cregit-Linux how code gets into the kernel

Release 4.15 mm/mlock.c

Directory: mm
// SPDX-License-Identifier: GPL-2.0
/*
 *      linux/mm/mlock.c
 *
 *  (C) Copyright 1995 Linus Torvalds
 *  (C) Copyright 2002 Christoph Hellwig
 */

#include <linux/capability.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/sched/user.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/mempolicy.h>
#include <linux/syscalls.h>
#include <linux/sched.h>
#include <linux/export.h>
#include <linux/rmap.h>
#include <linux/mmzone.h>
#include <linux/hugetlb.h>
#include <linux/memcontrol.h>
#include <linux/mm_inline.h>

#include "internal.h"


bool can_do_mlock(void) { if (rlimit(RLIMIT_MEMLOCK) != 0) return true; if (capable(CAP_IPC_LOCK)) return true; return false; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin2062.50%125.00%
Jeff Vander Stoep618.75%125.00%
Wang Xiaoqiang412.50%125.00%
Jiri Slaby26.25%125.00%
Total32100.00%4100.00%

EXPORT_SYMBOL(can_do_mlock); /* * Mlocked pages are marked with PageMlocked() flag for efficient testing * in vmscan and, possibly, the fault path; and to support semi-accurate * statistics. * * An mlocked page [PageMlocked(page)] is unevictable. As such, it will * be placed on the LRU "unevictable" list, rather than the [in]active lists. * The unevictable list is an LRU sibling list to the [in]active lists. * PageUnevictable is set to indicate the unevictable state. * * When lazy mlocking via vmscan, it is important to ensure that the * vma's VM_LOCKED status is not concurrently being modified, otherwise we * may have mlocked a page that is being munlocked. So lazy mlock must take * the mmap_sem for read, and verify that the vma really is locked * (see mm/rmap.c). */ /* * LRU accounting for clear_page_mlock() */
void clear_page_mlock(struct page *page) { if (!TestClearPageMlocked(page)) return; mod_zone_page_state(page_zone(page), NR_MLOCK, -hpage_nr_pages(page)); count_vm_event(UNEVICTABLE_PGCLEARED); if (!isolate_lru_page(page)) { putback_lru_page(page); } else { /* * We lost the race. the page already moved to evictable list. */ if (PageUnevictable(page)) count_vm_event(UNEVICTABLE_PGSTRANDED); } }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin5678.87%240.00%
David Rientjes1014.08%120.00%
Hugh Dickins45.63%120.00%
Motohiro Kosaki11.41%120.00%
Total71100.00%5100.00%

/* * Mark page as mlocked if not already. * If page on LRU, isolate and putback to move to unevictable list. */
void mlock_vma_page(struct page *page) { /* Serialize with page migration */ BUG_ON(!PageLocked(page)); VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page); if (!TestSetPageMlocked(page)) { mod_zone_page_state(page_zone(page), NR_MLOCK, hpage_nr_pages(page)); count_vm_event(UNEVICTABLE_PGMLOCKED); if (!isolate_lru_page(page)) putback_lru_page(page); } }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin5360.23%240.00%
Kirill A. Shutemov2528.41%120.00%
David Rientjes910.23%120.00%
Vlastimil Babka11.14%120.00%
Total88100.00%5100.00%

/* * Isolate a page from LRU with optional get_page() pin. * Assumes lru_lock already held and page already pinned. */
static bool __munlock_isolate_lru_page(struct page *page, bool getpage) { if (PageLRU(page)) { struct lruvec *lruvec; lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); if (getpage) get_page(page); ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_lru(page)); return true; } return false; }

Contributors

PersonTokensPropCommitsCommitProp
Vlastimil Babka7198.61%150.00%
Mel Gorman11.39%150.00%
Total72100.00%2100.00%

/* * Finish munlock after successful page isolation * * Page must be locked. This is a wrapper for try_to_munlock() * and putback_lru_page() with munlock accounting. */
static void __munlock_isolated_page(struct page *page) { /* * Optimization: if the page was mapped just once, that's our mapping * and we don't need to check all the other vmas. */ if (page_mapcount(page) > 1) try_to_munlock(page); /* Did try_to_unlock() succeed or punt? */ if (!PageMlocked(page)) count_vm_event(UNEVICTABLE_PGMUNLOCKED); putback_lru_page(page); }

