- Linux-stable-mirror - lists.linaro.org

FAILED: patch "[PATCH] media: qcom: camss: cleanup media device allocated resource" 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 69080ec3d0daba8a894025476c98ab16b5a505a4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025082155-riches-diaper-55d5@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 69080ec3d0daba8a894025476c98ab16b5a505a4 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy <vladimir.zapolskiy(a)linaro.org> Date: Tue, 13 May 2025 17:23:45 +0300 Subject: [PATCH] media: qcom: camss: cleanup media device allocated resource on error path A call to media_device_init() requires media_device_cleanup() counterpart to complete cleanup and release any allocated resources. This has been done in the driver .remove() right from the beginning, but error paths on .probe() shall also be fixed. Fixes: a1d7c116fcf7 ("media: camms: Add core files") Cc: stable(a)vger.kernel.org Signed-off-by: Vladimir Zapolskiy <vladimir.zapolskiy(a)linaro.org> Reviewed-by: Bryan O'Donoghue <bryan.odonoghue(a)linaro.org> Signed-off-by: Bryan O'Donoghue <bod(a)kernel.org> Signed-off-by: Hans Verkuil <hverkuil(a)xs4all.nl> diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c index 06f42875702f..f76773dbd296 100644 --- a/drivers/media/platform/qcom/camss/camss.c +++ b/drivers/media/platform/qcom/camss/camss.c @@ -3625,7 +3625,7 @@ static int camss_probe(struct platform_device *pdev) ret = v4l2_device_register(camss->dev, &camss->v4l2_dev); if (ret < 0) { dev_err(dev, "Failed to register V4L2 device: %d\n", ret); - goto err_genpd_cleanup; + goto err_media_device_cleanup; } v4l2_async_nf_init(&camss->notifier, &camss->v4l2_dev); @@ -3680,6 +3680,8 @@ static int camss_probe(struct platform_device *pdev) v4l2_device_unregister(&camss->v4l2_dev); v4l2_async_nf_cleanup(&camss->notifier); pm_runtime_disable(dev); +err_media_device_cleanup: + media_device_cleanup(&camss->media_dev); err_genpd_cleanup: camss_genpd_cleanup(camss);

3 months, 1 week

2
2
0 0

FAILED: patch "[PATCH] media: venus: protect against spurious interrupts during" 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 3200144a2fa4209dc084a19941b9b203b43580f0 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025082150-feminize-barterer-4a0f@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 3200144a2fa4209dc084a19941b9b203b43580f0 Mon Sep 17 00:00:00 2001 From: Jorge Ramirez-Ortiz <jorge.ramirez(a)oss.qualcomm.com> Date: Fri, 6 Jun 2025 17:25:22 +0200 Subject: [PATCH] media: venus: protect against spurious interrupts during probe Make sure the interrupt handler is initialized before the interrupt is registered. If the IRQ is registered before hfi_create(), it's possible that an interrupt fires before the handler setup is complete, leading to a NULL dereference. This error condition has been observed during system boot on Rb3Gen2. Fixes: af2c3834c8ca ("[media] media: venus: adding core part and helper functions") Cc: stable(a)vger.kernel.org Signed-off-by: Jorge Ramirez-Ortiz <jorge.ramirez(a)oss.qualcomm.com> Reviewed-by: Bryan O'Donoghue <bryan.odonoghue(a)linaro.org> Reviewed-by: Vikash Garodia <quic_vgarodia(a)quicinc.com> Reviewed-by: Dikshita Agarwal <quic_dikshita(a)quicinc.com> Tested-by: Dikshita Agarwal <quic_dikshita(a)quicinc.com> # RB5 Signed-off-by: Bryan O'Donoghue <bod(a)kernel.org> Signed-off-by: Hans Verkuil <hverkuil(a)xs4all.nl> diff --git a/drivers/media/platform/qcom/venus/core.c b/drivers/media/platform/qcom/venus/core.c index d305d74bb152..5bd99d0aafe4 100644 --- a/drivers/media/platform/qcom/venus/core.c +++ b/drivers/media/platform/qcom/venus/core.c @@ -424,13 +424,13 @@ static int venus_probe(struct platform_device *pdev) INIT_DELAYED_WORK(&core->work, venus_sys_error_handler); init_waitqueue_head(&core->sys_err_done); - ret = devm_request_threaded_irq(dev, core->irq, hfi_isr, venus_isr_thread, - IRQF_TRIGGER_HIGH | IRQF_ONESHOT, - "venus", core); + ret = hfi_create(core, &venus_core_ops); if (ret) goto err_core_put; - ret = hfi_create(core, &venus_core_ops); + ret = devm_request_threaded_irq(dev, core->irq, hfi_isr, venus_isr_thread, + IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + "venus", core); if (ret) goto err_core_put;

