October 2024 - Linux-stable-mirror

+ nilfs2-propagate-directory-read-errors-from-nilfs_find_entry.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: nilfs2: propagate directory read errors from nilfs_find_entry() has been added to the -mm mm-hotfixes-unstable branch. Its filename is nilfs2-propagate-directory-read-errors-from-nilfs_find_entry.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Subject: nilfs2: propagate directory read errors from nilfs_find_entry() Date: Fri, 4 Oct 2024 12:35:31 +0900 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 The current interface of nilfs_find_entry() and its callers is outdated and cannot propagate error codes such as -EIO and -ENOMEM returned via nilfs_find_entry(), so fix it together.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> --- fs/nilfs2/dir.c | 48 ++++++++++++++++++++++---------------------- fs/nilfs2/namei.c | 39 +++++++++++++++++++++++------------ fs/nilfs2/nilfs.h | 2 - 3 files changed, 52 insertions(+), 37 deletions(-) --- a/fs/nilfs2/dir.c~nilfs2-propagate-directory-read-errors-from-nilfs_find_entry +++ a/fs/nilfs2/dir.c @@ -289,7 +289,7 @@ static int nilfs_readdir(struct file *fi * 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 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 } } 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, --- a/fs/nilfs2/namei.c~nilfs2-propagate-directory-read-errors-from-nilfs_find_entry +++ a/fs/nilfs2/namei.c @@ -55,12 +55,20 @@ nilfs_lookup(struct inode *dir, struct d { 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 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 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 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; --- a/fs/nilfs2/nilfs.h~nilfs2-propagate-directory-read-errors-from-nilfs_find_entry +++ a/fs/nilfs2/nilfs.h @@ -254,7 +254,7 @@ static inline __u32 nilfs_mask_flags(umo /* 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 **); _ Patches currently in -mm which might be from konishi.ryusuke(a)gmail.com are nilfs2-propagate-directory-read-errors-from-nilfs_find_entry.patch

1 month

1
0
0 0

[merged mm-hotfixes-stable] secretmem-disable-memfd_secret-if-arch-cannot-set-direct-map.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: secretmem: disable memfd_secret() if arch cannot set direct map has been removed from the -mm tree. Its filename was secretmem-disable-memfd_secret-if-arch-cannot-set-direct-map.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: Patrick Roy <roypat(a)amazon.co.uk> Subject: secretmem: disable memfd_secret() if arch cannot set direct map Date: Tue, 1 Oct 2024 09:00:41 +0100 Return -ENOSYS from memfd_secret() syscall if !can_set_direct_map(). This is the case for example on some arm64 configurations, where marking 4k PTEs in the direct map not present can only be done if the direct map is set up at 4k granularity in the first place (as ARM's break-before-make semantics do not easily allow breaking apart large/gigantic pages). More precisely, on arm64 systems with !can_set_direct_map(), set_direct_map_invalid_noflush() is a no-op, however it returns success (0) instead of an error. This means that memfd_secret will seemingly "work" (e.g. syscall succeeds, you can mmap the fd and fault in pages), but it does not actually achieve its goal of removing its memory from the direct map. Note that with this patch, memfd_secret() will start erroring on systems where can_set_direct_map() returns false (arm64 with CONFIG_RODATA_FULL_DEFAULT_ENABLED=n, CONFIG_DEBUG_PAGEALLOC=n and CONFIG_KFENCE=n), but that still seems better than the current silent failure. Since CONFIG_RODATA_FULL_DEFAULT_ENABLED defaults to 'y', most arm64 systems actually have a working memfd_secret() and aren't be affected. From going through the iterations of the original memfd_secret patch series, it seems that disabling the syscall in these scenarios was the intended behavior [1] (preferred over having set_direct_map_invalid_noflush return an error as that would result in SIGBUSes at page-fault time), however the check for it got dropped between v16 [2] and v17 [3], when secretmem moved away from CMA allocations. [1]: https://lore.kernel.org/lkml/20201124164930.GK8537@kernel.org/ [2]: https://lore.kernel.org/lkml/20210121122723.3446-11-rppt@kernel.org/#t [3]: https://lore.kernel.org/lkml/20201125092208.12544-10-rppt@kernel.org/ Link: https://lkml.kernel.org/r/20241001080056.784735-1-roypat@amazon.co.uk Fixes: 1507f51255c9 ("mm: introduce memfd_secret system call to create "secret" memory areas") Signed-off-by: Patrick Roy <roypat(a)amazon.co.uk> Reviewed-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Cc: Alexander Graf <graf(a)amazon.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: James Gowans <jgowans(a)amazon.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/secretmem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) --- a/mm/secretmem.c~secretmem-disable-memfd_secret-if-arch-cannot-set-direct-map +++ a/mm/secretmem.c @@ -238,7 +238,7 @@ SYSCALL_DEFINE1(memfd_secret, unsigned i /* make sure local flags do not confict with global fcntl.h */ BUILD_BUG_ON(SECRETMEM_FLAGS_MASK & O_CLOEXEC); - if (!secretmem_enable) + if (!secretmem_enable || !can_set_direct_map()) return -ENOSYS; if (flags & ~(SECRETMEM_FLAGS_MASK | O_CLOEXEC)) @@ -280,7 +280,7 @@ static struct file_system_type secretmem static int __init secretmem_init(void) { - if (!secretmem_enable) + if (!secretmem_enable || !can_set_direct_map()) return 0; secretmem_mnt = kern_mount(&secretmem_fs); _ Patches currently in -mm which might be from roypat(a)amazon.co.uk are

