sched: Add new scheduler syscalls to support an extended scheduling parameters ABI

Add the syscalls needed for supporting scheduling algorithms
with extended scheduling parameters (e.g., SCHED_DEADLINE).

In general, it makes possible to specify a periodic/sporadic task,
that executes for a given amount of runtime at each instance, and is
scheduled according to the urgency of their own timing constraints,
i.e.:

 - a (maximum/typical) instance execution time,
 - a minimum interval between consecutive instances,
 - a time constraint by which each instance must be completed.

Thus, both the data structure that holds the scheduling parameters of
the tasks and the system calls dealing with it must be extended.
Unfortunately, modifying the existing struct sched_param would break
the ABI and result in potentially serious compatibility issues with
legacy binaries.

For these reasons, this patch:

 - defines the new struct sched_attr, containing all the fields
   that are necessary for specifying a task in the computational
   model described above;

 - defines and implements the new scheduling related syscalls that
   manipulate it, i.e., sched_setattr() and sched_getattr().

Syscalls are introduced for x86 (32 and 64 bits) and ARM only, as a
proof of concept and for developing and testing purposes. Making them
available on other architectures is straightforward.

Since no "user" for these new parameters is introduced in this patch,
the implementation of the new system calls is just identical to their
already existing counterpart. Future patches that implement scheduling
policies able to exploit the new data structure must also take care of
modifying the sched_*attr() calls accordingly with their own purposes.

Signed-off-by: Dario Faggioli <raistlin@linux.it>
[ Rewrote to use sched_attr. ]
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
[ Removed sched_setscheduler2() for now. ]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-3-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/arm/include/asm/unistd.h

@@ -15,7 +15,7 @@
 
 #include <uapi/asm/unistd.h>
 
-#define __NR_syscalls  (380)
+#define __NR_syscalls  (384)
 #define __ARM_NR_cmpxchg		(__ARM_NR_BASE+0x00fff0)
 
 #define __ARCH_WANT_STAT64

arch/arm/include/uapi/asm/unistd.h

@@ -406,6 +406,8 @@
 #define __NR_process_vm_writev		(__NR_SYSCALL_BASE+377)
 #define __NR_kcmp			(__NR_SYSCALL_BASE+378)
 #define __NR_finit_module		(__NR_SYSCALL_BASE+379)
+#define __NR_sched_setattr		(__NR_SYSCALL_BASE+380)
+#define __NR_sched_getattr		(__NR_SYSCALL_BASE+381)
 
 /*
  * This may need to be greater than __NR_last_syscall+1 in order to

arch/arm/kernel/calls.S

@@ -389,6 +389,8 @@
 		CALL(sys_process_vm_writev)
 		CALL(sys_kcmp)
 		CALL(sys_finit_module)
+/* 380 */	CALL(sys_sched_setattr)
+		CALL(sys_sched_getattr)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted

arch/x86/syscalls/syscall_32.tbl

@@ -357,3 +357,5 @@
 348	i386	process_vm_writev	sys_process_vm_writev		compat_sys_process_vm_writev
 349	i386	kcmp			sys_kcmp
 350	i386	finit_module		sys_finit_module
+351	i386	sched_setattr		sys_sched_setattr
+352	i386	sched_getattr		sys_sched_getattr

arch/x86/syscalls/syscall_64.tbl

@@ -320,6 +320,8 @@
 311	64	process_vm_writev	sys_process_vm_writev
 312	common	kcmp			sys_kcmp
 313	common	finit_module		sys_finit_module
+314	common	sched_setattr		sys_sched_setattr
+315	common	sched_getattr		sys_sched_getattr
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

