diff options
| -rw-r--r-- | mm/vma.c | 81 | ||||
| -rw-r--r-- | tools/testing/vma/vma.c | 100 |
2 files changed, 111 insertions, 70 deletions
@@ -57,6 +57,22 @@ struct mmap_state { .state = VMA_MERGE_START, \ } +/* + * If, at any point, the VMA had unCoW'd mappings from parents, it will maintain + * more than one anon_vma_chain connecting it to more than one anon_vma. A merge + * would mean a wider range of folios sharing the root anon_vma lock, and thus + * potential lock contention, we do not wish to encourage merging such that this + * scales to a problem. + */ +static bool vma_had_uncowed_parents(struct vm_area_struct *vma) +{ + /* + * The list_is_singular() test is to avoid merging VMA cloned from + * parents. This can improve scalability caused by anon_vma lock. + */ + return vma && vma->anon_vma && !list_is_singular(&vma->anon_vma_chain); +} + static inline bool is_mergeable_vma(struct vma_merge_struct *vmg, bool merge_next) { struct vm_area_struct *vma = merge_next ? vmg->next : vmg->prev; @@ -82,24 +98,28 @@ static inline bool is_mergeable_vma(struct vma_merge_struct *vmg, bool merge_nex return true; } -static inline bool is_mergeable_anon_vma(struct anon_vma *anon_vma1, - struct anon_vma *anon_vma2, struct vm_area_struct *vma) +static bool is_mergeable_anon_vma(struct vma_merge_struct *vmg, bool merge_next) { + struct vm_area_struct *tgt = merge_next ? vmg->next : vmg->prev; + struct vm_area_struct *src = vmg->middle; /* exisitng merge case. */ + struct anon_vma *tgt_anon = tgt->anon_vma; + struct anon_vma *src_anon = vmg->anon_vma; + /* - * The list_is_singular() test is to avoid merging VMA cloned from - * parents. This can improve scalability caused by anon_vma lock. + * We _can_ have !src, vmg->anon_vma via copy_vma(). In this instance we + * will remove the existing VMA's anon_vma's so there's no scalability + * concerns. */ - if ((!anon_vma1 || !anon_vma2) && (!vma || - list_is_singular(&vma->anon_vma_chain))) - return true; - return anon_vma1 == anon_vma2; -} + VM_WARN_ON(src && src_anon != src->anon_vma); -/* Are the anon_vma's belonging to each VMA compatible with one another? */ -static inline bool are_anon_vmas_compatible(struct vm_area_struct *vma1, - struct vm_area_struct *vma2) -{ - return is_mergeable_anon_vma(vma1->anon_vma, vma2->anon_vma, NULL); + /* Case 1 - we will dup_anon_vma() from src into tgt. */ + if (!tgt_anon && src_anon) + return !vma_had_uncowed_parents(src); + /* Case 2 - we will simply use tgt's anon_vma. */ + if (tgt_anon && !src_anon) + return !vma_had_uncowed_parents(tgt); + /* Case 3 - the anon_vma's are already shared. */ + return src_anon == tgt_anon; } /* @@ -164,7 +184,7 @@ static bool can_vma_merge_before(struct vma_merge_struct *vmg) pgoff_t pglen = PHYS_PFN(vmg->end - vmg->start); if (is_mergeable_vma(vmg, /* merge_next = */ true) && - is_mergeable_anon_vma(vmg->anon_vma, vmg->next->anon_vma, vmg->next)) { + is_mergeable_anon_vma(vmg, /* merge_next = */ true)) { if (vmg->next->vm_pgoff == vmg->pgoff + pglen) return true; } @@ -184,7 +204,7 @@ static bool can_vma_merge_before(struct vma_merge_struct *vmg) static bool can_vma_merge_after(struct vma_merge_struct *vmg) { if (is_mergeable_vma(vmg, /* merge_next = */ false) && - is_mergeable_anon_vma(vmg->anon_vma, vmg->prev->anon_vma, vmg->prev)) { + is_mergeable_anon_vma(vmg, /* merge_next = */ false)) { if (vmg->prev->vm_pgoff + vma_pages(vmg->prev) == vmg->pgoff) return true; } @@ -400,8 +420,10 @@ static bool can_vma_merge_left(struct vma_merge_struct *vmg) static bool can_vma_merge_right(struct vma_merge_struct *vmg, bool can_merge_left) { - if (!vmg->next || vmg->end != vmg->next->vm_start || - !can_vma_merge_before(vmg)) + struct vm_area_struct *next = vmg->next; + struct vm_area_struct *prev; + + if (!next || vmg->end != next->vm_start || !can_vma_merge_before(vmg)) return false; if (!can_merge_left) @@ -414,7 +436,9 @@ static bool can_vma_merge_right(struct vma_merge_struct *vmg, * * We therefore check this in addition to mergeability to either side. */ - return are_anon_vmas_compatible(vmg->prev, vmg->next); + prev = vmg->prev; + return !prev->anon_vma || !next->anon_vma || + prev->anon_vma == next->anon_vma; } /* @@ -554,7 +578,9 @@ static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, } /* - * dup_anon_vma() - Helper function to duplicate anon_vma + * dup_anon_vma() - Helper function to duplicate anon_vma on VMA merge in the + * instance that the destination VMA has no anon_vma but the source does. + * * @dst: The destination VMA * @src: The source VMA * @dup: Pointer to the destination VMA when successful. @@ -565,9 +591,18 @@ static int dup_anon_vma(struct vm_area_struct *dst, struct vm_area_struct *src, struct vm_area_struct **dup) { /* - * 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. + * There are three cases to consider for correctly propagating + * anon_vma's on merge. + * + * The first is trivial - neither VMA has anon_vma, we need not do + * anything. + * + * The second where both have anon_vma is also a no-op, as they must + * then be the same, so there is simply nothing to copy. + * + * Here we cover the third - if the destination VMA has no anon_vma, + * that is it is unfaulted, we need to ensure that the newly merged + * range is referenced by the anon_vma's of the source. */ if (src->anon_vma && !dst->anon_vma) { int ret; diff --git a/tools/testing/vma/vma.c b/tools/testing/vma/vma.c index 11f761769b5b..7cfd6e31db10 100644 --- a/tools/testing/vma/vma.c +++ b/tools/testing/vma/vma.c @@ -185,6 +185,15 @@ static void vmg_set_range(struct vma_merge_struct *vmg, unsigned long start, vmg->__adjust_next_start = false; } +/* Helper function to set both the VMG range and its anon_vma. */ +static void vmg_set_range_anon_vma(struct vma_merge_struct *vmg, unsigned long start, + unsigned long end, pgoff_t pgoff, vm_flags_t flags, + struct anon_vma *anon_vma) +{ + vmg_set_range(vmg, start, end, pgoff, flags); + vmg->anon_vma = anon_vma; +} + /* * Helper function to try to merge a new VMA. * @@ -265,6 +274,22 @@ static void dummy_close(struct vm_area_struct *) { } +static void __vma_set_dummy_anon_vma(struct vm_area_struct *vma, + struct anon_vma_chain *avc, + struct anon_vma *anon_vma) +{ + vma->anon_vma = anon_vma; + INIT_LIST_HEAD(&vma->anon_vma_chain); + list_add(&avc->same_vma, &vma->anon_vma_chain); + avc->anon_vma = vma->anon_vma; +} + +static void vma_set_dummy_anon_vma(struct vm_area_struct *vma, + struct anon_vma_chain *avc) +{ + __vma_set_dummy_anon_vma(vma, avc, &dummy_anon_vma); +} + static bool test_simple_merge(void) { struct vm_area_struct *vma; @@ -953,6 +978,7 @@ static bool test_merge_existing(void) const struct vm_operations_struct vm_ops = { .close = dummy_close, }; + struct anon_vma_chain avc = {}; /* * Merge right case - partial span. @@ -968,10 +994,10 @@ static bool test_merge_existing(void) vma->vm_ops = &vm_ops; /* This should have no impact. */ vma_next = alloc_and_link_vma(&mm, 0x6000, 0x9000, 6, flags); vma_next->vm_ops = &vm_ops; /* This should have no impact. */ - vmg_set_range(&vmg, 0x3000, 0x6000, 3, flags); + vmg_set_range_anon_vma(&vmg, 0x3000, 0x6000, 3, flags, &dummy_anon_vma); vmg.middle = vma; vmg.prev = vma; - vma->anon_vma = &dummy_anon_vma; + vma_set_dummy_anon_vma(vma, &avc); ASSERT_EQ(merge_existing(&vmg), vma_next); ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS); ASSERT_EQ(vma_next->vm_start, 0x3000); @@ -1001,9 +1027,9 @@ static bool test_merge_existing(void) vma = alloc_and_link_vma(&mm, 0x2000, 0x6000, 2, flags); vma_next = alloc_and_link_vma(&mm, 0x6000, 0x9000, 6, flags); vma_next->vm_ops = &vm_ops; /* This should have no impact. */ - vmg_set_range(&vmg, 0x2000, 0x6000, 2, flags); + vmg_set_range_anon_vma(&vmg, 0x2000, 0x6000, 2, flags, &dummy_anon_vma); vmg.middle = vma; - vma->anon_vma = &dummy_anon_vma; + vma_set_dummy_anon_vma(vma, &avc); ASSERT_EQ(merge_existing(&vmg), vma_next); ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS); ASSERT_EQ(vma_next->vm_start, 0x2000); @@ -1030,11 +1056,10 @@ static bool test_merge_existing(void) vma_prev->vm_ops = &vm_ops; /* This should have no impact. */ vma = alloc_and_link_vma(&mm, 0x3000, 0x7000, 3, flags); vma->vm_ops = &vm_ops; /* This should have no impact. */ - vmg_set_range(&vmg, 0x3000, 0x6000, 3, flags); + vmg_set_range_anon_vma(&vmg, 0x3000, 0x6000, 3, flags, &dummy_anon_vma); vmg.prev = vma_prev; vmg.middle = vma; - vma->anon_vma = &dummy_anon_vma; - + vma_set_dummy_anon_vma(vma, &avc); ASSERT_EQ(merge_existing(&vmg), vma_prev); ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS); ASSERT_EQ(vma_prev->vm_start, 0); @@ -1064,10 +1089,10 @@ static bool test_merge_existing(void) vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags); vma_prev->vm_ops = &vm_ops; /* This should have no impact. */ vma = alloc_and_link_vma(&mm, 0x3000, 0x7000, 3, flags); - vmg_set_range(&vmg, 0x3000, 0x7000, 3, flags); + vmg_set_range_anon_vma(&vmg, 0x3000, 0x7000, 3, flags, &dummy_anon_vma); vmg.prev = vma_prev; vmg.middle = vma; - vma->anon_vma = &dummy_anon_vma; + vma_set_dummy_anon_vma(vma, &avc); ASSERT_EQ(merge_existing(&vmg), vma_prev); ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS); ASSERT_EQ(vma_prev->vm_start, 0); @@ -1094,10 +1119,10 @@ static bool test_merge_existing(void) vma_prev->vm_ops = &vm_ops; /* This should have no impact. */ vma = alloc_and_link_vma(&mm, 0x3000, 0x7000, 3, flags); vma_next = alloc_and_link_vma(&mm, 0x7000, 0x9000, 7, flags); - vmg_set_range(&vmg, 0x3000, 0x7000, 3, flags); + vmg_set_range_anon_vma(&vmg, 0x3000, 0x7000, 3, flags, &dummy_anon_vma); vmg.prev = vma_prev; vmg.middle = vma; - vma->anon_vma = &dummy_anon_vma; + vma_set_dummy_anon_vma(vma, &avc); ASSERT_EQ(merge_existing(&vmg), vma_prev); ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS); ASSERT_EQ(vma_prev->vm_start, 0); @@ -1180,12 +1205,9 @@ static bool test_anon_vma_non_mergeable(void) .mm = &mm, .vmi = &vmi, }; - struct anon_vma_chain dummy_anon_vma_chain1 = { - .anon_vma = &dummy_anon_vma, - }; - struct anon_vma_chain dummy_anon_vma_chain2 = { - .anon_vma = &dummy_anon_vma, - }; + struct anon_vma_chain dummy_anon_vma_chain_1 = {}; + struct anon_vma_chain dummy_anon_vma_chain_2 = {}; + struct anon_vma dummy_anon_vma_2; /* * In the case of modified VMA merge, merging both left and right VMAs @@ -1209,24 +1231,11 @@ static bool test_anon_vma_non_mergeable(void) * * However, when prev is compared to next, the merge should fail. */ - - INIT_LIST_HEAD(&vma_prev->anon_vma_chain); - list_add(&dummy_anon_vma_chain1.same_vma, &vma_prev->anon_vma_chain); - ASSERT_TRUE(list_is_singular(&vma_prev->anon_vma_chain)); - vma_prev->anon_vma = &dummy_anon_vma; - ASSERT_TRUE(is_mergeable_anon_vma(NULL, vma_prev->anon_vma, vma_prev)); - - INIT_LIST_HEAD(&vma_next->anon_vma_chain); - list_add(&dummy_anon_vma_chain2.same_vma, &vma_next->anon_vma_chain); - ASSERT_TRUE(list_is_singular(&vma_next->anon_vma_chain)); - vma_next->anon_vma = (struct anon_vma *)2; - ASSERT_TRUE(is_mergeable_anon_vma(NULL, vma_next->anon_vma, vma_next)); - - ASSERT_FALSE(is_mergeable_anon_vma(vma_prev->anon_vma, vma_next->anon_vma, NULL)); - - vmg_set_range(&vmg, 0x3000, 0x7000, 3, flags); + vmg_set_range_anon_vma(&vmg, 0x3000, 0x7000, 3, flags, NULL); vmg.prev = vma_prev; vmg.middle = vma; + vma_set_dummy_anon_vma(vma_prev, &dummy_anon_vma_chain_1); + __vma_set_dummy_anon_vma(vma_next, &dummy_anon_vma_chain_2, &dummy_anon_vma_2); ASSERT_EQ(merge_existing(&vmg), vma_prev); ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS); @@ -1253,17 +1262,12 @@ static bool test_anon_vma_non_mergeable(void) vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags); vma_next = alloc_and_link_vma(&mm, 0x7000, 0x9000, 7, flags); - INIT_LIST_HEAD(&vma_prev->anon_vma_chain); - list_add(&dummy_anon_vma_chain1.same_vma, &vma_prev->anon_vma_chain); - vma_prev->anon_vma = (struct anon_vma *)1; - - INIT_LIST_HEAD(&vma_next->anon_vma_chain); - list_add(&dummy_anon_vma_chain2.same_vma, &vma_next->anon_vma_chain); - vma_next->anon_vma = (struct anon_vma *)2; - - vmg_set_range(&vmg, 0x3000, 0x7000, 3, flags); + vmg_set_range_anon_vma(&vmg, 0x3000, 0x7000, 3, flags, NULL); vmg.prev = vma_prev; + vma_set_dummy_anon_vma(vma_prev, &dummy_anon_vma_chain_1); + __vma_set_dummy_anon_vma(vma_next, &dummy_anon_vma_chain_2, &dummy_anon_vma_2); + vmg.anon_vma = NULL; ASSERT_EQ(merge_new(&vmg), vma_prev); ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS); ASSERT_EQ(vma_prev->vm_start, 0); @@ -1363,8 +1367,8 @@ static bool test_dup_anon_vma(void) vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags); vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags); vma_next = alloc_and_link_vma(&mm, 0x5000, 0x8000, 5, flags); - - vma->anon_vma = &dummy_anon_vma; + vmg.anon_vma = &dummy_anon_vma; + vma_set_dummy_anon_vma(vma, &dummy_anon_vma_chain); vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags); vmg.prev = vma_prev; vmg.middle = vma; @@ -1392,7 +1396,7 @@ static bool test_dup_anon_vma(void) vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags); vma = alloc_and_link_vma(&mm, 0x3000, 0x8000, 3, flags); - vma->anon_vma = &dummy_anon_vma; + vma_set_dummy_anon_vma(vma, &dummy_anon_vma_chain); vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags); vmg.prev = vma_prev; vmg.middle = vma; @@ -1420,7 +1424,7 @@ static bool test_dup_anon_vma(void) vma = alloc_and_link_vma(&mm, 0, 0x5000, 0, flags); vma_next = alloc_and_link_vma(&mm, 0x5000, 0x8000, 5, flags); - vma->anon_vma = &dummy_anon_vma; + vma_set_dummy_anon_vma(vma, &dummy_anon_vma_chain); vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags); vmg.prev = vma; vmg.middle = vma; @@ -1447,6 +1451,7 @@ static bool test_vmi_prealloc_fail(void) .mm = &mm, .vmi = &vmi, }; + struct anon_vma_chain avc = {}; struct vm_area_struct *vma_prev, *vma; /* @@ -1459,9 +1464,10 @@ static bool test_vmi_prealloc_fail(void) vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags); vma->anon_vma = &dummy_anon_vma; - vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags); + vmg_set_range_anon_vma(&vmg, 0x3000, 0x5000, 3, flags, &dummy_anon_vma); vmg.prev = vma_prev; vmg.middle = vma; + vma_set_dummy_anon_vma(vma, &avc); fail_prealloc = true; |