search for: producer_lock

...e(struct ptr_ring *r, void **queue, + int size, gfp_t gfp, + void (*destroy)(void *)) { - unsigned long flags; int producer = 0; - void **queue = __ptr_ring_init_queue_alloc(size, gfp); void **old; void *ptr; - if (!queue) - return -ENOMEM; - - spin_lock_irqsave(&(r)->producer_lock, flags); - while ((ptr = ptr_ring_consume(r))) if (producer < size) queue[producer++] = ptr; @@ -380,6 +374,23 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, old = r->queue; r->queue = queue; + return old; +} + +static inline int ptr_ring_resiz...

...e(struct ptr_ring *r, void **queue, + int size, gfp_t gfp, + void (*destroy)(void *)) { - unsigned long flags; int producer = 0; - void **queue = __ptr_ring_init_queue_alloc(size, gfp); void **old; void *ptr; - if (!queue) - return -ENOMEM; - - spin_lock_irqsave(&(r)->producer_lock, flags); - while ((ptr = ptr_ring_consume(r))) if (producer < size) queue[producer++] = ptr; @@ -380,6 +374,23 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, old = r->queue; r->queue = queue; + return old; +} + +static inline int ptr_ring_resiz...

...tr_ring.h index 37b4bb2..6866df4 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -101,12 +101,18 @@ static inline bool ptr_ring_full_bh(struct ptr_ring *r) /* Note: callers invoking this in a loop must use a compiler barrier, * for example cpu_relax(). Callers must hold producer_lock. + * Callers are responsible for making sure pointer that is being queued + * points to a valid data. */ static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr) { if (unlikely(!r->size) || r->queue[r->producer]) return -ENOSPC; + /* Make sure the pointer we are stori...

...tr_ring.h index 37b4bb2..6866df4 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -101,12 +101,18 @@ static inline bool ptr_ring_full_bh(struct ptr_ring *r) /* Note: callers invoking this in a loop must use a compiler barrier, * for example cpu_relax(). Callers must hold producer_lock. + * Callers are responsible for making sure pointer that is being queued + * points to a valid data. */ static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr) { if (unlikely(!r->size) || r->queue[r->producer]) return -ENOSPC; + /* Make sure the pointer we are stori...

...to consumers, but that actually requires an smb_wmb > or a stronger barrier. This is not the exact situation we are seeing. Let me try to explain the situation Affected on ARM64 platform. 1) tun_net_xmit calls skb_array_produce, which pushes the skb to the ptr_ring, this push is protected by a producer_lock. 2)Prior to this call the tun_net_xmit calls skb_orphan which calls the skb->destructor and sets skb->destructor and skb->sk as NULL. 2.a) These 2 writes are getting reordered 3) At the same time in the receive side (tun_ring_recv), which gets executed in another core calls skb_array_...

...stronger barrier. > This is not the exact situation we are seeing. Could you test the patch pls? > Let me try to explain the situation > > Affected on ARM64 platform. > 1) tun_net_xmit calls skb_array_produce, which pushes the skb to the > ptr_ring, this push is protected by a producer_lock. > > 2)Prior to this call the tun_net_xmit calls skb_orphan which calls the > skb->destructor and sets skb->destructor and skb->sk as NULL. > > 2.a) These 2 writes are getting reordered > > 3) At the same time in the receive side (tun_ring_recv), which gets executed...

Hi all: This series tries to switch to use skb array in tun. This is used to eliminate the spinlock contention between producer and consumer. The conversion was straightforward: just introdce a tx skb array and use it instead of sk_receive_queue. A minor issue is to keep the tx_queue_len behaviour, since tun used to use it for the length of sk_receive_queue. This is done through: - add the

Hi all: This series tries to switch to use skb array in tun. This is used to eliminate the spinlock contention between producer and consumer. The conversion was straightforward: just introdce a tx skb array and use it instead of sk_receive_queue. A minor issue is to keep the tx_queue_len behaviour, since tun used to use it for the length of sk_receive_queue. This is done through: - add the

Hi all: This series tries to switch to use skb array in tun. This is used to eliminate the spinlock contention between producer and consumer. The conversion was straightforward: just introdce a tx skb array and use it instead of sk_receive_queue. A minor issue is to keep the tx_queue_len behaviour, since tun used to use it for the length of sk_receive_queue. This is done through: - add the

Hi all: This series tries to switch to use skb array in tun. This is used to eliminate the spinlock contention between producer and consumer. The conversion was straightforward: just introdce a tx skb array and use it instead of sk_receive_queue. A minor issue is to keep the tx_queue_len behaviour, since tun used to use it for the length of sk_receive_queue. This is done through: - add the

...--- a/include/linux/ptr_ring.h > > +++ b/include/linux/ptr_ring.h > > @@ -101,12 +101,18 @@ static inline bool ptr_ring_full_bh(struct ptr_ring *r) > > /* Note: callers invoking this in a loop must use a compiler barrier, > > * for example cpu_relax(). Callers must hold producer_lock. > > + * Callers are responsible for making sure pointer that is being queued > > + * points to a valid data. > > */ > > static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr) > > { > > if (unlikely(!r->size) || r->queue[r->produce...

...--- a/include/linux/ptr_ring.h > > +++ b/include/linux/ptr_ring.h > > @@ -101,12 +101,18 @@ static inline bool ptr_ring_full_bh(struct ptr_ring *r) > > /* Note: callers invoking this in a loop must use a compiler barrier, > > * for example cpu_relax(). Callers must hold producer_lock. > > + * Callers are responsible for making sure pointer that is being queued > > + * points to a valid data. > > */ > > static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr) > > { > > if (unlikely(!r->size) || r->queue[r->produce...

We used to queue tx packets in sk_receive_queue, this is less efficient since it requires spinlocks to synchronize between producer and consumer. This patch tries to address this by: - introduce a new mode which will be only enabled with IFF_TX_ARRAY set and switch from sk_receive_queue to a fixed size of skb array with 256 entries in this mode. - introduce a new proto_ops peek_len which was

We used to queue tx packets in sk_receive_queue, this is less efficient since it requires spinlocks to synchronize between producer and consumer. This patch tries to address this by: - introduce a new mode which will be only enabled with IFF_TX_ARRAY set and switch from sk_receive_queue to a fixed size of skb array with 256 entries in this mode. - introduce a new proto_ops peek_len which was

...100644 > --- a/include/linux/ptr_ring.h > +++ b/include/linux/ptr_ring.h > @@ -101,12 +101,18 @@ static inline bool ptr_ring_full_bh(struct ptr_ring *r) > > /* Note: callers invoking this in a loop must use a compiler barrier, > * for example cpu_relax(). Callers must hold producer_lock. > + * Callers are responsible for making sure pointer that is being queued > + * points to a valid data. > */ > static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr) > { > if (unlikely(!r->size) || r->queue[r->producer]) > return -ENOSPC; &...