September 2024 - Linux-stable-mirror

[PATCH v2] x86/hyperv: fix kexec crash due to VP assist page corruption

by Anirudh Rayabharam

From: Anirudh Rayabharam (Microsoft) <anirudh(a)anirudhrb.com> commit 9636be85cc5b ("x86/hyperv: Fix hyperv_pcpu_input_arg handling when CPUs go online/offline") introduces a new cpuhp state for hyperv initialization. cpuhp_setup_state() returns the state number if state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN and 0 for all other states. For the hyperv case, since a new cpuhp state was introduced it would return 0. However, in hv_machine_shutdown(), the cpuhp_remove_state() call is conditioned upon "hyperv_init_cpuhp > 0". This will never be true and so hv_cpu_die() won't be called on all CPUs. This means the VP assist page won't be reset. When the kexec kernel tries to setup the VP assist page again, the hypervisor corrupts the memory region of the old VP assist page causing a panic in case the kexec kernel is using that memory elsewhere. This was originally fixed in commit dfe94d4086e4 ("x86/hyperv: Fix kexec panic/hang issues"). Get rid of hyperv_init_cpuhp entirely since we are no longer using a dynamic cpuhp state and use CPUHP_AP_HYPERV_ONLINE directly with cpuhp_remove_state(). Cc: stable(a)vger.kernel.org Fixes: 9636be85cc5b ("x86/hyperv: Fix hyperv_pcpu_input_arg handling when CPUs go online/offline") Signed-off-by: Anirudh Rayabharam (Microsoft) <anirudh(a)anirudhrb.com> --- v1->v2: - Remove hyperv_init_cpuhp entirely and use CPUHP_AP_HYPERV_ONLINE directly with cpuhp_remove_state(). v1: https://lore.kernel.org/linux-hyperv/87wmk2xt5i.fsf@redhat.com/T/#m54b8ae17… --- arch/x86/hyperv/hv_init.c | 5 +---- arch/x86/include/asm/mshyperv.h | 1 - arch/x86/kernel/cpu/mshyperv.c | 4 ++-- 3 files changed, 3 insertions(+), 7 deletions(-) diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 17a71e92a343..95eada2994e1 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -35,7 +35,6 @@ #include <clocksource/hyperv_timer.h> #include <linux/highmem.h> -int hyperv_init_cpuhp; u64 hv_current_partition_id = ~0ull; EXPORT_SYMBOL_GPL(hv_current_partition_id); @@ -607,8 +606,6 @@ void __init hyperv_init(void) register_syscore_ops(&hv_syscore_ops); - hyperv_init_cpuhp = cpuhp; - if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_ACCESS_PARTITION_ID) hv_get_partition_id(); @@ -637,7 +634,7 @@ void __init hyperv_init(void) clean_guest_os_id: wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, 0); - cpuhp_remove_state(cpuhp); + cpuhp_remove_state(CPUHP_AP_HYPERV_ONLINE); free_ghcb_page: free_percpu(hv_ghcb_pg); free_vp_assist_page: diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 390c4d13956d..5f0bc6a6d025 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -40,7 +40,6 @@ static inline unsigned char hv_get_nmi_reason(void) } #if IS_ENABLED(CONFIG_HYPERV) -extern int hyperv_init_cpuhp; extern bool hyperv_paravisor_present; extern void *hv_hypercall_pg; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index e0fd57a8ba84..e98db51f25ba 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -199,8 +199,8 @@ static void hv_machine_shutdown(void) * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor * corrupts the old VP Assist Pages and can crash the kexec kernel. */ - if (kexec_in_progress && hyperv_init_cpuhp > 0) - cpuhp_remove_state(hyperv_init_cpuhp); + if (kexec_in_progress) + cpuhp_remove_state(CPUHP_AP_HYPERV_ONLINE); /* The function calls stop_other_cpus(). */ native_machine_shutdown(); -- 2.45.2

1 month, 2 weeks

4
3
0 0

Re: Patch "drm/drm-bridge: Drop conditionals around of_node pointers" has been added to the 6.6-stable t

