From f958d7b528b1b40c44cfda5eabe2d82760d868c3 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 11 Apr 2019 10:06:20 -0700 Subject: mm: make page ref count overflow check tighter and more explicit We have a VM_BUG_ON() to check that the page reference count doesn't underflow (or get close to overflow) by checking the sign of the count. That's all fine, but we actually want to allow people to use a "get page ref unless it's already very high" helper function, and we want that one to use the sign of the page ref (without triggering this VM_BUG_ON). Change the VM_BUG_ON to only check for small underflows (or _very_ close to overflowing), and ignore overflows which have strayed into negative territory. Acked-by: Matthew Wilcox Cc: Jann Horn Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 80bb6408fe73..541d99b86aea 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -965,6 +965,10 @@ static inline bool is_pci_p2pdma_page(const struct page *page) } #endif /* CONFIG_DEV_PAGEMAP_OPS */ +/* 127: arbitrary random number, small enough to assemble well */ +#define page_ref_zero_or_close_to_overflow(page) \ + ((unsigned int) page_ref_count(page) + 127u <= 127u) + static inline void get_page(struct page *page) { page = compound_head(page); @@ -972,7 +976,7 @@ static inline void get_page(struct page *page) * Getting a normal page or the head of a compound page * requires to already have an elevated page->_refcount. */ - VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page); + VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page); page_ref_inc(page); } -- cgit v1.2.3 From 88b1a17dfc3ed7728316478fae0f5ad508f50397 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 11 Apr 2019 10:14:59 -0700 Subject: mm: add 'try_get_page()' helper function This is the same as the traditional 'get_page()' function, but instead of unconditionally incrementing the reference count of the page, it only does so if the count was "safe". It returns whether the reference count was incremented (and is marked __must_check, since the caller obviously has to be aware of it). Also like 'get_page()', you can't use this function unless you already had a reference to the page. The intent is that you can use this exactly like get_page(), but in situations where you want to limit the maximum reference count. The code currently does an unconditional WARN_ON_ONCE() if we ever hit the reference count issues (either zero or negative), as a notification that the conditional non-increment actually happened. NOTE! The count access for the "safety" check is inherently racy, but that doesn't matter since the buffer we use is basically half the range of the reference count (ie we look at the sign of the count). Acked-by: Matthew Wilcox Cc: Jann Horn Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/include/linux/mm.h b/include/linux/mm.h index 541d99b86aea..7000ddd807e0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -980,6 +980,15 @@ static inline void get_page(struct page *page) page_ref_inc(page); } +static inline __must_check bool try_get_page(struct page *page) +{ + page = compound_head(page); + if (WARN_ON_ONCE(page_ref_count(page) <= 0)) + return false; + page_ref_inc(page); + return true; +} + static inline void put_page(struct page *page) { page = compound_head(page); -- cgit v1.2.3 From 8fde12ca79aff9b5ba951fce1a2641901b8d8e64 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 11 Apr 2019 10:49:19 -0700 Subject: mm: prevent get_user_pages() from overflowing page refcount If the page refcount wraps around past zero, it will be freed while there are still four billion references to it. One of the possible avenues for an attacker to try to make this happen is by doing direct IO on a page multiple times. This patch makes get_user_pages() refuse to take a new page reference if there are already more than two billion references to the page. Reported-by: Jann Horn Acked-by: Matthew Wilcox Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- mm/gup.c | 48 ++++++++++++++++++++++++++++++++++++------------ mm/hugetlb.c | 13 +++++++++++++ 2 files changed, 49 insertions(+), 12 deletions(-) diff --git a/mm/gup.c b/mm/gup.c index 75029649baca..81e0bdefa2cc 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -157,8 +157,12 @@ retry: goto retry; } - if (flags & FOLL_GET) - get_page(page); + if (flags & FOLL_GET) { + if (unlikely(!try_get_page(page))) { + page = ERR_PTR(-ENOMEM); + goto out; + } + } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) @@ -295,7 +299,10 @@ retry_locked: if (pmd_trans_unstable(pmd)) ret = -EBUSY; } else { - get_page(page); + if (unlikely(!try_get_page(page))) { + spin_unlock(ptl); + return ERR_PTR(-ENOMEM); + } spin_unlock(ptl); lock_page(page); ret = split_huge_page(page); @@ -497,7 +504,10 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, if (is_device_public_page(*page)) goto unmap; } - get_page(*page); + if (unlikely(!try_get_page(*page))) { + ret = -ENOMEM; + goto unmap; + } out: ret = 0; unmap: @@ -1393,6 +1403,20 @@ static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) } } +/* + * Return the compund head page with ref appropriately incremented, + * or NULL if that failed. + */ +static inline struct page *try_get_compound_head(struct page *page, int refs) +{ + struct page *head = compound_head(page); + if (WARN_ON_ONCE(page_ref_count(head) < 0)) + return NULL; + if (unlikely(!page_cache_add_speculative(head, refs))) + return NULL; + return head; +} + #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) @@ -1427,9 +1451,9 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); - head = compound_head(page); - if (!page_cache_get_speculative(head)) + head = try_get_compound_head(page, 1); + if (!head) goto pte_unmap; if (unlikely(pte_val(pte) != pte_val(*ptep))) { @@ -1568,8 +1592,8 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, refs++; } while (addr += PAGE_SIZE, addr != end); - head = compound_head(pmd_page(orig)); - if (!page_cache_add_speculative(head, refs)) { + head = try_get_compound_head(pmd_page(orig), refs); + if (!head) { *nr -= refs; return 0; } @@ -1606,8 +1630,8 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, refs++; } while (addr += PAGE_SIZE, addr != end); - head = compound_head(pud_page(orig)); - if (!page_cache_add_speculative(head, refs)) { + head = try_get_compound_head(pud_page(orig), refs); + if (!head) { *nr -= refs; return 0; } @@ -1643,8 +1667,8 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, refs++; } while (addr += PAGE_SIZE, addr != end); - head = compound_head(pgd_page(orig)); - if (!page_cache_add_speculative(head, refs)) { + head = try_get_compound_head(pgd_page(orig), refs); + if (!head) { *nr -= refs; return 0; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 8dfdffc34a99..c220315dc533 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4298,6 +4298,19 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT; page = pte_page(huge_ptep_get(pte)); + + /* + * Instead of doing 'try_get_page()' below in the same_page + * loop, just check the count once here. + */ + if (unlikely(page_count(page) <= 0)) { + if (pages) { + spin_unlock(ptl); + remainder = 0; + err = -ENOMEM; + break; + } + } same_page: if (pages) { pages[i] = mem_map_offset(page, pfn_offset); -- cgit v1.2.3 From 15fab63e1e57be9fdb5eec1bbc5916e9825e9acb Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 5 Apr 2019 14:02:10 -0700 Subject: fs: prevent page refcount overflow in pipe_buf_get Change pipe_buf_get() to return a bool indicating whether it succeeded in raising the refcount of the page (if the thing in the pipe is a page). This removes another mechanism for overflowing the page refcount. All callers converted to handle a failure. Reported-by: Jann Horn Signed-off-by: Matthew Wilcox Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 12 ++++++------ fs/pipe.c | 4 ++-- fs/splice.c | 12 ++++++++++-- include/linux/pipe_fs_i.h | 10 ++++++---- kernel/trace/trace.c | 6 +++++- 5 files changed, 29 insertions(+), 15 deletions(-) diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 809c0f2f9942..64f4de983468 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2034,10 +2034,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len; ret = -EINVAL; - if (rem < len) { - pipe_unlock(pipe); - goto out; - } + if (rem < len) + goto out_free; rem = len; while (rem) { @@ -2055,7 +2053,9 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1); pipe->nrbufs--; } else { - pipe_buf_get(pipe, ibuf); + if (!pipe_buf_get(pipe, ibuf)) + goto out_free; + *obuf = *ibuf; obuf->flags &= ~PIPE_BUF_FLAG_GIFT; obuf->len = rem; @@ -2078,11 +2078,11 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, ret = fuse_dev_do_write(fud, &cs, len); pipe_lock(pipe); +out_free: for (idx = 0; idx < nbuf; idx++) pipe_buf_release(pipe, &bufs[idx]); pipe_unlock(pipe); -out: kvfree(bufs); return ret; } diff --git a/fs/pipe.c b/fs/pipe.c index bdc5d3c0977d..b1543b85c14a 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -189,9 +189,9 @@ EXPORT_SYMBOL(generic_pipe_buf_steal); * in the tee() system call, when we duplicate the buffers in one * pipe into another. */ -void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) +bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - get_page(buf->page); + return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); diff --git a/fs/splice.c b/fs/splice.c index de2ede048473..f30af82b850d 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1588,7 +1588,11 @@ retry: * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } *obuf = *ibuf; /* @@ -1660,7 +1664,11 @@ static int link_pipe(struct pipe_inode_info *ipipe, * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } obuf = opipe->bufs + nbuf; *obuf = *ibuf; diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 5a3bb3b7c9ad..3f2a42c11e20 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -108,18 +108,20 @@ struct pipe_buf_operations { /* * Get a reference to the pipe buffer. */ - void (*get)(struct pipe_inode_info *, struct pipe_buffer *); + bool (*get)(struct pipe_inode_info *, struct pipe_buffer *); }; /** * pipe_buf_get - get a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to + * + * Return: %true if the reference was successfully obtained. */ -static inline void pipe_buf_get(struct pipe_inode_info *pipe, +static inline __must_check bool pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - buf->ops->get(pipe, buf); + return buf->ops->get(pipe, buf); } /** @@ -178,7 +180,7 @@ struct pipe_inode_info *alloc_pipe_info(void); void free_pipe_info(struct pipe_inode_info *); /* Generic pipe buffer ops functions */ -void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); +bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c4238b441624..0f300d488c9f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6835,12 +6835,16 @@ static void buffer_pipe_buf_release(struct pipe_inode_info *pipe, buf->private = 0; } -static void buffer_pipe_buf_get(struct pipe_inode_info *pipe, +static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private; + if (ref->ref > INT_MAX/2) + return false; + ref->ref++; + return true; } /* Pipe buffer operations for a buffer. */ -- cgit v1.2.3