mirror of
https://github.com/torvalds/linux.git
synced 2024-12-13 06:32:50 +00:00
49f0ce5f92
Some applications that run on HPC clusters are designed around the availability of RAM and the overcommit ratio is fine tuned to get the maximum usage of memory without swapping. With growing memory, the 1%-of-all-RAM grain provided by overcommit_ratio has become too coarse for these workload (on a 2TB machine it represents no less than 20GB). This patch adds the new overcommit_kbytes sysctl variable that allow a much finer grain. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix nommu build] Signed-off-by: Jerome Marchand <jmarchan@redhat.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
456 lines
11 KiB
C
456 lines
11 KiB
C
#include <linux/mm.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/string.h>
|
|
#include <linux/export.h>
|
|
#include <linux/err.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/security.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/swapops.h>
|
|
#include <linux/mman.h>
|
|
#include <linux/hugetlb.h>
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
#include "internal.h"
|
|
|
|
#define CREATE_TRACE_POINTS
|
|
#include <trace/events/kmem.h>
|
|
|
|
/**
|
|
* kstrdup - allocate space for and copy an existing string
|
|
* @s: the string to duplicate
|
|
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
|
|
*/
|
|
char *kstrdup(const char *s, gfp_t gfp)
|
|
{
|
|
size_t len;
|
|
char *buf;
|
|
|
|
if (!s)
|
|
return NULL;
|
|
|
|
len = strlen(s) + 1;
|
|
buf = kmalloc_track_caller(len, gfp);
|
|
if (buf)
|
|
memcpy(buf, s, len);
|
|
return buf;
|
|
}
|
|
EXPORT_SYMBOL(kstrdup);
|
|
|
|
/**
|
|
* kstrndup - allocate space for and copy an existing string
|
|
* @s: the string to duplicate
|
|
* @max: read at most @max chars from @s
|
|
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
|
|
*/
|
|
char *kstrndup(const char *s, size_t max, gfp_t gfp)
|
|
{
|
|
size_t len;
|
|
char *buf;
|
|
|
|
if (!s)
|
|
return NULL;
|
|
|
|
len = strnlen(s, max);
|
|
buf = kmalloc_track_caller(len+1, gfp);
|
|
if (buf) {
|
|
memcpy(buf, s, len);
|
|
buf[len] = '\0';
|
|
}
|
|
return buf;
|
|
}
|
|
EXPORT_SYMBOL(kstrndup);
|
|
|
|
/**
|
|
* kmemdup - duplicate region of memory
|
|
*
|
|
* @src: memory region to duplicate
|
|
* @len: memory region length
|
|
* @gfp: GFP mask to use
|
|
*/
|
|
void *kmemdup(const void *src, size_t len, gfp_t gfp)
|
|
{
|
|
void *p;
|
|
|
|
p = kmalloc_track_caller(len, gfp);
|
|
if (p)
|
|
memcpy(p, src, len);
|
|
return p;
|
|
}
|
|
EXPORT_SYMBOL(kmemdup);
|
|
|
|
/**
|
|
* memdup_user - duplicate memory region from user space
|
|
*
|
|
* @src: source address in user space
|
|
* @len: number of bytes to copy
|
|
*
|
|
* Returns an ERR_PTR() on failure.
|
|
*/
|
|
void *memdup_user(const void __user *src, size_t len)
|
|
{
|
|
void *p;
|
|
|
|
/*
|
|
* Always use GFP_KERNEL, since copy_from_user() can sleep and
|
|
* cause pagefault, which makes it pointless to use GFP_NOFS
|
|
* or GFP_ATOMIC.