by Pascal Ernster

[2024-09-04 19:50] Sasha Levin: > This is a note to let you know that I've just added the patch titled > > drm/drm-bridge: Drop conditionals around of_node pointers > > to the 6.6-stable tree which can be found at: > http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… > > The filename of the patch is: > drm-drm-bridge-drop-conditionals-around-of_node-poin.patch > and it can be found in the queue-6.6 subdirectory. > > If you, or anyone else, feels it should not be added to the stable tree, > please let <stable(a)vger.kernel.org> know about it. > > > > commit 74f5f42c35daf9aedbc96283321c30fc591c634f > Author: Sui Jingfeng <sui.jingfeng(a)linux.dev> > Date: Wed May 8 02:00:00 2024 +0800 > > drm/drm-bridge: Drop conditionals around of_node pointers > > [ Upstream commit ad3323a6ccb7d43bbeeaa46d5311c43d5d361fc7 ] > > Having conditional around the of_node pointer of the drm_bridge structure > is not necessary, since drm_bridge structure always has the of_node as its > member. > > Let's drop the conditional to get a better looks, please also note that > this is following the already accepted commitments. see commit d8dfccde2709 > ("drm/bridge: Drop conditionals around of_node pointers") for reference. > > Signed-off-by: Sui Jingfeng <sui.jingfeng(a)linux.dev> > Reviewed-by: Laurent Pinchart <laurent.pinchart+renesas(a)ideasonboard.com> > Signed-off-by: Robert Foss <rfoss(a)kernel.org> > Link: https://patchwork.freedesktop.org/patch/msgid/20240507180001.1358816-1-sui.… > Signed-off-by: Sasha Levin <sashal(a)kernel.org> > > diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c > index 62d8a291c49c..70b05582e616 100644 > --- a/drivers/gpu/drm/drm_bridge.c > +++ b/drivers/gpu/drm/drm_bridge.c > @@ -353,13 +353,8 @@ int drm_bridge_attach(struct drm_encoder *encoder, struct drm_bridge *bridge, > bridge->encoder = NULL; > list_del(&bridge->chain_node); > > -#ifdef CONFIG_OF > DRM_ERROR("failed to attach bridge %pOF to encoder %s: %d\n", > bridge->of_node, encoder->name, ret); > -#else > - DRM_ERROR("failed to attach bridge to encoder %s: %d\n", > - encoder->name, ret); > -#endif > > return ret; > } Hi Sasha, this breaks the x86_64 build for me. AFAICT this patch cannot work without commit d8dfccde2709de4327c3d62b50e5dc012f08836f "drm/bridge: Drop conditionals around of_node pointers", but that commit is only present in Linux >= 6.7. This issue affects the 6.6, 6.1 and 5.15 branches. Regards Pascal

1 month, 2 weeks

2
1
0 0

[PATCH 1/1] can: esd_usb: Remove CAN_CTRLMODE_3_SAMPLES for CAN-USB/3-FD

by Stefan Mätje

Remove the CAN_CTRLMODE_3_SAMPLES announcement for CAN-USB/3-FD devices because these devices don't support it. The hardware has a Microchip SAM E70 microcontroller that uses a Bosch MCAN IP core as CAN FD controller. But this MCAN core doesn't support triple sampling. Fixes: 80662d943075 ("can: esd_usb: Add support for esd CAN-USB/3") Cc: stable(a)vger.kernel.org Signed-off-by: Stefan Mätje <stefan.maetje(a)esd.eu> --- drivers/net/can/usb/esd_usb.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c index 41a0e4261d15..03ad10b01867 100644 --- a/drivers/net/can/usb/esd_usb.c +++ b/drivers/net/can/usb/esd_usb.c @@ -3,7 +3,7 @@ * CAN driver for esd electronics gmbh CAN-USB/2, CAN-USB/3 and CAN-USB/Micro * * Copyright (C) 2010-2012 esd electronic system design gmbh, Matthias Fuchs <socketcan(a)esd.eu> - * Copyright (C) 2022-2023 esd electronics gmbh, Frank Jungclaus <frank.jungclaus(a)esd.eu> + * Copyright (C) 2022-2024 esd electronics gmbh, Frank Jungclaus <frank.jungclaus(a)esd.eu> */ #include <linux/can.h> @@ -1116,9 +1116,6 @@ static int esd_usb_3_set_bittiming(struct net_device *netdev) if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) flags |= ESD_USB_3_BAUDRATE_FLAG_LOM; - if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES) - flags |= ESD_USB_3_BAUDRATE_FLAG_TRS; - baud_x->nom.brp = cpu_to_le16(nom_bt->brp & (nom_btc->brp_max - 1)); baud_x->nom.sjw = cpu_to_le16(nom_bt->sjw & (nom_btc->sjw_max - 1)); baud_x->nom.tseg1 = cpu_to_le16((nom_bt->prop_seg + nom_bt->phase_seg1) @@ -1219,7 +1216,6 @@ static int esd_usb_probe_one_net(struct usb_interface *intf, int index) switch (le16_to_cpu(dev->udev->descriptor.idProduct)) { case ESD_USB_CANUSB3_PRODUCT_ID: priv->can.clock.freq = ESD_USB_3_CAN_CLOCK; - priv->can.ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES; priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD; priv->can.bittiming_const = &esd_usb_3_nom_bittiming_const; priv->can.data_bittiming_const = &esd_usb_3_data_bittiming_const; -- 2.34.1