1 month

1
0
0 0

[merged mm-hotfixes-stable] fs-proc-kcorec-allow-translation-of-physical-memory-addresses.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: fs/proc/kcore.c: allow translation of physical memory addresses has been removed from the -mm tree. Its filename was fs-proc-kcorec-allow-translation-of-physical-memory-addresses.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: Alexander Gordeev <agordeev(a)linux.ibm.com> Subject: fs/proc/kcore.c: allow translation of physical memory addresses Date: Mon, 30 Sep 2024 14:21:19 +0200 When /proc/kcore is read an attempt to read the first two pages results in HW-specific page swap on s390 and another (so called prefix) pages are accessed instead. That leads to a wrong read. Allow architecture-specific translation of memory addresses using kc_xlate_dev_mem_ptr() and kc_unxlate_dev_mem_ptr() callbacks similarily to /dev/mem xlate_dev_mem_ptr() and unxlate_dev_mem_ptr() callbacks. That way an architecture can deal with specific physical memory ranges. Re-use the existing /dev/mem callback implementation on s390, which handles the described prefix pages swapping correctly. For other architectures the default callback is basically NOP. It is expected the condition (vaddr == __va(__pa(vaddr))) always holds true for KCORE_RAM memory type. Link: https://lkml.kernel.org/r/20240930122119.1651546-1-agordeev@linux.ibm.com Signed-off-by: Alexander Gordeev <agordeev(a)linux.ibm.com> Suggested-by: Heiko Carstens <hca(a)linux.ibm.com> Cc: Vasily Gorbik <gor(a)linux.ibm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- arch/s390/include/asm/io.h | 2 + fs/proc/kcore.c | 36 +++++++++++++++++++++++++++++++++-- 2 files changed, 36 insertions(+), 2 deletions(-) --- a/arch/s390/include/asm/io.h~fs-proc-kcorec-allow-translation-of-physical-memory-addresses +++ a/arch/s390/include/asm/io.h @@ -16,8 +16,10 @@ #include <asm/pci_io.h> #define xlate_dev_mem_ptr xlate_dev_mem_ptr +#define kc_xlate_dev_mem_ptr xlate_dev_mem_ptr void *xlate_dev_mem_ptr(phys_addr_t phys); #define unxlate_dev_mem_ptr unxlate_dev_mem_ptr +#define kc_unxlate_dev_mem_ptr unxlate_dev_mem_ptr void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr); #define IO_SPACE_LIMIT 0 --- a/fs/proc/kcore.c~fs-proc-kcorec-allow-translation-of-physical-memory-addresses +++ a/fs/proc/kcore.c @@ -50,6 +50,20 @@ static struct proc_dir_entry *proc_root_ #define kc_offset_to_vaddr(o) ((o) + PAGE_OFFSET) #endif +#ifndef kc_xlate_dev_mem_ptr +#define kc_xlate_dev_mem_ptr kc_xlate_dev_mem_ptr +static inline void *kc_xlate_dev_mem_ptr(phys_addr_t phys) +{ + return __va(phys); +} +#endif +#ifndef kc_unxlate_dev_mem_ptr +#define kc_unxlate_dev_mem_ptr kc_unxlate_dev_mem_ptr +static inline void kc_unxlate_dev_mem_ptr(phys_addr_t phys, void *virt) +{ +} +#endif + static LIST_HEAD(kclist_head); static DECLARE_RWSEM(kclist_lock); static int kcore_need_update = 1; @@ -471,6 +485,8 @@ static ssize_t read_kcore_iter(struct ki while (buflen) { struct page *page; unsigned long pfn; + phys_addr_t phys; + void *__start; /* * If this is the first iteration or the address is not within @@ -537,7 +553,8 @@ static ssize_t read_kcore_iter(struct ki } break; case KCORE_RAM: - pfn = __pa(start) >> PAGE_SHIFT; + phys = __pa(start); + pfn = phys >> PAGE_SHIFT; page = pfn_to_online_page(pfn); /* @@ -557,13 +574,28 @@ static ssize_t read_kcore_iter(struct ki fallthrough; case KCORE_VMEMMAP: case KCORE_TEXT: + if (m->type == KCORE_RAM) { + __start = kc_xlate_dev_mem_ptr(phys); + if (!__start) { + ret = -ENOMEM; + if (iov_iter_zero(tsz, iter) != tsz) + ret = -EFAULT; + goto out; + } + } else { + __start = (void *)start; + } + /* * Sadly we must use a bounce buffer here to be able to * make use of copy_from_kernel_nofault(), as these * memory regions might not always be mapped on all * architectures. */ - if (copy_from_kernel_nofault(buf, (void *)start, tsz)) { + ret = copy_from_kernel_nofault(buf, __start, tsz); + if (m->type == KCORE_RAM) + kc_unxlate_dev_mem_ptr(phys, __start); + if (ret) { if (iov_iter_zero(tsz, iter) != tsz) { ret = -EFAULT; goto out; _ Patches currently in -mm which might be from agordeev(a)linux.ibm.com are

