diff options
| -rw-r--r-- | Documentation/filesystems/proc.rst | 4 | ||||
| -rw-r--r-- | MAINTAINERS | 1 | ||||
| -rw-r--r-- | drivers/rapidio/rio_cm.c | 3 | ||||
| -rw-r--r-- | include/linux/fs.h | 6 | ||||
| -rw-r--r-- | include/linux/scatterlist.h | 4 | ||||
| -rw-r--r-- | init/initramfs.c | 1 | ||||
| -rw-r--r-- | init/main.c | 1 | ||||
| -rw-r--r-- | lib/scatterlist.c | 8 | ||||
| -rw-r--r-- | mm/madvise.c | 2 | ||||
| -rw-r--r-- | mm/util.c | 40 | ||||
| -rw-r--r-- | mm/vma.c | 23 | ||||
| -rw-r--r-- | mm/vma.h | 47 | ||||
| -rw-r--r-- | tools/testing/selftests/mm/gup_longterm.c | 7 | ||||
| -rw-r--r-- | tools/testing/vma/vma_internal.h | 16 |
14 files changed, 134 insertions, 29 deletions
diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 2a17865dfe39..5236cb52e357 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -584,7 +584,6 @@ encoded manner. The codes are the following: ms may share gd stack segment growns down pf pure PFN range - dw disabled write to the mapped file lo pages are locked in memory io memory mapped I/O area sr sequential read advise provided @@ -607,8 +606,11 @@ encoded manner. The codes are the following: mt arm64 MTE allocation tags are enabled um userfaultfd missing tracking uw userfaultfd wr-protect tracking + ui userfaultfd minor fault ss shadow/guarded control stack page sl sealed + lf lock on fault pages + dp always lazily freeable mapping == ======================================= Note that there is no guarantee that every flag and associated mnemonic will diff --git a/MAINTAINERS b/MAINTAINERS index 0183c028fa18..0c1d245bf7b8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15921,6 +15921,7 @@ R: Liam R. Howlett <Liam.Howlett@oracle.com> R: Nico Pache <npache@redhat.com> R: Ryan Roberts <ryan.roberts@arm.com> R: Dev Jain <dev.jain@arm.com> +R: Barry Song <baohua@kernel.org> L: linux-mm@kvack.org S: Maintained W: http://www.linux-mm.org diff --git a/drivers/rapidio/rio_cm.c b/drivers/rapidio/rio_cm.c index 97287e838ce1..66464674223f 100644 --- a/drivers/rapidio/rio_cm.c +++ b/drivers/rapidio/rio_cm.c @@ -783,6 +783,9 @@ static int riocm_ch_send(u16 ch_id, void *buf, int len) if (buf == NULL || ch_id == 0 || len == 0 || len > RIO_MAX_MSG_SIZE) return -EINVAL; + if (len < sizeof(struct rio_ch_chan_hdr)) + return -EINVAL; /* insufficient data from user */ + ch = riocm_get_channel(ch_id); if (!ch) { riocm_error("%s(%d) ch_%d not found", current->comm, diff --git a/include/linux/fs.h b/include/linux/fs.h index 96c7925a6551..4ec77da65f14 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2274,10 +2274,12 @@ static inline bool file_has_valid_mmap_hooks(struct file *file) return true; } +int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma); + static inline int call_mmap(struct file *file, struct vm_area_struct *vma) { - if (WARN_ON_ONCE(file->f_op->mmap_prepare)) - return -EINVAL; + if (file->f_op->mmap_prepare) + return compat_vma_mmap_prepare(file, vma); return file->f_op->mmap(file, vma); } diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 0cdbfc42f153..6f8a4965f9b9 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -99,7 +99,7 @@ static inline bool sg_is_last(struct scatterlist *sg) * @sg: The current sg entry * * Description: - * Usually the next entry will be @sg@ + 1, but if this sg element is part + * Usually the next entry will be @sg + 1, but if this sg element is part * of a chained scatterlist, it could jump to the start of a new * scatterlist array. * @@ -254,7 +254,7 @@ static inline void __sg_chain(struct scatterlist *chain_sg, * @sgl: Second scatterlist * * Description: - * Links @prv@ and @sgl@ together, to form a longer scatterlist. + * Links @prv and @sgl together, to form a longer scatterlist. * **/ static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents, diff --git a/init/initramfs.c b/init/initramfs.c index 72bad44a1d41..097673b97784 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> #include <linux/async.h> +#include <linux/export.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/types.h> diff --git a/init/main.c b/init/main.c index ed576c7f475d..225a58279acd 100644 --- a/init/main.c +++ b/init/main.c @@ -13,6 +13,7 @@ #define DEBUG /* Enable initcall_debug */ #include <linux/types.h> +#include <linux/export.h> #include <linux/extable.h> #include <linux/module.h> #include <linux/proc_fs.h> diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 7582dfab7fe3..4af1c8b0775a 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -73,9 +73,9 @@ EXPORT_SYMBOL(sg_nents_for_len); * Should only be used casually, it (currently) scans the entire list * to get the last entry. * - * Note that the @sgl@ pointer passed in need not be the first one, - * the important bit is that @nents@ denotes the number of entries that - * exist from @sgl@. + * Note that the @sgl pointer passed in need not be the first one, + * the important bit is that @nents denotes the number of entries that + * exist from @sgl. * **/ struct scatterlist *sg_last(struct scatterlist *sgl, unsigned int nents) @@ -345,7 +345,7 @@ EXPORT_SYMBOL(__sg_alloc_table); * @gfp_mask: GFP allocation mask * * Description: - * Allocate and initialize an sg table. If @nents@ is larger than + * Allocate and initialize an sg table. If @nents is larger than * SG_MAX_SINGLE_ALLOC a chained sg table will be setup. * **/ diff --git a/mm/madvise.c b/mm/madvise.c index 5f7a66a1617e..1d44a35ae85c 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -508,6 +508,7 @@ restart: pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0; @@ -741,6 +742,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, start_pte = pte; if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0; diff --git a/mm/util.c b/mm/util.c index 448117da071f..0b270c43d7d1 100644 --- a/mm/util.c +++ b/mm/util.c @@ -1131,3 +1131,43 @@ void flush_dcache_folio(struct folio *folio) } EXPORT_SYMBOL(flush_dcache_folio); #endif + +/** + * compat_vma_mmap_prepare() - Apply the file's .mmap_prepare() hook to an + * existing VMA + * @file: The file which possesss an f_op->mmap_prepare() hook + * @vma: The VMA to apply the .mmap_prepare() hook to. + * + * Ordinarily, .mmap_prepare() is invoked directly upon mmap(). However, certain + * 'wrapper' file systems invoke a nested mmap hook of an underlying file. + * + * Until all filesystems are converted to use .mmap_prepare(), we must be + * conservative and continue to invoke these 'wrapper' filesystems using the + * deprecated .mmap() hook. + * + * However we have a problem if the underlying file system possesses an + * .mmap_prepare() hook, as we are in a different context when we invoke the + * .mmap() hook, already having a VMA to deal with. + * + * compat_vma_mmap_prepare() is a compatibility function that takes VMA state, + * establishes a struct vm_area_desc descriptor, passes to the underlying + * .mmap_prepare() hook and applies any changes performed by it. + * + * Once the conversion of filesystems is complete this function will no longer + * be required and will be removed. + * + * Returns: 0 on success or error. + */ +int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma) +{ + struct vm_area_desc desc; + int err; + + err = file->f_op->mmap_prepare(vma_to_desc(vma, &desc)); + if (err) + return err; + set_vma_from_desc(vma, &desc); + + return 0; +} +EXPORT_SYMBOL(compat_vma_mmap_prepare); @@ -967,26 +967,9 @@ static __must_check struct vm_area_struct *vma_merge_existing_range( err = dup_anon_vma(next, middle, &anon_dup); } - if (err) + if (err || commit_merge(vmg)) goto abort; - err = commit_merge(vmg); - if (err) { - VM_WARN_ON(err != -ENOMEM); - - if (anon_dup) - unlink_anon_vmas(anon_dup); - - /* - * We've cleaned up any cloned anon_vma's, no VMAs have been - * modified, no harm no foul if the user requests that we not - * report this and just give up, leaving the VMAs unmerged. - */ - if (!vmg->give_up_on_oom) - vmg->state = VMA_MERGE_ERROR_NOMEM; - return NULL; - } - khugepaged_enter_vma(vmg->target, vmg->flags); vmg->state = VMA_MERGE_SUCCESS; return vmg->target; @@ -995,6 +978,9 @@ abort: vma_iter_set(vmg->vmi, start); vma_iter_load(vmg->vmi); + if (anon_dup) + unlink_anon_vmas(anon_dup); + /* * This means we have failed to clone anon_vma's correctly, but no * actual changes to VMAs have occurred, so no harm no foul - if the @@ -3127,7 +3113,6 @@ int __vm_munmap(unsigned long start, size_t len, bool unlock) return ret; } - /* Insert vm structure into process list sorted by address * and into the inode's i_mmap tree. If vm_file is non-NULL * then i_mmap_rwsem is taken here. @@ -222,6 +222,53 @@ static inline int vma_iter_store_gfp(struct vma_iterator *vmi, return 0; } + +/* + * Temporary helper functions for file systems which wrap an invocation of + * f_op->mmap() but which might have an underlying file system which implements + * f_op->mmap_prepare(). + */ + +static inline struct vm_area_desc *vma_to_desc(struct vm_area_struct *vma, + struct vm_area_desc *desc) +{ + desc->mm = vma->vm_mm; + desc->start = vma->vm_start; + desc->end = vma->vm_end; + + desc->pgoff = vma->vm_pgoff; + desc->file = vma->vm_file; + desc->vm_flags = vma->vm_flags; + desc->page_prot = vma->vm_page_prot; + + desc->vm_ops = NULL; + desc->private_data = NULL; + + return desc; +} + +static inline void set_vma_from_desc(struct vm_area_struct *vma, + struct vm_area_desc *desc) +{ + /* + * Since we're invoking .mmap_prepare() despite having a partially + * established VMA, we must take care to handle setting fields + * correctly. + */ + + /* Mutable fields. Populated with initial state. */ + vma->vm_pgoff = desc->pgoff; + if (vma->vm_file != desc->file) + vma_set_file(vma, desc->file); + if (vma->vm_flags != desc->vm_flags) + vm_flags_set(vma, desc->vm_flags); + vma->vm_page_prot = desc->page_prot; + + /* User-defined fields. */ + vma->vm_ops = desc->vm_ops; + vma->vm_private_data = desc->private_data; +} + int do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c index 8a97ac5176a4..29047d2e0c49 100644 --- a/tools/testing/selftests/mm/gup_longterm.c +++ b/tools/testing/selftests/mm/gup_longterm.c @@ -298,8 +298,11 @@ static void run_with_memfd(test_fn fn, const char *desc) log_test_start("%s ... with memfd", desc); fd = memfd_create("test", 0); - if (fd < 0) + if (fd < 0) { ksft_print_msg("memfd_create() failed (%s)\n", strerror(errno)); + log_test_result(KSFT_SKIP); + return; + } fn(fd, pagesize); close(fd); @@ -366,6 +369,8 @@ static void run_with_memfd_hugetlb(test_fn fn, const char *desc, fd = memfd_create("test", flags); if (fd < 0) { ksft_print_msg("memfd_create() failed (%s)\n", strerror(errno)); + log_test_result(KSFT_SKIP); + return; } fn(fd, hugetlbsize); diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h index 4505b1c31be1..14718ca23a05 100644 --- a/tools/testing/vma/vma_internal.h +++ b/tools/testing/vma/vma_internal.h @@ -159,6 +159,14 @@ typedef __bitwise unsigned int vm_fault_t; #define ASSERT_EXCLUSIVE_WRITER(x) +/** + * swap - swap values of @a and @b + * @a: first value + * @b: second value + */ +#define swap(a, b) \ + do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) + struct kref { refcount_t refcount; }; @@ -1468,4 +1476,12 @@ static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma) (void)vma; } +static inline void vma_set_file(struct vm_area_struct *vma, struct file *file) +{ + /* Changing an anonymous vma with this is illegal */ + get_file(file); + swap(vma->vm_file, file); + fput(file); +} + #endif /* __MM_VMA_INTERNAL_H */ |