Contributors

PersonTokensPropCommitsCommitProp
Vlastimil Babka4088.89%150.00%
MinChan Kim511.11%150.00%
Total45100.00%2100.00%

/* * Accounting for page isolation fail during munlock * * Performs accounting when page isolation fails in munlock. There is nothing * else to do because it means some other task has already removed the page * from the LRU. putback_lru_page() will take care of removing the page from * the unevictable list, if necessary. vmscan [page_referenced()] will move * the page back to the unevictable list if some other vma has it mlocked. */
static void __munlock_isolation_failed(struct page *page) { if (PageUnevictable(page)) __count_vm_event(UNEVICTABLE_PGSTRANDED); else __count_vm_event(UNEVICTABLE_PGMUNLOCKED); }

Contributors

PersonTokensPropCommitsCommitProp
Vlastimil Babka29100.00%2100.00%
Total29100.00%2100.00%

/** * munlock_vma_page - munlock a vma page * @page - page to be unlocked, either a normal page or THP page head * * returns the size of the page as a page mask (0 for normal page, * HPAGE_PMD_NR - 1 for THP head page) * * called from munlock()/munmap() path with page supposedly on the LRU. * When we munlock a page, because the vma where we found the page is being * munlock()ed or munmap()ed, we want to check whether other vmas hold the * page locked so that we can leave it on the unevictable lru list and not * bother vmscan with it. However, to walk the page's rmap list in * try_to_munlock() we must isolate the page from the LRU. If some other * task has removed the page from the LRU, we won't be able to do that. * So we clear the PageMlocked as we might not get another chance. If we * can't isolate the page, we leave it for putback_lru_page() and vmscan * [page_referenced()/try_to_unmap()] to deal with. */
unsigned int munlock_vma_page(struct page *page) { int nr_pages; struct zone *zone = page_zone(page); /* For try_to_munlock() and to serialize with page migration */ BUG_ON(!PageLocked(page)); VM_BUG_ON_PAGE(PageTail(page), page); /* * Serialize with any parallel __split_huge_page_refcount() which * might otherwise copy PageMlocked to part of the tail pages before * we clear it in the head page. It also stabilizes hpage_nr_pages(). */ spin_lock_irq(zone_lru_lock(zone)); if (!TestClearPageMlocked(page)) { /* Potentially, PTE-mapped THP: do not skip the rest PTEs */ nr_pages = 1; goto unlock_out; } nr_pages = hpage_nr_pages(page); __mod_zone_page_state(zone, NR_MLOCK, -nr_pages); if (__munlock_isolate_lru_page(page, true)) { spin_unlock_irq(zone_lru_lock(zone)); __munlock_isolated_page(page); goto out; } __munlock_isolation_failed(page); unlock_out: spin_unlock_irq(zone_lru_lock(zone)); out: return nr_pages - 1; }

Contributors

PersonTokensPropCommitsCommitProp
Vlastimil Babka5439.42%436.36%
Nicholas Piggin4029.20%218.18%
Kirill A. Shutemov2417.52%218.18%
Mel Gorman96.57%19.09%
Michel Lespinasse75.11%19.09%
David Rientjes32.19%19.09%
Total137100.00%11100.00%

/* * convert get_user_pages() return value to posix mlock() error */
static int __mlock_posix_error_return(long retval) { if (retval == -EFAULT) retval = -ENOMEM; else if (retval == -ENOMEM) retval = -EAGAIN; return retval; }

Contributors

PersonTokensPropCommitsCommitProp
Lee Schermerhorn37100.00%1100.00%
Total37100.00%1100.00%

