#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/string.h>
+#include <linux/compiler.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 <linux/vmalloc.h>
+
+#include <asm/sections.h>
#include <asm/uaccess.h>
#include "internal.h"
-#define CREATE_TRACE_POINTS
-#include <trace/events/kmem.h>
+static inline int is_kernel_rodata(unsigned long addr)
+{
+ return addr >= (unsigned long)__start_rodata &&
+ addr < (unsigned long)__end_rodata;
+}
+
+/**
+ * kfree_const - conditionally free memory
+ * @x: pointer to the memory
+ *
+ * Function calls kfree only if @x is not in .rodata section.
+ */
+void kfree_const(const void *x)
+{
+ if (!is_kernel_rodata((unsigned long)x))
+ kfree(x);
+}
+EXPORT_SYMBOL(kfree_const);
/**
* kstrdup - allocate space for and copy an existing string
}
EXPORT_SYMBOL(kstrdup);
+/**
+ * kstrdup_const - conditionally duplicate an existing const string
+ * @s: the string to duplicate
+ * @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ *
+ * Function returns source string if it is in .rodata section otherwise it
+ * fallbacks to kstrdup.
+ * Strings allocated by kstrdup_const should be freed by kfree_const.
+ */
+const char *kstrdup_const(const char *s, gfp_t gfp)
+{
+ if (is_kernel_rodata((unsigned long)s))
+ return s;
+
+ return kstrdup(s, gfp);
+}
+EXPORT_SYMBOL(kstrdup_const);
+
/**
* kstrndup - allocate space for and copy an existing string
* @s: the string to duplicate
}
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
}
/* 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)
+int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t)
{
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();
- for_each_thread(task, t) {
- if (vm_is_stack_for_task(t, vma)) {
- ret = t->pid;
- goto done;
- }
- }
-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;
- mm->unmap_area = arch_unmap_area;
}
#endif
* If the architecture not support this function, simply return with no
* page pinned
*/
-int __attribute__((weak)) __get_user_pages_fast(unsigned long start,
+int __weak __get_user_pages_fast(unsigned long start,
int nr_pages, int write, struct page **pages)
{
return 0;
* 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 __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;
+ return get_user_pages_unlocked(current, mm, start, nr_pages,
+ write, 0, pages);
}
EXPORT_SYMBOL_GPL(get_user_pages_fast);
{
if (unlikely(offset + PAGE_ALIGN(len) < offset))
return -EINVAL;
- if (unlikely(offset & ~PAGE_MASK))
+ if (unlikely(offset_in_page(offset)))
return -EINVAL;
return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
}
EXPORT_SYMBOL(kvfree);
+static inline void *__page_rmapping(struct page *page)
+{
+ unsigned long mapping;
+
+ mapping = (unsigned long)page->mapping;
+ mapping &= ~PAGE_MAPPING_FLAGS;
+
+ return (void *)mapping;
+}
+
+/* Neutral page->mapping pointer to address_space or anon_vma or other */
+void *page_rmapping(struct page *page)
+{
+ page = compound_head(page);
+ return __page_rmapping(page);
+}
+
+struct anon_vma *page_anon_vma(struct page *page)
+{
+ unsigned long mapping;
+
+ page = compound_head(page);
+ mapping = (unsigned long)page->mapping;
+ if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
+ return NULL;
+ return __page_rmapping(page);
+}
+
struct address_space *page_mapping(struct page *page)
{
- struct address_space *mapping = page->mapping;
+ unsigned long mapping;
+
+ /* This happens if someone calls flush_dcache_page on slab page */
+ if (unlikely(PageSlab(page)))
+ return NULL;
- VM_BUG_ON(PageSlab(page));
-#ifdef CONFIG_SWAP
if (unlikely(PageSwapCache(page))) {
swp_entry_t entry;
entry.val = page_private(page);
- mapping = swap_address_space(entry);
- } else
-#endif
- if ((unsigned long)mapping & PAGE_MAPPING_ANON)
- mapping = NULL;
- return mapping;
+ return swap_address_space(entry);
+ }
+
+ mapping = (unsigned long)page->mapping;
+ if (mapping & PAGE_MAPPING_FLAGS)
+ return NULL;
+ return page->mapping;
}
-/* 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);
+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;
+}
+
+/**
+ * get_cmdline() - copy the cmdline value to a buffer.
+ * @task: the task whose cmdline value to copy.
+ * @buffer: the buffer to copy to.
+ * @buflen: the length of the buffer. Larger cmdline values are truncated
+ * to this length.
+ * Returns the size of the cmdline field copied. Note that the copy does
+ * not guarantee an ending NULL byte.
+ */
+int get_cmdline(struct task_struct *task, char *buffer, int buflen)
+{
+ int res = 0;
+ unsigned int len;
+ struct mm_struct *mm = get_task_mm(task);
+ if (!mm)
+ goto out;
+ if (!mm->arg_end)
+ goto out_mm; /* Shh! No looking before we're done */
+
+ len = mm->arg_end - mm->arg_start;
+
+ if (len > buflen)
+ len = buflen;
+
+ res = access_process_vm(task, mm->arg_start, buffer, len, 0);
+
+ /*
+ * If the nul at the end of args has been overwritten, then
+ * assume application is using setproctitle(3).
+ */
+ if (res > 0 && buffer[res-1] != '\0' && len < buflen) {
+ len = strnlen(buffer, res);
+ if (len < res) {
+ res = len;
+ } else {
+ len = mm->env_end - mm->env_start;
+ if (len > buflen - res)
+ len = buflen - res;
+ res += access_process_vm(task, mm->env_start,
+ buffer+res, len, 0);
+ res = strnlen(buffer, res);
+ }
+ }
+out_mm:
+ mmput(mm);
+out:
+ return res;
+}