1 month

1
0
0 0

[merged mm-hotfixes-stable] selftests-mm-fixed-incorrect-buffer-mirror-size-in-hmm2-double_map-test.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: selftests/mm: fix incorrect buffer->mirror size in hmm2 double_map test has been removed from the -mm tree. Its filename was selftests-mm-fixed-incorrect-buffer-mirror-size-in-hmm2-double_map-test.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: Donet Tom <donettom(a)linux.ibm.com> Subject: selftests/mm: fix incorrect buffer->mirror size in hmm2 double_map test Date: Fri, 27 Sep 2024 00:07:52 -0500 The hmm2 double_map test was failing due to an incorrect buffer->mirror size. The buffer->mirror size was 6, while buffer->ptr size was 6 * PAGE_SIZE. The test failed because the kernel's copy_to_user function was attempting to copy a 6 * PAGE_SIZE buffer to buffer->mirror. Since the size of buffer->mirror was incorrect, copy_to_user failed. This patch corrects the buffer->mirror size to 6 * PAGE_SIZE. Test Result without this patch ============================== # RUN hmm2.hmm2_device_private.double_map ... # hmm-tests.c:1680:double_map:Expected ret (-14) == 0 (0) # double_map: Test terminated by assertion # FAIL hmm2.hmm2_device_private.double_map not ok 53 hmm2.hmm2_device_private.double_map Test Result with this patch =========================== # RUN hmm2.hmm2_device_private.double_map ... # OK hmm2.hmm2_device_private.double_map ok 53 hmm2.hmm2_device_private.double_map Link: https://lkml.kernel.org/r/20240927050752.51066-1-donettom@linux.ibm.com Fixes: fee9f6d1b8df ("mm/hmm/test: add selftests for HMM") Signed-off-by: Donet Tom <donettom(a)linux.ibm.com> Reviewed-by: Muhammad Usama Anjum <usama.anjum(a)collabora.com> Cc: J��r��me Glisse <jglisse(a)redhat.com> Cc: Kees Cook <keescook(a)chromium.org> Cc: Mark Brown <broonie(a)kernel.org> Cc: Przemek Kitszel <przemyslaw.kitszel(a)intel.com> Cc: Ritesh Harjani (IBM) <ritesh.list(a)gmail.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Ralph Campbell <rcampbell(a)nvidia.com> Cc: Jason Gunthorpe <jgg(a)mellanox.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- tools/testing/selftests/mm/hmm-tests.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/tools/testing/selftests/mm/hmm-tests.c~selftests-mm-fixed-incorrect-buffer-mirror-size-in-hmm2-double_map-test +++ a/tools/testing/selftests/mm/hmm-tests.c @@ -1657,7 +1657,7 @@ TEST_F(hmm2, double_map) buffer->fd = -1; buffer->size = size; - buffer->mirror = malloc(npages); + buffer->mirror = malloc(size); ASSERT_NE(buffer->mirror, NULL); /* Reserve a range of addresses. */ _ Patches currently in -mm which might be from donettom(a)linux.ibm.com are

