From 74874c57939444b19993fe3dd6c0b70aba4f468c Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Wed, 2 Oct 2024 08:39:32 +0100 Subject: [PATCH 01/28] mm/mmap: correct error handling in mmap_region() Commit f8d112a4e657 ("mm/mmap: avoid zeroing vma tree in mmap_region()") changed how error handling is performed in mmap_region(). The error value defaults to -ENOMEM, but then gets reassigned immediately to the result of vms_gather_munmap_vmas() if we are performing a MAP_FIXED mapping over existing VMAs (and thus unmapping them). This overwrites the error value, potentially clearing it. After this, we invoke may_expand_vm() and possibly vm_area_alloc(), and check to see if they failed. If they do so, then we perform error-handling logic, but importantly, we do NOT update the error code. This means that, if vms_gather_munmap_vmas() succeeds, but one of these calls does not, the function will return indicating no error, but rather an address value of zero, which is entirely incorrect. Correct this and avoid future confusion by strictly setting error on each and every occasion we jump to the error handling logic, and set the error code immediately prior to doing so. This way we can see at a glance that the error code is always correct. Many thanks to Vegard Nossum who spotted this issue in discussion around this problem. Link: https://lkml.kernel.org/r/20241002073932.13482-1-lorenzo.stoakes@oracle.com Fixes: f8d112a4e657 ("mm/mmap: avoid zeroing vma tree in mmap_region()") Signed-off-by: Lorenzo Stoakes Suggested-by: Vegard Nossum Reviewed-by: Vlastimil Babka Cc: "Liam R. Howlett" Signed-off-by: Andrew Morton --- mm/mmap.c | 32 +++++++++++++++++++++----------- 1 file changed, 21 insertions(+), 11 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index dd4b35a25aeb..9c0fb43064b5 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1371,7 +1371,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, struct maple_tree mt_detach; unsigned long end = addr + len; bool writable_file_mapping = false; - int error = -ENOMEM; + int error; VMA_ITERATOR(vmi, mm, addr); VMG_STATE(vmg, mm, &vmi, addr, end, vm_flags, pgoff); @@ -1396,8 +1396,10 @@ unsigned long mmap_region(struct file *file, unsigned long addr, } /* Check against address space limit. */ - if (!may_expand_vm(mm, vm_flags, pglen - vms.nr_pages)) + if (!may_expand_vm(mm, vm_flags, pglen - vms.nr_pages)) { + error = -ENOMEM; goto abort_munmap; + } /* * Private writable mapping: check memory availability @@ -1405,8 +1407,11 @@ unsigned long mmap_region(struct file *file, unsigned long addr, if (accountable_mapping(file, vm_flags)) { charged = pglen; charged -= vms.nr_accounted; - if (charged && security_vm_enough_memory_mm(mm, charged)) - goto abort_munmap; + if (charged) { + error = security_vm_enough_memory_mm(mm, charged); + if (error) + goto abort_munmap; + } vms.nr_accounted = 0; vm_flags |= VM_ACCOUNT; @@ -1422,8 +1427,10 @@ unsigned long mmap_region(struct file *file, unsigned long addr, * not unmapped, but the maps are removed from the list. */ vma = vm_area_alloc(mm); - if (!vma) + if (!vma) { + error = -ENOMEM; goto unacct_error; + } vma_iter_config(&vmi, addr, end); vma_set_range(vma, addr, end, pgoff); @@ -1453,9 +1460,10 @@ unsigned long mmap_region(struct file *file, unsigned long addr, * Expansion is handled above, merging is handled below. * Drivers should not alter the address of the VMA. */ - error = -EINVAL; - if (WARN_ON((addr != vma->vm_start))) + if (WARN_ON((addr != vma->vm_start))) { + error = -EINVAL; goto close_and_free_vma; + } vma_iter_config(&vmi, addr, end); /* @@ -1500,13 +1508,15 @@ unsigned long mmap_region(struct file *file, unsigned long addr, } /* Allow architectures to sanity-check the vm_flags */ - error = -EINVAL; - if (!arch_validate_flags(vma->vm_flags)) + if (!arch_validate_flags(vma->vm_flags)) { + error = -EINVAL; goto close_and_free_vma; + } - error = -ENOMEM; - if (vma_iter_prealloc(&vmi, vma)) + if (vma_iter_prealloc(&vmi, vma)) { + error = -ENOMEM; goto close_and_free_vma; + } /* Lock the VMA since it is modified after insertion into VMA tree */ vma_start_write(vma); From 08cfa12adf888db98879dbd735bc741360a34168 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Fri, 4 Oct 2024 12:35:31 +0900 Subject: [PATCH 02/28] nilfs2: propagate directory read errors from nilfs_find_entry() Syzbot reported that a task hang occurs in vcs_open() during a fuzzing test for nilfs2. The root cause of this problem is that in nilfs_find_entry(), which searches for directory entries, ignores errors when loading a directory page/folio via nilfs_get_folio() fails. If the filesystem images is corrupted, and the i_size of the directory inode is large, and the directory page/folio is successfully read but fails the sanity check, for example when it is zero-filled, nilfs_check_folio() may continue to spit out error messages in bursts. Fix this issue by propagating the error to the callers when loading a page/folio fails in nilfs_find_entry(). The current interface of nilfs_find_entry() and its callers is outdated and cannot propagate error codes such as -EIO and -ENOMEM returned via nilfs_find_entry(), so fix it together. Link: https://lkml.kernel.org/r/20241004033640.6841-1-konishi.ryusuke@gmail.com Fixes: 2ba466d74ed7 ("nilfs2: directory entry operations") Signed-off-by: Ryusuke Konishi Reported-by: Lizhi Xu Closes: https://lkml.kernel.org/r/20240927013806.3577931-1-lizhi.xu@windriver.com Reported-by: syzbot+8a192e8d090fa9a31135@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=8a192e8d090fa9a31135 Cc: Signed-off-by: Andrew Morton --- fs/nilfs2/dir.c | 48 ++++++++++++++++++++++++----------------------- fs/nilfs2/namei.c | 39 +++++++++++++++++++++++++------------- fs/nilfs2/nilfs.h | 2 +- 3 files changed, 52 insertions(+), 37 deletions(-) diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index fe5b1a30c509..a8602729586a 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -289,7 +289,7 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx) * The folio is mapped and unlocked. When the caller is finished with * the entry, it should call folio_release_kmap(). * - * On failure, returns NULL and the caller should ignore foliop. + * On failure, returns an error pointer and the caller should ignore foliop. */ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, const struct qstr *qstr, struct folio **foliop) @@ -312,22 +312,24 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, do { char *kaddr = nilfs_get_folio(dir, n, foliop); - if (!IS_ERR(kaddr)) { - de = (struct nilfs_dir_entry *)kaddr; - kaddr += nilfs_last_byte(dir, n) - reclen; - while ((char *) de <= kaddr) { - if (de->rec_len == 0) { - nilfs_error(dir->i_sb, - "zero-length directory entry"); - folio_release_kmap(*foliop, kaddr); - goto out; - } - if (nilfs_match(namelen, name, de)) - goto found; - de = nilfs_next_entry(de); + if (IS_ERR(kaddr)) + return ERR_CAST(kaddr); + + de = (struct nilfs_dir_entry *)kaddr; + kaddr += nilfs_last_byte(dir, n) - reclen; + while ((char *)de <= kaddr) { + if (de->rec_len == 0) { + nilfs_error(dir->i_sb, + "zero-length directory entry"); + folio_release_kmap(*foliop, kaddr); + goto out; } - folio_release_kmap(*foliop, kaddr); + if (nilfs_match(namelen, name, de)) + goto found; + de = nilfs_next_entry(de); } + folio_release_kmap(*foliop, kaddr); + if (++n >= npages) n = 0; /* next folio is past the blocks we've got */ @@ -340,7 +342,7 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir, } } while (n != start); out: - return NULL; + return ERR_PTR(-ENOENT); found: ei->i_dir_start_lookup = n; @@ -384,18 +386,18 @@ fail: return NULL; } -ino_t nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr) +int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino) { - ino_t res = 0; struct nilfs_dir_entry *de; struct folio *folio; de = nilfs_find_entry(dir, qstr, &folio); - if (de) { - res = le64_to_cpu(de->inode); - folio_release_kmap(folio, de); - } - return res; + if (IS_ERR(de)) + return PTR_ERR(de); + + *ino = le64_to_cpu(de->inode); + folio_release_kmap(folio, de); + return 0; } void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de, diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index c950139db6ef..4905063790c5 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -55,12 +55,20 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode; ino_t ino; + int res; if (dentry->d_name.len > NILFS_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); - ino = nilfs_inode_by_name(dir, &dentry->d_name); - inode = ino ? nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino) : NULL; + res = nilfs_inode_by_name(dir, &dentry->d_name, &ino); + if (res) { + if (res != -ENOENT) + return ERR_PTR(res); + inode = NULL; + } else { + inode = nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino); + } + return d_splice_alias(inode, dentry); } @@ -263,10 +271,11 @@ static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry) struct folio *folio; int err; - err = -ENOENT; de = nilfs_find_entry(dir, &dentry->d_name, &folio); - if (!de) + if (IS_ERR(de)) { + err = PTR_ERR(de); goto out; + } inode = d_inode(dentry); err = -EIO; @@ -362,10 +371,11 @@ static int nilfs_rename(struct mnt_idmap *idmap, if (unlikely(err)) return err; - err = -ENOENT; old_de = nilfs_find_entry(old_dir, &old_dentry->d_name, &old_folio); - if (!old_de) + if (IS_ERR(old_de)) { + err = PTR_ERR(old_de); goto out; + } if (S_ISDIR(old_inode->i_mode)) { err = -EIO; @@ -382,10 +392,12 @@ static int nilfs_rename(struct mnt_idmap *idmap, if (dir_de && !nilfs_empty_dir(new_inode)) goto out_dir; - err = -ENOENT; - new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, &new_folio); - if (!new_de) + new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, + &new_folio); + if (IS_ERR(new_de)) { + err = PTR_ERR(new_de); goto