + struct rq *rq; + u64 clock; + + preempt_disable(); + + rq = this_rq(); + if (smp_load_acquire(&rq->scx.flags) & SCX_RQ_CLK_VALID) { + /* + * If the rq clock is valid, use the cached rq clock. + * + * Note that scx_bpf_now() is re-entrant between a process + * context and an interrupt context (e.g., timer interrupt). + * However, we don't need to consider the race between them + * because such race is not observable from a caller. + */ + clock = READ_ONCE(rq->scx.clock); + } else { + /* + * Otherwise, return a fresh rq clock. + * + * The rq clock is updated outside of the rq lock. + * In this case, keep the updated rq clock invalid so the next + * kfunc call outside the rq lock gets a fresh rq clock. + */ + clock = sched_clock_cpu(cpu_of(rq)); + } + + preempt_enable(); + + return clock; +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(scx_kfunc_ids_any) +BTF_ID_FLAGS(func, scx_bpf_kick_cpu) +BTF_ID_FLAGS(func, scx_bpf_dsq_nr_queued) +BTF_ID_FLAGS(func, scx_bpf_destroy_dsq) +BTF_ID_FLAGS(func, bpf_iter_scx_dsq_new, KF_ITER_NEW | KF_RCU_PROTECTED) +BTF_ID_FLAGS(func, bpf_iter_scx_dsq_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_scx_dsq_destroy, KF_ITER_DESTROY) +BTF_ID_FLAGS(func, scx_bpf_exit_bstr, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, scx_bpf_error_bstr, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, scx_bpf_dump_bstr, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, scx_bpf_cpuperf_cap) +BTF_ID_FLAGS(func, scx_bpf_cpuperf_cur) +BTF_ID_FLAGS(func, scx_bpf_cpuperf_set) +BTF_ID_FLAGS(func, scx_bpf_nr_cpu_ids) +BTF_ID_FLAGS(func, scx_bpf_get_possible_cpumask, KF_ACQUIRE) +BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE) +BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE) +BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_cpu_rq) +#ifdef CONFIG_CGROUP_SCHED +BTF_ID_FLAGS(func, scx_bpf_task_cgroup, KF_RCU | KF_ACQUIRE) +#endif +BTF_ID_FLAGS(func, scx_bpf_now) +BTF_KFUNCS_END(scx_kfunc_ids_any) + +static const struct btf_kfunc_id_set scx_kfunc_set_any = { + .owner = THIS_MODULE, + .set = &scx_kfunc_ids_any, +}; + +static int __init scx_init(void) +{ + int ret; + + /* + * kfunc registration can't be done from init_sched_ext_class() as + * register_btf_kfunc_id_set() needs most of the system to be up. + * + * Some kfuncs are context-sensitive and can only be called from + * specific SCX ops. They are grouped into BTF sets accordingly. + * Unfortunately, BPF currently doesn't have a way of enforcing such + * restrictions. Eventually, the verifier should be able to enforce + * them. For now, register them the same and make each kfunc explicitly + * check using scx_kf_allowed(). + */ + if ((ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, + &scx_kfunc_set_enqueue_dispatch)) || + (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, + &scx_kfunc_set_dispatch)) || + (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, + &scx_kfunc_set_cpu_release)) || + (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, + &scx_kfunc_set_unlocked)) || + (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, + &scx_kfunc_set_unlocked)) || + (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, + &scx_kfunc_set_any)) || + (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, + &scx_kfunc_set_any)) || + (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, + &scx_kfunc_set_any))) { + pr_err("sched_ext: Failed to register kfunc sets (%d)\n", ret); + return ret; + } + + ret = scx_idle_init(); + if (ret) { + pr_err("sched_ext: Failed to initialize idle tracking (%d)\n", ret); + return ret; + } + + ret = register_bpf_struct_ops(&bpf_sched_ext_ops, sched_ext_ops); + if (ret) { + pr_err("sched_ext: Failed to register struct_ops (%d)\n", ret); + return ret; + } + + ret = register_pm_notifier(&scx_pm_notifier); + if (ret) { + pr_err("sched_ext: Failed to register PM notifier (%d)\n", ret); + return ret; + } + + scx_kset = kset_create_and_add("sched_ext", &scx_uevent_ops, kernel_kobj); + if (!scx_kset) { + pr_err("sched_ext: Failed to create /sys/kernel/sched_ext\n"); + return -ENOMEM; + } + + ret = sysfs_create_group(&scx_kset->kobj, &scx_global_attr_group); + if (ret < 0) { + pr_err("sched_ext: Failed to add global attributes\n"); + return ret; + } + + return 0; +} +__initcall(scx_init); diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h new file mode 100644 index 0000000000000000000000000000000000000000..5bd5199f93c61ec04c8d4d7e7470bbef1aba0b47 --- /dev/null +++ b/kernel/sched/ext.h @@ -0,0 +1,119 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst + * + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo + * Copyright (c) 2022 David Vernet + */ +#ifdef CONFIG_SCHED_CLASS_EXT + +static inline bool scx_kf_allowed_if_unlocked(void) +{ + return !current->scx.kf_mask; +} + +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); +int scx_fork(struct task_struct *p); +void scx_post_fork(struct task_struct *p); +void scx_cancel_fork(struct task_struct *p); +bool scx_can_stop_tick(struct rq *rq); +void scx_rq_activate(struct rq *rq); +void scx_rq_deactivate(struct rq *rq); +int scx_check_setscheduler(struct task_struct *p, int policy); +bool task_should_scx(int policy); +void init_sched_ext_class(void); + +static inline u32 scx_cpuperf_target(s32 cpu) +{ + if (scx_enabled()) + return cpu_rq(cpu)->scx.cpuperf_target; + else + return 0; +} + +static inline bool task_on_scx(const struct task_struct *p) +{ + return scx_enabled() && p->sched_class == &ext_sched_class; +} + +static inline bool scx_allow_ttwu_queue(const struct task_struct *p) +{ + return !scx_enabled() || + static_branch_likely(&scx_ops_allow_queued_wakeup) || + p->sched_class != &ext_sched_class; +} + +#ifdef CONFIG_SCHED_CORE +bool scx_prio_less(const struct task_struct *a, const struct task_struct *b, + bool in_fi); +#endif + +#else /* CONFIG_SCHED_CLASS_EXT */ + +static inline void scx_tick(struct rq *rq) {} +static inline void scx_pre_fork(struct task_struct *p) {} +static inline int scx_fork(struct task_struct *p) { return 0; } +static inline void scx_post_fork(struct task_struct *p) {} +static inline void scx_cancel_fork(struct task_struct *p) {} +static inline u32 scx_cpuperf_target(s32 cpu) { return 0; } +static inline bool scx_can_stop_tick(struct rq *rq) { return true; } +static inline void scx_rq_activate(struct rq *rq) {} +static inline void scx_rq_deactivate(struct rq *rq) {} +static inline int scx_check_setscheduler(struct task_struct *p, int policy) { return 0; } +static inline bool task_on_scx(const struct task_struct *p) { return false; } +static inline bool scx_allow_ttwu_queue(const struct task_struct *p) { return true; } +static inline void init_sched_ext_class(void) {} + +#endif /* CONFIG_SCHED_CLASS_EXT */ + +#if defined(CONFIG_SCHED_CLASS_EXT) && defined(CONFIG_SMP) +void __scx_update_idle(struct rq *rq, bool idle, bool do_notify); + +static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) +{ + if (scx_enabled()) + __scx_update_idle(rq, idle, do_notify); +} +#else +static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) {} +#endif + +#ifdef CONFIG_CGROUP_SCHED +#ifdef CONFIG_EXT_GROUP_SCHED +void scx_tg_init(struct task_group *tg); +int scx_tg_online(struct task_group *tg); +void scx_tg_offline(struct task_group *tg); +int scx_cgroup_can_attach(struct cgroup_taskset *tset); +void scx_cgroup_move_task(struct task_struct *p); +void scx_cgroup_finish_attach(void); +void scx_cgroup_cancel_attach(struct cgroup_taskset *tset); +void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight); +void scx_group_set_idle(struct task_group *tg, bool idle); +#else /* CONFIG_EXT_GROUP_SCHED */ +static inline void scx_tg_init(struct task_group *tg) {} +static inline int scx_tg_online(struct task_group *tg) { return 0; } +static inline void scx_tg_offline(struct task_group *tg) {} +static inline int scx_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; } +static inline void scx_cgroup_move_task(struct task_struct *p) {} +static inline void scx_cgroup_finish_attach(void) {} +static inline void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) {} +static inline void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight) {} +static inline void scx_group_set_idle(struct task_group *tg, bool idle) {} +#endif /* CONFIG_EXT_GROUP_SCHED */ +#endif /* CONFIG_CGROUP_SCHED */ diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c new file mode 100644 index 0000000000000000000000000000000000000000..9824c5061a95a45af2f7178b9cfeef33e0e3a30b --- /dev/null +++ b/kernel/sched/ext_idle.c @@ -0,0 +1,752 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst + * + * Built-in idle CPU tracking policy. + * + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo + * Copyright (c) 2022 David Vernet + * Copyright (c) 2024 Andrea Righi + */ +#include "ext_idle.h" + +/* Enable/disable built-in idle CPU selection policy */ +DEFINE_STATIC_KEY_FALSE(scx_builtin_idle_enabled); + +#ifdef CONFIG_SMP +#ifdef CONFIG_CPUMASK_OFFSTACK +#define CL_ALIGNED_IF_ONSTACK +#else +#define CL_ALIGNED_IF_ONSTACK __cacheline_aligned_in_smp +#endif + +/* Enable/disable LLC aware optimizations */ +DEFINE_STATIC_KEY_FALSE(scx_selcpu_topo_llc); + +/* Enable/disable NUMA aware optimizations */ +DEFINE_STATIC_KEY_FALSE(scx_selcpu_topo_numa); + +static struct { + cpumask_var_t cpu; + cpumask_var_t smt; +} idle_masks CL_ALIGNED_IF_ONSTACK; + +bool scx_idle_test_and_clear_cpu(int cpu) +{ +#ifdef CONFIG_SCHED_SMT + /* + * SMT mask should be cleared whether we can claim @cpu or not. The SMT + * cluster is not wholly idle either way. This also prevents + * scx_pick_idle_cpu() from getting caught in an infinite loop. + */ + if (sched_smt_active()) { + const struct cpumask *smt = cpu_smt_mask(cpu); + + /* + * If offline, @cpu is not its own sibling and + * scx_pick_idle_cpu() can get caught in an infinite loop as + * @cpu is never cleared from idle_masks.smt. Ensure that @cpu + * is eventually cleared. + * + * NOTE: Use cpumask_intersects() and cpumask_test_cpu() to + * reduce memory writes, which may help alleviate cache + * coherence pressure. + */ + if (cpumask_intersects(smt, idle_masks.smt)) + cpumask_andnot(idle_masks.smt, idle_masks.smt, smt); + else if (cpumask_test_cpu(cpu, idle_masks.smt)) + __cpumask_clear_cpu(cpu, idle_masks.smt); + } +#endif + return cpumask_test_and_clear_cpu(cpu, idle_masks.cpu); +} + +s32 scx_pick_idle_cpu(const struct cpumask *cpus_allowed, u64 flags) +{ + int cpu; + +retry: + if (sched_smt_active()) { + cpu = cpumask_any_and_distribute(idle_masks.smt, cpus_allowed); + if (cpu < nr_cpu_ids) + goto found; + + if (flags & SCX_PICK_IDLE_CORE) + return -EBUSY; + } + + cpu = cpumask_any_and_distribute(idle_masks.cpu, cpus_allowed); + if (cpu >= nr_cpu_ids) + return -EBUSY; + +found: + if (scx_idle_test_and_clear_cpu(cpu)) + return cpu; + else + goto retry; +} + +/* + * Return the amount of CPUs in the same LLC domain of @cpu (or zero if the LLC + * domain is not defined). + */ +static unsigned int llc_weight(s32 cpu) +{ + struct sched_domain *sd; + + sd = rcu_dereference(per_cpu(sd_llc, cpu)); + if (!sd) + return 0; + + return sd->span_weight; +} + +/* + * Return the cpumask representing the LLC domain of @cpu (or NULL if the LLC + * domain is not defined). + */ +static struct cpumask *llc_span(s32 cpu) +{ + struct sched_domain *sd; + + sd = rcu_dereference(per_cpu(sd_llc, cpu)); + if (!sd) + return 0; + + return sched_domain_span(sd); +} + +/* + * Return the amount of CPUs in the same NUMA domain of @cpu (or zero if the + * NUMA domain is not defined). + */ +static unsigned int numa_weight(s32 cpu) +{ + struct sched_domain *sd; + struct sched_group *sg; + + sd = rcu_dereference(per_cpu(sd_numa, cpu)); + if (!sd) + return 0; + sg = sd->groups; + if (!sg) + return 0; + + return sg->group_weight; +} + +/* + * Return the cpumask representing the NUMA domain of @cpu (or NULL if the NUMA + * domain is not defined). + */ +static struct cpumask *numa_span(s32 cpu) +{ + struct sched_domain *sd; + struct sched_group *sg; + + sd = rcu_dereference(per_cpu(sd_numa, cpu)); + if (!sd) + return NULL; + sg = sd->groups; + if (!sg) + return NULL; + + return sched_group_span(sg); +} + +/* + * Return true if the LLC domains do not perfectly overlap with the NUMA + * domains, false otherwise. + */ +static bool llc_numa_mismatch(void) +{ + int cpu; + + /* + * We need to scan all online CPUs to verify whether their scheduling + * domains overlap. + * + * While it is rare to encounter architectures with asymmetric NUMA + * topologies, CPU hotplugging or virtualized environments can result + * in asymmetric configurations. + * + * For example: + * + * NUMA 0: + * - LLC 0: cpu0..cpu7 + * - LLC 1: cpu8..cpu15 [offline] + * + * NUMA 1: + * - LLC 0: cpu16..cpu23 + * - LLC 1: cpu24..cpu31 + * + * In this case, if we only check the first online CPU (cpu0), we might + * incorrectly assume that the LLC and NUMA domains are fully + * overlapping, which is incorrect (as NUMA 1 has two distinct LLC + * domains). + */ + for_each_online_cpu(cpu) + if (llc_weight(cpu) != numa_weight(cpu)) + return true; + + return false; +} + +/* + * Initialize topology-aware scheduling. + * + * Detect if the system has multiple LLC or multiple NUMA domains and enable + * cache-aware / NUMA-aware scheduling optimizations in the default CPU idle + * selection policy. + * + * Assumption: the kernel's internal topology representation assumes that each + * CPU belongs to a single LLC domain, and that each LLC domain is entirely + * contained within a single NUMA node. + */ +void scx_idle_update_selcpu_topology(void) +{ + bool enable_llc = false, enable_numa = false; + unsigned int nr_cpus; + s32 cpu = cpumask_first(cpu_online_mask); + + /* + * Enable LLC domain optimization only when there are multiple LLC + * domains among the online CPUs. If all online CPUs are part of a + * single LLC domain, the idle CPU selection logic can choose any + * online CPU without bias. + * + * Note that it is sufficient to check the LLC domain of the first + * online CPU to determine whether a single LLC domain includes all + * CPUs. + */ + rcu_read_lock(); + nr_cpus = llc_weight(cpu); + if (nr_cpus > 0) { + if (nr_cpus < num_online_cpus()) + enable_llc = true; + pr_debug("sched_ext: LLC=%*pb weight=%u\n", + cpumask_pr_args(llc_span(cpu)), llc_weight(cpu)); + } + + /* + * Enable NUMA optimization only when there are multiple NUMA domains + * among the online CPUs and the NUMA domains don't perfectly overlaps + * with the LLC domains. + * + * If all CPUs belong to the same NUMA node and the same LLC domain, + * enabling both NUMA and LLC optimizations is unnecessary, as checking + * for an idle CPU in the same domain twice is redundant. + */ + nr_cpus = numa_weight(cpu); + if (nr_cpus > 0) { + if (nr_cpus < num_online_cpus() && llc_numa_mismatch()) + enable_numa = true; + pr_debug("sched_ext: NUMA=%*pb weight=%u\n", + cpumask_pr_args(numa_span(cpu)), numa_weight(cpu)); + } + rcu_read_unlock(); + + pr_debug("sched_ext: LLC idle selection %s\n", + str_enabled_disabled(enable_llc)); + pr_debug("sched_ext: NUMA idle selection %s\n", + str_enabled_disabled(enable_numa)); + + if (enable_llc) + static_branch_enable_cpuslocked(&scx_selcpu_topo_llc); + else + static_branch_disable_cpuslocked(&scx_selcpu_topo_llc); + if (enable_numa) + static_branch_enable_cpuslocked(&scx_selcpu_topo_numa); + else + static_branch_disable_cpuslocked(&scx_selcpu_topo_numa); +} + +/* + * Built-in CPU idle selection policy: + * + * 1. Prioritize full-idle cores: + * - always prioritize CPUs from fully idle cores (both logical CPUs are + * idle) to avoid interference caused by SMT. + * + * 2. Reuse the same CPU: + * - prefer the last used CPU to take advantage of cached data (L1, L2) and + * branch prediction optimizations. + * + * 3. Pick a CPU within the same LLC (Last-Level Cache): + * - if the above conditions aren't met, pick a CPU that shares the same LLC + * to maintain cache locality. + * + * 4. Pick a CPU within the same NUMA node, if enabled: + * - choose a CPU from the same NUMA node to reduce memory access latency. + * + * 5. Pick any idle CPU usable by the task. + * + * Step 3 and 4 are performed only if the system has, respectively, multiple + * LLC domains / multiple NUMA nodes (see scx_selcpu_topo_llc and + * scx_selcpu_topo_numa). + * + * NOTE: tasks that can only run on 1 CPU are excluded by this logic, because + * we never call ops.select_cpu() for them, see select_task_rq(). + */ +s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool *found) +{ + const struct cpumask *llc_cpus = NULL; + const struct cpumask *numa_cpus = NULL; + s32 cpu; + + *found = false; + + /* + * This is necessary to protect llc_cpus. + */ + rcu_read_lock(); + + /* + * Determine the scheduling domain only if the task is allowed to run + * on all CPUs. + * + * This is done primarily for efficiency, as it avoids the overhead of + * updating a cpumask every time we need to select an idle CPU (which + * can be costly in large SMP systems), but it also aligns logically: + * if a task's scheduling domain is restricted by user-space (through + * CPU affinity), the task will simply use the flat scheduling domain + * defined by user-space. + */ + if (p->nr_cpus_allowed >= num_possible_cpus()) { + if (static_branch_maybe(CONFIG_NUMA, &scx_selcpu_topo_numa)) + numa_cpus = numa_span(prev_cpu); + + if (static_branch_maybe(CONFIG_SCHED_MC, &scx_selcpu_topo_llc)) + llc_cpus = llc_span(prev_cpu); + } + + /* + * If WAKE_SYNC, try to migrate the wakee to the waker's CPU. + */ + if (wake_flags & SCX_WAKE_SYNC) { + cpu = smp_processor_id(); + + /* + * If the waker's CPU is cache affine and prev_cpu is idle, + * then avoid a migration. + */ + if (cpus_share_cache(cpu, prev_cpu) && + scx_idle_test_and_clear_cpu(prev_cpu)) { + cpu = prev_cpu; + goto cpu_found; + } + + /* + * If the waker's local DSQ is empty, and the system is under + * utilized, try to wake up @p to the local DSQ of the waker. + * + * Checking only for an empty local DSQ is insufficient as it + * could give the wakee an unfair advantage when the system is + * oversaturated. + * + * Checking only for the presence of idle CPUs is also + * insufficient as the local DSQ of the waker could have tasks + * piled up on it even if there is an idle core elsewhere on + * the system. + */ + if (!cpumask_empty(idle_masks.cpu) && + !(current->flags & PF_EXITING) && + cpu_rq(cpu)->scx.local_dsq.nr == 0) { + if (cpumask_test_cpu(cpu, p->cpus_ptr)) + goto cpu_found; + } + } + + /* + * If CPU has SMT, any wholly idle CPU is likely a better pick than + * partially idle @prev_cpu. + */ + if (sched_smt_active()) { + /* + * Keep using @prev_cpu if it's part of a fully idle core. + */ + if (cpumask_test_cpu(prev_cpu, idle_masks.smt) && + scx_idle_test_and_clear_cpu(prev_cpu)) { + cpu = prev_cpu; + goto cpu_found; + } + + /* + * Search for any fully idle core in the same LLC domain. + */ + if (llc_cpus) { + cpu = scx_pick_idle_cpu(llc_cpus, SCX_PICK_IDLE_CORE); + if (cpu >= 0) + goto cpu_found; + } + + /* + * Search for any fully idle core in the same NUMA node. + */ + if (numa_cpus) { + cpu = scx_pick_idle_cpu(numa_cpus, SCX_PICK_IDLE_CORE); + if (cpu >= 0) + goto cpu_found; + } + + /* + * Search for any full idle core usable by the task. + */ + cpu = scx_pick_idle_cpu(p->cpus_ptr, SCX_PICK_IDLE_CORE); + if (cpu >= 0) + goto cpu_found; + } + + /* + * Use @prev_cpu if it's idle. + */ + if (scx_idle_test_and_clear_cpu(prev_cpu)) { + cpu = prev_cpu; + goto cpu_found; + } + + /* + * Search for any idle CPU in the same LLC domain. + */ + if (llc_cpus) { + cpu = scx_pick_idle_cpu(llc_cpus, 0); + if (cpu >= 0) + goto cpu_found; + } + + /* + * Search for any idle CPU in the same NUMA node. + */ + if (numa_cpus) { + cpu = scx_pick_idle_cpu(numa_cpus, 0); + if (cpu >= 0) + goto cpu_found; + } + + /* + * Search for any idle CPU usable by the task. + */ + cpu = scx_pick_idle_cpu(p->cpus_ptr, 0); + if (cpu >= 0) + goto cpu_found; + + rcu_read_unlock(); + return prev_cpu; + +cpu_found: + rcu_read_unlock(); + + *found = true; + return cpu; +} + +void scx_idle_reset_masks(void) +{ + /* + * Consider all online cpus idle. Should converge to the actual state + * quickly. + */ + cpumask_copy(idle_masks.cpu, cpu_online_mask); + cpumask_copy(idle_masks.smt, cpu_online_mask); +} + +void scx_idle_init_masks(void) +{ + BUG_ON(!alloc_cpumask_var(&idle_masks.cpu, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&idle_masks.smt, GFP_KERNEL)); +} + +static void update_builtin_idle(int cpu, bool idle) +{ + assign_cpu(cpu, idle_masks.cpu, idle); + +#ifdef CONFIG_SCHED_SMT + if (sched_smt_active()) { + const struct cpumask *smt = cpu_smt_mask(cpu); + + if (idle) { + /* + * idle_masks.smt handling is racy but that's fine as + * it's only for optimization and self-correcting. + */ + if (!cpumask_subset(smt, idle_masks.cpu)) + return; + cpumask_or(idle_masks.smt, idle_masks.smt, smt); + } else { + cpumask_andnot(idle_masks.smt, idle_masks.smt, smt); + } + } +#endif +} + +/* + * Update the idle state of a CPU to @idle. + * + * If @do_notify is true, ops.update_idle() is invoked to notify the scx + * scheduler of an actual idle state transition (idle to busy or vice + * versa). If @do_notify is false, only the idle state in the idle masks is + * refreshed without invoking ops.update_idle(). + * + * This distinction is necessary, because an idle CPU can be "reserved" and + * awakened via scx_bpf_pick_idle_cpu() + scx_bpf_kick_cpu(), marking it as + * busy even if no tasks are dispatched. In this case, the CPU may return + * to idle without a true state transition. Refreshing the idle masks + * without invoking ops.update_idle() ensures accurate idle state tracking + * while avoiding unnecessary updates and maintaining balanced state + * transitions. + */ +void __scx_update_idle(struct rq *rq, bool idle, bool do_notify) +{ + int cpu = cpu_of(rq); + + lockdep_assert_rq_held(rq); + + /* + * Trigger ops.update_idle() only when transitioning from a task to + * the idle thread and vice versa. + * + * Idle transitions are indicated by do_notify being set to true, + * managed by put_prev_task_idle()/set_next_task_idle(). + */ + if (SCX_HAS_OP(update_idle) && do_notify && !scx_rq_bypassing(rq)) + SCX_CALL_OP(SCX_KF_REST, update_idle, rq, cpu_of(rq), idle); + + /* + * Update the idle masks: + * - for real idle transitions (do_notify == true) + * - for idle-to-idle transitions (indicated by the previous task + * being the idle thread, managed by pick_task_idle()) + * + * Skip updating idle masks if the previous task is not the idle + * thread, since set_next_task_idle() has already handled it when + * transitioning from a task to the idle thread (calling this + * function with do_notify == true). + * + * In this way we can avoid updating the idle masks twice, + * unnecessarily. + */ + if (static_branch_likely(&scx_builtin_idle_enabled)) + if (do_notify || is_idle_task(rq->curr)) + update_builtin_idle(cpu, idle); +} +#endif /* CONFIG_SMP */ + +/******************************************************************************** + * Helpers that can be called from the BPF scheduler. + */ +__bpf_kfunc_start_defs(); + +static bool check_builtin_idle_enabled(void) +{ + if (static_branch_likely(&scx_builtin_idle_enabled)) + return true; + + scx_ops_error("built-in idle tracking is disabled"); + return false; +} + +/** + * scx_bpf_select_cpu_dfl - The default implementation of ops.select_cpu() + * @p: task_struct to select a CPU for + * @prev_cpu: CPU @p was on previously + * @wake_flags: %SCX_WAKE_* flags + * @is_idle: out parameter indicating whether the returned CPU is idle + * + * Can only be called from ops.select_cpu() if the built-in CPU selection is + * enabled - ops.update_idle() is missing or %SCX_OPS_KEEP_BUILTIN_IDLE is set. + * @p, @prev_cpu and @wake_flags match ops.select_cpu(). + * + * Returns the picked CPU with *@is_idle indicating whether the picked CPU is + * currently idle and thus a good candidate for direct dispatching. + */ +__bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, + u64 wake_flags, bool *is_idle) +{ + if (!check_builtin_idle_enabled()) + goto prev_cpu; + + if (!scx_kf_allowed(SCX_KF_SELECT_CPU)) + goto prev_cpu; + +#ifdef CONFIG_SMP + return scx_select_cpu_dfl(p, prev_cpu, wake_flags, is_idle); +#endif + +prev_cpu: + *is_idle = false; + return prev_cpu; +} + +/** + * scx_bpf_get_idle_cpumask - Get a referenced kptr to the idle-tracking + * per-CPU cpumask. + * + * Returns NULL if idle tracking is not enabled, or running on a UP kernel. + */ +__bpf_kfunc const struct cpumask *scx_bpf_get_idle_cpumask(void) +{ + if (!check_builtin_idle_enabled()) + return cpu_none_mask; + +#ifdef CONFIG_SMP + return idle_masks.cpu; +#else + return cpu_none_mask; +#endif +} + +/** + * scx_bpf_get_idle_smtmask - Get a referenced kptr to the idle-tracking, + * per-physical-core cpumask. Can be used to determine if an entire physical + * core is free. + * + * Returns NULL if idle tracking is not enabled, or running on a UP kernel. + */ +__bpf_kfunc const struct cpumask *scx_bpf_get_idle_smtmask(void) +{ + if (!check_builtin_idle_enabled()) + return cpu_none_mask; + +#ifdef CONFIG_SMP + if (sched_smt_active()) + return idle_masks.smt; + else + return idle_masks.cpu; +#else + return cpu_none_mask; +#endif +} + +/** + * scx_bpf_put_idle_cpumask - Release a previously acquired referenced kptr to + * either the percpu, or SMT idle-tracking cpumask. + * @idle_mask: &cpumask to use + */ +__bpf_kfunc void scx_bpf_put_idle_cpumask(const struct cpumask *idle_mask) +{ + /* + * Empty function body because we aren't actually acquiring or releasing + * a reference to a global idle cpumask, which is read-only in the + * caller and is never released. The acquire / release semantics here + * are just used to make the cpumask a trusted pointer in the caller. + */ +} + +/** + * scx_bpf_test_and_clear_cpu_idle - Test and clear @cpu's idle state + * @cpu: cpu to test and clear idle for + * + * Returns %true if @cpu was idle and its idle state was successfully cleared. + * %false otherwise. + * + * Unavailable if ops.update_idle() is implemented and + * %SCX_OPS_KEEP_BUILTIN_IDLE is not set. + */ +__bpf_kfunc bool scx_bpf_test_and_clear_cpu_idle(s32 cpu) +{ + if (!check_builtin_idle_enabled()) + return false; + + if (ops_cpu_valid(cpu, NULL)) + return scx_idle_test_and_clear_cpu(cpu); + else + return false; +} + +/** + * scx_bpf_pick_idle_cpu - Pick and claim an idle cpu + * @cpus_allowed: Allowed cpumask + * @flags: %SCX_PICK_IDLE_CPU_* flags + * + * Pick and claim an idle cpu in @cpus_allowed. Returns the picked idle cpu + * number on success. -%EBUSY if no matching cpu was found. + * + * Idle CPU tracking may race against CPU scheduling state transitions. For + * example, this function may return -%EBUSY as CPUs are transitioning into the + * idle state. If the caller then assumes that there will be dispatch events on + * the CPUs as they were all busy, the scheduler may end up stalling with CPUs + * idling while there are pending tasks. Use scx_bpf_pick_any_cpu() and + * scx_bpf_kick_cpu() to guarantee that there will be at least one dispatch + * event in the near future. + * + * Unavailable if ops.update_idle() is implemented and + * %SCX_OPS_KEEP_BUILTIN_IDLE is not set. + */ +__bpf_kfunc s32 scx_bpf_pick_idle_cpu(const struct cpumask *cpus_allowed, + u64 flags) +{ + if (!check_builtin_idle_enabled()) + return -EBUSY; + + return scx_pick_idle_cpu(cpus_allowed, flags); +} + +/** + * scx_bpf_pick_any_cpu - Pick and claim an idle cpu if available or pick any CPU + * @cpus_allowed: Allowed cpumask + * @flags: %SCX_PICK_IDLE_CPU_* flags + * + * Pick and claim an idle cpu in @cpus_allowed. If none is available, pick any + * CPU in @cpus_allowed. Guaranteed to succeed and returns the picked idle cpu + * number if @cpus_allowed is not empty. -%EBUSY is returned if @cpus_allowed is + * empty. + * + * If ops.update_idle() is implemented and %SCX_OPS_KEEP_BUILTIN_IDLE is not + * set, this function can't tell which CPUs are idle and will always pick any + * CPU. + */ +__bpf_kfunc s32 scx_bpf_pick_any_cpu(const struct cpumask *cpus_allowed, + u64 flags) +{ + s32 cpu; + + if (static_branch_likely(&scx_builtin_idle_enabled)) { + cpu = scx_pick_idle_cpu(cpus_allowed, flags); + if (cpu >= 0) + return cpu; + } + + cpu = cpumask_any_distribute(cpus_allowed); + if (cpu < nr_cpu_ids) + return cpu; + else + return -EBUSY; +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(scx_kfunc_ids_idle) +BTF_ID_FLAGS(func, scx_bpf_get_idle_cpumask, KF_ACQUIRE) +BTF_ID_FLAGS(func, scx_bpf_get_idle_smtmask, KF_ACQUIRE) +BTF_ID_FLAGS(func, scx_bpf_put_idle_cpumask, KF_RELEASE) +BTF_ID_FLAGS(func, scx_bpf_test_and_clear_cpu_idle) +BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu, KF_RCU) +BTF_KFUNCS_END(scx_kfunc_ids_idle) + +static const struct btf_kfunc_id_set scx_kfunc_set_idle = { + .owner = THIS_MODULE, + .set = &scx_kfunc_ids_idle, +}; + +BTF_KFUNCS_START(scx_kfunc_ids_select_cpu) +BTF_ID_FLAGS(func, scx_bpf_select_cpu_dfl, KF_RCU) +BTF_KFUNCS_END(scx_kfunc_ids_select_cpu) + +static const struct btf_kfunc_id_set scx_kfunc_set_select_cpu = { + .owner = THIS_MODULE, + .set = &scx_kfunc_ids_select_cpu, +}; + +int scx_idle_init(void) +{ + int ret; + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_select_cpu) || + register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_idle) || + register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &scx_kfunc_set_idle) || + register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &scx_kfunc_set_idle); + + return ret; +} diff --git a/kernel/sched/ext_idle.h b/kernel/sched/ext_idle.h new file mode 100644 index 0000000000000000000000000000000000000000..7a13a74815ba7dcccbb460291f909dbc027ea236 --- /dev/null +++ b/kernel/sched/ext_idle.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst + * + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo + * Copyright (c) 2022 David Vernet + * Copyright (c) 2024 Andrea Righi + */ +#ifndef _KERNEL_SCHED_EXT_IDLE_H +#define _KERNEL_SCHED_EXT_IDLE_H + +extern struct static_key_false scx_builtin_idle_enabled; + +#ifdef CONFIG_SMP +extern struct static_key_false scx_selcpu_topo_llc; +extern struct static_key_false scx_selcpu_topo_numa; + +void scx_idle_update_selcpu_topology(void); +void scx_idle_reset_masks(void); +void scx_idle_init_masks(void); +bool scx_idle_test_and_clear_cpu(int cpu); +s32 scx_pick_idle_cpu(const struct cpumask *cpus_allowed, u64 flags); +#else /* !CONFIG_SMP */ +static inline void scx_idle_update_selcpu_topology(void) {} +static inline void scx_idle_reset_masks(void) {} +static inline void scx_idle_init_masks(void) {} +static inline bool scx_idle_test_and_clear_cpu(int cpu) { return false; } +static inline s32 scx_pick_idle_cpu(const struct cpumask *cpus_allowed, u64 flags) +{ + return -EBUSY; +} +#endif /* CONFIG_SMP */ + +s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool *found); + +extern int scx_idle_init(void); + +#endif /* _KERNEL_SCHED_EXT_IDLE_H */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6b30b3811c880c257d61b2f8a2021212101a0d64..05dc05f065b79138b5e86e69273531e4084dd41a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1336,23 +1336,17 @@ static void update_tg_load_avg(struct cfs_rq *cfs_rq) } #endif /* CONFIG_SMP */ -/* - * Update the current task's runtime statistics. - */ -static void update_curr(struct cfs_rq *cfs_rq) +static s64 update_curr_se(struct rq *rq, struct sched_entity *curr) { - struct sched_entity *curr = cfs_rq->curr; - u64 now = rq_clock_task(rq_of(cfs_rq)); - u64 delta_exec; - - if (unlikely(!curr)) - return; + u64 now = rq_clock_task(rq); + s64 delta_exec; delta_exec = now - curr->exec_start; - if (unlikely((s64)delta_exec <= 0)) - return; + if (unlikely(delta_exec <= 0)) + return delta_exec; curr->exec_start = now; + curr->sum_exec_runtime += delta_exec; if (schedstat_enabled()) { struct sched_statistics *stats; @@ -1362,8 +1356,43 @@ static void update_curr(struct cfs_rq *cfs_rq) max(delta_exec, stats->exec_max)); } - curr->sum_exec_runtime += delta_exec; - schedstat_add(cfs_rq->exec_clock, delta_exec); + return delta_exec; +} + +/* + * Used by other classes to account runtime. + */ +s64 update_curr_common(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + s64 delta_exec; + + delta_exec = update_curr_se(rq, &curr->se); + if (unlikely(delta_exec <= 0)) + return delta_exec; + + trace_sched_stat_runtime(curr, delta_exec, 0); + + account_group_exec_runtime(curr, delta_exec); + cgroup_account_cputime(curr, delta_exec); + + return delta_exec; +} + +/* + * Update the current task's runtime statistics. + */ +static void update_curr(struct cfs_rq *cfs_rq) +{ + struct sched_entity *curr = cfs_rq->curr; + s64 delta_exec; + + if (unlikely(!curr)) + return; + + delta_exec = update_curr_se(rq_of(cfs_rq), curr); + if (unlikely(delta_exec <= 0)) + return; curr->vruntime += calc_delta_fair(delta_exec, curr); update_deadline(cfs_rq, curr); @@ -4012,7 +4041,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, } } -void reweight_task(struct task_struct *p, const struct load_weight *lw) +static void reweight_task_fair(struct rq *rq, struct task_struct *p, const struct load_weight *lw) { struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); @@ -5665,7 +5694,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) * 4) do not run the "skip" process, if something else is available */ static struct sched_entity * -pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr) +pick_next_entity(struct cfs_rq *cfs_rq) { /* * Enabling NEXT_BUDDY will affect latency but not fairness. @@ -7659,7 +7688,7 @@ static void set_next_buddy(struct sched_entity *se); * decreased. We remove the task from the rbtree and * update the fair scheduling stats: */ -static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) +static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) { struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; @@ -7738,6 +7767,8 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) dequeue_throttle: util_est_update(&rq->cfs, p, task_sleep); hrtick_update(rq); + + return true; } #ifdef CONFIG_SMP @@ -8847,7 +8878,7 @@ static inline void eenv_pd_busy_time(struct energy_env *eenv, for_each_cpu(cpu, pd_cpus) { unsigned long util = cpu_util(cpu, p, -1, 0); - busy_time += effective_cpu_util(cpu, util, ENERGY_UTIL, NULL); + busy_time += effective_cpu_util(cpu, util, NULL, NULL); } eenv->pd_busy_time = min(eenv->pd_cap, busy_time); @@ -8870,16 +8901,32 @@ eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus, for_each_cpu(cpu, pd_cpus) { struct task_struct *tsk = (cpu == dst_cpu) ? p : NULL; unsigned long util = cpu_util(cpu, p, dst_cpu, 1); - unsigned long eff_util; + unsigned long eff_util, min, max; /* * Performance domain frequency: utilization clamping * must be considered since it affects the selection * of the performance domain frequency. - * NOTE: in case RT tasks are running, by default the - * FREQUENCY_UTIL's utilization can be max OPP. + * NOTE: in case RT tasks are running, by default the min + * utilization can be max OPP. */ - eff_util = effective_cpu_util(cpu, util, FREQUENCY_UTIL, tsk); + eff_util = effective_cpu_util(cpu, util, &min, &max); + + /* Task's uclamp can modify min and max value */ + if (tsk && uclamp_is_used()) { + min = max(min, uclamp_eff_value(p, UCLAMP_MIN)); + + /* + * If there is no active max uclamp constraint, + * directly use task's one, otherwise keep max. + */ + if (uclamp_rq_is_idle(cpu_rq(cpu))) + max = uclamp_eff_value(p, UCLAMP_MAX); + else + max = max(max, uclamp_eff_value(p, UCLAMP_MAX)); + } + + eff_util = sugov_effective_cpu_perf(cpu, eff_util, min, max); max_util = max(max_util, eff_util); } @@ -9521,7 +9568,7 @@ static void set_next_buddy(struct sched_entity *se) /* * Preempt the current task with a newly woken task if needed: */ -static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) +static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int wake_flags) { struct task_struct *curr = rq->curr; struct sched_entity *se = &curr->se, *pse = &p->se; @@ -9535,7 +9582,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ /* * This is possible from callers such as attach_tasks(), in which we - * unconditionally check_preempt_curr() after an enqueue (which may have + * unconditionally wakeup_preempt() after an enqueue (which may have * lead to a throttle). This both saves work and prevents false * next-buddy nomination below. */ @@ -9591,7 +9638,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ /* * BATCH and IDLE tasks do not preempt others. */ - if (unlikely(p->policy != SCHED_NORMAL)) + if (unlikely(!normal_policy(p->policy))) return; cfs_rq = cfs_rq_of(se); @@ -10130,7 +10177,6 @@ void qos_smt_check_need_resched(void) } #endif -#ifdef CONFIG_SMP static struct task_struct *pick_task_fair(struct rq *rq) { struct sched_entity *se; @@ -10142,26 +10188,32 @@ static struct task_struct *pick_task_fair(struct rq *rq) return NULL; do { - struct sched_entity *curr = cfs_rq->curr; - - /* When we pick for a remote RQ, we'll not have done put_prev_entity() */ - if (curr) { - if (curr->on_rq) - update_curr(cfs_rq); - else - curr = NULL; + /* Might not have done put_prev_entity() */ + if (cfs_rq->curr && cfs_rq->curr->on_rq) + update_curr(cfs_rq); - if (unlikely(check_cfs_rq_runtime(cfs_rq))) - goto again; - } + if (unlikely(check_cfs_rq_runtime(cfs_rq))) + goto again; - se = pick_next_entity(cfs_rq, curr); + se = pick_next_entity(cfs_rq); cfs_rq = group_cfs_rq(se); +#ifdef CONFIG_QOS_SCHED + if (check_qos_cfs_rq(cfs_rq)) { + cfs_rq = &rq->cfs; + WARN(cfs_rq->nr_running == 0, + "rq->nr_running=%u, cfs_rq->idle_h_nr_running=%u\n", + rq->nr_running, cfs_rq->idle_h_nr_running); + if (unlikely(!cfs_rq->nr_running)) + return NULL; + } +#endif } while (cfs_rq); return task_of(se); } -#endif + +static void __set_next_task_fair(struct rq *rq, struct task_struct *p, bool first); +static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first); struct task_struct * pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) @@ -10189,11 +10241,13 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf } #endif - if (!sched_fair_runnable(rq)) + p = pick_task_fair(rq); + if (!p) goto idle; + se = &p->se; #ifdef CONFIG_FAIR_GROUP_SCHED - if (!prev || prev->sched_class != &fair_sched_class) { + if (prev->sched_class != &fair_sched_class) { #ifdef CONFIG_QOS_SCHED if (cfs_rq->idle_h_nr_running != 0 && rq->online) goto qos_simple; @@ -10208,62 +10262,14 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf * * Therefore attempt to avoid putting and setting the entire cgroup * hierarchy, only change the part that actually changes. - */ - - do { - struct sched_entity *curr = cfs_rq->curr; - - /* - * Since we got here without doing put_prev_entity() we also - * have to consider cfs_rq->curr. If it is still a runnable - * entity, update_curr() will update its vruntime, otherwise - * forget we've ever seen it. - */ - if (curr) { - if (curr->on_rq) - update_curr(cfs_rq); - else - curr = NULL; - - /* - * This call to check_cfs_rq_runtime() will do the - * throttle and dequeue its entity in the parent(s). - * Therefore the nr_running test will indeed - * be correct. - */ - if (unlikely(check_cfs_rq_runtime(cfs_rq))) { - cfs_rq = &rq->cfs; - - if (!cfs_rq->nr_running) - goto idle; - - goto simple; - } - } - - se = pick_next_entity(cfs_rq, curr); - cfs_rq = group_cfs_rq(se); -#ifdef CONFIG_QOS_SCHED - if (check_qos_cfs_rq(cfs_rq)) { - cfs_rq = &rq->cfs; - WARN(cfs_rq->nr_running == 0, - "rq->nr_running=%u, cfs_rq->idle_h_nr_running=%u\n", - rq->nr_running, cfs_rq->idle_h_nr_running); - if (unlikely(!cfs_rq->nr_running)) - return NULL; - } -#endif - } while (cfs_rq); - - p = task_of(se); - - /* + * * Since we haven't yet done put_prev_entity and if the selected task * is a different task than we started out with, try and touch the * least amount of cfs_rqs. */ if (prev != p) { struct sched_entity *pse = &prev->se; + struct cfs_rq *cfs_rq; while (!(cfs_rq = is_same_group(se, pse))) { int se_depth = se->depth; @@ -10281,9 +10287,11 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf put_prev_entity(cfs_rq, pse); set_next_entity(cfs_rq, se); + + __set_next_task_fair(rq, p, true); } - goto done; + return p; #ifdef CONFIG_QOS_SCHED qos_simple: @@ -10291,7 +10299,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf put_prev_task(rq, prev); do { - se = pick_next_entity(cfs_rq, NULL); + se = pick_next_entity(cfs_rq); if (check_qos_cfs_rq(group_cfs_rq(se))) { cfs_rq = &rq->cfs; if (!cfs_rq->nr_running) @@ -10309,50 +10317,13 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf se = parent_entity(se); } - goto done; + __set_next_task_fair(rq, p, true); + return p; #endif simple: #endif - if (prev) - put_prev_task(rq, prev); - - do { - se = pick_next_entity(cfs_rq, NULL); - set_next_entity(cfs_rq, se); - cfs_rq = group_cfs_rq(se); - } while (cfs_rq); - - p = task_of(se); - -done: __maybe_unused; -#ifdef CONFIG_SMP - /* - * Move the next running task to the front of - * the list, so our cfs_tasks list becomes MRU - * one. - */ -#ifdef CONFIG_QOS_SCHED_PRIO_LB - adjust_rq_cfs_tasks(list_move, rq, &p->se); -#else - list_move(&p->se.group_node, &rq->cfs_tasks); -#endif -#endif - - if (hrtick_enabled_fair(rq)) - hrtick_start_fair(rq, p); - - update_misfit_status(p, rq); - sched_fair_update_stop_tick(rq, p); - -#ifdef CONFIG_QOS_SCHED - qos_schedule_throttle(p); -#endif - -#ifdef CONFIG_QOS_SCHED_SMT_EXPELLER - qos_smt_expel(this_cpu, p); -#endif - + put_prev_set_next_task(rq, prev, p); return p; idle: @@ -10409,15 +10380,15 @@ done: __maybe_unused; return NULL; } -static struct task_struct *__pick_next_task_fair(struct rq *rq) +static struct task_struct *__pick_next_task_fair(struct rq *rq, struct task_struct *prev) { - return pick_next_task_fair(rq, NULL, NULL); + return pick_next_task_fair(rq, prev, NULL); } /* * Account for a descheduled task: */ -static void put_prev_task_fair(struct rq *rq, struct task_struct *prev) +static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct task_struct *next) { struct sched_entity *se = &prev->se; struct cfs_rq *cfs_rq; @@ -11171,7 +11142,7 @@ static void attach_task(struct rq *rq, struct task_struct *p) WARN_ON_ONCE(task_rq(p) != rq); activate_task(rq, p, ENQUEUE_NOCLOCK); - check_preempt_curr(rq, p, 0); + wakeup_preempt(rq, p, 0); } /* @@ -11261,28 +11232,18 @@ static inline void update_blocked_load_status(struct rq *rq, bool has_blocked) { static bool __update_blocked_others(struct rq *rq, bool *done) { - const struct sched_class *curr_class; - u64 now = rq_clock_pelt(rq); - unsigned long thermal_pressure; - bool decayed; + bool updated; /* * update_load_avg() can call cpufreq_update_util(). Make sure that RT, * DL and IRQ signals have been updated before updating CFS. */ - curr_class = rq->curr->sched_class; - - thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq)); - - decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) | - update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) | - update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure) | - update_irq_load_avg(rq, 0); + updated = update_other_load_avgs(rq); if (others_have_blocked(rq)) *done = false; - return decayed; + return updated; } #ifdef CONFIG_FAIR_GROUP_SCHED @@ -14804,7 +14765,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) if (p->prio > oldprio) resched_curr(rq); } else - check_preempt_curr(rq, p, 0); + wakeup_preempt(rq, p, 0); } #ifdef CONFIG_FAIR_GROUP_SCHED @@ -14906,16 +14867,11 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p) if (task_current(rq, p)) resched_curr(rq); else - check_preempt_curr(rq, p, 0); + wakeup_preempt(rq, p, 0); } } -/* Account for a task changing its policy or group. - * - * This routine is mostly called to set cfs_rq->curr field when a task - * migrates between groups/classes. - */ -static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first) +static void __set_next_task_fair(struct rq *rq, struct task_struct *p, bool first) { struct sched_entity *se = &p->se; @@ -14932,6 +14888,33 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first) #endif } #endif + if (!first) + return; + + if (hrtick_enabled_fair(rq)) + hrtick_start_fair(rq, p); + + update_misfit_status(p, rq); + sched_fair_update_stop_tick(rq, p); + +#ifdef CONFIG_QOS_SCHED + qos_schedule_throttle(p); +#endif + +#ifdef CONFIG_QOS_SCHED_SMT_EXPELLER + qos_smt_expel(rq->cpu, p); +#endif +} + +/* + * Account for a task changing its policy or group. + * + * This routine is mostly called to set cfs_rq->curr field when a task + * migrates between groups/classes. + */ +static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first) +{ + struct sched_entity *se = &p->se; for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); @@ -14940,6 +14923,8 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first) /* ensure bandwidth has been allocated on our new cfs_rq */ account_cfs_rq_runtime(cfs_rq, 0); } + + __set_next_task_fair(rq, p, first); } void init_cfs_rq(struct cfs_rq *cfs_rq) @@ -15294,15 +15279,15 @@ DEFINE_SCHED_CLASS(fair) = { .yield_task = yield_task_fair, .yield_to_task = yield_to_task_fair, - .check_preempt_curr = check_preempt_wakeup, + .wakeup_preempt = check_preempt_wakeup_fair, + .pick_task = pick_task_fair, .pick_next_task = __pick_next_task_fair, .put_prev_task = put_prev_task_fair, .set_next_task = set_next_task_fair, #ifdef CONFIG_SMP .balance = balance_fair, - .pick_task = pick_task_fair, .select_task_rq = select_task_rq_fair, .migrate_task_rq = migrate_task_rq_fair, @@ -15316,6 +15301,7 @@ DEFINE_SCHED_CLASS(fair) = { .task_tick = task_tick_fair, .task_fork = task_fork_fair, + .reweight_task = reweight_task_fair, .prio_changed = prio_changed_fair, .switched_from = switched_from_fair, .switched_to = switched_to_fair, diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 86618f71918fe20cabe7c73fb50f645a77d44fbe..f093c3a021d7f9554403f9c2df504207f4c4586c 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -441,32 +441,27 @@ balance_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) /* * Idle tasks are unconditionally rescheduled: */ -static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int flags) +static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags) { resched_curr(rq); } -static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) +static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct task_struct *next) { + scx_update_idle(rq, false, true); } static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) { update_idle_core(rq); + scx_update_idle(rq, true, true); schedstat_inc(rq->sched_goidle); } -#ifdef CONFIG_SMP -static struct task_struct *pick_task_idle(struct rq *rq) -{ - return rq->idle; -} -#endif - -struct task_struct *pick_next_task_idle(struct rq *rq) +struct task_struct *pick_task_idle(struct rq *rq) { - struct task_struct *next = rq->idle; - + scx_update_idle(rq, true, false); + #ifdef CONFIG_SCHED_SOFT_QUOTA if (sched_feat(SOFT_QUOTA)) { if (unthrottle_cfs_rq_soft_quota(rq) && rq->cfs.nr_running) @@ -474,22 +469,21 @@ struct task_struct *pick_next_task_idle(struct rq *rq) } #endif - set_next_task_idle(rq, next, true); - - return next; + return rq->idle; } /* * It is not legal to sleep in the idle task - print a warning * message if some code attempts to do it: */ -static void +static bool dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags) { raw_spin_rq_unlock_irq(rq); printk(KERN_ERR "bad: scheduling from the idle thread!