November 2024 - Linux-stable-mirror

[merged mm-hotfixes-stable] mm-refactor-arch_calc_vm_flag_bits-and-arm64-mte-handling.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm: refactor arch_calc_vm_flag_bits() and arm64 MTE handling has been removed from the -mm tree. Its filename was mm-refactor-arch_calc_vm_flag_bits-and-arm64-mte-handling.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Subject: mm: refactor arch_calc_vm_flag_bits() and arm64 MTE handling Date: Tue, 29 Oct 2024 18:11:47 +0000 Currently MTE is permitted in two circumstances (desiring to use MTE having been specified by the VM_MTE flag) - where MAP_ANONYMOUS is specified, as checked by arch_calc_vm_flag_bits() and actualised by setting the VM_MTE_ALLOWED flag, or if the file backing the mapping is shmem, in which case we set VM_MTE_ALLOWED in shmem_mmap() when the mmap hook is activated in mmap_region(). The function that checks that, if VM_MTE is set, VM_MTE_ALLOWED is also set is the arm64 implementation of arch_validate_flags(). Unfortunately, we intend to refactor mmap_region() to perform this check earlier, meaning that in the case of a shmem backing we will not have invoked shmem_mmap() yet, causing the mapping to fail spuriously. It is inappropriate to set this architecture-specific flag in general mm code anyway, so a sensible resolution of this issue is to instead move the check somewhere else. We resolve this by setting VM_MTE_ALLOWED much earlier in do_mmap(), via the arch_calc_vm_flag_bits() call. This is an appropriate place to do this as we already check for the MAP_ANONYMOUS case here, and the shmem file case is simply a variant of the same idea - we permit RAM-backed memory. This requires a modification to the arch_calc_vm_flag_bits() signature to pass in a pointer to the struct file associated with the mapping, however this is not too egregious as this is only used by two architectures anyway - arm64 and parisc. So this patch performs this adjustment and removes the unnecessary assignment of VM_MTE_ALLOWED in shmem_mmap(). [akpm(a)linux-foundation.org: fix whitespace, per Catalin] Link: https://lkml.kernel.org/r/ec251b20ba1964fb64cf1607d2ad80c47f3873df.17302246… Fixes: deb0f6562884 ("mm/mmap: undo ->mmap() when arch_validate_flags() fails") Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Suggested-by: Catalin Marinas <catalin.marinas(a)arm.com> Reported-by: Jann Horn <jannh(a)google.com> Reviewed-by: Catalin Marinas <catalin.marinas(a)arm.com> Reviewed-by: Vlastimil Babka <vbabka(a)suse.cz> Cc: Andreas Larsson <andreas(a)gaisler.com> Cc: David S. Miller <davem(a)davemloft.net> Cc: Helge Deller <deller(a)gmx.de> Cc: James E.J. Bottomley <James.Bottomley(a)HansenPartnership.com> Cc: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Mark Brown <broonie(a)kernel.org> Cc: Peter Xu <peterx(a)redhat.com> Cc: Will Deacon <will(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- arch/arm64/include/asm/mman.h | 10 +++++++--- arch/parisc/include/asm/mman.h | 5 +++-- include/linux/mman.h | 7 ++++--- mm/mmap.c | 2 +- mm/nommu.c | 2 +- mm/shmem.c | 3 --- 6 files changed, 16 insertions(+), 13 deletions(-) --- a/arch/arm64/include/asm/mman.h~mm-refactor-arch_calc_vm_flag_bits-and-arm64-mte-handling +++ a/arch/arm64/include/asm/mman.h @@ -6,6 +6,8 @@ #ifndef BUILD_VDSO #include <linux/compiler.h> +#include <linux/fs.h> +#include <linux/shmem_fs.h> #include <linux/types.h> static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, @@ -31,19 +33,21 @@ static inline unsigned long arch_calc_vm } #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) -static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags) +static inline unsigned long arch_calc_vm_flag_bits(struct file *file, + unsigned long flags) { /* * Only allow MTE on anonymous mappings as these are guaranteed to be * backed by tags-capable memory. The vm_flags may be overridden by a * filesystem supporting MTE (RAM-based). */ - if (system_supports_mte() && (flags & MAP_ANONYMOUS)) + if (system_supports_mte() && + ((flags & MAP_ANONYMOUS) || shmem_file(file))) return VM_MTE_ALLOWED; return 0; } -#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags) +#define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags) static inline bool arch_validate_prot(unsigned long prot, unsigned long addr __always_unused) --- a/arch/parisc/include/asm/mman.h~mm-refactor-arch_calc_vm_flag_bits-and-arm64-mte-handling +++ a/arch/parisc/include/asm/mman.h @@ -2,6 +2,7 @@ #ifndef __ASM_MMAN_H__ #define __ASM_MMAN_H__ +#include <linux/fs.h> #include <uapi/asm/mman.h> /* PARISC cannot allow mdwe as it needs writable stacks */ @@ -11,7 +12,7 @@ static inline bool arch_memory_deny_writ } #define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported -static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags) +static inline unsigned long arch_calc_vm_flag_bits(struct file *file, unsigned long flags) { /* * The stack on parisc grows upwards, so if userspace requests memory @@ -23,6 +24,6 @@ static inline unsigned long arch_calc_vm return 0; } -#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags) +#define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags) #endif /* __ASM_MMAN_H__ */ --- a/include/linux/mman.h~mm-refactor-arch_calc_vm_flag_bits-and-arm64-mte-handling +++ a/include/linux/mman.h @@ -2,6 +2,7 @@ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H +#include <linux/fs.h> #include <linux/mm.h> #include <linux/percpu_counter.h> @@ -94,7 +95,7 @@ static inline void vm_unacct_memory(long #endif #ifndef arch_calc_vm_flag_bits -#define arch_calc_vm_flag_bits(flags) 0 +#define arch_calc_vm_flag_bits(file, flags) 0 #endif #ifndef arch_validate_prot @@ -151,13 +152,13 @@ calc_vm_prot_bits(unsigned long prot, un * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline unsigned long -calc_vm_flag_bits(unsigned long flags) +calc_vm_flag_bits(struct file *file, unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | - arch_calc_vm_flag_bits(flags); + arch_calc_vm_flag_bits(file, flags); } unsigned long vm_commit_limit(void); --- a/mm/mmap.c~mm-refactor-arch_calc_vm_flag_bits-and-arm64-mte-handling +++ a/mm/mmap.c @@ -344,7 +344,7 @@ unsigned long do_mmap(struct file *file, * to. we assume access permissions have been handled by the open * of the memory object, so we don't do any here. */ - vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(flags) | + vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(file, flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; /* Obtain the address to map to. we verify (or select) it and ensure --- a/mm/nommu.c~mm-refactor-arch_calc_vm_flag_bits-and-arm64-mte-handling +++ a/mm/nommu.c @@ -842,7 +842,7 @@ static unsigned long determine_vm_flags( { unsigned long vm_flags; - vm_flags = calc_vm_prot_bits(prot, 0) | calc_vm_flag_bits(flags); + vm_flags = calc_vm_prot_bits(prot, 0) | calc_vm_flag_bits(file, flags); if (!file) { /* --- a/mm/shmem.c~mm-refactor-arch_calc_vm_flag_bits-and-arm64-mte-handling +++ a/mm/shmem.c @@ -2733,9 +2733,6 @@ static int shmem_mmap(struct file *file, if (ret) return ret; - /* arm64 - allow memory tagging on RAM-based files */ - vm_flags_set(vma, VM_MTE_ALLOWED); - file_accessed(file); /* This is anonymous shared memory if it is unlinked at the time of mmap */ if (inode->i_nlink) _ Patches currently in -mm which might be from lorenzo.stoakes(a)oracle.com are selftests-mm-add-pkey_sighandler_xx-hugetlb_dio-to-gitignore.patch mm-refactor-mm_access-to-not-return-null.patch mm-madvise-unrestrict-process_madvise-for-current-process.patch maple_tree-do-not-hash-pointers-on-dump-in-debug-mode.patch tools-testing-fix-phys_addr_t-size-on-64-bit-systems.patch tools-testing-add-additional-vma_internalh-stubs.patch mm-isolate-mmap-internal-logic-to-mm-vmac.patch mm-refactor-__mmap_region.patch mm-remove-unnecessary-reset-state-logic-on-merge-new-vma.patch mm-defer-second-attempt-at-merge-on-mmap.patch mm-pagewalk-add-the-ability-to-install-ptes.patch mm-add-pte_marker_guard-pte-marker.patch mm-madvise-implement-lightweight-guard-page-mechanism.patch tools-testing-update-tools-uapi-header-for-mman-commonh.patch selftests-mm-add-self-tests-for-guard-page-feature.patch mm-remove-unnecessary-page_table_lock-on-stack-expansion.patch

