From 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Mon, 21 Sep 2026 17:37:22 -0700 Subject: sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling bug alb_break_llc() decides whether to break LLC preference during active load balance. It does so by testing that every runnable fair task on the source rq prefers its LLC: env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable But the two counters cover different sets. nr_pref_llc_running is updated in account_llc_enqueue()/account_llc_dequeue(), next to cfs_rq->nr_queued, so it follows queued tasks. h_nr_runnable is updated in set_delayed()/ clear_delayed() and drops delay-dequeued tasks. So under DELAY_DEQUEUE, a preferring task that goes to sleep stays counted in nr_pref_llc_running while h_nr_runnable falls. The equality then breaks, alb_break_llc() returns false, and active balance is free to pull a task off its preferred LLC. Active balance only moves runnable tasks, and this is the only LLC check it consults: once the stopper runs, LBF_ACTIVE_LB skips the per-task test in can_migrate_task(). The runnable set is the one we want. Fix it on the counter side. A task should be counted in nr_pref_llc_running exactly while it is both queued on its preferred LLC (pref_llc_queued) and runnable (!sched_delayed). Define that membership once in task_pref_llc_runnable(), and adjust the counter only through pref_llc_running_inc()/pref_llc_running_dec() from the four sites that change either input: account_llc_enqueue(), account_llc_dequeue(), set_delayed() and clear_delayed(). Gating every update on the same predicate keeps the delay, wake and dequeue paths from double-counting or underflowing; see the comments at those sites for the ordering. nr_llc_running and sd->llc_counts are not touched and stay on queued semantics. Fixes: 714059f79ff0 ("sched/cache: Handle moving single tasks to/from their preferred LLC") Closes: https://lore.kernel.org/lkml/20260827135000.735138-1-zhanxusheng@xiaomi.com/ Reported-by: Zhan Xusheng Suggested-by: Chen Yu Signed-off-by: Tim Chen Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Kayra Cizmeci Cc: # v7.2.x Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com --- mm/mmap.c | 1900 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 1900 insertions(+) create mode 100644 mm/mmap.c (limited to 'mm/mmap.c') diff --git a/mm/mmap.c b/mm/mmap.c new file mode 100644 index 000000000..4bf26b0f1 --- /dev/null +++ b/mm/mmap.c @@ -0,0 +1,1900 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * mm/mmap.c + * + * Written by obz. + * + * Address space accounting code + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +#include "internal.h" + +#ifndef arch_mmap_check +#define arch_mmap_check(addr, len, flags) (0) +#endif + +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS +const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN; +int mmap_rnd_bits_max __ro_after_init = CONFIG_ARCH_MMAP_RND_BITS_MAX; +int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS; +#endif +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS +const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN; +const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX; +int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS; +#endif + +static bool ignore_rlimit_data; +core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644); + +/* Update vma->vm_page_prot to reflect vma->vm_flags. */ +void vma_set_page_prot(struct vm_area_struct *vma) +{ + vma_flags_t vma_flags = vma->flags; + pgprot_t vm_page_prot; + + vm_page_prot = vma_pgprot_modify(vma->vm_page_prot, vma_flags); + if (vma_wants_writenotify(vma, vm_page_prot)) { + vma_flags_clear(&vma_flags, VMA_SHARED_BIT); + vm_page_prot = vma_pgprot_modify(vm_page_prot, vma_flags); + } + /* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */ + WRITE_ONCE(vma->vm_page_prot, vm_page_prot); +} + +/* + * 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) +{ + const struct mm_struct *mm = current->mm; + const bool is_def_locked = + vma_flags_test(&mm->def_vma_flags, VMA_LOCKED_BIT); + unsigned long mapped_addr; + + mapped_addr = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); + if (IS_ERR_VALUE(mapped_addr)) + return mapped_addr; + + return mlock_future_ok(mm, is_def_locked, len) ? 0 : -EAGAIN; +} + +SYSCALL_DEFINE1(brk, unsigned long, brk) +{ + unsigned long newbrk, oldbrk, origbrk; + struct mm_struct *mm = current->mm; + struct vm_area_struct *brkvma, *next = NULL; + unsigned long min_brk; + bool populate = false; + LIST_HEAD(uf); + struct vma_iterator vmi; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + origbrk = mm->brk; + + min_brk = mm->start_brk; +#ifdef CONFIG_COMPAT_BRK + /* + * CONFIG_COMPAT_BRK can still be overridden by setting + * randomize_va_space to 2, which will still cause mm->start_brk + * to be arbitrarily shifted + */ + if (!current->brk_randomized) + min_brk = mm->end_data; +#endif + if (brk < min_brk) + goto out; + + /* + * Check against rlimit here. If this check is done later after the test + * of oldbrk with newbrk then it can escape the test and let the data + * segment grow beyond its set limit the in case where the limit is + * not page aligned -Ram Gupta + */ + if (check_data_rlimit(rlimit(RLIMIT_DATA), brk, mm->start_brk, + mm->end_data, mm->start_data)) + goto out; + + newbrk = PAGE_ALIGN(brk); + oldbrk = PAGE_ALIGN(mm->brk); + if (oldbrk == newbrk) { + mm->brk = brk; + goto success; + } + + /* Always allow shrinking brk. */ + if (brk <= mm->brk) { + /* Search one past newbrk */ + vma_iter_init(&vmi, mm, newbrk); + brkvma = vma_find(&vmi, oldbrk); + if (!brkvma || brkvma->vm_start >= oldbrk) + goto out; /* mapping intersects with an existing non-brk vma. */ + /* + * mm->brk must be protected by write mmap_lock. + * do_vmi_align_munmap() will drop the lock on success, so + * update it before calling do_vma_munmap(). + */ + mm->brk = brk; + if (do_vmi_align_munmap(&vmi, brkvma, mm, newbrk, oldbrk, &uf, + /* unlock = */ true)) + goto out; + + goto success_unlocked; + } + + if (check_brk_limits(oldbrk, newbrk - oldbrk)) + goto out; + + /* + * Only check if the next VMA is within the stack_guard_gap of the + * expansion area + */ + vma_iter_init(&vmi, mm, oldbrk); + next = vma_find(&vmi, newbrk + PAGE_SIZE + stack_guard_gap); + if (next && newbrk + PAGE_SIZE > vm_start_gap(next)) + goto out; + + brkvma = vma_prev_limit(&vmi, mm->start_brk); + /* Ok, looks good - let it rip. */ + if (do_brk_flags(&vmi, brkvma, oldbrk, newbrk - oldbrk, + EMPTY_VMA_FLAGS) < 0) + goto out; + + mm->brk = brk; + if (vma_flags_test(&mm->def_vma_flags, VMA_LOCKED_BIT)) + populate = true; + +success: + mmap_write_unlock(mm); +success_unlocked: + userfaultfd_unmap_complete(mm, &uf); + if (populate) + mm_populate(oldbrk, newbrk - oldbrk); + return brk; + +out: + mm->brk = origbrk; + mmap_write_unlock(mm); + return origbrk; +} + +/* + * 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) +{ + hint &= PAGE_MASK; + if (((void *)hint != NULL) && + (hint < mmap_min_addr)) + return PAGE_ALIGN(mmap_min_addr); + return hint; +} + +bool mlock_future_ok(const struct mm_struct *mm, bool is_vma_locked, + unsigned long bytes) +{ + unsigned long locked_pages, limit_pages; + + if (!is_vma_locked || capable(CAP_IPC_LOCK)) + return true; + + locked_pages = bytes >> PAGE_SHIFT; + locked_pages += mm->locked_vm; + + limit_pages = rlimit(RLIMIT_MEMLOCK); + limit_pages >>= PAGE_SHIFT; + + return locked_pages <= limit_pages; +} + +static inline u64 file_mmap_size_max(struct file *file, struct inode *inode) +{ + if (S_ISREG(inode->i_mode)) + return MAX_LFS_FILESIZE; + + if (S_ISBLK(inode->i_mode)) + return MAX_LFS_FILESIZE; + + if (S_ISSOCK(inode->i_mode)) + return MAX_LFS_FILESIZE; + + /* Special "we do even unsigned file positions" case */ + if (file->f_op->fop_flags & FOP_UNSIGNED_OFFSET) + return 0; + + /* Yes, random drivers might want more. But I'm tired of buggy drivers */ + return ULONG_MAX; +} + +static inline bool file_mmap_ok(struct file *file, struct inode *inode, + unsigned long pgoff, unsigned long len) +{ + u64 maxsize = file_mmap_size_max(file, inode); + + if (maxsize && len > maxsize) + return false; + maxsize -= len; + if (pgoff > maxsize >> PAGE_SHIFT) + return false; + return true; +} + +/** + * do_mmap() - Perform a userland memory mapping into the current process + * address space of length @len with protection bits @prot, mmap flags @flags + * (from which VMA flags will be inferred), and any additional VMA flags to + * apply @vma_flags. If this is a file-backed mapping then the file is specified + * in @file and page offset into the file via @pgoff. + * + * This function does not perform security checks on the file and assumes, if + * @uf is non-NULL, the caller has provided a list head to track unmap events + * for userfaultfd @uf. + * + * It also simply indicates whether memory population is required by setting + * @populate, which must be non-NULL, expecting the caller to actually perform + * this task itself if appropriate. + * + * This function will invoke architecture-specific (and if provided and + * relevant, file system-specific) logic to determine the most appropriate + * unmapped area in which to place the mapping if not MAP_FIXED. + * + * Callers which require userland mmap() behaviour should invoke vm_mmap(), + * which is also exported for module use. + * + * Those which require this behaviour less security checks, userfaultfd and + * populate behaviour, and who handle the mmap write lock themselves, should + * call this function. + * + * Note that the returned address may reside within a merged VMA if an + * appropriate merge were to take place, so it doesn't necessarily specify the + * start of a VMA, rather only the start of a valid mapped range of length + * @len bytes, rounded down to the nearest page size. + * + * The caller must write-lock current->mm->mmap_lock. + * + * @file: An optional struct file pointer describing the file which is to be + * mapped, if a file-backed mapping. + * @addr: If non-zero, hints at (or if @flags has MAP_FIXED set, specifies) the + * address at which to perform this mapping. See mmap (2) for details. Must be + * page-aligned. + * @len: The length of the mapping. Will be page-aligned and must be at least 1 + * page in size. + * @prot: Protection bits describing access required to the mapping. See mmap + * (2) for details. + * @flags: Flags specifying how the mapping should be performed, see mmap (2) + * for details. + * @vma_flags: VMA flags which should be set by default, or EMPTY_VMA_FLAGS + * otherwise. + * @pgoff: Page offset into the @file if file-backed, should be 0 otherwise. + * @populate: A pointer to a value which will be set to 0 if no population of + * the range is required, or the number of bytes to populate if it is. Must be + * non-NULL. See mmap (2) for details as to under what circumstances population + * of the range occurs. + * @uf: An optional pointer to a list head to track userfaultfd unmap events + * should unmapping events arise. If provided, it is up to the caller to manage + * this. + * + * Returns: Either an error, or the address at which the requested mapping has + * been performed. + */ +unsigned long do_mmap(struct file *file, unsigned long addr, + unsigned long len, unsigned long prot, + unsigned long flags, vma_flags_t vma_flags, + unsigned long pgoff, unsigned long *populate, + struct list_head *uf) +{ + struct mm_struct *mm = current->mm; + int pkey = 0; + + *populate = 0; + + mmap_assert_write_locked(mm); + + if (!len) + return -EINVAL; + + /* + * Does the application expect PROT_READ to imply PROT_EXEC? + * + * (the exception is when the underlying filesystem is noexec + * mounted, in which case we don't add PROT_EXEC.) + */ + if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC)) + if (!(file && path_noexec(&file->f_path))) + prot |= PROT_EXEC; + + /* force arch specific MAP_FIXED handling in get_unmapped_area */ + if (flags & MAP_FIXED_NOREPLACE) + flags |= MAP_FIXED; + + if (!(flags & MAP_FIXED)) + addr = round_hint_to_min(addr); + + /* Careful about overflows.. */ + len = PAGE_ALIGN(len); + if (!len) + return -ENOMEM; + + /* offset overflow? */ + if ((pgoff + (len >> PAGE_SHIFT)) < pgoff) + return -EOVERFLOW; + + /* Too many mappings? */ + if (mm->map_count > get_sysctl_max_map_count()) + return -ENOMEM; + + /* + * addr is returned from get_unmapped_area, + * There are two cases: + * 1> MAP_FIXED == false + * unallocated memory, no need to check sealing. + * 1> MAP_FIXED == true + * sealing is checked inside mmap_region when + * do_vmi_munmap is called. + */ + + if (prot == PROT_EXEC) { + pkey = execute_only_pkey(mm); + if (pkey < 0) + pkey = 0; + } + + /* Do simple checking here so the lower-level routines won't have + * to. we assume access permissions have been handled by the open + * of the memory object, so we don't do any here. + */ + vma_flags_set_mask(&vma_flags, + legacy_to_vma_flags(calc_vm_prot_bits(prot, pkey))); + vma_flags_set_mask(&vma_flags, + legacy_to_vma_flags(calc_vm_flag_bits(file, flags))); + vma_flags_set_mask(&vma_flags, mm->def_vma_flags); + vma_flags_set(&vma_flags, VMA_MAYREAD_BIT, VMA_MAYWRITE_BIT, + VMA_MAYEXEC_BIT); + + /* Obtain the address to map to. we verify (or select) it and ensure + * that it represents a valid section of the address space. + */ + addr = __get_unmapped_area(file, addr, len, pgoff, flags, vma_flags); + if (IS_ERR_VALUE(addr)) + return addr; + + if (flags & MAP_FIXED_NOREPLACE) { + if (find_vma_intersection(mm, addr, addr + len)) + return -EEXIST; + } + + if (flags & MAP_LOCKED) + if (!can_do_mlock()) + return -EPERM; + + if (!mlock_future_ok(mm, vma_flags_test(&vma_flags, VMA_LOCKED_BIT), len)) + return -EAGAIN; + + if (file) { + struct inode *inode = file_inode(file); + unsigned long flags_mask; + int err; + + if (!file_mmap_ok(file, inode, pgoff, len)) + return -EOVERFLOW; + + flags_mask = LEGACY_MAP_MASK; + if (file->f_op->fop_flags & FOP_MMAP_SYNC) + flags_mask |= MAP_SYNC; + + switch (flags & MAP_TYPE) { + case MAP_SHARED: + /* + * Force use of MAP_SHARED_VALIDATE with non-legacy + * flags. E.g. MAP_SYNC is dangerous to use with + * MAP_SHARED as you don't know which consistency model + * you will get. We silently ignore unsupported flags + * with MAP_SHARED to preserve backward compatibility. + */ + flags &= LEGACY_MAP_MASK; + fallthrough; + case MAP_SHARED_VALIDATE: + if (flags & ~flags_mask) + return -EOPNOTSUPP; + if (prot & PROT_WRITE) { + if (!(file->f_mode & FMODE_WRITE)) + return -EACCES; + if (IS_SWAPFILE(file->f_mapping->host)) + return -ETXTBSY; + } + + /* + * Make sure we don't allow writing to an append-only + * file.. + */ + if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE)) + return -EACCES; + + vma_flags_set(&vma_flags, VMA_SHARED_BIT, VMA_MAYSHARE_BIT); + if (!(file->f_mode & FMODE_WRITE)) + vma_flags_clear(&vma_flags, VMA_MAYWRITE_BIT, + VMA_SHARED_BIT); + fallthrough; + case MAP_PRIVATE: + if (!(file->f_mode & FMODE_READ)) + return -EACCES; + if (path_noexec(&file->f_path)) { + if (vma_flags_test(&vma_flags, VMA_EXEC_BIT)) + return -EPERM; + vma_flags_clear(&vma_flags, VMA_MAYEXEC_BIT); + } + + if (!can_mmap_file(file)) + return -ENODEV; + if (vma_flags_can_grow(&vma_flags)) + return -EINVAL; + break; + + default: + return -EINVAL; + } + + /* + * Check to see if we are violating any seals and update VMA + * flags if necessary to avoid future seal violations. + */ + err = memfd_check_seals_mmap(file, &vma_flags); + if (err) + return (unsigned long)err; + } else { + switch (flags & MAP_TYPE) { + case MAP_SHARED: + if (vma_flags_can_grow(&vma_flags)) + return -EINVAL; + /* + * Ignore pgoff. + */ + pgoff = 0; + vma_flags_set(&vma_flags, VMA_SHARED_BIT, VMA_MAYSHARE_BIT); + break; + case MAP_DROPPABLE: { + vma_flags_t droppable = VMA_DROPPABLE; + + if (vma_flags_empty(&droppable)) + return -EOPNOTSUPP; + vma_flags_set_mask(&vma_flags, droppable); + + /* + * A locked or stack area makes no sense to