include/linux/sched.h

@@ -56,6 +56,66 @@ struct sched_param {
 
 #include <asm/processor.h>
 
+#define SCHED_ATTR_SIZE_VER0	48	/* sizeof first published struct */
+
+/*
+ * Extended scheduling parameters data structure.
+ *
+ * This is needed because the original struct sched_param can not be
+ * altered without introducing ABI issues with legacy applications
+ * (e.g., in sched_getparam()).
+ *
+ * However, the possibility of specifying more than just a priority for
+ * the tasks may be useful for a wide variety of application fields, e.g.,
+ * multimedia, streaming, automation and control, and many others.
+ *
+ * This variant (sched_attr) is meant at describing a so-called
+ * sporadic time-constrained task. In such model a task is specified by:
+ *  - the activation period or minimum instance inter-arrival time;
+ *  - the maximum (or average, depending on the actual scheduling
+ *    discipline) computation time of all instances, a.k.a. runtime;
+ *  - the deadline (relative to the actual activation time) of each
+ *    instance.
+ * Very briefly, a periodic (sporadic) task asks for the execution of
+ * some specific computation --which is typically called an instance--
+ * (at most) every period. Moreover, each instance typically lasts no more
+ * than the runtime and must be completed by time instant t equal to
+ * the instance activation time + the deadline.
+ *
+ * This is reflected by the actual fields of the sched_attr structure:
+ *
+ *  @size		size of the structure, for fwd/bwd compat.
+ *
+ *  @sched_policy	task's scheduling policy
+ *  @sched_flags	for customizing the scheduler behaviour
+ *  @sched_nice		task's nice value      (SCHED_NORMAL/BATCH)
+ *  @sched_priority	task's static priority (SCHED_FIFO/RR)
+ *  @sched_deadline	representative of the task's deadline
+ *  @sched_runtime	representative of the task's runtime
+ *  @sched_period	representative of the task's period
+ *
+ * Given this task model, there are a multiplicity of scheduling algorithms
+ * and policies, that can be used to ensure all the tasks will make their
+ * timing constraints.
+ */
+struct sched_attr {
+	u32 size;
+
+	u32 sched_policy;
+	u64 sched_flags;
+
+	/* SCHED_NORMAL, SCHED_BATCH */
+	s32 sched_nice;
+
+	/* SCHED_FIFO, SCHED_RR */
+	u32 sched_priority;
+
+	/* SCHED_DEADLINE */
+	u64 sched_runtime;
+	u64 sched_deadline;
+	u64 sched_period;
+};
+
 struct exec_domain;
 struct futex_pi_state;
 struct robust_list_head;
@@ -1958,6 +2018,8 @@ extern int sched_setscheduler(struct task_struct *, int,
 			      const struct sched_param *);
 extern int sched_setscheduler_nocheck(struct task_struct *, int,
 				      const struct sched_param *);
+extern int sched_setattr(struct task_struct *,
+			 const struct sched_attr *);
 extern struct task_struct *idle_task(int cpu);
 /**
  * is_idle_task - is the specified task an idle task?

include/linux/syscalls.h

@@ -38,6 +38,7 @@ struct rlimit;
 struct rlimit64;
 struct rusage;
 struct sched_param;
+struct sched_attr;
 struct sel_arg_struct;
 struct semaphore;
 struct sembuf;
@@ -279,9 +280,14 @@ asmlinkage long sys_sched_setscheduler(pid_t pid, int policy,
 					struct sched_param __user *param);
 asmlinkage long sys_sched_setparam(pid_t pid,
 					struct sched_param __user *param);
+asmlinkage long sys_sched_setattr(pid_t pid,
+					struct sched_attr __user *attr);
 asmlinkage long sys_sched_getscheduler(pid_t pid);
 asmlinkage long sys_sched_getparam(pid_t pid,
 					struct sched_param __user *param);
+asmlinkage long sys_sched_getattr(pid_t pid,
+					struct sched_attr __user *attr,
+					unsigned int size);
 asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
 					unsigned long __user *user_mask_ptr);
 asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,

kernel/sched/core.c

@@ -2817,6 +2817,7 @@ out_unlock:
 	__task_rq_unlock(rq);
 }
 #endif
+
 void set_user_nice(struct task_struct *p, long nice)
 {
 	int old_prio, delta, on_rq;
@@ -2991,22 +2992,29 @@ static struct task_struct *find_process_by_pid(pid_t pid)
 	return pid ? find_task_by_vpid(pid) : current;
 }
 
-/* Actually do priority change: must hold rq lock. */
+/* Actually do priority change: must hold pi & rq lock. */
-static void
+static void __setscheduler(struct rq *rq, struct task_struct *p,
-__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
+			   const struct sched_attr *attr)
 {
+	int policy = attr->sched_policy;
+
 	p->policy = policy;
-	p->rt_priority = prio;
+
+	if (rt_policy(policy))
+		p->rt_priority = attr->sched_priority;
+	else
+		p->static_prio = NICE_TO_PRIO(attr->sched_nice);
+
 	p->normal_prio = normal_prio(p);
-	/* we are holding p->pi_lock already */
 	p->prio = rt_mutex_getprio(p);
+
 	if (rt_prio(p->prio))
 		p->sched_class = &rt_sched_class;
 	else
 		p->sched_class = &fair_sched_class;
+
 	set_load_weight(p);
 }
-
 /*
  * check the target process has a UID that matches the current process's
  */
@@ -3023,10 +3031,12 @@ static bool check_same_owner(struct task_struct *p)
 	return match;
 }
 
