| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20250206202109.384179-6-arighi@nvidia.com>
Date: Thu, 6 Feb 2025 21:15:35 +0100
From: Andrea Righi <arighi@...dia.com>
To: Tejun Heo <tj@...nel.org>,
David Vernet <void@...ifault.com>,
Changwoo Min <changwoo@...lia.com>
Cc: Ingo Molnar <mingo@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Juri Lelli <juri.lelli@...hat.com>,
Vincent Guittot <vincent.guittot@...aro.org>,
Dietmar Eggemann <dietmar.eggemann@....com>,
Steven Rostedt <rostedt@...dmis.org>,
Ben Segall <bsegall@...gle.com>,
Mel Gorman <mgorman@...e.de>,
Valentin Schneider <vschneid@...hat.com>,
Ian May <ianm@...dia.com>,
bpf@...r.kernel.org,
linux-kernel@...r.kernel.org
Subject: [PATCH 5/5] sched_ext: idle: Introduce node-aware idle cpu kfunc helpers
Add the following kfunc's to provide scx schedulers direct access to
per-node idle cpumasks information:
int scx_bpf_cpu_to_node(s32 cpu)
const struct cpumask *scx_bpf_get_idle_cpumask_node(int node)
const struct cpumask *scx_bpf_get_idle_smtmask_node(int node)
s32 scx_bpf_pick_idle_cpu_node(const cpumask_t *cpus_allowed,
int node, u64 flags)
Signed-off-by: Andrea Righi <arighi@...dia.com>
---
kernel/sched/ext_idle.c | 121 +++++++++++++++++++++++
tools/sched_ext/include/scx/common.bpf.h | 4 +
tools/sched_ext/include/scx/compat.bpf.h | 19 ++++
3 files changed, 144 insertions(+)
diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index 0deef6987f76e..df8cd76c86fdd 100644
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -680,6 +680,33 @@ void __scx_update_idle(struct rq *rq, bool idle, bool do_notify)
/********************************************************************************
* Helpers that can be called from the BPF scheduler.
*/
+
+static int validate_node(int node)
+{
+ if (!static_branch_likely(&scx_builtin_idle_per_node)) {
+ scx_ops_error("per-node idle tracking is disabled");
+ return -ENOTSUPP;
+ }
+
+ /* Return no entry for NUMA_NO_NODE (not a critical scx error) */
+ if (node == NUMA_NO_NODE)
+ return -ENOENT;
+
+ /* Make sure node is in a valid range */
+ if (node < 0 || node >= nr_node_ids) {
+ scx_ops_error("invalid node %d", node);
+ return -EINVAL;
+ }
+
+ /* Make sure the node is part of the set of possible nodes */
+ if (!node_possible(node)) {
+ scx_ops_error("unavailable node %d", node);
+ return -EINVAL;
+ }
+
+ return node;
+}
+
__bpf_kfunc_start_defs();
static bool check_builtin_idle_enabled(void)
@@ -691,6 +718,21 @@ static bool check_builtin_idle_enabled(void)
return false;
}
+/**
+ * scx_bpf_cpu_to_node - Return the NUMA node the given @cpu belongs to
+ */
+__bpf_kfunc int scx_bpf_cpu_to_node(s32 cpu)
+{
+#ifdef CONFIG_NUMA
+ if (cpu < 0 || cpu >= nr_cpu_ids)
+ return -EINVAL;
+
+ return idle_cpu_to_node(cpu);
+#else
+ return 0;
+#endif
+}
+
/**
* scx_bpf_select_cpu_dfl - The default implementation of ops.select_cpu()
* @p: task_struct to select a CPU for
@@ -723,6 +765,27 @@ __bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu,
return prev_cpu;
}
+/**
+ * scx_bpf_get_idle_cpumask_node - Get a referenced kptr to the
+ * idle-tracking per-CPU cpumask of a target NUMA node.
+ *
+ * Returns an empty cpumask if idle tracking is not enabled, if @node is
+ * not valid, or running on a UP kernel. In this case the actual error will
+ * be reported to the BPF scheduler via scx_ops_error().
+ */
+__bpf_kfunc const struct cpumask *scx_bpf_get_idle_cpumask_node(int node)
+{
+ node = validate_node(node);
+ if (node < 0)
+ return cpu_none_mask;
+
+#ifdef CONFIG_SMP
+ return idle_cpumask(node)->cpu;
+#else
+ return cpu_none_mask;
+#endif
+}
+
/**
* scx_bpf_get_idle_cpumask - Get a referenced kptr to the idle-tracking
* per-CPU cpumask.
@@ -747,6 +810,31 @@ __bpf_kfunc const struct cpumask *scx_bpf_get_idle_cpumask(void)
#endif
}
+/**
+ * scx_bpf_get_idle_smtmask_node - Get a referenced kptr to the
+ * idle-tracking, per-physical-core cpumask of a target NUMA node. Can be
+ * used to determine if an entire physical core is free.
+ *
+ * Returns an empty cpumask if idle tracking is not enabled, if @node is
+ * not valid, or running on a UP kernel. In this case the actual error will
+ * be reported to the BPF scheduler via scx_ops_error().
