diff --git a/drivers/misc/lkdtm/refcount.c b/drivers/misc/lkdtm/refcount.c index de7c5ab528d9efa6ef1d633ef37de2fe61b44304..af384fd6935c70286b4538bdf877bd871758a93b 100644 --- a/drivers/misc/lkdtm/refcount.c +++ b/drivers/misc/lkdtm/refcount.c @@ -182,6 +182,21 @@ void lkdtm_REFCOUNT_SUB_AND_TEST_NEGATIVE(void) check_negative(&neg, 3); } +/* + * A refcount_sub_and_test() by zero when the counter is at zero should act like + * refcount_sub_and_test() above when going negative. + */ +static void lkdtm_REFCOUNT_SUB_AND_TEST_ZERO(void) +{ + refcount_t neg = REFCOUNT_INIT(0); + + pr_info("attempting bad refcount_sub_and_test() at zero\n"); + if (refcount_sub_and_test(0, &neg)) + pr_warn("Weird: refcount_sub_and_test() reported zero\n"); + + check_negative(&neg, 0); +} + static void check_from_zero(refcount_t *ref) { switch (refcount_read(ref)) { diff --git a/fs/inode.c b/fs/inode.c index 06b23a65c642b3dc4bf0c5df2cee714335598e03..88b14cd3e86186e737b0ca668b33e3c5b91c198a 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -455,6 +455,39 @@ static void inode_lru_list_del(struct inode *inode) this_cpu_dec(nr_unused); } +static void inode_pin_lru_isolating(struct inode *inode) +{ + lockdep_assert_held(&inode->i_lock); + WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE)); + inode->i_state |= I_LRU_ISOLATING; +} + +static void inode_unpin_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + WARN_ON(!(inode->i_state & I_LRU_ISOLATING)); + inode->i_state &= ~I_LRU_ISOLATING; + smp_mb(); + wake_up_bit(&inode->i_state, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); +} + +static void inode_wait_for_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + if (inode->i_state & I_LRU_ISOLATING) { + DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING); + wait_queue_head_t *wqh; + + wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); + __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); + spin_lock(&inode->i_lock); + WARN_ON(inode->i_state & I_LRU_ISOLATING); + } + spin_unlock(&inode->i_lock); +} + /** * inode_sb_list_add - add inode to the superblock list of inodes * @inode: inode to add @@ -567,6 +600,8 @@ static void evict(struct inode *inode) inode_sb_list_del(inode); + inode_wait_for_lru_isolating(inode); + /* * Wait for flusher thread to be done with the inode so that filesystem * does not start destroying it while writeback is still running. Since @@ -766,7 +801,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, } if (inode_has_buffers(inode) || inode->i_data.nrpages) { - __iget(inode); + inode_pin_lru_isolating(inode); spin_unlock(&inode->i_lock); spin_unlock(lru_lock); if (remove_inode_buffers(inode)) { @@ -779,7 +814,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, if (current->reclaim_state) current->reclaim_state->reclaimed_slab += reap; } - iput(inode); + inode_unpin_lru_isolating(inode); spin_lock(lru_lock); return LRU_RETRY; } diff --git a/include/linux/fs.h b/include/linux/fs.h index a7cd19c3d3d060ed212c92f0d350aea8dc85e29b..784b1316beae57cba5f77542124d78082ffe14f4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2211,6 +2211,9 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * Used to detect that mark_inode_dirty() should not move * inode between dirty lists. * + * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding + * i_count. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2233,6 +2236,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_CREATING (1 << 15) #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) +#define __I_LRU_ISOLATING 19 +#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 497990c69b0bf1352d47ecf7a79e30ff5cc71090..3f17de9f7de4cda445e360e7bb3b18edf3940b55 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -274,12 +274,12 @@ static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, in if (oldp) *oldp = old; - if (old == i) { + if (old > 0 && old == i) { smp_acquire__after_ctrl_dep(); return true; } - if (unlikely(old < 0 || old - i < 0)) + if (unlikely(old <= 0 || old - i < 0)) refcount_warn_saturate(r, REFCOUNT_SUB_UAF); return false; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ead591002b0ca7d3846038bf8a5c2378e8f884d6..15ffaefba6382147c4f11d17464dad65c84215d2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5199,11 +5199,28 @@ static struct cftype mem_cgroup_legacy_files[] = { */ static DEFINE_IDR(mem_cgroup_idr); +static DEFINE_SPINLOCK(memcg_idr_lock); + +static int mem_cgroup_alloc_id(void) +{ + int ret; + + idr_preload(GFP_KERNEL); + spin_lock(&memcg_idr_lock); + ret = idr_alloc(&mem_cgroup_idr, NULL, 1, MEM_CGROUP_ID_MAX, + GFP_NOWAIT); + spin_unlock(&memcg_idr_lock); + idr_preload_end(); + return ret; +} static void mem_cgroup_id_remove(struct mem_cgroup *memcg) { if (memcg->id.id > 0) { + spin_lock(&memcg_idr_lock); idr_remove(&mem_cgroup_idr, memcg->id.id); + spin_unlock(&memcg_idr_lock); + memcg->id.id = 0; } } @@ -5338,9 +5355,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) if (!memcg) return ERR_PTR(error); - memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, - 1, MEM_CGROUP_ID_MAX, - GFP_KERNEL); + memcg->id.id = mem_cgroup_alloc_id(); if (memcg->id.id < 0) { error = memcg->id.id; goto fail;