\n"); dump_stack(); raw_spin_rq_lock_irq(rq); + return true; } /* @@ -529,15 +523,14 @@ DEFINE_SCHED_CLASS(idle) = { /* dequeue is not valid, we print a debug message there: */ .dequeue_task = dequeue_task_idle, - .check_preempt_curr = check_preempt_curr_idle, + .wakeup_preempt = wakeup_preempt_idle, - .pick_next_task = pick_next_task_idle, + .pick_task = pick_task_idle, .put_prev_task = put_prev_task_idle, .set_next_task = set_next_task_idle, #ifdef CONFIG_SMP .balance = balance_idle, - .pick_task = pick_task_idle, .select_task_rq = select_task_rq_idle, .set_cpus_allowed = set_cpus_allowed_common, #endif diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 549b9ecfda7dd19e94aa5734ab8b20b3f40ebde6..caa4144be1d17fcc9793b5426a18a9565240cf1c 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -957,7 +957,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) /* * When we're idle and a woken (rt) task is - * throttled check_preempt_curr() will set + * throttled wakeup_preempt() will set * skip_update and the time between the wakeup * and this unthrottle will get accounted as * 'runtime'. @@ -1050,24 +1050,15 @@ static void update_curr_rt(struct rq *rq) { struct task_struct *curr = rq->curr; struct sched_rt_entity *rt_se = &curr->rt; - u64 delta_exec; - u64 now; + s64 delta_exec; if (curr->sched_class != &rt_sched_class) return; - now = rq_clock_task(rq); - delta_exec = now - curr->se.exec_start; - if (unlikely((s64)delta_exec <= 0)) + delta_exec = update_curr_common(rq); + if (unlikely(delta_exec <= 0)) return; - schedstat_set(curr->stats.exec_max, - max(curr->stats.exec_max, delta_exec)); - - trace_sched_stat_runtime(curr, delta_exec, 0); - - update_current_exec_runtime(curr, now, delta_exec); - if (!rt_bandwidth_enabled()) return; @@ -1552,7 +1543,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags) enqueue_pushable_task(rq, p); } -static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) +static bool dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) { struct sched_rt_entity *rt_se = &p->rt; @@ -1560,6 +1551,8 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) dequeue_rt_entity(rt_se, flags); dequeue_pushable_task(rq, p); + + return true; } /* @@ -1719,7 +1712,7 @@ static int balance_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf) /* * Preempt the current task with a newly woken task if needed: */ -static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flags) +static void wakeup_preempt_rt(struct rq *rq, struct task_struct *p, int flags) { if (p->prio < rq->curr->prio) { resched_curr(rq); @@ -1815,17 +1808,7 @@ static struct task_struct *pick_task_rt(struct rq *rq) return p; } -static struct task_struct *pick_next_task_rt(struct rq *rq) -{ - struct task_struct *p = pick_task_rt(rq); - - if (p) - set_next_task_rt(rq, p, true); - - return p; -} - -static void put_prev_task_rt(struct rq *rq, struct task_struct *p) +static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct task_struct *next) { struct sched_rt_entity *rt_se = &p->rt; struct rt_rq *rt_rq = &rq->rt; @@ -2711,15 +2694,14 @@ DEFINE_SCHED_CLASS(rt) = { .dequeue_task = dequeue_task_rt, .yield_task = yield_task_rt, - .check_preempt_curr = check_preempt_curr_rt, + .wakeup_preempt = wakeup_preempt_rt, - .pick_next_task = pick_next_task_rt, + .pick_task = pick_task_rt, .put_prev_task = put_prev_task_rt, .set_next_task = set_next_task_rt, #ifdef CONFIG_SMP .balance = balance_rt, - .pick_task = pick_task_rt, .select_task_rq = select_task_rq_rt, .set_cpus_allowed = set_cpus_allowed_common, .rq_online = rq_online_rt, diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 0e21ad151ec952c84c393a6bd98e48b1ffc18878..f923dff7a911a36364b6963d5ad0c2f3d5f441e6 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -69,6 +69,9 @@ #include #include #include +#ifndef __GENKSYMS__ +#include +#endif #include #include @@ -188,9 +191,19 @@ static inline int idle_policy(int policy) { return policy == SCHED_IDLE; } + +static inline int normal_policy(int policy) +{ +#ifdef CONFIG_SCHED_CLASS_EXT + if (policy == SCHED_EXT) + return true; +#endif + return policy == SCHED_NORMAL; +} + static inline int fair_policy(int policy) { - return policy == SCHED_NORMAL || policy == SCHED_BATCH; + return normal_policy(policy) || policy == SCHED_BATCH; } static inline int rt_policy(int policy) @@ -238,6 +251,24 @@ static inline void update_avg(u64 *avg, u64 sample) #define shr_bound(val, shift) \ (val >> min_t(typeof(shift), shift, BITS_PER_TYPE(typeof(val)) - 1)) +/* + * cgroup weight knobs should use the common MIN, DFL and MAX values which are + * 1, 100 and 10000 respectively. While it loses a bit of range on both ends, it + * maps pretty well onto the shares value used by scheduler and the round-trip + * conversions preserve the original value over the entire range. + */ +static inline unsigned long sched_weight_from_cgroup(unsigned long cgrp_weight) +{ + return DIV_ROUND_CLOSEST_ULL(cgrp_weight * 1024, CGROUP_WEIGHT_DFL); +} + +static inline unsigned long sched_weight_to_cgroup(unsigned long weight) +{ + return clamp_t(unsigned long, + DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024), + CGROUP_WEIGHT_MIN, CGROUP_WEIGHT_MAX); +} + /* * !! For sched_setattr_nocheck() (kernel) only !! * @@ -424,10 +455,7 @@ struct task_group { /* runqueue "owned" by this group on each CPU */ struct cfs_rq **cfs_rq; unsigned long shares; - - /* A positive value indicates that this is a SCHED_IDLE group. */ - int idle; - + KABI_BROKEN_REMOVE(int idle) #ifdef CONFIG_SMP /* * load_avg can be heavily contended at clock tick time, so put @@ -489,15 +517,27 @@ struct task_group { #else KABI_RESERVE(2) #endif + +#ifdef CONFIG_EXT_GROUP_SCHED + KABI_USE2(3, u32 scx_flags, u32 scx_weight) /* SCX_TG_* */ +#else KABI_RESERVE(3) +#endif + +#ifdef CONFIG_GROUP_SCHED_WEIGHT + /* A positive value indicates that this is a SCHED_IDLE group. */ + KABI_USE(4, int idle) +#else KABI_RESERVE(4) +#endif + KABI_RESERVE(5) KABI_RESERVE(6) KABI_RESERVE(7) KABI_RESERVE(8) }; -#ifdef CONFIG_FAIR_GROUP_SCHED +#ifdef CONFIG_GROUP_SCHED_WEIGHT #define ROOT_TASK_GROUP_LOAD NICE_0_LOAD /* @@ -528,6 +568,11 @@ static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data) return walk_tg_tree_from(&root_task_group, down, up, data); } +static inline struct task_group *css_tg(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct task_group, css) : NULL; +} + extern int tg_nop(struct task_group *tg, void *data); #ifdef CONFIG_BPF_SCHED extern int tg_change_tag(struct task_group *tg, void *data); @@ -562,7 +607,7 @@ extern void sched_online_group(struct task_group *tg, extern void sched_destroy_group(struct task_group *tg); extern void sched_release_group(struct task_group *tg); -extern void sched_move_task(struct task_struct *tsk); +extern void sched_move_task(struct task_struct *tsk, bool for_autogroup); #ifdef CONFIG_QOS_SCHED_SMART_GRID extern void start_auto_affinity(struct auto_affinity *auto_affi); @@ -598,6 +643,9 @@ extern void set_task_rq_fair(struct sched_entity *se, static inline void set_task_rq_fair(struct sched_entity *se, struct cfs_rq *prev, struct cfs_rq *next) { } #endif /* CONFIG_SMP */ +#else /* !CONFIG_FAIR_GROUP_SCHED */ +static inline int sched_group_set_shares(struct task_group *tg, unsigned long shares) { return 0; } +static inline int sched_group_set_idle(struct task_group *tg, long idle) { return 0; } #endif /* CONFIG_FAIR_GROUP_SCHED */ #else /* CONFIG_CGROUP_SCHED */ @@ -659,6 +707,11 @@ do { \ # define u64_u32_load(var) u64_u32_load_copy(var, var##_copy) # define u64_u32_store(var, val) u64_u32_store_copy(var, var##_copy, val) +struct balance_callback { + struct balance_callback *next; + void (*func)(struct rq *rq); +}; + /* CFS-related fields in a runqueue */ struct cfs_rq { struct load_weight load; @@ -794,6 +847,47 @@ struct cfs_rq { KABI_RESERVE(8) }; +#ifdef CONFIG_SCHED_CLASS_EXT +/* scx_rq->flags, protected by the rq lock */ +enum scx_rq_flags { + /* + * A hotplugged CPU starts scheduling before rq_online_scx(). Track + * ops.cpu_on/offline() state so that ops.enqueue/dispatch() are called + * only while the BPF scheduler considers the CPU to be online. + */ + SCX_RQ_ONLINE = 1 << 0, + SCX_RQ_CAN_STOP_TICK = 1 << 1, + SCX_RQ_BAL_PENDING = 1 << 2, /* balance hasn't run yet */ + SCX_RQ_BAL_KEEP = 1 << 3, /* balance decided to keep current */ + SCX_RQ_BYPASSING = 1 << 4, + SCX_RQ_CLK_VALID = 1 << 5, /* RQ clock is fresh and valid */ + + SCX_RQ_IN_WAKEUP = 1 << 16, + SCX_RQ_IN_BALANCE = 1 << 17, +}; + +struct scx_rq { + struct scx_dispatch_q local_dsq; + struct list_head runnable_list; /* runnable tasks on this rq */ + struct list_head ddsp_deferred_locals; /* deferred ddsps from enq */ + unsigned long ops_qseq; + u64 extra_enq_flags; /* see move_task_to_local_dsq() */ + u32 nr_running; + u32 cpuperf_target; /* [0, SCHED_CAPACITY_SCALE] */ + bool cpu_released; + u32 flags; + u64 clock; /* current per-rq clock -- see scx_bpf_now() */ + cpumask_var_t cpus_to_kick; + cpumask_var_t cpus_to_kick_if_idle; + cpumask_var_t cpus_to_preempt; + cpumask_var_t cpus_to_wait; + unsigned long pnt_seq; + struct balance_callback deferred_bal_cb; + struct irq_work deferred_irq_work; + struct irq_work kick_cpus_irq_work; +}; +#endif /* CONFIG_SCHED_CLASS_EXT */ + static inline int rt_bandwidth_enabled(void) { return sysctl_sched_rt_runtime >= 0; @@ -1094,11 +1188,6 @@ DECLARE_STATIC_KEY_FALSE(sched_uclamp_used); #endif /* CONFIG_UCLAMP_TASK */ struct rq; -struct balance_callback { - struct balance_callback *next; - void (*func)(struct rq *rq); -}; - /* * This is the main, per-CPU runqueue data structure. * @@ -1338,6 +1427,9 @@ struct rq { KABI_RESERVE(6) KABI_RESERVE(7) KABI_RESERVE(8) +#if defined(CONFIG_SCHED_CLASS_EXT) + KABI_EXTEND(struct scx_rq scx) +#endif }; #ifdef CONFIG_FAIR_GROUP_SCHED @@ -1779,6 +1871,38 @@ struct rq_flags { extern struct balance_callback balance_push_callback; +#ifdef CONFIG_SCHED_CLASS_EXT +extern const struct sched_class ext_sched_class; + +DECLARE_STATIC_KEY_FALSE(__scx_ops_enabled); /* SCX BPF scheduler loaded */ +DECLARE_STATIC_KEY_FALSE(__scx_switched_all); /* all fair class tasks on SCX */ + +#define scx_enabled() static_branch_unlikely(&__scx_ops_enabled) +#define scx_switched_all() static_branch_unlikely(&__scx_switched_all) + +static inline void scx_rq_clock_update(struct rq *rq, u64 clock) +{ + if (!scx_enabled()) + return; + WRITE_ONCE(rq->scx.clock, clock); + smp_store_release(&rq->scx.flags, rq->scx.flags | SCX_RQ_CLK_VALID); +} + +static inline void scx_rq_clock_invalidate(struct rq *rq) +{ + if (!scx_enabled()) + return; + WRITE_ONCE(rq->scx.flags, rq->scx.flags & ~SCX_RQ_CLK_VALID); +} + +#else /* !CONFIG_SCHED_CLASS_EXT */ +#define scx_enabled() false +#define scx_switched_all() false + +static inline void scx_rq_clock_update(struct rq *rq, u64 clock) {} +static inline void scx_rq_clock_invalidate(struct rq *rq) {} +#endif /* !CONFIG_SCHED_CLASS_EXT */ + /* * Lockdep annotation that avoids accidental unlocks; it's like a * sticky/continuous lockdep_assert_held(). @@ -1808,7 +1932,7 @@ static inline void rq_unpin_lock(struct rq *rq, struct rq_flags *rf) if (rq->clock_update_flags > RQCF_ACT_SKIP) rf->clock_update_flags = RQCF_UPDATED; #endif - + scx_rq_clock_invalidate(rq); lockdep_unpin_lock(__rq_lockp(rq), rf->cookie); } @@ -1848,6 +1972,11 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf) raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); } +DEFINE_LOCK_GUARD_1(task_rq_lock, struct task_struct, + _T->rq = task_rq_lock(_T->lock, &_T->rf), + task_rq_unlock(_T->rq, _T->lock, &_T->rf), + struct rq *rq; struct rq_flags rf) + static inline void rq_lock_irqsave(struct rq *rq, struct rq_flags *rf) __acquires(rq->lock) @@ -2364,6 +2493,7 @@ static inline int task_on_rq_migrating(struct task_struct *p) #define WF_SYNC 0x10 /* Waker goes to sleep after wakeup */ #define WF_MIGRATED 0x20 /* Internal use, task got migrated */ #define WF_CURRENT_CPU 0x40 /* Prefer to move the wakee to the current CPU. */ +#define WF_RQ_SELECTED 0x80 /* ->select_task_rq() was called */ #ifdef CONFIG_SMP static_assert(WF_EXEC == SD_BALANCE_EXEC); @@ -2399,9 +2529,14 @@ extern const u32 sched_prio_to_wmult[40]; * MOVE - paired with SAVE/RESTORE, explicitly does not preserve the location * in the runqueue. * + * NOCLOCK - skip the update_rq_clock() (avoids double updates) + * + * MIGRATION - p->on_rq == TASK_ON_RQ_MIGRATING (used for DEADLINE) + * * ENQUEUE_HEAD - place at front of runqueue (tail if not specified) * ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline) * ENQUEUE_MIGRATED - the task was migrated during wakeup + * ENQUEUE_RQ_SELECTED - ->select_task_rq() was called * */ @@ -2409,6 +2544,7 @@ extern const u32 sched_prio_to_wmult[40]; #define DEQUEUE_SAVE 0x02 /* Matches ENQUEUE_RESTORE */ #define DEQUEUE_MOVE 0x04 /* Matches ENQUEUE_MOVE */ #define DEQUEUE_NOCLOCK 0x08 /* Matches ENQUEUE_NOCLOCK */ +#define DEQUEUE_MIGRATING 0x100 /* Matches ENQUEUE_MIGRATING */ #define ENQUEUE_WAKEUP 0x01 #define ENQUEUE_RESTORE 0x02 @@ -2423,6 +2559,8 @@ extern const u32 sched_prio_to_wmult[40]; #define ENQUEUE_MIGRATED 0x00 #endif #define ENQUEUE_INITIAL 0x80 +#define ENQUEUE_MIGRATING 0x100 +#define ENQUEUE_RQ_SELECTED 0x400 #define RETRY_TASK ((void *)-1UL) @@ -2432,6 +2570,8 @@ struct affinity_context { unsigned int flags; }; +extern s64 update_curr_common(struct rq *rq); + struct sched_class { #ifdef CONFIG_UCLAMP_TASK @@ -2439,22 +2579,37 @@ struct sched_class { #endif void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags); - void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags); + KABI_REPLACE(void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags), + bool (*dequeue_task)(struct rq *rq, struct task_struct *p, int flags)) void (*yield_task) (struct rq *rq); bool (*yield_to_task)(struct rq *rq, struct task_struct *p); - void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags); + KABI_REPLACE(void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags), + void (*wakeup_preempt)(struct rq *rq, struct task_struct *p, int flags)) - struct task_struct *(*pick_next_task)(struct rq *rq); + /* + * Optional! When implemented pick_next_task() should be equivalent to: + * + * next = pick_task(); + * if (next) { + * put_prev_task(prev); + * set_next_task_first(next); + * } + */ + KABI_REPLACE(struct task_struct *(*pick_next_task)(struct rq *rq), + struct task_struct *(*pick_next_task)(struct rq *rq, struct task_struct *prev)) - void (*put_prev_task)(struct rq *rq, struct task_struct *p); + KABI_REPLACE(void (*put_prev_task)(struct rq *rq, struct task_struct *p), + void (*put_prev_task)(struct rq *rq, + struct task_struct *p, struct task_struct *next)) void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first); #ifdef CONFIG_SMP - int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf); + KABI_BROKEN_REMOVE(int (*balance)(struct rq *rq, + struct task_struct *prev, struct rq_flags *rf)) int (*select_task_rq)(struct task_struct *p, int task_cpu, int flags); - struct task_struct * (*pick_task)(struct rq *rq); + KABI_BROKEN_REMOVE(struct task_struct * (*pick_task)(struct rq *rq)) void (*migrate_task_rq)(struct task_struct *p, int new_cpu); @@ -2494,14 +2649,18 @@ struct sched_class { #if defined(CONFIG_SCHED_CORE) || defined(CONFIG_CGROUP_IFS) int (*task_is_throttled)(struct task_struct *p, int cpu); #endif - KABI_RESERVE(1) - KABI_RESERVE(2) + KABI_USE(1, void (*reweight_task)(struct rq *this_rq, + struct task_struct *task, const struct load_weight *lw)) + KABI_USE(2, void (*switching_to) (struct rq *this_rq, struct task_struct *task)) + KABI_EXTEND(void (*switch_class)(struct rq *rq, struct task_struct *next)) + KABI_EXTEND(int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)) + KABI_EXTEND(struct task_struct *(*pick_task)(struct rq *rq)) }; static inline void put_prev_task(struct rq *rq, struct task_struct *prev) { WARN_ON_ONCE(rq->curr != prev); - prev->sched_class->put_prev_task(rq, prev); + prev->sched_class->put_prev_task(rq, prev, NULL); } static inline void set_next_task(struct rq *rq, struct task_struct *next) @@ -2509,6 +2668,18 @@ static inline void set_next_task(struct rq *rq, struct task_struct *next) next->sched_class->set_next_task(rq, next, false); } +static inline void put_prev_set_next_task(struct rq *rq, + struct task_struct *prev, + struct task_struct *next) +{ + WARN_ON_ONCE(rq->curr != prev); + + if (next == prev) + return; + + prev->sched_class->put_prev_task(rq, prev, next); + next->sched_class->set_next_task(rq, next, true); +} /* * Helper to define a sched_class instance; each one is placed in a separate @@ -2529,19 +2700,41 @@ const struct sched_class name##_sched_class \ extern struct sched_class __sched_class_highest[]; extern struct sched_class __sched_class_lowest[]; +extern const struct sched_class stop_sched_class; +extern const struct sched_class dl_sched_class; +extern const struct sched_class rt_sched_class; +extern const struct sched_class fair_sched_class; +extern const struct sched_class idle_sched_class; + +/* + * Iterate only active classes. SCX can take over all fair tasks or be + * completely disabled. If the former, skip fair. If the latter, skip SCX. + */ +static inline const struct sched_class *next_active_class(const struct sched_class *class) +{ + class++; +#ifdef CONFIG_SCHED_CLASS_EXT + if (scx_switched_all() && class == &fair_sched_class) + class++; + if (!scx_enabled() && class == &ext_sched_class) + class++; +#endif + return class; +} + #define for_class_range(class, _from, _to) \ for (class = (_from); class < (_to); class++) #define for_each_class(class) \ for_class_range(class, __sched_class_highest, __sched_class_lowest) -#define sched_class_above(_a, _b) ((_a) < (_b)) +#define for_active_class_range(class, _from, _to) \ + for (class = (_from); class != (_to); class = next_active_class(class)) -extern const struct sched_class stop_sched_class; -extern const struct sched_class dl_sched_class; -extern const struct sched_class rt_sched_class; -extern const struct sched_class fair_sched_class; -extern const struct sched_class idle_sched_class; +#define for_each_active_class(class) \ + for_active_class_range(class, __sched_class_highest, __sched_class_lowest) + +#define sched_class_above(_a, _b) ((_a) < (_b)) static inline bool sched_stop_runnable(struct rq *rq) { @@ -2564,7 +2757,7 @@ static inline bool sched_fair_runnable(struct rq *rq) } extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf); -extern struct task_struct *pick_next_task_idle(struct rq *rq); +extern struct task_struct *pick_task_idle(struct rq *rq); #define SCA_CHECK 0x01 #define SCA_MIGRATE_DISABLE 0x02 @@ -2577,8 +2770,32 @@ extern void update_group_capacity(struct sched_domain *sd, int cpu); extern void trigger_load_balance(struct rq *rq); +extern int __set_cpus_allowed_ptr(struct task_struct *p, struct affinity_context *ctx); extern void set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx); +static inline bool task_allowed_on_cpu(struct task_struct *p, int cpu) +{ + /* When not in the task's cpumask, no point in looking further. */ + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + return false; + + /* Can @cpu run a user thread? */ + if (!(p->flags & PF_KTHREAD) && !task_cpu_possible(cpu, p)) + return false; + + return true; +} + +static inline cpumask_t *alloc_user_cpus_ptr(int node) +{ + /* + * See do_set_cpus_allowed() above for the rcu_head usage. + */ + int size = max_t(int, cpumask_size(), sizeof(struct rcu_head)); + + return kmalloc_node(size, GFP_KERNEL, node); +} + static inline struct task_struct *get_push_task(struct rq *rq) { struct task_struct *p = rq->curr; @@ -2600,7 +2817,25 @@ static inline struct task_struct *get_push_task(struct rq *rq) extern int push_cpu_stop(void *arg); -#endif +#else /* !CONFIG_SMP: */ + +static inline bool task_allowed_on_cpu(struct task_struct *p, int cpu) +{ + return true; +} + +static inline int __set_cpus_allowed_ptr(struct task_struct *p, + struct affinity_context *ctx) +{ + return set_cpus_allowed_ptr(p, ctx->new_mask); +} + +static inline cpumask_t *alloc_user_cpus_ptr(int node) +{ + return NULL; +} + +#endif /* !CONFIG_SMP */ #ifdef CONFIG_CPU_IDLE static inline void idle_set_state(struct rq *rq, @@ -2638,8 +2873,6 @@ extern void init_sched_dl_class(void); extern void init_sched_rt_class(void); extern void init_sched_fair_class(void); -extern void reweight_task(struct task_struct *p, const struct load_weight *lw); - extern void resched_curr(struct rq *rq); extern void resched_cpu(int cpu); @@ -2719,7 +2952,7 @@ static inline void sub_nr_running(struct rq *rq, unsigned count) extern void activate_task(struct rq *rq, struct task_struct *p, int flags); extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags); -extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags); +extern void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags); #ifdef CONFIG_PREEMPT_RT #define SCHED_NR_MIGRATE_BREAK 8 @@ -3189,24 +3422,16 @@ static inline unsigned long capacity_orig_of(int cpu) return cpu_rq(cpu)->cpu_capacity_orig; } -/** - * enum cpu_util_type - CPU utilization type - * @FREQUENCY_UTIL: Utilization used to select frequency - * @ENERGY_UTIL: Utilization used during energy calculation - * - * The utilization signals of all scheduling classes (CFS/RT/DL) and IRQ time - * need to be aggregated differently depending on the usage made of them. This - * enum is used within effective_cpu_util() to differentiate the types of - * utilization expected by the callers, and adjust the aggregation accordingly. - */ -enum cpu_util_type { - FREQUENCY_UTIL, - ENERGY_UTIL, -}; +bool update_other_load_avgs(struct rq *rq); unsigned long effective_cpu_util(int cpu, unsigned long util_cfs, - enum cpu_util_type type, - struct task_struct *p); + unsigned long *min, + unsigned long *max); + +unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual, + unsigned long min, + unsigned long max); + /* * Verify the fitness of task @p to run on @cpu taking into account the @@ -3241,7 +3466,10 @@ static inline unsigned long cpu_util_rt(struct rq *rq) { return READ_ONCE(rq->avg_rt.util_avg); } -#endif + +#else /* !CONFIG_SMP */ +static inline bool update_other_load_avgs(struct rq *rq) { return false; } +#endif /* CONFIG_SMP */ #ifdef CONFIG_UCLAMP_TASK unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id); @@ -3343,6 +3571,36 @@ static inline bool uclamp_is_used(void) { return static_branch_likely(&sched_uclamp_used); } + +#define for_each_clamp_id(clamp_id) \ + for ((clamp_id) = 0; (clamp_id) < UCLAMP_CNT; (clamp_id)++) + +extern unsigned int sysctl_sched_uclamp_util_min_rt_default; + + +static inline unsigned int uclamp_none(enum uclamp_id clamp_id) +{ + if (clamp_id == UCLAMP_MIN) + return 0; + return SCHED_CAPACITY_SCALE; +} + +/* Integer rounded range for each bucket */ +#define UCLAMP_BUCKET_DELTA DIV_ROUND_CLOSEST(SCHED_CAPACITY_SCALE, UCLAMP_BUCKETS) + +static inline unsigned int uclamp_bucket_id(unsigned int clamp_value) +{ + return min_t(unsigned int, clamp_value / UCLAMP_BUCKET_DELTA, UCLAMP_BUCKETS - 1); +} + +static inline void uclamp_se_set(struct uclamp_se *uc_se, + unsigned int value, bool user_defined) +{ + uc_se->value = value; + uc_se->bucket_id = uclamp_bucket_id(value); + uc_se->user_defined = user_defined; +} + #else /* CONFIG_UCLAMP_TASK */ static inline unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id) @@ -3385,6 +3643,7 @@ static inline bool uclamp_rq_is_idle(struct rq *rq) { return false; } + #endif /* CONFIG_UCLAMP_TASK */ #ifdef CONFIG_HAVE_SCHED_AVG_IRQ @@ -3516,16 +3775,6 @@ extern int sched_dynamic_mode(const char *str); extern void sched_dynamic_update(int mode); #endif -static inline void update_current_exec_runtime(struct task_struct *curr, - u64 now, u64 delta_exec) -{ - curr->se.sum_exec_runtime += delta_exec; - account_group_exec_runtime(curr, delta_exec); - - curr->se.exec_start = now; - cgroup_account_cputime(curr, delta_exec); -} - #ifdef CONFIG_SCHED_MM_CID #define SCHED_MM_CID_PERIOD_NS (100ULL * 1000000) /* 100ms */ @@ -3772,7 +4021,90 @@ extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se); #ifdef CONFIG_BPF_SCHED bool bpf_sched_is_cpu_allowed(struct task_struct *p, int cpu); -#endif +#endif /* CONFIG_BPF_SCHED */ +#ifdef CONFIG_RT_MUTEXES +static inline int __rt_effective_prio(struct task_struct *pi_task, int prio) +{ + if (pi_task) + prio = min(prio, pi_task->prio); + + return prio; +} + +static inline int rt_effective_prio(struct task_struct *p, int prio) +{ + struct task_struct *pi_task = rt_mutex_get_top_task(p); + + return __rt_effective_prio(pi_task, prio); +} +#else +static inline int rt_effective_prio(struct task_struct *p, int prio) +{ + return prio; +} +#endif /* CONFIG_RT_MUTEXES */ + +static inline int __normal_prio(int policy, int rt_prio, int nice) +{ + int prio; + + if (dl_policy(policy)) + prio = MAX_DL_PRIO - 1; + else if (rt_policy(policy)) + prio = MAX_RT_PRIO - 1 - rt_prio; + else + prio = NICE_TO_PRIO(nice); + + return prio; +} + +/* + * Calculate the expected normal priority: i.e. priority + * without taking RT-inheritance into account. Might be + * boosted by interactivity modifiers. Changes upon fork, + * setprio syscalls, and whenever the interactivity + * estimator recalculates. + */ +static inline int normal_prio(struct task_struct *p) +{ + return __normal_prio(p->policy, p->rt_priority, PRIO_TO_NICE(p->static_prio)); +} + +extern int __sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, bool user, bool pi); +extern int __sched_setaffinity(struct task_struct *p, struct affinity_context *ctx); +extern void __setscheduler_prio(struct task_struct *p, int prio); +extern void __setscheduler_params(struct task_struct *p, const struct sched_attr *attr); +/* + * pick from mainline + * 98442f0ccd82 ("sched: Fix delayed_dequeue vs switched_from_fair()") + * 5db91545ef81 ("sched: Pass correct scheduling policy to __setscheduler_class") + */ +extern const struct sched_class *__setscheduler_class(int policy, int prio); +extern void set_load_weight(struct task_struct *p, bool update_load); +extern void enqueue_task(struct rq *rq, struct task_struct *p, int flags); +extern bool dequeue_task(struct rq *rq, struct task_struct *p, int flags); + +extern void check_class_changing(struct rq *rq, struct task_struct *p, + const struct sched_class *prev_class); +extern void check_class_changed(struct rq *rq, struct task_struct *p, + const struct sched_class *prev_class, + int oldprio); + +#ifdef CONFIG_SMP +extern struct balance_callback *splice_balance_callbacks(struct rq *rq); +extern void balance_callbacks(struct rq *rq, struct balance_callback *head); +#else + +static inline struct balance_callback *splice_balance_callbacks(struct rq *rq) +{ + return NULL; +} + +static inline void balance_callbacks(struct rq *rq, struct balance_callback *head) +{ +} + +#endif /* CONFIG_SMP */ #ifdef CONFIG_SCHED_SOFT_DOMAIN void build_soft_domain(void); @@ -3802,5 +4134,24 @@ static inline int destroy_soft_domain(struct task_group *tg) } #endif +#ifdef CONFIG_SCHED_CLASS_EXT +/* + * Used by SCX in the enable/disable paths to move tasks between sched_classes + * and establish invariants. + */ +struct sched_enq_and_set_ctx { + struct task_struct *p; + int queue_flags; + bool queued; + bool running; +}; + +void sched_deq_and_put_task(struct task_struct *p, int queue_flags, + struct sched_enq_and_set_ctx *ctx); +void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx); + +#endif /* CONFIG_SCHED_CLASS_EXT */ + +#include "ext.h" #endif /* _KERNEL_SCHED_SCHED_H */ diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index 85590599b4d60545b7774222971f8f7baa678dac..058dd42e3d9b52c8fd7e378d55cea642547afca8 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -23,7 +23,7 @@ balance_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) #endif /* CONFIG_SMP */ static void -check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags) +wakeup_preempt_stop(struct rq *rq, struct task_struct *p, int flags) { /* we're never preempted */ } @@ -41,26 +41,17 @@ static struct task_struct *pick_task_stop(struct rq *rq) return rq->stop; } -static struct task_struct *pick_next_task_stop(struct rq *rq) -{ - struct task_struct *p = pick_task_stop(rq); - - if (p) - set_next_task_stop(rq, p, true); - - return p; -} - static void enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags) { add_nr_running(rq, 1); } -static void +static bool dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags) { sub_nr_running(rq, 1); + return true; } static void yield_task_stop(struct rq *rq) @@ -68,20 +59,9 @@ static void yield_task_stop(struct rq *rq) BUG(); /* the stop task should never yield, its pointless. */ } -static void put_prev_task_stop(struct rq *rq, struct task_struct *prev) +static void put_prev_task_stop(struct rq *rq, struct task_struct *prev, struct task_struct *next) { - struct task_struct *curr = rq->curr; - u64 now, delta_exec; - - now = rq_clock_task(rq); - delta_exec = now - curr->se.exec_start; - if (unlikely((s64)delta_exec < 0)) - delta_exec = 0; - - schedstat_set(curr->stats.exec_max, - max(curr->stats.exec_max, delta_exec)); - - update_current_exec_runtime(curr, now, delta_exec); + update_curr_common(rq); } /* @@ -120,15 +100,14 @@ DEFINE_SCHED_CLASS(stop) = { .dequeue_task = dequeue_task_stop, .yield_task = yield_task_stop, - .check_preempt_curr = check_preempt_curr_stop, + .wakeup_preempt = wakeup_preempt_stop, - .pick_next_task = pick_next_task_stop, + .pick_task = pick_task_stop, .put_prev_task = put_prev_task_stop, .set_next_task = set_next_task_stop, #ifdef CONFIG_SMP .balance = balance_stop, - .pick_task = pick_task_stop, .select_task_rq = select_task_rq_stop, .set_cpus_allowed = set_cpus_allowed_common, #endif diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c new file mode 100644 index 0000000000000000000000000000000000000000..396fb2518c79e9702ca940cd29003a8c1973d86e --- /dev/null +++ b/kernel/sched/syscalls.c @@ -0,0 +1,1713 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * kernel/sched/syscalls.c + * + * Core kernel scheduler syscalls related code + * + * Copyright (C) 1991-2002 Linus Torvalds + * Copyright (C) 1998-2024 Ingo Molnar, Red Hat + */ +#include +#include +#include + +#include + +#include "sched.h" +#include "autogroup.h" + +/* + * Calculate the current priority, i.e. the priority + * taken into account by the scheduler. This value might + * be boosted by RT tasks, or might be boosted by + * interactivity modifiers. Will be RT if the task got + * RT-boosted. If not then it returns p->normal_prio. + */ +static int effective_prio(struct task_struct *p) +{ + p->normal_prio = normal_prio(p); + /* + * If we are RT tasks or we were boosted to RT priority, + * keep the priority unchanged. Otherwise, update priority + * to the normal priority: + */ + if (!rt_prio(p->prio)) + return p->normal_prio; + return p->prio; +} + +void set_user_nice(struct task_struct *p, long nice) +{ + bool queued, running; + struct rq *rq; + int old_prio; + + if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE) + return; + /* + * We have to be careful, if called from sys_setpriority(), + * the task might be in the middle of scheduling on another CPU. + */ + CLASS(task_rq_lock, rq_guard)(p); + rq = rq_guard.rq; + + update_rq_clock(rq); + + /* + * The RT priorities are set via sched_setscheduler(), but we still + * allow the 'normal' nice value to be set - but as expected + * it won't have any effect on scheduling until the task is + * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR: + */ + if (task_has_dl_policy(p) || task_has_rt_policy(p)) { + p->static_prio = NICE_TO_PRIO(nice); + return; + } + + queued = task_on_rq_queued(p); + running = task_current(rq, p); + if (queued) + dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK); + if (running) + put_prev_task(rq, p); + + p->static_prio = NICE_TO_PRIO(nice); + set_load_weight(p, true); + old_prio = p->prio; + p->prio = effective_prio(p); + + if (queued) + enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK); + if (running) + set_next_task(rq, p); + + /* + * If the task increased its priority or is running and + * lowered its priority, then reschedule its CPU: + */ + p->sched_class->prio_changed(rq, p, old_prio); +} + +/* + * is_nice_reduction - check if nice value is an actual reduction + * + * Similar to can_nice() but does not perform a capability check. + * + * @p: task + * @nice: nice value + */ +static bool is_nice_reduction(const struct task_struct *p, const int nice) +{ + /* Convert nice value [19,-20] to rlimit style value [1,40]: */ + int nice_rlim = nice_to_rlimit(nice); + + return (nice_rlim <= task_rlimit(p, RLIMIT_NICE)); +} + +/* + * can_nice - check if a task can reduce its nice value + * @p: task + * @nice: nice value + */ +int can_nice(const struct task_struct *p, const int nice) +{ + return is_nice_reduction(p, nice) || capable(CAP_SYS_NICE); +} + +#ifdef __ARCH_WANT_SYS_NICE + +/* + * sys_nice - change the priority of the current process. + * @increment: priority increment + * + * sys_setpriority is a more generic, but much slower function that + * does similar things. + */ +SYSCALL_DEFINE1(nice, int, increment) +{ + long nice, retval; + + /* + * Setpriority might change our priority at the same moment. + * We don't have to worry. Conceptually one call occurs first + * and we have a single winner. + */ + increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH); + nice = task_nice(current) + increment; + + nice = clamp_val(nice, MIN_NICE, MAX_NICE); + if (increment < 0 && !can_nice(current, nice)) + return -EPERM; + + retval = security_task_setnice(current, nice); + if (retval) + return retval; + + set_user_nice(current, nice); + return 0; +} + +#endif + +/** + * task_prio - return the priority value of a given task. + * @p: the task in question. + * + * Return: The priority value as seen by users in /proc. + * + * sched policy return value kernel prio user prio/nice + * + * normal, batch, idle [0 ... 39] [100 ... 139] 0/[-20 ... 19] + * fifo, rr [-2 ... -100] [98 ... 0] [1 ... 99] + * deadline -101 -1 0 + */ +int task_prio(const struct task_struct *p) +{ + return p->prio - MAX_RT_PRIO; +} + +/** + * idle_cpu - is a given CPU idle currently? + * @cpu: the processor in question. + * + * Return: 1 if the CPU is currently idle. 0 otherwise. + */ +int idle_cpu(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + if (rq->curr != rq->idle) + return 0; + + if (rq->nr_running) + return 0; + +#ifdef CONFIG_SMP + if (rq->ttwu_pending) + return 0; +#endif + + return 1; +} + +/** + * available_idle_cpu - is a given CPU idle for enqueuing work. + * @cpu: the CPU in question. + * + * Return: 1 if the CPU is currently idle. 0 otherwise. + */ +int available_idle_cpu(int cpu) +{ + if (!idle_cpu(cpu)) + return 0; + + if (vcpu_is_preempted(cpu)) + return 0; + + return 1; +} + +/** + * idle_task - return the idle task for a given CPU. + * @cpu: the processor in question. + * + * Return: The idle task for the CPU @cpu. + */ +struct task_struct *idle_task(int cpu) +{ + return cpu_rq(cpu)->idle; +} + +#ifdef CONFIG_SCHED_CORE +int sched_core_idle_cpu(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + if (sched_core_enabled(rq) && rq->curr == rq->idle) + return 1; + + return idle_cpu(cpu); +} + +#endif + +#ifdef CONFIG_SMP +/* + * Load avg and utiliztion metrics need to be updated periodically and before + * consumption. This function updates the metrics for all subsystems except for + * the fair class. @rq must be locked and have its clock updated. + */ +bool update_other_load_avgs(struct rq *rq) +{ + u64 now = rq_clock_pelt(rq); + const struct sched_class *curr_class = rq->curr->sched_class; + unsigned long hw_pressure = arch_scale_thermal_pressure(cpu_of(rq)); + + lockdep_assert_rq_held(rq); + + return update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) | + update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) | + update_thermal_load_avg(now, rq, hw_pressure) | + update_irq_load_avg(rq, 0); +} + +/* + * This function computes an effective utilization for the given CPU, to be + * used for frequency selection given the linear relation: f = u * f_max. + * + * The scheduler tracks the following metrics: + * + * cpu_util_{cfs,rt,dl,irq}() + * cpu_bw_dl() + * + * Where the cfs,rt and dl util numbers are tracked with the same metric and + * synchronized windows and are thus directly comparable. + * + * The cfs,rt,dl utilization are the running times measured with rq->clock_task + * which excludes things like IRQ and steal-time. These latter are then accrued + * in the irq utilization. + * + * The DL bandwidth number otoh is not a measured metric but a value computed + * based on the task model parameters and gives the minimal utilization + * required to meet deadlines. + */ +unsigned long effective_cpu_util(int cpu, unsigned long util_cfs, + unsigned long *min, + unsigned long *max) +{ + unsigned long util, irq, scale; + struct rq *rq = cpu_rq(cpu); + + scale = arch_scale_cpu_capacity(cpu); + + /* + * Early check to see if IRQ/steal time saturates the CPU, can be + * because of inaccuracies in how we track these -- see + * update_irq_load_avg(). + */ + irq = cpu_util_irq(rq); + if (unlikely(irq >= scale)) { + if (min) + *min = scale; + if (max) + *max = scale; + return scale; + } + + if (min) { + /* + * The minimum utilization returns the highest level between: + * - the computed DL bandwidth needed with the IRQ pressure which + * steals time to the deadline task. + * - The minimum performance requirement for CFS and/or RT. + */ + *min = max(irq + cpu_bw_dl(rq), uclamp_rq_get(rq, UCLAMP_MIN)); + + /* + * When an RT task is runnable and uclamp is not used, we must + * ensure that the task will run at maximum compute capacity. + */ + if (!uclamp_is_used() && rt_rq_is_runnable(&rq->rt)) + *min = max(*min, scale); + } + + /* + * Because the time spend on RT/DL tasks is visible as 'lost' time to + * CFS tasks and we use the same metric to track the effective + * utilization (PELT windows are synchronized) we can directly add them + * to obtain the CPU's actual utilization. + */ + util = util_cfs + cpu_util_rt(rq); + util += cpu_util_dl(rq); + + /* + * The maximum hint is a soft bandwidth requirement, which can be lower + * than the actual utilization because of uclamp_max requirements. + */ + if (max) + *max = min(scale, uclamp_rq_get(rq, UCLAMP_MAX)); + + if (util >= scale) + return scale; + + /* + * There is still idle time; further improve the number by using the + * irq metric. Because IRQ/steal time is hidden from the task clock we + * need to scale the task numbers: + * + * max - irq + * U' = irq + --------- * U + * max + */ + util = scale_irq_capacity(util, irq, scale); + util += irq; + + return min(scale, util); +} + +unsigned long sched_cpu_util(int cpu) +{ + return effective_cpu_util(cpu, cpu_util_cfs(cpu), NULL, NULL); +} +#endif /* CONFIG_SMP */ + +/** + * find_process_by_pid - find a process with a matching PID value. + * @pid: the pid in question. + * + * The task of @pid, if found. %NULL otherwise. + */ +static struct task_struct *find_process_by_pid(pid_t pid) +{ + return pid ? find_task_by_vpid(pid) : current; +} + +static struct task_struct *find_get_task(pid_t pid) +{ + struct task_struct *p; + guard(rcu)(); + + p = find_process_by_pid(pid); + if (likely(p)) + get_task_struct(p); + + return p; +} + +DEFINE_CLASS(find_get_task, struct task_struct *, if (_T) put_task_struct(_T), + find_get_task(pid), pid_t pid) + +/* + * sched_setparam() passes in -1 for its policy, to let the functions + * it calls know not to change it. + */ +#define SETPARAM_POLICY -1 + +void __setscheduler_params(struct task_struct *p, + const struct sched_attr *attr) +{ + int policy = attr->sched_policy; + + if (policy == SETPARAM_POLICY) + policy = p->policy; + + p->policy = policy; + + if (dl_policy(policy)) + __setparam_dl(p, attr); + else if (fair_policy(policy)) + p->static_prio = NICE_TO_PRIO(attr->sched_nice); + + /* rt-policy tasks do not have a timerslack */ + if (task_is_realtime(p)) { + p->timer_slack_ns = 0; + } else if (p->timer_slack_ns == 0) { + /* when switching back to non-rt policy, restore timerslack */ + p->timer_slack_ns = p->default_timer_slack_ns; + } + + /* + * __sched_setscheduler() ensures attr->sched_priority == 0 when + * !rt_policy. Always setting this ensures that things like + * getparam()/getattr() don't report silly values for !rt tasks. + */ + p->rt_priority = attr->sched_priority; + p->normal_prio = normal_prio(p); + set_load_weight(p, true); +} + +/* + * Check the target process has a UID that matches the current process's: + */ +static bool check_same_owner(struct task_struct *p) +{ + const struct cred *cred = current_cred(), *pcred; + guard(rcu)(); + + pcred = __task_cred(p); + return (uid_eq(cred->euid, pcred->euid) || + uid_eq(cred->euid, pcred->uid)); +} + +#ifdef CONFIG_UCLAMP_TASK + +static int uclamp_validate(struct task_struct *p, + const struct sched_attr *attr) +{ + int util_min = p->uclamp_req[UCLAMP_MIN].value; + int util_max = p->uclamp_req[UCLAMP_MAX].value; + + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) { + util_min = attr->sched_util_min; + + if (util_min + 1 > SCHED_CAPACITY_SCALE + 1) + return -EINVAL; + } + + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) { + util_max = attr->sched_util_max; + + if (util_max + 1 > SCHED_CAPACITY_SCALE + 1) + return -EINVAL; + } + + if (util_min != -1 && util_max != -1 && util_min > util_max) + return -EINVAL; + + /* + * We have valid uclamp attributes; make sure uclamp is enabled. + * + * We need to do that here, because enabling static branches is a + * blocking operation which obviously cannot be done while holding + * scheduler locks. + */ + static_branch_enable(&sched_uclamp_used); + + return 0; +} + +static bool uclamp_reset(const struct sched_attr *attr, + enum uclamp_id clamp_id, + struct uclamp_se *uc_se) +{ + /* Reset on sched class change for a non user-defined clamp value. */ + if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)) && + !uc_se->user_defined) + return true; + + /* Reset on sched_util_{min,max} == -1. */ + if (clamp_id == UCLAMP_MIN && + attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN && + attr->sched_util_min == -1) { + return true; + } + + if (clamp_id == UCLAMP_MAX && + attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX && + attr->sched_util_max == -1) { + return true; + } + + return false; +} + +static void __setscheduler_uclamp(struct task_struct *p, + const struct sched_attr *attr) +{ + enum uclamp_id clamp_id; + + for_each_clamp_id(clamp_id) { + struct uclamp_se *uc_se = &p->uclamp_req[clamp_id]; + unsigned int value; + + if (!uclamp_reset(attr, clamp_id, uc_se)) + continue; + + /* + * RT by default have a 100% boost value that could be modified + * at runtime. + */ + if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN)) + value = sysctl_sched_uclamp_util_min_rt_default; + else + value = uclamp_none(clamp_id); + + uclamp_se_set(uc_se, value, false); + + } + + if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP))) + return; + + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN && + attr->sched_util_min != -1) { + uclamp_se_set(&p->uclamp_req[UCLAMP_MIN], + attr->sched_util_min, true); + } + + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX && + attr->sched_util_max != -1) { + uclamp_se_set(&p->uclamp_req[UCLAMP_MAX], + attr->sched_util_max, true); + } +} + +#else /* !CONFIG_UCLAMP_TASK: */ + +static inline int uclamp_validate(struct task_struct *p, + const struct sched_attr *attr) +{ + return -EOPNOTSUPP; +} +static void __setscheduler_uclamp(struct task_struct *p, + const struct sched_attr *attr) { } +#endif + +/* + * Allow unprivileged RT tasks to decrease priority. + * Only issue a capable test if needed and only once to avoid an audit + * event on permitted non-privileged operations: + */ +static int user_check_sched_setscheduler(struct task_struct *p, + const struct sched_attr *attr, + int policy, int reset_on_fork) +{ + if (fair_policy(policy)) { + if (attr->sched_nice < task_nice(p) && + !is_nice_reduction(p, attr->sched_nice)) + goto req_priv; + } + + if (rt_policy(policy)) { + unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); + + /* Can't set/change the rt policy: */ + if (policy != p->policy && !rlim_rtprio) + goto req_priv; + + /* Can't increase priority: */ + if (attr->sched_priority > p->rt_priority && + attr->sched_priority > rlim_rtprio) + goto req_priv; + } + + /* + * Can't set/change SCHED_DEADLINE policy at all for now + * (safest behavior); in the future we would like to allow + * unprivileged DL tasks to increase their relative deadline + * or reduce their runtime (both ways reducing utilization) + */ + if (dl_policy(policy)) + goto req_priv; + + /* + * Treat SCHED_IDLE as nice 20. Only allow a switch to + * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. + */ + if (task_has_idle_policy(p) && !idle_policy(policy)) { + if (!is_nice_reduction(p, task_nice(p))) + goto req_priv; + } + + /* Can't change other user's priorities: */ + if (!check_same_owner(p)) + goto req_priv; + + /* Normal users shall not reset the sched_reset_on_fork flag: */ + if (p->sched_reset_on_fork && !reset_on_fork) + goto req_priv; + + return 0; + +req_priv: + if (!capable(CAP_SYS_NICE)) + return -EPERM; + + return 0; +} + +int __sched_setscheduler(struct task_struct *p, + const struct sched_attr *attr, + bool user, bool pi) +{ + int oldpolicy = -1, policy = attr->sched_policy; + int retval, oldprio, newprio, queued, running; + const struct sched_class *prev_class; + struct balance_callback *head; + struct rq_flags rf; + int reset_on_fork; + int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; + struct rq *rq; + bool cpuset_locked = false; + + /* The pi code expects interrupts enabled */ + BUG_ON(pi && in_interrupt()); +recheck: + /* Double check policy once rq lock held: */ + if (policy < 0) { + reset_on_fork = p->sched_reset_on_fork; + policy = oldpolicy = p->policy; + } else { + reset_on_fork = !!(attr->sched_flags & SCHED_FLAG_RESET_ON_FORK); + + if (!valid_policy(policy)) + return -EINVAL; + } + + if (attr->sched_flags & ~(SCHED_FLAG_ALL | SCHED_FLAG_SUGOV)) + return -EINVAL; + + /* + * Valid priorities for SCHED_FIFO and SCHED_RR are + * 1..MAX_RT_PRIO-1, valid priority for SCHED_NORMAL, + * SCHED_BATCH and SCHED_IDLE is 0. + */ + if (attr->sched_priority > MAX_RT_PRIO-1) + return -EINVAL; + if ((dl_policy(policy) && !__checkparam_dl(attr)) || + (rt_policy(policy) != (attr->sched_priority != 0))) + return -EINVAL; + + if (user) { + retval = user_check_sched_setscheduler(p, attr, policy, reset_on_fork); + if (retval) + return retval; + + if (attr->sched_flags & SCHED_FLAG_SUGOV) + return -EINVAL; + + retval = security_task_setscheduler(p); + if (retval) + return retval; + } + + /* Update task specific "requested" clamps */ + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) { + retval = uclamp_validate(p, attr); + if (retval) + return retval; + } + + /* + * SCHED_DEADLINE bandwidth accounting relies on stable cpusets + * information. + */ + if (dl_policy(policy) || dl_policy(p->policy)) { + cpuset_locked = true; + cpuset_lock(); + } + + /* + * Make sure no PI-waiters arrive (or leave) while we are + * changing the priority of the task: + * + * To be able to change p->policy safely, the appropriate + * runqueue lock must be held. + */ + rq = task_rq_lock(p, &rf); + update_rq_clock(rq); + + /* + * Changing the policy of the stop threads its a very bad idea: + */ + if (p == rq->stop) { + retval = -EINVAL; + goto unlock; + } + + retval = scx_check_setscheduler(p, policy); + if (retval) + goto unlock; + + /* + * If not changing anything there's no need to proceed further, + * but store a possible modification of reset_on_fork. + */ + if (unlikely(policy == p->policy)) { + if (fair_policy(policy) && attr->sched_nice != task_nice(p)) + goto change; + if (rt_policy(policy) && attr->sched_priority != p->rt_priority) + goto change; + if (dl_policy(policy) && dl_param_changed(p, attr)) + goto change; + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) + goto change; + + p->sched_reset_on_fork = reset_on_fork; + retval = 0; + goto unlock; + } +change: + +#ifdef CONFIG_QOS_SCHED + /* + * If the scheduling policy of an offline task is set to a policy + * other than SCHED_IDLE, the online task preemption and cpu resource + * isolation will be invalid, so return -EINVAL in this case. + */ + if (unlikely(is_offline_level(task_group(p)->qos_level) && !idle_policy(policy))) { + retval = -EINVAL; + goto unlock; + } +#endif + + if (user) { +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Do not allow realtime tasks into groups that have no runtime + * assigned. + */ + if (rt_bandwidth_enabled() && rt_policy(policy) && + task_group(p)->rt_bandwidth.rt_runtime == 0 && + !task_group_is_autogroup(task_group(p))) { + retval = -EPERM; + goto unlock; + } +#endif +#ifdef CONFIG_SMP + if (dl_bandwidth_enabled() && dl_policy(policy) && + !(attr->sched_flags & SCHED_FLAG_SUGOV)) { + cpumask_t *span = rq->rd->span; + + /* + * Don't allow tasks with an affinity mask smaller than + * the entire root_domain to become SCHED_DEADLINE. We + * will also fail if there's no bandwidth available. + */ + if (!cpumask_subset(span, p->cpus_ptr) || + rq->rd->dl_bw.bw == 0) { + retval = -EPERM; + goto unlock; + } + } +#endif + } + + /* Re-check policy now with rq lock held: */ + if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { + policy = oldpolicy = -1; + task_rq_unlock(rq, p, &rf); + if (cpuset_locked) + cpuset_unlock(); + goto recheck; + } + + /* + * If setscheduling to SCHED_DEADLINE (or changing the parameters + * of a SCHED_DEADLINE task) we need to check if enough bandwidth + * is available. + */ + if ((dl_policy(policy) || dl_task(p)) && sched_dl_overflow(p, policy, attr)) { + retval = -EBUSY; + goto unlock; + } + + p->sched_reset_on_fork = reset_on_fork; + oldprio = p->prio; + + newprio = __normal_prio(policy, attr->sched_priority, attr->sched_nice); + if (pi) { + /* + * Take priority boosted tasks into account. If the new + * effective priority is unchanged, we just store the new + * normal parameters and do not touch the scheduler class and + * the runqueue. This will be done when the task deboost + * itself. + */ + newprio = rt_effective_prio(p, newprio); + if (newprio == oldprio) + queue_flags &= ~DEQUEUE_MOVE; + } + + queued = task_on_rq_queued(p); + running = task_current(rq, p); + if (queued) + dequeue_task(rq, p, queue_flags); + if (running) + put_prev_task(rq, p); + + prev_class = p->sched_class; + + if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) { + __setscheduler_params(p, attr); + __setscheduler_prio(p, newprio); + } + __setscheduler_uclamp(p, attr); + check_class_changing(rq, p, prev_class); + + if (queued) { + /* + * We enqueue to tail when the priority of a task is + * increased (user space view). + */ + if (oldprio < p->prio) + queue_flags |= ENQUEUE_HEAD; + + enqueue_task(rq, p, queue_flags); + } + if (running) + set_next_task(rq, p); + + check_class_changed(rq, p, prev_class, oldprio); + + /* Avoid rq from going away on us: */ + preempt_disable(); + head = splice_balance_callbacks(rq); + task_rq_unlock(rq, p, &rf); + + if (pi) { + if (cpuset_locked) + cpuset_unlock(); + rt_mutex_adjust_pi(p); + } + + /* Run balance callbacks after we've adjusted the PI chain: */ + balance_callbacks(rq, head); + preempt_enable(); + + return 0; + +unlock: + task_rq_unlock(rq, p, &rf); + if (cpuset_locked) + cpuset_unlock(); + return retval; +} + +static int _sched_setscheduler(struct task_struct *p, int policy, + const struct sched_param *param, bool check) +{ + struct sched_attr attr = { + .sched_policy = policy, + .sched_priority = param->sched_priority, + .sched_nice = PRIO_TO_NICE(p->static_prio), + }; + + /* Fixup the legacy SCHED_RESET_ON_FORK hack. */ + if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) { + attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; + policy &= ~SCHED_RESET_ON_FORK; + attr.sched_policy = policy; + } + + return __sched_setscheduler(p, &attr, check, true); +} +/** + * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. + * @p: the task in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * Use sched_set_fifo(), read its comment. + * + * Return: 0 on success. An error code otherwise. + * + * NOTE that the task may be already dead. + */ +int sched_setscheduler(struct task_struct *p, int policy, + const struct sched_param *param) +{ + return _sched_setscheduler(p, policy, param, true); +} + +int sched_setattr(struct task_struct *p, const struct sched_attr *attr) +{ + return __sched_setscheduler(p, attr, true, true); +} + +int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr) +{ + return __sched_setscheduler(p, attr, false, true); +} + +/** + * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. + * @p: the task in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * Just like sched_setscheduler, only don't bother checking if the + * current context has permission. For example, this is needed in + * stop_machine(): we create temporary high priority worker threads, + * but our caller might not have that capability. + * + * Return: 0 on success. An error code otherwise. + */ +int sched_setscheduler_nocheck(struct task_struct *p, int policy, + const struct sched_param *param) +{ + return _sched_setscheduler(p, policy, param, false); +} + +/* + * SCHED_FIFO is a broken scheduler model; that is, it is fundamentally + * incapable of resource management, which is the one thing an OS really should + * be doing. + * + * This is of course the reason it is limited to privileged users only. + * + * Worse still; it is fundamentally impossible to compose static priority + * workloads. You cannot take two correctly working static prio workloads + * and smash them together and still expect them to work. + * + * For this reason 'all' FIFO tasks the kernel creates are basically at: + * + * MAX_RT_PRIO / 2 + * + * The administrator _MUST_ configure the system, the kernel simply doesn't + * know enough information to make a sensible choice. + */ +void sched_set_fifo(struct task_struct *p) +{ + struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 }; + WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0); +} + +/* + * For when you don't much care about FIFO, but want to be above SCHED_NORMAL. + */ +void sched_set_fifo_low(struct task_struct *p) +{ + struct sched_param sp = { .sched_priority = 1 }; + WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0); +} + +void sched_set_normal(struct task_struct *p, int nice) +{ + struct sched_attr attr = { + .sched_policy = SCHED_NORMAL, + .sched_nice = nice, + }; + WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0); +} + +static int +do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) +{ + struct sched_param lparam; + + if (!param || pid < 0) + return -EINVAL; + if (copy_from_user(&lparam, param, sizeof(struct sched_param))) + return -EFAULT; + + CLASS(find_get_task, p)(pid); + if (!p) + return -ESRCH; + + return sched_setscheduler(p, policy, &lparam); +} + +/* + * Mimics kernel/events/core.c perf_copy_attr(). + */ +static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *attr) +{ + u32 size; + int ret; + + /* Zero the full structure, so that a short copy will be nice: */ + memset(attr, 0, sizeof(*attr)); + + ret = get_user(size, &uattr->size); + if (ret) + return ret; + + /* ABI compatibility quirk: */ + if (!size) + size = SCHED_ATTR_SIZE_VER0; + if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE) + goto err_size; + + ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size); + if (ret) { + if (ret == -E2BIG) + goto err_size; + return ret; + } + + if ((attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) && + size < SCHED_ATTR_SIZE_VER1) + return -EINVAL; + + /* + * XXX: Do we want to be lenient like existing syscalls; or do we want + * to be strict and return an error on out-of-bounds values? + */ + attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE); + + return 0; + +err_size: + put_user(sizeof(*attr), &uattr->size); + return -E2BIG; +} + +static void get_params(struct task_struct *p, struct sched_attr *attr) +{ + if (task_has_dl_policy(p)) + __getparam_dl(p, attr); + else if (task_has_rt_policy(p)) + attr->sched_priority = p->rt_priority; + else + attr->sched_nice = task_nice(p); +} + +/** + * sys_sched_setscheduler - set/change the scheduler policy and RT priority + * @pid: the pid in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param) +{ + if (policy < 0) + return -EINVAL; + + return do_sched_setscheduler(pid, policy, param); +} + +/** + * sys_sched_setparam - set/change the RT priority of a thread + * @pid: the pid in question. + * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) +{ + return do_sched_setscheduler(pid, SETPARAM_POLICY, param); +} + +/** + * sys_sched_setattr - same as above, but with extended sched_attr + * @pid: the pid in question. + * @uattr: structure containing the extended parameters. + * @flags: for future extension. + */ +SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, flags) +{ + struct sched_attr attr; + int retval; + + if (!uattr || pid < 0 || flags) + return -EINVAL; + + retval = sched_copy_attr(uattr, &attr); + if (retval) + return retval; + + if ((int)attr.sched_policy < 0) + return -EINVAL; + if (attr.sched_flags & SCHED_FLAG_KEEP_POLICY) + attr.sched_policy = SETPARAM_POLICY; + + CLASS(find_get_task, p)(pid); + if (!p) + return -ESRCH; + + if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS) + get_params(p, &attr); + + return sched_setattr(p, &attr); +} + +/** + * sys_sched_getscheduler - get the policy (scheduling class) of a thread + * @pid: the pid in question. + * + * Return: On success, the policy of the thread. Otherwise, a negative error + * code. + */ +SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) +{ + struct task_struct *p; + int retval; + + if (pid < 0) + return -EINVAL; + + guard(rcu)(); + p = find_process_by_pid(pid); + if (!p) + return -ESRCH; + + retval = security_task_getscheduler(p); + if (!retval) { + retval = p->policy; + if (p->sched_reset_on_fork) + retval |= SCHED_RESET_ON_FORK; + } + return retval; +} + +/** + * sys_sched_getparam - get the RT priority of a thread + * @pid: the pid in question. + * @param: structure containing the RT priority. + * + * Return: On success, 0 and the RT priority is in @param. Otherwise, an error + * code. + */ +SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) +{ + struct sched_param lp = { .sched_priority = 0 }; + struct task_struct *p; + int retval; + + if (!param || pid < 0) + return -EINVAL; + + scoped_guard (rcu) { + p = find_process_by_pid(pid); + if (!p) + return -ESRCH; + + retval = security_task_getscheduler(p); + if (retval) + return retval; + + if (task_has_rt_policy(p)) + lp.sched_priority = p->rt_priority; + } + + /* + * This one might sleep, we cannot do it with a spinlock held ... + */ + return copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0; +} + +/* + * Copy the kernel size attribute structure (which might be larger + * than what user-space knows about) to user-space. + * + * Note that all cases are valid: user-space buffer can be larger or + * smaller than the kernel-space buffer. The usual case is that both + * have the same size. + */ +static int +sched_attr_copy_to_user(struct sched_attr __user *uattr, + struct sched_attr *kattr, + unsigned int usize) +{ + unsigned int ksize = sizeof(*kattr); + + if (!access_ok(uattr, usize)) + return -EFAULT; + + /* + * sched_getattr() ABI forwards and backwards compatibility: + * + * If usize == ksize then we just copy everything to user-space and all is good. + * + * If usize < ksize then we only copy as much as user-space has space for, + * this keeps ABI compatibility