1 month, 2 weeks

3
2
0 0

[PATCH V2] mm/gup: Clear the LRU flag of a page before adding to LRU batch

by yangge1116＠126.com

From: yangge <yangge1116(a)126.com> If a large number of CMA memory are configured in system (for example, the CMA memory accounts for 50% of the system memory), starting a virtual virtual machine, it will call pin_user_pages_remote(..., FOLL_LONGTERM, ...) to pin memory. Normally if a page is present and in CMA area, pin_user_pages_remote() will migrate the page from CMA area to non-CMA area because of FOLL_LONGTERM flag. But the current code will cause the migration failure due to unexpected page refcounts, and eventually cause the virtual machine fail to start. If a page is added in LRU batch, its refcount increases one, remove the page from LRU batch decreases one. Page migration requires the page is not referenced by others except page mapping. Before migrating a page, we should try to drain the page from LRU batch in case the page is in it, however, folio_test_lru() is not sufficient to tell whether the page is in LRU batch or not, if the page is in LRU batch, the migration will fail. To solve the problem above, we modify the logic of adding to LRU batch. Before adding a page to LRU batch, we clear the LRU flag of the page so that we can check whether the page is in LRU batch by folio_test_lru(page). Seems making the LRU flag of the page invisible a long time is no problem, because a new page is allocated from buddy and added to the lru batch, its LRU flag is also not visible for a long time. Cc: <stable(a)vger.kernel.org> Signed-off-by: yangge <yangge1116(a)126.com> --- mm/swap.c | 43 +++++++++++++++++++++++++++++++------------ 1 file changed, 31 insertions(+), 12 deletions(-) diff --git a/mm/swap.c b/mm/swap.c index dc205bd..9caf6b0 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -211,10 +211,6 @@ static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; - /* block memcg migration while the folio moves between lru */ - if (move_fn != lru_add_fn && !folio_test_clear_lru(folio)) - continue; - folio_lruvec_relock_irqsave(folio, &lruvec, &flags); move_fn(lruvec, folio); @@ -255,11 +251,16 @@ static void lru_move_tail_fn(struct lruvec *lruvec, struct folio *folio) void folio_rotate_reclaimable(struct folio *folio) { if (!folio_test_locked(folio) && !folio_test_dirty(folio) && - !folio_test_unevictable(folio) && folio_test_lru(folio)) { + !folio_test_unevictable(folio)) { struct folio_batch *fbatch; unsigned long flags; folio_get(folio); + if (!folio_test_clear_lru(folio)) { + folio_put(folio); + return; + } + local_lock_irqsave(&lru_rotate.lock, flags); fbatch = this_cpu_ptr(&lru_rotate.fbatch); folio_batch_add_and_move(fbatch, folio, lru_move_tail_fn); @@ -352,11 +353,15 @@ static void folio_activate_drain(int cpu) void folio_activate(struct folio *folio) { - if (folio_test_lru(folio) && !folio_test_active(folio) && - !folio_test_unevictable(folio)) { + if (!folio_test_active(folio) && !folio_test_unevictable(folio)) { struct folio_batch *fbatch; folio_get(folio); + if (!folio_test_clear_lru(folio)) { + folio_put(folio); + return; + } + local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.activate); folio_batch_add_and_move(fbatch, folio, folio_activate_fn); @@ -700,6 +705,11 @@ void deactivate_file_folio(struct folio *folio) return; folio_get(folio); + if (!folio_test_clear_lru(folio)) { + folio_put(folio); + return; + } + local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_deactivate_file); folio_batch_add_and_move(fbatch, folio, lru_deactivate_file_fn); @@ -716,11 +726,16 @@ void deactivate_file_folio(struct folio *folio) */ void folio_deactivate(struct folio *folio) { - if (folio_test_lru(folio) && !folio_test_unevictable(folio) && - (folio_test_active(folio) || lru_gen_enabled())) { + if (!folio_test_unevictable(folio) && (folio_test_active(folio) || + lru_gen_enabled())) { struct folio_batch *fbatch; folio_get(folio); + if (!folio_test_clear_lru(folio)) { + folio_put(folio); + return; + } + local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_deactivate); folio_batch_add_and_move(fbatch, folio, lru_deactivate_fn); @@ -737,12 +752,16 @@ void folio_deactivate(struct folio *folio) */ void folio_mark_lazyfree(struct folio *folio) { - if (folio_test_lru(folio) && folio_test_anon(folio) && - folio_test_swapbacked(folio) && !folio_test_swapcache(folio) && - !folio_test_unevictable(folio)) { + if (folio_test_anon(folio) && folio_test_swapbacked(folio) && + !folio_test_swapcache(folio) && !folio_test_unevictable(folio)) { struct folio_batch *fbatch; folio_get(folio); + if (!folio_test_clear_lru(folio)) { + folio_put(folio); + return; + } + local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_lazyfree); folio_batch_add_and_move(fbatch, folio, lru_lazyfree_fn); -- 2.7.4