|
|
*/
|
|
p = kmalloc_track_caller(len, GFP_KERNEL);
|
|
if (!p)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
if (copy_from_user(p, src, len)) {
|
|
kfree(p);
|
|
return ERR_PTR(-EFAULT);
|
|
}
|
|
|
|
return p;
|
|
}
|
|
EXPORT_SYMBOL(memdup_user);
|
|
|
|
static __always_inline void *__do_krealloc(const void *p, size_t new_size,
|
|
gfp_t flags)
|
|
{
|
|
void *ret;
|
|
size_t ks = 0;
|
|
|
|
if (p)
|
|
ks = ksize(p);
|
|
|
|
if (ks >= new_size)
|
|
return (void *)p;
|
|
|
|
ret = kmalloc_track_caller(new_size, flags);
|
|
if (ret && p)
|
|
memcpy(ret, p, ks);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/**
|
|
* __krealloc - like krealloc() but don't free @p.
|
|
* @p: object to reallocate memory for.
|
|
* @new_size: how many bytes of memory are required.
|
|
* @flags: the type of memory to allocate.
|
|
*
|
|
* This function is like krealloc() except it never frees the originally
|
|
* allocated buffer. Use this if you don't want to free the buffer immediately
|
|
* like, for example, with RCU.
|
|
*/
|
|
void *__krealloc(const void *p, size_t new_size, gfp_t flags)
|
|
{
|
|
if (unlikely(!new_size))
|
|
return ZERO_SIZE_PTR;
|
|
|
|
return __do_krealloc(p, new_size, flags);
|
|
|
|
}
|
|
EXPORT_SYMBOL(__krealloc);
|
|
|
|
/**
|
|
* krealloc - reallocate memory. The contents will remain unchanged.
|
|
* @p: object to reallocate memory for.
|
|
* @new_size: how many bytes of memory are required.
|
|
* @flags: the type of memory to allocate.
|
|
*
|
|
* The contents of the object pointed to are preserved up to the
|
|
* lesser of the new and old sizes. If @p is %NULL, krealloc()
|
|
* behaves exactly like kmalloc(). If @new_size is 0 and @p is not a
|
|
* %NULL pointer, the object pointed to is freed.
|
|
*/
|
|
void *krealloc(const void *p, size_t new_size, gfp_t flags)
|
|
{
|
|
void *ret;
|
|
|
|
if (unlikely(!new_size)) {
|
|
kfree(p);
|
|
return ZERO_SIZE_PTR;
|
|
}
|
|
|
|
ret = __do_krealloc(p, new_size, flags);
|
|
if (ret && p != ret)
|
|
kfree(p);
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(krealloc);
|
|
|
|
/**
|
|
* kzfree - like kfree but zero memory
|
|
* @p: object to free memory of
|
|
*
|
|
* The memory of the object @p points to is zeroed before freed.
|
|
* If @p is %NULL, kzfree() does nothing.
|
|
*
|
|
* Note: this function zeroes the whole allocated buffer which can be a good
|
|
* deal bigger than the requested buffer size passed to kmalloc(). So be
|
|
* careful when using this function in performance sensitive code.
|
|
*/
|
|
void kzfree(const void *p)
|
|
{
|
|
size_t ks;
|
|
void *mem = (void *)p;
|
|
|
|
if (unlikely(ZERO_OR_NULL_PTR(mem)))
|
|
return;
|
|
ks = ksize(mem);
|
|
memset(mem, 0, ks);
|
|
kfree(mem);
|
|
}
|
|
EXPORT_SYMBOL(kzfree);
|
|
|
|
/*
|
|
* strndup_user - duplicate an existing string from user space
|
|
* @s: The string to duplicate
|
|
* @n: Maximum number of bytes to copy, including the trailing NUL.
