linux/mm/util.c

// SPDX-License-Identifier: GPL-2.0-only
#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/sched/mm.h>
#include <linux/sched/signal.h>
#include <linux/sched/task_stack.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 <linux/userfaultfd_k.h>
#include <linux/elf.h>
#include <linux/elf-randomize.h>
#include <linux/personality.h>
#include <linux/random.h>
#include <linux/processor.h>
#include <linux/sizes.h>
#include <linux/compat.h>

#include <linux/uaccess.h>

#include <kunit/visibility.h>

#include "internal.h"
#include "swap.h"

/**
 * 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)
{ … }
EXPORT_SYMBOL(…);

/**
 * 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
 *
 * Return: newly allocated copy of @s or %NULL in case of error
 */
noinline
char *kstrdup(const char *s, gfp_t gfp)
{ … }
EXPORT_SYMBOL(…);

/**
 * 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
 *
 * Note: Strings allocated by kstrdup_const should be freed by kfree_const and
 * must not be passed to krealloc().
 *
 * Return: source string if it is in .rodata section otherwise
 * fallback to kstrdup.
 */
const char *kstrdup_const(const char *s, gfp_t gfp)
{ … }
EXPORT_SYMBOL(…);

/**
 * 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
 *
 * Note: Use kmemdup_nul() instead if the size is known exactly.
 *
 * Return: newly allocated copy of @s or %NULL in case of error
 */
char *kstrndup(const char *s, size_t max, gfp_t gfp)
{ … }
EXPORT_SYMBOL(…);

/**
 * kmemdup - duplicate region of memory
 *
 * @src: memory region to duplicate
 * @len: memory region length
 * @gfp: GFP mask to use
 *
 * Return: newly allocated copy of @src or %NULL in case of error,
 * result is physically contiguous. Use kfree() to free.
 */
void *kmemdup_noprof(const void *src, size_t len, gfp_t gfp)
{ … }
EXPORT_SYMBOL(…);

/**
 * kmemdup_array - duplicate a given array.
 *
 * @src: array to duplicate.
 * @count: number of elements to duplicate from array.
 * @element_size: size of each element of array.
 * @gfp: GFP mask to use.
 *
 * Return: duplicated array of @src or %NULL in case of error,
 * result is physically contiguous. Use kfree() to free.
 */
void *kmemdup_array(const void *src, size_t count, size_t element_size, gfp_t gfp)
{ … }
EXPORT_SYMBOL(…);

/**
 * kvmemdup - duplicate region of memory
 *
 * @src: memory region to duplicate
 * @len: memory region length
 * @gfp: GFP mask to use
 *
 * Return: newly allocated copy of @src or %NULL in case of error,
 * result may be not physically contiguous. Use kvfree() to free.
 */
void *kvmemdup(const void *src, size_t len, gfp_t gfp)
{ … }
EXPORT_SYMBOL(…);

/**
 * kmemdup_nul - Create a NUL-terminated string from unterminated data
 * @s: The data to stringify
 * @len: The size of the data
 * @gfp: the GFP mask used in the kmalloc() call when allocating memory
 *
 * Return: newly allocated copy of @s with NUL-termination or %NULL in
 * case of error
 */
char *kmemdup_nul(const char *s, size_t len, gfp_t gfp)
{ … }
EXPORT_SYMBOL(…);

static kmem_buckets *user_buckets __ro_after_init;

static int __init init_user_buckets(void)
{ … }
subsys_initcall(init_user_buckets);

/**
 * memdup_user - duplicate memory region from user space
 *
 * @src: source address in user space
 * @len: number of bytes to copy
 *
 * Return: an ERR_PTR() on failure.  Result is physically
 * contiguous, to be freed by kfree().
 */
void *memdup_user(const void __user *src, size_t len)
{ … }
EXPORT_SYMBOL(…);

/**
 * vmemdup_user - duplicate memory region from user space
 *
 * @src: source address in user space
 * @len: number of bytes to copy
 *
 * Return: an ERR_PTR() on failure.  Result may be not
 * physically contiguous.  Use kvfree() to free.
 */
void *vmemdup_user(const void __user *src, size_t len)
{ … }
EXPORT_SYMBOL(…);

/**
 * 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.
 *
 * Return: newly allocated copy of @s or an ERR_PTR() in case of error
 */
char *strndup_user(const char __user *s, long n)
{ … }
EXPORT_SYMBOL(…);

/**
 * memdup_user_nul - duplicate memory region from user space and NUL-terminate
 *
 * @src: source address in user space
 * @len: number of bytes to copy
 *
 * Return: an ERR_PTR() on failure.
 */
void *memdup_user_nul(const void __user *src, size_t len)
{ … }
EXPORT_SYMBOL(…);

