--- zzzz-none-000/linux-3.10.107/fs/proc/task_mmu.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/fs/proc/task_mmu.c 2021-02-04 17:41:59.000000000 +0000 @@ -1,4 +1,5 @@ #include +#include #include #include #include @@ -11,6 +12,8 @@ #include #include #include +#include +#include #include #include @@ -19,7 +22,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) { - unsigned long data, text, lib, swap; + unsigned long data, text, lib, swap, ptes, pmds; unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss; /* @@ -40,6 +43,8 @@ text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10; lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text; swap = get_mm_counter(mm, MM_SWAPENTS); + ptes = PTRS_PER_PTE * sizeof(pte_t) * atomic_long_read(&mm->nr_ptes); + pmds = PTRS_PER_PMD * sizeof(pmd_t) * mm_nr_pmds(mm); seq_printf(m, "VmPeak:\t%8lu kB\n" "VmSize:\t%8lu kB\n" @@ -52,6 +57,7 @@ "VmExe:\t%8lu kB\n" "VmLib:\t%8lu kB\n" "VmPTE:\t%8lu kB\n" + "VmPMD:\t%8lu kB\n" "VmSwap:\t%8lu kB\n", hiwater_vm << (PAGE_SHIFT-10), total_vm << (PAGE_SHIFT-10), @@ -61,8 +67,10 @@ total_rss << (PAGE_SHIFT-10), data << (PAGE_SHIFT-10), mm->stack_vm << (PAGE_SHIFT-10), text, lib, - (PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10, + ptes >> 10, + pmds >> 10, swap << (PAGE_SHIFT-10)); + hugetlb_report_usage(m, mm); } unsigned long task_vsize(struct mm_struct *mm) @@ -82,42 +90,16 @@ return mm->total_vm; } -static void pad_len_spaces(struct seq_file *m, int len) -{ - len = 25 + sizeof(void*) * 6 - len; - if (len < 1) - len = 1; - seq_printf(m, "%*c", len, ' '); -} - #ifdef CONFIG_NUMA /* - * These functions are for numa_maps but called in generic **maps seq_file - * ->start(), ->stop() ops. - * - * numa_maps scans all vmas under mmap_sem and checks their mempolicy. - * Each mempolicy object is controlled by reference counting. The problem here - * is how to avoid accessing dead mempolicy object. - * - * Because we're holding mmap_sem while reading seq_file, it's safe to access - * each vma's mempolicy, no vma objects will never drop refs to mempolicy. - * - * A task's mempolicy (task->mempolicy) has different behavior. task->mempolicy - * is set and replaced under mmap_sem but unrefed and cleared under task_lock(). - * So, without task_lock(), we cannot trust get_vma_policy() because we cannot - * gurantee the task never exits under us. But taking task_lock() around - * get_vma_plicy() causes lock order problem. - * - * To access task->mempolicy without lock, we hold a reference count of an - * object pointed by task->mempolicy and remember it. This will guarantee - * that task->mempolicy points to an alive object or NULL in numa_maps accesses. + * Save get_task_policy() for show_numa_map(). */ static void hold_task_mempolicy(struct proc_maps_private *priv) { struct task_struct *task = priv->task; task_lock(task); - priv->task_mempolicy = task->mempolicy; + priv->task_mempolicy = get_task_policy(task); mpol_get(priv->task_mempolicy); task_unlock(task); } @@ -134,125 +116,161 @@ } #endif -static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma) +static void vma_stop(struct proc_maps_private *priv) { - if (vma && vma != priv->tail_vma) { - struct mm_struct *mm = vma->vm_mm; - release_task_mempolicy(priv); - up_read(&mm->mmap_sem); - mmput(mm); - } + struct mm_struct *mm = priv->mm; + + release_task_mempolicy(priv); + up_read(&mm->mmap_sem); + mmput(mm); +} + +static struct vm_area_struct * +m_next_vma(struct proc_maps_private *priv, struct vm_area_struct *vma) +{ + if (vma == priv->tail_vma) + return NULL; + return vma->vm_next ?: priv->tail_vma; +} + +static void m_cache_vma(struct seq_file *m, struct vm_area_struct *vma) +{ + if (m->count < m->size) /* vma is copied successfully */ + m->version = m_next_vma(m->private, vma) ? vma->vm_start : -1UL; } -static void *m_start(struct seq_file *m, loff_t *pos) +static void *m_start(struct seq_file *m, loff_t *ppos) { struct proc_maps_private *priv = m->private; unsigned long last_addr = m->version; struct mm_struct *mm; - struct vm_area_struct *vma, *tail_vma = NULL; - loff_t l = *pos; - - /* Clear the per syscall fields in priv */ - priv->task = NULL; - priv->tail_vma = NULL; - - /* - * We remember last_addr rather than next_addr to hit with - * mmap_cache most of the time. We have zero last_addr at - * the beginning and also after lseek. We will have -1 last_addr - * after the end of the vmas. - */ + struct vm_area_struct *vma; + unsigned int pos = *ppos; + /* See m_cache_vma(). Zero at the start or after lseek. */ if (last_addr == -1UL) return NULL; - priv->task = get_pid_task(priv->pid, PIDTYPE_PID); + priv->task = get_proc_task(priv->inode); if (!priv->task) return ERR_PTR(-ESRCH); - mm = mm_access(priv->task, PTRACE_MODE_READ_FSCREDS); - if (!mm || IS_ERR(mm)) - return mm; - down_read(&mm->mmap_sem); + mm = priv->mm; + if (!mm || !atomic_inc_not_zero(&mm->mm_users)) + return NULL; - tail_vma = get_gate_vma(priv->task->mm); - priv->tail_vma = tail_vma; + down_read(&mm->mmap_sem); hold_task_mempolicy(priv); - /* Start with last addr hint */ - vma = find_vma(mm, last_addr); - if (last_addr && vma) { - vma = vma->vm_next; - goto out; + priv->tail_vma = get_gate_vma(mm); + + if (last_addr) { + vma = find_vma(mm, last_addr); + if (vma && (vma = m_next_vma(priv, vma))) + return vma; } - /* - * Check the vma index is within the range and do - * sequential scan until m_index. - */ - vma = NULL; - if ((unsigned long)l < mm->map_count) { - vma = mm->mmap; - while (l-- && vma) + m->version = 0; + if (pos < mm->map_count) { + for (vma = mm->mmap; pos; pos--) { + m->version = vma->vm_start; vma = vma->vm_next; - goto out; + } + return vma; } - if (l != mm->map_count) - tail_vma = NULL; /* After gate vma */ - -out: - if (vma) - return vma; + /* we do not bother to update m->version in this case */ + if (pos == mm->map_count && priv->tail_vma) + return priv->tail_vma; - release_task_mempolicy(priv); - /* End of vmas has been reached */ - m->version = (tail_vma != NULL)? 