1 month

1
0
0 0

[merged mm-hotfixes-stable] device-dax-correct-pgoff-align-in-dax_set_mapping.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: device-dax: correct pgoff align in dax_set_mapping() has been removed from the -mm tree. Its filename was device-dax-correct-pgoff-align-in-dax_set_mapping.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: "Kun(llfl)" <llfl(a)linux.alibaba.com> Subject: device-dax: correct pgoff align in dax_set_mapping() Date: Fri, 27 Sep 2024 15:45:09 +0800 pgoff should be aligned using ALIGN_DOWN() instead of ALIGN(). Otherwise, vmf->address not aligned to fault_size will be aligned to the next alignment, that can result in memory failure getting the wrong address. It's a subtle situation that only can be observed in page_mapped_in_vma() after the page is page fault handled by dev_dax_huge_fault. Generally, there is little chance to perform page_mapped_in_vma in dev-dax's page unless in specific error injection to the dax device to trigger an MCE - memory-failure. In that case, page_mapped_in_vma() will be triggered to determine which task is accessing the failure address and kill that task in the end. We used self-developed dax device (which is 2M aligned mapping) , to perform error injection to random address. It turned out that error injected to non-2M-aligned address was causing endless MCE until panic. Because page_mapped_in_vma() kept resulting wrong address and the task accessing the failure address was never killed properly: [ 3783.719419] Memory failure: 0x200c9742: recovery action for dax page: Recovered [ 3784.049006] mce: Uncorrected hardware memory error in user-access at 200c9742380 [ 3784.049190] Memory failure: 0x200c9742: recovery action for dax page: Recovered [ 3784.448042] mce: Uncorrected hardware memory error in user-access at 200c9742380 [ 3784.448186] Memory failure: 0x200c9742: recovery action for dax page: Recovered [ 3784.792026] mce: Uncorrected hardware memory error in user-access at 200c9742380 [ 3784.792179] Memory failure: 0x200c9742: recovery action for dax page: Recovered [ 3785.162502] mce: Uncorrected hardware memory error in user-access at 200c9742380 [ 3785.162633] Memory failure: 0x200c9742: recovery action for dax page: Recovered [ 3785.461116] mce: Uncorrected hardware memory error in user-access at 200c9742380 [ 3785.461247] Memory failure: 0x200c9742: recovery action for dax page: Recovered [ 3785.764730] mce: Uncorrected hardware memory error in user-access at 200c9742380 [ 3785.764859] Memory failure: 0x200c9742: recovery action for dax page: Recovered [ 3786.042128] mce: Uncorrected hardware memory error in user-access at 200c9742380 [ 3786.042259] Memory failure: 0x200c9742: recovery action for dax page: Recovered [ 3786.464293] mce: Uncorrected hardware memory error in user-access at 200c9742380 [ 3786.464423] Memory failure: 0x200c9742: recovery action for dax page: Recovered [ 3786.818090] mce: Uncorrected hardware memory error in user-access at 200c9742380 [ 3786.818217] Memory failure: 0x200c9742: recovery action for dax page: Recovered [ 3787.085297] mce: Uncorrected hardware memory error in user-access at 200c9742380 [ 3787.085424] Memory failure: 0x200c9742: recovery action for dax page: Recovered It took us several weeks to pinpoint this problem,�� but we eventually used bpftrace to trace the page fault and mce address and successfully identified the issue. Joao added: ; Likely we never reproduce in production because we always pin : device-dax regions in the region align they provide (Qemu does : similarly with prealloc in hugetlb/file backed memory). I think this : bug requires that we touch *unpinned* device-dax regions unaligned to : the device-dax selected alignment (page size i.e. 4K/2M/1G) Link: https://lkml.kernel.org/r/23c02a03e8d666fef11bbe13e85c69c8b4ca0624.17274216… Fixes: b9b5777f09be ("device-dax: use ALIGN() for determining pgoff") Signed-off-by: Kun(llfl) <llfl(a)linux.alibaba.com> Tested-by: JianXiong Zhao <zhaojianxiong.zjx(a)alibaba-inc.com> Reviewed-by: Joao Martins <joao.m.martins(a)oracle.com> Cc: Dan Williams <dan.j.williams(a)intel.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- drivers/dax/device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/drivers/dax/device.c~device-dax-correct-pgoff-align-in-dax_set_mapping +++ a/drivers/dax/device.c @@ -86,7 +86,7 @@ static void dax_set_mapping(struct vm_fa nr_pages = 1; pgoff = linear_page_index(vmf->vma, - ALIGN(vmf->address, fault_size)); + ALIGN_DOWN(vmf->address, fault_size)); for (i = 0; i < nr_pages; i++) { struct page *page = pfn_to_page(pfn_t_to_pfn(pfn) + i); _ Patches currently in -mm which might be from llfl(a)linux.alibaba.com are