2 months

1
0
0 0

[merged mm-hotfixes-stable] mm-refactor-map_deny_write_exec.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm: refactor map_deny_write_exec() has been removed from the -mm tree. Its filename was mm-refactor-map_deny_write_exec.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Subject: mm: refactor map_deny_write_exec() Date: Tue, 29 Oct 2024 18:11:46 +0000 Refactor the map_deny_write_exec() to not unnecessarily require a VMA parameter but rather to accept VMA flags parameters, which allows us to use this function early in mmap_region() in a subsequent commit. While we're here, we refactor the function to be more readable and add some additional documentation. Link: https://lkml.kernel.org/r/6be8bb59cd7c68006ebb006eb9d8dc27104b1f70.17302246… Fixes: deb0f6562884 ("mm/mmap: undo ->mmap() when arch_validate_flags() fails") Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reported-by: Jann Horn <jannh(a)google.com> Reviewed-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Reviewed-by: Vlastimil Babka <vbabka(a)suse.cz> Reviewed-by: Jann Horn <jannh(a)google.com> Cc: Andreas Larsson <andreas(a)gaisler.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: David S. Miller <davem(a)davemloft.net> Cc: Helge Deller <deller(a)gmx.de> Cc: James E.J. Bottomley <James.Bottomley(a)HansenPartnership.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Mark Brown <broonie(a)kernel.org> Cc: Peter Xu <peterx(a)redhat.com> Cc: Will Deacon <will(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mman.h | 21 ++++++++++++++++++--- mm/mmap.c | 2 +- mm/mprotect.c | 2 +- mm/vma.h | 2 +- 4 files changed, 21 insertions(+), 6 deletions(-) --- a/include/linux/mman.h~mm-refactor-map_deny_write_exec +++ a/include/linux/mman.h @@ -188,16 +188,31 @@ static inline bool arch_memory_deny_writ * * d) mmap(PROT_READ | PROT_EXEC) * mmap(PROT_READ | PROT_EXEC | PROT_BTI) + * + * This is only applicable if the user has set the Memory-Deny-Write-Execute + * (MDWE) protection mask for the current process. + * + * @old specifies the VMA flags the VMA originally possessed, and @new the ones + * we propose to set. + * + * Return: false if proposed change is OK, true if not ok and should be denied. */ -static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags) +static inline bool map_deny_write_exec(unsigned long old, unsigned long new) { + /* If MDWE is disabled, we have nothing to deny. */ if (!test_bit(MMF_HAS_MDWE, &current->mm->flags)) return false; - if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE)) + /* If the new VMA is not executable, we have nothing to deny. */ + if (!(new & VM_EXEC)) + return false; + + /* Under MDWE we do not accept newly writably executable VMAs... */ + if (new & VM_WRITE) return true; - if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC)) + /* ...nor previously non-executable VMAs becoming executable. */ + if (!(old & VM_EXEC)) return true; return false; --- a/mm/mmap.c~mm-refactor-map_deny_write_exec +++ a/mm/mmap.c @@ -1505,7 +1505,7 @@ unsigned long mmap_region(struct file *f vma_set_anonymous(vma); } - if (map_deny_write_exec(vma, vma->vm_flags)) { + if (map_deny_write_exec(vma->vm_flags, vma->vm_flags)) { error = -EACCES; goto close_and_free_vma; } --- a/mm/mprotect.c~mm-refactor-map_deny_write_exec +++ a/mm/mprotect.c @@ -810,7 +810,7 @@ static int do_mprotect_pkey(unsigned lon break; } - if (map_deny_write_exec(vma, newflags)) { + if (map_deny_write_exec(vma->vm_flags, newflags)) { error = -EACCES; break; } --- a/mm/vma.h~mm-refactor-map_deny_write_exec +++ a/mm/vma.h @@ -42,7 +42,7 @@ struct vma_munmap_struct { int vma_count; /* Number of vmas that will be removed */ bool unlock; /* Unlock after the munmap */ bool clear_ptes; /* If there are outstanding PTE to be cleared */ - /* 1 byte hole */ + /* 2 byte hole */ unsigned long nr_pages; /* Number of pages being removed */ unsigned long locked_vm; /* Number of locked pages */ unsigned long nr_accounted; /* Number of VM_ACCOUNT pages */ _ Patches currently in -mm which might be from lorenzo.stoakes(a)oracle.com are selftests-mm-add-pkey_sighandler_xx-hugetlb_dio-to-gitignore.patch mm-refactor-mm_access-to-not-return-null.patch mm-madvise-unrestrict-process_madvise-for-current-process.patch maple_tree-do-not-hash-pointers-on-dump-in-debug-mode.patch tools-testing-fix-phys_addr_t-size-on-64-bit-systems.patch tools-testing-add-additional-vma_internalh-stubs.patch mm-isolate-mmap-internal-logic-to-mm-vmac.patch mm-refactor-__mmap_region.patch mm-remove-unnecessary-reset-state-logic-on-merge-new-vma.patch mm-defer-second-attempt-at-merge-on-mmap.patch mm-pagewalk-add-the-ability-to-install-ptes.patch mm-add-pte_marker_guard-pte-marker.patch mm-madvise-implement-lightweight-guard-page-mechanism.patch tools-testing-update-tools-uapi-header-for-mman-commonh.patch selftests-mm-add-self-tests-for-guard-page-feature.patch mm-remove-unnecessary-page_table_lock-on-stack-expansion.patch