/* * Prepare page for fast batched LRU putback via putback_lru_evictable_pagevec() * * The fast path is available only for evictable pages with single mapping. * Then we can bypass the per-cpu pvec and get better performance. * when mapcount > 1 we need try_to_munlock() which can fail. * when !page_evictable(), we need the full redo logic of putback_lru_page to * avoid leaving evictable page in unevictable list. * * In case of success, @page is added to @pvec and @pgrescued is incremented * in case that the page was previously unevictable. @page is also unlocked. */
static bool __putback_lru_fast_prepare(struct page *page, struct pagevec *pvec, int *pgrescued) { VM_BUG_ON_PAGE(PageLRU(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); if (page_mapcount(page) <= 1 && page_evictable(page)) { pagevec_add(pvec, page); if (TestClearPageUnevictable(page)) (*pgrescued)++; unlock_page(page); return true; } return false; }

Contributors

PersonTokensPropCommitsCommitProp
Vlastimil Babka8293.18%150.00%
Sasha Levin66.82%150.00%
Total88100.00%2100.00%

/* * Putback multiple evictable pages to the LRU * * Batched putback of evictable pages that bypasses the per-cpu pvec. Some of * the pages might have meanwhile become unevictable but that is OK. */
static void __putback_lru_fast(struct pagevec *pvec, int pgrescued) { count_vm_events(UNEVICTABLE_PGMUNLOCKED, pagevec_count(pvec)); /* *__pagevec_lru_add() calls release_pages() so we don't call * put_page() explicitly */ __pagevec_lru_add(pvec); count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); }

Contributors

PersonTokensPropCommitsCommitProp
Vlastimil Babka37100.00%1100.00%
Total37100.00%1100.00%

/* * Munlock a batch of pages from the same zone * * The work is split to two main phases. First phase clears the Mlocked flag * and attempts to isolate the pages, all under a single zone lru lock. * The second phase finishes the munlock only for pages where isolation * succeeded. * * Note that the pagevec may be modified during the process. */
static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) { int i; int nr = pagevec_count(pvec); int delta_munlocked = -nr; struct pagevec pvec_putback; int pgrescued = 0; pagevec_init(&pvec_putback); /* Phase 1: page isolation */ spin_lock_irq(zone_lru_lock(zone)); for (i = 0; i < nr; i++) { struct page *page = pvec->pages[i]; if (TestClearPageMlocked(page)) { /* * We already have pin from follow_page_mask() * so we can spare the get_page() here. */ if (__munlock_isolate_lru_page(page, false)) continue; else __munlock_isolation_failed(page); } else { delta_munlocked++; } /* * We won't be munlocking this page in the next phase * but we still need to release the follow_page_mask() * pin. We cannot do it under lru_lock however. If it's * the last pin, __page_cache_release() would deadlock. */ pagevec_add(&pvec_putback, pvec->pages[i]); pvec->pages[i] = NULL; } __mod_zone_page_state(zone, NR_MLOCK, delta_munlocked); spin_unlock_irq(zone_lru_lock(zone)); /* Now we can release pins of pages that we are not munlocking */ pagevec_release(&pvec_putback); /* Phase 2: page munlock */ for (i = 0; i < nr; i++) { struct page *page = pvec->pages[i]; if (page) { lock_page(page); if (!__putback_lru_fast_prepare(page, &pvec_putback, &pgrescued)) { /* * Slow path. We don't want to lose the last * pin before unlock_page() */ get_page(page); /* for putback_lru_page() */ __munlock_isolated_page(page); unlock_page(page); put_page(page); /* from follow_page_mask() */ } } } /* * Phase 3: page putback for pages that qualified for the fast path * This will also call put_page() to return pin from follow_page_mask() */ if (pagevec_count(&pvec_putback)) __putback_lru_fast(&pvec_putback, pgrescued); }

Contributors

PersonTokensPropCommitsCommitProp
Vlastimil Babka24394.19%675.00%
Yisheng Xie93.49%112.50%
Mel Gorman62.33%112.50%
Total258100.00%8100.00%

