From d0e9fe1758f222f13ec893f856552d81a10d266d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 10 Apr 2010 10:36:19 -0700 Subject: Simplify and comment on anon_vma re-use for anon_vma_prepare() This changes the anon_vma reuse case to require that we only reuse simple anon_vma's - ie the case when the vma only has a single anon_vma associated with it. This means that a reuse of an anon_vma from an adjacent vma will always guarantee that both vma's are associated not only with the same anon_vma, they will also have the same anon_vma chain (of just a single entry in this case). And since anon_vma re-use was the only case where the same anon_vma might be associated with different chains of anon_vma's, we now have the case that every vma that shares the same anon_vma will always also have the same chain. That makes it much easier to think about merging vma's that share the same anon_vma's: you can always just drop the other anon_vma chain in anon_vma_merge() since you know that they are always identical. This also splits up the function to validate the anon_vma re-use, and adds a lot of commentary about the possible races. Reviewed-by: Rik van Riel Acked-by: Johannes Weiner Tested-by: Borislav Petkov [ "That didn't fix it" ] Signed-off-by: Linus Torvalds --- mm/mmap.c | 86 +++++++++++++++++++++++++++++++++++++++++++++------------------ 1 file changed, 62 insertions(+), 24 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index 75557c639ad4..acb023e2d35a 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -824,6 +824,61 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, return NULL; } +/* + * Rough compatbility check to quickly see if it's even worth looking + * at sharing an anon_vma. + * + * They need to have the same vm_file, and the flags can only differ + * in things that mprotect may change. + * + * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that + * we can merge the two vma's. For example, we refuse to merge a vma if + * there is a vm_ops->close() function, because that indicates that the + * driver is doing some kind of reference counting. But that doesn't + * really matter for the anon_vma sharing case. + */ +static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b) +{ + return a->vm_end == b->vm_start && + mpol_equal(vma_policy(a), vma_policy(b)) && + a->vm_file == b->vm_file && + !((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC)) && + b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); +} + +/* + * Do some basic sanity checking to see if we can re-use the anon_vma + * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be + * the same as 'old', the other will be the new one that is trying + * to share the anon_vma. + * + * NOTE! This runs with mm_sem held for reading, so it is possible that + * the anon_vma of 'old' is concurrently in the process of being set up + * by another page fault trying to merge _that_. But that's ok: if it + * is being set up, that automatically means that it will be a singleton + * acceptable for merging, so we can do all of this optimistically. But + * we do that ACCESS_ONCE() to make sure that we never re-load the pointer. + * + * IOW: that the "list_is_singular()" test on the anon_vma_chain only + * matters for the 'stable anon_vma' case (ie the thing we want to avoid + * is to return an anon_vma that is "complex" due to having gone through + * a fork). + * + * We also make sure that the two vma's are compatible (adjacent, + * and with the same memory policies). That's all stable, even with just + * a read lock on the mm_sem. + */ +static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) +{ + if (anon_vma_compatible(a, b)) { + struct anon_vma *anon_vma = ACCESS_ONCE(old->anon_vma); + + if (anon_vma && list_is_singular(&old->anon_vma_chain)) + return anon_vma; + } + return NULL; +} + /* * find_mergeable_anon_vma is used by anon_vma_prepare, to check * neighbouring vmas for a suitable anon_vma, before it goes off @@ -834,28 +889,16 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, */ struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) { + struct anon_vma *anon_vma; struct vm_area_struct *near; - unsigned long vm_flags; near = vma->vm_next; if (!near) goto try_prev; - /* - * Since only mprotect tries to remerge vmas, match flags - * which might be mprotected into each other later on. - * Neither mlock nor madvise tries to remerge at present, - * so leave their flags as obstructing a merge. - */ - vm_flags = vma->vm_flags & ~(VM_READ|VM_WRITE|VM_EXEC); - vm_flags |= near->vm_flags & (VM_READ|VM_WRITE|VM_EXEC); - - if (near->anon_vma && vma->vm_end == near->vm_start && - mpol_equal(vma_policy(vma), vma_policy(near)) && - can_vma_merge_before(near, vm_flags, - NULL, vma->vm_file, vma->vm_pgoff + - ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT))) - return near->anon_vma; + anon_vma = reusable_anon_vma(near, vma, near); + if (anon_vma) + return anon_vma; try_prev: /* * It is potentially slow to have to call find_vma_prev here. @@ -868,14 +911,9 @@ try_prev: if (!near) goto none; - vm_flags = vma->vm_flags & ~(VM_READ|VM_WRITE|VM_EXEC); - vm_flags |= near->vm_flags & (VM_READ|VM_WRITE|VM_EXEC); - - if (near->anon_vma && near->vm_end == vma->vm_start && - mpol_equal(vma_policy(near), vma_policy(vma)) && - can_vma_merge_after(near, vm_flags, - NULL, vma->vm_file, vma->vm_pgoff)) - return near->anon_vma; + anon_vma = reusable_anon_vma(near, near, vma); + if (anon_vma) + return anon_vma; none: /* * There's no absolute need to look only at touching neighbours: -- cgit v1.2.3 From 287d97ac032136724143cde8d5964b414d562ee3 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 10 Apr 2010 15:22:30 -0700 Subject: vma_adjust: fix the copying of anon_vma chains When we move the boundaries between two vma's due to things like mprotect, we need to make sure that the anon_vma of the pages that got moved from one vma to another gets properly copied around. And that was not always the case, in this rather hard-to-follow code sequence. Clarify the code, and fix it so that it copies the anon_vma from the right source. Reviewed-by: Rik van Riel Acked-by: Johannes Weiner Tested-by: Borislav Petkov [ "Yeah, not so much this one either" ] Signed-off-by: Linus Torvalds --- mm/mmap.c | 24 ++++++++---------------- 1 file changed, 8 insertions(+), 16 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index acb023e2d35a..f90ea92f755a 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -507,11 +507,12 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start, struct address_space *mapping = NULL; struct prio_tree_root *root = NULL; struct file *file = vma->vm_file; - struct anon_vma *anon_vma = NULL; long adjust_next = 0; int remove_next = 0; if (next && !insert) { + struct vm_area_struct *exporter = NULL; + if (end >= next->vm_end) { /* * vma expands, overlapping all the next, and @@ -519,7 +520,7 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start, */ again: remove_next = 1 + (end > next->vm_end); end = next->vm_end; - anon_vma = next->anon_vma; + exporter = next; importer = vma; } else if (end > next->vm_start) { /* @@ -527,7 +528,7 @@ again: remove_next = 1 + (end > next->vm_end); * mprotect case 5 shifting the boundary up. */ adjust_next = (end - next->vm_start) >> PAGE_SHIFT; - anon_vma = next->anon_vma; + exporter = next; importer = vma; } else if (end < vma->vm_end) { /* @@ -536,28 +537,19 @@ again: remove_next = 1 + (end > next->vm_end); * mprotect case 4 shifting the boundary down. */ adjust_next = - ((vma->vm_end - end) >> PAGE_SHIFT); - anon_vma = next->anon_vma; + exporter = vma; importer = next; } - } - /* - * When changing only vma->vm_end, we don't really need anon_vma lock. - */ - if (vma->anon_vma && (insert || importer || start != vma->vm_start)) - anon_vma = vma->anon_vma; - if (anon_vma) { /* * Easily overlooked: when mprotect shifts the boundary, * make sure the expanding vma has anon_vma set if the * shrinking vma had, to cover any anon pages imported. */ - if (importer && !importer->anon_vma) { - /* Block reverse map lookups until things are set up. */ - if (anon_vma_clone(importer, vma)) { + if (exporter && exporter->anon_vma && !importer->anon_vma) { + if (anon_vma_clone(importer, exporter)) return -ENOMEM; - } - importer->anon_vma = anon_vma; + importer->anon_vma = exporter->anon_vma; } } -- cgit v1.2.3 From 646d87b481dab4ba8301716600dfd276605b0ab0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 11 Apr 2010 17:15:03 -0700 Subject: anon_vma: clone the anon_vma chain in the right order We want to walk the chain in reverse order when cloning it, so that the order of the result chain will be the same as the order in the source chain. When we add entries to the chain, they go at the head of the chain, so we want to add the source head last. Reviewed-by: Rik van Riel Acked-by: Johannes Weiner Tested-by: Borislav Petkov [ "No, it still oopses" ] Signed-off-by: Linus Torvalds --- mm/rmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/rmap.c b/mm/rmap.c index eaa7a09eb72e..ee97d38ed7d9 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -182,7 +182,7 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { struct anon_vma_chain *avc, *pavc; - list_for_each_entry(pavc, &src->anon_vma_chain, same_vma) { + list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) { avc = anon_vma_chain_alloc(); if (!avc) goto enomem_failure; -- cgit v1.2.3 From ea90002b0fa7bdee86ec22eba1d951f30bf043a6 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 12 Apr 2010 12:44:29 -0700 Subject: anonvma: when setting up page->mapping, we need to pick the _oldest_ anonvma Otherwise we might be mapping in a page in a new mapping, but that page (through the swapcache) would later be mapped into an old mapping too. The page->mapping must be the case that works for everybody, not just the mapping that happened to page it in first. Here's the scenario: - page gets allocated/mapped by process A. Let's call the anon_vma we associate the page with 'A' to keep it easy to track. - Process A forks, creating process B. The anon_vma in B is 'B', and has a chain that looks like 'B' -> 'A'. Everything is fine. - Swapping happens. The page (with mapping pointing to 'A') gets swapped out (perhaps not to disk - it's enough to assume that it's just not mapped any more, and lives entirely in the swap-cache) - Process B pages it in, which goes like this: do_swap_page -> page = lookup_swap_cache(entry); ... set_pte_at(mm, address, page_table, pte); page_add_anon_rmap(page, vma, address); And think about what happens here! In particular, what happens is that this will now be the "first" mapping of that page, so page_add_anon_rmap() used to do if (first) __page_set_anon_rmap(page, vma, address); and notice what anon_vma it will use? It will use the anon_vma for process B! What happens then? Trivial: process 'A' also pages it in (nothing happens, it's not the first mapping), and then process 'B' execve's or exits or unmaps, making anon_vma B go away. End result: process A has a page that points to anon_vma B, but anon_vma B does not exist any more. This can go on forever. Forget about RCU grace periods, forget about locking, forget anything like that. The bug is simply that page->mapping points to an anon_vma that was correct at one point, but was _not_ the one that was shared by all users of that possible mapping. Changing it to always use the deepest anon_vma in the anonvma chain gets us to the safest model. This can be improved in certain cases: if we know the page is private to just this particular mapping (for example, it's a new page, or it is the only swapcache entry), we could pick the top (most specific) anon_vma. But that's a future optimization. Make it _work_ reliably first. Reviewed-by: Rik van Riel Acked-by: Johannes Weiner Tested-by: Borislav Petkov [ "What do you know, I think you fixed it!" ] Signed-off-by: Linus Torvalds --- mm/rmap.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/mm/rmap.c b/mm/rmap.c index ee97d38ed7d9..4bad3267537a 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -734,9 +734,20 @@ void page_move_anon_rmap(struct page *page, static void __page_set_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { - struct anon_vma *anon_vma = vma->anon_vma; + struct anon_vma_chain *avc; + struct anon_vma *anon_vma; + + BUG_ON(!vma->anon_vma); + + /* + * We must use the _oldest_ possible anon_vma for the page mapping! + * + * So take the last AVC chain entry in the vma, which is the deepest + * ancestor, and use the anon_vma from that. + */ + avc = list_entry(vma->anon_vma_chain.prev, struct anon_vma_chain, same_vma); + anon_vma = avc->anon_vma; - BUG_ON(!anon_vma); anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; page->mapping = (struct address_space *) anon_vma; page->index = linear_page_index(vma, address); -- cgit v1.2.3