summaryrefslogtreecommitdiff
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/Makefile3
-rw-r--r--block/ioprio.c241
2 files changed, 243 insertions, 1 deletions
diff --git a/block/Makefile b/block/Makefile
index 506a0c570be2..b4c4d3b99a2d 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -7,7 +7,8 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
blk-iopoll.o blk-lib.o blk-mq.o blk-mq-tag.o \
blk-mq-sysfs.o blk-mq-cpu.o blk-mq-cpumap.o ioctl.o \
- genhd.o scsi_ioctl.o partition-generic.o partitions/
+ genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
+ partitions/
obj-$(CONFIG_BLK_DEV_BSG) += bsg.o
obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o
diff --git a/block/ioprio.c b/block/ioprio.c
new file mode 100644
index 000000000000..e50170ca7c33
--- /dev/null
+++ b/block/ioprio.c
@@ -0,0 +1,241 @@
+/*
+ * fs/ioprio.c
+ *
+ * Copyright (C) 2004 Jens Axboe <axboe@kernel.dk>
+ *
+ * Helper functions for setting/querying io priorities of processes. The
+ * system calls closely mimmick getpriority/setpriority, see the man page for
+ * those. The prio argument is a composite of prio class and prio data, where
+ * the data argument has meaning within that class. The standard scheduling
+ * classes have 8 distinct prio levels, with 0 being the highest prio and 7
+ * being the lowest.
+ *
+ * IOW, setting BE scheduling class with prio 2 is done ala:
+ *
+ * unsigned int prio = (IOPRIO_CLASS_BE << IOPRIO_CLASS_SHIFT) | 2;
+ *
+ * ioprio_set(PRIO_PROCESS, pid, prio);
+ *
+ * See also Documentation/block/ioprio.txt
+ *
+ */
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/ioprio.h>
+#include <linux/blkdev.h>
+#include <linux/capability.h>
+#include <linux/syscalls.h>
+#include <linux/security.h>
+#include <linux/pid_namespace.h>
+
+int set_task_ioprio(struct task_struct *task, int ioprio)
+{
+ int err;
+ struct io_context *ioc;
+ const struct cred *cred = current_cred(), *tcred;
+
+ rcu_read_lock();
+ tcred = __task_cred(task);
+ if (!uid_eq(tcred->uid, cred->euid) &&
+ !uid_eq(tcred->uid, cred->uid) && !capable(CAP_SYS_NICE)) {
+ rcu_read_unlock();
+ return -EPERM;
+ }
+ rcu_read_unlock();
+
+ err = security_task_setioprio(task, ioprio);
+ if (err)
+ return err;
+
+ ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE);
+ if (ioc) {
+ ioc->ioprio = ioprio;
+ put_io_context(ioc);
+ }
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(set_task_ioprio);
+
+SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
+{
+ int class = IOPRIO_PRIO_CLASS(ioprio);
+ int data = IOPRIO_PRIO_DATA(ioprio);
+ struct task_struct *p, *g;
+ struct user_struct *user;
+ struct pid *pgrp;
+ kuid_t uid;
+ int ret;
+
+ switch (class) {
+ case IOPRIO_CLASS_RT:
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ /* fall through, rt has prio field too */
+ case IOPRIO_CLASS_BE:
+ if (data >= IOPRIO_BE_NR || data < 0)
+ return -EINVAL;
+
+ break;
+ case IOPRIO_CLASS_IDLE:
+ break;
+ case IOPRIO_CLASS_NONE:
+ if (data)
+ return -EINVAL;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ ret = -ESRCH;
+ rcu_read_lock();
+ switch (which) {
+ case IOPRIO_WHO_PROCESS:
+ if (!who)
+ p = current;
+ else
+ p = find_task_by_vpid(who);
+ if (p)
+ ret = set_task_ioprio(p, ioprio);
+ break;
+ case IOPRIO_WHO_PGRP:
+ if (!who)
+ pgrp = task_pgrp(current);
+ else
+ pgrp = find_vpid(who);
+ do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
+ ret = set_task_ioprio(p, ioprio);
+ if (ret)
+ break;
+ } while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+ break;
+ case IOPRIO_WHO_USER:
+ uid = make_kuid(current_user_ns(), who);
+ if (!uid_valid(uid))
+ break;
+ if (!who)
+ user = current_user();
+ else
+ user = find_user(uid);
+
+ if (!user)
+ break;
+
+ do_each_thread(g, p) {
+ if (!uid_eq(task_uid(p), uid))
+ continue;
+ ret = set_task_ioprio(p, ioprio);
+ if (ret)
+ goto free_uid;
+ } while_each_thread(g, p);
+free_uid:
+ if (who)
+ free_uid(user);
+ break;
+ default:
+ ret = -EINVAL;
+ }
+
+ rcu_read_unlock();
+ return ret;
+}
+
+static int get_task_ioprio(struct task_struct *p)
+{
+ int ret;
+
+ ret = security_task_getioprio(p);
+ if (ret)
+ goto out;
+ ret = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, IOPRIO_NORM);
+ if (p->io_context)
+ ret = p->io_context->ioprio;
+out:
+ return ret;
+}
+
+int ioprio_best(unsigned short aprio, unsigned short bprio)
+{
+ unsigned short aclass = IOPRIO_PRIO_CLASS(aprio);
+ unsigned short bclass = IOPRIO_PRIO_CLASS(bprio);
+
+ if (aclass == IOPRIO_CLASS_NONE)
+ aclass = IOPRIO_CLASS_BE;
+ if (bclass == IOPRIO_CLASS_NONE)
+ bclass = IOPRIO_CLASS_BE;
+
+ if (aclass == bclass)
+ return min(aprio, bprio);
+ if (aclass > bclass)
+ return bprio;
+ else
+ return aprio;
+}
+
+SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
+{
+ struct task_struct *g, *p;
+ struct user_struct *user;
+ struct pid *pgrp;
+ kuid_t uid;
+ int ret = -ESRCH;
+ int tmpio;
+
+ rcu_read_lock();
+ switch (which) {
+ case IOPRIO_WHO_PROCESS:
+ if (!who)
+ p = current;
+ else
+ p = find_task_by_vpid(who);
+ if (p)
+ ret = get_task_ioprio(p);
+ break;
+ case IOPRIO_WHO_PGRP:
+ if (!who)
+ pgrp = task_pgrp(current);
+ else
+ pgrp = find_vpid(who);
+ do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
+ tmpio = get_task_ioprio(p);
+ if (tmpio < 0)
+ continue;
+ if (ret == -ESRCH)
+ ret = tmpio;
+ else
+ ret = ioprio_best(ret, tmpio);
+ } while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+ break;
+ case IOPRIO_WHO_USER:
+ uid = make_kuid(current_user_ns(), who);
+ if (!who)
+ user = current_user();
+ else
+ user = find_user(uid);
+
+ if (!user)
+ break;
+
+ do_each_thread(g, p) {
+ if (!uid_eq(task_uid(p), user->uid))
+ continue;
+ tmpio = get_task_ioprio(p);
+ if (tmpio < 0)
+ continue;
+ if (ret == -ESRCH)
+ ret = tmpio;
+ else
+ ret = ioprio_best(ret, tmpio);
+ } while_each_thread(g, p);
+
+ if (who)
+ free_uid(user);
+ break;
+ default:
+ ret = -EINVAL;
+ }
+
+ rcu_read_unlock();
+ return ret;
+}