/* * Fill up pagevec for __munlock_pagevec using pte walk * * The function expects that the struct page corresponding to @start address is * a non-TPH page already pinned and in the @pvec, and that it belongs to @zone. * * The rest of @pvec is filled by subsequent pages within the same pmd and same * zone, as long as the pte's are present and vm_normal_page() succeeds. These * pages also get pinned. * * Returns the address of the next page that should be scanned. This equals * @start + PAGE_SIZE when no page could be added by the pte walk. */
static unsigned long __munlock_pagevec_fill(struct pagevec *pvec, struct vm_area_struct *vma, struct zone *zone, unsigned long start, unsigned long end) { pte_t *pte; spinlock_t *ptl; /* * Initialize pte walk starting at the already pinned page where we * are sure that there is a pte, as it was pinned under the same * mmap_sem write op. */ pte = get_locked_pte(vma->vm_mm, start, &ptl); /* Make sure we do not cross the page table boundary */ end = pgd_addr_end(start, end); end = p4d_addr_end(start, end); end = pud_addr_end(start, end); end = pmd_addr_end(start, end); /* The page next to the pinned page is the first we will try to get */ start += PAGE_SIZE; while (start < end) { struct page *page = NULL; pte++; if (pte_present(*pte)) page = vm_normal_page(vma, start, *pte); /* * Break if page could not be obtained or the page's node+zone does not * match */ if (!page || page_zone(page) != zone) break; /* * Do not use pagevec for PTE-mapped THP, * munlock_vma_pages_range() will handle them. */ if (PageTransCompound(page)) break; get_page(page); /* * Increase the address that will be returned *before* the * eventual break due to pvec becoming full by adding the page */ start += PAGE_SIZE; if (pagevec_add(pvec, page) == 0) break; } pte_unmap_unlock(pte, ptl); return start; }

Contributors

PersonTokensPropCommitsCommitProp
Vlastimil Babka14979.26%337.50%
Kirill A. Shutemov189.57%225.00%
Rik Van Riel84.26%112.50%
Nicholas Piggin73.72%112.50%
JoonSoo Kim63.19%112.50%
Total188100.00%8100.00%

/* * munlock_vma_pages_range() - munlock all pages in the vma range.' * @vma - vma containing range to be munlock()ed. * @start - start address in @vma of the range * @end - end of range in @vma. * * For mremap(), munmap() and exit(). * * Called with @vma VM_LOCKED. * * Returns with VM_LOCKED cleared. Callers must be prepared to * deal with this. * * We don't save and restore VM_LOCKED here because pages are * still on lru. In unmap path, pages might be scanned by reclaim * and re-mlocked by try_to_{munlock|unmap} before we unmap and * free them. This will result in freeing mlocked pages. */
void munlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { vma->vm_flags &= VM_LOCKED_CLEAR_MASK; while (start < end) { struct page *page; unsigned int page_mask = 0; unsigned long page_increm; struct pagevec pvec; struct zone *zone; pagevec_init(&pvec); /* * Although FOLL_DUMP is intended for get_dump_page(), * it just so happens that its special treatment of the * ZERO_PAGE (returning an error instead of doing get_page) * suits munlock very well (and if somehow an abnormal page * has sneaked into the range, we won't oops here: great). */ page = follow_page(vma, start, FOLL_GET | FOLL_DUMP); if (page && !IS_ERR(page)) { if (PageTransTail(page)) { VM_BUG_ON_PAGE(PageMlocked(page), page); put_page(page); /* follow_page_mask() */ } else if (PageTransHuge(page)) { lock_page(page); /* * Any THP page found by follow_page_mask() may * have gotten split before reaching * munlock_vma_page(), so we need to compute * the page_mask here instead. */ page_mask = munlock_vma_page(page); unlock_page(page); put_page(page); /* follow_page_mask() */ } else { /* * Non-huge pages are handled in batches via * pagevec. The pin from follow_page_mask() * prevents them from collapsing by THP. */ pagevec_add(&pvec, page); zone = page_zone(page); /* * Try to fill the rest of pagevec using fast * pte walk. This will also update start to * the next page to process. Then munlock the * pagevec. */ start = __munlock_pagevec_fill(&pvec, vma, zone, start, end); __munlock_pagevec(&pvec, zone); goto next; } } page_increm = 1 + page_mask; start += page_increm * PAGE_SIZE; next: cond_resched(); } }

