October 2024 - Linux-stable-mirror

FAILED: patch "[PATCH] drm/amdgpu/smu13: always apply the powersave optimization" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 7a1613e47e65ba6967085ad99dee95420346a0ce # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024102019-mummy-veteran-1b27@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 7a1613e47e65ba6967085ad99dee95420346a0ce Mon Sep 17 00:00:00 2001 From: Alex Deucher <alexander.deucher(a)amd.com> Date: Thu, 3 Oct 2024 10:09:50 -0400 Subject: [PATCH] drm/amdgpu/smu13: always apply the powersave optimization It can avoid margin issues in some very demanding applications. Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3618 Link: https://gitlab.freedesktop.org/drm/amd/-/issues/3131 Fixes: c50fe289ed72 ("drm/amdgpu/swsmu: always force a state reprogram on init") Reviewed-by: Kenneth Feng <kenneth.feng(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> (cherry picked from commit 62f38b4ccaa6aa063ca781d80b10aacd39dc5c76) Cc: stable(a)vger.kernel.org diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 1d024b122b0c..cb923e33fd6f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2555,18 +2555,16 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu, workload_mask = 1 << workload_type; /* Add optimizations for SMU13.0.0/10. Reuse the power saving profile */ - if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE) { - if ((amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 0) && - ((smu->adev->pm.fw_version == 0x004e6601) || - (smu->adev->pm.fw_version >= 0x004e7300))) || - (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 10) && - smu->adev->pm.fw_version >= 0x00504500)) { - workload_type = smu_cmn_to_asic_specific_index(smu, - CMN2ASIC_MAPPING_WORKLOAD, - PP_SMC_POWER_PROFILE_POWERSAVING); - if (workload_type >= 0) - workload_mask |= 1 << workload_type; - } + if ((amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 0) && + ((smu->adev->pm.fw_version == 0x004e6601) || + (smu->adev->pm.fw_version >= 0x004e7300))) || + (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 10) && + smu->adev->pm.fw_version >= 0x00504500)) { + workload_type = smu_cmn_to_asic_specific_index(smu, + CMN2ASIC_MAPPING_WORKLOAD, + PP_SMC_POWER_PROFILE_POWERSAVING); + if (workload_type >= 0) + workload_mask |= 1 << workload_type; } ret = smu_cmn_send_smc_msg_with_param(smu,

2 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] drm/amdgpu/smu13: always apply the powersave optimization" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 7a1613e47e65ba6967085ad99dee95420346a0ce # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024102018-distrust-unworthy-142c@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 7a1613e47e65ba6967085ad99dee95420346a0ce Mon Sep 17 00:00:00 2001 From: Alex Deucher <alexander.deucher(a)amd.com> Date: Thu, 3 Oct 2024 10:09:50 -0400 Subject: [PATCH] drm/amdgpu/smu13: always apply the powersave optimization It can avoid margin issues in some very demanding applications. Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3618 Link: https://gitlab.freedesktop.org/drm/amd/-/issues/3131 Fixes: c50fe289ed72 ("drm/amdgpu/swsmu: always force a state reprogram on init") Reviewed-by: Kenneth Feng <kenneth.feng(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> (cherry picked from commit 62f38b4ccaa6aa063ca781d80b10aacd39dc5c76) Cc: stable(a)vger.kernel.org diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 1d024b122b0c..cb923e33fd6f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2555,18 +2555,16 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu, workload_mask = 1 << workload_type; /* Add optimizations for SMU13.0.0/10. Reuse the power saving profile */ - if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE) { - if ((amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 0) && - ((smu->adev->pm.fw_version == 0x004e6601) || - (smu->adev->pm.fw_version >= 0x004e7300))) || - (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 10) && - smu->adev->pm.fw_version >= 0x00504500)) { - workload_type = smu_cmn_to_asic_specific_index(smu, - CMN2ASIC_MAPPING_WORKLOAD, - PP_SMC_POWER_PROFILE_POWERSAVING); - if (workload_type >= 0) - workload_mask |= 1 << workload_type; - } + if ((amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 0) && + ((smu->adev->pm.fw_version == 0x004e6601) || + (smu->adev->pm.fw_version >= 0x004e7300))) || + (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 10) && + smu->adev->pm.fw_version >= 0x00504500)) { + workload_type = smu_cmn_to_asic_specific_index(smu, + CMN2ASIC_MAPPING_WORKLOAD, + PP_SMC_POWER_PROFILE_POWERSAVING); + if (workload_type >= 0) + workload_mask |= 1 << workload_type; } ret = smu_cmn_send_smc_msg_with_param(smu,

2 months, 3 weeks

1
0
0 0

[PATCH] usb: phy: Fix API devm_usb_put_phy() can not release the phy

by Zijun Hu

From: Zijun Hu <quic_zijuhu(a)quicinc.com> For devm_usb_put_phy(), its comment says it needs to invoke usb_put_phy() to release the phy, but it does not do that actually, so it can not fully undo what the API devm_usb_get_phy() does, that is wrong, fixed by using devres_release() instead of devres_destroy() within the API. Fixes: cedf8602373a ("usb: phy: move bulk of otg/otg.c to phy/phy.c") Cc: stable(a)vger.kernel.org Signed-off-by: Zijun Hu <quic_zijuhu(a)quicinc.com> --- The API is directly used by drivers/usb/musb/sunxi.c, sorry for that i can't evaluate relevant impact since i know nothing about sunxi. --- drivers/usb/phy/phy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c index 06e0fb23566c..06f789097989 100644 --- a/drivers/usb/phy/phy.c +++ b/drivers/usb/phy/phy.c @@ -628,7 +628,7 @@ void devm_usb_put_phy(struct device *dev, struct usb_phy *phy) { int r; - r = devres_destroy(dev, devm_usb_phy_release, devm_usb_phy_match, phy); + r = devres_release(dev, devm_usb_phy_release, devm_usb_phy_match, phy); dev_WARN_ONCE(dev, r, "couldn't find PHY resource\n"); } EXPORT_SYMBOL_GPL(devm_usb_put_phy); --- base-commit: 07b887f8236eb3ed52f1fe83e385e6436dc4b052 change-id: 20241020-usb_phy_fix-9d7c67ef4ab4 Best regards, -- Zijun Hu <quic_zijuhu(a)quicinc.com>