be droppable. + * + * Also, since droppable pages can just go away at any time + * it makes no sense to copy them on fork or dump them. + * + * And don't attempt to combine with hugetlb for now. + */ + if (flags & (MAP_LOCKED | MAP_HUGETLB)) + return -EINVAL; + if (vma_flags_can_grow(&vma_flags)) + return -EINVAL; + + /* + * If the pages can be dropped, then it doesn't make + * sense to reserve them. + */ + vma_flags_set(&vma_flags, VMA_NORESERVE_BIT); + + /* + * Likewise, they're volatile enough that they + * shouldn't survive forks or coredumps. + */ + vma_flags_set(&vma_flags, VMA_WIPEONFORK_BIT, + VMA_DONTDUMP_BIT); + + fallthrough; + } + case MAP_PRIVATE: + /* + * Set pgoff according to addr for anon_vma. + */ + pgoff = addr >> PAGE_SHIFT; + break; + default: + return -EINVAL; + } + } + + /* + * Set VMA_NORESERVE_BIT if we should not account for the memory use + * of this mapping. + */ + if (flags & MAP_NORESERVE) { + /* We honor MAP_NORESERVE if allowed to overcommit */ + if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) + vma_flags_set(&vma_flags, VMA_NORESERVE_BIT); + + /* hugetlb applies strict overcommit unless MAP_NORESERVE */ + if (file && is_file_hugepages(file)) + vma_flags_set(&vma_flags, VMA_NORESERVE_BIT); + } + + addr = mmap_region(file, addr, len, vma_flags, pgoff, uf); + if (!IS_ERR_VALUE(addr) && + (vma_flags_test(&vma_flags, VMA_LOCKED_BIT) || + (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE)) + *populate = len; + return addr; +} + +unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long pgoff) +{ + struct file *file = NULL; + unsigned long retval; + + if (!(flags & MAP_ANONYMOUS)) { + audit_mmap_fd(fd, flags); + file = fget(fd); + if (!file) + return -EBADF; + if (is_file_hugepages(file)) { + len = ALIGN(len, huge_page_size(hstate_file(file))); + } else if (unlikely(flags & MAP_HUGETLB)) { + retval = -EINVAL; + goto out_fput; + } + } else if (flags & MAP_HUGETLB) { + struct hstate *hs; + + hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); + if (!hs) + return -EINVAL; + + len = ALIGN(len, huge_page_size(hs)); + /* + * VM_NORESERVE is used because the reservations will be + * taken when vm_ops->mmap() is called + */ + file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, + mk_vma_flags(VMA_NORESERVE_BIT), + HUGETLB_ANONHUGE_INODE, + (flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); + if (IS_ERR(file)) + return PTR_ERR(file); + } + + retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); +out_fput: + if (file) + fput(file); + return retval; +} + +SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, + unsigned long, prot, unsigned long, flags, + unsigned long, fd, unsigned long, pgoff) +{ + return ksys_mmap_pgoff(addr, len, prot, flags, fd, 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 */ + +/* + * 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(vma_flags_t vma_flags) +{ + if (vma_flags_test_single_mask(&vma_flags, VMA_SHADOW_STACK)) + return PAGE_SIZE; + + return 0; +} + +/* + * 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) +{ + unsigned long addr; + + if (info->flags & VM_UNMAPPED_AREA_TOPDOWN) + addr = unmapped_area_topdown(info); + else + addr = unmapped_area(info); + + trace_vm_unmapped_area(addr, info); + return addr; +} + +/* 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, vma_flags_t vma_flags) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma, *prev; + struct vm_unmapped_area_info info = {}; + const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); + + if (len > mmap_end - mmap_min_addr) + return -ENOMEM; + + if (flags & MAP_FIXED) + return addr; + + if (addr) { + addr = PAGE_ALIGN(addr); + vma = find_vma_prev(mm, addr, &prev); + if (mmap_end - len >= addr && addr >= mmap_min_addr && + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) + return addr; + } + + info.length = len; + info.low_limit = mm->mmap_base; + info.high_limit = mmap_end; + info.start_gap = stack_guard_placement(vma_flags); + if (filp && is_file_hugepages(filp)) + info.align_mask = huge_page_mask_align(filp); + return vm_unmapped_area(&info); +} + +#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, + legacy_to_vma_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, vma_flags_t vma_flags) +{ + struct vm_area_struct *vma, *prev; + struct mm_struct *mm = current->mm; + struct vm_unmapped_area_info info = {}; + const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); + + /* requested length too big for entire address space */ + if (len > mmap_end - mmap_min_addr) + return -ENOMEM; + + if (flags & MAP_FIXED) + return addr; + + /* requesting a specific address */ + if (addr) { + addr = PAGE_ALIGN(addr); + vma = find_vma_prev(mm, addr, &prev); + if (mmap_end - len >= addr && addr >= mmap_min_addr && + (!vma || addr + len <= vm_start_gap(vma)) && + (!prev || addr >= vm_end_gap(prev))) + return addr; + } + + info.flags = VM_UNMAPPED_AREA_TOPDOWN; + info.length = len; + info.low_limit = PAGE_SIZE; + info.high_limit = arch_get_mmap_base(addr, mm->mmap_base); + info.start_gap = stack_guard_placement(vma_flags); + if (filp && is_file_hugepages(filp)) + info.align_mask = huge_page_mask_align(filp); + addr = vm_unmapped_area(&info); + + /* + * A failed mmap() very likely causes application failure, + * so fall back to the bottom-up function here. This