2 months

1
0
0 0

[merged mm-hotfixes-stable] mm-unconditionally-close-vmas-on-error.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm: unconditionally close VMAs on error has been removed from the -mm tree. Its filename was mm-unconditionally-close-vmas-on-error.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Subject: mm: unconditionally close VMAs on error Date: Tue, 29 Oct 2024 18:11:45 +0000 Incorrect invocation of VMA callbacks when the VMA is no longer in a consistent state is bug prone and risky to perform. With regards to the important vm_ops->close() callback We have gone to great lengths to try to track whether or not we ought to close VMAs. Rather than doing so and risking making a mistake somewhere, instead unconditionally close and reset vma->vm_ops to an empty dummy operations set with a NULL .close operator. We introduce a new function to do so - vma_close() - and simplify existing vms logic which tracked whether we needed to close or not. This simplifies the logic, avoids incorrect double-calling of the .close() callback and allows us to update error paths to simply call vma_close() unconditionally - making VMA closure idempotent. Link: https://lkml.kernel.org/r/28e89dda96f68c505cb6f8e9fc9b57c3e9f74b42.17302246… Fixes: deb0f6562884 ("mm/mmap: undo ->mmap() when arch_validate_flags() fails") Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reported-by: Jann Horn <jannh(a)google.com> Reviewed-by: Vlastimil Babka <vbabka(a)suse.cz> Reviewed-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Reviewed-by: Jann Horn <jannh(a)google.com> Cc: Andreas Larsson <andreas(a)gaisler.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: David S. Miller <davem(a)davemloft.net> Cc: Helge Deller <deller(a)gmx.de> Cc: James E.J. Bottomley <James.Bottomley(a)HansenPartnership.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Mark Brown <broonie(a)kernel.org> Cc: Peter Xu <peterx(a)redhat.com> Cc: Will Deacon <will(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/internal.h | 18 ++++++++++++++++++ mm/mmap.c | 5 ++--- mm/nommu.c | 3 +-- mm/vma.c | 14 +++++--------- mm/vma.h | 4 +--- 5 files changed, 27 insertions(+), 17 deletions(-) --- a/mm/internal.h~mm-unconditionally-close-vmas-on-error +++ a/mm/internal.h @@ -135,6 +135,24 @@ static inline int mmap_file(struct file return err; } +/* + * If the VMA has a close hook then close it, and since closing it might leave + * it in an inconsistent state which makes the use of any hooks suspect, clear + * them down by installing dummy empty hooks. + */ +static inline void vma_close(struct vm_area_struct *vma) +{ + if (vma->vm_ops && vma->vm_ops->close) { + vma->vm_ops->close(vma); + + /* + * The mapping is in an inconsistent state, and no further hooks + * may be invoked upon it. + */ + vma->vm_ops = &vma_dummy_vm_ops; + } +} + #ifdef CONFIG_MMU /* Flags for folio_pte_batch(). */ --- a/mm/mmap.c~mm-unconditionally-close-vmas-on-error +++ a/mm/mmap.c @@ -1573,8 +1573,7 @@ expanded: return addr; close_and_free_vma: - if (file && !vms.closed_vm_ops && vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); + vma_close(vma); if (file || vma->vm_file) { unmap_and_free_vma: @@ -1934,7 +1933,7 @@ void exit_mmap(struct mm_struct *mm) do { if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); - remove_vma(vma, /* unreachable = */ true, /* closed = */ false); + remove_vma(vma, /* unreachable = */ true); count++; cond_resched(); vma = vma_next(&vmi); --- a/mm/nommu.c~mm-unconditionally-close-vmas-on-error +++ a/mm/nommu.c @@ -589,8 +589,7 @@ static int delete_vma_from_mm(struct vm_ */ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) { - if (vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); + vma_close(vma); if (vma->vm_file) fput(vma->vm_file); put_nommu_region(vma->vm_region); --- a/mm/vma.c~mm-unconditionally-close-vmas-on-error +++ a/mm/vma.c @@ -323,11 +323,10 @@ static bool can_vma_merge_right(struct v /* * Close a vm structure and free it. */ -void remove_vma(struct vm_area_struct *vma, bool unreachable, bool closed) +void remove_vma(struct vm_area_struct *vma, bool unreachable) { might_sleep(); - if (!closed && vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); + vma_close(vma); if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); @@ -1115,9 +1114,7 @@ void vms_clean_up_area(struct vma_munmap vms_clear_ptes(vms, mas_detach, true); mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) - if (vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); - vms->closed_vm_ops = true; + vma_close(vma); } /* @@ -1160,7 +1157,7 @@ void vms_complete_munmap_vmas(struct vma /* Remove and clean up vmas */ mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) - remove_vma(vma, /* = */ false, vms->closed_vm_ops); + remove_vma(vma, /* unreachable = */ false); vm_unacct_memory(vms->nr_accounted); validate_mm(mm); @@ -1684,8 +1681,7 @@ struct vm_area_struct *copy_vma(struct v return new_vma; out_vma_link: - if (new_vma->vm_ops && new_vma->vm_ops->close) - new_vma->vm_ops->close(new_vma); + vma_close(new_vma); if (new_vma->vm_file) fput(new_vma->vm_file); --- a/mm/vma.h~mm-unconditionally-close-vmas-on-error +++ a/mm/vma.h @@ -42,7 +42,6 @@ struct vma_munmap_struct { int vma_count; /* Number of vmas that will be removed */ bool unlock; /* Unlock after the munmap */ bool clear_ptes; /* If there are outstanding PTE to be cleared */ - bool closed_vm_ops; /* call_mmap() was encountered, so vmas may be closed */ /* 1 byte hole */ unsigned long nr_pages; /* Number of pages being removed */ unsigned long locked_vm; /* Number of locked pages */ @@ -198,7 +197,6 @@ static inline void init_vma_munmap(struc vms->unmap_start = FIRST_USER_ADDRESS; vms->unmap_end = USER_PGTABLES_CEILING; vms->clear_ptes = false; - vms->closed_vm_ops = false; } #endif @@ -269,7 +267,7 @@ int do_vmi_munmap(struct vma_iterator *v unsigned long start, size_t len, struct list_head *uf, bool unlock); -void remove_vma(struct vm_area_struct *vma, bool unreachable, bool closed); +void remove_vma(struct vm_area_struct *vma, bool unreachable); void unmap_region(struct ma_state *mas, struct vm_area_struct *vma, struct vm_area_struct *prev, struct vm_area_struct *next); _ Patches currently in -mm which might be from lorenzo.stoakes(a)oracle.com are selftests-mm-add-pkey_sighandler_xx-hugetlb_dio-to-gitignore.patch mm-refactor-mm_access-to-not-return-null.patch mm-madvise-unrestrict-process_madvise-for-current-process.patch maple_tree-do-not-hash-pointers-on-dump-in-debug-mode.patch tools-testing-fix-phys_addr_t-size-on-64-bit-systems.patch tools-testing-add-additional-vma_internalh-stubs.patch mm-isolate-mmap-internal-logic-to-mm-vmac.patch mm-refactor-__mmap_region.patch mm-remove-unnecessary-reset-state-logic-on-merge-new-vma.patch mm-defer-second-attempt-at-merge-on-mmap.patch mm-pagewalk-add-the-ability-to-install-ptes.patch mm-add-pte_marker_guard-pte-marker.patch mm-madvise-implement-lightweight-guard-page-mechanism.patch tools-testing-update-tools-uapi-header-for-mman-commonh.patch selftests-mm-add-self-tests-for-guard-page-feature.patch mm-remove-unnecessary-page_table_lock-on-stack-expansion.patch