2 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] scsi: ufs: core: Requeue aborted request" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 8fa075804cb3b00960dd5c06554308175c834530 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024102014-dorsal-renounce-5242@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 8fa075804cb3b00960dd5c06554308175c834530 Mon Sep 17 00:00:00 2001 From: Peter Wang <peter.wang(a)mediatek.com> Date: Tue, 1 Oct 2024 17:19:17 +0800 Subject: [PATCH] scsi: ufs: core: Requeue aborted request After the SQ cleanup fix, the CQ will receive a response with the corresponding tag marked as OCS: ABORTED. To align with the behavior of Legacy SDB mode, the handling of OCS: ABORTED has been changed to match that of OCS_INVALID_COMMAND_STATUS (SDB), with both returning a SCSI result of DID_REQUEUE. Furthermore, the workaround implemented before the SQ cleanup fix can be removed. Fixes: ab248643d3d6 ("scsi: ufs: core: Add error handling for MCQ mode") Cc: stable(a)vger.kernel.org Signed-off-by: Peter Wang <peter.wang(a)mediatek.com> Link: https://lore.kernel.org/r/20241001091917.6917-3-peter.wang@mediatek.com Reviewed-by: Bart Van Assche <bvanassche(a)acm.org> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 6a71ebf953e2..f845166dc0d7 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -5416,10 +5416,12 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp, } break; case OCS_ABORTED: - result |= DID_ABORT << 16; - break; case OCS_INVALID_COMMAND_STATUS: result |= DID_REQUEUE << 16; + dev_warn(hba->dev, + "OCS %s from controller for tag %d\n", + (ocs == OCS_ABORTED ? "aborted" : "invalid"), + lrbp->task_tag); break; case OCS_INVALID_CMD_TABLE_ATTR: case OCS_INVALID_PRDT_ATTR: @@ -6465,26 +6467,12 @@ static bool ufshcd_abort_one(struct request *rq, void *priv) struct scsi_device *sdev = cmd->device; struct Scsi_Host *shost = sdev->host; struct ufs_hba *hba = shost_priv(shost); - struct ufshcd_lrb *lrbp = &hba->lrb[tag]; - struct ufs_hw_queue *hwq; - unsigned long flags; *ret = ufshcd_try_to_abort_task(hba, tag); dev_err(hba->dev, "Aborting tag %d / CDB %#02x %s\n", tag, hba->lrb[tag].cmd ? hba->lrb[tag].cmd->cmnd[0] : -1, *ret ? "failed" : "succeeded"); - /* Release cmd in MCQ mode if abort succeeds */ - if (hba->mcq_enabled && (*ret == 0)) { - hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(lrbp->cmd)); - if (!hwq) - return 0; - spin_lock_irqsave(&hwq->cq_lock, flags); - if (ufshcd_cmd_inflight(lrbp->cmd)) - ufshcd_release_scsi_cmd(hba, lrbp); - spin_unlock_irqrestore(&hwq->cq_lock, flags); - } - return *ret == 0; }

