Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (205 commits)
  ceph: update for write_inode API change
  ceph: reset osd after relevant messages timed out
  ceph: fix flush_dirty_caps race with caps migration
  ceph: include migrating caps in issued set
  ceph: fix osdmap decoding when pools include (removed) snaps
  ceph: return EBADF if waiting for caps on closed file
  ceph: set osd request message front length correctly
  ceph: reset front len on return to msgpool; BUG on mismatched front iov
  ceph: fix snaptrace decoding on cap migration between mds
  ceph: use single osd op reply msg
  ceph: reset bits on connection close
  ceph: remove bogus mds forward warning
  ceph: remove fragile __map_osds optimization
  ceph: fix connection fault STANDBY check
  ceph: invalidate_authorizer without con->mutex held
  ceph: don't clobber write return value when using O_SYNC
  ceph: fix client_request_forward decoding
  ceph: drop messages on unregistered mds sessions; cleanup
  ceph: fix comments, locking in destroy_inode
  ceph: move dereference after NULL test
  ...

Fix trivial conflicts in Documentation/ioctl/ioctl-number.txt

64 files changed, 27917 insertions, 0 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index 7405f071be6..5f85b594761 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -235,6 +235,7 @@ config NFS_COMMON
 
 source "net/sunrpc/Kconfig"
 source "fs/smbfs/Kconfig"
+source "fs/ceph/Kconfig"
 source "fs/cifs/Kconfig"
 source "fs/ncpfs/Kconfig"
 source "fs/coda/Kconfig"
diff --git a/fs/Makefile b/fs/Makefile
index c3633aa4691..97f340f14ba 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -125,3 +125,4 @@ obj-$(CONFIG_OCFS2_FS)		+= ocfs2/
 obj-$(CONFIG_BTRFS_FS)		+= btrfs/
 obj-$(CONFIG_GFS2_FS)           += gfs2/
 obj-$(CONFIG_EXOFS_FS)          += exofs/
+obj-$(CONFIG_CEPH_FS)		+= ceph/
diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
new file mode 100644
index 00000000000..04b8280582a
--- /dev/null
+++ b/fs/ceph/Kconfig
@@ -0,0 +1,27 @@
+config CEPH_FS
+        tristate "Ceph distributed file system (EXPERIMENTAL)"
+	depends on INET && EXPERIMENTAL
+	select LIBCRC32C
+	select CONFIG_CRYPTO_AES
+	help
+	  Choose Y or M here to include support for mounting the
+	  experimental Ceph distributed file system.  Ceph is an extremely
+	  scalable file system designed to provide high performance,
+	  reliable access to petabytes of storage.
+
+	  More information at http://ceph.newdream.net/.
+
+	  If unsure, say N.
+
+config CEPH_FS_PRETTYDEBUG
+	bool "Include file:line in ceph debug output"
+	depends on CEPH_FS
+	default n
+	help
+	  If you say Y here, debug output will include a filename and
+	  line to aid debugging.  This icnreases kernel size and slows
+	  execution slightly when debug call sites are enabled (e.g.,
+	  via CONFIG_DYNAMIC_DEBUG).
+
+	  If unsure, say N.
+
diff --git a/fs/ceph/Makefile b/fs/ceph/Makefile
new file mode 100644
index 00000000000..6a660e610be
--- /dev/null
+++ b/fs/ceph/Makefile
@@ -0,0 +1,39 @@
+#
+# Makefile for CEPH filesystem.
+#
+
+ifneq ($(KERNELRELEASE),)
+
+obj-$(CONFIG_CEPH_FS) += ceph.o
+
+ceph-objs := super.o inode.o dir.o file.o addr.o ioctl.o \
+	export.o caps.o snap.o xattr.o \
+	messenger.o msgpool.o buffer.o pagelist.o \
+	mds_client.o mdsmap.o \
+	mon_client.o \
+	osd_client.o osdmap.o crush/crush.o crush/mapper.o crush/hash.o \
+	debugfs.o \
+	auth.o auth_none.o \
+	crypto.o armor.o \
+	auth_x.o \
+	ceph_fs.o ceph_strings.o ceph_hash.o ceph_frag.o
+
+else
+#Otherwise we were called directly from the command
+# line; invoke the kernel build system.
