[PATCH] 2.5: (better) syscalls for setting task affinity

[PATCH] 2.5: (better) syscalls for setting task affinity

[Robert Love]

[ This post adds length and pointer checks to the syscalls such that we
can portably change the size of cpus_allowed. ]

The attached patch implements a syscall interface for setting and
retrieving a task's CPU affinity (task->cpus_allowed):

	int sched_set_affinity(pid_t pid, unsigned int len,
			       unsigned long *new_mask_ptr);

	int sched_get_affinity(pid_t pid, unsigned int *user_len_ptr,
			       unsigned long *user_mask_ptr)

sched_set_affinity uses the set_cpus_allowed function in Ingo's new
scheduler to do all the hard work.  Additionally, this patch is based
off Ingo's previous syscall affinity patch and my proc-based affinity
patch.  Much credit to Ingo for this past work and his current
scheduler.

Security is enforced: calling user must match task's uid or euid or
possess CAP_SYS_NICE.

We can safely change the size of cpus_allowed.  One can use:

	sched_get_affinity(0, &len, NULL);

to get the size of cpus_allowed.  The use of this interface, thus,
should be portable as we scale cpus_allowed over sizeof(long).

I think exporting cpus_allowed as a bit mask is the proper user
interface for CPU affinity.  Certainly more complicated solutions exist,
but this should get the job done.  I have also updated my proc-based
solution although Ingo and others have flamed^Wconvinced me a
syscall-based interface is ideal.  I agree, mostly on the basis that
/proc may not be mounted but I have posted an updated proc-based
solution anyhow for proper discussion.

Patch is against 2.5.6-pre1.  Enjoy,

	Robert Love

diff -urN linus/arch/i386/kernel/entry.S linux/arch/i386/kernel/entry.S
--- linus/arch/i386/kernel/entry.S	Tue Feb 26 20:17:01 2002
+++ linux/arch/i386/kernel/entry.S	Tue Feb 26 20:44:06 2002
@@ -716,6 +716,8 @@
 	.long SYMBOL_NAME(sys_lremovexattr)
 	.long SYMBOL_NAME(sys_fremovexattr)
 	.long SYMBOL_NAME(sys_tkill)
+	.long SYMBOL_NAME(sys_sched_set_affinity)
+	.long SYMBOL_NAME(sys_sched_get_affinity)	/* 240 */
 
 	.rept NR_syscalls-(.-sys_call_table)/4
 		.long SYMBOL_NAME(sys_ni_syscall)
diff -urN linus/include/asm-i386/unistd.h linux/include/asm-i386/unistd.h
--- linus/include/asm-i386/unistd.h	Tue Feb 26 20:17:14 2002
+++ linux/include/asm-i386/unistd.h	Tue Feb 26 23:54:21 2002
@@ -243,6 +243,8 @@
 #define __NR_lremovexattr	236
 #define __NR_fremovexattr	237
 #define __NR_tkill		238
+#define __NR_sched_set_affinity 239
+#define __NR_sched_get_affinity 240
 
 /* user-visible error numbers are in the range -1 - -124: see <asm-i386/errno.h> */
 
diff -urN linus/kernel/sched.c linux/kernel/sched.c
--- linus/kernel/sched.c	Tue Feb 26 20:17:37 2002
+++ linux/kernel/sched.c	Tue Feb 26 23:52:38 2002
@@ -1215,6 +1215,99 @@
 	return retval;
 }
 
+/**
+ * sys_sched_set_affinity - set the cpu affinity of a process
+ * @pid: pid of the process
+ * @len: length of new_mask
+ * @new_mask: user-space pointer to the new cpu mask
+ */
+asmlinkage int sys_sched_set_affinity(pid_t pid, unsigned int len,
+				      unsigned long *new_mask_ptr)
+{
+	unsigned long new_mask;
+	task_t *p;
+	int retval;
+
+	if (len < sizeof(new_mask))
+		return -EINVAL;
+
+	if (!new_mask_ptr)
+		return -EINVAL;
+
+	if (copy_from_user(&new_mask, new_mask_ptr, sizeof(new_mask)))
+		return -EFAULT;
+
+	new_mask &= cpu_online_map;
+	if (!new_mask)
+		return -EINVAL;
+
+	read_lock(&tasklist_lock);
+
+	retval = -ESRCH;
+	p = find_process_by_pid(pid);
+	if (!p)
+		goto out_unlock;
+
+	retval = -EPERM;
+	if ((current->euid != p->euid) && (current->euid != p->uid) &&
+			!capable(CAP_SYS_NICE))
+		goto out_unlock;
+
+	retval = 0;
+#ifdef CONFIG_SMP
+	set_cpus_allowed(p, new_mask);
+#endif
+
+out_unlock:
+	read_unlock(&tasklist_lock);
+out:
+	return retval;
+}
+
+/**
+ * sys_sched_get_affinity - get the cpu affinity of a process
+ * @pid: pid of the process
+ * @user_len_ptr: userspace pointer to the length of the mask
+ * @user_mask_ptr: userspace pointer to the mask
+ */
+asmlinkage int sys_sched_get_affinity(pid_t pid, unsigned int *user_len_ptr,
+				      unsigned long *user_mask_ptr)
+{
+	unsigned long mask;
+	unsigned int len, user_len;
+	task_t *p;
+	int retval;
+
+	len = sizeof(mask);
+
+	if (copy_from_user(&user_len, user_len_ptr, sizeof(user_len)))
+		return -EFAULT;
+
+	if (copy_to_user(user_len_ptr, &len, sizeof(len)))
+		return -EFAULT;
+
+	if (user_len < len)
+		return -EINVAL;
+
+	read_lock(&tasklist_lock);
+
+	retval = -ESRCH;
+	p = find_process_by_pid(pid);
+	if (!p)
+		goto out_unlock;
+
+	retval = 0;
+	mask = p->cpus_allowed & cpu_online_map;
+
+out_unlock:
+	read_unlock(&tasklist_lock);
+	if (retval)
+		return retval;
+	if (copy_to_user(user_mask_ptr, &mask, sizeof(mask)))
+		return -EFAULT;
+	return 0;
+}
+
 asmlinkage long sys_sched_yield(void)
 {
 	runqueue_t *rq;

Re: [PATCH] 2.5: (better) syscalls for setting task affinity

[Robert Love]

[-- Attachment #1: Type: text/plain, Size: 483 bytes --]

On Wed, 2002-02-27 at 18:45, Robert Love wrote:

> The attached patch implements a syscall interface for setting and
> retrieving a task's CPU affinity (task->cpus_allowed):

I should posted a test program to demonstrate the syscalls - find such
an attachment below.  It demonstrates using sched_get_affinity to find
the length of the cpu bitmask and then get and set a new value.

`pid_t p' is the process in question.
`unsigned long new_mask' is the new bitmask.

	Robert Love





[-- Attachment #2: affinity.c --]
[-- Type: text/x-c, Size: 1075 bytes --]

/*
 * Example of sched_set_affinity and sched_get_affinity
 * 	Robert Love, 20020227
 */

#include <stdio.h>
#include <stdlib.h>
#include <linux/unistd.h>
#include <unistd.h>

#define __NR_sched_set_affinity 239
#define __NR_sched_get_affinity 240

_syscall3 (int, sched_set_affinity, pid_t, pid, unsigned int, len, unsigned long *, new_mask_ptr)
_syscall3 (int, sched_get_affinity, pid_t, pid, unsigned int *, user_len_ptr, unsigned long *, user_mask_ptr)

int main(int argc, char * argv[])
{
	unsigned long new_mask = 2;
	unsigned int len;
	unsigned long cur_mask;
	pid_t p = getpid();
	int ret;

	ret = sched_get_affinity(p, &len, NULL);
	printf(" len = %u\n", len);

	ret = sched_get_affinity(p, &len, &cur_mask);
	printf(" sched_get_affinity = %d, cur_mask = %ld\n", ret, cur_mask);

	ret = sched_set_affinity(p, len, &new_mask);
	printf(" sched_set_affinity = %d, new_mask = %ld\n", ret, new_mask);

	ret = sched_get_affinity(p, &len, &cur_mask);
	printf(" sched_get_affinity = %d, cur_mask = %ld\n", ret, cur_mask);

	return 0;
}

Re: [PATCH] 2.5: (better) syscalls for setting task affinity

[Mike Kravetz]

On Wed, Feb 27, 2002 at 06:45:21PM -0500, Robert Love wrote:
> [ This post adds length and pointer checks to the syscalls such that we
> can portably change the size of cpus_allowed. ]

Great!  That is what I was going to suggest to your first patch.

-- 
Mike