as well. We skip the rest. + * + * If usize > ksize then user-space is using a newer version of the ABI, + * which part the kernel doesn't know about. Just ignore it - tooling can + * detect the kernel's knowledge of attributes from the attr->size value + * which is set to ksize in this case. + */ + kattr->size = min(usize, ksize); + + if (copy_to_user(uattr, kattr, kattr->size)) + return -EFAULT; + + return 0; +} + +/** + * sys_sched_getattr - similar to sched_getparam, but with sched_attr + * @pid: the pid in question. + * @uattr: structure containing the extended parameters. + * @usize: sizeof(attr) for fwd/bwd comp. + * @flags: for future extension. + */ +SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, usize, unsigned int, flags) +{ + struct sched_attr kattr = { }; + struct task_struct *p; + int retval; + + if (!uattr || pid < 0 || usize > PAGE_SIZE || + usize < SCHED_ATTR_SIZE_VER0 || flags) + return -EINVAL; + + scoped_guard (rcu) { + p = find_process_by_pid(pid); + if (!p) + return -ESRCH; + + retval = security_task_getscheduler(p); + if (retval) + return retval; + + kattr.sched_policy = p->policy; + if (p->sched_reset_on_fork) + kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; + get_params(p, &kattr); + kattr.sched_flags &= SCHED_FLAG_ALL; + +#ifdef CONFIG_UCLAMP_TASK + /* + * This could race with another potential updater, but this is fine + * because it'll correctly read the old or the new value. We don't need + * to guarantee who wins the race as long as it doesn't return garbage. + */ + kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value; + kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value; +#endif + } + + return sched_attr_copy_to_user(uattr, &kattr, usize); +} + +#ifdef CONFIG_SMP +int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask) +{ + /* + * If the task isn't a deadline task or admission control is + * disabled then we don't care about affinity changes. + */ + if (!task_has_dl_policy(p) || !dl_bandwidth_enabled()) + return 0; + + /* + * Since bandwidth control happens on root_domain basis, + * if admission test is enabled, we only admit -deadline + * tasks allowed to run on all the CPUs in the task's + * root_domain. + */ + guard(rcu)(); + if (!cpumask_subset(task_rq(p)->rd->span, mask)) + return -EBUSY; + + return 0; +} +#endif /* CONFIG_SMP */ + +int __sched_setaffinity(struct task_struct *p, struct affinity_context *ctx) +{ + int retval; + cpumask_var_t cpus_allowed, new_mask; + + if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) + return -ENOMEM; + + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) { + retval = -ENOMEM; + goto out_free_cpus_allowed; + } + + cpuset_cpus_allowed(p, cpus_allowed); + cpumask_and(new_mask, ctx->new_mask, cpus_allowed); + + ctx->new_mask = new_mask; + ctx->flags |= SCA_CHECK; + + retval = dl_task_check_affinity(p, new_mask); + if (retval) + goto out_free_new_mask; + + retval = __set_cpus_allowed_ptr(p, ctx); + if (retval) + goto out_free_new_mask; + + cpuset_cpus_allowed(p, cpus_allowed); + if (!cpumask_subset(new_mask, cpus_allowed)) { + /* + * We must have raced with a concurrent cpuset update. + * Just reset the cpumask to the cpuset's cpus_allowed. + */ + cpumask_copy(new_mask, cpus_allowed); + + /* + * If SCA_USER is set, a 2nd call to __set_cpus_allowed_ptr() + * will restore the previous user_cpus_ptr value. + * + * In the unlikely event a previous user_cpus_ptr exists, + * we need to further restrict the mask to what is allowed + * by that old user_cpus_ptr. + */ + if (unlikely((ctx->flags & SCA_USER) && ctx->user_mask)) { + bool empty = !cpumask_and(new_mask, new_mask, + ctx->user_mask); + + if (empty) + cpumask_copy(new_mask, cpus_allowed); + } + __set_cpus_allowed_ptr(p, ctx); + retval = -EINVAL; + } + +out_free_new_mask: + free_cpumask_var(new_mask); +out_free_cpus_allowed: + free_cpumask_var(cpus_allowed); + return retval; +} + +long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) +{ + struct affinity_context ac; + struct cpumask *user_mask; + int retval; + + CLASS(find_get_task, p)(pid); + if (!p) + return -ESRCH; + + if (p->flags & PF_NO_SETAFFINITY) + return -EINVAL; + + if (!check_same_owner(p)) { + guard(rcu)(); + if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) + return -EPERM; + } + + retval = security_task_setscheduler(p); + if (retval) + return retval; + + /* + * With non-SMP configs, user_cpus_ptr/user_mask isn't used and + * alloc_user_cpus_ptr() returns NULL. + */ + user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE); + if (user_mask) { + cpumask_copy(user_mask, in_mask); + } else if (IS_ENABLED(CONFIG_SMP)) { + return -ENOMEM; + } + + ac = (struct affinity_context){ + .new_mask = in_mask, + .user_mask = user_mask, + .flags = SCA_USER, + }; + + retval = __sched_setaffinity(p, &ac); + kfree(ac.user_mask); + + return retval; +} + +static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, + struct cpumask *new_mask) +{ + if (len < cpumask_size()) + cpumask_clear(new_mask); + else if (len > cpumask_size()) + len = cpumask_size(); + + return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0; +} + +/** + * sys_sched_setaffinity - set the CPU affinity of a process + * @pid: pid of the process + * @len: length in bytes of the bitmask pointed to by user_mask_ptr + * @user_mask_ptr: user-space pointer to the new CPU mask + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, + unsigned long __user *, user_mask_ptr) +{ + cpumask_var_t new_mask; + int retval; + + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) + return -ENOMEM; + + retval = get_user_cpu_mask(user_mask_ptr, len, new_mask); + if (retval == 0) + retval = sched_setaffinity(pid, new_mask); + free_cpumask_var(new_mask); + return retval; +} + +long sched_getaffinity(pid_t pid, struct cpumask *mask) +{ + struct task_struct *p; + int retval; + + guard(rcu)(); + p = find_process_by_pid(pid); + if (!p) + return -ESRCH; + + retval = security_task_getscheduler(p); + if (retval) + return retval; + + guard(raw_spinlock_irqsave)(&p->pi_lock); + cpumask_and(mask, &p->cpus_mask, cpu_active_mask); + + return 0; +} + +/** + * sys_sched_getaffinity - get the CPU affinity of a process + * @pid: pid of the process + * @len: length in bytes of the bitmask pointed to by user_mask_ptr + * @user_mask_ptr: user-space pointer to hold the current CPU mask + * + * Return: size of CPU mask copied to user_mask_ptr on success. An + * error code otherwise. + */ +SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, + unsigned long __user *, user_mask_ptr) +{ + int ret; + cpumask_var_t mask; + + if ((len * BITS_PER_BYTE) < nr_cpu_ids) + return -EINVAL; + if (len & (sizeof(unsigned long)-1)) + return -EINVAL; + + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + ret = sched_getaffinity(pid, mask); + if (ret == 0) { + unsigned int retlen = min(len, cpumask_size()); + + if (copy_to_user(user_mask_ptr, cpumask_bits(mask), retlen)) + ret = -EFAULT; + else + ret = retlen; + } + free_cpumask_var(mask); + + return ret; +} + +static void do_sched_yield(void) +{ + struct rq_flags rf; + struct rq *rq; + + rq = this_rq_lock_irq(&rf); + + schedstat_inc(rq->yld_count); + current->sched_class->yield_task(rq); + + preempt_disable(); + rq_unlock_irq(rq, &rf); + sched_preempt_enable_no_resched(); + + schedule(); +} + +/** + * sys_sched_yield - yield the current processor to other threads. + * + * This function yields the current CPU to other tasks. If there are no + * other threads running on this CPU then this function will return. + * + * Return: 0. + */ +SYSCALL_DEFINE0(sched_yield) +{ + do_sched_yield(); + return 0; +} + +/** + * yield - yield the current processor to other threads. + * + * Do not ever use this function, there's a 99% chance you're doing it wrong. + * + * The scheduler is at all times free to pick the calling task as the most + * eligible task to run, if removing the yield() call from your code breaks + * it, it's already broken. + * + * Typical broken usage is: + * + * while (!event) + * yield(); + * + * where one assumes that yield() will let 'the other' process run that will + * make event true. If the current task is a SCHED_FIFO task that will never + * happen. Never use yield() as a progress guarantee!! + * + * If you want to use yield() to wait for something, use wait_event(). + * If you want to use yield() to be 'nice' for others, use cond_resched(). + * If you still want to use yield(), do not! + */ +void __sched yield(void) +{ + set_current_state(TASK_RUNNING); + do_sched_yield(); +} +EXPORT_SYMBOL(yield); + +/** + * yield_to - yield the current processor to another thread in + * your thread group, or accelerate that thread toward the + * processor it's on. + * @p: target task + * @preempt: whether task preemption is allowed or not + * + * It's the caller's job to ensure that the target task struct + * can't go away on us before we can do any checks. + * + * Return: + * true (>0) if we indeed boosted the target task. + * false (0) if we failed to boost the target. + * -ESRCH if there's no task to yield to. + */ +int __sched yield_to(struct task_struct *p, bool preempt) +{ + struct task_struct *curr = current; + struct rq *rq, *p_rq; + int yielded = 0; + + scoped_guard (raw_spinlock_irqsave, &p->pi_lock) { + rq = this_rq(); + +again: + p_rq = task_rq(p); + /* + * If we're the only runnable task on the rq and target rq also + * has only one task, there's absolutely no point in yielding. + */ + if (rq->nr_running == 1 && p_rq->nr_running == 1) + return -ESRCH; + + guard(double_rq_lock)(rq, p_rq); + if (task_rq(p) != p_rq) + goto again; + + if (!curr->sched_class->yield_to_task) + return 0; + + if (curr->sched_class != p->sched_class) + return 0; + + if (task_on_cpu(p_rq, p) || !task_is_running(p)) + return 0; + + yielded = curr->sched_class->yield_to_task(rq, p); + if (yielded) { + schedstat_inc(rq->yld_count); + /* + * Make p's CPU reschedule; pick_next_entity + * takes care of fairness. + */ + if (preempt && rq != p_rq) + resched_curr(p_rq); + } + } + + if (yielded) + schedule(); + + return yielded; +} + +/** + * sys_sched_get_priority_max - return maximum RT priority. + * @policy: scheduling class. + * + * Return: On success, this syscall returns the maximum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. + */ +SYSCALL_DEFINE1(sched_get_priority_max, int, policy) +{ + int ret = -EINVAL; + + switch (policy) { + case SCHED_FIFO: + case SCHED_RR: + ret = MAX_RT_PRIO-1; + break; + case SCHED_DEADLINE: + case SCHED_NORMAL: + case SCHED_BATCH: + case SCHED_IDLE: + case SCHED_EXT: + ret = 0; + break; + } + return ret; +} + +/** + * sys_sched_get_priority_min - return minimum RT priority. + * @policy: scheduling class. + * + * Return: On success, this syscall returns the minimum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. + */ +SYSCALL_DEFINE1(sched_get_priority_min, int, policy) +{ + int ret = -EINVAL; + + switch (policy) { + case SCHED_FIFO: + case SCHED_RR: + ret = 1; + break; + case SCHED_DEADLINE: + case SCHED_NORMAL: + case SCHED_BATCH: + case SCHED_IDLE: + case SCHED_EXT: + ret = 0; + } + return ret; +} + +static int sched_rr_get_interval(pid_t pid, struct timespec64 *t) +{ + unsigned int time_slice = 0; + int retval; + + if (pid < 0) + return -EINVAL; + + scoped_guard (rcu) { + struct task_struct *p = find_process_by_pid(pid); + if (!p) + return -ESRCH; + + retval = security_task_getscheduler(p); + if (retval) + return retval; + + scoped_guard (task_rq_lock, p) { + struct rq *rq = scope.rq; + if (p->sched_class->get_rr_interval) + time_slice = p->sched_class->get_rr_interval(rq, p); + } + } + + jiffies_to_timespec64(time_slice, t); + return 0; +} + +/** + * sys_sched_rr_get_interval - return the default timeslice of a process. + * @pid: pid of the process. + * @interval: userspace pointer to the timeslice value. + * + * this syscall writes the default timeslice value of a given process + * into the user-space timespec buffer. A value of '0' means infinity. + * + * Return: On success, 0 and the timeslice is in @interval. Otherwise, + * an error code. + */ +SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, + struct __kernel_timespec __user *, interval) +{ + struct timespec64 t; + int retval = sched_rr_get_interval(pid, &t); + + if (retval == 0) + retval = put_timespec64(&t, interval); + + return retval; +} + +#ifdef CONFIG_COMPAT_32BIT_TIME +SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid, + struct old_timespec32 __user *, interval) +{ + struct timespec64 t; + int retval = sched_rr_get_interval(pid, &t); + + if (retval == 0) + retval = put_old_timespec32(&t, interval); + return retval; +} +#endif diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 423fb97a3f2714d58cc4814dae191d8c492b9386..0a29386fda0b46c8bb68a6d7f6111db127bf6079 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1256,9 +1256,7 @@ static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = { }; #ifdef CONFIG_KEYS -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "kfuncs which will be used in BPF programs"); +__bpf_kfunc_start_defs(); /** * bpf_lookup_user_key - lookup a key by its serial @@ -1408,16 +1406,16 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr, } #endif /* CONFIG_SYSTEM_DATA_VERIFICATION */ -__diag_pop(); +__bpf_kfunc_end_defs(); -BTF_SET8_START(key_sig_kfunc_set) +BTF_KFUNCS_START(key_sig_kfunc_set) BTF_ID_FLAGS(func, bpf_lookup_user_key, KF_ACQUIRE | KF_RET_NULL | KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_lookup_system_key, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_key_put, KF_RELEASE) #ifdef CONFIG_SYSTEM_DATA_VERIFICATION BTF_ID_FLAGS(func, bpf_verify_pkcs7_signature, KF_SLEEPABLE) #endif -BTF_SET8_END(key_sig_kfunc_set) +BTF_KFUNCS_END(key_sig_kfunc_set) static const struct btf_kfunc_id_set bpf_key_sig_kfunc_set = { .owner = THIS_MODULE, @@ -2400,7 +2398,8 @@ int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, - u64 *probe_offset, u64 *probe_addr) + u64 *probe_offset, u64 *probe_addr, + unsigned long *missed) { bool is_tracepoint, is_syscall_tp; struct bpf_prog *prog; @@ -2435,7 +2434,7 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, #ifdef CONFIG_KPROBE_EVENTS if (flags & TRACE_EVENT_FL_KPROBE) err = bpf_get_kprobe_info(event, fd_type, buf, - probe_offset, probe_addr, + probe_offset, probe_addr, missed, event->attr.type == PERF_TYPE_TRACEPOINT); #endif #ifdef CONFIG_UPROBE_EVENTS diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index f0ae3bcd07ce60810bf081c422373178e21b010f..98b59166199153947763c6460d2bf08f687b4b70 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1259,6 +1259,12 @@ static const struct file_operations kprobe_events_ops = { .write = probes_write, }; +static unsigned long trace_kprobe_missed(struct trace_kprobe *tk) +{ + return trace_kprobe_is_return(tk) ? + tk->rp.kp.nmissed + tk->rp.nmissed : tk->rp.kp.nmissed; +} + /* Probes profiling interfaces */ static int probes_profile_seq_show(struct seq_file *m, void *v) { @@ -1270,8 +1276,7 @@ static int probes_profile_seq_show(struct seq_file *m, void *v) return 0; tk = to_trace_kprobe(ev); - nmissed = trace_kprobe_is_return(tk) ? - tk->rp.kp.nmissed + tk->rp.nmissed : tk->rp.kp.nmissed; + nmissed = trace_kprobe_missed(tk); seq_printf(m, " %-44s %15lu %15lu\n", trace_probe_name(&tk->tp), trace_kprobe_nhit(tk), @@ -1617,7 +1622,8 @@ NOKPROBE_SYMBOL(kretprobe_perf_func); int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, const char **symbol, u64 *probe_offset, - u64 *probe_addr, bool perf_type_tracepoint) + u64 *probe_addr, unsigned long *missed, + bool perf_type_tracepoint) { const char *pevent = trace_event_name(event->tp_event); const char *group = event->tp_event->class->system; @@ -1636,6 +1642,8 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, *probe_addr = kallsyms_show_value(current_cred()) ? (unsigned long)tk->rp.kp.addr : 0; *symbol = tk->symbol; + if (missed) + *missed = trace_kprobe_missed(tk); return 0; } #endif /* CONFIG_PERF_EVENTS */ diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 1500c5c060b1416d5442ad7f733ce0daaee17f5b..b168d6dd077316d3e333fa9ad586dfc242de45c0 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -1067,8 +1067,6 @@ parse_probe_arg(char *arg, const struct fetch_type *type, return ret; } -#define BYTES_TO_BITS(nb) ((BITS_PER_LONG * (nb)) / sizeof(long)) - /* Bitfield type needs to be parsed into a fetch function */ static int __parse_bitfield_probe_arg(const char *bf, const struct fetch_type *t, diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 6313fe17bca7aa40296e9445f0fe2e130065d19e..2d8c99e7aeb2b769b7fe9e45306eb70fb51a2374 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -12,21 +12,26 @@ #define pr_fmt(fmt) "watchdog: " fmt -#include #include -#include #include #include +#include +#include +#include +#include +#include +#include #include +#include +#include #include #include + #include #include #include -#include #include -#include static DEFINE_MUTEX(watchdog_mutex); @@ -36,6 +41,8 @@ static DEFINE_MUTEX(watchdog_mutex); # define WATCHDOG_HARDLOCKUP_DEFAULT 0 #endif +#define NUM_SAMPLE_PERIODS 5 + unsigned long __read_mostly watchdog_enabled; int __read_mostly watchdog_user_enabled = 1; static int __read_mostly watchdog_hardlockup_user_enabled = WATCHDOG_HARDLOCKUP_DEFAULT; @@ -317,6 +324,188 @@ __setup("watchdog_thresh=", watchdog_thresh_setup); static void __lockup_detector_cleanup(void); +#ifdef CONFIG_SOFTLOCKUP_DETECTOR_INTR_STORM +enum stats_per_group { + STATS_SYSTEM, + STATS_SOFTIRQ, + STATS_HARDIRQ, + STATS_IDLE, + NUM_STATS_PER_GROUP, +}; + +static const enum cpu_usage_stat tracked_stats[NUM_STATS_PER_GROUP] = { + CPUTIME_SYSTEM, + CPUTIME_SOFTIRQ, + CPUTIME_IRQ, + CPUTIME_IDLE, +}; + +static DEFINE_PER_CPU(u16, cpustat_old[NUM_STATS_PER_GROUP]); +static DEFINE_PER_CPU(u8, cpustat_util[NUM_SAMPLE_PERIODS][NUM_STATS_PER_GROUP]); +static DEFINE_PER_CPU(u8, cpustat_tail); + +/* + * We don't need nanosecond resolution. A granularity of 16ms is + * sufficient for our precision, allowing us to use u16 to store + * cpustats, which will roll over roughly every ~1000 seconds. + * 2^24 ~= 16 * 10^6 + */ +static u16 get_16bit_precision(u64 data_ns) +{ + return data_ns >> 24LL; /* 2^24ns ~= 16.8ms */ +} + +static void update_cpustat(void) +{ + int i; + u8 util; + u16 old_stat, new_stat; + struct kernel_cpustat kcpustat; + u64 *cpustat = kcpustat.cpustat; + u8 tail = __this_cpu_read(cpustat_tail); + u16 sample_period_16 = get_16bit_precision(sample_period); + + kcpustat_cpu_fetch(&kcpustat, smp_processor_id()); + + for (i = 0; i < NUM_STATS_PER_GROUP; i++) { + old_stat = __this_cpu_read(cpustat_old[i]); + new_stat = get_16bit_precision(cpustat[tracked_stats[i]]); + util = DIV_ROUND_UP(100 * (new_stat - old_stat), sample_period_16); + __this_cpu_write(cpustat_util[tail][i], util); + __this_cpu_write(cpustat_old[i], new_stat); + } + + __this_cpu_write(cpustat_tail, (tail + 1) % NUM_SAMPLE_PERIODS); +} + +static void print_cpustat(void) +{ + int i, group; + u8 tail = __this_cpu_read(cpustat_tail); + u64 sample_period_second = sample_period; + + do_div(sample_period_second, NSEC_PER_SEC); + + /* + * Outputting the "watchdog" prefix on every line is redundant and not + * concise, and the original alarm information is sufficient for + * positioning in logs, hence here printk() is used instead of pr_crit(). + */ + printk(KERN_CRIT "CPU#%d Utilization every %llus during lockup:\n", + smp_processor_id(), sample_period_second); + + for (i = 0; i < NUM_SAMPLE_PERIODS; i++) { + group = (tail + i) % NUM_SAMPLE_PERIODS; + printk(KERN_CRIT "\t#%d: %3u%% system,\t%3u%% softirq,\t" + "%3u%% hardirq,\t%3u%% idle\n", i + 1, + __this_cpu_read(cpustat_util[group][STATS_SYSTEM]), + __this_cpu_read(cpustat_util[group][STATS_SOFTIRQ]), + __this_cpu_read(cpustat_util[group][STATS_HARDIRQ]), + __this_cpu_read(cpustat_util[group][STATS_IDLE])); + } +} + +#define HARDIRQ_PERCENT_THRESH 50 +#define NUM_HARDIRQ_REPORT 5 +struct irq_counts { + int irq; + u32 counts; +}; + +static DEFINE_PER_CPU(bool, snapshot_taken); + +/* Tabulate the most frequent interrupts. */ +static void tabulate_irq_count(struct irq_counts *irq_counts, int irq, u32 counts, int rank) +{ + int i; + struct irq_counts new_count = {irq, counts}; + + for (i = 0; i < rank; i++) { + if (counts > irq_counts[i].counts) + swap(new_count, irq_counts[i]); + } +} + +/* + * If the hardirq time exceeds HARDIRQ_PERCENT_THRESH% of the sample_period, + * then the cause of softlockup might be interrupt storm. In this case, it + * would be useful to start interrupt counting. + */ +static bool need_counting_irqs(void) +{ + u8 util; + int tail = __this_cpu_read(cpustat_tail); + + tail = (tail + NUM_HARDIRQ_REPORT - 1) % NUM_HARDIRQ_REPORT; + util = __this_cpu_read(cpustat_util[tail][STATS_HARDIRQ]); + return util > HARDIRQ_PERCENT_THRESH; +} + +static void start_counting_irqs(void) +{ + if (!__this_cpu_read(snapshot_taken)) { + kstat_snapshot_irqs(); + __this_cpu_write(snapshot_taken, true); + } +} + +static void stop_counting_irqs(void) +{ + __this_cpu_write(snapshot_taken, false); +} + +static void print_irq_counts(void) +{ + unsigned int i, count; + struct irq_counts irq_counts_sorted[NUM_HARDIRQ_REPORT] = { + {-1, 0}, {-1, 0}, {-1, 0}, {-1, 0}, {-1, 0} + }; + + if (__this_cpu_read(snapshot_taken)) { + for_each_active_irq(i) { + count = kstat_get_irq_since_snapshot(i); + tabulate_irq_count(irq_counts_sorted, i, count, NUM_HARDIRQ_REPORT); + } + + /* + * Outputting the "watchdog" prefix on every line is redundant and not + * concise, and the original alarm information is sufficient for + * positioning in logs, hence here printk() is used instead of pr_crit(). + */ + printk(KERN_CRIT "CPU#%d Detect HardIRQ Time exceeds %d%%. Most frequent HardIRQs:\n", + smp_processor_id(), HARDIRQ_PERCENT_THRESH); + + for (i = 0; i < NUM_HARDIRQ_REPORT; i++) { + if (irq_counts_sorted[i].irq == -1) + break; + + printk(KERN_CRIT "\t#%u: %-10u\tirq#%d\n", + i + 1, irq_counts_sorted[i].counts, + irq_counts_sorted[i].irq); + } + + /* + * If the hardirq time is less than HARDIRQ_PERCENT_THRESH% in the last + * sample_period, then we suspect the interrupt storm might be subsiding. + */ + if (!need_counting_irqs()) + stop_counting_irqs(); + } +} + +static void report_cpu_status(void) +{ + print_cpustat(); + print_irq_counts(); +} +#else +static inline void update_cpustat(void) { } +static inline void report_cpu_status(void) { } +static inline bool need_counting_irqs(void) { return false; } +static inline void start_counting_irqs(void) { } +static inline void stop_counting_irqs(void) { } +#endif + /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- * lockups can have false positives under extreme conditions. So we generally @@ -348,7 +537,7 @@ static void set_sample_period(void) * and hard thresholds) to increment before the * hardlockup detector generates a warning */ - sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / 5); + sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / NUM_SAMPLE_PERIODS); watchdog_update_hrtimer_threshold(sample_period); } @@ -418,6 +607,26 @@ static int is_softlockup(unsigned long touch_ts, unsigned long now) { if ((watchdog_enabled & WATCHDOG_SOFTOCKUP_ENABLED) && watchdog_thresh) { + /* + * If period_ts has not been updated during a sample_period, then + * in the subsequent few sample_periods, period_ts might also not + * be updated, which could indicate a potential softlockup. In + * this case, if we suspect the cause of the potential softlockup + * might be interrupt storm, then we need to count the interrupts + * to find which interrupt is storming. + */ + if (time_after_eq(now, period_ts + get_softlockup_thresh() / NUM_SAMPLE_PERIODS) && + need_counting_irqs()) + start_counting_irqs(); + + /* + * A poorly behaving BPF scheduler can live-lock the system into + * soft lockups. Tell sched_ext to try ejecting the BPF + * scheduler when close to a soft lockup. + */ + if (time_after_eq(now, period_ts + get_softlockup_thresh() * 3 / 4)) + scx_softlockup(now - touch_ts); + /* Warn about unreasonable delays. */ if (time_after(now, period_ts + get_softlockup_thresh())) return now - touch_ts; @@ -440,6 +649,7 @@ static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work); static int softlockup_fn(void *data) { update_touch_ts(); + stop_counting_irqs(); complete(this_cpu_ptr(&softlockup_completion)); return 0; @@ -487,6 +697,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) */ period_ts = READ_ONCE(*this_cpu_ptr(&watchdog_report_ts)); + update_cpustat(); + /* Reset the interval when touched by known problematic code. */ if (period_ts == SOFTLOCKUP_DELAY_REPORT) { if (unlikely(__this_cpu_read(softlockup_touch_sync))) { @@ -521,6 +733,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); + report_cpu_status(); print_modules(); print_irqtrace_events(current); if (regs) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 0dc5e7d6579e6cb9cd72de5b55d9c4c1a2f0ee48..68f4317e59f1d9a5bc19cb090c1fc265ac988a5e 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1037,6 +1037,20 @@ config SOFTLOCKUP_DETECTOR chance to run. The current stack trace is displayed upon detection and the system will stay locked up. +config SOFTLOCKUP_DETECTOR_INTR_STORM + bool "Detect Interrupt Storm in Soft Lockups" + depends on SOFTLOCKUP_DETECTOR && IRQ_TIME_ACCOUNTING + select GENERIC_IRQ_STAT_SNAPSHOT + default y if NR_CPUS <= 128 + help + Say Y here to enable the kernel to detect interrupt storm + during "soft lockups". + + "soft lockups" can be caused by a variety of reasons. If one is + caused by an interrupt storm, then the storming interrupts will not + be on the callstack. To detect this case, it is necessary to report + the CPU stats and the interrupt counts during the "soft lockups". + config BOOTPARAM_SOFTLOCKUP_PANIC bool "Panic (Reboot) On Soft Lockups" depends on SOFTLOCKUP_DETECTOR diff --git a/lib/dump_stack.c b/lib/dump_stack.c index 83471e81501a7249306ef62e173c4dce7960adc7..6e667c445539b9d5f8769a288f4caea32e44c39a 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -68,6 +68,7 @@ void dump_stack_print_info(const char *log_lvl) print_worker_info(log_lvl, current); print_stop_info(log_lvl, current); + print_scx_info(log_lvl, current); } /** diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 6ae2ba8e06a2138d77e6b0d5f51c67e17658b1a7..156a81b808baabcaf5c812f7e0ab155f48334eb2 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -580,10 +580,6 @@ static struct bucket_table *rhashtable_insert_one( */ rht_assign_locked(bkt, obj); - atomic_inc(&ht->nelems); - if (rht_grow_above_75(ht, tbl)) - schedule_work(&ht->run_work); - return NULL; } @@ -611,15 +607,23 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); data = ERR_PTR(-EAGAIN); } else { + bool inserted; + flags = rht_lock(tbl, bkt); data = rhashtable_lookup_one(ht, bkt, tbl, hash, key, obj); new_tbl = rhashtable_insert_one(ht, bkt, tbl, hash, obj, data); + inserted = data && !new_tbl; + if (inserted) + atomic_inc(&ht->nelems); if (PTR_ERR(new_tbl) != -EEXIST) data = ERR_CAST(new_tbl); rht_unlock(tbl, bkt, flags); + + if (inserted && rht_grow_above_75(ht, tbl)) + schedule_work(&ht->run_work); } } while (!IS_ERR_OR_NULL(new_tbl)); diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index 5918d1b32e196005330fe51b0dabcb5b7709b910..09b41363f84559855a125116b3e8409112819ebb 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -7,7 +7,7 @@ #include #include -extern struct bpf_struct_ops bpf_bpf_dummy_ops; +static struct bpf_struct_ops bpf_bpf_dummy_ops; /* A common type for test_N with return value in bpf_dummy_ops */ typedef int (*dummy_ops_test_ret_fn)(struct bpf_dummy_ops_state *state, ...); @@ -17,6 +17,8 @@ struct bpf_dummy_ops_test_args { struct bpf_dummy_ops_state state; }; +static struct btf *bpf_dummy_ops_btf; + static struct bpf_dummy_ops_test_args * dummy_ops_init_args(const union bpf_attr *kattr, unsigned int nr) { @@ -84,10 +86,17 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, struct bpf_tramp_link *link = NULL; void *image = NULL; unsigned int op_idx; + u32 image_off = 0; int prog_ret; + s32 type_id; int err; - if (prog->aux->attach_btf_id != st_ops->type_id) + type_id = btf_find_by_name_kind(bpf_dummy_ops_btf, + bpf_bpf_dummy_ops.name, + BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + if (prog->aux->attach_btf_id != type_id) return -EOPNOTSUPP; func_proto = prog->aux->attach_func_proto; @@ -101,13 +110,6 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, goto out; } - image = bpf_jit_alloc_exec(PAGE_SIZE); - if (!image) { - err = -ENOMEM; - goto out; - } - set_vm_flush_reset_perms(image); - link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; @@ -120,11 +122,12 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, op_idx = prog->expected_attach_type; err = bpf_struct_ops_prepare_trampoline(tlinks, link, &st_ops->func_models[op_idx], - image, image + PAGE_SIZE); + &image, &image_off, + true); if (err < 0) goto out; - set_memory_rox((long)image, 1); + arch_protect_bpf_trampoline(image, PAGE_SIZE); prog_ret = dummy_ops_call_op(image, args); err = dummy_ops_copy_args(args); @@ -134,7 +137,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, err = -EFAULT; out: kfree(args); - bpf_jit_free_exec(image); + bpf_struct_ops_image_free(image); if (link) bpf_link_put(&link->link); kfree(tlinks); @@ -143,6 +146,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, static int bpf_dummy_init(struct btf *btf) { + bpf_dummy_ops_btf = btf; return 0; } @@ -220,7 +224,29 @@ static void bpf_dummy_unreg(void *kdata) { } -struct bpf_struct_ops bpf_bpf_dummy_ops = { +static int bpf_dummy_test_1(struct bpf_dummy_ops_state *cb) +{ + return 0; +} + +static int bpf_dummy_test_2(struct bpf_dummy_ops_state *cb, int a1, unsigned short a2, + char a3, unsigned long a4) +{ + return 0; +} + +static int bpf_dummy_test_sleepable(struct bpf_dummy_ops_state *cb) +{ + return 0; +} + +static struct bpf_dummy_ops __bpf_bpf_dummy_ops = { + .test_1 = bpf_dummy_test_1, + .test_2 = bpf_dummy_test_2, + .test_sleepable = bpf_dummy_test_sleepable, +}; + +static struct bpf_struct_ops bpf_bpf_dummy_ops = { .verifier_ops = &bpf_dummy_verifier_ops, .init = bpf_dummy_init, .check_member = bpf_dummy_ops_check_member, @@ -228,4 +254,12 @@ struct bpf_struct_ops bpf_bpf_dummy_ops = { .reg = bpf_dummy_reg, .unreg = bpf_dummy_unreg, .name = "bpf_dummy_ops", + .cfi_stubs = &__bpf_bpf_dummy_ops, + .owner = THIS_MODULE, }; + +static int __init bpf_dummy_struct_ops_init(void) +{ + return register_bpf_struct_ops(&bpf_bpf_dummy_ops, bpf_dummy_ops); +} +late_initcall(bpf_dummy_struct_ops_init); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 73fb9db55798c86ca0a18d353afb235159911ae3..43771eacd2bb603396ebcb97f2c0dd061a36fec0 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -504,9 +504,8 @@ static int bpf_test_finish(const union bpf_attr *kattr, * architecture dependent calling conventions. 7+ can be supported in the * future. */ -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "Global functions as their definitions will be in vmlinux BTF"); +__bpf_kfunc_start_defs(); + __bpf_kfunc int bpf_fentry_test1(int a) { return a + 1; @@ -606,23 +605,23 @@ __bpf_kfunc void bpf_kfunc_call_memb_release(struct prog_test_member *p) { } -__diag_pop(); +__bpf_kfunc_end_defs(); -BTF_SET8_START(bpf_test_modify_return_ids) +BTF_KFUNCS_START(bpf_test_modify_return_ids) BTF_ID_FLAGS(func, bpf_modify_return_test) BTF_ID_FLAGS(func, bpf_modify_return_test2) BTF_ID_FLAGS(func, bpf_fentry_test1, KF_SLEEPABLE) -BTF_SET8_END(bpf_test_modify_return_ids) +BTF_KFUNCS_END(bpf_test_modify_return_ids) static const struct btf_kfunc_id_set bpf_test_modify_return_set = { .owner = THIS_MODULE, .set = &bpf_test_modify_return_ids, }; -BTF_SET8_START(test_sk_check_kfunc_ids) +BTF_KFUNCS_START(test_sk_check_kfunc_ids) BTF_ID_FLAGS(func, bpf_kfunc_call_test_release, KF_RELEASE) BTF_ID_FLAGS(func, bpf_kfunc_call_memb_release, KF_RELEASE) -BTF_SET8_END(test_sk_check_kfunc_ids) +BTF_KFUNCS_END(test_sk_check_kfunc_ids) static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size, u32 size, u32 headroom, u32 tailroom) diff --git a/net/core/filter.c b/net/core/filter.c index eee64a67df40540a2a395bbad987f72fc9882525..d32c0000d3459e8aa7aae4716350e2bc0ca2bcc5 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -12019,9 +12019,7 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id) return func; } -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "Global functions as their definitions will be in vmlinux BTF"); +__bpf_kfunc_start_defs(); __bpf_kfunc int bpf_dynptr_from_skb(struct sk_buff *skb, u64 flags, struct bpf_dynptr_kern *ptr__uninit) { @@ -12143,7 +12141,7 @@ __bpf_kfunc int bpf_skb_change_dev(struct __sk_buff *skb_ctx, u32 ifindex) return 0; } #endif -__diag_pop(); +__bpf_kfunc_end_defs(); int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, struct bpf_dynptr_kern *ptr__uninit) @@ -12159,21 +12157,21 @@ int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, return 0; } -BTF_SET8_START(bpf_kfunc_check_set_skb) +BTF_KFUNCS_START(bpf_kfunc_check_set_skb) BTF_ID_FLAGS(func, bpf_dynptr_from_skb) -BTF_SET8_END(bpf_kfunc_check_set_skb) +BTF_KFUNCS_END(bpf_kfunc_check_set_skb) -BTF_SET8_START(bpf_kfunc_check_set_xdp) +BTF_KFUNCS_START(bpf_kfunc_check_set_xdp) BTF_ID_FLAGS(func, bpf_dynptr_from_xdp) #ifdef CONFIG_HISOCK BTF_ID_FLAGS(func, bpf_xdp_set_ingress_dst) BTF_ID_FLAGS(func, bpf_xdp_change_dev) #endif -BTF_SET8_END(bpf_kfunc_check_set_xdp) +BTF_KFUNCS_END(bpf_kfunc_check_set_xdp) -BTF_SET8_START(bpf_kfunc_check_set_sock_addr) +BTF_KFUNCS_START(bpf_kfunc_check_set_sock_addr) BTF_ID_FLAGS(func, bpf_sock_addr_set_sun_path) -BTF_SET8_END(bpf_kfunc_check_set_sock_addr) +BTF_KFUNCS_END(bpf_kfunc_check_set_sock_addr) #ifdef CONFIG_HISOCK BTF_SET8_START(bpf_kfunc_check_set_sock_ops) @@ -12236,10 +12234,7 @@ static int __init bpf_kfunc_init(void) } late_initcall(bpf_kfunc_init); -/* Disables missing prototype warnings */ -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "Global functions as their definitions will be in vmlinux BTF"); +__bpf_kfunc_start_defs(); /* bpf_sock_destroy: Destroy the given socket with ECONNABORTED error code. * @@ -12273,11 +12268,11 @@ __bpf_kfunc int bpf_sock_destroy(struct sock_common *sock) return sk->sk_prot->diag_destroy(sk, ECONNABORTED); } -__diag_pop() +__bpf_kfunc_end_defs(); -BTF_SET8_START(bpf_sk_iter_kfunc_ids) +BTF_KFUNCS_START(bpf_sk_iter_kfunc_ids) BTF_ID_FLAGS(func, bpf_sock_destroy, KF_TRUSTED_ARGS) -BTF_SET8_END(bpf_sk_iter_kfunc_ids) +BTF_KFUNCS_END(bpf_sk_iter_kfunc_ids) static int tracing_iter_filter(const struct bpf_prog *prog, u32 kfunc_id) { diff --git a/net/core/xdp.c b/net/core/xdp.c index 5ee3f8f165e5aa68bcc1134087a25956ea685a33..39738e00e732408c670d2dc317312ab3e5112fab 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -692,9 +692,7 @@ struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf) return nxdpf; } -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "Global functions as their definitions will be in vmlinux BTF"); +__bpf_kfunc_start_defs(); /** * bpf_xdp_metadata_rx_timestamp - Read XDP frame RX timestamp. @@ -734,13 +732,13 @@ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash, return -EOPNOTSUPP; } -__diag_pop(); +__bpf_kfunc_end_defs(); -BTF_SET8_START(xdp_metadata_kfunc_ids) +BTF_KFUNCS_START(xdp_metadata_kfunc_ids) #define XDP_METADATA_KFUNC(_, name) BTF_ID_FLAGS(func, name, KF_TRUSTED_ARGS) XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC -BTF_SET8_END(xdp_metadata_kfunc_ids) +BTF_KFUNCS_END(xdp_metadata_kfunc_ids) static const struct btf_kfunc_id_set xdp_metadata_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 39dcccf0f174b95f2ec4cd7bed3cc86a73dede3b..5d83d7b058faffe722916888635cb4c4690f1e23 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -12,7 +12,7 @@ #include /* "extern" is to avoid sparse warning. It is only used in bpf_struct_ops.c. */ -extern struct bpf_struct_ops bpf_tcp_congestion_ops; +static struct bpf_struct_ops bpf_tcp_congestion_ops; static u32 unsupported_ops[] = { offsetof(struct tcp_congestion_ops, get_info), @@ -20,6 +20,7 @@ static u32 unsupported_ops[] = { static const struct btf_type *tcp_sock_type; static u32 tcp_sock_id, sock_id; +static const struct btf_type *tcp_congestion_ops_type; static int bpf_tcp_ca_init(struct btf *btf) { @@ -36,6 +37,11 @@ static int bpf_tcp_ca_init(struct btf *btf) tcp_sock_id = type_id; tcp_sock_type = btf_type_by_id(btf, tcp_sock_id); + type_id = btf_find_by_name_kind(btf, "tcp_congestion_ops", BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + tcp_congestion_ops_type = btf_type_by_id(btf, type_id); + return 0; } @@ -149,7 +155,7 @@ static u32 prog_ops_moff(const struct bpf_prog *prog) u32 midx; midx = prog->expected_attach_type; - t = bpf_tcp_congestion_ops.type; + t = tcp_congestion_ops_type; m = &btf_type_member(t)[midx]; return __btf_member_bit_offset(t, m) / 8; @@ -195,13 +201,13 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, } } -BTF_SET8_START(bpf_tcp_ca_check_kfunc_ids) +BTF_KFUNCS_START(bpf_tcp_ca_check_kfunc_ids) BTF_ID_FLAGS(func, tcp_reno_ssthresh) BTF_ID_FLAGS(func, tcp_reno_cong_avoid) BTF_ID_FLAGS(func, tcp_reno_undo_cwnd) BTF_ID_FLAGS(func, tcp_slow_start) BTF_ID_FLAGS(func, tcp_cong_avoid_ai) -BTF_SET8_END(bpf_tcp_ca_check_kfunc_ids) +BTF_KFUNCS_END(bpf_tcp_ca_check_kfunc_ids) static const struct btf_kfunc_id_set bpf_tcp_ca_kfunc_set = { .owner = THIS_MODULE, @@ -271,7 +277,75 @@ static int bpf_tcp_ca_validate(void *kdata) return tcp_validate_congestion_control(kdata); } -struct bpf_struct_ops bpf_tcp_congestion_ops = { +static u32 bpf_tcp_ca_ssthresh(struct sock *sk) +{ + return 0; +} + +static void bpf_tcp_ca_cong_avoid(struct sock *sk, u32 ack, u32 acked) +{ +} + +static void bpf_tcp_ca_set_state(struct sock *sk, u8 new_state) +{ +} + +static void bpf_tcp_ca_cwnd_event(struct sock *sk, enum tcp_ca_event ev) +{ +} + +static void bpf_tcp_ca_in_ack_event(struct sock *sk, u32 flags) +{ +} + +static void bpf_tcp_ca_pkts_acked(struct sock *sk, const struct ack_sample *sample) +{ +} + +static u32 bpf_tcp_ca_min_tso_segs(struct sock *sk) +{ + return 0; +} + +static void bpf_tcp_ca_cong_control(struct sock *sk, const struct rate_sample *rs) +{ +} + +static u32 bpf_tcp_ca_undo_cwnd(struct sock *sk) +{ + return 0; +} + +static u32 bpf_tcp_ca_sndbuf_expand(struct sock *sk) +{ + return 0; +} + +static void __bpf_tcp_ca_init(struct sock *sk) +{ +} + +static void __bpf_tcp_ca_release(struct sock *sk) +{ +} + +static struct tcp_congestion_ops __bpf_ops_tcp_congestion_ops = { + .ssthresh = bpf_tcp_ca_ssthresh, + .cong_avoid = bpf_tcp_ca_cong_avoid, + .set_state = bpf_tcp_ca_set_state, + .cwnd_event = bpf_tcp_ca_cwnd_event, + .in_ack_event = bpf_tcp_ca_in_ack_event, + .pkts_acked = bpf_tcp_ca_pkts_acked, + .min_tso_segs = bpf_tcp_ca_min_tso_segs, + .cong_control = bpf_tcp_ca_cong_control, + .undo_cwnd = bpf_tcp_ca_undo_cwnd, + .sndbuf_expand = bpf_tcp_ca_sndbuf_expand, + + .init = __bpf_tcp_ca_init, + .release = __bpf_tcp_ca_release, +}; + +static struct bpf_struct_ops bpf_tcp_congestion_ops = { .verifier_ops = &bpf_tcp_ca_verifier_ops, .reg = bpf_tcp_ca_reg, .unreg = bpf_tcp_ca_unreg, @@ -281,10 +355,17 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = { .init = bpf_tcp_ca_init, .validate = bpf_tcp_ca_validate, .name = "tcp_congestion_ops", + .cfi_stubs = &__bpf_ops_tcp_congestion_ops, + .owner = THIS_MODULE, }; static int __init bpf_tcp_ca_kfunc_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + int ret; + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + ret = ret ?: register_bpf_struct_ops(&bpf_tcp_congestion_ops, tcp_congestion_ops); + + return ret; } late_initcall(bpf_tcp_ca_kfunc_init); diff --git a/net/ipv4/fou_bpf.c b/net/ipv4/fou_bpf.c index 3760a14b6b576b07c60879bf58831c382cd103bc..06e5572f296f1e70d49e10cd343ab09d3aa30009 100644 --- a/net/ipv4/fou_bpf.c +++ b/net/ipv4/fou_bpf.c @@ -22,9 +22,7 @@ enum bpf_fou_encap_type { FOU_BPF_ENCAP_GUE, }; -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "Global functions as their definitions will be in BTF"); +__bpf_kfunc_start_defs(); /* bpf_skb_set_fou_encap - Set FOU encap parameters * @@ -100,12 +98,12 @@ __bpf_kfunc int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx, return 0; } -__diag_pop() +__bpf_kfunc_end_defs(); -BTF_SET8_START(fou_kfunc_set) +BTF_KFUNCS_START(fou_kfunc_set) BTF_ID_FLAGS(func, bpf_skb_set_fou_encap) BTF_ID_FLAGS(func, bpf_skb_get_fou_encap) -BTF_SET8_END(fou_kfunc_set) +BTF_KFUNCS_END(fou_kfunc_set) static const struct btf_kfunc_id_set fou_bpf_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 146792cd26fed4e61cd72a5d85263b2c7c7b2636..56bb7a9621ab4d042b16c600e066a80b46991a8a 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -1154,7 +1154,7 @@ static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = { .set_state = bbr_set_state, }; -BTF_SET8_START(tcp_bbr_check_kfunc_ids) +BTF_KFUNCS_START(tcp_bbr_check_kfunc_ids) #ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE BTF_ID_FLAGS(func, bbr_init) @@ -1167,7 +1167,7 @@ BTF_ID_FLAGS(func, bbr_min_tso_segs) BTF_ID_FLAGS(func, bbr_set_state) #endif #endif -BTF_SET8_END(tcp_bbr_check_kfunc_ids) +BTF_KFUNCS_END(tcp_bbr_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_bbr_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 95dbb2799be4639f106a4ce5f601ec2b6a43ca4a..48617d99abb0d4be003913e40d7a69d95db0138d 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -145,11 +145,7 @@ EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control); int tcp_update_congestion_control(struct tcp_congestion_ops *ca, struct tcp_congestion_ops *old_ca) { struct tcp_congestion_ops *existing; - int ret; - - ret = tcp_validate_congestion_control(ca); - if (ret) - return ret; + int ret = 0; ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name)); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 5ff7be13deb6b7c698f45330d11f4e35f98af683..103e93f7a9f148a4cacc29887f6dc10b259b93cf 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -487,7 +487,7 @@ static struct tcp_congestion_ops cubictcp __read_mostly = { .name = "cubic", }; -BTF_SET8_START(tcp_cubic_check_kfunc_ids) +BTF_KFUNCS_START(tcp_cubic_check_kfunc_ids) #ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE BTF_ID_FLAGS(func, cubictcp_init) @@ -498,7 +498,7 @@ BTF_ID_FLAGS(func, cubictcp_cwnd_event) BTF_ID_FLAGS(func, cubictcp_acked) #endif #endif -BTF_SET8_END(tcp_cubic_check_kfunc_ids) +BTF_KFUNCS_END(tcp_cubic_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_cubic_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 8ad62713b0ba2b2561ded013057a73900cba51f0..b004280855f878ee1cb90e576c9e302e8a8762ef 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -271,7 +271,7 @@ static struct tcp_congestion_ops dctcp_reno __read_mostly = { .name = "dctcp-reno", }; -BTF_SET8_START(tcp_dctcp_check_kfunc_ids) +BTF_KFUNCS_START(tcp_dctcp_check_kfunc_ids) #ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE BTF_ID_FLAGS(func, dctcp_init) @@ -282,7 +282,7 @@ BTF_ID_FLAGS(func, dctcp_cwnd_undo) BTF_ID_FLAGS(func, dctcp_state) #endif #endif -BTF_SET8_END(tcp_dctcp_check_kfunc_ids) +BTF_KFUNCS_END(tcp_dctcp_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_dctcp_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index b21799d468d2815413cc1334cb6c5e5df7fe231d..d2492d050fe601fbb1ce8e3cb598603914712a83 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -230,9 +230,7 @@ static int _nf_conntrack_btf_struct_access(struct bpf_verifier_log *log, return 0; } -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "Global functions as their definitions will be in nf_conntrack BTF"); +__bpf_kfunc_start_defs(); /* bpf_xdp_ct_alloc - Allocate a new CT entry * @@ -467,9 +465,9 @@ __bpf_kfunc int bpf_ct_change_status(struct nf_conn *nfct, u32 status) return nf_ct_change_status_common(nfct, status); } -__diag_pop() +__bpf_kfunc_end_defs(); -BTF_SET8_START(nf_ct_kfunc_set) +BTF_KFUNCS_START(nf_ct_kfunc_set) BTF_ID_FLAGS(func, bpf_xdp_ct_alloc, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_xdp_ct_lookup, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_skb_ct_alloc, KF_ACQUIRE | KF_RET_NULL) @@ -480,7 +478,7 @@ BTF_ID_FLAGS(func, bpf_ct_set_timeout, KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_ct_change_timeout, KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_ct_set_status, KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_ct_change_status, KF_TRUSTED_ARGS) -BTF_SET8_END(nf_ct_kfunc_set) +BTF_KFUNCS_END(nf_ct_kfunc_set) static const struct btf_kfunc_id_set nf_conntrack_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/netfilter/nf_nat_bpf.c b/net/netfilter/nf_nat_bpf.c index 141ee7783223dad0e8511565c233873223c3e2e2..481be15609b16ab892aa1ba891d6906477623891 100644 --- a/net/netfilter/nf_nat_bpf.c +++ b/net/netfilter/nf_nat_bpf.c @@ -12,9 +12,7 @@ #include #include -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "Global functions as their definitions will be in nf_nat BTF"); +__bpf_kfunc_start_defs(); /* bpf_ct_set_nat_info - Set source or destination nat address * @@ -54,11 +52,11 @@ __bpf_kfunc int bpf_ct_set_nat_info(struct nf_conn___init *nfct, return nf_nat_setup_info(ct, &range, manip) == NF_DROP ? -ENOMEM : 0; } -__diag_pop() +__bpf_kfunc_end_defs(); -BTF_SET8_START(nf_nat_kfunc_set) +BTF_KFUNCS_START(nf_nat_kfunc_set) BTF_ID_FLAGS(func, bpf_ct_set_nat_info, KF_TRUSTED_ARGS) -BTF_SET8_END(nf_nat_kfunc_set) +BTF_KFUNCS_END(nf_nat_kfunc_set) static const struct btf_kfunc_id_set nf_bpf_nat_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/xfrm/xfrm_interface_bpf.c b/net/xfrm/xfrm_interface_bpf.c index d74f3fd20f2bf25f0166b293fc378823b2612e8b..5ea15037ebd1049ee1938a0bac0a335d04dd87c5 100644 --- a/net/xfrm/xfrm_interface_bpf.c +++ b/net/xfrm/xfrm_interface_bpf.c @@ -27,9 +27,7 @@ struct bpf_xfrm_info { int link; }; -__diag_push(); -__diag_ignore_all("-Wmissing-prototypes", - "Global functions as their definitions will be in xfrm_interface BTF"); +__bpf_kfunc_start_defs(); /* bpf_skb_get_xfrm_info - Get XFRM metadata * @@ -93,12 +91,12 @@ __bpf_kfunc int bpf_skb_set_xfrm_info(struct __sk_buff *skb_ctx, const struct bp return 0; } -__diag_pop() +__bpf_kfunc_end_defs(); -BTF_SET8_START(xfrm_ifc_kfunc_set) +BTF_KFUNCS_START(xfrm_ifc_kfunc_set) BTF_ID_FLAGS(func, bpf_skb_get_xfrm_info) BTF_ID_FLAGS(func, bpf_skb_set_xfrm_info) -BTF_SET8_END(xfrm_ifc_kfunc_set) +BTF_KFUNCS_END(xfrm_ifc_kfunc_set) static const struct btf_kfunc_id_set xfrm_interface_kfunc_set = { .owner = THIS_MODULE, diff --git a/scripts/gdb/linux/interrupts.py b/scripts/gdb/linux/interrupts.py index ef478e273791f359edc722b28c4d35f55bc8e2ee..7e50f3b9dfad46389b87ab455a5b7b03119161de 100644 --- a/scripts/gdb/linux/interrupts.py +++ b/scripts/gdb/linux/interrupts.py @@ -37,7 +37,7 @@ def show_irq_desc(prec, irq): any_count = 0 if desc['kstat_irqs']: for cpu in cpus.each_online_cpu(): - any_count += cpus.per_cpu(desc['kstat_irqs'], cpu) + any_count += cpus.per_cpu(desc['kstat_irqs'], cpu)['cnt'] if (desc['action'] == 0 or irq_desc_is_chained(desc)) and any_count == 0: return text; @@ -45,7 +45,7 @@ def show_irq_desc(prec, irq): text += "%*d: " % (prec, irq) for cpu in cpus.each_online_cpu(): if desc['kstat_irqs']: - count = cpus.per_cpu(desc['kstat_irqs'], cpu) + count = cpus.per_cpu(desc['kstat_irqs'], cpu)['cnt'] else: count = 0 text += "%10u" % (count) @@ -177,7 +177,7 @@ def arm_common_show_interrupts(prec): if desc == 0: continue for cpu in cpus.each_online_cpu(): - text += "%10u" % (cpus.per_cpu(desc['kstat_irqs'], cpu)) + text += "%10u" % (cpus.per_cpu(desc['kstat_irqs'], cpu)['cnt']) text += " %s" % (ipi_types[ipi].string()) text += "\n" return text diff --git a/tools/Makefile b/tools/Makefile index 37e9f6804832641c176afe5ef150031748a77e9a..8021267f7e5b69467c637c7492cc2518c5a317d5 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -29,6 +29,7 @@ help: @echo ' pci - PCI tools' @echo ' perf - Linux performance measurement and analysis tool' @echo ' selftests - various kernel selftests' + @echo ' sched_ext - sched_ext example schedulers' @echo ' bootconfig - boot config tool' @echo ' spi - spi tools' @echo ' tmon - thermal monitoring and tuning tool' @@ -92,6 +93,9 @@ perf: FORCE $(Q)mkdir -p $(PERF_O) . $(Q)$(MAKE) --no-print-directory -C perf O=$(PERF_O) subdir= +sched_ext: FORCE + $(call descend,sched_ext) + selftests: FORCE $(call descend,testing/$@) @@ -185,6 +189,9 @@ perf_clean: $(Q)mkdir -p $(PERF_O) . $(Q)$(MAKE) --no-print-directory -C perf O=$(PERF_O) subdir= clean +sched_ext_clean: + $(call descend,sched_ext,clean) + selftests_clean: $(call descend,testing/$(@:_clean=),clean) @@ -214,6 +221,7 @@ clean: acpi_clean cgroup_clean counter_clean cpupower_clean hv_clean firewire_cl mm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ freefall_clean build_clean libbpf_clean libsubcmd_clean \ gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean \ - intel-speed-select_clean tracing_clean thermal_clean thermometer_clean thermal-engine_clean + intel-speed-select_clean tracing_clean thermal_clean thermometer_clean thermal-engine_clean \ + sched_ext_clean .PHONY: FORCE diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst index 5006e724d1bc01c1afe5e13fb4ca29a33725a3ea..5e60825818dd37867c80f90b25ea6e63c521ff92 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst @@ -257,18 +257,48 @@ EXAMPLES return 0; } -This is example BPF application with two BPF programs and a mix of BPF maps -and global variables. Source code is split across two source code files. +**$ cat example3.bpf.c** + +:: + + #include + #include + #include + /* This header file is provided by the bpf_testmod module. */ + #include "bpf_testmod.h" + + int test_2_result = 0; + + /* bpf_Testmod.ko calls this function, passing a "4" + * and testmod_map->data. + */ + SEC("struct_ops/test_2") + void BPF_PROG(test_2, int a, int b) + { + test_2_result = a + b; + } + + SEC(".struct_ops") + struct bpf_testmod_ops testmod_map = { + .test_2 = (void *)test_2, + .data = 0x1, + }; + +This is example BPF application with three BPF programs and a mix of BPF +maps and global variables. Source code is split across three source code +files. **$ clang --target=bpf -g example1.bpf.c -o example1.bpf.o** **$ clang --target=bpf -g example2.bpf.c -o example2.bpf.o** -**$ bpftool gen object example.bpf.o example1.bpf.o example2.bpf.o** +**$ clang --target=bpf -g example3.bpf.c -o example3.bpf.o** + +**$ bpftool gen object example.bpf.o example1.bpf.o example2.bpf.o example3.bpf.o** -This set of commands compiles *example1.bpf.c* and *example2.bpf.c* -individually and then statically links respective object files into the final -BPF ELF object file *example.bpf.o*. +This set of commands compiles *example1.bpf.c*, *example2.bpf.c* and +*example3.bpf.c* individually and then statically links respective object +files into the final BPF ELF object file *example.bpf.o*. **$ bpftool gen skeleton example.bpf.o name example | tee example.skel.h** @@ -291,7 +321,15 @@ BPF ELF object file *example.bpf.o*. struct bpf_map *data; struct bpf_map *bss; struct bpf_map *my_map; + struct bpf_map *testmod_map; } maps; + struct { + struct example__testmod_map__bpf_testmod_ops { + const struct bpf_program *test_1; + const struct bpf_program *test_2; + int data; + } *testmod_map; + } struct_ops; struct { struct bpf_program *handle_sys_enter; struct bpf_program *handle_sys_exit; @@ -304,6 +342,7 @@ BPF ELF object file *example.bpf.o*. struct { int x; } data; + int test_2_result; } *bss; struct example__data { _Bool global_flag; @@ -342,10 +381,16 @@ BPF ELF object file *example.bpf.o*. skel->rodata->param1 = 128; + /* Change the value through the pointer of shadow type */ + skel->struct_ops.testmod_map->data = 13; + err = example__load(skel); if (err) goto cleanup; + /* The result of the function test_2() */ + printf("test_2_result: %d\n", skel->bss->test_2_result); + err = example__attach(skel); if (err) goto cleanup; @@ -372,6 +417,7 @@ BPF ELF object file *example.bpf.o*. :: + test_2_result: 17 my_map name: my_map sys_enter prog FD: 8 my_static_var: 7 diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 882bf8e6e70e44c10844bde9cae216da468d39cf..34515fbe9414e1cb908e0896b289a13a2bada4ed 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -54,6 +54,20 @@ static bool str_has_suffix(const char *str, const char *suffix) return true; } +static const struct btf_type * +resolve_func_ptr(const struct btf *btf, __u32 id, __u32 *res_id) +{ + const struct btf_type *t; + + t = skip_mods_and_typedefs(btf, id, NULL); + if (!btf_is_ptr(t)) + return NULL; + + t = skip_mods_and_typedefs(btf, t->type, res_id); + + return btf_is_func_proto(t) ? t : NULL; +} + static void get_obj_name(char *name, const char *file) { /* Using basename() GNU version which doesn't modify arg. */ @@ -903,6 +917,207 @@ codegen_progs_skeleton(struct bpf_object *obj, size_t prog_cnt, bool populate_li } } +static int walk_st_ops_shadow_vars(struct btf *btf, const char *ident, + const struct btf_type *map_type, __u32 map_type_id) +{ + LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts, .indent_level = 3); + const struct btf_type *member_type; + __u32 offset, next_offset = 0; + const struct btf_member *m; + struct btf_dump *d = NULL; + const char *member_name; + __u32 member_type_id; + int i, err = 0, n; + int size; + + d = btf_dump__new(btf, codegen_btf_dump_printf, NULL, NULL); + if (!d) + return -errno; + + n = btf_vlen(map_type); + for (i = 0, m = btf_members(map_type); i < n; i++, m++) { + member_type = skip_mods_and_typedefs(btf, m->type, &member_type_id); + member_name = btf__name_by_offset(btf, m->name_off); + + offset = m->offset / 8; + if (next_offset < offset) + printf("\t\t\tchar __padding_%d[%d];\n", i, offset - next_offset); + + switch (btf_kind(member_type)) { + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + /* scalar type */ + printf("\t\t\t"); + opts.field_name = member_name; + err = btf_dump__emit_type_decl(d, member_type_id, &opts); + if (err) { + p_err("Failed to emit type declaration for %s: %d", member_name, err); + goto out; + } + printf(";\n"); + + size = btf__resolve_size(btf, member_type_id); + if (size < 0) { + p_err("Failed to resolve size of %s: %d\n", member_name, size); + err = size; + goto out; + } + + next_offset = offset + size; + break; + + case BTF_KIND_PTR: + if (resolve_func_ptr(btf, m->type, NULL)) { + /* Function pointer */ + printf("\t\t\tstruct bpf_program *%s;\n", member_name); + + next_offset = offset + sizeof(void *); + break; + } + /* All pointer types are unsupported except for + * function pointers. + */ + fallthrough; + + default: + /* Unsupported types + * + * Types other than scalar types and function + * pointers are currently not supported in order to + * prevent conflicts in the generated code caused + * by multiple definitions. For instance, if the + * struct type FOO is used in a struct_ops map, + * bpftool has to generate definitions for FOO, + * which may result in conflicts if FOO is defined + * in different skeleton files. + */ + size = btf__resolve_size(btf, member_type_id); + if (size < 0) { + p_err("Failed to resolve size of %s: %d\n", member_name, size); + err = size; + goto out; + } + printf("\t\t\tchar __unsupported_%d[%d];\n", i, size); + + next_offset = offset + size; + break; + } + } + + /* Cannot fail since it must be a struct type */ + size = btf__resolve_size(btf, map_type_id); + if (next_offset < (__u32)size) + printf("\t\t\tchar __padding_end[%d];\n", size - next_offset); + +out: + btf_dump__free(d); + + return err; +} + +/* Generate the pointer of the shadow type for a struct_ops map. + * + * This function adds a pointer of the shadow type for a struct_ops map. + * The members of a struct_ops map can be exported through a pointer to a + * shadow type. The user can access these members through the pointer. + * + * A shadow type includes not all members, only members of some types. + * They are scalar types and function pointers. The function pointers are + * translated to the pointer of the struct bpf_program. The scalar types + * are translated to the original type without any modifiers. + * + * Unsupported types will be translated to a char array to occupy the same + * space as the original field, being renamed as __unsupported_*. The user + * should treat these fields as opaque data. + */ +static int gen_st_ops_shadow_type(const char *obj_name, struct btf *btf, const char *ident, + const struct bpf_map *map) +{ + const struct btf_type *map_type; + const char *type_name; + __u32 map_type_id; + int err; + + map_type_id = bpf_map__btf_value_type_id(map); + if (map_type_id == 0) + return -EINVAL; + map_type = btf__type_by_id(btf, map_type_id); + if (!map_type) + return -EINVAL; + + type_name = btf__name_by_offset(btf, map_type->name_off); + + printf("\t\tstruct %s__%s__%s {\n", obj_name, ident, type_name); + + err = walk_st_ops_shadow_vars(btf, ident, map_type, map_type_id); + if (err) + return err; + + printf("\t\t} *%s;\n", ident); + + return 0; +} + +static int gen_st_ops_shadow(const char *obj_name, struct btf *btf, struct bpf_object *obj) +{ + int err, st_ops_cnt = 0; + struct bpf_map *map; + char ident[256]; + + if (!btf) + return 0; + + /* Generate the pointers to shadow types of + * struct_ops maps. + */ + bpf_object__for_each_map(map, obj) { + if (bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS) + continue; + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + + if (st_ops_cnt == 0) /* first struct_ops map */ + printf("\tstruct {\n"); + st_ops_cnt++; + + err = gen_st_ops_shadow_type(obj_name, btf, ident, map); + if (err) + return err; + } + + if (st_ops_cnt) + printf("\t} struct_ops;\n"); + + return 0; +} + +/* Generate the code to initialize the pointers of shadow types. */ +static void gen_st_ops_shadow_init(struct btf *btf, struct bpf_object *obj) +{ + struct bpf_map *map; + char ident[256]; + + if (!btf) + return; + + /* Initialize the pointers to_ops shadow types of + * struct_ops maps. + */ + bpf_object__for_each_map(map, obj) { + if (bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS) + continue; + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + codegen("\ + \n\ + obj->struct_ops.