+
+KERNELDIR ?= /lib/modules/$(shell uname -r)/build
+PWD := $(shell pwd)
+
+default: all
+
+all:
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_FS=m modules
+
+modules_install:
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_FS=m modules_install
+
+clean:
+	$(MAKE) -C $(KERNELDIR) M=$(PWD) clean
+
+endif
diff --git a/fs/ceph/README b/fs/ceph/README
new file mode 100644
index 00000000000..18352fab37c
--- /dev/null
+++ b/fs/ceph/README
@@ -0,0 +1,20 @@
+#
+# The following files are shared by (and manually synchronized
+# between) the Ceph userland and kernel client.
+#
+# userland                  kernel
+src/include/ceph_fs.h	    fs/ceph/ceph_fs.h
+src/include/ceph_fs.cc	    fs/ceph/ceph_fs.c
+src/include/msgr.h	    fs/ceph/msgr.h
+src/include/rados.h	    fs/ceph/rados.h
+src/include/ceph_strings.cc fs/ceph/ceph_strings.c
+src/include/ceph_frag.h	    fs/ceph/ceph_frag.h
+src/include/ceph_frag.cc    fs/ceph/ceph_frag.c
+src/include/ceph_hash.h	    fs/ceph/ceph_hash.h
+src/include/ceph_hash.cc    fs/ceph/ceph_hash.c
+src/crush/crush.c	    fs/ceph/crush/crush.c
+src/crush/crush.h	    fs/ceph/crush/crush.h
+src/crush/mapper.c	    fs/ceph/crush/mapper.c
+src/crush/mapper.h	    fs/ceph/crush/mapper.h
+src/crush/hash.h	    fs/ceph/crush/hash.h
+src/crush/hash.c	    fs/ceph/crush/hash.c
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
new file mode 100644
index 00000000000..23bb0ceabe3
--- /dev/null
+++ b/fs/ceph/addr.c
@@ -0,0 +1,1188 @@
+#include "ceph_debug.h"
+
+#include <linux/backing-dev.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/writeback.h>	/* generic_writepages */
+#include <linux/pagevec.h>
+#include <linux/task_io_accounting_ops.h>
+
+#include "super.h"
+#include "osd_client.h"
+
+/*
+ * Ceph address space ops.
+ *
+ * There are a few funny things going on here.
+ *
+ * The page->private field is used to reference a struct
+ * ceph_snap_context for _every_ dirty page.  This indicates which
+ * snapshot the page was logically dirtied in, and thus which snap
+ * context needs to be associated with the osd write during writeback.
+ *
+ * Similarly, struct ceph_inode_info maintains a set of counters to
+ * count dirty pages on the inode.  In the absense of snapshots,
+ * i_wrbuffer_ref == i_wrbuffer_ref_head == the dirty page count.
+ *
+ * When a snapshot is taken (that is, when the client receives
+ * notification that a snapshot was taken), each inode with caps and
+ * with dirty pages (dirty pages implies there is a cap) gets a new
+ * ceph_cap_snap in the i_cap_snaps list (which is sorted in ascending
+ * order, new snaps go to the tail).  The i_wrbuffer_ref_head count is
+ * moved to capsnap->dirty. (Unless a sync write is currently in
+ * progress.  In that case, the capsnap is said to be "pending", new
+ * writes cannot start, and the capsnap isn't "finalized" until the
+ * write completes (or fails) and a final size/mtime for the inode for
+ * that snap can be settled upon.)  i_wrbuffer_ref_head is reset to 0.
+ *
+ * On writeback, we must submit writes to the osd IN SNAP ORDER.  So,
+ * we look for the first capsnap in i_cap_snaps and write out pages in
+ * that snap context _only_.  Then we move on to the next capsnap,
+ * eventually reaching the "live" or "head" context (i.e., pages that
+ * are not yet snapped) and are writing the most recently dirtied
+ * pages.
