aboutsummaryrefslogtreecommitdiff
path: root/mm/nommu.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/nommu.c')
-rw-r--r--mm/nommu.c192
1 files changed, 133 insertions, 59 deletions
diff --git a/mm/nommu.c b/mm/nommu.c
index 79c3cac87af..4a852f6c570 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -13,8 +13,11 @@
* Copyright (c) 2007-2010 Paul Mundt <lethal@linux-sh.org>
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/export.h>
#include <linux/mm.h>
+#include <linux/vmacache.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/file.h>
@@ -24,11 +27,14 @@
#include <linux/vmalloc.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
+#include <linux/compiler.h>
#include <linux/mount.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/audit.h>
+#include <linux/sched/sysctl.h>
+#include <linux/printk.h>
#include <asm/uaccess.h>
#include <asm/tlb.h>
@@ -55,13 +61,15 @@
void *high_memory;
struct page *mem_map;
unsigned long max_mapnr;
-unsigned long num_physpages;
unsigned long highest_memmap_pfn;
struct percpu_counter vm_committed_as;
int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
int sysctl_overcommit_ratio = 50; /* default is 50% */
+unsigned long sysctl_overcommit_kbytes __read_mostly;
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;
@@ -82,7 +90,6 @@ unsigned long vm_memory_committed(void)
EXPORT_SYMBOL_GPL(vm_memory_committed);
EXPORT_SYMBOL(mem_map);
-EXPORT_SYMBOL(num_physpages);
/* list of mapped, potentially shareable regions */
static struct kmem_cache *vm_region_jar;
@@ -139,10 +146,10 @@ unsigned int kobjsize(const void *objp)
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;
@@ -189,9 +196,10 @@ finish_or_fault:
* 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;
@@ -226,8 +234,7 @@ 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)
{
@@ -279,6 +286,10 @@ EXPORT_SYMBOL(vmalloc_to_pfn);
long vread(char *buf, char *addr, unsigned long count)
{
+ /* Don't allow overflow */
+ if ((unsigned long) buf + count < count)
+ count = -(unsigned long) buf;
+
memcpy(buf, addr, count);
return count;
}
@@ -290,7 +301,7 @@ long vwrite(char *buf, char *addr, unsigned long count)
count = -(unsigned long) addr;
memcpy(addr, buf, count);
- return(count);
+ return count;
}
/*
@@ -453,7 +464,7 @@ EXPORT_SYMBOL_GPL(vm_unmap_aliases);
* Implement a stub for vmalloc_sync_all() if the architecture chose not to
* have one.
*/
-void __attribute__((weak)) vmalloc_sync_all(void)
+void __weak vmalloc_sync_all(void)
{
}
@@ -762,16 +773,23 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
*/
static void delete_vma_from_mm(struct vm_area_struct *vma)
{
+ int i;
struct address_space *mapping;
struct mm_struct *mm = vma->vm_mm;
+ struct task_struct *curr = current;
kenter("%p", vma);
protect_vma(vma, 0);
mm->map_count--;
- if (mm->mmap_cache == vma)
- mm->mmap_cache = NULL;
+ for (i = 0; i < VMACACHE_SIZE; i++) {
+ /* if the vma is cached, invalidate the entire cache */
+ if (curr->vmacache[i] == vma) {
+ vmacache_invalidate(mm);
+ break;
+ }
+ }
/* remove the VMA from the mapping */
if (vma->vm_file) {
@@ -819,8 +837,8 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
struct vm_area_struct *vma;
/* check the cache first */
- vma = mm->mmap_cache;
- if (vma && vma->vm_start <= addr && vma->vm_end > addr)
+ vma = vmacache_find(mm, addr);
+ if (likely(vma))
return vma;
/* trawl the list (there may be multiple mappings in which addr
@@ -829,7 +847,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
if (vma->vm_start > addr)
return NULL;
if (vma->vm_end > addr) {
- mm->mmap_cache = vma;
+ vmacache_update(addr, vma);
return vma;
}
}
@@ -868,8 +886,8 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
unsigned long end = addr + len;
/* check the cache first */
- vma = mm->mmap_cache;
- if (vma && vma->vm_start == addr && vma->vm_end == end)
+ vma = vmacache_find_exact(mm, addr, end);
+ if (vma)
return vma;
/* trawl the list (there may be multiple mappings in which addr
@@ -880,7 +898,7 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
if (vma->vm_start > addr)
return NULL;
if (vma->vm_end == end) {
- mm->mmap_cache = vma;
+ vmacache_update(addr, vma);
return vma;
}
}
@@ -932,7 +950,7 @@ static int validate_mmap_request(struct file *file,
struct address_space *mapping;
/* files must support mmap */
- if (!file->f_op || !file->f_op->mmap)
+ if (!file->f_op->mmap)
return -ENODEV;
