diff mbox series

[1/3] eventdev: fix race condition on timer list counter

Message ID 1591960798-24024-1-git-send-email-phil.yang@arm.com (mailing list archive)
State Superseded, archived
Delegated to: Jerin Jacob
Headers
Series [1/3] eventdev: fix race condition on timer list counter |

Checks

Context Check Description
ci/checkpatch success coding style OK
ci/iol-broadcom-Performance success Performance Testing PASS
ci/iol-intel-Performance success Performance Testing PASS
ci/iol-nxp-Performance success Performance Testing PASS
ci/iol-mellanox-Performance success Performance Testing PASS
ci/iol-testing success Testing PASS
ci/Intel-compilation fail Compilation issues

Commit Message

Phil Yang June 12, 2020, 11:19 a.m. UTC 
  The n_poll_lcores counter and poll_lcore array are shared between lcores
and the update of these variables are out of the protection of spinlock
on each lcore timer list. The read-modify-write operations of the counter
are not atomic, so it has the potential of race condition between lcores.

Use c11 atomics with RELAXED ordering to prevent confliction.

Fixes: cc7b73ea9e3b ("eventdev: add new software timer adapter")
Cc: erik.g.carrillo@intel.com
Cc: stable@dpdk.org

Signed-off-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
---
 lib/librte_eventdev/rte_event_timer_adapter.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

Comments

Carrillo, Erik G June 18, 2020, 3:17 p.m. UTC | #1 
Hi Phil,

Good catch - thanks for the fix.   I've commented in-line:

> -----Original Message-----
> From: Phil Yang <phil.yang@arm.com>
> Sent: Friday, June 12, 2020 6:20 AM
> To: dev@dpdk.org; Carrillo, Erik G <erik.g.carrillo@intel.com>
> Cc: drc@linux.vnet.ibm.com; honnappa.nagarahalli@arm.com;
> ruifeng.wang@arm.com; dharmik.thakkar@arm.com; nd@arm.com;
> stable@dpdk.org
> Subject: [PATCH 1/3] eventdev: fix race condition on timer list counter
> 
> The n_poll_lcores counter and poll_lcore array are shared between lcores
> and the update of these variables are out of the protection of spinlock on
> each lcore timer list. The read-modify-write operations of the counter are
> not atomic, so it has the potential of race condition between lcores.
> 
> Use c11 atomics with RELAXED ordering to prevent confliction.
> 
> Fixes: cc7b73ea9e3b ("eventdev: add new software timer adapter")
> Cc: erik.g.carrillo@intel.com
> Cc: stable@dpdk.org
> 
> Signed-off-by: Phil Yang <phil.yang@arm.com>
> Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> ---
>  lib/librte_eventdev/rte_event_timer_adapter.c | 16 ++++++++++++----
>  1 file changed, 12 insertions(+), 4 deletions(-)
> 
> diff --git a/lib/librte_eventdev/rte_event_timer_adapter.c
> b/lib/librte_eventdev/rte_event_timer_adapter.c
> index 005459f..6a0e283 100644
> --- a/lib/librte_eventdev/rte_event_timer_adapter.c
> +++ b/lib/librte_eventdev/rte_event_timer_adapter.c
> @@ -583,6 +583,7 @@ swtim_callback(struct rte_timer *tim)
>  	uint16_t nb_evs_invalid = 0;
>  	uint64_t opaque;
>  	int ret;
> +	int n_lcores;
> 
>  	opaque = evtim->impl_opaque[1];
>  	adapter = (struct rte_event_timer_adapter *)(uintptr_t)opaque;
> @@ -605,8 +606,12 @@ swtim_callback(struct rte_timer *tim)
>  				      "with immediate expiry value");
>  		}
> 
> -		if (unlikely(rte_atomic16_test_and_set(&sw-
> >in_use[lcore].v)))
> -			sw->poll_lcores[sw->n_poll_lcores++] = lcore;
> +		if (unlikely(rte_atomic16_test_and_set(&sw-
> >in_use[lcore].v))) {
> +			n_lcores = __atomic_fetch_add(&sw->n_poll_lcores,
> 1,
> +						__ATOMIC_RELAXED);

Just a nit, but let's align the continued line with the opening parentheses in
this location and below.  With these changes:

Acked-by: Erik Gabriel Carrillo <erik.g.carrillo@intel.com>

> +			__atomic_store_n(&sw->poll_lcores[n_lcores],
> lcore,
> +						__ATOMIC_RELAXED);
> +		}
>  	} else {
>  		EVTIM_BUF_LOG_DBG("buffered an event timer expiry
> event");
> 
> @@ -1011,6 +1016,7 @@ __swtim_arm_burst(const struct
> rte_event_timer_adapter *adapter,
>  	uint32_t lcore_id = rte_lcore_id();
>  	struct rte_timer *tim, *tims[nb_evtims];
>  	uint64_t cycles;
> +	int n_lcores;
> 
>  #ifdef RTE_LIBRTE_EVENTDEV_DEBUG
>  	/* Check that the service is running. */ @@ -1033,8 +1039,10 @@
> __swtim_arm_burst(const struct rte_event_timer_adapter *adapter,
>  	if (unlikely(rte_atomic16_test_and_set(&sw->in_use[lcore_id].v))) {
>  		EVTIM_LOG_DBG("Adding lcore id = %u to list of lcores to
> poll",
>  			      lcore_id);
> -		sw->poll_lcores[sw->n_poll_lcores] = lcore_id;
> -		++sw->n_poll_lcores;
> +		n_lcores = __atomic_fetch_add(&sw->n_poll_lcores, 1,
> +						__ATOMIC_RELAXED);
> +		__atomic_store_n(&sw->poll_lcores[n_lcores], lcore_id,
> +						__ATOMIC_RELAXED);
>  	}
> 
>  	ret = rte_mempool_get_bulk(sw->tim_pool, (void **)tims,
> --
> 2.7.4
Honnappa Nagarahalli June 18, 2020, 6:25 p.m. UTC | #2 
<snip>

