From: Xinghai Cen cenxinghai@h-partners.com
Some patches of RDMA from Linux to openEuler-6.6
Chengchang Tang (2): RDMA/hns: Fix spin_unlock_irqrestore() called with IRQs enabled RDMA/hns: Fix 1bit-ECC recovery address in non-4K OS
Junxian Huang (3): RDMA/hns: Fix VF triggering PF reset in abnormal interrupt handler RDMA/hns: Optimize hem allocation performance RDMA/hns: Fix restricted __le16 degrades to integer issue
drivers/infiniband/hw/hns/hns_roce_hem.c | 10 ++++++---- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 13 ++++++++----- drivers/infiniband/hw/hns/hns_roce_qp.c | 16 ++++++++-------- 3 files changed, 22 insertions(+), 17 deletions(-)
mainline inclusion from mainline-v6.11-rc5 commit 74d315b5af180220d561684d15897730135733a6 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAR316 CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git/commit/?id=74d...
----------------------------------------------------------------------
Fix missuse of spin_lock_irq()/spin_unlock_irq() when spin_lock_irqsave()/spin_lock_irqrestore() was hold.
This was discovered through the lock debugging, and the corresponding log is as follows:
raw_local_irq_restore() called with IRQs enabled WARNING: CPU: 96 PID: 2074 at kernel/locking/irqflag-debug.c:10 warn_bogus_irq_restore+0x30/0x40 ... Call trace: warn_bogus_irq_restore+0x30/0x40 _raw_spin_unlock_irqrestore+0x84/0xc8 add_qp_to_list+0x11c/0x148 [hns_roce_hw_v2] hns_roce_create_qp_common.constprop.0+0x240/0x780 [hns_roce_hw_v2] hns_roce_create_qp+0x98/0x160 [hns_roce_hw_v2] create_qp+0x138/0x258 ib_create_qp_kernel+0x50/0xe8 create_mad_qp+0xa8/0x128 ib_mad_port_open+0x218/0x448 ib_mad_init_device+0x70/0x1f8 add_client_context+0xfc/0x220 enable_device_and_get+0xd0/0x140 ib_register_device.part.0+0xf4/0x1c8 ib_register_device+0x34/0x50 hns_roce_register_device+0x174/0x3d0 [hns_roce_hw_v2] hns_roce_init+0xfc/0x2c0 [hns_roce_hw_v2] __hns_roce_hw_v2_init_instance+0x7c/0x1d0 [hns_roce_hw_v2] hns_roce_hw_v2_init_instance+0x9c/0x180 [hns_roce_hw_v2]
Fixes: 9a4435375cd1 ("IB/hns: Add driver files for hns RoCE driver") Signed-off-by: Chengchang Tang tangchengchang@huawei.com Signed-off-by: Junxian Huang huangjunxian6@hisilicon.com Link: https://patch.msgid.link/20240906093444.3571619-6-huangjunxian6@hisilicon.co... Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Xinghai Cen cenxinghai@h-partners.com --- drivers/infiniband/hw/hns/hns_roce_qp.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index d490a45d9222..2eb2694acf21 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -1579,19 +1579,19 @@ void hns_roce_lock_cqs(struct hns_roce_cq *send_cq, struct hns_roce_cq *recv_cq) __acquire(&send_cq->lock); __acquire(&recv_cq->lock); } else if (unlikely(send_cq != NULL && recv_cq == NULL)) { - spin_lock_irq(&send_cq->lock); + spin_lock(&send_cq->lock); __acquire(&recv_cq->lock); } else if (unlikely(send_cq == NULL && recv_cq != NULL)) { - spin_lock_irq(&recv_cq->lock); + spin_lock(&recv_cq->lock); __acquire(&send_cq->lock); } else if (send_cq == recv_cq) { - spin_lock_irq(&send_cq->lock); + spin_lock(&send_cq->lock); __acquire(&recv_cq->lock); } else if (send_cq->cqn < recv_cq->cqn) { - spin_lock_irq(&send_cq->lock); + spin_lock(&send_cq->lock); spin_lock_nested(&recv_cq->lock, SINGLE_DEPTH_NESTING); } else { - spin_lock_irq(&recv_cq->lock); + spin_lock(&recv_cq->lock); spin_lock_nested(&send_cq->lock, SINGLE_DEPTH_NESTING); } } @@ -1611,13 +1611,13 @@ void hns_roce_unlock_cqs(struct hns_roce_cq *send_cq, spin_unlock(&recv_cq->lock); } else if (send_cq == recv_cq) { __release(&recv_cq->lock); - spin_unlock_irq(&send_cq->lock); + spin_unlock(&send_cq->lock); } else if (send_cq->cqn < recv_cq->cqn) { spin_unlock(&recv_cq->lock); - spin_unlock_irq(&send_cq->lock); + spin_unlock(&send_cq->lock); } else { spin_unlock(&send_cq->lock); - spin_unlock_irq(&recv_cq->lock); + spin_unlock(&recv_cq->lock); } }