3 months, 1 week

2
2
0 0

FAILED: patch "[PATCH] media: venus: hfi: explicitly release IRQ during teardown" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-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-5.10.y git checkout FETCH_HEAD git cherry-pick -x 640803003cd903cea73dc6a86bf6963e238e2b3f # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025082137-defiant-headstone-4d37@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 640803003cd903cea73dc6a86bf6963e238e2b3f Mon Sep 17 00:00:00 2001 From: Jorge Ramirez-Ortiz <jorge.ramirez(a)oss.qualcomm.com> Date: Thu, 19 Jun 2025 09:48:30 +0200 Subject: [PATCH] media: venus: hfi: explicitly release IRQ during teardown Ensure the IRQ is disabled - and all pending handlers completed - before dismantling the interrupt routing and clearing related pointers. This prevents any possibility of the interrupt triggering after the handler context has been invalidated. Fixes: d96d3f30c0f2 ("[media] media: venus: hfi: add Venus HFI files") Cc: stable(a)vger.kernel.org Signed-off-by: Jorge Ramirez-Ortiz <jorge.ramirez(a)oss.qualcomm.com> Reviewed-by: Dikshita Agarwal <quic_dikshita(a)quicinc.com> Tested-by: Dikshita Agarwal <quic_dikshita(a)quicinc.com> # RB5 Reviewed-by: Bryan O'Donoghue <bryan.odonoghue(a)linaro.org> Signed-off-by: Bryan O'Donoghue <bod(a)kernel.org> Signed-off-by: Hans Verkuil <hverkuil(a)xs4all.nl> diff --git a/drivers/media/platform/qcom/venus/hfi_venus.c b/drivers/media/platform/qcom/venus/hfi_venus.c index c982f4527bb0..cec7f5964d3d 100644 --- a/drivers/media/platform/qcom/venus/hfi_venus.c +++ b/drivers/media/platform/qcom/venus/hfi_venus.c @@ -1682,6 +1682,7 @@ void venus_hfi_destroy(struct venus_core *core) venus_interface_queues_release(hdev); mutex_destroy(&hdev->lock); kfree(hdev); + disable_irq(core->irq); core->ops = NULL; }