out_dir; + } nilfs_set_link(new_dir, new_de, new_folio, old_inode); folio_release_kmap(new_folio, new_de); nilfs_mark_inode_dirty(new_dir); @@ -440,12 +452,13 @@ out: */ static struct dentry *nilfs_get_parent(struct dentry *child) { - unsigned long ino; + ino_t ino; + int res; struct nilfs_root *root; - ino = nilfs_inode_by_name(d_inode(child), &dotdot_name); - if (!ino) - return ERR_PTR(-ENOENT); + res = nilfs_inode_by_name(d_inode(child), &dotdot_name, &ino); + if (res) + return ERR_PTR(res); root = NILFS_I(d_inode(child))->i_root; diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index fb1c4c5bae7c..45d03826eaf1 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -254,7 +254,7 @@ static inline __u32 nilfs_mask_flags(umode_t mode, __u32 flags) /* dir.c */ int nilfs_add_link(struct dentry *, struct inode *); -ino_t nilfs_inode_by_name(struct inode *, const struct qstr *); +int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino); int nilfs_make_empty(struct inode *, struct inode *); struct nilfs_dir_entry *nilfs_find_entry(struct inode *, const struct qstr *, struct folio **); From 963a7f4d3b90ee195b895ca06b95757fcba02d1a Mon Sep 17 00:00:00 2001 From: OGAWA Hirofumi Date: Fri, 4 Oct 2024 15:03:49 +0900 Subject: [PATCH 03/28] fat: fix uninitialized variable syszbot produced this with a corrupted fs image. In theory, however an IO error would trigger this also. This affects just an error report, so should not be a serious error. Link: https://lkml.kernel.org/r/87r08wjsnh.fsf@mail.parknet.co.jp Link: https://lkml.kernel.org/r/66ff2c95.050a0220.49194.03e9.GAE@google.com Signed-off-by: OGAWA Hirofumi Reported-by: syzbot+ef0d7bc412553291aa86@syzkaller.appspotmail.com Cc: Signed-off-by: Andrew Morton --- fs/fat/namei_vfat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 6423e1dedf14..15bf32c21ac0 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -1037,7 +1037,7 @@ error_inode: if (corrupt < 0) { fat_fs_error(new_dir->i_sb, "%s: Filesystem corrupted (i_pos %lld)", - __func__, sinfo.i_pos); + __func__, new_i_pos); } goto out; } From e61ef21e27e8deed8c474e9f47f4aa7bc37e138c Mon Sep 17 00:00:00 2001 From: Edward Liaw Date: Thu, 3 Oct 2024 21:17:10 +0000 Subject: [PATCH 04/28] selftests/mm: replace atomic_bool with pthread_barrier_t Patch series "selftests/mm: fix deadlock after pthread_create". On Android arm, pthread_create followed by a fork caused a deadlock in the case where the fork required work to be completed by the created thread. Update the synchronization primitive to use pthread_barrier instead of atomic_bool. Apply the same fix to the wp-fork-with-event test. This patch (of 2): Swap synchronization primitive with pthread_barrier, so that stdatomic.h does not need to be included. The synchronization is needed on Android ARM64; we see a deadlock with pthread_create when the parent thread races forward before the child has a chance to start doing work. Link: https://lkml.kernel.org/r/20241003211716.371786-1-edliaw@google.com Link: https://lkml.kernel.org/r/20241003211716.371786-2-edliaw@google.com Fixes: cff294582798 ("selftests/mm: extend and rename uffd pagemap test") Signed-off-by: Edward Liaw Cc: Lokesh Gidra Cc: Peter Xu Cc: Shuah Khan Cc: Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-common.c | 5 +++-- tools/testing/selftests/mm/uffd-common.h | 3 +-- tools/testing/selftests/mm/uffd-unit-tests.c | 14 ++++++++------ 3 files changed, 12 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index 717539eddf98..852e7281026e 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -18,7 +18,7 @@ bool test_uffdio_wp = true; unsigned long long *count_verify; uffd_test_ops_t *uffd_test_ops; uffd_test_case_ops_t *uffd_test_case_ops; -atomic_bool ready_for_fork; +pthread_barrier_t ready_for_fork; static int uffd_mem_fd_create(off_t mem_size, bool hugetlb) { @@ -519,7 +519,8 @@ void *uffd_poll_thread(void *arg) pollfd[1].fd = pipefd[cpu*2]; pollfd[1].events = POLLIN; - ready_for_fork = true; + /* Ready for parent thread to fork */ + pthread_barrier_wait(&ready_for_fork); for (;;) { ret = poll(pollfd, 2, -1); diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index a70ae10b5f62..3e6228d8e0dc 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -33,7 +33,6 @@ #include #include #include -#include #include "../kselftest.h" #include "vm_util.h" @@ -105,7 +104,7 @@ extern bool map_shared; extern bool test_uffdio_wp; extern unsigned long long *count_verify; extern volatile bool test_uffdio_copy_eexist; -extern atomic_bool ready_for_fork; +extern pthread_barrier_t ready_for_fork; extern uffd_test_ops_t anon_uffd_test_ops; extern uffd_test_ops_t shmem_uffd_test_ops; diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index b3d21eed203d..3db2296ac631 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -774,7 +774,7 @@ static void uffd_sigbus_test_common(bool wp) char c; struct uffd_args args = { 0 }; - ready_for_fork = false; + pthread_barrier_init(&ready_for_fork, NULL, 2); fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); @@ -791,8 +791,9 @@ static void uffd_sigbus_test_common(bool wp) if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) err("uffd_poll_thread create"); - while (!ready_for_fork) - ; /* Wait for the poll_thread to start executing before forking */ + /* Wait for child thread to start before forking */ + pthread_barrier_wait(&ready_for_fork); + pthread_barrier_destroy(&ready_for_fork); pid = fork(); if (pid < 0) @@ -833,7 +834,7 @@ static void uffd_events_test_common(bool wp) char c; struct uffd_args args = { 0 }; - ready_for_fork = false; + pthread_barrier_init(&ready_for_fork, NULL, 2); fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); if (uffd_register(uffd, area_dst, nr_pages * page_size, @@ -844,8 +845,9 @@ static void uffd_events_test_common(bool wp) if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) err("uffd_poll_thread create"); - while (!ready_for_fork) - ; /* Wait for the poll_thread to start executing before forking */ + /* Wait for child thread to start before forking */ + pthread_barrier_wait(&ready_for_fork); + pthread_barrier_destroy(&ready_for_fork); pid = fork(); if (pid < 0) From e142cc87ac4ec618f2ccf5f68aedcd6e28a59d9d Mon Sep 17 00:00:00 2001 From: Edward Liaw Date: Thu, 3 Oct 2024 21:17:11 +0000 Subject: [PATCH 05/28] selftests/mm: fix deadlock for fork after pthread_create on ARM On Android with arm, there is some synchronization needed to avoid a deadlock when forking after pthread_create. Link: https://lkml.kernel.org/r/20241003211716.371786-3-edliaw@google.com Fixes: cff294582798 ("selftests/mm: extend and rename uffd pagemap test") Signed-off-by: Edward Liaw Cc: Lokesh Gidra Cc: Peter Xu Cc: Shuah Khan Cc: Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-unit-tests.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 3db2296ac631..c8a3b1c7edff 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -241,6 +241,9 @@ static void *fork_event_consumer(void *data) fork_event_args *args = data; struct uffd_msg msg = { 0 }; + /* Ready for parent thread to fork */ + pthread_barrier_wait(&ready_for_fork); + /* Read until a full msg received */ while (uffd_read_msg(args->parent_uffd, &msg)); @@ -308,8 +311,12 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) /* Prepare a thread to resolve EVENT_FORK */ if (with_event) { + pthread_barrier_init(&ready_for_fork, NULL, 2); if (pthread_create(&thread, NULL, fork_event_consumer, &args)) err("pthread_create()"); + /* Wait for child thread to start before forking */ + pthread_barrier_wait(&ready_for_fork); + pthread_barrier_destroy(&ready_for_fork); } child = fork(); From 8f3ce3d996bf1e2f8474ec3ddabdb8765c19e6ea Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 7 Oct 2024 16:30:49 +0200 Subject: [PATCH 06/28] mm: percpu: increase PERCPU_DYNAMIC_SIZE_SHIFT on certain builds. Arnd reported a build failure due to the BUILD_BUG_ON() statement in alloc_kmem_cache_cpus(). The test PERCPU_DYNAMIC_EARLY_SIZE < NR_KMALLOC_TYPES * KMALLOC_SHIFT_HIGH * sizeof(struct kmem_cache_cpu) The factors that increase the right side of the equation: - PAGE_SIZE > 4KiB increases KMALLOC_SHIFT_HIGH - For the local_lock_t in kmem_cache_cpu: - PREEMPT_RT adds an actual lock. - LOCKDEP increases the size of the lock. - LOCK_STAT adds additional bytes plus padding to the lockdep structure. The net difference with and without PREEMPT_RT is 88 bytes for the lock_lock_t, 96 bytes for kmem_cache_cpu due to additional padding. This is enough to exceed the 80KiB limit with 16KiB page size - the 8KiB page size is fine. Increase PERCPU_DYNAMIC_SIZE_SHIFT to 13 on configs with PAGE_SIZE larger than 4KiB and LOCKDEP enabled. Link: https://lkml.kernel.org/r/20241007143049.gyMpEu89@linutronix.de Fixes: d8fccd9ca5f9 ("arm64: Allow to enable PREEMPT_RT.") Signed-off-by: Sebastian Andrzej Siewior Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202410020326.iaZIteIx-lkp@intel.com/ Reported-by: Arnd Bergmann Closes: https://lore.kernel.org/20241004095702.637528-1-arnd@kernel.org Acked-by: Arnd Bergmann Acked-by: Vlastimil Babka Acked-by: David Rientjes Cc: Christoph Lameter Cc: Dennis Zhou Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Joonsoo Kim Cc: Pekka Enberg Cc: Roman Gushchin Cc: Tejun Heo Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- include/linux/percpu.