orangefs: add orangefs_revalidate_mapping

This is modeled after NFS, except our method is different.  We use a
simple timer to determine whether to invalidate the page cache.  This
is bound to perform.

This addes a sysfs parameter cache_timeout_msecs which controls the time
between page cache invalidations.
Signed-off-by: Martin Brandenburg <martin@omnibond.com>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>

fs/orangefs/file.c

@@ -241,18 +241,78 @@ ssize_t wait_for_direct_io(enum ORANGEFS_io_type type, struct inode *inode,
 	return ret;
 }
 
+int orangefs_revalidate_mapping(struct inode *inode)
+{
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	struct address_space *mapping = inode->i_mapping;
+	unsigned long *bitlock = &orangefs_inode->bitlock;
+	int ret;
+
+	while (1) {
+		ret = wait_on_bit(bitlock, 1, TASK_KILLABLE);
+		if (ret)
+			return ret;
+		spin_lock(&inode->i_lock);
+		if (test_bit(1, bitlock)) {
+			spin_unlock(&inode->i_lock);
+			continue;
+		}
+		if (!time_before(jiffies, orangefs_inode->mapping_time))
+			break;
+		spin_unlock(&inode->i_lock);
+		return 0;
+	}
+
+	set_bit(1, bitlock);
+	smp_wmb();
+	spin_unlock(&inode->i_lock);
+
+	unmap_mapping_range(mapping, 0, 0, 0);
+	ret = filemap_write_and_wait(mapping);
+	if (!ret)
+		ret = invalidate_inode_pages2(mapping);
+
+	orangefs_inode->mapping_time = jiffies +
+	    orangefs_cache_timeout_msecs*HZ/1000;
+
+	clear_bit(1, bitlock);
+	smp_mb__after_atomic();
+	wake_up_bit(bitlock, 1);
+
+	return ret;
+}
+
 static ssize_t orangefs_file_read_iter(struct kiocb *iocb,
     struct iov_iter *iter)
 {
+	int ret;
 	orangefs_stats.reads++;
-	return generic_file_read_iter(iocb, iter);
+
+	down_read(&file_inode(iocb->ki_filp)->i_rwsem);
+	ret = orangefs_revalidate_mapping(file_inode(iocb->ki_filp));
+	if (ret)
+		goto out;
+
+	ret = generic_file_read_iter(iocb, iter);
+out:
+	up_read(&file_inode(iocb->ki_filp)->i_rwsem);
+	return ret;
 }
 
 static ssize_t orangefs_file_write_iter(struct kiocb *iocb,
     struct iov_iter *iter)
 {
+	int ret;
 	orangefs_stats.writes++;
-	return generic_file_write_iter(iocb, iter);
+
+	if (iocb->ki_pos > i_size_read(file_inode(iocb->ki_filp))) {
+		ret = orangefs_revalidate_mapping(file_inode(iocb->ki_filp));
+		if (ret)
+			return ret;
+	}
+
+	ret = generic_file_write_iter(iocb, iter);
+	return ret;
 }
 
 /*
@@ -341,6 +401,12 @@ static const struct vm_operations_struct orangefs_file_vm_ops = {
  */
 static int orangefs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
+	int ret;
+
+	ret = orangefs_revalidate_mapping(file_inode(file));
+	if (ret)
+		return ret;
+
 	gossip_debug(GOSSIP_FILE_DEBUG,
 		     "orangefs_file_mmap: called on %s\n",
 		     (file ?

fs/orangefs/orangefs-kernel.h

@@ -193,9 +193,11 @@ struct orangefs_inode_s {
 	sector_t last_failed_block_index_read;
 
 	unsigned long getattr_time;
+	unsigned long mapping_time;
 	int attr_valid;
 	kuid_t attr_uid;
 	kgid_t attr_gid;
+	unsigned long bitlock;
 