-static int __sched_setscheduler(struct task_struct *p, int policy,
+static int __sched_setscheduler(struct task_struct *p,
-				const struct sched_param *param, bool user)
+				const struct sched_attr *attr,
+				bool user)
 {
 	int retval, oldprio, oldpolicy = -1, on_rq, running;
+	int policy = attr->sched_policy;
 	unsigned long flags;
 	const struct sched_class *prev_class;
 	struct rq *rq;
@@ -3054,17 +3064,22 @@ recheck:
 	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
 	 * SCHED_BATCH and SCHED_IDLE is 0.
 	 */
-	if (param->sched_priority < 0 ||
+	if (attr->sched_priority < 0 ||
-	    (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
+	    (p->mm && attr->sched_priority > MAX_USER_RT_PRIO-1) ||
-	    (!p->mm && param->sched_priority > MAX_RT_PRIO-1))
+	    (!p->mm && attr->sched_priority > MAX_RT_PRIO-1))
 		return -EINVAL;
-	if (rt_policy(policy) != (param->sched_priority != 0))
+	if (rt_policy(policy) != (attr->sched_priority != 0))
 		return -EINVAL;
 
 	/*
 	 * Allow unprivileged RT tasks to decrease priority:
 	 */
 	if (user && !capable(CAP_SYS_NICE)) {
+		if (fair_policy(policy)) {
+			if (!can_nice(p, attr->sched_nice))
+				return -EPERM;
+		}
+
 		if (rt_policy(policy)) {
 			unsigned long rlim_rtprio =
 					task_rlimit(p, RLIMIT_RTPRIO);
@@ -3074,8 +3089,8 @@ recheck:
 				return -EPERM;
 
 			/* can't increase priority */
-			if (param->sched_priority > p->rt_priority &&
+			if (attr->sched_priority > p->rt_priority &&
-			    param->sched_priority > rlim_rtprio)
+			    attr->sched_priority > rlim_rtprio)
 				return -EPERM;
 		}
 
@@ -3123,11 +3138,16 @@ recheck:
 	/*
 	 * If not changing anything there's no need to proceed further:
 	 */
-	if (unlikely(policy == p->policy && (!rt_policy(policy) ||
+	if (unlikely(policy == p->policy)) {
-			param->sched_priority == p->rt_priority))) {
+		if (fair_policy(policy) && attr->sched_nice != TASK_NICE(p))
+			goto change;
+		if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
+			goto change;
+
 		task_rq_unlock(rq, p, &flags);
 		return 0;
 	}
+change:
 
 #ifdef CONFIG_RT_GROUP_SCHED
 	if (user) {
@@ -3161,7 +3181,7 @@ recheck:
 
 	oldprio = p->prio;
 	prev_class = p->sched_class;
-	__setscheduler(rq, p, policy, param->sched_priority);
+	__setscheduler(rq, p, attr);
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
@@ -3189,10 +3209,20 @@ recheck:
 int sched_setscheduler(struct task_struct *p, int policy,
 		       const struct sched_param *param)
 {
-	return __sched_setscheduler(p, policy, param, true);
+	struct sched_attr attr = {
+		.sched_policy   = policy,
+		.sched_priority = param->sched_priority
+	};
+	return __sched_setscheduler(p, &attr, true);
 }
 EXPORT_SYMBOL_GPL(sched_setscheduler);
 
+int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
+{
+	return __sched_setscheduler(p, attr, true);
+}
+EXPORT_SYMBOL_GPL(sched_setattr);
+
 /**
  * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
  * @p: the task in question.
@@ -3209,7 +3239,11 @@ EXPORT_SYMBOL_GPL(sched_setscheduler);
 int sched_setscheduler_nocheck(struct task_struct *p, int policy,
 			       const struct sched_param *param)
 {
-	return __sched_setscheduler(p, policy, param, false);
+	struct sched_attr attr = {
+		.sched_policy   = policy,
+		.sched_priority = param->sched_priority
+	};
+	return __sched_setscheduler(p, &attr, false);
 }
 
 static int
@@ -3234,6 +3268,79 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 	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;
+
+	if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0))
+		return -EFAULT;
+
+	/*
+	 * 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;
+
+	if (size > PAGE_SIZE)	/* silly large */
+		goto err_size;
+
+	if (!size)		/* abi compat */
+		size = SCHED_ATTR_SIZE_VER0;
+
+	if (size < SCHED_ATTR_SIZE_VER0)
+		goto err_size;
+
+	/*
+	 * If we're handed a bigger struct than we know of,
+	 * ensure all the unknown bits are 0 - i.e. new
+	 * user-space does not rely on any kernel feature
+	 * extensions we dont know about yet.
+	 */
+	if (size > sizeof(*attr)) {
+		unsigned char __user *addr;
+		unsigned char __user *end;
+		unsigned char val;
+
+		addr = (void __user *)uattr + sizeof(*attr);
+		end  = (void __user *)uattr + size;
+
+		for (; addr < end; addr++) {
+			ret = get_user(val, addr);
+			if (ret)
+				return ret;
+			if (val)
+				goto err_size;
+		}
+		size = sizeof(*attr);
+	}
+
+	ret = copy_from_user(attr, uattr, size);
+	if (ret)
+		return -EFAULT;
+
+	/*
+	 * 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, -20, 19);
+
+out:
+	return ret;
+
+err_size:
+	put_user(sizeof(*attr), &uattr->size);
+	ret = -E2BIG;
+	goto out;
+}
+
 /**
  * sys_sched_setscheduler - set/change the scheduler policy and RT priority
  * @pid: the pid in question.
@@ -3264,6 +3371,33 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
 	return do_sched_setscheduler(pid, -1, param);
 }
 
