summary refs log tree commit diff
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/base.c185
-rw-r--r--fs/proc/inode.c7
-rw-r--r--fs/proc/meminfo.c23
-rw-r--r--fs/proc/proc_sysctl.c2
-rw-r--r--fs/proc/task_mmu.c10
5 files changed, 126 insertions, 101 deletions
diff --git a/fs/proc/base.c b/fs/proc/base.c
index a11eb7196ec8..31370da2ee7c 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1024,23 +1024,107 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
 	char buffer[PROC_NUMBUF];
 	int oom_adj = OOM_ADJUST_MIN;
 	size_t len;
-	unsigned long flags;
 
 	if (!task)
 		return -ESRCH;
-	if (lock_task_sighand(task, &flags)) {
-		if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX)
-			oom_adj = OOM_ADJUST_MAX;
-		else
-			oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
-				  OOM_SCORE_ADJ_MAX;
-		unlock_task_sighand(task, &flags);
-	}
+	if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX)
+		oom_adj = OOM_ADJUST_MAX;
+	else
+		oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
+			  OOM_SCORE_ADJ_MAX;
 	put_task_struct(task);
 	len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj);
 	return simple_read_from_buffer(buf, count, ppos, buffer, len);
 }
 
+static int __set_oom_adj(struct file *file, int oom_adj, bool legacy)
+{
+	static DEFINE_MUTEX(oom_adj_mutex);
+	struct mm_struct *mm = NULL;
+	struct task_struct *task;
+	int err = 0;
+
+	task = get_proc_task(file_inode(file));
+	if (!task)
+		return -ESRCH;
+
+	mutex_lock(&oom_adj_mutex);
+	if (legacy) {
+		if (oom_adj < task->signal->oom_score_adj &&
+				!capable(CAP_SYS_RESOURCE)) {
+			err = -EACCES;
+			goto err_unlock;
+		}
+		/*
+		 * /proc/pid/oom_adj is provided for legacy purposes, ask users to use
+		 * /proc/pid/oom_score_adj instead.
+		 */
+		pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
+			  current->comm, task_pid_nr(current), task_pid_nr(task),
+			  task_pid_nr(task));
+	} else {
+		if ((short)oom_adj < task->signal->oom_score_adj_min &&
+				!capable(CAP_SYS_RESOURCE)) {
+			err = -EACCES;
+			goto err_unlock;
+		}
+	}
+
+	/*
+	 * Make sure we will check other processes sharing the mm if this is
+	 * not vfrok which wants its own oom_score_adj.
+	 * pin the mm so it doesn't go away and get reused after task_unlock
+	 */
+	if (!task->vfork_done) {
+		struct task_struct *p = find_lock_task_mm(task);
+
+		if (p) {
+			if (atomic_read(&p->mm->mm_users) > 1) {
+				mm = p->mm;
+				atomic_inc(&mm->mm_count);
+			}
+			task_unlock(p);
+		}
+	}
+
+	task->signal->oom_score_adj = oom_adj;
+	if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE))
+		task->signal->oom_score_adj_min = (short)oom_adj;
+	trace_oom_score_adj_update(task);
+
+	if (mm) {
+		struct task_struct *p;
+
+		rcu_read_lock();
+		for_each_process(p) {
+			if (same_thread_group(task, p))
+				continue;
+
+			/* do not touch kernel threads or the global init */
+			if (p->flags & PF_KTHREAD || is_global_init(p))
+				continue;
+
+			task_lock(p);
+			if (!p->vfork_done && process_shares_mm(p, mm)) {
+				pr_info("updating oom_score_adj for %d (%s) from %d to %d because it shares mm with %d (%s). Report if this is unexpected.\n",
+						task_pid_nr(p), p->comm,
+						p->signal->oom_score_adj, oom_adj,
+						task_pid_nr(task), task->comm);
+				p->signal->oom_score_adj = oom_adj;
+				if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE))
+					p->signal->oom_score_adj_min = (short)oom_adj;
+			}
+			task_unlock(p);
+		}
+		rcu_read_unlock();
+		mmdrop(mm);
+	}
+err_unlock:
+	mutex_unlock(&oom_adj_mutex);
+	put_task_struct(task);
+	return err;
+}
+
 /*
  * /proc/pid/oom_adj exists solely for backwards compatibility with previous
  * kernels.  The effective policy is defined by oom_score_adj, which has a
@@ -1054,10 +1138,8 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
 static ssize_t oom_adj_write(struct file *file, const char __user *buf,
 			     size_t count, loff_t *ppos)
 {
-	struct task_struct *task;
 	char buffer[PROC_NUMBUF];
 	int oom_adj;
-	unsigned long flags;
 	int err;
 
 	memset(buffer, 0, sizeof(buffer));
@@ -1077,23 +1159,6 @@ static ssize_t oom_adj_write(struct file *file, const char __user *buf,
 		goto out;
 	}
 