1 month, 2 weeks

8
26
0 0

[PATCH 1/1] iommu/vt-d: Prevent boot failure with devices requiring ATS

by Lu Baolu

SOC-integrated devices on some platforms require their PCI ATS enabled for operation when the IOMMU is in scalable mode. Those devices are reported via ACPI/SATC table with the ATC_REQUIRED bit set in the Flags field. The PCI subsystem offers the 'pci=noats' kernel command to disable PCI ATS on all devices. Using 'pci=noat' with devices that require PCI ATS can cause a conflict, leading to boot failure, especially if the device is a graphics device. To prevent this issue, check PCI ATS support before enumerating the IOMMU devices. If any device requires PCI ATS, but PCI ATS is disabled by 'pci=noats', switch the IOMMU to operate in legacy mode to ensure successful booting. Fixes: 97f2f2c5317f ("iommu/vt-d: Enable ATS for the devices in SATC table") Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/12036 Cc: stable(a)vger.kernel.org Signed-off-by: Lu Baolu <baolu.lu(a)linux.intel.com> --- drivers/iommu/intel/iommu.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 4aa070cf56e7..8f275e046e91 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -3127,10 +3127,26 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) (void *)satc + satc->header.length, satc->segment, satcu->devices, satcu->devices_cnt); - if (ret > 0) - break; - else if (ret < 0) + if (ret < 0) return ret; + + if (ret > 0) { + /* + * The device requires PCI/ATS when the IOMMU + * works in the scalable mode. If PCI/ATS is + * disabled using the pci=noats kernel parameter, + * the IOMMU will default to legacy mode. Users + * are informed of this change. + */ + if (intel_iommu_sm && satcu->atc_required && + !pci_ats_supported(info->dev)) { + pci_warn(info->dev, + "PCI/ATS not supported, system working in IOMMU legacy mode\n"); + intel_iommu_sm = 0; + } + + break; + } } else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) { if (dmar_remove_dev_scope(info, satc->segment, satcu->devices, satcu->devices_cnt)) -- 2.34.1

1 month, 2 weeks

5
7
0 0

[PATCH 00/11] arm64: qcom: set of fixes for SM8350 platform

by Dmitry Baryshkov

A set of fixes that target stability of the SM8350 platform. Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov(a)linaro.org> --- Dmitry Baryshkov (11): clk: qcom: dispcc-sm8250: use CLK_SET_RATE_PARENT for branch clocks clk: qcom: dispcc-sm8250: use special function for Lucid 5LPE PLL drm/msm/dsi: correct programming sequence for SM8350 / SM8450 interconnect: qcom: sm8350: drop DISP nodes interconnect: qcom: sm8450: drop DISP nodes dt-bindings: interconnect: qcom,sm8350: drop DISP nodes dt-bindings: interconnect: qcom,sm8450: drop DISP nodes interconnect: qcom: sm8250: Enable sync_state arm64: dts: qcom: sm8350: add MDSS registers interconnect arm64: dts: qcom: sm8350: add refgen regulator arm64: defconfig: build CONFIG_REGULATOR_QCOM_REFGEN as module arch/arm64/boot/dts/qcom/sm8350.dtsi | 16 ++- arch/arm64/configs/defconfig | 1 + drivers/clk/qcom/clk-alpha-pll.c | 52 +++++++++ drivers/clk/qcom/clk-alpha-pll.h | 2 + drivers/clk/qcom/dispcc-sm8250.c | 12 +- drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c | 12 +- drivers/interconnect/qcom/sm8350.c | 155 +------------------------ drivers/interconnect/qcom/sm8350.h | 10 -- drivers/interconnect/qcom/sm8450.c | 145 ----------------------- drivers/interconnect/qcom/sm8450.h | 12 -- include/dt-bindings/interconnect/qcom,sm8350.h | 10 -- include/dt-bindings/interconnect/qcom,sm8450.h | 10 -- 12 files changed, 91 insertions(+), 346 deletions(-) --- base-commit: 668d33c9ff922c4590c58754ab064aaf53c387dd change-id: 20240804-sm8350-fixes-9e731f79c56f Best regards, -- Dmitry Baryshkov <dmitry.baryshkov(a)linaro.org>

