From e7dcd9990e42ccfc798d4eb55e2dbf9d7d434c6b Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 31 May 2012 16:26:17 -0700 Subject: proc: remove mm_for_maps() mm_for_maps() is a simple wrapper for mm_access(), and the name is misleading, so just remove it and use mm_access() directly. Signed-off-by: Cong Wang Cc: Oleg Nesterov Cc: Alexey Dobriyan Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/proc/task_mmu.c') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 7faaf2acc57..83ede6e3b5e 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -125,7 +125,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) if (!priv->task) return ERR_PTR(-ESRCH); - mm = mm_for_maps(priv->task); + mm = mm_access(priv->task, PTRACE_MODE_READ); if (!mm || IS_ERR(mm)) return mm; down_read(&mm->mmap_sem); @@ -919,7 +919,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, if (!pm.buffer) goto out_task; - mm = mm_for_maps(task); + mm = mm_access(task, PTRACE_MODE_READ); ret = PTR_ERR(mm); if (!mm || IS_ERR(mm)) goto out_free; -- cgit v1.2.3-70-g09d2 From 052fb0d635df5d49dfc85687d94e1a87bf09378d Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 31 May 2012 16:26:19 -0700 Subject: proc: report file/anon bit in /proc/pid/pagemap This is an implementation of Andrew's proposal to extend the pagemap file bits to report what is missing about tasks' working set. The problem with the working set detection is multilateral. In the criu (checkpoint/restore) project we dump the tasks' memory into image files and to do it properly we need to detect which pages inside mappings are really in use. The mincore syscall I though could help with this did not. First, it doesn't report swapped pages, thus we cannot find out which parts of anonymous mappings to dump. Next, it does report pages from page cache as present even if they are not mapped, and it doesn't make that has not been cow-ed. Note, that issue with swap pages is critical -- we must dump swap pages to image file. But the issues with file pages are optimization -- we can take all file pages to image, this would be correct, but if we know that a page is not mapped or not cow-ed, we can remove them from dump file. The dump would still be self-consistent, though significantly smaller in size (up to 10 times smaller on real apps). Andrew noticed, that the proc pagemap file solved 2 of 3 above issues -- it reports whether a page is present or swapped and it doesn't report not mapped page cache pages. But, it doesn't distinguish cow-ed file pages from not cow-ed. I would like to make the last unused bit in this file to report whether the page mapped into respective pte is PageAnon or not. [comment stolen from Pavel Emelyanov's v1 patch] Signed-off-by: Konstantin Khlebnikov Cc: Pavel Emelyanov Cc: Matt Mackall Cc: Hugh Dickins Cc: Rik van Riel Acked-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/pagemap.txt | 2 +- fs/proc/task_mmu.c | 48 +++++++++++++++++++++++++++----------------- 2 files changed, 31 insertions(+), 19 deletions(-) (limited to 'fs/proc/task_mmu.c') diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt index 4600cbe3d6b..7587493c67f 100644 --- a/Documentation/vm/pagemap.txt +++ b/Documentation/vm/pagemap.txt @@ -16,7 +16,7 @@ There are three components to pagemap: * Bits 0-4 swap type if swapped * Bits 5-54 swap offset if swapped * Bits 55-60 page shift (page size = 1<vm_start <= addr) && !is_vm_hugetlb_page(vma)) { pte = pte_offset_map(pmd, addr); - pte_to_pagemap_entry(&pme, *pte); + pte_to_pagemap_entry(&pme, vma, addr, *pte); /* unmap before userspace copy */ pte_unmap(pte); } @@ -869,11 +881,11 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask, * For each page in the address space, this file contains one 64-bit entry * consisting of the following: * - * Bits 0-55 page frame number (PFN) if present + * Bits 0-54 page frame number (PFN) if present * Bits 0-4 swap type if swapped - * Bits 5-55 swap offset if swapped + * Bits 5-54 swap offset if swapped * Bits 55-60 page shift (page size = 1< Date: Thu, 31 May 2012 16:26:20 -0700 Subject: proc/smaps: carefully handle migration entries Currently smaps reports migration entries as "swap", as result "swap" can appears in shared mapping. This patch converts migration entries into pages and handles them as usual. Signed-off-by: Konstantin Khlebnikov Cc: Andi Kleen Cc: Pavel Emelyanov Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'fs/proc/task_mmu.c') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 02476f5889f..e2c1155ac09 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -402,18 +402,20 @@ static void smaps_pte_entry(pte_t ptent, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = mss->vma; - struct page *page; + struct page *page = NULL; int mapcount; - if (is_swap_pte(ptent)) { - mss->swap += ptent_size; - return; - } + 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(ptent)) - return; + if (!non_swap_entry(swpent)) + mss->swap += ptent_size; + else if (is_migration_entry(swpent)) + page = migration_entry_to_page(swpent); + } - page = vm_normal_page(vma, addr, ptent); if (!page) return; -- cgit v1.2.3-70-g09d2 From bca15543736f9be6d84e0bbc262ea7069076b9e6 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 31 May 2012 16:26:20 -0700 Subject: proc/smaps: show amount of nonlinear ptes in vma Currently, nonlinear mappings can not be distinguished from ordinary mappings. This patch adds into /proc/pid/smaps line "Nonlinear: kB", where size is amount of nonlinear ptes in vma, this line appears only if VM_NONLINEAR is set. This information may be useful not only for checkpoint/restore project. Requested by Pavel Emelyanov. Signed-off-by: Konstantin Khlebnikov Cc: Andi Kleen Cc: Pavel Emelyanov Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'fs/proc/task_mmu.c') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index e2c1155ac09..4540b8f76f1 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -393,6 +393,7 @@ struct mem_size_stats { unsigned long anonymous; unsigned long anonymous_thp; unsigned long swap; + unsigned long nonlinear; u64 pss; }; @@ -402,6 +403,7 @@ static void smaps_pte_entry(pte_t ptent, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = mss->vma; + pgoff_t pgoff = linear_page_index(vma, addr); struct page *page = NULL; int mapcount; @@ -414,6 +416,9 @@ static void smaps_pte_entry(pte_t ptent, unsigned long addr, mss->swap += ptent_size; 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) @@ -422,6 +427,9 @@ static void smaps_pte_entry(pte_t ptent, unsigned long addr, if (PageAnon(page)) mss->anonymous += ptent_size; + if (page->index != pgoff) + mss->nonlinear += ptent_size; + mss->resident += ptent_size; /* Accumulate the size in pages that have been accessed. */ if (pte_young(ptent) || PageReferenced(page)) @@ -523,6 +531,10 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) (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); + if (m->count < m->size) /* vma is copied successfully */ m->version = (vma != get_gate_vma(task->mm)) ? vma->vm_start : 0; -- cgit v1.2.3-70-g09d2