%1$s = bpf_map__initial_value(obj->maps.%1$s, NULL);\n\ + \n\ + ", ident); + } +} + static int do_skeleton(int argc, char **argv) { char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")]; @@ -1046,6 +1261,11 @@ static int do_skeleton(int argc, char **argv) printf("\t} maps;\n"); } + btf = bpf_object__btf(obj); + err = gen_st_ops_shadow(obj_name, btf, obj); + if (err) + goto out; + if (prog_cnt) { printf("\tstruct {\n"); bpf_object__for_each_program(prog, obj) { @@ -1069,7 +1289,6 @@ static int do_skeleton(int argc, char **argv) printf("\t} links;\n"); } - btf = bpf_object__btf(obj); if (btf) { err = codegen_datasecs(obj, obj_name); if (err) @@ -1127,6 +1346,12 @@ static int do_skeleton(int argc, char **argv) if (err) \n\ goto err_out; \n\ \n\ + ", obj_name); + + gen_st_ops_shadow_init(btf, obj); + + codegen("\ + \n\ return obj; \n\ err_out: \n\ %1$s__destroy(obj); \n\ @@ -1436,6 +1661,10 @@ static int do_subskeleton(int argc, char **argv) printf("\t} maps;\n"); } + err = gen_st_ops_shadow(obj_name, btf, obj); + if (err) + goto out; + if (prog_cnt) { printf("\tstruct {\n"); bpf_object__for_each_program(prog, obj) { @@ -1547,6 +1776,12 @@ static int do_subskeleton(int argc, char **argv) if (err) \n\ goto err; \n\ \n\ + "); + + gen_st_ops_shadow_init(btf, obj); + + codegen("\ + \n\ return obj; \n\ err: \n\ %1$s__destroy(obj); \n\ diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h index 7319f6ced10860e3f0c30c599086384a5268740f..272f15d0e43489469ecbf42aeace02b187166851 100644 --- a/tools/include/linux/bitops.h +++ b/tools/include/linux/bitops.h @@ -20,6 +20,8 @@ #define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(u32)) #define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) +#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_BYTE) + extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); extern unsigned int __sw_hweight32(unsigned int w); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a457d4f82da2850f0ab8a23ff3eac698e5fea938..f8301a68c76b1d4a6ccd204a989b0a1f94546abd 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1335,6 +1335,9 @@ enum { /* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ BPF_F_PATH_FD = (1U << 14), + +/* Flag for value_type_btf_obj_fd, the fd is available */ + BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15), }; /* Flags for BPF_PROG_QUERY. */ @@ -1408,6 +1411,11 @@ union bpf_attr { * to using 5 hash functions). */ __u64 map_extra; + + __s32 value_type_btf_obj_fd; /* fd pointing to a BTF + * type data for + * btf_vmlinux_value_type_id. + */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -5122,6 +5130,8 @@ union bpf_attr { * **BPF_F_TIMER_ABS** * Start the timer in absolute expire value instead of the * default relative one. + * **BPF_F_TIMER_CPU_PIN** + * Timer will be pinned to the CPU of the caller. * * Return * 0 on success. @@ -6484,7 +6494,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; - __u32 :32; /* alignment pad */ + __u32 btf_vmlinux_id; __u64 map_extra; } __attribute__((aligned(8))); @@ -6568,20 +6578,27 @@ struct bpf_link_info { __aligned_u64 file_name; /* in/out */ __u32 name_len; __u32 offset; /* offset from file_name */ + __u64 cookie; } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */ struct { __aligned_u64 func_name; /* in/out */ __u32 name_len; __u32 offset; /* offset from func_name */ __u64 addr; + __u64 missed; + __u64 cookie; } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */ struct { __aligned_u64 tp_name; /* in/out */ __u32 name_len; + __u32 :32; + __u64 cookie; } tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */ struct { __u64 config; __u32 type; + __u32 :32; + __u64 cookie; } event; /* BPF_PERF_EVENT_EVENT */ struct { __u64:64; @@ -7349,9 +7366,11 @@ struct bpf_core_relo { * Flags to control bpf_timer_start() behaviour. * - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is * relative to current time. + * - BPF_F_TIMER_CPU_PIN: Timer will be pinned to the CPU of the caller. */ enum { BPF_F_TIMER_ABS = (1ULL << 0), + BPF_F_TIMER_CPU_PIN = (1ULL << 1), }; /* BPF numbers iterator state */ diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h index 3bac0a8ceab26ee78c37b425a76115aa21c20c06..359a14cc76a4038aeacef14b2915d5ce60d0cf44 100644 --- a/tools/include/uapi/linux/sched.h +++ b/tools/include/uapi/linux/sched.h @@ -118,6 +118,7 @@ struct clone_args { /* SCHED_ISO: reserved but not implemented yet */ #define SCHED_IDLE 5 #define SCHED_DEADLINE 6 +#define SCHED_EXT 7 /* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */ #define SCHED_RESET_ON_FORK 0x40000000 diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index a5e21d9baf6126209c9685a95d9fe497c9572e94..04ccbd5b2d0dde18067244ca55b634dc3e5aafcd 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -171,7 +171,8 @@ int bpf_map_create(enum bpf_map_type map_type, __u32 max_entries, const struct bpf_map_create_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, map_extra); + const size_t attr_sz = offsetofend(union bpf_attr, + value_type_btf_obj_fd); union bpf_attr attr; int fd; @@ -193,6 +194,7 @@ int bpf_map_create(enum bpf_map_type map_type, attr.btf_key_type_id = OPTS_GET(opts, btf_key_type_id, 0); attr.btf_value_type_id = OPTS_GET(opts, btf_value_type_id, 0); attr.btf_vmlinux_value_type_id = OPTS_GET(opts, btf_vmlinux_value_type_id, 0); + attr.value_type_btf_obj_fd = OPTS_GET(opts, value_type_btf_obj_fd, 0); attr.inner_map_fd = OPTS_GET(opts, inner_map_fd, 0); attr.map_flags = OPTS_GET(opts, map_flags, 0); diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 107fef7488682946f89ccd578ee38dddbcf96b75..db0ff8ade19a44227f7ea951ae5d8b7c07ba85c1 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -51,8 +51,10 @@ struct bpf_map_create_opts { __u32 numa_node; __u32 map_ifindex; + __s32 value_type_btf_obj_fd; + size_t:0; }; -#define bpf_map_create_opts__last_field map_ifindex +#define bpf_map_create_opts__last_field value_type_btf_obj_fd LIBBPF_API int bpf_map_create(enum bpf_map_type map_type, const char *map_name, diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 828c1d2f173eadb38ff2f4ae5e406d0861f3f114..4f058925aa727f2386cad5ab5c9419ae4f8cf37b 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -522,6 +522,7 @@ struct bpf_map { struct bpf_map_def def; __u32 numa_node; __u32 btf_var_idx; + int mod_btf_fd; __u32 btf_key_type_id; __u32 btf_value_type_id; __u32 btf_vmlinux_value_type_id; @@ -922,22 +923,29 @@ find_member_by_name(const struct btf *btf, const struct btf_type *t, return NULL; } +static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name, + __u16 kind, struct btf **res_btf, + struct module_btf **res_mod_btf); + #define STRUCT_OPS_VALUE_PREFIX "bpf_struct_ops_" static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, const char *name, __u32 kind); static int -find_struct_ops_kern_types(const struct btf *btf, const char *tname, +find_struct_ops_kern_types(struct bpf_object *obj, const char *tname, + struct module_btf **mod_btf, const struct btf_type **type, __u32 *type_id, const struct btf_type **vtype, __u32 *vtype_id, const struct btf_member **data_member) { const struct btf_type *kern_type, *kern_vtype; const struct btf_member *kern_data_member; + struct btf *btf; __s32 kern_vtype_id, kern_type_id; __u32 i; - kern_type_id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT); + kern_type_id = find_ksym_btf_id(obj, tname, BTF_KIND_STRUCT, + &btf, mod_btf); if (kern_type_id < 0) { pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n", tname); @@ -990,15 +998,30 @@ static bool bpf_map__is_struct_ops(const struct bpf_map *map) return map->def.type == BPF_MAP_TYPE_STRUCT_OPS; } +static bool is_valid_st_ops_program(struct bpf_object *obj, + const struct bpf_program *prog) +{ + int i; + + for (i = 0; i < obj->nr_programs; i++) { + if (&obj->programs[i] == prog) + return prog->type == BPF_PROG_TYPE_STRUCT_OPS; + } + + return false; +} + /* Init the map's fields that depend on kern_btf */ -static int bpf_map__init_kern_struct_ops(struct bpf_map *map, - const struct btf *btf, - const struct btf *kern_btf) +static int bpf_map__init_kern_struct_ops(struct bpf_map *map) { const struct btf_member *member, *kern_member, *kern_data_member; const struct btf_type *type, *kern_type, *kern_vtype; __u32 i, kern_type_id, kern_vtype_id, kern_data_off; + struct bpf_object *obj = map->obj; + const struct btf *btf = obj->btf; struct bpf_struct_ops *st_ops; + const struct btf *kern_btf; + struct module_btf *mod_btf; void *data, *kern_data; const char *tname; int err; @@ -1006,16 +1029,19 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map, st_ops = map->st_ops; type = st_ops->type; tname = st_ops->tname; - err = find_struct_ops_kern_types(kern_btf, tname, + err = find_struct_ops_kern_types(obj, tname, &mod_btf, &kern_type, &kern_type_id, &kern_vtype, &kern_vtype_id, &kern_data_member); if (err) return err; + kern_btf = mod_btf ? mod_btf->btf : obj->btf_vmlinux; + pr_debug("struct_ops init_kern %s: type_id:%u kern_type_id:%u kern_vtype_id:%u\n", map->name, st_ops->type_id, kern_type_id, kern_vtype_id); + map->mod_btf_fd = mod_btf ? mod_btf->fd : -1; map->def.value_size = kern_vtype->size; map->btf_vmlinux_value_type_id = kern_vtype_id; @@ -1073,9 +1099,16 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map, if (btf_is_ptr(mtype)) { struct bpf_program *prog; - prog = st_ops->progs[i]; + /* Update the value from the shadow type */ + prog = *(void **)mdata; + st_ops->progs[i] = prog; if (!prog) continue; + if (!is_valid_st_ops_program(obj, prog)) { + pr_warn("struct_ops init_kern %s: member %s is not a struct_ops program\n", + map->name, mname); + return -ENOTSUP; + } kern_mtype = skip_mods_and_typedefs(kern_btf, kern_mtype->type, @@ -1091,6 +1124,8 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map, return -ENOTSUP; } + if (mod_btf) + prog->attach_btf_obj_fd = mod_btf->fd; prog->attach_btf_id = kern_type_id; prog->expected_attach_type = kern_member_idx; @@ -1133,8 +1168,7 @@ static int bpf_object__init_kern_struct_ops_maps(struct bpf_object *obj) if (!bpf_map__is_struct_ops(map)) continue; - err = bpf_map__init_kern_struct_ops(map, obj->btf, - obj->btf_vmlinux); + err = bpf_map__init_kern_struct_ops(map); if (err) return err; } @@ -1199,6 +1233,7 @@ static int init_struct_ops_maps(struct bpf_object *obj, const char *sec_name, map->name = strdup(var_name); if (!map->name) return -ENOMEM; + map->btf_value_type_id = type_id; map->def.type = BPF_MAP_TYPE_STRUCT_OPS; map->def.key_size = sizeof(int); @@ -3047,9 +3082,15 @@ static bool prog_needs_vmlinux_btf(struct bpf_program *prog) return false; } +static bool map_needs_vmlinux_btf(struct bpf_map *map) +{ + return bpf_map__is_struct_ops(map); +} + static bool obj_needs_vmlinux_btf(const struct bpf_object *obj) { struct bpf_program *prog; + struct bpf_map *map; int i; /* CO-RE relocations need kernel BTF, only when btf_custom_path @@ -3074,6 +3115,11 @@ static bool obj_needs_vmlinux_btf(const struct bpf_object *obj) return true; } + bpf_object__for_each_map(map, obj) { + if (map_needs_vmlinux_btf(map)) + return true; + } + return false; } @@ -5116,8 +5162,13 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.numa_node = map->numa_node; create_attr.map_extra = map->map_extra; - if (bpf_map__is_struct_ops(map)) + if (bpf_map__is_struct_ops(map)) { create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; + if (map->mod_btf_fd >= 0) { + create_attr.value_type_btf_obj_fd = map->mod_btf_fd; + create_attr.map_flags |= BPF_F_VTYPE_BTF_OBJ_FD; + } + } if (obj->btf && btf__fd(obj->btf) >= 0) { create_attr.btf_fd = btf__fd(obj->btf); @@ -5161,6 +5212,10 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.btf_value_type_id = 0; map->btf_key_type_id = 0; map->btf_value_type_id = 0; + break; + case BPF_MAP_TYPE_STRUCT_OPS: + create_attr.btf_value_type_id = 0; + break; default: break; } @@ -9133,7 +9188,9 @@ static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, return NULL; } -/* Collect the reloc from ELF and populate the st_ops->progs[] */ +/* Collect the reloc from ELF, populate the st_ops->progs[], and update + * st_ops->data for shadow type. + */ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Data *data) { @@ -9247,6 +9304,14 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, } st_ops->progs[member_idx] = prog; + + /* st_ops->data will be exposed to users, being returned by + * bpf_map__initial_value() as a pointer to the shadow + * type. All function pointers in the original struct type + * should be converted to a pointer to struct bpf_program + * in the shadow type. + */ + *((struct bpf_program **)(st_ops->data + moff)) = prog; } return 0; @@ -9436,7 +9501,9 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attac *btf_obj_fd = 0; *btf_type_id = 1; } else { - err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id); + err = find_kernel_btf_id(prog->obj, attach_name, + attach_type, btf_obj_fd, + btf_type_id); } if (err) { pr_warn("prog '%s': failed to find kernel BTF type ID of '%s': %d\n", @@ -9701,6 +9768,12 @@ int bpf_map__set_initial_value(struct bpf_map *map, void *bpf_map__initial_value(struct bpf_map *map, size_t *psize) { + if (bpf_map__is_struct_ops(map)) { + if (psize) + *psize = map->def.value_size; + return map->st_ops->data; + } + if (!map->mmaped) return NULL; *psize = map->def.value_size; diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 9c4db90b92b6b55bb143d80c308085003becc20b..98373d126d9d77a7313c452c20f1a95974248b9d 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -326,6 +326,7 @@ static int probe_map_create(enum bpf_map_type map_type) case BPF_MAP_TYPE_STRUCT_OPS: /* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */ opts.btf_vmlinux_value_type_id = 1; + opts.value_type_btf_obj_fd = -1; exp_err = -524; /* -ENOTSUPP */ break; case BPF_MAP_TYPE_BLOOM_FILTER: diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index c0c8d7f9514b040c6b7787c36472b3fae8f272ee..f9c396fe81dc4b8d9597059ac7f559fc8f444251 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -304,8 +304,6 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr, return ret2; } -#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_LONG / sizeof(long)) - static int convert_variable_type(Dwarf_Die *vr_die, struct probe_trace_arg *tvar, const char *cast, bool user_access) @@ -335,7 +333,7 @@ static int convert_variable_type(Dwarf_Die *vr_die, total = dwarf_bytesize(vr_die); if (boffs < 0 || total < 0) return -ENOENT; - ret = snprintf(buf, 16, "b%d@%d/%zd", bsize, boffs, + ret = snprintf(buf, 16, "b%d@%d/%d", bsize, boffs, BYTES_TO_BITS(total)); goto formatted; } diff --git a/tools/sched_ext/.gitignore b/tools/sched_ext/.gitignore new file mode 100644 index 0000000000000000000000000000000000000000..d6264fe1c8cdb3828107ec847653f4ebcbf556a6 --- /dev/null +++ b/tools/sched_ext/.gitignore @@ -0,0 +1,2 @@ +tools/ +build/ diff --git a/tools/sched_ext/Makefile b/tools/sched_ext/Makefile new file mode 100644 index 0000000000000000000000000000000000000000..ca3815e572d8d2030e61663204eb7e46e36d1e3b --- /dev/null +++ b/tools/sched_ext/Makefile @@ -0,0 +1,246 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2022 Meta Platforms, Inc. and affiliates. +include ../build/Build.include +include ../scripts/Makefile.arch +include ../scripts/Makefile.include + +all: all_targets + +ifneq ($(LLVM),) +ifneq ($(filter %/,$(LLVM)),) +LLVM_PREFIX := $(LLVM) +else ifneq ($(filter -%,$(LLVM)),) +LLVM_SUFFIX := $(LLVM) +endif + +CLANG_TARGET_FLAGS_arm := arm-linux-gnueabi +CLANG_TARGET_FLAGS_arm64 := aarch64-linux-gnu +CLANG_TARGET_FLAGS_hexagon := hexagon-linux-musl +CLANG_TARGET_FLAGS_m68k := m68k-linux-gnu +CLANG_TARGET_FLAGS_mips := mipsel-linux-gnu +CLANG_TARGET_FLAGS_powerpc := powerpc64le-linux-gnu +CLANG_TARGET_FLAGS_riscv := riscv64-linux-gnu +CLANG_TARGET_FLAGS_s390 := s390x-linux-gnu +CLANG_TARGET_FLAGS_x86 := x86_64-linux-gnu +CLANG_TARGET_FLAGS := $(CLANG_TARGET_FLAGS_$(ARCH)) + +ifeq ($(CROSS_COMPILE),) +ifeq ($(CLANG_TARGET_FLAGS),) +$(error Specify CROSS_COMPILE or add '--target=' option to lib.mk) +else +CLANG_FLAGS += --target=$(CLANG_TARGET_FLAGS) +endif # CLANG_TARGET_FLAGS +else +CLANG_FLAGS += --target=$(notdir $(CROSS_COMPILE:%-=%)) +endif # CROSS_COMPILE + +CC := $(LLVM_PREFIX)clang$(LLVM_SUFFIX) $(CLANG_FLAGS) -fintegrated-as +else +CC := $(CROSS_COMPILE)gcc +endif # LLVM + +CURDIR := $(abspath .) +TOOLSDIR := $(abspath ..) +LIBDIR := $(TOOLSDIR)/lib +BPFDIR := $(LIBDIR)/bpf +TOOLSINCDIR := $(TOOLSDIR)/include +BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool +APIDIR := $(TOOLSINCDIR)/uapi +GENDIR := $(abspath ../../include/generated) +GENHDR := $(GENDIR)/autoconf.h + +ifeq ($(O),) +OUTPUT_DIR := $(CURDIR)/build +else +OUTPUT_DIR := $(O)/build +endif # O +OBJ_DIR := $(OUTPUT_DIR)/obj +INCLUDE_DIR := $(OUTPUT_DIR)/include +BPFOBJ_DIR := $(OBJ_DIR)/libbpf +SCXOBJ_DIR := $(OBJ_DIR)/sched_ext +BINDIR := $(OUTPUT_DIR)/bin +BPFOBJ := $(BPFOBJ_DIR)/libbpf.a +ifneq ($(CROSS_COMPILE),) +HOST_BUILD_DIR := $(OBJ_DIR)/host +HOST_OUTPUT_DIR := host-tools +HOST_INCLUDE_DIR := $(HOST_OUTPUT_DIR)/include +else +HOST_BUILD_DIR := $(OBJ_DIR) +HOST_OUTPUT_DIR := $(OUTPUT_DIR) +HOST_INCLUDE_DIR := $(INCLUDE_DIR) +endif +HOST_BPFOBJ := $(HOST_BUILD_DIR)/libbpf/libbpf.a +RESOLVE_BTFIDS := $(HOST_BUILD_DIR)/resolve_btfids/resolve_btfids +DEFAULT_BPFTOOL := $(HOST_OUTPUT_DIR)/sbin/bpftool + +VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ + $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ + ../../vmlinux \ + /sys/kernel/btf/vmlinux \ + /boot/vmlinux-$(shell uname -r) +VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) +ifeq ($(VMLINUX_BTF),) +$(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)") +endif + +BPFTOOL ?= $(DEFAULT_BPFTOOL) + +ifneq ($(wildcard $(GENHDR)),) + GENFLAGS := -DHAVE_GENHDR +endif + +CFLAGS += -g -O2 -rdynamic -pthread -Wall -Werror $(GENFLAGS) \ + -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ + -I$(TOOLSINCDIR) -I$(APIDIR) -I$(CURDIR)/include + +# Silence some warnings when compiled with clang +ifneq ($(LLVM),) +CFLAGS += -Wno-unused-command-line-argument +endif + +LDFLAGS = -lelf -lz -lpthread + +IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - &1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) -dM -E - $@ +else + $(call msg,CP,,$@) + $(Q)cp "$(VMLINUX_H)" $@ +endif + +$(SCXOBJ_DIR)/%.bpf.o: %.bpf.c $(INCLUDE_DIR)/vmlinux.h include/scx/*.h \ + | $(BPFOBJ) $(SCXOBJ_DIR) + $(call msg,CLNG-BPF,,$(notdir $@)) + $(Q)$(CLANG) $(BPF_CFLAGS) -target bpf -c $< -o $@ + +$(INCLUDE_DIR)/%.bpf.skel.h: $(SCXOBJ_DIR)/%.bpf.o $(INCLUDE_DIR)/vmlinux.h $(BPFTOOL) + $(eval sched=$(notdir $@)) + $(call msg,GEN-SKEL,,$(sched)) + $(Q)$(BPFTOOL) gen object $(<:.o=.linked1.o) $< + $(Q)$(BPFTOOL) gen object $(<:.o=.linked2.o) $(<:.o=.linked1.o) + $(Q)$(BPFTOOL) gen object $(<:.o=.linked3.o) $(<:.o=.linked2.o) + $(Q)diff $(<:.o=.linked2.o) $(<:.o=.linked3.o) + $(Q)$(BPFTOOL) gen skeleton $(<:.o=.linked3.o) name $(subst .bpf.skel.h,,$(sched)) > $@ + $(Q)$(BPFTOOL) gen subskeleton $(<:.o=.linked3.o) name $(subst .bpf.skel.h,,$(sched)) > $(@:.skel.h=.subskel.h) + +SCX_COMMON_DEPS := include/scx/common.h include/scx/user_exit_info.h | $(BINDIR) + +c-sched-targets = scx_simple scx_qmap scx_central scx_flatcg + +$(addprefix $(BINDIR)/,$(c-sched-targets)): \ + $(BINDIR)/%: \ + $(filter-out %.bpf.c,%.c) \ + $(INCLUDE_DIR)/%.bpf.skel.h \ + $(SCX_COMMON_DEPS) + $(eval sched=$(notdir $@)) + $(CC) $(CFLAGS) -c $(sched).c -o $(SCXOBJ_DIR)/$(sched).o + $(CC) -o $@ $(SCXOBJ_DIR)/$(sched).o $(HOST_BPFOBJ) $(LDFLAGS) + +$(c-sched-targets): %: $(BINDIR)/% + +install: all + $(Q)mkdir -p $(DESTDIR)/usr/local/bin/ + $(Q)cp $(BINDIR)/* $(DESTDIR)/usr/local/bin/ + +clean: + rm -rf $(OUTPUT_DIR) $(HOST_OUTPUT_DIR) + rm -f *.o *.bpf.o *.bpf.skel.h *.bpf.subskel.h + rm -f $(c-sched-targets) + +help: + @echo 'Building targets' + @echo '================' + @echo '' + @echo ' all - Compile all schedulers' + @echo '' + @echo 'Alternatively, you may compile individual schedulers:' + @echo '' + @printf ' %s\n' $(c-sched-targets) + @echo '' + @echo 'For any scheduler build target, you may specify an alternative' + @echo 'build output path with the O= environment variable. For example:' + @echo '' + @echo ' O=/tmp/sched_ext make all' + @echo '' + @echo 'will compile all schedulers, and emit the build artifacts to' + @echo '/tmp/sched_ext/build.' + @echo '' + @echo '' + @echo 'Installing targets' + @echo '==================' + @echo '' + @echo ' install - Compile and install all schedulers to /usr/bin.' + @echo ' You may specify the DESTDIR= environment variable' + @echo ' to indicate a prefix for /usr/bin. For example:' + @echo '' + @echo ' DESTDIR=/tmp/sched_ext make install' + @echo '' + @echo ' will build the schedulers in CWD/build, and' + @echo ' install the schedulers to /tmp/sched_ext/usr/bin.' + @echo '' + @echo '' + @echo 'Cleaning targets' + @echo '================' + @echo '' + @echo ' clean - Remove all generated files' + +all_targets: $(c-sched-targets) + +.PHONY: all all_targets $(c-sched-targets) clean help + +# delete failed targets +.DELETE_ON_ERROR: + +# keep intermediate (.bpf.skel.h, .bpf.o, etc) targets +.SECONDARY: diff --git a/tools/sched_ext/README.md b/tools/sched_ext/README.md new file mode 100644 index 0000000000000000000000000000000000000000..16a42e4060f64c9e0366b6fbdba8921b58cef7af --- /dev/null +++ b/tools/sched_ext/README.md @@ -0,0 +1,270 @@ +SCHED_EXT EXAMPLE SCHEDULERS +============================ + +# Introduction + +This directory contains a number of example sched_ext schedulers. These +schedulers are meant to provide examples of different types of schedulers +that can be built using sched_ext, and illustrate how various features of +sched_ext can be used. + +Some of the examples are performant, production-ready schedulers. That is, for +the correct workload and with the correct tuning, they may be deployed in a +production environment with acceptable or possibly even improved performance. +Others are just examples that in practice, would not provide acceptable +performance (though they could be improved to get there). + +This README will describe these example schedulers, including describing the +types of workloads or scenarios they're designed to accommodate, and whether or +not they're production ready. For more details on any of these schedulers, +please see the header comment in their .bpf.c file. + + +# Compiling the examples + +There are a few toolchain dependencies for compiling the example schedulers. + +## Toolchain dependencies + +1. clang >= 16.0.0 + +The schedulers are BPF programs, and therefore must be compiled with clang. gcc +is actively working on adding a BPF backend compiler as well, but are still +missing some features such as BTF type tags which are necessary for using +kptrs. + +2. pahole >= 1.25 + +You may need pahole in order to generate BTF from DWARF. + +3. rust >= 1.70.0 + +Rust schedulers uses features present in the rust toolchain >= 1.70.0. You +should be able to use the stable build from rustup, but if that doesn't +work, try using the rustup nightly build. + +There are other requirements as well, such as make, but these are the main / +non-trivial ones. + +## Compiling the kernel + +In order to run a sched_ext scheduler, you'll have to run a kernel compiled +with the patches in this repository, and with a minimum set of necessary +Kconfig options: + +``` +CONFIG_BPF=y +CONFIG_SCHED_CLASS_EXT=y +CONFIG_BPF_SYSCALL=y +CONFIG_BPF_JIT=y +CONFIG_DEBUG_INFO_BTF=y +``` + +It's also recommended that you also include the following Kconfig options: + +``` +CONFIG_BPF_JIT_ALWAYS_ON=y +CONFIG_BPF_JIT_DEFAULT_ON=y +CONFIG_PAHOLE_HAS_SPLIT_BTF=y +CONFIG_PAHOLE_HAS_BTF_TAG=y +``` + +There is a `Kconfig` file in this directory whose contents you can append to +your local `.config` file, as long as there are no conflicts with any existing +options in the file. + +## Getting a vmlinux.h file + +You may notice that most of the example schedulers include a "vmlinux.h" file. +This is a large, auto-generated header file that contains all of the types +defined in some vmlinux binary that was compiled with +[BTF](https://docs.kernel.org/bpf/btf.html) (i.e. with the BTF-related Kconfig +options specified above). + +The header file is created using `bpftool`, by passing it a vmlinux binary +compiled with BTF as follows: + +```bash +$ bpftool btf dump file /path/to/vmlinux format c > vmlinux.h +``` + +`bpftool` analyzes all of the BTF encodings in the binary, and produces a +header file that can be included by BPF programs to access those types. For +example, using vmlinux.h allows a scheduler to access fields defined directly +in vmlinux as follows: + +```c +#include "vmlinux.h" +// vmlinux.h is also implicitly included by scx_common.bpf.h. +#include "scx_common.bpf.h" + +/* + * vmlinux.h provides definitions for struct task_struct and + * struct scx_enable_args. + */ +void BPF_STRUCT_OPS(example_enable, struct task_struct *p, + struct scx_enable_args *args) +{ + bpf_printk("Task %s enabled in example scheduler", p->comm); +} + +// vmlinux.h provides the definition for struct sched_ext_ops. +SEC(".struct_ops.link") +struct sched_ext_ops example_ops { + .enable = (void *)example_enable, + .name = "example", +} +``` + +The scheduler build system will generate this vmlinux.h file as part of the +scheduler build pipeline. It looks for a vmlinux file in the following +dependency order: + +1. If the O= environment variable is defined, at `$O/vmlinux` +2. If the KBUILD_OUTPUT= environment variable is defined, at + `$KBUILD_OUTPUT/vmlinux` +3. At `../../vmlinux` (i.e. at the root of the kernel tree where you're + compiling the schedulers) +3. `/sys/kernel/btf/vmlinux` +4. `/boot/vmlinux-$(uname -r)` + +In other words, if you have compiled a kernel in your local repo, its vmlinux +file will be used to generate vmlinux.h. Otherwise, it will be the vmlinux of +the kernel you're currently running on. This means that if you're running on a +kernel with sched_ext support, you may not need to compile a local kernel at +all. + +### Aside on CO-RE + +One of the cooler features of BPF is that it supports +[CO-RE](https://nakryiko.com/posts/bpf-core-reference-guide/) (Compile Once Run +Everywhere). This feature allows you to reference fields inside of structs with +types defined internal to the kernel, and not have to recompile if you load the +BPF program on a different kernel with the field at a different offset. In our +example above, we print out a task name with `p->comm`. CO-RE would perform +relocations for that access when the program is loaded to ensure that it's +referencing the correct offset for the currently running kernel. + +## Compiling the schedulers + +Once you have your toolchain setup, and a vmlinux that can be used to generate +a full vmlinux.h file, you can compile the schedulers using `make`: + +```bash +$ make -j($nproc) +``` + +# Example schedulers + +This directory contains the following example schedulers. These schedulers are +for testing and demonstrating different aspects of sched_ext. While some may be +useful in limited scenarios, they are not intended to be practical. + +For more scheduler implementations, tools and documentation, visit +https://github.com/sched-ext/scx. + +## scx_simple + +A simple scheduler that provides an example of a minimal sched_ext scheduler. +scx_simple can be run in either global weighted vtime mode, or FIFO mode. + +Though very simple, in limited scenarios, this scheduler can perform reasonably +well on single-socket systems with a unified L3 cache. + +## scx_qmap + +Another simple, yet slightly more complex scheduler that provides an example of +a basic weighted FIFO queuing policy. It also provides examples of some common +useful BPF features, such as sleepable per-task storage allocation in the +`ops.prep_enable()` callback, and using the `BPF_MAP_TYPE_QUEUE` map type to +enqueue tasks. It also illustrates how core-sched support could be implemented. + +## scx_central + +A "central" scheduler where scheduling decisions are made from a single CPU. +This scheduler illustrates how scheduling decisions can be dispatched from a +single CPU, allowing other cores to run with infinite slices, without timer +ticks, and without having to incur the overhead of making scheduling decisions. + +The approach demonstrated by this scheduler may be useful for any workload that +benefits from minimizing scheduling overhead and timer ticks. An example of +where this could be particularly useful is running VMs, where running with +infinite slices and no timer ticks allows the VM to avoid unnecessary expensive +vmexits. + +## scx_flatcg + +A flattened cgroup hierarchy scheduler. This scheduler implements hierarchical +weight-based cgroup CPU control by flattening the cgroup hierarchy into a single +layer, by compounding the active weight share at each level. The effect of this +is a much more performant CPU controller, which does not need to descend down +cgroup trees in order to properly compute a cgroup's share. + +Similar to scx_simple, in limited scenarios, this scheduler can perform +reasonably well on single socket-socket systems with a unified L3 cache and show +significantly lowered hierarchical scheduling overhead. + + +# Troubleshooting + +There are a number of common issues that you may run into when building the +schedulers. We'll go over some of the common ones here. + +## Build Failures + +### Old version of clang + +``` +error: static assertion failed due to requirement 'SCX_DSQ_FLAG_BUILTIN': bpftool generated vmlinux.h is missing high bits for 64bit enums, upgrade clang and pahole + _Static_assert(SCX_DSQ_FLAG_BUILTIN, + ^~~~~~~~~~~~~~~~~~~~ +1 error generated. +``` + +This means you built the kernel or the schedulers with an older version of +clang than what's supported (i.e. older than 16.0.0). To remediate this: + +1. `which clang` to make sure you're using a sufficiently new version of clang. + +2. `make fullclean` in the root path of the repository, and rebuild the kernel + and schedulers. + +3. Rebuild the kernel, and then your example schedulers. + +The schedulers are also cleaned if you invoke `make mrproper` in the root +directory of the tree. + +### Stale kernel build / incomplete vmlinux.h file + +As described above, you'll need a `vmlinux.h` file that was generated from a +vmlinux built with BTF, and with sched_ext support enabled. If you don't, +you'll see errors such as the following which indicate that a type being +referenced in a scheduler is unknown: + +``` +/path/to/sched_ext/tools/sched_ext/user_exit_info.h:25:23: note: forward declaration of 'struct scx_exit_info' + +const struct scx_exit_info *ei) + +^ +``` + +In order to resolve this, please follow the steps above in +[Getting a vmlinux.h file](#getting-a-vmlinuxh-file) in order to ensure your +schedulers are using a vmlinux.h file that includes the requisite types. + +## Misc + +### llvm: [OFF] + +You may see the following output when building the schedulers: + +``` +Auto-detecting system features: +... clang-bpf-co-re: [ on ] +... llvm: [ OFF ] +... libcap: [ on ] +... libbfd: [ on ] +``` + +Seeing `llvm: [ OFF ]` here is not an issue. You can safely ignore. diff --git a/tools/sched_ext/include/bpf-compat/gnu/stubs.h b/tools/sched_ext/include/bpf-compat/gnu/stubs.h new file mode 100644 index 0000000000000000000000000000000000000000..ad7d139ce907b2abe5fdcc0af0eda0f5575fe115 --- /dev/null +++ b/tools/sched_ext/include/bpf-compat/gnu/stubs.h @@ -0,0 +1,11 @@ +/* + * Dummy gnu/stubs.h. clang can end up including /usr/include/gnu/stubs.h when + * compiling BPF files although its content doesn't play any role. The file in + * turn includes stubs-64.h or stubs-32.h depending on whether __x86_64__ is + * defined. When compiling a BPF source, __x86_64__ isn't set and thus + * stubs-32.h is selected. However, the file is not there if the system doesn't + * have 32bit glibc devel package installed leading to a build failure. + * + * The problem is worked around by making this file available in the include + * search paths before the system one when building BPF. + */ 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 0000000000000000000000000000000000000000..7849405614b154cca8e769db86dcddc40e34313a --- /dev/null +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -0,0 +1,620 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo + * Copyright (c) 2022 David Vernet + */ +#ifndef __SCX_COMMON_BPF_H +#define __SCX_COMMON_BPF_H + +#ifdef LSP +#define __bpf__ +#include "../vmlinux.h" +#else +#include "vmlinux.h" +#endif + +#include +#include +#include +#include "user_exit_info.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; +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_cpu_ids(void) __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(void) __ksym; +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(const cpumask_t *cpus_allowed, u64 flags) __ksym; +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; + +/* + * 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) + +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(); + } +} + +#define READ_ONCE(x) \ +({ \ + union { typeof(x) __val; char __c[1]; } __u = \ + { .__c = { 0 } }; \ + __read_once_size(&(x), __u.__c, sizeof(x)); \ + __u.__val; \ +}) + +#define WRITE_ONCE(x, val) \ +({ \ + union { typeof(x) __val; char __c[1]; } __u = \ + { .__val = (val) }; \ + __write_once_size(&(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; +} + +#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 0000000000000000000000000000000000000000..dc18b99e55cd169ed120412bdac8403274de0b24 --- /dev/null +++ b/tools/sched_ext/include/scx/common.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 Tejun Heo + * Copyright (c) 2023 David Vernet + */ +#ifndef __SCHED_EXT_COMMON_H +#define __SCHED_EXT_COMMON_H + +#ifdef __KERNEL__ +#error "Should not be included by BPF programs" +#endif + +#include +#include +#include +#include +#include + +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() +#include +#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 0000000000000000000000000000000000000000..50e1499ae0935a7fdbe0b6fbf3bfbcee5bc707c2 --- /dev/null +++ b/tools/sched_ext/include/scx/compat.bpf.h @@ -0,0 +1,143 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 Tejun Heo + * Copyright (c) 2024 David Vernet + */ +#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; \ +}) + +#define scx_bpf_now() \ + (bpf_ksym_exists(scx_bpf_now) ? \ + scx_bpf_now() : \ + bpf_ktime_get_ns()) + +/* + * 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 0000000000000000000000000000000000000000..b50280e2ba2bacbd4e4cd447fe2b064fba402fda --- /dev/null +++ b/tools/sched_ext/include/scx/compat.h @@ -0,0 +1,187 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 Tejun Heo + * Copyright (c) 2024 David Vernet + */ +#ifndef __SCX_COMPAT_H +#define __SCX_COMPAT_H + +#include +#include +#include +#include + +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_SWITCH_PARTIAL \ + __COMPAT_ENUM_OR_ZERO("scx_ops_flags", "SCX_OPS_SWITCH_PARTIAL") + +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/enums.autogen.bpf.h b/tools/sched_ext/include/scx/enums.autogen.bpf.h new file mode 100644 index 0000000000000000000000000000000000000000..0e941a0d6f8888426805985c2e908a17ba48b420 --- /dev/null +++ b/tools/sched_ext/include/scx/enums.autogen.bpf.h @@ -0,0 +1,105 @@ +/* + * 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_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 0000000000000000000000000000000000000000..88137a140e726db3d145daeb00bf491db212ba10 --- /dev/null +++ b/tools/sched_ext/include/scx/enums.autogen.h @@ -0,0 +1,41 @@ +/* + * 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_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 0000000000000000000000000000000000000000..af704c5d6334522361c0016ac3bb3c43767481a3 --- /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 0000000000000000000000000000000000000000..34cbebe974b7b71d8f678b370242f1e57de59a94 --- /dev/null +++ b/tools/sched_ext/include/scx/enums.h @@ -0,0 +1,27 @@ +/* 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); + SCX_BUG_ON(!res, "enum not found(%s)", name); +} + +#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 0000000000000000000000000000000000000000..66f856640ee7e29fc1ce050000c5807f69ef7395 --- /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 + * Copyright (c) 2022 David Vernet + */ +#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 + +#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 +#include + +/* 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 */ diff --git a/tools/sched_ext/scx_central.bpf.c b/tools/sched_ext/scx_central.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..50bc1737c167a174955458fc1b608a592b43c11d --- /dev/null +++ b/tools/sched_ext/scx_central.bpf.c @@ -0,0 +1,356 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A central FIFO sched_ext scheduler which demonstrates the followings: + * + * a. Making all scheduling decisions from one CPU: + * + * The central CPU is the only one making scheduling decisions. All other + * CPUs kick the central CPU when they run out of tasks to run. + * + * There is one global BPF queue and the central CPU schedules all CPUs by + * dispatching from the global queue to each CPU's local dsq from dispatch(). + * This isn't the most straightforward. e.g. It'd be easier to bounce + * through per-CPU BPF queues. The current design is chosen to maximally + * utilize and verify various SCX mechanisms such as LOCAL_ON dispatching. + * + * b. Tickless operation + * + * All tasks are dispatched with the infinite slice which allows stopping the + * ticks on CONFIG_NO_HZ_FULL kernels running with the proper nohz_full + * parameter. The tickless operation can be observed through + * /proc/interrupts. + * + * Periodic switching is enforced by a periodic timer checking all CPUs and + * preempting them as necessary. Unfortunately, BPF timer currently doesn't + * have a way to pin to a specific CPU, so the periodic timer isn't pinned to + * the central CPU. + * + * c. Preemption + * + * Kthreads are unconditionally queued to the head of a matching local dsq + * and dispatched with SCX_DSQ_PREEMPT. This ensures that a kthread is always + * prioritized over user threads, which is required for ensuring forward + * progress as e.g. the periodic timer may run on a ksoftirqd and if the + * ksoftirqd gets starved by a user thread, there may not be anything else to + * vacate that user thread. + * + * SCX_KICK_PREEMPT is used to trigger scheduling and CPUs to move to the + * next tasks. + * + * This scheduler is designed to maximize usage of various SCX mechanisms. A + * more practical implementation would likely put the scheduling loop outside + * the central CPU's dispatch() path and add some form of priority mechanism. + * + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo + * Copyright (c) 2022 David Vernet + */ +#include + +char _license[] SEC("license") = "GPL"; + +enum { + FALLBACK_DSQ_ID = 0, + MS_TO_NS = 1000LLU * 1000, + TIMER_INTERVAL_NS = 1 * MS_TO_NS, +}; + +const volatile s32 central_cpu; +const volatile u32 nr_cpu_ids = 1; /* !0 for veristat, set during init */ +const volatile u64 slice_ns; + +bool timer_pinned = true; +u64 nr_total, nr_locals, nr_queued, nr_lost_pids; +u64 nr_timers, nr_dispatches, nr_mismatches, nr_retries; +u64 nr_overflows; + +UEI_DEFINE(uei); + +struct { + __uint(type, BPF_MAP_TYPE_QUEUE); + __uint(max_entries, 4096); + __type(value, s32); +} central_q SEC(".maps"); + +/* can't use percpu map due to bad lookups */ +bool RESIZABLE_ARRAY(data, cpu_gimme_task); +u64 RESIZABLE_ARRAY(data, cpu_started_at); + +struct central_timer { + struct bpf_timer timer; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, u32); + __type(value, struct central_timer); +} central_timer SEC(".maps"); + +s32 BPF_STRUCT_OPS(central_select_cpu, struct task_struct *p, + s32 prev_cpu, u64 wake_flags) +{ + /* + * Steer wakeups to the central CPU as much as possible to avoid + * disturbing other CPUs. It's safe to blindly return the central cpu as + * select_cpu() is a hint and if @p can't be on it, the kernel will + * automatically pick a fallback CPU. + */ + return central_cpu; +} + +void BPF_STRUCT_OPS(central_enqueue, struct task_struct *p, u64 enq_flags) +{ + s32 pid = p->pid; + + __sync_fetch_and_add(&nr_total, 1); + + /* + * Push per-cpu kthreads at the head of local dsq's and preempt the + * corresponding CPU. This ensures that e.g. ksoftirqd isn't blocked + * behind other threads which is necessary for forward progress + * guarantee as we depend on the BPF timer which may run from ksoftirqd. + */ + if ((p->flags & PF_KTHREAD) && p->nr_cpus_allowed == 1) { + __sync_fetch_and_add(&nr_locals, 1); + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_INF, + enq_flags | SCX_ENQ_PREEMPT); + return; + } + + if (bpf_map_push_elem(¢ral_q, &pid, 0)) { + __sync_fetch_and_add(&nr_overflows, 1); + scx_bpf_dsq_insert(p, FALLBACK_DSQ_ID, SCX_SLICE_INF, enq_flags); + return; + } + + __sync_fetch_and_add(&nr_queued, 1); + + if (!scx_bpf_task_running(p)) + scx_bpf_kick_cpu(central_cpu, SCX_KICK_PREEMPT); +} + +static bool dispatch_to_cpu(s32 cpu) +{ + struct task_struct *p; + s32 pid; + + bpf_repeat(BPF_MAX_LOOPS) { + if (bpf_map_pop_elem(¢ral_q, &pid)) + break; + + __sync_fetch_and_sub(&nr_queued, 1); + + p = bpf_task_from_pid(pid); + if (!p) { + __sync_fetch_and_add(&nr_lost_pids, 1); + continue; + } + + /* + * If we can't run the task at the top, do the dumb thing and + * bounce it to the fallback dsq. + */ + if (!bpf_cpumask_test_cpu(cpu, p->cpus_ptr)) { + __sync_fetch_and_add(&nr_mismatches, 1); + scx_bpf_dsq_insert(p, FALLBACK_DSQ_ID, SCX_SLICE_INF, 0); + bpf_task_release(p); + /* + * We might run out of dispatch buffer slots if we continue dispatching + * to the fallback DSQ, without dispatching to the local DSQ of the + * target CPU. In such a case, break the loop now as will fail the + * next dispatch operation. + */ + if (!scx_bpf_dispatch_nr_slots()) + break; + continue; + } + + /* dispatch to local and mark that @cpu doesn't need more */ + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | cpu, SCX_SLICE_INF, 0); + + if (cpu != central_cpu) + scx_bpf_kick_cpu(cpu, SCX_KICK_IDLE); + + bpf_task_release(p); + return true; + } + + return false; +} + +void BPF_STRUCT_OPS(central_dispatch, s32 cpu, struct task_struct *prev) +{ + if (cpu == central_cpu) { + /* dispatch for all other CPUs first */ + __sync_fetch_and_add(&nr_dispatches, 1); + + bpf_for(cpu, 0, nr_cpu_ids) { + bool *gimme; + + if (!scx_bpf_dispatch_nr_slots()) + break; + + /* central's gimme is never set */ + gimme = ARRAY_ELEM_PTR(cpu_gimme_task, cpu, nr_cpu_ids); + if (!gimme || !*gimme) + continue; + + if (dispatch_to_cpu(cpu)) + *gimme = false; + } + + /* + * Retry if we ran out of dispatch buffer slots as we might have + * skipped some CPUs and also need to dispatch for self. The ext + * core automatically retries if the local dsq is empty but we + * can't rely on that as we're dispatching for other CPUs too. + * Kick self explicitly to retry. + */ + if (!scx_bpf_dispatch_nr_slots()) { + __sync_fetch_and_add(&nr_retries, 1); + scx_bpf_kick_cpu(central_cpu, SCX_KICK_PREEMPT); + return; + } + + /* look for a task to run on the central CPU */ + if (scx_bpf_dsq_move_to_local(FALLBACK_DSQ_ID)) + return; + dispatch_to_cpu(central_cpu); + } else { + bool *gimme; + + if (scx_bpf_dsq_move_to_local(FALLBACK_DSQ_ID)) + return; + + gimme = ARRAY_ELEM_PTR(cpu_gimme_task, cpu, nr_cpu_ids); + if (gimme) + *gimme = true; + + /* + * Force dispatch on the scheduling CPU so that it finds a task + * to run for us. + */ + scx_bpf_kick_cpu(central_cpu, SCX_KICK_PREEMPT); + } +} + +void BPF_STRUCT_OPS(central_running, struct task_struct *p) +{ + s32 cpu = scx_bpf_task_cpu(p); + u64 *started_at = ARRAY_ELEM_PTR(cpu_started_at, cpu, nr_cpu_ids); + if (started_at) + *started_at = scx_bpf_now() ?: 1; /* 0 indicates idle */ +} + +void BPF_STRUCT_OPS(central_stopping, struct task_struct *p, bool runnable) +{ + s32 cpu = scx_bpf_task_cpu(p); + u64 *started_at = ARRAY_ELEM_PTR(cpu_started_at, cpu, nr_cpu_ids); + if (started_at) + *started_at = 0; +} + +static int central_timerfn(void *map, int *key, struct bpf_timer *timer) +{ + u64 now = scx_bpf_now(); + u64 nr_to_kick = nr_queued; + s32 i, curr_cpu; + + curr_cpu = bpf_get_smp_processor_id(); + if (timer_pinned && (curr_cpu != central_cpu)) { + scx_bpf_error("Central timer ran on CPU %d, not central CPU %d", + curr_cpu, central_cpu); + return 0; + } + + bpf_for(i, 0, nr_cpu_ids) { + s32 cpu = (nr_timers + i) % nr_cpu_ids; + u64 *started_at; + + if (cpu == central_cpu) + continue; + + /* kick iff the current one exhausted its slice */ + started_at = ARRAY_ELEM_PTR(cpu_started_at, cpu, nr_cpu_ids); + if (started_at && *started_at && + time_before(now, *started_at + slice_ns)) + continue; + + /* and there's something pending */ + if (scx_bpf_dsq_nr_queued(FALLBACK_DSQ_ID) || + scx_bpf_dsq_nr_queued(SCX_DSQ_LOCAL_ON | cpu)) + ; + else if (nr_to_kick) + nr_to_kick--; + else + continue; + + scx_bpf_kick_cpu(cpu, SCX_KICK_PREEMPT); + } + + bpf_timer_start(timer, TIMER_INTERVAL_NS, BPF_F_TIMER_CPU_PIN); + __sync_fetch_and_add(&nr_timers, 1); + return 0; +} + +int BPF_STRUCT_OPS_SLEEPABLE(central_init) +{ + u32 key = 0; + struct bpf_timer *timer; + int ret; + + ret = scx_bpf_create_dsq(FALLBACK_DSQ_ID, -1); + if (ret) + return ret; + + timer = bpf_map_lookup_elem(¢ral_timer, &key); + if (!timer) + return -ESRCH; + + if (bpf_get_smp_processor_id() != central_cpu) { + scx_bpf_error("init from non-central CPU"); + return -EINVAL; + } + + bpf_timer_init(timer, ¢ral_timer, CLOCK_MONOTONIC); + bpf_timer_set_callback(timer, central_timerfn); + + ret = bpf_timer_start(timer, TIMER_INTERVAL_NS, BPF_F_TIMER_CPU_PIN); + /* + * BPF_F_TIMER_CPU_PIN is pretty new (>=6.7). If we're running in a + * kernel which doesn't have it, bpf_timer_start() will return -EINVAL. + * Retry without the PIN. This would be the perfect use case for + * bpf_core_enum_value_exists() but the enum type doesn't have a name + * and can't be used with bpf_core_enum_value_exists(). Oh well... + */ + if (ret == -EINVAL) { + timer_pinned = false; + ret = bpf_timer_start(timer, TIMER_INTERVAL_NS, 0); + } + if (ret) + scx_bpf_error("bpf_timer_start failed (%d)", ret); + return ret; +} + +void BPF_STRUCT_OPS(central_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SCX_OPS_DEFINE(central_ops, + /* + * We are offloading all scheduling decisions to the central CPU + * and thus being the last task on a given CPU doesn't mean + * anything special. Enqueue the last tasks like any other tasks. + */ + .flags = SCX_OPS_ENQ_LAST, + + .select_cpu = (void *)central_select_cpu, + .enqueue = (void *)central_enqueue, + .dispatch = (void *)central_dispatch, + .running = (void *)central_running, + .stopping = (void *)central_stopping, + .init = (void *)central_init, + .exit = (void *)central_exit, + .name = "central"); diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c new file mode 100644 index 0000000000000000000000000000000000000000..1e9f74525d8fefcf8b9fd9a4afb259810153f29d --- /dev/null +++ b/tools/sched_ext/scx_central.c @@ -0,0 +1,136 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo + * Copyright (c) 2022 David Vernet + */ +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include "scx_central.bpf.skel.h" + +const char help_fmt[] = +"A central FIFO sched_ext scheduler.\n" +"\n" +"See the top-level comment in .bpf.c for more details.