From 3089bf614c7e2fd441ee001e3ff3d18326f6f091 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Fri, 23 Sep 2016 20:21:56 -0700 Subject: shmem: fix tmpfs to handle the huge= option properly shmem_get_unmapped_area() checks SHMEM_SB(sb)->huge incorrectly, which leads to a reversed effect of "huge=" mount option. Fix the check in shmem_get_unmapped_area(). Note, the default value of SHMEM_SB(sb)->huge remains as SHMEM_HUGE_NEVER. User will need to specify "huge=" option to enable huge page mappings. Reported-by: Hillf Danton Signed-off-by: Toshi Kani Acked-by: Kirill A. Shutemov Reviewed-by: Aneesh Kumar K.V Signed-off-by: Hugh Dickins Signed-off-by: Linus Torvalds --- mm/shmem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/shmem.c b/mm/shmem.c index fd8b2b5741b1..aec5b492d947 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1980,7 +1980,7 @@ unsigned long shmem_get_unmapped_area(struct file *file, return addr; sb = shm_mnt->mnt_sb; } - if (SHMEM_SB(sb)->huge != SHMEM_HUGE_NEVER) + if (SHMEM_SB(sb)->huge == SHMEM_HUGE_NEVER) return addr; } -- cgit v1.2.3 From 71664665c3e3ca5ff61ef5fc65480f82cd575eb2 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 23 Sep 2016 20:24:23 -0700 Subject: huge tmpfs: fix Committed_AS leak Under swapping load on huge tmpfs, /proc/meminfo's Committed_AS grows bigger and bigger: just a cosmetic issue for most users, but disabling for those who run without overcommit (/proc/sys/vm/overcommit_memory 2). shmem_uncharge() was forgetting to unaccount __vm_enough_memory's charge, and shmem_charge() was forgetting it on the filesystem-full error path. Fixes: 800d8c63b2e9 ("shmem: add huge pages support") Signed-off-by: Hugh Dickins Acked-by: Kirill A. Shutemov Signed-off-by: Linus Torvalds --- mm/shmem.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/shmem.c b/mm/shmem.c index aec5b492d947..971fc83e6402 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -270,7 +270,7 @@ bool shmem_charge(struct inode *inode, long pages) info->alloced -= pages; shmem_recalc_inode(inode); spin_unlock_irqrestore(&info->lock, flags); - + shmem_unacct_blocks(info->flags, pages); return false; } percpu_counter_add(&sbinfo->used_blocks, pages); @@ -291,6 +291,7 @@ void shmem_uncharge(struct inode *inode, long pages) if (sbinfo->max_blocks) percpu_counter_sub(&sbinfo->used_blocks, pages); + shmem_unacct_blocks(info->flags, pages); } /* -- cgit v1.2.3 From b385d21f27d86426472f6ae92a231095f7de2a8d Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 23 Sep 2016 20:27:04 -0700 Subject: mm: delete unnecessary and unsafe init_tlb_ubc() init_tlb_ubc() looked unnecessary to me: tlb_ubc is statically initialized with zeroes in the init_task, and copied from parent to child while it is quiescent in arch_dup_task_struct(); so I went to delete it. But inserted temporary debug WARN_ONs in place of init_tlb_ubc() to check that it was always empty at that point, and found them firing: because memcg reclaim can recurse into global reclaim (when allocating biosets for swapout in my case), and arrive back at the init_tlb_ubc() in shrink_node_memcg(). Resetting tlb_ubc.flush_required at that point is wrong: if the upper level needs a deferred TLB flush, but the lower level turns out not to, we miss a TLB flush. But fortunately, that's the only part of the protocol that does not nest: with the initialization removed, cpumask collects bits from upper and lower levels, and flushes TLB when needed. Fixes: 72b252aed506 ("mm: send one IPI per CPU to TLB flush all entries after unmapping pages") Signed-off-by: Hugh Dickins Acked-by: Mel Gorman Cc: stable@vger.kernel.org # 4.3+ Signed-off-by: Linus Torvalds --- mm/vmscan.c | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'mm') diff --git a/mm/vmscan.c b/mm/vmscan.c index b1e12a1ea9cf..0fe8b7113868 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2303,23 +2303,6 @@ out: } } -#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH -static void init_tlb_ubc(void) -{ - /* - * This deliberately does not clear the cpumask as it's expensive - * and unnecessary. If there happens to be data in there then the - * first SWAP_CLUSTER_MAX pages will send an unnecessary IPI and - * then will be cleared. - */ - current->tlb_ubc.flush_required = false; -} -#else -static inline void init_tlb_ubc(void) -{ -} -#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ - /* * This is a basic per-node page freer. Used by both kswapd and direct reclaim. */ @@ -2355,8 +2338,6 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() && sc->priority == DEF_PRIORITY); - init_tlb_ubc(); - blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { -- cgit v1.2.3