2 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] scsi: ufs: core: Set SDEV_OFFLINE when UFS is shut down" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 19a198b67767d952c8f3d0cf24eb3100522a8223 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024102050-unequal-radiator-f679@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 19a198b67767d952c8f3d0cf24eb3100522a8223 Mon Sep 17 00:00:00 2001 From: Seunghwan Baek <sh8267.baek(a)samsung.com> Date: Thu, 29 Aug 2024 18:39:13 +0900 Subject: [PATCH] scsi: ufs: core: Set SDEV_OFFLINE when UFS is shut down There is a history of deadlock if reboot is performed at the beginning of booting. SDEV_QUIESCE was set for all LU's scsi_devices by UFS shutdown, and at that time the audio driver was waiting on blk_mq_submit_bio() holding a mutex_lock while reading the fw binary. After that, a deadlock issue occurred while audio driver shutdown was waiting for mutex_unlock of blk_mq_submit_bio(). To solve this, set SDEV_OFFLINE for all LUs except WLUN, so that any I/O that comes down after a UFS shutdown will return an error. [ 31.907781]I[0: swapper/0: 0] 1 130705007 1651079834 11289729804 0 D( 2) 3 ffffff882e208000 * init [device_shutdown] [ 31.907793]I[0: swapper/0: 0] Mutex: 0xffffff8849a2b8b0: owner[0xffffff882e28cb00 kworker/6:0 :49] [ 31.907806]I[0: swapper/0: 0] Call trace: [ 31.907810]I[0: swapper/0: 0] __switch_to+0x174/0x338 [ 31.907819]I[0: swapper/0: 0] __schedule+0x5ec/0x9cc [ 31.907826]I[0: swapper/0: 0] schedule+0x7c/0xe8 [ 31.907834]I[0: swapper/0: 0] schedule_preempt_disabled+0x24/0x40 [ 31.907842]I[0: swapper/0: 0] __mutex_lock+0x408/0xdac [ 31.907849]I[0: swapper/0: 0] __mutex_lock_slowpath+0x14/0x24 [ 31.907858]I[0: swapper/0: 0] mutex_lock+0x40/0xec [ 31.907866]I[0: swapper/0: 0] device_shutdown+0x108/0x280 [ 31.907875]I[0: swapper/0: 0] kernel_restart+0x4c/0x11c [ 31.907883]I[0: swapper/0: 0] __arm64_sys_reboot+0x15c/0x280 [ 31.907890]I[0: swapper/0: 0] invoke_syscall+0x70/0x158 [ 31.907899]I[0: swapper/0: 0] el0_svc_common+0xb4/0xf4 [ 31.907909]I[0: swapper/0: 0] do_el0_svc+0x2c/0xb0 [ 31.907918]I[0: swapper/0: 0] el0_svc+0x34/0xe0 [ 31.907928]I[0: swapper/0: 0] el0t_64_sync_handler+0x68/0xb4 [ 31.907937]I[0: swapper/0: 0] el0t_64_sync+0x1a0/0x1a4 [ 31.908774]I[0: swapper/0: 0] 49 0 11960702 11236868007 0 D( 2) 6 ffffff882e28cb00 * kworker/6:0 [__bio_queue_enter] [ 31.908783]I[0: swapper/0: 0] Call trace: [ 31.908788]I[0: swapper/0: 0] __switch_to+0x174/0x338 [ 31.908796]I[0: swapper/0: 0] __schedule+0x5ec/0x9cc [ 31.908803]I[0: swapper/0: 0] schedule+0x7c/0xe8 [ 31.908811]I[0: swapper/0: 0] __bio_queue_enter+0xb8/0x178 [ 31.908818]I[0: swapper/0: 0] blk_mq_submit_bio+0x194/0x67c [ 31.908827]I[0: swapper/0: 0] __submit_bio+0xb8/0x19c Fixes: b294ff3e3449 ("scsi: ufs: core: Enable power management for wlun") Cc: stable(a)vger.kernel.org Signed-off-by: Seunghwan Baek <sh8267.baek(a)samsung.com> Link: https://lore.kernel.org/r/20240829093913.6282-2-sh8267.baek@samsung.com Reviewed-by: Bart Van Assche <bvanassche(a)acm.org> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index f845166dc0d7..706dc81eb924 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -10197,7 +10197,9 @@ static void ufshcd_wl_shutdown(struct device *dev) shost_for_each_device(sdev, hba->host) { if (sdev == hba->ufs_device_wlun) continue; - scsi_device_quiesce(sdev); + mutex_lock(&sdev->state_mutex); + scsi_device_set_state(sdev, SDEV_OFFLINE); + mutex_unlock(&sdev->state_mutex); } __ufshcd_wl_suspend(hba, UFS_SHUTDOWN_PM);