-	task = get_proc_task(file_inode(file));
-	if (!task) {
-		err = -ESRCH;
-		goto out;
-	}
-
-	task_lock(task);
-	if (!task->mm) {
-		err = -EINVAL;
-		goto err_task_lock;
-	}
-
-	if (!lock_task_sighand(task, &flags)) {
-		err = -ESRCH;
-		goto err_task_lock;
-	}
-
 	/*
 	 * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
 	 * value is always attainable.
@@ -1103,27 +1168,7 @@ static ssize_t oom_adj_write(struct file *file, const char __user *buf,
 	else
 		oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE;
 
-	if (oom_adj < task->signal->oom_score_adj &&
-	    !capable(CAP_SYS_RESOURCE)) {
-		err = -EACCES;
-		goto err_sighand;
-	}
-
-	/*
-	 * /proc/pid/oom_adj is provided for legacy purposes, ask users to use
-	 * /proc/pid/oom_score_adj instead.
-	 */
-	pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
-		  current->comm, task_pid_nr(current), task_pid_nr(task),
-		  task_pid_nr(task));
-
-	task->signal->oom_score_adj = oom_adj;
-	trace_oom_score_adj_update(task);
-err_sighand:
-	unlock_task_sighand(task, &flags);
-err_task_lock:
-	task_unlock(task);
-	put_task_struct(task);
+	err = __set_oom_adj(file, oom_adj, true);
 out:
 	return err < 0 ? err : count;
 }
@@ -1140,15 +1185,11 @@ static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
 	struct task_struct *task = get_proc_task(file_inode(file));
 	char buffer[PROC_NUMBUF];
 	short oom_score_adj = OOM_SCORE_ADJ_MIN;
-	unsigned long flags;
 	size_t len;
 
 	if (!task)
 		return -ESRCH;
-	if (lock_task_sighand(task, &flags)) {
-		oom_score_adj = task->signal->oom_score_adj;
-		unlock_task_sighand(task, &flags);
-	}
+	oom_score_adj = task->signal->oom_score_adj;
 	put_task_struct(task);
 	len = snprintf(buffer, sizeof(buffer), "%hd\n", oom_score_adj);
 	return simple_read_from_buffer(buf, count, ppos, buffer, len);
@@ -1157,9 +1198,7 @@ static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
 static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
 					size_t count, loff_t *ppos)
 {
-	struct task_struct *task;
 	char buffer[PROC_NUMBUF];
-	unsigned long flags;
 	int oom_score_adj;
 	int err;
 
@@ -1180,39 +1219,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
 		goto out;
 	}
 
-	task = get_proc_task(file_inode(file));
-	if (!task) {
-		err = -ESRCH;
-		goto out;
-	}
-
-	task_lock(task);
-	if (!task->mm) {
-		err = -EINVAL;
-		goto err_task_lock;
-	}
-
-	if (!lock_task_sighand(task, &flags)) {
-		err = -ESRCH;
-		goto err_task_lock;
-	}
-
-	if ((short)oom_score_adj < task->signal->oom_score_adj_min &&
-			!capable(CAP_SYS_RESOURCE)) {
-		err = -EACCES;
-		goto err_sighand;
-	}
-
-	task->signal->oom_score_adj = (short)oom_score_adj;
-	if (has_capability_noaudit(current, CAP_SYS_RESOURCE))
-		task->signal->oom_score_adj_min = (short)oom_score_adj;
-	trace_oom_score_adj_update(task);
-
-err_sighand:
-	unlock_task_sighand(task, &flags);
-err_task_lock:
-	task_unlock(task);
-	put_task_struct(task);
+	err = __set_oom_adj(file, oom_score_adj, false);
 out:
 	return err < 0 ? err : count;
 }
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index a5b2c33745b7..c1b72388e571 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -474,6 +474,13 @@ int proc_fill_super(struct super_block *s, void *data, int silent)
 	s->s_magic = PROC_SUPER_MAGIC;
 	s->s_op = &proc_sops;
 	s->s_time_gran = 1;
+
+	/*
+	 * procfs isn't actually a stacking filesystem; however, there is
+	 * too much magic going on inside it to permit stacking things on
+	 * top of it
+	 */
+	s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
 	
 	pde_get(&proc_root);
 	root_inode = proc_get_inode(s, &proc_root);
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 83720460c5bc..09e18fdf61e5 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -40,7 +40,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	si_swapinfo(&i);
 	committed = percpu_counter_read_positive(&vm_committed_as);
 