1 month

1
0
0 0

[merged mm-hotfixes-stable] kthread-unpark-only-parked-kthread.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: kthread: unpark only parked kthread has been removed from the -mm tree. Its filename was kthread-unpark-only-parked-kthread.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: Frederic Weisbecker <frederic(a)kernel.org> Subject: kthread: unpark only parked kthread Date: Fri, 13 Sep 2024 23:46:34 +0200 Calling into kthread unparking unconditionally is mostly harmless when the kthread is already unparked. The wake up is then simply ignored because the target is not in TASK_PARKED state. However if the kthread is per CPU, the wake up is preceded by a call to kthread_bind() which expects the task to be inactive and in TASK_PARKED state, which obviously isn't the case if it is unparked. As a result, calling kthread_stop() on an unparked per-cpu kthread triggers such a warning: WARNING: CPU: 0 PID: 11 at kernel/kthread.c:525 __kthread_bind_mask kernel/kthread.c:525 <TASK> kthread_stop+0x17a/0x630 kernel/kthread.c:707 destroy_workqueue+0x136/0xc40 kernel/workqueue.c:5810 wg_destruct+0x1e2/0x2e0 drivers/net/wireguard/device.c:257 netdev_run_todo+0xe1a/0x1000 net/core/dev.c:10693 default_device_exit_batch+0xa14/0xa90 net/core/dev.c:11769 ops_exit_list net/core/net_namespace.c:178 [inline] cleanup_net+0x89d/0xcc0 net/core/net_namespace.c:640 process_one_work kernel/workqueue.c:3231 [inline] process_scheduled_works+0xa2c/0x1830 kernel/workqueue.c:3312 worker_thread+0x86d/0xd70 kernel/workqueue.c:3393 kthread+0x2f0/0x390 kernel/kthread.c:389 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 </TASK> Fix this with skipping unecessary unparking while stopping a kthread. Link: https://lkml.kernel.org/r/20240913214634.12557-1-frederic@kernel.org Fixes: 5c25b5ff89f0 ("workqueue: Tag bound workers with KTHREAD_IS_PER_CPU") Signed-off-by: Frederic Weisbecker <frederic(a)kernel.org> Reported-by: syzbot+943d34fa3cf2191e3068(a)syzkaller.appspotmail.com Tested-by: syzbot+943d34fa3cf2191e3068(a)syzkaller.appspotmail.com Suggested-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: Hillf Danton <hdanton(a)sina.com> Cc: Tejun Heo <tj(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- kernel/kthread.c | 2 ++ 1 file changed, 2 insertions(+) --- a/kernel/kthread.c~kthread-unpark-only-parked-kthread +++ a/kernel/kthread.c @@ -623,6 +623,8 @@ void kthread_unpark(struct task_struct * { struct kthread *kthread = to_kthread(k); + if (!test_bit(KTHREAD_SHOULD_PARK, &kthread->flags)) + return; /* * Newly created kthread was parked when the CPU was offline. * The binding was lost and we need to set it again. _ Patches currently in -mm which might be from frederic(a)kernel.org are