2 months

1
0
0 0

[merged mm-hotfixes-stable] mm-avoid-unsafe-vma-hook-invocation-when-error-arises-on-mmap-hook.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm: avoid unsafe VMA hook invocation when error arises on mmap hook has been removed from the -mm tree. Its filename was mm-avoid-unsafe-vma-hook-invocation-when-error-arises-on-mmap-hook.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Subject: mm: avoid unsafe VMA hook invocation when error arises on mmap hook Date: Tue, 29 Oct 2024 18:11:44 +0000 Patch series "fix error handling in mmap_region() and refactor (hotfixes)", v4. mmap_region() is somewhat terrifying, with spaghetti-like control flow and numerous means by which issues can arise and incomplete state, memory leaks and other unpleasantness can occur. A large amount of the complexity arises from trying to handle errors late in the process of mapping a VMA, which forms the basis of recently observed issues with resource leaks and observable inconsistent state. This series goes to great lengths to simplify how mmap_region() works and to avoid unwinding errors late on in the process of setting up the VMA for the new mapping, and equally avoids such operations occurring while the VMA is in an inconsistent state. The patches in this series comprise the minimal changes required to resolve existing issues in mmap_region() error handling, in order that they can be hotfixed and backported. There is additionally a follow up series which goes further, separated out from the v1 series and sent and updated separately. This patch (of 5): After an attempted mmap() fails, we are no longer in a situation where we can safely interact with VMA hooks. This is currently not enforced, meaning that we need complicated handling to ensure we do not incorrectly call these hooks. We can avoid the whole issue by treating the VMA as suspect the moment that the file->f_ops->mmap() function reports an error by replacing whatever VMA operations were installed with a dummy empty set of VMA operations. We do so through a new helper function internal to mm - mmap_file() - which is both more logically named than the existing call_mmap() function and correctly isolates handling of the vm_op reassignment to mm. All the existing invocations of call_mmap() outside of mm are ultimately nested within the call_mmap() from mm, which we now replace. It is therefore safe to leave call_mmap() in place as a convenience function (and to avoid churn). The invokers are: ovl_file_operations -> mmap -> ovl_mmap() -> backing_file_mmap() coda_file_operations -> mmap -> coda_file_mmap() shm_file_operations -> shm_mmap() shm_file_operations_huge -> shm_mmap() dma_buf_fops -> dma_buf_mmap_internal -> i915_dmabuf_ops -> i915_gem_dmabuf_mmap() None of these callers interact with vm_ops or mappings in a problematic way on error, quickly exiting out. Link: https://lkml.kernel.org/r/cover.1730224667.git.lorenzo.stoakes@oracle.com Link: https://lkml.kernel.org/r/d41fd763496fd0048a962f3fd9407dc72dd4fd86.17302246… Fixes: deb0f6562884 ("mm/mmap: undo ->mmap() when arch_validate_flags() fails") Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Reported-by: Jann Horn <jannh(a)google.com> Reviewed-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Reviewed-by: Vlastimil Babka <vbabka(a)suse.cz> Reviewed-by: Jann Horn <jannh(a)google.com> Cc: Andreas Larsson <andreas(a)gaisler.com> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: David S. Miller <davem(a)davemloft.net> Cc: Helge Deller <deller(a)gmx.de> Cc: James E.J. Bottomley <James.Bottomley(a)HansenPartnership.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Mark Brown <broonie(a)kernel.org> Cc: Peter Xu <peterx(a)redhat.com> Cc: Will Deacon <will(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/internal.h | 27 +++++++++++++++++++++++++++ mm/mmap.c | 6 +++--- mm/nommu.c | 4 ++-- 3 files changed, 32 insertions(+), 5 deletions(-) --- a/mm/internal.h~mm-avoid-unsafe-vma-hook-invocation-when-error-arises-on-mmap-hook +++ a/mm/internal.h @@ -108,6 +108,33 @@ static inline void *folio_raw_mapping(co return (void *)(mapping & ~PAGE_MAPPING_FLAGS); } +/* + * This is a file-backed mapping, and is about to be memory mapped - invoke its + * mmap hook and safely handle error conditions. On error, VMA hooks will be + * mutated. + * + * @file: File which backs the mapping. + * @vma: VMA which we are mapping. + * + * Returns: 0 if success, error otherwise. + */ +static inline int mmap_file(struct file *file, struct vm_area_struct *vma) +{ + int err = call_mmap(file, vma); + + if (likely(!err)) + return 0; + + /* + * OK, we tried to call the file hook for mmap(), but an error + * arose. The mapping is in an inconsistent state and we most not invoke + * any further hooks on it. + */ + vma->vm_ops = &vma_dummy_vm_ops; + + return err; +} + #ifdef CONFIG_MMU /* Flags for folio_pte_batch(). */ --- a/mm/mmap.c~mm-avoid-unsafe-vma-hook-invocation-when-error-arises-on-mmap-hook +++ a/mm/mmap.c @@ -1422,7 +1422,7 @@ unsigned long mmap_region(struct file *f /* * clear PTEs while the vma is still in the tree so that rmap * cannot race with the freeing later in the truncate scenario. - * This is also needed for call_mmap(), which is why vm_ops + * This is also needed for mmap_file(), which is why vm_ops * close function is called. */ vms_clean_up_area(&vms, &mas_detach); @@ -1447,7 +1447,7 @@ unsigned long mmap_region(struct file *f if (file) { vma->vm_file = get_file(file); - error = call_mmap(file, vma); + error = mmap_file(file, vma); if (error) goto unmap_and_free_vma; @@ -1470,7 +1470,7 @@ unsigned long mmap_region(struct file *f vma_iter_config(&vmi, addr, end); /* - * If vm_flags changed after call_mmap(), we should try merge + * If vm_flags changed after mmap_file(), we should try merge * vma again as we may succeed this time. */ if (unlikely(vm_flags != vma->vm_flags && vmg.prev)) { --- a/mm/nommu.c~mm-avoid-unsafe-vma-hook-invocation-when-error-arises-on-mmap-hook +++ a/mm/nommu.c @@ -885,7 +885,7 @@ static int do_mmap_shared_file(struct vm { int ret; - ret = call_mmap(vma->vm_file, vma); + ret = mmap_file(vma->vm_file, vma); if (ret == 0) { vma->vm_region->vm_top = vma->vm_region->vm_end; return 0; @@ -918,7 +918,7 @@ static int do_mmap_private(struct vm_are * happy. */ if (capabilities & NOMMU_MAP_DIRECT) { - ret = call_mmap(vma->vm_file, vma); + ret = mmap_file(vma->vm_file, vma); /* shouldn't return success if we're not sharing */ if (WARN_ON_ONCE(!is_nommu_shared_mapping(vma->vm_flags))) ret = -ENOSYS; _ Patches currently in -mm which might be from lorenzo.stoakes(a)oracle.com are selftests-mm-add-pkey_sighandler_xx-hugetlb_dio-to-gitignore.patch mm-refactor-mm_access-to-not-return-null.patch mm-madvise-unrestrict-process_madvise-for-current-process.patch maple_tree-do-not-hash-pointers-on-dump-in-debug-mode.patch tools-testing-fix-phys_addr_t-size-on-64-bit-systems.patch tools-testing-add-additional-vma_internalh-stubs.patch mm-isolate-mmap-internal-logic-to-mm-vmac.patch mm-refactor-__mmap_region.patch mm-remove-unnecessary-reset-state-logic-on-merge-new-vma.patch mm-defer-second-attempt-at-merge-on-mmap.patch mm-pagewalk-add-the-ability-to-install-ptes.patch mm-add-pte_marker_guard-pte-marker.patch mm-madvise-implement-lightweight-guard-page-mechanism.patch tools-testing-update-tools-uapi-header-for-mman-commonh.patch selftests-mm-add-self-tests-for-guard-page-feature.patch mm-remove-unnecessary-page_table_lock-on-stack-expansion.patch