-	cached = global_page_state(NR_FILE_PAGES) -
+	cached = global_node_page_state(NR_FILE_PAGES) -
 			total_swapcache_pages() - i.bufferram;
 	if (cached < 0)
 		cached = 0;
@@ -105,6 +105,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 #endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 		"AnonHugePages:  %8lu kB\n"
+		"ShmemHugePages: %8lu kB\n"
+		"ShmemPmdMapped: %8lu kB\n"
 #endif
 #ifdef CONFIG_CMA
 		"CmaTotal:       %8lu kB\n"
@@ -136,23 +138,23 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 #endif
 		K(i.totalswap),
 		K(i.freeswap),
-		K(global_page_state(NR_FILE_DIRTY)),
-		K(global_page_state(NR_WRITEBACK)),
-		K(global_page_state(NR_ANON_PAGES)),
-		K(global_page_state(NR_FILE_MAPPED)),
+		K(global_node_page_state(NR_FILE_DIRTY)),
+		K(global_node_page_state(NR_WRITEBACK)),
+		K(global_node_page_state(NR_ANON_MAPPED)),
+		K(global_node_page_state(NR_FILE_MAPPED)),
 		K(i.sharedram),
 		K(global_page_state(NR_SLAB_RECLAIMABLE) +
 				global_page_state(NR_SLAB_UNRECLAIMABLE)),
 		K(global_page_state(NR_SLAB_RECLAIMABLE)),
 		K(global_page_state(NR_SLAB_UNRECLAIMABLE)),
-		global_page_state(NR_KERNEL_STACK) * THREAD_SIZE / 1024,
+		global_page_state(NR_KERNEL_STACK_KB),
 		K(global_page_state(NR_PAGETABLE)),
 #ifdef CONFIG_QUICKLIST
 		K(quicklist_total_size()),
 #endif
-		K(global_page_state(NR_UNSTABLE_NFS)),
+		K(global_node_page_state(NR_UNSTABLE_NFS)),
 		K(global_page_state(NR_BOUNCE)),
-		K(global_page_state(NR_WRITEBACK_TEMP)),
+		K(global_node_page_state(NR_WRITEBACK_TEMP)),
 		K(vm_commit_limit()),
 		K(committed),
 		(unsigned long)VMALLOC_TOTAL >> 10,
@@ -162,8 +164,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		, atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)
 #endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		, K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
-		   HPAGE_PMD_NR)
+		, K(global_node_page_state(NR_ANON_THPS) * HPAGE_PMD_NR)
+		, K(global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR)
+		, K(global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR)
 #endif
 #ifdef CONFIG_CMA
 		, K(totalcma_pages)
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 5e57c3e46e1d..b59db94d2ff4 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -623,7 +623,7 @@ static bool proc_sys_fill_cache(struct file *file,
 
 	qname.name = table->procname;
 	qname.len  = strlen(table->procname);
-	qname.hash = full_name_hash(qname.name, qname.len);
+	qname.hash = full_name_hash(dir, qname.name, qname.len);
 
 	child = d_lookup(dir, &qname);
 	if (!child) {
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 4648c7f63ae2..187d84ef9de9 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -448,6 +448,7 @@ struct mem_size_stats {
 	unsigned long referenced;
 	unsigned long anonymous;
 	unsigned long anonymous_thp;
+	unsigned long shmem_thp;
 	unsigned long swap;
 	unsigned long shared_hugetlb;
 	unsigned long private_hugetlb;
@@ -576,7 +577,12 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 	page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
 	if (IS_ERR_OR_NULL(page))
 		return;
-	mss->anonymous_thp += HPAGE_PMD_SIZE;
+	if (PageAnon(page))
+		mss->anonymous_thp += HPAGE_PMD_SIZE;
+	else if (PageSwapBacked(page))
+		mss->shmem_thp += HPAGE_PMD_SIZE;
+	else
+		VM_BUG_ON_PAGE(1, page);
 	smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd));
 }
 #else
@@ -770,6 +776,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   "Referenced:     %8lu kB\n"
 		   "Anonymous:      %8lu kB\n"
 		   "AnonHugePages:  %8lu kB\n"
+		   "ShmemPmdMapped: %8lu kB\n"
 		   "Shared_Hugetlb: %8lu kB\n"
 		   "Private_Hugetlb: %7lu kB\n"
 		   "Swap:           %8lu kB\n"
@@ -787,6 +794,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   mss.referenced >> 10,
 		   mss.anonymous >> 10,
 		   mss.anonymous_thp >> 10,
+		   mss.shmem_thp >> 10,
 		   mss.shared_hugetlb >> 10,
 		   mss.private_hugetlb >> 10,
 		   mss.swap >> 10,
generated by cgit-pink 1.4.1 (git 2.36.1) at 2024-10-06 06:39:10 +0000