1 month

1
0
0 0

[PATCH] scsi: fnic: move flush_work initialization out of if block

by Martin Wilck

(resending, sorry - I'd forgotten to add the mailing list) After commit 379a58caa199 ("scsi: fnic: Move fnic_fnic_flush_tx() to a work queue"), it can happen that a work item is sent to an uninitialized work queue. This may has the effect that the item being queued is never actually queued, and any further actions depending on it will not proceed. The following warning is observed while the fnic driver is loaded: kernel: WARNING: CPU: 11 PID: 0 at ../kernel/workqueue.c:1524 __queue_work+0x373/0x410 kernel: <IRQ> kernel: queue_work_on+0x3a/0x50 kernel: fnic_wq_copy_cmpl_handler+0x54a/0x730 [fnic 62fbff0c42e7fb825c60a55cde2fb91facb2ed24] kernel: fnic_isr_msix_wq_copy+0x2d/0x60 [fnic 62fbff0c42e7fb825c60a55cde2fb91facb2ed24] kernel: __handle_irq_event_percpu+0x36/0x1a0 kernel: handle_irq_event_percpu+0x30/0x70 kernel: handle_irq_event+0x34/0x60 kernel: handle_edge_irq+0x7e/0x1a0 kernel: __common_interrupt+0x3b/0xb0 kernel: common_interrupt+0x58/0xa0 kernel: </IRQ> It has been observed that this may break the rediscovery of fibre channel devices after a temporary fabric failure. This patch fixes it by moving the work queue initialization out of an if block in fnic_probe(). Signed-off-by: Martin Wilck <mwilck(a)suse.com> Fixes: 379a58caa199 ("scsi: fnic: Move fnic_fnic_flush_tx() to a work queue") Cc: stable(a)vger.kernel.org --- drivers/scsi/fnic/fnic_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c index 0044717d4486..adec0df24bc4 100644 --- a/drivers/scsi/fnic/fnic_main.c +++ b/drivers/scsi/fnic/fnic_main.c @@ -830,7 +830,6 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) spin_lock_init(&fnic->vlans_lock); INIT_WORK(&fnic->fip_frame_work, fnic_handle_fip_frame); INIT_WORK(&fnic->event_work, fnic_handle_event); - INIT_WORK(&fnic->flush_work, fnic_flush_tx); skb_queue_head_init(&fnic->fip_frame_queue); INIT_LIST_HEAD(&fnic->evlist); INIT_LIST_HEAD(&fnic->vlans); @@ -948,6 +947,7 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&fnic->link_work, fnic_handle_link); INIT_WORK(&fnic->frame_work, fnic_handle_frame); + INIT_WORK(&fnic->flush_work, fnic_flush_tx); skb_queue_head_init(&fnic->frame_queue); skb_queue_head_init(&fnic->tx_queue); -- 2.46.1