 	DECLARE_HASHTABLE(xattr_cache, 4);
 };
@@ -390,6 +392,7 @@ bool __is_daemon_in_service(void);
 /*
  * defined in file.c
  */
+int orangefs_revalidate_mapping(struct inode *);
 ssize_t wait_for_direct_io(enum ORANGEFS_io_type, struct inode *, loff_t *,
     struct iov_iter *, size_t, loff_t, struct orangefs_write_range *);
 ssize_t do_readv_writev(enum ORANGEFS_io_type, struct file *, loff_t *,
@@ -427,6 +430,7 @@ int orangefs_normalize_to_errno(__s32 error_code);
 extern struct mutex orangefs_request_mutex;
 extern int op_timeout_secs;
 extern int slot_timeout_secs;
+extern int orangefs_cache_timeout_msecs;
 extern int orangefs_dcache_timeout_msecs;
 extern int orangefs_getattr_timeout_msecs;
 extern struct list_head orangefs_superblocks;

fs/orangefs/orangefs-mod.c

@@ -30,6 +30,7 @@ static ulong module_parm_debug_mask;
 __u64 orangefs_gossip_debug_mask;
 int op_timeout_secs = ORANGEFS_DEFAULT_OP_TIMEOUT_SECS;
 int slot_timeout_secs = ORANGEFS_DEFAULT_SLOT_TIMEOUT_SECS;
+int orangefs_cache_timeout_msecs = 50;
 int orangefs_dcache_timeout_msecs = 50;
 int orangefs_getattr_timeout_msecs = 50;
 

fs/orangefs/orangefs-sysfs.c

@@ -62,6 +62,14 @@
  *			Slots are requested and waited for,
  *			the wait times out after slot_timeout_secs.
  *
+ * What:		/sys/fs/orangefs/cache_timeout_msecs
+ * Date:		Mar 2018
+ * Contact:		Martin Brandenburg <martin@omnibond.com>
+ * Description:
+ *			Time in milliseconds between which
+ *			orangefs_revalidate_mapping will invalidate the page
+ *			cache.
+ *
  * What:		/sys/fs/orangefs/dcache_timeout_msecs
  * Date:		Jul 2016
  * Contact:		Martin Brandenburg <martin@omnibond.com>
@@ -221,6 +229,13 @@ static ssize_t sysfs_int_show(struct kobject *kobj,
 				       "%d\n",
 				       slot_timeout_secs);
 			goto out;
+		} else if (!strcmp(attr->attr.name,
+				   "cache_timeout_msecs")) {
+			rc = scnprintf(buf,
+				       PAGE_SIZE,
+				       "%d\n",
+				       orangefs_cache_timeout_msecs);
+			goto out;
 		} else if (!strcmp(attr->attr.name,
 				   "dcache_timeout_msecs")) {
 			rc = scnprintf(buf,
@@ -277,6 +292,9 @@ static ssize_t sysfs_int_store(struct kobject *kobj,
 	} else if (!strcmp(attr->attr.name, "slot_timeout_secs")) {
 		rc = kstrtoint(buf, 0, &slot_timeout_secs);
 		goto out;
+	} else if (!strcmp(attr->attr.name, "cache_timeout_msecs")) {
+		rc = kstrtoint(buf, 0, &orangefs_cache_timeout_msecs);
+		goto out;
 	} else if (!strcmp(attr->attr.name, "dcache_timeout_msecs")) {
 		rc = kstrtoint(buf, 0, &orangefs_dcache_timeout_msecs);
 		goto out;
@@ -818,6 +836,9 @@ static struct orangefs_attribute op_timeout_secs_attribute =
 static struct orangefs_attribute slot_timeout_secs_attribute =
 	__ATTR(slot_timeout_secs, 0664, sysfs_int_show, sysfs_int_store);
 
+static struct orangefs_attribute cache_timeout_msecs_attribute =
+	__ATTR(cache_timeout_msecs, 0664, sysfs_int_show, sysfs_int_store);
+
 static struct orangefs_attribute dcache_timeout_msecs_attribute =
 	__ATTR(dcache_timeout_msecs, 0664, sysfs_int_show, sysfs_int_store);
 
@@ -861,6 +882,7 @@ static struct orangefs_attribute perf_time_interval_secs_attribute =
 static struct attribute *orangefs_default_attrs[] = {
 	&op_timeout_secs_attribute.attr,
 	&slot_timeout_secs_attribute.attr,
+	&cache_timeout_msecs_attribute.attr,
 	&dcache_timeout_msecs_attribute.attr,
 	&getattr_timeout_msecs_attribute.attr,
 	&readahead_count_attribute.attr,