From a298b5be71c788b006321a316b2f45a9a6937832 Mon Sep 17 00:00:00 2001 From: Yihang Li Date: Fri, 14 Apr 2023 16:20:42 +0800 Subject: [PATCH 098/108] scsi: hisi_sas: Ensure all enabled PHYs up during controller reset mainline inclusion from mainline-v6.4-rc1 commit 89954f024c3ae5e8674d9b5313a7cc08e79c6f6d category: feature bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8F82P Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=89954f024c3ae5e8674d9b5313a7cc08e79c6f6d ---------------------------------------------------------------------- For the controller reset operation, hisi_sas_phy_enable() is executed for each enabled local PHY, and refresh the port id of each device based on the latest hisi_sas_phy->port_id after 1 second sleep, hisi_sas_phy->port_id is configured in the interrupt processing function phy_up_v3_hw(). However, in directly attached scenario, for some SATA disks the amount of time for phyup more than 1s sometimes. In this case, incorrect port id may be configured in hisi_sas_refresh_port_id(). As a result, all the internal IOs fail and disk lost, such as follows: [10717.666565] hisi_sas_v3_hw 0000:74:02.0: phyup: phy1 link_rate=10(sata) [10718.826813] hisi_sas_v3_hw 0000:74:02.0: erroneous completion iptt=63 task=00000000c1ab1c2b dev id=200 addr=5000000000000501 CQ hdr: 0x8000007 0xc8003f 0x0 0x0 Error info: 0x0 0x0 0x0 0x0 [10718.843428] sas: TMF task open reject failed 5000000000000501 [10718.849242] hisi_sas_v3_hw 0000:74:02.0: erroneous completion iptt=64 task=00000000c1ab1c2b dev id=200 addr=5000000000000501 CQ hdr: 0x8000007 0xc80040 0x0 0x0 Error info: 0x0 0x0 0x0 0x0 [10718.865856] sas: TMF task open reject failed 5000000000000501 [10718.871670] hisi_sas_v3_hw 0000:74:02.0: erroneous completion iptt=65 task=00000000c1ab1c2b dev id=200 addr=5000000000000501 CQ hdr: 0x8000007 0xc80041 0x0 0x0 Error info: 0x0 0x0 0x0 0x0 [10718.888284] sas: TMF task open reject failed 5000000000000501 [10718.894093] sas: executing TMF for 5000000000000501 failed after 3 attempts! [10718.901114] hisi_sas_v3_hw 0000:74:02.0: ata disk 5000000000000501 reset failed [10718.908410] hisi_sas_v3_hw 0000:74:02.0: controller reset complete ..... [10773.298633] ata216.00: revalidation failed (errno=-19) [10773.303753] ata216.00: disable device So the time of waitting for PHYs up is 1s which may be not enough. To solve the issue, running hisi_sas_phy_enable() in parallel through async operations and use wait_for_completion_timeout() to wait for PHYs come up instead of directly sleep for 1 second. Signed-off-by: Yihang Li Signed-off-by: Xiang Chen Signed-off-by: xiabing Signed-off-by: YunYi Yang Conflicts: drivers/scsi/hisi_sas/hisi_sas_main.c --- drivers/scsi/hisi_sas/hisi_sas_main.c | 33 ++++++++++++++++++++++++--- 1 file changed, 30 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 91146ce048b8..9d2e0d2df0b6 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -1660,14 +1660,41 @@ void hisi_sas_controller_reset_prepare(struct hisi_hba *hisi_hba) } EXPORT_SYMBOL_GPL(hisi_sas_controller_reset_prepare); +static void hisi_sas_async_init_wait_phyup(void *data, async_cookie_t cookie) +{ + struct hisi_sas_phy *phy = data; + struct hisi_hba *hisi_hba = phy->hisi_hba; + struct device *dev = hisi_hba->dev; + DECLARE_COMPLETION_ONSTACK(completion); + int phy_no = phy->sas_phy.id; + + phy->reset_completion = &completion; + hisi_sas_phy_enable(hisi_hba, phy_no, 1); + if (!wait_for_completion_timeout(&completion, + HISI_SAS_WAIT_PHYUP_TIMEOUT)) + dev_warn(dev, "phy%d wait phyup timed out\n", phy_no); + + phy->reset_completion = NULL; +} + void hisi_sas_controller_reset_done(struct hisi_hba *hisi_hba) { struct Scsi_Host *shost = hisi_hba->shost; + ASYNC_DOMAIN_EXCLUSIVE(async); + int phy_no; /* Init and wait for PHYs to come up and all libsas event finished. */ - hisi_hba->hw->phys_init(hisi_hba); - /* Sleep 1s to wait for phy up */ - msleep(1000); + for (phy_no = 0; phy_no < hisi_hba->n_phy; phy_no++) { + struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no]; + + if (!(hisi_hba->phy_state & BIT(phy_no))) + continue; + + async_schedule_domain(hisi_sas_async_init_wait_phyup, + phy, &async); + } + + async_synchronize_full_domain(&async); hisi_sas_refresh_port_id(hisi_hba); clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags); -- 2.27.0