> 
> Hi Phil,
> 
> Good catch - thanks for the fix.   I've commented in-line:
> 
> > -----Original Message-----
> > From: Phil Yang <phil.yang@arm.com>
> > Sent: Friday, June 12, 2020 6:20 AM
> > To: dev@dpdk.org; Carrillo, Erik G <erik.g.carrillo@intel.com>
> > Cc: drc@linux.vnet.ibm.com; honnappa.nagarahalli@arm.com;
> > ruifeng.wang@arm.com; dharmik.thakkar@arm.com; nd@arm.com;
> > stable@dpdk.org
> > Subject: [PATCH 1/3] eventdev: fix race condition on timer list
> > counter
> >
> > The n_poll_lcores counter and poll_lcore array are shared between
> > lcores and the update of these variables are out of the protection of
> > spinlock on each lcore timer list. The read-modify-write operations of
> > the counter are not atomic, so it has the potential of race condition
> between lcores.
> >
> > Use c11 atomics with RELAXED ordering to prevent confliction.
> >
> > Fixes: cc7b73ea9e3b ("eventdev: add new software timer adapter")
> > Cc: erik.g.carrillo@intel.com
> > Cc: stable@dpdk.org
> >
> > Signed-off-by: Phil Yang <phil.yang@arm.com>
> > Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
> > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > ---
> >  lib/librte_eventdev/rte_event_timer_adapter.c | 16 ++++++++++++----
> >  1 file changed, 12 insertions(+), 4 deletions(-)
> >
> > diff --git a/lib/librte_eventdev/rte_event_timer_adapter.c
> > b/lib/librte_eventdev/rte_event_timer_adapter.c
> > index 005459f..6a0e283 100644
> > --- a/lib/librte_eventdev/rte_event_timer_adapter.c
> > +++ b/lib/librte_eventdev/rte_event_timer_adapter.c
> > @@ -583,6 +583,7 @@ swtim_callback(struct rte_timer *tim)
> >  	uint16_t nb_evs_invalid = 0;
> >  	uint64_t opaque;
> >  	int ret;
> > +	int n_lcores;
> >
> >  	opaque = evtim->impl_opaque[1];
> >  	adapter = (struct rte_event_timer_adapter *)(uintptr_t)opaque; @@
> > -605,8 +606,12 @@ swtim_callback(struct rte_timer *tim)
> >  				      "with immediate expiry value");
> >  		}
> >
> > -		if (unlikely(rte_atomic16_test_and_set(&sw-
> > >in_use[lcore].v)))
> > -			sw->poll_lcores[sw->n_poll_lcores++] = lcore;
> > +		if (unlikely(rte_atomic16_test_and_set(&sw-
> > >in_use[lcore].v))) {
> > +			n_lcores = __atomic_fetch_add(&sw->n_poll_lcores,
> > 1,
> > +						__ATOMIC_RELAXED);
Since this commit will be back ported, we should prefer to use rte_atomic APIs for this commit. Otherwise, we will have a mix of rte_atomic and C11 APIs.
My suggestion is to fix this bug using rte_atomic so that backported code will have only rte_atomic APIs. Add another commit (if required) in this series to make the bug fix use C11 APIs (this commit will not be backported).

> 
> Just a nit, but let's align the continued line with the opening parentheses in
> this location and below.  With these changes:
> 
> Acked-by: Erik Gabriel Carrillo <erik.g.carrillo@intel.com>
> 
> > +			__atomic_store_n(&sw->poll_lcores[n_lcores],
> > lcore,
> > +						__ATOMIC_RELAXED);
> > +		}
> >  	} else {
> >  		EVTIM_BUF_LOG_DBG("buffered an event timer expiry event");
> >
> > @@ -1011,6 +1016,7 @@ __swtim_arm_burst(const struct
> > rte_event_timer_adapter *adapter,
> >  	uint32_t lcore_id = rte_lcore_id();
> >  	struct rte_timer *tim, *tims[nb_evtims];
> >  	uint64_t cycles;
> > +	int n_lcores;
> >
> >  #ifdef RTE_LIBRTE_EVENTDEV_DEBUG
> >  	/* Check that the service is running. */ @@ -1033,8 +1039,10 @@
> > __swtim_arm_burst(const struct rte_event_timer_adapter *adapter,
> >  	if (unlikely(rte_atomic16_test_and_set(&sw->in_use[lcore_id].v))) {
> >  		EVTIM_LOG_DBG("Adding lcore id = %u to list of lcores to
> poll",
> >  			      lcore_id);
> > -		sw->poll_lcores[sw->n_poll_lcores] = lcore_id;
> > -		++sw->n_poll_lcores;
> > +		n_lcores = __atomic_fetch_add(&sw->n_poll_lcores, 1,
> > +						__ATOMIC_RELAXED);
> > +		__atomic_store_n(&sw->poll_lcores[n_lcores], lcore_id,
> > +						__ATOMIC_RELAXED);
> >  	}
> >
> >  	ret = rte_mempool_get_bulk(sw->tim_pool, (void **)tims,
> > --
> > 2.7.4
Phil Yang June 22, 2020, 9:09 a.m. UTC | #3 
> -----Original Message-----
> From: Carrillo, Erik G <erik.g.carrillo@intel.com>
> Sent: Thursday, June 18, 2020 11:18 PM
> To: Phil Yang <Phil.Yang@arm.com>; dev@dpdk.org
> Cc: drc@linux.vnet.ibm.com; Honnappa Nagarahalli
> <Honnappa.Nagarahalli@arm.com>; Ruifeng Wang
> <Ruifeng.Wang@arm.com>; Dharmik Thakkar <Dharmik.Thakkar@arm.com>;
> nd <nd@arm.com>; stable@dpdk.org
> Subject: RE: [PATCH 1/3] eventdev: fix race condition on timer list counter
> 
> Hi Phil,
> 
> Good catch - thanks for the fix.   I've commented in-line:
> 
> > -----Original Message-----
> > From: Phil Yang <phil.yang@arm.com>
> > Sent: Friday, June 12, 2020 6:20 AM
> > To: dev@dpdk.org; Carrillo, Erik G <erik.g.carrillo@intel.com>
> > Cc: drc@linux.vnet.ibm.com; honnappa.nagarahalli@arm.com;
> > ruifeng.wang@arm.com; dharmik.thakkar@arm.com; nd@arm.com;
> > stable@dpdk.org
> > Subject: [PATCH 1/3] eventdev: fix race condition on timer list counter
> >
> > The n_poll_lcores counter and poll_lcore array are shared between lcores
> > and the update of these variables are out of the protection of spinlock on
> > each lcore timer list. The read-modify-write operations of the counter are
> > not atomic, so it has the potential of race condition between lcores.
> >
> > Use c11 atomics with RELAXED ordering to prevent confliction.
> >
> > Fixes: cc7b73ea9e3b ("eventdev: add new software timer adapter")
> > Cc: erik.g.carrillo@intel.com
> > Cc: stable@dpdk.org
> >
> > Signed-off-by: Phil Yang <phil.yang@arm.com>
> > Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
> > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > ---
> >  lib/librte_eventdev/rte_event_timer_adapter.c | 16 ++++++++++++----
> >  1 file changed, 12 insertions(+), 4 deletions(-)
> >
> > diff --git a/lib/librte_eventdev/rte_event_timer_adapter.c
> > b/lib/librte_eventdev/rte_event_timer_adapter.c
> > index 005459f..6a0e283 100644
> > --- a/lib/librte_eventdev/rte_event_timer_adapter.c
> > +++ b/lib/librte_eventdev/rte_event_timer_adapter.c
> > @@ -583,6 +583,7 @@ swtim_callback(struct rte_timer *tim)
> >  	uint16_t nb_evs_invalid = 0;
> >  	uint64_t opaque;
> >  	int ret;
> > +	int n_lcores;
> >
> >  	opaque = evtim->impl_opaque[1];
> >  	adapter = (struct rte_event_timer_adapter *)(uintptr_t)opaque;
> > @@ -605,8 +606,12 @@ swtim_callback(struct rte_timer *tim)
> >  				      "with immediate expiry value");
> >  		}
> >
> > -		if (unlikely(rte_atomic16_test_and_set(&sw-
> > >in_use[lcore].v)))
> > -			sw->poll_lcores[sw->n_poll_lcores++] = lcore;
> > +		if (unlikely(rte_atomic16_test_and_set(&sw-
> > >in_use[lcore].v))) {
> > +			n_lcores = __atomic_fetch_add(&sw->n_poll_lcores,
> > 1,
> > +						__ATOMIC_RELAXED);
> 
> Just a nit, but let's align the continued line with the opening parentheses in
> this location and below.  With these changes:

Thanks Erik. 
I will do it in the new version.