/* Check if the vma is being used as a stack by this task */
int vma_is_stack_for_current(struct vm_area_struct *vma)
{ … }

/*
 * Change backing file, only valid to use during initial VMA setup.
 */
void vma_set_file(struct vm_area_struct *vma, struct file *file)
{ … }
EXPORT_SYMBOL(…);

#ifndef STACK_RND_MASK
#define STACK_RND_MASK …
#endif

unsigned long randomize_stack_top(unsigned long stack_top)
{ … }

/**
 * randomize_page - Generate a random, page aligned address
 * @start:	The smallest acceptable address the caller will take.
 * @range:	The size of the area, starting at @start, within which the
 *		random address must fall.
 *
 * If @start + @range would overflow, @range is capped.
 *
 * NOTE: Historical use of randomize_range, which this replaces, presumed that
 * @start was already page aligned.  We now align it regardless.
 *
 * Return: A page aligned address within [start, start + range).  On error,
 * @start is returned.
 */
unsigned long randomize_page(unsigned long start, unsigned long range)
{ … }

#ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
unsigned long __weak arch_randomize_brk(struct mm_struct *mm)
{
	/* Is the current task 32bit ? */
	if (!IS_ENABLED(CONFIG_64BIT) || is_compat_task())
		return randomize_page(mm->brk, SZ_32M);

	return randomize_page(mm->brk, SZ_1G);
}

unsigned long arch_mmap_rnd(void)
{
	unsigned long rnd;

#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
	if (is_compat_task())
		rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
	else
#endif /* CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS */
		rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);

	return rnd << PAGE_SHIFT;
}

static int mmap_is_legacy(struct rlimit *rlim_stack)
{
	if (current->personality & ADDR_COMPAT_LAYOUT)
		return 1;

	/* On parisc the stack always grows up - so a unlimited stack should
	 * not be an indicator to use the legacy memory layout. */
	if (rlim_stack->rlim_cur == RLIM_INFINITY &&
		!IS_ENABLED(CONFIG_STACK_GROWSUP))
		return 1;

	return sysctl_legacy_va_layout;
}

/*
 * Leave enough space between the mmap area and the stack to honour ulimit in
 * the face of randomisation.
 */
#define MIN_GAP …
#define MAX_GAP …

static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
{
#ifdef CONFIG_STACK_GROWSUP
	/*
	 * For an upwards growing stack the calculation is much simpler.
	 * Memory for the maximum stack size is reserved at the top of the
	 * task. mmap_base starts directly below the stack and grows
	 * downwards.
	 */
	return PAGE_ALIGN_DOWN(mmap_upper_limit(rlim_stack) - rnd);
#else
	unsigned long gap = rlim_stack->rlim_cur;
	unsigned long pad = stack_guard_gap;

	/* Account for stack randomization if necessary */
	if (current->flags & PF_RANDOMIZE)
		pad += (STACK_RND_MASK << PAGE_SHIFT);

	/* Values close to RLIM_INFINITY can overflow. */
	if (gap + pad > gap)
		gap += pad;

	if (gap < MIN_GAP)
		gap = MIN_GAP;
	else if (gap > MAX_GAP)
		gap = MAX_GAP;

	return PAGE_ALIGN(STACK_TOP - gap - rnd);
#endif
}

void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
{
	unsigned long random_factor = 0UL;

	if (current->flags & PF_RANDOMIZE)
		random_factor = arch_mmap_rnd();

	if (mmap_is_legacy(rlim_stack)) {
		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
		clear_bit(MMF_TOPDOWN, &mm->flags);
	} else {
		mm->mmap_base = mmap_base(random_factor, rlim_stack);
		set_bit(MMF_TOPDOWN, &mm->flags);
	}
}
#elif defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
{
	mm->mmap_base = TASK_UNMAPPED_BASE;
	clear_bit(MMF_TOPDOWN, &mm->flags);
}
#endif
#ifdef CONFIG_MMU
EXPORT_SYMBOL_IF_KUNIT(…);
#endif

/**
 * __account_locked_vm - account locked pages to an mm's locked_vm
 * @mm:          mm to account against
 * @pages:       number of pages to account
 * @inc:         %true if @pages should be considered positive, %false if not
 * @task:        task used to check RLIMIT_MEMLOCK
 * @bypass_rlim: %true if checking RLIMIT_MEMLOCK should be skipped
 *
 * Assumes @task and @mm are valid (i.e. at least one reference on each), and
 * that mmap_lock is held as writer.
 *
 * Return:
 * * 0       on success
 * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded.
 */
int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
			struct task_struct *task, bool bypass_rlim)
{ … }
EXPORT_SYMBOL_GPL(…);