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/include/linux/percpu.h b/include/linux/percpu.h index b6321fc49159..52b5ea663b9f 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -41,7 +41,11 @@ PCPU_MIN_ALLOC_SHIFT) #ifdef CONFIG_RANDOM_KMALLOC_CACHES -#define PERCPU_DYNAMIC_SIZE_SHIFT 12 +# if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PAGE_SIZE_4KB) +# define PERCPU_DYNAMIC_SIZE_SHIFT 13 +# else +# define PERCPU_DYNAMIC_SIZE_SHIFT 12 +#endif /* LOCKDEP and PAGE_SIZE > 4KiB */ #else #define PERCPU_DYNAMIC_SIZE_SHIFT 10 #endif From 6fa1066fc5d00cb9f1b0e83b7ff6ef98d26ba2aa Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Mon, 7 Oct 2024 23:42:04 +0200 Subject: [PATCH 07/28] mm/mremap: fix move_normal_pmd/retract_page_tables race In mremap(), move_page_tables() looks at the type of the PMD entry and the specified address range to figure out by which method the next chunk of page table entries should be moved. At that point, the mmap_lock is held in write mode, but no rmap locks are held yet. For PMD entries that point to page tables and are fully covered by the source address range, move_pgt_entry(NORMAL_PMD, ...) is called, which first takes rmap locks, then does move_normal_pmd(). move_normal_pmd() takes the necessary page table locks at source and destination, then moves an entire page table from the source to the destination. The problem is: The rmap locks, which protect against concurrent page table removal by retract_page_tables() in the THP code, are only taken after the PMD entry has been read and it has been decided how to move it. So we can race as follows (with two processes that have mappings of the same tmpfs file that is stored on a tmpfs mount with huge=advise); note that process A accesses page tables through the MM while process B does it through the file rmap: process A process B ========= ========= mremap mremap_to move_vma move_page_tables get_old_pmd alloc_new_pmd *** PREEMPT *** madvise(MADV_COLLAPSE) do_madvise madvise_walk_vmas madvise_vma_behavior madvise_collapse hpage_collapse_scan_file collapse_file retract_page_tables i_mmap_lock_read(mapping) pmdp_collapse_flush i_mmap_unlock_read(mapping) move_pgt_entry(NORMAL_PMD, ...) take_rmap_locks move_normal_pmd drop_rmap_locks When this happens, move_normal_pmd() can end up creating bogus PMD entries in the line `pmd_populate(mm, new_pmd, pmd_pgtable(pmd))`. The effect depends on arch-specific and machine-specific details; on x86, you can end up with physical page 0 mapped as a page table, which is likely exploitable for user->kernel privilege escalation. Fix the race by letting process B recheck that the PMD still points to a page table after the rmap locks have been taken. Otherwise, we bail and let the caller fall back to the PTE-level copying path, which will then bail immediately at the pmd_none() check. Bug reachability: Reaching this bug requires that you can create shmem/file THP mappings - anonymous THP uses different code that doesn't zap stuff under rmap locks. File THP is gated on an experimental config flag (CONFIG_READ_ONLY_THP_FOR_FS), so on normal distro kernels you need shmem THP to hit this bug. As far as I know, getting shmem THP normally requires that you can mount your own tmpfs with the right mount flags, which would require creating your own user+mount namespace; though I don't know if some distros maybe enable shmem THP by default or something like that. Bug impact: This issue can likely be used for user->kernel privilege escalation when it is reachable. Link: https://lkml.kernel.org/r/20241007-move_normal_pmd-vs-collapse-fix-2-v1-1-5ead9631f2ea@google.com Fixes: 1d65b771bc08 ("mm/khugepaged: retract_page_tables() without mmap or vma lock") Signed-off-by: Jann Horn Signed-off-by: David Hildenbrand Co-developed-by: David Hildenbrand Closes: https://project-zero.issues.chromium.org/371047675 Acked-by: Qi Zheng Reviewed-by: Lorenzo Stoakes Cc: Hugh Dickins Cc: Joel Fernandes Cc: Matthew Wilcox Cc: Signed-off-by: Andrew Morton --- mm/mremap.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/mm/mremap.c b/mm/mremap.c index 24712f8dbb6b..dda09e957a5d 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -238,6 +238,7 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr, { spinlock_t *old_ptl, *new_ptl; struct mm_struct *mm = vma->vm_mm; + bool res = false; pmd_t pmd; if (!arch_supports_page_table_move()) @@ -277,19 +278,25 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr, if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); - /* Clear the pmd */ pmd = *old_pmd; + + /* Racing with collapse? */ + if (unlikely(!pmd_present(pmd) || pmd_leaf(pmd))) + goto out_unlock; + /* Clear the pmd */ pmd_clear(old_pmd); + res = true; VM_BUG_ON(!pmd_none(*new_pmd)); pmd_populate(mm, new_pmd, pmd_pgtable(pmd)); flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE); +out_unlock: if (new_ptl != old_ptl) spin_unlock(new_ptl); spin_unlock(old_ptl); - return true; + return res; } #else static inline bool move_normal_pmd(struct vm_area_struct *vma, From dc783ba4b9df3fb3e76e968b2cbeb9960069263c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 7 Oct 2024 22:52:24 +0200 Subject: [PATCH 08/28] lib: alloc_tag_module_unload must wait for pending kfree_rcu calls Ben Greear reports following splat: ------------[ cut here ]------------ net/netfilter/nf_nat_core.c:1114 module nf_nat func:nf_nat_register_fn has 256 allocated at module unload WARNING: CPU: 1 PID: 10421 at lib/alloc_tag.c:168 alloc_tag_module_unload+0x22b/0x3f0 Modules linked in: nf_nat(-) btrfs ufs qnx4 hfsplus hfs minix vfat msdos fat ... Hardware name: Default string Default string/SKYBAY, BIOS 5.12 08/04/2020 RIP: 0010:alloc_tag_module_unload+0x22b/0x3f0 codetag_unload_module+0x19b/0x2a0 ? codetag_load_module+0x80/0x80 nf_nat module exit calls kfree_rcu on those addresses, but the free operation is likely still pending by the time alloc_tag checks for leaks. Wait for outstanding kfree_rcu operations to complete before checking resolves this warning. Reproducer: unshare -n iptables-nft -t nat -A PREROUTING -p tcp grep nf_nat /proc/allocinfo # will list 4 allocations rmmod nft_chain_nat rmmod nf_nat # will WARN. [akpm@linux-foundation.org: add comment] Link: https://lkml.kernel.org/r/20241007205236.11847-1-fw@strlen.de Fixes: a473573964e5 ("lib: code tagging module support") Signed-off-by: Florian Westphal Reported-by: Ben Greear Closes: https://lore.kernel.org/netdev/bdaaef9d-4364-4171-b82b-bcfc12e207eb@candelatech.com/ Cc: Uladzislau Rezki Cc: Vlastimil Babka Cc: Suren Baghdasaryan Cc: Kent Overstreet Cc: Signed-off-by: Andrew Morton --- lib/codetag.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/lib/codetag.c b/lib/codetag.c index afa8a2d4f317..d1fbbb7c2ec3 100644 --- a/lib/codetag.c +++ b/lib/codetag.c @@ -228,6 +228,9 @@ bool codetag_unload_module(struct module *mod) if (!mod) return true; + /* await any module's kfree_rcu() operations to complete */ + kvfree_rcu_barrier(); + mutex_lock(&codetag_lock); list_for_each_entry(cttype, &codetag_types, link) { struct codetag_module *found = NULL; From 5778ace04e6f07043f1564bc9b47b1098608cfdd Mon Sep 17 00:00:00 2001 From: Brahmajit Das Date: Sat, 5 Oct 2024 12:07:00 +0530 Subject: [PATCH 09/28] fs/proc: fix build with GCC 15 due to -Werror=unterminated-string-initialization show show_smap_vma_flags() has been a using misspelled initializer in mnemonics[] - it needed to initialize 2 element array of char and it used NUL-padded 2 character string literals (i.e. 3-element initializer). This has been spotted by gcc-15[*]; prior to that gcc quietly dropped the 3rd eleemnt of initializers. To fix this we are increasing the size of mnemonics[] (from mnemonics[BITS_PER_LONG][2] to mnemonics[BITS_PER_LONG][3]) to accomodate the NUL-padded string literals. This also helps us in simplyfying the logic for printing of the flags as instead of printing each character from the mnemonics[], we can just print the mnemonics[] using seq_printf. [*]: fs/proc/task_mmu.c:917:49: error: initializer-string for array of `char' is too long [-Werror=unterminate d-string-initialization] 917 | [0 ... (BITS_PER_LONG-1)] = "??", | ^~~~ fs/proc/task_mmu.c:917:49: error: initializer-string for array of `char' is too long [-Werror=unterminate d-string-initialization] fs/proc/task_mmu.c:917:49: error: initializer-string for array of `char' is too long [-Werror=unterminate d-string-initialization] fs/proc/task_mmu.c:917:49: error: initializer-string for array of `char' is too long [-Werror=unterminate d-string-initialization] fs/proc/task_mmu.c:917:49: error: initializer-string for array of `char' is too long [-Werror=unterminate d-string-initialization] fs/proc/task_mmu.c:917:49: error: initializer-string for array of `char' is too long [-Werror=unterminate d-string-initialization] ... Stephen pointed out: : The C standard explicitly allows for a string initializer to be too long : due to the NUL byte at the end ... so this warning may be overzealous. but let's make the warning go away anwyay. Link: https://lkml.kernel.org/r/20241005063700.2241027-1-brahmajit.xyz@gmail.com Link: https://lkml.kernel.org/r/20241003093040.47c08382@canb.auug.org.au Signed-off-by: Brahmajit Das Cc: Cyrill Gorcunov Cc: David Hildenbrand Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- fs/proc/task_mmu.