\n" +"\n" +"Usage: %s [-s SLICE_US] [-c CPU]\n" +"\n" +" -s SLICE_US Override slice duration\n" +" -c CPU Override the central CPU (default: 0)\n" +" -v Print libbpf debug messages\n" +" -h Display this help and exit\n"; + +static bool verbose; +static volatile int exit_req; + +static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args) +{ + if (level == LIBBPF_DEBUG && !verbose) + return 0; + return vfprintf(stderr, format, args); +} + +static void sigint_handler(int dummy) +{ + exit_req = 1; +} + +int main(int argc, char **argv) +{ + struct scx_central *skel; + struct bpf_link *link; + __u64 seq = 0, ecode; + __s32 opt; + cpu_set_t *cpuset; + + libbpf_set_print(libbpf_print_fn); + signal(SIGINT, sigint_handler); + signal(SIGTERM, sigint_handler); +restart: + skel = SCX_OPS_OPEN(central_ops, scx_central); + + skel->rodata->central_cpu = 0; + skel->rodata->nr_cpu_ids = libbpf_num_possible_cpus(); + skel->rodata->slice_ns = __COMPAT_ENUM_OR_ZERO("scx_public_consts", "SCX_SLICE_DFL"); + + while ((opt = getopt(argc, argv, "s:c:pvh")) != -1) { + switch (opt) { + case 's': + skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000; + break; + case 'c': + skel->rodata->central_cpu = strtoul(optarg, NULL, 0); + break; + case 'v': + verbose = true; + break; + default: + fprintf(stderr, help_fmt, basename(argv[0])); + return opt != 'h'; + } + } + + /* Resize arrays so their element count is equal to cpu count. */ + RESIZE_ARRAY(skel, data, cpu_gimme_task, skel->rodata->nr_cpu_ids); + RESIZE_ARRAY(skel, data, cpu_started_at, skel->rodata->nr_cpu_ids); + + SCX_OPS_LOAD(skel, central_ops, scx_central, uei); + + /* + * Affinitize the loading thread to the central CPU, as: + * - That's where the BPF timer is first invoked in the BPF program. + * - We probably don't want this user space component to take up a core + * from a task that would benefit from avoiding preemption on one of + * the tickless cores. + * + * Until BPF supports pinning the timer, it's not guaranteed that it + * will always be invoked on the central CPU. In practice, this + * suffices the majority of the time. + */ + cpuset = CPU_ALLOC(skel->rodata->nr_cpu_ids); + SCX_BUG_ON(!cpuset, "Failed to allocate cpuset"); + CPU_ZERO(cpuset); + CPU_SET(skel->rodata->central_cpu, cpuset); + SCX_BUG_ON(sched_setaffinity(0, sizeof(*cpuset), cpuset), + "Failed to affinitize to central CPU %d (max %d)", + skel->rodata->central_cpu, skel->rodata->nr_cpu_ids - 1); + CPU_FREE(cpuset); + + link = SCX_OPS_ATTACH(skel, central_ops, scx_central); + + if (!skel->data->timer_pinned) + printf("WARNING : BPF_F_TIMER_CPU_PIN not available, timer not pinned to central\n"); + + while (!exit_req && !UEI_EXITED(skel, uei)) { + printf("[SEQ %llu]\n", seq++); + printf("total :%10" PRIu64 " local:%10" PRIu64 " queued:%10" PRIu64 " lost:%10" PRIu64 "\n", + skel->bss->nr_total, + skel->bss->nr_locals, + skel->bss->nr_queued, + skel->bss->nr_lost_pids); + printf("timer :%10" PRIu64 " dispatch:%10" PRIu64 " mismatch:%10" PRIu64 " retry:%10" PRIu64 "\n", + skel->bss->nr_timers, + skel->bss->nr_dispatches, + skel->bss->nr_mismatches, + skel->bss->nr_retries); + printf("overflow:%10" PRIu64 "\n", + skel->bss->nr_overflows); + fflush(stdout); + sleep(1); + } + + bpf_link__destroy(link); + ecode = UEI_REPORT(skel, uei); + scx_central__destroy(skel); + + if (UEI_ECODE_RESTART(ecode)) + goto restart; + return 0; +} diff --git a/tools/sched_ext/scx_flatcg.bpf.c b/tools/sched_ext/scx_flatcg.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..2c720e3ecad59369eef61b98613c3670a8bcae33 --- /dev/null +++ b/tools/sched_ext/scx_flatcg.bpf.c @@ -0,0 +1,954 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A demo sched_ext flattened cgroup hierarchy scheduler. It implements + * hierarchical weight-based cgroup CPU control by flattening the cgroup + * hierarchy into a single layer by compounding the active weight share at each + * level. Consider the following hierarchy with weights in parentheses: + * + * R + A (100) + B (100) + * | \ C (100) + * \ D (200) + * + * Ignoring the root and threaded cgroups, only B, C and D can contain tasks. + * Let's say all three have runnable tasks. The total share that each of these + * three cgroups is entitled to can be calculated by compounding its share at + * each level. + * + * For example, B is competing against C and in that competition its share is + * 100/(100+100) == 1/2. At its parent level, A is competing against D and A's + * share in that competition is 100/(200+100) == 1/3. B's eventual share in the + * system can be calculated by multiplying the two shares, 1/2 * 1/3 == 1/6. C's + * eventual shaer is the same at 1/6. D is only competing at the top level and + * its share is 200/(100+200) == 2/3. + * + * So, instead of hierarchically scheduling level-by-level, we can consider it + * as B, C and D competing each other with respective share of 1/6, 1/6 and 2/3 + * and keep updating the eventual shares as the cgroups' runnable states change. + * + * This flattening of hierarchy can bring a substantial performance gain when + * the cgroup hierarchy is nested multiple levels. in a simple benchmark using + * wrk[8] on apache serving a CGI script calculating sha1sum of a small file, it + * outperforms CFS by ~3% with CPU controller disabled and by ~10% with two + * apache instances competing with 2:1 weight ratio nested four level deep. + * + * However, the gain comes at the cost of not being able to properly handle + * thundering herd of cgroups. For example, if many cgroups which are nested + * behind a low priority parent cgroup wake up around the same time, they may be + * able to consume more CPU cycles than they are entitled to. In many use cases, + * this isn't a real concern especially given the performance gain. Also, there + * are ways to mitigate the problem further by e.g. introducing an extra + * scheduling layer on cgroup delegation boundaries. + * + * The scheduler first picks the cgroup to run and then schedule the tasks + * within by using nested weighted vtime scheduling by default. The + * cgroup-internal scheduling can be switched to FIFO with the -f option. + */ +#include +#include "scx_flatcg.h" + +/* + * Maximum amount of retries to find a valid cgroup. + */ +enum { + FALLBACK_DSQ = 0, + CGROUP_MAX_RETRIES = 1024, +}; + +char _license[] SEC("license") = "GPL"; + +const volatile u32 nr_cpus = 32; /* !0 for veristat, set during init */ +const volatile u64 cgrp_slice_ns; +const volatile bool fifo_sched; + +u64 cvtime_now; +UEI_DEFINE(uei); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, FCG_NR_STATS); +} stats SEC(".maps"); + +static void stat_inc(enum fcg_stat_idx idx) +{ + u32 idx_v = idx; + + u64 *cnt_p = bpf_map_lookup_elem(&stats, &idx_v); + if (cnt_p) + (*cnt_p)++; +} + +struct fcg_cpu_ctx { + u64 cur_cgid; + u64 cur_at; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, struct fcg_cpu_ctx); + __uint(max_entries, 1); +} cpu_ctx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct fcg_cgrp_ctx); +} cgrp_ctx SEC(".maps"); + +struct cgv_node { + struct bpf_rb_node rb_node; + __u64 cvtime; + __u64 cgid; +}; + +private(CGV_TREE) struct bpf_spin_lock cgv_tree_lock; +private(CGV_TREE) struct bpf_rb_root cgv_tree __contains(cgv_node, rb_node); + +struct cgv_node_stash { + struct cgv_node __kptr *node; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 16384); + __type(key, __u64); + __type(value, struct cgv_node_stash); +} cgv_node_stash SEC(".maps"); + +struct fcg_task_ctx { + u64 bypassed_at; +}; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct fcg_task_ctx); +} task_ctx SEC(".maps"); + +/* gets inc'd on weight tree changes to expire the cached hweights */ +u64 hweight_gen = 1; + +static u64 div_round_up(u64 dividend, u64 divisor) +{ + return (dividend + divisor - 1) / divisor; +} + +static bool cgv_node_less(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct cgv_node *cgc_a, *cgc_b; + + cgc_a = container_of(a, struct cgv_node, rb_node); + cgc_b = container_of(b, struct cgv_node, rb_node); + + return cgc_a->cvtime < cgc_b->cvtime; +} + +static struct fcg_cpu_ctx *find_cpu_ctx(void) +{ + struct fcg_cpu_ctx *cpuc; + u32 idx = 0; + + cpuc = bpf_map_lookup_elem(&cpu_ctx, &idx); + if (!cpuc) { + scx_bpf_error("cpu_ctx lookup failed"); + return NULL; + } + return cpuc; +} + +static struct fcg_cgrp_ctx *find_cgrp_ctx(struct cgroup *cgrp) +{ + struct fcg_cgrp_ctx *cgc; + + cgc = bpf_cgrp_storage_get(&cgrp_ctx, cgrp, 0, 0); + if (!cgc) { + scx_bpf_error("cgrp_ctx lookup failed for cgid %llu", cgrp->kn->id); + return NULL; + } + return cgc; +} + +static struct fcg_cgrp_ctx *find_ancestor_cgrp_ctx(struct cgroup *cgrp, int level) +{ + struct fcg_cgrp_ctx *cgc; + + cgrp = bpf_cgroup_ancestor(cgrp, level); + if (!cgrp) { + scx_bpf_error("ancestor cgroup lookup failed"); + return NULL; + } + + cgc = find_cgrp_ctx(cgrp); + if (!cgc) + scx_bpf_error("ancestor cgrp_ctx lookup failed"); + bpf_cgroup_release(cgrp); + return cgc; +} + +static void cgrp_refresh_hweight(struct cgroup *cgrp, struct fcg_cgrp_ctx *cgc) +{ + int level; + + if (!cgc->nr_active) { + stat_inc(FCG_STAT_HWT_SKIP); + return; + } + + if (cgc->hweight_gen == hweight_gen) { + stat_inc(FCG_STAT_HWT_CACHE); + return; + } + + stat_inc(FCG_STAT_HWT_UPDATES); + bpf_for(level, 0, cgrp->level + 1) { + struct fcg_cgrp_ctx *cgc; + bool is_active; + + cgc = find_ancestor_cgrp_ctx(cgrp, level); + if (!cgc) + break; + + if (!level) { + cgc->hweight = FCG_HWEIGHT_ONE; + cgc->hweight_gen = hweight_gen; + } else { + struct fcg_cgrp_ctx *pcgc; + + pcgc = find_ancestor_cgrp_ctx(cgrp, level - 1); + if (!pcgc) + break; + + /* + * We can be opportunistic here and not grab the + * cgv_tree_lock and deal with the occasional races. + * However, hweight updates are already cached and + * relatively low-frequency. Let's just do the + * straightforward thing. + */ + bpf_spin_lock(&cgv_tree_lock); + is_active = cgc->nr_active; + if (is_active) { + cgc->hweight_gen = pcgc->hweight_gen; + cgc->hweight = + div_round_up(pcgc->hweight * cgc->weight, + pcgc->child_weight_sum); + } + bpf_spin_unlock(&cgv_tree_lock); + + if (!is_active) { + stat_inc(FCG_STAT_HWT_RACE); + break; + } + } + } +} + +static void cgrp_cap_budget(struct cgv_node *cgv_node, struct fcg_cgrp_ctx *cgc) +{ + u64 delta, cvtime, max_budget; + + /* + * A node which is on the rbtree can't be pointed to from elsewhere yet + * and thus can't be updated and repositioned. Instead, we collect the + * vtime deltas separately and apply it asynchronously here. + */ + delta = __sync_fetch_and_sub(&cgc->cvtime_delta, cgc->cvtime_delta); + cvtime = cgv_node->cvtime + delta; + + /* + * Allow a cgroup to carry the maximum budget proportional to its + * hweight such that a full-hweight cgroup can immediately take up half + * of the CPUs at the most while staying at the front of the rbtree. + */ + max_budget = (cgrp_slice_ns * nr_cpus * cgc->hweight) / + (2 * FCG_HWEIGHT_ONE); + if (time_before(cvtime, cvtime_now - max_budget)) + cvtime = cvtime_now - max_budget; + + cgv_node->cvtime = cvtime; +} + +static void cgrp_enqueued(struct cgroup *cgrp, struct fcg_cgrp_ctx *cgc) +{ + struct cgv_node_stash *stash; + struct cgv_node *cgv_node; + u64 cgid = cgrp->kn->id; + + /* paired with cmpxchg in try_pick_next_cgroup() */ + if (__sync_val_compare_and_swap(&cgc->queued, 0, 1)) { + stat_inc(FCG_STAT_ENQ_SKIP); + return; + } + + stash = bpf_map_lookup_elem(&cgv_node_stash, &cgid); + if (!stash) { + scx_bpf_error("cgv_node lookup failed for cgid %llu", cgid); + return; + } + + /* NULL if the node is already on the rbtree */ + cgv_node = bpf_kptr_xchg(&stash->node, NULL); + if (!cgv_node) { + stat_inc(FCG_STAT_ENQ_RACE); + return; + } + + bpf_spin_lock(&cgv_tree_lock); + cgrp_cap_budget(cgv_node, cgc); + bpf_rbtree_add(&cgv_tree, &cgv_node->rb_node, cgv_node_less); + bpf_spin_unlock(&cgv_tree_lock); +} + +static void set_bypassed_at(struct task_struct *p, struct fcg_task_ctx *taskc) +{ + /* + * Tell fcg_stopping() that this bypassed the regular scheduling path + * and should be force charged to the cgroup. 0 is used to indicate that + * the task isn't bypassing, so if the current runtime is 0, go back by + * one nanosecond. + */ + taskc->bypassed_at = p->se.sum_exec_runtime ?: (u64)-1; +} + +s32 BPF_STRUCT_OPS(fcg_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) +{ + struct fcg_task_ctx *taskc; + bool is_idle = false; + s32 cpu; + + cpu = scx_bpf_select_cpu_dfl(p, prev_cpu, wake_flags, &is_idle); + + taskc = bpf_task_storage_get(&task_ctx, p, 0, 0); + if (!taskc) { + scx_bpf_error("task_ctx lookup failed"); + return cpu; + } + + /* + * If select_cpu_dfl() is recommending local enqueue, the target CPU is + * idle. Follow it and charge the cgroup later in fcg_stopping() after + * the fact. + */ + if (is_idle) { + set_bypassed_at(p, taskc); + stat_inc(FCG_STAT_LOCAL); + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0); + } + + return cpu; +} + +void BPF_STRUCT_OPS(fcg_enqueue, struct task_struct *p, u64 enq_flags) +{ + struct fcg_task_ctx *taskc; + struct cgroup *cgrp; + struct fcg_cgrp_ctx *cgc; + + taskc = bpf_task_storage_get(&task_ctx, p, 0, 0); + if (!taskc) { + scx_bpf_error("task_ctx lookup failed"); + return; + } + + /* + * Use the direct dispatching and force charging to deal with tasks with + * custom affinities so that we don't have to worry about per-cgroup + * dq's containing tasks that can't be executed from some CPUs. + */ + if (p->nr_cpus_allowed != nr_cpus) { + set_bypassed_at(p, taskc); + + /* + * The global dq is deprioritized as we don't want to let tasks + * to boost themselves by constraining its cpumask. The + * deprioritization is rather severe, so let's not apply that to + * per-cpu kernel threads. This is ham-fisted. We probably wanna + * implement per-cgroup fallback dq's instead so that we have + * more control over when tasks with custom cpumask get issued. + */ + if (p->nr_cpus_allowed == 1 && (p->flags & PF_KTHREAD)) { + stat_inc(FCG_STAT_LOCAL); + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, + enq_flags); + } else { + stat_inc(FCG_STAT_GLOBAL); + scx_bpf_dsq_insert(p, FALLBACK_DSQ, SCX_SLICE_DFL, + enq_flags); + } + return; + } + + cgrp = __COMPAT_scx_bpf_task_cgroup(p); + cgc = find_cgrp_ctx(cgrp); + if (!cgc) + goto out_release; + + if (fifo_sched) { + scx_bpf_dsq_insert(p, cgrp->kn->id, SCX_SLICE_DFL, enq_flags); + } else { + u64 tvtime = p->scx.dsq_vtime; + + /* + * Limit the amount of budget that an idling task can accumulate + * to one slice. + */ + if (time_before(tvtime, cgc->tvtime_now - SCX_SLICE_DFL)) + tvtime = cgc->tvtime_now - SCX_SLICE_DFL; + + scx_bpf_dsq_insert_vtime(p, cgrp->kn->id, SCX_SLICE_DFL, + tvtime, enq_flags); + } + + cgrp_enqueued(cgrp, cgc); +out_release: + bpf_cgroup_release(cgrp); +} + +/* + * Walk the cgroup tree to update the active weight sums as tasks wake up and + * sleep. The weight sums are used as the base when calculating the proportion a + * given cgroup or task is entitled to at each level. + */ +static void update_active_weight_sums(struct cgroup *cgrp, bool runnable) +{ + struct fcg_cgrp_ctx *cgc; + bool updated = false; + int idx; + + cgc = find_cgrp_ctx(cgrp); + if (!cgc) + return; + + /* + * In most cases, a hot cgroup would have multiple threads going to + * sleep and waking up while the whole cgroup stays active. In leaf + * cgroups, ->nr_runnable which is updated with __sync operations gates + * ->nr_active updates, so that we don't have to grab the cgv_tree_lock + * repeatedly for a busy cgroup which is staying active. + */ + if (runnable) { + if (__sync_fetch_and_add(&cgc->nr_runnable, 1)) + return; + stat_inc(FCG_STAT_ACT); + } else { + if (__sync_sub_and_fetch(&cgc->nr_runnable, 1)) + return; + stat_inc(FCG_STAT_DEACT); + } + + /* + * If @cgrp is becoming runnable, its hweight should be refreshed after + * it's added to the weight tree so that enqueue has the up-to-date + * value. If @cgrp is becoming quiescent, the hweight should be + * refreshed before it's removed from the weight tree so that the usage + * charging which happens afterwards has access to the latest value. + */ + if (!runnable) + cgrp_refresh_hweight(cgrp, cgc); + + /* propagate upwards */ + bpf_for(idx, 0, cgrp->level) { + int level = cgrp->level - idx; + struct fcg_cgrp_ctx *cgc, *pcgc = NULL; + bool propagate = false; + + cgc = find_ancestor_cgrp_ctx(cgrp, level); + if (!cgc) + break; + if (level) { + pcgc = find_ancestor_cgrp_ctx(cgrp, level - 1); + if (!pcgc) + break; + } + + /* + * We need the propagation protected by a lock to synchronize + * against weight changes. There's no reason to drop the lock at + * each level but bpf_spin_lock() doesn't want any function + * calls while locked. + */ + bpf_spin_lock(&cgv_tree_lock); + + if (runnable) { + if (!cgc->nr_active++) { + updated = true; + if (pcgc) { + propagate = true; + pcgc->child_weight_sum += cgc->weight; + } + } + } else { + if (!--cgc->nr_active) { + updated = true; + if (pcgc) { + propagate = true; + pcgc->child_weight_sum -= cgc->weight; + } + } + } + + bpf_spin_unlock(&cgv_tree_lock); + + if (!propagate) + break; + } + + if (updated) + __sync_fetch_and_add(&hweight_gen, 1); + + if (runnable) + cgrp_refresh_hweight(cgrp, cgc); +} + +void BPF_STRUCT_OPS(fcg_runnable, struct task_struct *p, u64 enq_flags) +{ + struct cgroup *cgrp; + + cgrp = __COMPAT_scx_bpf_task_cgroup(p); + update_active_weight_sums(cgrp, true); + bpf_cgroup_release(cgrp); +} + +void BPF_STRUCT_OPS(fcg_running, struct task_struct *p) +{ + struct cgroup *cgrp; + struct fcg_cgrp_ctx *cgc; + + if (fifo_sched) + return; + + cgrp = __COMPAT_scx_bpf_task_cgroup(p); + cgc = find_cgrp_ctx(cgrp); + if (cgc) { + /* + * @cgc->tvtime_now always progresses forward as tasks start + * executing. The test and update can be performed concurrently + * from multiple CPUs and thus racy. Any error should be + * contained and temporary. Let's just live with it. + */ + if (time_before(cgc->tvtime_now, p->scx.dsq_vtime)) + cgc->tvtime_now = p->scx.dsq_vtime; + } + bpf_cgroup_release(cgrp); +} + +void BPF_STRUCT_OPS(fcg_stopping, struct task_struct *p, bool runnable) +{ + struct fcg_task_ctx *taskc; + struct cgroup *cgrp; + struct fcg_cgrp_ctx *cgc; + + /* + * Scale the execution time by the inverse of the weight and charge. + * + * Note that the default yield implementation yields by setting + * @p->scx.slice to zero and the following would treat the yielding task + * as if it has consumed all its slice. If this penalizes yielding tasks + * too much, determine the execution time by taking explicit timestamps + * instead of depending on @p->scx.slice. + */ + if (!fifo_sched) + p->scx.dsq_vtime += + (SCX_SLICE_DFL - p->scx.slice) * 100 / p->scx.weight; + + taskc = bpf_task_storage_get(&task_ctx, p, 0, 0); + if (!taskc) { + scx_bpf_error("task_ctx lookup failed"); + return; + } + + if (!taskc->bypassed_at) + return; + + cgrp = __COMPAT_scx_bpf_task_cgroup(p); + cgc = find_cgrp_ctx(cgrp); + if (cgc) { + __sync_fetch_and_add(&cgc->cvtime_delta, + p->se.sum_exec_runtime - taskc->bypassed_at); + taskc->bypassed_at = 0; + } + bpf_cgroup_release(cgrp); +} + +void BPF_STRUCT_OPS(fcg_quiescent, struct task_struct *p, u64 deq_flags) +{ + struct cgroup *cgrp; + + cgrp = __COMPAT_scx_bpf_task_cgroup(p); + update_active_weight_sums(cgrp, false); + bpf_cgroup_release(cgrp); +} + +void BPF_STRUCT_OPS(fcg_cgroup_set_weight, struct cgroup *cgrp, u32 weight) +{ + struct fcg_cgrp_ctx *cgc, *pcgc = NULL; + + cgc = find_cgrp_ctx(cgrp); + if (!cgc) + return; + + if (cgrp->level) { + pcgc = find_ancestor_cgrp_ctx(cgrp, cgrp->level - 1); + if (!pcgc) + return; + } + + bpf_spin_lock(&cgv_tree_lock); + if (pcgc && cgc->nr_active) + pcgc->child_weight_sum += (s64)weight - cgc->weight; + cgc->weight = weight; + bpf_spin_unlock(&cgv_tree_lock); +} + +static bool try_pick_next_cgroup(u64 *cgidp) +{ + struct bpf_rb_node *rb_node; + struct cgv_node_stash *stash; + struct cgv_node *cgv_node; + struct fcg_cgrp_ctx *cgc; + struct cgroup *cgrp; + u64 cgid; + + /* pop the front cgroup and wind cvtime_now accordingly */ + bpf_spin_lock(&cgv_tree_lock); + + rb_node = bpf_rbtree_first(&cgv_tree); + if (!rb_node) { + bpf_spin_unlock(&cgv_tree_lock); + stat_inc(FCG_STAT_PNC_NO_CGRP); + *cgidp = 0; + return true; + } + + rb_node = bpf_rbtree_remove(&cgv_tree, rb_node); + bpf_spin_unlock(&cgv_tree_lock); + + if (!rb_node) { + /* + * This should never happen. bpf_rbtree_first() was called + * above while the tree lock was held, so the node should + * always be present. + */ + scx_bpf_error("node could not be removed"); + return true; + } + + cgv_node = container_of(rb_node, struct cgv_node, rb_node); + cgid = cgv_node->cgid; + + if (time_before(cvtime_now, cgv_node->cvtime)) + cvtime_now = cgv_node->cvtime; + + /* + * If lookup fails, the cgroup's gone. Free and move on. See + * fcg_cgroup_exit(). + */ + cgrp = bpf_cgroup_from_id(cgid); + if (!cgrp) { + stat_inc(FCG_STAT_PNC_GONE); + goto out_free; + } + + cgc = bpf_cgrp_storage_get(&cgrp_ctx, cgrp, 0, 0); + if (!cgc) { + bpf_cgroup_release(cgrp); + stat_inc(FCG_STAT_PNC_GONE); + goto out_free; + } + + if (!scx_bpf_dsq_move_to_local(cgid)) { + bpf_cgroup_release(cgrp); + stat_inc(FCG_STAT_PNC_EMPTY); + goto out_stash; + } + + /* + * Successfully consumed from the cgroup. This will be our current + * cgroup for the new slice. Refresh its hweight. + */ + cgrp_refresh_hweight(cgrp, cgc); + + bpf_cgroup_release(cgrp); + + /* + * As the cgroup may have more tasks, add it back to the rbtree. Note + * that here we charge the full slice upfront and then exact later + * according to the actual consumption. This prevents lowpri thundering + * herd from saturating the machine. + */ + bpf_spin_lock(&cgv_tree_lock); + cgv_node->cvtime += cgrp_slice_ns * FCG_HWEIGHT_ONE / (cgc->hweight ?: 1); + cgrp_cap_budget(cgv_node, cgc); + bpf_rbtree_add(&cgv_tree, &cgv_node->rb_node, cgv_node_less); + bpf_spin_unlock(&cgv_tree_lock); + + *cgidp = cgid; + stat_inc(FCG_STAT_PNC_NEXT); + return true; + +out_stash: + stash = bpf_map_lookup_elem(&cgv_node_stash, &cgid); + if (!stash) { + stat_inc(FCG_STAT_PNC_GONE); + goto out_free; + } + + /* + * Paired with cmpxchg in cgrp_enqueued(). If they see the following + * transition, they'll enqueue the cgroup. If they are earlier, we'll + * see their task in the dq below and requeue the cgroup. + */ + __sync_val_compare_and_swap(&cgc->queued, 1, 0); + + if (scx_bpf_dsq_nr_queued(cgid)) { + bpf_spin_lock(&cgv_tree_lock); + bpf_rbtree_add(&cgv_tree, &cgv_node->rb_node, cgv_node_less); + bpf_spin_unlock(&cgv_tree_lock); + stat_inc(FCG_STAT_PNC_RACE); + } else { + cgv_node = bpf_kptr_xchg(&stash->node, cgv_node); + if (cgv_node) { + scx_bpf_error("unexpected !NULL cgv_node stash"); + goto out_free; + } + } + + return false; + +out_free: + bpf_obj_drop(cgv_node); + return false; +} + +void BPF_STRUCT_OPS(fcg_dispatch, s32 cpu, struct task_struct *prev) +{ + struct fcg_cpu_ctx *cpuc; + struct fcg_cgrp_ctx *cgc; + struct cgroup *cgrp; + u64 now = scx_bpf_now(); + bool picked_next = false; + + cpuc = find_cpu_ctx(); + if (!cpuc) + return; + + if (!cpuc->cur_cgid) + goto pick_next_cgroup; + + if (time_before(now, cpuc->cur_at + cgrp_slice_ns)) { + if (scx_bpf_dsq_move_to_local(cpuc->cur_cgid)) { + stat_inc(FCG_STAT_CNS_KEEP); + return; + } + stat_inc(FCG_STAT_CNS_EMPTY); + } else { + stat_inc(FCG_STAT_CNS_EXPIRE); + } + + /* + * The current cgroup is expiring. It was already charged a full slice. + * Calculate the actual usage and accumulate the delta. + */ + cgrp = bpf_cgroup_from_id(cpuc->cur_cgid); + if (!cgrp) { + stat_inc(FCG_STAT_CNS_GONE); + goto pick_next_cgroup; + } + + cgc = bpf_cgrp_storage_get(&cgrp_ctx, cgrp, 0, 0); + if (cgc) { + /* + * We want to update the vtime delta and then look for the next + * cgroup to execute but the latter needs to be done in a loop + * and we can't keep the lock held. Oh well... + */ + bpf_spin_lock(&cgv_tree_lock); + __sync_fetch_and_add(&cgc->cvtime_delta, + (cpuc->cur_at + cgrp_slice_ns - now) * + FCG_HWEIGHT_ONE / (cgc->hweight ?: 1)); + bpf_spin_unlock(&cgv_tree_lock); + } else { + stat_inc(FCG_STAT_CNS_GONE); + } + + bpf_cgroup_release(cgrp); + +pick_next_cgroup: + cpuc->cur_at = now; + + if (scx_bpf_dsq_move_to_local(FALLBACK_DSQ)) { + cpuc->cur_cgid = 0; + return; + } + + bpf_repeat(CGROUP_MAX_RETRIES) { + if (try_pick_next_cgroup(&cpuc->cur_cgid)) { + picked_next = true; + break; + } + } + + /* + * This only happens if try_pick_next_cgroup() races against enqueue + * path for more than CGROUP_MAX_RETRIES times, which is extremely + * unlikely and likely indicates an underlying bug. There shouldn't be + * any stall risk as the race is against enqueue. + */ + if (!picked_next) + stat_inc(FCG_STAT_PNC_FAIL); +} + +s32 BPF_STRUCT_OPS(fcg_init_task, struct task_struct *p, + struct scx_init_task_args *args) +{ + struct fcg_task_ctx *taskc; + struct fcg_cgrp_ctx *cgc; + + /* + * @p is new. Let's ensure that its task_ctx is available. We can sleep + * in this function and the following will automatically use GFP_KERNEL. + */ + taskc = bpf_task_storage_get(&task_ctx, p, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!taskc) + return -ENOMEM; + + taskc->bypassed_at = 0; + + if (!(cgc = find_cgrp_ctx(args->cgroup))) + return -ENOENT; + + p->scx.dsq_vtime = cgc->tvtime_now; + + return 0; +} + +int BPF_STRUCT_OPS_SLEEPABLE(fcg_cgroup_init, struct cgroup *cgrp, + struct scx_cgroup_init_args *args) +{ + struct fcg_cgrp_ctx *cgc; + struct cgv_node *cgv_node; + struct cgv_node_stash empty_stash = {}, *stash; + u64 cgid = cgrp->kn->id; + int ret; + + /* + * Technically incorrect as cgroup ID is full 64bit while dsq ID is + * 63bit. Should not be a problem in practice and easy to spot in the + * unlikely case that it breaks. + */ + ret = scx_bpf_create_dsq(cgid, -1); + if (ret) + return ret; + + cgc = bpf_cgrp_storage_get(&cgrp_ctx, cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!cgc) { + ret = -ENOMEM; + goto err_destroy_dsq; + } + + cgc->weight = args->weight; + cgc->hweight = FCG_HWEIGHT_ONE; + + ret = bpf_map_update_elem(&cgv_node_stash, &cgid, &empty_stash, + BPF_NOEXIST); + if (ret) { + if (ret != -ENOMEM) + scx_bpf_error("unexpected stash creation error (%d)", + ret); + goto err_destroy_dsq; + } + + stash = bpf_map_lookup_elem(&cgv_node_stash, &cgid); + if (!stash) { + scx_bpf_error("unexpected cgv_node stash lookup failure"); + ret = -ENOENT; + goto err_destroy_dsq; + } + + cgv_node = bpf_obj_new(struct cgv_node); + if (!cgv_node) { + ret = -ENOMEM; + goto err_del_cgv_node; + } + + cgv_node->cgid = cgid; + cgv_node->cvtime = cvtime_now; + + cgv_node = bpf_kptr_xchg(&stash->node, cgv_node); + if (cgv_node) { + scx_bpf_error("unexpected !NULL cgv_node stash"); + ret = -EBUSY; + goto err_drop; + } + + return 0; + +err_drop: + bpf_obj_drop(cgv_node); +err_del_cgv_node: + bpf_map_delete_elem(&cgv_node_stash, &cgid); +err_destroy_dsq: + scx_bpf_destroy_dsq(cgid); + return ret; +} + +void BPF_STRUCT_OPS(fcg_cgroup_exit, struct cgroup *cgrp) +{ + u64 cgid = cgrp->kn->id; + + /* + * For now, there's no way find and remove the cgv_node if it's on the + * cgv_tree. Let's drain them in the dispatch path as they get popped + * off the front of the tree. + */ + bpf_map_delete_elem(&cgv_node_stash, &cgid); + scx_bpf_destroy_dsq(cgid); +} + +void BPF_STRUCT_OPS(fcg_cgroup_move, struct task_struct *p, + struct cgroup *from, struct cgroup *to) +{ + struct fcg_cgrp_ctx *from_cgc, *to_cgc; + s64 delta; + + /* find_cgrp_ctx() triggers scx_ops_error() on lookup failures */ + if (!(from_cgc = find_cgrp_ctx(from)) || !(to_cgc = find_cgrp_ctx(to))) + return; + + delta = time_delta(p->scx.dsq_vtime, from_cgc->tvtime_now); + p->scx.dsq_vtime = to_cgc->tvtime_now + delta; +} + +s32 BPF_STRUCT_OPS_SLEEPABLE(fcg_init) +{ + return scx_bpf_create_dsq(FALLBACK_DSQ, -1); +} + +void BPF_STRUCT_OPS(fcg_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SCX_OPS_DEFINE(flatcg_ops, + .select_cpu = (void *)fcg_select_cpu, + .enqueue = (void *)fcg_enqueue, + .dispatch = (void *)fcg_dispatch, + .runnable = (void *)fcg_runnable, + .running = (void *)fcg_running, + .stopping = (void *)fcg_stopping, + .quiescent = (void *)fcg_quiescent, + .init_task = (void *)fcg_init_task, + .cgroup_set_weight = (void *)fcg_cgroup_set_weight, + .cgroup_init = (void *)fcg_cgroup_init, + .cgroup_exit = (void *)fcg_cgroup_exit, + .cgroup_move = (void *)fcg_cgroup_move, + .init = (void *)fcg_init, + .exit = (void *)fcg_exit, + .flags = SCX_OPS_HAS_CGROUP_WEIGHT | SCX_OPS_ENQ_EXITING, + .name = "flatcg"); diff --git a/tools/sched_ext/scx_flatcg.c b/tools/sched_ext/scx_flatcg.c new file mode 100644 index 0000000000000000000000000000000000000000..6dd423eeb4ff98e13e4a02fe098cbff26b01c118 --- /dev/null +++ b/tools/sched_ext/scx_flatcg.c @@ -0,0 +1,234 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 Tejun Heo + * Copyright (c) 2023 David Vernet + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "scx_flatcg.h" +#include "scx_flatcg.bpf.skel.h" + +#ifndef FILEID_KERNFS +#define FILEID_KERNFS 0xfe +#endif + +const char help_fmt[] = +"A flattened cgroup hierarchy sched_ext scheduler.\n" +"\n" +"See the top-level comment in .bpf.c for more details.\n" +"\n" +"Usage: %s [-s SLICE_US] [-i INTERVAL] [-f] [-v]\n" +"\n" +" -s SLICE_US Override slice duration\n" +" -i INTERVAL Report interval\n" +" -f Use FIFO scheduling instead of weighted vtime scheduling\n" +" -v Print libbpf debug messages\n" +" -h Display this help and exit\n"; + +static bool verbose; +static volatile int exit_req; + +static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args) +{ + if (level == LIBBPF_DEBUG && !verbose) + return 0; + return vfprintf(stderr, format, args); +} + +static void sigint_handler(int dummy) +{ + exit_req = 1; +} + +static float read_cpu_util(__u64 *last_sum, __u64 *last_idle) +{ + FILE *fp; + char buf[4096]; + char *line, *cur = NULL, *tok; + __u64 sum = 0, idle = 0; + __u64 delta_sum, delta_idle; + int idx; + + fp = fopen("/proc/stat", "r"); + if (!fp) { + perror("fopen(\"/proc/stat\")"); + return 0.0; + } + + if (!fgets(buf, sizeof(buf), fp)) { + perror("fgets(\"/proc/stat\")"); + fclose(fp); + return 0.0; + } + fclose(fp); + + line = buf; + for (idx = 0; (tok = strtok_r(line, " \n", &cur)); idx++) { + char *endp = NULL; + __u64 v; + + if (idx == 0) { + line = NULL; + continue; + } + v = strtoull(tok, &endp, 0); + if (!endp || *endp != '\0') { + fprintf(stderr, "failed to parse %dth field of /proc/stat (\"%s\")\n", + idx, tok); + continue; + } + sum += v; + if (idx == 4) + idle = v; + } + + delta_sum = sum - *last_sum; + delta_idle = idle - *last_idle; + *last_sum = sum; + *last_idle = idle; + + return delta_sum ? (float)(delta_sum - delta_idle) / delta_sum : 0.0; +} + +static void fcg_read_stats(struct scx_flatcg *skel, __u64 *stats) +{ + __u64 cnts[FCG_NR_STATS][skel->rodata->nr_cpus]; + __u32 idx; + + memset(stats, 0, sizeof(stats[0]) * FCG_NR_STATS); + + for (idx = 0; idx < FCG_NR_STATS; idx++) { + int ret, cpu; + + ret = bpf_map_lookup_elem(bpf_map__fd(skel->maps.stats), + &idx, cnts[idx]); + if (ret < 0) + continue; + for (cpu = 0; cpu < skel->rodata->nr_cpus; cpu++) + stats[idx] += cnts[idx][cpu]; + } +} + +int main(int argc, char **argv) +{ + struct scx_flatcg *skel; + struct bpf_link *link; + struct timespec intv_ts = { .tv_sec = 2, .tv_nsec = 0 }; + bool dump_cgrps = false; + __u64 last_cpu_sum = 0, last_cpu_idle = 0; + __u64 last_stats[FCG_NR_STATS] = {}; + unsigned long seq = 0; + __s32 opt; + __u64 ecode; + + libbpf_set_print(libbpf_print_fn); + signal(SIGINT, sigint_handler); + signal(SIGTERM, sigint_handler); +restart: + skel = SCX_OPS_OPEN(flatcg_ops, scx_flatcg); + + skel->rodata->nr_cpus = libbpf_num_possible_cpus(); + skel->rodata->cgrp_slice_ns = __COMPAT_ENUM_OR_ZERO("scx_public_consts", "SCX_SLICE_DFL"); + + while ((opt = getopt(argc, argv, "s:i:dfvh")) != -1) { + double v; + + switch (opt) { + case 's': + v = strtod(optarg, NULL); + skel->rodata->cgrp_slice_ns = v * 1000; + break; + case 'i': + v = strtod(optarg, NULL); + intv_ts.tv_sec = v; + intv_ts.tv_nsec = (v - (float)intv_ts.tv_sec) * 1000000000; + break; + case 'd': + dump_cgrps = true; + break; + case 'f': + skel->rodata->fifo_sched = true; + break; + case 'v': + verbose = true; + break; + case 'h': + default: + fprintf(stderr, help_fmt, basename(argv[0])); + return opt != 'h'; + } + } + + printf("slice=%.1lfms intv=%.1lfs dump_cgrps=%d", + (double)skel->rodata->cgrp_slice_ns / 1000000.0, + (double)intv_ts.tv_sec + (double)intv_ts.tv_nsec / 1000000000.0, + dump_cgrps); + + SCX_OPS_LOAD(skel, flatcg_ops, scx_flatcg, uei); + link = SCX_OPS_ATTACH(skel, flatcg_ops, scx_flatcg); + + while (!exit_req && !UEI_EXITED(skel, uei)) { + __u64 acc_stats[FCG_NR_STATS]; + __u64 stats[FCG_NR_STATS]; + float cpu_util; + int i; + + cpu_util = read_cpu_util(&last_cpu_sum, &last_cpu_idle); + + fcg_read_stats(skel, acc_stats); + for (i = 0; i < FCG_NR_STATS; i++) + stats[i] = acc_stats[i] - last_stats[i]; + + memcpy(last_stats, acc_stats, sizeof(acc_stats)); + + printf("\n[SEQ %6lu cpu=%5.1lf hweight_gen=%" PRIu64 "]\n", + seq++, cpu_util * 100.0, skel->data->hweight_gen); + printf(" act:%6llu deact:%6llu global:%6llu local:%6llu\n", + stats[FCG_STAT_ACT], + stats[FCG_STAT_DEACT], + stats[FCG_STAT_GLOBAL], + stats[FCG_STAT_LOCAL]); + printf("HWT cache:%6llu update:%6llu skip:%6llu race:%6llu\n", + stats[FCG_STAT_HWT_CACHE], + stats[FCG_STAT_HWT_UPDATES], + stats[FCG_STAT_HWT_SKIP], + stats[FCG_STAT_HWT_RACE]); + printf("ENQ skip:%6llu race:%6llu\n", + stats[FCG_STAT_ENQ_SKIP], + stats[FCG_STAT_ENQ_RACE]); + printf("CNS keep:%6llu expire:%6llu empty:%6llu gone:%6llu\n", + stats[FCG_STAT_CNS_KEEP], + stats[FCG_STAT_CNS_EXPIRE], + stats[FCG_STAT_CNS_EMPTY], + stats[FCG_STAT_CNS_GONE]); + printf("PNC next:%6llu empty:%6llu nocgrp:%6llu gone:%6llu race:%6llu fail:%6llu\n", + stats[FCG_STAT_PNC_NEXT], + stats[FCG_STAT_PNC_EMPTY], + stats[FCG_STAT_PNC_NO_CGRP], + stats[FCG_STAT_PNC_GONE], + stats[FCG_STAT_PNC_RACE], + stats[FCG_STAT_PNC_FAIL]); + printf("BAD remove:%6llu\n", + acc_stats[FCG_STAT_BAD_REMOVAL]); + fflush(stdout); + + nanosleep(&intv_ts, NULL); + } + + bpf_link__destroy(link); + ecode = UEI_REPORT(skel, uei); + scx_flatcg__destroy(skel); + + if (UEI_ECODE_RESTART(ecode)) + goto restart; + return 0; +} diff --git a/tools/sched_ext/scx_flatcg.h b/tools/sched_ext/scx_flatcg.h new file mode 100644 index 0000000000000000000000000000000000000000..6f2ea50acb1cb3adbb624ae4b109ddd4bed27da5 --- /dev/null +++ b/tools/sched_ext/scx_flatcg.h @@ -0,0 +1,51 @@ +#ifndef __SCX_EXAMPLE_FLATCG_H +#define __SCX_EXAMPLE_FLATCG_H + +enum { + FCG_HWEIGHT_ONE = 1LLU << 16, +}; + +enum fcg_stat_idx { + FCG_STAT_ACT, + FCG_STAT_DEACT, + FCG_STAT_LOCAL, + FCG_STAT_GLOBAL, + + FCG_STAT_HWT_UPDATES, + FCG_STAT_HWT_CACHE, + FCG_STAT_HWT_SKIP, + FCG_STAT_HWT_RACE, + + FCG_STAT_ENQ_SKIP, + FCG_STAT_ENQ_RACE, + + FCG_STAT_CNS_KEEP, + FCG_STAT_CNS_EXPIRE, + FCG_STAT_CNS_EMPTY, + FCG_STAT_CNS_GONE, + + FCG_STAT_PNC_NO_CGRP, + FCG_STAT_PNC_NEXT, + FCG_STAT_PNC_EMPTY, + FCG_STAT_PNC_GONE, + FCG_STAT_PNC_RACE, + FCG_STAT_PNC_FAIL, + + FCG_STAT_BAD_REMOVAL, + + FCG_NR_STATS, +}; + +struct fcg_cgrp_ctx { + u32 nr_active; + u32 nr_runnable; + u32 queued; + u32 weight; + u32 hweight; + u64 child_weight_sum; + u64 hweight_gen; + s64 cvtime_delta; + u64 tvtime_now; +}; + +#endif /* __SCX_EXAMPLE_FLATCG_H */ diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..3a20bb0c014a100b410f682f78d9319a00661009 --- /dev/null +++ b/tools/sched_ext/scx_qmap.bpf.c @@ -0,0 +1,827 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A simple five-level FIFO queue scheduler. + * + * There are five FIFOs implemented using BPF_MAP_TYPE_QUEUE. A task gets + * assigned to one depending on its compound weight. Each CPU round robins + * through the FIFOs and dispatches more from FIFOs with higher indices - 1 from + * queue0, 2 from queue1, 4 from queue2 and so on. + * + * This scheduler demonstrates: + * + * - BPF-side queueing using PIDs. + * - Sleepable per-task storage allocation using ops.prep_enable(). + * - Using ops.cpu_release() to handle a higher priority scheduling class taking + * the CPU away. + * - Core-sched support. + * + * This scheduler is primarily for demonstration and testing of sched_ext + * features and unlikely to be useful for actual workloads. + * + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo + * Copyright (c) 2022 David Vernet + */ +#include + +enum consts { + ONE_SEC_IN_NS = 1000000000, + SHARED_DSQ = 0, + HIGHPRI_DSQ = 1, + HIGHPRI_WEIGHT = 8668, /* this is what -20 maps to */ +}; + +char _license[] SEC("license") = "GPL"; + +const volatile u64 slice_ns; +const volatile u32 stall_user_nth; +const volatile u32 stall_kernel_nth; +const volatile u32 dsp_inf_loop_after; +const volatile u32 dsp_batch; +const volatile bool highpri_boosting; +const volatile bool print_shared_dsq; +const volatile s32 disallow_tgid; +const volatile bool suppress_dump; + +u64 nr_highpri_queued; +u32 test_error_cnt; + +UEI_DEFINE(uei); + +struct qmap { + __uint(type, BPF_MAP_TYPE_QUEUE); + __uint(max_entries, 4096); + __type(value, u32); +} queue0 SEC(".maps"), + queue1 SEC(".maps"), + queue2 SEC(".maps"), + queue3 SEC(".maps"), + queue4 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 5); + __type(key, int); + __array(values, struct qmap); +} queue_arr SEC(".maps") = { + .values = { + [0] = &queue0, + [1] = &queue1, + [2] = &queue2, + [3] = &queue3, + [4] = &queue4, + }, +}; + +/* + * If enabled, CPU performance target is set according to the queue index + * according to the following table. + */ +static const u32 qidx_to_cpuperf_target[] = { + [0] = SCX_CPUPERF_ONE * 0 / 4, + [1] = SCX_CPUPERF_ONE * 1 / 4, + [2] = SCX_CPUPERF_ONE * 2 / 4, + [3] = SCX_CPUPERF_ONE * 3 / 4, + [4] = SCX_CPUPERF_ONE * 4 / 4, +}; + +/* + * Per-queue sequence numbers to implement core-sched ordering. + * + * Tail seq is assigned to each queued task and incremented. Head seq tracks the + * sequence number of the latest dispatched task. The distance between the a + * task's seq and the associated queue's head seq is called the queue distance + * and used when comparing two tasks for ordering. See qmap_core_sched_before(). + */ +static u64 core_sched_head_seqs[5]; +static u64 core_sched_tail_seqs[5]; + +/* Per-task scheduling context */ +struct task_ctx { + bool force_local; /* Dispatch directly to local_dsq */ + bool highpri; + u64 core_sched_seq; +}; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct task_ctx); +} task_ctx_stor SEC(".maps"); + +struct cpu_ctx { + u64 dsp_idx; /* dispatch index */ + u64 dsp_cnt; /* remaining count */ + u32 avg_weight; + u32 cpuperf_target; +}; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 1); + __type(key, u32); + __type(value, struct cpu_ctx); +} cpu_ctx_stor SEC(".maps"); + +/* Statistics */ +u64 nr_enqueued, nr_dispatched, nr_reenqueued, nr_dequeued, nr_ddsp_from_enq; +u64 nr_core_sched_execed; +u64 nr_expedited_local, nr_expedited_remote, nr_expedited_lost, nr_expedited_from_timer; +u32 cpuperf_min, cpuperf_avg, cpuperf_max; +u32 cpuperf_target_min, cpuperf_target_avg, cpuperf_target_max; + +static s32 pick_direct_dispatch_cpu(struct task_struct *p, s32 prev_cpu) +{ + s32 cpu; + + if (p->nr_cpus_allowed == 1 || + scx_bpf_test_and_clear_cpu_idle(prev_cpu)) + return prev_cpu; + + cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0); + if (cpu >= 0) + return cpu; + + return -1; +} + +static struct task_ctx *lookup_task_ctx(struct task_struct *p) +{ + struct task_ctx *tctx; + + if (!(tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0))) { + scx_bpf_error("task_ctx lookup failed"); + return NULL; + } + return tctx; +} + +s32 BPF_STRUCT_OPS(qmap_select_cpu, struct task_struct *p, + s32 prev_cpu, u64 wake_flags) +{ + struct task_ctx *tctx; + s32 cpu; + + if (!(tctx = lookup_task_ctx(p))) + return -ESRCH; + + cpu = pick_direct_dispatch_cpu(p, prev_cpu); + + if (cpu >= 0) { + tctx->force_local = true; + return cpu; + } else { + return prev_cpu; + } +} + +static int weight_to_idx(u32 weight) +{ + /* Coarsely map the compound weight to a FIFO. */ + if (weight <= 25) + return 0; + else if (weight <= 50) + return 1; + else if (weight < 200) + return 2; + else if (weight < 400) + return 3; + else + return 4; +} + +void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags) +{ + static u32 user_cnt, kernel_cnt; + struct task_ctx *tctx; + u32 pid = p->pid; + int idx = weight_to_idx(p->scx.weight); + void *ring; + s32 cpu; + + if (p->flags & PF_KTHREAD) { + if (stall_kernel_nth && !(++kernel_cnt % stall_kernel_nth)) + return; + } else { + if (stall_user_nth && !(++user_cnt % stall_user_nth)) + return; + } + + if (test_error_cnt && !--test_error_cnt) + scx_bpf_error("test triggering error"); + + if (!(tctx = lookup_task_ctx(p))) + return; + + /* + * All enqueued tasks must have their core_sched_seq updated for correct + * core-sched ordering. Also, take a look at the end of qmap_dispatch(). + */ + tctx->core_sched_seq = core_sched_tail_seqs[idx]++; + + /* + * If qmap_select_cpu() is telling us to or this is the last runnable + * task on the CPU, enqueue locally. + */ + if (tctx->force_local) { + tctx->force_local = false; + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, slice_ns, enq_flags); + return; + } + + /* if select_cpu() wasn't called, try direct dispatch */ + if (!(enq_flags & SCX_ENQ_CPU_SELECTED) && + (cpu = pick_direct_dispatch_cpu(p, scx_bpf_task_cpu(p))) >= 0) { + __sync_fetch_and_add(&nr_ddsp_from_enq, 1); + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | cpu, slice_ns, enq_flags); + return; + } + + /* + * If the task was re-enqueued due to the CPU being preempted by a + * higher priority scheduling class, just re-enqueue the task directly + * on the global DSQ. As we want another CPU to pick it up, find and + * kick an idle CPU. + */ + if (enq_flags & SCX_ENQ_REENQ) { + s32 cpu; + + scx_bpf_dsq_insert(p, SHARED_DSQ, 0, enq_flags); + cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0); + if (cpu >= 0) + scx_bpf_kick_cpu(cpu, SCX_KICK_IDLE); + return; + } + + ring = bpf_map_lookup_elem(&queue_arr, &idx); + if (!ring) { + scx_bpf_error("failed to find ring %d", idx); + return; + } + + /* Queue on the selected FIFO. If the FIFO overflows, punt to global. */ + if (bpf_map_push_elem(ring, &pid, 0)) { + scx_bpf_dsq_insert(p, SHARED_DSQ, slice_ns, enq_flags); + return; + } + + if (highpri_boosting && p->scx.weight >= HIGHPRI_WEIGHT) { + tctx->highpri = true; + __sync_fetch_and_add(&nr_highpri_queued, 1); + } + __sync_fetch_and_add(&nr_enqueued, 1); +} + +/* + * The BPF queue map doesn't support removal and sched_ext can handle spurious + * dispatches. qmap_dequeue() is only used to collect statistics. + */ +void BPF_STRUCT_OPS(qmap_dequeue, struct task_struct *p, u64 deq_flags) +{ + __sync_fetch_and_add(&nr_dequeued, 1); + if (deq_flags & SCX_DEQ_CORE_SCHED_EXEC) + __sync_fetch_and_add(&nr_core_sched_execed, 1); +} + +static void update_core_sched_head_seq(struct task_struct *p) +{ + int idx = weight_to_idx(p->scx.weight); + struct task_ctx *tctx; + + if ((tctx = lookup_task_ctx(p))) + core_sched_head_seqs[idx] = tctx->core_sched_seq; +} + +/* + * To demonstrate the use of scx_bpf_dsq_move(), implement silly selective + * priority boosting mechanism by scanning SHARED_DSQ looking for highpri tasks, + * moving them to HIGHPRI_DSQ and then consuming them first. This makes minor + * difference only when dsp_batch is larger than 1. + * + * scx_bpf_dispatch[_vtime]_from_dsq() are allowed both from ops.dispatch() and + * non-rq-lock holding BPF programs. As demonstration, this function is called + * from qmap_dispatch() and monitor_timerfn(). + */ +static bool dispatch_highpri(bool from_timer) +{ + struct task_struct *p; + s32 this_cpu = bpf_get_smp_processor_id(); + + /* scan SHARED_DSQ and move highpri tasks to HIGHPRI_DSQ */ + bpf_for_each(scx_dsq, p, SHARED_DSQ, 0) { + static u64 highpri_seq; + struct task_ctx *tctx; + + if (!(tctx = lookup_task_ctx(p))) + return false; + + if (tctx->highpri) { + /* exercise the set_*() and vtime interface too */ + __COMPAT_scx_bpf_dsq_move_set_slice( + BPF_FOR_EACH_ITER, slice_ns * 2); + __COMPAT_scx_bpf_dsq_move_set_vtime( + BPF_FOR_EACH_ITER, highpri_seq++); + __COMPAT_scx_bpf_dsq_move_vtime( + BPF_FOR_EACH_ITER, p, HIGHPRI_DSQ, 0); + } + } + + /* + * Scan HIGHPRI_DSQ and dispatch until a task that can run on this CPU + * is found. + */ + bpf_for_each(scx_dsq, p, HIGHPRI_DSQ, 0) { + bool dispatched = false; + s32 cpu; + + if (bpf_cpumask_test_cpu(this_cpu, p->cpus_ptr)) + cpu = this_cpu; + else + cpu = scx_bpf_pick_any_cpu(p->cpus_ptr, 0); + + if (__COMPAT_scx_bpf_dsq_move(BPF_FOR_EACH_ITER, p, + SCX_DSQ_LOCAL_ON | cpu, + SCX_ENQ_PREEMPT)) { + if (cpu == this_cpu) { + dispatched = true; + __sync_fetch_and_add(&nr_expedited_local, 1); + } else { + __sync_fetch_and_add(&nr_expedited_remote, 1); + } + if (from_timer) + __sync_fetch_and_add(&nr_expedited_from_timer, 1); + } else { + __sync_fetch_and_add(&nr_expedited_lost, 1); + } + + if (dispatched) + return true; + } + + return false; +} + +void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev) +{ + struct task_struct *p; + struct cpu_ctx *cpuc; + struct task_ctx *tctx; + u32 zero = 0, batch = dsp_batch ?: 1; + void *fifo; + s32 i, pid; + + if (dispatch_highpri(false)) + return; + + if (!nr_highpri_queued && scx_bpf_dsq_move_to_local(SHARED_DSQ)) + return; + + if (dsp_inf_loop_after && nr_dispatched > dsp_inf_loop_after) { + /* + * PID 2 should be kthreadd which should mostly be idle and off + * the scheduler. Let's keep dispatching it to force the kernel + * to call this function over and over again. + */ + p = bpf_task_from_pid(2); + if (p) { + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, slice_ns, 0); + bpf_task_release(p); + return; + } + } + + if (!(cpuc = bpf_map_lookup_elem(&cpu_ctx_stor, &zero))) { + scx_bpf_error("failed to look up cpu_ctx"); + return; + } + + for (i = 0; i < 5; i++) { + /* Advance the dispatch cursor and pick the fifo. */ + if (!cpuc->dsp_cnt) { + cpuc->dsp_idx = (cpuc->dsp_idx + 1) % 5; + cpuc->dsp_cnt = 1 << cpuc->dsp_idx; + } + + fifo = bpf_map_lookup_elem(&queue_arr, &cpuc->dsp_idx); + if (!fifo) { + scx_bpf_error("failed to find ring %llu", cpuc->dsp_idx); + return; + } + + /* Dispatch or advance. */ + bpf_repeat(BPF_MAX_LOOPS) { + struct task_ctx *tctx; + + if (bpf_map_pop_elem(fifo, &pid)) + break; + + p = bpf_task_from_pid(pid); + if (!p) + continue; + + if (!(tctx = lookup_task_ctx(p))) { + bpf_task_release(p); + return; + } + + if (tctx->highpri) + __sync_fetch_and_sub(&nr_highpri_queued, 1); + + update_core_sched_head_seq(p); + __sync_fetch_and_add(&nr_dispatched, 1); + + scx_bpf_dsq_insert(p, SHARED_DSQ, slice_ns, 0); + bpf_task_release(p); + + batch--; + cpuc->dsp_cnt--; + if (!batch || !scx_bpf_dispatch_nr_slots()) { + if (dispatch_highpri(false)) + return; + scx_bpf_dsq_move_to_local(SHARED_DSQ); + return; + } + if (!cpuc->dsp_cnt) + break; + } + + cpuc->dsp_cnt = 0; + } + + /* + * No other tasks. @prev will keep running. Update its core_sched_seq as + * if the task were enqueued and dispatched immediately. + */ + if (prev) { + tctx = bpf_task_storage_get(&task_ctx_stor, prev, 0, 0); + if (!tctx) { + scx_bpf_error("task_ctx lookup failed"); + return; + } + + tctx->core_sched_seq = + core_sched_tail_seqs[weight_to_idx(prev->scx.weight)]++; + } +} + +void BPF_STRUCT_OPS(qmap_tick, struct task_struct *p) +{ + struct cpu_ctx *cpuc; + u32 zero = 0; + int idx; + + if (!(cpuc = bpf_map_lookup_elem(&cpu_ctx_stor, &zero))) { + scx_bpf_error("failed to look up cpu_ctx"); + return; + } + + /* + * Use the running avg of weights to select the target cpuperf level. + * This is a demonstration of the cpuperf feature rather than a + * practical strategy to regulate CPU frequency. + */ + cpuc->avg_weight = cpuc->avg_weight * 3 / 4 + p->scx.weight / 4; + idx = weight_to_idx(cpuc->avg_weight); + cpuc->cpuperf_target = qidx_to_cpuperf_target[idx]; + + scx_bpf_cpuperf_set(scx_bpf_task_cpu(p), cpuc->cpuperf_target); +} + +/* + * The distance from the head of the queue scaled by the weight of the queue. + * The lower the number, the older the task and the higher the priority. + */ +static s64 task_qdist(struct task_struct *p) +{ + int idx = weight_to_idx(p->scx.weight); + struct task_ctx *tctx; + s64 qdist; + + tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0); + if (!tctx) { + scx_bpf_error("task_ctx lookup failed"); + return 0; + } + + qdist = tctx->core_sched_seq - core_sched_head_seqs[idx]; + + /* + * As queue index increments, the priority doubles. The queue w/ index 3 + * is dispatched twice more frequently than 2. Reflect the difference by + * scaling qdists accordingly. Note that the shift amount needs to be + * flipped depending on the sign to avoid flipping priority direction. + */ + if (qdist >= 0) + return qdist << (4 - idx); + else + return qdist << idx; +} + +/* + * This is called to determine the task ordering when core-sched is picking + * tasks to execute on SMT siblings and should encode about the same ordering as + * the regular scheduling path. Use the priority-scaled distances from the head + * of the queues to compare the two tasks which should be consistent with the + * dispatch path behavior. + */ +bool BPF_STRUCT_OPS(qmap_core_sched_before, + struct task_struct *a, struct task_struct *b) +{ + return task_qdist(a) > task_qdist(b); +} + +void BPF_STRUCT_OPS(qmap_cpu_release, s32 cpu, struct scx_cpu_release_args *args) +{ + u32 cnt; + + /* + * Called when @cpu is taken by a higher priority scheduling class. This + * makes @cpu no longer available for executing sched_ext tasks. As we + * don't want the tasks in @cpu's local dsq to sit there until @cpu + * becomes available again, re-enqueue them into the global dsq. See + * %SCX_ENQ_REENQ handling in qmap_enqueue(). + */ + cnt = scx_bpf_reenqueue_local(); + if (cnt) + __sync_fetch_and_add(&nr_reenqueued, cnt); +} + +s32 BPF_STRUCT_OPS(qmap_init_task, struct task_struct *p, + struct scx_init_task_args *args) +{ + if (p->tgid == disallow_tgid) + p->scx.disallow = true; + + /* + * @p is new. Let's ensure that its task_ctx is available. We can sleep + * in this function and the following will automatically use GFP_KERNEL. + */ + if (bpf_task_storage_get(&task_ctx_stor, p, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE)) + return 0; + else + return -ENOMEM; +} + +void BPF_STRUCT_OPS(qmap_dump, struct scx_dump_ctx *dctx) +{ + s32 i, pid; + + if (suppress_dump) + return; + + bpf_for(i, 0, 5) { + void *fifo; + + if (!(fifo = bpf_map_lookup_elem(&queue_arr, &i))) + return; + + scx_bpf_dump("QMAP FIFO[%d]:", i); + bpf_repeat(4096) { + if (bpf_map_pop_elem(fifo, &pid)) + break; + scx_bpf_dump(" %d", pid); + } + scx_bpf_dump("\n"); + } +} + +void BPF_STRUCT_OPS(qmap_dump_cpu, struct scx_dump_ctx *dctx, s32 cpu, bool idle) +{ + u32 zero = 0; + struct cpu_ctx *cpuc; + + if (suppress_dump || idle) + return; + if (!(cpuc = bpf_map_lookup_percpu_elem(&cpu_ctx_stor, &zero, cpu))) + return; + + scx_bpf_dump("QMAP: dsp_idx=%llu dsp_cnt=%llu avg_weight=%u cpuperf_target=%u", + cpuc->dsp_idx, cpuc->dsp_cnt, cpuc->avg_weight, + cpuc->cpuperf_target); +} + +void BPF_STRUCT_OPS(qmap_dump_task, struct scx_dump_ctx *dctx, struct task_struct *p) +{ + struct task_ctx *taskc; + + if (suppress_dump) + return; + if (!(taskc = bpf_task_storage_get(&task_ctx_stor, p, 0, 0))) + return; + + scx_bpf_dump("QMAP: force_local=%d core_sched_seq=%llu", + taskc->force_local, taskc->core_sched_seq); +} + +/* + * Print out the online and possible CPU map using bpf_printk() as a + * demonstration of using the cpumask kfuncs and ops.cpu_on/offline(). + */ +static void print_cpus(void) +{ + const struct cpumask *possible, *online; + s32 cpu; + char buf[128] = "", *p; + int idx; + + possible = scx_bpf_get_possible_cpumask(); + online = scx_bpf_get_online_cpumask(); + + idx = 0; + bpf_for(cpu, 0, scx_bpf_nr_cpu_ids()) { + if (!(p = MEMBER_VPTR(buf, [idx++]))) + break; + if (bpf_cpumask_test_cpu(cpu, online)) + *p++ = 'O'; + else if (bpf_cpumask_test_cpu(cpu, possible)) + *p++ = 'X'; + else + *p++ = ' '; + + if ((cpu & 7) == 7) { + if (!(p = MEMBER_VPTR(buf, [idx++]))) + break; + *p++ = '|'; + } + } + buf[sizeof(buf) - 1] = '\0'; + + scx_bpf_put_cpumask(online); + scx_bpf_put_cpumask(possible); + + bpf_printk("CPUS: |%s", buf); +} + +void BPF_STRUCT_OPS(qmap_cpu_online, s32 cpu) +{ + bpf_printk("CPU %d coming online", cpu); + /* @cpu is already online at this point */ + print_cpus(); +} + +void BPF_STRUCT_OPS(qmap_cpu_offline, s32 cpu) +{ + bpf_printk("CPU %d going offline", cpu); + /* @cpu is still online at this point */ + print_cpus(); +} + +struct monitor_timer { + struct bpf_timer timer; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, u32); + __type(value, struct monitor_timer); +} monitor_timer SEC(".maps"); + +/* + * Print out the min, avg and max performance levels of CPUs every second to + * demonstrate the cpuperf interface. + */ +static void monitor_cpuperf(void) +{ + u32 zero = 0, nr_cpu_ids; + u64 cap_sum = 0, cur_sum = 0, cur_min = SCX_CPUPERF_ONE, cur_max = 0; + u64 target_sum = 0, target_min = SCX_CPUPERF_ONE, target_max = 0; + const struct cpumask *online; + int i, nr_online_cpus = 0; + + nr_cpu_ids = scx_bpf_nr_cpu_ids(); + online = scx_bpf_get_online_cpumask(); + + bpf_for(i, 0, nr_cpu_ids) { + struct cpu_ctx *cpuc; + u32 cap, cur; + + if (!bpf_cpumask_test_cpu(i, online)) + continue; + nr_online_cpus++; + + /* collect the capacity and current cpuperf */ + cap = scx_bpf_cpuperf_cap(i); + cur = scx_bpf_cpuperf_cur(i); + + cur_min = cur < cur_min ? cur : cur_min; + cur_max = cur > cur_max ? cur : cur_max; + + /* + * $cur is relative to $cap. Scale it down accordingly so that + * it's in the same scale as other CPUs and $cur_sum/$cap_sum + * makes sense. + */ + cur_sum += cur * cap / SCX_CPUPERF_ONE; + cap_sum += cap; + + if (!(cpuc = bpf_map_lookup_percpu_elem(&cpu_ctx_stor, &zero, i))) { + scx_bpf_error("failed to look up cpu_ctx"); + goto out; + } + + /* collect target */ + cur = cpuc->cpuperf_target; + target_sum += cur; + target_min = cur < target_min ? cur : target_min; + target_max = cur > target_max ? cur : target_max; + } + + cpuperf_min = cur_min; + cpuperf_avg = cur_sum * SCX_CPUPERF_ONE / cap_sum; + cpuperf_max = cur_max; + + cpuperf_target_min = target_min; + cpuperf_target_avg = target_sum / nr_online_cpus; + cpuperf_target_max = target_max; +out: + scx_bpf_put_cpumask(online); +} + +/* + * Dump the currently queued tasks in the shared DSQ to demonstrate the usage of + * scx_bpf_dsq_nr_queued() and DSQ iterator. Raise the dispatch batch count to + * see meaningful dumps in the trace pipe. + */ +static void dump_shared_dsq(void) +{ + struct task_struct *p; + s32 nr; + + if (!