Contributors

PersonTokensPropCommitsCommitProp
Vlastimil Babka8942.18%323.08%
Kirill A. Shutemov6430.33%215.38%
Hugh Dickins3014.22%215.38%
Michel Lespinasse167.58%17.69%
Nicholas Piggin83.79%17.69%
Alexey Dobriyan10.47%17.69%
JoonSoo Kim10.47%17.69%
Eric B Munson10.47%17.69%
Rik Van Riel10.47%17.69%
Total211100.00%13100.00%

/* * mlock_fixup - handle mlock[all]/munlock[all] requests. * * Filters out "special" vmas -- VM_LOCKED never gets set for these, and * munlock is a no-op. However, for some special vmas, we go ahead and * populate the ptes. * * For vmas that pass the filters, merge/split as appropriate. */
static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, vm_flags_t newflags) { struct mm_struct *mm = vma->vm_mm; pgoff_t pgoff; int nr_pages; int ret = 0; int lock = !!(newflags & VM_LOCKED); vm_flags_t old_flags = vma->vm_flags; if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm)) /* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */ goto out; pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx); if (*prev) { vma = *prev; goto success; } if (start != vma->vm_start) { ret = split_vma(mm, vma, start, 1); if (ret) goto out; } if (end != vma->vm_end) { ret = split_vma(mm, vma, end, 0); if (ret) goto out; } success: /* * Keep track of amount of locked VM. */ nr_pages = (end - start) >> PAGE_SHIFT; if (!lock) nr_pages = -nr_pages; else if (old_flags & VM_LOCKED) nr_pages = 0; mm->locked_vm += nr_pages; /* * vm_flags is protected by the mmap_sem held in write mode. * It's okay if try_to_unmap_one unmaps a page just after we * set VM_LOCKED, populate_vma_page_range will bring it back. */ if (lock) vma->vm_flags = newflags; else munlock_vma_pages_range(vma, start, end); out: *prev = vma; return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Chris Wright7725.67%16.25%
Linus Torvalds (pre-git)7625.33%318.75%
Nicholas Piggin5719.00%16.25%
Andrew Morton4113.67%212.50%
Simon Guo186.00%16.25%
Hugh Dickins175.67%212.50%
Motohiro Kosaki51.67%16.25%
Andrea Arcangeli41.33%16.25%
Stephen Wilson20.67%16.25%
Kirill A. Shutemov10.33%16.25%
Eric B Munson10.33%16.25%
Michel Lespinasse10.33%16.25%
Total300100.00%16100.00%


static int apply_vma_lock_flags(unsigned long start, size_t len, vm_flags_t flags) { unsigned long nstart, end, tmp; struct vm_area_struct * vma, * prev; int error; VM_BUG_ON(offset_in_page(start)); VM_BUG_ON(len != PAGE_ALIGN(len)); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; vma = find_vma(current->mm, start); if (!vma || vma->vm_start > start) return -ENOMEM; prev = vma->vm_prev; if (start > vma->vm_start) prev = vma; for (nstart = start ; ; ) { vm_flags_t newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK; newflags |= flags; /* Here we know that vma->vm_start <= nstart < vma->vm_end. */ tmp = vma->vm_end; if (tmp > end) tmp = end; error = mlock_fixup(vma, &prev, nstart, tmp, newflags); if (error) break; nstart = tmp; if (nstart < prev->vm_end) nstart = prev->vm_end; if (nstart >= end) break; vma = prev->vm_next; if (!vma || vma->vm_start != nstart) { error = -ENOMEM; break; } } return error; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)15866.95%327.27%
Chris Wright4820.34%19.09%
Michel Lespinasse114.66%218.18%
Eric B Munson83.39%218.18%
Linus Torvalds72.97%19.09%
Alexander Kuleshov31.27%19.09%
Motohiro Kosaki10.42%19.09%
Total236100.00%11100.00%

/* * Go through vma areas and sum size of mlocked * vma pages, as return value. * Note deferred memory locking case(mlock2(,,MLOCK_ONFAULT) * is also counted. * Return value: previously mlocked page counts */
static int count_mm_mlocked_page_nr(struct mm_struct *mm, unsigned long start, size_t len) { struct vm_area_struct *vma; int count = 0; if (mm == NULL) mm = current->mm; vma = find_vma(mm, start); if (vma == NULL) vma = mm->mmap; for (; vma ; vma = vma->vm_next) { if (start >= vma->vm_end) continue; if (start + len <= vma->vm_start) break; if (vma->vm_flags & VM_LOCKED) { if (start > vma->vm_start) count -= (start - vma->vm_start); if (start + len < vma->vm_end) { count += start + len - vma->vm_start; break; } count += vma->vm_end - vma->vm_start; } } return count >> PAGE_SHIFT; }

