svcrdma: dma unmap the correct length for the RPCRDMA header page.
Subsystems (3)
PATCH 1/1 svcrdma: dma unmap the correct length for the RPCRDMA header page.
The svcrdma module was incorrectly unmapping the RPCRDMA header page. On IBM pserver systems this causes a resource leak that results in running out of bus address space (10 cthon iterations will reproduce it). The code was mapping the full page but only unmapping the actual header length. The fix is to only map the header length.
I also cleaned up the use of ib_dma_map_page() calls since the unmap logic always uses ib_dma_unmap_single(). I made these symmetrical.
---
net/sunrpc/xprtrdma/svc_rdma_sendto.c | 12 ++++++------ net/sunrpc/xprtrdma/svc_rdma_transport.c | 10 +++++----- 2 files changed, 11 insertions(+), 11 deletions(-)
net/sunrpc/xprtrdma/svc_rdma_sendto.c +6 -6
@@ -128,7 +128,8 @@ static int fast_reg_xdr(struct svcxprt_rdma *xprt, page_bytes -= sge_bytes; frmr->page_list->page_list[page_no] = -ib_dma_map_page (xprt->sc_cm_id->device, page,0 , +ib_dma_map_single (xprt->sc_cm_id->device, +page_address (page),PAGE_SIZE ,DMA_TO_DEVICE );if (ib_dma_mapping_error (xprt->sc_cm_id->device, frmr->page_list->page_list[page_no]))
@@ -532,18 +533,17 @@ static int send_reply(struct svcxprt_rdma *rdma,clear_bit (RDMACTXT_F_FAST_UNREG , &ctxt->flags);/* Prepare the SGE for the RPCRDMA Header */ + ctxt->sge[0 ].lkey = rdma->sc_dma_lkey; + ctxt->sge[0 ].length =svc_rdma_xdr_get_reply_hdr_len (rdma_resp); ctxt->sge[0 ].addr = -ib_dma_map_page (rdma->sc_cm_id->device, - page,0 ,PAGE_SIZE ,DMA_TO_DEVICE ); +ib_dma_map_single (rdma->sc_cm_id->device,page_address (page), + ctxt->sge[0 ].length,DMA_TO_DEVICE );if (ib_dma_mapping_error (rdma->sc_cm_id->device, ctxt->sge[0 ].addr)) goto err;atomic_inc (&rdma->sc_dma_used); ctxt->direction =DMA_TO_DEVICE ; - ctxt->sge[0 ].length =svc_rdma_xdr_get_reply_hdr_len (rdma_resp); - ctxt->sge[0 ].lkey = rdma->sc_dma_lkey; -/* Determine how many of our SGE are to be transmitted */ for (sge_no =1 ; byte_count && sge_no < vec->count; sge_no++) { sge_bytes =min_t (size_t, vec->sge[sge_no].iov_len, byte_count);
net/sunrpc/xprtrdma/svc_rdma_transport.c +5 -5
@@ -500,8 +500,8 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt)BUG_ON (sge_no >= xprt->sc_max_sge); page =svc_rdma_get_page (); ctxt->pages[sge_no] = page; - pa =ib_dma_map_page (xprt->sc_cm_id->device, - page,0 ,PAGE_SIZE , + pa =ib_dma_map_single (xprt->sc_cm_id->device, +page_address (page),PAGE_SIZE ,DMA_FROM_DEVICE );if (ib_dma_mapping_error (xprt->sc_cm_id->device, pa)) goto err_put_ctxt;
@@ -1315,8 +1315,8 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, length =svc_rdma_xdr_encode_error (xprt, rmsgp, err, va);/* Prepare SGE for local address */ - sge.addr =ib_dma_map_page (xprt->sc_cm_id->device, - p,0 ,PAGE_SIZE ,DMA_FROM_DEVICE ); + sge.addr =ib_dma_map_single (xprt->sc_cm_id->device, +page_address (p),PAGE_SIZE ,DMA_FROM_DEVICE );if (ib_dma_mapping_error (xprt->sc_cm_id->device, sge.addr)) {put_page (p);return ;
@@ -1343,7 +1343,7 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp,if (ret) {dprintk ("svcrdma: Error %d posting send for protocol error\n" , ret); -ib_dma_unmap_page (xprt->sc_cm_id->device, +ib_dma_unmap_single (xprt->sc_cm_id->device, sge.addr,PAGE_SIZE ,DMA_FROM_DEVICE );svc_rdma_put_context (ctxt,1 );
Hey Bruce,
Do you think this can make 2.6.30?
Thanks,
Steve.
Quoted 95 lines · Steve Wise
The svcrdma module was incorrectly unmapping the RPCRDMA header page. On IBM pserver systems this causes a resource leak that results in running out of bus address space (10 cthon iterations will reproduce it). The code was mapping the full page but only unmapping the actual header length. The fix is to only map the header length.
