AutoPage Migration - add /proc/<tgid>/migrate
Add a "migrate" control file to per process /proc subdir to allow
external trigger of task auto [==self] migration. When lazy
auto-migration is enabled, this effectively resets all unmappable
pages so that the next touch will cause a migrate on fault, if
the page is remote from the faulting task. This allows one to
"poke" a task externally to force "re-affinitization on next
touch" independent of inter-node migration.
On read, show current value of task's "migrate_pending". Nearly
useless, but I wanted to avoid a "write-only" file.
On write, if value is non-zero, set migrate_pending to 1 and set
'NOTIFY_RESUME thread info flag to cause task to handle the pending
migration. If value is zero, clear the migrate_pending--also not very
useful, but falls out of the code. Don't bother to reset the thread
info flag when clearing migrate_pending -- just being lazy. It's a
no-op in this case as far as auto-migration, but might have been set
by something else.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@xxxxxx>
fs/proc/base.c | 6 ++++
fs/proc/internal.h | 2 +
fs/proc/task_mmu.c | 70 +++++++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 78 insertions(+)
Index: linux-2.6.36-mmotm-101103-1217/fs/proc/base.c
===================================================================
--- linux-2.6.36-mmotm-101103-1217.orig/fs/proc/base.c
+++ linux-2.6.36-mmotm-101103-1217/fs/proc/base.c
@@ -2743,6 +2743,9 @@ static const struct pid_entry tgid_base_
REG("maps", S_IRUGO, proc_maps_operations),
#ifdef CONFIG_NUMA
REG("numa_maps", S_IRUGO, proc_numa_maps_operations),
+#ifdef CONFIG_AUTO_MIGRATION
+ REG("migrate", S_IRUGO|S_IWUSR, proc_migrate_operations),
+#endif
#endif
REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations),
LNK("cwd", proc_cwd_link),
@@ -3080,6 +3083,9 @@ static const struct pid_entry tid_base_s
REG("maps", S_IRUGO, proc_maps_operations),
#ifdef CONFIG_NUMA
REG("numa_maps", S_IRUGO, proc_numa_maps_operations),
+#ifdef CONFIG_AUTO_MIGRATION
+ REG("migrate", S_IRUGO|S_IWUSR, proc_migrate_operations),
+#endif
#endif
REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations),
LNK("cwd", proc_cwd_link),
Index: linux-2.6.36-mmotm-101103-1217/fs/proc/internal.h
===================================================================
--- linux-2.6.36-mmotm-101103-1217.orig/fs/proc/internal.h
+++ linux-2.6.36-mmotm-101103-1217/fs/proc/internal.h
@@ -59,6 +59,8 @@ extern const struct file_operations proc
extern const struct file_operations proc_clear_refs_operations;
extern const struct file_operations proc_pagemap_operations;
extern const struct file_operations proc_net_operations;
+extern const struct file_operations proc_migrate_operations;
+
extern const struct inode_operations proc_net_inode_operations;
void proc_init_inodecache(void);
Index: linux-2.6.36-mmotm-101103-1217/fs/proc/task_mmu.c
===================================================================
--- linux-2.6.36-mmotm-101103-1217.orig/fs/proc/task_mmu.c
+++ linux-2.6.36-mmotm-101103-1217/fs/proc/task_mmu.c
@@ -1016,4 +1016,74 @@ const struct file_operations proc_numa_m
.llseek = seq_lseek,
.release = seq_release_private,
};
+
+#ifdef CONFIG_AUTO_MIGRATION
+/*
+ * read/write task's "migrate_pending" flag.
+ * on write, set TIF_NOTIFY_RESUME thread info flag so that task
+ * will handle "migrate_pending" on next return to user space --
+ * no later than next clock tick.
+ */
+static ssize_t proc_migrate_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct task_struct *task;
+ char buffer[PROC_NUMBUF];
+ size_t len;
+ int migpend;
+ loff_t __ppos = *ppos;
+
+ task = get_proc_task(file->f_dentry->d_inode);
+ if (!task)
+ return -ESRCH;
+ migpend = task->migrate_pending;
+ put_task_struct(task);
+
+ len = snprintf(buffer, sizeof(buffer), "%i\n", migpend);
+ if (__ppos >= len)
+ return 0;
+ if (count > len-__ppos)
+ count = len-__ppos;
+ if (copy_to_user(buf, buffer + __ppos, count))
+ return -EFAULT;
+ *ppos = __ppos + count;
+ return count;
+}
+
+static ssize_t proc_migrate_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct task_struct *task;
+ char buffer[PROC_NUMBUF], *end;
+ int migpend;
+
+ if (!capable(CAP_SYS_RESOURCE))
+ return -EPERM;
+ memset(buffer, 0, sizeof(buffer));
+ if (count > sizeof(buffer) - 1)
+ count = sizeof(buffer) - 1;
+ if (copy_from_user(buffer, buf, count))
+ return -EFAULT;
+ migpend = simple_strtol(buffer, &end, 0);
+ if (*end == '\n')
+ end++;
+ if (end - buffer == 0)
+ return -EIO;
+
+ task = get_proc_task(file->f_dentry->d_inode);
+ if (!task)
+ return -ESRCH;
+ task->migrate_pending = !!migpend;
+ if (migpend)
+ set_tsk_thread_flag(task, TIF_NOTIFY_RESUME);
+ put_task_struct(task);
+
+ return end - buffer;
+}
+
+const struct file_operations proc_migrate_operations = {
+ .read = proc_migrate_read,
+ .write = proc_migrate_write,
+};
+#endif
#endif
--
To unsubscribe from this list: send the line "unsubscribe linux-numa" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
