X-Git-Url: http://pileus.org/git/?a=blobdiff_plain;f=mm%2Fnommu.c;h=298884dcd6e71e4723a203a82f1613cbfcec19ec;hb=9e7c414350a6fa4e5f9b7e5f7e074fa75ba850c3;hp=2f3ea749c3184057559cc06ef60960d39bb4bac2;hpb=5e0e61dd2c89c673f89fb57dcd3cc746dc0c1706;p=~andy%2Flinux

diff --git a/mm/nommu.c b/mm/nommu.c
index 2f3ea749c31..298884dcd6e 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -63,6 +63,8 @@ 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 */
+unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */
 int heap_stack_gap = 0;
 
 atomic_long_t mmap_pages_allocated;
@@ -228,8 +230,7 @@ int follow_pfn(struct vm_area_struct *vma, unsigned long address,
 }
 EXPORT_SYMBOL(follow_pfn);
 
-DEFINE_RWLOCK(vmlist_lock);
-struct vm_struct *vmlist;
+LIST_HEAD(vmap_area_list);
 
 void vfree(const void *addr)
 {
@@ -1770,7 +1771,7 @@ unsigned long vm_brk(unsigned long addr, unsigned long len)
  *
  * MREMAP_FIXED is not supported under NOMMU conditions
  */
-unsigned long do_mremap(unsigned long addr,
+static unsigned long do_mremap(unsigned long addr,
 			unsigned long old_len, unsigned long new_len,
 			unsigned long flags, unsigned long new_addr)
 {
@@ -1805,7 +1806,6 @@ unsigned long do_mremap(unsigned long addr,
 	vma->vm_end = vma->vm_start + new_len;
 	return vma->vm_start;
 }
-EXPORT_SYMBOL(do_mremap);
 
 SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 		unsigned long, new_len, unsigned long, flags,
@@ -1838,6 +1838,16 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(remap_pfn_range);
 
+int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
+{
+	unsigned long pfn = start >> PAGE_SHIFT;
+	unsigned long vm_len = vma->vm_end - vma->vm_start;
+
+	pfn += vma->vm_pgoff;
+	return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_iomap_memory);
+
 int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 			unsigned long pgoff)
 {
@@ -1888,7 +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);
 
@@ -1929,10 +1939,10 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 			free -= totalreserve_pages;
 
 		/*
-		 * Leave the last 3% for root
+		 * Reserve some for root
 		 */
 		if (!cap_sys_admin)
-			free -= free / 32;
+			free -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
 
 		if (free > pages)
 			return 0;
@@ -1942,16 +1952,19 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 
 	allowed = totalram_pages * sysctl_overcommit_ratio / 100;
 	/*
-	 * Leave the last 3% for root
+	 * Reserve some 3% for root
 	 */
 	if (!cap_sys_admin)
-		allowed -= allowed / 32;
+		allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
 	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;
@@ -2113,3 +2126,45 @@ 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)
+
+/*
+ * Initialise sysctl_admin_reserve_kbytes.
+ *
+ * The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin
+ * to log in and kill a memory hogging process.
+ *
+ * Systems with more than 256MB will reserve 8MB, enough to recover
+ * with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will
+ * only reserve 3% of free pages by default.
+ */
+static int __meminit init_admin_reserve(void)
+{
+	unsigned long free_kbytes;
+
+	free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10);
+
+	sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13);
+	return 0;
+}
+module_init(init_admin_reserve)