3 months, 1 week

2
2
0 0

FAILED: patch "[PATCH] f2fs: fix to avoid out-of-boundary access in dnode page" 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 77de19b6867f2740cdcb6c9c7e50d522b47847a4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025082107-suitcase-motivator-6687@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 77de19b6867f2740cdcb6c9c7e50d522b47847a4 Mon Sep 17 00:00:00 2001 From: Chao Yu <chao(a)kernel.org> Date: Thu, 17 Jul 2025 21:26:33 +0800 Subject: [PATCH] f2fs: fix to avoid out-of-boundary access in dnode page As Jiaming Zhang reported: <TASK> __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x1c1/0x2a0 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0x17e/0x800 mm/kasan/report.c:480 kasan_report+0x147/0x180 mm/kasan/report.c:593 data_blkaddr fs/f2fs/f2fs.h:3053 [inline] f2fs_data_blkaddr fs/f2fs/f2fs.h:3058 [inline] f2fs_get_dnode_of_data+0x1a09/0x1c40 fs/f2fs/node.c:855 f2fs_reserve_block+0x53/0x310 fs/f2fs/data.c:1195 prepare_write_begin fs/f2fs/data.c:3395 [inline] f2fs_write_begin+0xf39/0x2190 fs/f2fs/data.c:3594 generic_perform_write+0x2c7/0x910 mm/filemap.c:4112 f2fs_buffered_write_iter fs/f2fs/file.c:4988 [inline] f2fs_file_write_iter+0x1ec8/0x2410 fs/f2fs/file.c:5216 new_sync_write fs/read_write.c:593 [inline] vfs_write+0x546/0xa90 fs/read_write.c:686 ksys_write+0x149/0x250 fs/read_write.c:738 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xf3/0x3d0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f The root cause is in the corrupted image, there is a dnode has the same node id w/ its inode, so during f2fs_get_dnode_of_data(), it tries to access block address in dnode at offset 934, however it parses the dnode as inode node, so that get_dnode_addr() returns 360, then it tries to access page address from 360 + 934 * 4 = 4096 w/ 4 bytes. To fix this issue, let's add sanity check for node id of all direct nodes during f2fs_get_dnode_of_data(). Cc: stable(a)kernel.org Reported-by: Jiaming Zhang <r772577952(a)gmail.com> Closes: https://groups.google.com/g/syzkaller/c/-ZnaaOOfO3M Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 4b3d9070e299..76aba1961b54 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -815,6 +815,16 @@ int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) for (i = 1; i <= level; i++) { bool done = false; + if (nids[i] && nids[i] == dn->inode->i_ino) { + err = -EFSCORRUPTED; + f2fs_err_ratelimited(sbi, + "inode mapping table is corrupted, run fsck to fix it, " + "ino:%lu, nid:%u, level:%d, offset:%d", + dn->inode->i_ino, nids[i], level, offset[level]); + set_sbi_flag(sbi, SBI_NEED_FSCK); + goto release_pages; + } + if (!nids[i] && mode == ALLOC_NODE) { /* alloc new node */ if (!f2fs_alloc_nid(sbi, &(nids[i]))) {

3 months, 1 week

2
2
0 0

FAILED: patch "[PATCH] media: v4l2-ctrls: Don't reset handler's error in" 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 5a0400aca5fa7c6b8ba456c311a460e733571c88 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025082154-botany-sandstone-7eeb@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 5a0400aca5fa7c6b8ba456c311a460e733571c88 Mon Sep 17 00:00:00 2001 From: Sakari Ailus <sakari.ailus(a)linux.intel.com> Date: Thu, 8 May 2025 18:55:38 +0300 Subject: [PATCH] media: v4l2-ctrls: Don't reset handler's error in v4l2_ctrl_handler_free() It's a common pattern in drivers to free the control handler's resources and then return the handler's error code on drivers' error handling paths. Alas, the v4l2_ctrl_handler_free() function also zeroes the error field, effectively indicating successful return to the caller. There's no apparent need to touch the error field while releasing the control handler's resources and cleaning up stale pointers. Not touching the handler's error field is a more certain way to address this problem than changing all the users, in which case the pattern would be likely to re-emerge in new drivers. Do just that, don't touch the control handler's error field in v4l2_ctrl_handler_free(). Fixes: 0996517cf8ea ("V4L/DVB: v4l2: Add new control handling framework") Cc: stable(a)vger.kernel.org Signed-off-by: Sakari Ailus <sakari.ailus(a)linux.intel.com> Reviewed-by: Hans Verkuil <hverkuil(a)xs4all.nl> Reviewed-by: Laurent Pinchart <laurent.pinchart(a)ideasonboard.com> Signed-off-by: Hans Verkuil <hverkuil(a)xs4all.nl> diff --git a/drivers/media/v4l2-core/v4l2-ctrls-core.c b/drivers/media/v4l2-core/v4l2-ctrls-core.c index b45809a82f9a..d28596c720d8 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-core.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-core.c @@ -1661,7 +1661,6 @@ void v4l2_ctrl_handler_free(struct v4l2_ctrl_handler *hdl) kvfree(hdl->buckets); hdl->buckets = NULL; hdl->cached = NULL; - hdl->error = 0; mutex_unlock(hdl->lock); mutex_destroy(&hdl->_lock); }