2 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] scsi: mpi3mr: Validate SAS port assignments" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x b9e63d6c7c0e94a99e1af7c9c0c7fad13a2f2453 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024102028-henchman-favorable-6119@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From b9e63d6c7c0e94a99e1af7c9c0c7fad13a2f2453 Mon Sep 17 00:00:00 2001 From: Ranjan Kumar <ranjan.kumar(a)broadcom.com> Date: Tue, 8 Oct 2024 13:13:53 +0530 Subject: [PATCH] scsi: mpi3mr: Validate SAS port assignments A sanity check on phy_mask was added in commit 3668651def2c ("scsi: mpi3mr: Sanitise num_phys"). This causes warning messages when more than 64 phys are detected and devices connected to phys greater than 64 are dropped. The phy_mask bitmap is only needed for controller phys and not required for expander phys. Controller phys can go up to a maximum of 64 and therefore u64 is good enough to contain phy_mask bitmap. To suppress those warnings and allow devices to be discovered as before the offending commit, restrict the phy_mask setting and lowest phy setting only to the controller phys. Fixes: 3668651def2c ("scsi: mpi3mr: Sanitise num_phys") Cc: stable(a)vger.kernel.org Reported-by: kernel test robot <lkp(a)intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202410051943.Mp9o5DlF-lkp@intel.com/ Reported-by: Alexander Motin <mav(a)ixsystems.com> Signed-off-by: Ranjan Kumar <ranjan.kumar(a)broadcom.com> Link: https://lore.kernel.org/r/20241008074353.200379-1-ranjan.kumar@broadcom.com Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> diff --git a/drivers/scsi/mpi3mr/mpi3mr.h b/drivers/scsi/mpi3mr/mpi3mr.h index fcb0fa31536b..16e0baeb8799 100644 --- a/drivers/scsi/mpi3mr/mpi3mr.h +++ b/drivers/scsi/mpi3mr/mpi3mr.h @@ -542,8 +542,8 @@ struct mpi3mr_hba_port { * @port_list: List of ports belonging to a SAS node * @num_phys: Number of phys associated with port * @marked_responding: used while refresing the sas ports - * @lowest_phy: lowest phy ID of current sas port - * @phy_mask: phy_mask of current sas port + * @lowest_phy: lowest phy ID of current sas port, valid for controller port + * @phy_mask: phy_mask of current sas port, valid for controller port * @hba_port: HBA port entry * @remote_identify: Attached device identification * @rphy: SAS transport layer rphy object diff --git a/drivers/scsi/mpi3mr/mpi3mr_transport.c b/drivers/scsi/mpi3mr/mpi3mr_transport.c index ccd23def2e0c..0ba9e6a6a13c 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_transport.c +++ b/drivers/scsi/mpi3mr/mpi3mr_transport.c @@ -590,12 +590,13 @@ static enum sas_linkrate mpi3mr_convert_phy_link_rate(u8 link_rate) * @mrioc: Adapter instance reference * @mr_sas_port: Internal Port object * @mr_sas_phy: Internal Phy object + * @host_node: Flag to indicate this is a host_node * * Return: None. */ static void mpi3mr_delete_sas_phy(struct mpi3mr_ioc *mrioc, struct mpi3mr_sas_port *mr_sas_port, - struct mpi3mr_sas_phy *mr_sas_phy) + struct mpi3mr_sas_phy *mr_sas_phy, u8 host_node) { u64 sas_address = mr_sas_port->remote_identify.sas_address; @@ -605,9 +606,13 @@ static void mpi3mr_delete_sas_phy(struct mpi3mr_ioc *mrioc, list_del(&mr_sas_phy->port_siblings); mr_sas_port->num_phys--; - mr_sas_port->phy_mask &= ~(1 << mr_sas_phy->phy_id); - if (mr_sas_port->lowest_phy == mr_sas_phy->phy_id) - mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; + + if (host_node) { + mr_sas_port->phy_mask &= ~(1 << mr_sas_phy->phy_id); + + if (mr_sas_port->lowest_phy == mr_sas_phy->phy_id) + mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; + } sas_port_delete_phy(mr_sas_port->port, mr_sas_phy->phy); mr_sas_phy->phy_belongs_to_port = 0; } @@ -617,12 +622,13 @@ static void mpi3mr_delete_sas_phy(struct mpi3mr_ioc *mrioc, * @mrioc: Adapter instance reference * @mr_sas_port: Internal Port object * @mr_sas_phy: Internal Phy object + * @host_node: Flag to indicate this is a host_node * * Return: None. */ static void mpi3mr_add_sas_phy(struct mpi3mr_ioc *mrioc, struct mpi3mr_sas_port *mr_sas_port, - struct mpi3mr_sas_phy *mr_sas_phy) + struct mpi3mr_sas_phy *mr_sas_phy, u8 host_node) { u64 sas_address = mr_sas_port->remote_identify.sas_address; @@ -632,9 +638,12 @@ static void mpi3mr_add_sas_phy(struct mpi3mr_ioc *mrioc, list_add_tail(&mr_sas_phy->port_siblings, &mr_sas_port->phy_list); mr_sas_port->num_phys++; - mr_sas_port->phy_mask |= (1 << mr_sas_phy->phy_id); - if (mr_sas_phy->phy_id < mr_sas_port->lowest_phy) - mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; + if (host_node) { + mr_sas_port->phy_mask |= (1 << mr_sas_phy->phy_id); + + if (mr_sas_phy->phy_id < mr_sas_port->lowest_phy) + mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; + } sas_port_add_phy(mr_sas_port->port, mr_sas_phy->phy); mr_sas_phy->phy_belongs_to_port = 1; } @@ -675,7 +684,7 @@ static void mpi3mr_add_phy_to_an_existing_port(struct mpi3mr_ioc *mrioc, if (srch_phy == mr_sas_phy) return; } - mpi3mr_add_sas_phy(mrioc, mr_sas_port, mr_sas_phy); + mpi3mr_add_sas_phy(mrioc, mr_sas_port, mr_sas_phy, mr_sas_node->host_node); return; } } @@ -736,7 +745,7 @@ static void mpi3mr_del_phy_from_an_existing_port(struct mpi3mr_ioc *mrioc, mpi3mr_delete_sas_port(mrioc, mr_sas_port); else mpi3mr_delete_sas_phy(mrioc, mr_sas_port, - mr_sas_phy); + mr_sas_phy, mr_sas_node->host_node); return; } } @@ -1028,7 +1037,7 @@ mpi3mr_alloc_hba_port(struct mpi3mr_ioc *mrioc, u16 port_id) /** * mpi3mr_get_hba_port_by_id - find hba port by id * @mrioc: Adapter instance reference - * @port_id - Port ID to search + * @port_id: Port ID to search * * Return: mpi3mr_hba_port reference for the matched port */ @@ -1367,7 +1376,8 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, mpi3mr_sas_port_sanity_check(mrioc, mr_sas_node, mr_sas_port->remote_identify.sas_address, hba_port); - if (mr_sas_node->num_phys >= sizeof(mr_sas_port->phy_mask) * 8) + if (mr_sas_node->host_node && mr_sas_node->num_phys >= + sizeof(mr_sas_port->phy_mask) * 8) ioc_info(mrioc, "max port count %u could be too high\n", mr_sas_node->num_phys); @@ -1377,7 +1387,7 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, (mr_sas_node->phy[i].hba_port != hba_port)) continue; - if (i >= sizeof(mr_sas_port->phy_mask) * 8) { + if (mr_sas_node->host_node && (i >= sizeof(mr_sas_port->phy_mask) * 8)) { ioc_warn(mrioc, "skipping port %u, max allowed value is %zu\n", i, sizeof(mr_sas_port->phy_mask) * 8); goto out_fail; @@ -1385,7 +1395,8 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, list_add_tail(&mr_sas_node->phy[i].port_siblings, &mr_sas_port->phy_list); mr_sas_port->num_phys++; - mr_sas_port->phy_mask |= (1 << i); + if (mr_sas_node->host_node) + mr_sas_port->phy_mask |= (1 << i); } if (!mr_sas_port->num_phys) { @@ -1394,7 +1405,8 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, goto out_fail; } - mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; + if (mr_sas_node->host_node) + mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; if (mr_sas_port->remote_identify.device_type == SAS_END_DEVICE) { tgtdev = mpi3mr_get_tgtdev_by_addr(mrioc,