0: -1UL; - up_read(&mm->mmap_sem); - mmput(mm); - return tail_vma; + vma_stop(priv); + return NULL; } static void *m_next(struct seq_file *m, void *v, loff_t *pos) { struct proc_maps_private *priv = m->private; - struct vm_area_struct *vma = v; - struct vm_area_struct *tail_vma = priv->tail_vma; + struct vm_area_struct *next; (*pos)++; - if (vma && (vma != tail_vma) && vma->vm_next) - return vma->vm_next; - vma_stop(priv, vma); - return (vma != tail_vma)? tail_vma: NULL; + next = m_next_vma(priv, v); + if (!next) + vma_stop(priv); + return next; } static void m_stop(struct seq_file *m, void *v) { struct proc_maps_private *priv = m->private; - struct vm_area_struct *vma = v; - if (!IS_ERR(vma)) - vma_stop(priv, vma); - if (priv->task) + if (!IS_ERR_OR_NULL(v)) + vma_stop(priv); + if (priv->task) { put_task_struct(priv->task); + priv->task = NULL; + } +} + +static int proc_maps_open(struct inode *inode, struct file *file, + const struct seq_operations *ops, int psize) +{ + struct proc_maps_private *priv = __seq_open_private(file, ops, psize); + + if (!priv) + return -ENOMEM; + + priv->inode = inode; + priv->mm = proc_mem_open(inode, PTRACE_MODE_READ); + if (IS_ERR(priv->mm)) { + int err = PTR_ERR(priv->mm); + + seq_release_private(inode, file); + return err; + } + + return 0; +} + +static int proc_map_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct proc_maps_private *priv = seq->private; + + if (priv->mm) + mmdrop(priv->mm); + + return seq_release_private(inode, file); } static int do_maps_open(struct inode *inode, struct file *file, const struct seq_operations *ops) { - struct proc_maps_private *priv; - int ret = -ENOMEM; - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (priv) { - priv->pid = proc_pid(inode); - ret = seq_open(file, ops); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = priv; - } else { - kfree(priv); - } + return proc_maps_open(inode, file, ops, + sizeof(struct proc_maps_private)); +} + +/* + * Indicate if the VMA is a stack for the given task; for + * /proc/PID/maps that is the stack of the main task. + */ +static int is_stack(struct proc_maps_private *priv, + struct vm_area_struct *vma, int is_pid) +{ + int stack = 0; + + if (is_pid) { + stack = vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack; + } else { + struct inode *inode = priv->inode; + struct task_struct *task; + + rcu_read_lock(); + task = pid_task(proc_pid(inode), PIDTYPE_PID); + if (task) + stack = vma_is_stack_for_task(vma, task); + rcu_read_unlock(); } - return ret; + return stack; } static void @@ -261,13 +279,11 @@ struct mm_struct *mm = vma->vm_mm; struct file *file = vma->vm_file; struct proc_maps_private *priv = m->private; - struct task_struct *task = priv->task; vm_flags_t flags = vma->vm_flags; unsigned long ino = 0; unsigned long long pgoff = 0; unsigned long start, end; dev_t dev = 0; - int len; const char *name = NULL; if (file) { @@ -279,9 +295,14 @@ /* We don't show the stack guard page in /proc/maps */ start = vma->vm_start; + if (stack_guard_page_start(vma, start)) + start += PAGE_SIZE; end = vma->vm_end; + if (stack_guard_page_end(vma, end)) + end -= PAGE_SIZE; - seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n", + seq_setwidth(m, 25 + sizeof(void *) * 6 - 1); + seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ", start, end, flags & VM_READ ? 'r' : '-', @@ -289,22 +310,26 @@ flags & VM_EXEC ? 'x' : '-', flags & VM_MAYSHARE ? 's' : 'p', pgoff, - MAJOR(dev), MINOR(dev), ino, &len); + MAJOR(dev), MINOR(dev), ino); /* * Print the dentry name for named mappings, and a * special [heap] marker for the heap: */ if (file) { - pad_len_spaces(m, len); - seq_path(m, &file->f_path, "\n"); + seq_pad(m, ' '); + seq_file_path(m, file, "\n"); goto done; } + if (vma->vm_ops && vma->vm_ops->name) { + name = vma->vm_ops->name(vma); + if (name) + goto done; + } + name = arch_vma_name(vma); if (!name) { - pid_t tid; - if (!mm) { name = "[vdso]"; goto done; @@ -316,27 +341,13 @@ goto done; } - tid = vm_is_stack(task, vma, is_pid); - - if (tid != 0) { - /* - * Thread stack in /proc/PID/task/TID/maps or - * the main process stack. - */ - if (!is_pid || (vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack)) { - name = "[stack]"; - } else { - /* Thread stack in /proc/PID/maps */ - pad_len_spaces(m, len); - seq_printf(m, "[stack:%d]", tid); - } - } + if (is_stack(priv, vma, is_pid)) + name = "[stack]"; } done: if (name) { - pad_len_spaces(m, len); + seq_pad(m, ' '); seq_puts(m, name); } seq_putc(m, '\n'); @@ -344,15 +355,8 @@ static int show_map(struct seq_file *m, void *v, int is_pid) { - struct vm_area_struct *vma = v; - struct proc_maps_private *priv = m->private; - struct task_struct *task = priv->task; - - show_map_vma(m, vma, is_pid); - - if (m->count < m->size) /* vma is copied successfully */ - m->version = (vma != get_gate_vma(task->mm)) - ? vma->vm_start : 0; + show_map_vma(m, v, is_pid); + m_cache_vma(m, v); return 0; } @@ -394,14 +398,14 @@ .open = pid_maps_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = proc_map_release, }; const struct file_operations proc_tid_maps_operations = { .open = tid_maps_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = proc_map_release, }; /* @@ -425,7 +429,6 @@ #ifdef CONFIG_PROC_PAGE_MONITOR struct mem_size_stats { - struct vm_area_struct *vma; unsigned long resident; unsigned long shared_clean; unsigned long shared_dirty; @@ -435,75 +438,111 @@ unsigned long anonymous; unsigned long anonymous_thp; unsigned long swap; - unsigned long nonlinear; + unsigned long shared_hugetlb; + unsigned long private_hugetlb; u64 pss; + u64 swap_pss; }; +static void smaps_account(struct mem_size_stats *mss, struct page *page, + unsigned long size, bool young, bool dirty) +{ + int mapcount; + + if (PageAnon(page)) + mss->anonymous += size; -static void smaps_pte_entry(pte_t ptent, unsigned long addr, - unsigned long ptent_size, struct mm_walk *walk) + mss->resident += size; + /* Accumulate the size in pages that have been accessed. */ + if (young || page_is_young(page) || PageReferenced(page)) + mss->referenced += size; + mapcount = page_mapcount(page); + if (mapcount >= 2) { + u64 pss_delta; + + if (dirty || PageDirty(page)) + mss->shared_dirty += size; + else + mss->shared_clean += size; + pss_delta = (u64)size << PSS_SHIFT; + do_div(pss_delta, mapcount); + mss->pss += pss_delta; + } else { + if (dirty || PageDirty(page)) + mss->private_dirty += size; + else + mss->private_clean += size; + mss->pss += (u64)size << PSS_SHIFT; + } +} + +static void smaps_pte_entry(pte_t *pte, unsigned long addr, + struct mm_walk *walk) { struct mem_size_stats *mss = walk->private; - struct vm_area_struct *vma = mss->vma; - pgoff_t pgoff = linear_page_index(vma, addr); + struct vm_area_struct *vma = walk->vma; struct page *page = NULL; - int mapcount; - if (pte_present(ptent)) { - page = vm_normal_page(vma, addr, ptent); - } else if (is_swap_pte(ptent)) { - swp_entry_t swpent = pte_to_swp_entry(ptent); + if (pte_present(*pte)) { + page = vm_normal_page(vma, addr, *pte); + } else if (is_swap_pte(*pte)) { + swp_entry_t swpent = pte_to_swp_entry(*pte); + + if (!non_swap_entry(swpent)) { + int mapcount; + + mss->swap += PAGE_SIZE; + mapcount = swp_swapcount(swpent); + if (mapcount >= 2) { + u64 pss_delta = (u64)PAGE_SIZE << PSS_SHIFT; - if (!non_swap_entry(swpent)) - mss->swap += ptent_size; - else if (is_migration_entry(swpent)) + do_div(pss_delta, mapcount); + mss->swap_pss += pss_delta; + } else { + mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT; + } + } else if (is_migration_entry(swpent)) page = migration_entry_to_page(swpent); - } else if (pte_file(ptent)) { - if (pte_to_pgoff(ptent) != pgoff) - mss->nonlinear += ptent_size; } if (!page) return; + smaps_account(mss, page, PAGE_SIZE, pte_young(*pte), pte_dirty(*pte)); +} - if (PageAnon(page)) - mss->anonymous += ptent_size; - - if (page->index != pgoff) - mss->nonlinear += ptent_size; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, + struct mm_walk *walk) +{ + struct mem_size_stats *mss = walk->private; + struct vm_area_struct *vma = walk->vma; + struct page *page; - mss->resident += ptent_size; - /* Accumulate the size in pages that have been accessed. */ - if (pte_young(ptent) || PageReferenced(page)) - mss->referenced += ptent_size; - mapcount = page_mapcount(page); - if (mapcount >= 2) { - if (pte_dirty(ptent) || PageDirty(page)) - mss->shared_dirty += ptent_size; - else - mss->shared_clean += ptent_size; - mss->pss += (ptent_size << PSS_SHIFT) / mapcount; - } else { - if (pte_dirty(ptent) || PageDirty(page)) - mss->private_dirty += ptent_size; - else - mss->private_clean += ptent_size; - mss->pss += (ptent_size << PSS_SHIFT); - } + /* FOLL_DUMP will return -EFAULT on huge zero page */ + page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP); + if (IS_ERR_OR_NULL(page)) + return; + mss->anonymous_thp += HPAGE_PMD_SIZE; + smaps_account(mss, page, HPAGE_PMD_SIZE, + pmd_young(*pmd), pmd_dirty(*pmd)); +} +#else +static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, + struct mm_walk *walk) +{ } +#endif static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { - struct mem_size_stats *mss = walk->private; - struct vm_area_struct *vma = mss->vma; + struct vm_area_struct *vma = walk->vma; pte_t *pte; spinlock_t *ptl; - if (pmd_trans_huge_lock(pmd, vma) == 1) { - smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk); - spin_unlock(&walk->mm->page_table_lock); - mss->anonymous_thp += HPAGE_PMD_SIZE; + if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + smaps_pmd_entry(pmd, addr, walk); + spin_unlock(ptl); return 0; } @@ -516,7 +555,7 @@ */ pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) - smaps_pte_entry(*pte, addr, PAGE_SIZE, walk); + smaps_pte_entry(pte, addr, walk); pte_unmap_unlock(pte - 1, ptl); cond_resched(); return 0; @@ -544,6 +583,9 @@ [ilog2(VM_GROWSDOWN)] = "gd", [ilog2(VM_PFNMAP)] = "pf", [ilog2(VM_DENYWRITE)] = "dw", +#ifdef CONFIG_X86_INTEL_MPX + [ilog2(VM_MPX)] = "mp", +#endif [ilog2(VM_LOCKED)] = "lo", [ilog2(VM_IO)] = "io", [ilog2(VM_SEQ_READ)] = "sr", @@ -553,13 +595,17 @@ [ilog2(VM_ACCOUNT)] = "ac", [ilog2(VM_NORESERVE)] = "nr", [ilog2(VM_HUGETLB)] = "ht", - [ilog2(VM_NONLINEAR)] = "nl", [ilog2(VM_ARCH_1)] = "ar", [ilog2(VM_DONTDUMP)] = "dd", +#ifdef CONFIG_MEM_SOFT_DIRTY + [ilog2(VM_SOFTDIRTY)] = "sd", +#endif [ilog2(VM_MIXEDMAP)] = "mm", [ilog2(VM_HUGEPAGE)] = "hg", [ilog2(VM_NOHUGEPAGE)] = "nh", [ilog2(VM_MERGEABLE)] = "mg", + [ilog2(VM_UFFD_MISSING)]= "um", + [ilog2(VM_UFFD_WP)] = "uw", }; size_t i; @@ -573,23 +619,51 @@ seq_putc(m, '\n'); } +#ifdef CONFIG_HUGETLB_PAGE +static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, + unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct mem_size_stats *mss = walk->private; + struct vm_area_struct *vma = walk->vma; + struct page *page = NULL; + + if (pte_present(*pte)) { + page = vm_normal_page(vma, addr, *pte); + } else if (is_swap_pte(*pte)) { + swp_entry_t swpent = pte_to_swp_entry(*pte); + + if (is_migration_entry(swpent)) + page = migration_entry_to_page(swpent); + } + if (page) { + int mapcount = page_mapcount(page); + + if (mapcount >= 2) + mss->shared_hugetlb += huge_page_size(hstate_vma(vma)); + else + mss->private_hugetlb += huge_page_size(hstate_vma(vma)); + } + return 0; +} +#endif /* HUGETLB_PAGE */ + static int show_smap(struct seq_file *m, void *v, int is_pid) { - struct proc_maps_private *priv = m->private; - struct task_struct *task = priv->task; struct vm_area_struct *vma = v; struct mem_size_stats mss; struct mm_walk smaps_walk = { .pmd_entry = smaps_pte_range, +#ifdef CONFIG_HUGETLB_PAGE + .hugetlb_entry = smaps_hugetlb_range, +#endif .mm = vma->vm_mm, .private = &mss, }; memset(&mss, 0, sizeof mss); - mss.vma = vma; /* mmap_sem is held in m_start */ - if (vma->vm_mm && !is_vm_hugetlb_page(vma)) - walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk); + walk_page_vma(vma, &smaps_walk); show_map_vma(m, vma, is_pid); @@ -604,7 +678,10 @@ "Referenced: %8lu kB\n" "Anonymous: %8lu kB\n" "AnonHugePages: %8lu kB\n" + "Shared_Hugetlb: %8lu kB\n" + "Private_Hugetlb: %7lu kB\n" "Swap: %8lu kB\n" + "SwapPss: %8lu kB\n" "KernelPageSize: %8lu kB\n" "MMUPageSize: %8lu kB\n" "Locked: %8lu kB\n", @@ -618,21 +695,17 @@ mss.referenced >> 10, mss.anonymous >> 10, mss.anonymous_thp >> 10, + mss.shared_hugetlb >> 10, + mss.private_hugetlb >> 10, mss.swap >> 10, + (unsigned long)(mss.swap_pss >> (10 + PSS_SHIFT)), vma_kernel_pagesize(vma) >> 10, vma_mmu_pagesize(vma) >> 10, (vma->vm_flags & VM_LOCKED) ? (unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0); - if (vma->vm_flags & VM_NONLINEAR) - seq_printf(m, "Nonlinear: %8lu kB\n", - mss.nonlinear >> 10); - show_smap_vma_flags(m, vma); - - if (m->count < m->size) /* vma is copied successfully */ - m->version = (vma != get_gate_vma(task->mm)) - ? vma->vm_start : 0; + m_cache_vma(m, vma); return 0; } @@ -674,31 +747,117 @@ .open = pid_smaps_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = proc_map_release, }; const struct file_operations proc_tid_smaps_operations = { .open = tid_smaps_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = proc_map_release, +}; + +enum clear_refs_types { + CLEAR_REFS_ALL = 1, + CLEAR_REFS_ANON, + CLEAR_REFS_MAPPED, + CLEAR_REFS_SOFT_DIRTY, + CLEAR_REFS_MM_HIWATER_RSS, + CLEAR_REFS_LAST, }; +struct clear_refs_private { + enum clear_refs_types type; +}; + +#ifdef CONFIG_MEM_SOFT_DIRTY +static inline void clear_soft_dirty(struct vm_area_struct *vma, + unsigned long addr, pte_t *pte) +{ + /* + * The soft-dirty tracker uses #PF-s to catch writes + * to pages, so write-protect the pte as well. See the + * Documentation/vm/soft-dirty.txt for full description + * of how soft-dirty works. + */ + pte_t ptent = *pte; + + if (pte_present(ptent)) { + ptent = ptep_modify_prot_start(vma->vm_mm, addr, pte); + ptent = pte_wrprotect(ptent); + ptent = pte_clear_soft_dirty(ptent); + ptep_modify_prot_commit(vma->vm_mm, addr, pte, ptent); + } else if (is_swap_pte(ptent)) { + ptent = pte_swp_clear_soft_dirty(ptent); + set_pte_at(vma->vm_mm, addr, pte, ptent); + } +} +#else +static inline void clear_soft_dirty(struct vm_area_struct *vma, + unsigned long addr, pte_t *pte) +{ +} +#endif + +#if defined(CONFIG_MEM_SOFT_DIRTY) && defined(CONFIG_TRANSPARENT_HUGEPAGE) +static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp) +{ + pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp); + + pmd = pmd_wrprotect(pmd); + pmd = pmd_clear_soft_dirty(pmd); + + if (vma->vm_flags & VM_SOFTDIRTY) + vma->vm_flags &= ~VM_SOFTDIRTY; + + set_pmd_at(vma->vm_mm, addr, pmdp, pmd); +} +#else +static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp) +{ +} +#endif + static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { - struct vm_area_struct *vma = walk->private; + struct clear_refs_private *cp = walk->private; + struct vm_area_struct *vma = walk->vma; pte_t *pte, ptent; spinlock_t *ptl; struct page *page; - split_huge_page_pmd(vma, addr, pmd); + if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + if (cp->type == CLEAR_REFS_SOFT_DIRTY) { + clear_soft_dirty_pmd(vma, addr, pmd); + goto out; + } + + page = pmd_page(*pmd); + + /* Clear accessed and referenced bits. */ + pmdp_test_and_clear_young(vma, addr, pmd); + test_and_clear_page_young(page); + ClearPageReferenced(page); +out: + spin_unlock(ptl); + return 0; + } + if (pmd_trans_unstable(pmd)) return 0; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) { ptent = *pte; + + if (cp->type == CLEAR_REFS_SOFT_DIRTY) { + clear_soft_dirty(vma, addr, pte); + continue; + } + if (!pte_present(ptent)) continue; @@ -708,6 +867,7 @@ /* Clear accessed and referenced bits. */ ptep_test_and_clear_young(vma, addr, pte); + test_and_clear_page_young(page); ClearPageReferenced(page); } pte_unmap_unlock(pte - 1, ptl); @@ -715,9 +875,27 @@ return 0; } -#define CLEAR_REFS_ALL 1 -#define CLEAR_REFS_ANON 2 -#define CLEAR_REFS_MAPPED 3 +static int clear_refs_test_walk(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + struct clear_refs_private *cp = walk->private; + struct vm_area_struct *vma = walk->vma; + + if (vma->vm_flags & VM_PFNMAP) + return 1; + + /* + * Writing 1 to /proc/pid/clear_refs affects all pages. + * Writing 2 to /proc/pid/clear_refs only affects anonymous pages. + * Writing 3 to /proc/pid/clear_refs only affects file mapped pages. + * Writing 4 to /proc/pid/clear_refs affects all pages. + */ + if (cp->type == CLEAR_REFS_ANON && vma->vm_file) + return 1; + if (cp->type == CLEAR_REFS_MAPPED && !vma->vm_file) + return 1; + return 0; +} static ssize_t clear_refs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) @@ -726,7 +904,8 @@ char buffer[PROC_NUMBUF]; struct mm_struct *mm; struct vm_area_struct *vma; - int type; + enum clear_refs_types type; + int itype; int rv; memset(buffer, 0, sizeof(buffer)); @@ -734,43 +913,61 @@ count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) return -EFAULT; - rv = kstrtoint(strstrip(buffer), 10, &type); + rv = kstrtoint(strstrip(buffer), 10, &itype); if (rv < 0) return rv; - if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED) + type = (enum clear_refs_types)itype; + if (type < CLEAR_REFS_ALL || type >= CLEAR_REFS_LAST) return -EINVAL; + task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; mm = get_task_mm(task); if (mm) { + struct clear_refs_private cp = { + .type = type, + }; struct mm_walk clear_refs_walk = { .pmd_entry = clear_refs_pte_range, + .test_walk = clear_refs_test_walk, .mm = mm, + .private = &cp, }; - down_read(&mm->mmap_sem); - for (vma = mm->mmap; vma; vma = vma->vm_next) { - clear_refs_walk.private = vma; - if (is_vm_hugetlb_page(vma)) - continue; + + if (type == CLEAR_REFS_MM_HIWATER_RSS) { /* - * Writing 1 to /proc/pid/clear_refs affects all pages. - * - * Writing 2 to /proc/pid/clear_refs only affects - * Anonymous pages. - * - * Writing 3 to /proc/pid/clear_refs only affects file - * mapped pages. + * Writing 5 to /proc/pid/clear_refs resets the peak + * resident set size to this mm's current rss value. */ - if (type == CLEAR_REFS_ANON && vma->vm_file) - continue; - if (type == CLEAR_REFS_MAPPED && !vma->vm_file) - continue; - walk_page_range(vma->vm_start, vma->vm_end, - &clear_refs_walk); + down_write(&mm->mmap_sem); + reset_mm_hiwater_rss(mm); + up_write(&mm->mmap_sem); + goto out_mm; } + + down_read(&mm->mmap_sem); + if (type == CLEAR_REFS_SOFT_DIRTY) { + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (!(vma->vm_flags & VM_SOFTDIRTY)) + continue; + up_read(&mm->mmap_sem); + down_write(&mm->mmap_sem); + for (vma = mm->mmap; vma; vma = vma->vm_next) { + vma->vm_flags &= ~VM_SOFTDIRTY; + vma_set_page_prot(vma); + } + downgrade_write(&mm->mmap_sem); + break; + } + mmu_notifier_invalidate_range_start(mm, 0, -1); + } + walk_page_range(0, ~0UL, &clear_refs_walk); + if (type == CLEAR_REFS_SOFT_DIRTY) + mmu_notifier_invalidate_range_end(mm, 0, -1); flush_tlb_mm(mm); up_read(&mm->mmap_sem); +out_mm: mmput(mm); } put_task_struct(task); @@ -790,32 +987,26 @@ struct pagemapread { int pos, len; /* units: PM_ENTRY_BYTES, not bytes */ pagemap_entry_t *buffer; + bool show_pfn; }; #define PAGEMAP_WALK_SIZE (PMD_SIZE) #define PAGEMAP_WALK_MASK (PMD_MASK) -#define PM_ENTRY_BYTES sizeof(pagemap_entry_t) -#define PM_STATUS_BITS 3 -#define PM_STATUS_OFFSET (64 - PM_STATUS_BITS) -#define PM_STATUS_MASK (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET) -#define PM_STATUS(nr) (((nr) << PM_STATUS_OFFSET) & PM_STATUS_MASK) -#define PM_PSHIFT_BITS 6 -#define PM_PSHIFT_OFFSET (PM_STATUS_OFFSET - PM_PSHIFT_BITS) -#define PM_PSHIFT_MASK (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET) -#define PM_PSHIFT(x) (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK) -#define PM_PFRAME_MASK ((1LL << PM_PSHIFT_OFFSET) - 1) -#define PM_PFRAME(x) ((x) & PM_PFRAME_MASK) - -#define PM_PRESENT PM_STATUS(4LL) -#define PM_SWAP PM_STATUS(2LL) -#define PM_FILE PM_STATUS(1LL) -#define PM_NOT_PRESENT PM_PSHIFT(PAGE_SHIFT) +#define PM_ENTRY_BYTES sizeof(pagemap_entry_t) +#define PM_PFRAME_BITS 55 +#define PM_PFRAME_MASK GENMASK_ULL(PM_PFRAME_BITS - 1, 0) +#define PM_SOFT_DIRTY BIT_ULL(55) +#define PM_MMAP_EXCLUSIVE BIT_ULL(56) +#define PM_FILE