May 2025 - Linux-stable-mirror

FAILED: patch "[PATCH] dmaengine: idxd: Refactor remove call with idxd_cleanup()" 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 a409e919ca321cc0e28f8abf96fde299f0072a81 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051938-garden-pungent-45cd@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a409e919ca321cc0e28f8abf96fde299f0072a81 Mon Sep 17 00:00:00 2001 From: Shuai Xue <xueshuai(a)linux.alibaba.com> Date: Fri, 4 Apr 2025 20:02:17 +0800 Subject: [PATCH] dmaengine: idxd: Refactor remove call with idxd_cleanup() helper The idxd_cleanup() helper cleans up perfmon, interrupts, internals and so on. Refactor remove call with the idxd_cleanup() helper to avoid code duplication. Note, this also fixes the missing put_device() for idxd groups, enginces and wqs. Fixes: bfe1d56091c1 ("dmaengine: idxd: Init and probe for Intel data accelerators") Cc: stable(a)vger.kernel.org Suggested-by: Vinicius Costa Gomes <vinicius.gomes(a)intel.com> Signed-off-by: Shuai Xue <xueshuai(a)linux.alibaba.com> Reviewed-by: Fenghua Yu <fenghuay(a)nvidia.com> Reviewed-by: Dave Jiang <dave.jiang(a)intel.com> Link: https://lore.kernel.org/r/20250404120217.48772-10-xueshuai@linux.alibaba.com Signed-off-by: Vinod Koul <vkoul(a)kernel.org> diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 974b926bd930..760b7d81fcd8 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -1308,7 +1308,6 @@ static void idxd_shutdown(struct pci_dev *pdev) static void idxd_remove(struct pci_dev *pdev) { struct idxd_device *idxd = pci_get_drvdata(pdev); - struct idxd_irq_entry *irq_entry; idxd_unregister_devices(idxd); /* @@ -1321,21 +1320,12 @@ static void idxd_remove(struct pci_dev *pdev) get_device(idxd_confdev(idxd)); device_unregister(idxd_confdev(idxd)); idxd_shutdown(pdev); - if (device_pasid_enabled(idxd)) - idxd_disable_system_pasid(idxd); idxd_device_remove_debugfs(idxd); - - irq_entry = idxd_get_ie(idxd, 0); - free_irq(irq_entry->vector, irq_entry); - pci_free_irq_vectors(pdev); + idxd_cleanup(idxd); pci_iounmap(pdev, idxd->reg_base); - if (device_user_pasid_enabled(idxd)) - idxd_disable_sva(pdev); - pci_disable_device(pdev); - destroy_workqueue(idxd->wq); - perfmon_pmu_remove(idxd); put_device(idxd_confdev(idxd)); idxd_free(idxd); + pci_disable_device(pdev); } static struct pci_driver idxd_pci_driver = {