2 months

1
0
0 0

[merged mm-hotfixes-stable] mm-thp-fix-deferred-split-unqueue-naming-and-locking.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/thp: fix deferred split unqueue naming and locking has been removed from the -mm tree. Its filename was mm-thp-fix-deferred-split-unqueue-naming-and-locking.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Hugh Dickins <hughd(a)google.com> Subject: mm/thp: fix deferred split unqueue naming and locking Date: Sun, 27 Oct 2024 13:02:13 -0700 (PDT) Recent changes are putting more pressure on THP deferred split queues: under load revealing long-standing races, causing list_del corruptions, "Bad page state"s and worse (I keep BUGs in both of those, so usually don't get to see how badly they end up without). The relevant recent changes being 6.8's mTHP, 6.10's mTHP swapout, and 6.12's mTHP swapin, improved swap allocation, and underused THP splitting. Before fixing locking: rename misleading folio_undo_large_rmappable(), which does not undo large_rmappable, to folio_unqueue_deferred_split(), which is what it does. But that and its out-of-line __callee are mm internals of very limited usability: add comment and WARN_ON_ONCEs to check usage; and return a bool to say if a deferred split was unqueued, which can then be used in WARN_ON_ONCEs around safety checks (sparing callers the arcane conditionals in __folio_unqueue_deferred_split()). Just omit the folio_unqueue_deferred_split() from free_unref_folios(), all of whose callers now call it beforehand (and if any forget then bad_page() will tell) - except for its caller put_pages_list(), which itself no longer has any callers (and will be deleted separately). Swapout: mem_cgroup_swapout() has been resetting folio->memcg_data 0 without checking and unqueueing a THP folio from deferred split list; which is unfortunate, since the split_queue_lock depends on the memcg (when memcg is enabled); so swapout has been unqueueing such THPs later, when freeing the folio, using the pgdat's lock instead: potentially corrupting the memcg's list. __remove_mapping() has frozen refcount to 0 here, so no problem with calling folio_unqueue_deferred_split() before resetting memcg_data. That goes back to 5.4 commit 87eaceb3faa5 ("mm: thp: make deferred split shrinker memcg aware"): which included a check on swapcache before adding to deferred queue, but no check on deferred queue before adding THP to swapcache. That worked fine with the usual sequence of events in reclaim (though there were a couple of rare ways in which a THP on deferred queue could have been swapped out), but 6.12 commit dafff3f4c850 ("mm: split underused THPs") avoids splitting underused THPs in reclaim, which makes swapcache THPs on deferred queue commonplace. Keep the check on swapcache before adding to deferred queue? Yes: it is no longer essential, but preserves the existing behaviour, and is likely to be a worthwhile optimization (vmstat showed much more traffic on the queue under swapping load if the check was removed); update its comment. Memcg-v1 move (deprecated): mem_cgroup_move_account() has been changing folio->memcg_data without checking and unqueueing a THP folio from the deferred list, sometimes corrupting "from" memcg's list, like swapout. Refcount is non-zero here, so folio_unqueue_deferred_split() can only be used in a WARN_ON_ONCE to validate the fix, which must be done earlier: mem_cgroup_move_charge_pte_range() first try to split the THP (splitting of course unqueues), or skip it if that fails. Not ideal, but moving charge has been requested, and khugepaged should repair the THP later: nobody wants new custom unqueueing code just for this deprecated case. The 87eaceb3faa5 commit did have the code to move from one deferred list to another (but was not conscious of its unsafety while refcount non-0); but that was removed by 5.6 commit fac0516b5534 ("mm: thp: don't need care deferred split queue in memcg charge move path"), which argued that the existence of a PMD mapping guarantees that the THP cannot be on a deferred list. As above, false in rare cases, and now commonly false. Backport to 6.11 should be straightforward. Earlier backports must take care that other _deferred_list fixes and dependencies are included. There is not a strong case for backports, but they can fix cornercases. Link: https://lkml.kernel.org/r/8dc111ae-f6db-2da7-b25c-7a20b1effe3b@google.com Fixes: 87eaceb3faa5 ("mm: thp: make deferred split shrinker memcg aware") Fixes: dafff3f4c850 ("mm: split underused THPs") Signed-off-by: Hugh Dickins <hughd(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Reviewed-by: Yang Shi <shy828301(a)gmail.com> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: Barry Song <baohua(a)kernel.org> Cc: Chris Li <chrisl(a)kernel.org> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Kefeng Wang <wangkefeng.wang(a)huawei.com> Cc: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Nhat Pham <nphamcs(a)gmail.com> Cc: Ryan Roberts <ryan.roberts(a)arm.com> Cc: Shakeel Butt <shakeel.butt(a)linux.dev> Cc: Usama Arif <usamaarif642(a)gmail.com> Cc: Wei Yang <richard.weiyang(a)gmail.com> Cc: Zi Yan <ziy(a)nvidia.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/huge_memory.c | 35 ++++++++++++++++++++++++++--------- mm/internal.h | 10 +++++----- mm/memcontrol-v1.c | 25 +++++++++++++++++++++++++ mm/memcontrol.c | 8 +++++--- mm/migrate.c | 4 ++-- mm/page_alloc.c | 1 - mm/swap.c | 4 ++-- mm/vmscan.c | 4 ++-- 8 files changed, 67 insertions(+), 24 deletions(-) --- a/mm/huge_memory.c~mm-thp-fix-deferred-split-unqueue-naming-and-locking +++ a/mm/huge_memory.c @@ -3588,10 +3588,27 @@ int split_folio_to_list(struct folio *fo return split_huge_page_to_list_to_order(&folio->page, list, ret); } -void __folio_undo_large_rmappable(struct folio *folio) +/* + * __folio_unqueue_deferred_split() is not to be called directly: + * the folio_unqueue_deferred_split() inline wrapper in mm/internal.h + * limits its calls to those folios which may have a _deferred_list for + * queueing THP splits, and that list is (racily observed to be) non-empty. + * + * It is unsafe to call folio_unqueue_deferred_split() until folio refcount is + * zero: because even when split_queue_lock is held, a non-empty _deferred_list + * might be in use on deferred_split_scan()'s unlocked on-stack list. + * + * If memory cgroups are enabled, split_queue_lock is in the mem_cgroup: it is + * therefore important to unqueue deferred split before changing folio memcg. + */ +bool __folio_unqueue_deferred_split(struct folio *folio) { struct deferred_split *ds_queue; unsigned long flags; + bool unqueued = false; + + WARN_ON_ONCE(folio_ref_count(folio)); + WARN_ON_ONCE(!mem_cgroup_disabled() && !folio_memcg(folio)); ds_queue = get_deferred_split_queue(folio); spin_lock_irqsave(&ds_queue->split_queue_lock, flags); @@ -3603,8 +3620,11 @@ void __folio_undo_large_rmappable(struct MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } list_del_init(&folio->_deferred_list); + unqueued = true; } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); + + return unqueued; /* useful for debug warnings */ } /* partially_mapped=false won't clear PG_partially_mapped folio flag */ @@ -3627,14 +3647,11 @@ void deferred_split_folio(struct folio * return; /* - * The try_to_unmap() in page reclaim path might reach here too, - * this may cause a race condition to corrupt deferred split queue. - * And, if page reclaim is already handling the same folio, it is - * unnecessary to handle it again in shrinker. - * - * Check the swapcache flag to determine if the folio is being - * handled by page reclaim since THP swap would add the folio into - * swap cache before calling try_to_unmap(). + * Exclude swapcache: originally to avoid a corrupt deferred split + * queue. Nowadays that is fully prevented by mem_cgroup_swapout(); + * but if page reclaim is already handling the same folio, it is + * unnecessary to handle it again in the shrinker, so excluding + * swapcache here may still be a useful optimization. */ if (folio_test_swapcache(folio)) return; --- a/mm/internal.h~mm-thp-fix-deferred-split-unqueue-naming-and-locking +++ a/mm/internal.h @@ -639,11 +639,11 @@ static inline void folio_set_order(struc #endif } -void __folio_undo_large_rmappable(struct folio *folio); -static inline void folio_undo_large_rmappable(struct folio *folio) +bool __folio_unqueue_deferred_split(struct folio *folio); +static inline bool folio_unqueue_deferred_split(struct folio *folio) { if (folio_order(folio) <= 1 || !folio_test_large_rmappable(folio)) - return; + return false; /* * At this point, there is no one trying to add the folio to @@ -651,9 +651,9 @@ static inline void folio_undo_large_rmap * to check without acquiring the split_queue_lock. */ if (data_race(list_empty(&folio->_deferred_list))) - return; + return false; - __folio_undo_large_rmappable(folio); + return __folio_unqueue_deferred_split(folio); } static inline struct folio *page_rmappable_folio(struct page *page) --- a/mm/memcontrol.c~mm-thp-fix-deferred-split-unqueue-naming-and-locking +++ a/mm/memcontrol.c @@ -4629,9 +4629,6 @@ static void uncharge_folio(struct folio struct obj_cgroup *objcg; VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); - VM_BUG_ON_FOLIO(folio_order(folio) > 1 && - !folio_test_hugetlb(folio) && - !list_empty(&folio->_deferred_list), folio); /* * Nobody should be changing or seriously looking at @@ -4678,6 +4675,7 @@ static void uncharge_folio(struct folio ug->nr_memory += nr_pages; ug->pgpgout++; + WARN_ON_ONCE(folio_unqueue_deferred_split(folio)); folio->memcg_data = 0; } @@ -4789,6 +4787,9 @@ void mem_cgroup_migrate(struct folio *ol /* Transfer the charge and the css ref */ commit_charge(new, memcg); + + /* Warning should never happen, so don't worry about refcount non-0 */ + WARN_ON_ONCE(folio_unqueue_deferred_split(old)); old->memcg_data = 0; } @@ -4975,6 +4976,7 @@ void mem_cgroup_swapout(struct folio *fo VM_BUG_ON_FOLIO(oldid, folio); mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries); + folio_unqueue_deferred_split(folio); folio->memcg_data = 0; if (!mem_cgroup_is_root(memcg)) --- a/mm/memcontrol-v1.c~mm-thp-fix-deferred-split-unqueue-naming-and-locking +++ a/mm/memcontrol-v1.c @@ -848,6 +848,8 @@ static int mem_cgroup_move_account(struc css_get(&to->css); css_put(&from->css); + /* Warning should never happen, so don't worry about refcount non-0 */ + WARN_ON_ONCE(folio_unqueue_deferred_split(folio)); folio->memcg_data = (unsigned long)to; __folio_memcg_unlock(from); @@ -1217,7 +1219,9 @@ static int mem_cgroup_move_charge_pte_ra enum mc_target_type target_type; union mc_target target; struct folio *folio; + bool tried_split_before = false; +retry_pmd: ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { if (mc.precharge < HPAGE_PMD_NR) { @@ -1227,6 +1231,27 @@ static int mem_cgroup_move_charge_pte_ra target_type = get_mctgt_type_thp(vma, addr, *pmd, &target); if (target_type == MC_TARGET_PAGE) { folio = target.folio; + /* + * Deferred split queue locking depends on memcg, + * and unqueue is unsafe unless folio refcount is 0: + * split or skip if on the queue? first try to split. + */ + if (!list_empty(&folio->_deferred_list)) { + spin_unlock(ptl); + if (!tried_split_before) + split_folio(folio); + folio_unlock(folio); + folio_put(folio); + if (tried_split_before) + return 0; + tried_split_before = true; + goto retry_pmd; + } + /* + * So long as that pmd lock is held, the folio cannot + * be racily added to the _deferred_list, because + * __folio_remove_rmap() will find !partially_mapped. + */ if (folio_isolate_lru(folio)) { if (!mem_cgroup_move_account(folio, true, mc.from, mc.to)) { --- a/mm/migrate.c~mm-thp-fix-deferred-split-unqueue-naming-and-locking +++ a/mm/migrate.c @@ -490,7 +490,7 @@ static int __folio_migrate_mapping(struc folio_test_large_rmappable(folio)) { if (!folio_ref_freeze(folio, expected_count)) return -EAGAIN; - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); folio_ref_unfreeze(folio, expected_count); } @@ -515,7 +515,7 @@ static int __folio_migrate_mapping(struc } /* Take off deferred split queue while frozen and memcg set */ - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); /* * Now we know that no one else is looking at the folio: --- a/mm/page_alloc.c~mm-thp-fix-deferred-split-unqueue-naming-and-locking +++ a/mm/page_alloc.c @@ -2681,7 +2681,6 @@ void free_unref_folios(struct folio_batc unsigned long pfn = folio_pfn(folio); unsigned int order = folio_order(folio); - folio_undo_large_rmappable(folio); if (!free_pages_prepare(&folio->page, order)) continue; /* --- a/mm/swap.c~mm-thp-fix-deferred-split-unqueue-naming-and-locking +++ a/mm/swap.c @@ -121,7 +121,7 @@ void __folio_put(struct folio *folio) } page_cache_release(folio); - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); mem_cgroup_uncharge(folio); free_unref_page(&folio->page, folio_order(folio)); } @@ -988,7 +988,7 @@ void folios_put_refs(struct folio_batch free_huge_folio(folio); continue; } - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); __page_cache_release(folio, &lruvec, &flags); if (j != i) --- a/mm/vmscan.c~mm-thp-fix-deferred-split-unqueue-naming-and-locking +++ a/mm/vmscan.c @@ -1476,7 +1476,7 @@ free_it: */ nr_reclaimed += nr_pages; - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); if (folio_batch_add(&free_folios, folio) == 0) { mem_cgroup_uncharge_folios(&free_folios); try_to_unmap_flush(); @@ -1864,7 +1864,7 @@ static unsigned int move_folios_to_lru(s if (unlikely(folio_put_testzero(folio))) { __folio_clear_lru_flags(folio); - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); if (folio_batch_add(&free_folios, folio) == 0) { spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_folios(&free_folios); _ Patches currently in -mm which might be from hughd(a)google.com are mm-delete-the-unused-put_pages_list.patch

