[Bug 1853990] Re: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error
** Changed in: kunpeng920/ubuntu-18.04 Status: Fix Committed => Fix Released ** Changed in: kunpeng920 Status: Fix Committed => Fix Released ** Changed in: kunpeng920/ubuntu-18.04 Milestone: None => ubuntu-18.04.4-sru-1 -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1853990 Title: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error To manage notifications about this bug go to: https://bugs.launchpad.net/kunpeng920/+bug/1853990/+subscriptions -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
[Bug 1853990] Re: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error
This bug was fixed in the package linux - 4.15.0-88.88 --- linux (4.15.0-88.88) bionic; urgency=medium * bionic/linux: 4.15.0-88.88 -proposed tracker (LP: #1862824) * Segmentation fault (kernel oops) with memory-hotplug in ubuntu_kernel_selftests on Bionic kernel (LP: #1862312) - Revert "mm/memory_hotplug: fix online/offline_pages called w.o. mem_hotplug_lock" - mm/memory_hotplug: fix online/offline_pages called w.o. mem_hotplug_lock linux (4.15.0-87.87) bionic; urgency=medium * bionic/linux: 4.15.0-87.87 -proposed tracker (LP: #1861165) * Bionic update: upstream stable patchset 2020-01-22 (LP: #1860602) - scsi: lpfc: Fix discovery failures when target device connectivity bounces - scsi: mpt3sas: Fix clear pending bit in ioctl status - scsi: lpfc: Fix locking on mailbox command completion - Input: atmel_mxt_ts - disable IRQ across suspend - iommu/tegra-smmu: Fix page tables in > 4 GiB memory - scsi: target: compare full CHAP_A Algorithm strings - scsi: lpfc: Fix SLI3 hba in loop mode not discovering devices - scsi: csiostor: Don't enable IRQs too early - powerpc/pseries: Mark accumulate_stolen_time() as notrace - powerpc/pseries: Don't fail hash page table insert for bolted mapping - powerpc/tools: Don't quote $objdump in scripts - dma-debug: add a schedule point in debug_dma_dump_mappings() - clocksource/drivers/asm9260: Add a check for of_clk_get - powerpc/security/book3s64: Report L1TF status in sysfs - powerpc/book3s64/hash: Add cond_resched to avoid soft lockup warning - ext4: update direct I/O read lock pattern for IOCB_NOWAIT - jbd2: Fix statistics for the number of logged blocks - scsi: tracing: Fix handling of TRANSFER LENGTH == 0 for READ(6) and WRITE(6) - scsi: lpfc: Fix duplicate unreg_rpi error in port offline flow - f2fs: fix to update dir's i_pino during cross_rename - clk: qcom: Allow constant ratio freq tables for rcg - irqchip/irq-bcm7038-l1: Enable parent IRQ if necessary - irqchip: ingenic: Error out if IRQ domain creation failed - fs/quota: handle overflows of sysctl fs.quota.* and report as unsigned long - scsi: lpfc: fix: Coverity: lpfc_cmpl_els_rsp(): Null pointer dereferences - scsi: ufs: fix potential bug which ends in system hang - powerpc/pseries/cmm: Implement release() function for sysfs device - powerpc/security: Fix wrong message when RFI Flush is disable - scsi: atari_scsi: sun3_scsi: Set sg_tablesize to 1 instead of SG_NONE - clk: pxa: fix one of the pxa RTC clocks - bcache: at least try to shrink 1 node in bch_mca_scan() - HID: logitech-hidpp: Silence intermittent get_battery_capacity errors - libnvdimm/btt: fix variable 'rc' set but not used - HID: Improve Windows Precision Touchpad detection. - scsi: pm80xx: Fix for SATA device discovery - scsi: ufs: Fix error handing during hibern8 enter - scsi: scsi_debug: num_tgts must be >= 0 - scsi: NCR5380: Add disconnect_mask module parameter - scsi: iscsi: Don't send data to unbound connection - scsi: target: iscsi: Wait for all commands to finish before freeing a session - gpio: mpc8xxx: Don't overwrite default irq_set_type callback - apparmor: fix unsigned len comparison with less than zero - scripts/kallsyms: fix definitely-lost memory leak - cdrom: respect device capabilities during opening action - perf script: Fix