1 month, 2 weeks

2
4
0 0

[PATCH] cxl/region: Fix logic for finding a free cxl decoder

by Zijun Hu

From: Zijun Hu <quic_zijuhu(a)quicinc.com> match_free_decoder()'s logic for finding a free cxl decoder depends on a prerequisite that all child decoders are sorted by ID in ascending order but the prerequisite may not be guaranteed, fix by finding a free cxl decoder with minimal ID. Fixes: 384e624bb211 ("cxl/region: Attach endpoint decoders") Closes: https://lore.kernel.org/all/cdfc6f98-1aa0-4cb5-bd7d-93256552c39b@icloud.com/ Cc: stable(a)vger.kernel.org Signed-off-by: Zijun Hu <quic_zijuhu(a)quicinc.com> --- drivers/cxl/core/region.c | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 21ad5f242875..b9607b4fc40b 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -797,21 +797,26 @@ static size_t show_targetN(struct cxl_region *cxlr, char *buf, int pos) static int match_free_decoder(struct device *dev, void *data) { struct cxl_decoder *cxld; - int *id = data; + struct cxl_decoder *target_cxld; + struct device **target_device = data; if (!is_switch_decoder(dev)) return 0; cxld = to_cxl_decoder(dev); - - /* enforce ordered allocation */ - if (cxld->id != *id) + if (cxld->region) return 0; - if (!cxld->region) - return 1; - - (*id)++; + if (!*target_device) { + *target_device = get_device(dev); + return 0; + } + /* enforce ordered allocation */ + target_cxld = to_cxl_decoder(*target_device); + if (cxld->id < target_cxld->id) { + put_device(*target_device); + *target_device = get_device(dev); + } return 0; } @@ -839,8 +844,7 @@ cxl_region_find_decoder(struct cxl_port *port, struct cxl_endpoint_decoder *cxled, struct cxl_region *cxlr) { - struct device *dev; - int id = 0; + struct device *dev = NULL; if (port == cxled_to_port(cxled)) return &cxled->cxld; @@ -849,7 +853,8 @@ cxl_region_find_decoder(struct cxl_port *port, dev = device_find_child(&port->dev, &cxlr->params, match_auto_decoder); else - dev = device_find_child(&port->dev, &id, match_free_decoder); + /* Need to put_device(@dev) after use */ + device_for_each_child(&port->dev, &dev, match_free_decoder); if (!dev) return NULL; /* --- base-commit: 67784a74e258a467225f0e68335df77acd67b7ab change-id: 20240903-fix_cxld-4f6575a90619 Best regards, -- Zijun Hu <quic_zijuhu(a)quicinc.com>

1 month, 2 weeks

2
2
0 0

[for-linus][PATCH 6/6] eventfs: Use list_del_rcu() for SRCU protected list variable