BIT_ULL(61) +#define PM_SWAP BIT_ULL(62) +#define PM_PRESENT BIT_ULL(63) + #define PM_END_OF_BUFFER 1 -static inline pagemap_entry_t make_pme(u64 val) +static inline pagemap_entry_t make_pme(u64 frame, u64 flags) { - return (pagemap_entry_t) { .pme = val }; + return (pagemap_entry_t) { .pme = (frame & PM_PFRAME_MASK) | flags }; } static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme, @@ -831,119 +1022,143 @@ struct mm_walk *walk) { struct pagemapread *pm = walk->private; - unsigned long addr; + unsigned long addr = start; int err = 0; - pagemap_entry_t pme = make_pme(PM_NOT_PRESENT); - for (addr = start; addr < end; addr += PAGE_SIZE) { - err = add_to_pagemap(addr, &pme, pm); - if (err) + while (addr < end) { + struct vm_area_struct *vma = find_vma(walk->mm, addr); + pagemap_entry_t pme = make_pme(0, 0); + /* End of address space hole, which we mark as non-present. */ + unsigned long hole_end; + + if (vma) + hole_end = min(end, vma->vm_start); + else + hole_end = end; + + for (; addr < hole_end; addr += PAGE_SIZE) { + err = add_to_pagemap(addr, &pme, pm); + if (err) + goto out; + } + + if (!vma) break; + + /* Addresses in the VMA. */ + if (vma->vm_flags & VM_SOFTDIRTY) + pme = make_pme(0, PM_SOFT_DIRTY); + for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) { + err = add_to_pagemap(addr, &pme, pm); + if (err) + goto out; + } } +out: return err; } -static void pte_to_pagemap_entry(pagemap_entry_t *pme, +static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, struct vm_area_struct *vma, unsigned long addr, pte_t pte) { - u64 frame, flags; + u64 frame = 0, flags = 0; struct page *page = NULL; if (pte_present(pte)) { - frame = pte_pfn(pte); - flags = PM_PRESENT; + if (pm->show_pfn) + frame = pte_pfn(pte); + flags |= PM_PRESENT; page = vm_normal_page(vma, addr, pte); + if (pte_soft_dirty(pte)) + flags |= PM_SOFT_DIRTY; } else if (is_swap_pte(pte)) { - swp_entry_t entry = pte_to_swp_entry(pte); - + swp_entry_t entry; + if (pte_swp_soft_dirty(pte)) + flags |= PM_SOFT_DIRTY; + entry = pte_to_swp_entry(pte); frame = swp_type(entry) | (swp_offset(entry) << MAX_SWAPFILES_SHIFT); - flags = PM_SWAP; + flags |= PM_SWAP; if (is_migration_entry(entry)) page = migration_entry_to_page(entry); - } else { - *pme = make_pme(PM_NOT_PRESENT); - return; } if (page && !PageAnon(page)) flags |= PM_FILE; + if (page && page_mapcount(page) == 1) + flags |= PM_MMAP_EXCLUSIVE; + if (vma->vm_flags & VM_SOFTDIRTY) + flags |= PM_SOFT_DIRTY; - *pme = make_pme(PM_PFRAME(frame) | PM_PSHIFT(PAGE_SHIFT) | flags); -} - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, - pmd_t pmd, int offset) -{ - /* - * Currently pmd for thp is always present because thp can not be - * swapped-out, migrated, or HWPOISONed (split in such cases instead.) - * This if-check is just to prepare for future implementation. - */ - if (pmd_present(pmd)) - *pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset) - | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT); - else - *pme = make_pme(PM_NOT_PRESENT); -} -#else -static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, - pmd_t pmd, int offset) -{ + return make_pme(frame, flags); } -#endif -static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, +static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, struct mm_walk *walk) { - struct vm_area_struct *vma; + struct vm_area_struct *vma = walk->vma; struct pagemapread *pm = walk->private; - pte_t *pte; + spinlock_t *ptl; + pte_t *pte, *orig_pte; int err = 0; - pagemap_entry_t pme = make_pme(PM_NOT_PRESENT); - /* find the first VMA at or above 'addr' */ - vma = find_vma(walk->mm, addr); - if (vma && pmd_trans_huge_lock(pmd, vma) == 1) { +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (pmd_trans_huge_lock(pmdp, vma, &ptl) == 1) { + u64 flags = 0, frame = 0; + pmd_t pmd = *pmdp; + + if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(pmd)) + flags |= PM_SOFT_DIRTY; + + /* + * Currently pmd for thp is always present because thp + * can not be swapped-out, migrated, or HWPOISONed + * (split in such cases instead.) + * This if-check is just to prepare for future implementation. + */ + if (pmd_present(pmd)) { + struct page *page = pmd_page(pmd); + + if (page_mapcount(page) == 1) + flags |= PM_MMAP_EXCLUSIVE; + + flags |= PM_PRESENT; + if (pm->show_pfn) + frame = pmd_pfn(pmd) + + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + } + for (; addr != end; addr += PAGE_SIZE) { - unsigned long offset; + pagemap_entry_t pme = make_pme(frame, flags); - offset = (addr & ~PAGEMAP_WALK_MASK) >> - PAGE_SHIFT; - thp_pmd_to_pagemap_entry(&pme, *pmd, offset); err = add_to_pagemap(addr, &pme, pm); if (err) break; + if (pm->show_pfn && (flags & PM_PRESENT)) + frame++; } - spin_unlock(&walk->mm->page_table_lock); + spin_unlock(ptl); return err; } - if (pmd_trans_unstable(pmd)) + if (pmd_trans_unstable(pmdp)) return 0; - for (; addr != end; addr += PAGE_SIZE) { +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ - /* check to see if we've left 'vma' behind - * and need a new, higher one */ - if (vma && (addr >= vma->vm_end)) { - vma = find_vma(walk->mm, addr); - pme = make_pme(PM_NOT_PRESENT); - } + /* + * We can assume that @vma always points to a valid one and @end never + * goes beyond vma->vm_end. + */ + orig_pte = pte = pte_offset_map_lock(walk->mm, pmdp, addr, &ptl); + for (; addr < end; pte++, addr += PAGE_SIZE) { + pagemap_entry_t pme; - /* check that 'vma' actually covers this address, - * and that it isn't a huge page vma */ - if (vma && (vma->vm_start <= addr) && - !is_vm_hugetlb_page(vma)) { - pte = pte_offset_map(pmd, addr); - pte_to_pagemap_entry(&pme, vma, addr, *pte); - /* unmap before userspace copy */ - pte_unmap(pte); - } + pme = pte_to_pagemap_entry(pm, vma, addr, *pte); err = add_to_pagemap(addr, &pme, pm); if (err) - return err; + break; } + pte_unmap_unlock(orig_pte, ptl); cond_resched(); @@ -951,31 +1166,44 @@ } #ifdef CONFIG_HUGETLB_PAGE -static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, - pte_t pte, int offset) -{ - if (pte_present(pte)) - *pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset) - | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT); - else - *pme = make_pme(PM_NOT_PRESENT); -} - /* This function walks within one hugetlb entry in the single call */ -static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask, +static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct pagemapread *pm = walk->private; + struct vm_area_struct *vma = walk->vma; + u64 flags = 0, frame = 0; int err = 0; - pagemap_entry_t pme; + pte_t pte; + + if (vma->vm_flags & VM_SOFTDIRTY) + flags |= PM_SOFT_DIRTY; + + pte = huge_ptep_get(ptep); + if (pte_present(pte)) { + struct page *page = pte_page(pte); + + if (!PageAnon(page)) + flags |= PM_FILE; + + if (page_mapcount(page) == 1) + flags |= PM_MMAP_EXCLUSIVE; + + flags |= PM_PRESENT; + if (pm->show_pfn) + frame = pte_pfn(pte) + + ((addr & ~hmask) >> PAGE_SHIFT); + } for (; addr != end; addr += PAGE_SIZE) { - int offset = (addr & ~hmask) >> PAGE_SHIFT; - huge_pte_to_pagemap_entry(&pme, *pte, offset); + pagemap_entry_t pme = make_pme(frame, flags); + err = add_to_pagemap(addr, &pme, pm); if (err) return err; + if (pm->show_pfn && (flags & PM_PRESENT)) + frame++; } cond_resched(); @@ -993,7 +1221,9 @@ * Bits 0-54 page frame number (PFN) if present * Bits 0-4 swap type if swapped * Bits 5-54 swap offset if swapped - * Bits 55-60 page shift (page size = 1<private_data; struct pagemapread pm; - int ret = -ESRCH; struct mm_walk pagemap_walk = {}; unsigned long src; unsigned long svpfn; unsigned long start_vaddr; unsigned long end_vaddr; - int copied = 0; + int ret = 0, copied = 0; - if (!task) + if (!mm || !atomic_inc_not_zero(&mm->mm_users)) goto out; ret = -EINVAL; /* file position must be aligned */ if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES)) - goto out_task; + goto out_mm; ret = 0; if (!count) - goto out_task; + goto out_mm; + + /* do not disclose physical addresses: attack vector */ + pm.show_pfn = file_ns_capable(file, &init_user_ns, CAP_SYS_ADMIN); pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT); pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY); ret = -ENOMEM; if (!pm.buffer) - goto out_task; - - mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); - ret = PTR_ERR(mm); - if (!mm || IS_ERR(mm)) - goto out_free; + goto out_mm; - pagemap_walk.pmd_entry = pagemap_pte_range; + pagemap_walk.pmd_entry = pagemap_pmd_range; pagemap_walk.pte_hole = pagemap_pte_hole; #ifdef CONFIG_HUGETLB_PAGE pagemap_walk.hugetlb_entry = pagemap_hugetlb_range; @@ -1056,10 +1282,10 @@ src = *ppos; svpfn = src / PM_ENTRY_BYTES; start_vaddr = svpfn << PAGE_SHIFT; - end_vaddr = TASK_SIZE_OF(task); + end_vaddr = mm->task_size; /* watch out for wraparound */ - if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT) + if (svpfn > mm->task_size >> PAGE_SHIFT) start_vaddr = end_vaddr; /* @@ -1086,7 +1312,7 @@ len = min(count, PM_ENTRY_BYTES * pm.pos); if (copy_to_user(buf, pm.buffer, len)) { ret = -EFAULT; - goto out_mm; + goto out_free; } copied += len; buf += len; @@ -1096,22 +1322,31 @@ if (!ret || ret == PM_END_OF_BUFFER) ret = copied; -out_mm: - mmput(mm); out_free: kfree(pm.buffer); -out_task: - put_task_struct(task); +out_mm: + mmput(mm); out: return ret; } static int pagemap_open(struct inode *inode, struct file *file) { - /* do not disclose physical addresses to unprivileged - userspace (closes a rowhammer attack vector) */ - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; + struct mm_struct *mm; + + mm = proc_mem_open(inode, PTRACE_MODE_READ); + if (IS_ERR(mm)) + return PTR_ERR(mm); + file->private_data = mm; + return 0; +} + +static int pagemap_release(struct inode *inode, struct file *file) +{ + struct mm_struct *mm = file->private_data; + + if (mm) + mmdrop(mm); return 0; } @@ -1119,13 +1354,13 @@ .llseek = mem_lseek, /* borrow this */ .read = pagemap_read, .open = pagemap_open, + .release = pagemap_release, }; #endif /* CONFIG_PROC_PAGE_MONITOR */ #ifdef CONFIG_NUMA struct numa_maps { - struct vm_area_struct *vma; unsigned long pages; unsigned long anon; unsigned long active; @@ -1191,33 +1426,59 @@ return page; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static struct page *can_gather_numa_stats_pmd(pmd_t pmd, + struct vm_area_struct *vma, + unsigned long addr) +{ + struct page *page; + int nid; + + if (!pmd_present(pmd)) + return NULL; + + page = vm_normal_page_pmd(vma, addr, pmd); + if (!page) + return