/**
 * account_locked_vm - account locked pages to an mm's locked_vm
 * @mm:          mm to account against, may be NULL
 * @pages:       number of pages to account
 * @inc:         %true if @pages should be considered positive, %false if not
 *
 * Assumes a non-NULL @mm is valid (i.e. at least one reference on it).
 *
 * Return:
 * * 0       on success, or if mm is NULL
 * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded.
 */
int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc)
{ … }
EXPORT_SYMBOL_GPL(…);

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 vm_mmap(struct file *file, unsigned long addr,
	unsigned long len, unsigned long prot,
	unsigned long flag, unsigned long offset)
{ … }
EXPORT_SYMBOL(…);

/**
 * __kvmalloc_node - attempt to allocate physically contiguous memory, but upon
 * failure, fall back to non-contiguous (vmalloc) allocation.
 * @size: size of the request.
 * @b: which set of kmalloc buckets to allocate from.
 * @flags: gfp mask for the allocation - must be compatible (superset) with GFP_KERNEL.
 * @node: numa node to allocate from
 *
 * Uses kmalloc to get the memory but if the allocation fails then falls back
 * to the vmalloc allocator. Use kvfree for freeing the memory.
 *
 * GFP_NOWAIT and GFP_ATOMIC are not supported, neither is the __GFP_NORETRY modifier.
 * __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is
 * preferable to the vmalloc fallback, due to visible performance drawbacks.
 *
 * Return: pointer to the allocated memory of %NULL in case of failure
 */
void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node)
{ … }
EXPORT_SYMBOL(…);

/**
 * kvfree() - Free memory.
 * @addr: Pointer to allocated memory.
 *
 * kvfree frees memory allocated by any of vmalloc(), kmalloc() or kvmalloc().
 * It is slightly more efficient to use kfree() or vfree() if you are certain
 * that you know which one to use.
 *
 * Context: Either preemptible task context or not-NMI interrupt.
 */
void kvfree(const void *addr)
{ … }
EXPORT_SYMBOL(…);

/**
 * kvfree_sensitive - Free a data object containing sensitive information.
 * @addr: address of the data object to be freed.
 * @len: length of the data object.
 *
 * Use the special memzero_explicit() function to clear the content of a
 * kvmalloc'ed object containing sensitive data to make sure that the
 * compiler won't optimize out the data clearing.
 */
void kvfree_sensitive(const void *addr, size_t len)
{ … }
EXPORT_SYMBOL(…);

void *kvrealloc_noprof(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
{ … }
EXPORT_SYMBOL(…);

/**
 * __vmalloc_array - allocate memory for a virtually contiguous array.
 * @n: number of elements.
 * @size: element size.
 * @flags: the type of memory to allocate (see kmalloc).
 */
void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags)
{ … }
EXPORT_SYMBOL(…);

/**
 * vmalloc_array - allocate memory for a virtually contiguous array.
 * @n: number of elements.
 * @size: element size.
 */
void *vmalloc_array_noprof(size_t n, size_t size)
{ … }
EXPORT_SYMBOL(…);

/**
 * __vcalloc - allocate and zero memory for a virtually contiguous array.
 * @n: number of elements.
 * @size: element size.
 * @flags: the type of memory to allocate (see kmalloc).
 */
void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags)
{ … }
EXPORT_SYMBOL(…);

/**
 * vcalloc - allocate and zero memory for a virtually contiguous array.
 * @n: number of elements.
 * @size: element size.
 */
void *vcalloc_noprof(size_t n, size_t size)
{ … }
EXPORT_SYMBOL(…);

struct anon_vma *folio_anon_vma(struct folio *folio)
{ … }

/**
 * folio_mapping - Find the mapping where this folio is stored.
 * @folio: The folio.
 *
 * For folios which are in the page cache, return the mapping that this
 * page belongs to.  Folios in the swap cache return the swap mapping
 * this page is stored in (which is different from the mapping for the
 * swap file or swap device where the data is stored).
 *
 * You can call this for folios which aren't in the swap cache or page
 * cache and it will return NULL.
 */
struct address_space *folio_mapping(struct folio *folio)
{ … }
EXPORT_SYMBOL(…);