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> Chi Zhiling reported: We found a null pointer accessing in tracefs[1], the reason is that the variable 'ei_child' is set to LIST_POISON1, that means the list was removed in eventfs_remove_rec. so when access the ei_child->is_freed, the panic triggered. by the way, the following script can reproduce this panic loop1 (){ while true do echo "p:kp submit_bio" > /sys/kernel/debug/tracing/kprobe_events echo "" > /sys/kernel/debug/tracing/kprobe_events done } loop2 (){ while true do tree /sys/kernel/debug/tracing/events/kprobes/ done } loop1 & loop2 [1]: [ 1147.959632][T17331] Unable to handle kernel paging request at virtual address dead000000000150 [ 1147.968239][T17331] Mem abort info: [ 1147.971739][T17331] ESR = 0x0000000096000004 [ 1147.976172][T17331] EC = 0x25: DABT (current EL), IL = 32 bits [ 1147.982171][T17331] SET = 0, FnV = 0 [ 1147.985906][T17331] EA = 0, S1PTW = 0 [ 1147.989734][T17331] FSC = 0x04: level 0 translation fault [ 1147.995292][T17331] Data abort info: [ 1147.998858][T17331] ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 [ 1148.005023][T17331] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [ 1148.010759][T17331] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 1148.016752][T17331] [dead000000000150] address between user and kernel address ranges [ 1148.024571][T17331] Internal error: Oops: 0000000096000004 [#1] SMP [ 1148.030825][T17331] Modules linked in: team_mode_loadbalance team nlmon act_gact cls_flower sch_ingress bonding tls macvlan dummy ib_core bridge stp llc veth amdgpu amdxcp mfd_core gpu_sched drm_exec drm_buddy radeon crct10dif_ce video drm_suballoc_helper ghash_ce drm_ttm_helper sha2_ce ttm sha256_arm64 i2c_algo_bit sha1_ce sbsa_gwdt cp210x drm_display_helper cec sr_mod cdrom drm_kms_helper binfmt_misc sg loop fuse drm dm_mod nfnetlink ip_tables autofs4 [last unloaded: tls] [ 1148.072808][T17331] CPU: 3 PID: 17331 Comm: ls Tainted: G W ------- ---- 6.6.43 #2 [ 1148.081751][T17331] Source Version: 21b3b386e948bedd29369af66f3e98ab01b1c650 [ 1148.088783][T17331] Hardware name: Greatwall GW-001M1A-FTF/GW-001M1A-FTF, BIOS KunLun BIOS V4.0 07/16/2020 [ 1148.098419][T17331] pstate: 20000005 (nzCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 1148.106060][T17331] pc : eventfs_iterate+0x2c0/0x398 [ 1148.111017][T17331] lr : eventfs_iterate+0x2fc/0x398 [ 1148.115969][T17331] sp : ffff80008d56bbd0 [ 1148.119964][T17331] x29: ffff80008d56bbf0 x28: ffff001ff5be2600 x27: 0000000000000000 [ 1148.127781][T17331] x26: ffff001ff52ca4e0 x25: 0000000000009977 x24: dead000000000100 [ 1148.135598][T17331] x23: 0000000000000000 x22: 000000000000000b x21: ffff800082645f10 [ 1148.143415][T17331] x20: ffff001fddf87c70 x19: ffff80008d56bc90 x18: 0000000000000000 [ 1148.151231][T17331] x17: 0000000000000000 x16: 0000000000000000 x15: ffff001ff52ca4e0 [ 1148.159048][T17331] x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 [ 1148.166864][T17331] x11: 0000000000000000 x10: 0000000000000000 x9 : ffff8000804391d0 [ 1148.174680][T17331] x8 : 0000000180000000 x7 : 0000000000000018 x6 : 0000aaab04b92862 [ 1148.182498][T17331] x5 : 0000aaab04b92862 x4 : 0000000080000000 x3 : 0000000000000068 [ 1148.190314][T17331] x2 : 000000000000000f x1 : 0000000000007ea8 x0 : 0000000000000001 [ 1148.198131][T17331] Call trace: [ 1148.201259][T17331] eventfs_iterate+0x2c0/0x398 [ 1148.205864][T17331] iterate_dir+0x98/0x188 [ 1148.210036][T17331] __arm64_sys_getdents64+0x78/0x160 [ 1148.215161][T17331] invoke_syscall+0x78/0x108 [ 1148.219593][T17331] el0_svc_common.constprop.0+0x48/0xf0 [ 1148.224977][T17331] do_el0_svc+0x24/0x38 [ 1148.228974][T17331] el0_svc+0x40/0x168 [ 1148.232798][T17331] el0t_64_sync_handler+0x120/0x130 [ 1148.237836][T17331] el0t_64_sync+0x1a4/0x1a8 [ 1148.242182][T17331] Code: 54ffff6c f9400676 910006d6 f9000676 (b9405300) [ 1148.248955][T17331] ---[ end trace 0000000000000000 ]--- The issue is that list_del() is used on an SRCU protected list variable before the synchronization occurs. This can poison the list pointers while there is a reader iterating the list. This is simply fixed by using list_del_rcu() that is specifically made for this purpose. Link: https://lore.kernel.org/linux-trace-kernel/20240829085025.3600021-1-chizhil… Cc: stable(a)vger.kernel.org Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Link: https://lore.kernel.org/20240904131605.640d42b1@gandalf.local.home Fixes: 43aa6f97c2d03 ("eventfs: Get rid of dentry pointers without refcounts") Reported-by: Chi Zhiling <chizhiling(a)kylinos.cn> Tested-by: Chi Zhiling <chizhiling(a)kylinos.cn> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- fs/tracefs/event_inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 01e99e98457d..8705c77a9e75 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -862,7 +862,7 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level) list_for_each_entry(ei_child, &ei->children, list) eventfs_remove_rec(ei_child, level + 1); - list_del(&ei->list); + list_del_rcu(&ei->list); free_ei(ei); } -- 2.43.0

