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

FAILED: patch "[PATCH] mm: huge_memory: add vma_thp_disabled() and" 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 963756aac1f011d904ddd9548ae82286d3a91f96 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101842-flatness-osmosis-b08e@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 963756aac1f011d904ddd9548ae82286d3a91f96 Mon Sep 17 00:00:00 2001 From: Kefeng Wang <wangkefeng.wang(a)huawei.com> Date: Fri, 11 Oct 2024 12:24:44 +0200 Subject: [PATCH] mm: huge_memory: add vma_thp_disabled() and thp_disabled_by_hw() Patch series "mm: don't install PMD mappings when THPs are disabled by the hw/process/vma". During testing, it was found that we can get PMD mappings in processes where THP (and more precisely, PMD mappings) are supposed to be disabled. While it works as expected for anon+shmem, the pagecache is the problematic bit. For s390 KVM this currently means that a VM backed by a file located on filesystem with large folio support can crash when KVM tries accessing the problematic page, because the readahead logic might decide to use a PMD-sized THP and faulting it into the page tables will install a PMD mapping, something that s390 KVM cannot tolerate. This might also be a problem with HW that does not support PMD mappings, but I did not try reproducing it. Fix it by respecting the ways to disable THPs when deciding whether we can install a PMD mapping. khugepaged should already be taking care of not collapsing if THPs are effectively disabled for the hw/process/vma. This patch (of 2): Add vma_thp_disabled() and thp_disabled_by_hw() helpers to be shared by shmem_allowable_huge_orders() and __thp_vma_allowable_orders(). [david(a)redhat.com: rename to vma_thp_disabled(), split out thp_disabled_by_hw() ] Link: https://lkml.kernel.org/r/20241011102445.934409-2-david@redhat.com Fixes: 793917d997df ("mm/readahead: Add large folio readahead") Signed-off-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: David Hildenbrand <david(a)redhat.com> Reported-by: Leo Fu <bfu(a)redhat.com> Tested-by: Thomas Huth <thuth(a)redhat.com> Reviewed-by: Ryan Roberts <ryan.roberts(a)arm.com> Cc: Boqiao Fu <bfu(a)redhat.com> Cc: Christian Borntraeger <borntraeger(a)linux.ibm.com> Cc: Claudio Imbrenda <imbrenda(a)linux.ibm.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Janosch Frank <frankja(a)linux.ibm.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 67d0ab3c3bba..ef5b80e48599 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -322,6 +322,24 @@ struct thpsize { (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) +static inline bool vma_thp_disabled(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + /* + * Explicitly disabled through madvise or prctl, or some + * architectures may disable THP for some mappings, for + * example, s390 kvm. + */ + return (vm_flags & VM_NOHUGEPAGE) || + test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags); +} + +static inline bool thp_disabled_by_hw(void) +{ + /* If the hardware/firmware marked hugepage support disabled. */ + return transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED); +} + unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 87b49ecc7b1e..2fb328880b50 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -109,18 +109,7 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, if (!vma->vm_mm) /* vdso */ return 0; - /* - * Explicitly disabled through madvise or prctl, or some - * architectures may disable THP for some mappings, for - * example, s390 kvm. - * */ - if ((vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) - return 0; - /* - * If the hardware/firmware marked hugepage support disabled. - */ - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED)) + if (thp_disabled_by_hw() || vma_thp_disabled(vma, vm_flags)) return 0; /* khugepaged doesn't collapse DAX vma, but page fault is fine. */ diff --git a/mm/shmem.c b/mm/shmem.c index 4f11b5506363..c5adb987b23c 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1664,12 +1664,7 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, loff_t i_size; int order; - if (vma && ((vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))) - return 0; - - /* If the hardware/firmware marked hugepage support disabled. */ - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED)) + if (thp_disabled_by_hw() || (vma && vma_thp_disabled(vma, vm_flags))) return 0; global_huge = shmem_huge_global_enabled(inode, index, write_end,