+ *
+ * Invalidate and so forth must take care to ensure the dirty page
+ * accounting is preserved.
+ */
+
+#define CONGESTION_ON_THRESH(congestion_kb) (congestion_kb >> (PAGE_SHIFT-10))
+#define CONGESTION_OFF_THRESH(congestion_kb)				\
+	(CONGESTION_ON_THRESH(congestion_kb) -				\
+	 (CONGESTION_ON_THRESH(congestion_kb) >> 2))
+
+
+
+/*
+ * Dirty a page.  Optimistically adjust accounting, on the assumption
+ * that we won't race with invalidate.  If we do, readjust.
+ */
+static int ceph_set_page_dirty(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	struct inode *inode;
+	struct ceph_inode_info *ci;
+	int undo = 0;
+	struct ceph_snap_context *snapc;
+
+	if (unlikely(!mapping))
+		return !TestSetPageDirty(page);
+
+	if (TestSetPageDirty(page)) {
+		dout("%p set_page_dirty %p idx %lu -- already dirty\n",
+		     mapping->host, page, page->index);
+		return 0;
+	}
+
+	inode = mapping->host;
+	ci = ceph_inode(inode);
+
+	/*
+	 * Note that we're grabbing a snapc ref here without holding
+	 * any locks!
+	 */
+	snapc = ceph_get_snap_context(ci->i_snap_realm->cached_context);
+
+	/* dirty the head */
+	spin_lock(&inode->i_lock);
+	if (ci->i_wrbuffer_ref_head == 0)
+		ci->i_head_snapc = ceph_get_snap_context(snapc);
+	++ci->i_wrbuffer_ref_head;
+	if (ci->i_wrbuffer_ref == 0)
+		igrab(inode);
+	++ci->i_wrbuffer_ref;
+	dout("%p set_page_dirty %p idx %lu head %d/%d -> %d/%d "
+	     "snapc %p seq %lld (%d snaps)\n",
+	     mapping->host, page, page->index,
+	     ci->i_wrbuffer_ref-1, ci->i_wrbuffer_ref_head-1,
+	     ci->i_wrbuffer_ref, ci->i_wrbuffer_ref_head,
+	     snapc, snapc->seq, snapc->num_snaps);
+	spin_unlock(&inode->i_lock);
+
+	/* now adjust page */
+	spin_lock_irq(&mapping->tree_lock);
+	if (page->mapping) {	/* Race with truncate? */
+		WARN_ON_ONCE(!PageUptodate(page));
+
+		if (mapping_cap_account_dirty(mapping)) {
+			__inc_zone_page_state(page, NR_FILE_DIRTY);
+			__inc_bdi_stat(mapping->backing_dev_info,
+					BDI_RECLAIMABLE);
+			task_io_account_write(PAGE_CACHE_SIZE);
+		}
+		radix_tree_tag_set(&mapping->page_tree,
+				page_index(page), PAGECACHE_TAG_DIRTY);
+
+		/*
+		 * Reference snap context in page->private.  Also set
+		 * PagePrivate so that we get invalidatepage callback.
+		 */
+		page->private = (unsigned long)snapc;
+		SetPagePrivate(page);
+	} else {
+		dout("ANON set_page_dirty %p (raced truncate?)\n", page);
+		undo = 1;
+	}
+
+	spin_unlock_irq(&mapping->tree_lock);
+
+	if (undo)
+		/* whoops, we failed to dirty the page */
+		ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
+
+	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+
+	BUG_ON(!PageDirty(page));
+	return 1;
+}
+
+/*
+ * If we are truncating the full page (i.e. offset == 0), adjust the
+ * dirty page counters appropriately.  Only called if there is private
+ * data on the page.