1 month, 2 weeks

1
0
0 0

[for-linus][PATCH 5/6] tracing: Avoid possible softlockup in tracing_iter_reset()

by Steven Rostedt

From: Zheng Yejian <zhengyejian(a)huaweicloud.com> In __tracing_open(), when max latency tracers took place on the cpu, the time start of its buffer would be updated, then event entries with timestamps being earlier than start of the buffer would be skipped (see tracing_iter_reset()). Softlockup will occur if the kernel is non-preemptible and too many entries were skipped in the loop that reset every cpu buffer, so add cond_resched() to avoid it. Cc: stable(a)vger.kernel.org Fixes: 2f26ebd549b9a ("tracing: use timestamp to determine start of latency traces") Link: https://lore.kernel.org/20240827124654.3817443-1-zhengyejian@huaweicloud.com Suggested-by: Steven Rostedt <rostedt(a)goodmis.org> Signed-off-by: Zheng Yejian <zhengyejian(a)huaweicloud.com> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- kernel/trace/trace.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ebe7ce2f5f4a..edf6bc817aa1 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3958,6 +3958,8 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) break; entries++; ring_buffer_iter_advance(buf_iter); + /* This could be a big loop */ + cond_resched(); } per_cpu_ptr(iter->array_buffer->data, cpu)->skipped_entries = entries; -- 2.43.0

1 month, 2 weeks

1
0
0 0

[for-linus][PATCH 4/6] tracing/osnoise: Use a cpumask to know what threads are kthreads