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 72f14fd59c2d..e52bd96137a6 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -909,8 +909,15 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) { /* * Don't forget to update Documentation/ on changes. + * + * The length of the second argument of mnemonics[] + * needs to be 3 instead of previously set 2 + * (i.e. from [BITS_PER_LONG][2] to [BITS_PER_LONG][3]) + * to avoid spurious + * -Werror=unterminated-string-initialization warning + * with GCC 15 */ - static const char mnemonics[BITS_PER_LONG][2] = { + static const char mnemonics[BITS_PER_LONG][3] = { /* * In case if we meet a flag we don't know about. */ @@ -987,11 +994,8 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) for (i = 0; i < BITS_PER_LONG; i++) { if (!mnemonics[i][0]) continue; - if (vma->vm_flags & (1UL << i)) { - seq_putc(m, mnemonics[i][0]); - seq_putc(m, mnemonics[i][1]); - seq_putc(m, ' '); - } + if (vma->vm_flags & (1UL << i)) + seq_printf(m, "%s ", mnemonics[i]); } seq_putc(m, '\n'); } From f8dc524e5929695664fd05a7c3e369cd7edcf8a9 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Wed, 9 Oct 2024 21:10:32 +0100 Subject: [PATCH 10/28] MAINTAINERS: add memory mapping/VMA co-maintainers Add myself and Liam as co-maintainers of the memory mapping and VMA code alongside Andrew as we are heavily involved in its implementation and maintenance. Link: https://lkml.kernel.org/r/20241009201032.6130-1-lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Acked-by: Vlastimil Babka Acked-by: Liam R. Howlett Signed-off-by: Andrew Morton --- MAINTAINERS | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 7ad507f49324..51430c225666 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14907,9 +14907,9 @@ N: include/linux/page[-_]* MEMORY MAPPING M: Andrew Morton -R: Liam R. Howlett +M: Liam R. Howlett +M: Lorenzo Stoakes R: Vlastimil Babka -R: Lorenzo Stoakes L: linux-mm@kvack.org S: Maintained W: http://www.linux-mm.org @@ -24737,9 +24737,9 @@ F: tools/testing/vsock/ VMA M: Andrew Morton -R: Liam R. Howlett +M: Liam R. Howlett +M: Lorenzo Stoakes R: Vlastimil Babka -R: Lorenzo Stoakes L: linux-mm@kvack.org S: Maintained W: https://www.linux-mm.org From 3f4e74cb3f2d06c3128e5b22c603a0dd4ab6f540 Mon Sep 17 00:00:00 2001 From: Andy Chiu Date: Wed, 9 Oct 2024 22:49:34 +0800 Subject: [PATCH 11/28] mailmap: add an entry for Andy Chiu Map my outdated addresses within mailmap. Link: https://lkml.kernel.org/r/20241009144934.43027-1-andybnac@gmail.com Signed-off-by: Andy Chiu Cc: Greentime Hu Cc: Paul Walmsley Cc: Leon Chien Signed-off-by: Andrew Morton --- .mailmap | 2 ++ 1 file changed, 2 insertions(+) diff --git a/.mailmap b/.mailmap index 54580db9c59b..442da8603cef 100644 --- a/.mailmap +++ b/.mailmap @@ -73,6 +73,8 @@ Andrey Ryabinin Andrzej Hajda André Almeida Andy Adamson +Andy Chiu +Andy Chiu Andy Shevchenko Andy Shevchenko Anilkumar Kolli From a5e8eb25135a48d400e5a695ba9329bc632c3bb4 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 8 Oct 2024 22:13:29 +0300 Subject: [PATCH 12/28] mm: remove unused stub for can_swapin_thp() When can_swapin_thp() is unused, it prevents kernel builds with clang, `make W=1` and CONFIG_WERROR=y: mm/memory.c:4184:20: error: unused function 'can_swapin_thp' [-Werror,-Wunused-function] Fix this by removing the unused stub. See also commit 6863f5643dd7 ("kbuild: allow Clang to find unused static inline functions for W=1 build"). Link: https://lkml.kernel.org/r/20241008191329.2332346-1-andriy.shevchenko@linux.intel.com Fixes: 242d12c98174 ("mm: support large folios swap-in for sync io devices") Signed-off-by: Andy Shevchenko Acked-by: Barry Song Cc: Bill Wendling Cc: Chuanhua Han Cc: Justin Stitt Cc: Nathan Chancellor Cc: Nick Desaulniers Signed-off-by: Andrew Morton --- mm/memory.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index 2366578015ad..c0869a962ddd 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4181,11 +4181,6 @@ fallback: return __alloc_swap_folio(vmf); } #else /* !CONFIG_TRANSPARENT_HUGEPAGE */ -static inline bool can_swapin_thp(struct vm_fault *vmf, pte_t *ptep, int nr_pages) -{ - return false; -} - static struct folio *alloc_swap_folio(struct vm_fault *vmf) { return __alloc_swap_folio(vmf); From 2d6a1c835685de3b0c8e8dc871f60f4ef92ab01a Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Thu, 10 Oct 2024 20:53:23 +0800 Subject: [PATCH 13/28] mm/damon/tests/sysfs-kunit.h: fix memory leak in damon_sysfs_test_add_targets() The sysfs_target->regions allocated in damon_sysfs_regions_alloc() is not freed in damon_sysfs_test_add_targets(), which cause the following memory leak, free it to fix it. unreferenced object 0xffffff80c2a8db80 (size 96): comm "kunit_try_catch", pid 187, jiffies 4294894363 hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace (crc 0): [<0000000001e3714d>] kmemleak_alloc+0x34/0x40 [<000000008e6835c1>] __kmalloc_cache_noprof+0x26c/0x2f4 [<000000001286d9f8>] damon_sysfs_test_add_targets+0x1cc/0x738 [<0000000032ef8f77>] kunit_try_run_case+0x13c/0x3ac [<00000000f3edea23>] kunit_generic_run_threadfn_adapter+0x80/0xec [<00000000adf936cf>] kthread+0x2e8/0x374 [<0000000041bb1628>] ret_from_fork+0x10/0x20 Link: https://lkml.kernel.org/r/20241010125323.3127187-1-ruanjinjie@huawei.com Fixes: b8ee5575f763 ("mm/damon/sysfs-test: add a unit test for damon_sysfs_set_targets()") Signed-off-by: Jinjie Ruan Reviewed-by: SeongJae Park Cc: Signed-off-by: Andrew Morton --- mm/damon/tests/sysfs-kunit.h | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/damon/tests/sysfs-kunit.h b/mm/damon/tests/sysfs-kunit.h index 1c9b596057a7..7b5c7b307da9 100644 --- a/mm/damon/tests/sysfs-kunit.h +++ b/mm/damon/tests/sysfs-kunit.h @@ -67,6 +67,7 @@ static void damon_sysfs_test_add_targets(struct kunit *test) damon_destroy_ctx(ctx); kfree(sysfs_targets->targets_arr); kfree(sysfs_targets); + kfree(sysfs_target->regions); kfree(sysfs_target); } From 37f0b47c5143c2957909ced44fc09ffb118c99f7 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 11 Oct 2024 18:17:02 -0700 Subject: [PATCH 14/28] mm: khugepaged: fix the arguments order in khugepaged_collapse_file trace point The "addr" and "is_shmem" arguments have different order in TP_PROTO and TP_ARGS. This resulted in the incorrect trace result: text-hugepage-644429 [276] 392092.878683: mm_khugepaged_collapse_file: mm=0xffff20025d52c440, hpage_pfn=0x200678c00, index=512, addr=1, is_shmem=0, filename=text-hugepage, nr=512, result=failed The value of "addr" is wrong because it was treated as bool value, the type of is_shmem. Fix the order in TP_PROTO to keep "addr" is before "is_shmem" since the original patch review suggested this order to achieve best packing. And use "lx" for "addr" instead of "ld" in TP_printk because address is typically shown in hex. After the fix, the trace result looks correct: text-hugepage-7291 [004] 128.627251: mm_khugepaged_collapse_file: mm=0xffff0001328f9500, hpage_pfn=0x20016ea00, index=512, addr=0x400000, is_shmem=0, filename=text-hugepage, nr=512, result=failed Link: https://lkml.kernel.org/r/20241012011702.1084846-1-yang@os.amperecomputing.com Fixes: 4c9473e87e75 ("mm/khugepaged: add tracepoint to collapse_file()") Signed-off-by: Yang Shi Cc: Gautam Menghani Cc: Steven Rostedt (Google) Cc: [6.2+] Signed-off-by: Andrew Morton --- include/trace/events/huge_memory.h | 4 ++-- mm/khugepaged.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index b5f5369b6300..9d5c00b0285c 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -208,7 +208,7 @@ TRACE_EVENT(mm_khugepaged_scan_file, TRACE_EVENT(mm_khugepaged_collapse_file, TP_PROTO(struct mm_struct *mm, struct folio *new_folio, pgoff_t index, - bool is_shmem, unsigned long addr, struct file *file, + unsigned long addr, bool is_shmem, struct file *file, int nr, int result), TP_ARGS(mm, new_folio, index, addr, is_shmem, file, nr, result), TP_STRUCT__entry( @@ -233,7 +233,7 @@ TRACE_EVENT(mm_khugepaged_collapse_file, __entry->result = result; ), - TP_printk("mm=%p, hpage_pfn=0x%lx, index=%ld, addr=%ld, is_shmem=%d, filename=%s, nr=%d, result=%s", + TP_printk("mm=%p, hpage_pfn=0x%lx, index=%ld, addr=%lx, is_shmem=%d, filename=%s, nr=%d, result=%s", __entry->mm, __entry->hpfn, __entry->index, diff --git a/mm/khugepaged.c b/mm/khugepaged.c index f9c39898eaff..a420eff92011 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2227,7 +2227,7 @@ rollback: folio_put(new_folio); out: VM_BUG_ON(!list_empty(&pagelist)); - trace_mm_khugepaged_collapse_file(mm, new_folio, index, is_shmem, addr, file, HPAGE_PMD_NR, result); + trace_mm_khugepaged_collapse_file(mm, new_folio, index, addr, is_shmem, file, HPAGE_PMD_NR, result); return result; } From a6e0ceb7bf48695d199f93432b35cb11502da0e4 Mon Sep 17 00:00:00 2001 From: Sidhartha Kumar Date: Fri, 11 Oct 2024 17:44:50 -0400 Subject: [PATCH 15/28] maple_tree: check for MA_STATE_BULK on setting wr_rebalance It is possible for a bulk operation (MA_STATE_BULK is set) to enter the new_end < mt_min_slots[type] case and set wr_rebalance as a store type. This is incorrect as bulk stores do not rebalance per write, but rather after the all of the writes are done through the mas_bulk_rebalance() path. Therefore, add a check to make sure MA_STATE_BULK is not set before we return wr_rebalance as the store type. Also add a test to make sure wr_rebalance is never the store type when doing bulk operations via mas_expected_entries() This is a hotfix for this rc however it has no userspace effects as there are no users of the bulk insertion mode. Link: https://lkml.kernel.org/r/20241011214451.7286-1-sidhartha.kumar@oracle.com Fixes: 5d659bbb52a2 ("maple_tree: introduce mas_wr_store_type()") Suggested-by: Liam Howlett Signed-off-by: Sidhartha Reviewed-by: Wei Yang Reviewed-by: Liam Howlett Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- lib/maple_tree.c | 2 +- tools/testing/radix-tree/maple.c | 26 ++++++++++++++++++++++++++ 2 files changed, 27 insertions(+), 1 deletion(-) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 20990ecba2dd..ce7c7a7a8258 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -4218,7 +4218,7 @@ static inline void mas_wr_store_type(struct ma_wr_state *wr_mas) /* Potential spanning rebalance collapsing a node */ if (new_end < mt_min_slots[wr_mas->type]) { - if (!mte_is_root(mas->node)) { + if (!mte_is_root(mas->node) && !