All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v2] nvme-rdma: handle nvme completion data length
@ 2020-10-23  6:59 ` zhenwei pi
  0 siblings, 0 replies; 8+ messages in thread
From: zhenwei pi @ 2020-10-23  6:59 UTC (permalink / raw)
  To: kbusch, hch, sagi, axboe; +Cc: linux-nvme, linux-kernel, pizhenwei

Hit a kernel warning:
refcount_t: underflow; use-after-free.
WARNING: CPU: 0 PID: 0 at lib/refcount.c:28

RIP: 0010:refcount_warn_saturate+0xd9/0xe0
Call Trace:
 <IRQ>
 nvme_rdma_recv_done+0xf3/0x280 [nvme_rdma]
 __ib_process_cq+0x76/0x150 [ib_core]
 ...

The reason is that a zero bytes message received from target, and the
host side continues to process without length checking, then the
previous CQE is processed twice.

Handle data length, ignore zero bytes message, and try to recovery for
corrupted CQE case.

Thanks to Chao Leng for suggestions.

Signed-off-by: zhenwei pi <pizhenwei@bytedance.com>
---
 drivers/nvme/host/rdma.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 9e378d0a0c01..2ecadd309f4a 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1767,6 +1767,21 @@ static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 		return;
 	}
 
+	/* received data length checking */
+	if (unlikely(wc->byte_len < len)) {
+		/* zero bytes message could be ignored */
+		if (!wc->byte_len) {
+			nvme_rdma_post_recv(queue, qe);
+			return;
+		}
+
+		/* corrupted completion, try to recovry */
+		dev_err(queue->ctrl->ctrl.device,
+			"Unexpected nvme completion length(%d)\n", wc->byte_len);
+		nvme_rdma_error_recovery(queue->ctrl);
+		return;
+	}
+
 	ib_dma_sync_single_for_cpu(ibdev, qe->dma, len, DMA_FROM_DEVICE);
 	/*
 	 * AEN requests are special as they don't time out and can
-- 
2.11.0


^ permalink raw reply related	[flat|nested] 8+ messages in thread
* [PATCH v2] nvme-rdma: handle nvme completion data length
@ 2020-10-23  6:59 ` zhenwei pi
  0 siblings, 0 replies; 8+ messages in thread
From: zhenwei pi @ 2020-10-23  6:59 UTC (permalink / raw)
  To: kbusch, hch, sagi, axboe; +Cc: pizhenwei, linux-kernel, linux-nvme

Hit a kernel warning:
refcount_t: underflow; use-after-free.
WARNING: CPU: 0 PID: 0 at lib/refcount.c:28

RIP: 0010:refcount_warn_saturate+0xd9/0xe0
Call Trace:
 <IRQ>
 nvme_rdma_recv_done+0xf3/0x280 [nvme_rdma]
 __ib_process_cq+0x76/0x150 [ib_core]
 ...

The reason is that a zero bytes message received from target, and the
host side continues to process without length checking, then the
previous CQE is processed twice.

Handle data length, ignore zero bytes message, and try to recovery for
corrupted CQE case.

Thanks to Chao Leng for suggestions.

Signed-off-by: zhenwei pi <pizhenwei@bytedance.com>
---
 drivers/nvme/host/rdma.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 9e378d0a0c01..2ecadd309f4a 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1767,6 +1767,21 @@ static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 		return;
 	}
 
+	/* received data length checking */
+	if (unlikely(wc->byte_len < len)) {
+		/* zero bytes message could be ignored */
+		if (!wc->byte_len) {
+			nvme_rdma_post_recv(queue, qe);
+			return;
+		}
+
+		/* corrupted completion, try to recovry */
+		dev_err(queue->ctrl->ctrl.device,
+			"Unexpected nvme completion length(%d)\n", wc->byte_len);
+		nvme_rdma_error_recovery(queue->ctrl);
+		return;
+	}
+
 	ib_dma_sync_single_for_cpu(ibdev, qe->dma, len, DMA_FROM_DEVICE);
 	/*
 	 * AEN requests are special as they don't time out and can
-- 
2.11.0


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

^ permalink raw reply related	[flat|nested] 8+ messages in thread
* Re: [PATCH v2] nvme-rdma: handle nvme completion data length
  2020-10-23  6:59 ` zhenwei pi
@ 2020-10-23  8:45   ` Chao Leng
  -1 siblings, 0 replies; 8+ messages in thread
From: Chao Leng @ 2020-10-23  8:45 UTC (permalink / raw)
  To: zhenwei pi, kbusch, hch, sagi, axboe; +Cc: linux-kernel, linux-nvme

Looks good.

Reviewed-by: Chao Leng <lengchao@huawei.com>

On 2020/10/23 14:59, zhenwei pi wrote:
> Hit a kernel warning:
> refcount_t: underflow; use-after-free.
> WARNING: CPU: 0 PID: 0 at lib/refcount.c:28
> 
> RIP: 0010:refcount_warn_saturate+0xd9/0xe0
> Call Trace:
>   <IRQ>
>   nvme_rdma_recv_done+0xf3/0x280 [nvme_rdma]
>   __ib_process_cq+0x76/0x150 [ib_core]
>   ...
> 
> The reason is that a zero bytes message received from target, and the
> host side continues to process without length checking, then the
> previous CQE is processed twice.
> 
> Handle data length, ignore zero bytes message, and try to recovery for
> corrupted CQE case.
> 
> Thanks to Chao Leng for suggestions.
> 
> Signed-off-by: zhenwei pi <pizhenwei@bytedance.com>
> ---
>   drivers/nvme/host/rdma.c | 15 +++++++++++++++
>   1 file changed, 15 insertions(+)
> 
> diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
> index 9e378d0a0c01..2ecadd309f4a 100644
> --- a/drivers/nvme/host/rdma.c
> +++ b/drivers/nvme/host/rdma.c
> @@ -1767,6 +1767,21 @@ static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
>   		return;
>   	}
>   
> +	/* received data length checking */
> +	if (unlikely(wc->byte_len < len)) {
> +		/* zero bytes message could be ignored */
> +		if (!wc->byte_len) {
> +			nvme_rdma_post_recv(queue, qe);
> +			return;
> +		}
> +
> +		/* corrupted completion, try to recovry */
> +		dev_err(queue->ctrl->ctrl.device,
> +			"Unexpected nvme completion length(%d)\n", wc->byte_len);
> +		nvme_rdma_error_recovery(queue->ctrl);
> +		return;
> +	}
> +
>   	ib_dma_sync_single_for_cpu(ibdev, qe->dma, len, DMA_FROM_DEVICE);
>   	/*
>   	 * AEN requests are special as they don't time out and can
> 

^ permalink raw reply	[flat|nested] 8+ messages in thread
* Re: [PATCH v2] nvme-rdma: handle nvme completion data length
@ 2020-10-23  8:45   ` Chao Leng
  0 siblings, 0 replies; 8+ messages in thread
From: Chao Leng @ 2020-10-23  8:45 UTC (permalink / raw)
  To: zhenwei pi, kbusch, hch, sagi, axboe; +Cc: linux-kernel, linux-nvme

Looks good.

Reviewed-by: Chao Leng <lengchao@huawei.com>

On 2020/10/23 14:59, zhenwei pi wrote:
> Hit a kernel warning:
> refcount_t: underflow; use-after-free.
> WARNING: CPU: 0 PID: 0 at lib/refcount.c:28
> 
> RIP: 0010:refcount_warn_saturate+0xd9/0xe0
> Call Trace:
>   <IRQ>
>   nvme_rdma_recv_done+0xf3/0x280 [nvme_rdma]
>   __ib_process_cq+0x76/0x150 [ib_core]
>   ...
> 
> The reason is that a zero bytes message received from target, and the
> host side continues to process without length checking, then the
> previous CQE is processed twice.
> 
> Handle data length, ignore zero bytes message, and try to recovery for
> corrupted CQE case.
> 
> Thanks to Chao Leng for suggestions.
> 
> Signed-off-by: zhenwei pi <pizhenwei@bytedance.com>
> ---
>   drivers/nvme/host/rdma.c | 15 +++++++++++++++
>   1 file changed, 15 insertions(+)
> 
> diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
> index 9e378d0a0c01..2ecadd309f4a 100644
> --- a/drivers/nvme/host/rdma.c
> +++ b/drivers/nvme/host/rdma.c
> @@ -1767,6 +1767,21 @@ static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
>   		return;
>   	}
>   
> +	/* received data length checking */
> +	if (unlikely(wc->byte_len < len)) {
> +		/* zero bytes message could be ignored */
> +		if (!wc->byte_len) {
> +			nvme_rdma_post_recv(queue, qe);
> +			return;
> +		}
> +
> +		/* corrupted completion, try to recovry */
> +		dev_err(queue->ctrl->ctrl.device,
> +			"Unexpected nvme completion length(%d)\n", wc->byte_len);
> +		nvme_rdma_error_recovery(queue->ctrl);
> +		return;
> +	}
> +
>   	ib_dma_sync_single_for_cpu(ibdev, qe->dma, len, DMA_FROM_DEVICE);
>   	/*
>   	 * AEN requests are special as they don't time out and can
> 

_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

^ permalink raw reply	[flat|nested] 8+ messages in thread
* Re: [PATCH v2] nvme-rdma: handle nvme completion data length
  2020-10-23  6:59 ` zhenwei pi
@ 2020-10-23 18:01   ` Sagi Grimberg
  -1 siblings, 0 replies; 8+ messages in thread
From: Sagi Grimberg @ 2020-10-23 18:01 UTC (permalink / raw)
  To: zhenwei pi, kbusch, hch, axboe; +Cc: linux-nvme, linux-kernel


> diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
> index 9e378d0a0c01..2ecadd309f4a 100644
> --- a/drivers/nvme/host/rdma.c
> +++ b/drivers/nvme/host/rdma.c
> @@ -1767,6 +1767,21 @@ static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
>   		return;
>   	}
>   
> +	/* received data length checking */
> +	if (unlikely(wc->byte_len < len)) {
> +		/* zero bytes message could be ignored */
> +		if (!wc->byte_len) {
> +			nvme_rdma_post_recv(queue, qe);
> +			return;
> +		}

Nothing in the spec defines zero-length messages, hence we cannot
support something that is not standard. If your array needs this,
please submit a TPAR to the NVMe TWG.

^ permalink raw reply	[flat|nested] 8+ messages in thread
* Re: [PATCH v2] nvme-rdma: handle nvme completion data length
@ 2020-10-23 18:01   ` Sagi Grimberg
  0 siblings, 0 replies; 8+ messages in thread
From: Sagi Grimberg @ 2020-10-23 18:01 UTC (permalink / raw)
  To: zhenwei pi, kbusch, hch, axboe; +Cc: linux-kernel, linux-nvme


> diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
> index 9e378d0a0c01..2ecadd309f4a 100644
> --- a/drivers/nvme/host/rdma.c
> +++ b/drivers/nvme/host/rdma.c
> @@ -1767,6 +1767,21 @@ static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
>   		return;
>   	}
>   
> +	/* received data length checking */
> +	if (unlikely(wc->byte_len < len)) {
> +		/* zero bytes message could be ignored */
> +		if (!wc->byte_len) {
> +			nvme_rdma_post_recv(queue, qe);
> +			return;
> +		}

Nothing in the spec defines zero-length messages, hence we cannot
support something that is not standard. If your array needs this,
please submit a TPAR to the NVMe TWG.

_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

^ permalink raw reply	[flat|nested] 8+ messages in thread
* Re: [PATCH v2] nvme-rdma: handle nvme completion data length
  2020-10-23 18:01   ` Sagi Grimberg
@ 2020-10-24  7:36     ` Christoph Hellwig
  -1 siblings, 0 replies; 8+ messages in thread
From: Christoph Hellwig @ 2020-10-24  7:36 UTC (permalink / raw)
  To: Sagi Grimberg; +Cc: zhenwei pi, kbusch, hch, axboe, linux-nvme, linux-kernel

On Fri, Oct 23, 2020 at 11:01:40AM -0700, Sagi Grimberg wrote:
>>   +	/* received data length checking */
>> +	if (unlikely(wc->byte_len < len)) {
>> +		/* zero bytes message could be ignored */
>> +		if (!wc->byte_len) {
>> +			nvme_rdma_post_recv(queue, qe);
>> +			return;
>> +		}
>
> Nothing in the spec defines zero-length messages, hence we cannot
> support something that is not standard. If your array needs this,
> please submit a TPAR to the NVMe TWG.

We'll still need sanity checking instead of the recount underflow,
I think tearing down the connection here and kicking off error recovery
is probably the best idea.

^ permalink raw reply	[flat|nested] 8+ messages in thread
* Re: [PATCH v2] nvme-rdma: handle nvme completion data length
@ 2020-10-24  7:36     ` Christoph Hellwig
  0 siblings, 0 replies; 8+ messages in thread
From: Christoph Hellwig @ 2020-10-24  7:36 UTC (permalink / raw)
  To: Sagi Grimberg; +Cc: linux-kernel, linux-nvme, axboe, zhenwei pi, kbusch, hch

On Fri, Oct 23, 2020 at 11:01:40AM -0700, Sagi Grimberg wrote:
>>   +	/* received data length checking */
>> +	if (unlikely(wc->byte_len < len)) {
>> +		/* zero bytes message could be ignored */
>> +		if (!wc->byte_len) {
>> +			nvme_rdma_post_recv(queue, qe);
>> +			return;
>> +		}
>
> Nothing in the spec defines zero-length messages, hence we cannot
> support something that is not standard. If your array needs this,
> please submit a TPAR to the NVMe TWG.

We'll still need sanity checking instead of the recount underflow,
I think tearing down the connection here and kicking off error recovery
is probably the best idea.

_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

^ permalink raw reply	[flat|nested] 8+ messages in thread
end of thread, other threads:[~2020-10-24  7:36 UTC | newest]

Thread overview: 8+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-10-23  6:59 [PATCH v2] nvme-rdma: handle nvme completion data length zhenwei pi
2020-10-23  6:59 ` zhenwei pi
2020-10-23  8:45 ` Chao Leng
2020-10-23  8:45   ` Chao Leng
2020-10-23 18:01 ` Sagi Grimberg
2020-10-23 18:01   ` Sagi Grimberg
2020-10-24  7:36   ` Christoph Hellwig
2020-10-24  7:36     ` Christoph Hellwig

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.