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> The start_kthread() and stop_thread() code was not always called with the interface_lock held. This means that the kthread variable could be unexpectedly changed causing the kthread_stop() to be called on it when it should not have been, leading to: while true; do rtla timerlat top -u -q & PID=$!; sleep 5; kill -INT $PID; sleep 0.001; kill -TERM $PID; wait $PID; done Causing the following OOPS: Oops: general protection fault, probably for non-canonical address 0xdffffc0000000002: 0000 [#1] PREEMPT SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017] CPU: 5 UID: 0 PID: 885 Comm: timerlatu/5 Not tainted 6.11.0-rc4-test-00002-gbc754cc76d1b-dirty #125 a533010b71dab205ad2f507188ce8c82203b0254 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 RIP: 0010:hrtimer_active+0x58/0x300 Code: 48 c1 ee 03 41 54 48 01 d1 48 01 d6 55 53 48 83 ec 20 80 39 00 0f 85 30 02 00 00 49 8b 6f 30 4c 8d 75 10 4c 89 f0 48 c1 e8 03 <0f> b6 3c 10 4c 89 f0 83 e0 07 83 c0 03 40 38 f8 7c 09 40 84 ff 0f RSP: 0018:ffff88811d97f940 EFLAGS: 00010202 RAX: 0000000000000002 RBX: ffff88823c6b5b28 RCX: ffffed10478d6b6b RDX: dffffc0000000000 RSI: ffffed10478d6b6c RDI: ffff88823c6b5b28 RBP: 0000000000000000 R08: ffff88823c6b5b58 R09: ffff88823c6b5b60 R10: ffff88811d97f957 R11: 0000000000000010 R12: 00000000000a801d R13: ffff88810d8b35d8 R14: 0000000000000010 R15: ffff88823c6b5b28 FS: 0000000000000000(0000) GS:ffff88823c680000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000561858ad7258 CR3: 000000007729e001 CR4: 0000000000170ef0 Call Trace: <TASK> ? die_addr+0x40/0xa0 ? exc_general_protection+0x154/0x230 ? asm_exc_general_protection+0x26/0x30 ? hrtimer_active+0x58/0x300 ? __pfx_mutex_lock+0x10/0x10 ? __pfx_locks_remove_file+0x10/0x10 hrtimer_cancel+0x15/0x40 timerlat_fd_release+0x8e/0x1f0 ? security_file_release+0x43/0x80 __fput+0x372/0xb10 task_work_run+0x11e/0x1f0 ? _raw_spin_lock+0x85/0xe0 ? __pfx_task_work_run+0x10/0x10 ? poison_slab_object+0x109/0x170 ? do_exit+0x7a0/0x24b0 do_exit+0x7bd/0x24b0 ? __pfx_migrate_enable+0x10/0x10 ? __pfx_do_exit+0x10/0x10 ? __pfx_read_tsc+0x10/0x10 ? ktime_get+0x64/0x140 ? _raw_spin_lock_irq+0x86/0xe0 do_group_exit+0xb0/0x220 get_signal+0x17ba/0x1b50 ? vfs_read+0x179/0xa40 ? timerlat_fd_read+0x30b/0x9d0 ? __pfx_get_signal+0x10/0x10 ? __pfx_timerlat_fd_read+0x10/0x10 arch_do_signal_or_restart+0x8c/0x570 ? __pfx_arch_do_signal_or_restart+0x10/0x10 ? vfs_read+0x179/0xa40 ? ksys_read+0xfe/0x1d0 ? __pfx_ksys_read+0x10/0x10 syscall_exit_to_user_mode+0xbc/0x130 do_syscall_64+0x74/0x110 ? __pfx___rseq_handle_notify_resume+0x10/0x10 ? __pfx_ksys_read+0x10/0x10 ? fpregs_restore_userregs+0xdb/0x1e0 ? fpregs_restore_userregs+0xdb/0x1e0 ? syscall_exit_to_user_mode+0x116/0x130 ? do_syscall_64+0x74/0x110 ? do_syscall_64+0x74/0x110 ? do_syscall_64+0x74/0x110 entry_SYSCALL_64_after_hwframe+0x71/0x79 RIP: 0033:0x7ff0070eca9c Code: Unable to access opcode bytes at 0x7ff0070eca72. RSP: 002b:00007ff006dff8c0 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 RAX: 0000000000000000 RBX: 0000000000000005 RCX: 00007ff0070eca9c RDX: 0000000000000400 RSI: 00007ff006dff9a0 RDI: 0000000000000003 RBP: 00007ff006dffde0 R08: 0000000000000000 R09: 00007ff000000ba0 R10: 00007ff007004b08 R11: 0000000000000246 R12: 0000000000000003 R13: 00007ff006dff9a0 R14: 0000000000000007 R15: 0000000000000008 </TASK> Modules linked in: snd_hda_intel snd_intel_dspcfg snd_intel_sdw_acpi snd_hda_codec snd_hwdep snd_hda_core ---[ end trace 0000000000000000 ]--- This is because it would mistakenly call kthread_stop() on a user space thread making it "exit" before it actually exits. Since kthreads are created based on global behavior, use a cpumask to know when kthreads are running and that they need to be shutdown before proceeding to do new work. Link: https://lore.kernel.org/all/20240820130001.124768-1-tglozar@redhat.com/ This was debugged by using the persistent ring buffer: Link: https://lore.kernel.org/all/20240823013902.135036960@goodmis.org/ Note, locking was originally used to fix this, but that proved to cause too many deadlocks to work around: https://lore.kernel.org/linux-trace-kernel/20240823102816.5e55753b@gandalf.… Cc: stable(a)vger.kernel.org Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: "Luis Claudio R. Goncalves" <lgoncalv(a)redhat.com> Link: https://lore.kernel.org/20240904103428.08efdf4c@gandalf.local.home Fixes: e88ed227f639e ("tracing/timerlat: Add user-space interface") Reported-by: Tomas Glozar <tglozar(a)redhat.com> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- kernel/trace/trace_osnoise.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 400a72cd6ab5..8543d941b870 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1614,6 +1614,7 @@ static int run_osnoise(void) static struct cpumask osnoise_cpumask; static struct cpumask save_cpumask; +static struct cpumask kthread_cpumask; /* * osnoise_sleep - sleep until the next period @@ -1677,6 +1678,7 @@ static inline int osnoise_migration_pending(void) */ mutex_lock(&interface_lock); this_cpu_osn_var()->kthread = NULL; + cpumask_clear_cpu(smp_processor_id(), &kthread_cpumask); mutex_unlock(&interface_lock); return 1; @@ -1949,9 +1951,10 @@ static void stop_kthread(unsigned int cpu) kthread = per_cpu(per_cpu_osnoise_var, cpu).kthread; if (kthread) { - if (test_bit(OSN_WORKLOAD, &osnoise_options)) { + if (cpumask_test_and_clear_cpu(cpu, &kthread_cpumask) && + !WARN_ON(!test_bit(OSN_WORKLOAD, &osnoise_options))) { kthread_stop(kthread); - } else { + } else if (!WARN_ON(test_bit(OSN_WORKLOAD, &osnoise_options))) { /* * This is a user thread waiting on the timerlat_fd. We need * to close all users, and the best way to guarantee this is @@ -2023,6 +2026,7 @@ static int start_kthread(unsigned int cpu) } per_cpu(per_cpu_osnoise_var, cpu).kthread = kthread; + cpumask_set_cpu(cpu, &kthread_cpumask); return 0; } @@ -2050,8 +2054,16 @@ static int start_per_cpu_kthreads(void) */ cpumask_and(current_mask, cpu_online_mask, &osnoise_cpumask); - for_each_possible_cpu(cpu) + for_each_possible_cpu(cpu) { + if (cpumask_test_and_clear_cpu(cpu, &kthread_cpumask)) { + struct task_struct *kthread; + + kthread = per_cpu(per_cpu_osnoise_var, cpu).kthread; + if (!WARN_ON(!kthread)) + kthread_stop(kthread); + } per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL; + } for_each_cpu(cpu, current_mask) { retval = start_kthread(cpu); -- 2.43.0

1 month, 2 weeks

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror September 2024