18 hours, 19 minutes

1
0
0 0

FAILED: patch "[PATCH] mm: huge_memory: add vma_thp_disabled() and" failed to apply to 6.11-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.11-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-6.11.y git checkout FETCH_HEAD git cherry-pick -x 963756aac1f011d904ddd9548ae82286d3a91f96 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101835-eloquent-could-27ce@gregkh' --subject-prefix 'PATCH 6.11.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 963756aac1f011d904ddd9548ae82286d3a91f96 Mon Sep 17 00:00:00 2001 From: Kefeng Wang <wangkefeng.wang(a)huawei.com> Date: Fri, 11 Oct 2024 12:24:44 +0200 Subject: [PATCH] mm: huge_memory: add vma_thp_disabled() and thp_disabled_by_hw() Patch series "mm: don't install PMD mappings when THPs are disabled by the hw/process/vma". During testing, it was found that we can get PMD mappings in processes where THP (and more precisely, PMD mappings) are supposed to be disabled. While it works as expected for anon+shmem, the pagecache is the problematic bit. For s390 KVM this currently means that a VM backed by a file located on filesystem with large folio support can crash when KVM tries accessing the problematic page, because the readahead logic might decide to use a PMD-sized THP and faulting it into the page tables will install a PMD mapping, something that s390 KVM cannot tolerate. This might also be a problem with HW that does not support PMD mappings, but I did not try reproducing it. Fix it by respecting the ways to disable THPs when deciding whether we can install a PMD mapping. khugepaged should already be taking care of not collapsing if THPs are effectively disabled for the hw/process/vma. This patch (of 2): Add vma_thp_disabled() and thp_disabled_by_hw() helpers to be shared by shmem_allowable_huge_orders() and __thp_vma_allowable_orders(). [david(a)redhat.com: rename to vma_thp_disabled(), split out thp_disabled_by_hw() ] Link: https://lkml.kernel.org/r/20241011102445.934409-2-david@redhat.com Fixes: 793917d997df ("mm/readahead: Add large folio readahead") Signed-off-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: David Hildenbrand <david(a)redhat.com> Reported-by: Leo Fu <bfu(a)redhat.com> Tested-by: Thomas Huth <thuth(a)redhat.com> Reviewed-by: Ryan Roberts <ryan.roberts(a)arm.com> Cc: Boqiao Fu <bfu(a)redhat.com> Cc: Christian Borntraeger <borntraeger(a)linux.ibm.com> Cc: Claudio Imbrenda <imbrenda(a)linux.ibm.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Janosch Frank <frankja(a)linux.ibm.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 67d0ab3c3bba..ef5b80e48599 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -322,6 +322,24 @@ struct thpsize { (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) +static inline bool vma_thp_disabled(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + /* + * Explicitly disabled through madvise or prctl, or some + * architectures may disable THP for some mappings, for + * example, s390 kvm. + */ + return (vm_flags & VM_NOHUGEPAGE) || + test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags); +} + +static inline bool thp_disabled_by_hw(void) +{ + /* If the hardware/firmware marked hugepage support disabled. */ + return transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED); +} + unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 87b49ecc7b1e..2fb328880b50 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -109,18 +109,7 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, if (!vma->vm_mm) /* vdso */ return 0; - /* - * Explicitly disabled through madvise or prctl, or some - * architectures may disable THP for some mappings, for - * example, s390 kvm. - * */ - if ((vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) - return 0; - /* - * If the hardware/firmware marked hugepage support disabled. - */ - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED)) + if (thp_disabled_by_hw() || vma_thp_disabled(vma, vm_flags)) return 0; /* khugepaged doesn't collapse DAX vma, but page fault is fine. */ diff --git a/mm/shmem.c b/mm/shmem.c index 4f11b5506363..c5adb987b23c 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1664,12 +1664,7 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, loff_t i_size; int order; - if (vma && ((vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))) - return 0; - - /* If the hardware/firmware marked hugepage support disabled. */ - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED)) + if (thp_disabled_by_hw() || (vma && vma_thp_disabled(vma, vm_flags))) return 0; global_huge = shmem_huge_global_enabled(inode, index, write_end,

18 hours, 19 minutes

1
0
0 0

FAILED: patch "[PATCH] mm: don't install PMD mappings when THPs are disabled by the" 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 2b0f922323ccfa76219bcaacd35cd50aeaa13592 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101842-empty-espresso-c8a3@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 2b0f922323ccfa76219bcaacd35cd50aeaa13592 Mon Sep 17 00:00:00 2001 From: David Hildenbrand <david(a)redhat.com> Date: Fri, 11 Oct 2024 12:24:45 +0200 Subject: [PATCH] mm: don't install PMD mappings when THPs are disabled by the hw/process/vma We (or rather, readahead logic :) ) might be allocating a THP in the pagecache and then try mapping it into a process that explicitly disabled THP: we might end up installing PMD mappings. This is a problem for s390x KVM, which explicitly remaps all PMD-mapped THPs to be PTE-mapped in s390_enable_sie()->thp_split_mm(), before starting the VM. For example, starting a VM backed on a file system with large folios supported makes the VM crash when the VM tries accessing such a mapping using KVM. Is it also a problem when the HW disabled THP using TRANSPARENT_HUGEPAGE_UNSUPPORTED? At least on x86 this would be the case without X86_FEATURE_PSE. In the future, we might be able to do better on s390x and only disallow PMD mappings -- what s390x and likely TRANSPARENT_HUGEPAGE_UNSUPPORTED really wants. For now, fix it by essentially performing the same check as would be done in __thp_vma_allowable_orders() or in shmem code, where this works as expected, and disallow PMD mappings, making us fallback to PTE mappings. Link: https://lkml.kernel.org/r/20241011102445.934409-3-david@redhat.com Fixes: 793917d997df ("mm/readahead: Add large folio readahead") Signed-off-by: David Hildenbrand <david(a)redhat.com> Reported-by: Leo Fu <bfu(a)redhat.com> Tested-by: Thomas Huth <thuth(a)redhat.com> Cc: Thomas Huth <thuth(a)redhat.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Ryan Roberts <ryan.roberts(a)arm.com> Cc: Christian Borntraeger <borntraeger(a)linux.ibm.com> Cc: Janosch Frank <frankja(a)linux.ibm.com> Cc: Claudio Imbrenda <imbrenda(a)linux.ibm.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/memory.c b/mm/memory.c index c0869a962ddd..30feedabc932 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4920,6 +4920,15 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) pmd_t entry; vm_fault_t ret = VM_FAULT_FALLBACK; + /* + * It is too late to allocate a small folio, we already have a large + * folio in the pagecache: especially s390 KVM cannot tolerate any + * PMD mappings, but PTE-mapped THP are fine. So let's simply refuse any + * PMD mappings if THPs are disabled. + */ + if (thp_disabled_by_hw() || vma_thp_disabled(vma, vma->vm_flags)) + return ret; + if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return ret;