2 months

1
0
0 0

FAILED: patch "[PATCH] nilfs2: fix kernel bug due to missing clearing of checked" 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 41e192ad2779cae0102879612dfe46726e4396aa # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024110529-clapper-deferred-1146@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 41e192ad2779cae0102879612dfe46726e4396aa Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Date: Fri, 18 Oct 2024 04:33:10 +0900 Subject: [PATCH] nilfs2: fix kernel bug due to missing clearing of checked flag Syzbot reported that in directory operations after nilfs2 detects filesystem corruption and degrades to read-only, __block_write_begin_int(), which is called to prepare block writes, may fail the BUG_ON check for accesses exceeding the folio/page size, triggering a kernel bug. This was found to be because the "checked" flag of a page/folio was not cleared when it was discarded by nilfs2's own routine, which causes the sanity check of directory entries to be skipped when the directory page/folio is reloaded. So, fix that. This was necessary when the use of nilfs2's own page discard routine was applied to more than just metadata files. Link: https://lkml.kernel.org/r/20241017193359.5051-1-konishi.ryusuke@gmail.com Fixes: 8c26c4e2694a ("nilfs2: fix issue with flush kernel thread after remount in RO mode because of driver's internal error or metadata corruption") Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: syzbot+d6ca2daf692c7a82f959(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=d6ca2daf692c7a82f959 Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 5436eb0424bd..10def4b55995 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -401,6 +401,7 @@ void nilfs_clear_folio_dirty(struct folio *folio) folio_clear_uptodate(folio); folio_clear_mappedtodisk(folio); + folio_clear_checked(folio); head = folio_buffers(folio); if (head) {

2 months

2
1
0 0

[GIT PULL 01/10] xfs: convert perag to use xarrays

by Darrick J. Wong

Hi Carlos, Please pull this branch with changes for xfs for 6.13-rc1. As usual, I did a test-merge with the main upstream branch as of a few minutes ago, and didn't see any conflicts. Please let me know if you encounter any problems. --D The following changes since commit 59b723cd2adbac2a34fc8e12c74ae26ae45bf230: Linux 6.12-rc6 (2024-11-03 14:05:52 -1000) are available in the Git repository at: https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux.git tags/perag-xarray-6.13_2024-11-05 for you to fetch changes up to d66496578b2a099ea453f56782f1cd2bf63a8029: xfs: insert the pag structures into the xarray later (2024-11-05 13:38:27 -0800) ---------------------------------------------------------------- xfs: convert perag to use xarrays [v5.5 01/10] Convert the xfs_mount perag tree to use an xarray instead of a radix tree. There should be no functional changes here. With a bit of luck, this should all go splendidly. Signed-off-by: Darrick J. Wong <djwong(a)kernel.org> ---------------------------------------------------------------- Christoph Hellwig (22): xfs: fix superfluous clearing of info->low in __xfs_getfsmap_datadev xfs: remove the unused pagb_count field in struct xfs_perag xfs: remove the unused pag_active_wq field in struct xfs_perag xfs: pass a pag to xfs_difree_inode_chunk xfs: remove the agno argument to xfs_free_ag_extent xfs: add xfs_agbno_to_fsb and xfs_agbno_to_daddr helpers xfs: add a xfs_agino_to_ino helper xfs: pass a pag to xfs_extent_busy_{search,reuse} xfs: keep a reference to the pag for busy extents xfs: remove the mount field from struct xfs_busy_extents xfs: remove the unused trace_xfs_iwalk_ag trace point xfs: remove the unused xrep_bmap_walk_rmap trace point xfs: constify pag arguments to trace points xfs: pass a perag structure to the xfs_ag_resv_init_error trace point xfs: pass objects to the xfs_irec_merge_{pre,post} trace points xfs: pass the iunlink item to the xfs_iunlink_update_dinode trace point xfs: pass objects to the xrep_ibt_walk_rmap tracepoint xfs: pass the pag to the trace_xrep_calc_ag_resblks{,_btsize} trace points xfs: pass the pag to the xrep_newbt_extent_class tracepoints xfs: convert remaining trace points to pass pag structures xfs: split xfs_initialize_perag xfs: insert the pag structures into the xarray later Darrick J. Wong (1): xfs: fix simplify extent lookup in xfs_can_free_eofblocks fs/xfs/libxfs/xfs_ag.c | 135 ++++++++++++++------------ fs/xfs/libxfs/xfs_ag.h | 30 +++++- fs/xfs/libxfs/xfs_ag_resv.c | 3 +- fs/xfs/libxfs/xfs_alloc.c | 32 +++---- fs/xfs/libxfs/xfs_alloc.h | 5 +- fs/xfs/libxfs/xfs_alloc_btree.c | 2 +- fs/xfs/libxfs/xfs_btree.c | 7 +- fs/xfs/libxfs/xfs_ialloc.c | 67 ++++++------- fs/xfs/libxfs/xfs_ialloc_btree.c | 2 +- fs/xfs/libxfs/xfs_inode_util.c | 4 +- fs/xfs/libxfs/xfs_refcount.c | 11 +-- fs/xfs/libxfs/xfs_refcount_btree.c | 3 +- fs/xfs/libxfs/xfs_rmap_btree.c | 2 +- fs/xfs/scrub/agheader_repair.c | 16 +--- fs/xfs/scrub/alloc_repair.c | 10 +- fs/xfs/scrub/bmap.c | 5 +- fs/xfs/scrub/bmap_repair.c | 4 +- fs/xfs/scrub/common.c | 2 +- fs/xfs/scrub/cow_repair.c | 18 ++-- fs/xfs/scrub/ialloc.c | 8 +- fs/xfs/scrub/ialloc_repair.c | 25 ++--- fs/xfs/scrub/newbt.c | 46 ++++----- fs/xfs/scrub/reap.c | 8 +- fs/xfs/scrub/refcount_repair.c | 5 +- fs/xfs/scrub/repair.c | 13 ++- fs/xfs/scrub/rmap_repair.c | 9 +- fs/xfs/scrub/trace.h | 161 +++++++++++++++---------------- fs/xfs/xfs_bmap_util.c | 8 +- fs/xfs/xfs_buf_item_recover.c | 5 +- fs/xfs/xfs_discard.c | 20 ++-- fs/xfs/xfs_extent_busy.c | 31 +++--- fs/xfs/xfs_extent_busy.h | 14 ++- fs/xfs/xfs_extfree_item.c | 4 +- fs/xfs/xfs_filestream.c | 5 +- fs/xfs/xfs_fsmap.c | 25 ++--- fs/xfs/xfs_health.c | 8 +- fs/xfs/xfs_inode.c | 5 +- fs/xfs/xfs_iunlink_item.c | 13 ++- fs/xfs/xfs_iwalk.c | 17 ++-- fs/xfs/xfs_log_cil.c | 3 +- fs/xfs/xfs_log_recover.c | 5 +- fs/xfs/xfs_trace.c | 1 + fs/xfs/xfs_trace.h | 191 ++++++++++++++++--------------------- fs/xfs/xfs_trans.c | 2 +- 44 files changed, 459 insertions(+), 531 deletions(-)