2 weeks, 6 days

1
0
0 0

FAILED: patch "[PATCH] dmaengine: idxd: Refactor remove call with idxd_cleanup()" 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 a409e919ca321cc0e28f8abf96fde299f0072a81 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051938-reactor-print-6033@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a409e919ca321cc0e28f8abf96fde299f0072a81 Mon Sep 17 00:00:00 2001 From: Shuai Xue <xueshuai(a)linux.alibaba.com> Date: Fri, 4 Apr 2025 20:02:17 +0800 Subject: [PATCH] dmaengine: idxd: Refactor remove call with idxd_cleanup() helper The idxd_cleanup() helper cleans up perfmon, interrupts, internals and so on. Refactor remove call with the idxd_cleanup() helper to avoid code duplication. Note, this also fixes the missing put_device() for idxd groups, enginces and wqs. Fixes: bfe1d56091c1 ("dmaengine: idxd: Init and probe for Intel data accelerators") Cc: stable(a)vger.kernel.org Suggested-by: Vinicius Costa Gomes <vinicius.gomes(a)intel.com> Signed-off-by: Shuai Xue <xueshuai(a)linux.alibaba.com> Reviewed-by: Fenghua Yu <fenghuay(a)nvidia.com> Reviewed-by: Dave Jiang <dave.jiang(a)intel.com> Link: https://lore.kernel.org/r/20250404120217.48772-10-xueshuai@linux.alibaba.com Signed-off-by: Vinod Koul <vkoul(a)kernel.org> diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 974b926bd930..760b7d81fcd8 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -1308,7 +1308,6 @@ static void idxd_shutdown(struct pci_dev *pdev) static void idxd_remove(struct pci_dev *pdev) { struct idxd_device *idxd = pci_get_drvdata(pdev); - struct idxd_irq_entry *irq_entry; idxd_unregister_devices(idxd); /* @@ -1321,21 +1320,12 @@ static void idxd_remove(struct pci_dev *pdev) get_device(idxd_confdev(idxd)); device_unregister(idxd_confdev(idxd)); idxd_shutdown(pdev); - if (device_pasid_enabled(idxd)) - idxd_disable_system_pasid(idxd); idxd_device_remove_debugfs(idxd); - - irq_entry = idxd_get_ie(idxd, 0); - free_irq(irq_entry->vector, irq_entry); - pci_free_irq_vectors(pdev); + idxd_cleanup(idxd); pci_iounmap(pdev, idxd->reg_base); - if (device_user_pasid_enabled(idxd)) - idxd_disable_sva(pdev); - pci_disable_device(pdev); - destroy_workqueue(idxd->wq); - perfmon_pmu_remove(idxd); put_device(idxd_confdev(idxd)); idxd_free(idxd); + pci_disable_device(pdev); } static struct pci_driver idxd_pci_driver = {

2 weeks, 6 days

1
0
0 0

FAILED: patch "[PATCH] dmaengine: idxd: fix memory leak in error handling path of" 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 90022b3a6981ec234902be5dbf0f983a12c759fc # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051919-legislate-uptake-1812@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 90022b3a6981ec234902be5dbf0f983a12c759fc Mon Sep 17 00:00:00 2001 From: Shuai Xue <xueshuai(a)linux.alibaba.com> Date: Fri, 4 Apr 2025 20:02:15 +0800 Subject: [PATCH] dmaengine: idxd: fix memory leak in error handling path of idxd_pci_probe Memory allocated for idxd is not freed if an error occurs during idxd_pci_probe(). To fix it, free the allocated memory in the reverse order of allocation before exiting the function in case of an error. Fixes: bfe1d56091c1 ("dmaengine: idxd: Init and probe for Intel data accelerators") Cc: stable(a)vger.kernel.org Signed-off-by: Shuai Xue <xueshuai(a)linux.alibaba.com> Reviewed-by: Dave Jiang <dave.jiang(a)intel.com> Reviewed-by: Fenghua Yu <fenghuay(a)nvidia.com> Link: https://lore.kernel.org/r/20250404120217.48772-8-xueshuai@linux.alibaba.com Signed-off-by: Vinod Koul <vkoul(a)kernel.org> diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 302d8983ed8c..f2b5b17538c0 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -587,6 +587,17 @@ static void idxd_read_caps(struct idxd_device *idxd) idxd->hw.iaa_cap.bits = ioread64(idxd->reg_base + IDXD_IAACAP_OFFSET); } +static void idxd_free(struct idxd_device *idxd) +{ + if (!idxd) + return; + + put_device(idxd_confdev(idxd)); + bitmap_free(idxd->opcap_bmap); + ida_free(&idxd_ida, idxd->id); + kfree(idxd); +} + static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_data *data) { struct device *dev = &pdev->dev; @@ -1255,7 +1266,7 @@ int idxd_pci_probe_alloc(struct idxd_device *idxd, struct pci_dev *pdev, err: pci_iounmap(pdev, idxd->reg_base); err_iomap: - put_device(idxd_confdev(idxd)); + idxd_free(idxd); err_idxd_alloc: pci_disable_device(pdev); return rc;

2 weeks, 6 days

1
0
0 0

FAILED: patch "[PATCH] dmaengine: idxd: Add missing idxd cleanup to fix memory leak" 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 d5449ff1b04dfe9ed8e455769aa01e4c2ccf6805 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051952-skyward-derail-feae@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From d5449ff1b04dfe9ed8e455769aa01e4c2ccf6805 Mon Sep 17 00:00:00 2001 From: Shuai Xue <xueshuai(a)linux.alibaba.com> Date: Fri, 4 Apr 2025 20:02:16 +0800 Subject: [PATCH] dmaengine: idxd: Add missing idxd cleanup to fix memory leak in remove call The remove call stack is missing idxd cleanup to free bitmap, ida and the idxd_device. Call idxd_free() helper routines to make sure we exit gracefully. Fixes: bfe1d56091c1 ("dmaengine: idxd: Init and probe for Intel data accelerators") Cc: stable(a)vger.kernel.org Suggested-by: Vinicius Costa Gomes <vinicius.gomes(a)intel.com> Signed-off-by: Shuai Xue <xueshuai(a)linux.alibaba.com> Reviewed-by: Fenghua Yu <fenghuay(a)nvidia.com> Reviewed-by: Dave Jiang <dave.jiang(a)intel.com> Link: https://lore.kernel.org/r/20250404120217.48772-9-xueshuai@linux.alibaba.com Signed-off-by: Vinod Koul <vkoul(a)kernel.org> diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index f2b5b17538c0..974b926bd930 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -1335,6 +1335,7 @@ static void idxd_remove(struct pci_dev *pdev) destroy_workqueue(idxd->wq); perfmon_pmu_remove(idxd); put_device(idxd_confdev(idxd)); + idxd_free(idxd); } static struct pci_driver idxd_pci_driver = {

2 weeks, 6 days

1
0
0 0

FAILED: patch "[PATCH] nvmet: pci-epf: clear completion queue IRQ flag on delete" failed to apply to 6.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.14-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-6.14.y git checkout FETCH_HEAD git cherry-pick -x 85adf2094abb9084770dc4ab302aaa9c5d26dd2d # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051914-expulsion-cinema-9689@gregkh' --subject-prefix 'PATCH 6.14.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 85adf2094abb9084770dc4ab302aaa9c5d26dd2d Mon Sep 17 00:00:00 2001 From: Damien Le Moal <dlemoal(a)kernel.org> Date: Fri, 9 May 2025 08:25:00 +0900 Subject: [PATCH] nvmet: pci-epf: clear completion queue IRQ flag on delete The function nvmet_pci_epf_delete_cq() unconditionally calls nvmet_pci_epf_remove_irq_vector() even for completion queues that do not have interrupts enabled. Furthermore, for completion queues that do have IRQ enabled, deleting and re-creating the completion queue leaves the flag NVMET_PCI_EPF_Q_IRQ_ENABLED set, even if the completion queue is being re-created with IRQ disabled. Fix these issues by calling nvmet_pci_epf_remove_irq_vector() only if NVMET_PCI_EPF_Q_IRQ_ENABLED is set and make sure to always clear that flag. Fixes: 0faa0fe6f90e ("nvmet: New NVMe PCI endpoint function target driver") Cc: stable(a)vger.kernel.org Signed-off-by: Damien Le Moal <dlemoal(a)kernel.org> Signed-off-by: Christoph Hellwig <hch(a)lst.de> diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c index 7fab7f3d79b7..d5442991f2fb 100644 --- a/drivers/nvme/target/pci-epf.c +++ b/drivers/nvme/target/pci-epf.c @@ -1344,7 +1344,8 @@ static u16 nvmet_pci_epf_delete_cq(struct nvmet_ctrl *tctrl, u16 cqid) cancel_delayed_work_sync(&cq->work); nvmet_pci_epf_drain_queue(cq); - nvmet_pci_epf_remove_irq_vector(ctrl, cq->vector); + if (test_and_clear_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags)) + nvmet_pci_epf_remove_irq_vector(ctrl, cq->vector); nvmet_pci_epf_mem_unmap(ctrl->nvme_epf, &cq->pci_map); return NVME_SC_SUCCESS;

2 weeks, 6 days

1
0
0 0

FAILED: patch "[PATCH] mm: hugetlb: fix incorrect fallback for subpool" 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 a833a693a490ecff8ba377654c6d4d333718b6b1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051910-sharpness-improvise-0b77@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a833a693a490ecff8ba377654c6d4d333718b6b1 Mon Sep 17 00:00:00 2001 From: Wupeng Ma <mawupeng1(a)huawei.com> Date: Thu, 10 Apr 2025 14:26:33 +0800 Subject: [PATCH] mm: hugetlb: fix incorrect fallback for subpool During our testing with hugetlb subpool enabled, we observe that hstate->resv_huge_pages may underflow into negative values. Root cause analysis reveals a race condition in subpool reservation fallback handling as follow: hugetlb_reserve_pages() /* Attempt subpool reservation */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); /* Global reservation may fail after subpool allocation */ if (hugetlb_acct_memory(h, gbl_reserve) < 0) goto out_put_pages; out_put_pages: /* This incorrectly restores reservation to subpool */ hugepage_subpool_put_pages(spool, chg); When hugetlb_acct_memory() fails after subpool allocation, the current implementation over-commits subpool reservations by returning the full 'chg' value instead of the actual allocated 'gbl_reserve' amount. This discrepancy propagates to global reservations during subsequent releases, eventually causing resv_huge_pages underflow. This problem can be trigger easily with the following steps: 1. reverse hugepage for hugeltb allocation 2. mount hugetlbfs with min_size to enable hugetlb subpool 3. alloc hugepages with two task(make sure the second will fail due to insufficient amount of hugepages) 4. with for a few seconds and repeat step 3 which will make hstate->resv_huge_pages to go below zero. To fix this problem, return corrent amount of pages to subpool during the fallback after hugepage_subpool_get_pages is called. Link: https://lkml.kernel.org/r/20250410062633.3102457-1-mawupeng1@huawei.com Fixes: 1c5ecae3a93f ("hugetlbfs: add minimum size accounting to subpools") Signed-off-by: Wupeng Ma <mawupeng1(a)huawei.com> Tested-by: Joshua Hahn <joshua.hahnjy(a)gmail.com> Reviewed-by: Oscar Salvador <osalvador(a)suse.de> Cc: David Hildenbrand <david(a)redhat.com> Cc: Ma Wupeng <mawupeng1(a)huawei.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6ea1be71aa42..7ae38bfb9096 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3010,7 +3010,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct folio *folio; - long retval, gbl_chg; + long retval, gbl_chg, gbl_reserve; map_chg_state map_chg; int ret, idx; struct hugetlb_cgroup *h_cg = NULL; @@ -3163,8 +3163,16 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), h_cg); out_subpool_put: - if (map_chg) - hugepage_subpool_put_pages(spool, 1); + /* + * put page to subpool iff the quota of subpool's rsv_hpages is used + * during hugepage_subpool_get_pages. + */ + if (map_chg && !gbl_chg) { + gbl_reserve = hugepage_subpool_put_pages(spool, 1); + hugetlb_acct_memory(h, -gbl_reserve); + } + + out_end_reservation: if (map_chg != MAP_CHG_ENFORCED) vma_end_reservation(h, vma, addr); @@ -7239,7 +7247,7 @@ bool hugetlb_reserve_pages(struct inode *inode, struct vm_area_struct *vma, vm_flags_t vm_flags) { - long chg = -1, add = -1; + long chg = -1, add = -1, spool_resv, gbl_resv; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; @@ -7374,8 +7382,16 @@ bool hugetlb_reserve_pages(struct inode *inode, return true; out_put_pages: - /* put back original number of pages, chg */ - (void)hugepage_subpool_put_pages(spool, chg); + spool_resv = chg - gbl_reserve; + if (spool_resv) { + /* put sub pool's reservation back, chg - gbl_reserve */ + gbl_resv = hugepage_subpool_put_pages(spool, spool_resv); + /* + * subpool's reserved pages can not be put back due to race, + * return to hstate. + */ + hugetlb_acct_memory(h, -gbl_resv); + } out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), h_cg);

2 weeks, 6 days

1
0
0 0

FAILED: patch "[PATCH] mm: hugetlb: fix incorrect fallback for subpool" 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 a833a693a490ecff8ba377654c6d4d333718b6b1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051909-bluff-anchovy-3f6f@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a833a693a490ecff8ba377654c6d4d333718b6b1 Mon Sep 17 00:00:00 2001 From: Wupeng Ma <mawupeng1(a)huawei.com> Date: Thu, 10 Apr 2025 14:26:33 +0800 Subject: [PATCH] mm: hugetlb: fix incorrect fallback for subpool During our testing with hugetlb subpool enabled, we observe that hstate->resv_huge_pages may underflow into negative values. Root cause analysis reveals a race condition in subpool reservation fallback handling as follow: hugetlb_reserve_pages() /* Attempt subpool reservation */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); /* Global reservation may fail after subpool allocation */ if (hugetlb_acct_memory(h, gbl_reserve) < 0) goto out_put_pages; out_put_pages: /* This incorrectly restores reservation to subpool */ hugepage_subpool_put_pages(spool, chg); When hugetlb_acct_memory() fails after subpool allocation, the current implementation over-commits subpool reservations by returning the full 'chg' value instead of the actual allocated 'gbl_reserve' amount. This discrepancy propagates to global reservations during subsequent releases, eventually causing resv_huge_pages underflow. This problem can be trigger easily with the following steps: 1. reverse hugepage for hugeltb allocation 2. mount hugetlbfs with min_size to enable hugetlb subpool 3. alloc hugepages with two task(make sure the second will fail due to insufficient amount of hugepages) 4. with for a few seconds and repeat step 3 which will make hstate->resv_huge_pages to go below zero. To fix this problem, return corrent amount of pages to subpool during the fallback after hugepage_subpool_get_pages is called. Link: https://lkml.kernel.org/r/20250410062633.3102457-1-mawupeng1@huawei.com Fixes: 1c5ecae3a93f ("hugetlbfs: add minimum size accounting to subpools") Signed-off-by: Wupeng Ma <mawupeng1(a)huawei.com> Tested-by: Joshua Hahn <joshua.hahnjy(a)gmail.com> Reviewed-by: Oscar Salvador <osalvador(a)suse.de> Cc: David Hildenbrand <david(a)redhat.com> Cc: Ma Wupeng <mawupeng1(a)huawei.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6ea1be71aa42..7ae38bfb9096 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3010,7 +3010,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct folio *folio; - long retval, gbl_chg; + long retval, gbl_chg, gbl_reserve; map_chg_state map_chg; int ret, idx; struct hugetlb_cgroup *h_cg = NULL; @@ -3163,8 +3163,16 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), h_cg); out_subpool_put: - if (map_chg) - hugepage_subpool_put_pages(spool, 1); + /* + * put page to subpool iff the quota of subpool's rsv_hpages is used + * during hugepage_subpool_get_pages. + */ + if (map_chg && !gbl_chg) { + gbl_reserve = hugepage_subpool_put_pages(spool, 1); + hugetlb_acct_memory(h, -gbl_reserve); + } + + out_end_reservation: if (map_chg != MAP_CHG_ENFORCED) vma_end_reservation(h, vma, addr); @@ -7239,7 +7247,7 @@ bool hugetlb_reserve_pages(struct inode *inode, struct vm_area_struct *vma, vm_flags_t vm_flags) { - long chg = -1, add = -1; + long chg = -1, add = -1, spool_resv, gbl_resv; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; @@ -7374,8 +7382,16 @@ bool hugetlb_reserve_pages(struct inode *inode, return true; out_put_pages: - /* put back original number of pages, chg */ - (void)hugepage_subpool_put_pages(spool, chg); + spool_resv = chg - gbl_reserve; + if (spool_resv) { + /* put sub pool's reservation back, chg - gbl_reserve */ + gbl_resv = hugepage_subpool_put_pages(spool, spool_resv); + /* + * subpool's reserved pages can not be put back due to race, + * return to hstate. + */ + hugetlb_acct_memory(h, -gbl_resv); + } out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), h_cg);

2 weeks, 6 days

1
0
0 0

FAILED: patch "[PATCH] mm: hugetlb: fix incorrect fallback for subpool" 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 a833a693a490ecff8ba377654c6d4d333718b6b1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051908-repulsive-crazed-331a@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a833a693a490ecff8ba377654c6d4d333718b6b1 Mon Sep 17 00:00:00 2001 From: Wupeng Ma <mawupeng1(a)huawei.com> Date: Thu, 10 Apr 2025 14:26:33 +0800 Subject: [PATCH] mm: hugetlb: fix incorrect fallback for subpool During our testing with hugetlb subpool enabled, we observe that hstate->resv_huge_pages may underflow into negative values. Root cause analysis reveals a race condition in subpool reservation fallback handling as follow: hugetlb_reserve_pages() /* Attempt subpool reservation */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); /* Global reservation may fail after subpool allocation */ if (hugetlb_acct_memory(h, gbl_reserve) < 0) goto out_put_pages; out_put_pages: /* This incorrectly restores reservation to subpool */ hugepage_subpool_put_pages(spool, chg); When hugetlb_acct_memory() fails after subpool allocation, the current implementation over-commits subpool reservations by returning the full 'chg' value instead of the actual allocated 'gbl_reserve' amount. This discrepancy propagates to global reservations during subsequent releases, eventually causing resv_huge_pages underflow. This problem can be trigger easily with the following steps: 1. reverse hugepage for hugeltb allocation 2. mount hugetlbfs with min_size to enable hugetlb subpool 3. alloc hugepages with two task(make sure the second will fail due to insufficient amount of hugepages) 4. with for a few seconds and repeat step 3 which will make hstate->resv_huge_pages to go below zero. To fix this problem, return corrent amount of pages to subpool during the fallback after hugepage_subpool_get_pages is called. Link: https://lkml.kernel.org/r/20250410062633.3102457-1-mawupeng1@huawei.com Fixes: 1c5ecae3a93f ("hugetlbfs: add minimum size accounting to subpools") Signed-off-by: Wupeng Ma <mawupeng1(a)huawei.com> Tested-by: Joshua Hahn <joshua.hahnjy(a)gmail.com> Reviewed-by: Oscar Salvador <osalvador(a)suse.de> Cc: David Hildenbrand <david(a)redhat.com> Cc: Ma Wupeng <mawupeng1(a)huawei.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6ea1be71aa42..7ae38bfb9096 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3010,7 +3010,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct folio *folio; - long retval, gbl_chg; + long retval, gbl_chg, gbl_reserve; map_chg_state map_chg; int ret, idx; struct hugetlb_cgroup *h_cg = NULL; @@ -3163,8 +3163,16 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), h_cg); out_subpool_put: - if (map_chg) - hugepage_subpool_put_pages(spool, 1); + /* + * put page to subpool iff the quota of subpool's rsv_hpages is used + * during hugepage_subpool_get_pages. + */ + if (map_chg && !gbl_chg) { + gbl_reserve = hugepage_subpool_put_pages(spool, 1); + hugetlb_acct_memory(h, -gbl_reserve); + } + + out_end_reservation: if (map_chg != MAP_CHG_ENFORCED) vma_end_reservation(h, vma, addr); @@ -7239,7 +7247,7 @@ bool hugetlb_reserve_pages(struct inode *inode, struct vm_area_struct *vma, vm_flags_t vm_flags) { - long chg = -1, add = -1; + long chg = -1, add = -1, spool_resv, gbl_resv; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; @@ -7374,8 +7382,16 @@ bool hugetlb_reserve_pages(struct inode *inode, return true; out_put_pages: - /* put back original number of pages, chg */ - (void)hugepage_subpool_put_pages(spool, chg); + spool_resv = chg - gbl_reserve; + if (spool_resv) { + /* put sub pool's reservation back, chg - gbl_reserve */ + gbl_resv = hugepage_subpool_put_pages(spool, spool_resv); + /* + * subpool's reserved pages can not be put back due to race, + * return to hstate. + */ + hugetlb_acct_memory(h, -gbl_resv); + } out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), h_cg);