> 
> Acked-by: Erik Gabriel Carrillo <erik.g.carrillo@intel.com>
> 
> > +			__atomic_store_n(&sw->poll_lcores[n_lcores],
> > lcore,
> > +						__ATOMIC_RELAXED);
> > +		}
> >  	} else {
> >  		EVTIM_BUF_LOG_DBG("buffered an event timer expiry
> > event");
> >
> > @@ -1011,6 +1016,7 @@ __swtim_arm_burst(const struct
> > rte_event_timer_adapter *adapter,
> >  	uint32_t lcore_id = rte_lcore_id();
> >  	struct rte_timer *tim, *tims[nb_evtims];
> >  	uint64_t cycles;
> > +	int n_lcores;
> >
> >  #ifdef RTE_LIBRTE_EVENTDEV_DEBUG
> >  	/* Check that the service is running. */ @@ -1033,8 +1039,10 @@
> > __swtim_arm_burst(const struct rte_event_timer_adapter *adapter,
> >  	if (unlikely(rte_atomic16_test_and_set(&sw->in_use[lcore_id].v))) {
> >  		EVTIM_LOG_DBG("Adding lcore id = %u to list of lcores to
> > poll",
> >  			      lcore_id);
> > -		sw->poll_lcores[sw->n_poll_lcores] = lcore_id;
> > -		++sw->n_poll_lcores;
> > +		n_lcores = __atomic_fetch_add(&sw->n_poll_lcores, 1,
> > +						__ATOMIC_RELAXED);
> > +		__atomic_store_n(&sw->poll_lcores[n_lcores], lcore_id,
> > +						__ATOMIC_RELAXED);
> >  	}
> >
> >  	ret = rte_mempool_get_bulk(sw->tim_pool, (void **)tims,
> > --
> > 2.7.4
Phil Yang June 22, 2020, 9:48 a.m. UTC | #4 
> -----Original Message-----
> From: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> Sent: Friday, June 19, 2020 2:26 AM
> To: Carrillo, Erik G <erik.g.carrillo@intel.com>; Phil Yang
> <Phil.Yang@arm.com>; dev@dpdk.org
> Cc: drc@linux.vnet.ibm.com; Ruifeng Wang <Ruifeng.Wang@arm.com>;
> Dharmik Thakkar <Dharmik.Thakkar@arm.com>; nd <nd@arm.com>;
> stable@dpdk.org; Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>;
> nd <nd@arm.com>
> Subject: RE: [PATCH 1/3] eventdev: fix race condition on timer list counter
> 
> <snip>
> 
> >
> > Hi Phil,
> >
> > Good catch - thanks for the fix.   I've commented in-line:
> >
> > > -----Original Message-----
> > > From: Phil Yang <phil.yang@arm.com>
> > > Sent: Friday, June 12, 2020 6:20 AM
> > > To: dev@dpdk.org; Carrillo, Erik G <erik.g.carrillo@intel.com>
> > > Cc: drc@linux.vnet.ibm.com; honnappa.nagarahalli@arm.com;
> > > ruifeng.wang@arm.com; dharmik.thakkar@arm.com; nd@arm.com;
> > > stable@dpdk.org
> > > Subject: [PATCH 1/3] eventdev: fix race condition on timer list
> > > counter
> > >
> > > The n_poll_lcores counter and poll_lcore array are shared between
> > > lcores and the update of these variables are out of the protection of
> > > spinlock on each lcore timer list. The read-modify-write operations of
> > > the counter are not atomic, so it has the potential of race condition
> > between lcores.
> > >
> > > Use c11 atomics with RELAXED ordering to prevent confliction.
> > >
> > > Fixes: cc7b73ea9e3b ("eventdev: add new software timer adapter")
> > > Cc: erik.g.carrillo@intel.com
> > > Cc: stable@dpdk.org
> > >
> > > Signed-off-by: Phil Yang <phil.yang@arm.com>
> > > Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
> > > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > > ---
> > >  lib/librte_eventdev/rte_event_timer_adapter.c | 16 ++++++++++++----
> > >  1 file changed, 12 insertions(+), 4 deletions(-)
> > >
> > > diff --git a/lib/librte_eventdev/rte_event_timer_adapter.c
> > > b/lib/librte_eventdev/rte_event_timer_adapter.c
> > > index 005459f..6a0e283 100644
> > > --- a/lib/librte_eventdev/rte_event_timer_adapter.c
> > > +++ b/lib/librte_eventdev/rte_event_timer_adapter.c
> > > @@ -583,6 +583,7 @@ swtim_callback(struct rte_timer *tim)
> > >  uint16_t nb_evs_invalid = 0;
> > >  uint64_t opaque;
> > >  int ret;
> > > +int n_lcores;
> > >
> > >  opaque = evtim->impl_opaque[1];
> > >  adapter = (struct rte_event_timer_adapter *)(uintptr_t)opaque; @@
> > > -605,8 +606,12 @@ swtim_callback(struct rte_timer *tim)
> > >        "with immediate expiry value");
> > >  }
> > >
> > > -if (unlikely(rte_atomic16_test_and_set(&sw-
> > > >in_use[lcore].v)))
> > > -sw->poll_lcores[sw->n_poll_lcores++] = lcore;
> > > +if (unlikely(rte_atomic16_test_and_set(&sw-
> > > >in_use[lcore].v))) {
> > > +n_lcores = __atomic_fetch_add(&sw->n_poll_lcores,
> > > 1,
> > > +__ATOMIC_RELAXED);
> Since this commit will be back ported, we should prefer to use rte_atomic
> APIs for this commit. Otherwise, we will have a mix of rte_atomic and C11
> APIs.
> My suggestion is to fix this bug using rte_atomic so that backported code will
> have only rte_atomic APIs. Add another commit (if required) in this series to
> make the bug fix use C11 APIs (this commit will not be backported).

Agree. 
I will change this patch to the rte_atomic version in the next version.