From: Junxian Huang huangjunxian6@hisilicon.com
mainline inclusion from mainline-v6.11-rc5 commit 4321feefa5501a746ebf6a7d8b59e6b955ae1860 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAR316 CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
----------------------------------------------------------------------
In abnormal interrupt handler, a PF reset will be triggered even if the device is a VF. It should be a VF reset.
Fixes: 2b9acb9a97fe ("RDMA/hns: Add the process of AEQ overflow for hip08") Signed-off-by: Junxian Huang huangjunxian6@hisilicon.com Link: https://patch.msgid.link/20240906093444.3571619-7-huangjunxian6@hisilicon.co... Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Xinghai Cen cenxinghai@h-partners.com --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 8a2472b978c5..619de7259cd4 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -6623,6 +6623,7 @@ static irqreturn_t abnormal_interrupt_basic(struct hns_roce_dev *hr_dev, struct pci_dev *pdev = hr_dev->pci_dev; struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev); const struct hnae3_ae_ops *ops = ae_dev->ops; + enum hnae3_reset_type reset_type; irqreturn_t int_work = IRQ_NONE; u32 int_en;
@@ -6634,10 +6635,12 @@ static irqreturn_t abnormal_interrupt_basic(struct hns_roce_dev *hr_dev, roce_write(hr_dev, ROCEE_VF_ABN_INT_ST_REG, 1 << HNS_ROCE_V2_VF_INT_ST_AEQ_OVERFLOW_S);
+ reset_type = hr_dev->is_vf ? + HNAE3_VF_FUNC_RESET : HNAE3_FUNC_RESET; + /* Set reset level for reset_event() */ if (ops->set_default_reset_request) - ops->set_default_reset_request(ae_dev, - HNAE3_FUNC_RESET); + ops->set_default_reset_request(ae_dev, reset_type); if (ops->reset_event) ops->reset_event(pdev, NULL);
mainline inclusion from mainline-v6.11-rc5 commit ce196f6297c7f3ab7780795e40efd6c521f60c8b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAR316 CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
----------------------------------------------------------------------
The 1bit-ECC recovery address read from HW only contain bits 64:12, so it should be fixed left-shifted 12 bits when used.
Currently, the driver will shift the address left by PAGE_SHIFT when used, which is wrong in non-4K OS.
Fixes: 2de949abd6a5 ("RDMA/hns: Recover 1bit-ECC error of RAM on chip") Signed-off-by: Chengchang Tang tangchengchang@huawei.com Signed-off-by: Junxian Huang huangjunxian6@hisilicon.com Link: https://patch.msgid.link/20240906093444.3571619-8-huangjunxian6@hisilicon.co... Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Xinghai Cen cenxinghai@h-partners.com --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 619de7259cd4..d133c418d6a5 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -6710,7 +6710,7 @@ static u64 fmea_get_ram_res_addr(u32 res_type, __le64 *data) res_type == ECC_RESOURCE_SCCC) return le64_to_cpu(*data);
- return le64_to_cpu(*data) << PAGE_SHIFT; + return le64_to_cpu(*data) << HNS_HW_PAGE_SHIFT; }
static int fmea_recover_others(struct hns_roce_dev *hr_dev, u32 res_type,
From: Junxian Huang huangjunxian6@hisilicon.com
mainline inclusion from mainline-v6.11-rc5 commit fe51f6254d81f5a69c31df16353d6539b2b51630 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAR316 CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
----------------------------------------------------------------------
When allocating MTT hem, for each hop level of each hem that is being allocated, the driver iterates the hem list to find out whether the bt page has been allocated in this hop level. If not, allocate a new one and splice it to the list. The time complexity is O(n^2) in worst cases.