/* work out if what we've got could possibly be shared
@@ -941,7 +959,7 @@ static int validate_mmap_request(struct file *file,
*/
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)
@@ -950,7 +968,7 @@ static int validate_mmap_request(struct file *file,
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;
@@ -985,11 +1003,11 @@ static int validate_mmap_request(struct file *file,
!(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))
return -EAGAIN;
if (!(capabilities & BDI_CAP_MAP_DIRECT))
@@ -997,8 +1015,7 @@ static int validate_mmap_request(struct file *file,
/* we mustn't privatise shared mappings */
capabilities &= ~BDI_CAP_MAP_COPY;
- }
- else {
+ } else {
/* we're going to read the file into private memory we
* allocate */
if (!(capabilities & BDI_CAP_MAP_COPY))
@@ -1029,23 +1046,20 @@ static int validate_mmap_request(struct file *file,
if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) {
if (prot & PROT_EXEC)
return -EPERM;
- }
- else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) {
+ } else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) {
/* handle implication of PROT_EXEC by PROT_READ */
if (current->personality & READ_IMPLIES_EXEC) {
if (capabilities & BDI_CAP_EXEC_MAP)
prot |= PROT_EXEC;
}
- }
- else if ((prot & PROT_READ) &&
+ } else if ((prot & PROT_READ) &&
(prot & PROT_EXEC) &&
!(capabilities & BDI_CAP_EXEC_MAP)
) {
/* backing file is not executable, try to copy */
capabilities &= ~BDI_CAP_MAP_DIRECT;
}
- }
- else {
+ } else {
/* anonymous mappings are always memory backed and can be
* privately mapped
*/
@@ -1235,7 +1249,7 @@ error_free:
return ret;
enomem:
- printk("Allocation of length %lu from process %d (%s) failed\n",
+ pr_err("Allocation of length %lu from process %d (%s) failed\n",
len, current->pid, current->comm);
show_free_areas(0);
return -ENOMEM;
@@ -1249,7 +1263,8 @@ unsigned long do_mmap_pgoff(struct file *file,
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;
@@ -1259,6 +1274,8 @@ unsigned long do_mmap_pgoff(struct file *file,
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,
@@ -1322,8 +1339,8 @@ unsigned long do_mmap_pgoff(struct file *file,
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)
@@ -1650,7 +1667,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
/* find the first potentially overlapping VMA */
vma = find_vma(mm, start);
if (!vma) {
- static int limit = 0;
+ static int limit;
if (limit < 5) {
printk(KERN_WARNING
"munmap of memory not mmapped by process %d"
@@ -1765,7 +1782,7 @@ 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)
{
@@ -1800,7 +1817,6 @@ 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,
@@ -1814,9 +1830,11 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
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;
}
@@ -1831,6 +1849,16 @@ 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)
{
@@ -1852,10 +1880,6 @@ unsigned long arch_get_unmapped_area(struct file *file, unsigned long addr,
return -ENOMEM;
}
-void arch_unmap_area(struct mm_struct *mm, unsigned long addr)
-{
-}
-
void unmap_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen,
int even_cows)
@@ -1881,7 +1905,7 @@ 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);
@@ -1903,7 +1927,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
*/
free -= global_page_state(NR_SHMEM);
- free += nr_swap_pages;
+ free += get_nr_swap_pages();
/*
* Any slabs which are created with the
@@ -1922,10 +1946,10 @@ 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;
@@ -1933,18 +1957,20 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
goto error;
}
- allowed = totalram_pages * sysctl_overcommit_ratio / 100;
+ allowed = vm_commit_limit();
/*
- * Leave the last 3% for root
+ * Reserve some 3% for root
*/
if (!cap_sys_admin)
- allowed -= allowed / 32;
- allowed += total_swap_pages;
+ allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
- /* 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;
@@ -1967,6 +1993,12 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
}
EXPORT_SYMBOL(filemap_fault);
+void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ BUG();
+}
+EXPORT_SYMBOL(filemap_map_pages);
+
int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr,
unsigned long size, pgoff_t pgoff)
{
@@ -2106,3 +2138,45 @@ 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)
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-09 12:33:23 +0000