I also cleaned up the use of
ib_dma_map_page()calls since the unmap logic always usesib_dma_unmap_single(). I made these symmetrical.Signed-off-by Steve Wise <[email protected]>Signed-off-by Tom Tucker <[email protected]>---
net/sunrpc/xprtrdma/svc_rdma_sendto.c | 12 ++++++------ net/sunrpc/xprtrdma/svc_rdma_transport.c | 10 +++++----- 2 files changed, 11 insertions(+), 11 deletions(-)net/sunrpc/xprtrdma/svc_rdma_sendto.c +6
-6@@ -128,7 +128,8 @@ static int fast_reg_xdr(struct svcxprt_rdma *xprt, page_bytes -= sge_bytes; frmr->page_list->page_list[page_no] = -ib_dma_map_page (xprt->sc_cm_id->device, page,0 , +ib_dma_map_single (xprt->sc_cm_id->device, +page_address (page),PAGE_SIZE ,DMA_TO_DEVICE );if (ib_dma_mapping_error (xprt->sc_cm_id->device, frmr->page_list->page_list[page_no]))@@ -532,18 +533,17 @@ static int send_reply(struct svcxprt_rdma *rdma,clear_bit (RDMACTXT_F_FAST_UNREG , &ctxt->flags);/* Prepare the SGE for the RPCRDMA Header */ + ctxt->sge[0 ].lkey = rdma->sc_dma_lkey; + ctxt->sge[0 ].length =svc_rdma_xdr_get_reply_hdr_len (rdma_resp); ctxt->sge[0 ].addr = -ib_dma_map_page (rdma->sc_cm_id->device, - page,0 ,PAGE_SIZE ,DMA_TO_DEVICE ); +ib_dma_map_single (rdma->sc_cm_id->device,page_address (page), + ctxt->sge[0 ].length,DMA_TO_DEVICE );if (ib_dma_mapping_error (rdma->sc_cm_id->device, ctxt->sge[0 ].addr)) goto err;atomic_inc (&rdma->sc_dma_used); ctxt->direction =DMA_TO_DEVICE ; - ctxt->sge[0 ].length =svc_rdma_xdr_get_reply_hdr_len (rdma_resp); - ctxt->sge[0 ].lkey = rdma->sc_dma_lkey; -/* Determine how many of our SGE are to be transmitted */ for (sge_no =1 ; byte_count && sge_no < vec->count; sge_no++) { sge_bytes =min_t (size_t, vec->sge[sge_no].iov_len, byte_count);net/sunrpc/xprtrdma/svc_rdma_transport.c +5
-6@@ -500,8 +500,8 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt)BUG_ON (sge_no >= xprt->sc_max_sge); page =svc_rdma_get_page (); ctxt->pages[sge_no] = page; - pa =ib_dma_map_page (xprt->sc_cm_id->device, - page,0 ,PAGE_SIZE , + pa =ib_dma_map_single (xprt->sc_cm_id->device, +page_address (page),PAGE_SIZE ,DMA_FROM_DEVICE );if (ib_dma_mapping_error (xprt->sc_cm_id->device, pa)) goto err_put_ctxt;@@ -1315,8 +1315,8 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, length =svc_rdma_xdr_encode_error (xprt, rmsgp, err, va);/* Prepare SGE for local address */ - sge.addr =ib_dma_map_page (xprt->sc_cm_id->device, - p,0 ,PAGE_SIZE ,DMA_FROM_DEVICE ); + sge.addr =ib_dma_map_single (xprt->sc_cm_id->device, +page_address (p),PAGE_SIZE ,DMA_FROM_DEVICE );if (ib_dma_mapping_error (xprt->sc_cm_id->device, sge.addr)) {put_page (p);return ;@@ -1343,7 +1343,7 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp,if (ret) {dprintk ("svcrdma: Error %d posting send for protocol error\n" , ret); -ib_dma_unmap_page (xprt->sc_cm_id->device, +ib_dma_unmap_single (xprt->sc_cm_id->device, sge.addr,PAGE_SIZE ,DMA_FROM_DEVICE );svc_rdma_put_context (ctxt,1 ); --To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Quoted 3 lines · Steve Wise
Hey Bruce,
Do you think this can make 2.6.30?
I was going to save it for 2.6.31; vague mental scorecard:
- 2.6.30 is close to release
- I think of rdma (correctly or not?) as a little young, so don't prioritize bug-fixes to it quite as highly
- A resource leak (even as large as this) isn't the worst category of bug.
But I may be wrong.
--b.
Quoted 98 lines
Thanks,
Steve.
Quoted 90 lines · Steve Wise
The svcrdma module was incorrectly unmapping the RPCRDMA header page. On IBM pserver systems this causes a resource leak that results in running out of bus address space (10 cthon iterations will reproduce it). The code was mapping the full page but only unmapping the actual header length. The fix is to only map the header length.