(nr = scx_bpf_dsq_nr_queued(SHARED_DSQ))) + return; + + bpf_printk("Dumping %d tasks in SHARED_DSQ in reverse order", nr); + + bpf_rcu_read_lock(); + bpf_for_each(scx_dsq, p, SHARED_DSQ, SCX_DSQ_ITER_REV) + bpf_printk("%s[%d]", p->comm, p->pid); + bpf_rcu_read_unlock(); +} + +static int monitor_timerfn(void *map, int *key, struct bpf_timer *timer) +{ + bpf_rcu_read_lock(); + dispatch_highpri(true); + bpf_rcu_read_unlock(); + + monitor_cpuperf(); + + if (print_shared_dsq) + dump_shared_dsq(); + + bpf_timer_start(timer, ONE_SEC_IN_NS, 0); + return 0; +} + +s32 BPF_STRUCT_OPS_SLEEPABLE(qmap_init) +{ + u32 key = 0; + struct bpf_timer *timer; + s32 ret; + + print_cpus(); + + ret = scx_bpf_create_dsq(SHARED_DSQ, -1); + if (ret) + return ret; + + ret = scx_bpf_create_dsq(HIGHPRI_DSQ, -1); + if (ret) + return ret; + + timer = bpf_map_lookup_elem(&monitor_timer, &key); + if (!timer) + return -ESRCH; + + bpf_timer_init(timer, &monitor_timer, CLOCK_MONOTONIC); + bpf_timer_set_callback(timer, monitor_timerfn); + + return bpf_timer_start(timer, ONE_SEC_IN_NS, 0); +} + +void BPF_STRUCT_OPS(qmap_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SCX_OPS_DEFINE(qmap_ops, + .select_cpu = (void *)qmap_select_cpu, + .enqueue = (void *)qmap_enqueue, + .dequeue = (void *)qmap_dequeue, + .dispatch = (void *)qmap_dispatch, + .tick = (void *)qmap_tick, + .core_sched_before = (void *)qmap_core_sched_before, + .cpu_release = (void *)qmap_cpu_release, + .init_task = (void *)qmap_init_task, + .dump = (void *)qmap_dump, + .dump_cpu = (void *)qmap_dump_cpu, + .dump_task = (void *)qmap_dump_task, + .cpu_online = (void *)qmap_cpu_online, + .cpu_offline = (void *)qmap_cpu_offline, + .init = (void *)qmap_init, + .exit = (void *)qmap_exit, + .timeout_ms = 5000U, + .name = "qmap"); diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c new file mode 100644 index 0000000000000000000000000000000000000000..c4912ab2e76f21362d2c7e9f300b48ae0179c73c --- /dev/null +++ b/tools/sched_ext/scx_qmap.c @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo + * Copyright (c) 2022 David Vernet + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include "scx_qmap.bpf.skel.h" + +const char help_fmt[] = +"A simple five-level FIFO queue sched_ext scheduler.\n" +"\n" +"See the top-level comment in .bpf.c for more details.\n" +"\n" +"Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-l COUNT] [-b COUNT]\n" +" [-P] [-d PID] [-D LEN] [-p] [-v]\n" +"\n" +" -s SLICE_US Override slice duration\n" +" -e COUNT Trigger scx_bpf_error() after COUNT enqueues\n" +" -t COUNT Stall every COUNT'th user thread\n" +" -T COUNT Stall every COUNT'th kernel thread\n" +" -l COUNT Trigger dispatch infinite looping after COUNT dispatches\n" +" -b COUNT Dispatch upto COUNT tasks together\n" +" -P Print out DSQ content to trace_pipe every second, use with -b\n" +" -H Boost nice -20 tasks in SHARED_DSQ, use with -b\n" +" -d PID Disallow a process from switching into SCHED_EXT (-1 for self)\n" +" -D LEN Set scx_exit_info.dump buffer length\n" +" -S Suppress qmap-specific debug dump\n" +" -p Switch only tasks on SCHED_EXT policy instead of all\n" +" -v Print libbpf debug messages\n" +" -h Display this help and exit\n"; + +static bool verbose; +static volatile int exit_req; + +static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args) +{ + if (level == LIBBPF_DEBUG && !verbose) + return 0; + return vfprintf(stderr, format, args); +} + +static void sigint_handler(int dummy) +{ + exit_req = 1; +} + +int main(int argc, char **argv) +{ + struct scx_qmap *skel; + struct bpf_link *link; + int opt; + + libbpf_set_print(libbpf_print_fn); + signal(SIGINT, sigint_handler); + signal(SIGTERM, sigint_handler); + + skel = SCX_OPS_OPEN(qmap_ops, scx_qmap); + + skel->rodata->slice_ns = __COMPAT_ENUM_OR_ZERO("scx_public_consts", "SCX_SLICE_DFL"); + + while ((opt = getopt(argc, argv, "s:e:t:T:l:b:PHd:D:Spvh")) != -1) { + switch (opt) { + case 's': + skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000; + break; + case 'e': + skel->bss->test_error_cnt = strtoul(optarg, NULL, 0); + break; + case 't': + skel->rodata->stall_user_nth = strtoul(optarg, NULL, 0); + break; + case 'T': + skel->rodata->stall_kernel_nth = strtoul(optarg, NULL, 0); + break; + case 'l': + skel->rodata->dsp_inf_loop_after = strtoul(optarg, NULL, 0); + break; + case 'b': + skel->rodata->dsp_batch = strtoul(optarg, NULL, 0); + break; + case 'P': + skel->rodata->print_shared_dsq = true; + break; + case 'H': + skel->rodata->highpri_boosting = true; + break; + case 'd': + skel->rodata->disallow_tgid = strtol(optarg, NULL, 0); + if (skel->rodata->disallow_tgid < 0) + skel->rodata->disallow_tgid = getpid(); + break; + case 'D': + skel->struct_ops.qmap_ops->exit_dump_len = strtoul(optarg, NULL, 0); + break; + case 'S': + skel->rodata->suppress_dump = true; + break; + case 'p': + skel->struct_ops.qmap_ops->flags |= SCX_OPS_SWITCH_PARTIAL; + break; + case 'v': + verbose = true; + break; + default: + fprintf(stderr, help_fmt, basename(argv[0])); + return opt != 'h'; + } + } + + SCX_OPS_LOAD(skel, qmap_ops, scx_qmap, uei); + link = SCX_OPS_ATTACH(skel, qmap_ops, scx_qmap); + + while (!exit_req && !UEI_EXITED(skel, uei)) { + long nr_enqueued = skel->bss->nr_enqueued; + long nr_dispatched = skel->bss->nr_dispatched; + + printf("stats : enq=%lu dsp=%lu delta=%ld reenq=%"PRIu64" deq=%"PRIu64" core=%"PRIu64" enq_ddsp=%"PRIu64"\n", + nr_enqueued, nr_dispatched, nr_enqueued - nr_dispatched, + skel->bss->nr_reenqueued, skel->bss->nr_dequeued, + skel->bss->nr_core_sched_execed, + skel->bss->nr_ddsp_from_enq); + printf(" exp_local=%"PRIu64" exp_remote=%"PRIu64" exp_timer=%"PRIu64" exp_lost=%"PRIu64"\n", + skel->bss->nr_expedited_local, + skel->bss->nr_expedited_remote, + skel->bss->nr_expedited_from_timer, + skel->bss->nr_expedited_lost); + if (__COMPAT_has_ksym("scx_bpf_cpuperf_cur")) + printf("cpuperf: cur min/avg/max=%u/%u/%u target min/avg/max=%u/%u/%u\n", + skel->bss->cpuperf_min, + skel->bss->cpuperf_avg, + skel->bss->cpuperf_max, + skel->bss->cpuperf_target_min, + skel->bss->cpuperf_target_avg, + skel->bss->cpuperf_target_max); + fflush(stdout); + sleep(1); + } + + bpf_link__destroy(link); + UEI_REPORT(skel, uei); + scx_qmap__destroy(skel); + /* + * scx_qmap implements ops.cpu_on/offline() and doesn't need to restart + * on CPU hotplug events. + */ + return 0; +} diff --git a/tools/sched_ext/scx_show_state.py b/tools/sched_ext/scx_show_state.py new file mode 100644 index 0000000000000000000000000000000000000000..b800d4f5f2e9952baeb8c7ad2a73df9f4ac8e512 --- /dev/null +++ b/tools/sched_ext/scx_show_state.py @@ -0,0 +1,42 @@ +#!/usr/bin/env drgn +# +# Copyright (C) 2024 Tejun Heo +# Copyright (C) 2024 Meta Platforms, Inc. and affiliates. + +desc = """ +This is a drgn script to show the current sched_ext state. +For more info on drgn, visit https://github.com/osandov/drgn. +""" + +import drgn +import sys + +def err(s): + print(s, file=sys.stderr, flush=True) + sys.exit(1) + +def read_int(name): + return int(prog[name].value_()) + +def read_atomic(name): + return prog[name].counter.value_() + +def read_static_key(name): + return prog[name].key.enabled.counter.value_() + +def ops_state_str(state): + return prog['scx_ops_enable_state_str'][state].string_().decode() + +ops = prog['scx_ops'] +enable_state = read_atomic("scx_ops_enable_state_var") + +print(f'ops : {ops.name.string_().decode()}') +print(f'enabled : {read_static_key("__scx_ops_enabled")}') +print(f'switching_all : {read_int("scx_switching_all")}') +print(f'switched_all : {read_static_key("__scx_switched_all")}') +print(f'enable_state : {ops_state_str(enable_state)} ({enable_state})') +print(f'in_softlockup : {prog["scx_in_softlockup"].value_()}') +print(f'breather_depth: {read_atomic("scx_ops_breather_depth")}') +print(f'bypass_depth : {prog["scx_ops_bypass_depth"].value_()}') +print(f'nr_rejected : {read_atomic("scx_nr_rejected")}') +print(f'enable_seq : {read_atomic("scx_enable_seq")}') diff --git a/tools/sched_ext/scx_simple.bpf.c b/tools/sched_ext/scx_simple.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..e6de99dba7db6a407f4ebe9deaa4a1105d3c9f3b --- /dev/null +++ b/tools/sched_ext/scx_simple.bpf.c @@ -0,0 +1,151 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A simple scheduler. + * + * By default, it operates as a simple global weighted vtime scheduler and can + * be switched to FIFO scheduling. It also demonstrates the following niceties. + * + * - Statistics tracking how many tasks are queued to local and global dsq's. + * - Termination notification for userspace. + * + * While very simple, this scheduler should work reasonably well on CPUs with a + * uniform L3 cache topology. While preemption is not implemented, the fact that + * the scheduling queue is shared across all CPUs means that whatever is at the + * front of the queue is likely to be executed fairly quickly given enough + * number of CPUs. The FIFO scheduling mode may be beneficial to some workloads + * but comes with the usual problems with FIFO scheduling where saturating + * threads can easily drown out interactive ones. + * + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo + * Copyright (c) 2022 David Vernet + */ +#include + +char _license[] SEC("license") = "GPL"; + +const volatile bool fifo_sched; + +static u64 vtime_now; +UEI_DEFINE(uei); + +/* + * Built-in DSQs such as SCX_DSQ_GLOBAL cannot be used as priority queues + * (meaning, cannot be dispatched to with scx_bpf_dsq_insert_vtime()). We + * therefore create a separate DSQ with ID 0 that we dispatch to and consume + * from. If scx_simple only supported global FIFO scheduling, then we could just + * use SCX_DSQ_GLOBAL. + */ +#define SHARED_DSQ 0 + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(u64)); + __uint(max_entries, 2); /* [local, global] */ +} stats SEC(".maps"); + +static void stat_inc(u32 idx) +{ + u64 *cnt_p = bpf_map_lookup_elem(&stats, &idx); + if (cnt_p) + (*cnt_p)++; +} + +s32 BPF_STRUCT_OPS(simple_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) +{ + bool is_idle = false; + s32 cpu; + + cpu = scx_bpf_select_cpu_dfl(p, prev_cpu, wake_flags, &is_idle); + if (is_idle) { + stat_inc(0); /* count local queueing */ + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0); + } + + return cpu; +} + +void BPF_STRUCT_OPS(simple_enqueue, struct task_struct *p, u64 enq_flags) +{ + stat_inc(1); /* count global queueing */ + + if (fifo_sched) { + scx_bpf_dsq_insert(p, SHARED_DSQ, SCX_SLICE_DFL, enq_flags); + } else { + u64 vtime = p->scx.dsq_vtime; + + /* + * Limit the amount of budget that an idling task can accumulate + * to one slice. + */ + if (time_before(vtime, vtime_now - SCX_SLICE_DFL)) + vtime = vtime_now - SCX_SLICE_DFL; + + scx_bpf_dsq_insert_vtime(p, SHARED_DSQ, SCX_SLICE_DFL, vtime, + enq_flags); + } +} + +void BPF_STRUCT_OPS(simple_dispatch, s32 cpu, struct task_struct *prev) +{ + scx_bpf_dsq_move_to_local(SHARED_DSQ); +} + +void BPF_STRUCT_OPS(simple_running, struct task_struct *p) +{ + if (fifo_sched) + return; + + /* + * Global vtime always progresses forward as tasks start executing. The + * test and update can be performed concurrently from multiple CPUs and + * thus racy. Any error should be contained and temporary. Let's just + * live with it. + */ + if (time_before(vtime_now, p->scx.dsq_vtime)) + vtime_now = p->scx.dsq_vtime; +} + +void BPF_STRUCT_OPS(simple_stopping, struct task_struct *p, bool runnable) +{ + if (fifo_sched) + return; + + /* + * Scale the execution time by the inverse of the weight and charge. + * + * Note that the default yield implementation yields by setting + * @p->scx.slice to zero and the following would treat the yielding task + * as if it has consumed all its slice. If this penalizes yielding tasks + * too much, determine the execution time by taking explicit timestamps + * instead of depending on @p->scx.slice. + */ + p->scx.dsq_vtime += (SCX_SLICE_DFL - p->scx.slice) * 100 / p->scx.weight; +} + +void BPF_STRUCT_OPS(simple_enable, struct task_struct *p) +{ + p->scx.dsq_vtime = vtime_now; +} + +s32 BPF_STRUCT_OPS_SLEEPABLE(simple_init) +{ + return scx_bpf_create_dsq(SHARED_DSQ, -1); +} + +void BPF_STRUCT_OPS(simple_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SCX_OPS_DEFINE(simple_ops, + .select_cpu = (void *)simple_select_cpu, + .enqueue = (void *)simple_enqueue, + .dispatch = (void *)simple_dispatch, + .running = (void *)simple_running, + .stopping = (void *)simple_stopping, + .enable = (void *)simple_enable, + .init = (void *)simple_init, + .exit = (void *)simple_exit, + .name = "simple"); diff --git a/tools/sched_ext/scx_simple.c b/tools/sched_ext/scx_simple.c new file mode 100644 index 0000000000000000000000000000000000000000..76d83199545cb27673a42a236a6d7e5940ecd550 --- /dev/null +++ b/tools/sched_ext/scx_simple.c @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2022 Tejun Heo + * Copyright (c) 2022 David Vernet + */ +#include +#include +#include +#include +#include +#include +#include "scx_simple.bpf.skel.h" + +const char help_fmt[] = +"A simple sched_ext scheduler.\n" +"\n" +"See the top-level comment in .bpf.c for more details.\n" +"\n" +"Usage: %s [-f] [-v]\n" +"\n" +" -f Use FIFO scheduling instead of weighted vtime scheduling\n" +" -v Print libbpf debug messages\n" +" -h Display this help and exit\n"; + +static bool verbose; +static volatile int exit_req; + +static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args) +{ + if (level == LIBBPF_DEBUG && !verbose) + return 0; + return vfprintf(stderr, format, args); +} + +static void sigint_handler(int simple) +{ + exit_req = 1; +} + +static void read_stats(struct scx_simple *skel, __u64 *stats) +{ + int nr_cpus = libbpf_num_possible_cpus(); + __u64 cnts[2][nr_cpus]; + __u32 idx; + + memset(stats, 0, sizeof(stats[0]) * 2); + + for (idx = 0; idx < 2; idx++) { + int ret, cpu; + + ret = bpf_map_lookup_elem(bpf_map__fd(skel->maps.stats), + &idx, cnts[idx]); + if (ret < 0) + continue; + for (cpu = 0; cpu < nr_cpus; cpu++) + stats[idx] += cnts[idx][cpu]; + } +} + +int main(int argc, char **argv) +{ + struct scx_simple *skel; + struct bpf_link *link; + __u32 opt; + __u64 ecode; + + libbpf_set_print(libbpf_print_fn); + signal(SIGINT, sigint_handler); + signal(SIGTERM, sigint_handler); +restart: + skel = SCX_OPS_OPEN(simple_ops, scx_simple); + + while ((opt = getopt(argc, argv, "fvh")) != -1) { + switch (opt) { + case 'f': + skel->rodata->fifo_sched = true; + break; + case 'v': + verbose = true; + break; + default: + fprintf(stderr, help_fmt, basename(argv[0])); + return opt != 'h'; + } + } + + SCX_OPS_LOAD(skel, simple_ops, scx_simple, uei); + link = SCX_OPS_ATTACH(skel, simple_ops, scx_simple); + + while (!exit_req && !UEI_EXITED(skel, uei)) { + __u64 stats[2]; + + read_stats(skel, stats); + printf("local=%llu global=%llu\n", stats[0], stats[1]); + fflush(stdout); + sleep(1); + } + + bpf_link__destroy(link); + ecode = UEI_REPORT(skel, uei); + scx_simple__destroy(skel); + + if (UEI_ECODE_RESTART(ecode)) + goto restart; + return 0; +} diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 5c77c4e00443c83ac4351bd02ca59b2db9b77dd7..8290ba2e33fe21902d6ad2a190ea3c973cbb7ae2 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -74,6 +74,7 @@ TARGETS += riscv TARGETS += rlimits TARGETS += rseq TARGETS += rtc +TARGETS += sched_ext TARGETS += seccomp TARGETS += sgx TARGETS += sigaltstack @@ -107,10 +108,10 @@ TARGETS += zram TARGETS_HOTPLUG = cpu-hotplug TARGETS_HOTPLUG += memory-hotplug -# User can optionally provide a TARGETS skiplist. By default we skip -# BPF since it has cutting edge build time dependencies which require -# more effort to install. -SKIP_TARGETS ?= bpf +# User can optionally provide a TARGETS skiplist. By default we skip +# targets using BPF since it has cutting edge build time dependencies +# which require more effort to install. +SKIP_TARGETS ?= bpf sched_ext ifneq ($(SKIP_TARGETS),) TMP := $(filter-out $(SKIP_TARGETS), $(TARGETS)) override TARGETS := $(TMP) diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h index 4494eaa9937e5771751e1b238ed0570c3c3a728a..facf41fec72f1a94f1f0f95a2e90457fc37d3faa 100644 --- a/tools/testing/selftests/bpf/bpf_experimental.h +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -159,7 +159,34 @@ extern void *bpf_percpu_obj_new_impl(__u64 local_type_id, void *meta) __ksym; */ extern void bpf_percpu_obj_drop_impl(void *kptr, void *meta) __ksym; +struct bpf_iter_task_vma; + +extern int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it, + struct task_struct *task, + unsigned long addr) __ksym; +extern struct vm_area_struct *bpf_iter_task_vma_next(struct bpf_iter_task_vma *it) __ksym; +extern void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it) __ksym; + /* Convenience macro to wrap over bpf_obj_drop_impl */ #define bpf_percpu_obj_drop(kptr) bpf_percpu_obj_drop_impl(kptr, NULL) +struct bpf_iter_css_task; +struct cgroup_subsys_state; +extern int bpf_iter_css_task_new(struct bpf_iter_css_task *it, + struct cgroup_subsys_state *css, unsigned int flags) __weak __ksym; +extern struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it) __weak __ksym; +extern void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it) __weak __ksym; + +struct bpf_iter_task; +extern int bpf_iter_task_new(struct bpf_iter_task *it, + struct task_struct *task, unsigned int flags) __weak __ksym; +extern struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it) __weak __ksym; +extern void bpf_iter_task_destroy(struct bpf_iter_task *it) __weak __ksym; + +struct bpf_iter_css; +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; + #endif diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 2e8adf059fa3b867f977255d3be13412c1c7c42e..fb9930edfac0a08276b1bee5b3c3391922164044 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ +#include #include #include #include @@ -113,13 +114,12 @@ bpf_testmod_test_mod_kfunc(int i) __bpf_kfunc int bpf_iter_testmod_seq_new(struct bpf_iter_testmod_seq *it, s64 value, int cnt) { - if (cnt < 0) { - it->cnt = 0; + it->cnt = cnt; + + if (cnt < 0) return -EINVAL; - } it->value = value; - it->cnt = cnt; return 0; } @@ -134,6 +134,14 @@ __bpf_kfunc s64 *bpf_iter_testmod_seq_next(struct bpf_iter_testmod_seq* it) return &it->value; } +__bpf_kfunc s64 bpf_iter_testmod_seq_value(int val, struct bpf_iter_testmod_seq* it__iter) +{ + if (it__iter->cnt < 0) + return 0; + + return val + it__iter->value; +} + __bpf_kfunc void bpf_iter_testmod_seq_destroy(struct bpf_iter_testmod_seq *it) { it->cnt = 0; @@ -340,11 +348,12 @@ static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = { .write = bpf_testmod_test_write, }; -BTF_SET8_START(bpf_testmod_common_kfunc_ids) +BTF_KFUNCS_START(bpf_testmod_common_kfunc_ids) BTF_ID_FLAGS(func, bpf_iter_testmod_seq_new, KF_ITER_NEW) BTF_ID_FLAGS(func, bpf_iter_testmod_seq_next, KF_ITER_NEXT | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_testmod_seq_destroy, KF_ITER_DESTROY) -BTF_SET8_END(bpf_testmod_common_kfunc_ids) +BTF_ID_FLAGS(func, bpf_iter_testmod_seq_value) +BTF_KFUNCS_END(bpf_testmod_common_kfunc_ids) static const struct btf_kfunc_id_set bpf_testmod_common_kfunc_set = { .owner = THIS_MODULE, @@ -490,7 +499,7 @@ __bpf_kfunc static u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused return arg; } -BTF_SET8_START(bpf_testmod_check_kfunc_ids) +BTF_KFUNCS_START(bpf_testmod_check_kfunc_ids) BTF_ID_FLAGS(func, bpf_testmod_test_mod_kfunc) BTF_ID_FLAGS(func, bpf_kfunc_call_test1) BTF_ID_FLAGS(func, bpf_kfunc_call_test2) @@ -516,13 +525,95 @@ BTF_ID_FLAGS(func, bpf_kfunc_call_test_ref, KF_TRUSTED_ARGS | KF_RCU) BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE) BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg) BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset) -BTF_SET8_END(bpf_testmod_check_kfunc_ids) +BTF_KFUNCS_END(bpf_testmod_check_kfunc_ids) + +static int bpf_testmod_ops_init(struct btf *btf) +{ + return 0; +} + +static bool bpf_testmod_ops_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + return bpf_tracing_btf_ctx_access(off, size, type, prog, info); +} + +static int bpf_testmod_ops_init_member(const struct btf_type *t, + const struct btf_member *member, + void *kdata, const void *udata) +{ + if (member->offset == offsetof(struct bpf_testmod_ops, data) * 8) { + /* For data fields, this function has to copy it and return + * 1 to indicate that the data has been handled by the + * struct_ops type, or the verifier will reject the map if + * the value of the data field is not zero. + */ + ((struct bpf_testmod_ops *)kdata)->data = ((struct bpf_testmod_ops *)udata)->data; + return 1; + } + return 0; +} static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_testmod_check_kfunc_ids, }; +static const struct bpf_verifier_ops bpf_testmod_verifier_ops = { + .is_valid_access = bpf_testmod_ops_is_valid_access, +}; + +static int bpf_dummy_reg(void *kdata) +{ + struct bpf_testmod_ops *ops = kdata; + + /* Some test cases (ex. struct_ops_maybe_null) may not have test_2 + * initialized, so we need to check for NULL. + */ + if (ops->test_2) + ops->test_2(4, ops->data); + + return 0; +} + +static void bpf_dummy_unreg(void *kdata) +{ +} + +static int bpf_testmod_test_1(void) +{ + return 0; +} + +static void bpf_testmod_test_2(int a, int b) +{ +} + +static int bpf_testmod_ops__test_maybe_null(int dummy, + struct task_struct *task__nullable) +{ + return 0; +} + +static struct bpf_testmod_ops __bpf_testmod_ops = { + .test_1 = bpf_testmod_test_1, + .test_2 = bpf_testmod_test_2, + .test_maybe_null = bpf_testmod_ops__test_maybe_null, +}; + +struct bpf_struct_ops bpf_bpf_testmod_ops = { + .verifier_ops = &bpf_testmod_verifier_ops, + .init = bpf_testmod_ops_init, + .init_member = bpf_testmod_ops_init_member, + .reg = bpf_dummy_reg, + .unreg = bpf_dummy_unreg, + .cfi_stubs = &__bpf_testmod_ops, + .name = "bpf_testmod_ops", + .owner = THIS_MODULE, +}; + extern int bpf_fentry_test1(int a); static int bpf_testmod_init(void) @@ -533,6 +624,7 @@ static int bpf_testmod_init(void) ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_testmod_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_testmod_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &bpf_testmod_kfunc_set); + ret = ret ?: register_bpf_struct_ops(&bpf_bpf_testmod_ops, bpf_testmod_ops); if (ret < 0) return ret; if (bpf_fentry_test1(0) < 0) diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h index f32793efe095ba68bc1a388b46486dbb68d4c6a4..971458acfac350c0e09c7d76457a31ae9564b4b0 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h @@ -5,6 +5,8 @@ #include +struct task_struct; + struct bpf_testmod_test_read_ctx { char *buf; loff_t off; @@ -28,4 +30,19 @@ struct bpf_iter_testmod_seq { int cnt; }; +struct bpf_testmod_ops { + int (*test_1)(void); + void (*test_2)(int a, int b); + /* Used to test nullable arguments. */ + int (*test_maybe_null)(int dummy, struct task_struct *task); + + /* The following fields are used to test shadow copies. */ + char onebyte; + struct { + int a; + int b; + } unsupported; + int data; +}; + #endif /* _BPF_TESTMOD_H */ diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index f141e278b16fd49a9f077082047c130a16e0e1af..2cacc8fa96977202db0d987ad13e75cdf2d0d40f 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -7,10 +7,10 @@ #include "bpf_iter_ipv6_route.skel.h" #include "bpf_iter_netlink.skel.h" #include "bpf_iter_bpf_map.skel.h" -#include "bpf_iter_task.skel.h" +#include "bpf_iter_tasks.skel.h" #include "bpf_iter_task_stack.skel.h" #include "bpf_iter_task_file.skel.h" -#include "bpf_iter_task_vma.skel.h" +#include "bpf_iter_task_vmas.skel.h" #include "bpf_iter_task_btf.skel.h" #include "bpf_iter_tcp4.skel.h" #include "bpf_iter_tcp6.skel.h" @@ -215,12 +215,12 @@ static void *do_nothing_wait(void *arg) static void test_task_common_nocheck(struct bpf_iter_attach_opts *opts, int *num_unknown, int *num_known) { - struct bpf_iter_task *skel; + struct bpf_iter_tasks *skel; pthread_t thread_id; void *ret; - skel = bpf_iter_task__open_and_load(); - if (!ASSERT_OK_PTR(skel, "bpf_iter_task__open_and_load")) + skel = bpf_iter_tasks__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_tasks__open_and_load")) return; ASSERT_OK(pthread_mutex_lock(&do_nothing_mutex), "pthread_mutex_lock"); @@ -239,7 +239,7 @@ static void test_task_common_nocheck(struct bpf_iter_attach_opts *opts, ASSERT_FALSE(pthread_join(thread_id, &ret) || ret != NULL, "pthread_join"); - bpf_iter_task__destroy(skel); + bpf_iter_tasks__destroy(skel); } static void test_task_common(struct bpf_iter_attach_opts *opts, int num_unknown, int num_known) @@ -307,10 +307,10 @@ static void test_task_pidfd(void) static void test_task_sleepable(void) { - struct bpf_iter_task *skel; + struct bpf_iter_tasks *skel; - skel = bpf_iter_task__open_and_load(); - if (!ASSERT_OK_PTR(skel, "bpf_iter_task__open_and_load")) + skel = bpf_iter_tasks__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_tasks__open_and_load")) return; do_dummy_read(skel->progs.dump_task_sleepable); @@ -320,7 +320,7 @@ static void test_task_sleepable(void) ASSERT_GT(skel->bss->num_success_copy_from_user_task, 0, "num_success_copy_from_user_task"); - bpf_iter_task__destroy(skel); + bpf_iter_tasks__destroy(skel); } static void test_task_stack(void) @@ -1401,19 +1401,19 @@ static void str_strip_first_line(char *str) static void test_task_vma_common(struct bpf_iter_attach_opts *opts) { int err, iter_fd = -1, proc_maps_fd = -1; - struct bpf_iter_task_vma *skel; + struct bpf_iter_task_vmas *skel; int len, read_size = 4; char maps_path[64]; - skel = bpf_iter_task_vma__open(); - if (!ASSERT_OK_PTR(skel, "bpf_iter_task_vma__open")) + skel = bpf_iter_task_vmas__open(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_task_vmas__open")) return; skel->bss->pid = getpid(); skel->bss->one_task = opts ? 1 : 0; - err = bpf_iter_task_vma__load(skel); - if (!ASSERT_OK(err, "bpf_iter_task_vma__load")) + err = bpf_iter_task_vmas__load(skel); + if (!ASSERT_OK(err, "bpf_iter_task_vmas__load")) goto out; skel->links.proc_maps = bpf_program__attach_iter( @@ -1464,25 +1464,25 @@ static void test_task_vma_common(struct bpf_iter_attach_opts *opts) out: close(proc_maps_fd); close(iter_fd); - bpf_iter_task_vma__destroy(skel); + bpf_iter_task_vmas__destroy(skel); } static void test_task_vma_dead_task(void) { - struct bpf_iter_task_vma *skel; + struct bpf_iter_task_vmas *skel; int wstatus, child_pid = -1; time_t start_tm, cur_tm; int err, iter_fd = -1; int wait_sec = 3; - skel = bpf_iter_task_vma__open(); - if (!ASSERT_OK_PTR(skel, "bpf_iter_task_vma__open")) + skel = bpf_iter_task_vmas__open(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_task_vmas__open")) return; skel->bss->pid = getpid(); - err = bpf_iter_task_vma__load(skel); - if (!ASSERT_OK(err, "bpf_iter_task_vma__load")) + err = bpf_iter_task_vmas__load(skel); + if (!ASSERT_OK(err, "bpf_iter_task_vmas__load")) goto out; skel->links.proc_maps = bpf_program__attach_iter( @@ -1535,7 +1535,7 @@ static void test_task_vma_dead_task(void) out: waitpid(child_pid, &wstatus, 0); close(iter_fd); - bpf_iter_task_vma__destroy(skel); + bpf_iter_task_vmas__destroy(skel); } void test_bpf_sockmap_map_iter_fd(void) diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c b/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c index e02feb5fae97dd814775c0149893b4507cef2332..574d9a0cdc8e4a33c730bcb11a4136d60f718e86 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c @@ -4,6 +4,7 @@ #include #include #include +#include "iters_css_task.skel.h" #include "cgroup_iter.skel.h" #include "cgroup_helpers.h" @@ -263,6 +264,35 @@ static void test_walk_dead_self_only(struct cgroup_iter *skel) close(cgrp_fd); } +static void test_walk_self_only_css_task(void) +{ + struct iters_css_task *skel; + int err; + + skel = iters_css_task__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + bpf_program__set_autoload(skel->progs.cgroup_id_printer, true); + + err = iters_css_task__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + err = join_cgroup(cg_path[CHILD2]); + if (!ASSERT_OK(err, "join_cgroup")) + goto cleanup; + + skel->bss->target_pid = getpid(); + snprintf(expected_output, sizeof(expected_output), + PROLOGUE "%8llu\n" EPILOGUE, cg_id[CHILD2]); + read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[CHILD2], + BPF_CGROUP_ITER_SELF_ONLY, "test_walk_self_only_css_task"); + ASSERT_EQ(skel->bss->css_task_cnt, 1, "css_task_cnt"); +cleanup: + iters_css_task__destroy(skel); +} + void test_cgroup_iter(void) { struct cgroup_iter *skel = NULL; @@ -293,6 +323,9 @@ void test_cgroup_iter(void) test_walk_self_only(skel); if (test__start_subtest("cgroup_iter__dead_self_only")) test_walk_dead_self_only(skel); + if (test__start_subtest("cgroup_iter__self_only_css_task")) + test_walk_self_only_css_task(); + out: cgroup_iter__destroy(skel); cleanup_cgroups(); diff --git a/tools/testing/selftests/bpf/prog_tests/global_func_dead_code.c b/tools/testing/selftests/bpf/prog_tests/global_func_dead_code.c new file mode 100644 index 0000000000000000000000000000000000000000..65309894b27acf47deaf0e969c05b3b482f9dfd2 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/global_func_dead_code.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include +#include "verifier_global_subprogs.skel.h" +#include "freplace_dead_global_func.skel.h" + +void test_global_func_dead_code(void) +{ + struct verifier_global_subprogs *tgt_skel = NULL; + struct freplace_dead_global_func *skel = NULL; + char log_buf[4096]; + int err, tgt_fd; + + /* first, try to load target with good global subprog */ + tgt_skel = verifier_global_subprogs__open(); + if (!ASSERT_OK_PTR(tgt_skel, "tgt_skel_good_open")) + return; + + bpf_program__set_autoload(tgt_skel->progs.chained_global_func_calls_success, true); + + err = verifier_global_subprogs__load(tgt_skel); + if (!ASSERT_OK(err, "tgt_skel_good_load")) + goto out; + + tgt_fd = bpf_program__fd(tgt_skel->progs.chained_global_func_calls_success); + + /* Attach to good non-eliminated subprog */ + skel = freplace_dead_global_func__open(); + if (!ASSERT_OK_PTR(skel, "skel_good_open")) + goto out; + + err = bpf_program__set_attach_target(skel->progs.freplace_prog, tgt_fd, "global_good"); + ASSERT_OK(err, "attach_target_good"); + + err = freplace_dead_global_func__load(skel); + if (!ASSERT_OK(err, "skel_good_load")) + goto out; + + freplace_dead_global_func__destroy(skel); + + /* Try attaching to dead code-eliminated subprog */ + skel = freplace_dead_global_func__open(); + if (!ASSERT_OK_PTR(skel, "skel_dead_open")) + goto out; + + bpf_program__set_log_buf(skel->progs.freplace_prog, log_buf, sizeof(log_buf)); + err = bpf_program__set_attach_target(skel->progs.freplace_prog, tgt_fd, "global_dead"); + ASSERT_OK(err, "attach_target_dead"); + + err = freplace_dead_global_func__load(skel); + if (!ASSERT_ERR(err, "skel_dead_load")) + goto out; + + ASSERT_HAS_SUBSTR(log_buf, "Subprog global_dead doesn't exist", "dead_subprog_missing_msg"); + +out: + verifier_global_subprogs__destroy(tgt_skel); + freplace_dead_global_func__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c index 10804ae5ae972bea66cd03fae138c4c519fadd38..bf84d4a1d9ae2c68ceeac9f25373fd9df01b6935 100644 --- a/tools/testing/selftests/bpf/prog_tests/iters.c +++ b/tools/testing/selftests/bpf/prog_tests/iters.c @@ -1,13 +1,25 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include +#include +#include +#include +#include +#include #include +#include "cgroup_helpers.h" #include "iters.skel.h" #include "iters_state_safety.skel.h" #include "iters_looping.skel.h" #include "iters_num.skel.h" #include "iters_testmod_seq.skel.h" +#include "iters_task_vma.skel.h" +#include "iters_task.skel.h" +#include "iters_css_task.skel.h" +#include "iters_css.skel.h" +#include "iters_task_failure.skel.h" static void subtest_num_iters(void) { @@ -90,11 +102,199 @@ static void subtest_testmod_seq_iters(void) iters_testmod_seq__destroy(skel); } +static void subtest_task_vma_iters(void) +{ + unsigned long start, end, bpf_iter_start, bpf_iter_end; + struct iters_task_vma *skel; + char rest_of_line[1000]; + unsigned int seen; + FILE *f = NULL; + int err; + + skel = iters_task_vma__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + return; + + skel->bss->target_pid = getpid(); + + err = iters_task_vma__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto cleanup; + + getpgid(skel->bss->target_pid); + iters_task_vma__detach(skel); + + if (!ASSERT_GT(skel->bss->vmas_seen, 0, "vmas_seen_gt_zero")) + goto cleanup; + + f = fopen("/proc/self/maps", "r"); + if (!ASSERT_OK_PTR(f, "proc_maps_fopen")) + goto cleanup; + + seen = 0; + while (fscanf(f, "%lx-%lx %[^\n]\n", &start, &end, rest_of_line) == 3) { + /* [vsyscall] vma isn't _really_ part of task->mm vmas. + * /proc/PID/maps returns it when out of vmas - see get_gate_vma + * calls in fs/proc/task_mmu.c + */ + if (strstr(rest_of_line, "[vsyscall]")) + continue; + + bpf_iter_start = skel->bss->vm_ranges[seen].vm_start; + bpf_iter_end = skel->bss->vm_ranges[seen].vm_end; + + ASSERT_EQ(bpf_iter_start, start, "vma->vm_start match"); + ASSERT_EQ(bpf_iter_end, end, "vma->vm_end match"); + seen++; + } + + if (!ASSERT_EQ(skel->bss->vmas_seen, seen, "vmas_seen_eq")) + goto cleanup; + +cleanup: + if (f) + fclose(f); + iters_task_vma__destroy(skel); +} + +static pthread_mutex_t do_nothing_mutex; + +static void *do_nothing_wait(void *arg) +{ + pthread_mutex_lock(&do_nothing_mutex); + pthread_mutex_unlock(&do_nothing_mutex); + + pthread_exit(arg); +} + +#define thread_num 2 + +static void subtest_task_iters(void) +{ + struct iters_task *skel = NULL; + pthread_t thread_ids[thread_num]; + void *ret; + int err; + + skel = iters_task__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto cleanup; + skel->bss->target_pid = getpid(); + err = iters_task__attach(skel); + if (!ASSERT_OK(err, "iters_task__attach")) + goto cleanup; + pthread_mutex_lock(&do_nothing_mutex); + for (int i = 0; i < thread_num; i++) + ASSERT_OK(pthread_create(&thread_ids[i], NULL, &do_nothing_wait, NULL), + "pthread_create"); + + syscall(SYS_getpgid); + iters_task__detach(skel); + ASSERT_EQ(skel->bss->procs_cnt, 1, "procs_cnt"); + ASSERT_EQ(skel->bss->threads_cnt, thread_num + 1, "threads_cnt"); + ASSERT_EQ(skel->bss->proc_threads_cnt, thread_num + 1, "proc_threads_cnt"); + pthread_mutex_unlock(&do_nothing_mutex); + for (int i = 0; i < thread_num; i++) + ASSERT_OK(pthread_join(thread_ids[i], &ret), "pthread_join"); +cleanup: + iters_task__destroy(skel); +} + +extern int stack_mprotect(void); + +static void subtest_css_task_iters(void) +{ + struct iters_css_task *skel = NULL; + int err, cg_fd, cg_id; + const char *cgrp_path = "/cg1"; + + err = setup_cgroup_environment(); + if (!ASSERT_OK(err, "setup_cgroup_environment")) + goto cleanup; + cg_fd = create_and_get_cgroup(cgrp_path); + if (!ASSERT_GE(cg_fd, 0, "create_and_get_cgroup")) + goto cleanup; + cg_id = get_cgroup_id(cgrp_path); + err = join_cgroup(cgrp_path); + if (!ASSERT_OK(err, "join_cgroup")) + goto cleanup; + + skel = iters_css_task__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto cleanup; + + skel->bss->target_pid = getpid(); + skel->bss->cg_id = cg_id; + err = iters_css_task__attach(skel); + if (!ASSERT_OK(err, "iters_task__attach")) + goto cleanup; + err = stack_mprotect(); + if (!ASSERT_EQ(err, -1, "stack_mprotect") || + !ASSERT_EQ(errno, EPERM, "stack_mprotect")) + goto cleanup; + iters_css_task__detach(skel); + ASSERT_EQ(skel->bss->css_task_cnt, 1, "css_task_cnt"); + +cleanup: + cleanup_cgroup_environment(); + iters_css_task__destroy(skel); +} + +static void subtest_css_iters(void) +{ + struct iters_css *skel = NULL; + struct { + const char *path; + int fd; + } cgs[] = { + { "/cg1" }, + { "/cg1/cg2" }, + { "/cg1/cg2/cg3" }, + { "/cg1/cg2/cg3/cg4" }, + }; + int err, cg_nr = ARRAY_SIZE(cgs); + int i; + + err = setup_cgroup_environment(); + if (!ASSERT_OK(err, "setup_cgroup_environment")) + goto cleanup; + for (i = 0; i < cg_nr; i++) { + cgs[i].fd = create_and_get_cgroup(cgs[i].path); + if (!ASSERT_GE(cgs[i].fd, 0, "create_and_get_cgroup")) + goto cleanup; + } + + skel = iters_css__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto cleanup; + + skel->bss->target_pid = getpid(); + skel->bss->root_cg_id = get_cgroup_id(cgs[0].path); + skel->bss->leaf_cg_id = get_cgroup_id(cgs[cg_nr - 1].path); + err = iters_css__attach(skel); + + if (!ASSERT_OK(err, "iters_task__attach")) + goto cleanup; + + syscall(SYS_getpgid); + ASSERT_EQ(skel->bss->pre_order_cnt, cg_nr, "pre_order_cnt"); + ASSERT_EQ(skel->bss->first_cg_id, get_cgroup_id(cgs[0].path), "first_cg_id"); + + ASSERT_EQ(skel->bss->post_order_cnt, cg_nr, "post_order_cnt"); + ASSERT_EQ(skel->bss->last_cg_id, get_cgroup_id(cgs[0].path), "last_cg_id"); + ASSERT_EQ(skel->bss->tree_high, cg_nr - 1, "tree_high"); + iters_css__detach(skel); +cleanup: + cleanup_cgroup_environment(); + iters_css__destroy(skel); +} + void test_iters(void) { RUN_TESTS(iters_state_safety); RUN_TESTS(iters_looping); RUN_TESTS(iters); + RUN_TESTS(iters_css_task); if (env.has_testmod) RUN_TESTS(iters_testmod_seq); @@ -103,4 +303,13 @@ void test_iters(void) subtest_num_iters(); if (test__start_subtest("testmod_seq")) subtest_testmod_seq_iters(); + if (test__start_subtest("task_vma")) + subtest_task_vma_iters(); + if (test__start_subtest("task")) + subtest_task_iters(); + if (test__start_subtest("css_task")) + subtest_css_task_iters(); + if (test__start_subtest("css")) + subtest_css_iters(); + RUN_TESTS(iters_task_failure); } diff --git a/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c b/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c index 3f1f58d3a729c444ac1246ed6720bee88a5a0d95..a1f7e7378a64cebb39f11b0c005fdd5785feceed 100644 --- a/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c @@ -29,6 +29,10 @@ static void test_success(void) bpf_program__set_autoload(skel->progs.non_sleepable_1, true); bpf_program__set_autoload(skel->progs.non_sleepable_2, true); bpf_program__set_autoload(skel->progs.task_trusted_non_rcuptr, true); + bpf_program__set_autoload(skel->progs.rcu_read_lock_subprog, true); + bpf_program__set_autoload(skel->progs.rcu_read_lock_global_subprog, true); + bpf_program__set_autoload(skel->progs.rcu_read_lock_subprog_lock, true); + bpf_program__set_autoload(skel->progs.rcu_read_lock_subprog_unlock, true); err = rcu_read_lock__load(skel); if (!ASSERT_OK(err, "skel_load")) goto out; @@ -75,6 +79,8 @@ static const char * const inproper_region_tests[] = { "inproper_sleepable_helper", "inproper_sleepable_kfunc", "nested_rcu_region", + "rcu_read_lock_global_subprog_lock", + "rcu_read_lock_global_subprog_unlock", }; static void test_inproper_region(void) diff --git a/tools/testing/selftests/bpf/prog_tests/spin_lock.c b/tools/testing/selftests/bpf/prog_tests/spin_lock.c index f29c08d93beb1d2b471a59226265ef5878f7e6c3..11814d6b81e4e8295cc8bd9104beb3ed50e1b50b 100644 --- a/tools/testing/selftests/bpf/prog_tests/spin_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/spin_lock.c @@ -48,6 +48,8 @@ static struct { { "lock_id_mismatch_innermapval_kptr", "bpf_spin_unlock of different lock" }, { "lock_id_mismatch_innermapval_global", "bpf_spin_unlock of different lock" }, { "lock_id_mismatch_innermapval_mapval", "bpf_spin_unlock of different lock" }, + { "lock_global_subprog_call1", "global function calls are not allowed while holding a lock" }, + { "lock_global_subprog_call2", "global function calls are not allowed while holding a lock" }, }; static int match_regex(const char *pattern, const char *string) diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_maybe_null.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_maybe_null.c new file mode 100644 index 0000000000000000000000000000000000000000..01dc2613c8a51889352a848e30bdac4558005fbf --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_maybe_null.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include + +#include "struct_ops_maybe_null.skel.h" +#include "struct_ops_maybe_null_fail.skel.h" + +/* Test that the verifier accepts a program that access a nullable pointer + * with a proper check. + */ +static void maybe_null(void) +{ + struct struct_ops_maybe_null *skel; + + skel = struct_ops_maybe_null__open_and_load(); + if (!ASSERT_OK_PTR(skel, "struct_ops_module_open_and_load")) + return; + + struct_ops_maybe_null__destroy(skel); +} + +/* Test that the verifier rejects a program that access a nullable pointer + * without a check beforehand. + */ +static void maybe_null_fail(void) +{ + struct struct_ops_maybe_null_fail *skel; + + skel = struct_ops_maybe_null_fail__open_and_load(); + if (ASSERT_ERR_PTR(skel, "struct_ops_module_fail__open_and_load")) + return; + + struct_ops_maybe_null_fail__destroy(skel); +} + +void test_struct_ops_maybe_null(void) +{ + /* The verifier verifies the programs at load time, so testing both + * programs in the same compile-unit is complicated. We run them in + * separate objects to simplify the testing. + */ + if (test__start_subtest("maybe_null")) + maybe_null(); + if (test__start_subtest("maybe_null_fail")) + maybe_null_fail(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c new file mode 100644 index 0000000000000000000000000000000000000000..7d6facf46ebb21ac01c0880063d6f3735d4fa473 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include +#include + +#include "struct_ops_module.skel.h" + +static void check_map_info(struct bpf_map_info *info) +{ + struct bpf_btf_info btf_info; + char btf_name[256]; + u32 btf_info_len = sizeof(btf_info); + int err, fd; + + fd = bpf_btf_get_fd_by_id(info->btf_vmlinux_id); + if (!ASSERT_GE(fd, 0, "get_value_type_btf_obj_fd")) + return; + + memset(&btf_info, 0, sizeof(btf_info)); + btf_info.name = ptr_to_u64(btf_name); + btf_info.name_len = sizeof(btf_name); + err = bpf_btf_get_info_by_fd(fd, &btf_info, &btf_info_len); + if (!ASSERT_OK(err, "get_value_type_btf_obj_info")) + goto cleanup; + + if (!ASSERT_EQ(strcmp(btf_name, "bpf_testmod"), 0, "get_value_type_btf_obj_name")) + goto cleanup; + +cleanup: + close(fd); +} + +static void test_struct_ops_load(void) +{ + struct struct_ops_module *skel; + struct bpf_map_info info = {}; + struct bpf_link *link; + int err; + u32 len; + + skel = struct_ops_module__open(); + if (!ASSERT_OK_PTR(skel, "struct_ops_module_open")) + return; + + skel->struct_ops.testmod_1->data = 13; + skel->struct_ops.testmod_1->test_2 = skel->progs.test_3; + /* Since test_2() is not being used, it should be disabled from + * auto-loading, or it will fail to load. + */ + bpf_program__set_autoload(skel->progs.test_2, false); + + err = struct_ops_module__load(skel); + if (!ASSERT_OK(err, "struct_ops_module_load")) + goto cleanup; + + len = sizeof(info); + err = bpf_map_get_info_by_fd(bpf_map__fd(skel->maps.testmod_1), &info, + &len); + if (!ASSERT_OK(err, "bpf_map_get_info_by_fd")) + goto cleanup; + + link = bpf_map__attach_struct_ops(skel->maps.testmod_1); + ASSERT_OK_PTR(link, "attach_test_mod_1"); + + /* test_3() will be called from bpf_dummy_reg() in bpf_testmod.c + * + * In bpf_testmod.c it will pass 4 and 13 (the value of data) to + * .test_2. So, the value of test_2_result should be 20 (4 + 13 + + * 3). + */ + ASSERT_EQ(skel->bss->test_2_result, 20, "check_shadow_variables"); + + bpf_link__destroy(link); + + check_map_info(&info); + +cleanup: + struct_ops_module__destroy(skel); +} + +void serial_test_struct_ops_module(void) +{ + if (test__start_subtest("test_struct_ops_load")) + test_struct_ops_load(); +} + diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c index ce2c61d62fc6c1cc00ae08b0545ffa6a4701a1bb..760ad96b4be099ed74779d8895165df5d212f091 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer.c +++ b/tools/testing/selftests/bpf/prog_tests/timer.c @@ -15,6 +15,7 @@ static int timer(struct timer *timer_skel) ASSERT_EQ(timer_skel->data->callback_check, 52, "callback_check1"); ASSERT_EQ(timer_skel->data->callback2_check, 52, "callback2_check1"); + ASSERT_EQ(timer_skel->bss->pinned_callback_check, 0, "pinned_callback_check1"); prog_fd = bpf_program__fd(timer_skel->progs.test1); err = bpf_prog_test_run_opts(prog_fd, &topts); @@ -33,6 +34,9 @@ static int timer(struct timer *timer_skel) /* check that timer_cb3() was executed twice */ ASSERT_EQ(timer_skel->bss->abs_data, 12, "abs_data"); + /* check that timer_cb_pinned() was executed twice */ + ASSERT_EQ(timer_skel->bss->pinned_callback_check, 2, "pinned_callback_check"); + /* check that there were no errors in timer execution */ ASSERT_EQ(timer_skel->bss->err, 0, "err"); diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 5cfa7a6316b63c7ac3e2263ec99f3c9592e038f4..6de0aeebbb4a9efd65789985e0443a2a82af3819 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -25,6 +25,7 @@ #include "verifier_direct_stack_access_wraparound.skel.h" #include "verifier_div0.skel.h" #include "verifier_div_overflow.skel.h" +#include "verifier_global_subprogs.skel.h" #include "verifier_gotol.skel.h" #include "verifier_helper_access_var_len.skel.h" #include "verifier_helper_packet_access.skel.h" @@ -78,6 +79,7 @@ #include "verifier_xadd.skel.h" #include "verifier_xdp.skel.h" #include "verifier_xdp_direct_packet_access.skel.h" +#include "verifier_bits_iter.skel.h" #define MAX_ENTRIES 11 @@ -134,6 +136,7 @@ void test_verifier_direct_packet_access(void) { RUN(verifier_direct_packet_acces void test_verifier_direct_stack_access_wraparound(void) { RUN(verifier_direct_stack_access_wraparound); } void test_verifier_div0(void) { RUN(verifier_div0); } void test_verifier_div_overflow(void) { RUN(verifier_div_overflow); } +void test_verifier_global_subprogs(void) { RUN(verifier_global_subprogs); } void test_verifier_gotol(void) { RUN(verifier_gotol); } void test_verifier_helper_access_var_len(void) { RUN(verifier_helper_access_var_len); } void test_verifier_helper_packet_access(void) { RUN(verifier_helper_packet_access); } @@ -186,6 +189,7 @@ void test_verifier_var_off(void) { RUN(verifier_var_off); } void test_verifier_xadd(void) { RUN(verifier_xadd); } void test_verifier_xdp(void) { RUN(verifier_xdp); } void test_verifier_xdp_direct_packet_access(void) { RUN(verifier_xdp_direct_packet_access); } +void test_verifier_bits_iter(void) { RUN(verifier_bits_iter); } static int init_test_val_map(struct bpf_object *obj, char *map_name) { diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c similarity index 100% rename from tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c rename to tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c similarity index 100% rename from tools/testing/selftests/bpf/progs/bpf_iter_task.c rename to tools/testing/selftests/bpf/progs/bpf_iter_tasks.c diff --git a/tools/testing/selftests/bpf/progs/freplace_dead_global_func.c b/tools/testing/selftests/bpf/progs/freplace_dead_global_func.c new file mode 100644 index 0000000000000000000000000000000000000000..e6a75f86cac64e51f70ee20b977c10f07cf8ccd1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/freplace_dead_global_func.c @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include + +SEC("freplace") +int freplace_prog(void) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/iters_css.c b/tools/testing/selftests/bpf/progs/iters_css.c new file mode 100644 index 0000000000000000000000000000000000000000..ec1f6c2f590bec59ad2ef593b04a3a62d4e85895 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_css.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Chuyi Zhou */ + +#include "vmlinux.h" +#include +#include +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +pid_t target_pid; +u64 root_cg_id, leaf_cg_id; +u64 first_cg_id, last_cg_id; + +int pre_order_cnt, post_order_cnt, tree_high; + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +SEC("fentry.s/" SYS_PREFIX "sys_getpgid") +int iter_css_for_each(const void *ctx) +{ + struct task_struct *cur_task = bpf_get_current_task_btf(); + struct cgroup_subsys_state *root_css, *leaf_css, *pos; + struct cgroup *root_cgrp, *leaf_cgrp, *cur_cgrp; + + if (cur_task->pid != target_pid) + return 0; + + root_cgrp = bpf_cgroup_from_id(root_cg_id); + + if (!root_cgrp) + return 0; + + leaf_cgrp = bpf_cgroup_from_id(leaf_cg_id); + + if (!leaf_cgrp) { + bpf_cgroup_release(root_cgrp); + return 0; + } + root_css = &root_cgrp->self; + leaf_css = &leaf_cgrp->self; + pre_order_cnt = post_order_cnt = tree_high = 0; + first_cg_id = last_cg_id = 0; + + bpf_rcu_read_lock(); + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) { + cur_cgrp = pos->cgroup; + post_order_cnt++; + last_cg_id = cur_cgrp->kn->id; + } + + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_PRE) { + cur_cgrp = pos->cgroup; + pre_order_cnt++; + if (!first_cg_id) + first_cg_id = cur_cgrp->kn->id; + } + + bpf_for_each(css, pos, leaf_css, BPF_CGROUP_ITER_ANCESTORS_UP) + tree_high++; + + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_ANCESTORS_UP) + tree_high--; + bpf_rcu_read_unlock(); + bpf_cgroup_release(root_cgrp); + bpf_cgroup_release(leaf_cgrp); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/iters_css_task.c b/tools/testing/selftests/bpf/progs/iters_css_task.c new file mode 100644 index 0000000000000000000000000000000000000000..9ac758649cb8ccd0af666a865ea314c9e7fa5819 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_css_task.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Chuyi Zhou */ + +#include "vmlinux.h" +#include +#include +#include +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym; +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; + +pid_t target_pid; +int css_task_cnt; +u64 cg_id; + +SEC("lsm/file_mprotect") +int BPF_PROG(iter_css_task_for_each, struct vm_area_struct *vma, + unsigned long reqprot, unsigned long prot, int ret) +{ + struct task_struct *cur_task = bpf_get_current_task_btf(); + struct cgroup_subsys_state *css; + struct task_struct *task; + struct cgroup *cgrp; + + if (cur_task->pid != target_pid) + return ret; + + cgrp = bpf_cgroup_from_id(cg_id); + + if (!cgrp) + return -EPERM; + + css = &cgrp->self; + css_task_cnt = 0; + + bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) + if (task->pid == target_pid) + css_task_cnt++; + + bpf_cgroup_release(cgrp); + + return -EPERM; +} + +static inline u64 cgroup_id(struct cgroup *cgrp) +{ + return cgrp->kn->id; +} + +SEC("?iter/cgroup") +int cgroup_id_printer(struct bpf_iter__cgroup *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct cgroup *cgrp = ctx->cgroup; + struct cgroup_subsys_state *css; + struct task_struct *task; + + /* epilogue */ + if (cgrp == NULL) { + BPF_SEQ_PRINTF(seq, "epilogue\n"); + return 0; + } + + /* prologue */ + if (ctx->meta->seq_num == 0) + BPF_SEQ_PRINTF(seq, "prologue\n"); + + BPF_SEQ_PRINTF(seq, "%8llu\n", cgroup_id(cgrp)); + + css = &cgrp->self; + css_task_cnt = 0; + bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) { + if (task->pid == target_pid) + css_task_cnt++; + } + + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int BPF_PROG(iter_css_task_for_each_sleep) +{ + u64 cgrp_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp = bpf_cgroup_from_id(cgrp_id); + struct cgroup_subsys_state *css; + struct task_struct *task; + + if (cgrp == NULL) + return 0; + css = &cgrp->self; + + bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) { + + } + bpf_cgroup_release(cgrp); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/iters_task.c b/tools/testing/selftests/bpf/progs/iters_task.c new file mode 100644 index 0000000000000000000000000000000000000000..c9b4055cd410ae6378066e28e2f41c9b23d47ab1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_task.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Chuyi Zhou */ + +#include "vmlinux.h" +#include +#include +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +pid_t target_pid; +int procs_cnt, threads_cnt, proc_threads_cnt; + +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +SEC("fentry.s/" SYS_PREFIX "sys_getpgid") +int iter_task_for_each_sleep(void *ctx) +{ + struct task_struct *cur_task = bpf_get_current_task_btf(); + struct task_struct *pos; + + if (cur_task->pid != target_pid) + return 0; + procs_cnt = threads_cnt = proc_threads_cnt = 0; + + bpf_rcu_read_lock(); + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) + if (pos->pid == target_pid) + procs_cnt++; + + bpf_for_each(task, pos, cur_task, BPF_TASK_ITER_PROC_THREADS) + proc_threads_cnt++; + + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_THREADS) + if (pos->tgid == target_pid) + threads_cnt++; + bpf_rcu_read_unlock(); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/iters_task_failure.c b/tools/testing/selftests/bpf/progs/iters_task_failure.c new file mode 100644 index 0000000000000000000000000000000000000000..6b1588d706527321f15cfa2dae9e900bd4393bea --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_task_failure.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Chuyi Zhou */ + +#include "vmlinux.h" +#include +#include +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("expected an RCU CS when using bpf_iter_task_next") +int BPF_PROG(iter_tasks_without_lock) +{ + struct task_struct *pos; + + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) { + + } + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("expected an RCU CS when using bpf_iter_css_next") +int BPF_PROG(iter_css_without_lock) +{ + u64 cg_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp = bpf_cgroup_from_id(cg_id); + struct cgroup_subsys_state *root_css, *pos; + + if (!cgrp) + return 0; + root_css = &cgrp->self; + + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) { + + } + bpf_cgroup_release(cgrp); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("expected an RCU CS when using bpf_iter_task_next") +int BPF_PROG(iter_tasks_lock_and_unlock) +{ + struct task_struct *pos; + + bpf_rcu_read_lock(); + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) { + bpf_rcu_read_unlock(); + + bpf_rcu_read_lock(); + } + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("expected an RCU CS when using bpf_iter_css_next") +int BPF_PROG(iter_css_lock_and_unlock) +{ + u64 cg_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp = bpf_cgroup_from_id(cg_id); + struct cgroup_subsys_state *root_css, *pos; + + if (!cgrp) + return 0; + root_css = &cgrp->self; + + bpf_rcu_read_lock(); + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) { + bpf_rcu_read_unlock(); + + bpf_rcu_read_lock(); + } + bpf_rcu_read_unlock(); + bpf_cgroup_release(cgrp); + return 0; +} + +SEC("?fentry/" SYS_PREFIX "sys_getpgid") +__failure __msg("css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs") +int BPF_PROG(iter_css_task_for_each) +{ + u64 cg_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp = bpf_cgroup_from_id(cg_id); + struct cgroup_subsys_state *css; + struct task_struct *task; + + if (cgrp == NULL) + return 0; + css = &cgrp->self; + + bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) { + + } + bpf_cgroup_release(cgrp); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/iters_task_vma.c b/tools/testing/selftests/bpf/progs/iters_task_vma.c new file mode 100644 index 0000000000000000000000000000000000000000..6812015bfb97d44a279cbaf73455877ad942b0c2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_task_vma.