Le 03/09/2020 à 09:11, Christoph Hellwig a écrit :
Except that we do not actually have such a patch. For normal user
writes we only use ->write_iter if ->write is not present. But what
shows up in the profile is that /dev/zero only has a read_iter op and
not a normal read. I've added a patch below that implements a normal
read which might help a tad with this workload, but should not be part
of a regression.
With that patch below, throughput is 113.5MB/s (instead of 99.9MB/s).
So a 14% improvement. That's not bad.
Christophe
---
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index abd4ffdc8cdebc..1dc99ab158457a 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -726,6 +726,27 @@ static ssize_t read_iter_zero(struct kiocb *iocb, struct iov_iter *iter)
return written;
}
+static ssize_t read_zero(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ size_t cleared = 0;
+
+ while (count) {
+ size_t chunk = min_t(size_t, count, PAGE_SIZE);
+
+ if (clear_user(buf + cleared, chunk))
+ return cleared ? cleared : -EFAULT;
+ cleared += chunk;
+ count -= chunk;
+
+ if (signal_pending(current))
+ return cleared ? cleared : -ERESTARTSYS;
+ cond_resched();
+ }
+
+ return cleared;
+}
+
static int mmap_zero(struct file *file, struct vm_area_struct *vma)
{
#ifndef CONFIG_MMU
@@ -921,6 +942,7 @@ static const struct file_operations zero_fops = {
.llseek = zero_lseek,
.write = write_zero,
.read_iter = read_iter_zero,
+ .read = read_zero,
.write_iter = write_iter_zero,
.mmap = mmap_zero,
.get_unmapped_area = get_unmapped_area_zero,