Currently the allocation for-loop uses 'unit' as the step size. This actually has taken into account the reuse of last-hop-level MTT bt pages by multiple buffer pages. Thus pages of last hop level will never have been allocated, so there is no need to iterate the hem list in last hop level.
Removing this unnecessary iteration can reduce the time complexity to O(n).
Fixes: 38389eaa4db1 ("RDMA/hns: Add mtr support for mixed multihop addressing") Signed-off-by: Junxian Huang huangjunxian6@hisilicon.com Link: https://patch.msgid.link/20240906093444.3571619-9-huangjunxian6@hisilicon.co... Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Xinghai Cen cenxinghai@h-partners.com --- drivers/infiniband/hw/hns/hns_roce_hem.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c index bfe36eb0658d..cdb231e16fe2 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.c +++ b/drivers/infiniband/hw/hns/hns_roce_hem.c @@ -1135,10 +1135,12 @@ static int hem_list_alloc_mid_bt(struct hns_roce_dev *hr_dev,
/* config L1 bt to last bt and link them to corresponding parent */ for (level = 1; level < hopnum; level++) { - cur = hem_list_search_item(&mid_bt[level], offset); - if (cur) { - hem_ptrs[level] = cur; - continue; + if (!hem_list_is_bottom_bt(hopnum, level)) { + cur = hem_list_search_item(&mid_bt[level], offset); + if (cur) { + hem_ptrs[level] = cur; + continue; + } }
step = hem_list_calc_ba_range(hopnum, level, unit);
From: Junxian Huang huangjunxian6@hisilicon.com
mainline inclusion from mainline-v6.11-rc5 commit f4ccc0a2a0c5977540f519588636b5bc81aae2db category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAR316 CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
----------------------------------------------------------------------
Fix sparse warnings: restricted __le16 degrades to integer.
Fixes: 5a87279591a1 ("RDMA/hns: Support hns HW stats") Reported-by: kernel test robot lkp@intel.com Closes: https://lore.kernel.org/oe-kbuild-all/202409080508.g4mNSLwy-lkp@intel.com/ Signed-off-by: Junxian Huang huangjunxian6@hisilicon.com Link: https://patch.msgid.link/20240909065331.3950268-1-huangjunxian6@hisilicon.co... Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Xinghai Cen cenxinghai@h-partners.com --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index d133c418d6a5..bc0b944ecfac 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -1845,8 +1845,8 @@ static int hns_roce_hw_v2_query_counter(struct hns_roce_dev *hr_dev,
for (i = 0; i < HNS_ROCE_HW_CNT_TOTAL && i < *num_counters; i++) { bd_idx = i / CNT_PER_DESC; - if (!(desc[bd_idx].flag & HNS_ROCE_CMD_FLAG_NEXT) && - bd_idx != HNS_ROCE_HW_CNT_TOTAL / CNT_PER_DESC) + if (bd_idx != HNS_ROCE_HW_CNT_TOTAL / CNT_PER_DESC && + !(desc[bd_idx].flag & cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT))) break;
cnt_data = (__le64 *)&desc[bd_idx].data[0];
反馈： 您发送到kernel@openeuler.org的补丁/补丁集，已成功转换为PR！ PR链接地址： https://gitee.com/openeuler/kernel/pulls/11545 邮件列表地址：https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/S...
FeedBack: The patch(es) which you have sent to kernel@openeuler.org mailing list has been converted to a pull request successfully! Pull request link: https://gitee.com/openeuler/kernel/pulls/11545 Mailing list address: https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/S...
-
Chengchang Tang -
patchwork bot