Contributors

PersonTokensPropCommitsCommitProp
Simon Guo160100.00%1100.00%
Total160100.00%1100.00%


static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags) { unsigned long locked; unsigned long lock_limit; int error = -ENOMEM; if (!can_do_mlock()) return -EPERM; len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; locked = len >> PAGE_SHIFT; if (down_write_killable(&current->mm->mmap_sem)) return -EINTR; locked += current->mm->locked_vm; if ((locked > lock_limit) && (!capable(CAP_IPC_LOCK))) { /* * It is possible that the regions requested intersect with * previously mlocked areas, that part area in "mm->locked_vm" * should not be counted to new mlock increment count. So check * and adjust locked count if necessary. */ locked -= count_mm_mlocked_page_nr(current->mm, start, len); } /* check against resource limits */ if ((locked <= lock_limit) || capable(CAP_IPC_LOCK)) error = apply_vma_lock_flags(start, len, flags); up_write(&current->mm->mmap_sem); if (error) return error; error = __mm_populate(start, len, 0); if (error) return __mlock_posix_error_return(error); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)7236.36%425.00%
Simon Guo3216.16%16.25%
Davidlohr Bueso A199.60%16.25%
Eric B Munson168.08%16.25%
Michel Lespinasse157.58%212.50%
Kirill A. Shutemov136.57%16.25%
Chris Wright105.05%16.25%
Michal Hocko94.55%16.25%
Rik Van Riel73.54%16.25%
Alexander Kuleshov31.52%16.25%
Andrew Morton10.51%16.25%
Linus Torvalds10.51%16.25%
Total198100.00%16100.00%

SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) { return do_mlock(start, len, VM_LOCKED); } SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags) { vm_flags_t vm_flags = VM_LOCKED; if (flags & ~MLOCK_ONFAULT) return -EINVAL; if (flags & MLOCK_ONFAULT) vm_flags |= VM_LOCKONFAULT; return do_mlock(start, len, vm_flags); } SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) { int ret; len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; if (down_write_killable(&current->mm->mmap_sem)) return -EINTR; ret = apply_vma_lock_flags(start, len, 0); up_write(&current->mm->mmap_sem); return ret; } /* * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall) * and translate into the appropriate modifications to mm->def_flags and/or the * flags for all current VMAs. * * There are a couple of subtleties with this. If mlockall() is called multiple * times with different flags, the values do not necessarily stack. If mlockall * is called once including the MCL_FUTURE flag and then a second time without * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags. */
static int apply_mlockall_flags(int flags) { struct vm_area_struct * vma, * prev = NULL; vm_flags_t to_add = 0; current->mm->def_flags &= VM_LOCKED_CLEAR_MASK; if (flags & MCL_FUTURE) { current->mm->def_flags |= VM_LOCKED; if (flags & MCL_ONFAULT) current->mm->def_flags |= VM_LOCKONFAULT; if (!(flags & MCL_CURRENT)) goto out; } if (flags & MCL_CURRENT) { to_add |= VM_LOCKED; if (flags & MCL_ONFAULT) to_add |= VM_LOCKONFAULT; } for (vma = current->mm->mmap; vma ; vma = prev->vm_next) { vm_flags_t newflags; newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK; newflags |= to_add; /* Ignore errors */ mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags); cond_resched_rcu_qs(); } out: return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)7446.84%19.09%
Eric B Munson5333.54%218.18%
Chris Wright1912.03%218.18%
Gerald Schaefer53.16%19.09%
Paul E. McKenney31.90%218.18%
Michel Lespinasse21.27%19.09%
Motohiro Kosaki10.63%19.09%
Andi Kleen10.63%19.09%
Total158100.00%11100.00%

