mm: deduplicate memory overcommitment code

Currently we have two copies of the same code which implements memory
overcommitment logic.  Let's move it into mm/util.c and hence avoid
duplication.  No functional changes here.

Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 124 insertions, 0 deletions

diff --git a/mm/util.c b/mm/util.c
index 4fb14ca5a419..47a57e557614 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -396,6 +396,13 @@ int __page_mapcount(struct page *page)
 }
 EXPORT_SYMBOL_GPL(__page_mapcount);
 
+int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;
+int sysctl_overcommit_ratio __read_mostly = 50;
+unsigned long sysctl_overcommit_kbytes __read_mostly;
+int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
+unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */
+unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */
+
 int overcommit_ratio_handler(struct ctl_table *table, int write,
                              void __user *buffer, size_t *lenp,
                              loff_t *ppos)
@@ -437,6 +444,123 @@ unsigned long vm_commit_limit(void)
         return allowed;
 }
 
+/*
+ * Make sure vm_committed_as in one cacheline and not cacheline shared with
+ * other variables. It can be updated by several CPUs frequently.
+ */
+struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp;
+
+/*
+ * The global memory commitment made in the system can be a metric
+ * that can be used to drive ballooning decisions when Linux is hosted
+ * as a guest. On Hyper-V, the host implements a policy engine for dynamically
+ * balancing memory across competing virtual machines that are hosted.
+ * Several metrics drive this policy engine including the guest reported
+ * memory commitment.
+ */
+unsigned long vm_memory_committed(void)
+{
+        return percpu_counter_read_positive(&vm_committed_as);
+}
+EXPORT_SYMBOL_GPL(vm_memory_committed);
+
+/*
+ * Check that a process has enough memory to allocate a new virtual
+ * mapping. 0 means there is enough memory for the allocation to
+ * succeed and -ENOMEM implies there is not.
+ *
+ * We currently support three overcommit policies, which are set via the
+ * vm.overcommit_memory sysctl.  See Documentation/vm/overcommit-accounting
+ *
+ * Strict overcommit modes added 2002 Feb 26 by Alan Cox.
+ * Additional code 2002 Jul 20 by Robert Love.
+ *
+ * cap_sys_admin is 1 if the process has admin privileges, 0 otherwise.
+ *
+ * Note this is a helper function intended to be used by LSMs which
+ * wish to use this logic.
+ */
+int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
+{
+        long free, allowed, reserve;
+
+        VM_WARN_ONCE(percpu_counter_read(&vm_committed_as) <
+                        -(s64)vm_committed_as_batch * num_online_cpus(),
+                        "memory commitment underflow");
+
+        vm_acct_memory(pages);
+
+        /*
+         * Sometimes we want to use more memory than we have
+         */
+        if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS)
+                return 0;
+
+        if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
+                free = global_page_state(NR_FREE_PAGES);
+                free += global_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_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_page_state(NR_SLAB_RECLAIMABLE);
+
+                /*
+                 * Leave reserved pages. The pages are not for anonymous pages.
+                 */
+                if (free <= totalreserve_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;
+        }
+
+        allowed = vm_commit_limit();
+        /*
+         * Reserve some for root
+         */
+        if (!cap_sys_admin)
+                allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
+
+        /*
+         * Don't let a single process grow so big a user can't recover
+         */
+        if (mm) {
+                reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10);
+                allowed -= min_t(long, mm->total_vm / 32, reserve);
+        }
+
+        if (percpu_counter_read_positive(&vm_committed_as) < allowed)
+                return 0;
+error:
+        vm_unacct_memory(pages);
+
+        return -ENOMEM;
+}
+
 /**
  * get_cmdline() - copy the cmdline value to a buffer.
  * @task:     the task whose cmdline value to copy.