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include "bpf_experimental.h" +#include +#include "bpf_misc.h" + +pid_t target_pid = 0; +unsigned int vmas_seen = 0; + +struct { + __u64 vm_start; + __u64 vm_end; +} vm_ranges[1000]; + +SEC("raw_tp/sys_enter") +int iter_task_vma_for_each(const void *ctx) +{ + struct task_struct *task = bpf_get_current_task_btf(); + struct vm_area_struct *vma; + unsigned int seen = 0; + + if (task->pid != target_pid) + return 0; + + if (vmas_seen) + return 0; + + bpf_for_each(task_vma, vma, task, 0) { + /* + * Hack code here: + * the compiler will assign the variable 'seen' + * and the array index to different, unrelated + * registers. As a result, the verifier will + * reject the code due to potential out-of-bounds + * access to the vm_ranges array. However, by + * multiplying both sides of the inequality by 16, + * we can ensure the code passes the verification + * test. + */ + if (seen * 16 >= 16000) + break; + + vm_ranges[seen].vm_start = vma->vm_start; + vm_ranges[seen].vm_end = vma->vm_end; + seen++; + } + + vmas_seen = seen; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c index 3873fb6c292a1768b4a2ef1e2ba451da0f89c229..4a176e6aede897a760ca8246e4ec63f7efcb6ffe 100644 --- a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c +++ b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c @@ -12,6 +12,7 @@ struct bpf_iter_testmod_seq { extern int bpf_iter_testmod_seq_new(struct bpf_iter_testmod_seq *it, s64 value, int cnt) __ksym; extern s64 *bpf_iter_testmod_seq_next(struct bpf_iter_testmod_seq *it) __ksym; +extern s64 bpf_iter_testmod_seq_value(int blah, struct bpf_iter_testmod_seq *it) __ksym; extern void bpf_iter_testmod_seq_destroy(struct bpf_iter_testmod_seq *it) __ksym; const volatile __s64 exp_empty = 0 + 1; @@ -76,4 +77,53 @@ int testmod_seq_truncated(const void *ctx) return 0; } +SEC("?raw_tp") +__failure +__msg("expected an initialized iter_testmod_seq as arg #2") +int testmod_seq_getter_before_bad(const void *ctx) +{ + struct bpf_iter_testmod_seq it; + + return bpf_iter_testmod_seq_value(0, &it); +} + +SEC("?raw_tp") +__failure +__msg("expected an initialized iter_testmod_seq as arg #2") +int testmod_seq_getter_after_bad(const void *ctx) +{ + struct bpf_iter_testmod_seq it; + s64 sum = 0, *v; + + bpf_iter_testmod_seq_new(&it, 100, 100); + + while ((v = bpf_iter_testmod_seq_next(&it))) { + sum += *v; + } + + bpf_iter_testmod_seq_destroy(&it); + + return sum + bpf_iter_testmod_seq_value(0, &it); +} + +SEC("?socket") +__success __retval(1000000) +int testmod_seq_getter_good(const void *ctx) +{ + struct bpf_iter_testmod_seq it; + s64 sum = 0, *v; + + bpf_iter_testmod_seq_new(&it, 100, 100); + + while ((v = bpf_iter_testmod_seq_next(&it))) { + sum += *v; + } + + sum *= bpf_iter_testmod_seq_value(0, &it); + + bpf_iter_testmod_seq_destroy(&it); + + return sum; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c b/tools/testing/selftests/bpf/progs/rcu_read_lock.c index 14fb01437fb8db7b88264370aafe995139ef3f57..ab3a532b7dd6d28ade18760117716fbdd8656ce5 100644 --- a/tools/testing/selftests/bpf/progs/rcu_read_lock.c +++ b/tools/testing/selftests/bpf/progs/rcu_read_lock.c @@ -319,3 +319,123 @@ int cross_rcu_region(void *ctx) bpf_rcu_read_unlock(); return 0; } + +__noinline +static int static_subprog(void *ctx) +{ + volatile int ret = 0; + + if (bpf_get_prandom_u32()) + return ret + 42; + return ret + bpf_get_prandom_u32(); +} + +__noinline +int global_subprog(u64 a) +{ + volatile int ret = a; + + return ret + static_subprog(NULL); +} + +__noinline +static int static_subprog_lock(void *ctx) +{ + volatile int ret = 0; + + bpf_rcu_read_lock(); + if (bpf_get_prandom_u32()) + return ret + 42; + return ret + bpf_get_prandom_u32(); +} + +__noinline +int global_subprog_lock(u64 a) +{ + volatile int ret = a; + + return ret + static_subprog_lock(NULL); +} + +__noinline +static int static_subprog_unlock(void *ctx) +{ + volatile int ret = 0; + + bpf_rcu_read_unlock(); + if (bpf_get_prandom_u32()) + return ret + 42; + return ret + bpf_get_prandom_u32(); +} + +__noinline +int global_subprog_unlock(u64 a) +{ + volatile int ret = a; + + return ret + static_subprog_unlock(NULL); +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int rcu_read_lock_subprog(void *ctx) +{ + volatile int ret = 0; + + bpf_rcu_read_lock(); + if (bpf_get_prandom_u32()) + ret += static_subprog(ctx); + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int rcu_read_lock_global_subprog(void *ctx) +{ + volatile int ret = 0; + + bpf_rcu_read_lock(); + if (bpf_get_prandom_u32()) + ret += global_subprog(ret); + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int rcu_read_lock_subprog_lock(void *ctx) +{ + volatile int ret = 0; + + ret += static_subprog_lock(ctx); + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int rcu_read_lock_global_subprog_lock(void *ctx) +{ + volatile int ret = 0; + + ret += global_subprog_lock(ret); + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int rcu_read_lock_subprog_unlock(void *ctx) +{ + volatile int ret = 0; + + bpf_rcu_read_lock(); + ret += static_subprog_unlock(ctx); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int rcu_read_lock_global_subprog_unlock(void *ctx) +{ + volatile int ret = 0; + + bpf_rcu_read_lock(); + ret += global_subprog_unlock(ret); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c new file mode 100644 index 0000000000000000000000000000000000000000..b450f72e744ad22a78d98bc3b539527abc7e01c6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include +#include +#include "../bpf_testmod/bpf_testmod.h" + +char _license[] SEC("license") = "GPL"; + +pid_t tgid = 0; + +/* This is a test BPF program that uses struct_ops to access an argument + * that may be NULL. This is a test for the verifier to ensure that it can + * rip PTR_MAYBE_NULL correctly. + */ +SEC("struct_ops/test_maybe_null") +int BPF_PROG(test_maybe_null, int dummy, + struct task_struct *task) +{ + if (task) + tgid = task->tgid; + + return 0; +} + +SEC(".struct_ops.link") +struct bpf_testmod_ops testmod_1 = { + .test_maybe_null = (void *)test_maybe_null, +}; + diff --git a/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c new file mode 100644 index 0000000000000000000000000000000000000000..6283099ec383a38bb11c47c6c8f9d51c6dd220e0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include +#include +#include "../bpf_testmod/bpf_testmod.h" + +char _license[] SEC("license") = "GPL"; + +pid_t tgid = 0; + +SEC("struct_ops/test_maybe_null_struct_ptr") +int BPF_PROG(test_maybe_null_struct_ptr, int dummy, + struct task_struct *task) +{ + tgid = task->tgid; + + return 0; +} + +SEC(".struct_ops.link") +struct bpf_testmod_ops testmod_struct_ptr = { + .test_maybe_null = (void *)test_maybe_null_struct_ptr, +}; + diff --git a/tools/testing/selftests/bpf/progs/struct_ops_module.c b/tools/testing/selftests/bpf/progs/struct_ops_module.c new file mode 100644 index 0000000000000000000000000000000000000000..25952fa093482fa2d89e36510460f5119d48f5e8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_module.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include +#include +#include +#include "../bpf_testmod/bpf_testmod.h" + +char _license[] SEC("license") = "GPL"; + +int test_2_result = 0; + +SEC("struct_ops/test_1") +int BPF_PROG(test_1) +{ + return 0xdeadbeef; +} + +SEC("struct_ops/test_2") +void BPF_PROG(test_2, int a, int b) +{ + test_2_result = a + b; +} + +SEC("struct_ops/test_3") +int BPF_PROG(test_3, int a, int b) +{ + test_2_result = a + b + 3; + return a + b + 3; +} + +SEC(".struct_ops.link") +struct bpf_testmod_ops testmod_1 = { + .test_1 = (void *)test_1, + .test_2 = (void *)test_2, + .data = 0x1, +}; + diff --git a/tools/testing/selftests/bpf/progs/test_global_func12.c b/tools/testing/selftests/bpf/progs/test_global_func12.c index 7f159d83c6f673f78f3b7c89e9ce7e1cfffdeef4..6e03d42519a675398011c76e069f674baf4307a6 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func12.c +++ b/tools/testing/selftests/bpf/progs/test_global_func12.c @@ -19,5 +19,7 @@ int global_func12(struct __sk_buff *skb) { const struct S s = {.x = skb->len }; - return foo(&s); + foo(&s); + + return 1; } diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock.c b/tools/testing/selftests/bpf/progs/test_spin_lock.c index b2440a0ff422a395eef70ba7edca75dd7c9deb1f..d8d77bdffd3d262b5c0d466a183628649003a283 100644 --- a/tools/testing/selftests/bpf/progs/test_spin_lock.c +++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c @@ -101,4 +101,69 @@ int bpf_spin_lock_test(struct __sk_buff *skb) err: return err; } + +struct bpf_spin_lock lockA __hidden SEC(".data.A"); + +__noinline +static int static_subprog(struct __sk_buff *ctx) +{ + volatile int ret = 0; + + if (ctx->protocol) + return ret; + return ret + ctx->len; +} + +__noinline +static int static_subprog_lock(struct __sk_buff *ctx) +{ + volatile int ret = 0; + + ret = static_subprog(ctx); + bpf_spin_lock(&lockA); + return ret + ctx->len; +} + +__noinline +static int static_subprog_unlock(struct __sk_buff *ctx) +{ + volatile int ret = 0; + + ret = static_subprog(ctx); + bpf_spin_unlock(&lockA); + return ret + ctx->len; +} + +SEC("tc") +int lock_static_subprog_call(struct __sk_buff *ctx) +{ + int ret = 0; + + bpf_spin_lock(&lockA); + if (ctx->mark == 42) + ret = static_subprog(ctx); + bpf_spin_unlock(&lockA); + return ret; +} + +SEC("tc") +int lock_static_subprog_lock(struct __sk_buff *ctx) +{ + int ret = 0; + + ret = static_subprog_lock(ctx); + bpf_spin_unlock(&lockA); + return ret; +} + +SEC("tc") +int lock_static_subprog_unlock(struct __sk_buff *ctx) +{ + int ret = 0; + + bpf_spin_lock(&lockA); + ret = static_subprog_unlock(ctx); + return ret; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c index 293ac1049d38893a8ca11d5a3d82a8d6ace74942..1c8b678e2e9a397786bb02d3de559b3ae50205cf 100644 --- a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c +++ b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c @@ -201,4 +201,48 @@ CHECK(innermapval_mapval, &iv->lock, &v->lock); #undef CHECK +__noinline +int global_subprog(struct __sk_buff *ctx) +{ + volatile int ret = 0; + + if (ctx->protocol) + ret += ctx->protocol; + return ret + ctx->mark; +} + +__noinline +static int static_subprog_call_global(struct __sk_buff *ctx) +{ + volatile int ret = 0; + + if (ctx->protocol) + return ret; + return ret + ctx->len + global_subprog(ctx); +} + +SEC("?tc") +int lock_global_subprog_call1(struct __sk_buff *ctx) +{ + int ret = 0; + + bpf_spin_lock(&lockA); + if (ctx->mark == 42) + ret = global_subprog(ctx); + bpf_spin_unlock(&lockA); + return ret; +} + +SEC("?tc") +int lock_global_subprog_call2(struct __sk_buff *ctx) +{ + int ret = 0; + + bpf_spin_lock(&lockA); + if (ctx->mark == 42) + ret = static_subprog_call_global(ctx); + bpf_spin_unlock(&lockA); + return ret; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/timer.c b/tools/testing/selftests/bpf/progs/timer.c index 9a16d95213e11527c15cfb44b4fef8d9415f47fa..8b946c8188c65d10ed86de886ea9aead585de86d 100644 --- a/tools/testing/selftests/bpf/progs/timer.c +++ b/tools/testing/selftests/bpf/progs/timer.c @@ -51,7 +51,7 @@ struct { __uint(max_entries, 1); __type(key, int); __type(value, struct elem); -} abs_timer SEC(".maps"); +} abs_timer SEC(".maps"), soft_timer_pinned SEC(".maps"), abs_timer_pinned SEC(".maps"); __u64 bss_data; __u64 abs_data; @@ -59,6 +59,8 @@ __u64 err; __u64 ok; __u64 callback_check = 52; __u64 callback2_check = 52; +__u64 pinned_callback_check; +__s32 pinned_cpu; #define ARRAY 1 #define HTAB 2 @@ -329,3 +331,62 @@ int BPF_PROG2(test3, int, a) return 0; } + +/* callback for pinned timer */ +static int timer_cb_pinned(void *map, int *key, struct bpf_timer *timer) +{ + __s32 cpu = bpf_get_smp_processor_id(); + + if (cpu != pinned_cpu) + err |= 16384; + + pinned_callback_check++; + return 0; +} + +static void test_pinned_timer(bool soft) +{ + int key = 0; + void *map; + struct bpf_timer *timer; + __u64 flags = BPF_F_TIMER_CPU_PIN; + __u64 start_time; + + if (soft) { + map = &soft_timer_pinned; + start_time = 0; + } else { + map = &abs_timer_pinned; + start_time = bpf_ktime_get_boot_ns(); + flags |= BPF_F_TIMER_ABS; + } + + timer = bpf_map_lookup_elem(map, &key); + if (timer) { + if (bpf_timer_init(timer, map, CLOCK_BOOTTIME) != 0) + err |= 4096; + bpf_timer_set_callback(timer, timer_cb_pinned); + pinned_cpu = bpf_get_smp_processor_id(); + bpf_timer_start(timer, start_time + 1000, flags); + } else { + err |= 8192; + } +} + +SEC("fentry/bpf_fentry_test4") +int BPF_PROG2(test4, int, a) +{ + bpf_printk("test4"); + test_pinned_timer(true); + + return 0; +} + +SEC("fentry/bpf_fentry_test5") +int BPF_PROG2(test5, int, a) +{ + bpf_printk("test5"); + test_pinned_timer(false); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c new file mode 100644 index 0000000000000000000000000000000000000000..b6b018baed4633394c785fdb68a7594077ebc48d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c @@ -0,0 +1,232 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2024 Yafang Shao */ + +#include "vmlinux.h" +#include +#include + +#include "bpf_misc.h" +#include "task_kfunc_common.h" + +char _license[] SEC("license") = "GPL"; + +int bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, + u32 nr_bits) __ksym __weak; +int *bpf_iter_bits_next(struct bpf_iter_bits *it) __ksym __weak; +void bpf_iter_bits_destroy(struct bpf_iter_bits *it) __ksym __weak; + +u64 bits_array[511] = {}; + +SEC("iter.s/cgroup") +__description("bits iter without destroy") +__failure __msg("Unreleased reference") +int BPF_PROG(no_destroy, struct bpf_iter_meta *meta, struct cgroup *cgrp) +{ + struct bpf_iter_bits it; + u64 data = 1; + + bpf_iter_bits_new(&it, &data, 1); + bpf_iter_bits_next(&it); + return 0; +} + +SEC("iter/cgroup") +__description("uninitialized iter in ->next()") +__failure __msg("expected an initialized iter_bits as arg #1") +int BPF_PROG(next_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp) +{ + struct bpf_iter_bits *it = NULL; + + bpf_iter_bits_next(it); + return 0; +} + +SEC("iter/cgroup") +__description("uninitialized iter in ->destroy()") +__failure __msg("expected an initialized iter_bits as arg #1") +int BPF_PROG(destroy_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp) +{ + struct bpf_iter_bits it = {}; + + bpf_iter_bits_destroy(&it); + return 0; +} + +SEC("syscall") +__description("null pointer") +__success __retval(0) +int null_pointer(void) +{ + struct bpf_iter_bits iter; + int err, nr = 0; + int *bit; + + err = bpf_iter_bits_new(&iter, NULL, 1); + bpf_iter_bits_destroy(&iter); + if (err != -EINVAL) + return 1; + + bpf_for_each(bits, bit, NULL, 1) + nr++; + return nr; +} + +SEC("syscall") +__description("bits copy") +__success __retval(10) +int bits_copy(void) +{ + u64 data = 0xf7310UL; /* 4 + 3 + 2 + 1 + 0*/ + int nr = 0; + int *bit; + + bpf_for_each(bits, bit, &data, 1) + nr++; + return nr; +} + +SEC("syscall") +__description("bits memalloc") +__success __retval(64) +int bits_memalloc(void) +{ + u64 data[2]; + int nr = 0; + int *bit; + + __builtin_memset(&data, 0xf0, sizeof(data)); /* 4 * 16 */ + bpf_for_each(bits, bit, &data[0], sizeof(data) / sizeof(u64)) + nr++; + return nr; +} + +SEC("syscall") +__description("bit index") +__success __retval(8) +int bit_index(void) +{ + u64 data = 0x100; + int bit_idx = 0; + int *bit; + + bpf_for_each(bits, bit, &data, 1) { + if (*bit == 0) + continue; + bit_idx = *bit; + } + return bit_idx; +} + +SEC("syscall") +__description("bits too big") +__success __retval(0) +int bits_too_big(void) +{ + u64 data[4]; + int nr = 0; + int *bit; + + __builtin_memset(&data, 0xff, sizeof(data)); + bpf_for_each(bits, bit, &data[0], 512) /* Be greater than 511 */ + nr++; + return nr; +} + +SEC("syscall") +__description("fewer words") +__success __retval(1) +int fewer_words(void) +{ + u64 data[2] = {0x1, 0xff}; + int nr = 0; + int *bit; + + bpf_for_each(bits, bit, &data[0], 1) + nr++; + return nr; +} + +SEC("syscall") +__description("zero words") +__success __retval(0) +int zero_words(void) +{ + u64 data[2] = {0x1, 0xff}; + int nr = 0; + int *bit; + + bpf_for_each(bits, bit, &data[0], 0) + nr++; + return nr; +} + +SEC("syscall") +__description("huge words") +__success __retval(0) +int huge_words(void) +{ + u64 data[8] = {0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1}; + int nr = 0; + int *bit; + + bpf_for_each(bits, bit, &data[0], 67108865) + nr++; + return nr; +} + +SEC("syscall") +__description("max words") +__success __retval(4) +int max_words(void) +{ + volatile int nr = 0; + int *bit; + + bits_array[0] = (1ULL << 63) | 1U; + bits_array[510] = (1ULL << 33) | (1ULL << 32); + + bpf_for_each(bits, bit, bits_array, 511) { + if (nr == 0 && *bit != 0) + break; + if (nr == 2 && *bit != 32672) + break; + nr++; + } + return nr; +} + +SEC("syscall") +__description("bad words") +__success __retval(0) +int bad_words(void) +{ + void *bad_addr = (void *)-4095; + struct bpf_iter_bits iter; + volatile int nr; + int *bit; + int err; + + err = bpf_iter_bits_new(&iter, bad_addr, 1); + bpf_iter_bits_destroy(&iter); + if (err != -EFAULT) + return 1; + + nr = 0; + bpf_for_each(bits, bit, bad_addr, 1) + nr++; + if (nr != 0) + return 2; + + err = bpf_iter_bits_new(&iter, bad_addr, 4); + bpf_iter_bits_destroy(&iter); + if (err != -EFAULT) + return 3; + + nr = 0; + bpf_for_each(bits, bit, bad_addr, 4) + nr++; + if (nr != 0) + return 4; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c new file mode 100644 index 0000000000000000000000000000000000000000..bd696a431244814033b37e34049d2ec440945674 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include +#include +#include +#include +#include +#include "bpf_misc.h" + +int arr[1]; +int unkn_idx; +const volatile bool call_dead_subprog = false; + +__noinline long global_bad(void) +{ + return arr[unkn_idx]; /* BOOM */ +} + +__noinline long global_good(void) +{ + return arr[0]; +} + +__noinline long global_calls_bad(void) +{ + return global_good() + global_bad() /* does BOOM indirectly */; +} + +__noinline long global_calls_good_only(void) +{ + return global_good(); +} + +__noinline long global_dead(void) +{ + return arr[0] * 2; +} + +SEC("?raw_tp") +__success __log_level(2) +/* main prog is validated completely first */ +__msg("('global_calls_good_only') is global and assumed valid.") +/* eventually global_good() is transitively validated as well */ +__msg("Validating global_good() func") +__msg("('global_good') is safe for any args that match its prototype") +int chained_global_func_calls_success(void) +{ + int sum = 0; + + if (call_dead_subprog) + sum += global_dead(); + return global_calls_good_only() + sum; +} + +SEC("?raw_tp") +__failure __log_level(2) +/* main prog validated successfully first */ +__msg("('global_calls_bad') is global and assumed valid.") +/* eventually we validate global_bad() and fail */ +__msg("Validating global_bad() func") +__msg("math between map_value pointer and register") /* BOOM */ +int chained_global_func_calls_bad(void) +{ + return global_calls_bad(); +} + +/* do out of bounds access forcing verifier to fail verification if this + * global func is called + */ +__noinline int global_unsupp(const int *mem) +{ + if (!mem) + return 0; + return mem[100]; /* BOOM */ +} + +const volatile bool skip_unsupp_global = true; + +SEC("?raw_tp") +__success +int guarded_unsupp_global_called(void) +{ + if (!skip_unsupp_global) + return global_unsupp(NULL); + return 0; +} + +SEC("?raw_tp") +__failure __log_level(2) +__msg("Func#1 ('global_unsupp') is global and assumed valid.") +__msg("Validating global_unsupp() func#1...") +__msg("value is outside of the allowed memory range") +int unguarded_unsupp_global_called(void) +{ + int x = 0; + + return global_unsupp(&x); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_spin_lock.c b/tools/testing/selftests/bpf/progs/verifier_spin_lock.c index 9c1aa69650f8e1f459d544ce1213d521dddbf830..fb316c080c849125ed744da0bb65581c7e75086e 100644 --- a/tools/testing/selftests/bpf/progs/verifier_spin_lock.c +++ b/tools/testing/selftests/bpf/progs/verifier_spin_lock.c @@ -330,7 +330,7 @@ l1_%=: r7 = r0; \ SEC("cgroup/skb") __description("spin_lock: test10 lock in subprog without unlock") -__failure __msg("unlock is missing") +__success __failure_unpriv __msg_unpriv("") __naked void lock_in_subprog_without_unlock(void) { diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c index 4b8b0f45d17d7169de40362d17936ff4bb8ffb8b..83d187de7f6b4384ae3317d614a53d93c61b9357 100644 --- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -370,12 +370,10 @@ __naked int parent_stack_slot_precise(void) SEC("?raw_tp") __success __log_level(2) __msg("9: (0f) r1 += r6") -__msg("mark_precise: frame0: last_idx 9 first_idx 6") +__msg("mark_precise: frame0: last_idx 9 first_idx 0") __msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7") __msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4") __msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)") -__msg("mark_precise: frame0: parent state regs= stack=-8:") -__msg("mark_precise: frame0: last_idx 5 first_idx 0") __msg("mark_precise: frame0: regs= stack=-8 before 5: (85) call pc+6") __msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0") __msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6") diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c index b4edd845493451c224940287e3c19d6c64b1c2fb..bd858cf08e8fc8223b0db9aa1587899add65143c 100644 --- a/tools/testing/selftests/bpf/test_loader.c +++ b/tools/testing/selftests/bpf/test_loader.c @@ -480,7 +480,7 @@ static bool is_unpriv_capable_map(struct bpf_map *map) } } -static int do_prog_test_run(int fd_prog, int *retval) +static int do_prog_test_run(int fd_prog, int *retval, bool empty_opts) { __u8 tmp_out[TEST_DATA_LEN << 2] = {}; __u8 tmp_in[TEST_DATA_LEN] = {}; @@ -493,6 +493,10 @@ static int do_prog_test_run(int fd_prog, int *retval) .repeat = 1, ); + if (empty_opts) { + memset(&topts, 0, sizeof(struct bpf_test_run_opts)); + topts.sz = sizeof(struct bpf_test_run_opts); + } err = bpf_prog_test_run_opts(fd_prog, &topts); saved_errno = errno; @@ -625,7 +629,8 @@ void run_subtest(struct test_loader *tester, } } - do_prog_test_run(bpf_program__fd(tprog), &retval); + do_prog_test_run(bpf_program__fd(tprog), &retval, + bpf_program__type(tprog) == BPF_PROG_TYPE_SYSCALL ? true : false); if (retval != subspec->retval && subspec->retval != POINTER_VALUE) { PRINT_FAIL("Unexpected retval: %d != %d\n", retval, subspec->retval); goto tobj_cleanup; diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index e0dd101c9f2bd4258886f37d83bfb81cb479902c..faefa19308863eb9203681622a914e64e2c03a78 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -1400,13 +1400,19 @@ static void test_map_stress(void) #define MAX_DELAY_US 50000 #define MIN_DELAY_RANGE_US 5000 -static int map_update_retriable(int map_fd, const void *key, const void *value, - int flags, int attempts) +static bool can_retry(int err) +{ + return (err == EAGAIN || err == EBUSY || + (err == ENOMEM && map_opts.map_flags == BPF_F_NO_PREALLOC)); +} + +int map_update_retriable(int map_fd, const void *key, const void *value, int flags, int attempts, + retry_for_error_fn need_retry) { int delay = rand() % MIN_DELAY_RANGE_US; while (bpf_map_update_elem(map_fd, key, value, flags)) { - if (!attempts || (errno != EAGAIN && errno != EBUSY)) + if (!attempts || !need_retry(errno)) return -errno; if (delay <= MAX_DELAY_US / 2) @@ -1449,11 +1455,13 @@ static void test_update_delete(unsigned int fn, void *data) key = value = i; if (do_update) { - err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES); + err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES, + can_retry); if (err) printf("error %d %d\n", err, errno); assert(err == 0); - err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES); + err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES, + can_retry); if (err) printf("error %d %d\n", err, errno); assert(err == 0); diff --git a/tools/testing/selftests/bpf/test_maps.h b/tools/testing/selftests/bpf/test_maps.h index f6fbca761732f9db137964fb5cefdd8308fb1bee..e4ac704a536c1a28bcdc4ddaaf0156eccfceabc7 100644 --- a/tools/testing/selftests/bpf/test_maps.h +++ b/tools/testing/selftests/bpf/test_maps.h @@ -4,6 +4,7 @@ #include #include +#include #define CHECK(condition, tag, format...) ({ \ int __ret = !!(condition); \ @@ -16,4 +17,8 @@ extern int skips; +typedef bool (*retry_for_error_fn)(int err); +int map_update_retriable(int map_fd, const void *key, const void *value, int flags, int attempts, + retry_for_error_fn need_retry); + #endif diff --git a/tools/testing/selftests/sched_ext/.gitignore b/tools/testing/selftests/sched_ext/.gitignore new file mode 100644 index 0000000000000000000000000000000000000000..ae5491a114c09021cd935f552769265d370581a0 --- /dev/null +++ b/tools/testing/selftests/sched_ext/.gitignore @@ -0,0 +1,6 @@ +* +!*.c +!*.h +!Makefile +!.gitignore +!config diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile new file mode 100644 index 0000000000000000000000000000000000000000..0117622246007fda57f7fcec8ff71b4c6a351f95 --- /dev/null +++ b/tools/testing/selftests/sched_ext/Makefile @@ -0,0 +1,211 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2022 Meta Platforms, Inc. and affiliates. +include ../../../build/Build.include +include ../../../scripts/Makefile.arch +include ../../../scripts/Makefile.include + +TEST_GEN_PROGS := runner + +# override lib.mk's default rules +OVERRIDE_TARGETS := 1 +include ../lib.mk + +CURDIR := $(abspath .) +REPOROOT := $(abspath ../../../..) +TOOLSDIR := $(REPOROOT)/tools +LIBDIR := $(TOOLSDIR)/lib +BPFDIR := $(LIBDIR)/bpf +TOOLSINCDIR := $(TOOLSDIR)/include +BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool +APIDIR := $(TOOLSINCDIR)/uapi +GENDIR := $(REPOROOT)/include/generated +GENHDR := $(GENDIR)/autoconf.h +SCXTOOLSDIR := $(TOOLSDIR)/sched_ext +SCXTOOLSINCDIR := $(TOOLSDIR)/sched_ext/include + +OUTPUT_DIR := $(OUTPUT)/build +OBJ_DIR := $(OUTPUT_DIR)/obj +INCLUDE_DIR := $(OUTPUT_DIR)/include +BPFOBJ_DIR := $(OBJ_DIR)/libbpf +SCXOBJ_DIR := $(OBJ_DIR)/sched_ext +BPFOBJ := $(BPFOBJ_DIR)/libbpf.a +LIBBPF_OUTPUT := $(OBJ_DIR)/libbpf/libbpf.a + +DEFAULT_BPFTOOL := $(OUTPUT_DIR)/host/sbin/bpftool +HOST_OBJ_DIR := $(OBJ_DIR)/host/bpftool +HOST_LIBBPF_OUTPUT := $(OBJ_DIR)/host/libbpf/ +HOST_LIBBPF_DESTDIR := $(OUTPUT_DIR)/host/ +HOST_DESTDIR := $(OUTPUT_DIR)/host/ + +VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ + $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ + ../../../../vmlinux \ + /sys/kernel/btf/vmlinux \ + /boot/vmlinux-$(shell uname -r) +VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) +ifeq ($(VMLINUX_BTF),) +$(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)") +endif + +BPFTOOL ?= $(DEFAULT_BPFTOOL) + +ifneq ($(wildcard $(GENHDR)),) + GENFLAGS := -DHAVE_GENHDR +endif + +CFLAGS += -g -O2 -rdynamic -pthread -Wall -Werror $(GENFLAGS) \ + -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ + -I$(TOOLSINCDIR) -I$(APIDIR) -I$(CURDIR)/include -I$(SCXTOOLSINCDIR) + +# Silence some warnings when compiled with clang +ifneq ($(LLVM),) +CFLAGS += -Wno-unused-command-line-argument +endif + +LDFLAGS = -lelf -lz -lpthread -lzstd + +IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - &1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) $(2) -dM -E - $@ +else + $(call msg,CP,,$@) + $(Q)cp "$(VMLINUX_H)" $@ +endif + +$(SCXOBJ_DIR)/%.bpf.o: %.bpf.c $(INCLUDE_DIR)/vmlinux.h | $(BPFOBJ) $(SCXOBJ_DIR) + $(call msg,CLNG-BPF,,$(notdir $@)) + $(Q)$(CLANG) $(BPF_CFLAGS) -target bpf -c $< -o $@ + +$(INCLUDE_DIR)/%.bpf.skel.h: $(SCXOBJ_DIR)/%.bpf.o $(INCLUDE_DIR)/vmlinux.h $(BPFTOOL) | $(INCLUDE_DIR) + $(eval sched=$(notdir $@)) + $(call msg,GEN-SKEL,,$(sched)) + $(Q)$(BPFTOOL) gen object $(<:.o=.linked1.o) $< + $(Q)$(BPFTOOL) gen object $(<:.o=.linked2.o) $(<:.o=.linked1.o) + $(Q)$(BPFTOOL) gen object $(<:.o=.linked3.o) $(<:.o=.linked2.o) + $(Q)diff $(<:.o=.linked2.o) $(<:.o=.linked3.o) + $(Q)$(BPFTOOL) gen skeleton $(<:.o=.linked3.o) name $(subst .bpf.skel.h,,$(sched)) > $@ + $(Q)$(BPFTOOL) gen subskeleton $(<:.o=.linked3.o) name $(subst .bpf.skel.h,,$(sched)) > $(@:.skel.h=.subskel.h) + +################ +# C schedulers # +################ + +override define CLEAN + rm -rf $(OUTPUT_DIR) + rm -f $(TEST_GEN_PROGS) +endef + +# Every testcase takes all of the BPF progs are dependencies by default. This +# allows testcases to load any BPF scheduler, which is useful for testcases +# that don't need their own prog to run their test. +all_test_bpfprogs := $(foreach prog,$(wildcard *.bpf.c),$(INCLUDE_DIR)/$(patsubst %.c,%.skel.h,$(prog))) + +auto-test-targets := \ + create_dsq \ + enq_last_no_enq_fails \ + enq_select_cpu_fails \ + ddsp_bogus_dsq_fail \ + ddsp_vtimelocal_fail \ + dsp_local_on \ + exit \ + hotplug \ + init_enable_count \ + maximal \ + maybe_null \ + minimal \ + prog_run \ + reload_loop \ + select_cpu_dfl \ + select_cpu_dfl_nodispatch \ + select_cpu_dispatch \ + select_cpu_dispatch_bad_dsq \ + select_cpu_dispatch_dbl_dsp \ + select_cpu_vtime \ + test_example \ + +testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets))) + +$(SCXOBJ_DIR)/runner.o: runner.c | $(SCXOBJ_DIR) $(BPFOBJ) + $(CC) $(CFLAGS) -c $< -o $@ + +# Create all of the test targets object files, whose testcase objects will be +# registered into the runner in ELF constructors. +# +# Note that we must do double expansion here in order to support conditionally +# compiling BPF object files only if one is present, as the wildcard Make +# function doesn't support using implicit rules otherwise. +$(testcase-targets): $(SCXOBJ_DIR)/%.o: %.c $(SCXOBJ_DIR)/runner.o $(all_test_bpfprogs) | $(SCXOBJ_DIR) + $(eval test=$(patsubst %.o,%.c,$(notdir $@))) + $(CC) $(CFLAGS) -c $< -o $@ + +$(SCXOBJ_DIR)/util.o: util.c | $(SCXOBJ_DIR) + $(CC) $(CFLAGS) -c $< -o $@ + +$(OUTPUT)/runner: $(SCXOBJ_DIR)/runner.o $(SCXOBJ_DIR)/util.o $(BPFOBJ) $(testcase-targets) + @echo "$(testcase-targets)" + $(CC) $(CFLAGS) -o $@ $^ $(LDFLAGS) + +.DEFAULT_GOAL := all + +.DELETE_ON_ERROR: + +.SECONDARY: diff --git a/tools/testing/selftests/sched_ext/config b/tools/testing/selftests/sched_ext/config new file mode 100644 index 0000000000000000000000000000000000000000..0de9b4ee249d328480325f14bbd27c3fc9e821d4 --- /dev/null +++ b/tools/testing/selftests/sched_ext/config @@ -0,0 +1,9 @@ +CONFIG_SCHED_DEBUG=y +CONFIG_SCHED_CLASS_EXT=y +CONFIG_CGROUPS=y +CONFIG_CGROUP_SCHED=y +CONFIG_EXT_GROUP_SCHED=y +CONFIG_BPF=y +CONFIG_BPF_SYSCALL=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_BTF=y diff --git a/tools/testing/selftests/sched_ext/create_dsq.bpf.c b/tools/testing/selftests/sched_ext/create_dsq.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..2cfc4ffd60e28fb282f7ee68aab6585cf480609d --- /dev/null +++ b/tools/testing/selftests/sched_ext/create_dsq.bpf.c @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Create and destroy DSQs in a loop. + * + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ + +#include + +char _license[] SEC("license") = "GPL"; + +void BPF_STRUCT_OPS(create_dsq_exit_task, struct task_struct *p, + struct scx_exit_task_args *args) +{ + scx_bpf_destroy_dsq(p->pid); +} + +s32 BPF_STRUCT_OPS_SLEEPABLE(create_dsq_init_task, struct task_struct *p, + struct scx_init_task_args *args) +{ + s32 err; + + err = scx_bpf_create_dsq(p->pid, -1); + if (err) + scx_bpf_error("Failed to create DSQ for %s[%d]", + p->comm, p->pid); + + return err; +} + +s32 BPF_STRUCT_OPS_SLEEPABLE(create_dsq_init) +{ + u32 i; + s32 err; + + bpf_for(i, 0, 1024) { + err = scx_bpf_create_dsq(i, -1); + if (err) { + scx_bpf_error("Failed to create DSQ %d", i); + return 0; + } + } + + bpf_for(i, 0, 1024) { + scx_bpf_destroy_dsq(i); + } + + return 0; +} + +SEC(".struct_ops.link") +struct sched_ext_ops create_dsq_ops = { + .init_task = (void *) create_dsq_init_task, + .exit_task = (void *) create_dsq_exit_task, + .init = (void *) create_dsq_init, + .name = "create_dsq", +}; diff --git a/tools/testing/selftests/sched_ext/create_dsq.c b/tools/testing/selftests/sched_ext/create_dsq.c new file mode 100644 index 0000000000000000000000000000000000000000..d67431f57ac6567689665c5c91e48a4bd7e68bcd --- /dev/null +++ b/tools/testing/selftests/sched_ext/create_dsq.c @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ +#include +#include +#include +#include +#include "create_dsq.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status setup(void **ctx) +{ + struct create_dsq *skel; + + skel = create_dsq__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(create_dsq__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct create_dsq *skel = ctx; + struct bpf_link *link; + + link = bpf_map__attach_struct_ops(skel->maps.create_dsq_ops); + if (!link) { + SCX_ERR("Failed to attach scheduler"); + return SCX_TEST_FAIL; + } + + bpf_link__destroy(link); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct create_dsq *skel = ctx; + + create_dsq__destroy(skel); +} + +struct scx_test create_dsq = { + .name = "create_dsq", + .description = "Create and destroy a dsq in a loop", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&create_dsq) diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..6f4c3f5a1c5d99a3f14debc30810e5fe220f91e6 --- /dev/null +++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + * Copyright (c) 2024 Tejun Heo + */ +#include + +char _license[] SEC("license") = "GPL"; + +UEI_DEFINE(uei); + +s32 BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_select_cpu, struct task_struct *p, + s32 prev_cpu, u64 wake_flags) +{ + s32 cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0); + + if (cpu >= 0) { + /* + * If we dispatch to a bogus DSQ that will fall back to the + * builtin global DSQ, we fail gracefully. + */ + scx_bpf_dsq_insert_vtime(p, 0xcafef00d, SCX_SLICE_DFL, + p->scx.dsq_vtime, 0); + return cpu; + } + + return prev_cpu; +} + +void BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops ddsp_bogus_dsq_fail_ops = { + .select_cpu = (void *) ddsp_bogus_dsq_fail_select_cpu, + .exit = (void *) ddsp_bogus_dsq_fail_exit, + .name = "ddsp_bogus_dsq_fail", + .timeout_ms = 1000U, +}; diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c new file mode 100644 index 0000000000000000000000000000000000000000..b6d13496b24e8c30f34c04ebccaf3af3214b6853 --- /dev/null +++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + * Copyright (c) 2024 Tejun Heo + */ +#include +#include +#include +#include +#include "ddsp_bogus_dsq_fail.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status setup(void **ctx) +{ + struct ddsp_bogus_dsq_fail *skel; + + skel = ddsp_bogus_dsq_fail__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(ddsp_bogus_dsq_fail__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct ddsp_bogus_dsq_fail *skel = ctx; + struct bpf_link *link; + + link = bpf_map__attach_struct_ops(skel->maps.ddsp_bogus_dsq_fail_ops); + SCX_FAIL_IF(!link, "Failed to attach struct_ops"); + + sleep(1); + + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR)); + bpf_link__destroy(link); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct ddsp_bogus_dsq_fail *skel = ctx; + + ddsp_bogus_dsq_fail__destroy(skel); +} + +struct scx_test ddsp_bogus_dsq_fail = { + .name = "ddsp_bogus_dsq_fail", + .description = "Verify we gracefully fail, and fall back to using a " + "built-in DSQ, if we do a direct dispatch to an invalid" + " DSQ in ops.select_cpu()", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&ddsp_bogus_dsq_fail) diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..e4a55027778fd08b5e769c37291810462481f952 --- /dev/null +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + * Copyright (c) 2024 Tejun Heo + */ +#include + +char _license[] SEC("license") = "GPL"; + +UEI_DEFINE(uei); + +s32 BPF_STRUCT_OPS(ddsp_vtimelocal_fail_select_cpu, struct task_struct *p, + s32 prev_cpu, u64 wake_flags) +{ + s32 cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0); + + if (cpu >= 0) { + /* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */ + scx_bpf_dsq_insert_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, + p->scx.dsq_vtime, 0); + return cpu; + } + + return prev_cpu; +} + +void BPF_STRUCT_OPS(ddsp_vtimelocal_fail_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops ddsp_vtimelocal_fail_ops = { + .select_cpu = (void *) ddsp_vtimelocal_fail_select_cpu, + .exit = (void *) ddsp_vtimelocal_fail_exit, + .name = "ddsp_vtimelocal_fail", + .timeout_ms = 1000U, +}; diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c new file mode 100644 index 0000000000000000000000000000000000000000..af9ce4ee8baac83c54b3b7493db2bc73bbd59d0a --- /dev/null +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + * Copyright (c) 2024 Tejun Heo + */ +#include +#include +#include +#include "ddsp_vtimelocal_fail.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status setup(void **ctx) +{ + struct ddsp_vtimelocal_fail *skel; + + skel = ddsp_vtimelocal_fail__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(ddsp_vtimelocal_fail__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct ddsp_vtimelocal_fail *skel = ctx; + struct bpf_link *link; + + link = bpf_map__attach_struct_ops(skel->maps.ddsp_vtimelocal_fail_ops); + SCX_FAIL_IF(!link, "Failed to attach struct_ops"); + + sleep(1); + + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR)); + bpf_link__destroy(link); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct ddsp_vtimelocal_fail *skel = ctx; + + ddsp_vtimelocal_fail__destroy(skel); +} + +struct scx_test ddsp_vtimelocal_fail = { + .name = "ddsp_vtimelocal_fail", + .description = "Verify we gracefully fail, and fall back to using a " + "built-in DSQ, if we do a direct vtime dispatch to a " + "built-in DSQ from DSQ in ops.select_cpu()", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&ddsp_vtimelocal_fail) diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..c02b2aa6fc641eff1b8c0b8a0bf452d9a8f479ed --- /dev/null +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ +#include + +char _license[] SEC("license") = "GPL"; +const volatile s32 nr_cpus; + +UEI_DEFINE(uei); + +struct { + __uint(type, BPF_MAP_TYPE_QUEUE); + __uint(max_entries, 8192); + __type(value, s32); +} queue SEC(".maps"); + +s32 BPF_STRUCT_OPS(dsp_local_on_select_cpu, struct task_struct *p, + s32 prev_cpu, u64 wake_flags) +{ + return prev_cpu; +} + +void BPF_STRUCT_OPS(dsp_local_on_enqueue, struct task_struct *p, + u64 enq_flags) +{ + s32 pid = p->pid; + + if (bpf_map_push_elem(&queue, &pid, 0)) + scx_bpf_error("Failed to enqueue %s[%d]", p->comm, p->pid); +} + +void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev) +{ + s32 pid, target; + struct task_struct *p; + + if (bpf_map_pop_elem(&queue, &pid)) + return; + + p = bpf_task_from_pid(pid); + if (!p) + return; + + if (p->nr_cpus_allowed == nr_cpus && !is_migration_disabled(p)) + target = bpf_get_prandom_u32() % nr_cpus; + else + target = scx_bpf_task_cpu(p); + + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0); + bpf_task_release(p); +} + +void BPF_STRUCT_OPS(dsp_local_on_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops dsp_local_on_ops = { + .select_cpu = (void *) dsp_local_on_select_cpu, + .enqueue = (void *) dsp_local_on_enqueue, + .dispatch = (void *) dsp_local_on_dispatch, + .exit = (void *) dsp_local_on_exit, + .name = "dsp_local_on", + .timeout_ms = 1000U, +}; diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.c b/tools/testing/selftests/sched_ext/dsp_local_on.c new file mode 100644 index 0000000000000000000000000000000000000000..e1f2ce4abfe6434198a84ccd6c108015cb210231 --- /dev/null +++ b/tools/testing/selftests/sched_ext/dsp_local_on.c @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ +#include +#include +#include +#include "dsp_local_on.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status setup(void **ctx) +{ + struct dsp_local_on *skel; + + skel = dsp_local_on__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + + skel->rodata->nr_cpus = libbpf_num_possible_cpus(); + SCX_FAIL_IF(dsp_local_on__load(skel), "Failed to load skel"); + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct dsp_local_on *skel = ctx; + struct bpf_link *link; + + link = bpf_map__attach_struct_ops(skel->maps.dsp_local_on_ops); + SCX_FAIL_IF(!link, "Failed to attach struct_ops"); + + /* Just sleeping is fine, plenty of scheduling events happening */ + sleep(1); + + bpf_link__destroy(link); + + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG)); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct dsp_local_on *skel = ctx; + + dsp_local_on__destroy(skel); +} + +struct scx_test dsp_local_on = { + .name = "dsp_local_on", + .description = "Verify we can directly dispatch tasks to a local DSQs " + "from ops.dispatch()", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&dsp_local_on) diff --git a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..e1bd13e48889f107b2fbae271b16f6976285212a --- /dev/null +++ b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A scheduler that validates the behavior of direct dispatching with a default + * select_cpu implementation. + * + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ + +#include + +char _license[] SEC("license") = "GPL"; + +u32 exit_kind; + +void BPF_STRUCT_OPS_SLEEPABLE(enq_last_no_enq_fails_exit, struct scx_exit_info *info) +{ + exit_kind = info->kind; +} + +SEC(".struct_ops.link") +struct sched_ext_ops enq_last_no_enq_fails_ops = { + .name = "enq_last_no_enq_fails", + /* Need to define ops.enqueue() with SCX_OPS_ENQ_LAST */ + .flags = SCX_OPS_ENQ_LAST, + .exit = (void *) enq_last_no_enq_fails_exit, + .timeout_ms = 1000U, +}; diff --git a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c new file mode 100644 index 0000000000000000000000000000000000000000..d3387ae036794dc0ab47ce073ead4a010305e609 --- /dev/null +++ b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ +#include +#include +#include +#include +#include "enq_last_no_enq_fails.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status setup(void **ctx) +{ + struct enq_last_no_enq_fails *skel; + + skel = enq_last_no_enq_fails__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(enq_last_no_enq_fails__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct enq_last_no_enq_fails *skel = ctx; + struct bpf_link *link; + + link = bpf_map__attach_struct_ops(skel->maps.enq_last_no_enq_fails_ops); + if (!link) { + SCX_ERR("Incorrectly failed at attaching scheduler"); + return SCX_TEST_FAIL; + } + if (!skel->bss->exit_kind) { + SCX_ERR("Incorrectly stayed loaded"); + return SCX_TEST_FAIL; + } + + bpf_link__destroy(link); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct enq_last_no_enq_fails *skel = ctx; + + enq_last_no_enq_fails__destroy(skel); +} + +struct scx_test enq_last_no_enq_fails = { + .name = "enq_last_no_enq_fails", + .description = "Verify we eject a scheduler if we specify " + "the SCX_OPS_ENQ_LAST flag without defining " + "ops.enqueue()", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&enq_last_no_enq_fails) diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..a7cf868d5e311d8f9e7649657a53e63237b0e516 --- /dev/null +++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ + +#include + +char _license[] SEC("license") = "GPL"; + +/* Manually specify the signature until the kfunc is added to the scx repo. */ +s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, + bool *found) __ksym; + +s32 BPF_STRUCT_OPS(enq_select_cpu_fails_select_cpu, struct task_struct *p, + s32 prev_cpu, u64 wake_flags) +{ + return prev_cpu; +} + +void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p, + u64 enq_flags) +{ + /* + * Need to initialize the variable or the verifier will fail to load. + * Improving these semantics is actively being worked on. + */ + bool found = false; + + /* Can only call from ops.select_cpu() */ + scx_bpf_select_cpu_dfl(p, 0, 0, &found); + + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); +} + +SEC(".struct_ops.link") +struct sched_ext_ops enq_select_cpu_fails_ops = { + .select_cpu = (void *) enq_select_cpu_fails_select_cpu, + .enqueue = (void *) enq_select_cpu_fails_enqueue, + .name = "enq_select_cpu_fails", + .timeout_ms = 1000U, +}; diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c new file mode 100644 index 0000000000000000000000000000000000000000..a80e3a3b3698c664fd85bfa14dcc3ca4eabbc19a --- /dev/null +++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ +#include +#include +#include +#include +#include "enq_select_cpu_fails.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status setup(void **ctx) +{ + struct enq_select_cpu_fails *skel; + + skel = enq_select_cpu_fails__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(enq_select_cpu_fails__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct enq_select_cpu_fails *skel = ctx; + struct bpf_link *link; + + link = bpf_map__attach_struct_ops(skel->maps.enq_select_cpu_fails_ops); + if (!link) { + SCX_ERR("Failed to attach scheduler"); + return SCX_TEST_FAIL; + } + + sleep(1); + + bpf_link__destroy(link); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct enq_select_cpu_fails *skel = ctx; + + enq_select_cpu_fails__destroy(skel); +} + +struct scx_test enq_select_cpu_fails = { + .name = "enq_select_cpu_fails", + .description = "Verify we fail to call scx_bpf_select_cpu_dfl() " + "from ops.enqueue()", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&enq_select_cpu_fails) diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..4bc36182d3ffc2fb10e4e2c4eb92fccbfd7fec41 --- /dev/null +++ b/tools/testing/selftests/sched_ext/exit.bpf.c @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ + +#include + +char _license[] SEC("license") = "GPL"; + +#include "exit_test.h" + +const volatile int exit_point; +UEI_DEFINE(uei); + +#define EXIT_CLEANLY() scx_bpf_exit(exit_point, "%d", exit_point) + +#define DSQ_ID 0 + +s32 BPF_STRUCT_OPS(exit_select_cpu, struct task_struct *p, + s32 prev_cpu, u64 wake_flags) +{ + bool found; + + if (exit_point == EXIT_SELECT_CPU) + EXIT_CLEANLY(); + + return scx_bpf_select_cpu_dfl(p, prev_cpu, wake_flags, &found); +} + +void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags) +{ + if (exit_point == EXIT_ENQUEUE) + EXIT_CLEANLY(); + + scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); +} + +void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) +{ + if (exit_point == EXIT_DISPATCH) + EXIT_CLEANLY(); + + scx_bpf_dsq_move_to_local(DSQ_ID); +} + +void BPF_STRUCT_OPS(exit_enable, struct task_struct *p) +{ + if (exit_point == EXIT_ENABLE) + EXIT_CLEANLY(); +} + +s32 BPF_STRUCT_OPS(exit_init_task, struct task_struct *p, + struct scx_init_task_args *args) +{ + if (exit_point == EXIT_INIT_TASK) + EXIT_CLEANLY(); + + return 0; +} + +void BPF_STRUCT_OPS(exit_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +s32 BPF_STRUCT_OPS_SLEEPABLE(exit_init) +{ + if (exit_point == EXIT_INIT) + EXIT_CLEANLY(); + + return scx_bpf_create_dsq(DSQ_ID, -1); +} + +SEC(".struct_ops.link") +struct sched_ext_ops exit_ops = { + .select_cpu = (void *) exit_select_cpu, + .enqueue = (void *) exit_enqueue, + .dispatch = (void *) exit_dispatch, + .init_task = (void *) exit_init_task, + .enable = (void *) exit_enable, + .exit = (void *) exit_exit, + .init = (void *) exit_init, + .name = "exit", + .timeout_ms = 1000U, +}; diff --git a/tools/testing/selftests/sched_ext/exit.c b/tools/testing/selftests/sched_ext/exit.c new file mode 100644 index 0000000000000000000000000000000000000000..ee25824b1cbe6d0cb4aa1ba866e67ce5c242b298 --- /dev/null +++ b/tools/testing/selftests/sched_ext/exit.c @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ +#include +#include +#include +#include +#include +#include "exit.bpf.skel.h" +#include "scx_test.h" + +#include "exit_test.h" + +static enum scx_test_status run(void *ctx) +{ + enum exit_test_case tc; + + for (tc = 0; tc < NUM_EXITS; tc++) { + struct exit *skel; + struct bpf_link *link; + char buf[16]; + + /* + * On single-CPU systems, ops.select_cpu() is never + * invoked, so skip this test to avoid getting stuck + * indefinitely. + */ + if (tc == EXIT_SELECT_CPU && libbpf_num_possible_cpus() == 1) + continue; + + skel = exit__open(); + SCX_ENUM_INIT(skel); + skel->rodata->exit_point = tc; + exit__load(skel); + link = bpf_map__attach_struct_ops(skel->maps.exit_ops); + if (!link) { + SCX_ERR("Failed to attach scheduler"); + exit__destroy(skel); + return SCX_TEST_FAIL; + } + + /* Assumes uei.kind is written last */ + while (skel->data->uei.kind == EXIT_KIND(SCX_EXIT_NONE)) + sched_yield(); + + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG_BPF)); + SCX_EQ(skel->data->uei.exit_code, tc); + sprintf(buf, "%d", tc); + SCX_ASSERT(!strcmp(skel->data->uei.msg, buf)); + bpf_link__destroy(link); + exit__destroy(skel); + } + + return SCX_TEST_PASS; +} + +struct scx_test exit_test = { + .name = "exit", + .description = "Verify we can cleanly exit a scheduler in multiple places", + .run = run, +}; +REGISTER_SCX_TEST(&exit_test) diff --git a/tools/testing/selftests/sched_ext/exit_test.h b/tools/testing/selftests/sched_ext/exit_test.h new file mode 100644 index 0000000000000000000000000000000000000000..94f0268b9cb8e5db6cb025c90fb93d14b6a05ce2 --- /dev/null +++ b/tools/testing/selftests/sched_ext/exit_test.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ + +#ifndef __EXIT_TEST_H__ +#define __EXIT_TEST_H__ + +enum exit_test_case { + EXIT_SELECT_CPU, + EXIT_ENQUEUE, + EXIT_DISPATCH, + EXIT_ENABLE, + EXIT_INIT_TASK, + EXIT_INIT, + NUM_EXITS, +}; + +#endif // # __EXIT_TEST_H__ diff --git a/tools/testing/selftests/sched_ext/hotplug.bpf.c b/tools/testing/selftests/sched_ext/hotplug.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..6c9f25c9bf53e58534ea20cc2c8a202636f532cd --- /dev/null +++ b/tools/testing/selftests/sched_ext/hotplug.bpf.c @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ + +#include + +char _license[] SEC("license") = "GPL"; + +#include "hotplug_test.h" + +UEI_DEFINE(uei); + +void BPF_STRUCT_OPS(hotplug_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +static void exit_from_hotplug(s32 cpu, bool onlining) +{ + /* + * Ignored, just used to verify that we can invoke blocking kfuncs + * from the hotplug path. + */ + scx_bpf_create_dsq(0, -1); + + s64 code = SCX_ECODE_ACT_RESTART | HOTPLUG_EXIT_RSN; + + if (onlining) + code |= HOTPLUG_ONLINING; + + scx_bpf_exit(code, "hotplug event detected (%d going %s)", cpu, + onlining ? "online" : "offline"); +} + +void BPF_STRUCT_OPS_SLEEPABLE(hotplug_cpu_online, s32 cpu) +{ + exit_from_hotplug(cpu, true); +} + +void BPF_STRUCT_OPS_SLEEPABLE(hotplug_cpu_offline, s32 cpu) +{ + exit_from_hotplug(cpu, false); +} + +SEC(".struct_ops.link") +struct sched_ext_ops hotplug_cb_ops = { + .cpu_online = (void *) hotplug_cpu_online, + .cpu_offline = (void *) hotplug_cpu_offline, + .exit = (void *) hotplug_exit, + .name = "hotplug_cbs", + .timeout_ms = 1000U, +}; + +SEC(".struct_ops.link") +struct sched_ext_ops hotplug_nocb_ops = { + .exit = (void *) hotplug_exit, + .name = "hotplug_nocbs", + .timeout_ms = 1000U, +}; diff --git a/tools/testing/selftests/sched_ext/hotplug.c b/tools/testing/selftests/sched_ext/hotplug.c new file mode 100644 index 0000000000000000000000000000000000000000..1c9ceb661c43ea5d1b6b1fed9b11235ee2a34a06 --- /dev/null +++ b/tools/testing/selftests/sched_ext/hotplug.c @@ -0,0 +1,170 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ +#include +#include +#include +#include +#include +#include + +#include "hotplug_test.h" +#include "hotplug.bpf.skel.h" +#include "scx_test.h" +#include "util.h" + +const char *online_path = "/sys/devices/system/cpu/cpu1/online"; + +static bool is_cpu_online(void) +{ + return file_read_long(online_path) > 0; +} + +static void toggle_online_status(bool online) +{ + long val = online ? 1 : 0; + int ret; + + ret = file_write_long(online_path, val); + if (ret != 0) + fprintf(stderr, "Failed to bring CPU %s (%s)", + online ? "online" : "offline", strerror(errno)); +} + +static enum scx_test_status setup(void **ctx) +{ + if (!is_cpu_online()) + return SCX_TEST_SKIP; + + return SCX_TEST_PASS; +} + +static enum scx_test_status test_hotplug(bool onlining, bool cbs_defined) +{ + struct hotplug *skel; + struct bpf_link *link; + long kind, code; + + SCX_ASSERT(is_cpu_online()); + + skel = hotplug__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(hotplug__load(skel), "Failed to load skel"); + + /* Testing the offline -> online path, so go offline before starting */ + if (onlining) + toggle_online_status(0); + + if (cbs_defined) { + kind = SCX_KIND_VAL(SCX_EXIT_UNREG_BPF); + code = SCX_ECODE_VAL(SCX_ECODE_ACT_RESTART) | HOTPLUG_EXIT_RSN; + if (onlining) + code |= HOTPLUG_ONLINING; + } else { + kind = SCX_KIND_VAL(SCX_EXIT_UNREG_KERN); + code = SCX_ECODE_VAL(SCX_ECODE_ACT_RESTART) | + SCX_ECODE_VAL(SCX_ECODE_RSN_HOTPLUG); + } + + if (cbs_defined) + link = bpf_map__attach_struct_ops(skel->maps.hotplug_cb_ops); + else + link = bpf_map__attach_struct_ops(skel->maps.hotplug_nocb_ops); + + if (!link) { + SCX_ERR("Failed to attach scheduler"); + hotplug__destroy(skel); + return SCX_TEST_FAIL; + } + + toggle_online_status(onlining ? 