[PATCH RFC 14/16] fs/proc/vmcore: let procfs copy out reads

Implement ->proc_read_buf() so procfs copies what is read to userspace
after it unpinned the entry. __read_vmcore() fills procfs' buffer
through a kvec iov_iter. So a read goes through that buffer now instead
of straight from the old memory into the reader's, which is what
splice() did already. mmap() isn't affected. On ppc64 a machine check
while reading the old memory used to be recovered through the exception
table of copy_to_user(), by accident. copy_oldmem_page() copies with
_copy_mc_to_iter() now, so a read through procfs' buffer recovers from
it as well.

The buffer is 128k, which keeps the entry pinned for one such piece at
a time, and /proc/vmcore asks for PROC_ENTRY_FULL_READS so that a
larger read is filled in pieces. kexec-tools treats a short read of it
as fatal. A read that faults on its buffer in a later piece returns the
pieces before it now instead of failing with -EFAULT. fadump removes
/proc/vmcore when its memory is released and that no longer waits for a
reader that faults on its buffer.

Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>
---
 fs/proc/vmcore.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index ccb795b85509..1c1e71231f4e 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c

@@ -27,6 +27,7 @@
 #include <linux/mutex.h>
 #include <linux/vmalloc.h>
 #include <linux/pagemap.h>
+#include <linux/sizes.h>
 #include <linux/uio.h>
 #include <linux/cc_platform.h>
 #include <asm/io.h>

@@ -427,9 +428,14 @@ static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos)
 	return acc;
 }
 
-static ssize_t read_vmcore(struct kiocb *iocb, struct iov_iter *iter)
+static ssize_t read_vmcore(struct file *file, char *buf, size_t count,
+			   loff_t *ppos)
 {
-	return __read_vmcore(iter, &iocb->ki_pos);
+	struct kvec kvec = { .iov_base = buf, .iov_len = count };
+	struct iov_iter iter;
+
+	iov_iter_kvec(&iter, ITER_DEST, &kvec, 1, count);
+	return __read_vmcore(&iter, ppos);
 }
 
 /**

@@ -709,9 +715,11 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 #endif
 
 static const struct proc_ops vmcore_proc_ops = {
+	.proc_flags	= PROC_ENTRY_FULL_READS,
 	.proc_open	= open_vmcore,
 	.proc_release	= release_vmcore,
-	.proc_read_iter	= read_vmcore,
+	.proc_read_buf	= read_vmcore,
+	.proc_read_size	= SZ_128K,
 	.proc_lseek	= default_llseek,
 	.proc_mmap	= mmap_vmcore,
 };

-- 
2.53.0