From 5e2d2cc2588bd3307ce3937acbc2ed03c830a861 Mon Sep 17 00:00:00 2001
From: Liangyan <liangyan.peng@linux.alibaba.com>
Date: Mon, 26 Aug 2019 20:16:33 +0800
Subject: [PATCH 1/2] sched/fair: Don't assign runtime for throttled cfs_rq
do_sched_cfs_period_timer() will refill cfs_b runtime and call
distribute_cfs_runtime to unthrottle cfs_rq, sometimes cfs_b->runtime
will allocate all quota to one cfs_rq incorrectly, then other cfs_rqs
attached to this cfs_b can't get runtime and will be throttled.
We find that one throttled cfs_rq has non-negative
cfs_rq->runtime_remaining and cause an unexpetced cast from s64 to u64
in snippet:
distribute_cfs_runtime() {
runtime = -cfs_rq->runtime_remaining + 1;
}
The runtime here will change to a large number and consume all
cfs_b->runtime in this cfs_b period.
According to Ben Segall, the throttled cfs_rq can have
account_cfs_rq_runtime called on it because it is throttled before
idle_balance, and the idle_balance calls update_rq_clock to add time
that is accounted to the task.
This commit prevents cfs_rq to be assgined new runtime if it has been
throttled until that distribute_cfs_runtime is called.
Signed-off-by: Liangyan <liangyan.peng@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Reviewed-by: Ben Segall <bsegall@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: shanpeic@linux.alibaba.com
Cc: stable@vger.kernel.org
Cc: xlpang@linux.alibaba.com
Fixes: d3d9dc330236 ("sched: Throttle entities exceeding their allowed bandwidth")
Link: https://lkml.kernel.org/r/20190826121633.6538-1-liangyan.peng@linux.alibaba.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
kernel/sched/fair.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index bc9cfeaac8bd..500f5db0de0b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4470,6 +4470,8 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
if (likely(cfs_rq->runtime_remaining > 0))
return;
+ if (cfs_rq->throttled)
+ return;
/*
* if we're unable to extend our runtime we resched so that the active
* hierarchy can be throttled
@@ -4673,6 +4675,9 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b,
if (!cfs_rq_throttled(cfs_rq))
goto next;
+ /* By the above check, this should never be true */
+ SCHED_WARN_ON(cfs_rq->runtime_remaining > 0);
+
runtime = -cfs_rq->runtime_remaining + 1;
if (runtime > remaining)
runtime = remaining;
From 1251201c0d34fadf69d56efa675c2b7dd0a90eca Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 4 Sep 2019 09:55:32 +0200
Subject: [PATCH 2/2] sched/core: Fix uclamp ABI bug, clean up and robustify
sched_read_attr() ABI logic and code
Thadeu Lima de Souza Cascardo reported that 'chrt' broke on recent kernels:
$ chrt -p $$
chrt: failed to get pid 26306's policy: Argument list too long
and he has root-caused the bug to the following commit increasing sched_attr
size and breaking sched_read_attr() into returning -EFBIG:
a509a7cd7974 ("sched/uclamp: Extend sched_setattr() to support utilization clamping")
The other, bigger bug is that the whole sched_getattr() and sched_read_attr()
logic of checking non-zero bits in new ABI components is arguably broken,
and pretty much any extension of the ABI will spuriously break the ABI.
That's way too fragile.
Instead implement the perf syscall's extensible ABI instead, which we
already implement on the sched_setattr() side:
- if user-attributes have the same size as kernel attributes then the
logic is unchanged.
- if user-attributes are larger than the kernel knows about then simply
skip the extra bits, but set attr->size to the (smaller) kernel size
so that tooling can (in principle) handle older kernel as well.
- if user-attributes are smaller than the kernel knows about then just
copy whatever user-space can accept.
Also clean up the whole logic:
- Simplify the code flow - there's no need for 'ret' for example.
- Standardize on 'kattr/uattr' and 'ksize/usize' naming to make sure we
always know which side we are dealing with.
- Why is it called 'read' when what it does is to copy to user? This
code is so far away from VFS read() semantics that the naming is
actively confusing. Name it sched_attr_copy_to_user() instead, which
mirrors other copy_to_user() functionality.
- Move the attr->size assignment from the head of sched_getattr() to the
sched_attr_copy_to_user() function. Nothing else within the kernel
should care about the size of the structure.