2 months

1
0
0 0

+ util_macrosh-fix-rework-find_closest-macros.patch added to mm-nonmm-unstable branch

by Andrew Morton

The patch titled Subject: util_macros.h: fix/rework find_closest() macros has been added to the -mm mm-nonmm-unstable branch. Its filename is util_macrosh-fix-rework-find_closest-macros.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-nonmm-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Alexandru Ardelean <aardelean(a)baylibre.com> Subject: util_macros.h: fix/rework find_closest() macros Date: Tue, 5 Nov 2024 16:54:05 +0200 A bug was found in the find_closest() (find_closest_descending() is also affected after some testing), where for certain values with small progressions, the rounding (done by averaging 2 values) causes an incorrect index to be returned. The rounding issues occur for progressions of 1, 2 and 3. It goes away when the progression/interval between two values is 4 or larger. It's particularly bad for progressions of 1. For example if there's an array of 'a = { 1, 2, 3 }', using 'find_closest(2, a ...)' would return 0 (the index of '1'), rather than returning 1 (the index of '2'). This means that for exact values (with a progression of 1), find_closest() will misbehave and return the index of the value smaller than the one we're searching for. For progressions of 2 and 3, the exact values are obtained correctly; but values aren't approximated correctly (as one would expect). Starting with progressions of 4, all seems to be good (one gets what one would expect). While one could argue that 'find_closest()' should not be used for arrays with progressions of 1 (i.e. '{1, 2, 3, ...}', the macro should still behave correctly. The bug was found while testing the 'drivers/iio/adc/ad7606.c', specifically the oversampling feature. For reference, the oversampling values are listed as: static const unsigned int ad7606_oversampling_avail[7] = { 1, 2, 4, 8, 16, 32, 64, }; When doing: 1. $ echo 1 > /sys/bus/iio/devices/iio\:device0/oversampling_ratio $ cat /sys/bus/iio/devices/iio\:device0/oversampling_ratio 1 # this is fine 2. $ echo 2 > /sys/bus/iio/devices/iio\:device0/oversampling_ratio $ cat /sys/bus/iio/devices/iio\:device0/oversampling_ratio 1 # this is wrong; 2 should be returned here 3. $ echo 3 > /sys/bus/iio/devices/iio\:device0/oversampling_ratio $ cat /sys/bus/iio/devices/iio\:device0/oversampling_ratio 2 # this is fine 4. $ echo 4 > /sys/bus/iio/devices/iio\:device0/oversampling_ratio $ cat /sys/bus/iio/devices/iio\:device0/oversampling_ratio 4 # this is fine And from here-on, the values are as correct (one gets what one would expect.) While writing a kunit test for this bug, a peculiar issue was found for the array in the 'drivers/hwmon/ina2xx.c' & 'drivers/iio/adc/ina2xx-adc.c' drivers. While running the kunit test (for 'ina226_avg_tab' from these drivers): * idx = find_closest([-1 to 2], ina226_avg_tab, ARRAY_SIZE(ina226_avg_tab)); This returns idx == 0, so value. * idx = find_closest(3, ina226_avg_tab, ARRAY_SIZE(ina226_avg_tab)); This returns idx == 0, value 1; and now one could argue whether 3 is closer to 4 or to 1. This quirk only appears for value '3' in this array, but it seems to be a another rounding issue. * And from 4 onwards the 'find_closest'() works fine (one gets what one would expect). This change reworks the find_closest() macros to also check the difference between the left and right elements when 'x'. If the distance to the right is smaller (than the distance to the left), the index is incremented by 1. This also makes redundant the need for using the DIV_ROUND_CLOSEST() macro. In order to accommodate for any mix of negative + positive values, the internal variables '__fc_x', '__fc_mid_x', '__fc_left' & '__fc_right' are forced to 'long' type. This also addresses any potential bugs/issues with 'x' being of an unsigned type. In those situations any comparison between signed & unsigned would be promoted to a comparison between 2 unsigned numbers; this is especially annoying when '__fc_left' & '__fc_right' underflow. The find_closest_descending() macro was also reworked and duplicated from the find_closest(), and it is being iterated in reverse. The main reason for this is to get the same indices as 'find_closest()' (but in reverse). The comparison for '__fc_right < __fc_left' favors going the array in ascending order. For example for array '{ 1024, 512, 256, 128, 64, 16, 4, 1 }' and x = 3, we get: __fc_mid_x = 2 __fc_left = -1 __fc_right = -2 Then '__fc_right < __fc_left' evaluates to true and '__fc_i++' becomes 7 which is not quite incorrect, but 3 is closer to 4 than to 1. This change has been validated with the kunit from the next patch. Link: https://lkml.kernel.org/r/20241105145406.554365-1-aardelean@baylibre.com Fixes: 95d119528b0b ("util_macros.h: add find_closest() macro") Signed-off-by: Alexandru Ardelean <aardelean(a)baylibre.com> Cc: Bartosz Golaszewski <bartosz.golaszewski(a)linaro.org> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/util_macros.h | 56 ++++++++++++++++++++++++---------- 1 file changed, 40 insertions(+), 16 deletions(-) --- a/include/linux/util_macros.h~util_macrosh-fix-rework-find_closest-macros +++ a/include/linux/util_macros.h @@ -4,19 +4,6 @@ #include <linux/math.h> -#define __find_closest(x, a, as, op) \ -({ \ - typeof(as) __fc_i, __fc_as = (as) - 1; \ - typeof(x) __fc_x = (x); \ - typeof(*a) const *__fc_a = (a); \ - for (__fc_i = 0; __fc_i < __fc_as; __fc_i++) { \ - if (__fc_x op DIV_ROUND_CLOSEST(__fc_a[__fc_i] + \ - __fc_a[__fc_i + 1], 2)) \ - break; \ - } \ - (__fc_i); \ -}) - /** * find_closest - locate the closest element in a sorted array * @x: The reference value. @@ -25,8 +12,27 @@ * @as: Size of 'a'. * * Returns the index of the element closest to 'x'. + * Note: If using an array of negative numbers (or mixed positive numbers), + * then be sure that 'x' is of a signed-type to get good results. */ -#define find_closest(x, a, as) __find_closest(x, a, as, <=) +#define find_closest(x, a, as) \ +({ \ + typeof(as) __fc_i, __fc_as = (as) - 1; \ + long __fc_mid_x, __fc_x = (x); \ + long __fc_left, __fc_right; \ + typeof(*a) const *__fc_a = (a); \ + for (__fc_i = 0; __fc_i < __fc_as; __fc_i++) { \ + __fc_mid_x = (__fc_a[__fc_i] + __fc_a[__fc_i + 1]) / 2; \ + if (__fc_x <= __fc_mid_x) { \ + __fc_left = __fc_x - __fc_a[__fc_i]; \ + __fc_right = __fc_a[__fc_i + 1] - __fc_x; \ + if (__fc_right < __fc_left) \ + __fc_i++; \ + break; \ + } \ + } \ + (__fc_i); \ +}) /** * find_closest_descending - locate the closest element in a sorted array @@ -36,9 +42,27 @@ * @as: Size of 'a'. * * Similar to find_closest() but 'a' is expected to be sorted in descending - * order. + * order. The iteration is done in reverse order, so that the comparison + * of '__fc_right' & '__fc_left' also works for unsigned numbers. */ -#define find_closest_descending(x, a, as) __find_closest(x, a, as, >=) +#define find_closest_descending(x, a, as) \ +({ \ + typeof(as) __fc_i, __fc_as = (as) - 1; \ + long __fc_mid_x, __fc_x = (x); \ + long __fc_left, __fc_right; \ + typeof(*a) const *__fc_a = (a); \ + for (__fc_i = __fc_as; __fc_i >= 1; __fc_i--) { \ + __fc_mid_x = (__fc_a[__fc_i] + __fc_a[__fc_i - 1]) / 2; \ + if (__fc_x <= __fc_mid_x) { \ + __fc_left = __fc_x - __fc_a[__fc_i]; \ + __fc_right = __fc_a[__fc_i - 1] - __fc_x; \ + if (__fc_right < __fc_left) \ + __fc_i--; \ + break; \ + } \ + } \ + (__fc_i); \ +}) /** * is_insidevar - check if the @ptr points inside the @var memory range. _ Patches currently in -mm which might be from aardelean(a)baylibre.com are util_macrosh-fix-rework-find_closest-macros.patch lib-util_macros_kunit-add-kunit-test-for-util_macrosh.patch

