* Copyright (c) 2007-2010 Paul Mundt <lethal@linux-sh.org>
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
-#include <linux/tracehook.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/audit.h>
+#include <linux/sched/sysctl.h>
#include <asm/uaccess.h>
#include <asm/tlb.h>
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;
+/*
+ * 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);
+
EXPORT_SYMBOL(mem_map);
EXPORT_SYMBOL(num_physpages);
return PAGE_SIZE << compound_order(page);
}
-int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long start, int nr_pages, unsigned int foll_flags,
- struct page **pages, struct vm_area_struct **vmas,
- int *retry)
+long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, unsigned long nr_pages,
+ unsigned int foll_flags, struct page **pages,
+ struct vm_area_struct **vmas, int *nonblocking)
{
struct vm_area_struct *vma;
unsigned long vm_flags;
* slab page or a secondary page from a compound page
* - don't permit access to VMAs that don't support it, such as I/O mappings
*/
-int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long start, int nr_pages, int write, int force,
- struct page **pages, struct vm_area_struct **vmas)
+long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, unsigned long nr_pages,
+ int write, int force, struct page **pages,
+ struct vm_area_struct **vmas)
{
int flags = 0;
}
EXPORT_SYMBOL(follow_pfn);
-DEFINE_RWLOCK(vmlist_lock);
-struct vm_struct *vmlist;
+LIST_HEAD(vmap_area_list);
void vfree(const void *addr)
{
* between processes, it syncs the pagetable across all
* processes.
*/
-struct vm_struct *alloc_vm_area(size_t size)
+struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
{
BUG();
return NULL;
if (vma->vm_file) {
mapping = vma->vm_file->f_mapping;
+ mutex_lock(&mapping->i_mmap_mutex);
flush_dcache_mmap_lock(mapping);
- vma_prio_tree_insert(vma, &mapping->i_mmap);
+ vma_interval_tree_insert(vma, &mapping->i_mmap);
flush_dcache_mmap_unlock(mapping);
+ mutex_unlock(&mapping->i_mmap_mutex);
}
/* add the VMA to the tree */
if (vma->vm_file) {
mapping = vma->vm_file->f_mapping;
+ mutex_lock(&mapping->i_mmap_mutex);
flush_dcache_mmap_lock(mapping);
- vma_prio_tree_remove(vma, &mapping->i_mmap);
+ vma_interval_tree_remove(vma, &mapping->i_mmap);
flush_dcache_mmap_unlock(mapping);
+ mutex_unlock(&mapping->i_mmap_mutex);
}
/* remove from the MM's tree and list */
if (vma->vm_next)
vma->vm_next->vm_prev = vma->vm_prev;
-
- vma->vm_mm = NULL;
}
/*
kenter("%p", vma);
if (vma->vm_ops && vma->vm_ops->close)
vma->vm_ops->close(vma);
- if (vma->vm_file) {
+ if (vma->vm_file)
fput(vma->vm_file);
- if (vma->vm_flags & VM_EXECUTABLE)
- removed_exe_file_vma(mm);
- }
put_nommu_region(vma->vm_region);
kmem_cache_free(vm_area_cachep, vma);
}
struct vm_area_struct *vma;
/* check the cache first */
- vma = mm->mmap_cache;
+ vma = ACCESS_ONCE(mm->mmap_cache);
if (vma && vma->vm_start <= addr && vma->vm_end > addr)
return vma;
unsigned long *_capabilities)
{
unsigned long capabilities, rlen;
- unsigned long reqprot = prot;
int ret;
/* do the simple checks first */
*/
mapping = file->f_mapping;
if (!mapping)
- mapping = file->f_path.dentry->d_inode->i_mapping;
+ mapping = file_inode(file)->i_mapping;
capabilities = 0;
if (mapping && mapping->backing_dev_info)
if (!capabilities) {
/* no explicit capabilities set, so assume some
* defaults */
- switch (file->f_path.dentry->d_inode->i_mode & S_IFMT) {
+ switch (file_inode(file)->i_mode & S_IFMT) {
case S_IFREG:
case S_IFBLK:
capabilities = BDI_CAP_MAP_COPY;
!(file->f_mode & FMODE_WRITE))
return -EACCES;
- if (IS_APPEND(file->f_path.dentry->d_inode) &&
+ if (IS_APPEND(file_inode(file)) &&
(file->f_mode & FMODE_WRITE))
return -EACCES;
- if (locks_verify_locked(file->f_path.dentry->d_inode))
+ if (locks_verify_locked(file_inode(file)))
return -EAGAIN;
if (!(capabilities & BDI_CAP_MAP_DIRECT))
}
/* allow the security API to have its say */
- ret = security_file_mmap(file, reqprot, prot, flags, addr, 0);
+ ret = security_mmap_addr(addr);
if (ret < 0)
return ret;
* it's being traced - otherwise breakpoints set in it may interfere
* with another untraced process
*/
- if ((flags & MAP_PRIVATE) && tracehook_expect_breakpoints(current))
+ if ((flags & MAP_PRIVATE) && current->ptrace)
vm_flags &= ~VM_MAYSHARE;
return vm_flags;
unsigned long len,
unsigned long prot,
unsigned long flags,
- unsigned long pgoff)
+ unsigned long pgoff,
+ unsigned long *populate)
{
struct vm_area_struct *vma;
struct vm_region *region;
kenter(",%lx,%lx,%lx,%lx,%lx", addr, len, prot, flags, pgoff);
+ *populate = 0;
+
/* decide whether we should attempt the mapping, and if so what sort of
* mapping */
ret = validate_mmap_request(file, addr, len, prot, flags, pgoff,
vma->vm_pgoff = pgoff;
if (file) {
- region->vm_file = file;
- get_file(file);
- vma->vm_file = file;
- get_file(file);