|
|
*/
|
|
char *strndup_user(const char __user *s, long n)
|
|
{
|
|
char *p;
|
|
long length;
|
|
|
|
length = strnlen_user(s, n);
|
|
|
|
if (!length)
|
|
return ERR_PTR(-EFAULT);
|
|
|
|
if (length > n)
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
p = memdup_user(s, length);
|
|
|
|
if (IS_ERR(p))
|
|
return p;
|
|
|
|
p[length - 1] = '\0';
|
|
|
|
return p;
|
|
}
|
|
EXPORT_SYMBOL(strndup_user);
|
|
|
|
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
|
|
struct vm_area_struct *prev, struct rb_node *rb_parent)
|
|
{
|
|
struct vm_area_struct *next;
|
|
|
|
vma->vm_prev = prev;
|
|
if (prev) {
|
|
next = prev->vm_next;
|
|
prev->vm_next = vma;
|
|
} else {
|
|
mm->mmap = vma;
|
|
if (rb_parent)
|
|
next = rb_entry(rb_parent,
|
|
struct vm_area_struct, vm_rb);
|
|
else
|
|
next = NULL;
|
|
}
|
|
vma->vm_next = next;
|
|
if (next)
|
|
next->vm_prev = vma;
|
|
}
|
|
|
|
/* Check if the vma is being used as a stack by this task */
|
|
static int vm_is_stack_for_task(struct task_struct *t,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
|
|
}
|
|
|
|
/*
|
|
* Check if the vma is being used as a stack.
|
|
* If is_group is non-zero, check in the entire thread group or else
|
|
* just check in the current task. Returns the pid of the task that
|
|
* the vma is stack for.
|
|
*/
|
|
pid_t vm_is_stack(struct task_struct *task,
|
|
struct vm_area_struct *vma, int in_group)
|
|
{
|
|
pid_t ret = 0;
|
|
|
|
if (vm_is_stack_for_task(task, vma))
|
|
return task->pid;
|
|
|
|
if (in_group) {
|
|
struct task_struct *t;
|
|
rcu_read_lock();
|
|
if (!pid_alive(task))
|
|
goto done;
|
|
|
|
t = task;
|
|
do {
|
|
if (vm_is_stack_for_task(t, vma)) {
|
|
ret = t->pid;
|
|
goto done;
|
|
}
|
|
} while_each_thread(task, t);
|
|
done:
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
#if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
|
|
void arch_pick_mmap_layout(struct mm_struct *mm)
|
|
{
|
|
mm->mmap_base = TASK_UNMAPPED_BASE;
|
|
mm->get_unmapped_area = arch_get_unmapped_area;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Like get_user_pages_fast() except its IRQ-safe in that it won't fall
|
|
* back to the regular GUP.
|
|
* If the architecture not support this function, simply return with no
|
|
* page pinned
|
|
*/
|
|
int __attribute__((weak)) __get_user_pages_fast(unsigned long start,
|
|
int nr_pages, int write, struct page **pages)
|
|
{
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__get_user_pages_fast);
|
|
|
|
/**
|
|
* get_user_pages_fast() - pin user pages in memory
|
|
* @start: starting user address
|
|
* @nr_pages: number of pages from start to pin
|
|
* @write: whether pages will be written to
|
|
* @pages: array that receives pointers to the pages pinned.
|
|
* Should be at least nr_pages long.
|
|
*
|
|
* Returns number of pages pinned. This may be fewer than the number
|
|
* requested. If nr_pages is 0 or negative, returns 0. If no pages
|
|
* were pinned, returns -errno.
|
|
*
|
|
* get_user_pages_fast provides equivalent functionality to get_user_pages,
|
|
* operating on current and current->mm, with force=0 and vma=NULL. However
|
|
* unlike get_user_pages, it must be called without mmap_sem held.
|
|
*
|
|
* get_user_pages_fast may take mmap_sem and page table locks, so no
|
|
* assumptions can be made about lack of locking. get_user_pages_fast is to be
|
|
* implemented in a way that is advantageous (vs get_user_pages()) when the
|
|
* user memory area is already faulted in and present in ptes. However if the
|
|
* pages have to be faulted in, it may turn out to be slightly slower so
|
|
* callers need to carefully consider what to use. On many architectures,
|
|
* get_user_pages_fast simply falls back to get_user_pages.