NULL; + + if (PageReserved(page)) + return NULL; + + nid = page_to_nid(page); + if (!node_isset(nid, node_states[N_MEMORY])) + return NULL; + + return page; +} +#endif + static int gather_pte_stats(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { - struct numa_maps *md; + struct numa_maps *md = walk->private; + struct vm_area_struct *vma = walk->vma; spinlock_t *ptl; pte_t *orig_pte; pte_t *pte; - md = walk->private; - - if (pmd_trans_huge_lock(pmd, md->vma) == 1) { - pte_t huge_pte = *(pte_t *)pmd; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { struct page *page; - page = can_gather_numa_stats(huge_pte, md->vma, addr); + page = can_gather_numa_stats_pmd(*pmd, vma, addr); if (page) - gather_stats(page, md, pte_dirty(huge_pte), + gather_stats(page, md, pmd_dirty(*pmd), HPAGE_PMD_SIZE/PAGE_SIZE); - spin_unlock(&walk->mm->page_table_lock); + spin_unlock(ptl); return 0; } if (pmd_trans_unstable(pmd)) return 0; +#endif orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); do { - struct page *page = can_gather_numa_stats(*pte, md->vma, addr); + struct page *page = can_gather_numa_stats(*pte, vma, addr); if (!page) continue; gather_stats(page, md, pte_dirty(*pte), 1); @@ -1227,26 +1488,27 @@ return 0; } #ifdef CONFIG_HUGETLB_PAGE -static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask, +static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { + pte_t huge_pte = huge_ptep_get(pte); struct numa_maps *md; struct page *page; - if (pte_none(*pte)) + if (!pte_present(huge_pte)) return 0; - page = pte_page(*pte); + page = pte_page(huge_pte); if (!page) return 0; md = walk->private; - gather_stats(page, md, pte_dirty(*pte), 1); + gather_stats(page, md, pte_dirty(huge_pte), 1); return 0; } #else -static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask, +static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { return 0; @@ -1263,12 +1525,16 @@ struct vm_area_struct *vma = v; struct numa_maps *md = &numa_priv->md; struct file *file = vma->vm_file; - struct task_struct *task = proc_priv->task; struct mm_struct *mm = vma->vm_mm; - struct mm_walk walk = {}; + struct mm_walk walk = { + .hugetlb_entry = gather_hugetlb_stats, + .pmd_entry = gather_pte_stats, + .private = md, + .mm = mm, + }; struct mempolicy *pol; - int n; - char buffer[50]; + char buffer[64]; + int nid; if (!mm) return 0; @@ -1276,43 +1542,30 @@ /* Ensure we start with an empty set of numa_maps statistics. */ memset(md, 0, sizeof(*md)); - md->vma = vma; - - walk.hugetlb_entry = gather_hugetbl_stats; - walk.pmd_entry = gather_pte_stats; - walk.private = md; - walk.mm = mm; - - pol = get_vma_policy(task, vma, vma->vm_start); - mpol_to_str(buffer, sizeof(buffer), pol); - mpol_cond_put(pol); + pol = __get_vma_policy(vma, vma->vm_start); + if (pol) { + mpol_to_str(buffer, sizeof(buffer), pol); + mpol_cond_put(pol); + } else { + mpol_to_str(buffer, sizeof(buffer), proc_priv->task_mempolicy); + } seq_printf(m, "%08lx %s", vma->vm_start, buffer); if (file) { - seq_printf(m, " file="); - seq_path(m, &file->f_path, "\n\t= "); + seq_puts(m, " file="); + seq_file_path(m, file, "\n\t= "); } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) { - seq_printf(m, " heap"); - } else { - pid_t tid = vm_is_stack(task, vma, is_pid); - if (tid != 0) { - /* - * Thread stack in /proc/PID/task/TID/maps or - * the main process stack. - */ - if (!is_pid || (vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack)) - seq_printf(m, " stack"); - else - seq_printf(m, " stack:%d", tid); - } + seq_puts(m, " heap"); + } else if (is_stack(proc_priv, vma, is_pid)) { + seq_puts(m, " stack"); } if (is_vm_hugetlb_page(vma)) - seq_printf(m, " huge"); + seq_puts(m, " huge"); - walk_page_range(vma->vm_start, vma->vm_end, &walk); + /* mmap_sem is held by m_start */ + walk_page_vma(vma, &walk); if (!md->pages) goto out; @@ -1338,14 +1591,14 @@ if (md->writeback) seq_printf(m, " writeback=%lu", md->writeback); - for_each_node_state(n, N_MEMORY) - if (md->node[n]) - seq_printf(m, " N%d=%lu", n, md->node[n]); + for_each_node_state(nid, N_MEMORY) + if (md->node[nid]) + seq_printf(m, " N%d=%lu", nid, md->node[nid]); + + seq_printf(m, " kernelpagesize_kB=%lu", vma_kernel_pagesize(vma) >> 10); out: seq_putc(m, '\n'); - - if (m->count < m->size) - m->version = (vma != proc_priv->tail_vma) ? vma->vm_start : 0; + m_cache_vma(m, vma); return 0; } @@ -1376,20 +1629,8 @@ static int numa_maps_open(struct inode *inode, struct file *file, const struct seq_operations *ops) { - struct numa_maps_private *priv; - int ret = -ENOMEM; - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (priv) { - priv->proc_maps.pid = proc_pid(inode); - ret = seq_open(file, ops); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = priv; - } else { - kfree(priv); - } - } - return ret; + return proc_maps_open(inode, file, ops, + sizeof(struct numa_maps_private)); } static int pid_numa_maps_open(struct inode *inode, struct file *file) @@ -1406,13 +1647,13 @@ .open = pid_numa_maps_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = proc_map_release, }; const struct file_operations proc_tid_numa_maps_operations = { .open = tid_numa_maps_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = proc_map_release, }; #endif /* CONFIG_NUMA */