18 hours, 20 minutes

1
0
0 0

FAILED: patch "[PATCH] mm: don't install PMD mappings when THPs are disabled by the" 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 2b0f922323ccfa76219bcaacd35cd50aeaa13592 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101837-mammogram-headsman-2dec@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 2b0f922323ccfa76219bcaacd35cd50aeaa13592 Mon Sep 17 00:00:00 2001 From: David Hildenbrand <david(a)redhat.com> Date: Fri, 11 Oct 2024 12:24:45 +0200 Subject: [PATCH] mm: don't install PMD mappings when THPs are disabled by the hw/process/vma We (or rather, readahead logic :) ) might be allocating a THP in the pagecache and then try mapping it into a process that explicitly disabled THP: we might end up installing PMD mappings. This is a problem for s390x KVM, which explicitly remaps all PMD-mapped THPs to be PTE-mapped in s390_enable_sie()->thp_split_mm(), before starting the VM. For example, starting a VM backed on a file system with large folios supported makes the VM crash when the VM tries accessing such a mapping using KVM. Is it also a problem when the HW disabled THP using TRANSPARENT_HUGEPAGE_UNSUPPORTED? At least on x86 this would be the case without X86_FEATURE_PSE. In the future, we might be able to do better on s390x and only disallow PMD mappings -- what s390x and likely TRANSPARENT_HUGEPAGE_UNSUPPORTED really wants. For now, fix it by essentially performing the same check as would be done in __thp_vma_allowable_orders() or in shmem code, where this works as expected, and disallow PMD mappings, making us fallback to PTE mappings. Link: https://lkml.kernel.org/r/20241011102445.934409-3-david@redhat.com Fixes: 793917d997df ("mm/readahead: Add large folio readahead") Signed-off-by: David Hildenbrand <david(a)redhat.com> Reported-by: Leo Fu <bfu(a)redhat.com> Tested-by: Thomas Huth <thuth(a)redhat.com> Cc: Thomas Huth <thuth(a)redhat.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Ryan Roberts <ryan.roberts(a)arm.com> Cc: Christian Borntraeger <borntraeger(a)linux.ibm.com> Cc: Janosch Frank <frankja(a)linux.ibm.com> Cc: Claudio Imbrenda <imbrenda(a)linux.ibm.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/memory.c b/mm/memory.c index c0869a962ddd..30feedabc932 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4920,6 +4920,15 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) pmd_t entry; vm_fault_t ret = VM_FAULT_FALLBACK; + /* + * It is too late to allocate a small folio, we already have a large + * folio in the pagecache: especially s390 KVM cannot tolerate any + * PMD mappings, but PTE-mapped THP are fine. So let's simply refuse any + * PMD mappings if THPs are disabled. + */ + if (thp_disabled_by_hw() || vma_thp_disabled(vma, vma->vm_flags)) + return ret; + if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return ret;

18 hours, 20 minutes

1
0
0 0

FAILED: patch "[PATCH] mm/swapfile: skip HugeTLB pages for unuse_vma" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x 7528c4fb1237512ee18049f852f014eba80bbe8d # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101858-rewire-vocation-c981@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 7528c4fb1237512ee18049f852f014eba80bbe8d Mon Sep 17 00:00:00 2001 From: Liu Shixin <liushixin2(a)huawei.com> Date: Tue, 15 Oct 2024 09:45:21 +0800 Subject: [PATCH] mm/swapfile: skip HugeTLB pages for unuse_vma I got a bad pud error and lost a 1GB HugeTLB when calling swapoff. The problem can be reproduced by the following steps: 1. Allocate an anonymous 1GB HugeTLB and some other anonymous memory. 2. Swapout the above anonymous memory. 3. run swapoff and we will get a bad pud error in kernel message: mm/pgtable-generic.c:42: bad pud 00000000743d215d(84000001400000e7) We can tell that pud_clear_bad is called by pud_none_or_clear_bad in unuse_pud_range() by ftrace. And therefore the HugeTLB pages will never be freed because we lost it from page table. We can skip HugeTLB pages for unuse_vma to fix it. Link: https://lkml.kernel.org/r/20241015014521.570237-1-liushixin2@huawei.com Fixes: 0fe6e20b9c4c ("hugetlb, rmap: add reverse mapping for hugepage") Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Acked-by: Muchun Song <muchun.song(a)linux.dev> Cc: Naoya Horiguchi <nao.horiguchi(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/swapfile.c b/mm/swapfile.c index eb782fcd5627..b0915f3fab31 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2313,7 +2313,7 @@ static int unuse_mm(struct mm_struct *mm, unsigned int type) mmap_read_lock(mm); for_each_vma(vmi, vma) { - if (vma->anon_vma) { + if (vma->anon_vma && !is_vm_hugetlb_page(vma)) { ret = unuse_vma(vma, type); if (ret) break;