2 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] scsi: mpi3mr: Validate SAS port assignments" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x b9e63d6c7c0e94a99e1af7c9c0c7fad13a2f2453 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024102027-late-goggles-8ae6@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From b9e63d6c7c0e94a99e1af7c9c0c7fad13a2f2453 Mon Sep 17 00:00:00 2001 From: Ranjan Kumar <ranjan.kumar(a)broadcom.com> Date: Tue, 8 Oct 2024 13:13:53 +0530 Subject: [PATCH] scsi: mpi3mr: Validate SAS port assignments A sanity check on phy_mask was added in commit 3668651def2c ("scsi: mpi3mr: Sanitise num_phys"). This causes warning messages when more than 64 phys are detected and devices connected to phys greater than 64 are dropped. The phy_mask bitmap is only needed for controller phys and not required for expander phys. Controller phys can go up to a maximum of 64 and therefore u64 is good enough to contain phy_mask bitmap. To suppress those warnings and allow devices to be discovered as before the offending commit, restrict the phy_mask setting and lowest phy setting only to the controller phys. Fixes: 3668651def2c ("scsi: mpi3mr: Sanitise num_phys") Cc: stable(a)vger.kernel.org Reported-by: kernel test robot <lkp(a)intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202410051943.Mp9o5DlF-lkp@intel.com/ Reported-by: Alexander Motin <mav(a)ixsystems.com> Signed-off-by: Ranjan Kumar <ranjan.kumar(a)broadcom.com> Link: https://lore.kernel.org/r/20241008074353.200379-1-ranjan.kumar@broadcom.com Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> diff --git a/drivers/scsi/mpi3mr/mpi3mr.h b/drivers/scsi/mpi3mr/mpi3mr.h index fcb0fa31536b..16e0baeb8799 100644 --- a/drivers/scsi/mpi3mr/mpi3mr.h +++ b/drivers/scsi/mpi3mr/mpi3mr.h @@ -542,8 +542,8 @@ struct mpi3mr_hba_port { * @port_list: List of ports belonging to a SAS node * @num_phys: Number of phys associated with port * @marked_responding: used while refresing the sas ports - * @lowest_phy: lowest phy ID of current sas port - * @phy_mask: phy_mask of current sas port + * @lowest_phy: lowest phy ID of current sas port, valid for controller port + * @phy_mask: phy_mask of current sas port, valid for controller port * @hba_port: HBA port entry * @remote_identify: Attached device identification * @rphy: SAS transport layer rphy object diff --git a/drivers/scsi/mpi3mr/mpi3mr_transport.c b/drivers/scsi/mpi3mr/mpi3mr_transport.c index ccd23def2e0c..0ba9e6a6a13c 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_transport.c +++ b/drivers/scsi/mpi3mr/mpi3mr_transport.c @@ -590,12 +590,13 @@ static enum sas_linkrate mpi3mr_convert_phy_link_rate(u8 link_rate) * @mrioc: Adapter instance reference * @mr_sas_port: Internal Port object * @mr_sas_phy: Internal Phy object + * @host_node: Flag to indicate this is a host_node * * Return: None. */ static void mpi3mr_delete_sas_phy(struct mpi3mr_ioc *mrioc, struct mpi3mr_sas_port *mr_sas_port, - struct mpi3mr_sas_phy *mr_sas_phy) + struct mpi3mr_sas_phy *mr_sas_phy, u8 host_node) { u64 sas_address = mr_sas_port->remote_identify.sas_address; @@ -605,9 +606,13 @@ static void mpi3mr_delete_sas_phy(struct mpi3mr_ioc *mrioc, list_del(&mr_sas_phy->port_siblings); mr_sas_port->num_phys--; - mr_sas_port->phy_mask &= ~(1 << mr_sas_phy->phy_id); - if (mr_sas_port->lowest_phy == mr_sas_phy->phy_id) - mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; + + if (host_node) { + mr_sas_port->phy_mask &= ~(1 << mr_sas_phy->phy_id); + + if (mr_sas_port->lowest_phy == mr_sas_phy->phy_id) + mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; + } sas_port_delete_phy(mr_sas_port->port, mr_sas_phy->phy); mr_sas_phy->phy_belongs_to_port = 0; } @@ -617,12 +622,13 @@ static void mpi3mr_delete_sas_phy(struct mpi3mr_ioc *mrioc, * @mrioc: Adapter instance reference * @mr_sas_port: Internal Port object * @mr_sas_phy: Internal Phy object + * @host_node: Flag to indicate this is a host_node * * Return: None. */ static void mpi3mr_add_sas_phy(struct mpi3mr_ioc *mrioc, struct mpi3mr_sas_port *mr_sas_port, - struct mpi3mr_sas_phy *mr_sas_phy) + struct mpi3mr_sas_phy *mr_sas_phy, u8 host_node) { u64 sas_address = mr_sas_port->remote_identify.sas_address; @@ -632,9 +638,12 @@ static void mpi3mr_add_sas_phy(struct mpi3mr_ioc *mrioc, list_add_tail(&mr_sas_phy->port_siblings, &mr_sas_port->phy_list); mr_sas_port->num_phys++; - mr_sas_port->phy_mask |= (1 << mr_sas_phy->phy_id); - if (mr_sas_phy->phy_id < mr_sas_port->lowest_phy) - mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; + if (host_node) { + mr_sas_port->phy_mask |= (1 << mr_sas_phy->phy_id); + + if (mr_sas_phy->phy_id < mr_sas_port->lowest_phy) + mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; + } sas_port_add_phy(mr_sas_port->port, mr_sas_phy->phy); mr_sas_phy->phy_belongs_to_port = 1; } @@ -675,7 +684,7 @@ static void mpi3mr_add_phy_to_an_existing_port(struct mpi3mr_ioc *mrioc, if (srch_phy == mr_sas_phy) return; } - mpi3mr_add_sas_phy(mrioc, mr_sas_port, mr_sas_phy); + mpi3mr_add_sas_phy(mrioc, mr_sas_port, mr_sas_phy, mr_sas_node->host_node); return; } } @@ -736,7 +745,7 @@ static void mpi3mr_del_phy_from_an_existing_port(struct mpi3mr_ioc *mrioc, mpi3mr_delete_sas_port(mrioc, mr_sas_port); else mpi3mr_delete_sas_phy(mrioc, mr_sas_port, - mr_sas_phy); + mr_sas_phy, mr_sas_node->host_node); return; } } @@ -1028,7 +1037,7 @@ mpi3mr_alloc_hba_port(struct mpi3mr_ioc *mrioc, u16 port_id) /** * mpi3mr_get_hba_port_by_id - find hba port by id * @mrioc: Adapter instance reference - * @port_id - Port ID to search + * @port_id: Port ID to search * * Return: mpi3mr_hba_port reference for the matched port */ @@ -1367,7 +1376,8 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, mpi3mr_sas_port_sanity_check(mrioc, mr_sas_node, mr_sas_port->remote_identify.sas_address, hba_port); - if (mr_sas_node->num_phys >= sizeof(mr_sas_port->phy_mask) * 8) + if (mr_sas_node->host_node && mr_sas_node->num_phys >= + sizeof(mr_sas_port->phy_mask) * 8) ioc_info(mrioc, "max port count %u could be too high\n", mr_sas_node->num_phys); @@ -1377,7 +1387,7 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, (mr_sas_node->phy[i].hba_port != hba_port)) continue; - if (i >= sizeof(mr_sas_port->phy_mask) * 8) { + if (mr_sas_node->host_node && (i >= sizeof(mr_sas_port->phy_mask) * 8)) { ioc_warn(mrioc, "skipping port %u, max allowed value is %zu\n", i, sizeof(mr_sas_port->phy_mask) * 8); goto out_fail; @@ -1385,7 +1395,8 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, list_add_tail(&mr_sas_node->phy[i].port_siblings, &mr_sas_port->phy_list); mr_sas_port->num_phys++; - mr_sas_port->phy_mask |= (1 << i); + if (mr_sas_node->host_node) + mr_sas_port->phy_mask |= (1 << i); } if (!mr_sas_port->num_phys) { @@ -1394,7 +1405,8 @@ static struct mpi3mr_sas_port *mpi3mr_sas_port_add(struct mpi3mr_ioc *mrioc, goto out_fail; } - mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; + if (mr_sas_node->host_node) + mr_sas_port->lowest_phy = ffs(mr_sas_port->phy_mask) - 1; if (mr_sas_port->remote_identify.device_type == SAS_END_DEVICE) { tgtdev = mpi3mr_get_tgtdev_by_addr(mrioc,