Thanks,
Phil

> 
> >
> > Just a nit, but let's align the continued line with the opening parentheses in
> > this location and below.  With these changes:
> >
> > Acked-by: Erik Gabriel Carrillo <erik.g.carrillo@intel.com>
> >
> > > +__atomic_store_n(&sw->poll_lcores[n_lcores],
> > > lcore,
> > > +__ATOMIC_RELAXED);
> > > +}
> > >  } else {
> > >  EVTIM_BUF_LOG_DBG("buffered an event timer expiry event");
> > >
> > > @@ -1011,6 +1016,7 @@ __swtim_arm_burst(const struct
> > > rte_event_timer_adapter *adapter,
> > >  uint32_t lcore_id = rte_lcore_id();
> > >  struct rte_timer *tim, *tims[nb_evtims];
> > >  uint64_t cycles;
> > > +int n_lcores;
> > >
> > >  #ifdef RTE_LIBRTE_EVENTDEV_DEBUG
> > >  /* Check that the service is running. */ @@ -1033,8 +1039,10 @@
> > > __swtim_arm_burst(const struct rte_event_timer_adapter *adapter,
> > >  if (unlikely(rte_atomic16_test_and_set(&sw->in_use[lcore_id].v))) {
> > >  EVTIM_LOG_DBG("Adding lcore id = %u to list of lcores to
> > poll",
> > >        lcore_id);
> > > -sw->poll_lcores[sw->n_poll_lcores] = lcore_id;
> > > -++sw->n_poll_lcores;
> > > +n_lcores = __atomic_fetch_add(&sw->n_poll_lcores, 1,
> > > +__ATOMIC_RELAXED);
> > > +__atomic_store_n(&sw->poll_lcores[n_lcores], lcore_id,
> > > +__ATOMIC_RELAXED);
> > >  }
> > >
> > >  ret = rte_mempool_get_bulk(sw->tim_pool, (void **)tims,
> > > --
> > > 2.7.4
>
Jerin Jacob July 1, 2020, 11:22 a.m. UTC | #5 
On Mon, Jun 22, 2020 at 3:18 PM Phil Yang <Phil.Yang@arm.com> wrote:
>
> > -----Original Message-----
> > From: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> > Sent: Friday, June 19, 2020 2:26 AM
> > To: Carrillo, Erik G <erik.g.carrillo@intel.com>; Phil Yang
> > <Phil.Yang@arm.com>; dev@dpdk.org
> > Cc: drc@linux.vnet.ibm.com; Ruifeng Wang <Ruifeng.Wang@arm.com>;
> > Dharmik Thakkar <Dharmik.Thakkar@arm.com>; nd <nd@arm.com>;
> > stable@dpdk.org; Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>;
> > nd <nd@arm.com>
> > Subject: RE: [PATCH 1/3] eventdev: fix race condition on timer list counter
> >

> > Since this commit will be back ported, we should prefer to use rte_atomic
> > APIs for this commit. Otherwise, we will have a mix of rte_atomic and C11
> > APIs.
> > My suggestion is to fix this bug using rte_atomic so that backported code will
> > have only rte_atomic APIs. Add another commit (if required) in this series to
> > make the bug fix use C11 APIs (this commit will not be backported).
>
> Agree.
> I will change this patch to the rte_atomic version in the next version.

Hi Phil,

Could you send the next version? I would like to take this series for
RC1(next-eventdev tree)


>
> Thanks,
> Phil
>
Phil Yang July 2, 2020, 3:26 a.m. UTC | #6 
> -----Original Message-----
> From: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> Sent: Friday, June 19, 2020 2:26 AM
> To: Carrillo, Erik G <erik.g.carrillo@intel.com>; Phil Yang
> <Phil.Yang@arm.com>; dev@dpdk.org
> Cc: drc@linux.vnet.ibm.com; Ruifeng Wang <Ruifeng.Wang@arm.com>;
> Dharmik Thakkar <Dharmik.Thakkar@arm.com>; nd <nd@arm.com>;
> stable@dpdk.org; Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>;
> nd <nd@arm.com>
> Subject: RE: [PATCH 1/3] eventdev: fix race condition on timer list counter
> 
> <snip>
> 
> >
> > Hi Phil,
> >
> > Good catch - thanks for the fix.   I've commented in-line:
> >
> > > -----Original Message-----
> > > From: Phil Yang <phil.yang@arm.com>
> > > Sent: Friday, June 12, 2020 6:20 AM
> > > To: dev@dpdk.org; Carrillo, Erik G <erik.g.carrillo@intel.com>
> > > Cc: drc@linux.vnet.ibm.com; honnappa.nagarahalli@arm.com;
> > > ruifeng.wang@arm.com; dharmik.thakkar@arm.com; nd@arm.com;
> > > stable@dpdk.org
> > > Subject: [PATCH 1/3] eventdev: fix race condition on timer list
> > > counter
> > >
> > > The n_poll_lcores counter and poll_lcore array are shared between
> > > lcores and the update of these variables are out of the protection of
> > > spinlock on each lcore timer list. The read-modify-write operations of
> > > the counter are not atomic, so it has the potential of race condition
> > between lcores.
> > >
> > > Use c11 atomics with RELAXED ordering to prevent confliction.
> > >
> > > Fixes: cc7b73ea9e3b ("eventdev: add new software timer adapter")
> > > Cc: erik.g.carrillo@intel.com
> > > Cc: stable@dpdk.org
> > >
> > > Signed-off-by: Phil Yang <phil.yang@arm.com>
> > > Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
> > > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > > ---
> > >  lib/librte_eventdev/rte_event_timer_adapter.c | 16 ++++++++++++----
> > >  1 file changed, 12 insertions(+), 4 deletions(-)
> > >
> > > diff --git a/lib/librte_eventdev/rte_event_timer_adapter.c
> > > b/lib/librte_eventdev/rte_event_timer_adapter.c
> > > index 005459f..6a0e283 100644
> > > --- a/lib/librte_eventdev/rte_event_timer_adapter.c
> > > +++ b/lib/librte_eventdev/rte_event_timer_adapter.c
> > > @@ -583,6 +583,7 @@ swtim_callback(struct rte_timer *tim)
> > >  uint16_t nb_evs_invalid = 0;
> > >  uint64_t opaque;
> > >  int ret;
> > > +int n_lcores;
> > >
> > >  opaque = evtim->impl_opaque[1];
> > >  adapter = (struct rte_event_timer_adapter *)(uintptr_t)opaque; @@
> > > -605,8 +606,12 @@ swtim_callback(struct rte_timer *tim)
> > >        "with immediate expiry value");
> > >  }
> > >
> > > -if (unlikely(rte_atomic16_test_and_set(&sw-
> > > >in_use[lcore].v)))
> > > -sw->poll_lcores[sw->n_poll_lcores++] = lcore;
> > > +if (unlikely(rte_atomic16_test_and_set(&sw-
> > > >in_use[lcore].v))) {
> > > +n_lcores = __atomic_fetch_add(&sw->n_poll_lcores,
> > > 1,
> > > +__ATOMIC_RELAXED);
> Since this commit will be back ported, we should prefer to use rte_atomic
> APIs for this commit. Otherwise, we will have a mix of rte_atomic and C11
> APIs.
> My suggestion is to fix this bug using rte_atomic so that backported code will
> have only rte_atomic APIs. Add another commit (if required) in this series to
> make the bug fix use C11 APIs (this commit will not be backported).

