linux-kernel - [PATCH v3 38/66] fs/proc/task_mmu: Stop using linked list and highest_vm

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20211005012959.1110504-39-Liam.Howlett@oracle.com>
Date:   Tue, 5 Oct 2021 01:30:53 +0000
From:   Liam Howlett <liam.howlett@...cle.com>
To:     "maple-tree@...ts.infradead.org" <maple-tree@...ts.infradead.org>,
        "linux-mm@...ck.org" <linux-mm@...ck.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        David Hildenbrand <david@...hat.com>,
        Douglas Gilbert <dgilbert@...erlog.com>
CC:     Song Liu <songliubraving@...com>,
        Davidlohr Bueso <dave@...olabs.net>,
        "Paul E . McKenney" <paulmck@...nel.org>,
        Matthew Wilcox <willy@...radead.org>,
        David Rientjes <rientjes@...gle.com>,
        Axel Rasmussen <axelrasmussen@...gle.com>,
        Suren Baghdasaryan <surenb@...gle.com>,
        Vlastimil Babka <vbabka@...e.cz>,
        Rik van Riel <riel@...riel.com>,
        Peter Zijlstra <peterz@...radead.org>
Subject: [PATCH v3 38/66] fs/proc/task_mmu: Stop using linked list and
 highest_vm_end

From: "Liam R. Howlett" <Liam.Howlett@...cle.com>

Remove references to mm_struct linked list and highest_vm_end for when they are removed

Signed-off-by: Liam R. Howlett <Liam.Howlett@...cle.com>
---
 fs/proc/task_mmu.c | 47 ++++++++++++++++++++++++++++------------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 63d07414d583..e2482ceab6dc 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -164,14 +164,13 @@ static void *m_start(struct seq_file *m, loff_t *ppos)
 static void *m_next(struct seq_file *m, void *v, loff_t *ppos)
 {
 	struct proc_maps_private *priv = m->private;
-	struct vm_area_struct *next, *vma = v;
+	struct vm_area_struct *next = NULL, *vma = v;
 
-	if (vma == priv->tail_vma)
-		next = NULL;
-	else if (vma->vm_next)
-		next = vma->vm_next;
-	else
-		next = priv->tail_vma;
+	if (vma != priv->tail_vma) {
+		next = vma_next(vma->vm_mm, vma);
+		if (!next)
+			next = priv->tail_vma;
+	}
 
 	*ppos = next ? next->vm_start : -1UL;
 
@@ -839,16 +838,16 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
 {
 	struct proc_maps_private *priv = m->private;
 	struct mem_size_stats mss;
-	struct mm_struct *mm;
+	struct mm_struct *mm = priv->mm;
 	struct vm_area_struct *vma;
-	unsigned long last_vma_end = 0;
+	unsigned long vma_start = 0, last_vma_end = 0;
 	int ret = 0;
+	MA_STATE(mas, &mm->mm_mt, 0, 0);
 
 	priv->task = get_proc_task(priv->inode);
 	if (!priv->task)
 		return -ESRCH;
 
-	mm = priv->mm;
 	if (!mm || !mmget_not_zero(mm)) {
 		ret = -ESRCH;
 		goto out_put_task;
@@ -861,8 +860,14 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
 		goto out_put_mm;
 
 	hold_task_mempolicy(priv);
+	rcu_read_lock();
+	vma = mas_find(&mas, 0);
+
+	if (unlikely(!vma))
+		goto empty_set;
 
-	for (vma = priv->mm->mmap; vma;) {
+	vma_start = vma->vm_start;
+	do {
 		smap_gather_stats(vma, &mss, 0);
 		last_vma_end = vma->vm_end;
 
@@ -871,12 +876,15 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
 		 * access it for write request.
 		 */
 		if (mmap_lock_is_contended(mm)) {
+			rcu_read_unlock();
+			mas_pause(&mas);
 			mmap_read_unlock(mm);
 			ret = mmap_read_lock_killable(mm);
 			if (ret) {
 				release_task_mempolicy(priv);
 				goto out_put_mm;
 			}
+			rcu_read_lock();
 
 			/*
 			 * After dropping the lock, there are four cases to
@@ -914,7 +922,7 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
 			 *    contains last_vma_end.
 			 *    Iterate VMA' from last_vma_end.
 			 */
-			vma = find_vma(mm, last_vma_end - 1);
+			vma = mas_find(&mas, ULONG_MAX);
 			/* Case 3 above */
 			if (!vma)
 				break;
@@ -928,16 +936,16 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
 				smap_gather_stats(vma, &mss, last_vma_end);
 		}
 		/* Case 2 above */
-		vma = vma->vm_next;
-	}
+	} while ((vma = mas_find(&mas, ULONG_MAX)) != NULL);
 
-	show_vma_header_prefix(m, priv->mm->mmap->vm_start,
-			       last_vma_end, 0, 0, 0, 0);
+empty_set:
+	show_vma_header_prefix(m, vma_start, last_vma_end, 0, 0, 0, 0);
 	seq_pad(m, ' ');
 	seq_puts(m, "[rollup]\n");
 
 	__show_smap(m, &mss, true);
 
+	rcu_read_unlock();
 	release_task_mempolicy(priv);
 	mmap_read_unlock(mm);
 
@@ -1225,6 +1233,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 		return -ESRCH;
 	mm = get_task_mm(task);
 	if (mm) {
+		MA_STATE(mas, &mm->mm_mt, 0, 0);
 		struct mmu_notifier_range range;
 		struct clear_refs_private cp = {
 			.type = type,
@@ -1244,19 +1253,21 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 		}
 
 		if (type == CLEAR_REFS_SOFT_DIRTY) {
-			for (vma = mm->mmap; vma; vma = vma->vm_next) {
+			mas_lock(&mas);
+			mas_for_each(&mas, vma, ULONG_MAX) {
 				if (!(vma->vm_flags & VM_SOFTDIRTY))
 					continue;
 				vma->vm_flags &= ~VM_SOFTDIRTY;
 				vma_set_page_prot(vma);
 			}
+			mas_unlock(&mas);
 
 			inc_tlb_flush_pending(mm);
 			mmu_notifier_range_init(&range, MMU_NOTIFY_SOFT_DIRTY,
 						0, NULL, mm, 0, -1UL);
 			mmu_notifier_invalidate_range_start(&range);
 		}
-		walk_page_range(mm, 0, mm->highest_vm_end, &clear_refs_walk_ops,
+		walk_page_range(mm, 0, -1, &clear_refs_walk_ops,
 				&cp);
 		if (type == CLEAR_REFS_SOFT_DIRTY) {
 			mmu_notifier_invalidate_range_end(&range);
-- 
2.30.2