|
|
*/
|
|
int __attribute__((weak)) get_user_pages_fast(unsigned long start,
|
|
int nr_pages, int write, struct page **pages)
|
|
{
|
|
struct mm_struct *mm = current->mm;
|
|
int ret;
|
|
|
|
down_read(&mm->mmap_sem);
|
|
ret = get_user_pages(current, mm, start, nr_pages,
|
|
write, 0, pages, NULL);
|
|
up_read(&mm->mmap_sem);
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(get_user_pages_fast);
|
|
|
|
unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
|
|
unsigned long len, unsigned long prot,
|
|
unsigned long flag, unsigned long pgoff)
|
|
{
|
|
unsigned long ret;
|
|
struct mm_struct *mm = current->mm;
|
|
unsigned long populate;
|
|
|
|
ret = security_mmap_file(file, prot, flag);
|
|
if (!ret) {
|
|
down_write(&mm->mmap_sem);
|
|
ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
|
|
&populate);
|
|
up_write(&mm->mmap_sem);
|
|
if (populate)
|
|
mm_populate(ret, populate);
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
unsigned long vm_mmap(struct file *file, unsigned long addr,
|
|
unsigned long len, unsigned long prot,
|
|
unsigned long flag, unsigned long offset)
|
|
{
|
|
if (unlikely(offset + PAGE_ALIGN(len) < offset))
|
|
return -EINVAL;
|
|
if (unlikely(offset & ~PAGE_MASK))
|
|
return -EINVAL;
|
|
|
|
return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
|
|
}
|
|
EXPORT_SYMBOL(vm_mmap);
|
|
|
|
struct address_space *page_mapping(struct page *page)
|
|
{
|
|
struct address_space *mapping = page->mapping;
|
|
|
|
/* This happens if someone calls flush_dcache_page on slab page */
|
|
if (unlikely(PageSlab(page)))
|
|
return NULL;
|
|
|
|
if (unlikely(PageSwapCache(page))) {
|
|
swp_entry_t entry;
|
|
|
|
entry.val = page_private(page);
|
|
mapping = swap_address_space(entry);
|
|
} else if ((unsigned long)mapping & PAGE_MAPPING_ANON)
|
|
mapping = NULL;
|
|
return mapping;
|
|
}
|
|
|
|
int overcommit_ratio_handler(struct ctl_table *table, int write,
|
|
void __user *buffer, size_t *lenp,
|
|
loff_t *ppos)
|
|
{
|
|
int ret;
|
|
|
|
ret = proc_dointvec(table, write, buffer, lenp, ppos);
|
|
if (ret == 0 && write)
|
|
sysctl_overcommit_kbytes = 0;
|
|
return ret;
|
|
}
|
|
|
|
int overcommit_kbytes_handler(struct ctl_table *table, int write,
|
|
void __user *buffer, size_t *lenp,
|
|
loff_t *ppos)
|
|
{
|
|
int ret;
|
|
|
|
ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
|
|
if (ret == 0 && write)
|
|
sysctl_overcommit_ratio = 0;
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
|
|
*/
|
|
unsigned long vm_commit_limit(void)
|
|
{
|
|
unsigned long allowed;
|
|
|
|
if (sysctl_overcommit_kbytes)
|
|
allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10);
|
|
else
|
|
allowed = ((totalram_pages - hugetlb_total_pages())
|
|
* sysctl_overcommit_ratio / 100);
|
|
allowed += total_swap_pages;
|
|
|
|
return allowed;
|
|
}
|
|
|
|
|
|
/* Tracepoints definitions. */
|
|
EXPORT_TRACEPOINT_SYMBOL(kmalloc);
|
|
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
|
|
EXPORT_TRACEPOINT_SYMBOL(kmalloc_node);
|
|
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc_node);
|
|
EXPORT_TRACEPOINT_SYMBOL(kfree);
|
|
EXPORT_TRACEPOINT_SYMBOL(kmem_cache_free);
|