- if (vm_flags & VM_EXECUTABLE) {
- added_exe_file_vma(current->mm);
- vma->vm_mm = current->mm;
- }
+ region->vm_file = get_file(file);
+ vma->vm_file = get_file(file);
}
down_write(&nommu_region_sem);
continue;
/* search for overlapping mappings on the same file */
- if (pregion->vm_file->f_path.dentry->d_inode !=
- file->f_path.dentry->d_inode)
+ if (file_inode(pregion->vm_file) !=
+ file_inode(file))
continue;
if (pregion->vm_pgoff >= pgend)
kmem_cache_free(vm_region_jar, region);
if (vma->vm_file)
fput(vma->vm_file);
- if (vma->vm_flags & VM_EXECUTABLE)
- removed_exe_file_vma(vma->vm_mm);
kmem_cache_free(vm_area_cachep, vma);
kleave(" = %d", ret);
return ret;
show_free_areas(0);
return -ENOMEM;
}
-EXPORT_SYMBOL(do_mmap_pgoff);
SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
unsigned long, prot, unsigned long, flags,
flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
- down_write(¤t->mm->mmap_sem);
- retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
- up_write(¤t->mm->mmap_sem);
+ retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
if (file)
fput(file);
}
EXPORT_SYMBOL(do_munmap);
-SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
+int vm_munmap(unsigned long addr, size_t len)
{
- int ret;
struct mm_struct *mm = current->mm;
+ int ret;
down_write(&mm->mmap_sem);
ret = do_munmap(mm, addr, len);
up_write(&mm->mmap_sem);
return ret;
}
+EXPORT_SYMBOL(vm_munmap);
+
+SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
+{
+ return vm_munmap(addr, len);
+}
/*
* release all the mappings made in a process's VM space
kleave("");
}
-unsigned long do_brk(unsigned long addr, unsigned long len)
+unsigned long vm_brk(unsigned long addr, unsigned long len)
{
return -ENOMEM;
}
*
* 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)
{
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,
return ret;
}
-struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
- unsigned int foll_flags)
+struct page *follow_page_mask(struct vm_area_struct *vma,
+ unsigned long address, unsigned int flags,
+ unsigned int *page_mask)
{
+ *page_mask = 0;
return NULL;
}
if (addr != (pfn << PAGE_SHIFT))
return -EINVAL;
- vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
+ vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
return 0;
}
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)
{
*/
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);
return 0;
if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
- unsigned long n;
+ free = global_page_state(NR_FREE_PAGES);
+ free += global_page_state(NR_FILE_PAGES);
- free = global_page_state(NR_FILE_PAGES);
- free += nr_swap_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
*/
free += global_page_state(NR_SLAB_RECLAIMABLE);
- /*
- * Leave the last 3% for root
- */
- if (!cap_sys_admin)
- free -= free / 32;
-
- if (free > pages)
- return 0;
-
- /*
- * nr_free_pages() is very expensive on large systems,
- * only call if we're about to fail.
- */
- n = nr_free_pages();
-
/*
* Leave reserved pages. The pages are not for anonymous pages.
*/
- if (n <= totalreserve_pages)
+ if (free <= totalreserve_pages)
goto error;
else
- n -= totalreserve_pages;
+ free -= totalreserve_pages;
/*
- * Leave the last 3% for root
+ * Reserve some for root
*/
if (!cap_sys_admin)
- n -= n / 32;
- free += n;
+ free -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
if (free > pages)
return 0;
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;
}
EXPORT_SYMBOL(filemap_fault);
+int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long size, pgoff_t pgoff)
+{
+ BUG();
+ return 0;
+}
+EXPORT_SYMBOL(generic_file_remap_pages);
+
static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
unsigned long addr, void *buf, int len, int write)
{
size_t newsize)
{
struct vm_area_struct *vma;
- struct prio_tree_iter iter;
struct vm_region *region;
pgoff_t low, high;
size_t r_size, r_top;
high = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
down_write(&nommu_region_sem);
+ mutex_lock(&inode->i_mapping->i_mmap_mutex);
/* search for VMAs that fall within the dead zone */
- vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap,
- low, high) {
+ vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap, low, high) {
/* found one - only interested if it's shared out of the page
* cache */
if (vma->vm_flags & VM_SHARED) {
+ mutex_unlock(&inode->i_mapping->i_mmap_mutex);
up_write(&nommu_region_sem);
return -ETXTBSY; /* not quite true, but near enough */
}
* we don't check for any regions that start beyond the EOF as there
* shouldn't be any
*/
- vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap,
- 0, ULONG_MAX) {
+ vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap,
+ 0, ULONG_MAX) {
if (!(vma->vm_flags & VM_SHARED))
continue;
}
}
+ mutex_unlock(&inode->i_mapping->i_mmap_mutex);
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)