3 months, 1 week

2
2
0 0

FAILED: patch "[PATCH] media: v4l2-ctrls: Don't reset handler's error in" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-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-5.10.y git checkout FETCH_HEAD git cherry-pick -x 5a0400aca5fa7c6b8ba456c311a460e733571c88 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025082153-curliness-sitting-639b@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 5a0400aca5fa7c6b8ba456c311a460e733571c88 Mon Sep 17 00:00:00 2001 From: Sakari Ailus <sakari.ailus(a)linux.intel.com> Date: Thu, 8 May 2025 18:55:38 +0300 Subject: [PATCH] media: v4l2-ctrls: Don't reset handler's error in v4l2_ctrl_handler_free() It's a common pattern in drivers to free the control handler's resources and then return the handler's error code on drivers' error handling paths. Alas, the v4l2_ctrl_handler_free() function also zeroes the error field, effectively indicating successful return to the caller. There's no apparent need to touch the error field while releasing the control handler's resources and cleaning up stale pointers. Not touching the handler's error field is a more certain way to address this problem than changing all the users, in which case the pattern would be likely to re-emerge in new drivers. Do just that, don't touch the control handler's error field in v4l2_ctrl_handler_free(). Fixes: 0996517cf8ea ("V4L/DVB: v4l2: Add new control handling framework") Cc: stable(a)vger.kernel.org Signed-off-by: Sakari Ailus <sakari.ailus(a)linux.intel.com> Reviewed-by: Hans Verkuil <hverkuil(a)xs4all.nl> Reviewed-by: Laurent Pinchart <laurent.pinchart(a)ideasonboard.com> Signed-off-by: Hans Verkuil <hverkuil(a)xs4all.nl> diff --git a/drivers/media/v4l2-core/v4l2-ctrls-core.c b/drivers/media/v4l2-core/v4l2-ctrls-core.c index b45809a82f9a..d28596c720d8 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-core.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-core.c @@ -1661,7 +1661,6 @@ void v4l2_ctrl_handler_free(struct v4l2_ctrl_handler *hdl) kvfree(hdl->buckets); hdl->buckets = NULL; hdl->cached = NULL; - hdl->error = 0; mutex_unlock(hdl->lock); mutex_destroy(&hdl->_lock); }

3 months, 1 week

2
2
0 0

FAILED: patch "[PATCH] media: rainshadow-cec: fix TOCTOU race condition in" 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 7af160aea26c7dc9e6734d19306128cce156ec40 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025082119-december-ranking-b3a3@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 7af160aea26c7dc9e6734d19306128cce156ec40 Mon Sep 17 00:00:00 2001 From: Gui-Dong Han <hanguidong02(a)gmail.com> Date: Fri, 6 Jun 2025 03:04:59 +0000 Subject: [PATCH] media: rainshadow-cec: fix TOCTOU race condition in rain_interrupt() In the interrupt handler rain_interrupt(), the buffer full check on rain->buf_len is performed before acquiring rain->buf_lock. This creates a Time-of-Check to Time-of-Use (TOCTOU) race condition, as rain->buf_len is concurrently accessed and modified in the work handler rain_irq_work_handler() under the same lock. Multiple interrupt invocations can race, with each reading buf_len before it becomes full and then proceeding. This can lead to both interrupts attempting to write to the buffer, incrementing buf_len beyond its capacity (DATA_SIZE) and causing a buffer overflow. Fix this bug by moving the spin_lock() to before the buffer full check. This ensures that the check and the subsequent buffer modification are performed atomically, preventing the race condition. An corresponding spin_unlock() is added to the overflow path to correctly release the lock. This possible bug was found by an experimental static analysis tool developed by our team. Fixes: 0f314f6c2e77 ("[media] rainshadow-cec: new RainShadow Tech HDMI CEC driver") Cc: stable(a)vger.kernel.org Signed-off-by: Gui-Dong Han <hanguidong02(a)gmail.com> Signed-off-by: Hans Verkuil <hverkuil(a)xs4all.nl> diff --git a/drivers/media/cec/usb/rainshadow/rainshadow-cec.c b/drivers/media/cec/usb/rainshadow/rainshadow-cec.c index ee870ea1a886..6f8d6797c614 100644 --- a/drivers/media/cec/usb/rainshadow/rainshadow-cec.c +++ b/drivers/media/cec/usb/rainshadow/rainshadow-cec.c @@ -171,11 +171,12 @@ static irqreturn_t rain_interrupt(struct serio *serio, unsigned char data, { struct rain *rain = serio_get_drvdata(serio); + spin_lock(&rain->buf_lock); if (rain->buf_len == DATA_SIZE) { + spin_unlock(&rain->buf_lock); dev_warn_once(rain->dev, "buffer overflow\n"); return IRQ_HANDLED; } - spin_lock(&rain->buf_lock); rain->buf_len++; rain->buf[rain->buf_wr_idx] = data; rain->buf_wr_idx = (rain->buf_wr_idx + 1) & 0xff;

3 months, 1 week

2
1
0 0

[alternative-merged] mm-memory_hotplug-fix-hwpoisoned-large-folio-handling-in-do_migrate_range.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/memory_hotplug: fix hwpoisoned large folio handling in do_migrate_range has been removed from the -mm tree. Its filename was mm-memory_hotplug-fix-hwpoisoned-large-folio-handling-in-do_migrate_range.patch This patch was dropped because an alternative patch was or shall be merged ------------------------------------------------------ From: Jinjiang Tu <tujinjiang(a)huawei.com> Subject: mm/memory_hotplug: fix hwpoisoned large folio handling in do_migrate_range Date: Fri, 27 Jun 2025 20:57:47 +0800 In do_migrate_range(), the hwpoisoned folio may be large folio, which can't be handled by unmap_poisoned_folio(). I can reproduce this issue in qemu after adding delay in memory_failure() BUG: kernel NULL pointer dereference, address: 0000000000000000 Workqueue: kacpi_hotplug acpi_hotplug_work_fn RIP: 0010:try_to_unmap_one+0x16a/0xfc0 <TASK> rmap_walk_anon+0xda/0x1f0 try_to_unmap+0x78/0x80 ? __pfx_try_to_unmap_one+0x10/0x10 ? __pfx_folio_not_mapped+0x10/0x10 ? __pfx_folio_lock_anon_vma_read+0x10/0x10 unmap_poisoned_folio+0x60/0x140 do_migrate_range+0x4d1/0x600 ? slab_memory_callback+0x6a/0x190 ? notifier_call_chain+0x56/0xb0 offline_pages+0x3e6/0x460 memory_subsys_offline+0x130/0x1f0 device_offline+0xba/0x110 acpi_bus_offline+0xb7/0x130 acpi_scan_hot_remove+0x77/0x290 acpi_device_hotplug+0x1e0/0x240 acpi_hotplug_work_fn+0x1a/0x30 process_one_work+0x186/0x340 In this case, just make offline_pages() fail. Also, do_migrate_range() may be called between memory_failure() setting the hwposion flag and isolation of the folio from the lru, so remove WARN_ON(). Also, in other places unmap_poisoned_folio() is called when the folio is isolated, so obey that in do_migrate_range(). Link: https://lkml.kernel.org/r/20250627125747.3094074-3-tujinjiang@huawei.com Fixes: b15c87263a69 ("hwpoison, memory_hotplug: allow hwpoisoned pages to be offlined") Signed-off-by: Jinjiang Tu <tujinjiang(a)huawei.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: Miaohe Lin <linmiaohe(a)huawei.com> Cc: Michal Hocko <mhocko(a)kernel.org> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/memory_hotplug.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) --- a/mm/memory_hotplug.c~mm-memory_hotplug-fix-hwpoisoned-large-folio-handling-in-do_migrate_range +++ a/mm/memory_hotplug.c @@ -1791,7 +1791,7 @@ found: return 0; } -static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) +static int do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) { struct folio *folio; unsigned long pfn; @@ -1815,8 +1815,10 @@ static void do_migrate_range(unsigned lo pfn = folio_pfn(folio) + folio_nr_pages(folio) - 1; if (folio_contain_hwpoisoned_page(folio)) { - if (WARN_ON(folio_test_lru(folio))) - folio_isolate_lru(folio); + if (folio_test_large(folio) && !folio_test_hugetlb(folio)) + goto err_out; + if (folio_test_lru(folio) && !folio_isolate_lru(folio)) + goto err_out; if (folio_mapped(folio)) { folio_lock(folio); unmap_poisoned_folio(folio, pfn, false); @@ -1873,6 +1875,11 @@ put_folio: putback_movable_pages(&source); } } + return 0; +err_out: + folio_put(folio); + putback_movable_pages(&source); + return -EBUSY; } static int __init cmdline_parse_movable_node(char *p) @@ -2006,11 +2013,9 @@ int offline_pages(unsigned long start_pf ret = scan_movable_pages(pfn, end_pfn, &pfn); if (!ret) { - /* - * TODO: fatal migration failures should bail - * out - */ - do_migrate_range(pfn, end_pfn); + ret = do_migrate_range(pfn, end_pfn); + if (ret) + break; } } while (!ret); _ Patches currently in -mm which might be from tujinjiang(a)huawei.com are

3 months, 1 week

1
0
0 0

+ mm-khugepaged-fix-the-address-passed-to-notifier-on-testing-young.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/khugepaged: fix the address passed to notifier on testing young has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-khugepaged-fix-the-address-passed-to-notifier-on-testing-young.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Wei Yang <richard.weiyang(a)gmail.com> Subject: mm/khugepaged: fix the address passed to notifier on testing young Date: Fri, 22 Aug 2025 06:33:18 +0000 Commit 8ee53820edfd ("thp: mmu_notifier_test_young") introduced mmu_notifier_test_young(), but we should pass the address need to test. In xxx_scan_pmd(), the actual iteration address is "_address" not "address". We seem to misuse the variable on the very beginning. Change it to the right one. Link: https://lkml.kernel.org/r/20250822063318.11644-1-richard.weiyang@gmail.com Fixes: 8ee53820edfd ("thp: mmu_notifier_test_young") Signed-off-by: Wei Yang <richard.weiyang(a)gmail.com> Reviewed-by: Dev Jain <dev.jain(a)arm.com> Reviewed-by: Zi Yan <ziy(a)nvidia.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: Nico Pache <npache(a)redhat.com> Cc: Ryan Roberts <ryan.roberts(a)arm.com> Cc: Barry Song <baohua(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/khugepaged.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/mm/khugepaged.c~mm-khugepaged-fix-the-address-passed-to-notifier-on-testing-young +++ a/mm/khugepaged.c @@ -1418,7 +1418,7 @@ static int hpage_collapse_scan_pmd(struc if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, - address))) + _address))) referenced++; } if (!writable) { _ Patches currently in -mm which might be from richard.weiyang(a)gmail.com are mm-khugepaged-fix-the-address-passed-to-notifier-on-testing-young.patch mm-rmap-do-__folio_mod_stat-in-__folio_add_rmap.patch selftests-mm-do-check_huge_anon-with-a-number-been-passed-in.patch mm-rmap-not-necessary-to-mask-off-folio_pages_mapped.patch mm-rmap-use-folio_large_nr_pages-when-we-are-sure-it-is-a-large-folio.patch selftests-mm-put-general-ksm-operation-into-vm_util.patch selftests-mm-test-that-rmap-behave-as-expected.patch mm-khugepaged-use-list_xxx-helper-to-improve-readability.patch

3 months, 1 week

1
0
0 0

+ mm-fix-possible-deadlock-in-kmemleak.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm: gix possible deadlock in kmemleak has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-fix-possible-deadlock-in-kmemleak.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Gu Bowen <gubowen5(a)huawei.com> Subject: mm: gix possible deadlock in kmemleak Date: Fri, 22 Aug 2025 15:35:41 +0800 There are some AA deadlock issues in kmemleak, similar to the situation reported by Breno [1]. The deadlock path is as follows: mem_pool_alloc() -> raw_spin_lock_irqsave(&kmemleak_lock, flags); -> pr_warn() -> netconsole subsystem -> netpoll -> __alloc_skb -> __create_object -> raw_spin_lock_irqsave(&kmemleak_lock, flags); To solve this problem, switch to printk_safe mode before printing warning message, this will redirect all printk()-s to a special per-CPU buffer, which will be flushed later from a safe context (irq work), and this deadlock problem can be avoided. The proper API to use should be printk_deferred_enter()/printk_deferred_exit() [2]. Another way is to place the warn print after kmemleak is released. Link: https://lkml.kernel.org/r/20250822073541.1886469-1-gubowen5@huawei.com Link: https://lore.kernel.org/all/20250731-kmemleak_lock-v1-1-728fd470198f@debian… [1] Link: https://lore.kernel.org/all/5ca375cd-4a20-4807-b897-68b289626550@redhat.com/ [2] Signed-off-by: Gu Bowen <gubowen5(a)huawei.com> Cc: Breno Leitao <leitao(a)debian.org> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: John Ogness <john.ogness(a)linutronix.de> Cc: Lu Jialin <lujialin4(a)huawei.com> Cc: Petr Mladek <pmladek(a)suse.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/kmemleak.c | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) --- a/mm/kmemleak.c~mm-fix-possible-deadlock-in-kmemleak +++ a/mm/kmemleak.c @@ -437,9 +437,15 @@ static struct kmemleak_object *__lookup_ else if (untagged_objp == untagged_ptr || alias) return object; else { + /* + * Printk deferring due to the kmemleak_lock held. + * This is done to avoid deadlock. + */ + printk_deferred_enter(); kmemleak_warn("Found object by alias at 0x%08lx\n", ptr); dump_object_info(object); + printk_deferred_exit(); break; } } @@ -736,6 +742,11 @@ static int __link_object(struct kmemleak else if (untagged_objp + parent->size <= untagged_ptr) link = &parent->rb_node.rb_right; else { + /* + * Printk deferring due to the kmemleak_lock held. + * This is done to avoid deadlock. + */ + printk_deferred_enter(); kmemleak_stop("Cannot insert 0x%lx into the object search tree (overlaps existing)\n", ptr); /* @@ -743,6 +754,7 @@ static int __link_object(struct kmemleak * be freed while the kmemleak_lock is held. */ dump_object_info(parent); + printk_deferred_exit(); return -EEXIST; } } @@ -856,13 +868,8 @@ static void delete_object_part(unsigned raw_spin_lock_irqsave(&kmemleak_lock, flags); object = __find_and_remove_object(ptr, 1, objflags); - if (!object) { -#ifdef DEBUG - kmemleak_warn("Partially freeing unknown object at 0x%08lx (size %zu)\n", - ptr, size); -#endif + if (!object) goto unlock; - } /* * Create one or two objects that may result from the memory block @@ -882,8 +889,14 @@ static void delete_object_part(unsigned unlock: raw_spin_unlock_irqrestore(&kmemleak_lock, flags); - if (object) + if (object) { __delete_object(object); + } else { +#ifdef DEBUG + kmemleak_warn("Partially freeing unknown object at 0x%08lx (size %zu)\n", + ptr, size); +#endif + } out: if (object_l) _ Patches currently in -mm which might be from gubowen5(a)huawei.com are mm-fix-possible-deadlock-in-kmemleak.patch

3 months, 1 week

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror