afs: Fix mmap coherency vs 3rd-party changes

Fix the coherency management of mmap'd data such that 3rd-party changes
become visible as soon as possible after the callback notification is
delivered by the fileserver.  This is done by the following means:

 (1) When we break a callback on a vnode specified by the CB.CallBack call
     from the server, we queue a work item (vnode->cb_work) to go and
     clobber all the PTEs mapping to that inode.

     This causes the CPU to trip through the ->map_pages() and
     ->page_mkwrite() handlers if userspace attempts to access the page(s)
     again.

     (Ideally, this would be done in the service handler for CB.CallBack,
     but the server is waiting for our reply before considering, and we
     have a list of vnodes, all of which need breaking - and the process of
     getting the mmap_lock and stripping the PTEs on all CPUs could be
     quite slow.)

 (2) Call afs_validate() from the ->map_pages() handler to check to see if
     the file has changed and to get a new callback promise from the
     server.

Also handle the fileserver telling us that it's dropping all callbacks,
possibly after it's been restarted by sending us a CB.InitCallBackState*
call by the following means:

 (3) Maintain a per-cell list of afs files that are currently mmap'd
     (cell->fs_open_mmaps).

 (4) Add a work item to each server that is invoked if there are any open
     mmaps when CB.InitCallBackState happens.  This work item goes through
     the aforementioned list and invokes the vnode->cb_work work item for
     each one that is currently using this server.

     This causes the PTEs to be cleared, causing ->map_pages() or
     ->page_mkwrite() to be called again, thereby calling afs_validate()
     again.

I've chosen to simply strip the PTEs at the point of notification reception
rather than invalidate all the pages as well because (a) it's faster, (b)
we may get a notification for other reasons than the data being altered (in
which case we don't want to clobber the pagecache) and (c) we need to ask
the server to find out - and I don't want to wait for the reply before
holding up userspace.

This was tested using the attached test program:

	#include <stdbool.h>
	#include <stdio.h>
	#include <stdlib.h>
	#include <unistd.h>
	#include <fcntl.h>
	#include <sys/mman.h>
	int main(int argc, char *argv[])
	{
		size_t size = getpagesize();
		unsigned char *p;
		bool mod = (argc == 3);
		int fd;
		if (argc != 2 && argc != 3) {
			fprintf(stderr, "Format: %s <file> [mod]\n", argv[0]);
			exit(2);
		}
		fd = open(argv[1], mod ? O_RDWR : O_RDONLY);
		if (fd < 0) {
			perror(argv[1]);
			exit(1);
		}

		p = mmap(NULL, size, mod ? PROT_READ|PROT_WRITE : PROT_READ,
			 MAP_SHARED, fd, 0);
		if (p == MAP_FAILED) {
			perror("mmap");
			exit(1);
		}
		for (;;) {
			if (mod) {
				p[0]++;
				msync(p, size, MS_ASYNC);
				fsync(fd);
			}
			printf("%02x", p[0]);
			fflush(stdout);
			sleep(1);
		}
	}

It runs in two modes: in one mode, it mmaps a file, then sits in a loop
reading the first byte, printing it and sleeping for a second; in the
second mode it mmaps a file, then sits in a loop incrementing the first
byte and flushing, then printing and sleeping.

Two instances of this program can be run on different machines, one doing
the reading and one doing the writing.  The reader should see the changes
made by the writer, but without this patch, they aren't because validity
checking is being done lazily - only on entry to the filesystem.

Testing the InitCallBackState change is more complicated.  The server has
to be taken offline, the saved callback state file removed and then the
server restarted whilst the reading-mode program continues to run.  The
client machine then has to poke the server to trigger the InitCallBackState
call.

Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Markus Suvanto <markus.suvanto@gmail.com>
cc: linux-afs@lists.infradead.org
Link: https://lore.kernel.org/r/163111668833.283156.382633263709075739.stgit@warthog.procyon.org.uk/

1 files changed, 40 insertions, 2 deletions

diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index 7d9b23d981bf..1dd7543dbf9f 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -21,6 +21,37 @@
 #include "internal.h"
 
 /*
+ * Handle invalidation of an mmap'd file.  We invalidate all the PTEs referring
+ * to the pages in this file's pagecache, forcing the kernel to go through
+ * ->fault() or ->page_mkwrite() - at which point we can handle invalidation
+ * more fully.
+ */
+void afs_invalidate_mmap_work(struct work_struct *work)
+{
+	struct afs_vnode *vnode = container_of(work, struct afs_vnode, cb_work);
+
+	unmap_mapping_pages(vnode->vfs_inode.i_mapping, 0, 0, false);
+}
+
+void afs_server_init_callback_work(struct work_struct *work)
+{
+	struct afs_server *server = container_of(work, struct afs_server, initcb_work);
+	struct afs_vnode *vnode;
+	struct afs_cell *cell = server->cell;
+
+	down_read(&cell->fs_open_mmaps_lock);
+
+	list_for_each_entry(vnode, &cell->fs_open_mmaps, cb_mmap_link) {
+		if (vnode->cb_server == server) {
+			clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
+			queue_work(system_unbound_wq, &vnode->cb_work);
+		}
+	}
+
+	up_read(&cell->fs_open_mmaps_lock);
+}
+
+/*
  * Allow the fileserver to request callback state (re-)initialisation.
  * Unfortunately, UUIDs are not guaranteed unique.
  */
@@ -29,8 +60,10 @@ void afs_init_callback_state(struct afs_server *server)
 	rcu_read_lock();
 	do {
 		server->cb_s_break++;
-		server = rcu_dereference(server->uuid_next);
-	} while (0);
+		if (!list_empty(&server->cell->fs_open_mmaps))
+			queue_work(system_unbound_wq, &server->initcb_work);
+
+	} while ((server = rcu_dereference(server->uuid_next)));
 	rcu_read_unlock();
 }
 
@@ -49,6 +82,11 @@ void __afs_break_callback(struct afs_vnode *vnode, enum afs_cb_break_reason reas
 		if (vnode->lock_state == AFS_VNODE_LOCK_WAITING_FOR_CB)
 			afs_lock_may_be_available(vnode);
 
+		if (reason != afs_cb_break_for_deleted &&
+		    vnode->status.type == AFS_FTYPE_FILE &&
+		    atomic_read(&vnode->cb_nr_mmap))
+			queue_work(system_unbound_wq, &vnode->cb_work);
+
 		trace_afs_cb_break(&vnode->fid, vnode->cb_break, reason, true);
 	} else {
 		trace_afs_cb_break(&vnode->fid, vnode->cb_break, reason, false);