2 weeks, 6 days

1
0
0 0

FAILED: patch "[PATCH] mm: hugetlb: fix incorrect fallback for subpool" 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 a833a693a490ecff8ba377654c6d4d333718b6b1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051907-laxative-caviar-b847@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a833a693a490ecff8ba377654c6d4d333718b6b1 Mon Sep 17 00:00:00 2001 From: Wupeng Ma <mawupeng1(a)huawei.com> Date: Thu, 10 Apr 2025 14:26:33 +0800 Subject: [PATCH] mm: hugetlb: fix incorrect fallback for subpool During our testing with hugetlb subpool enabled, we observe that hstate->resv_huge_pages may underflow into negative values. Root cause analysis reveals a race condition in subpool reservation fallback handling as follow: hugetlb_reserve_pages() /* Attempt subpool reservation */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); /* Global reservation may fail after subpool allocation */ if (hugetlb_acct_memory(h, gbl_reserve) < 0) goto out_put_pages; out_put_pages: /* This incorrectly restores reservation to subpool */ hugepage_subpool_put_pages(spool, chg); When hugetlb_acct_memory() fails after subpool allocation, the current implementation over-commits subpool reservations by returning the full 'chg' value instead of the actual allocated 'gbl_reserve' amount. This discrepancy propagates to global reservations during subsequent releases, eventually causing resv_huge_pages underflow. This problem can be trigger easily with the following steps: 1. reverse hugepage for hugeltb allocation 2. mount hugetlbfs with min_size to enable hugetlb subpool 3. alloc hugepages with two task(make sure the second will fail due to insufficient amount of hugepages) 4. with for a few seconds and repeat step 3 which will make hstate->resv_huge_pages to go below zero. To fix this problem, return corrent amount of pages to subpool during the fallback after hugepage_subpool_get_pages is called. Link: https://lkml.kernel.org/r/20250410062633.3102457-1-mawupeng1@huawei.com Fixes: 1c5ecae3a93f ("hugetlbfs: add minimum size accounting to subpools") Signed-off-by: Wupeng Ma <mawupeng1(a)huawei.com> Tested-by: Joshua Hahn <joshua.hahnjy(a)gmail.com> Reviewed-by: Oscar Salvador <osalvador(a)suse.de> Cc: David Hildenbrand <david(a)redhat.com> Cc: Ma Wupeng <mawupeng1(a)huawei.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6ea1be71aa42..7ae38bfb9096 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3010,7 +3010,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct folio *folio; - long retval, gbl_chg; + long retval, gbl_chg, gbl_reserve; map_chg_state map_chg; int ret, idx; struct hugetlb_cgroup *h_cg = NULL; @@ -3163,8 +3163,16 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), h_cg); out_subpool_put: - if (map_chg) - hugepage_subpool_put_pages(spool, 1); + /* + * put page to subpool iff the quota of subpool's rsv_hpages is used + * during hugepage_subpool_get_pages. + */ + if (map_chg && !gbl_chg) { + gbl_reserve = hugepage_subpool_put_pages(spool, 1); + hugetlb_acct_memory(h, -gbl_reserve); + } + + out_end_reservation: if (map_chg != MAP_CHG_ENFORCED) vma_end_reservation(h, vma, addr); @@ -7239,7 +7247,7 @@ bool hugetlb_reserve_pages(struct inode *inode, struct vm_area_struct *vma, vm_flags_t vm_flags) { - long chg = -1, add = -1; + long chg = -1, add = -1, spool_resv, gbl_resv; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; @@ -7374,8 +7382,16 @@ bool hugetlb_reserve_pages(struct inode *inode, return true; out_put_pages: - /* put back original number of pages, chg */ - (void)hugepage_subpool_put_pages(spool, chg); + spool_resv = chg - gbl_reserve; + if (spool_resv) { + /* put sub pool's reservation back, chg - gbl_reserve */ + gbl_resv = hugepage_subpool_put_pages(spool, spool_resv); + /* + * subpool's reserved pages can not be put back due to race, + * return to hstate. + */ + hugetlb_acct_memory(h, -gbl_resv); + } out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), h_cg);