1 : 0); + + while (!UEI_EXITED(skel, uei)) + sched_yield(); + + SCX_EQ(skel->data->uei.kind, kind); + SCX_EQ(UEI_REPORT(skel, uei), code); + + if (!onlining) + toggle_online_status(1); + + bpf_link__destroy(link); + hotplug__destroy(skel); + + return SCX_TEST_PASS; +} + +static enum scx_test_status test_hotplug_attach(void) +{ + struct hotplug *skel; + struct bpf_link *link; + enum scx_test_status status = SCX_TEST_PASS; + long kind, code; + + SCX_ASSERT(is_cpu_online()); + SCX_ASSERT(scx_hotplug_seq() > 0); + + skel = SCX_OPS_OPEN(hotplug_nocb_ops, hotplug); + SCX_ASSERT(skel); + + SCX_OPS_LOAD(skel, hotplug_nocb_ops, hotplug, uei); + + /* + * Take the CPU offline to increment the global hotplug seq, which + * should cause attach to fail due to us setting the hotplug seq above + */ + toggle_online_status(0); + link = bpf_map__attach_struct_ops(skel->maps.hotplug_nocb_ops); + + toggle_online_status(1); + + SCX_ASSERT(link); + while (!UEI_EXITED(skel, uei)) + sched_yield(); + + kind = SCX_KIND_VAL(SCX_EXIT_UNREG_KERN); + code = SCX_ECODE_VAL(SCX_ECODE_ACT_RESTART) | + SCX_ECODE_VAL(SCX_ECODE_RSN_HOTPLUG); + SCX_EQ(skel->data->uei.kind, kind); + SCX_EQ(UEI_REPORT(skel, uei), code); + + bpf_link__destroy(link); + hotplug__destroy(skel); + + return status; +} + +static enum scx_test_status run(void *ctx) +{ + +#define HP_TEST(__onlining, __cbs_defined) ({ \ + if (test_hotplug(__onlining, __cbs_defined) != SCX_TEST_PASS) \ + return SCX_TEST_FAIL; \ +}) + + HP_TEST(true, true); + HP_TEST(false, true); + HP_TEST(true, false); + HP_TEST(false, false); + +#undef HP_TEST + + return test_hotplug_attach(); +} + +static void cleanup(void *ctx) +{ + toggle_online_status(1); +} + +struct scx_test hotplug_test = { + .name = "hotplug", + .description = "Verify hotplug behavior", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&hotplug_test) diff --git a/tools/testing/selftests/sched_ext/hotplug_test.h b/tools/testing/selftests/sched_ext/hotplug_test.h new file mode 100644 index 0000000000000000000000000000000000000000..73d236f90787d7c6d5b978850f6e4c46661e1c1a --- /dev/null +++ b/tools/testing/selftests/sched_ext/hotplug_test.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ + +#ifndef __HOTPLUG_TEST_H__ +#define __HOTPLUG_TEST_H__ + +enum hotplug_test_flags { + HOTPLUG_EXIT_RSN = 1LLU << 0, + HOTPLUG_ONLINING = 1LLU << 1, +}; + +#endif // # __HOTPLUG_TEST_H__ diff --git a/tools/testing/selftests/sched_ext/init_enable_count.bpf.c b/tools/testing/selftests/sched_ext/init_enable_count.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..5eb9edb1837dc7f6a940195dda055acf317c97d6 --- /dev/null +++ b/tools/testing/selftests/sched_ext/init_enable_count.bpf.c @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A scheduler that verifies that we do proper counting of init, enable, etc + * callbacks. + * + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ + +#include + +char _license[] SEC("license") = "GPL"; + +u64 init_task_cnt, exit_task_cnt, enable_cnt, disable_cnt; +u64 init_fork_cnt, init_transition_cnt; + +s32 BPF_STRUCT_OPS_SLEEPABLE(cnt_init_task, struct task_struct *p, + struct scx_init_task_args *args) +{ + __sync_fetch_and_add(&init_task_cnt, 1); + + if (args->fork) + __sync_fetch_and_add(&init_fork_cnt, 1); + else + __sync_fetch_and_add(&init_transition_cnt, 1); + + return 0; +} + +void BPF_STRUCT_OPS(cnt_exit_task, struct task_struct *p) +{ + __sync_fetch_and_add(&exit_task_cnt, 1); +} + +void BPF_STRUCT_OPS(cnt_enable, struct task_struct *p) +{ + __sync_fetch_and_add(&enable_cnt, 1); +} + +void BPF_STRUCT_OPS(cnt_disable, struct task_struct *p) +{ + __sync_fetch_and_add(&disable_cnt, 1); +} + +SEC(".struct_ops.link") +struct sched_ext_ops init_enable_count_ops = { + .init_task = (void *) cnt_init_task, + .exit_task = (void *) cnt_exit_task, + .enable = (void *) cnt_enable, + .disable = (void *) cnt_disable, + .name = "init_enable_count", +}; diff --git a/tools/testing/selftests/sched_ext/init_enable_count.c b/tools/testing/selftests/sched_ext/init_enable_count.c new file mode 100644 index 0000000000000000000000000000000000000000..eddf9e0e26e7f01a8863df82ae78d3896cae27d6 --- /dev/null +++ b/tools/testing/selftests/sched_ext/init_enable_count.c @@ -0,0 +1,157 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ +#include +#include +#include +#include +#include +#include +#include "scx_test.h" +#include "init_enable_count.bpf.skel.h" + +#define SCHED_EXT 7 + +static enum scx_test_status run_test(bool global) +{ + struct init_enable_count *skel; + struct bpf_link *link; + const u32 num_children = 5, num_pre_forks = 1024; + int ret, i, status; + struct sched_param param = {}; + pid_t pids[num_pre_forks]; + + skel = init_enable_count__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + + if (!global) + skel->struct_ops.init_enable_count_ops->flags |= SCX_OPS_SWITCH_PARTIAL; + + SCX_FAIL_IF(init_enable_count__load(skel), "Failed to load skel"); + + /* + * Fork a bunch of children before we attach the scheduler so that we + * ensure (at least in practical terms) that there are more tasks that + * transition from SCHED_OTHER -> SCHED_EXT than there are tasks that + * take the fork() path either below or in other processes. + */ + for (i = 0; i < num_pre_forks; i++) { + pids[i] = fork(); + SCX_FAIL_IF(pids[i] < 0, "Failed to fork child"); + if (pids[i] == 0) { + sleep(1); + exit(0); + } + } + + link = bpf_map__attach_struct_ops(skel->maps.init_enable_count_ops); + SCX_FAIL_IF(!link, "Failed to attach struct_ops"); + + for (i = 0; i < num_pre_forks; i++) { + SCX_FAIL_IF(waitpid(pids[i], &status, 0) != pids[i], + "Failed to wait for pre-forked child\n"); + + SCX_FAIL_IF(status != 0, "Pre-forked child %d exited with status %d\n", i, + status); + } + + bpf_link__destroy(link); + SCX_GE(skel->bss->init_task_cnt, num_pre_forks); + SCX_GE(skel->bss->exit_task_cnt, num_pre_forks); + + link = bpf_map__attach_struct_ops(skel->maps.init_enable_count_ops); + SCX_FAIL_IF(!link, "Failed to attach struct_ops"); + + /* SCHED_EXT children */ + for (i = 0; i < num_children; i++) { + pids[i] = fork(); + SCX_FAIL_IF(pids[i] < 0, "Failed to fork child"); + + if (pids[i] == 0) { + ret = sched_setscheduler(0, SCHED_EXT, ¶m); + SCX_BUG_ON(ret, "Failed to set sched to sched_ext"); + + /* + * Reset to SCHED_OTHER for half of them. Counts for + * everything should still be the same regardless, as + * ops.disable() is invoked even if a task is still on + * SCHED_EXT before it exits. + */ + if (i % 2 == 0) { + ret = sched_setscheduler(0, SCHED_OTHER, ¶m); + SCX_BUG_ON(ret, "Failed to reset sched to normal"); + } + exit(0); + } + } + for (i = 0; i < num_children; i++) { + SCX_FAIL_IF(waitpid(pids[i], &status, 0) != pids[i], + "Failed to wait for SCX child\n"); + + SCX_FAIL_IF(status != 0, "SCX child %d exited with status %d\n", i, + status); + } + + /* SCHED_OTHER children */ + for (i = 0; i < num_children; i++) { + pids[i] = fork(); + if (pids[i] == 0) + exit(0); + } + + for (i = 0; i < num_children; i++) { + SCX_FAIL_IF(waitpid(pids[i], &status, 0) != pids[i], + "Failed to wait for normal child\n"); + + SCX_FAIL_IF(status != 0, "Normal child %d exited with status %d\n", i, + status); + } + + bpf_link__destroy(link); + + SCX_GE(skel->bss->init_task_cnt, 2 * num_children); + SCX_GE(skel->bss->exit_task_cnt, 2 * num_children); + + if (global) { + SCX_GE(skel->bss->enable_cnt, 2 * num_children); + SCX_GE(skel->bss->disable_cnt, 2 * num_children); + } else { + SCX_EQ(skel->bss->enable_cnt, num_children); + SCX_EQ(skel->bss->disable_cnt, num_children); + } + /* + * We forked a ton of tasks before we attached the scheduler above, so + * this should be fine. Technically it could be flaky if a ton of forks + * are happening at the same time in other processes, but that should + * be exceedingly unlikely. + */ + SCX_GT(skel->bss->init_transition_cnt, skel->bss->init_fork_cnt); + SCX_GE(skel->bss->init_fork_cnt, 2 * num_children); + + init_enable_count__destroy(skel); + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + enum scx_test_status status; + + status = run_test(true); + if (status != SCX_TEST_PASS) + return status; + + return run_test(false); +} + +struct scx_test init_enable_count = { + .name = "init_enable_count", + .description = "Verify we correctly count the occurrences of init, " + "enable, etc callbacks.", + .run = run, +}; +REGISTER_SCX_TEST(&init_enable_count) diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..430f5e13bf554492e6505822f1654b7ebfd4d3af --- /dev/null +++ b/tools/testing/selftests/sched_ext/maximal.bpf.c @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A scheduler with every callback defined. + * + * This scheduler defines every callback. + * + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ + +#include + +char _license[] SEC("license") = "GPL"; + +#define DSQ_ID 0 + +s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu, + u64 wake_flags) +{ + return prev_cpu; +} + +void BPF_STRUCT_OPS(maximal_enqueue, struct task_struct *p, u64 enq_flags) +{ + scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); +} + +void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags) +{} + +void BPF_STRUCT_OPS(maximal_dispatch, s32 cpu, struct task_struct *prev) +{ + scx_bpf_dsq_move_to_local(DSQ_ID); +} + +void BPF_STRUCT_OPS(maximal_runnable, struct task_struct *p, u64 enq_flags) +{} + +void BPF_STRUCT_OPS(maximal_running, struct task_struct *p) +{} + +void BPF_STRUCT_OPS(maximal_stopping, struct task_struct *p, bool runnable) +{} + +void BPF_STRUCT_OPS(maximal_quiescent, struct task_struct *p, u64 deq_flags) +{} + +bool BPF_STRUCT_OPS(maximal_yield, struct task_struct *from, + struct task_struct *to) +{ + return false; +} + +bool BPF_STRUCT_OPS(maximal_core_sched_before, struct task_struct *a, + struct task_struct *b) +{ + return false; +} + +void BPF_STRUCT_OPS(maximal_set_weight, struct task_struct *p, u32 weight) +{} + +void BPF_STRUCT_OPS(maximal_set_cpumask, struct task_struct *p, + const struct cpumask *cpumask) +{} + +void BPF_STRUCT_OPS(maximal_update_idle, s32 cpu, bool idle) +{} + +void BPF_STRUCT_OPS(maximal_cpu_acquire, s32 cpu, + struct scx_cpu_acquire_args *args) +{} + +void BPF_STRUCT_OPS(maximal_cpu_release, s32 cpu, + struct scx_cpu_release_args *args) +{} + +void BPF_STRUCT_OPS(maximal_cpu_online, s32 cpu) +{} + +void BPF_STRUCT_OPS(maximal_cpu_offline, s32 cpu) +{} + +s32 BPF_STRUCT_OPS(maximal_init_task, struct task_struct *p, + struct scx_init_task_args *args) +{ + return 0; +} + +void BPF_STRUCT_OPS(maximal_enable, struct task_struct *p) +{} + +void BPF_STRUCT_OPS(maximal_exit_task, struct task_struct *p, + struct scx_exit_task_args *args) +{} + +void BPF_STRUCT_OPS(maximal_disable, struct task_struct *p) +{} + +s32 BPF_STRUCT_OPS(maximal_cgroup_init, struct cgroup *cgrp, + struct scx_cgroup_init_args *args) +{ + return 0; +} + +void BPF_STRUCT_OPS(maximal_cgroup_exit, struct cgroup *cgrp) +{} + +s32 BPF_STRUCT_OPS(maximal_cgroup_prep_move, struct task_struct *p, + struct cgroup *from, struct cgroup *to) +{ + return 0; +} + +void BPF_STRUCT_OPS(maximal_cgroup_move, struct task_struct *p, + struct cgroup *from, struct cgroup *to) +{} + +void BPF_STRUCT_OPS(maximal_cgroup_cancel_move, struct task_struct *p, + struct cgroup *from, struct cgroup *to) +{} + +void BPF_STRUCT_OPS(maximal_cgroup_set_weight, struct cgroup *cgrp, u32 weight) +{} + +s32 BPF_STRUCT_OPS_SLEEPABLE(maximal_init) +{ + return scx_bpf_create_dsq(DSQ_ID, -1); +} + +void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info) +{} + +SEC(".struct_ops.link") +struct sched_ext_ops maximal_ops = { + .select_cpu = (void *) maximal_select_cpu, + .enqueue = (void *) maximal_enqueue, + .dequeue = (void *) maximal_dequeue, + .dispatch = (void *) maximal_dispatch, + .runnable = (void *) maximal_runnable, + .running = (void *) maximal_running, + .stopping = (void *) maximal_stopping, + .quiescent = (void *) maximal_quiescent, + .yield = (void *) maximal_yield, + .core_sched_before = (void *) maximal_core_sched_before, + .set_weight = (void *) maximal_set_weight, + .set_cpumask = (void *) maximal_set_cpumask, + .update_idle = (void *) maximal_update_idle, + .cpu_acquire = (void *) maximal_cpu_acquire, + .cpu_release = (void *) maximal_cpu_release, + .cpu_online = (void *) maximal_cpu_online, + .cpu_offline = (void *) maximal_cpu_offline, + .init_task = (void *) maximal_init_task, + .enable = (void *) maximal_enable, + .exit_task = (void *) maximal_exit_task, + .disable = (void *) maximal_disable, + .cgroup_init = (void *) maximal_cgroup_init, + .cgroup_exit = (void *) maximal_cgroup_exit, + .cgroup_prep_move = (void *) maximal_cgroup_prep_move, + .cgroup_move = (void *) maximal_cgroup_move, + .cgroup_cancel_move = (void *) maximal_cgroup_cancel_move, + .cgroup_set_weight = (void *) maximal_cgroup_set_weight, + .init = (void *) maximal_init, + .exit = (void *) maximal_exit, + .name = "maximal", +}; diff --git a/tools/testing/selftests/sched_ext/maximal.c b/tools/testing/selftests/sched_ext/maximal.c new file mode 100644 index 0000000000000000000000000000000000000000..c6be50a9941d55aa8994c69456e03a087e5b75fc --- /dev/null +++ b/tools/testing/selftests/sched_ext/maximal.c @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ +#include +#include +#include +#include +#include "maximal.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status setup(void **ctx) +{ + struct maximal *skel; + + skel = maximal__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(maximal__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct maximal *skel = ctx; + struct bpf_link *link; + + link = bpf_map__attach_struct_ops(skel->maps.maximal_ops); + SCX_FAIL_IF(!link, "Failed to attach scheduler"); + + bpf_link__destroy(link); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct maximal *skel = ctx; + + maximal__destroy(skel); +} + +struct scx_test maximal = { + .name = "maximal", + .description = "Verify we can load a scheduler with every callback defined", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&maximal) diff --git a/tools/testing/selftests/sched_ext/maybe_null.bpf.c b/tools/testing/selftests/sched_ext/maybe_null.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..cf4ae870cd4e56b0ddcf2cb868da71dfafcad00d --- /dev/null +++ b/tools/testing/selftests/sched_ext/maybe_null.bpf.c @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + */ + +#include + +char _license[] SEC("license") = "GPL"; + +u64 vtime_test; + +void BPF_STRUCT_OPS(maybe_null_running, struct task_struct *p) +{} + +void BPF_STRUCT_OPS(maybe_null_success_dispatch, s32 cpu, struct task_struct *p) +{ + if (p != NULL) + vtime_test = p->scx.dsq_vtime; +} + +bool BPF_STRUCT_OPS(maybe_null_success_yield, struct task_struct *from, + struct task_struct *to) +{ + if (to) + bpf_printk("Yielding to %s[%d]", to->comm, to->pid); + + return false; +} + +SEC(".struct_ops.link") +struct sched_ext_ops maybe_null_success = { + .dispatch = (void *) maybe_null_success_dispatch, + .yield = (void *) maybe_null_success_yield, + .enable = (void *) maybe_null_running, + .name = "minimal", +}; diff --git a/tools/testing/selftests/sched_ext/maybe_null.c b/tools/testing/selftests/sched_ext/maybe_null.c new file mode 100644 index 0000000000000000000000000000000000000000..aacf0c58ca4fae767ae1491eee3f272c0144da96 --- /dev/null +++ b/tools/testing/selftests/sched_ext/maybe_null.c @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + */ +#include +#include +#include +#include +#include "maybe_null.bpf.skel.h" +#include "maybe_null_fail_dsp.bpf.skel.h" +#include "maybe_null_fail_yld.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status run(void *ctx) +{ + struct maybe_null *skel; + struct maybe_null_fail_dsp *fail_dsp; + struct maybe_null_fail_yld *fail_yld; + + skel = maybe_null__open_and_load(); + if (!skel) { + SCX_ERR("Failed to open and load maybe_null skel"); + return SCX_TEST_FAIL; + } + maybe_null__destroy(skel); + + fail_dsp = maybe_null_fail_dsp__open_and_load(); + if (fail_dsp) { + maybe_null_fail_dsp__destroy(fail_dsp); + SCX_ERR("Should failed to open and load maybe_null_fail_dsp skel"); + return SCX_TEST_FAIL; + } + + fail_yld = maybe_null_fail_yld__open_and_load(); + if (fail_yld) { + maybe_null_fail_yld__destroy(fail_yld); + SCX_ERR("Should failed to open and load maybe_null_fail_yld skel"); + return SCX_TEST_FAIL; + } + + return SCX_TEST_PASS; +} + +struct scx_test maybe_null = { + .name = "maybe_null", + .description = "Verify if PTR_MAYBE_NULL works for .dispatch", + .run = run, +}; +REGISTER_SCX_TEST(&maybe_null) diff --git a/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c b/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..ec724d7b33d18dc692e882ef0dbb322479ea92f3 --- /dev/null +++ b/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + */ + +#include + +char _license[] SEC("license") = "GPL"; + +u64 vtime_test; + +void BPF_STRUCT_OPS(maybe_null_running, struct task_struct *p) +{} + +void BPF_STRUCT_OPS(maybe_null_fail_dispatch, s32 cpu, struct task_struct *p) +{ + vtime_test = p->scx.dsq_vtime; +} + +SEC(".struct_ops.link") +struct sched_ext_ops maybe_null_fail = { + .dispatch = (void *) maybe_null_fail_dispatch, + .enable = (void *) maybe_null_running, + .name = "maybe_null_fail_dispatch", +}; diff --git a/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c b/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..e6552cace020e5757b5c74d260fb4c5f36b61b74 --- /dev/null +++ b/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + */ + +#include + +char _license[] SEC("license") = "GPL"; + +u64 vtime_test; + +void BPF_STRUCT_OPS(maybe_null_running, struct task_struct *p) +{} + +bool BPF_STRUCT_OPS(maybe_null_fail_yield, struct task_struct *from, + struct task_struct *to) +{ + bpf_printk("Yielding to %s[%d]", to->comm, to->pid); + + return false; +} + +SEC(".struct_ops.link") +struct sched_ext_ops maybe_null_fail = { + .yield = (void *) maybe_null_fail_yield, + .enable = (void *) maybe_null_running, + .name = "maybe_null_fail_yield", +}; diff --git a/tools/testing/selftests/sched_ext/minimal.bpf.c b/tools/testing/selftests/sched_ext/minimal.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..6a7eccef0104550e12e2ac463cc5302d8d5eac64 --- /dev/null +++ b/tools/testing/selftests/sched_ext/minimal.bpf.c @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A completely minimal scheduler. + * + * This scheduler defines the absolute minimal set of struct sched_ext_ops + * fields: its name. It should _not_ fail to be loaded, and can be used to + * exercise the default scheduling paths in ext.c. + * + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ + +#include + +char _license[] SEC("license") = "GPL"; + +SEC(".struct_ops.link") +struct sched_ext_ops minimal_ops = { + .name = "minimal", +}; diff --git a/tools/testing/selftests/sched_ext/minimal.c b/tools/testing/selftests/sched_ext/minimal.c new file mode 100644 index 0000000000000000000000000000000000000000..89f7261757ffb4ba063537b4ba459ee323c25eda --- /dev/null +++ b/tools/testing/selftests/sched_ext/minimal.c @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ +#include +#include +#include +#include +#include "minimal.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status setup(void **ctx) +{ + struct minimal *skel; + + skel = minimal__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(minimal__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct minimal *skel = ctx; + struct bpf_link *link; + + link = bpf_map__attach_struct_ops(skel->maps.minimal_ops); + if (!link) { + SCX_ERR("Failed to attach scheduler"); + return SCX_TEST_FAIL; + } + + bpf_link__destroy(link); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct minimal *skel = ctx; + + minimal__destroy(skel); +} + +struct scx_test minimal = { + .name = "minimal", + .description = "Verify we can load a fully minimal scheduler", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&minimal) diff --git a/tools/testing/selftests/sched_ext/prog_run.bpf.c b/tools/testing/selftests/sched_ext/prog_run.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..00c267626a68fe558aa478b203175e027c9d9b18 --- /dev/null +++ b/tools/testing/selftests/sched_ext/prog_run.bpf.c @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A scheduler that validates that we can invoke sched_ext kfuncs in + * BPF_PROG_TYPE_SYSCALL programs. + * + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ + +#include + +UEI_DEFINE(uei); + +char _license[] SEC("license") = "GPL"; + +SEC("syscall") +int BPF_PROG(prog_run_syscall) +{ + scx_bpf_create_dsq(0, -1); + scx_bpf_exit(0xdeadbeef, "Exited from PROG_RUN"); + return 0; +} + +void BPF_STRUCT_OPS(prog_run_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops prog_run_ops = { + .exit = (void *) prog_run_exit, + .name = "prog_run", +}; diff --git a/tools/testing/selftests/sched_ext/prog_run.c b/tools/testing/selftests/sched_ext/prog_run.c new file mode 100644 index 0000000000000000000000000000000000000000..05974820ca69d8ba22b9b7af8312002a72f1282c --- /dev/null +++ b/tools/testing/selftests/sched_ext/prog_run.c @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ +#include +#include +#include +#include +#include +#include "prog_run.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status setup(void **ctx) +{ + struct prog_run *skel; + + skel = prog_run__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(prog_run__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct prog_run *skel = ctx; + struct bpf_link *link; + int prog_fd, err = 0; + + prog_fd = bpf_program__fd(skel->progs.prog_run_syscall); + if (prog_fd < 0) { + SCX_ERR("Failed to get BPF_PROG_RUN prog"); + return SCX_TEST_FAIL; + } + + LIBBPF_OPTS(bpf_test_run_opts, topts); + + link = bpf_map__attach_struct_ops(skel->maps.prog_run_ops); + if (!link) { + SCX_ERR("Failed to attach scheduler"); + close(prog_fd); + return SCX_TEST_FAIL; + } + + err = bpf_prog_test_run_opts(prog_fd, &topts); + SCX_EQ(err, 0); + + /* Assumes uei.kind is written last */ + while (skel->data->uei.kind == EXIT_KIND(SCX_EXIT_NONE)) + sched_yield(); + + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG_BPF)); + SCX_EQ(skel->data->uei.exit_code, 0xdeadbeef); + close(prog_fd); + bpf_link__destroy(link); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct prog_run *skel = ctx; + + prog_run__destroy(skel); +} + +struct scx_test prog_run = { + .name = "prog_run", + .description = "Verify we can call into a scheduler with BPF_PROG_RUN, and invoke kfuncs", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&prog_run) diff --git a/tools/testing/selftests/sched_ext/reload_loop.c b/tools/testing/selftests/sched_ext/reload_loop.c new file mode 100644 index 0000000000000000000000000000000000000000..308211d804364aae76331638a25171ac764a97d2 --- /dev/null +++ b/tools/testing/selftests/sched_ext/reload_loop.c @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ +#include +#include +#include +#include +#include +#include "maximal.bpf.skel.h" +#include "scx_test.h" + +static struct maximal *skel; +static pthread_t threads[2]; + +bool force_exit = false; + +static enum scx_test_status setup(void **ctx) +{ + skel = maximal__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(maximal__load(skel), "Failed to load skel"); + + return SCX_TEST_PASS; +} + +static void *do_reload_loop(void *arg) +{ + u32 i; + + for (i = 0; i < 1024 && !force_exit; i++) { + struct bpf_link *link; + + link = bpf_map__attach_struct_ops(skel->maps.maximal_ops); + if (link) + bpf_link__destroy(link); + } + + return NULL; +} + +static enum scx_test_status run(void *ctx) +{ + int err; + void *ret; + + err = pthread_create(&threads[0], NULL, do_reload_loop, NULL); + SCX_FAIL_IF(err, "Failed to create thread 0"); + + err = pthread_create(&threads[1], NULL, do_reload_loop, NULL); + SCX_FAIL_IF(err, "Failed to create thread 1"); + + SCX_FAIL_IF(pthread_join(threads[0], &ret), "thread 0 failed"); + SCX_FAIL_IF(pthread_join(threads[1], &ret), "thread 1 failed"); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + force_exit = true; + maximal__destroy(skel); +} + +struct scx_test reload_loop = { + .name = "reload_loop", + .description = "Stress test loading and unloading schedulers repeatedly in a tight loop", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&reload_loop) diff --git a/tools/testing/selftests/sched_ext/runner.c b/tools/testing/selftests/sched_ext/runner.c new file mode 100644 index 0000000000000000000000000000000000000000..aa2d7d32dda9b6879e4393dc8ff80b0f8431ab7f --- /dev/null +++ b/tools/testing/selftests/sched_ext/runner.c @@ -0,0 +1,212 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + * Copyright (c) 2024 Tejun Heo + */ +#include +#include +#include +#include +#include +#include "scx_test.h" + +const char help_fmt[] = +"The runner for sched_ext tests.\n" +"\n" +"The runner is statically linked against all testcases, and runs them all serially.\n" +"It's required for the testcases to be serial, as only a single host-wide sched_ext\n" +"scheduler may be loaded at any given time." +"\n" +"Usage: %s [-t TEST] [-h]\n" +"\n" +" -t TEST Only run tests whose name includes this string\n" +" -s Include print output for skipped tests\n" +" -l List all available tests\n" +" -q Don't print the test descriptions during run\n" +" -h Display this help and exit\n"; + +static volatile int exit_req; +static bool quiet, print_skipped, list; + +#define MAX_SCX_TESTS 2048 + +static struct scx_test __scx_tests[MAX_SCX_TESTS]; +static unsigned __scx_num_tests = 0; + +static void sigint_handler(int simple) +{ + exit_req = 1; +} + +static void print_test_preamble(const struct scx_test *test, bool quiet) +{ + printf("===== START =====\n"); + printf("TEST: %s\n", test->name); + if (!quiet) + printf("DESCRIPTION: %s\n", test->description); + printf("OUTPUT:\n"); +} + +static const char *status_to_result(enum scx_test_status status) +{ + switch (status) { + case SCX_TEST_PASS: + case SCX_TEST_SKIP: + return "ok"; + case SCX_TEST_FAIL: + return "not ok"; + default: + return ""; + } +} + +static void print_test_result(const struct scx_test *test, + enum scx_test_status status, + unsigned int testnum) +{ + const char *result = status_to_result(status); + const char *directive = status == SCX_TEST_SKIP ? "SKIP " : ""; + + printf("%s %u %s # %s\n", result, testnum, test->name, directive); + printf("===== END =====\n"); +} + +static bool should_skip_test(const struct scx_test *test, const char * filter) +{ + return !strstr(test->name, filter); +} + +static enum scx_test_status run_test(const struct scx_test *test) +{ + enum scx_test_status status; + void *context = NULL; + + if (test->setup) { + status = test->setup(&context); + if (status != SCX_TEST_PASS) + return status; + } + + status = test->run(context); + + if (test->cleanup) + test->cleanup(context); + + return status; +} + +static bool test_valid(const struct scx_test *test) +{ + if (!test) { + fprintf(stderr, "NULL test detected\n"); + return false; + } + + if (!test->name) { + fprintf(stderr, + "Test with no name found. Must specify test name.\n"); + return false; + } + + if (!test->description) { + fprintf(stderr, "Test %s requires description.\n", test->name); + return false; + } + + if (!test->run) { + fprintf(stderr, "Test %s has no run() callback\n", test->name); + return false; + } + + return true; +} + +int main(int argc, char **argv) +{ + const char *filter = NULL; + unsigned testnum = 0, i; + unsigned passed = 0, skipped = 0, failed = 0; + int opt; + + signal(SIGINT, sigint_handler); + signal(SIGTERM, sigint_handler); + + libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + + while ((opt = getopt(argc, argv, "qslt:h")) != -1) { + switch (opt) { + case 'q': + quiet = true; + break; + case 's': + print_skipped = true; + break; + case 'l': + list = true; + break; + case 't': + filter = optarg; + break; + default: + fprintf(stderr, help_fmt, basename(argv[0])); + return opt != 'h'; + } + } + + for (i = 0; i < __scx_num_tests; i++) { + enum scx_test_status status; + struct scx_test *test = &__scx_tests[i]; + + if (list) { + printf("%s\n", test->name); + if (i == (__scx_num_tests - 1)) + return 0; + continue; + } + + if (filter && should_skip_test(test, filter)) { + /* + * Printing the skipped tests and their preambles can + * add a lot of noise to the runner output. Printing + * this is only really useful for CI, so let's skip it + * by default. + */ + if (print_skipped) { + print_test_preamble(test, quiet); + print_test_result(test, SCX_TEST_SKIP, ++testnum); + } + continue; + } + + print_test_preamble(test, quiet); + status = run_test(test); + print_test_result(test, status, ++testnum); + switch (status) { + case SCX_TEST_PASS: + passed++; + break; + case SCX_TEST_SKIP: + skipped++; + break; + case SCX_TEST_FAIL: + failed++; + break; + } + } + printf("\n\n=============================\n\n"); + printf("RESULTS:\n\n"); + printf("PASSED: %u\n", passed); + printf("SKIPPED: %u\n", skipped); + printf("FAILED: %u\n", failed); + + return 0; +} + +void scx_test_register(struct scx_test *test) +{ + SCX_BUG_ON(!test_valid(test), "Invalid test found"); + SCX_BUG_ON(__scx_num_tests >= MAX_SCX_TESTS, "Maximum tests exceeded"); + + __scx_tests[__scx_num_tests++] = *test; +} diff --git a/tools/testing/selftests/sched_ext/scx_test.h b/tools/testing/selftests/sched_ext/scx_test.h new file mode 100644 index 0000000000000000000000000000000000000000..90b8d6915bb7e0b0743dc1c96c7faa80526085a0 --- /dev/null +++ b/tools/testing/selftests/sched_ext/scx_test.h @@ -0,0 +1,131 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 Tejun Heo + * Copyright (c) 2023 David Vernet + */ + +#ifndef __SCX_TEST_H__ +#define __SCX_TEST_H__ + +#include +#include +#include + +enum scx_test_status { + SCX_TEST_PASS = 0, + SCX_TEST_SKIP, + SCX_TEST_FAIL, +}; + +#define EXIT_KIND(__ent) __COMPAT_ENUM_OR_ZERO("scx_exit_kind", #__ent) + +struct scx_test { + /** + * name - The name of the testcase. + */ + const char *name; + + /** + * description - A description of your testcase: what it tests and is + * meant to validate. + */ + const char *description; + + /* + * setup - Setup the test. + * @ctx: A pointer to a context object that will be passed to run and + * cleanup. + * + * An optional callback that allows a testcase to perform setup for its + * run. A test may return SCX_TEST_SKIP to skip the run. + */ + enum scx_test_status (*setup)(void **ctx); + + /* + * run - Run the test. + * @ctx: Context set in the setup() callback. If @ctx was not set in + * setup(), it is NULL. + * + * The main test. Callers should return one of: + * + * - SCX_TEST_PASS: Test passed + * - SCX_TEST_SKIP: Test should be skipped + * - SCX_TEST_FAIL: Test failed + * + * This callback must be defined. + */ + enum scx_test_status (*run)(void *ctx); + + /* + * cleanup - Perform cleanup following the test + * @ctx: Context set in the setup() callback. If @ctx was not set in + * setup(), it is NULL. + * + * An optional callback that allows a test to perform cleanup after + * being run. This callback is run even if the run() callback returns + * SCX_TEST_SKIP or SCX_TEST_FAIL. It is not run if setup() returns + * SCX_TEST_SKIP or SCX_TEST_FAIL. + */ + void (*cleanup)(void *ctx); +}; + +void scx_test_register(struct scx_test *test); + +#define REGISTER_SCX_TEST(__test) \ + __attribute__((constructor)) \ + static void ___scxregister##__LINE__(void) \ + { \ + scx_test_register(__test); \ + } + +#define SCX_ERR(__fmt, ...) \ + do { \ + fprintf(stderr, "ERR: %s:%d\n", __FILE__, __LINE__); \ + fprintf(stderr, __fmt"\n", ##__VA_ARGS__); \ + } while (0) + +#define SCX_FAIL(__fmt, ...) \ + do { \ + SCX_ERR(__fmt, ##__VA_ARGS__); \ + return SCX_TEST_FAIL; \ + } while (0) + +#define SCX_FAIL_IF(__cond, __fmt, ...) \ + do { \ + if (__cond) \ + SCX_FAIL(__fmt, ##__VA_ARGS__); \ + } while (0) + +#define SCX_GT(_x, _y) SCX_FAIL_IF((_x) <= (_y), "Expected %s > %s (%lu > %lu)", \ + #_x, #_y, (u64)(_x), (u64)(_y)) +#define SCX_GE(_x, _y) SCX_FAIL_IF((_x) < (_y), "Expected %s >= %s (%lu >= %lu)", \ + #_x, #_y, (u64)(_x), (u64)(_y)) +#define SCX_LT(_x, _y) SCX_FAIL_IF((_x) >= (_y), "Expected %s < %s (%lu < %lu)", \ + #_x, #_y, (u64)(_x), (u64)(_y)) +#define SCX_LE(_x, _y) SCX_FAIL_IF((_x) > (_y), "Expected %s <= %s (%lu <= %lu)", \ + #_x, #_y, (u64)(_x), (u64)(_y)) +#define SCX_EQ(_x, _y) SCX_FAIL_IF((_x) != (_y), "Expected %s == %s (%lu == %lu)", \ + #_x, #_y, (u64)(_x), (u64)(_y)) +#define SCX_ASSERT(_x) SCX_FAIL_IF(!(_x), "Expected %s to be true (%lu)", \ + #_x, (u64)(_x)) + +#define SCX_ECODE_VAL(__ecode) ({ \ + u64 __val = 0; \ + bool __found = false; \ + \ + __found = __COMPAT_read_enum("scx_exit_code", #__ecode, &__val); \ + SCX_ASSERT(__found); \ + (s64)__val; \ +}) + +#define SCX_KIND_VAL(__kind) ({ \ + u64 __val = 0; \ + bool __found = false; \ + \ + __found = __COMPAT_read_enum("scx_exit_kind", #__kind, &__val); \ + SCX_ASSERT(__found); \ + __val; \ +}) + +#endif // # __SCX_TEST_H__ diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..13d0f5be788d1206f28a15c8415679c52fb74989 --- /dev/null +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A scheduler that validates the behavior of direct dispatching with a default + * select_cpu implementation. + * + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ + +#include + +char _license[] SEC("license") = "GPL"; + +bool saw_local = false; + +static bool task_is_test(const struct task_struct *p) +{ + return !bpf_strncmp(p->comm, 9, "select_cpu"); +} + +void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p, + u64 enq_flags) +{ + const struct cpumask *idle_mask = scx_bpf_get_idle_cpumask(); + + if (task_is_test(p) && + bpf_cpumask_test_cpu(scx_bpf_task_cpu(p), idle_mask)) { + saw_local = true; + } + scx_bpf_put_idle_cpumask(idle_mask); + + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); +} + +SEC(".struct_ops.link") +struct sched_ext_ops select_cpu_dfl_ops = { + .enqueue = (void *) select_cpu_dfl_enqueue, + .name = "select_cpu_dfl", +}; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.c new file mode 100644 index 0000000000000000000000000000000000000000..5b6e045e1109b9b626095aff7aa60984865cac19 --- /dev/null +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.c @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ +#include +#include +#include +#include +#include "select_cpu_dfl.bpf.skel.h" +#include "scx_test.h" + +#define NUM_CHILDREN 1028 + +static enum scx_test_status setup(void **ctx) +{ + struct select_cpu_dfl *skel; + + skel = select_cpu_dfl__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dfl__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct select_cpu_dfl *skel = ctx; + struct bpf_link *link; + pid_t pids[NUM_CHILDREN]; + int i, status; + + link = bpf_map__attach_struct_ops(skel->maps.select_cpu_dfl_ops); + SCX_FAIL_IF(!link, "Failed to attach scheduler"); + + for (i = 0; i < NUM_CHILDREN; i++) { + pids[i] = fork(); + if (pids[i] == 0) { + sleep(1); + exit(0); + } + } + + for (i = 0; i < NUM_CHILDREN; i++) { + SCX_EQ(waitpid(pids[i], &status, 0), pids[i]); + SCX_EQ(status, 0); + } + + SCX_ASSERT(!skel->bss->saw_local); + + bpf_link__destroy(link); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct select_cpu_dfl *skel = ctx; + + select_cpu_dfl__destroy(skel); +} + +struct scx_test select_cpu_dfl = { + .name = "select_cpu_dfl", + .description = "Verify the default ops.select_cpu() dispatches tasks " + "when idles cores are found, and skips ops.enqueue()", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&select_cpu_dfl) diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..815f1d5d61ac4352c8952332f7ce9cadfcd75345 --- /dev/null +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A scheduler that validates the behavior of direct dispatching with a default + * select_cpu implementation, and with the SCX_OPS_ENQ_DFL_NO_DISPATCH ops flag + * specified. + * + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ + +#include + +char _license[] SEC("license") = "GPL"; + +bool saw_local = false; + +/* Per-task scheduling context */ +struct task_ctx { + bool force_local; /* CPU changed by ops.select_cpu() */ +}; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct task_ctx); +} task_ctx_stor SEC(".maps"); + +/* Manually specify the signature until the kfunc is added to the scx repo. */ +s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, + bool *found) __ksym; + +s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_select_cpu, struct task_struct *p, + s32 prev_cpu, u64 wake_flags) +{ + struct task_ctx *tctx; + s32 cpu; + + tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0); + if (!tctx) { + scx_bpf_error("task_ctx lookup failed"); + return -ESRCH; + } + + cpu = scx_bpf_select_cpu_dfl(p, prev_cpu, wake_flags, + &tctx->force_local); + + return cpu; +} + +void BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_enqueue, struct task_struct *p, + u64 enq_flags) +{ + u64 dsq_id = SCX_DSQ_GLOBAL; + struct task_ctx *tctx; + + tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0); + if (!tctx) { + scx_bpf_error("task_ctx lookup failed"); + return; + } + + if (tctx->force_local) { + dsq_id = SCX_DSQ_LOCAL; + tctx->force_local = false; + saw_local = true; + } + + scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, enq_flags); +} + +s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task, + struct task_struct *p, struct scx_init_task_args *args) +{ + if (bpf_task_storage_get(&task_ctx_stor, p, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE)) + return 0; + else + return -ENOMEM; +} + +SEC(".struct_ops.link") +struct sched_ext_ops select_cpu_dfl_nodispatch_ops = { + .select_cpu = (void *) select_cpu_dfl_nodispatch_select_cpu, + .enqueue = (void *) select_cpu_dfl_nodispatch_enqueue, + .init_task = (void *) select_cpu_dfl_nodispatch_init_task, + .name = "select_cpu_dfl_nodispatch", +}; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c new file mode 100644 index 0000000000000000000000000000000000000000..9b5d232efb7f610b319721aaf57b815bf1e4e64e --- /dev/null +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ +#include +#include +#include +#include +#include "select_cpu_dfl_nodispatch.bpf.skel.h" +#include "scx_test.h" + +#define NUM_CHILDREN 1028 + +static enum scx_test_status setup(void **ctx) +{ + struct select_cpu_dfl_nodispatch *skel; + + skel = select_cpu_dfl_nodispatch__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dfl_nodispatch__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct select_cpu_dfl_nodispatch *skel = ctx; + struct bpf_link *link; + pid_t pids[NUM_CHILDREN]; + int i, status; + + link = bpf_map__attach_struct_ops(skel->maps.select_cpu_dfl_nodispatch_ops); + SCX_FAIL_IF(!link, "Failed to attach scheduler"); + + for (i = 0; i < NUM_CHILDREN; i++) { + pids[i] = fork(); + if (pids[i] == 0) { + sleep(1); + exit(0); + } + } + + for (i = 0; i < NUM_CHILDREN; i++) { + SCX_EQ(waitpid(pids[i], &status, 0), pids[i]); + SCX_EQ(status, 0); + } + + SCX_ASSERT(skel->bss->saw_local); + + bpf_link__destroy(link); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct select_cpu_dfl_nodispatch *skel = ctx; + + select_cpu_dfl_nodispatch__destroy(skel); +} + +struct scx_test select_cpu_dfl_nodispatch = { + .name = "select_cpu_dfl_nodispatch", + .description = "Verify behavior of scx_bpf_select_cpu_dfl() in " + "ops.select_cpu()", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&select_cpu_dfl_nodispatch) diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..4bb99699e9209c722f361a53fbe1953803236d4f --- /dev/null +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A scheduler that validates the behavior of direct dispatching with a default + * select_cpu implementation. + * + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ + +#include + +char _license[] SEC("license") = "GPL"; + +s32 BPF_STRUCT_OPS(select_cpu_dispatch_select_cpu, struct task_struct *p, + s32 prev_cpu, u64 wake_flags) +{ + u64 dsq_id = SCX_DSQ_LOCAL; + s32 cpu = prev_cpu; + + if (scx_bpf_test_and_clear_cpu_idle(cpu)) + goto dispatch; + + cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0); + if (cpu >= 0) + goto dispatch; + + dsq_id = SCX_DSQ_GLOBAL; + cpu = prev_cpu; + +dispatch: + scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, 0); + return cpu; +} + +SEC(".struct_ops.link") +struct sched_ext_ops select_cpu_dispatch_ops = { + .select_cpu = (void *) select_cpu_dispatch_select_cpu, + .name = "select_cpu_dispatch", + .timeout_ms = 1000U, +}; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.c new file mode 100644 index 0000000000000000000000000000000000000000..80283dbc41b7ece849d8c3ca8ff7b0734ec5cc5b --- /dev/null +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.c @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ +#include +#include +#include +#include +#include "select_cpu_dispatch.bpf.skel.h" +#include "scx_test.h" + +#define NUM_CHILDREN 1028 + +static enum scx_test_status setup(void **ctx) +{ + struct select_cpu_dispatch *skel; + + skel = select_cpu_dispatch__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dispatch__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct select_cpu_dispatch *skel = ctx; + struct bpf_link *link; + pid_t pids[NUM_CHILDREN]; + int i, status; + + link = bpf_map__attach_struct_ops(skel->maps.select_cpu_dispatch_ops); + SCX_FAIL_IF(!link, "Failed to attach scheduler"); + + for (i = 0; i < NUM_CHILDREN; i++) { + pids[i] = fork(); + if (pids[i] == 0) { + sleep(1); + exit(0); + } + } + + for (i = 0; i < NUM_CHILDREN; i++) { + SCX_EQ(waitpid(pids[i], &status, 0), pids[i]); + SCX_EQ(status, 0); + } + + bpf_link__destroy(link); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct select_cpu_dispatch *skel = ctx; + + select_cpu_dispatch__destroy(skel); +} + +struct scx_test select_cpu_dispatch = { + .name = "select_cpu_dispatch", + .description = "Test direct dispatching to built-in DSQs from " + "ops.select_cpu()", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&select_cpu_dispatch) diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..2a75de11b2cfd59b86ce6ed36ee676b4655708ba --- /dev/null +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A scheduler that validates the behavior of direct dispatching with a default + * select_cpu implementation. + * + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ + +#include + +char _license[] SEC("license") = "GPL"; + +UEI_DEFINE(uei); + +s32 BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_select_cpu, struct task_struct *p, + s32 prev_cpu, u64 wake_flags) +{ + /* Dispatching to a random DSQ should fail. */ + scx_bpf_dsq_insert(p, 0xcafef00d, SCX_SLICE_DFL, 0); + + return prev_cpu; +} + +void BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops select_cpu_dispatch_bad_dsq_ops = { + .select_cpu = (void *) select_cpu_dispatch_bad_dsq_select_cpu, + .exit = (void *) select_cpu_dispatch_bad_dsq_exit, + .name = "select_cpu_dispatch_bad_dsq", + .timeout_ms = 1000U, +}; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c new file mode 100644 index 0000000000000000000000000000000000000000..5e72ebbc90a5aa3f29690aea94da282f22dc5c0f --- /dev/null +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ +#include +#include +#include +#include +#include "select_cpu_dispatch_bad_dsq.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status setup(void **ctx) +{ + struct select_cpu_dispatch_bad_dsq *skel; + + skel = select_cpu_dispatch_bad_dsq__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dispatch_bad_dsq__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct select_cpu_dispatch_bad_dsq *skel = ctx; + struct bpf_link *link; + + link = bpf_map__attach_struct_ops(skel->maps.select_cpu_dispatch_bad_dsq_ops); + SCX_FAIL_IF(!link, "Failed to attach scheduler"); + + sleep(1); + + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR)); + bpf_link__destroy(link); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct select_cpu_dispatch_bad_dsq *skel = ctx; + + select_cpu_dispatch_bad_dsq__destroy(skel); +} + +struct scx_test select_cpu_dispatch_bad_dsq = { + .name = "select_cpu_dispatch_bad_dsq", + .description = "Verify graceful failure if we direct-dispatch to a " + "bogus DSQ in ops.select_cpu()", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&select_cpu_dispatch_bad_dsq) diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..99d075695c9743a4b817e48263f4467b8024ff9f --- /dev/null +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A scheduler that validates the behavior of direct dispatching with a default + * select_cpu implementation. + * + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ + +#include + +char _license[] SEC("license") = "GPL"; + +UEI_DEFINE(uei); + +s32 BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_select_cpu, struct task_struct *p, + s32 prev_cpu, u64 wake_flags) +{ + /* Dispatching twice in a row is disallowed. */ + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + + return prev_cpu; +} + +void BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops select_cpu_dispatch_dbl_dsp_ops = { + .select_cpu = (void *) select_cpu_dispatch_dbl_dsp_select_cpu, + .exit = (void *) select_cpu_dispatch_dbl_dsp_exit, + .name = "select_cpu_dispatch_dbl_dsp", + .timeout_ms = 1000U, +}; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c new file mode 100644 index 0000000000000000000000000000000000000000..aa85949478bcf4e22193bb5fcb7ed3c5c69e85fd --- /dev/null +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2023 David Vernet + * Copyright (c) 2023 Tejun Heo + */ +#include +#include +#include +#include +#include "select_cpu_dispatch_dbl_dsp.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status setup(void **ctx) +{ + struct select_cpu_dispatch_dbl_dsp *skel; + + skel = select_cpu_dispatch_dbl_dsp__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dispatch_dbl_dsp__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct select_cpu_dispatch_dbl_dsp *skel = ctx; + struct bpf_link *link; + + link = bpf_map__attach_struct_ops(skel->maps.select_cpu_dispatch_dbl_dsp_ops); + SCX_FAIL_IF(!link, "Failed to attach scheduler"); + + sleep(1); + + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR)); + bpf_link__destroy(link); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct select_cpu_dispatch_dbl_dsp *skel = ctx; + + select_cpu_dispatch_dbl_dsp__destroy(skel); +} + +struct scx_test select_cpu_dispatch_dbl_dsp = { + .name = "select_cpu_dispatch_dbl_dsp", + .description = "Verify graceful failure if we dispatch twice to a " + "DSQ in ops.select_cpu()", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&select_cpu_dispatch_dbl_dsp) diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c new file mode 100644 index 0000000000000000000000000000000000000000..bfcb96cd4954bdd65b3c5f8217eb145aafd9010e --- /dev/null +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c @@ -0,0 +1,92 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * A scheduler that validates that enqueue flags are properly stored and + * applied at dispatch time when a task is directly dispatched from + * ops.select_cpu(). We validate this by using scx_bpf_dsq_insert_vtime(), + * and making the test a very basic vtime scheduler. + * + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + * Copyright (c) 2024 Tejun Heo + */ + +#include + +char _license[] SEC("license") = "GPL"; + +volatile bool consumed; + +static u64 vtime_now; + +#define VTIME_DSQ 0 + +static inline bool vtime_before(u64 a, u64 b) +{ + return (s64)(a - b) < 0; +} + +static inline u64 task_vtime(const struct task_struct *p) +{ + u64 vtime = p->scx.dsq_vtime; + + if (vtime_before(vtime, vtime_now - SCX_SLICE_DFL)) + return vtime_now - SCX_SLICE_DFL; + else + return vtime; +} + +s32 BPF_STRUCT_OPS(select_cpu_vtime_select_cpu, struct task_struct *p, + s32 prev_cpu, u64 wake_flags) +{ + s32 cpu; + + cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0); + if (cpu >= 0) + goto ddsp; + + cpu = prev_cpu; + scx_bpf_test_and_clear_cpu_idle(cpu); +ddsp: + scx_bpf_dsq_insert_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0); + return cpu; +} + +void BPF_STRUCT_OPS(select_cpu_vtime_dispatch, s32 cpu, struct task_struct *p) +{ + if (scx_bpf_dsq_move_to_local(VTIME_DSQ)) + consumed = true; +} + +void BPF_STRUCT_OPS(select_cpu_vtime_running, struct task_struct *p) +{ + if (vtime_before(vtime_now, p->scx.dsq_vtime)) + vtime_now = p->scx.dsq_vtime; +} + +void BPF_STRUCT_OPS(select_cpu_vtime_stopping, struct task_struct *p, + bool runnable) +{ + p->scx.dsq_vtime += (SCX_SLICE_DFL - p->scx.slice) * 100 / p->scx.weight; +} + +void BPF_STRUCT_OPS(select_cpu_vtime_enable, struct task_struct *p) +{ + p->scx.dsq_vtime = vtime_now; +} + +s32 BPF_STRUCT_OPS_SLEEPABLE(select_cpu_vtime_init) +{ + return scx_bpf_create_dsq(VTIME_DSQ, -1); +} + +SEC(".struct_ops.link") +struct sched_ext_ops select_cpu_vtime_ops = { + .select_cpu = (void *) select_cpu_vtime_select_cpu, + .dispatch = (void *) select_cpu_vtime_dispatch, + .running = (void *) select_cpu_vtime_running, + .stopping = (void *) select_cpu_vtime_stopping, + .enable = (void *) select_cpu_vtime_enable, + .init = (void *) select_cpu_vtime_init, + .name = "select_cpu_vtime", + .timeout_ms = 1000U, +}; diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.c new file mode 100644 index 0000000000000000000000000000000000000000..1e9b5c9bfff1d3559395cf12b87294288ada081c --- /dev/null +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.c @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + * Copyright (c) 2024 Tejun Heo + */ +#include +#include +#include +#include +#include "select_cpu_vtime.bpf.skel.h" +#include "scx_test.h" + +static enum scx_test_status setup(void **ctx) +{ + struct select_cpu_vtime *skel; + + skel = select_cpu_vtime__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_vtime__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct select_cpu_vtime *skel = ctx; + struct bpf_link *link; + + SCX_ASSERT(!skel->bss->consumed); + + link = bpf_map__attach_struct_ops(skel->maps.select_cpu_vtime_ops); + SCX_FAIL_IF(!link, "Failed to attach scheduler"); + + sleep(1); + + SCX_ASSERT(skel->bss->consumed); + + bpf_link__destroy(link); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct select_cpu_vtime *skel = ctx; + + select_cpu_vtime__destroy(skel); +} + +struct scx_test select_cpu_vtime = { + .name = "select_cpu_vtime", + .description = "Test doing direct vtime-dispatching from " + "ops.select_cpu(), to a non-built-in DSQ", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&select_cpu_vtime) diff --git a/tools/testing/selftests/sched_ext/test_example.c b/tools/testing/selftests/sched_ext/test_example.c new file mode 100644 index 0000000000000000000000000000000000000000..ce36cdf03cdc5a15ed02825999d753cf167a13c8 --- /dev/null +++ b/tools/testing/selftests/sched_ext/test_example.c @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 Tejun Heo + * Copyright (c) 2024 David Vernet + */ +#include +#include +#include "scx_test.h" + +static bool setup_called = false; +static bool run_called = false; +static bool cleanup_called = false; + +static int context = 10; + +static enum scx_test_status setup(void **ctx) +{ + setup_called = true; + *ctx = &context; + + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + int *arg = ctx; + + SCX_ASSERT(setup_called); + SCX_ASSERT(!run_called && !cleanup_called); + SCX_EQ(*arg, context); + + run_called = true; + return SCX_TEST_PASS; +} + +static void cleanup (void *ctx) +{ + SCX_BUG_ON(!run_called || cleanup_called, "Wrong callbacks invoked"); +} + +struct scx_test example = { + .name = "example", + .description = "Validate the basic function of the test suite itself", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&example) diff --git a/tools/testing/selftests/sched_ext/util.c b/tools/testing/selftests/sched_ext/util.c new file mode 100644 index 0000000000000000000000000000000000000000..e47769c919187cd5cfa179b697cdb644a5e5235b --- /dev/null +++ b/tools/testing/selftests/sched_ext/util.c @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ +#include +#include +#include +#include +#include +#include + +/* Returns read len on success, or -errno on failure. */ +static ssize_t read_text(const char *path, char *buf, size_t max_len) +{ + ssize_t len; + int fd; + + fd = open(path, O_RDONLY); + if (fd < 0) + return -errno; + + len = read(fd, buf, max_len - 1); + + if (len >= 0) + buf[len] = 0; + + close(fd); + return len < 0 ? -errno : len; +} + +/* Returns written len on success, or -errno on failure. */ +static ssize_t write_text(const char *path, char *buf, ssize_t len) +{ + int fd; + ssize_t written; + + fd = open(path, O_WRONLY | O_APPEND); + if (fd < 0) + return -errno; + + written = write(fd, buf, len); + close(fd); + return written < 0 ? -errno : written; +} + +long file_read_long(const char *path) +{ + char buf[128]; + + + if (read_text(path, buf, sizeof(buf)) <= 0) + return -1; + + return atol(buf); +} + +int file_write_long(const char *path, long val) +{ + char buf[64]; + int ret; + + ret = sprintf(buf, "%lu", val); + if (ret < 0) + return ret; + + if (write_text(path, buf, sizeof(buf)) <= 0) + return -1; + + return 0; +} diff --git a/tools/testing/selftests/sched_ext/util.h b/tools/testing/selftests/sched_ext/util.h new file mode 100644 index 0000000000000000000000000000000000000000..bc13dfec1267aa5144ae19c17aff63c9ed91e279 --- /dev/null +++ b/tools/testing/selftests/sched_ext/util.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. + * Copyright (c) 2024 David Vernet + */ + +#ifndef __SCX_TEST_UTIL_H__ +#define __SCX_TEST_UTIL_H__ + +long file_read_long(const char *path); +int file_write_long(const char *path, long val); + +#endif // __SCX_TEST_H__