brstackinsn for AUXTRACE - perf regs: Make perf_reg_name() return "unknown" instead of NULL - s390/zcrypt: handle new reply code FILTERED_BY_HYPERVISOR - libfdt: define INT32_MAX and UINT32_MAX in libfdt_env.h - s390/cpum_sf: Check for SDBT and SDB consistency - ocfs2: fix passing zero to 'PTR_ERR' warning - kernel: sysctl: make drop_caches write-only - userfaultfd: require CAP_SYS_PTRACE for UFFD_FEATURE_EVENT_FORK - x86/mce: Fix possibly incorrect severity calculation on AMD - net, sysctl: Fix compiler warning when only cBPF is present - netfilter: nf_queue: enqueue skbs with NULL dst - ALSA: hda - Downgrade error message for single-cmd fallback - bonding: fix active-backup transition after link failure - perf strbuf: Remove redundant va_end() in strbuf_addv() - Make filldir[64]() verify the directory entry filename is valid - filldir[64]: remove WARN_ON_ONCE() for bad directory entries - netfilter: ebtables: compat: reject all padding in matches/watchers - 6pack,mkiss: fix possible deadlock - netfilter: bridge: make sure to pull arp header in br_nf_forward_arp() - inetpeer: fix data-race in inet_putpeer / inet_putpeer - net: add a READ_ONCE() in skb_peek_tail() - net: icmp: fix data-race in cmp_global_allow() - hrtimer: Annotate lockless access to timer->state - spi: fsl: don't map irq during probe - tty/serial: atmel: fix out of range clock divider handling - pinctrl: baytrail:
[Bug 1853990] Re: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error
** Changed in: kunpeng920/ubuntu-18.04 Status: In Progress => Fix Committed ** Changed in: kunpeng920 Status: In Progress => Fix Committed -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1853990 Title: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error To manage notifications about this bug go to: https://bugs.launchpad.net/kunpeng920/+bug/1853990/+subscriptions -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
[Bug 1853990] Re: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error
linux 4.15.0-87.87 works fine for me. Thanks. ** Tags removed: verification-needed-bionic ** Tags added: verification-done-bionic -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1853990 Title: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error To manage notifications about this bug go to: https://bugs.launchpad.net/kunpeng920/+bug/1853990/+subscriptions -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
[Bug 1853990] Re: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error
This bug is awaiting verification that the kernel in -proposed solves the problem. Please test the kernel and update this bug with the results. If the problem is solved, change the tag 'verification-needed- bionic' to 'verification-done-bionic'. If the problem still exists, change the tag 'verification-needed-bionic' to 'verification-failed- bionic'. If verification is not done by 5 working days from today, this fix will be dropped from the source code, and this bug will be closed. See https://wiki.ubuntu.com/Testing/EnableProposed for documentation how to enable and use -proposed. Thank you! ** Tags added: verification-needed-bionic -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1853990 Title: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error To manage notifications about this bug go to: https://bugs.launchpad.net/kunpeng920/+bug/1853990/+subscriptions -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
[Bug 1853990] Re: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error
** Changed in: kunpeng920/ubuntu-19.04 Status: In Progress => Fix Released ** Changed in: kunpeng920/ubuntu-19.04 Milestone: None => ubuntu-19.04-sru-12 ** Changed in: kunpeng920/ubuntu-18.04-hwe Status: Fix Committed => Fix Released ** Changed in: kunpeng920/ubuntu-18.04-hwe Milestone: ubuntu-18.04.4 => ubuntu-18.04.3-sru-7 -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1853990 Title: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error To manage notifications about this bug go to: https://bugs.launchpad.net/kunpeng920/+bug/1853990/+subscriptions -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
[Bug 1853990] Re: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error
This bug was fixed in the package linux - 5.0.0-40.44 --- linux (5.0.0-40.44) disco; urgency=medium * disco/linux: 5.0.0-40.44 -proposed tracker (LP: #1859724) * use-after-free in i915_ppgtt_close (LP: #1859522) // CVE-2020-7053 - SAUCE: drm/i915: Fix use-after-free when destroying GEM context * CVE-2019-14615 - drm/i915/gen9: Clear residual context state on context switch * System hang with kernel traces while entering reboot process on a Disco ARM64 moonshot node (LP: #1859582) - Revert "RDMA/cm: Fix memory leak in cm_add/remove_one" linux (5.0.0-39.43) disco; urgency=medium * disco/linux: 5.0.0-39.43 -proposed tracker (LP: #1858547) * [Regression] usb usb2-port2: Cannot enable. Maybe the USB cable is bad? (LP: #1856608) - SAUCE: Revert "usb: handle warm-reset port requests on hub resume" * PAN is broken for execute-only user mappings on ARMv8 (LP: #1858815) - arm64: Revert support for execute-only user mappings * Fix unusable USB hub on Dell TB16 after S3 (LP: #1855312) - SAUCE: USB: core: Make port power cycle a seperate helper function - SAUCE: USB: core: Attempt power cycle port when it's in eSS.Disabled state * [sas-1126]scsi: hisi_sas: Fix out of bound at debug_I_T_nexus_reset() (LP: #1853992) - scsi: hisi_sas: Fix out of bound at debug_I_T_nexus_reset() * [sas-1126]scsi: hisi_sas: Assign NCQ tag for all NCQ commands (LP: #1853995) - scsi: hisi_sas: Assign NCQ tag for all NCQ commands * [sas-1126]scsi: hisi_sas: Fix the conflict between device gone and host reset (LP: #1853997) - scsi: hisi_sas: Fix the conflict between device gone and host reset * scsi: hisi_sas: Check sas_port before using it (LP: #1855952) - scsi: hisi_sas: Check sas_port before using it * CVE-2019-18885 - btrfs: refactor btrfs_find_device() take fs_devices as argument - btrfs: merge btrfs_find_device and find_device * Integrate Intel SGX driver into linux-azure (LP: #1844245) - [Packaging] Add systemd service to load intel_sgx * [SRU][B/OEM-B/OEM-OSP1/D/E/F] Add LG I2C touchscreen multitouch support (LP: #1857541) - SAUCE: HID: multitouch: Add LG MELF0410 I2C touchscreen support * cifs: DFS Caching feature causing problems traversing multi-tier DFS setups (LP: #1854887) - cifs: Fix retrieval of DFS referrals in cifs_mount() * qede driver causes 100% CPU load (LP: #1855409) - qede: Handle infinite driver spinning for Tx timestamp. * [roce-1126]RDMA/hns: bugfix for slab-out-of-bounds when loading hip08 driver (LP: #1853989) - RDMA/hns: Bugfix for slab-out-of-bounds when unloading hip08 driver - RDMA/hns: bugfix for slab-out-of-bounds when loading hip08 driver * [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error (LP: #1853990) - RDMA/hns: Fixs hw access invalid dma memory error * [hns-1126]net: hns3: revert to old channel when setting new channel num fail (LP: #1853983) - net: hns3: revert to old channel when setting new channel num fail * [hns-1126]net: hns3: fix port setting handle for fibre port (LP: #1853984) - net: hns3: fix port setting handle for fibre port * [hns-1126] net: hns: add support for vlan TSO (LP: #1853937) - net: hns: add support for vlan TSO * [hns-1126]net: hns3: fix flow control configure issue for fibre port (LP: #1853948) - net: hns3: fix flow control configure issue for fibre port * mce: ras: When inject 1bit ecc error, there is no mce log recorded in the dmesg (LP: #1857413) - RAS/CEC: Increment cec_entered under the mutex lock - RAS/CEC: Check count_threshold unconditionally * efivarfs test in ubuntu_kernel_selftest failed on the second run (LP: #1809704) - selftests/efivarfs: clean up test files from test_create*() * CVE-2019-19082 - drm/amd/display: prevent memory