mm: limit growth of 3% hardcoded other user reserve

[karo-tx-linux.git] / mm / nommu.c

diff --git a/mm/nommu.c b/mm/nommu.c
index 2f1c75ed468e030929354b07226dbc3df1e59ffb..58e4a0a5125fc61841bf5aa60ac5830977675249 100644 (file)
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -63,6 +63,7 @@ int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
 int sysctl_overcommit_ratio = 50; /* default is 50% */
 int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
 int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
+unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */
 int heap_stack_gap = 0;
 
 atomic_long_t mmap_pages_allocated;
@@ -1897,7 +1898,7 @@ EXPORT_SYMBOL(unmap_mapping_range);
  */
 int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 {
-       unsigned long free, allowed;
+       unsigned long free, allowed, reserve;
 
        vm_acct_memory(pages);
 
@@ -1957,10 +1958,13 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
                allowed -= allowed / 32;
        allowed += total_swap_pages;
 
-       /* Don't let a single process grow too big:
-          leave 3% of the size of this process for other processes */
-       if (mm)
-               allowed -= mm->total_vm / 32;
+       /*
+        * 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(mm->total_vm / 32, reserve);
+       }
 
        if (percpu_counter_read_positive(&vm_committed_as) < allowed)
                return 0;
@@ -2122,3 +2126,24 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
        up_write(&nommu_region_sem);
        return 0;
 }
+
+/*
+ * Initialise sysctl_user_reserve_kbytes.
+ *
+ * This is intended to prevent a user from starting a single memory hogging
+ * process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER
+ * mode.
+ *
+ * The default value is min(3% of free memory, 128MB)
+ * 128MB is enough to recover with sshd/login, bash, and top/kill.
+ */
+static int __meminit init_user_reserve(void)
+{
+       unsigned long free_kbytes;
+
+       free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10);
+
+       sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17);
+       return 0;
+}
+module_init(init_user_reserve)