Add helper functions to speculatively perform operations without read-locking mmap_lock, expecting that mmap_lock will not be write-locked and mm is not modified from under us. Signed-off-by: Suren Baghdasaryan <surenb@xxxxxxxxxx> Suggested-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Cc: Andrii Nakryiko <andrii.nakryiko@xxxxxxxxx> --- Discussion [1] follow-up. If proves to be useful can be included in that patchset. Based on mm-unstable. [1] https://lore.kernel.org/all/20240730134605.GO33588@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx/ include/linux/mm_types.h | 3 +++ include/linux/mmap_lock.h | 53 +++++++++++++++++++++++++++++++-------- kernel/fork.c | 3 --- 3 files changed, 46 insertions(+), 13 deletions(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 003619fab20e..a426e6ced604 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -887,6 +887,9 @@ struct mm_struct { * Roughly speaking, incrementing the sequence number is * equivalent to releasing locks on VMAs; reading the sequence * number can be part of taking a read lock on a VMA. + * Incremented every time mmap_lock is write-locked/unlocked. + * Initialized to 0, therefore odd values indicate mmap_lock + * is write-locked and even values that it's released. * * Can be modified under write mmap_lock using RELEASE * semantics. diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index de9dc20b01ba..5410ce741d75 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -71,15 +71,12 @@ static inline void mmap_assert_write_locked(const struct mm_struct *mm) } #ifdef CONFIG_PER_VMA_LOCK -/* - * Drop all currently-held per-VMA locks. - * This is called from the mmap_lock implementation directly before releasing - * a write-locked mmap_lock (or downgrading it to read-locked). - * This should normally NOT be called manually from other places. - * If you want to call this manually anyway, keep in mind that this will release - * *all* VMA write locks, including ones from further up the stack. - */ -static inline void vma_end_write_all(struct mm_struct *mm) +static inline void init_mm_lock_seq(struct mm_struct *mm) +{ + mm->mm_lock_seq = 0; +} + +static inline void inc_mm_lock_seq(struct mm_struct *mm) { mmap_assert_write_locked(mm); /* @@ -91,19 +88,52 @@ static inline void vma_end_write_all(struct mm_struct *mm) */ smp_store_release(&mm->mm_lock_seq, mm->mm_lock_seq + 1); } + +static inline bool mmap_lock_speculation_start(struct mm_struct *mm, int *seq) +{ + /* Pairs with RELEASE semantics in inc_mm_lock_seq(). */ + *seq = smp_load_acquire(&mm->mm_lock_seq); + /* Allow speculation if mmap_lock is not write-locked */ + return (*seq & 1) == 0; +} + +static inline bool mmap_lock_speculation_end(struct mm_struct *mm, int seq) +{ + /* Pairs with RELEASE semantics in inc_mm_lock_seq(). */ + return seq == smp_load_acquire(&mm->mm_lock_seq); +} + #else -static inline void vma_end_write_all(struct mm_struct *mm) {} +static inline void init_mm_lock_seq(struct mm_struct *mm) {} +static inline void inc_mm_lock_seq(struct mm_struct *mm) {} +static inline bool mmap_lock_speculation_start(struct mm_struct *mm, int *seq) { return false; } +static inline bool mmap_lock_speculation_end(struct mm_struct *mm, int seq) { return false; } #endif +/* + * Drop all currently-held per-VMA locks. + * This is called from the mmap_lock implementation directly before releasing + * a write-locked mmap_lock (or downgrading it to read-locked). + * This should normally NOT be called manually from other places. + * If you want to call this manually anyway, keep in mind that this will release + * *all* VMA write locks, including ones from further up the stack. + */ +static inline void vma_end_write_all(struct mm_struct *mm) +{ + inc_mm_lock_seq(mm); +} + static inline void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); + init_mm_lock_seq(mm); } static inline void mmap_write_lock(struct mm_struct *mm) { __mmap_lock_trace_start_locking(mm, true); down_write(&mm->mmap_lock); + inc_mm_lock_seq(mm); __mmap_lock_trace_acquire_returned(mm, true, true); } @@ -111,6 +141,7 @@ static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) { __mmap_lock_trace_start_locking(mm, true); down_write_nested(&mm->mmap_lock, subclass); + inc_mm_lock_seq(mm); __mmap_lock_trace_acquire_returned(mm, true, true); } @@ -120,6 +151,8 @@ static inline int mmap_write_lock_killable(struct mm_struct *mm) __mmap_lock_trace_start_locking(mm, true); ret = down_write_killable(&mm->mmap_lock); + if (!ret) + inc_mm_lock_seq(mm); __mmap_lock_trace_acquire_returned(mm, true, ret == 0); return ret; } diff --git a/kernel/fork.c b/kernel/fork.c index 3d590e51ce84..73e37af8a24d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1259,9 +1259,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, seqcount_init(&mm->write_protect_seq); mmap_init_lock(mm); INIT_LIST_HEAD(&mm->mmlist); -#ifdef CONFIG_PER_VMA_LOCK - mm->mm_lock_seq = 0; -#endif mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; base-commit: 98808d08fc0f78ee638e0c0a88020fbbaf581ec6 -- 2.46.0.rc2.264.g509ed76dc8-goog