2 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] blk-rq-qos: fix crash on rq_qos_wait vs. rq_qos_wake_function" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x e972b08b91ef48488bae9789f03cfedb148667fb # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024102019-roundness-penholder-bb3f@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e972b08b91ef48488bae9789f03cfedb148667fb Mon Sep 17 00:00:00 2001 From: Omar Sandoval <osandov(a)fb.com> Date: Tue, 15 Oct 2024 10:59:46 -0700 Subject: [PATCH] blk-rq-qos: fix crash on rq_qos_wait vs. rq_qos_wake_function race We're seeing crashes from rq_qos_wake_function that look like this: BUG: unable to handle page fault for address: ffffafe180a40084 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 100000067 P4D 100000067 PUD 10027c067 PMD 10115d067 PTE 0 Oops: Oops: 0002 [#1] PREEMPT SMP PTI CPU: 17 UID: 0 PID: 0 Comm: swapper/17 Not tainted 6.12.0-rc3-00013-geca631b8fe80 #11 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:_raw_spin_lock_irqsave+0x1d/0x40 Code: 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 41 54 9c 41 5c fa 65 ff 05 62 97 30 4c 31 c0 ba 01 00 00 00 <f0> 0f b1 17 75 0a 4c 89 e0 41 5c c3 cc cc cc cc 89 c6 e8 2c 0b 00 RSP: 0018:ffffafe180580ca0 EFLAGS: 00010046 RAX: 0000000000000000 RBX: ffffafe180a3f7a8 RCX: 0000000000000011 RDX: 0000000000000001 RSI: 0000000000000003 RDI: ffffafe180a40084 RBP: 0000000000000000 R08: 00000000001e7240 R09: 0000000000000011 R10: 0000000000000028 R11: 0000000000000888 R12: 0000000000000002 R13: ffffafe180a40084 R14: 0000000000000000 R15: 0000000000000003 FS: 0000000000000000(0000) GS:ffff9aaf1f280000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffafe180a40084 CR3: 000000010e428002 CR4: 0000000000770ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <IRQ> try_to_wake_up+0x5a/0x6a0 rq_qos_wake_function+0x71/0x80 __wake_up_common+0x75/0xa0 __wake_up+0x36/0x60 scale_up.part.0+0x50/0x110 wb_timer_fn+0x227/0x450 ... So rq_qos_wake_function() calls wake_up_process(data->task), which calls try_to_wake_up(), which faults in raw_spin_lock_irqsave(&p->pi_lock). p comes from data->task, and data comes from the waitqueue entry, which is stored on the waiter's stack in rq_qos_wait(). Analyzing the core dump with drgn, I found that the waiter had already woken up and moved on to a completely unrelated code path, clobbering what was previously data->task. Meanwhile, the waker was passing the clobbered garbage in data->task to wake_up_process(), leading to the crash. What's happening is that in between rq_qos_wake_function() deleting the waitqueue entry and calling wake_up_process(), rq_qos_wait() is finding that it already got a token and returning. The race looks like this: rq_qos_wait() rq_qos_wake_function() ============================================================== prepare_to_wait_exclusive() data->got_token = true; list_del_init(&curr->entry); if (data.got_token) break; finish_wait(&rqw->wait, &data.wq); ^- returns immediately because list_empty_careful(&wq_entry->entry) is true ... return, go do something else ... wake_up_process(data->task) (NO LONGER VALID!)-^ Normally, finish_wait() is supposed to synchronize against the waker. But, as noted above, it is returning immediately because the waitqueue entry has already been removed from the waitqueue. The bug is that rq_qos_wake_function() is accessing the waitqueue entry AFTER deleting it. Note that autoremove_wake_function() wakes the waiter and THEN deletes the waitqueue entry, which is the proper order. Fix it by swapping the order. We also need to use list_del_init_careful() to match the list_empty_careful() in finish_wait(). Fixes: 38cfb5a45ee0 ("blk-wbt: improve waking of tasks") Cc: stable(a)vger.kernel.org Signed-off-by: Omar Sandoval <osandov(a)fb.com> Acked-by: Tejun Heo <tj(a)kernel.org> Reviewed-by: Johannes Thumshirn <johannes.thumshirn(a)wdc.com> Link: https://lore.kernel.org/r/d3bee2463a67b1ee597211823bf7ad3721c26e41.17290145… Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index 2cfb297d9a62..058f92c4f9d5 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -219,8 +219,8 @@ static int rq_qos_wake_function(struct wait_queue_entry *curr, data->got_token = true; smp_wmb(); - list_del_init(&curr->entry); wake_up_process(data->task); + list_del_init_careful(&curr->entry); return 1; }