18 hours, 24 minutes

1
0
0 0

FAILED: patch "[PATCH] mm: khugepaged: fix the arguments order in" 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 37f0b47c5143c2957909ced44fc09ffb118c99f7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101803-cage-smokiness-cb8b@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 37f0b47c5143c2957909ced44fc09ffb118c99f7 Mon Sep 17 00:00:00 2001 From: Yang Shi <yang(a)os.amperecomputing.com> Date: Fri, 11 Oct 2024 18:17:02 -0700 Subject: [PATCH] mm: khugepaged: fix the arguments order in khugepaged_collapse_file trace point The "addr" and "is_shmem" arguments have different order in TP_PROTO and TP_ARGS. This resulted in the incorrect trace result: text-hugepage-644429 [276] 392092.878683: mm_khugepaged_collapse_file: mm=0xffff20025d52c440, hpage_pfn=0x200678c00, index=512, addr=1, is_shmem=0, filename=text-hugepage, nr=512, result=failed The value of "addr" is wrong because it was treated as bool value, the type of is_shmem. Fix the order in TP_PROTO to keep "addr" is before "is_shmem" since the original patch review suggested this order to achieve best packing. And use "lx" for "addr" instead of "ld" in TP_printk because address is typically shown in hex. After the fix, the trace result looks correct: text-hugepage-7291 [004] 128.627251: mm_khugepaged_collapse_file: mm=0xffff0001328f9500, hpage_pfn=0x20016ea00, index=512, addr=0x400000, is_shmem=0, filename=text-hugepage, nr=512, result=failed Link: https://lkml.kernel.org/r/20241012011702.1084846-1-yang@os.amperecomputing.… Fixes: 4c9473e87e75 ("mm/khugepaged: add tracepoint to collapse_file()") Signed-off-by: Yang Shi <yang(a)os.amperecomputing.com> Cc: Gautam Menghani <gautammenghani201(a)gmail.com> Cc: Steven Rostedt (Google) <rostedt(a)goodmis.org> Cc: <stable(a)vger.kernel.org> [6.2+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index b5f5369b6300..9d5c00b0285c 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -208,7 +208,7 @@ TRACE_EVENT(mm_khugepaged_scan_file, TRACE_EVENT(mm_khugepaged_collapse_file, TP_PROTO(struct mm_struct *mm, struct folio *new_folio, pgoff_t index, - bool is_shmem, unsigned long addr, struct file *file, + unsigned long addr, bool is_shmem, struct file *file, int nr, int result), TP_ARGS(mm, new_folio, index, addr, is_shmem, file, nr, result), TP_STRUCT__entry( @@ -233,7 +233,7 @@ TRACE_EVENT(mm_khugepaged_collapse_file, __entry->result = result; ), - TP_printk("mm=%p, hpage_pfn=0x%lx, index=%ld, addr=%ld, is_shmem=%d, filename=%s, nr=%d, result=%s", + TP_printk("mm=%p, hpage_pfn=0x%lx, index=%ld, addr=%lx, is_shmem=%d, filename=%s, nr=%d, result=%s", __entry->mm, __entry->hpfn, __entry->index, diff --git a/mm/khugepaged.c b/mm/khugepaged.c index f9c39898eaff..a420eff92011 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2227,7 +2227,7 @@ rollback: folio_put(new_folio); out: VM_BUG_ON(!list_empty(&pagelist)); - trace_mm_khugepaged_collapse_file(mm, new_folio, index, is_shmem, addr, file, HPAGE_PMD_NR, result); + trace_mm_khugepaged_collapse_file(mm, new_folio, index, addr, is_shmem, file, HPAGE_PMD_NR, result); return result; }

18 hours, 26 minutes

1
0
0 0

FAILED: patch "[PATCH] nilfs2: propagate directory read errors from" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x 08cfa12adf888db98879dbd735bc741360a34168 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101855-landowner-harness-1529@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 08cfa12adf888db98879dbd735bc741360a34168 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Date: Fri, 4 Oct 2024 12:35:31 +0900 Subject: [PATCH] nilfs2: propagate directory read errors from nilfs_find_entry() Syzbot reported that a task hang occurs in vcs_open() during a fuzzing test for nilfs2. The root cause of this problem is that in nilfs_find_entry(), which searches for directory entries, ignores errors when loading a directory page/folio via nilfs_get_folio() fails. If the filesystem images is corrupted, and the i_size of the directory inode is large, and the directory page/folio is successfully read but fails the sanity check, for example when it is zero-filled, nilfs_check_folio() may continue to spit out error messages in bursts. Fix this issue by propagating the error to the callers when loading a page/folio fails in nilfs_find_entry(). The current interface of nilfs_find_entry() and its callers is outdated and cannot propagate error codes such as -EIO and -ENOMEM returned via nilfs_find_entry(), so fix it together. Link: https://lkml.kernel.org/r/20241004033640.6841-1-konishi.ryusuke@gmail.com Fixes: 2ba466d74ed7 ("nilfs2: directory entry operations") Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: Lizhi Xu <lizhi.xu(a)windriver.com> Closes: https://lkml.kernel.org/r/20240927013806.3577931-1-lizhi.xu@windriver.com Reported-by: syzbot+8a192e8d090fa9a31135(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=8a192e8d090fa9a31135 Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index fe5b1a30c509..a8602729586a 