/**
 * folio_copy - Copy the contents of one folio to another.
 * @dst: Folio to copy to.
 * @src: Folio to copy from.
 *
 * The bytes in the folio represented by @src are copied to @dst.
 * Assumes the caller has validated that @dst is at least as large as @src.
 * Can be called in atomic context for order-0 folios, but if the folio is
 * larger, it may sleep.
 */
void folio_copy(struct folio *dst, struct folio *src)
{ … }
EXPORT_SYMBOL(…);

int folio_mc_copy(struct folio *dst, struct folio *src)
{ … }
EXPORT_SYMBOL(…);

int sysctl_overcommit_memory __read_mostly = …;
int sysctl_overcommit_ratio __read_mostly = …;
unsigned long sysctl_overcommit_kbytes __read_mostly;
int sysctl_max_map_count __read_mostly = …;
unsigned long sysctl_user_reserve_kbytes __read_mostly = …; /* 128MB */
unsigned long sysctl_admin_reserve_kbytes __read_mostly = …; /* 8MB */

int overcommit_ratio_handler(const struct ctl_table *table, int write, void *buffer,
		size_t *lenp, loff_t *ppos)
{ … }

static void sync_overcommit_as(struct work_struct *dummy)
{ … }

int overcommit_policy_handler(const struct ctl_table *table, int write, void *buffer,
		size_t *lenp, loff_t *ppos)
{ … }

int overcommit_kbytes_handler(const struct ctl_table *table, int write, void *buffer,
		size_t *lenp, loff_t *ppos)
{ … }

/*
 * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
 */
unsigned long vm_commit_limit(void)
{ … }

/*
 * Make sure vm_committed_as in one cacheline and not cacheline shared with
 * other variables. It can be updated by several CPUs frequently.
 */
struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp;

/*
 * 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.
 *
 * The time cost of this is very low for small platforms, and for big
 * platform like a 2S/36C/72T Skylake server, in worst case where
 * vm_committed_as's spinlock is under severe contention, the time cost
 * could be about 30~40 microseconds.
 */
unsigned long vm_memory_committed(void)
{ … }
EXPORT_SYMBOL_GPL(…);

/*
 * Check that a process has enough memory to allocate a new virtual
 * mapping. 0 means there is enough memory for the allocation to
 * succeed and -ENOMEM implies there is not.
 *
 * We currently support three overcommit policies, which are set via the
 * vm.overcommit_memory sysctl.  See Documentation/mm/overcommit-accounting.rst
 *
 * Strict overcommit modes added 2002 Feb 26 by Alan Cox.
 * Additional code 2002 Jul 20 by Robert Love.
 *
 * cap_sys_admin is 1 if the process has admin privileges, 0 otherwise.
 *
 * Note this is a helper function intended to be used by LSMs which
 * wish to use this logic.
 */
int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
{ … }

/**
 * 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.
 *
 * Return: 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 __weak memcmp_pages(struct page *page1, struct page *page2)
{ … }

#ifdef CONFIG_PRINTK
/**
 * mem_dump_obj - Print available provenance information
 * @object: object for which to find provenance information.
 *
 * This function uses pr_cont(), so that the caller is expected to have
 * printed out whatever preamble is appropriate.  The provenance information
 * depends on the type of object and on how much debugging is enabled.
 * For example, for a slab-cache object, the slab name is printed, and,
 * if available, the return address and stack trace from the allocation
 * and last free path of that object.
 */
void mem_dump_obj(void *object)
{ … }
EXPORT_SYMBOL_GPL(…);
#endif

/*
 * A driver might set a page logically offline -- PageOffline() -- and
 * turn the page inaccessible in the hypervisor; after that, access to page
 * content can be fatal.
 *
 * Some special PFN walkers -- i.e., /proc/kcore -- read content of random
 * pages after checking PageOffline(); however, these PFN walkers can race
 * with drivers that set PageOffline().
 *
 * page_offline_freeze()/page_offline_thaw() allows for a subsystem to
 * synchronize with such drivers, achieving that a page cannot be set
 * PageOffline() while frozen.
 *
 * page_offline_begin()/page_offline_end() is used by drivers that care about
 * such races when setting a page PageOffline().
 */
static DECLARE_RWSEM(page_offline_rwsem);

void page_offline_freeze(void)
{ … }

void page_offline_thaw(void)
{ … }

void page_offline_begin(void)
{ … }
EXPORT_SYMBOL(…);

void page_offline_end(void)
{ … }
EXPORT_SYMBOL(…);

#ifndef flush_dcache_folio
void flush_dcache_folio(struct folio *folio)
{
	long i, nr = folio_nr_pages(folio);

	for (i = 0; i < nr; i++)
		flush_dcache_page(folio_page(folio, i));
}
EXPORT_SYMBOL(flush_dcache_folio);
#endif