2 months

1
0
0 0

[REGRESSION] The iwl4965 driver broke somewhere between 6.10.10 and 6.11.5 (probably 6.11rc)

by Alf Marius

Hi, I recently installed Arch Linux on an old laptop (Fujitsu-Siemens AMILO Xi 2550) and noticed that: - when booting Linux from the Arch ISO (kernel version 6.10.10) WIFI is working fine - after installing Arch Linux from the ISO and booting (kernel version 6.11.5) WIFI was not working properly By "not working properly" I mean: downloading small files or installing a few small packages was working ok, but when downloading larger files or installing larger packages with lots of dependencies, the connection would gradually slow down and eventually die. I reported this on the Arch Linux forum (https://bbs.archlinux.org/viewtopic.php?pid=2206757) and some helpful memeber suggested that this might be the commit that broke things: https://github.com/torvalds/linux/commit/02b682d54598f61cbb7dbb14d98ec18011… An Arch Linux packet manager (gromit) helped me debug this issue by building a couple of kernels that I tested. - https://pkgbuild.com/\~gromit/linux-bisection-kernels/linux-mainline-6.12rc… - https://pkgbuild.com/\~gromit/linux-bisection-kernels/linux-mainline-6.12rc… The first one didn't work, but the second (in which he reverted the commit linked above) did fix my problem. So, I guess this commit should be investigated by those in the know. Thats why I also added Andrii and Kalle to CC as they are listed in the commit message. My network controller: Intel corporation PRO/Wireless 4965 AG or AGN [Kedron] Network Connection (rev 61) Kernel driver in use: iwl4965 This is my first kernel bug report, hope I did everything right :) I'm ofc willing to help provide more info and debug locally here to help solve this issue. Thanks and good night Alf :) -- "The generation of random numbers is too important to be left to chance."

2 months

1
0
0 0

[PATCHSET v5.5 01/10] xfs: convert perag to use xarrays

by Darrick J. Wong

Hi all, Convert the xfs_mount perag tree to use an xarray instead of a radix tree. There should be no functional changes here. If you're going to start using this code, I strongly recommend pulling from my git trees, which are linked below. With a bit of luck, this should all go splendidly. Comments and questions are, as always, welcome. --D kernel git tree: https://git.kernel.org/cgit/linux/kernel/git/djwong/xfs-linux.git/log/?h=pe… --- Commits in this patchset: * xfs: fix simplify extent lookup in xfs_can_free_eofblocks * xfs: fix superfluous clearing of info->low in __xfs_getfsmap_datadev * xfs: remove the unused pagb_count field in struct xfs_perag * xfs: remove the unused pag_active_wq field in struct xfs_perag * xfs: pass a pag to xfs_difree_inode_chunk * xfs: remove the agno argument to xfs_free_ag_extent * xfs: add xfs_agbno_to_fsb and xfs_agbno_to_daddr helpers * xfs: add a xfs_agino_to_ino helper * xfs: pass a pag to xfs_extent_busy_{search,reuse} * xfs: keep a reference to the pag for busy extents * xfs: remove the mount field from struct xfs_busy_extents * xfs: remove the unused trace_xfs_iwalk_ag trace point * xfs: remove the unused xrep_bmap_walk_rmap trace point * xfs: constify pag arguments to trace points * xfs: pass a perag structure to the xfs_ag_resv_init_error trace point * xfs: pass objects to the xfs_irec_merge_{pre,post} trace points * xfs: pass the iunlink item to the xfs_iunlink_update_dinode trace point * xfs: pass objects to the xrep_ibt_walk_rmap tracepoint * xfs: pass the pag to the trace_xrep_calc_ag_resblks{,_btsize} trace points * xfs: pass the pag to the xrep_newbt_extent_class tracepoints * xfs: convert remaining trace points to pass pag structures * xfs: split xfs_initialize_perag * xfs: insert the pag structures into the xarray later --- fs/xfs/libxfs/xfs_ag.c | 135 ++++++++++++++----------- fs/xfs/libxfs/xfs_ag.h | 30 +++++- fs/xfs/libxfs/xfs_ag_resv.c | 3 - fs/xfs/libxfs/xfs_alloc.c | 32 +++--- fs/xfs/libxfs/xfs_alloc.h | 5 - fs/xfs/libxfs/xfs_alloc_btree.c | 2 fs/xfs/libxfs/xfs_btree.c | 7 + fs/xfs/libxfs/xfs_ialloc.c | 67 ++++++------- fs/xfs/libxfs/xfs_ialloc_btree.c | 2 fs/xfs/libxfs/xfs_inode_util.c | 4 - fs/xfs/libxfs/xfs_refcount.c | 11 +- fs/xfs/libxfs/xfs_refcount_btree.c | 3 - fs/xfs/libxfs/xfs_rmap_btree.c | 2 fs/xfs/scrub/agheader_repair.c | 16 +-- fs/xfs/scrub/alloc_repair.c | 10 +- fs/xfs/scrub/bmap.c | 5 - fs/xfs/scrub/bmap_repair.c | 4 - fs/xfs/scrub/common.c | 2 fs/xfs/scrub/cow_repair.c | 18 +-- fs/xfs/scrub/ialloc.c | 8 +- fs/xfs/scrub/ialloc_repair.c | 25 ++--- fs/xfs/scrub/newbt.c | 46 ++++----- fs/xfs/scrub/reap.c | 8 +- fs/xfs/scrub/refcount_repair.c | 5 - fs/xfs/scrub/repair.c | 13 +- fs/xfs/scrub/rmap_repair.c | 9 +- fs/xfs/scrub/trace.h | 161 ++++++++++++++---------------- fs/xfs/xfs_bmap_util.c | 8 +- fs/xfs/xfs_buf_item_recover.c | 5 - fs/xfs/xfs_discard.c | 20 ++-- fs/xfs/xfs_extent_busy.c | 31 ++---- fs/xfs/xfs_extent_busy.h | 14 +-- fs/xfs/xfs_extfree_item.c | 4 - fs/xfs/xfs_filestream.c | 5 - fs/xfs/xfs_fsmap.c | 25 ++--- fs/xfs/xfs_health.c | 8 +- fs/xfs/xfs_inode.c | 5 - fs/xfs/xfs_iunlink_item.c | 13 +- fs/xfs/xfs_iwalk.c | 17 ++- fs/xfs/xfs_log_cil.c | 3 - fs/xfs/xfs_log_recover.c | 5 - fs/xfs/xfs_trace.c | 1 fs/xfs/xfs_trace.h | 191 +++++++++++++++--------------------- fs/xfs/xfs_trans.c | 2 44 files changed, 459 insertions(+), 531 deletions(-)

2 months

1
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror November 2024