(mas->mas_flags & MA_STATE_BULK)) { mas->store_type = wr_rebalance; return; } diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 1873ddbe16cc..6ec18883e11e 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -36317,6 +36317,28 @@ static inline int check_vma_modification(struct maple_tree *mt) return 0; } +/* + * test to check that bulk stores do not use wr_rebalance as the store + * type. + */ +static inline void check_bulk_rebalance(struct maple_tree *mt) +{ + MA_STATE(mas, mt, ULONG_MAX, ULONG_MAX); + int max = 10; + + build_full_tree(mt, 0, 2); + + /* erase every entry in the tree */ + do { + /* set up bulk store mode */ + mas_expected_entries(&mas, max); + mas_erase(&mas); + MT_BUG_ON(mt, mas.store_type == wr_rebalance); + } while (mas_prev(&mas, 0) != NULL); + + mas_destroy(&mas); +} + void farmer_tests(void) { struct maple_node *node; @@ -36328,6 +36350,10 @@ void farmer_tests(void) check_vma_modification(&tree); mtree_destroy(&tree); + mt_init(&tree); + check_bulk_rebalance(&tree); + mtree_destroy(&tree); + tree.ma_root = xa_mk_value(0); mt_dump(&tree, mt_dump_dec); From 46e10f644ac0a48d719436d4e9d61289f3979835 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 11 Oct 2024 10:01:53 -0700 Subject: [PATCH 16/28] Docs/damon/maintainer-profile: add missing '_' suffixes for external web links Patch series "Docs/damon/maintainer-profile: a couple of minor hotfixes". DAMON maintainer-profile.rst file patches[1] that were merged into the v6.12-rc1 have a couple of minor mistakes. Fix those. [1] https://lore.kernel.org/20240826015741.80707-1-sj@kernel.org This patch (of 2): Links to external web pages on DAMON's maintainer-profile.rst are missing '_' suffixes. As a result, rendered document is having only verbose URLs that cannot be clicked. Fix those. Also, update the link texts for git trees to contain the names of the trees, for better readability and avoiding below Sphinx warning. maintainer-profile.rst:4: WARNING: Duplicate explicit target name: "tree". Link: https://lkml.kernel.org/r/20241011170154.70651-1-sj@kernel.org Link: https://lkml.kernel.org/r/20241011170154.70651-2-sj@kernel.org Fixes: 2e9b3d6e2e59 ("Docs/damon/maintainer-profile: add links in place") Signed-off-by: SeongJae Park Cc: Jonathan Corbet Signed-off-by: Andrew Morton --- Documentation/mm/damon/maintainer-profile.rst | 38 +++++++++---------- 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/Documentation/mm/damon/maintainer-profile.rst b/Documentation/mm/damon/maintainer-profile.rst index 2365c9a3c1f0..7b966480c79e 100644 --- a/Documentation/mm/damon/maintainer-profile.rst +++ b/Documentation/mm/damon/maintainer-profile.rst @@ -7,26 +7,26 @@ The DAMON subsystem covers the files that are listed in 'DATA ACCESS MONITOR' section of 'MAINTAINERS' file. The mailing lists for the subsystem are damon@lists.linux.dev and -linux-mm@kvack.org. Patches should be made against the mm-unstable `tree -` whenever possible and posted to -the mailing lists. +linux-mm@kvack.org. Patches should be made against the `mm-unstable tree +`_ whenever possible and posted +to the mailing lists. SCM Trees --------- There are multiple Linux trees for DAMON development. Patches under development or testing are queued in `damon/next -` by the DAMON maintainer. +`_ by the DAMON maintainer. Sufficiently reviewed patches will be queued in `mm-unstable -` by the memory management +`_ by the memory management subsystem maintainer. After more sufficient tests, the patches will be queued -in `mm-stable ` , and finally +in `mm-stable `_, and finally pull-requested to the mainline by the memory management subsystem maintainer. -Note again the patches for mm-unstable `tree -` are queued by the memory +Note again the patches for `mm-unstable tree +`_ are queued by the memory management subsystem maintainer. If the patches requires some patches in -damon/next `tree ` which not yet merged +`damon/next tree `_ which not yet merged in mm-unstable, please make sure the requirement is clearly specified. Submit checklist addendum @@ -37,25 +37,25 @@ When making DAMON changes, you should do below. - Build changes related outputs including kernel and documents. - Ensure the builds introduce no new errors or warnings. - Run and ensure no new failures for DAMON `selftests - ` and + `_ and `kunittests - `. + `_. Further doing below and putting the results will be helpful. - Run `damon-tests/corr - ` for normal + `_ for normal changes. - Run `damon-tests/perf - ` for performance + `_ for performance changes. Key cycle dates --------------- Patches can be sent anytime. Key cycle dates of the `mm-unstable -` and `mm-stable -` trees depend on the memory +`_ and `mm-stable +`_ trees depend on the memory management subsystem maintainer. Review cadence @@ -72,13 +72,13 @@ Mailing tool Like many other Linux kernel subsystems, DAMON uses the mailing lists (damon@lists.linux.dev and linux-mm@kvack.org) as the major communication channel. There is a simple tool called `HacKerMaiL -` (``hkml``), which is for people who +`_ (``hkml``), which is for people who are not very familiar with the mailing lists based communication. The tool could be particularly helpful for DAMON community members since it is developed and maintained by DAMON maintainer. The tool is also officially announced to support DAMON and general Linux kernel development workflow. -In other words, `hkml ` is a mailing +In other words, `hkml `_ is a mailing tool for DAMON community, which DAMON maintainer is committed to support. Please feel free to try and report issues or feature requests for the tool to the maintainer. @@ -98,8 +98,8 @@ slots, and attendees should reserve one of those at least 24 hours before the time slot, by reaching out to the maintainer. Schedules and available reservation time slots are available at the Google `doc -`. +`_. There is also a public Google `calendar -` +`_ that has the events. Anyone can subscribe it. DAMON maintainer will also provide periodic reminder to the mailing list (damon@lists.linux.dev). From f4050ccab716541454d2d33758eab6df1a092f7a Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 11 Oct 2024 10:01:54 -0700 Subject: [PATCH 17/28] Docs/damon/maintainer-profile: update deprecated awslabs GitHub URLs DAMON GitHub repos have moved from awslabs GitHub org to damonitor org[1]. Following the change, URLs on documents are also updated[2]. However, commit 2e9b3d6e2e59 ("Docs/damon/maintainer-profile: add links in place"), which was added just after the update, was using the deprecated GitHub URLs. Update those to use damonitor GitHub URLs instead. [1] https://lore.kernel.org/20240813232158.83903-1-sj@kernel.org [2] https://lore.kernel.org/20240826015741.80707-2-sj@kernel.org Link: https://lkml.kernel.org/r/20241011170154.70651-3-sj@kernel.org Fixes: 2e9b3d6e2e59 ("Docs/damon/maintainer-profile: add links in place") Signed-off-by: SeongJae Park Cc: Jonathan Corbet Signed-off-by: Andrew Morton --- Documentation/mm/damon/maintainer-profile.rst | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/Documentation/mm/damon/maintainer-profile.rst b/Documentation/mm/damon/maintainer-profile.rst index 7b966480c79e..ce3e98458339 100644 --- a/Documentation/mm/damon/maintainer-profile.rst +++ b/Documentation/mm/damon/maintainer-profile.rst @@ -37,17 +37,17 @@ When making DAMON changes, you should do below. - Build changes related outputs including kernel and documents. - Ensure the builds introduce no new errors or warnings. - Run and ensure no new failures for DAMON `selftests - `_ and + `_ and `kunittests - `_. + `_. Further doing below and putting the results will be helpful. - Run `damon-tests/corr - `_ for normal + `_ for normal changes. - Run `damon-tests/perf - `_ for performance + `_ for performance changes. Key cycle dates From 963756aac1f011d904ddd9548ae82286d3a91f96 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 11 Oct 2024 12:24:44 +0200 Subject: [PATCH 18/28] mm: huge_memory: add vma_thp_disabled() and thp_disabled_by_hw() Patch series "mm: don't install PMD mappings when THPs are disabled by the hw/process/vma". During testing, it was found that we can get PMD mappings in processes where THP (and more precisely, PMD mappings) are supposed to be disabled. While it works as expected for anon+shmem, the pagecache is the problematic bit. For s390 KVM this currently means that a VM backed by a file located on filesystem with large folio support can crash when KVM tries accessing the problematic page, because the readahead logic might decide to use a PMD-sized THP and faulting it into the page tables will install a PMD mapping, something that s390 KVM cannot tolerate. This might also be a problem with HW that does not support PMD mappings, but I did not try reproducing it. Fix it by respecting the ways to disable THPs when deciding whether we can install a PMD mapping. khugepaged should already be taking care of not collapsing if THPs are effectively disabled for the hw/process/vma. This patch (of 2): Add vma_thp_disabled() and thp_disabled_by_hw() helpers to be shared by shmem_allowable_huge_orders() and __thp_vma_allowable_orders(). [david@redhat.com: rename to vma_thp_disabled(), split out thp_disabled_by_hw() ] Link: https://lkml.kernel.org/r/20241011102445.934409-2-david@redhat.com Fixes: 793917d997df ("mm/readahead: Add large folio readahead") Signed-off-by: Kefeng Wang Signed-off-by: David Hildenbrand Reported-by: Leo Fu Tested-by: Thomas Huth Reviewed-by: Ryan Roberts Cc: Boqiao Fu Cc: Christian Borntraeger Cc: Claudio Imbrenda Cc: Hugh Dickins Cc: Janosch Frank Cc: Matthew Wilcox Cc: Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 18 ++++++++++++++++++ mm/huge_memory.c | 13 +------------ mm/shmem.c | 7 +------ 3 files changed, 20 insertions(+), 18 deletions(-) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 67d0ab3c3bba..ef5b80e48599 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -322,6 +322,24 @@ struct thpsize { (transparent_hugepage_flags & \ (1<vm_mm->flags); +} + +static inline bool thp_disabled_by_hw(void) +{ + /* If the hardware/firmware marked hugepage support disabled. */ + return transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED); +} + unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 87b49ecc7b1e..2fb328880b50 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -109,18 +109,7 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, if (!vma->vm_mm) /* vdso */ return 0; - /* - * Explicitly disabled through madvise or prctl, or some - * architectures may disable THP for some mappings, for - * example, s390 kvm. - * */ - if ((vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) - return 0; - /* - * If the hardware/firmware marked hugepage support disabled. - */ - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED)) + if (thp_disabled_by_hw() || vma_thp_disabled(vma, vm_flags)) return 0; /* khugepaged doesn't collapse DAX vma, but page fault is fine. */ diff --git a/mm/shmem.c b/mm/shmem.c index 4f11b5506363..c5adb987b23c 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1664,12 +1664,7 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, loff_t i_size; int order; - if (vma && ((vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))) - return 0; - - /* If the hardware/firmware marked hugepage support disabled. */ - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED)) + if (thp_disabled_by_hw() || (vma && vma_thp_disabled(vma, vm_flags))) return 0; global_huge = shmem_huge_global_enabled(inode, index, write_end, From 2b0f922323ccfa76219bcaacd35cd50aeaa13592 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 11 Oct 2024 12:24:45 +0200 Subject: [PATCH 19/28] mm: don't install PMD mappings when THPs are disabled by the hw/process/vma We (or rather, readahead logic :) ) might be allocating a THP in the pagecache and then try mapping it into a process that explicitly disabled THP: we might end up installing PMD mappings. This is a problem for s390x KVM, which explicitly remaps all PMD-mapped THPs to be PTE-mapped in s390_enable_sie()->thp_split_mm(), before starting the VM. For example, starting a VM backed on a file system with large folios supported makes the VM crash when the VM tries accessing such a mapping using KVM. Is it also a problem when the HW disabled THP using TRANSPARENT_HUGEPAGE_UNSUPPORTED? At least on x86 this would be the case without X86_FEATURE_PSE. In the future, we might be able to do better on s390x and only disallow PMD mappings -- what s390x and likely TRANSPARENT_HUGEPAGE_UNSUPPORTED really wants. For now, fix it by essentially performing the same check as would be done in __thp_vma_allowable_orders() or in shmem code, where this works as expected, and disallow PMD mappings, making us fallback to PTE mappings. Link: https://lkml.kernel.org/r/20241011102445.934409-3-david@redhat.com Fixes: 793917d997df ("mm/readahead: Add large folio readahead") Signed-off-by: David Hildenbrand Reported-by: Leo Fu Tested-by: Thomas Huth Cc: Thomas Huth Cc: Matthew Wilcox (Oracle) Cc: Ryan Roberts Cc: Christian Borntraeger Cc: Janosch Frank Cc: Claudio Imbrenda Cc: Hugh Dickins Cc: Kefeng Wang Cc: Signed-off-by: Andrew Morton --- mm/memory.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/mm/memory.c b/mm/memory.c index c0869a962ddd..30feedabc932 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4920,6 +4920,15 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) pmd_t entry; vm_fault_t ret = VM_FAULT_FALLBACK; + /* + * It is too late to allocate a small folio, we already have a large + * folio in the pagecache: especially s390 KVM cannot tolerate any + * PMD mappings, but PTE-mapped THP are fine. So let's simply refuse any + * PMD mappings if THPs are disabled. + */ + if (thp_disabled_by_hw() || vma_thp_disabled(vma, vma->vm_flags)) + return ret; + if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return ret; From 22ff9b0ff11a762852cd620972f265b3129e3fe7 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Sun, 13 Oct 2024 00:55:24 +0200 Subject: [PATCH 20/28] MAINTAINERS: kasan, kcov: add bugzilla links Add links to the Bugzilla component that's used to track KASAN and KCOV issues. Link: https://lkml.kernel.org/r/20241012225524.117871-1-andrey.konovalov@linux.dev Signed-off-by: Andrey Konovalov Acked-by: Dmitry Vyukov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Marco Elver Signed-off-by: Andrew Morton --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 51430c225666..a3b75fe83f47 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12242,6 +12242,7 @@ R: Dmitry Vyukov R: Vincenzo Frascino L: kasan-dev@googlegroups.com S: Maintained +B: https://bugzilla.kernel.org/buglist.cgi?component=Sanitizers&product=Memory%20Management F: Documentation/dev-tools/kasan.rst F: arch/*/include/asm/*kasan.h F: arch/*/mm/kasan_init* @@ -12265,6 +12266,7 @@ R: Dmitry Vyukov R: Andrey Konovalov L: kasan-dev@googlegroups.com S: Maintained +B: https://bugzilla.kernel.org/buglist.cgi?component=Sanitizers&product=Memory%20Management F: Documentation/dev-tools/kcov.rst F: include/linux/kcov.h F: include/uapi/linux/kcov.h From d60fcaf00d752c52fdf566d4184e6d04d9d08879 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 14 Oct 2024 18:24:44 +0800 Subject: [PATCH 21/28] mm: khugepaged: fix the incorrect statistics when collapsing large file folios Khugepaged already supports collapsing file large folios (including shmem mTHP) by commit 7de856ffd007 ("mm: khugepaged: support shmem mTHP collapse"), and the control parameters in khugepaged: 'khugepaged_max_ptes_swap' and 'khugepaged_max_ptes_none', still compare based on PTE granularity to determine whether a file collapse is needed. However, the statistics for 'present' and 'swap' in hpage_collapse_scan_file() do not take into account the large folios, which may lead to incorrect judgments regarding the khugepaged_max_ptes_swap/none parameters, resulting in unnecessary file collapses. To fix this issue, take into account the large folios' statistics for 'present' and 'swap' variables in the hpage_collapse_scan_file(). Link: https://lkml.kernel.org/r/c76305d96d12d030a1a346b50503d148364246d2.1728901391.git.baolin.wang@linux.alibaba.com Fixes: 7de856ffd007 ("mm: khugepaged: support shmem mTHP collapse") Signed-off-by: Baolin Wang Acked-by: David Hildenbrand Reviewed-by: Barry Song Reviewed-by: Zi Yan Reviewed-by: Yang Shi Cc: Hugh Dickins Cc: Matthew Wilcox Cc: Ryan Roberts Signed-off-by: Andrew Morton --- mm/khugepaged.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index a420eff92011..b538c3d48386 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2252,7 +2252,7 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, continue; if (xa_is_value(folio)) { - ++swap; + swap += 1 << xas_get_order(&xas); if (cc->is_khugepaged && swap > khugepaged_max_ptes_swap) { result = SCAN_EXCEED_SWAP_PTE; @@ -2299,7 +2299,7 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, * is just too costly... */ - present++; + present += folio_nr_pages(folio); if (need_resched()) { xas_pause(&xas); From 818f916e3a07bf0c64bbf5e250ad209eebe21c85 Mon Sep 17 00:00:00 2001 From: Jeongjun Park Date: Mon, 7 Oct 2024 16:06:23 +0900 Subject: [PATCH 22/28] mm: swap: prevent possible data-race in __try_to_reclaim_swap A report [1] was uploaded from syzbot. In the previous commit 862590ac3708 ("mm: swap: allow cache reclaim to skip slot cache"), the __try_to_reclaim_swap() function reads offset and folio->entry from folio without folio_lock protection. In the currently reported KCSAN log, it is assumed that the actual data-race will not occur because the calltrace that does WRITE already obtains the folio_lock and then writes. However, the existing __try_to_reclaim_swap() function was already implemented to perform reads under folio_lock protection [1], and there is a risk of a data-race occurring through a function other than the one shown in the KCSAN log. Therefore, I think it is appropriate to change read operations for folio to be performed under folio_lock. [1] ================================================================== BUG: KCSAN: data-race in __delete_from_swap_cache / __try_to_reclaim_swap write to 0xffffea0004c90328 of 8 bytes by task 5186 on cpu 0: __delete_from_swap_cache+0x1f0/0x290 mm/swap_state.c:163 delete_from_swap_cache+0x72/0xe0 mm/swap_state.c:243 folio_free_swap+0x1d8/0x1f0 mm/swapfile.c:1850 free_swap_cache mm/swap_state.c:293 [inline] free_pages_and_swap_cache+0x1fc/0x410 mm/swap_state.c:325 __tlb_batch_free_encoded_pages mm/mmu_gather.c:136 [inline] tlb_batch_pages_flush mm/mmu_gather.c:149 [inline] tlb_flush_mmu_free mm/mmu_gather.c:366 [inline] tlb_flush_mmu+0x2cf/0x440 mm/mmu_gather.c:373 zap_pte_range mm/memory.c:1700 [inline] zap_pmd_range mm/memory.c:1739 [inline] zap_pud_range mm/memory.c:1768 [inline] zap_p4d_range mm/memory.c:1789 [inline] unmap_page_range+0x1f3c/0x22d0 mm/memory.c:1810 unmap_single_vma+0x142/0x1d0 mm/memory.c:1856 unmap_vmas+0x18d/0x2b0 mm/memory.c:1900 exit_mmap+0x18a/0x690 mm/mmap.c:1864 __mmput+0x28/0x1b0 kernel/fork.c:1347 mmput+0x4c/0x60 kernel/fork.c:1369 exit_mm+0xe4/0x190 kernel/exit.c:571 do_exit+0x55e/0x17f0 kernel/exit.c:926 do_group_exit+0x102/0x150 kernel/exit.c:1088 get_signal+0xf2a/0x1070 kernel/signal.c:2917 arch_do_signal_or_restart+0x95/0x4b0 arch/x86/kernel/signal.c:337 exit_to_user_mode_loop kernel/entry/common.c:111 [inline] exit_to_user_mode_prepare include/linux/entry-common.h:328 [inline] __syscall_exit_to_user_mode_work kernel/entry/common.c:207 [inline] syscall_exit_to_user_mode+0x59/0x130 kernel/entry/common.c:218 do_syscall_64+0xd6/0x1c0 arch/x86/entry/common.c:89 entry_SYSCALL_64_after_hwframe+0x77/0x7f read to 0xffffea0004c90328 of 8 bytes by task 5189 on cpu 1: __try_to_reclaim_swap+0x9d/0x510 mm/swapfile.c:198 free_swap_and_cache_nr+0x45d/0x8a0 mm/swapfile.c:1915 zap_pte_range mm/memory.c:1656 [inline] zap_pmd_range mm/memory.c:1739 [inline] zap_pud_range mm/memory.c:1768 [inline] zap_p4d_range mm/memory.c:1789 [inline] unmap_page_range+0xcf8/0x22d0 mm/memory.c:1810 unmap_single_vma+0x142/0x1d0 mm/memory.c:1856 unmap_vmas+0x18d/0x2b0 mm/memory.c:1900 exit_mmap+0x18a/0x690 mm/mmap.c:1864 __mmput+0x28/0x1b0 kernel/fork.c:1347 mmput+0x4c/0x60 kernel/fork.c:1369 exit_mm+0xe4/0x190 kernel/exit.c:571 do_exit+0x55e/0x17f0 kernel/exit.c:926 __do_sys_exit kernel/exit.c:1055 [inline] __se_sys_exit kernel/exit.c:1053 [inline] __x64_sys_exit+0x1f/0x20 kernel/exit.c:1053 x64_sys_call+0x2d46/0x2d60 arch/x86/include/generated/asm/syscalls_64.h:61 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xc9/0x1c0 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f value changed: 0x0000000000000242 -> 0x0000000000000000 Link: https://lkml.kernel.org/r/20241007070623.23340-1-aha310510@gmail.com Reported-by: syzbot+fa43f1b63e3aa6f66329@syzkaller.appspotmail.com Fixes: 862590ac3708 ("mm: swap: allow cache reclaim to skip slot cache") Signed-off-by: Jeongjun Park Acked-by: Chris Li Reviewed-by: Kairui Song Signed-off-by: Andrew Morton --- mm/swapfile.