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -289,7 +289,7 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx) * The folio is mapped and unlocked. When the caller is finished with * the entry, it should call folio_release_kmap(). * - * On failure, returns NULL and the caller should ignore foliop. + * On failure, returns an error pointer and the caller should ignore foliop. */ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, const struct qstr *qstr, struct folio **foliop) @@ -312,22 +312,24 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, do { char *kaddr = nilfs_get_folio(dir, n, foliop); - if (!IS_ERR(kaddr)) { - de = (struct nilfs_dir_entry *)kaddr; - kaddr += nilfs_last_byte(dir, n) - reclen; - while ((char *) de <= kaddr) { - if (de->rec_len == 0) { - nilfs_error(dir->i_sb, - "zero-length directory entry"); - folio_release_kmap(*foliop, kaddr); - goto out; - } - if (nilfs_match(namelen, name, de)) - goto found; - de = nilfs_next_entry(de); + if (IS_ERR(kaddr)) + return ERR_CAST(kaddr); + + de = (struct nilfs_dir_entry *)kaddr; + kaddr += nilfs_last_byte(dir, n) - reclen; + while ((char *)de <= kaddr) { + if (de->rec_len == 0) { + nilfs_error(dir->i_sb, + "zero-length directory entry"); + folio_release_kmap(*foliop, kaddr); + goto out; } - folio_release_kmap(*foliop, kaddr); + if (nilfs_match(namelen, name, de)) + goto found; + de = nilfs_next_entry(de); } + folio_release_kmap(*foliop, kaddr); + if (++n >= npages) n = 0; /* next folio is past the blocks we've got */ @@ -340,7 +342,7 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, } } while (n != start); out: - return NULL; + return ERR_PTR(-ENOENT); found: ei->i_dir_start_lookup = n; @@ -384,18 +386,18 @@ fail: return NULL; } -ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr) +int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino) { - ino_t res = 0; struct nilfs_dir_entry *de; struct folio *folio; de = nilfs_find_entry(dir, qstr, &folio); - if (de) { - res = le64_to_cpu(de->inode); - folio_release_kmap(folio, de); - } - return res; + if (IS_ERR(de)) + return PTR_ERR(de); + + *ino = le64_to_cpu(de->inode); + folio_release_kmap(folio, de); + return 0; } void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de, diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index c950139db6ef..4905063790c5 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -55,12 +55,20 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode; ino_t ino; + int res; if (dentry->d_name.len > NILFS_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); - ino = nilfs_inode_by_name(dir, &dentry->d_name); - inode = ino ? nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino) : NULL; + res = nilfs_inode_by_name(dir, &dentry->d_name, &ino); + if (res) { + if (res != -ENOENT) + return ERR_PTR(res); + inode = NULL; + } else { + inode = nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino); + } + return d_splice_alias(inode, dentry); } @@ -263,10 +271,11 @@ static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry) struct folio *folio; int err; - err = -ENOENT; de = nilfs_find_entry(dir, &dentry->d_name, &folio); - if (!de) + if (IS_ERR(de)) { + err = PTR_ERR(de); goto out; + } inode = d_inode(dentry); err = -EIO; @@ -362,10 +371,11 @@ static int nilfs_rename(struct mnt_idmap *idmap, if (unlikely(err)) return err; - err = -ENOENT; old_de = nilfs_find_entry(old_dir, &old_dentry->d_name, &old_folio); - if (!old_de) + if (IS_ERR(old_de)) { + err = PTR_ERR(old_de); goto out; + } if (S_ISDIR(old_inode->i_mode)) { err = -EIO; @@ -382,10 +392,12 @@ static int nilfs_rename(struct mnt_idmap *idmap, if (dir_de && !nilfs_empty_dir(new_inode)) goto out_dir; - err = -ENOENT; - new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, &new_folio); - if (!new_de) + new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, + &new_folio); + if (IS_ERR(new_de)) { + err = PTR_ERR(new_de); goto out_dir; + } nilfs_set_link(new_dir, new_de, new_folio, old_inode); folio_release_kmap(new_folio, new_de); nilfs_mark_inode_dirty(new_dir); @@ -440,12 +452,13 @@ out: */ static struct dentry *nilfs_get_parent(struct dentry *child) { - unsigned long ino; + ino_t ino; + int res; struct nilfs_root *root; - ino = nilfs_inode_by_name(d_inode(child), &dotdot_name); - if (!ino) - return ERR_PTR(-ENOENT); + res = nilfs_inode_by_name(d_inode(child), &dotdot_name, &ino); + if (res) + return ERR_PTR(res); root = NILFS_I(d_inode(child))->i_root; diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index fb1c4c5bae7c..45d03826eaf1 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -254,7 +254,7 @@ static inline __u32 nilfs_mask_flags(umode_t mode, __u32 flags) /* dir.c */ int nilfs_add_link(struct dentry *, struct inode *); -ino_t nilfs_inode_by_name(struct inode *, const struct qstr *); +int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino); int nilfs_make_empty(struct inode *, struct inode *); struct nilfs_dir_entry *nilfs_find_entry(struct inode *, const struct qstr *, struct folio **);