scenario + * can happen with large stack limits and large mmap() + * allocations. + */ + if (offset_in_page(addr)) { + VM_BUG_ON(addr != -ENOMEM); + info.flags = 0; + info.low_limit = TASK_UNMAPPED_BASE; + info.high_limit = mmap_end; + addr = vm_unmapped_area(&info); + } + + return addr; +} + +#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, + legacy_to_vma_flags(vm_flags)); +} +#endif + +unsigned long mm_get_unmapped_area_vmaflags(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags, + vma_flags_t vma_flags) +{ + if (mm_flags_test(MMF_TOPDOWN, current->mm)) + return arch_get_unmapped_area_topdown(filp, addr, len, pgoff, + flags, vma_flags_to_legacy(vma_flags)); + return arch_get_unmapped_area(filp, addr, len, pgoff, flags, + vma_flags_to_legacy(vma_flags)); +} + +unsigned long +__get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags, vma_flags_t vma_flags) +{ + unsigned long (*get_area)(struct file *, unsigned long, + unsigned long, unsigned long, unsigned long) + = NULL; + + unsigned long error = arch_mmap_check(addr, len, flags); + if (error) + return error; + + /* Careful about overflows.. */ + if (len > TASK_SIZE) + return -ENOMEM; + + if (file) { + if (file->f_op->get_unmapped_area) + get_area = file->f_op->get_unmapped_area; + } else if (flags & MAP_SHARED) { + /* + * mmap_region() will call shmem_zero_setup() to create a file, + * so use shmem's get_unmapped_area in case it can be huge. + */ + get_area = shmem_get_unmapped_area; + } + + /* Always treat pgoff as zero for anonymous memory. */ + if (!file) + pgoff = 0; + + if (get_area) { + addr = get_area(file, addr, len, pgoff, flags); + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && !file + && !addr /* no hint */ + && IS_ALIGNED(len, PMD_SIZE)) { + /* Ensures that larger anonymous mappings are THP aligned. */ + addr = thp_get_unmapped_area_vmaflags(file, addr, len, + pgoff, flags, vma_flags); + } else { + addr = mm_get_unmapped_area_vmaflags(file, addr, len, + pgoff, flags, vma_flags); + } + if (IS_ERR_VALUE(addr)) + return addr; + + if (addr > TASK_SIZE - len) + return -ENOMEM; + if (offset_in_page(addr)) + return -EINVAL; + + error = security_mmap_addr(addr); + return error ? error : addr; +} + +unsigned long +mm_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + return mm_get_unmapped_area_vmaflags(file, addr, len, pgoff, flags, + EMPTY_VMA_FLAGS); +} +EXPORT_SYMBOL(mm_get_unmapped_area); + +/** + * 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) +{ + unsigned long index = start_addr; + + mmap_assert_locked(mm); + return mt_find(&mm->mm_mt, &index, end_addr - 1); +} +EXPORT_SYMBOL(find_vma_intersection); + +/** + * 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) +{ + unsigned long index = addr; + + mmap_assert_locked(mm); + return mt_find(&mm->mm_mt, &index, ULONG_MAX); +} +EXPORT_SYMBOL(find_vma); + +/** + * 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) +{ + struct vm_area_struct *vma; + VMA_ITERATOR(vmi, mm, addr); + + vma = vma_iter_load(&vmi); + *pprev = vma_prev(&vmi); + if (!vma) + vma = vma_next(&vmi); + return vma; +} + +/* enforced gap between the expanding stack and other mappings. */ +unsigned long stack_guard_gap = 256UL<comm, current->pid); + + if (prot) + return ret; + start = start & PAGE_MASK; + size = size & PAGE_MASK; + + if (start + size <= start) + return ret; + + /* Does pgoff wrap? */ + if (pgoff + (size >> PAGE_SHIFT) < pgoff) + return ret; + + if (mmap_read_lock_killable(mm)) + return -EINTR; + + /* + * Look up VMA under read lock first so we can perform the security + * without holding locks (which can be problematic). We reacquire a + * write lock later and check nothing changed underneath us. + */ + vma = vma_lookup(mm, start); + + if (!vma || !vma_test(vma, VMA_SHARED_BIT)) { + mmap_read_unlock(mm); + return -EINVAL; + } + + prot |= vma_test(vma, VMA_READ_BIT) ? PROT_READ : 0; + prot |= vma_test(vma, VMA_WRITE_BIT) ? PROT_WRITE : 0; + prot |= vma_test(vma, VMA_EXEC_BIT) ? PROT_EXEC : 0; + + flags &= MAP_NONBLOCK; + flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; + if (vma_test(vma, VMA_LOCKED_BIT)) + flags |= MAP_LOCKED; + + /* Save vm_flags used to calculate prot and flags, and recheck later. */ + vm_flags = vma->vm_flags; + file = get_file(vma->vm_file); + + mmap_read_unlock(mm); + + /* Call outside mmap_lock to be consistent with other callers. */ + ret = security_mmap_file(file, prot, flags); + if (ret) { + fput(file); + return ret; + } + + ret = -EINVAL; + + /* OK security check passed, take write lock + let it rip. */ + if (mmap_write_lock_killable(mm)) { + fput(file); + return -EINTR; + } + + vma = vma_lookup(mm, start); + + if (!vma) + goto out; + + /* Make sure things didn't change under us. */ + if (vma->vm_flags != vm_flags) + goto out; + if (vma->vm_file != file) + goto out; + + if (start + size > vma->vm_end) { + VMA_ITERATOR(vmi, mm, vma->vm_end); + struct vm_area_struct *next, *prev = vma; + + for_each_vma_range(vmi, next, start + size) { + /* hole between vmas ? */ + if (next->vm_start != prev->vm_end) + goto out; + + if (next->vm_file != vma->vm_file) + goto out; + + if (next->vm_flags != vma->vm_flags) + goto out; + + if (start + size <= next->vm_end) + break; + + prev = next; + } + + if (!next) + goto out; + } + + ret = do_mmap(vma->vm_file, start, size, + prot, flags, EMPTY_VMA_FLAGS, pgoff, &populate, NULL); +out: + mmap_write_unlock(mm); + fput(file); + if (populate) + mm_populate(ret, populate); + if (!IS_ERR_VALUE(ret)) + ret = 0; + return ret; +} + +int vm_brk_flags(unsigned long addr, unsigned long request, bool is_exec) +{ + const vma_flags_t vma_flags = is_exec ? + mk_vma_flags(VMA_EXEC_BIT) : EMPTY_VMA_FLAGS; + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma = NULL; + unsigned long len; + int ret; + bool populate; + LIST_HEAD(uf); + VMA_ITERATOR(vmi, mm, addr); + + len = PAGE_ALIGN(request); + if (len < request) + return -ENOMEM; + if (!len) + return 0; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + ret = check_brk_limits(addr, len); + if (ret) + goto limits_failed; + + ret = do_vmi_munmap(&vmi, mm, addr, len, &uf, 0); + if (ret) + goto munmap_failed; + + vma = vma_prev(&vmi); + ret = do_brk_flags(&vmi, vma, addr, len, vma_flags); + populate = vma_flags_test(&mm->def_vma_flags, VMA_LOCKED_BIT); + mmap_write_unlock(mm); + userfaultfd_unmap_complete(mm, &uf); + if (populate && !ret) + mm_populate(addr, len); + return ret; + +munmap_failed: +limits_failed: + mmap_write_unlock(mm); + return ret; +} + +static +unsigned long tear_down_vmas(struct mm_struct *mm, struct vma_iterator *vmi, + struct vm_area_struct *vma, unsigned long end) +{ + unsigned long nr_accounted = 0; + int count = 0; + + mmap_assert_write_locked(mm); + vma_iter_set(vmi, vma->vm_end); + do { + if (vma_test(vma, VMA_ACCOUNT_BIT)) + nr_accounted += vma_pages(vma); + vma_mark_detached(vma); + remove_vma(vma); + count++; + cond_resched(); + vma = vma_next(vmi); + } while (vma && vma->vm_end <= end); + + VM_WARN_ON_ONCE(count != mm->map_count); + return nr_accounted; +} + +/* Release all mmaps. */ +void exit_mmap(struct mm_struct *mm) +{ + struct mmu_gather tlb; + struct vm_area_struct *vma; + unsigned long nr_accounted = 0; + VMA_ITERATOR(vmi, mm, 0); + struct unmap_desc unmap; + + /* mm's last user has gone, and its about to be pulled down */ + mmu_notifier_release(mm); + + mmap_read_lock(mm); + arch_exit_mmap(mm); + + vma = vma_next(&vmi); + if (!vma) { + /* Can happen if dup_mmap() received an OOM */ + mmap_read_unlock(mm); + mmap_write_lock(mm); + goto destroy; + } + + unmap_all_init(&unmap, &vmi, vma); + flush_cache_mm(mm); + tlb_gather_mmu_fullmm(&tlb, mm); + /* update_hiwater_rss(mm) here? but nobody should be looking */ + /* Use ULONG_MAX here to ensure all VMAs in the mm are unmapped */ + unmap_vmas(&tlb, &unmap); + mmap_read_unlock(mm); + + /* + * Set MMF_OOM_SKIP to hide this task from the oom killer/reaper + * because the memory has been already freed. + */ + mm_flags_set(MMF_OOM_SKIP, mm); + mmap_write_lock(mm); + unmap.mm_wr_locked = true; + mt_clear_in_rcu(&mm->mm_mt); + unmap_pgtable_init(&unmap, &vmi); + free_pgtables(&tlb, &unmap); + tlb_finish_mmu(&tlb); + + /* + * Walk the list again, actually closing and freeing it, with preemption + * enabled, without holding any MM locks besides the unreachable + * mmap_write_lock. + */ + nr_accounted = tear_down_vmas(mm, &vmi, vma, ULONG_MAX); + +destroy: + __mt_destroy(&mm->mm_mt); + trace_exit_mmap(mm); + mmap_write_unlock(mm); + vm_unacct_memory(nr_accounted); +} + +/* + * 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, const vma_flags_t *vma_flags, + unsigned long npages) +{ + if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT) + return false; + + if (is_data_mapping_vma_flags(vma_flags) && + mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) { + /* Workaround for Valgrind */ + if (rlimit(RLIMIT_DATA) == 0 && + mm->data_vm + npages <= rlimit_max(RLIMIT_DATA) >> PAGE_SHIFT) + return true; + + pr_warn_once("%s (%d): VmData %lu exceed data ulimit %lu. Update limits%s.\n", + current->comm, current->pid, + (mm->data_vm + npages) << PAGE_SHIFT, + rlimit(RLIMIT_DATA), + ignore_rlimit_data ? "" : " or use boot option ignore_rlimit_data"); + + if (!ignore_rlimit_data) + return false; + } + + return true; +} + +void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) +{ + WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm)+npages); + + if (is_exec_mapping(flags)) + mm->exec_vm += npages; + else if (is_stack_mapping(flags)) + mm->stack_vm += npages; + else if (is_data_mapping(flags)) + mm->data_vm += 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) +{ + const struct vm_special_mapping *sm = vma->vm_private_data; + + if (sm->close) + sm->close(sm, vma); +} + +static const char *special_mapping_name(struct vm_area_struct *vma) +{ + return ((struct vm_special_mapping *)vma->vm_private_data)->name; +} + +static int special_mapping_mremap(struct vm_area_struct *new_vma) +{ + struct vm_special_mapping *sm = new_vma->vm_private_data; + + if (WARN_ON_ONCE(current->mm != new_vma->vm_mm)) + return -EFAULT; + + if (sm->mremap) + return sm->mremap(sm, new_vma); + + return 0; +} + +static int special_mapping_split(struct vm_area_struct *vma, unsigned long addr) +{ + /* + * Forbid splitting special mappings - kernel has expectations over + * the number of pages in mapping. Together with VMA_DONTEXPAND_BIT + * the size of vma should stay the same over the special mapping's + * lifetime. + */ + return -EINVAL; +} + +static const struct vm_operations_struct special_mapping_vmops = { + .close = special_mapping_close, + .fault = special_mapping_fault, + .mremap = special_mapping_mremap, + .name = special_mapping_name, + /* vDSO code relies that VVAR can't be accessed remotely */ + .access = NULL, + .may_split = special_mapping_split, +}; + +static vm_fault_t special_mapping_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + pgoff_t pgoff; + struct page **pages; + struct vm_special_mapping *sm = vma->vm_private_data; + + if (sm->fault) + return sm->fault(sm, vmf->vma, vmf); + + pages = sm->pages; + + for (pgoff = vmf->pgoff; pgoff && *pages; ++pages) + pgoff--; + + if (*pages) { + struct page *page = *pages; + get_page(page); + vmf->page = page; + return 0; + } + + return VM_FAULT_SIGBUS; +} + +bool vma_is_special_mapping(const struct vm_area_struct *vma, + const struct vm_special_mapping *sm) +{ + return vma->vm_private_data == sm && + vma->vm_ops == &special_mapping_vmops; +} + +/* + * 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, + vm_flags_t vm_flags, const struct vm_special_mapping *spec) +{ + return __install_special_mapping(mm, addr, len, vm_flags, (void *)spec, + &special_mapping_vmops); +} + +#ifdef CONFIG_SYSCTL +#if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \ + defined(CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT) +int sysctl_legacy_va_layout; +#endif + +static const struct ctl_table mmap_table[] = { + { + .procname = "max_map_count", + .data = &sysctl_max_map_count, + .maxlen = sizeof(sysctl_max_map_count), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + }, +#if defined(HAVE_ARCH_PICK_MMAP_LAYOUT) || \ + defined(CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT) + { + .procname = "legacy_va_layout", + .data = &sysctl_legacy_va_layout, + .maxlen = sizeof(sysctl_legacy_va_layout), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + }, +#endif +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS + { + .procname = "mmap_rnd_bits", + .data = &mmap_rnd_bits, + .maxlen = sizeof(mmap_rnd_bits), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&mmap_rnd_bits_min, + .extra2 = (void *)&mmap_rnd_bits_max, + }, +#endif +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS + { + .procname = "mmap_rnd_compat_bits", + .data = &mmap_rnd_compat_bits, + .maxlen = sizeof(mmap_rnd_compat_bits), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&mmap_rnd_compat_bits_min, + .extra2 = (void *)&mmap_rnd_compat_bits_max, + }, +#endif +}; +#endif /* CONFIG_SYSCTL */ + +/* + * initialise the percpu counter for VM, initialise VMA state. + */ +void __init mmap_init(void) +{ + int ret; + + ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL); + VM_BUG_ON(ret); +#ifdef CONFIG_SYSCTL + register_sysctl_init("vm", mmap_table); +#endif + vma_state_init(); +} + +/* + * 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) +{ + unsigned long free_kbytes; + + free_kbytes = K(global_zone_page_state(NR_FREE_PAGES)); + + sysctl_user_reserve_kbytes = min(free_kbytes / 32, SZ_128K); + return 0; +} +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) +{ + unsigned long free_kbytes; + + free_kbytes = K(global_zone_page_state(NR_FREE_PAGES)); + + sysctl_admin_reserve_kbytes = min(free_kbytes / 32, SZ_8K); + return 0; +} +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) +{ + unsigned long tmp, free_kbytes; + + switch (action) { + case MEM_ONLINE: + /* Default max is 128MB. Leave alone if modified by operator. */ + tmp = sysctl_user_reserve_kbytes; + if (tmp > 0 && tmp < SZ_128K) + init_user_reserve(); + + /* Default max is 8MB. Leave alone if modified by operator. */ + tmp = sysctl_admin_reserve_kbytes; + if (tmp > 0 && tmp < SZ_8K) + init_admin_reserve(); + + break; + case MEM_OFFLINE: + free_kbytes = K(global_zone_page_state(NR_FREE_PAGES)); + + if (sysctl_user_reserve_kbytes > free_kbytes) { + init_user_reserve(); + pr_info("vm.user_reserve_kbytes reset to %lu\n", + sysctl_user_reserve_kbytes); + } + + if (sysctl_admin_reserve_kbytes > free_kbytes) { + init_admin_reserve(); + pr_info("vm.admin_reserve_kbytes reset to %lu\n", + sysctl_admin_reserve_kbytes); + } + break; + default: + break; + } + return NOTIFY_OK; +} + +static int __meminit init_reserve_notifier(void) +{ + if (hotplug_memory_notifier(reserve_mem_notifier, DEFAULT_CALLBACK_PRI)) + pr_err("Failed registering memory add/remove notifier for admin reserve\n"); + + return 0; +} +subsys_initcall(init_reserve_notifier); + +/* + * Obtain a read lock on mm->mmap_lock, if the specified address is below the + * start of the VMA, the intent is to perform a write, and it is a + * downward-growing stack, then attempt to expand the stack to contain it. + * + * This function is intended only for obtaining an argument page from an ELF + * image, and is almost certainly NOT what you want to use for any other + * purpose. + * + * IMPORTANT - VMA fields are accessed without an mmap lock being held, so the + * VMA referenced must not be linked in any user-visible tree, i.e. it must be a + * new VMA being mapped. + * + * The function assumes that addr is either contained within the VMA or below + * it, and makes no attempt to validate this value beyond that. + * + * Returns true if the read lock was obtained and a stack was perhaps expanded, + * false if the stack expansion failed. + * + * On stack expansion the function temporarily acquires an mmap write lock + * before downgrading it. + */ +bool