Hi Honnappa,

It doesn't have an applicable rte_atomic_XXX API to fix this issue.
The rte_atomic32_inc doesn't return the original value of the input parameter and rte_atomic32_add_return can only return the new value.

Meanwhile, the rte_timer_alt_manage & rte_timer_stop_all API not support rte_atomic type parameters. We might need to rewrite these two APIs if we want to use rte_atomic operations for n_pol_lcores and poll_lcores array.

So, a better solution could be to backport the entire c11 solution to stable releases.

Thanks,
Phil

> 
> >
> > Just a nit, but let's align the continued line with the opening parentheses in
> > this location and below.  With these changes:
> >
> > Acked-by: Erik Gabriel Carrillo <erik.g.carrillo@intel.com>
> >
> > > +__atomic_store_n(&sw->poll_lcores[n_lcores],
> > > lcore,
> > > +__ATOMIC_RELAXED);
> > > +}
> > >  } else {
> > >  EVTIM_BUF_LOG_DBG("buffered an event timer expiry event");
> > >
> > > @@ -1011,6 +1016,7 @@ __swtim_arm_burst(const struct
> > > rte_event_timer_adapter *adapter,
> > >  uint32_t lcore_id = rte_lcore_id();
> > >  struct rte_timer *tim, *tims[nb_evtims];
> > >  uint64_t cycles;
> > > +int n_lcores;
> > >
> > >  #ifdef RTE_LIBRTE_EVENTDEV_DEBUG
> > >  /* Check that the service is running. */ @@ -1033,8 +1039,10 @@
> > > __swtim_arm_burst(const struct rte_event_timer_adapter *adapter,
> > >  if (unlikely(rte_atomic16_test_and_set(&sw->in_use[lcore_id].v))) {
> > >  EVTIM_LOG_DBG("Adding lcore id = %u to list of lcores to
> > poll",
> > >        lcore_id);
> > > -sw->poll_lcores[sw->n_poll_lcores] = lcore_id;
> > > -++sw->n_poll_lcores;
> > > +n_lcores = __atomic_fetch_add(&sw->n_poll_lcores, 1,
> > > +__ATOMIC_RELAXED);
> > > +__atomic_store_n(&sw->poll_lcores[n_lcores], lcore_id,
> > > +__ATOMIC_RELAXED);
> > >  }
> > >
> > >  ret = rte_mempool_get_bulk(sw->tim_pool, (void **)tims,
> > > --
> > > 2.7.4
>
Phil Yang July 2, 2020, 3:28 a.m. UTC | #7 
> -----Original Message-----
> From: Jerin Jacob <jerinjacobk@gmail.com>
> Sent: Wednesday, July 1, 2020 7:22 PM
> To: Phil Yang <Phil.Yang@arm.com>
> Cc: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>; Carrillo, Erik G
> <erik.g.carrillo@intel.com>; dev@dpdk.org; drc@linux.vnet.ibm.com;
> Ruifeng Wang <Ruifeng.Wang@arm.com>; Dharmik Thakkar
> <Dharmik.Thakkar@arm.com>; nd <nd@arm.com>; stable@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 1/3] eventdev: fix race condition on timer list
> counter
> 
> On Mon, Jun 22, 2020 at 3:18 PM Phil Yang <Phil.Yang@arm.com> wrote:
> >
> > > -----Original Message-----
> > > From: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> > > Sent: Friday, June 19, 2020 2:26 AM
> > > To: Carrillo, Erik G <erik.g.carrillo@intel.com>; Phil Yang
> > > <Phil.Yang@arm.com>; dev@dpdk.org
> > > Cc: drc@linux.vnet.ibm.com; Ruifeng Wang <Ruifeng.Wang@arm.com>;
> > > Dharmik Thakkar <Dharmik.Thakkar@arm.com>; nd <nd@arm.com>;
> > > stable@dpdk.org; Honnappa Nagarahalli
> <Honnappa.Nagarahalli@arm.com>;
> > > nd <nd@arm.com>
> > > Subject: RE: [PATCH 1/3] eventdev: fix race condition on timer list counter
> > >
> 
> > > Since this commit will be back ported, we should prefer to use rte_atomic
> > > APIs for this commit. Otherwise, we will have a mix of rte_atomic and C11
> > > APIs.
> > > My suggestion is to fix this bug using rte_atomic so that backported code
> will
> > > have only rte_atomic APIs. Add another commit (if required) in this series
> to
> > > make the bug fix use C11 APIs (this commit will not be backported).
> >
> > Agree.
> > I will change this patch to the rte_atomic version in the next version.
> 
> Hi Phil,
> 
> Could you send the next version? I would like to take this series for
> RC1(next-eventdev tree)

Thanks, Jerin.
I will upstream the new patch series soon.


> 
> 
> >
> > Thanks,
> > Phil
> >
Honnappa Nagarahalli July 2, 2020, 3:56 a.m. UTC | #8 
<snip>
> >
> > >
> > > Hi Phil,
> > >
> > > Good catch - thanks for the fix.   I've commented in-line:
> > >
> > > > -----Original Message-----
> > > > From: Phil Yang <phil.yang@arm.com>
> > > > Sent: Friday, June 12, 2020 6:20 AM
> > > > To: dev@dpdk.org; Carrillo, Erik G <erik.g.carrillo@intel.com>
> > > > Cc: drc@linux.vnet.ibm.com; honnappa.nagarahalli@arm.com;
> > > > ruifeng.wang@arm.com; dharmik.thakkar@arm.com; nd@arm.com;
> > > > stable@dpdk.org
> > > > Subject: [PATCH 1/3] eventdev: fix race condition on timer list
> > > > counter
> > > >
> > > > The n_poll_lcores counter and poll_lcore array are shared between
> > > > lcores and the update of these variables are out of the protection
> > > > of spinlock on each lcore timer list. The read-modify-write
> > > > operations of the counter are not atomic, so it has the potential
> > > > of race condition
> > > between lcores.
> > > >
> > > > Use c11 atomics with RELAXED ordering to prevent confliction.
> > > >
> > > > Fixes: cc7b73ea9e3b ("eventdev: add new software timer adapter")
> > > > Cc: erik.g.carrillo@intel.com
> > > > Cc: stable@dpdk.org
> > > >
> > > > Signed-off-by: Phil Yang <phil.yang@arm.com>
> > > > Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
> > > > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > > > ---
> > > >  lib/librte_eventdev/rte_event_timer_adapter.c | 16
> > > > ++++++++++++----
> > > >  1 file changed, 12 insertions(+), 4 deletions(-)
> > > >
> > > > diff --git a/lib/librte_eventdev/rte_event_timer_adapter.c
> > > > b/lib/librte_eventdev/rte_event_timer_adapter.c
> > > > index 005459f..6a0e283 100644
> > > > --- a/lib/librte_eventdev/rte_event_timer_adapter.c
> > > > +++ b/lib/librte_eventdev/rte_event_timer_adapter.c
> > > > @@ -583,6 +583,7 @@ swtim_callback(struct rte_timer *tim)
> > > > uint16_t nb_evs_invalid = 0;  uint64_t opaque;  int ret;
> > > > +int n_lcores;
> > > >
> > > >  opaque = evtim->impl_opaque[1];
> > > >  adapter = (struct rte_event_timer_adapter *)(uintptr_t)opaque; @@
> > > > -605,8 +606,12 @@ swtim_callback(struct rte_timer *tim)
> > > >        "with immediate expiry value");  }
> > > >
> > > > -if (unlikely(rte_atomic16_test_and_set(&sw-
> > > > >in_use[lcore].v)))
> > > > -sw->poll_lcores[sw->n_poll_lcores++] = lcore;
> > > > +if (unlikely(rte_atomic16_test_and_set(&sw-
> > > > >in_use[lcore].v))) {
> > > > +n_lcores = __atomic_fetch_add(&sw->n_poll_lcores,
> > > > 1,
> > > > +__ATOMIC_RELAXED);
> > Since this commit will be back ported, we should prefer to use
> > rte_atomic APIs for this commit. Otherwise, we will have a mix of
> > rte_atomic and C11 APIs.
> > My suggestion is to fix this bug using rte_atomic so that backported
> > code will have only rte_atomic APIs. Add another commit (if required)
> > in this series to make the bug fix use C11 APIs (this commit will not be
> backported).
> 
> Hi Honnappa,
> 
> It doesn't have an applicable rte_atomic_XXX API to fix this issue.
> The rte_atomic32_inc doesn't return the original value of the input parameter
> and rte_atomic32_add_return can only return the new value.
Ok, understood.