18 hours, 29 minutes

1
0
0 0

FAILED: patch "[PATCH] nilfs2: propagate directory read errors from" 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 08cfa12adf888db98879dbd735bc741360a34168 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101854-exterior-cufflink-ccf4@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 08cfa12adf888db98879dbd735bc741360a34168 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Date: Fri, 4 Oct 2024 12:35:31 +0900 Subject: [PATCH] nilfs2: propagate directory read errors from nilfs_find_entry() Syzbot reported that a task hang occurs in vcs_open() during a fuzzing test for nilfs2. The root cause of this problem is that in nilfs_find_entry(), which searches for directory entries, ignores errors when loading a directory page/folio via nilfs_get_folio() fails. If the filesystem images is corrupted, and the i_size of the directory inode is large, and the directory page/folio is successfully read but fails the sanity check, for example when it is zero-filled, nilfs_check_folio() may continue to spit out error messages in bursts. Fix this issue by propagating the error to the callers when loading a page/folio fails in nilfs_find_entry(). The current interface of nilfs_find_entry() and its callers is outdated and cannot propagate error codes such as -EIO and -ENOMEM returned via nilfs_find_entry(), so fix it together. Link: https://lkml.kernel.org/r/20241004033640.6841-1-konishi.ryusuke@gmail.com Fixes: 2ba466d74ed7 ("nilfs2: directory entry operations") Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: Lizhi Xu <lizhi.xu(a)windriver.com> Closes: https://lkml.kernel.org/r/20240927013806.3577931-1-lizhi.xu@windriver.com Reported-by: syzbot+8a192e8d090fa9a31135(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=8a192e8d090fa9a31135 Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index fe5b1a30c509..a8602729586a 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -289,7 +289,7 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx) * The folio is mapped and unlocked. When the caller is finished with * the entry, it should call folio_release_kmap(). * - * On failure, returns NULL and the caller should ignore foliop. + * On failure, returns an error pointer and the caller should ignore foliop. */ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, const struct qstr *qstr, struct folio **foliop) @@ -312,22 +312,24 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, do { char *kaddr = nilfs_get_folio(dir, n, foliop); - if (!IS_ERR(kaddr)) { - de = (struct nilfs_dir_entry *)kaddr; - kaddr += nilfs_last_byte(dir, n) - reclen; - while ((char *) de <= kaddr) { - if (de->rec_len == 0) { - nilfs_error(dir->i_sb, - "zero-length directory entry"); - folio_release_kmap(*foliop, kaddr); - goto out; - } - if (nilfs_match(namelen, name, de)) - goto found; - de = nilfs_next_entry(de); + if (IS_ERR(kaddr)) + return ERR_CAST(kaddr); + + de = (struct nilfs_dir_entry *)kaddr; + kaddr += nilfs_last_byte(dir, n) - reclen; + while ((char *)de <= kaddr) { + if (de->rec_len == 0) { + nilfs_error(dir->i_sb, + "zero-length directory entry"); + folio_release_kmap(*foliop, kaddr); + goto out; } - folio_release_kmap(*foliop, kaddr); + if (nilfs_match(namelen, name, de)) + goto found; + de = nilfs_next_entry(de); } + folio_release_kmap(*foliop, kaddr); + if (++n >= npages) n = 0; /* next folio is past the blocks we've got */ @@ -340,7 +342,7 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, } } while (n != start); out: - return NULL; + return ERR_PTR(-ENOENT); found: ei->i_dir_start_lookup = n; @@ -384,18 +386,18 @@ fail: return NULL; } -ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr) +int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino) { - ino_t res = 0; struct nilfs_dir_entry *de; struct folio *folio; de = nilfs_find_entry(dir, qstr, &folio); - if (de) { - res = le64_to_cpu(de->inode); - folio_release_kmap(folio, de); - } - return res; + if (IS_ERR(de)) + return PTR_ERR(de); + + *ino = le64_to_cpu(de->inode); + folio_release_kmap(folio, de); + return 0; } void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de, diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index c950139db6ef..4905063790c5 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -55,12 +55,20 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode; ino_t ino; + int res; if (dentry->d_name.len > NILFS_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); - ino = nilfs_inode_by_name(dir, &dentry->d_name); - inode = ino ? nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino) : NULL; + res = nilfs_inode_by_name(dir, &dentry->d_name, &ino); + if (res) { + if (res != -ENOENT) + return ERR_PTR(res); + inode = NULL; + } else { + inode = nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino); + } + return d_splice_alias(inode, dentry); } @@ -263,10 +271,11 @@ static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry) struct folio *folio; int err; - err = -ENOENT; de = nilfs_find_entry(dir, &dentry->d_name, &folio); - if (!de) + if (IS_ERR(de)) { + err = PTR_ERR(de); goto out; + } inode = d_inode(dentry); err = -EIO; @@ -362,10 +371,11 @@ static int nilfs_rename(struct mnt_idmap *idmap, if (unlikely(err)) return err; - err = -ENOENT; old_de = nilfs_find_entry(old_dir, &old_dentry->d_name, &old_folio); - if (!old_de) + if (IS_ERR(old_de)) { + err = PTR_ERR(old_de); goto out; + } if (S_ISDIR(old_inode->i_mode)) { err = -EIO; @@ -382,10 +392,12 @@ static int nilfs_rename(struct mnt_idmap *idmap, if (dir_de && !nilfs_empty_dir(new_inode)) goto out_dir; - err = -ENOENT; - new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, &new_folio); - if (!new_de) + new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, + &new_folio); + if (IS_ERR(new_de)) { + err = PTR_ERR(new_de); goto out_dir; + } nilfs_set_link(new_dir, new_de, new_folio, old_inode); folio_release_kmap(new_folio, new_de); nilfs_mark_inode_dirty(new_dir); @@ -440,12 +452,13 @@ out: */ static struct dentry *nilfs_get_parent(struct dentry *child) { - unsigned long ino; + ino_t ino; + int res; struct nilfs_root *root; - ino = nilfs_inode_by_name(d_inode(child), &dotdot_name); - if (!ino) - return ERR_PTR(-ENOENT); + res = nilfs_inode_by_name(d_inode(child), &dotdot_name, &ino); + if (res) + return ERR_PTR(res); root = NILFS_I(d_inode(child))->i_root; diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index fb1c4c5bae7c..45d03826eaf1 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -254,7 +254,7 @@ static inline __u32 nilfs_mask_flags(umode_t mode, __u32 flags) /* dir.c */ int nilfs_add_link(struct dentry *, struct inode *); -ino_t nilfs_inode_by_name(struct inode *, const struct qstr *); +int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino); int nilfs_make_empty(struct inode *, struct inode *); struct nilfs_dir_entry *nilfs_find_entry(struct inode *, const struct qstr *, struct folio **);