mmap_read_lock_maybe_expand(struct mm_struct *mm, + struct vm_area_struct *new_vma, + unsigned long addr, bool write) +{ + if (!write || addr >= new_vma->vm_start) { + mmap_read_lock(mm); + return true; + } + + if (!vma_test(new_vma, VMA_GROWSDOWN_BIT)) + return false; + + mmap_write_lock(mm); + if (expand_downwards(new_vma, addr)) { + mmap_write_unlock(mm); + return false; + } + + mmap_write_downgrade(mm); + return true; +} + +__latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) +{ + struct vm_area_struct *mpnt, *tmp; + int retval; + unsigned long charge = 0; + LIST_HEAD(uf); + VMA_ITERATOR(vmi, mm, 0); + + if (mmap_write_lock_killable(oldmm)) + return -EINTR; + flush_cache_dup_mm(oldmm); + uprobe_dup_mmap(oldmm, mm); + /* + * Not linked in yet - no deadlock potential: + */ + mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING); + + /* No ordering required: file already has been exposed. */ + dup_mm_exe_file(mm, oldmm); + + mm->total_vm = oldmm->total_vm; + mm->data_vm = oldmm->data_vm; + mm->exec_vm = oldmm->exec_vm; + mm->stack_vm = oldmm->stack_vm; + + /* Use __mt_dup() to efficiently build an identical maple tree. */ + retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL); + if (unlikely(retval)) + goto out; + + mt_clear_in_rcu(vmi.mas.tree); + for_each_vma(vmi, mpnt) { + struct file *file; + + retval = vma_start_write_killable(mpnt); + if (retval < 0) + goto loop_out; + if (vma_test(mpnt, VMA_DONTCOPY_BIT)) { + retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start, + mpnt->vm_end, GFP_KERNEL); + if (retval) + goto loop_out; + + vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt)); + continue; + } + charge = 0; + if (vma_test(mpnt, VMA_ACCOUNT_BIT)) { + unsigned long len = vma_pages(mpnt); + + if (security_vm_enough_memory_mm(oldmm, len)) /* sic */ + goto fail_nomem; + charge = len; + } + + tmp = vm_area_dup(mpnt); + if (!tmp) + goto fail_nomem; + retval = vma_dup_policy(mpnt, tmp); + if (retval) + goto fail_nomem_policy; + tmp->vm_mm = mm; + retval = dup_userfaultfd(tmp, &uf); + if (retval) + goto fail_nomem_anon_vma_fork; + + if (vma_test(tmp, VMA_WIPEONFORK_BIT)) { + /* + * VMA_WIPEONFORK_BIT gets a clean slate in the child. + * Don't prepare anon_vma until fault since we don't + * copy page for current vma. + */ + tmp->anon_vma = NULL; + } else if (anon_vma_fork(tmp, mpnt)) + goto fail_nomem_anon_vma_fork; + + vma_start_write(tmp); + vma_clear_flags_mask(tmp, VMA_LOCKED_MASK); + /* + * Copy/update hugetlb private vma information. + */ + if (is_vm_hugetlb_page(tmp)) + hugetlb_dup_vma_private(tmp); + + /* + * Link the vma into the MT. After using __mt_dup(), memory + * allocation is not necessary here, so it cannot fail. + */ + vma_iter_bulk_store(&vmi, tmp); + + mm->map_count++; + + if (tmp->vm_ops && tmp->vm_ops->open) + tmp->vm_ops->open(tmp); + + file = tmp->vm_file; + if (file) { + struct address_space *mapping = file->f_mapping; + + get_file(file); + i_mmap_lock_write(mapping); + if (vma_is_shared_maywrite(tmp)) + mapping_allow_writable(mapping); + flush_dcache_mmap_lock(mapping); + /* insert tmp into the share list, just after mpnt */ + mapping_rmap_tree_insert_after(tmp, mpnt, mapping); + flush_dcache_mmap_unlock(mapping); + i_mmap_unlock_write(mapping); + } + + if (!vma_test(tmp, VMA_WIPEONFORK_BIT)) + retval = copy_page_range(tmp, mpnt); + + if (retval) { + mpnt = vma_next(&vmi); + goto loop_out; + } + } + /* a new mm has just been created */ + retval = arch_dup_mmap(oldmm, mm); +loop_out: + vma_iter_free(&vmi); + if (!retval) { + mt_set_in_rcu(vmi.mas.tree); + ksm_fork(mm, oldmm); + khugepaged_fork(mm, oldmm); + } else { + unsigned long end; + + /* + * The entire maple tree has already been duplicated, but + * replacing the vmas failed at mpnt (which could be NULL if + * all were allocated but the last vma was not fully set up). + * Use the start address of the failure point to clean up the + * partially initialized tree. + */ + if (!mm->map_count) { + /* zero vmas were written to the new tree. */ + end = 0; + } else if (mpnt) { + /* partial tree failure */ + end = mpnt->vm_start; + } else { + /* All vmas were written to the new tree */ + end = ULONG_MAX; + } + + /* Hide mm from oom killer because the memory is being freed */ + mm_flags_set(MMF_OOM_SKIP, mm); + if (end) { + vma_iter_set(&vmi, 0); + tmp = vma_next(&vmi); + UNMAP_STATE(unmap, &vmi, /* first = */ tmp, + /* vma_start = */ 0, /* vma_end = */ end, + /* prev = */ NULL, /* next = */ NULL); + + /* + * Don't iterate over vmas beyond the failure point for + * both unmap_vma() and free_pgtables(). + */ + unmap.tree_end = end; + flush_cache_mm(mm); + unmap_region(&unmap); + charge = tear_down_vmas(mm, &vmi, tmp, end); + vm_unacct_memory(charge); + } + __mt_destroy(&mm->mm_mt); + /* + * The mm_struct is going to exit, but the locks will be dropped + * first. Set the mm_struct as unstable is advisable as it is + * not fully initialised. + */ + mm_flags_set(MMF_UNSTABLE, mm); + } +out: + mmap_write_unlock(mm); + flush_tlb_mm(oldmm); + mmap_write_unlock(oldmm); + if (!retval) + dup_userfaultfd_complete(&uf); + else + dup_userfaultfd_fail(&uf); + return retval; + +fail_nomem_anon_vma_fork: + mpol_put(vma_policy(tmp)); +fail_nomem_policy: + vm_area_free(tmp); +fail_nomem: + retval = -ENOMEM; + vm_unacct_memory(charge); + goto loop_out; +} -- cgit v1.3.1