> 
> Meanwhile, the rte_timer_alt_manage & rte_timer_stop_all API not support
> rte_atomic type parameters. We might need to rewrite these two APIs if we
> want to use rte_atomic operations for n_pol_lcores and poll_lcores array.
> 
> So, a better solution could be to backport the entire c11 solution to stable
> releases.
I am ok with the approach.
Erik, are you ok with this?

> 
> Thanks,
> Phil
> 
> >
> > >
> > > Just a nit, but let's align the continued line with the opening
> > > parentheses in this location and below.  With these changes:
> > >
> > > Acked-by: Erik Gabriel Carrillo <erik.g.carrillo@intel.com>
> > >
> > > > +__atomic_store_n(&sw->poll_lcores[n_lcores],
> > > > lcore,
> > > > +__ATOMIC_RELAXED);
> > > > +}
> > > >  } else {
> > > >  EVTIM_BUF_LOG_DBG("buffered an event timer expiry event");
> > > >
> > > > @@ -1011,6 +1016,7 @@ __swtim_arm_burst(const struct
> > > > rte_event_timer_adapter *adapter,  uint32_t lcore_id =
> > > > rte_lcore_id();  struct rte_timer *tim, *tims[nb_evtims];
> > > > uint64_t cycles;
> > > > +int n_lcores;
> > > >
> > > >  #ifdef RTE_LIBRTE_EVENTDEV_DEBUG
> > > >  /* Check that the service is running. */ @@ -1033,8 +1039,10 @@
> > > > __swtim_arm_burst(const struct rte_event_timer_adapter *adapter,
> > > > if (unlikely(rte_atomic16_test_and_set(&sw->in_use[lcore_id].v)))
> > > > {  EVTIM_LOG_DBG("Adding lcore id = %u to list of lcores to
> > > poll",
> > > >        lcore_id);
> > > > -sw->poll_lcores[sw->n_poll_lcores] = lcore_id;
> > > > -++sw->n_poll_lcores;
> > > > +n_lcores = __atomic_fetch_add(&sw->n_poll_lcores, 1,
> > > > +__ATOMIC_RELAXED); __atomic_store_n(&sw->poll_lcores[n_lcores],
> > > > +lcore_id, __ATOMIC_RELAXED);
> > > >  }
> > > >
> > > >  ret = rte_mempool_get_bulk(sw->tim_pool, (void **)tims,
> > > > --
> > > > 2.7.4
> >
Carrillo, Erik G July 2, 2020, 9:15 p.m. UTC | #9 
> -----Original Message-----
> From: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
> Sent: Wednesday, July 1, 2020 10:56 PM
> To: Phil Yang <Phil.Yang@arm.com>; Carrillo, Erik G
> <erik.g.carrillo@intel.com>; dev@dpdk.org
> Cc: drc@linux.vnet.ibm.com; Ruifeng Wang <Ruifeng.Wang@arm.com>;
> Dharmik Thakkar <Dharmik.Thakkar@arm.com>; stable@dpdk.org; nd
> <nd@arm.com>; jerinj@marvell.com; Honnappa Nagarahalli
> <Honnappa.Nagarahalli@arm.com>; nd <nd@arm.com>
> Subject: RE: [PATCH 1/3] eventdev: fix race condition on timer list counter
> 
> <snip>
> > >
> > > >
> > > > Hi Phil,
> > > >
> > > > Good catch - thanks for the fix.   I've commented in-line:
> > > >
> > > > > -----Original Message-----
> > > > > From: Phil Yang <phil.yang@arm.com>
> > > > > Sent: Friday, June 12, 2020 6:20 AM
> > > > > To: dev@dpdk.org; Carrillo, Erik G <erik.g.carrillo@intel.com>
> > > > > Cc: drc@linux.vnet.ibm.com; honnappa.nagarahalli@arm.com;
> > > > > ruifeng.wang@arm.com; dharmik.thakkar@arm.com; nd@arm.com;
> > > > > stable@dpdk.org
> > > > > Subject: [PATCH 1/3] eventdev: fix race condition on timer list
> > > > > counter
> > > > >
> > > > > The n_poll_lcores counter and poll_lcore array are shared
> > > > > between lcores and the update of these variables are out of the
> > > > > protection of spinlock on each lcore timer list. The
> > > > > read-modify-write operations of the counter are not atomic, so
> > > > > it has the potential of race condition
> > > > between lcores.
> > > > >
> > > > > Use c11 atomics with RELAXED ordering to prevent confliction.
> > > > >
> > > > > Fixes: cc7b73ea9e3b ("eventdev: add new software timer adapter")
> > > > > Cc: erik.g.carrillo@intel.com
> > > > > Cc: stable@dpdk.org
> > > > >
> > > > > Signed-off-by: Phil Yang <phil.yang@arm.com>
> > > > > Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
> > > > > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > > > > ---
> > > > >  lib/librte_eventdev/rte_event_timer_adapter.c | 16
> > > > > ++++++++++++----
> > > > >  1 file changed, 12 insertions(+), 4 deletions(-)
> > > > >
> > > > > diff --git a/lib/librte_eventdev/rte_event_timer_adapter.c
> > > > > b/lib/librte_eventdev/rte_event_timer_adapter.c
> > > > > index 005459f..6a0e283 100644
> > > > > --- a/lib/librte_eventdev/rte_event_timer_adapter.c
> > > > > +++ b/lib/librte_eventdev/rte_event_timer_adapter.c
> > > > > @@ -583,6 +583,7 @@ swtim_callback(struct rte_timer *tim)
> > > > > uint16_t nb_evs_invalid = 0;  uint64_t opaque;  int ret;
> > > > > +int n_lcores;
> > > > >
> > > > >  opaque = evtim->impl_opaque[1];  adapter = (struct
> > > > > rte_event_timer_adapter *)(uintptr_t)opaque; @@
> > > > > -605,8 +606,12 @@ swtim_callback(struct rte_timer *tim)
> > > > >        "with immediate expiry value");  }
> > > > >
> > > > > -if (unlikely(rte_atomic16_test_and_set(&sw-
> > > > > >in_use[lcore].v)))
> > > > > -sw->poll_lcores[sw->n_poll_lcores++] = lcore;
> > > > > +if (unlikely(rte_atomic16_test_and_set(&sw-
> > > > > >in_use[lcore].v))) {
> > > > > +n_lcores = __atomic_fetch_add(&sw->n_poll_lcores,
> > > > > 1,
> > > > > +__ATOMIC_RELAXED);
> > > Since this commit will be back ported, we should prefer to use
> > > rte_atomic APIs for this commit. Otherwise, we will have a mix of
> > > rte_atomic and C11 APIs.
> > > My suggestion is to fix this bug using rte_atomic so that backported
> > > code will have only rte_atomic APIs. Add another commit (if
> > > required) in this series to make the bug fix use C11 APIs (this
> > > commit will not be
> > backported).
> >
> > Hi Honnappa,
> >
> > It doesn't have an applicable rte_atomic_XXX API to fix this issue.
> > The rte_atomic32_inc doesn't return the original value of the input
> > parameter and rte_atomic32_add_return can only return the new value.
> Ok, understood.
> 
> >
> > Meanwhile, the rte_timer_alt_manage & rte_timer_stop_all API not
> > support rte_atomic type parameters. We might need to rewrite these two
> > APIs if we want to use rte_atomic operations for n_pol_lcores and
> poll_lcores array.
> >
> > So, a better solution could be to backport the entire c11 solution to
> > stable releases.
> I am ok with the approach.
> Erik, are you ok with this?
> 