+/**
+ * sys_sched_setattr - same as above, but with extended sched_attr
+ * @pid: the pid in question.
+ * @attr: structure containing the extended parameters.
+ */
+SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr)
+{
+	struct sched_attr attr;
+	struct task_struct *p;
+	int retval;
+
+	if (!uattr || pid < 0)
+		return -EINVAL;
+
+	if (sched_copy_attr(uattr, &attr))
+		return -EFAULT;
+
+	rcu_read_lock();
+	retval = -ESRCH;
+	p = find_process_by_pid(pid);
+	if (p != NULL)
+		retval = sched_setattr(p, &attr);
+	rcu_read_unlock();
+
+	return retval;
+}
+
 /**
  * sys_sched_getscheduler - get the policy (scheduling class) of a thread
  * @pid: the pid in question.
@@ -3334,6 +3468,92 @@ out_unlock:
 	return retval;
 }
 
+static int sched_read_attr(struct sched_attr __user *uattr,
+			   struct sched_attr *attr,
+			   unsigned int usize)
+{
+	int ret;
+
+	if (!access_ok(VERIFY_WRITE, uattr, usize))
+		return -EFAULT;
+
+	/*
+	 * If we're handed a smaller struct than we know of,
+	 * ensure all the unknown bits are 0 - i.e. old
+	 * user-space does not get uncomplete information.
+	 */
+	if (usize < sizeof(*attr)) {
+		unsigned char *addr;
+		unsigned char *end;
+
+		addr = (void *)attr + usize;
+		end  = (void *)attr + sizeof(*attr);
+
+		for (; addr < end; addr++) {
+			if (*addr)
+				goto err_size;
+		}
+
+		attr->size = usize;
+	}
+
+	ret = copy_to_user(uattr, attr, usize);
+	if (ret)
+		return -EFAULT;
+
+out:
+	return ret;
+
+err_size:
+	ret = -E2BIG;
+	goto out;
+}
+
+/**
+ * sys_sched_getattr - same as above, but with extended "sched_param"
+ * @pid: the pid in question.
+ * @attr: structure containing the extended parameters.
+ * @size: sizeof(attr) for fwd/bwd comp.
+ */
+SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
+		unsigned int, size)
+{
+	struct sched_attr attr = {
+		.size = sizeof(struct sched_attr),
+	};
+	struct task_struct *p;
+	int retval;
+
+	if (!uattr || pid < 0 || size > PAGE_SIZE ||
+	    size < SCHED_ATTR_SIZE_VER0)
+		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;
+
+	attr.sched_policy = p->policy;
+	if (task_has_rt_policy(p))
+		attr.sched_priority = p->rt_priority;
+	else
+		attr.sched_nice = TASK_NICE(p);
+
+	rcu_read_unlock();
+
+	retval = sched_read_attr(uattr, &attr, size);
+	return retval;
+
+out_unlock:
+	rcu_read_unlock();
+	return retval;
+}
+
 long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 {
 	cpumask_var_t cpus_allowed, new_mask;
@@ -6400,13 +6620,16 @@ EXPORT_SYMBOL(__might_sleep);
 static void normalize_task(struct rq *rq, struct task_struct *p)
 {
 	const struct sched_class *prev_class = p->sched_class;
+	struct sched_attr attr = {
+		.sched_policy = SCHED_NORMAL,
+	};
 	int old_prio = p->prio;
 	int on_rq;
 
 	on_rq = p->on_rq;
 	if (on_rq)
 		dequeue_task(rq, p, 0);
-	__setscheduler(rq, p, SCHED_NORMAL, 0);
+	__setscheduler(rq, p, &attr);
 	if (on_rq) {
 		enqueue_task(rq, p, 0);
 		resched_task(rq->curr);

kernel/sched/sched.h

@@ -81,11 +81,14 @@ extern void update_cpu_load_active(struct rq *this_rq);
  */
 #define RUNTIME_INF	((u64)~0ULL)
 
+static inline int fair_policy(int policy)
+{
+	return policy == SCHED_NORMAL || policy == SCHED_BATCH;
+}
+
 static inline int rt_policy(int policy)
 {
-	if (policy == SCHED_FIFO || policy == SCHED_RR)
+	return policy == SCHED_FIFO || policy == SCHED_RR;
-		return 1;
-	return 0;
 }
 
 static inline int task_has_rt_policy(struct task_struct *p)