18 hours, 29 minutes

1
0
0 0

FAILED: patch "[PATCH] nilfs2: propagate directory read errors from" 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 08cfa12adf888db98879dbd735bc741360a34168 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101853-recall-payee-2d9d@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 08cfa12adf888db98879dbd735bc741360a34168 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Date: Fri, 4 Oct 2024 12:35:31 +0900 Subject: [PATCH] nilfs2: propagate directory read errors from nilfs_find_entry() Syzbot reported that a task hang occurs in vcs_open() during a fuzzing test for nilfs2. The root cause of this problem is that in nilfs_find_entry(), which searches for directory entries, ignores errors when loading a directory page/folio via nilfs_get_folio() fails. If the filesystem images is corrupted, and the i_size of the directory inode is large, and the directory page/folio is successfully read but fails the sanity check, for example when it is zero-filled, nilfs_check_folio() may continue to spit out error messages in bursts. Fix this issue by propagating the error to the callers when loading a page/folio fails in nilfs_find_entry(). The current interface of nilfs_find_entry() and its callers is outdated and cannot propagate error codes such as -EIO and -ENOMEM returned via nilfs_find_entry(), so fix it together. Link: https://lkml.kernel.org/r/20241004033640.6841-1-konishi.ryusuke@gmail.com Fixes: 2ba466d74ed7 ("nilfs2: directory entry operations") Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: Lizhi Xu <lizhi.xu(a)windriver.com> Closes: https://lkml.kernel.org/r/20240927013806.3577931-1-lizhi.xu@windriver.com Reported-by: syzbot+8a192e8d090fa9a31135(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=8a192e8d090fa9a31135 Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index fe5b1a30c509..a8602729586a 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -289,7 +289,7 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx) * The folio is mapped and unlocked. When the caller is finished with * the entry, it should call folio_release_kmap(). * - * On failure, returns NULL and the caller should ignore foliop. + * On failure, returns an error pointer and the caller should ignore foliop. */ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, const struct qstr *qstr, struct folio **foliop) @@ -312,22 +312,24 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, do { char *kaddr = nilfs_get_folio(dir, n, foliop); - if (!IS_ERR(kaddr)) { - de = (struct nilfs_dir_entry *)kaddr; - kaddr += nilfs_last_byte(dir, n) - reclen; - while ((char *) de <= kaddr) { - if (de->rec_len == 0) { - nilfs_error(dir->i_sb, - "zero-length directory entry"); - folio_release_kmap(*foliop, kaddr); - goto out; - } - if (nilfs_match(namelen, name, de)) - goto found; - de = nilfs_next_entry(de); + if (IS_ERR(kaddr)) + return ERR_CAST(kaddr); + + de = (struct nilfs_dir_entry *)kaddr; + kaddr += nilfs_last_byte(dir, n) - reclen; + while ((char *)de <= kaddr) { + if (de->rec_len == 0) { + nilfs_error(dir->i_sb, + "zero-length directory entry"); + folio_release_kmap(*foliop, kaddr); + goto out; } - folio_release_kmap(*foliop, kaddr); + if (nilfs_match(namelen, name, de)) + goto found; + de = nilfs_next_entry(de); } + folio_release_kmap(*foliop, kaddr); + if (++n >= npages) n = 0; /* next folio is past the blocks we've got */ @@ -340,7 +342,7 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, } } while (n != start); out: - return NULL; + return ERR_PTR(-ENOENT); found: ei->i_dir_start_lookup = n; @@ -384,18 +386,18 @@ fail: return NULL; } -ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr) +int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino) { - ino_t res = 0; struct nilfs_dir_entry *de; struct folio *folio; de = nilfs_find_entry(dir, qstr, &folio); - if (de) { - res = le64_to_cpu(de->inode); - folio_release_kmap(folio, de); - } - return res; + if (IS_ERR(de)) + return PTR_ERR(de); + + *ino = le64_to_cpu(de->inode); + folio_release_kmap(folio, de); + return 0; } void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de, diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index c950139db6ef..4905063790c5 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -55,12 +55,20 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode; ino_t ino; + int res; if (dentry->d_name.len > NILFS_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); - ino = nilfs_inode_by_name(dir, &dentry->d_name); - inode = ino ? nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino) : NULL; + res = nilfs_inode_by_name(dir, &dentry->d_name, &ino); + if (res) { + if (res != -ENOENT) + return ERR_PTR(res); + inode = NULL; + } else { + inode = nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino); + } + return d_splice_alias(inode, dentry); } @@ -263,10 +271,11 @@ static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry) struct folio *folio; int err; - err = -ENOENT; de = nilfs_find_entry(dir, &dentry->d_name, &folio); - if (!de) + if (IS_ERR(de)) { + err = PTR_ERR(de); goto out; + } inode = d_inode(dentry); err = -EIO; @@ -362,10 +371,11 @@ static int nilfs_rename(struct mnt_idmap *idmap, if (unlikely(err)) return err; - err = -ENOENT; old_de = nilfs_find_entry(old_dir, &old_dentry->d_name, &old_folio); - if (!old_de) + if (IS_ERR(old_de)) { + err = PTR_ERR(old_de); goto out; + } if (S_ISDIR(old_inode->i_mode)) { err = -EIO; @@ -382,10 +392,12 @@ static int nilfs_rename(struct mnt_idmap *idmap, if (dir_de && !nilfs_empty_dir(new_inode)) goto out_dir; - err = -ENOENT; - new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, &new_folio); - if (!new_de) + new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, + &new_folio); + if (IS_ERR(new_de)) { + err = PTR_ERR(new_de); goto out_dir; + } nilfs_set_link(new_dir, new_de, new_folio, old_inode); folio_release_kmap(new_folio, new_de); nilfs_mark_inode_dirty(new_dir); @@ -440,12 +452,13 @@ out: */ static struct dentry *nilfs_get_parent(struct dentry *child) { - unsigned long ino; + ino_t ino; + int res; struct nilfs_root *root; - ino = nilfs_inode_by_name(d_inode(child), &dotdot_name); - if (!ino) - return ERR_PTR(-ENOENT); + res = nilfs_inode_by_name(d_inode(child), &dotdot_name, &ino); + if (res) + return ERR_PTR(res); root = NILFS_I(d_inode(child))->i_root; diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index fb1c4c5bae7c..45d03826eaf1 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -254,7 +254,7 @@ static inline __u32 nilfs_mask_flags(umode_t mode, __u32 flags) /* dir.c */ int nilfs_add_link(struct dentry *, struct inode *); -ino_t nilfs_inode_by_name(struct inode *, const struct qstr *); +int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino); int nilfs_make_empty(struct inode *, struct inode *); struct nilfs_dir_entry *nilfs_find_entry(struct inode *, const struct qstr *, struct folio **);