1 month

3
2
0 0

[PATCH v2] scsi: ufs: Use pre-calculated offsets in ufshcd_init_lrb

by Avri Altman

Replace manual offset calculations for response_upiu and prd_table in ufshcd_init_lrb() with pre-calculated offsets already stored in the utp_transfer_req_desc structure. The pre-calculated offsets are set differently in ufshcd_host_memory_configure() based on the UFSHCD_QUIRK_PRDT_BYTE_GRAN quirk, ensuring correct alignment and access. Fixes: 26f968d7de82 ("scsi: ufs: Introduce UFSHCD_QUIRK_PRDT_BYTE_GRAN quirk") Cc: stable(a)vger.kernel.org Signed-off-by: Avri Altman <avri.altman(a)wdc.com> --- Changes in v2: - add Fixes: and Cc: stable tags - fix kernel test robot warning about type mismatch by using le16_to_cpu --- drivers/ufs/core/ufshcd.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 8ea5a82503a9..85251c176ef7 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -2919,9 +2919,8 @@ static void ufshcd_init_lrb(struct ufs_hba *hba, struct ufshcd_lrb *lrb, int i) struct utp_transfer_req_desc *utrdlp = hba->utrdl_base_addr; dma_addr_t cmd_desc_element_addr = hba->ucdl_dma_addr + i * ufshcd_get_ucd_size(hba); - u16 response_offset = offsetof(struct utp_transfer_cmd_desc, - response_upiu); - u16 prdt_offset = offsetof(struct utp_transfer_cmd_desc, prd_table); + u16 response_offset = le16_to_cpu(utrdlp[i].response_upiu_offset); + u16 prdt_offset = le16_to_cpu(utrdlp[i].prd_table_offset); lrb->utr_descriptor_ptr = utrdlp + i; lrb->utrd_dma_addr = hba->utrdl_dma_addr + -- 2.25.1