+ */
+__bpf_kfunc const struct cpumask *scx_bpf_get_idle_smtmask_node(int node)
+{
+ node = validate_node(node);
+ if (node < 0)
+ return cpu_none_mask;
+
+#ifdef CONFIG_SMP
+ if (sched_smt_active())
+ return idle_cpumask(node)->smt;
+ else
+ return idle_cpumask(node)->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
@@ -811,6 +899,35 @@ __bpf_kfunc bool scx_bpf_test_and_clear_cpu_idle(s32 cpu)
return false;
}
+/**
+ * scx_bpf_pick_idle_cpu_node - Pick and claim an idle cpu from a NUMA node
+ * @cpus_allowed: Allowed cpumask
+ * @node: target NUMA node
+ * @flags: %SCX_PICK_IDLE_* flags
+ *
+ * Pick and claim an idle cpu in @cpus_allowed from the NUMA node @node.
+ *
+ * Returns the picked idle cpu number on success, or -%EBUSY if no matching
+ * cpu was found.
+ *
+ * The search starts from @node and proceeds to other online NUMA nodes in
+ * order of increasing distance (unless SCX_PICK_IDLE_IN_NODE is specified,
+ * in which case the search is limited to the target @node).
+ *
+ * Always returns an error if ops.update_idle() is implemented and
+ * %SCX_OPS_KEEP_BUILTIN_IDLE is not set, or if
+ * %SCX_OPS_BUILTIN_IDLE_PER_NODE is not set.
+ */
+__bpf_kfunc s32 scx_bpf_pick_idle_cpu_node(const struct cpumask *cpus_allowed,
+ int node, u64 flags)
+{
+ node = validate_node(node);
+ if (node < 0)
+ return node;
+
+ return scx_pick_idle_cpu(cpus_allowed, node, flags);
+}
+
/**
* scx_bpf_pick_idle_cpu - Pick and claim an idle cpu
* @cpus_allowed: Allowed cpumask
@@ -874,10 +991,14 @@ __bpf_kfunc s32 scx_bpf_pick_any_cpu(const struct cpumask *cpus_allowed,
__bpf_kfunc_end_defs();
BTF_KFUNCS_START(scx_kfunc_ids_idle)
+BTF_ID_FLAGS(func, scx_bpf_cpu_to_node)
+BTF_ID_FLAGS(func, scx_bpf_get_idle_cpumask_node, KF_ACQUIRE)
BTF_ID_FLAGS(func, scx_bpf_get_idle_cpumask, KF_ACQUIRE)
+BTF_ID_FLAGS(func, scx_bpf_get_idle_smtmask_node, 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_node, KF_RCU)
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)
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index 7055400030241..7dd8ba2964553 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -63,13 +63,17 @@ 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;
+int scx_bpf_cpu_to_node(s32 cpu) __ksym __weak;
const struct cpumask *scx_bpf_get_possible_cpumask(void) __ksym __weak;
const struct cpumask *scx_bpf_get_online_cpumask(void) __ksym __weak;
void scx_bpf_put_cpumask(const struct cpumask *cpumask) __ksym __weak;
+const struct cpumask *scx_bpf_get_idle_cpumask_node(int node) __ksym __weak;
const struct cpumask *scx_bpf_get_idle_cpumask(void) __ksym;
+const struct cpumask *scx_bpf_get_idle_smtmask_node(int node) __ksym __weak;
const struct cpumask *scx_bpf_get_idle_smtmask(void) __ksym;
void scx_bpf_put_idle_cpumask(const struct cpumask *cpumask) __ksym;
bool scx_bpf_test_and_clear_cpu_idle(s32 cpu) __ksym;
+s32 scx_bpf_pick_idle_cpu_node(const cpumask_t *cpus_allowed, int node, u64 flags) __ksym __weak;
s32 scx_bpf_pick_idle_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym;
s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym;
bool scx_bpf_task_running(const struct task_struct *p) __ksym;
diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h
index 50e1499ae0935..caa1a80f9a60c 100644
--- a/tools/sched_ext/include/scx/compat.bpf.h
+++ b/tools/sched_ext/include/scx/compat.bpf.h
@@ -130,6 +130,25 @@ bool scx_bpf_dispatch_vtime_from_dsq___compat(struct bpf_iter_scx_dsq *it__iter,
scx_bpf_now() : \
bpf_ktime_get_ns())
+#define __COMPAT_scx_bpf_cpu_to_node(cpu) \
+ (bpf_ksym_exists(scx_bpf_cpu_to_node) ? \
+ scx_bpf_cpu_to_node(cpu) : 0)
+
+#define __COMPAT_scx_bpf_get_idle_cpumask_node(node) \
+ (bpf_ksym_exists(scx_bpf_get_idle_cpumask_node) ? \
+ scx_bpf_get_idle_cpumask_node(node) : \
+ scx_bpf_get_idle_cpumask()) \
+
+#define __COMPAT_scx_bpf_get_idle_smtmask_node(node) \
+ (bpf_ksym_exists(scx_bpf_get_idle_smtmask_node) ? \
+ scx_bpf_get_idle_smtmask_node(node) : \
+ scx_bpf_get_idle_smtmask())
+
+#define __COMPAT_scx_bpf_pick_idle_cpu_node(cpus_allowed, node, flags) \
+ (bpf_ksym_exists(scx_bpf_pick_idle_cpu_node) ? \
+ scx_bpf_pick_idle_cpu_node(cpus_allowed, node, flags) : \
+ scx_bpf_pick_idle_cpu(cpus_allowed, flags))
+
/*
* Define sched_ext_ops. This may be expanded to define multiple variants for
* backward compatibility. See compat.h::SCX_OPS_LOAD/ATTACH().
--
2.48.1
Powered by blists - more mailing lists