leak * CVE-2019-19078 - ath10k: fix memory leak * CVE-2019-19077 - RDMA: Fix goto target to release the allocated memory * Disco update: upstream stable patchset 2019-12-17 (LP: #1856754) - rsi: release skb if rsi_prepare_beacon fails - arm64: tegra: Fix 'active-low' warning for Jetson TX1 regulator - sparc64: implement ioremap_uc - lp: fix sparc64 LPSETTIMEOUT ioctl - usb: gadget: u_serial: add missing port entry locking - tty: serial: fsl_lpuart: use the sg count from dma_map_sg - tty: serial: msm_serial: Fix flow control - serial: pl011: Fix DMA ->flush_buffer() - serial: serial_core: Perform NULL checks for break_ctl ops - serial: ifx6x60: add missed pm_runtime_disable - autofs: fix a leak in autofs_expire_indirect() - RDMA/hns: Correct the value of HNS_ROCE_HEM_CHUNK_LEN - iwlwifi: pcie: don't consider IV len in A-MSDU - exportfs_decode_fh(): negative pinned may become positive without the parent locked - audit_get_nd(): don't unlock parent too early - NFC: nxp-nci: Fix NULL pointer
[Bug 1853990] Re: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error
Thanks. Ubuntu-5.0.0-40.44 works for me. ** Tags removed: verification-needed-disco ** Tags added: verification-done-disco -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1853990 Title: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error To manage notifications about this bug go to: https://bugs.launchpad.net/kunpeng920/+bug/1853990/+subscriptions -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
[Bug 1853990] Re: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error
This bug is awaiting verification that the kernel in -proposed solves the problem. Please test the kernel and update this bug with the results. If the problem is solved, change the tag 'verification-needed- disco' to 'verification-done-disco'. If the problem still exists, change the tag 'verification-needed-disco' to 'verification-failed-disco'. If verification is not done by 5 working days from today, this fix will be dropped from the source code, and this bug will be closed. See https://wiki.ubuntu.com/Testing/EnableProposed for documentation how to enable and use -proposed. Thank you! ** Tags added: verification-needed-disco -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1853990 Title: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error To manage notifications about this bug go to: https://bugs.launchpad.net/kunpeng920/+bug/1853990/+subscriptions -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
[Bug 1853990] Re: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error
** Changed in: linux (Ubuntu Bionic) Status: In Progress => Fix Committed ** Changed in: linux (Ubuntu Disco) Status: In Progress => Fix Committed -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1853990 Title: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error To manage notifications about this bug go to: https://bugs.launchpad.net/kunpeng920/+bug/1853990/+subscriptions -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
[Bug 1853990] Re: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error
Patch has been sent out https://lists.ubuntu.com/archives/kernel-team/2019-December/106510.html ** Description changed: - "[Bug Description] + [SRU Justification] + + Impact: With SMMU enabled, kill RDMA process will cause unexpected SMMU event + Fix: Cherry-pick patches ec5bc2cc6 from upstream + Testcase: Kill RMDA process several times and check console output + + + [Bug Description] When smmu is enable, if execute the perftest command and then use 'kill -9' to exit, follow this operation repeatedly, the kernel will have a high probability to print the following smmu event: - arm-smmu-v3 arm-smmu-v3.1.auto: event 0x10 received: - arm-smmu-v3 arm-smmu-v3.1.auto: 0x7d10 - arm-smmu-v3 arm-smmu-v3.1.auto: 0x02090080 - arm-smmu-v3 arm-smmu-v3.1.auto: 0xf47cf000 - arm-smmu-v3 arm-smmu-v3.1.auto: 0xf47cf000 + arm-smmu-v3 