linux/mm/mmap.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * mm/mmap.c
 *
 * Written by obz.
 *
 * Address space accounting code	<[email protected]>
 */

#define pr_fmt(fmt) …

#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/backing-dev.h>
#include <linux/mm.h>
#include <linux/mm_inline.h>
#include <linux/shm.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/syscalls.h>
#include <linux/capability.h>
#include <linux/init.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/hugetlb.h>
#include <linux/shmem_fs.h>
#include <linux/profile.h>
#include <linux/export.h>
#include <linux/mount.h>
#include <linux/mempolicy.h>
#include <linux/rmap.h>
#include <linux/mmu_notifier.h>
#include <linux/mmdebug.h>
#include <linux/perf_event.h>
#include <linux/audit.h>
#include <linux/khugepaged.h>
#include <linux/uprobes.h>
#include <linux/notifier.h>
#include <linux/memory.h>
#include <linux/printk.h>
#include <linux/userfaultfd_k.h>
#include <linux/moduleparam.h>
#include <linux/pkeys.h>
#include <linux/oom.h>
#include <linux/sched/mm.h>
#include <linux/ksm.h>

#include <linux/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/tlb.h>
#include <asm/mmu_context.h>

#define CREATE_TRACE_POINTS
#include <trace/events/mmap.h>

#include "internal.h"

#ifndef arch_mmap_check
#define arch_mmap_check(addr, len, flags) …
#endif

#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
const int mmap_rnd_bits_min = …;
int mmap_rnd_bits_max __ro_after_init = …;
int mmap_rnd_bits __read_mostly = …;
#endif
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
const int mmap_rnd_compat_bits_min = …;
const int mmap_rnd_compat_bits_max = …;
int mmap_rnd_compat_bits __read_mostly = …;
#endif

static bool ignore_rlimit_data;
core_param(…);

/* Update vma->vm_page_prot to reflect vma->vm_flags. */
void vma_set_page_prot(struct vm_area_struct *vma)
{ … }

/*
 * check_brk_limits() - Use platform specific check of range & verify mlock
 * limits.
 * @addr: The address to check
 * @len: The size of increase.
 *
 * Return: 0 on success.
 */
static int check_brk_limits(unsigned long addr, unsigned long len)
{ … }
static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *brkvma,
		unsigned long addr, unsigned long request, unsigned long flags);
SYSCALL_DEFINE1(brk, unsigned long, brk)
{ … }

/*
 * If a hint addr is less than mmap_min_addr change hint to be as
 * low as possible but still greater than mmap_min_addr
 */
static inline unsigned long round_hint_to_min(unsigned long hint)
{ … }

bool mlock_future_ok(struct mm_struct *mm, unsigned long flags,
			unsigned long bytes)
{ … }

static inline u64 file_mmap_size_max(struct file *file, struct inode *inode)
{ … }

static inline bool file_mmap_ok(struct file *file, struct inode *inode,
				unsigned long pgoff, unsigned long len)
{ … }

/*
 * The caller must write-lock current->mm->mmap_lock.
 */
unsigned long do_mmap(struct file *file, unsigned long addr,
			unsigned long len, unsigned long prot,
			unsigned long flags, vm_flags_t vm_flags,
			unsigned long pgoff, unsigned long *populate,
			struct list_head *uf)
{ … }

unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len,
			      unsigned long prot, unsigned long flags,
			      unsigned long fd, unsigned long pgoff)
{ … }

SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
		unsigned long, prot, unsigned long, flags,
		unsigned long, fd, unsigned long, pgoff)
{ … }

#ifdef __ARCH_WANT_SYS_OLD_MMAP
struct mmap_arg_struct {
	unsigned long addr;
	unsigned long len;
	unsigned long prot;
	unsigned long flags;
	unsigned long fd;
	unsigned long offset;
};

SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
{
	struct mmap_arg_struct a;

	if (copy_from_user(&a, arg, sizeof(a)))
		return -EFAULT;
	if (offset_in_page(a.offset))
		return -EINVAL;

	return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
			       a.offset >> PAGE_SHIFT);
}
#endif /* __ARCH_WANT_SYS_OLD_MMAP */

/*
 * We account for memory if it's a private writeable mapping,
 * not hugepages and VM_NORESERVE wasn't set.
 */
static inline bool accountable_mapping(struct file *file, vm_flags_t vm_flags)
{ … }

/**
 * unmapped_area() - Find an area between the low_limit and the high_limit with
 * the correct alignment and offset, all from @info. Note: current->mm is used
 * for the search.
 *
 * @info: The unmapped area information including the range [low_limit -
 * high_limit), the alignment offset and mask.
 *
 * Return: A memory address or -ENOMEM.
 */
static unsigned long unmapped_area(struct vm_unmapped_area_info *info)
{ … }

/**
 * unmapped_area_topdown() - Find an area between the low_limit and the
 * high_limit with the correct alignment and offset at the highest available
 * address, all from @info. Note: current->mm is used for the search.
 *
 * @info: The unmapped area information including the range [low_limit -
 * high_limit), the alignment offset and mask.
 *
 * Return: A memory address or -ENOMEM.
 */
static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
{ … }

/*
 * Determine if the allocation needs to ensure that there is no
 * existing mapping within it's guard gaps, for use as start_gap.
 */
static inline unsigned long stack_guard_placement(vm_flags_t vm_flags)
{ … }

/*
 * Search for an unmapped address range.
 *
 * We are looking for a range that:
 * - does not intersect with any VMA;
 * - is contained within the [low_limit, high_limit) interval;
 * - is at least the desired size.
 * - satisfies (begin_addr & align_mask) == (align_offset & align_mask)
 */
unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info)
{ … }

/* Get an address range which is currently unmapped.
 * For shmat() with addr=0.
 *
 * Ugly calling convention alert:
 * Return value with the low bits set means error value,
 * ie
 *	if (ret & ~PAGE_MASK)
 *		error = ret;
 *
 * This function "knows" that -ENOMEM has the bits set.
 */
unsigned long
generic_get_unmapped_area(struct file *filp, unsigned long addr,
			  unsigned long len, unsigned long pgoff,
			  unsigned long flags, vm_flags_t vm_flags)
{ … }

#ifndef HAVE_ARCH_UNMAPPED_AREA
unsigned long
arch_get_unmapped_area(struct file *filp, unsigned long addr,
		       unsigned long len, unsigned long pgoff,
		       unsigned long flags, vm_flags_t vm_flags)
{
	return generic_get_unmapped_area(filp, addr, len, pgoff, flags,
					 vm_flags);
}
#endif

/*
 * This mmap-allocator allocates new areas top-down from below the
 * stack's low limit (the base):
 */
unsigned long
generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
				  unsigned long len, unsigned long pgoff,
				  unsigned long flags, vm_flags_t vm_flags)
{ … }

#ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
unsigned long
arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
			       unsigned long len, unsigned long pgoff,
			       unsigned long flags, vm_flags_t vm_flags)
{
	return generic_get_unmapped_area_topdown(filp, addr, len, pgoff, flags,
						 vm_flags);
}
#endif

unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, struct file *filp,
					   unsigned long addr, unsigned long len,
					   unsigned long pgoff, unsigned long flags,
					   vm_flags_t vm_flags)
{ … }

unsigned long
__get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
		unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags)
{ … }

unsigned long
mm_get_unmapped_area(struct mm_struct *mm, struct file *file,
		     unsigned long addr, unsigned long len,
		     unsigned long pgoff, unsigned long flags)
{ … }
EXPORT_SYMBOL(…);

/**
 * find_vma_intersection() - Look up the first VMA which intersects the interval
 * @mm: The process address space.
 * @start_addr: The inclusive start user address.
 * @end_addr: The exclusive end user address.
 *
 * Returns: The first VMA within the provided range, %NULL otherwise.  Assumes
 * start_addr < end_addr.
 */
struct vm_area_struct *find_vma_intersection(struct mm_struct *mm,
					     unsigned long start_addr,
					     unsigned long end_addr)
{ … }
EXPORT_SYMBOL(…);

/**
 * find_vma() - Find the VMA for a given address, or the next VMA.
 * @mm: The mm_struct to check
 * @addr: The address
 *
 * Returns: The VMA associated with addr, or the next VMA.
 * May return %NULL in the case of no VMA at addr or above.
 */
struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
{ … }
EXPORT_SYMBOL(…);

/**
 * find_vma_prev() - Find the VMA for a given address, or the next vma and
 * set %pprev to the previous VMA, if any.
 * @mm: The mm_struct to check
 * @addr: The address
 * @pprev: The pointer to set to the previous VMA
 *
 * Note that RCU lock is missing here since the external mmap_lock() is used
 * instead.
 *
 * Returns: The VMA associated with @addr, or the next vma.
 * May return %NULL in the case of no vma at addr or above.
 */
struct vm_area_struct *
find_vma_prev(struct mm_struct *mm, unsigned long addr,
			struct vm_area_struct **pprev)
{ … }

/*
 * Verify that the stack growth is acceptable and
 * update accounting. This is shared with both the
 * grow-up and grow-down cases.
 */
static int acct_stack_growth(struct vm_area_struct *vma,
			     unsigned long size, unsigned long grow)
{ … }

#if defined(CONFIG_STACK_GROWSUP)
/*
 * PA-RISC uses this for its stack.
 * vma is the last one with address > vma->vm_end.  Have to extend vma.
 */
static int expand_upwards(struct vm_area_struct *vma, unsigned long address)
{
	struct mm_struct *mm = vma->vm_mm;
	struct vm_area_struct *next;
	unsigned long gap_addr;
	int error = 0;
	VMA_ITERATOR(vmi, mm, vma->vm_start);

	if (!(vma->vm_flags & VM_GROWSUP))
		return -EFAULT;

	/* Guard against exceeding limits of the address space. */
	address &= PAGE_MASK;
	if (address >= (TASK_SIZE & PAGE_MASK))
		return -ENOMEM;
	address += PAGE_SIZE;

	/* Enforce stack_guard_gap */
	gap_addr = address + stack_guard_gap;

	/* Guard against overflow */
	if (gap_addr < address || gap_addr > TASK_SIZE)
		gap_addr = TASK_SIZE;

	next = find_vma_intersection(mm, vma->vm_end, gap_addr);
	if (next && vma_is_accessible(next)) {
		if (!(next->vm_flags & VM_GROWSUP))
			return -ENOMEM;
		/* Check that both stack segments have the same anon_vma? */
	}

	if (next)
		vma_iter_prev_range_limit(&vmi, address);

	vma_iter_config(&vmi, vma->vm_start, address);
	if (vma_iter_prealloc(&vmi, vma))
		return -ENOMEM;

	/* We must make sure the anon_vma is allocated. */
	if (unlikely(anon_vma_prepare(vma))) {
		vma_iter_free(&vmi);
		return -ENOMEM;
	}

	/* Lock the VMA before expanding to prevent concurrent page faults */
	vma_start_write(vma);
	/*
	 * vma->vm_start/vm_end cannot change under us because the caller
	 * is required to hold the mmap_lock in read mode.  We need the
	 * anon_vma lock to serialize against concurrent expand_stacks.
	 */
	anon_vma_lock_write(vma->anon_vma);