SYSCALL_DEFINE1(mlockall, int, flags) { unsigned long lock_limit; int ret; if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT))) return -EINVAL; if (!can_do_mlock()) return -EPERM; lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; if (down_write_killable(&current->mm->mmap_sem)) return -EINTR; ret = -ENOMEM; if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) || capable(CAP_IPC_LOCK)) ret = apply_mlockall_flags(flags); up_write(&current->mm->mmap_sem); if (!ret && (flags & MCL_CURRENT)) mm_populate(0, TASK_SIZE); return ret; } SYSCALL_DEFINE0(munlockall) { int ret; if (down_write_killable(&current->mm->mmap_sem)) return -EINTR; ret = apply_mlockall_flags(0); up_write(&current->mm->mmap_sem); return ret; } /* * Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB * shm segments) get accounted against the user_struct instead. */ static DEFINE_SPINLOCK(shmlock_user_lock);
int user_shm_lock(size_t size, struct user_struct *user) { unsigned long lock_limit, locked; int allowed = 0; locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; lock_limit = rlimit(RLIMIT_MEMLOCK); if (lock_limit == RLIM_INFINITY) allowed = 1; lock_limit >>= PAGE_SHIFT; spin_lock(&shmlock_user_lock); if (!allowed && locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK)) goto out; get_uid(user); user->locked_shm += locked; allowed = 1; out: spin_unlock(&shmlock_user_lock); return allowed; }

Contributors

PersonTokensPropCommitsCommitProp
Rik Van Riel8374.77%125.00%
Herbert van den Bergh1311.71%125.00%
Michael Kerrisk1210.81%125.00%
Jiri Slaby32.70%125.00%
Total111100.00%4100.00%


void user_shm_unlock(size_t size, struct user_struct *user) { spin_lock(&shmlock_user_lock); user->locked_shm -= (size + PAGE_SIZE - 1) >> PAGE_SHIFT; spin_unlock(&shmlock_user_lock); free_uid(user); }

Contributors

PersonTokensPropCommitsCommitProp
Rik Van Riel3988.64%150.00%
Michael Kerrisk511.36%150.00%
Total44100.00%2100.00%


Overall Contributors

PersonTokensPropCommitsCommitProp
Vlastimil Babka81327.79%1011.76%
Linus Torvalds (pre-git)51517.61%78.24%
Nicholas Piggin2709.23%22.35%
Simon Guo2117.21%22.35%
Chris Wright1715.85%44.71%
Eric B Munson1635.57%44.71%
Rik Van Riel1485.06%22.35%
Kirill A. Shutemov1454.96%67.06%
Michel Lespinasse712.43%55.88%
Hugh Dickins511.74%44.71%
Andrew Morton481.64%33.53%
Lee Schermerhorn381.30%11.18%
Michal Hocko371.26%11.18%
Davidlohr Bueso A361.23%11.18%
Heiko Carstens240.82%22.35%
David Rientjes220.75%11.18%
Michael Kerrisk170.58%11.18%
Mel Gorman160.55%22.35%
Herbert van den Bergh130.44%11.18%
Linus Torvalds110.38%22.35%
Alexander Kuleshov90.31%11.18%
Yisheng Xie90.31%11.18%
Jiri Slaby80.27%11.18%
Motohiro Kosaki80.27%22.35%
Alexey Klimov70.24%11.18%
JoonSoo Kim70.24%11.18%
Sasha Levin60.21%11.18%
Jeff Vander Stoep60.21%11.18%
Alexey Dobriyan60.21%11.18%
MinChan Kim50.17%11.18%
Gerald Schaefer50.17%11.18%
Andrea Arcangeli40.14%11.18%
Wang Xiaoqiang40.14%11.18%
Thomas Gleixner40.14%11.18%
Randy Dunlap30.10%11.18%
Paul E. McKenney30.10%22.35%
Arnd Bergmann30.10%11.18%
Ingo Molnar30.10%11.18%
Stephen Wilson20.07%11.18%
Paul Gortmaker10.03%11.18%
Andi Kleen10.03%11.18%
Greg Kroah-Hartman10.03%11.18%
Total2925100.00%85100.00%
Directory: mm
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with cregit.