arm-smmu-v3.1.auto: event 0x10 received: + arm-smmu-v3 arm-smmu-v3.1.auto: 0x7d10 + arm-smmu-v3 arm-smmu-v3.1.auto: 0x02090080 + arm-smmu-v3 arm-smmu-v3.1.auto: 0xf47cf000 + arm-smmu-v3 arm-smmu-v3.1.auto: 0xf47cf000 This is because the hw will periodically refresh the qpc cache until the next reset. This patch fixed it by removing the action that release qpc memory in the 'hns_roce_qp_free' function. - [Steps to Reproduce] 1. load hns-roce-hw-v2.ko and open smmu 2. run rdma app 3. kill RoCE process [Actual Results] fail [Expected Results] success [Reproducibility] Inevitably [Additional information] Hardware: D06 Firmware: NA Kernel: NA [Resolution] - "RDMA/hns: Fixs hw access invalid dma memory error + RDMA/hns: Fixs hw access invalid dma memory error ** Changed in: linux (Ubuntu Disco) Status: Incomplete => In Progress ** Changed in: linux (Ubuntu Disco) Assignee: (unassigned) => Ike Panhc (ikepanhc) ** Changed in: linux (Ubuntu Bionic) Status: Invalid => In Progress ** Changed in: linux (Ubuntu Bionic) Assignee: (unassigned) => Ike Panhc (ikepanhc) ** Changed in: kunpeng920 Status: New => In Progress ** Description changed: - [SRU Justification] + [Impact] + With SMMU enabled, kill RDMA process will cause unexpected SMMU event - Impact: With SMMU enabled, kill RDMA process will cause unexpected SMMU event - Fix: Cherry-pick patches ec5bc2cc6 from upstream - Testcase: Kill RMDA process several times and check console output + [Testcase] + Kill RMDA process several times and check console output + + [Regression Risk] + Only RDMA/hns driver modified. lowest risk to other drivers/platforms [Bug Description] When smmu is enable, if execute the perftest command and then use 'kill -9' to exit, follow this operation repeatedly, the kernel will have a high probability to print the following smmu event: arm-smmu-v3 arm-smmu-v3.1.auto: event 0x10 received: arm-smmu-v3 arm-smmu-v3.1.auto: 0x7d10 arm-smmu-v3 arm-smmu-v3.1.auto: 0x02090080 arm-smmu-v3 arm-smmu-v3.1.auto: 0xf47cf000 arm-smmu-v3 arm-smmu-v3.1.auto: 0xf47cf000 This is because the hw will periodically refresh the qpc cache until the next reset. This patch fixed it by removing the action that release qpc memory in the 'hns_roce_qp_free' function. [Steps to Reproduce] 1. load hns-roce-hw-v2.ko and open smmu 2. run rdma app 3. kill RoCE process [Actual Results] fail [Expected Results] success [Reproducibility] Inevitably [Additional information] Hardware: D06 Firmware: NA Kernel: NA [Resolution] RDMA/hns: Fixs hw access invalid dma memory error -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1853990 Title: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error To manage notifications about this bug go to: https://bugs.launchpad.net/kunpeng920/+bug/1853990/+subscriptions -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
[Bug 1853990] Re: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error
** Changed in: linux (Ubuntu) Status: Incomplete => Invalid ** Changed in: linux (Ubuntu Bionic) Status: Incomplete => Invalid -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1853990 Title: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error To manage notifications about this bug go to: https://bugs.launchpad.net/kunpeng920/+bug/1853990/+subscriptions -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
[Bug 1853990] Re: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error
** Also affects: linux (Ubuntu) Importance: Undecided Status: New ** Also affects: linux (Ubuntu Bionic) Importance: Undecided Status: New ** Also affects: linux (Ubuntu Disco) Importance: Undecided Status: New -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/1853990 Title: [roce-1126]RDMA/hns: Fixs hw access invalid dma memory error To manage notifications about this bug go to: https://bugs.launchpad.net/kunpeng920/+bug/1853990/+subscriptions -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