With these fixes the sched_getattr() syscall now nicely supports an
extensible ABI in both a forward and backward compatible fashion, and
will also fix the chrt bug.
As an added bonus the bogus -EFBIG return is removed as well, which as
Thadeu noted should have been -E2BIG to begin with.
Reported-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Acked-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Patrick Bellasi <patrick.bellasi@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: a509a7cd7974 ("sched/uclamp: Extend sched_setattr() to support utilization clamping")
Link: https://lkml.kernel.org/r/20190904075532.GA26751@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
kernel/sched/core.c | 78 ++++++++++++++++++++++-----------------------
1 file changed, 39 insertions(+), 39 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 010d578118d6..df9f1fe5689b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5105,37 +5105,40 @@ out_unlock:
return retval;
}
-static int sched_read_attr(struct sched_attr __user *uattr,
- struct sched_attr *attr,
- unsigned int usize)
+/*
+ * Copy the kernel size attribute structure (which might be larger
+ * than what user-space knows about) to user-space.
+ *
+ * Note that all cases are valid: user-space buffer can be larger or
+ * smaller than the kernel-space buffer. The usual case is that both
+ * have the same size.
+ */
+static int
+sched_attr_copy_to_user(struct sched_attr __user *uattr,
+ struct sched_attr *kattr,
+ unsigned int usize)
{
- int ret;
+ unsigned int ksize = sizeof(*kattr);
if (!access_ok(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.
+ * sched_getattr() ABI forwards and backwards compatibility:
+ *
+ * If usize == ksize then we just copy everything to user-space and all is good.
+ *
+ * If usize < ksize then we only copy as much as user-space has space for,
+ * this keeps ABI compatibility as well. We skip the rest.
+ *
+ * If usize > ksize then user-space is using a newer version of the ABI,
+ * which part the kernel doesn't know about. Just ignore it - tooling can
+ * detect the kernel's knowledge of attributes from the attr->size value
+ * which is set to ksize in this case.
*/
- if (usize < sizeof(*attr)) {
- unsigned char *addr;
- unsigned char *end;
+ kattr->size = min(usize, ksize);
- addr = (void *)attr + usize;
- end = (void *)attr + sizeof(*attr);
-
- for (; addr < end; addr++) {
- if (*addr)
- return -EFBIG;
- }
-
- attr->size = usize;
- }
-
- ret = copy_to_user(uattr, attr, attr->size);
- if (ret)
+ if (copy_to_user(uattr, kattr, kattr->size))
return -EFAULT;
return 0;
@@ -5145,20 +5148,18 @@ static int sched_read_attr(struct sched_attr __user *uattr,
* sys_sched_getattr - similar to sched_getparam, but with sched_attr
* @pid: the pid in question.
* @uattr: structure containing the extended parameters.
- * @size: sizeof(attr) for fwd/bwd comp.
+ * @usize: sizeof(attr) that user-space knows about, for forwards and backwards compatibility.
* @flags: for future extension.
*/
SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
- unsigned int, size, unsigned int, flags)
+ unsigned int, usize, unsigned int, flags)
{
- struct sched_attr attr = {
- .size = sizeof(struct sched_attr),
- };
+ struct sched_attr kattr = { };
struct task_struct *p;
int retval;
- if (!uattr || pid < 0 || size > PAGE_SIZE ||
- size < SCHED_ATTR_SIZE_VER0 || flags)
+ if (!uattr || pid < 0 || usize > PAGE_SIZE ||
+ usize < SCHED_ATTR_SIZE_VER0 || flags)
return -EINVAL;
rcu_read_lock();
@@ -5171,25 +5172,24 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
if (retval)
goto out_unlock;
- attr.sched_policy = p->policy;
+ kattr.sched_policy = p->policy;
if (p->sched_reset_on_fork)
- attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
+ kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
if (task_has_dl_policy(p))
- __getparam_dl(p, &attr);
+ __getparam_dl(p, &kattr);
else if (task_has_rt_policy(p))
- attr.sched_priority = p->rt_priority;
+ kattr.sched_priority = p->rt_priority;
else
- attr.sched_nice = task_nice(p);
+ kattr.sched_nice = task_nice(p);
#ifdef CONFIG_UCLAMP_TASK
- attr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
- attr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
+ kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
+ kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
#endif
rcu_read_unlock();
- retval = sched_read_attr(uattr, &attr, size);
- return retval;
+ return sched_attr_copy_to_user(uattr, &kattr, usize);
out_unlock:
rcu_read_unlock();