mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
d9b13c2030
Hanging has been observed while writing a file over NFSoRDMA. Dmesg on the server contains messages like these: [ 931.992501] svcrdma: Error -22 posting RDMA_READ [ 952.076879] svcrdma: Error -22 posting RDMA_READ [ 982.154127] svcrdma: Error -22 posting RDMA_READ [ 1012.235884] svcrdma: Error -22 posting RDMA_READ [ 1042.319194] svcrdma: Error -22 posting RDMA_READ Here is why: With the base memory management extension enabled, FRMR is used instead of FMR. The xprtrdma server issues each RDMA read request as the following bundle: (1)IB_WR_REG_MR, signaled; (2)IB_WR_RDMA_READ, signaled; (3)IB_WR_LOCAL_INV, signaled & fencing. These requests are signaled. In order to generate completion, the fast register work request is processed by the hfi1 send engine after being posted to the work queue, and the corresponding lkey is not valid until the request is processed. However, the rdmavt driver validates lkey when the RDMA read request is posted and thus it fails immediately with error -EINVAL (-22). This patch changes the work flow of local operations (fast register and local invalidate) so that fast register work requests are always processed immediately to ensure that the corresponding lkey is valid when subsequent work requests are posted. Local invalidate requests are processed immediately if fencing is not required and no previous local invalidate request is pending. To allow completion generation for signaled local operations that have been processed before posting to the work queue, an internal send flag RVT_SEND_COMPLETION_ONLY is added. The hfi1 send engine checks this flag and only generates completion for such requests. Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by: Jianxin Xiong <jianxin.xiong@intel.com> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by: Doug Ledford <dledford@redhat.com> |
||
|---|---|---|
| .. | ||
| affinity.c | ||
| affinity.h | ||
| aspm.h | ||
| chip_registers.h | ||
| chip.c | ||
| chip.h | ||
| common.h | ||
| debugfs.c | ||
| debugfs.h | ||
| device.c | ||
| device.h | ||
| dma.c | ||
| driver.c | ||
| efivar.c | ||
| efivar.h | ||
| eprom.c | ||
| eprom.h | ||
| file_ops.c | ||
| firmware.c | ||
| hfi.h | ||
| init.c | ||
| intr.c | ||
| iowait.h | ||
| Kconfig | ||
| mad.c | ||
| mad.h | ||
| Makefile | ||
| mmu_rb.c | ||
| mmu_rb.h | ||
| opa_compat.h | ||
| pcie.c | ||
| pio_copy.c | ||
| pio.c | ||
| pio.h | ||
| platform.c | ||
| platform.h | ||
| qp.c | ||
| qp.h | ||
| qsfp.c | ||
| qsfp.h | ||
| rc.c | ||
| ruc.c | ||
| sdma_txreq.h | ||
| sdma.c | ||
| sdma.h | ||
| sysfs.c | ||
| trace_ctxts.h | ||
| trace_dbg.h | ||
| trace_ibhdrs.h | ||
| trace_misc.h | ||
| trace_rc.h | ||
| trace_rx.h | ||
| trace_tx.h | ||
| trace.c | ||
| trace.h | ||
| uc.c | ||
| ud.c | ||
| user_exp_rcv.c | ||
| user_exp_rcv.h | ||
| user_pages.c | ||
| user_sdma.c | ||
| user_sdma.h | ||
| verbs_txreq.c | ||
| verbs_txreq.h | ||
| verbs.c | ||
| verbs.h | ||