Re: [PATCH v2] x86: bring back rep movsq for user access on CPUs without ERMS

[Linus Torvalds]

On Sun, 3 Sept 2023 at 13:49, Mateusz Guzik <mjguzik@xxxxxxxxx> wrote:
>
> "real fstat" is syscall(5, fd, &sb).
>
> Sapphire Rapids, will-it-scale, ops/s
>
> stock fstat     5088199
> patched fstat   7625244 (+49%)
> real fstat      8540383 (+67% / +12%)
>
> It dodges lockref et al, but it does not dodge SMAP which accounts for
> the difference.

Side note, since I was looking at this, I hacked up a quick way for
architectures to do their own optimized cp_new_stat() that avoids the
double-buffering.

Sadly it *is* architecture-specific due to padding and
architecture-specific field sizes (and thus EOVERFLOW rules), but it
is what it is.

I don't know how much it matters, but it might make a difference. And
'stat()' is most certainly worth optimizing for, even if glibc has
made our life more difficult.

Want to try out another entirely untested patch? Attached.

                Linus
 arch/x86/kernel/sys_x86_64.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
 fs/stat.c                    |  2 +-
 include/linux/stat.h         |  2 ++
 3 files changed, 47 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index c783aeb37dce..fca647f61bc1 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -22,6 +22,50 @@
 #include <asm/elf.h>
 #include <asm/ia32.h>
 
+int cp_new_stat(struct kstat *stat, struct stat __user *ubuf)
+{
+	typeof(ubuf->st_uid) uid;
+	typeof(ubuf->st_gid) gid;
+	typeof(ubuf->st_dev) dev = new_encode_dev(stat->dev);
+	typeof(ubuf->st_rdev) rdev = new_encode_dev(stat->rdev);
+
+	SET_UID(uid, from_kuid_munged(current_user_ns(), stat->uid));
+	SET_GID(gid, from_kgid_munged(current_user_ns(), stat->gid));
+
+	if (!user_write_access_begin(ubuf, sizeof(struct stat)))
+		return -EFAULT;
+
+	unsafe_put_user(dev,			&ubuf->st_dev,		Efault);
+	unsafe_put_user(stat->ino,		&ubuf->st_ino,		Efault);
+	unsafe_put_user(stat->nlink,		&ubuf->st_nlink,	Efault);
+
+	unsafe_put_user(stat->mode,		&ubuf->st_mode,		Efault);
+	unsafe_put_user(uid,			&ubuf->st_uid,		Efault);
+	unsafe_put_user(gid,			&ubuf->st_gid,		Efault);
+	unsafe_put_user(0,			&ubuf->__pad0,		Efault);
+	unsafe_put_user(rdev,			&ubuf->st_rdev,		Efault);
+	unsafe_put_user(stat->size,		&ubuf->st_size,		Efault);
+	unsafe_put_user(stat->blksize,		&ubuf->st_blksize,	Efault);
+	unsafe_put_user(stat->blocks,		&ubuf->st_blocks,	Efault);
+
+	unsafe_put_user(stat->atime.tv_sec,	&ubuf->st_atime,	Efault);
+	unsafe_put_user(stat->atime.tv_nsec,	&ubuf->st_atime_nsec,	Efault);
+	unsafe_put_user(stat->mtime.tv_sec,	&ubuf->st_mtime,	Efault);
+	unsafe_put_user(stat->mtime.tv_nsec,	&ubuf->st_mtime_nsec,	Efault);
+	unsafe_put_user(stat->ctime.tv_sec,	&ubuf->st_ctime,	Efault);
+	unsafe_put_user(stat->ctime.tv_nsec,	&ubuf->st_ctime_nsec,	Efault);
+	unsafe_put_user(0,			&ubuf->__unused[0],	Efault);
+	unsafe_put_user(0,			&ubuf->__unused[1],	Efault);
+	unsafe_put_user(0,			&ubuf->__unused[2],	Efault);
+
+	user_write_access_end();
+	return 0;
+
+Efault:
+	user_write_access_end();
+	return -EFAULT;
+}
+
 /*
  * Align a virtual address to avoid aliasing in the I$ on AMD F15h.
  */
diff --git a/fs/stat.c b/fs/stat.c
index e187dc79a313..782ad646ed27 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -415,7 +415,7 @@ SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, stat
 #  define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st))
 #endif
 
-static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf)
+int __weak cp_new_stat(struct kstat *stat, struct stat __user *statbuf)
 {
 	struct stat tmp;
 
diff --git a/include/linux/stat.h b/include/linux/stat.h
index 52150570d37a..f6199aa3e1cb 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -63,4 +63,6 @@ struct kstat {
 /* file attribute values */
 #define STATX_ATTR_CHANGE_MONOTONIC	0x8000000000000000ULL /* version monotonically increases */
 
+int cp_new_stat(struct kstat *stat, struct stat __user *ubuf);
+
 #endif