	/* Somebody else might have raced and expanded it already */
	if (address > vma->vm_end) {
		unsigned long size, grow;

		size = address - vma->vm_start;
		grow = (address - vma->vm_end) >> PAGE_SHIFT;

		error = -ENOMEM;
		if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) {
			error = acct_stack_growth(vma, size, grow);
			if (!error) {
				/*
				 * We only hold a shared mmap_lock lock here, so
				 * we need to protect against concurrent vma
				 * expansions.  anon_vma_lock_write() doesn't
				 * help here, as we don't guarantee that all
				 * growable vmas in a mm share the same root
				 * anon vma.  So, we reuse mm->page_table_lock
				 * to guard against concurrent vma expansions.
				 */
				spin_lock(&mm->page_table_lock);
				if (vma->vm_flags & VM_LOCKED)
					mm->locked_vm += grow;
				vm_stat_account(mm, vma->vm_flags, grow);
				anon_vma_interval_tree_pre_update_vma(vma);
				vma->vm_end = address;
				/* Overwrite old entry in mtree. */
				vma_iter_store(&vmi, vma);
				anon_vma_interval_tree_post_update_vma(vma);
				spin_unlock(&mm->page_table_lock);

				perf_event_mmap(vma);
			}
		}
	}
	anon_vma_unlock_write(vma->anon_vma);
	vma_iter_free(&vmi);
	validate_mm(mm);
	return error;
}
#endif /* CONFIG_STACK_GROWSUP */

/*
 * vma is the first one with address < vma->vm_start.  Have to extend vma.
 * mmap_lock held for writing.
 */
int expand_downwards(struct vm_area_struct *vma, unsigned long address)
{ … }

/* enforced gap between the expanding stack and other mappings. */
unsigned long stack_guard_gap = …;

static int __init cmdline_parse_stack_guard_gap(char *p)
{ … }
__setup(…);

#ifdef CONFIG_STACK_GROWSUP
int expand_stack_locked(struct vm_area_struct *vma, unsigned long address)
{
	return expand_upwards(vma, address);
}

struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned long addr)
{
	struct vm_area_struct *vma, *prev;

	addr &= PAGE_MASK;
	vma = find_vma_prev(mm, addr, &prev);
	if (vma && (vma->vm_start <= addr))
		return vma;
	if (!prev)
		return NULL;
	if (expand_stack_locked(prev, addr))
		return NULL;
	if (prev->vm_flags & VM_LOCKED)
		populate_vma_page_range(prev, addr, prev->vm_end, NULL);
	return prev;
}
#else
int expand_stack_locked(struct vm_area_struct *vma, unsigned long address)
{ … }

struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned long addr)
{ … }
#endif

#if defined(CONFIG_STACK_GROWSUP)

#define vma_expand_up …
#define vma_expand_down …

#else

#define vma_expand_up(vma,addr) …
#define vma_expand_down(vma, addr) …

#endif

/*
 * expand_stack(): legacy interface for page faulting. Don't use unless
 * you have to.
 *
 * This is called with the mm locked for reading, drops the lock, takes
 * the lock for writing, tries to look up a vma again, expands it if
 * necessary, and downgrades the lock to reading again.
 *
 * If no vma is found or it can't be expanded, it returns NULL and has
 * dropped the lock.
 */
struct vm_area_struct *expand_stack(struct mm_struct *mm, unsigned long addr)
{ … }

/* do_munmap() - Wrapper function for non-maple tree aware do_munmap() calls.
 * @mm: The mm_struct
 * @start: The start address to munmap
 * @len: The length to be munmapped.
 * @uf: The userfaultfd list_head
 *
 * Return: 0 on success, error otherwise.
 */
int do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
	      struct list_head *uf)
{ … }

unsigned long mmap_region(struct file *file, unsigned long addr,
		unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
		struct list_head *uf)
{ … }

static int __vm_munmap(unsigned long start, size_t len, bool unlock)
{ … }

int vm_munmap(unsigned long start, size_t len)
{ … }
EXPORT_SYMBOL(…);

SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
{ … }


/*
 * Emulation of deprecated remap_file_pages() syscall.
 */
SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
		unsigned long, prot, unsigned long, pgoff, unsigned long, flags)
{ … }

