proc: faster open/read/close with "permanent" files

Now that "struct proc_ops" exist we can start putting there stuff which
could not fly with VFS "struct file_operations"...

Most of fs/proc/inode.c file is dedicated to make open/read/.../close
reliable in the event of disappearing /proc entries which usually happens
if module is getting removed.  Files like /proc/cpuinfo which never
disappear simply do not need such protection.

Save 2 atomic ops, 1 allocation, 1 free per open/read/close sequence for such
"permanent" files.

Enable "permanent" flag for

	/proc/cpuinfo
	/proc/kmsg
	/proc/modules
	/proc/slabinfo
	/proc/stat
	/proc/sysvipc/*
	/proc/swaps

More will come once I figure out foolproof way to prevent out module
authors from marking their stuff "permanent" for performance reasons
when it is not.

This should help with scalability: benchmark is "read /proc/cpuinfo R times
by N threads scattered over the system".

	N	R	t, s (before)	t, s (after)
	-----------------------------------------------------
	64	4096	1.582458	1.530502	-3.2%
	256	4096	6.371926	6.125168	-3.9%
	1024	4096	25.64888	24.47528	-4.6%

Benchmark source:

#include <chrono>
#include <iostream>
#include <thread>
#include <vector>

#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <unistd.h>

const int NR_CPUS = sysconf(_SC_NPROCESSORS_ONLN);
int N;
const char *filename;
int R;

int xxx = 0;

int glue(int n)
{
	cpu_set_t m;
	CPU_ZERO(&m);
	CPU_SET(n, &m);
	return sched_setaffinity(0, sizeof(cpu_set_t), &m);
}

void f(int n)
{
	glue(n % NR_CPUS);

	while (*(volatile int *)&xxx == 0) {
	}

	for (int i = 0; i < R; i++) {
		int fd = open(filename, O_RDONLY);
		char buf[4096];
		ssize_t rv = read(fd, buf, sizeof(buf));
		asm volatile ("" :: "g" (rv));
		close(fd);
	}
}

int main(int argc, char *argv[])
{
	if (argc < 4) {
		std::cerr << "usage: " << argv[0] << ' ' << "N /proc/filename R
";
		return 1;
	}

	N = atoi(argv[1]);
	filename = argv[2];
	R = atoi(argv[3]);

	for (int i = 0; i < NR_CPUS; i++) {
		if (glue(i) == 0)
			break;
	}

	std::vector<std::thread> T;
	T.reserve(N);
	for (int i = 0; i < N; i++) {
		T.emplace_back(f, i);
	}

	auto t0 = std::chrono::system_clock::now();
	{
		*(volatile int *)&xxx = 1;
		for (auto& t: T) {
			t.join();
		}
	}
	auto t1 = std::chrono::system_clock::now();
	std::chrono::duration<double> dt = t1 - t0;
	std::cout << dt.count() << '
';

	return 0;
}

P.S.:
Explicit randomization marker is added because adding non-function pointer
will silently disable structure layout randomization.

[akpm@linux-foundation.org: coding style fixes]
Reported-by: kbuild test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Joe Perches <joe@perches.com>
Link: http://lkml.kernel.org/r/20200222201539.GA22576@avx2
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 28 insertions, 3 deletions

diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 3faed94e4b65..4ed6dabdf6ff 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -531,6 +531,12 @@ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
 	return p;
 }
 
+static inline void pde_set_flags(struct proc_dir_entry *pde)
+{
+	if (pde->proc_ops->proc_flags & PROC_ENTRY_PERMANENT)
+		pde->flags |= PROC_ENTRY_PERMANENT;
+}
+
 struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
 		struct proc_dir_entry *parent,
 		const struct proc_ops *proc_ops, void *data)
@@ -541,6 +547,7 @@ struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
 	if (!p)
 		return NULL;
 	p->proc_ops = proc_ops;
+	pde_set_flags(p);
 	return proc_register(parent, p);
 }
 EXPORT_SYMBOL(proc_create_data);
@@ -572,6 +579,7 @@ static int proc_seq_release(struct inode *inode, struct file *file)
 }
 
 static const struct proc_ops proc_seq_ops = {
+	/* not permanent -- can call into arbitrary seq_operations */
 	.proc_open	= proc_seq_open,
 	.proc_read	= seq_read,
 	.proc_lseek	= seq_lseek,
@@ -602,6 +610,7 @@ static int proc_single_open(struct inode *inode, struct file *file)
 }
 
 static const struct proc_ops proc_single_ops = {
+	/* not permanent -- can call into arbitrary ->single_show */
 	.proc_open	= proc_single_open,
 	.proc_read	= seq_read,
 	.proc_lseek	= seq_lseek,
@@ -662,9 +671,13 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 
 	de = pde_subdir_find(parent, fn, len);
 	if (de) {
-		rb_erase(&de->subdir_node, &parent->subdir);
-		if (S_ISDIR(de->mode)) {
-			parent->nlink--;
+		if (unlikely(pde_is_permanent(de))) {
+			WARN(1, "removing permanent /proc entry '%s'", de->name);
+			de = NULL;
+		} else {
+			rb_erase(&de->subdir_node, &parent->subdir);
+			if (S_ISDIR(de->mode))
+				parent->nlink--;
 		}
 	}
 	write_unlock(&proc_subdir_lock);
@@ -700,12 +713,24 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
 		write_unlock(&proc_subdir_lock);
 		return -ENOENT;
 	}
+	if (unlikely(pde_is_permanent(root))) {
+		write_unlock(&proc_subdir_lock);
+		WARN(1, "removing permanent /proc entry '%s/%s'",
+			root->parent->name, root->name);
+		return -EINVAL;
+	}
 	rb_erase(&root->subdir_node, &parent->subdir);
 
 	de = root;
 	while (1) {
 		next = pde_subdir_first(de);
 		if (next) {
+			if (unlikely(pde_is_permanent(root))) {
+				write_unlock(&proc_subdir_lock);
+				WARN(1, "removing permanent /proc entry '%s/%s'",
+					next->parent->name, next->name);
+				return -EINVAL;
+			}
 			rb_erase(&next->subdir_node, &de->subdir);
 			de = next;
 			continue;