[PATCH v2] nvmet-fc: associations list protected by rcu, instead of spinlock_irq where possible.

2021-01-03 Thread leonid . ravich
From: Leonid Ravich searching assoc_list protected by rcu_read_lock if list not changed inline. and according to the rcu list rules. queue array embedded into nvmet_fc_tgt_assoc protected by rcu_read_lock according to rcu dereference/assign rules. queue and assoc object freed after grace

[PATCH v2] nvmet-fc: associations list protected by rcu, instead of spinlock_irq where possible.

2021-01-03 Thread leonid . ravich
From: Leonid Ravich searching assoc_list protected by rcu_read_lock if list not changed inline. and according to the rcu list rules. queue array embedded into nvmet_fc_tgt_assoc protected by rcu_read_lock according to rcu dereference/assign rules. queue and assoc object freed after grace

[PATCH] nvmet-fc: associations list replaced with hlist rcu,

2020-12-24 Thread leonid . ravich
From: Leonid Ravich to remove locking from nvmet_fc_find_target_queue which called per IO. Signed-off-by: Leonid Ravich --- drivers/nvme/target/fc.c | 54 1 file changed, 32 insertions(+), 22 deletions(-) diff --git a/drivers/nvme/target/fc.c

[PATCH] nvmet-fc: associations list replaced with hlist rcu,

2020-12-24 Thread leonid . ravich
From: Leonid Ravich to remove locking from nvmet_fc_find_target_queue which called per IO. Signed-off-by: Leonid Ravich --- drivers/nvme/target/fc.c | 54 1 file changed, 32 insertions(+), 22 deletions(-) diff --git a/drivers/nvme/target/fc.c

[PATCH v2] dmaengine: ioat setting ioat timeout as module parameter

2020-07-01 Thread leonid . ravich
From: Leonid Ravich DMA transaction time to completion is a function of PCI bandwidth,transaction size and a queue depth. So hard coded value for timeouts might be wrong for some scenarios. Signed-off-by: Leonid Ravich --- Changing in v2 - misspelling of completion drivers/dma/ioat/dma.c

[PATCH] dmaengine: ioat setting ioat timeout as module parameter

2020-07-01 Thread leonid . ravich
From: Leonid Ravich DMA transaction time to complition is a function of PCI bandwidth,transaction size and a queue depth. So hard coded value for timeouts might be wrong for some scenarios. Signed-off-by: Leonid Ravich --- drivers/dma/ioat/dma.c | 12 drivers/dma/ioat/dma.h | 2