diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a3817aff662cce0b5e4df5dfaeb0c5faf25ec716..b32841bcc836ca7fdbd72fa3ac6aa7aa1db25272 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -5261,6 +5261,12 @@ do { \ }) #endif +#if defined(CONFIG_DEBUG_NET) +#define DEBUG_NET_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) +#else +#define DEBUG_NET_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) +#endif + /* * The list of packet types we will receive (as opposed to discard) * and the routines to invoke. diff --git a/mm/filemap.c b/mm/filemap.c index 3b0d8c6dd58704823de8485934cba7a6f61eb28b..0ee312dfedf0f5acb791f5ee3fa6a2832e4a3de8 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2206,7 +2206,7 @@ ssize_t generic_file_buffered_read(struct kiocb *iocb, if (unlikely(!iov_iter_count(iter))) return 0; - iov_iter_truncate(iter, inode->i_sb->s_maxbytes); + iov_iter_truncate(iter, inode->i_sb->s_maxbytes - iocb->ki_pos); index = *ppos >> PAGE_SHIFT; prev_index = ra->prev_pos >> PAGE_SHIFT; diff --git a/mm/internal.h b/mm/internal.h index e85e249a4d9b12c399695f87c2436e8b59228c56..61f3d1697072732b82cbed24f3b1b358a41556cf 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -153,6 +153,25 @@ enum scan_balance { void page_writeback_init(void); +/* + * This is a file-backed mapping, and is about to be memory mapped - invoke its + * mmap hook and safely handle error conditions. On error, VMA hooks will be + * mutated. + * + * @file: File which backs the mapping. + * @vma: VMA which we are mapping. + * + * Returns: 0 if success, error otherwise. + */ +int mmap_file(struct file *file, struct vm_area_struct *vma); + +/* + * If the VMA has a close hook then close it, and since closing it might leave + * it in an inconsistent state which makes the use of any hooks suspect, clear + * them down by installing dummy empty hooks. + */ +void vma_close(struct vm_area_struct *vma); + vm_fault_t do_swap_page(struct vm_fault *vmf); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, diff --git a/mm/mmap.c b/mm/mmap.c index 14e6bfdebbb82de95dfc3d463d0865642ca6de3f..59ee5bcc757d44c78fcf05bb32818a50727a3d1a 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -183,8 +183,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) struct vm_area_struct *next = vma->vm_next; might_sleep(); - if (vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); + vma_close(vma); if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); @@ -1761,7 +1760,7 @@ static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags) return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; } -unsigned long mmap_region(struct file *file, unsigned long addr, +static unsigned long __mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) { @@ -1830,11 +1829,6 @@ unsigned long mmap_region(struct file *file, unsigned long addr, if (error) goto free_vma; } - if (vm_flags & VM_SHARED) { - error = mapping_map_writable(file->f_mapping); - if (error) - goto allow_write_and_free_vma; - } /* ->mmap() can change vma->vm_file, but must guarantee that * vma_link() below can deny write-access if VM_DENYWRITE is set @@ -1842,9 +1836,9 @@ unsigned long mmap_region(struct file *file, unsigned long addr, * new file must not have been exposed to user-space, yet. */ vma->vm_file = get_file(file); - error = call_mmap(file, vma); + error = mmap_file(file, vma); if (error) - goto unmap_and_free_vma; + goto unmap_and_free_file_vma; /* Can addr have changed?? * @@ -1855,9 +1849,17 @@ unsigned long mmap_region(struct file *file, unsigned long addr, */ WARN_ON_ONCE(addr != vma->vm_start); + /* + * Drivers should not permit writability when previously it was + * disallowed. + */ + VM_WARN_ON_ONCE(vm_flags != vma->vm_flags && + !(vm_flags & VM_MAYWRITE) && + (vma->vm_flags & VM_MAYWRITE)); + addr = vma->vm_start; - /* If vm_flags changed after call_mmap(), we should try merge vma again + /* If vm_flags changed after mmap_file(), we should try merge vma again * as we may succeed this time. */ if (unlikely(vm_flags != vma->vm_flags && prev)) { @@ -1886,22 +1888,14 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vma_set_anonymous(vma); } - /* Allow architectures to sanity-check the vma */ - if (security_mmap_region(vma) || - !arch_validate_flags(vma->vm_flags)) { - error = -EINVAL; - if (file) - goto close_and_free_vma; - else - goto free_vma; - } +#ifdef CONFIG_SPARC64 + /* TODO: Fix SPARC ADI! */ + WARN_ON_ONCE(!arch_validate_flags(vm_flags)); +#endif vma_link(mm, vma, prev, rb_link, rb_parent); - /* Once vma denies write, undo our temporary denial count */ if (file) { unmap_writable: - if (vm_flags & VM_SHARED) - mapping_unmap_writable(file->f_mapping); if (vm_flags & VM_DENYWRITE) allow_write_access(file); } @@ -1935,18 +1929,12 @@ unsigned long mmap_region(struct file *file, unsigned long addr, return addr; -close_and_free_vma: - if (vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); -unmap_and_free_vma: +unmap_and_free_file_vma: vma->vm_file = NULL; fput(file); /* Undo any partial mapping done by a device driver. */ unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end); - if (vm_flags & VM_SHARED) - mapping_unmap_writable(file->f_mapping); -allow_write_and_free_vma: if (vm_flags & VM_DENYWRITE) allow_write_access(file); free_vma: @@ -2838,8 +2826,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, return 0; /* Clean everything up if vma_adjust failed. */ - if (new->vm_ops && new->vm_ops->close) - new->vm_ops->close(new); + vma_close(new); if (new->vm_file) fput(new->vm_file); unlink_anon_vmas(new); @@ -2989,6 +2976,36 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, return __do_munmap(mm, start, len, uf, false); } +unsigned long mmap_region(struct file *file, unsigned long addr, + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, + struct list_head *uf) +{ + unsigned long ret; + bool writable_file_mapping = false; + + /* Allow architectures to sanity-check the vm_flags. */ + if (!arch_validate_flags(vm_flags)) + return -EINVAL; + + /* Map writable and ensure this isn't a sealed memfd. */ + if (file && (vm_flags & VM_SHARED)) { + int error = mapping_map_writable(file->f_mapping); + + if (error) + return error; + writable_file_mapping = true; + } + + ret = __mmap_region(file, addr, len, vm_flags, pgoff, uf); + + /* Clear our write mapping regardless of error. */ + if (writable_file_mapping) + mapping_unmap_writable(file->f_mapping); + + validate_mm(current->mm); + return ret; +} + static int __vm_munmap(unsigned long start, size_t len, bool downgrade) { int ret; diff --git a/mm/nommu.c b/mm/nommu.c index 0faf39b32cdb95601307f541aa766cd697810933..f46a883e93e461d007b9498509d664f70575455d 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -662,8 +662,7 @@ static void delete_vma_from_mm(struct vm_area_struct *vma) */ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) { - if (vma->vm_ops && vma->vm_ops->close) - vma->vm_ops->close(vma); + vma_close(vma); if (vma->vm_file) fput(vma->vm_file); put_nommu_region(vma->vm_region); @@ -955,7 +954,7 @@ static int do_mmap_shared_file(struct vm_area_struct *vma) { int ret; - ret = call_mmap(vma->vm_file, vma); + ret = mmap_file(vma->vm_file, vma); if (ret == 0) { vma->vm_region->vm_top = vma->vm_region->vm_end; return 0; @@ -986,7 +985,7 @@ static int do_mmap_private(struct vm_area_struct *vma, * - VM_MAYSHARE will be set if it may attempt to share */ if (capabilities & NOMMU_MAP_DIRECT) { - ret = call_mmap(vma->vm_file, vma); + ret = mmap_file(vma->vm_file, vma); if (ret == 0) { /* shouldn't return success if we're not sharing */ BUG_ON(!(vma->vm_flags & VM_MAYSHARE)); diff --git a/mm/util.c b/mm/util.c index 7fd3c2bb3e4f539f37bec8331618bed8d1edcf09..dd88af382e81c4707a3d2b6d3386bb11ea66e07e 100644 --- a/mm/util.c +++ b/mm/util.c @@ -1073,3 +1073,36 @@ int __weak memcmp_pages(struct page *page1, struct page *page2) kunmap_atomic(addr1); return ret; } + +int mmap_file(struct file *file, struct vm_area_struct *vma) +{ + static const struct vm_operations_struct dummy_vm_ops = {}; + int err = call_mmap(file, vma); + + if (likely(!err)) + return 0; + + /* + * OK, we tried to call the file hook for mmap(), but an error + * arose. The mapping is in an inconsistent state and we most not invoke + * any further hooks on it. + */ + vma->vm_ops = &dummy_vm_ops; + + return err; +} + +void vma_close(struct vm_area_struct *vma) +{ + static const struct vm_operations_struct dummy_vm_ops = {}; + + if (vma->vm_ops && vma->vm_ops->close) { + vma->vm_ops->close(vma); + + /* + * The mapping is in an inconsistent state, and no further hooks + * may be invoked upon it. + */ + vma->vm_ops = &dummy_vm_ops; + } +} diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 3d5192177560db4a73687b5e322dfb19be43feb1..097d0d7c6cf80a1313e4fd48d963b64592085178 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -972,7 +972,7 @@ bool __skb_flow_dissect(const struct net *net, } } - WARN_ON_ONCE(!net); + DEBUG_NET_WARN_ON_ONCE(!net); if (net) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; struct bpf_prog_array *run_array;