18 hours, 29 minutes

1
0
0 0

FAILED: patch "[PATCH] nilfs2: propagate directory read errors from" 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 08cfa12adf888db98879dbd735bc741360a34168 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024101852-giggly-ipod-3b07@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 08cfa12adf888db98879dbd735bc741360a34168 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Date: Fri, 4 Oct 2024 12:35:31 +0900 Subject: [PATCH] nilfs2: propagate directory read errors from nilfs_find_entry() Syzbot reported that a task hang occurs in vcs_open() during a fuzzing test for nilfs2. The root cause of this problem is that in nilfs_find_entry(), which searches for directory entries, ignores errors when loading a directory page/folio via nilfs_get_folio() fails. If the filesystem images is corrupted, and the i_size of the directory inode is large, and the directory page/folio is successfully read but fails the sanity check, for example when it is zero-filled, nilfs_check_folio() may continue to spit out error messages in bursts. Fix this issue by propagating the error to the callers when loading a page/folio fails in nilfs_find_entry(). The current interface of nilfs_find_entry() and its callers is outdated and cannot propagate error codes such as -EIO and -ENOMEM returned via nilfs_find_entry(), so fix it together. Link: https://lkml.kernel.org/r/20241004033640.6841-1-konishi.ryusuke@gmail.com Fixes: 2ba466d74ed7 ("nilfs2: directory entry operations") Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: Lizhi Xu <lizhi.xu(a)windriver.com> Closes: https://lkml.kernel.org/r/20240927013806.3577931-1-lizhi.xu@windriver.com Reported-by: syzbot+8a192e8d090fa9a31135(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=8a192e8d090fa9a31135 Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index fe5b1a30c509..a8602729586a 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -289,7 +289,7 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx) * The folio is mapped and unlocked. When the caller is finished with * the entry, it should call folio_release_kmap(). * - * On failure, returns NULL and the caller should ignore foliop. + * On failure, returns an error pointer and the caller should ignore foliop. */ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, const struct qstr *qstr, struct folio **foliop) @@ -312,22 +312,24 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, do { char *kaddr = nilfs_get_folio(dir, n, foliop); - if (!IS_ERR(kaddr)) { - de = (struct nilfs_dir_entry *)kaddr; - kaddr += nilfs_last_byte(dir, n) - reclen; - while ((char *) de <= kaddr) { - if (de->rec_len == 0) { - nilfs_error(dir->i_sb, - "zero-length directory entry"); - folio_release_kmap(*foliop, kaddr); - goto out; - } - if (nilfs_match(namelen, name, de)) - goto found; - de = nilfs_next_entry(de); + if (IS_ERR(kaddr)) + return ERR_CAST(kaddr); + + de = (struct nilfs_dir_entry *)kaddr; + kaddr += nilfs_last_byte(dir, n) - reclen; + while ((char *)de <= kaddr) { + if (de->rec_len == 0) { + nilfs_error(dir->i_sb, + "zero-length directory entry"); + folio_release_kmap(*foliop, kaddr); + goto out; } - folio_release_kmap(*foliop, kaddr); + if (nilfs_match(namelen, name, de)) + goto found; + de = nilfs_next_entry(de); } + folio_release_kmap(*foliop, kaddr); + if (++n >= npages) n = 0; /* next folio is past the blocks we've got */ @@ -340,7 +342,7 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, } } while (n != start); out: - return NULL; + return ERR_PTR(-ENOENT); found: ei->i_dir_start_lookup = n; @@ -384,18 +386,18 @@ fail: return NULL; } -ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr) +int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino) { - ino_t res = 0; struct nilfs_dir_entry *de; struct folio *folio; de = nilfs_find_entry(dir, qstr, &folio); - if (de) { - res = le64_to_cpu(de->inode); - folio_release_kmap(folio, de); - } - return res; + if (IS_ERR(de)) + return PTR_ERR(de); + + *ino = le64_to_cpu(de->inode); + folio_release_kmap(folio, de); + return 0; } void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de, diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index c950139db6ef..4905063790c5 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -55,12 +55,20 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode; ino_t ino; + int res; if (dentry->d_name.len > NILFS_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); - ino = nilfs_inode_by_name(dir, &dentry->d_name); - inode = ino ? nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino) : NULL; + res = nilfs_inode_by_name(dir, &dentry->d_name, &ino); + if (res) { + if (res != -ENOENT) + return ERR_PTR(res); + inode = NULL; + } else { + inode = nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino); + } + return d_splice_alias(inode, dentry); } @@ -263,10 +271,11 @@ static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry) struct folio *folio; int err; - err = -ENOENT; de = nilfs_find_entry(dir, &dentry->d_name, &folio); - if (!de) + if (IS_ERR(de)) { + err = PTR_ERR(de); goto out; + } inode = d_inode(dentry); err = -EIO; @@ -362,10 +371,11 @@ static int nilfs_rename(struct mnt_idmap *idmap, if (unlikely(err)) return err; - err = -ENOENT; old_de = nilfs_find_entry(old_dir, &old_dentry->d_name, &old_folio); - if (!old_de) + if (IS_ERR(old_de)) { + err = PTR_ERR(old_de); goto out; + } if (S_ISDIR(old_inode->i_mode)) { err = -EIO; @@ -382,10 +392,12 @@ static int nilfs_rename(struct mnt_idmap *idmap, if (dir_de && !nilfs_empty_dir(new_inode)) goto out_dir; - err = -ENOENT; - new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, &new_folio); - if (!new_de) + new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, + &new_folio); + if (IS_ERR(new_de)) { + err = PTR_ERR(new_de); goto out_dir; + } nilfs_set_link(new_dir, new_de, new_folio, old_inode); folio_release_kmap(new_folio, new_de); nilfs_mark_inode_dirty(new_dir); @@ -440,12 +452,13 @@ out: */ static struct dentry *nilfs_get_parent(struct dentry *child) { - unsigned long ino; + ino_t ino; + int res; struct nilfs_root *root; - ino = nilfs_inode_by_name(d_inode(child), &dotdot_name); - if (!ino) - return ERR_PTR(-ENOENT); + res = nilfs_inode_by_name(d_inode(child), &dotdot_name, &ino); + if (res) + return ERR_PTR(res); root = NILFS_I(d_inode(child))->i_root; diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index fb1c4c5bae7c..45d03826eaf1 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -254,7 +254,7 @@ static inline __u32 nilfs_mask_flags(umode_t mode, __u32 flags) /* dir.c */ int nilfs_add_link(struct dentry *, struct inode *); -ino_t nilfs_inode_by_name(struct inode *, const struct qstr *); +int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino); int nilfs_make_empty(struct inode *, struct inode *); struct nilfs_dir_entry *nilfs_find_entry(struct inode *, const struct qstr *, struct folio **);

18 hours, 29 minutes

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror