From 7b6218ae1253491d56f21f4b1f3609f3dd873600 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 13 Feb 2025 14:46:39 -0800 Subject: mm: move per-vma lock into vm_area_struct Back when per-vma locks were introduces, vm_lock was moved out of vm_area_struct in [1] because of the performance regression caused by false cacheline sharing. Recent investigation [2] revealed that the regressions is limited to a rather old Broadwell microarchitecture and even there it can be mitigated by disabling adjacent cacheline prefetching, see [3]. Splitting single logical structure into multiple ones leads to more complicated management, extra pointer dereferences and overall less maintainable code. When that split-away part is a lock, it complicates things even further. With no performance benefits, there are no reasons for this split. Merging the vm_lock back into vm_area_struct also allows vm_area_struct to use SLAB_TYPESAFE_BY_RCU later in this patchset. Move vm_lock back into vm_area_struct, aligning it at the cacheline boundary and changing the cache to be cacheline-aligned as well. With kernel compiled using defconfig, this causes VMA memory consumption to grow from 160 (vm_area_struct) + 40 (vm_lock) bytes to 256 bytes: slabinfo before: ... : ... vma_lock ... 40 102 1 : ... vm_area_struct ... 160 51 2 : ... slabinfo after moving vm_lock: ... : ... vm_area_struct ... 256 32 2 : ... Aggregate VMA memory consumption per 1000 VMAs grows from 50 to 64 pages, which is 5.5MB per 100000 VMAs. Note that the size of this structure is dependent on the kernel configuration and typically the original size is higher than 160 bytes. Therefore these calculations are close to the worst case scenario. A more realistic vm_area_struct usage before this change is: ... : ... vma_lock ... 40 102 1 : ... vm_area_struct ... 176 46 2 : ... Aggregate VMA memory consumption per 1000 VMAs grows from 54 to 64 pages, which is 3.9MB per 100000 VMAs. This memory consumption growth can be addressed later by optimizing the vm_lock. [1] https://lore.kernel.org/all/20230227173632.3292573-34-surenb@google.com/ [2] https://lore.kernel.org/all/ZsQyI%2F087V34JoIt@xsang-OptiPlex-9020/ [3] https://lore.kernel.org/all/CAJuCfpEisU8Lfe96AYJDZ+OM4NoPmnw9bP53cT_kbfP_pR+-2g@mail.gmail.com/ Link: https://lkml.kernel.org/r/20250213224655.1680278-3-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Lorenzo Stoakes Reviewed-by: Shakeel Butt Reviewed-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Tested-by: Shivank Garg Link: https://lkml.kernel.org/r/5e19ec93-8307-47c2-bb13-3ddf7150624e@amd.com Cc: Christian Brauner Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: Hugh Dickins Cc: Jann Horn Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Klara Modin Cc: Lokesh Gidra Cc: Mateusz Guzik Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Oleg Nesterov Cc: Pasha Tatashin Cc: "Paul E . McKenney" Cc: Peter Xu Cc: Peter Zijlstra (Intel) Cc: Sourav Panda Cc: Wei Yang Cc: Will Deacon Cc: Heiko Carstens Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- kernel/fork.c | 49 +++++-------------------------------------------- 1 file changed, 5 insertions(+), 44 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 735405a9c5f3..bdbabe73fb29 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -436,35 +436,6 @@ static struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; -#ifdef CONFIG_PER_VMA_LOCK - -/* SLAB cache for vm_area_struct.lock */ -static struct kmem_cache *vma_lock_cachep; - -static bool vma_lock_alloc(struct vm_area_struct *vma) -{ - vma->vm_lock = kmem_cache_alloc(vma_lock_cachep, GFP_KERNEL); - if (!vma->vm_lock) - return false; - - init_rwsem(&vma->vm_lock->lock); - vma->vm_lock_seq = UINT_MAX; - - return true; -} - -static inline void vma_lock_free(struct vm_area_struct *vma) -{ - kmem_cache_free(vma_lock_cachep, vma->vm_lock); -} - -#else /* CONFIG_PER_VMA_LOCK */ - -static inline bool vma_lock_alloc(struct vm_area_struct *vma) { return true; } -static inline void vma_lock_free(struct vm_area_struct *vma) {} - -#endif /* CONFIG_PER_VMA_LOCK */ - struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) { struct vm_area_struct *vma; @@ -474,10 +445,6 @@ struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) return NULL; vma_init(vma, mm); - if (!vma_lock_alloc(vma)) { - kmem_cache_free(vm_area_cachep, vma); - return NULL; - } return vma; } @@ -496,10 +463,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) * will be reinitialized. */ data_race(memcpy(new, orig, sizeof(*new))); - if (!vma_lock_alloc(new)) { - kmem_cache_free(vm_area_cachep, new); - return NULL; - } + vma_lock_init(new); INIT_LIST_HEAD(&new->anon_vma_chain); vma_numab_state_init(new); dup_anon_vma_name(orig, new); @@ -511,7 +475,6 @@ void __vm_area_free(struct vm_area_struct *vma) { vma_numab_state_free(vma); free_anon_vma_name(vma); - vma_lock_free(vma); kmem_cache_free(vm_area_cachep, vma); } @@ -522,7 +485,7 @@ static void vm_area_free_rcu_cb(struct rcu_head *head) vm_rcu); /* The vma should not be locked while being destroyed. */ - VM_BUG_ON_VMA(rwsem_is_locked(&vma->vm_lock->lock), vma); + VM_BUG_ON_VMA(rwsem_is_locked(&vma->vm_lock.lock), vma); __vm_area_free(vma); } #endif @@ -3200,11 +3163,9 @@ void __init proc_caches_init(void) sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); - - vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT); -#ifdef CONFIG_PER_VMA_LOCK - vma_lock_cachep = KMEM_CACHE(vma_lock, SLAB_PANIC|SLAB_ACCOUNT); -#endif + vm_area_cachep = KMEM_CACHE(vm_area_struct, + SLAB_HWCACHE_ALIGN|SLAB_NO_MERGE|SLAB_PANIC| + SLAB_ACCOUNT); mmap_init(); nsproxy_cache_init(); } -- cgit v1.2.3-59-g8ed1b From 8ef95d8f15f9e785341775814f0ed2ee22017aa5 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 13 Feb 2025 14:46:40 -0800 Subject: mm: mark vma as detached until it's added into vma tree Current implementation does not set detached flag when a VMA is first allocated. This does not represent the real state of the VMA, which is detached until it is added into mm's VMA tree. Fix this by marking new VMAs as detached and resetting detached flag only after VMA is added into a tree. Introduce vma_mark_attached() to make the API more readable and to simplify possible future cleanup when vma->vm_mm might be used to indicate detached vma and vma_mark_attached() will need an additional mm parameter. Link: https://lkml.kernel.org/r/20250213224655.1680278-4-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Shakeel Butt Reviewed-by: Lorenzo Stoakes Reviewed-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Tested-by: Shivank Garg Link: https://lkml.kernel.org/r/5e19ec93-8307-47c2-bb13-3ddf7150624e@amd.com Cc: Christian Brauner Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: Hugh Dickins Cc: Jann Horn Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Klara Modin Cc: Lokesh Gidra Cc: Mateusz Guzik Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Oleg Nesterov Cc: Pasha Tatashin Cc: "Paul E . McKenney" Cc: Peter Xu Cc: Peter Zijlstra (Intel) Cc: Sourav Panda Cc: Wei Yang Cc: Will Deacon Cc: Heiko Carstens Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- include/linux/mm.h | 27 ++++++++++++++++++++------- kernel/fork.c | 4 ++++ mm/memory.c | 2 +- mm/vma.c | 6 +++--- mm/vma.h | 2 ++ tools/testing/vma/vma_internal.h | 17 ++++++++++++----- 6 files changed, 42 insertions(+), 16 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index bf3b6362927f..d333d4070362 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -821,12 +821,21 @@ static inline void vma_assert_locked(struct vm_area_struct *vma) vma_assert_write_locked(vma); } -static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) +static inline void vma_mark_attached(struct vm_area_struct *vma) +{ + vma->detached = false; +} + +static inline void vma_mark_detached(struct vm_area_struct *vma) { /* When detaching vma should be write-locked */ - if (detached) - vma_assert_write_locked(vma); - vma->detached = detached; + vma_assert_write_locked(vma); + vma->detached = true; +} + +static inline bool is_vma_detached(struct vm_area_struct *vma) +{ + return vma->detached; } static inline void release_fault_lock(struct vm_fault *vmf) @@ -857,8 +866,8 @@ static inline void vma_end_read(struct vm_area_struct *vma) {} static inline void vma_start_write(struct vm_area_struct *vma) {} static inline void vma_assert_write_locked(struct vm_area_struct *vma) { mmap_assert_write_locked(vma->vm_mm); } -static inline void vma_mark_detached(struct vm_area_struct *vma, - bool detached) {} +static inline void vma_mark_attached(struct vm_area_struct *vma) {} +static inline void vma_mark_detached(struct vm_area_struct *vma) {} static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, unsigned long address) @@ -891,7 +900,10 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) vma->vm_mm = mm; vma->vm_ops = &vma_dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); - vma_mark_detached(vma, false); +#ifdef CONFIG_PER_VMA_LOCK + /* vma is not locked, can't use vma_mark_detached() */ + vma->detached = true; +#endif vma_numab_state_init(vma); vma_lock_init(vma); } @@ -1086,6 +1098,7 @@ static inline int vma_iter_bulk_store(struct vma_iterator *vmi, if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; + vma_mark_attached(vma); return 0; } diff --git a/kernel/fork.c b/kernel/fork.c index bdbabe73fb29..5bf3e407c795 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -465,6 +465,10 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) data_race(memcpy(new, orig, sizeof(*new))); vma_lock_init(new); INIT_LIST_HEAD(&new->anon_vma_chain); +#ifdef CONFIG_PER_VMA_LOCK + /* vma is not locked, can't use vma_mark_detached() */ + new->detached = true; +#endif vma_numab_state_init(new); dup_anon_vma_name(orig, new); diff --git a/mm/memory.c b/mm/memory.c index 94feb51a7983..6ef014220e09 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -6374,7 +6374,7 @@ retry: goto inval; /* Check if the VMA got isolated after we found it */ - if (vma->detached) { + if (is_vma_detached(vma)) { vma_end_read(vma); count_vm_vma_lock_event(VMA_LOCK_MISS); /* The area was replaced with another one */ diff --git a/mm/vma.c b/mm/vma.c index 603e538a093f..702e2181f8b7 100644 --- a/mm/vma.c +++ b/mm/vma.c @@ -341,7 +341,7 @@ static void vma_complete(struct vma_prepare *vp, struct vma_iterator *vmi, if (vp->remove) { again: - vma_mark_detached(vp->remove, true); + vma_mark_detached(vp->remove); if (vp->file) { uprobe_munmap(vp->remove, vp->remove->vm_start, vp->remove->vm_end); @@ -1238,7 +1238,7 @@ static void reattach_vmas(struct ma_state *mas_detach) mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) - vma_mark_detached(vma, false); + vma_mark_attached(vma); __mt_destroy(mas_detach->tree); } @@ -1313,7 +1313,7 @@ static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms, if (error) goto munmap_gather_failed; - vma_mark_detached(next, true); + vma_mark_detached(next); nrpages = vma_pages(next); vms->nr_pages += nrpages; diff --git a/mm/vma.h b/mm/vma.h index e55e68abfbe3..bffb56afce5f 100644 --- a/mm/vma.h +++ b/mm/vma.h @@ -205,6 +205,7 @@ static inline int vma_iter_store_gfp(struct vma_iterator *vmi, if (unlikely(mas_is_err(&vmi->mas))) return -ENOMEM; + vma_mark_attached(vma); return 0; } @@ -437,6 +438,7 @@ static inline void vma_iter_store(struct vma_iterator *vmi, __mas_set_range(&vmi->mas, vma->vm_start, vma->vm_end - 1); mas_store_prealloc(&vmi->mas, vma); + vma_mark_attached(vma); } static inline unsigned long vma_iter_addr(struct vma_iterator *vmi) diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h index 4506e6fb3c6f..f93f7f74f97b 100644 --- a/tools/testing/vma/vma_internal.h +++ b/tools/testing/vma/vma_internal.h @@ -471,12 +471,16 @@ static inline void vma_lock_init(struct vm_area_struct *vma) } static inline void vma_assert_write_locked(struct vm_area_struct *); -static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) +static inline void vma_mark_attached(struct vm_area_struct *vma) +{ + vma->detached = false; +} + +static inline void vma_mark_detached(struct vm_area_struct *vma) { /* When detaching vma should be write-locked */ - if (detached) - vma_assert_write_locked(vma); - vma->detached = detached; + vma_assert_write_locked(vma); + vma->detached = true; } extern const struct vm_operations_struct vma_dummy_vm_ops; @@ -489,7 +493,8 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) vma->vm_mm = mm; vma->vm_ops = &vma_dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); - vma_mark_detached(vma, false); + /* vma is not locked, can't use vma_mark_detached() */ + vma->detached = true; vma_lock_init(vma); } @@ -515,6 +520,8 @@ static inline struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) memcpy(new, orig, sizeof(*new)); vma_lock_init(new); INIT_LIST_HEAD(&new->anon_vma_chain); + /* vma is not locked, can't use vma_mark_detached() */ + new->detached = true; return new; } -- cgit v1.2.3-59-g8ed1b From ce0853966085dd8eab7153ce0b815c4a07d86698 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 13 Feb 2025 14:46:45 -0800 Subject: mm: move mmap_init_lock() out of the header file mmap_init_lock() is used only from mm_init() in fork.c, therefore it does not have to reside in the header file. This move lets us avoid including additional headers in mmap_lock.h later, when mmap_init_lock() needs to initialize rcuwait object. Link: https://lkml.kernel.org/r/20250213224655.1680278-9-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Vlastimil Babka Reviewed-by: Lorenzo Stoakes Tested-by: Shivank Garg Link: https://lkml.kernel.org/r/5e19ec93-8307-47c2-bb13-3ddf7150624e@amd.com Cc: Christian Brauner Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: Hugh Dickins Cc: Jann Horn Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Klara Modin Cc: Liam R. Howlett Cc: Lokesh Gidra Cc: Mateusz Guzik Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Oleg Nesterov Cc: Pasha Tatashin Cc: "Paul E . McKenney" Cc: Peter Xu Cc: Peter Zijlstra (Intel) Cc: Shakeel Butt Cc: Sourav Panda Cc: Wei Yang Cc: Will Deacon Cc: Heiko Carstens Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- include/linux/mmap_lock.h | 6 ------ kernel/fork.c | 6 ++++++ 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 45a21faa3ff6..4706c6769902 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -122,12 +122,6 @@ static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int #endif /* CONFIG_PER_VMA_LOCK */ -static inline void mmap_init_lock(struct mm_struct *mm) -{ - init_rwsem(&mm->mmap_lock); - mm_lock_seqcount_init(mm); -} - static inline void mmap_write_lock(struct mm_struct *mm) { __mmap_lock_trace_start_locking(mm, true); diff --git a/kernel/fork.c b/kernel/fork.c index 5bf3e407c795..f1af413e5aa4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1230,6 +1230,12 @@ static void mm_init_uprobes_state(struct mm_struct *mm) #endif } +static void mmap_init_lock(struct mm_struct *mm) +{ + init_rwsem(&mm->mmap_lock); + mm_lock_seqcount_init(mm); +} + static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, struct user_namespace *user_ns) { -- cgit v1.2.3-59-g8ed1b From f35ab95ca0af7a27feab57b9d7e906405bddb093 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 13 Feb 2025 14:46:49 -0800 Subject: mm: replace vm_lock and detached flag with a reference count rw_semaphore is a sizable structure of 40 bytes and consumes considerable space for each vm_area_struct. However vma_lock has two important specifics which can be used to replace rw_semaphore with a simpler structure: 1. Readers never wait. They try to take the vma_lock and fall back to mmap_lock if that fails. 2. Only one writer at a time will ever try to write-lock a vma_lock because writers first take mmap_lock in write mode. Because of these requirements, full rw_semaphore functionality is not needed and we can replace rw_semaphore and the vma->detached flag with a refcount (vm_refcnt). When vma is in detached state, vm_refcnt is 0 and only a call to vma_mark_attached() can take it out of this state. Note that unlike before, now we enforce both vma_mark_attached() and vma_mark_detached() to be done only after vma has been write-locked. vma_mark_attached() changes vm_refcnt to 1 to indicate that it has been attached to the vma tree. When a reader takes read lock, it increments vm_refcnt, unless the top usable bit of vm_refcnt (0x40000000) is set, indicating presence of a writer. When writer takes write lock, it sets the top usable bit to indicate its presence. If there are readers, writer will wait using newly introduced mm->vma_writer_wait. Since all writers take mmap_lock in write mode first, there can be only one writer at a time. The last reader to release the lock will signal the writer to wake up. refcount might overflow if there are many competing readers, in which case read-locking will fail. Readers are expected to handle such failures. In summary: 1. all readers increment the vm_refcnt; 2. writer sets top usable (writer) bit of vm_refcnt; 3. readers cannot increment the vm_refcnt if the writer bit is set; 4. in the presence of readers, writer must wait for the vm_refcnt to drop to 1 (plus the VMA_LOCK_OFFSET writer bit), indicating an attached vma with no readers; 5. vm_refcnt overflow is handled by the readers. While this vm_lock replacement does not yet result in a smaller vm_area_struct (it stays at 256 bytes due to cacheline alignment), it allows for further size optimization by structure member regrouping to bring the size of vm_area_struct below 192 bytes. [surenb@google.com: fix a crash due to vma_end_read() that should have been removed] Link: https://lkml.kernel.org/r/20250220200208.323769-1-surenb@google.com Link: https://lkml.kernel.org/r/20250213224655.1680278-13-surenb@google.com Signed-off-by: Suren Baghdasaryan Suggested-by: Peter Zijlstra Suggested-by: Matthew Wilcox Tested-by: Shivank Garg Link: https://lkml.kernel.org/r/5e19ec93-8307-47c2-bb13-3ddf7150624e@amd.com Reviewed-by: Vlastimil Babka Cc: Christian Brauner Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: Hugh Dickins Cc: Jann Horn Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Klara Modin Cc: Liam R. Howlett Cc: Lokesh Gidra Cc: Lorenzo Stoakes Cc: Mateusz Guzik Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Oleg Nesterov Cc: Pasha Tatashin Cc: "Paul E . McKenney" Cc: Peter Xu Cc: Shakeel Butt Cc: Sourav Panda Cc: Wei Yang Cc: Will Deacon Cc: Heiko Carstens Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- include/linux/mm.h | 128 ++++++++++++++++++++++++++------------- include/linux/mm_types.h | 22 +++---- kernel/fork.c | 13 ++-- mm/init-mm.c | 1 + mm/memory.c | 90 ++++++++++++++++++++++++--- tools/testing/vma/linux/atomic.h | 5 ++ tools/testing/vma/vma_internal.h | 63 +++++++++---------- 7 files changed, 217 insertions(+), 105 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index c24c521e38a2..06f179c844c3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -32,6 +32,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -697,19 +698,54 @@ static inline void vma_numab_state_free(struct vm_area_struct *vma) {} #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_PER_VMA_LOCK -static inline void vma_lock_init(struct vm_area_struct *vma) +static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) { - init_rwsem(&vma->vm_lock.lock); +#ifdef CONFIG_DEBUG_LOCK_ALLOC + static struct lock_class_key lockdep_key; + + lockdep_init_map(&vma->vmlock_dep_map, "vm_lock", &lockdep_key, 0); +#endif + if (reset_refcnt) + refcount_set(&vma->vm_refcnt, 0); vma->vm_lock_seq = UINT_MAX; } +static inline bool is_vma_writer_only(int refcnt) +{ + /* + * With a writer and no readers, refcnt is VMA_LOCK_OFFSET if the vma + * is detached and (VMA_LOCK_OFFSET + 1) if it is attached. Waiting on + * a detached vma happens only in vma_mark_detached() and is a rare + * case, therefore most of the time there will be no unnecessary wakeup. + */ + return refcnt & VMA_LOCK_OFFSET && refcnt <= VMA_LOCK_OFFSET + 1; +} + +static inline void vma_refcount_put(struct vm_area_struct *vma) +{ + /* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */ + struct mm_struct *mm = vma->vm_mm; + int oldcnt; + + rwsem_release(&vma->vmlock_dep_map, _RET_IP_); + if (!__refcount_dec_and_test(&vma->vm_refcnt, &oldcnt)) { + + if (is_vma_writer_only(oldcnt - 1)) + rcuwait_wake_up(&mm->vma_writer_wait); + } +} + /* * Try to read-lock a vma. The function is allowed to occasionally yield false * locked result to avoid performance overhead, in which case we fall back to * using mmap_lock. The function should never yield false unlocked result. + * Returns the vma on success, NULL on failure to lock and EAGAIN if vma got + * detached. */ -static inline bool vma_start_read(struct vm_area_struct *vma) +static inline struct vm_area_struct *vma_start_read(struct vm_area_struct *vma) { + int oldcnt; + /* * Check before locking. A race might cause false locked result. * We can use READ_ONCE() for the mm_lock_seq here, and don't need @@ -718,15 +754,25 @@ static inline bool vma_start_read(struct vm_area_struct *vma) * need ordering is below. */ if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq.sequence)) - return false; + return NULL; - if (unlikely(down_read_trylock(&vma->vm_lock.lock) == 0)) - return false; + /* + * If VMA_LOCK_OFFSET is set, __refcount_inc_not_zero_limited_acquire() + * will fail because VMA_REF_LIMIT is less than VMA_LOCK_OFFSET. + * Acquire fence is required here to avoid reordering against later + * vm_lock_seq check and checks inside lock_vma_under_rcu(). + */ + if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt, + VMA_REF_LIMIT))) { + /* return EAGAIN if vma got detached from under us */ + return oldcnt ? NULL : ERR_PTR(-EAGAIN); + } + rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); /* - * Overflow might produce false locked result. + * Overflow of vm_lock_seq/mm_lock_seq might produce false locked result. * False unlocked result is impossible because we modify and check - * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq + * vma->vm_lock_seq under vma->vm_refcnt protection and mm->mm_lock_seq * modification invalidates all existing locks. * * We must use ACQUIRE semantics for the mm_lock_seq so that if we are @@ -735,10 +781,11 @@ static inline bool vma_start_read(struct vm_area_struct *vma) * This pairs with RELEASE semantics in vma_end_write_all(). */ if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&vma->vm_mm->mm_lock_seq))) { - up_read(&vma->vm_lock.lock); - return false; + vma_refcount_put(vma); + return NULL; } - return true; + + return vma; } /* @@ -749,8 +796,14 @@ static inline bool vma_start_read(struct vm_area_struct *vma) */ static inline bool vma_start_read_locked_nested(struct vm_area_struct *vma, int subclass) { + int oldcnt; + mmap_assert_locked(vma->vm_mm); - down_read_nested(&vma->vm_lock.lock, subclass); + if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt, + VMA_REF_LIMIT))) + return false; + + rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_); return true; } @@ -762,16 +815,12 @@ static inline bool vma_start_read_locked_nested(struct vm_area_struct *vma, int */ static inline bool vma_start_read_locked(struct vm_area_struct *vma) { - mmap_assert_locked(vma->vm_mm); - down_read(&vma->vm_lock.lock); - return true; + return vma_start_read_locked_nested(vma, 0); } static inline void vma_end_read(struct vm_area_struct *vma) { - rcu_read_lock(); /* keeps vma alive till the end of up_read */ - up_read(&vma->vm_lock.lock); - rcu_read_unlock(); + vma_refcount_put(vma); } /* WARNING! Can only be used if mmap_lock is expected to be write-locked */ @@ -813,38 +862,35 @@ static inline void vma_assert_write_locked(struct vm_area_struct *vma) static inline void vma_assert_locked(struct vm_area_struct *vma) { - if (!rwsem_is_locked(&vma->vm_lock.lock)) - vma_assert_write_locked(vma); + unsigned int mm_lock_seq; + + VM_BUG_ON_VMA(refcount_read(&vma->vm_refcnt) <= 1 && + !__is_vma_write_locked(vma, &mm_lock_seq), vma); } +/* + * WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these + * assertions should be made either under mmap_write_lock or when the object + * has been isolated under mmap_write_lock, ensuring no competing writers. + */ static inline void vma_assert_attached(struct vm_area_struct *vma) { - WARN_ON_ONCE(vma->detached); + WARN_ON_ONCE(!refcount_read(&vma->vm_refcnt)); } static inline void vma_assert_detached(struct vm_area_struct *vma) { - WARN_ON_ONCE(!vma->detached); + WARN_ON_ONCE(refcount_read(&vma->vm_refcnt)); } static inline void vma_mark_attached(struct vm_area_struct *vma) { - vma_assert_detached(vma); - vma->detached = false; -} - -static inline void vma_mark_detached(struct vm_area_struct *vma) -{ - /* When detaching vma should be write-locked */ vma_assert_write_locked(vma); - vma_assert_attached(vma); - vma->detached = true; + vma_assert_detached(vma); + refcount_set(&vma->vm_refcnt, 1); } -static inline bool is_vma_detached(struct vm_area_struct *vma) -{ - return vma->detached; -} +void vma_mark_detached(struct vm_area_struct *vma); static inline void release_fault_lock(struct vm_fault *vmf) { @@ -867,9 +913,9 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, #else /* CONFIG_PER_VMA_LOCK */ -static inline void vma_lock_init(struct vm_area_struct *vma) {} -static inline bool vma_start_read(struct vm_area_struct *vma) - { return false; } +static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) {} +static inline struct vm_area_struct *vma_start_read(struct vm_area_struct *vma) + { return NULL; } static inline void vma_end_read(struct vm_area_struct *vma) {} static inline void vma_start_write(struct vm_area_struct *vma) {} static inline void vma_assert_write_locked(struct vm_area_struct *vma) @@ -910,12 +956,8 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) vma->vm_mm = mm; vma->vm_ops = &vma_dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); -#ifdef CONFIG_PER_VMA_LOCK - /* vma is not locked, can't use vma_mark_detached() */ - vma->detached = true; -#endif vma_numab_state_init(vma); - vma_lock_init(vma); + vma_lock_init(vma, false); } /* Use when VMA is not part of the VMA tree and needs no locking */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 36dea20cd101..9de0a6cb3c2d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -19,6 +19,7 @@ #include #include #include +#include #include @@ -629,9 +630,8 @@ static inline struct anon_vma_name *anon_vma_name_alloc(const char *name) } #endif -struct vma_lock { - struct rw_semaphore lock; -}; +#define VMA_LOCK_OFFSET 0x40000000 +#define VMA_REF_LIMIT (VMA_LOCK_OFFSET - 1) struct vma_numab_state { /* @@ -709,19 +709,13 @@ struct vm_area_struct { }; #ifdef CONFIG_PER_VMA_LOCK - /* - * Flag to indicate areas detached from the mm->mm_mt tree. - * Unstable RCU readers are allowed to read this. - */ - bool detached; - /* * Can only be written (using WRITE_ONCE()) while holding both: * - mmap_lock (in write mode) - * - vm_lock->lock (in write mode) + * - vm_refcnt bit at VMA_LOCK_OFFSET is set * Can be read reliably while holding one of: * - mmap_lock (in read or write mode) - * - vm_lock->lock (in read or write mode) + * - vm_refcnt bit at VMA_LOCK_OFFSET is set or vm_refcnt > 1 * Can be read unreliably (using READ_ONCE()) for pessimistic bailout * while holding nothing (except RCU to keep the VMA struct allocated). * @@ -784,7 +778,10 @@ struct vm_area_struct { struct vm_userfaultfd_ctx vm_userfaultfd_ctx; #ifdef CONFIG_PER_VMA_LOCK /* Unstable RCU readers are allowed to read this. */ - struct vma_lock vm_lock ____cacheline_aligned_in_smp; + refcount_t vm_refcnt ____cacheline_aligned_in_smp; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map vmlock_dep_map; +#endif #endif } __randomize_layout; @@ -920,6 +917,7 @@ struct mm_struct { * by mmlist_lock */ #ifdef CONFIG_PER_VMA_LOCK + struct rcuwait vma_writer_wait; /* * This field has lock-like semantics, meaning it is sometimes * accessed with ACQUIRE/RELEASE semantics. diff --git a/kernel/fork.c b/kernel/fork.c index f1af413e5aa4..48a0038f606f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -463,12 +463,8 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) * will be reinitialized. */ data_race(memcpy(new, orig, sizeof(*new))); - vma_lock_init(new); + vma_lock_init(new, true); INIT_LIST_HEAD(&new->anon_vma_chain); -#ifdef CONFIG_PER_VMA_LOCK - /* vma is not locked, can't use vma_mark_detached() */ - new->detached = true; -#endif vma_numab_state_init(new); dup_anon_vma_name(orig, new); @@ -477,6 +473,8 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) void __vm_area_free(struct vm_area_struct *vma) { + /* The vma should be detached while being destroyed. */ + vma_assert_detached(vma); vma_numab_state_free(vma); free_anon_vma_name(vma); kmem_cache_free(vm_area_cachep, vma); @@ -488,8 +486,6 @@ static void vm_area_free_rcu_cb(struct rcu_head *head) struct vm_area_struct *vma = container_of(head, struct vm_area_struct, vm_rcu); - /* The vma should not be locked while being destroyed. */ - VM_BUG_ON_VMA(rwsem_is_locked(&vma->vm_lock.lock), vma); __vm_area_free(vma); } #endif @@ -1234,6 +1230,9 @@ static void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); mm_lock_seqcount_init(mm); +#ifdef CONFIG_PER_VMA_LOCK + rcuwait_init(&mm->vma_writer_wait); +#endif } static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, diff --git a/mm/init-mm.c b/mm/init-mm.c index 6af3ad675930..4600e7605cab 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -40,6 +40,7 @@ struct mm_struct init_mm = { .arg_lock = __SPIN_LOCK_UNLOCKED(init_mm.arg_lock), .mmlist = LIST_HEAD_INIT(init_mm.mmlist), #ifdef CONFIG_PER_VMA_LOCK + .vma_writer_wait = __RCUWAIT_INITIALIZER(init_mm.vma_writer_wait), .mm_lock_seq = SEQCNT_ZERO(init_mm.mm_lock_seq), #endif .user_ns = &init_user_ns, diff --git a/mm/memory.c b/mm/memory.c index f2f7dc215b6b..51f233404b02 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -6353,9 +6353,47 @@ fail: #endif #ifdef CONFIG_PER_VMA_LOCK +static inline bool __vma_enter_locked(struct vm_area_struct *vma, bool detaching) +{ + unsigned int tgt_refcnt = VMA_LOCK_OFFSET; + + /* Additional refcnt if the vma is attached. */ + if (!detaching) + tgt_refcnt++; + + /* + * If vma is detached then only vma_mark_attached() can raise the + * vm_refcnt. mmap_write_lock prevents racing with vma_mark_attached(). + */ + if (!refcount_add_not_zero(VMA_LOCK_OFFSET, &vma->vm_refcnt)) + return false; + + rwsem_acquire(&vma->vmlock_dep_map, 0, 0, _RET_IP_); + rcuwait_wait_event(&vma->vm_mm->vma_writer_wait, + refcount_read(&vma->vm_refcnt) == tgt_refcnt, + TASK_UNINTERRUPTIBLE); + lock_acquired(&vma->vmlock_dep_map, _RET_IP_); + + return true; +} + +static inline void __vma_exit_locked(struct vm_area_struct *vma, bool *detached) +{ + *detached = refcount_sub_and_test(VMA_LOCK_OFFSET, &vma->vm_refcnt); + rwsem_release(&vma->vmlock_dep_map, _RET_IP_); +} + void __vma_start_write(struct vm_area_struct *vma, unsigned int mm_lock_seq) { - down_write(&vma->vm_lock.lock); + bool locked; + + /* + * __vma_enter_locked() returns false immediately if the vma is not + * attached, otherwise it waits until refcnt is indicating that vma + * is attached with no readers. + */ + locked = __vma_enter_locked(vma, false); + /* * We should use WRITE_ONCE() here because we can have concurrent reads * from the early lockless pessimistic check in vma_start_read(). @@ -6363,10 +6401,40 @@ void __vma_start_write(struct vm_area_struct *vma, unsigned int mm_lock_seq) * we should use WRITE_ONCE() for cleanliness and to keep KCSAN happy. */ WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq); - up_write(&vma->vm_lock.lock); + + if (locked) { + bool detached; + + __vma_exit_locked(vma, &detached); + WARN_ON_ONCE(detached); /* vma should remain attached */ + } } EXPORT_SYMBOL_GPL(__vma_start_write); +void vma_mark_detached(struct vm_area_struct *vma) +{ + vma_assert_write_locked(vma); + vma_assert_attached(vma); + + /* + * We are the only writer, so no need to use vma_refcount_put(). + * The condition below is unlikely because the vma has been already + * write-locked and readers can increment vm_refcnt only temporarily + * before they check vm_lock_seq, realize the vma is locked and drop + * back the vm_refcnt. That is a narrow window for observing a raised + * vm_refcnt. + */ + if (unlikely(!refcount_dec_and_test(&vma->vm_refcnt))) { + /* Wait until vma is detached with no readers. */ + if (__vma_enter_locked(vma, true)) { + bool detached; + + __vma_exit_locked(vma, &detached); + WARN_ON_ONCE(!detached); + } + } +} + /* * Lookup and lock a VMA under RCU protection. Returned VMA is guaranteed to be * stable and not isolated. If the VMA is not found or is being modified the @@ -6384,15 +6452,17 @@ retry: if (!vma) goto inval; - if (!vma_start_read(vma)) - goto inval; + vma = vma_start_read(vma); + if (IS_ERR_OR_NULL(vma)) { + /* Check if the VMA got isolated after we found it */ + if (PTR_ERR(vma) == -EAGAIN) { + count_vm_vma_lock_event(VMA_LOCK_MISS); + /* The area was replaced with another one */ + goto retry; + } - /* Check if the VMA got isolated after we found it */ - if (is_vma_detached(vma)) { - vma_end_read(vma); - count_vm_vma_lock_event(VMA_LOCK_MISS); - /* The area was replaced with another one */ - goto retry; + /* Failed to lock the VMA */ + goto inval; } /* * At this point, we have a stable reference to a VMA: The VMA is diff --git a/tools/testing/vma/linux/atomic.h b/tools/testing/vma/linux/atomic.h index 3e1b6adc027b..788c597c4fde 100644 --- a/tools/testing/vma/linux/atomic.h +++ b/tools/testing/vma/linux/atomic.h @@ -9,4 +9,9 @@ #define atomic_set(x, y) uatomic_set(x, y) #define U8_MAX UCHAR_MAX +#ifndef atomic_cmpxchg_relaxed +#define atomic_cmpxchg_relaxed uatomic_cmpxchg +#define atomic_cmpxchg_release uatomic_cmpxchg +#endif /* atomic_cmpxchg_relaxed */ + #endif /* _LINUX_ATOMIC_H */ diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h index 34277842156c..ba838097d3f6 100644 --- a/tools/testing/vma/vma_internal.h +++ b/tools/testing/vma/vma_internal.h @@ -25,7 +25,7 @@ #include #include #include -#include +#include extern unsigned long stack_guard_gap; #ifdef CONFIG_MMU @@ -135,10 +135,6 @@ typedef __bitwise unsigned int vm_fault_t; */ #define pr_warn_once pr_err -typedef struct refcount_struct { - atomic_t refs; -} refcount_t; - struct kref { refcount_t refcount; }; @@ -233,15 +229,12 @@ struct mm_struct { unsigned long flags; /* Must use atomic bitops to access */ }; -struct vma_lock { - struct rw_semaphore lock; -}; - - struct file { struct address_space *f_mapping; }; +#define VMA_LOCK_OFFSET 0x40000000 + struct vm_area_struct { /* The first cache line has the info for VMA tree walking. */ @@ -269,16 +262,13 @@ struct vm_area_struct { }; #ifdef CONFIG_PER_VMA_LOCK - /* Flag to indicate areas detached from the mm->mm_mt tree */ - bool detached; - /* * Can only be written (using WRITE_ONCE()) while holding both: * - mmap_lock (in write mode) - * - vm_lock.lock (in write mode) + * - vm_refcnt bit at VMA_LOCK_OFFSET is set * Can be read reliably while holding one of: * - mmap_lock (in read or write mode) - * - vm_lock.lock (in read or write mode) + * - vm_refcnt bit at VMA_LOCK_OFFSET is set or vm_refcnt > 1 * Can be read unreliably (using READ_ONCE()) for pessimistic bailout * while holding nothing (except RCU to keep the VMA struct allocated). * @@ -287,7 +277,6 @@ struct vm_area_struct { * slowpath. */ unsigned int vm_lock_seq; - struct vma_lock vm_lock; #endif /* @@ -340,6 +329,10 @@ struct vm_area_struct { struct vma_numab_state *numab_state; /* NUMA Balancing state */ #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; +#ifdef CONFIG_PER_VMA_LOCK + /* Unstable RCU readers are allowed to read this. */ + refcount_t vm_refcnt; +#endif } __randomize_layout; struct vm_fault {}; @@ -464,33 +457,40 @@ static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi) return mas_find(&vmi->mas, ULONG_MAX); } -static inline void vma_lock_init(struct vm_area_struct *vma) -{ - init_rwsem(&vma->vm_lock.lock); - vma->vm_lock_seq = UINT_MAX; -} - +/* + * WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these + * assertions should be made either under mmap_write_lock or when the object + * has been isolated under mmap_write_lock, ensuring no competing writers. + */ static inline void vma_assert_attached(struct vm_area_struct *vma) { - WARN_ON_ONCE(vma->detached); + WARN_ON_ONCE(!refcount_read(&vma->vm_refcnt)); } static inline void vma_assert_detached(struct vm_area_struct *vma) { - WARN_ON_ONCE(!vma->detached); + WARN_ON_ONCE(refcount_read(&vma->vm_refcnt)); } static inline void vma_assert_write_locked(struct vm_area_struct *); static inline void vma_mark_attached(struct vm_area_struct *vma) { - vma->detached = false; + vma_assert_write_locked(vma); + vma_assert_detached(vma); + refcount_set(&vma->vm_refcnt, 1); } static inline void vma_mark_detached(struct vm_area_struct *vma) { - /* When detaching vma should be write-locked */ vma_assert_write_locked(vma); - vma->detached = true; + vma_assert_attached(vma); + /* We are the only writer, so no need to use vma_refcount_put(). */ + if (unlikely(!refcount_dec_and_test(&vma->vm_refcnt))) { + /* + * Reader must have temporarily raised vm_refcnt but it will + * drop it without using the vma since vma is write-locked. + */ + } } extern const struct vm_operations_struct vma_dummy_vm_ops; @@ -503,9 +503,7 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) vma->vm_mm = mm; vma->vm_ops = &vma_dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); - /* vma is not locked, can't use vma_mark_detached() */ - vma->detached = true; - vma_lock_init(vma); + vma->vm_lock_seq = UINT_MAX; } static inline struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) @@ -528,10 +526,9 @@ static inline struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) return NULL; memcpy(new, orig, sizeof(*new)); - vma_lock_init(new); + refcount_set(&new->vm_refcnt, 0); + new->vm_lock_seq = UINT_MAX; INIT_LIST_HEAD(&new->anon_vma_chain); - /* vma is not locked, can't use vma_mark_detached() */ - new->detached = true; return new; } -- cgit v1.2.3-59-g8ed1b From 3104138517fc66aad21f4a2487bb572e9fc2e3ec Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Thu, 13 Feb 2025 14:46:54 -0800 Subject: mm: make vma cache SLAB_TYPESAFE_BY_RCU To enable SLAB_TYPESAFE_BY_RCU for vma cache we need to ensure that object reuse before RCU grace period is over will be detected by lock_vma_under_rcu(). Current checks are sufficient as long as vma is detached before it is freed. The only place this is not currently happening is in exit_mmap(). Add the missing vma_mark_detached() in exit_mmap(). Another issue which might trick lock_vma_under_rcu() during vma reuse is vm_area_dup(), which copies the entire content of the vma into a new one, overriding new vma's vm_refcnt and temporarily making it appear as attached. This might trick a racing lock_vma_under_rcu() to operate on a reused vma if it found the vma before it got reused. To prevent this situation, we should ensure that vm_refcnt stays at detached state (0) when it is copied and advances to attached state only after it is added into the vma tree. Introduce vm_area_init_from() which preserves new vma's vm_refcnt and use it in vm_area_dup(). Since all vmas are in detached state with no current readers when they are freed, lock_vma_under_rcu() will not be able to take vm_refcnt after vma got detached even if vma is reused. vma_mark_attached() in modified to include a release fence to ensure all stores to the vma happen before vm_refcnt gets initialized. Finally, make vm_area_cachep SLAB_TYPESAFE_BY_RCU. This will facilitate vm_area_struct reuse and will minimize the number of call_rcu() calls. [surenb@google.com: remove atomic_set_release() usage in tools/] Link: https://lkml.kernel.org/r/20250217054351.2973666-1-surenb@google.com Link: https://lkml.kernel.org/r/20250213224655.1680278-18-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Vlastimil Babka Tested-by: Shivank Garg Link: https://lkml.kernel.org/r/5e19ec93-8307-47c2-bb13-3ddf7150624e@amd.com Cc: Christian Brauner Cc: David Hildenbrand Cc: David Howells Cc: Davidlohr Bueso Cc: Hugh Dickins Cc: Jann Horn Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Klara Modin Cc: Liam R. Howlett Cc: Lokesh Gidra Cc: Lorenzo Stoakes Cc: Mateusz Guzik Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Oleg Nesterov Cc: Pasha Tatashin Cc: "Paul E . McKenney" Cc: Peter Xu Cc: Peter Zijlstra (Intel) Cc: Shakeel Butt Cc: Sourav Panda Cc: Wei Yang Cc: Will Deacon Cc: Heiko Carstens Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- include/linux/mm.h | 4 +-- include/linux/mm_types.h | 13 +++++-- include/linux/slab.h | 6 ---- kernel/fork.c | 73 +++++++++++++++++++++++++--------------- mm/mmap.c | 3 +- mm/vma.c | 11 ++---- mm/vma.h | 2 +- tools/include/linux/refcount.h | 5 +++ tools/testing/vma/vma_internal.h | 9 ++--- 9 files changed, 70 insertions(+), 56 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index e3f962de1677..14115c9949d8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -258,8 +258,6 @@ void setup_initial_init_mm(void *start_code, void *end_code, struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); -/* Use only if VMA has no other users */ -void __vm_area_free(struct vm_area_struct *vma); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; @@ -890,7 +888,7 @@ static inline void vma_mark_attached(struct vm_area_struct *vma) { vma_assert_write_locked(vma); vma_assert_detached(vma); - refcount_set(&vma->vm_refcnt, 1); + refcount_set_release(&vma->vm_refcnt, 1); } void vma_mark_detached(struct vm_area_struct *vma); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c3aa0e20be41..6a93abb4452b 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -574,6 +574,12 @@ static inline void *folio_get_private(struct folio *folio) typedef unsigned long vm_flags_t; +/* + * freeptr_t represents a SLUB freelist pointer, which might be encoded + * and not dereferenceable if CONFIG_SLAB_FREELIST_HARDENED is enabled. + */ +typedef struct { unsigned long v; } freeptr_t; + /* * A region containing a mapping of a non-memory backed file under NOMMU * conditions. These are held in a global tree and are pinned by the VMAs that @@ -677,6 +683,9 @@ struct vma_numab_state { * * Only explicitly marked struct members may be accessed by RCU readers before * getting a stable reference. + * + * WARNING: when adding new members, please update vm_area_init_from() to copy + * them during vm_area_struct content duplication. */ struct vm_area_struct { /* The first cache line has the info for VMA tree walking. */ @@ -687,9 +696,7 @@ struct vm_area_struct { unsigned long vm_start; unsigned long vm_end; }; -#ifdef CONFIG_PER_VMA_LOCK - struct rcu_head vm_rcu; /* Used for deferred freeing. */ -#endif + freeptr_t vm_freeptr; /* Pointer used by SLAB_TYPESAFE_BY_RCU */ }; /* diff --git a/include/linux/slab.h b/include/linux/slab.h index ad902a2d692b..f8924fd6ea26 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -243,12 +243,6 @@ enum _slab_flag_bits { #define SLAB_NO_OBJ_EXT __SLAB_FLAG_UNUSED #endif -/* - * freeptr_t represents a SLUB freelist pointer, which might be encoded - * and not dereferenceable if CONFIG_SLAB_FREELIST_HARDENED is enabled. - */ -typedef struct { unsigned long v; } freeptr_t; - /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * diff --git a/kernel/fork.c b/kernel/fork.c index 48a0038f606f..364b2d4fd3ef 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -449,6 +449,42 @@ struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) return vma; } +static void vm_area_init_from(const struct vm_area_struct *src, + struct vm_area_struct *dest) +{ + dest->vm_mm = src->vm_mm; + dest->vm_ops = src->vm_ops; + dest->vm_start = src->vm_start; + dest->vm_end = src->vm_end; + dest->anon_vma = src->anon_vma; + dest->vm_pgoff = src->vm_pgoff; + dest->vm_file = src->vm_file; + dest->vm_private_data = src->vm_private_data; + vm_flags_init(dest, src->vm_flags); + memcpy(&dest->vm_page_prot, &src->vm_page_prot, + sizeof(dest->vm_page_prot)); + /* + * src->shared.rb may be modified concurrently when called from + * dup_mmap(), but the clone will reinitialize it. + */ + data_race(memcpy(&dest->shared, &src->shared, sizeof(dest->shared))); + memcpy(&dest->vm_userfaultfd_ctx, &src->vm_userfaultfd_ctx, + sizeof(dest->vm_userfaultfd_ctx)); +#ifdef CONFIG_ANON_VMA_NAME + dest->anon_name = src->anon_name; +#endif +#ifdef CONFIG_SWAP + memcpy(&dest->swap_readahead_info, &src->swap_readahead_info, + sizeof(dest->swap_readahead_info)); +#endif +#ifndef CONFIG_MMU + dest->vm_region = src->vm_region; +#endif +#ifdef CONFIG_NUMA + dest->vm_policy = src->vm_policy; +#endif +} + struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) { struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); @@ -458,11 +494,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) ASSERT_EXCLUSIVE_WRITER(orig->vm_flags); ASSERT_EXCLUSIVE_WRITER(orig->vm_file); - /* - * orig->shared.rb may be modified concurrently, but the clone - * will be reinitialized. - */ - data_race(memcpy(new, orig, sizeof(*new))); + vm_area_init_from(orig, new); vma_lock_init(new, true); INIT_LIST_HEAD(&new->anon_vma_chain); vma_numab_state_init(new); @@ -471,7 +503,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) return new; } -void __vm_area_free(struct vm_area_struct *vma) +void vm_area_free(struct vm_area_struct *vma) { /* The vma should be detached while being destroyed. */ vma_assert_detached(vma); @@ -480,25 +512,6 @@ void __vm_area_free(struct vm_area_struct *vma) kmem_cache_free(vm_area_cachep, vma); } -#ifdef CONFIG_PER_VMA_LOCK -static void vm_area_free_rcu_cb(struct rcu_head *head) -{ - struct vm_area_struct *vma = container_of(head, struct vm_area_struct, - vm_rcu); - - __vm_area_free(vma); -} -#endif - -void vm_area_free(struct vm_area_struct *vma) -{ -#ifdef CONFIG_PER_VMA_LOCK - call_rcu(&vma->vm_rcu, vm_area_free_rcu_cb); -#else - __vm_area_free(vma); -#endif -} - static void account_kernel_stack(struct task_struct *tsk, int account) { if (IS_ENABLED(CONFIG_VMAP_STACK)) { @@ -3156,6 +3169,11 @@ void __init mm_cache_init(void) void __init proc_caches_init(void) { + struct kmem_cache_args args = { + .use_freeptr_offset = true, + .freeptr_offset = offsetof(struct vm_area_struct, vm_freeptr), + }; + sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| @@ -3172,8 +3190,9 @@ void __init proc_caches_init(void) sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); - vm_area_cachep = KMEM_CACHE(vm_area_struct, - SLAB_HWCACHE_ALIGN|SLAB_NO_MERGE|SLAB_PANIC| + vm_area_cachep = kmem_cache_create("vm_area_struct", + sizeof(struct vm_area_struct), &args, + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| SLAB_ACCOUNT); mmap_init(); nsproxy_cache_init(); diff --git a/mm/mmap.c b/mm/mmap.c index 6401a1d73f4a..15d6cd7cc845 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1305,7 +1305,8 @@ void exit_mmap(struct mm_struct *mm) do { if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); - remove_vma(vma, /* unreachable = */ true); + vma_mark_detached(vma); + remove_vma(vma); count++; cond_resched(); vma = vma_next(&vmi); diff --git a/mm/vma.c b/mm/vma.c index 53f4d0efce4d..5cdc5612bfc1 100644 --- a/mm/vma.c +++ b/mm/vma.c @@ -420,19 +420,14 @@ static bool can_vma_merge_right(struct vma_merge_struct *vmg, /* * Close a vm structure and free it. */ -void remove_vma(struct vm_area_struct *vma, bool unreachable) +void remove_vma(struct vm_area_struct *vma) { might_sleep(); vma_close(vma); if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); - if (unreachable) { - vma_mark_detached(vma); - __vm_area_free(vma); - } else { - vm_area_free(vma); - } + vm_area_free(vma); } /* @@ -1218,7 +1213,7 @@ static void vms_complete_munmap_vmas(struct vma_munmap_struct *vms, /* Remove and clean up vmas */ mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) - remove_vma(vma, /* unreachable = */ false); + remove_vma(vma); vm_unacct_memory(vms->nr_accounted); validate_mm(mm); diff --git a/mm/vma.h b/mm/vma.h index 55be77ff042f..7356ca5a22d3 100644 --- a/mm/vma.h +++ b/mm/vma.h @@ -218,7 +218,7 @@ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool unlock); -void remove_vma(struct vm_area_struct *vma, bool unreachable); +void remove_vma(struct vm_area_struct *vma); void unmap_region(struct ma_state *mas, struct vm_area_struct *vma, struct vm_area_struct *prev, struct vm_area_struct *next); diff --git a/tools/include/linux/refcount.h b/tools/include/linux/refcount.h index 36cb29bc57c2..1f30956e070d 100644 --- a/tools/include/linux/refcount.h +++ b/tools/include/linux/refcount.h @@ -60,6 +60,11 @@ static inline void refcount_set(refcount_t *r, unsigned int n) atomic_set(&r->refs, n); } +static inline void refcount_set_release(refcount_t *r, unsigned int n) +{ + atomic_set(&r->refs, n); +} + static inline unsigned int refcount_read(const refcount_t *r) { return atomic_read(&r->refs); diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h index b385170fbb8f..572ab2cea763 100644 --- a/tools/testing/vma/vma_internal.h +++ b/tools/testing/vma/vma_internal.h @@ -476,7 +476,7 @@ static inline void vma_mark_attached(struct vm_area_struct *vma) { vma_assert_write_locked(vma); vma_assert_detached(vma); - refcount_set(&vma->vm_refcnt, 1); + refcount_set_release(&vma->vm_refcnt, 1); } static inline void vma_mark_detached(struct vm_area_struct *vma) @@ -696,14 +696,9 @@ static inline void mpol_put(struct mempolicy *) { } -static inline void __vm_area_free(struct vm_area_struct *vma) -{ - free(vma); -} - static inline void vm_area_free(struct vm_area_struct *vma) { - __vm_area_free(vma); + free(vma); } static inline void lru_add_drain(void) -- cgit v1.2.3-59-g8ed1b From 6af8cb80d3a9a6bbd521d8a7c949b4eafb7dba5d Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 3 Mar 2025 17:30:05 +0100 Subject: mm/rmap: basic MM owner tracking for large folios (!hugetlb) For small folios, we traditionally use the mapcount to decide whether it was "certainly mapped exclusively" by a single MM (mapcount == 1) or whether it "maybe mapped shared" by multiple MMs (mapcount > 1). For PMD-sized folios that were PMD-mapped, we were able to use a similar mechanism (single PMD mapping), but for PTE-mapped folios and in the future folios that span multiple PMDs, this does not work. So we need a different mechanism to handle large folios. Let's add a new mechanism to detect whether a large folio is "certainly mapped exclusively", or whether it is "maybe mapped shared". We'll use this information next to optimize CoW reuse for PTE-mapped anonymous THP, and to convert folio_likely_mapped_shared() to folio_maybe_mapped_shared(), independent of per-page mapcounts. For each large folio, we'll have two slots, whereby a slot stores: (1) an MM id: unique id assigned to each MM (2) a per-MM mapcount If a slot is unoccupied, it can be taken by the next MM that maps folio page. In addition, we'll remember the current state -- "mapped exclusively" vs. "maybe mapped shared" -- and use a bit spinlock to sync on updates and to reduce the total number of atomic accesses on updates. In the future, it might be possible to squeeze a proper spinlock into "struct folio". For now, keep it simple, as we require the whole thing with THP only, that is incompatible with RT. As we have to squeeze this information into the "struct folio" of even folios of order-1 (2 pages), and we generally want to reduce the required metadata, we'll assign each MM a unique ID that can fit into an int. In total, we can squeeze everything into 4x int (2x long) on 64bit. 32bit support is a bit challenging, because we only have 2x long == 2x int in order-1 folios. But we can make it work for now, because we neither expect many MMs nor very large folios on 32bit. We will reliably detect folios as "mapped exclusively" vs. "mapped shared" as long as only two MMs map pages of a folio at one point in time -- for example with fork() and short-lived child processes, or with apps that hand over state from one instance to another. As soon as three MMs are involved at the same time, we might detect "maybe mapped shared" although the folio is "mapped exclusively". Example 1: (1) App1 faults in a (shmem/file-backed) folio page -> Tracked as MM0 (2) App2 faults in a folio page -> Tracked as MM1 (4) App1 unmaps all folio pages -> We will detect "mapped exclusively". Example 2: (1) App1 faults in a (shmem/file-backed) folio page -> Tracked as MM0 (2) App2 faults in a folio page -> Tracked as MM1 (3) App3 faults in a folio page -> No slot available, tracked as "unknown" (4) App1 and App2 unmap all folio pages -> We will detect "maybe mapped shared". Make use of __always_inline to keep possible performance degradation when (un)mapping large folios to a minimum. Note: by squeezing the two flags into the "unsigned long" that stores the MM ids, we can use non-atomic __bit_spin_unlock() and non-atomic setting/clearing of the "maybe mapped shared" bit, effectively not adding any new atomics on the hot path when updating the large mapcount + new metadata, which further helps reduce the runtime overhead in micro-benchmarks. Link: https://lkml.kernel.org/r/20250303163014.1128035-13-david@redhat.com Signed-off-by: David Hildenbrand Cc: Andy Lutomirks^H^Hski Cc: Borislav Betkov Cc: Dave Hansen Cc: Ingo Molnar Cc: Jann Horn Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Kirill A. Shutemov Cc: Lance Yang Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcow (Oracle) Cc: Michal Koutn Cc: Muchun Song Cc: tejun heo Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Zefan Li Signed-off-by: Andrew Morton --- Documentation/mm/transhuge.rst | 8 ++ include/linux/mm_types.h | 49 ++++++++++++ include/linux/page-flags.h | 4 + include/linux/rmap.h | 165 +++++++++++++++++++++++++++++++++++++++++ kernel/fork.c | 36 +++++++++ mm/Kconfig | 4 + mm/internal.h | 5 ++ mm/page_alloc.c | 10 +++ 8 files changed, 281 insertions(+) (limited to 'kernel/fork.c') diff --git a/Documentation/mm/transhuge.rst b/Documentation/mm/transhuge.rst index a2cd8800d527..baa17d718a76 100644 --- a/Documentation/mm/transhuge.rst +++ b/Documentation/mm/transhuge.rst @@ -120,11 +120,19 @@ pages: and also increment/decrement folio->_nr_pages_mapped by ENTIRELY_MAPPED when _entire_mapcount goes from -1 to 0 or 0 to -1. + We also maintain the two slots for tracking MM owners (MM ID and + corresponding mapcount), and the current status ("maybe mapped shared" vs. + "mapped exclusively"). + - map/unmap of individual pages with PTE entry increment/decrement page->_mapcount, increment/decrement folio->_large_mapcount and also increment/decrement folio->_nr_pages_mapped when page->_mapcount goes from -1 to 0 or 0 to -1 as this counts the number of pages mapped by PTE. + We also maintain the two slots for tracking MM owners (MM ID and + corresponding mapcount), and the current status ("maybe mapped shared" vs. + "mapped exclusively"). + split_huge_page internally has to distribute the refcounts in the head page to the tail pages before clearing all PG_head/tail bits from the page structures. It can be done easily for refcounts taken by page table diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 9499eb8e8e66..aac7c87b04e1 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -292,6 +292,44 @@ typedef struct { #define NR_PAGES_IN_LARGE_FOLIO #endif +/* + * On 32bit, we can cut the required metadata in half, because: + * (a) PID_MAX_LIMIT implicitly limits the number of MMs we could ever have, + * so we can limit MM IDs to 15 bit (32767). + * (b) We don't expect folios where even a single complete PTE mapping by + * one MM would exceed 15 bits (order-15). + */ +#ifdef CONFIG_64BIT +typedef int mm_id_mapcount_t; +#define MM_ID_MAPCOUNT_MAX INT_MAX +typedef unsigned int mm_id_t; +#else /* !CONFIG_64BIT */ +typedef short mm_id_mapcount_t; +#define MM_ID_MAPCOUNT_MAX SHRT_MAX +typedef unsigned short mm_id_t; +#endif /* CONFIG_64BIT */ + +/* We implicitly use the dummy ID for init-mm etc. where we never rmap pages. */ +#define MM_ID_DUMMY 0 +#define MM_ID_MIN (MM_ID_DUMMY + 1) + +/* + * We leave the highest bit of each MM id unused, so we can store a flag + * in the highest bit of each folio->_mm_id[]. + */ +#define MM_ID_BITS ((sizeof(mm_id_t) * BITS_PER_BYTE) - 1) +#define MM_ID_MASK ((1U << MM_ID_BITS) - 1) +#define MM_ID_MAX MM_ID_MASK + +/* + * In order to use bit_spin_lock(), which requires an unsigned long, we + * operate on folio->_mm_ids when working on flags. + */ +#define FOLIO_MM_IDS_LOCK_BITNUM MM_ID_BITS +#define FOLIO_MM_IDS_LOCK_BIT BIT(FOLIO_MM_IDS_LOCK_BITNUM) +#define FOLIO_MM_IDS_SHARED_BITNUM (2 * MM_ID_BITS + 1) +#define FOLIO_MM_IDS_SHARED_BIT BIT(FOLIO_MM_IDS_SHARED_BITNUM) + /** * struct folio - Represents a contiguous set of bytes. * @flags: Identical to the page flags. @@ -318,6 +356,9 @@ typedef struct { * @_nr_pages_mapped: Do not use outside of rmap and debug code. * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). * @_nr_pages: Do not use directly, call folio_nr_pages(). + * @_mm_id: Do not use outside of rmap code. + * @_mm_ids: Do not use outside of rmap code. + * @_mm_id_mapcount: Do not use outside of rmap code. * @_hugetlb_subpool: Do not use directly, use accessor in hugetlb.h. * @_hugetlb_cgroup: Do not use directly, use accessor in hugetlb_cgroup.h. * @_hugetlb_cgroup_rsvd: Do not use directly, use accessor in hugetlb_cgroup.h. @@ -390,6 +431,11 @@ struct folio { atomic_t _entire_mapcount; atomic_t _pincount; #endif /* CONFIG_64BIT */ + mm_id_mapcount_t _mm_id_mapcount[2]; + union { + mm_id_t _mm_id[2]; + unsigned long _mm_ids; + }; /* private: the union with struct page is transitional */ }; unsigned long _usable_1[4]; @@ -1114,6 +1160,9 @@ struct mm_struct { #endif } lru_gen; #endif /* CONFIG_LRU_GEN_WALKS_MMU */ +#ifdef CONFIG_MM_ID + mm_id_t mm_id; +#endif /* CONFIG_MM_ID */ } __randomize_layout; /* diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index cab382bd965e..f26ce54c7aa4 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -1185,6 +1185,10 @@ static inline int folio_has_private(const struct folio *folio) return !!(folio->flags & PAGE_FLAGS_PRIVATE); } +static inline bool folio_test_large_maybe_mapped_shared(const struct folio *folio) +{ + return test_bit(FOLIO_MM_IDS_SHARED_BITNUM, &folio->_mm_ids); +} #undef PF_ANY #undef PF_HEAD #undef PF_NO_TAIL diff --git a/include/linux/rmap.h b/include/linux/rmap.h index d1e888cc97a5..c131b0efff0f 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -13,6 +13,7 @@ #include #include #include +#include /* * The anon_vma heads a list of private "related" vmas, to scan if @@ -173,6 +174,169 @@ static inline void anon_vma_merge(struct vm_area_struct *vma, struct anon_vma *folio_get_anon_vma(const struct folio *folio); +#ifdef CONFIG_MM_ID +static __always_inline void folio_lock_large_mapcount(struct folio *folio) +{ + bit_spin_lock(FOLIO_MM_IDS_LOCK_BITNUM, &folio->_mm_ids); +} + +static __always_inline void folio_unlock_large_mapcount(struct folio *folio) +{ + __bit_spin_unlock(FOLIO_MM_IDS_LOCK_BITNUM, &folio->_mm_ids); +} + +static inline unsigned int folio_mm_id(const struct folio *folio, int idx) +{ + VM_WARN_ON_ONCE(idx != 0 && idx != 1); + return folio->_mm_id[idx] & MM_ID_MASK; +} + +static inline void folio_set_mm_id(struct folio *folio, int idx, mm_id_t id) +{ + VM_WARN_ON_ONCE(idx != 0 && idx != 1); + folio->_mm_id[idx] &= ~MM_ID_MASK; + folio->_mm_id[idx] |= id; +} + +static inline void __folio_large_mapcount_sanity_checks(const struct folio *folio, + int diff, mm_id_t mm_id) +{ + VM_WARN_ON_ONCE(!folio_test_large(folio) || folio_test_hugetlb(folio)); + VM_WARN_ON_ONCE(diff <= 0); + VM_WARN_ON_ONCE(mm_id < MM_ID_MIN || mm_id > MM_ID_MAX); + + /* + * Make sure we can detect at least one complete PTE mapping of the + * folio in a single MM as "exclusively mapped". This is primarily + * a check on 32bit, where we currently reduce the size of the per-MM + * mapcount to a short. + */ + VM_WARN_ON_ONCE(diff > folio_large_nr_pages(folio)); + VM_WARN_ON_ONCE(folio_large_nr_pages(folio) - 1 > MM_ID_MAPCOUNT_MAX); + + VM_WARN_ON_ONCE(folio_mm_id(folio, 0) == MM_ID_DUMMY && + folio->_mm_id_mapcount[0] != -1); + VM_WARN_ON_ONCE(folio_mm_id(folio, 0) != MM_ID_DUMMY && + folio->_mm_id_mapcount[0] < 0); + VM_WARN_ON_ONCE(folio_mm_id(folio, 1) == MM_ID_DUMMY && + folio->_mm_id_mapcount[1] != -1); + VM_WARN_ON_ONCE(folio_mm_id(folio, 1) != MM_ID_DUMMY && + folio->_mm_id_mapcount[1] < 0); + VM_WARN_ON_ONCE(!folio_mapped(folio) && + folio_test_large_maybe_mapped_shared(folio)); +} + +static __always_inline void folio_set_large_mapcount(struct folio *folio, + int mapcount, struct vm_area_struct *vma) +{ + __folio_large_mapcount_sanity_checks(folio, mapcount, vma->vm_mm->mm_id); + + VM_WARN_ON_ONCE(folio_mm_id(folio, 0) != MM_ID_DUMMY); + VM_WARN_ON_ONCE(folio_mm_id(folio, 1) != MM_ID_DUMMY); + + /* Note: mapcounts start at -1. */ + atomic_set(&folio->_large_mapcount, mapcount - 1); + folio->_mm_id_mapcount[0] = mapcount - 1; + folio_set_mm_id(folio, 0, vma->vm_mm->mm_id); +} + +static __always_inline void folio_add_large_mapcount(struct folio *folio, + int diff, struct vm_area_struct *vma) +{ + const mm_id_t mm_id = vma->vm_mm->mm_id; + int new_mapcount_val; + + folio_lock_large_mapcount(folio); + __folio_large_mapcount_sanity_checks(folio, diff, mm_id); + + new_mapcount_val = atomic_read(&folio->_large_mapcount) + diff; + atomic_set(&folio->_large_mapcount, new_mapcount_val); + + /* + * If a folio is mapped more than once into an MM on 32bit, we + * can in theory overflow the per-MM mapcount (although only for + * fairly large folios), turning it negative. In that case, just + * free up the slot and mark the folio "mapped shared", otherwise + * we might be in trouble when unmapping pages later. + */ + if (folio_mm_id(folio, 0) == mm_id) { + folio->_mm_id_mapcount[0] += diff; + if (!IS_ENABLED(CONFIG_64BIT) && unlikely(folio->_mm_id_mapcount[0] < 0)) { + folio->_mm_id_mapcount[0] = -1; + folio_set_mm_id(folio, 0, MM_ID_DUMMY); + folio->_mm_ids |= FOLIO_MM_IDS_SHARED_BIT; + } + } else if (folio_mm_id(folio, 1) == mm_id) { + folio->_mm_id_mapcount[1] += diff; + if (!IS_ENABLED(CONFIG_64BIT) && unlikely(folio->_mm_id_mapcount[1] < 0)) { + folio->_mm_id_mapcount[1] = -1; + folio_set_mm_id(folio, 1, MM_ID_DUMMY); + folio->_mm_ids |= FOLIO_MM_IDS_SHARED_BIT; + } + } else if (folio_mm_id(folio, 0) == MM_ID_DUMMY) { + folio_set_mm_id(folio, 0, mm_id); + folio->_mm_id_mapcount[0] = diff - 1; + /* We might have other mappings already. */ + if (new_mapcount_val != diff - 1) + folio->_mm_ids |= FOLIO_MM_IDS_SHARED_BIT; + } else if (folio_mm_id(folio, 1) == MM_ID_DUMMY) { + folio_set_mm_id(folio, 1, mm_id); + folio->_mm_id_mapcount[1] = diff - 1; + /* Slot 0 certainly has mappings as well. */ + folio->_mm_ids |= FOLIO_MM_IDS_SHARED_BIT; + } + folio_unlock_large_mapcount(folio); +} + +static __always_inline void folio_sub_large_mapcount(struct folio *folio, + int diff, struct vm_area_struct *vma) +{ + const mm_id_t mm_id = vma->vm_mm->mm_id; + int new_mapcount_val; + + folio_lock_large_mapcount(folio); + __folio_large_mapcount_sanity_checks(folio, diff, mm_id); + + new_mapcount_val = atomic_read(&folio->_large_mapcount) - diff; + atomic_set(&folio->_large_mapcount, new_mapcount_val); + + /* + * There are valid corner cases where we might underflow a per-MM + * mapcount (some mappings added when no slot was free, some mappings + * added once a slot was free), so we always set it to -1 once we go + * negative. + */ + if (folio_mm_id(folio, 0) == mm_id) { + folio->_mm_id_mapcount[0] -= diff; + if (folio->_mm_id_mapcount[0] >= 0) + goto out; + folio->_mm_id_mapcount[0] = -1; + folio_set_mm_id(folio, 0, MM_ID_DUMMY); + } else if (folio_mm_id(folio, 1) == mm_id) { + folio->_mm_id_mapcount[1] -= diff; + if (folio->_mm_id_mapcount[1] >= 0) + goto out; + folio->_mm_id_mapcount[1] = -1; + folio_set_mm_id(folio, 1, MM_ID_DUMMY); + } + + /* + * If one MM slot owns all mappings, the folio is mapped exclusively. + * Note that if the folio is now unmapped (new_mapcount_val == -1), both + * slots must be free (mapcount == -1), and we'll also mark it as + * exclusive. + */ + if (folio->_mm_id_mapcount[0] == new_mapcount_val || + folio->_mm_id_mapcount[1] == new_mapcount_val) + folio->_mm_ids &= ~FOLIO_MM_IDS_SHARED_BIT; +out: + folio_unlock_large_mapcount(folio); +} +#else /* !CONFIG_MM_ID */ +/* + * See __folio_rmap_sanity_checks(), we might map large folios even without + * CONFIG_TRANSPARENT_HUGEPAGE. We'll keep that working for now. + */ static inline void folio_set_large_mapcount(struct folio *folio, int mapcount, struct vm_area_struct *vma) { @@ -191,6 +355,7 @@ static inline void folio_sub_large_mapcount(struct folio *folio, { atomic_sub(diff, &folio->_large_mapcount); } +#endif /* CONFIG_MM_ID */ #define folio_inc_large_mapcount(folio, vma) \ folio_add_large_mapcount(folio, 1, vma) diff --git a/kernel/fork.c b/kernel/fork.c index 364b2d4fd3ef..f9cf0f056eb6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -802,6 +802,36 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) #define mm_free_pgd(mm) #endif /* CONFIG_MMU */ +#ifdef CONFIG_MM_ID +static DEFINE_IDA(mm_ida); + +static inline int mm_alloc_id(struct mm_struct *mm) +{ + int ret; + + ret = ida_alloc_range(&mm_ida, MM_ID_MIN, MM_ID_MAX, GFP_KERNEL); + if (ret < 0) + return ret; + mm->mm_id = ret; + return 0; +} + +static inline void mm_free_id(struct mm_struct *mm) +{ + const mm_id_t id = mm->mm_id; + + mm->mm_id = MM_ID_DUMMY; + if (id == MM_ID_DUMMY) + return; + if (WARN_ON_ONCE(id < MM_ID_MIN || id > MM_ID_MAX)) + return; + ida_free(&mm_ida, id); +} +#else /* !CONFIG_MM_ID */ +static inline int mm_alloc_id(struct mm_struct *mm) { return 0; } +static inline void mm_free_id(struct mm_struct *mm) {} +#endif /* CONFIG_MM_ID */ + static void check_mm(struct mm_struct *mm) { int i; @@ -905,6 +935,7 @@ void __mmdrop(struct mm_struct *mm) WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); + mm_free_id(mm); destroy_context(mm); mmu_notifier_subscriptions_destroy(mm); check_mm(mm); @@ -1289,6 +1320,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, if (mm_alloc_pgd(mm)) goto fail_nopgd; + if (mm_alloc_id(mm)) + goto fail_noid; + if (init_new_context(p, mm)) goto fail_nocontext; @@ -1308,6 +1342,8 @@ fail_pcpu: fail_cid: destroy_context(mm); fail_nocontext: + mm_free_id(mm); +fail_noid: mm_free_pgd(mm); fail_nopgd: free_mm(mm); diff --git a/mm/Kconfig b/mm/Kconfig index 4c1640a197a0..a25c5476b3ad 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -815,11 +815,15 @@ config ARCH_WANT_GENERAL_HUGETLB config ARCH_WANTS_THP_SWAP def_bool n +config MM_ID + def_bool n + menuconfig TRANSPARENT_HUGEPAGE bool "Transparent Hugepage Support" depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT select COMPACTION select XARRAY_MULTI + select MM_ID help Transparent Hugepages allows the kernel to use huge pages and huge tlb transparently to the applications whenever possible. diff --git a/mm/internal.h b/mm/internal.h index fcf0aeae3934..04724971379c 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -763,6 +763,11 @@ static inline void prep_compound_head(struct page *page, unsigned int order) folio_set_order(folio, order); atomic_set(&folio->_large_mapcount, -1); atomic_set(&folio->_nr_pages_mapped, 0); + if (IS_ENABLED(CONFIG_MM_ID)) { + folio->_mm_ids = 0; + folio->_mm_id_mapcount[0] = -1; + folio->_mm_id_mapcount[1] = -1; + } if (IS_ENABLED(CONFIG_64BIT) || order > 1) { atomic_set(&folio->_pincount, 0); atomic_set(&folio->_entire_mapcount, -1); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e456a43811fd..c8daa3e64266 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -955,6 +955,16 @@ static int free_tail_page_prepare(struct page *head_page, struct page *page) bad_page(page, "nonzero nr_pages_mapped"); goto out; } + if (IS_ENABLED(CONFIG_MM_ID)) { + if (unlikely(folio->_mm_id_mapcount[0] != -1)) { + bad_page(page, "nonzero mm mapcount 0"); + goto out; + } + if (unlikely(folio->_mm_id_mapcount[1] != -1)) { + bad_page(page, "nonzero mm mapcount 1"); + goto out; + } + } if (IS_ENABLED(CONFIG_64BIT)) { if (unlikely(atomic_read(&folio->_entire_mapcount) + 1)) { bad_page(page, "nonzero entire_mapcount"); -- cgit v1.2.3-59-g8ed1b From b25bcabb6cefaa394fa03087c41d5cb82c23163d Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Mon, 17 Mar 2025 17:36:14 +0100 Subject: fork: use __vmalloc_node() for stack allocation Replace __vmalloc_node_range() by __vmalloc_node(). The last variant requires less parameters and it uses exactly the same arguments which are partly now hidden inside __vmalloc_node(). This change does not change any functionality. It makes the code a bit simpler. Link: https://lkml.kernel.org/r/20250317163614.166502-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) Acked-by: Michal Hocko Cc: Christian Brauner Cc: Oleg Nesterov Cc: Tejun Heo Signed-off-by: Andrew Morton --- kernel/fork.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index f9cf0f056eb6..83cb82643817 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -311,11 +311,9 @@ static int alloc_thread_stack_node(struct task_struct *tsk, int node) * so memcg accounting is performed manually on assigning/releasing * stacks to tasks. Drop __GFP_ACCOUNT. */ - stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN, - VMALLOC_START, VMALLOC_END, + stack = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, THREADINFO_GFP & ~__GFP_ACCOUNT, - PAGE_KERNEL, - 0, node, __builtin_return_address(0)); + node, __builtin_return_address(0)); if (!stack) return -ENOMEM; -- cgit v1.2.3-59-g8ed1b