1 month

4
9
0 0

[PATCH 3/3] Bluetooth: Remove debugfs directory on module init failure

by Aaron Thompson

From: Aaron Thompson <dev(a)aaront.org> If bt_init() fails, the debugfs directory currently is not removed. If the module is loaded again after that, the debugfs directory is not set up properly due to the existing directory. # modprobe bluetooth # ls -laF /sys/kernel/debug/bluetooth total 0 drwxr-xr-x 2 root root 0 Sep 27 14:26 ./ drwx------ 31 root root 0 Sep 27 14:25 ../ -r--r--r-- 1 root root 0 Sep 27 14:26 l2cap -r--r--r-- 1 root root 0 Sep 27 14:26 sco # modprobe -r bluetooth # ls -laF /sys/kernel/debug/bluetooth ls: cannot access '/sys/kernel/debug/bluetooth': No such file or directory # # modprobe bluetooth modprobe: ERROR: could not insert 'bluetooth': Invalid argument # dmesg | tail -n 6 Bluetooth: Core ver 2.22 NET: Registered PF_BLUETOOTH protocol family Bluetooth: HCI device and connection manager initialized Bluetooth: HCI socket layer initialized Bluetooth: Faking l2cap_init() failure for testing NET: Unregistered PF_BLUETOOTH protocol family # ls -laF /sys/kernel/debug/bluetooth total 0 drwxr-xr-x 2 root root 0 Sep 27 14:31 ./ drwx------ 31 root root 0 Sep 27 14:26 ../ # # modprobe bluetooth # dmesg | tail -n 7 Bluetooth: Core ver 2.22 debugfs: Directory 'bluetooth' with parent '/' already present! NET: Registered PF_BLUETOOTH protocol family Bluetooth: HCI device and connection manager initialized Bluetooth: HCI socket layer initialized Bluetooth: L2CAP socket layer initialized Bluetooth: SCO socket layer initialized # ls -laF /sys/kernel/debug/bluetooth total 0 drwxr-xr-x 2 root root 0 Sep 27 14:31 ./ drwx------ 31 root root 0 Sep 27 14:26 ../ # Cc: stable(a)vger.kernel.org Fixes: ffcecac6a738 ("Bluetooth: Create root debugfs directory during module init") Signed-off-by: Aaron Thompson <dev(a)aaront.org> --- net/bluetooth/af_bluetooth.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 67604ccec2f4..0d4b171b939a 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -825,6 +825,7 @@ static int __init bt_init(void) bt_sysfs_cleanup(); cleanup_led: bt_leds_cleanup(); + debugfs_remove_recursive(bt_debugfs); return err; } -- 2.39.5

1 month

1
0
0 0

[PATCH 1/3] Bluetooth: ISO: Fix multiple init when debugfs is disabled

by Aaron Thompson

From: Aaron Thompson <dev(a)aaront.org> If bt_debugfs is not created successfully, which happens if either CONFIG_DEBUG_FS or CONFIG_DEBUG_FS_ALLOW_ALL is unset, then iso_init() returns early and does not set iso_inited to true. This means that a subsequent call to iso_init() will result in duplicate calls to proto_register(), bt_sock_register(), etc. With CONFIG_LIST_HARDENED and CONFIG_BUG_ON_DATA_CORRUPTION enabled, the duplicate call to proto_register() triggers this BUG(): list_add double add: new=ffffffffc0b280d0, prev=ffffffffbab56250, next=ffffffffc0b280d0. ------------[ cut here ]------------ kernel BUG at lib/list_debug.c:35! Oops: invalid opcode: 0000 [#1] PREEMPT SMP PTI CPU: 2 PID: 887 Comm: bluetoothd Not tainted 6.10.11-1-ao-desktop #1 RIP: 0010:__list_add_valid_or_report+0x9a/0xa0 ... __list_add_valid_or_report+0x9a/0xa0 proto_register+0x2b5/0x340 iso_init+0x23/0x150 [bluetooth] set_iso_socket_func+0x68/0x1b0 [bluetooth] kmem_cache_free+0x308/0x330 hci_sock_sendmsg+0x990/0x9e0 [bluetooth] __sock_sendmsg+0x7b/0x80 sock_write_iter+0x9a/0x110 do_iter_readv_writev+0x11d/0x220 vfs_writev+0x180/0x3e0 do_writev+0xca/0x100 ... This change removes the early return. The check for iso_debugfs being NULL was unnecessary, it is always NULL when iso_inited is false. Cc: stable(a)vger.kernel.org Fixes: ccf74f2390d6 ("Bluetooth: Add BTPROTO_ISO socket type") Signed-off-by: Aaron Thompson <dev(a)aaront.org> --- net/bluetooth/iso.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index d5e00d0dd1a0..c9eefb43bf47 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -2301,13 +2301,9 @@ int iso_init(void) hci_register_cb(&iso_cb); - if (IS_ERR_OR_NULL(bt_debugfs)) - return 0; - - if (!iso_debugfs) { + if (!IS_ERR_OR_NULL(bt_debugfs)) iso_debugfs = debugfs_create_file("iso", 0444, bt_debugfs, NULL, &iso_debugfs_fops); - } iso_inited = true; -- 2.39.5

1 month

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror October 2024