2 weeks, 6 days

1
0
0 0

FAILED: patch "[PATCH] mm: hugetlb: fix incorrect fallback for subpool" 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 a833a693a490ecff8ba377654c6d4d333718b6b1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051905-getup-hatchery-57be@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a833a693a490ecff8ba377654c6d4d333718b6b1 Mon Sep 17 00:00:00 2001 From: Wupeng Ma <mawupeng1(a)huawei.com> Date: Thu, 10 Apr 2025 14:26:33 +0800 Subject: [PATCH] mm: hugetlb: fix incorrect fallback for subpool During our testing with hugetlb subpool enabled, we observe that hstate->resv_huge_pages may underflow into negative values. Root cause analysis reveals a race condition in subpool reservation fallback handling as follow: hugetlb_reserve_pages() /* Attempt subpool reservation */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); /* Global reservation may fail after subpool allocation */ if (hugetlb_acct_memory(h, gbl_reserve) < 0) goto out_put_pages; out_put_pages: /* This incorrectly restores reservation to subpool */ hugepage_subpool_put_pages(spool, chg); When hugetlb_acct_memory() fails after subpool allocation, the current implementation over-commits subpool reservations by returning the full 'chg' value instead of the actual allocated 'gbl_reserve' amount. This discrepancy propagates to global reservations during subsequent releases, eventually causing resv_huge_pages underflow. This problem can be trigger easily with the following steps: 1. reverse hugepage for hugeltb allocation 2. mount hugetlbfs with min_size to enable hugetlb subpool 3. alloc hugepages with two task(make sure the second will fail due to insufficient amount of hugepages) 4. with for a few seconds and repeat step 3 which will make hstate->resv_huge_pages to go below zero. To fix this problem, return corrent amount of pages to subpool during the fallback after hugepage_subpool_get_pages is called. Link: https://lkml.kernel.org/r/20250410062633.3102457-1-mawupeng1@huawei.com Fixes: 1c5ecae3a93f ("hugetlbfs: add minimum size accounting to subpools") Signed-off-by: Wupeng Ma <mawupeng1(a)huawei.com> Tested-by: Joshua Hahn <joshua.hahnjy(a)gmail.com> Reviewed-by: Oscar Salvador <osalvador(a)suse.de> Cc: David Hildenbrand <david(a)redhat.com> Cc: Ma Wupeng <mawupeng1(a)huawei.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6ea1be71aa42..7ae38bfb9096 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3010,7 +3010,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct folio *folio; - long retval, gbl_chg; + long retval, gbl_chg, gbl_reserve; map_chg_state map_chg; int ret, idx; struct hugetlb_cgroup *h_cg = NULL; @@ -3163,8 +3163,16 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), h_cg); out_subpool_put: - if (map_chg) - hugepage_subpool_put_pages(spool, 1); + /* + * put page to subpool iff the quota of subpool's rsv_hpages is used + * during hugepage_subpool_get_pages. + */ + if (map_chg && !gbl_chg) { + gbl_reserve = hugepage_subpool_put_pages(spool, 1); + hugetlb_acct_memory(h, -gbl_reserve); + } + + out_end_reservation: if (map_chg != MAP_CHG_ENFORCED) vma_end_reservation(h, vma, addr); @@ -7239,7 +7247,7 @@ bool hugetlb_reserve_pages(struct inode *inode, struct vm_area_struct *vma, vm_flags_t vm_flags) { - long chg = -1, add = -1; + long chg = -1, add = -1, spool_resv, gbl_resv; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; @@ -7374,8 +7382,16 @@ bool hugetlb_reserve_pages(struct inode *inode, return true; out_put_pages: - /* put back original number of pages, chg */ - (void)hugepage_subpool_put_pages(spool, chg); + spool_resv = chg - gbl_reserve; + if (spool_resv) { + /* put sub pool's reservation back, chg - gbl_reserve */ + gbl_resv = hugepage_subpool_put_pages(spool, spool_resv); + /* + * subpool's reserved pages can not be put back due to race, + * return to hstate. + */ + hugetlb_acct_memory(h, -gbl_resv); + } out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), h_cg);

2 weeks, 6 days

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror May 2025