I also cleaned up the use of
ib_dma_map_page()calls since the unmap logic always usesib_dma_unmap_single(). I made these symmetrical.Signed-off-by Steve Wise <[email protected]>Signed-off-by Tom Tucker <[email protected]>---
net/sunrpc/xprtrdma/svc_rdma_sendto.c | 12 ++++++------ net/sunrpc/xprtrdma/svc_rdma_transport.c | 10 +++++----- 2 files changed, 11 insertions(+), 11 deletions(-)net/sunrpc/xprtrdma/svc_rdma_sendto.c +5
-5@@ -128,7 +128,8 @@ static int fast_reg_xdr(struct svcxprt_rdma *xprt, page_bytes -= sge_bytes; frmr->page_list->page_list[page_no] = -ib_dma_map_page (xprt->sc_cm_id->device, page,0 , +ib_dma_map_single (xprt->sc_cm_id->device, +page_address (page),PAGE_SIZE ,DMA_TO_DEVICE );if (ib_dma_mapping_error (xprt->sc_cm_id->device, frmr->page_list->page_list[page_no]))@@ -532,18 +533,17 @@ static int send_reply(struct svcxprt_rdma *rdma,clear_bit (RDMACTXT_F_FAST_UNREG , &ctxt->flags);/* Prepare the SGE for the RPCRDMA Header */ + ctxt->sge[0 ].lkey = rdma->sc_dma_lkey; + ctxt->sge[0 ].length =svc_rdma_xdr_get_reply_hdr_len (rdma_resp); ctxt->sge[0 ].addr = -ib_dma_map_page (rdma->sc_cm_id->device, - page,0 ,PAGE_SIZE ,DMA_TO_DEVICE ); +ib_dma_map_single (rdma->sc_cm_id->device,page_address (page), + ctxt->sge[0 ].length,DMA_TO_DEVICE );if (ib_dma_mapping_error (rdma->sc_cm_id->device, ctxt->sge[0 ].addr)) goto err;atomic_inc (&rdma->sc_dma_used); ctxt->direction =DMA_TO_DEVICE ; - ctxt->sge[0 ].length =svc_rdma_xdr_get_reply_hdr_len (rdma_resp); - ctxt->sge[0 ].lkey = rdma->sc_dma_lkey; -/* Determine how many of our SGE are to be transmitted */ for (sge_no =1 ; byte_count && sge_no < vec->count; sge_no++) { sge_bytes =min_t (size_t, vec->sge[sge_no].iov_len, byte_count);net/sunrpc/xprtrdma/svc_rdma_transport.c +5
-6@@ -500,8 +500,8 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt)BUG_ON (sge_no >= xprt->sc_max_sge); page =svc_rdma_get_page (); ctxt->pages[sge_no] = page; - pa =ib_dma_map_page (xprt->sc_cm_id->device, - page,0 ,PAGE_SIZE , + pa =ib_dma_map_single (xprt->sc_cm_id->device, +page_address (page),PAGE_SIZE ,DMA_FROM_DEVICE );if (ib_dma_mapping_error (xprt->sc_cm_id->device, pa)) goto err_put_ctxt;@@ -1315,8 +1315,8 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, length =svc_rdma_xdr_encode_error (xprt, rmsgp, err, va);/* Prepare SGE for local address */ - sge.addr =ib_dma_map_page (xprt->sc_cm_id->device, - p,0 ,PAGE_SIZE ,DMA_FROM_DEVICE ); + sge.addr =ib_dma_map_single (xprt->sc_cm_id->device, +page_address (p),PAGE_SIZE ,DMA_FROM_DEVICE );if (ib_dma_mapping_error (xprt->sc_cm_id->device, sge.addr)) {put_page (p);return ;@@ -1343,7 +1343,7 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp,if (ret) {dprintk ("svcrdma: Error %d posting send for protocol error\n" , ret); -ib_dma_unmap_page (xprt->sc_cm_id->device, +ib_dma_unmap_single (xprt->sc_cm_id->device, sge.addr,PAGE_SIZE ,DMA_FROM_DEVICE );svc_rdma_put_context (ctxt,1 ); --To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Quoted 9 lines · J. Bruce Fields
Quoted 4 lines · Steve Wise
Hey Bruce,
Do you think this can make 2.6.30?
I was going to save it for 2.6.31; vague mental scorecard:
Quoted 9 lines
- 2.6.30 is close to release
- I think of rdma (correctly or not?) as a little young, so don't prioritize bug-fixes to it quite as highly
- A resource leak (even as large as this) isn't the worst category of bug.But I may be wrong.
Ok.
As a data point: this bug will exhaust the iommu address space on a IBM Power system within 10 cthon iterations...
Steve.
Quoted 16 lines · Steve Wise
Quoted 15 lines · J. Bruce Fields
Quoted 4 lines · Steve Wise
Hey Bruce,
Do you think this can make 2.6.30?
I was going to save it for 2.6.31; vague mental scorecard:
- 2.6.30 is close to release
- I think of rdma (correctly or not?) as a little young, so don't prioritize bug-fixes to it quite as highly
- A resource leak (even as large as this) isn't the worst category of bug.
Quoted 7 lines
Quoted 3 lines
But I may be wrong.
Ok.
As a data point: this bug will exhaust the iommu address space on a IBM Power system within 10 cthon iterations...
OK. I may get this in for 2.6.30.
--b.