ceph: add inline data to pagecache

Request reply and cap message can contain inline data. add inline data
to the page cache if there is Fc cap.

Signed-off-by: Yan, Zheng <zyan@redhat.com>

fs/ceph/addr.c

@@ -1318,6 +1318,49 @@ out:
 	return ret;
 }
 
+void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
+			   char	*data, size_t len)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct page *page;
+
+	if (locked_page) {
+		page = locked_page;
+	} else {
+		if (i_size_read(inode) == 0)
+			return;
+		page = find_or_create_page(mapping, 0,
+					   mapping_gfp_mask(mapping) & ~__GFP_FS);
+		if (!page)
+			return;
+		if (PageUptodate(page)) {
+			unlock_page(page);
+			page_cache_release(page);
+			return;
+		}
+	}
+
+	dout("fill_inline_data %p %llx.%llx len %lu locked_page %p\n",
+	     inode, ceph_vinop(inode), len, locked_page);
+
+	if (len > 0) {
+		void *kaddr = kmap_atomic(page);
+		memcpy(kaddr, data, len);
+		kunmap_atomic(kaddr);
+	}
+
+	if (page != locked_page) {
+		if (len < PAGE_CACHE_SIZE)
+			zero_user_segment(page, len, PAGE_CACHE_SIZE);
+		else
+			flush_dcache_page(page);
+
+		SetPageUptodate(page);
+		unlock_page(page);
+		page_cache_release(page);
+	}
+}
+
 static struct vm_operations_struct ceph_vmops = {
 	.fault		= ceph_filemap_fault,
 	.page_mkwrite	= ceph_page_mkwrite,

fs/ceph/caps.c

@@ -2405,6 +2405,7 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 	bool queue_invalidate = false;
 	bool queue_revalidate = false;
 	bool deleted_inode = false;
+	bool fill_inline = false;
 
 	dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
 	     inode, cap, mds, seq, ceph_cap_string(newcaps));
@@ -2578,6 +2579,13 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 	}
 	BUG_ON(cap->issued & ~cap->implemented);
 
+	if (inline_version > 0 && inline_version >= ci->i_inline_version) {
+		ci->i_inline_version = inline_version;
+		if (ci->i_inline_version != CEPH_INLINE_NONE &&
+		    (newcaps & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)))
+			fill_inline = true;
+	}
+
 	spin_unlock(&ci->i_ceph_lock);
 
 	if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
@@ -2591,6 +2599,9 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 			wake = true;
 	}
 
+	if (fill_inline)
+		ceph_fill_inline_data(inode, NULL, inline_data, inline_len);
+
 	if (queue_trunc) {
 		ceph_queue_vmtruncate(inode);
 		ceph_queue_revalidate(inode);

fs/ceph/inode.c

@@ -387,6 +387,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	spin_lock_init(&ci->i_ceph_lock);
 
 	ci->i_version = 0;
+	ci->i_inline_version = 0;
 	ci->i_time_warp_seq = 0;
 	ci->i_ceph_flags = 0;
 	ci->i_ordered_count = 0;
@@ -676,6 +677,7 @@ static int fill_inode(struct inode *inode,
 	bool wake = false;
 	bool queue_trunc = false;
 	bool new_version = false;
+	bool fill_inline = false;
 
 	dout("fill_inode %p ino %llx.%llx v %llu had %llu\n",
 	     inode, ceph_vinop(inode), le64_to_cpu(info->version),
@@ -875,8 +877,22 @@ static int fill_inode(struct inode *inode,
 			   ceph_vinop(inode));
 		__ceph_get_fmode(ci, cap_fmode);
 	}
+
+	if (iinfo->inline_version > 0 &&
+	    iinfo->inline_version >= ci->i_inline_version) {
+		int cache_caps = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
+		ci->i_inline_version = iinfo->inline_version;
+		if (ci->i_inline_version != CEPH_INLINE_NONE &&
+		    (le32_to_cpu(info->cap.caps) & cache_caps))
+			fill_inline = true;
+	}
+
 	spin_unlock(&ci->i_ceph_lock);
 
+	if (fill_inline)
+		ceph_fill_inline_data(inode, NULL,
+				      iinfo->inline_data, iinfo->inline_len);
+
 	if (wake)
 		wake_up_all(&ci->i_cap_wq);
 

fs/ceph/super.h

@@ -253,6 +253,7 @@ struct ceph_inode_info {
 	spinlock_t i_ceph_lock;
 
 	u64 i_version;
+	u64 i_inline_version;
 	u32 i_time_warp_seq;
 
 	unsigned i_ceph_flags;
@@ -858,7 +859,7 @@ extern int ceph_encode_dentry_release(void **p, struct dentry *dn,
 				      int mds, int drop, int unless);
 
 extern int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
-			 int *got, loff_t endoff);
+			 loff_t endoff, int *got, struct page **pinned_page);
 
 /* for counting open files by mode */
 static inline void __ceph_get_fmode(struct ceph_inode_info *ci, int mode)
@@ -880,6 +881,8 @@ extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 			    struct file *file, unsigned flags, umode_t mode,
 			    int *opened);
 extern int ceph_release(struct inode *inode, struct file *filp);
+extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
+				  char *data, size_t len);
 
 /* dir.c */
 extern const struct file_operations ceph_dir_fops;

fs/ceph/super.h.rej

@@ -0,0 +1,10 @@
+--- fs/ceph/super.h
++++ fs/ceph/super.h
+@@ -254,6 +255,7 @@
+	spinlock_t i_ceph_lock;
+
+	u64 i_version;
++	u64 i_inline_version;
+	u32 i_time_warp_seq;
+
+	unsigned i_ceph_flags;

include/linux/ceph/ceph_fs.h

@@ -552,6 +552,7 @@ struct ceph_filelock {
 
 int ceph_flags_to_mode(int flags);
 
+#define CEPH_INLINE_NONE	((__u64)-1)
 
 /* capability bits */
 #define CEPH_CAP_PIN         1  /* no specific capabilities beyond the pin */