2 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] fgraph: Use CPU hotplug mechanism to initialize idle shadow" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x 2c02f7375e658ae93d57a31a66f91b62754ef8f1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024102001-badly-overvalue-6662@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 2c02f7375e658ae93d57a31a66f91b62754ef8f1 Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt(a)goodmis.org> Date: Fri, 18 Oct 2024 21:43:00 -0400 Subject: [PATCH] fgraph: Use CPU hotplug mechanism to initialize idle shadow stacks The function graph infrastructure allocates a shadow stack for every task when enabled. This includes the idle tasks. The first time the function graph is invoked, the shadow stacks are created and never freed until the task exits. This includes the idle tasks. Only the idle tasks that were for online CPUs had their shadow stacks created when function graph tracing started. If function graph tracing is enabled and a CPU comes online, the idle task representing that CPU will not have its shadow stack created, and all function graph tracing for that idle task will be silently dropped. Instead, use the CPU hotplug mechanism to allocate the idle shadow stacks. This will include idle tasks for CPUs that come online during tracing. This issue can be reproduced by: # cd /sys/kernel/tracing # echo 0 > /sys/devices/system/cpu/cpu1/online # echo 0 > set_ftrace_pid # echo function_graph > current_tracer # echo 1 > options/funcgraph-proc # echo 1 > /sys/devices/system/cpu/cpu1 # grep '<idle>' per_cpu/cpu1/trace | head Before, nothing would show up. After: 1) <idle>-0 | 0.811 us | __enqueue_entity(); 1) <idle>-0 | 5.626 us | } /* enqueue_entity */ 1) <idle>-0 | | dl_server_update_idle_time() { 1) <idle>-0 | | dl_scaled_delta_exec() { 1) <idle>-0 | 0.450 us | arch_scale_cpu_capacity(); 1) <idle>-0 | 1.242 us | } 1) <idle>-0 | 1.908 us | } 1) <idle>-0 | | dl_server_start() { 1) <idle>-0 | | enqueue_dl_entity() { 1) <idle>-0 | | task_contending() { Note, if tracing stops and restarts, the old way would then initialize the onlined CPUs. Cc: stable(a)vger.kernel.org Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Thomas Gleixner <tglx(a)linutronix.de> Link: https://lore.kernel.org/20241018214300.6df82178@rorschach Fixes: 868baf07b1a25 ("ftrace: Fix memory leak with function graph and cpu hotplug") Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index d7d4fb403f6f..43f4e3f57438 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -1160,19 +1160,13 @@ void fgraph_update_pid_func(void) static int start_graph_tracing(void) { unsigned long **ret_stack_list; - int ret, cpu; + int ret; ret_stack_list = kmalloc(SHADOW_STACK_SIZE, GFP_KERNEL); if (!ret_stack_list) return -ENOMEM; - /* The cpu_boot init_task->ret_stack will never be freed */ - for_each_online_cpu(cpu) { - if (!idle_task(cpu)->ret_stack) - ftrace_graph_init_idle_task(idle_task(cpu), cpu); - } - do { ret = alloc_retstack_tasklist(ret_stack_list); } while (ret == -EAGAIN); @@ -1242,14 +1236,34 @@ static void ftrace_graph_disable_direct(bool disable_branch) fgraph_direct_gops = &fgraph_stub; } +/* The cpu_boot init_task->ret_stack will never be freed */ +static int fgraph_cpu_init(unsigned int cpu) +{ + if (!idle_task(cpu)->ret_stack) + ftrace_graph_init_idle_task(idle_task(cpu), cpu); + return 0; +} + int register_ftrace_graph(struct fgraph_ops *gops) { + static bool fgraph_initialized; int command = 0; int ret = 0; int i = -1; mutex_lock(&ftrace_lock); + if (!fgraph_initialized) { + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "fgraph_idle_init", + fgraph_cpu_init, NULL); + if (ret < 0) { + pr_warn("fgraph: Error to init cpu hotplug support\n"); + return ret; + } + fgraph_initialized = true; + ret = 0; + } + if (!fgraph_array[0]) { /* The array must always have real data on it */ for (i = 0; i < FGRAPH_ARRAY_SIZE; i++)

