| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1486145034-22210-13-git-send-email-longman@redhat.com>
Date: Fri, 3 Feb 2017 13:03:45 -0500
From: Waiman Long <longman@...hat.com>
To: Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
Jonathan Corbet <corbet@....net>
Cc: linux-kernel@...r.kernel.org, linux-doc@...r.kernel.org,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Davidlohr Bueso <dave@...olabs.net>,
Mike Galbraith <umgwanakikbuti@...il.com>,
Scott J Norton <scott.norton@....com>,
Waiman Long <longman@...hat.com>
Subject: [PATCH-tip v5 12/21] TP-futex: Return status code on FUTEX_LOCK calls
To better understand how the TP futexes are performing, it is useful to
return the internal status on the TP futexes. The FUTEX_LOCK futex(2)
syscall will now return a positive status code if no error happens. The
status code consists of the following 3 fields:
1) Bits 00-07: code on how the lock is acquired.
2) Bits 08-15: reserved
3) Bits 16-30: how many time the task sleeps in the optimistic
spinning loop.
By returning the TP status code, an external monitoring or tracking
program can have a macro view of how the TP futexes are performing.
Signed-off-by: Waiman Long <longman@...hat.com>
---
kernel/futex.c | 41 +++++++++++++++++++++++++++++++----------
1 file changed, 31 insertions(+), 10 deletions(-)
diff --git a/kernel/futex.c b/kernel/futex.c
index 348b44c..22f7906 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -3369,6 +3369,22 @@ void exit_robust_list(struct task_struct *curr)
*/
#define TP_HANDOFF_TIMEOUT 5000000 /* 5ms */
+/*
+ * The futex_lock() function returns the internal status of the TP futex.
+ * The status code consists of the following 3 fields:
+ * 1) bits 00-07: code on how the lock is acquired
+ * 0 - steals the lock
+ * 1 - top waiter (mutex owner) acquires the lock
+ * 2 - handed off the lock
+ * 2) bits 08-15: reserved
+ * 3) bits 15-30: how many times the task has slept or yield to scheduler
+ * in futex_spin_on_owner().
+ */
+#define TP_LOCK_STOLEN 0
+#define TP_LOCK_ACQUIRED 1
+#define TP_LOCK_HANDOFF 2
+#define TP_STATUS_SLEEP(val, sleep) ((val)|((sleep) << 16))
+
/**
* lookup_futex_state - Looking up the futex state structure.
* @hb: hash bucket
@@ -3453,9 +3469,11 @@ static inline int put_futex_state_unlocked(struct futex_state *state)
* preserve the flag bits
* endif
*
- * Return: 1 if lock acquired;
+ * Return: TP_LOCK_ACQUIRED if lock acquired;
+ * TP_LOCK_HANDOFF if lock was handed off;
* 0 if lock acquisition failed;
* -EFAULT if an error happened.
+ * *puval will contain the latest futex value when trylock fails.
*/
static inline int futex_trylock(u32 __user *uaddr, const u32 vpid, u32 *puval,
const bool waiter)
@@ -3468,7 +3486,7 @@ static inline int futex_trylock(u32 __user *uaddr, const u32 vpid, u32 *puval,
uval = *puval;
if (waiter && (uval & FUTEX_TID_MASK) == vpid)
- return 1;
+ return TP_LOCK_HANDOFF;
if (uval & FUTEX_TID_MASK)
return 0; /* Trylock fails */
@@ -3479,7 +3497,7 @@ static inline int futex_trylock(u32 __user *uaddr, const u32 vpid, u32 *puval,
if (unlikely(cmpxchg_futex_value(puval, uaddr, uval, vpid|flags)))
return -EFAULT;
- return *puval == uval;
+ return (*puval == uval) ? TP_LOCK_ACQUIRED : 0;
}
/**
@@ -3493,7 +3511,8 @@ static inline int futex_trylock(u32 __user *uaddr, const u32 vpid, u32 *puval,
* of faulting in the futex word. This function should only be called from
* within futex_spin_on_owner().
*
- * Return: 1 if lock acquired;
+ * Return: TP_LOCK_ACQUIRED if lock acquired;
+ * TP_LOCK_HANDOFF if lock was handed off;
* 0 if lock acquisition failed;
* -EFAULT if an error happened.
*/
@@ -3554,7 +3573,7 @@ static inline int futex_set_waiters_bit(u32 __user *uaddr, u32 *puval)
* unless the pid wraps around and the perceived owner is not the real owner.
* To guard against this case, we will have to use the robust futex feature.
*
- * Return: 0 if futex acquired, < 0 if an error happens.
+ * Return: TP status code if lock acquired, < 0 if an error happens.
*/
static int futex_spin_on_owner(u32 __user *uaddr, const u32 vpid,
struct futex_state *state)
@@ -3564,6 +3583,7 @@ static int futex_spin_on_owner(u32 __user *uaddr, const u32 vpid,
"\tLock is now acquired by pid %d!\n"
int ret, loopcnt = 1;
+ int nsleep = 0;
bool handoff_set = false;
u32 uval;
u32 owner_pid = 0;
@@ -3623,6 +3643,7 @@ static int futex_spin_on_owner(u32 __user *uaddr, const u32 vpid,
if (need_resched()) {
__set_current_state(TASK_RUNNING);
schedule_preempt_disabled();
+ nsleep++;
loopcnt = 0;
continue;
}
@@ -3693,6 +3714,7 @@ static int futex_spin_on_owner(u32 __user *uaddr, const u32 vpid,
*/
if (!(uval & FUTEX_OWNER_DIED) && (uval & FUTEX_WAITERS)) {
schedule_preempt_disabled();
+ nsleep++;
loopcnt = 0;
}
__set_current_state(TASK_RUNNING);
@@ -3719,7 +3741,7 @@ static int futex_spin_on_owner(u32 __user *uaddr, const u32 vpid,
WRITE_ONCE(state->handoff_pid, 0);
preempt_enable();
- return ret;
+ return (ret < 0) ? ret : TP_STATUS_SLEEP(ret, nsleep);
}
/*
@@ -3733,8 +3755,7 @@ static int futex_spin_on_owner(u32 __user *uaddr, const u32 vpid,
* This function is not inlined so that it can show up separately in perf
* profile for performance analysis purpose.
*
- * Return: 0 - lock acquired
- * < 0 - an error happens
+ * Return: TP status code if lock acquired, < 0 if an error happens.
*/
static noinline int futex_lock(u32 __user *uaddr, unsigned int flags)
{
@@ -3749,7 +3770,7 @@ static noinline int futex_lock(u32 __user *uaddr, unsigned int flags)
*/
ret = futex_trylock(uaddr, vpid, &uval, false);
if (ret)
- goto out;
+ return (ret < 0) ? ret : TP_LOCK_STOLEN;
/*
* Detect deadlocks.
@@ -3817,7 +3838,7 @@ static noinline int futex_lock(u32 __user *uaddr, unsigned int flags)
put_futex_key(&key);
out:
- return (ret < 0) ? ret : 0;
+ return ret;
}
/*
--
1.8.3.1
Powered by blists - more mailing lists