Yes, I'm OK with that as well.

Thanks,
Erik

> >
> > Thanks,
> > Phil
> >
> > >
> > > >
> > > > Just a nit, but let's align the continued line with the opening
> > > > parentheses in this location and below.  With these changes:
> > > >
> > > > Acked-by: Erik Gabriel Carrillo <erik.g.carrillo@intel.com>
> > > >
> > > > > +__atomic_store_n(&sw->poll_lcores[n_lcores],
> > > > > lcore,
> > > > > +__ATOMIC_RELAXED);
> > > > > +}
> > > > >  } else {
> > > > >  EVTIM_BUF_LOG_DBG("buffered an event timer expiry event");
> > > > >
> > > > > @@ -1011,6 +1016,7 @@ __swtim_arm_burst(const struct
> > > > > rte_event_timer_adapter *adapter,  uint32_t lcore_id =
> > > > > rte_lcore_id();  struct rte_timer *tim, *tims[nb_evtims];
> > > > > uint64_t cycles;
> > > > > +int n_lcores;
> > > > >
> > > > >  #ifdef RTE_LIBRTE_EVENTDEV_DEBUG
> > > > >  /* Check that the service is running. */ @@ -1033,8 +1039,10 @@
> > > > > __swtim_arm_burst(const struct rte_event_timer_adapter *adapter,
> > > > > if
> > > > > (unlikely(rte_atomic16_test_and_set(&sw->in_use[lcore_id].v)))
> > > > > {  EVTIM_LOG_DBG("Adding lcore id = %u to list of lcores to
> > > > poll",
> > > > >        lcore_id);
> > > > > -sw->poll_lcores[sw->n_poll_lcores] = lcore_id;
> > > > > -++sw->n_poll_lcores;
> > > > > +n_lcores = __atomic_fetch_add(&sw->n_poll_lcores, 1,
> > > > > +__ATOMIC_RELAXED); __atomic_store_n(&sw-
> >poll_lcores[n_lcores],
> > > > > +lcore_id, __ATOMIC_RELAXED);
> > > > >  }
> > > > >
> > > > >  ret = rte_mempool_get_bulk(sw->tim_pool, (void **)tims,
> > > > > --
> > > > > 2.7.4
> > >
Honnappa Nagarahalli July 2, 2020, 9:30 p.m. UTC | #10 
<snip>

> > > >
> > > > >
> > > > > Hi Phil,
> > > > >
> > > > > Good catch - thanks for the fix.   I've commented in-line:
> > > > >
> > > > > > -----Original Message-----
> > > > > > From: Phil Yang <phil.yang@arm.com>
> > > > > > Sent: Friday, June 12, 2020 6:20 AM
> > > > > > To: dev@dpdk.org; Carrillo, Erik G <erik.g.carrillo@intel.com>
> > > > > > Cc: drc@linux.vnet.ibm.com; honnappa.nagarahalli@arm.com;
> > > > > > ruifeng.wang@arm.com; dharmik.thakkar@arm.com; nd@arm.com;
> > > > > > stable@dpdk.org
> > > > > > Subject: [PATCH 1/3] eventdev: fix race condition on timer
> > > > > > list counter
> > > > > >
> > > > > > The n_poll_lcores counter and poll_lcore array are shared
> > > > > > between lcores and the update of these variables are out of
> > > > > > the protection of spinlock on each lcore timer list. The
> > > > > > read-modify-write operations of the counter are not atomic, so
> > > > > > it has the potential of race condition
> > > > > between lcores.
> > > > > >
> > > > > > Use c11 atomics with RELAXED ordering to prevent confliction.
> > > > > >
> > > > > > Fixes: cc7b73ea9e3b ("eventdev: add new software timer
> > > > > > adapter")
> > > > > > Cc: erik.g.carrillo@intel.com
> > > > > > Cc: stable@dpdk.org
> > > > > >
> > > > > > Signed-off-by: Phil Yang <phil.yang@arm.com>
> > > > > > Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
> > > > > > Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> > > > > > ---
> > > > > >  lib/librte_eventdev/rte_event_timer_adapter.c | 16
> > > > > > ++++++++++++----
> > > > > >  1 file changed, 12 insertions(+), 4 deletions(-)
> > > > > >
> > > > > > diff --git a/lib/librte_eventdev/rte_event_timer_adapter.c
> > > > > > b/lib/librte_eventdev/rte_event_timer_adapter.c
> > > > > > index 005459f..6a0e283 100644
> > > > > > --- a/lib/librte_eventdev/rte_event_timer_adapter.c
> > > > > > +++ b/lib/librte_eventdev/rte_event_timer_adapter.c
> > > > > > @@ -583,6 +583,7 @@ swtim_callback(struct rte_timer *tim)
> > > > > > uint16_t nb_evs_invalid = 0;  uint64_t opaque;  int ret;
> > > > > > +int n_lcores;
> > > > > >
> > > > > >  opaque = evtim->impl_opaque[1];  adapter = (struct
> > > > > > rte_event_timer_adapter *)(uintptr_t)opaque; @@
> > > > > > -605,8 +606,12 @@ swtim_callback(struct rte_timer *tim)
> > > > > >        "with immediate expiry value");  }
> > > > > >
> > > > > > -if (unlikely(rte_atomic16_test_and_set(&sw-
> > > > > > >in_use[lcore].v)))
> > > > > > -sw->poll_lcores[sw->n_poll_lcores++] = lcore;
> > > > > > +if (unlikely(rte_atomic16_test_and_set(&sw-
> > > > > > >in_use[lcore].v))) {
> > > > > > +n_lcores = __atomic_fetch_add(&sw->n_poll_lcores,
> > > > > > 1,
> > > > > > +__ATOMIC_RELAXED);
> > > > Since this commit will be back ported, we should prefer to use
> > > > rte_atomic APIs for this commit. Otherwise, we will have a mix of
> > > > rte_atomic and C11 APIs.
> > > > My suggestion is to fix this bug using rte_atomic so that
> > > > backported code will have only rte_atomic APIs. Add another commit
> > > > (if
> > > > required) in this series to make the bug fix use C11 APIs (this
> > > > commit will not be
> > > backported).
> > >
> > > Hi Honnappa,
> > >
> > > It doesn't have an applicable rte_atomic_XXX API to fix this issue.
> > > The rte_atomic32_inc doesn't return the original value of the input
> > > parameter and rte_atomic32_add_return can only return the new value.
> > Ok, understood.
> >
> > >
> > > Meanwhile, the rte_timer_alt_manage & rte_timer_stop_all API not
> > > support rte_atomic type parameters. We might need to rewrite these
> > > two APIs if we want to use rte_atomic operations for n_pol_lcores
> > > and
> > poll_lcores array.
> > >
> > > So, a better solution could be to backport the entire c11 solution
> > > to stable releases.
> > I am ok with the approach.
> > Erik, are you ok with this?
> >
> 
> Yes, I'm OK with that as well.
Thanks Erik. I think we need to add stable@dpdk.org to Cc for all the commits in the series.

