sched_ext: Implement sched_ext_ops.cpu_online/offline()

Add ops.cpu_online/offline() which are invoked when CPUs come online and
offline respectively. As the enqueue path already automatically bypasses
tasks to the local dsq on a deactivated CPU, BPF schedulers are guaranteed
to see tasks only on CPUs which are between online() and offline().

If the BPF scheduler doesn't implement ops.cpu_online/offline(), the
scheduler is automatically exited with SCX_ECODE_RESTART |
SCX_ECODE_RSN_HOTPLUG. Userspace can implement CPU hotpplug support
trivially by simply reinitializing and reloading the scheduler.

scx_qmap is updated to print out online CPUs on hotplug events. Other
schedulers are updated to restart based on ecode.

v3: - The previous implementation added @reason to
      sched_class.rq_on/offline() to distinguish between CPU hotplug events
      and topology updates. This was buggy and fragile as the methods are
      skipped if the current state equals the target state. Instead, add
      scx_rq_[de]activate() which are directly called from
      sched_cpu_de/activate(). This also allows ops.cpu_on/offline() to
      sleep which can be useful.

    - ops.dispatch() could be called on a CPU that the BPF scheduler was
      told to be offline. The dispatch patch is updated to bypass in such
      cases.

v2: - To accommodate lock ordering change between scx_cgroup_rwsem and
      cpus_read_lock(), CPU hotplug operations are put into its own SCX_OPI
      block and enabled eariler during scx_ope_enable() so that
      cpus_read_lock() can be dropped before acquiring scx_cgroup_rwsem.

    - Auto exit with ECODE added.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: David Vernet <dvernet@meta.com>
Acked-by: Josh Don <joshdon@google.com>
Acked-by: Hao Luo <haoluo@google.com>
Acked-by: Barret Rhoden <brho@google.com>

2 files changed, 54 insertions, 0 deletions

diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h
index c58024c980c8..cc56ff9aa252 100644
--- a/tools/sched_ext/include/scx/compat.h
+++ b/tools/sched_ext/include/scx/compat.h
@@ -8,6 +8,9 @@
 #define __SCX_COMPAT_H
 
 #include <bpf/btf.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <unistd.h>
 
 struct btf *__COMPAT_vmlinux_btf __attribute__((weak));
 
@@ -106,6 +109,28 @@ static inline bool __COMPAT_struct_has_field(const char *type, const char *field
 #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
@@ -123,6 +148,7 @@ static inline bool __COMPAT_struct_has_field(const char *type, const char *field
 										\
 	__skel = __scx_name##__open();						\
 	SCX_BUG_ON(!__skel, "Could not open " #__scx_name);			\
+	__skel->struct_ops.__ops_name->hotplug_seq = scx_hotplug_seq();		\
 	__skel; 								\
 })
 
diff --git a/tools/sched_ext/include/scx/user_exit_info.h b/tools/sched_ext/include/scx/user_exit_info.h
index c2ef85c645e1..891693ee604e 100644
--- a/tools/sched_ext/include/scx/user_exit_info.h
+++ b/tools/sched_ext/include/scx/user_exit_info.h
@@ -77,7 +77,35 @@ struct user_exit_info {
 	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 */