From 8c7829b04c523cdc732cb77f59f03320e09f3386 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 13 May 2019 17:21:50 -0700 Subject: mm: fix false-positive OVERCOMMIT_GUESS failures With the default overcommit==guess we occasionally run into mmap rejections despite plenty of memory that would get dropped under pressure but just isn't accounted reclaimable. One example of this is dying cgroups pinned by some page cache. A previous case was auxiliary path name memory associated with dentries; we have since annotated those allocations to avoid overcommit failures (see d79f7aa496fc ("mm: treat indirectly reclaimable memory as free in overcommit logic")). But trying to classify all allocated memory reliably as reclaimable and unreclaimable is a bit of a fool's errand. There could be a myriad of dependencies that constantly change with kernel versions. It becomes even more questionable of an effort when considering how this estimate of available memory is used: it's not compared to the system-wide allocated virtual memory in any way. It's not even compared to the allocating process's address space. It's compared to the single allocation request at hand! So we have an elaborate left-hand side of the equation that tries to assess the exact breathing room the system has available down to a page - and then compare it to an isolated allocation request with no additional context. We could fail an allocation of N bytes, but for two allocations of N/2 bytes we'd do this elaborate dance twice in a row and then still let N bytes of virtual memory through. This doesn't make a whole lot of sense. Let's take a step back and look at the actual goal of the heuristic. From the documentation: Heuristic overcommit handling. Obvious overcommits of address space are refused. Used for a typical system. It ensures a seriously wild allocation fails while allowing overcommit to reduce swap usage. root is allowed to allocate slightly more memory in this mode. This is the default. If all we want to do is catch clearly bogus allocation requests irrespective of the general virtual memory situation, the physical memory counter-part doesn't need to be that complicated, either. When in GUESS mode, catch wild allocations by comparing their request size to total amount of ram and swap in the system. Link: http://lkml.kernel.org/r/20190412191418.26333-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Roman Gushchin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/util.c | 51 +++++---------------------------------------------- 1 file changed, 5 insertions(+), 46 deletions(-) diff --git a/mm/util.c b/mm/util.c index 05a464929b3e..e2e4f8c3fa12 100644 --- a/mm/util.c +++ b/mm/util.c @@ -652,7 +652,7 @@ EXPORT_SYMBOL_GPL(vm_memory_committed); */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { - long free, allowed, reserve; + long allowed; VM_WARN_ONCE(percpu_counter_read(&vm_committed_as) < -(s64)vm_committed_as_batch * num_online_cpus(), @@ -667,51 +667,9 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) return 0; if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) { - free = global_zone_page_state(NR_FREE_PAGES); - free += global_node_page_state(NR_FILE_PAGES); - - /* - * shmem pages shouldn't be counted as free in this - * case, they can't be purged, only swapped out, and - * that won't affect the overall amount of available - * memory in the system. - */ - free -= global_node_page_state(NR_SHMEM); - - free += get_nr_swap_pages(); - - /* - * Any slabs which are created with the - * SLAB_RECLAIM_ACCOUNT flag claim to have contents - * which are reclaimable, under pressure. The dentry - * cache and most inode caches should fall into this - */ - free += global_node_page_state(NR_SLAB_RECLAIMABLE); - - /* - * Part of the kernel memory, which can be released - * under memory pressure. - */ - free += global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE); - - /* - * Leave reserved pages. The pages are not for anonymous pages. - */ - if (free <= totalreserve_pages) + if (pages > totalram_pages() + total_swap_pages) goto error; - else - free -= totalreserve_pages; - - /* - * Reserve some for root - */ - if (!cap_sys_admin) - free -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); - - if (free > pages) - return 0; - - goto error; + return 0; } allowed = vm_commit_limit(); @@ -725,7 +683,8 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) * Don't let a single process grow so big a user can't recover */ if (mm) { - reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); + long reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); + allowed -= min_t(long, mm->total_vm / 32, reserve); } -- cgit v1.2.3-59-g8ed1b