/*
 * do_brk_flags() - Increase the brk vma if the flags match.
 * @vmi: The vma iterator
 * @addr: The start address
 * @len: The length of the increase
 * @vma: The vma,
 * @flags: The VMA Flags
 *
 * Extend the brk VMA from addr to addr + len.  If the VMA is NULL or the flags
 * do not match then create a new anonymous VMA.  Eventually we may be able to
 * do some brk-specific accounting here.
 */
static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
		unsigned long addr, unsigned long len, unsigned long flags)
{ … }

int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
{ … }
EXPORT_SYMBOL(…);

/* Release all mmaps. */
void exit_mmap(struct mm_struct *mm)
{ … }

/* Insert vm structure into process list sorted by address
 * and into the inode's i_mmap tree.  If vm_file is non-NULL
 * then i_mmap_rwsem is taken here.
 */
int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
{ … }

/*
 * Return true if the calling process may expand its vm space by the passed
 * number of pages
 */
bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages)
{ … }

void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages)
{ … }

static vm_fault_t special_mapping_fault(struct vm_fault *vmf);

/*
 * Close hook, called for unmap() and on the old vma for mremap().
 *
 * Having a close hook prevents vma merging regardless of flags.
 */
static void special_mapping_close(struct vm_area_struct *vma)
{ … }

static const char *special_mapping_name(struct vm_area_struct *vma)
{ … }

static int special_mapping_mremap(struct vm_area_struct *new_vma)
{ … }

static int special_mapping_split(struct vm_area_struct *vma, unsigned long addr)
{ … }

static const struct vm_operations_struct special_mapping_vmops = …;

static vm_fault_t special_mapping_fault(struct vm_fault *vmf)
{ … }

static struct vm_area_struct *__install_special_mapping(
	struct mm_struct *mm,
	unsigned long addr, unsigned long len,
	unsigned long vm_flags, void *priv,
	const struct vm_operations_struct *ops)
{ … }

bool vma_is_special_mapping(const struct vm_area_struct *vma,
	const struct vm_special_mapping *sm)
{ … }

/*
 * Called with mm->mmap_lock held for writing.
 * Insert a new vma covering the given region, with the given flags.
 * Its pages are supplied by the given array of struct page *.
 * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated.
 * The region past the last page supplied will always produce SIGBUS.
 * The array pointer and the pages it points to are assumed to stay alive
 * for as long as this mapping might exist.
 */
struct vm_area_struct *_install_special_mapping(
	struct mm_struct *mm,
	unsigned long addr, unsigned long len,
	unsigned long vm_flags, const struct vm_special_mapping *spec)
{ … }

/*
 * initialise the percpu counter for VM
 */
void __init mmap_init(void)
{ … }

/*
 * 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 init_user_reserve(void)
{ … }
subsys_initcall(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 init_admin_reserve(void)
{ … }
subsys_initcall(init_admin_reserve);

/*
 * Reinititalise user and admin reserves if memory is added or removed.
 *
 * The default user reserve max is 128MB, and the default max for the
 * admin reserve is 8MB. These are usually, but not always, enough to
 * enable recovery from a memory hogging process using login/sshd, a shell,
 * and tools like top. It may make sense to increase or even disable the
 * reserve depending on the existence of swap or variations in the recovery
 * tools. So, the admin may have changed them.
 *
 * If memory is added and the reserves have been eliminated or increased above
 * the default max, then we'll trust the admin.
 *
 * If memory is removed and there isn't enough free memory, then we
 * need to reset the reserves.
 *
 * Otherwise keep the reserve set by the admin.
 */
static int reserve_mem_notifier(struct notifier_block *nb,
			     unsigned long action, void *data)
{ … }

static int __meminit init_reserve_notifier(void)
{ … }
subsys_initcall(init_reserve_notifier);

/*
 * Relocate a VMA downwards by shift bytes. There cannot be any VMAs between
 * this VMA and its relocated range, which will now reside at [vma->vm_start -
 * shift, vma->vm_end - shift).
 *
 * This function is almost certainly NOT what you want for anything other than
 * early executable temporary stack relocation.
 */
int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift)
{ … }