> 
> Thanks,
> Erik
> 
> > >
> > > Thanks,
> > > Phil
> > >
> > > >
> > > > >
> > > > > Just a nit, but let's align the continued line with the opening
> > > > > parentheses in this location and below.  With these changes:
> > > > >
> > > > > Acked-by: Erik Gabriel Carrillo <erik.g.carrillo@intel.com>
> > > > >
> > > > > > +__atomic_store_n(&sw->poll_lcores[n_lcores],
> > > > > > lcore,
> > > > > > +__ATOMIC_RELAXED);
> > > > > > +}
> > > > > >  } else {
> > > > > >  EVTIM_BUF_LOG_DBG("buffered an event timer expiry event");
> > > > > >
> > > > > > @@ -1011,6 +1016,7 @@ __swtim_arm_burst(const struct
> > > > > > rte_event_timer_adapter *adapter,  uint32_t lcore_id =
> > > > > > rte_lcore_id();  struct rte_timer *tim, *tims[nb_evtims];
> > > > > > uint64_t cycles;
> > > > > > +int n_lcores;
> > > > > >
> > > > > >  #ifdef RTE_LIBRTE_EVENTDEV_DEBUG
> > > > > >  /* Check that the service is running. */ @@ -1033,8 +1039,10
> > > > > > @@ __swtim_arm_burst(const struct rte_event_timer_adapter
> > > > > > *adapter, if
> > > > > > (unlikely(rte_atomic16_test_and_set(&sw->in_use[lcore_id].v)))
> > > > > > {  EVTIM_LOG_DBG("Adding lcore id = %u to list of lcores to
> > > > > poll",
> > > > > >        lcore_id);
> > > > > > -sw->poll_lcores[sw->n_poll_lcores] = lcore_id;
> > > > > > -++sw->n_poll_lcores;
> > > > > > +n_lcores = __atomic_fetch_add(&sw->n_poll_lcores, 1,
> > > > > > +__ATOMIC_RELAXED); __atomic_store_n(&sw-
> > >poll_lcores[n_lcores],
> > > > > > +lcore_id, __ATOMIC_RELAXED);
> > > > > >  }
> > > > > >
> > > > > >  ret = rte_mempool_get_bulk(sw->tim_pool, (void **)tims,
> > > > > > --
> > > > > > 2.7.4
> > > >
diff mbox series

Patch

diff --git a/lib/librte_eventdev/rte_event_timer_adapter.c b/lib/librte_eventdev/rte_event_timer_adapter.c
index 005459f..6a0e283 100644
--- a/lib/librte_eventdev/rte_event_timer_adapter.c
+++ b/lib/librte_eventdev/rte_event_timer_adapter.c
@@ -583,6 +583,7 @@  swtim_callback(struct rte_timer *tim)
 	uint16_t nb_evs_invalid = 0;
 	uint64_t opaque;
 	int ret;
+	int n_lcores;
 
 	opaque = evtim->impl_opaque[1];
 	adapter = (struct rte_event_timer_adapter *)(uintptr_t)opaque;
@@ -605,8 +606,12 @@  swtim_callback(struct rte_timer *tim)
 				      "with immediate expiry value");
 		}
 
-		if (unlikely(rte_atomic16_test_and_set(&sw->in_use[lcore].v)))
-			sw->poll_lcores[sw->n_poll_lcores++] = lcore;
+		if (unlikely(rte_atomic16_test_and_set(&sw->in_use[lcore].v))) {
+			n_lcores = __atomic_fetch_add(&sw->n_poll_lcores, 1,
+						__ATOMIC_RELAXED);
+			__atomic_store_n(&sw->poll_lcores[n_lcores], lcore,
+						__ATOMIC_RELAXED);
+		}
 	} else {
 		EVTIM_BUF_LOG_DBG("buffered an event timer expiry event");
 
@@ -1011,6 +1016,7 @@  __swtim_arm_burst(const struct rte_event_timer_adapter *adapter,
 	uint32_t lcore_id = rte_lcore_id();
 	struct rte_timer *tim, *tims[nb_evtims];
 	uint64_t cycles;
+	int n_lcores;
 
 #ifdef RTE_LIBRTE_EVENTDEV_DEBUG
 	/* Check that the service is running. */
@@ -1033,8 +1039,10 @@  __swtim_arm_burst(const struct rte_event_timer_adapter *adapter,
 	if (unlikely(rte_atomic16_test_and_set(&sw->in_use[lcore_id].v))) {
 		EVTIM_LOG_DBG("Adding lcore id = %u to list of lcores to poll",
 			      lcore_id);
-		sw->poll_lcores[sw->n_poll_lcores] = lcore_id;
-		++sw->n_poll_lcores;
+		n_lcores = __atomic_fetch_add(&sw->n_poll_lcores, 1,
+						__ATOMIC_RELAXED);
+		__atomic_store_n(&sw->poll_lcores[n_lcores], lcore_id,
+						__ATOMIC_RELAXED);
 	}
 
 	ret = rte_mempool_get_bulk(sw->tim_pool, (void **)tims,