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/mm/swapfile.c b/mm/swapfile.c index 0cded32414a1..eb782fcd5627 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -194,9 +194,6 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si, if (IS_ERR(folio)) return 0; - /* offset could point to the middle of a large folio */ - entry = folio->swap; - offset = swp_offset(entry); nr_pages = folio_nr_pages(folio); ret = -nr_pages; @@ -210,6 +207,10 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si, if (!folio_trylock(folio)) goto out; + /* offset could point to the middle of a large folio */ + entry = folio->swap; + offset = swp_offset(entry); + need_reclaim = ((flags & TTRS_ANYWAY) || ((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) || ((flags & TTRS_FULL) && mem_cgroup_swap_full(folio))); From cb2bb9c564acf45f1725696177fdb1bc067f4dbb Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Mon, 14 Oct 2024 22:50:57 +0200 Subject: [PATCH 23/28] MAINTAINERS: add Jann as memory mapping/VMA reviewer Add myself as a reviewer for memory mapping / VMA code. I will probably only reply to patches sporadically, but hopefully this will help me keep up with changes that look interesting security-wise. Link: https://lkml.kernel.org/r/20241014-maintainers-mmap-reviewer-v1-1-50dce0514752@google.com Signed-off-by: Jann Horn Acked-by: Liam R. Howlett Acked-by: Lorenzo Stoakes Acked-by: Vlastimil Babka Signed-off-by: Andrew Morton --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index a3b75fe83f47..942467edf58b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14912,6 +14912,7 @@ M: Andrew Morton M: Liam R. Howlett M: Lorenzo Stoakes R: Vlastimil Babka +R: Jann Horn L: linux-mm@kvack.org S: Maintained W: http://www.linux-mm.org @@ -24742,6 +24743,7 @@ M: Andrew Morton M: Liam R. Howlett M: Lorenzo Stoakes R: Vlastimil Babka +R: Jann Horn L: linux-mm@kvack.org S: Maintained W: https://www.linux-mm.org From 3e822bed2fbd1527d88f483342b1d2a468520a9a Mon Sep 17 00:00:00 2001 From: Nanyong Sun Date: Tue, 15 Oct 2024 10:02:57 +0800 Subject: [PATCH 24/28] selftests: mm: fix the incorrect usage() info of khugepaged The mount option of tmpfs should be huge=advise, not madvise which is not supported and may mislead the users. Link: https://lkml.kernel.org/r/20241015020257.139235-1-sunnanyong@huawei.com Fixes: 1b03d0d558a2 ("selftests/vm: add thp collapse file and tmpfs testing") Signed-off-by: Nanyong Sun Reviewed-by: Baolin Wang Reviewed-by: Anshuman Khandual Cc: Kefeng Wang Cc: Shuah Khan Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/khugepaged.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c index 56d4480e8d3c..8a4d34cce36b 100644 --- a/tools/testing/selftests/mm/khugepaged.c +++ b/tools/testing/selftests/mm/khugepaged.c @@ -1091,7 +1091,7 @@ static void usage(void) fprintf(stderr, "\n\t\"file,all\" mem_type requires kernel built with\n"); fprintf(stderr, "\tCONFIG_READ_ONLY_THP_FOR_FS=y\n"); fprintf(stderr, "\n\tif [dir] is a (sub)directory of a tmpfs mount, tmpfs must be\n"); - fprintf(stderr, "\tmounted with huge=madvise option for khugepaged tests to work\n"); + fprintf(stderr, "\tmounted with huge=advise option for khugepaged tests to work\n"); fprintf(stderr, "\n\tSupported Options:\n"); fprintf(stderr, "\t\t-h: This help message.\n"); fprintf(stderr, "\t\t-s: mTHP size, expressed as page order.\n"); From 7528c4fb1237512ee18049f852f014eba80bbe8d Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Tue, 15 Oct 2024 09:45:21 +0800 Subject: [PATCH 25/28] mm/swapfile: skip HugeTLB pages for unuse_vma I got a bad pud error and lost a 1GB HugeTLB when calling swapoff. The problem can be reproduced by the following steps: 1. Allocate an anonymous 1GB HugeTLB and some other anonymous memory. 2. Swapout the above anonymous memory. 3. run swapoff and we will get a bad pud error in kernel message: mm/pgtable-generic.c:42: bad pud 00000000743d215d(84000001400000e7) We can tell that pud_clear_bad is called by pud_none_or_clear_bad in unuse_pud_range() by ftrace. And therefore the HugeTLB pages will never be freed because we lost it from page table. We can skip HugeTLB pages for unuse_vma to fix it. Link: https://lkml.kernel.org/r/20241015014521.570237-1-liushixin2@huawei.com Fixes: 0fe6e20b9c4c ("hugetlb, rmap: add reverse mapping for hugepage") Signed-off-by: Liu Shixin Acked-by: Muchun Song Cc: Naoya Horiguchi Cc: Signed-off-by: Andrew Morton --- mm/swapfile.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/swapfile.c b/mm/swapfile.c index eb782fcd5627..b0915f3fab31 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2313,7 +2313,7 @@ static int unuse_mm(struct mm_struct *mm, unsigned int type) mmap_read_lock(mm); for_each_vma(vmi, vma) { - if (vma->anon_vma) { + if (vma->anon_vma && !is_vm_hugetlb_page(vma)) { ret = unuse_vma(vma, type); if (ret) break; From b130ba4a6259f6b64d8af15e9e7ab1e912bcb7ad Mon Sep 17 00:00:00 2001 From: Wei Xu Date: Mon, 14 Oct 2024 22:12:11 +0000 Subject: [PATCH 26/28] mm/mglru: only clear kswapd_failures if reclaimable lru_gen_shrink_node() unconditionally clears kswapd_failures, which can prevent kswapd from sleeping and cause 100% kswapd cpu usage even when kswapd repeatedly fails to make progress in reclaim. Only clear kswap_failures in lru_gen_shrink_node() if reclaim makes some progress, similar to shrink_node(). I happened to run into this problem in one of my tests recently. It requires a combination of several conditions: The allocator needs to allocate a right amount of pages such that it can wake up kswapd without itself being OOM killed; there is no memory for kswapd to reclaim (My test disables swap and cleans page cache first); no other process frees enough memory at the same time. Link: https://lkml.kernel.org/r/20241014221211.832591-1-weixugc@google.com Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists") Signed-off-by: Wei Xu Cc: Axel Rasmussen Cc: Brian Geffon Cc: Jan Alexander Steffens Cc: Suleiman Souhlal Cc: Yu Zhao Cc: Signed-off-by: Andrew Morton --- mm/vmscan.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 749cdc110c74..eb4e8440c507 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4963,8 +4963,8 @@ static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control * blk_finish_plug(&plug); done: - /* kswapd should never fail */ - pgdat->kswapd_failures = 0; + if (sc->nr_reclaimed > reclaimed) + pgdat->kswapd_failures = 0; } /****************************************************************************** From bea07fd63192b61209d48cbb81ef474cc3ee4c62 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Mon, 7 Oct 2024 16:28:32 +0100 Subject: [PATCH 27/28] maple_tree: correct tree corruption on spanning store Patch series "maple_tree: correct tree corruption on spanning store", v3. There has been a nasty yet subtle maple tree corruption bug that appears to have been in existence since the inception of the algorithm. This bug seems far more likely to happen since commit f8d112a4e657 ("mm/mmap: avoid zeroing vma tree in mmap_region()"), which is the point at which reports started to be submitted concerning this bug. We were made definitely aware of the bug thanks to the kind efforts of Bert Karwatzki who helped enormously in my being able to track this down and identify the cause of it. The bug arises when an attempt is made to perform a spanning store across two leaf nodes, where the right leaf node is the rightmost child of the shared parent, AND the store completely consumes the right-mode node. This results in mas_wr_spanning_store() mitakenly duplicating the new and existing entries at the maximum pivot within the range, and thus maple tree corruption. The fix patch corrects this by detecting this scenario and disallowing the mistaken duplicate copy. The fix patch commit message goes into great detail as to how this occurs. This series also includes a test which reliably reproduces the issue, and asserts that the fix works correctly. Bert has kindly tested the fix and confirmed it resolved his issues. Also Mikhail Gavrilov kindly reported what appears to be precisely the same bug, which this fix should also resolve. This patch (of 2): There has been a subtle bug present in the maple tree implementation from its inception. This arises from how stores are performed - when a store occurs, it will overwrite overlapping ranges and adjust the tree as necessary to accommodate this. A range may always ultimately span two leaf nodes. In this instance we walk the two leaf nodes, determine which elements are not overwritten to the left and to the right of the start and end of the ranges respectively and then rebalance the tree to contain these entries and the newly inserted one. This kind of store is dubbed a 'spanning store' and is implemented by mas_wr_spanning_store(). In order to reach this stage, mas_store_gfp() invokes mas_wr_preallocate(), mas_wr_store_type() and mas_wr_walk() in turn to walk the tree and update the object (mas) to traverse to the location where the write should be performed, determining its store type. When a spanning