2 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] fgraph: Use CPU hotplug mechanism to initialize idle shadow" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 2c02f7375e658ae93d57a31a66f91b62754ef8f1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024102000-mortician-chant-190e@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 2c02f7375e658ae93d57a31a66f91b62754ef8f1 Mon Sep 17 00:00:00 2001 From: Steven Rostedt <rostedt(a)goodmis.org> Date: Fri, 18 Oct 2024 21:43:00 -0400 Subject: [PATCH] fgraph: Use CPU hotplug mechanism to initialize idle shadow stacks The function graph infrastructure allocates a shadow stack for every task when enabled. This includes the idle tasks. The first time the function graph is invoked, the shadow stacks are created and never freed until the task exits. This includes the idle tasks. Only the idle tasks that were for online CPUs had their shadow stacks created when function graph tracing started. If function graph tracing is enabled and a CPU comes online, the idle task representing that CPU will not have its shadow stack created, and all function graph tracing for that idle task will be silently dropped. Instead, use the CPU hotplug mechanism to allocate the idle shadow stacks. This will include idle tasks for CPUs that come online during tracing. This issue can be reproduced by: # cd /sys/kernel/tracing # echo 0 > /sys/devices/system/cpu/cpu1/online # echo 0 > set_ftrace_pid # echo function_graph > current_tracer # echo 1 > options/funcgraph-proc # echo 1 > /sys/devices/system/cpu/cpu1 # grep '<idle>' per_cpu/cpu1/trace | head Before, nothing would show up. After: 1) <idle>-0 | 0.811 us | __enqueue_entity(); 1) <idle>-0 | 5.626 us | } /* enqueue_entity */ 1) <idle>-0 | | dl_server_update_idle_time() { 1) <idle>-0 | | dl_scaled_delta_exec() { 1) <idle>-0 | 0.450 us | arch_scale_cpu_capacity(); 1) <idle>-0 | 1.242 us | } 1) <idle>-0 | 1.908 us | } 1) <idle>-0 | | dl_server_start() { 1) <idle>-0 | | enqueue_dl_entity() { 1) <idle>-0 | | task_contending() { Note, if tracing stops and restarts, the old way would then initialize the onlined CPUs. Cc: stable(a)vger.kernel.org Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Thomas Gleixner <tglx(a)linutronix.de> Link: https://lore.kernel.org/20241018214300.6df82178@rorschach Fixes: 868baf07b1a25 ("ftrace: Fix memory leak with function graph and cpu hotplug") Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index d7d4fb403f6f..43f4e3f57438 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -1160,19 +1160,13 @@ void fgraph_update_pid_func(void) static int start_graph_tracing(void) { unsigned long **ret_stack_list; - int ret, cpu; + int ret; ret_stack_list = kmalloc(SHADOW_STACK_SIZE, GFP_KERNEL); if (!ret_stack_list) return -ENOMEM; - /* The cpu_boot init_task->ret_stack will never be freed */ - for_each_online_cpu(cpu) { - if (!idle_task(cpu)->ret_stack) - ftrace_graph_init_idle_task(idle_task(cpu), cpu); - } - do { ret = alloc_retstack_tasklist(ret_stack_list); } while (ret == -EAGAIN); @@ -1242,14 +1236,34 @@ static void ftrace_graph_disable_direct(bool disable_branch) fgraph_direct_gops = &fgraph_stub; } +/* The cpu_boot init_task->ret_stack will never be freed */ +static int fgraph_cpu_init(unsigned int cpu) +{ + if (!idle_task(cpu)->ret_stack) + ftrace_graph_init_idle_task(idle_task(cpu), cpu); + return 0; +} + int register_ftrace_graph(struct fgraph_ops *gops) { + static bool fgraph_initialized; int command = 0; int ret = 0; int i = -1; mutex_lock(&ftrace_lock); + if (!fgraph_initialized) { + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "fgraph_idle_init", + fgraph_cpu_init, NULL); + if (ret < 0) { + pr_warn("fgraph: Error to init cpu hotplug support\n"); + return ret; + } + fgraph_initialized = true; + ret = 0; + } + if (!fgraph_array[0]) { /* The array must always have real data on it */ for (i = 0; i < FGRAPH_ARRAY_SIZE; i++)

2 months, 3 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror October 2024