store is required, this function returns false stopping at the parent node which contains the target range, and mas_wr_store_type() marks the mas->store_type as wr_spanning_store to denote this fact. When we go to perform the store in mas_wr_spanning_store(), we first determine the elements AFTER the END of the range we wish to store (that is, to the right of the entry to be inserted) - we do this by walking to the NEXT pivot in the tree (i.e. r_mas.last + 1), starting at the node we have just determined contains the range over which we intend to write. We then turn our attention to the entries to the left of the entry we are inserting, whose state is represented by l_mas, and copy these into a 'big node', which is a special node which contains enough slots to contain two leaf node's worth of data. We then copy the entry we wish to store immediately after this - the copy and the insertion of the new entry is performed by mas_store_b_node(). After this we copy the elements to the right of the end of the range which we are inserting, if we have not exceeded the length of the node (i.e. r_mas.offset <= r_mas.end). Herein lies the bug - under very specific circumstances, this logic can break and corrupt the maple tree. Consider the following tree: Height 0 Root Node / \ pivot = 0xffff / \ pivot = ULONG_MAX / \ 1 A [-----] ... / \ pivot = 0x4fff / \ pivot = 0xffff / \ 2 (LEAVES) B [-----] [-----] C ^--- Last pivot 0xffff. Now imagine we wish to store an entry in the range [0x4000, 0xffff] (note that all ranges expressed in maple tree code are inclusive): 1. mas_store_gfp() descends the tree, finds node A at <=0xffff, then determines that this is a spanning store across nodes B and C. The mas state is set such that the current node from which we traverse further is node A. 2. In mas_wr_spanning_store() we try to find elements to the right of pivot 0xffff by searching for an index of 0x10000: - mas_wr_walk_index() invokes mas_wr_walk_descend() and mas_wr_node_walk() in turn. - mas_wr_node_walk() loops over entries in node A until EITHER it finds an entry whose pivot equals or exceeds 0x10000 OR it reaches the final entry. - Since no entry has a pivot equal to or exceeding 0x10000, pivot 0xffff is selected, leading to node C. - mas_wr_walk_traverse() resets the mas state to traverse node C. We loop around and invoke mas_wr_walk_descend() and mas_wr_node_walk() in turn once again. - Again, we reach the last entry in node C, which has a pivot of 0xffff. 3. We then copy the elements to the left of 0x4000 in node B to the big node via mas_store_b_node(), and insert the new [0x4000, 0xffff] entry too. 4. We determine whether we have any entries to copy from the right of the end of the range via - and with r_mas set up at the entry at pivot 0xffff, r_mas.offset <= r_mas.end, and then we DUPLICATE the entry at pivot 0xffff. 5. BUG! The maple tree is corrupted with a duplicate entry. This requires a very specific set of circumstances - we must be spanning the last element in a leaf node, which is the last element in the parent node. spanning store across two leaf nodes with a range that ends at that shared pivot. A potential solution to this problem would simply be to reset the walk each time we traverse r_mas, however given the rarity of this situation it seems that would be rather inefficient. Instead, this patch detects if the right hand node is populated, i.e. has anything we need to copy. We do so by only copying elements from the right of the entry being inserted when the maximum value present exceeds the last, rather than basing this on offset position. The patch also updates some comments and eliminates the unused bool return value in mas_wr_walk_index(). The work performed in commit f8d112a4e657 ("mm/mmap: avoid zeroing vma tree in mmap_region()") seems to have made the probability of this event much more likely, which is the point at which reports started to be submitted concerning this bug. The motivation for this change arose from Bert Karwatzki's report of encountering mm instability after the release of kernel v6.12-rc1 which, after the use of CONFIG_DEBUG_VM_MAPLE_TREE and similar configuration options, was identified as maple tree corruption. After Bert very generously provided his time and ability to reproduce this event consistently, I was able to finally identify that the issue discussed in this commit message was occurring for him. Link: https://lkml.kernel.org/r/cover.1728314402.git.lorenzo.stoakes@oracle.com Link: https://lkml.kernel.org/r/48b349a2a0f7c76e18772712d0997a5e12ab0a3b.1728314403.git.lorenzo.stoakes@oracle.com Fixes: 54a611b60590 ("Maple Tree: add new data structure") Signed-off-by: Lorenzo Stoakes Reported-by: Bert Karwatzki Closes: https://lore.kernel.org/all/20241001023402.3374-1-spasswolf@web.de/ Tested-by: Bert Karwatzki Reported-by: Mikhail Gavrilov Closes: https://lore.kernel.org/all/CABXGCsOPwuoNOqSMmAvWO2Fz4TEmPnjFj-b7iF+XFRu1h7-+Dg@mail.gmail.com/ Acked-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Tested-by: Mikhail Gavrilov Reviewed-by: Wei Yang Cc: Matthew Wilcox Cc: Sidhartha Kumar Cc: Signed-off-by: Andrew Morton --- lib/maple_tree.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index ce7c7a7a8258..3619301dda2e 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -2196,6 +2196,8 @@ static inline void mas_node_or_none(struct ma_state *mas, /* * mas_wr_node_walk() - Find the correct offset for the index in the @mas. + * If @mas->index cannot be found within the containing + * node, we traverse to the last entry in the node. * @wr_mas: The maple write state * * Uses mas_slot_locked() and does not need to worry about dead nodes. @@ -3532,7 +3534,7 @@ static bool mas_wr_walk(struct ma_wr_state *wr_mas) return true; } -static bool mas_wr_walk_index(struct ma_wr_state *wr_mas) +static void mas_wr_walk_index(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; @@ -3541,11 +3543,9 @@ static bool mas_wr_walk_index(struct ma_wr_state *wr_mas) wr_mas->content = mas_slot_locked(mas, wr_mas->slots, mas->offset); if (ma_is_leaf(wr_mas->type)) - return true; + return; mas_wr_walk_traverse(wr_mas); - } - return true; } /* * mas_extend_spanning_null() - Extend a store of a %NULL to include surrounding %NULLs. @@ -3765,8 +3765,8 @@ static noinline void mas_wr_spanning_store(struct ma_wr_state *wr_mas) memset(&b_node, 0, sizeof(struct maple_big_node)); /* Copy l_mas and store the value in b_node. */ mas_store_b_node(&l_wr_mas, &b_node, l_mas.end); - /* Copy r_mas into b_node. */ - if (r_mas.offset <= r_mas.end) + /* Copy r_mas into b_node if there is anything to copy. */ + if (r_mas.max > r_mas.last) mas_mab_cp(&r_mas, r_mas.offset, r_mas.end, &b_node, b_node.b_end + 1); else From e993457df65896696e165defa8a468a831d0da1b Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Mon, 7 Oct 2024 16:28:33 +0100 Subject: [PATCH 28/28] maple_tree: add regression test for spanning store bug Add a regression test to assert that, when performing a spanning store which consumes the entirety of the rightmost right leaf node does not result in maple tree corruption when doing so. This achieves this by building a test tree of 3 levels and establishing a store which ultimately results in a spanned store of this nature. Link: https://lkml.kernel.org/r/30cdc101a700d16e03ba2f9aa5d83f2efa894168.1728314403.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Acked-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Reviewed-by: Wei Yang Cc: Bert Karwatzki Cc: Matthew Wilcox Cc: Mikhail Gavrilov Cc: Sidhartha Kumar Signed-off-by: Andrew Morton --- tools/testing/radix-tree/maple.c | 84 ++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 6ec18883e11e..551ae6898c1d 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -36432,9 +36432,93 @@ void farmer_tests(void) check_nomem(&tree); } +static unsigned long get_last_index(struct ma_state *mas) +{ + struct maple_node *node = mas_mn(mas); + enum maple_type mt = mte_node_type(mas->node); + unsigned long *pivots = ma_pivots(node, mt); + unsigned long last_index = mas_data_end(mas); + + BUG_ON(last_index == 0); + + return pivots[last_index - 1] + 1; +} + +/* + * Assert that we handle spanning stores that consume the entirety of the right + * leaf node correctly. + */ +static void test_spanning_store_regression(void) +{ + unsigned long from = 0, to = 0; + DEFINE_MTREE(tree); + MA_STATE(mas, &tree, 0, 0); + + /* + * Build a 3-level tree. We require a parent node below the root node + * and 2 leaf nodes under it, so we can span the entirety of the right + * hand node. + */ + build_full_tree(&tree, 0, 3); + + /* Descend into position at depth 2. */ + mas_reset(&mas); + mas_start(&mas); + mas_descend(&mas); + mas_descend(&mas); + + /* + * We need to establish a tree like the below. + * + * Then we can try a store in [from, to] which results in a spanned + * store across nodes B and C, with the maple state at the time of the + * write being such that only the subtree at A and below is considered. + * + * Height + * 0 Root Node + * / \ + * pivot = to / \ pivot = ULONG_MAX + * / \ + * 1 A [-----] ... + * / \ + * pivot = from / \ pivot = to + * / \ + * 2 (LEAVES) B [-----] [-----] C + * ^--- Last pivot to. + */ + while (true) { + unsigned long tmp = get_last_index(&mas); + + if (mas_next_sibling(&mas)) { + from = tmp; + to = mas.max; + } else { + break; + } + } + + BUG_ON(from == 0 && to == 0); + + /* Perform the store. */ + mas_set_range(&mas, from, to); + mas_store_gfp(&mas, xa_mk_value(0xdead), GFP_KERNEL); + + /* If the regression occurs, the validation will fail. */ + mt_validate(&tree); + + /* Cleanup. */ + __mt_destroy(&tree); +} + +static void regression_tests(void) +{ + test_spanning_store_regression(); +} + void maple_tree_tests(void) { #if !defined(BENCH) + regression_tests(); farmer_tests(); #endif maple_tree_seed();