+ */
+static void ceph_invalidatepage(struct page *page, unsigned long offset)
+{
+	struct inode *inode;
+	struct ceph_inode_info *ci;
+	struct ceph_snap_context *snapc = (void *)page->private;
+
+	BUG_ON(!PageLocked(page));
+	BUG_ON(!page->private);
+	BUG_ON(!PagePrivate(page));
+	BUG_ON(!page->mapping);
+
+	inode = page->mapping->host;
+
+	/*
+	 * We can get non-dirty pages here due to races between
+	 * set_page_dirty and truncate_complete_page; just spit out a
+	 * warning, in case we end up with accounting problems later.
+	 */
+	if (!PageDirty(page))
+		pr_err("%p invalidatepage %p page not dirty\n", inode, page);
+
+	if (offset == 0)
+		ClearPageChecked(page);
+
+	ci = ceph_inode(inode);
+	if (offset == 0) {
+		dout("%p invalidatepage %p idx %lu full dirty page %lu\n",
+		     inode, page, page->index, offset);
+		ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
+		ceph_put_snap_context(snapc);
+		page->private = 0;
+		ClearPagePrivate(page);
+	} else {
+		dout("%p invalidatepage %p idx %lu partial dirty page\n",
+		     inode, page, page->index);
+	}
+}
+
+/* just a sanity check */
+static int ceph_releasepage(struct page *page, gfp_t g)
+{
+	struct inode *inode = page->mapping ? page->mapping->host : NULL;
+	dout("%p releasepage %p idx %lu\n", inode, page, page->index);
+	WARN_ON(PageDirty(page));
+	WARN_ON(page->private);
+	WARN_ON(PagePrivate(page));
+	return 0;
+}
+
+/*
+ * read a single page, without unlocking it.
+ */
+static int readpage_nounlock(struct file *filp, struct page *page)
+{
+	struct inode *inode = filp->f_dentry->d_inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->osdc;
+	int err = 0;
+	u64 len = PAGE_CACHE_SIZE;
+
+	dout("readpage inode %p file %p page %p index %lu\n",
+	     inode, filp, page, page->index);
+	err = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout,
+				  page->index << PAGE_CACHE_SHIFT, &len,
+				  ci->i_truncate_seq, ci->i_truncate_size,
+				  &page, 1);
+	if (err == -ENOENT)
+		err = 0;
+	if (err < 0) {
+		SetPageError(page);
+		goto out;
+	} else if (err < PAGE_CACHE_SIZE) {
+		/* zero fill remainder of page */
+		zero_user_segment(page, err, PAGE_CACHE_SIZE);
+	}
+	SetPageUptodate(page);
+
+out:
+	return err < 0 ? err : 0;
+}
+
+static int ceph_readpage(struct file *filp, struct page *page)
+{
+	int r = readpage_nounlock(filp, page);
+	unlock_page(page);
+	return r;
+}
+
+/*
+ * Build a vector of contiguous pages from the provided page list.
+ */
+static struct page **page_vector_from_list(struct list_head *page_list,
+					   unsigned *nr_pages)
+{
+	struct page **pages;
+	struct page *page;
+	int next_index, contig_pages = 0;
+
+	/* build page vector */
+	pages = kmalloc(sizeof(*pages) * *nr_pages, GFP_NOFS);
+	if (!pages)
+		return ERR_PTR(-ENOMEM);
+
+	BUG_ON(list_empty(page_list));
+	next_index = list_entry(page_list->prev, struct page, lru)->index;
+	list_for_each_entry_reverse(page, page_list, lru) {
+		if (page->index == next_index) {
+			dout("readpages page %d %p\n", contig_pages, page);
+			pages[contig_pages] = page;
+			contig_pages++;
+			next_index++;
+		} else {
+			break;
+		}
+	}
+	*nr_pages = contig_pages;
+	return pages;
+}
+
+/*
+ * Read multiple pages.  Leave pages we don't read + unlock in page_list;
+ * the caller (VM) cleans them up.
+ */
+static int ceph_readpages(struct file *file, struct address_space *mapping,
+			  struct list_head *page_list, unsigned nr_pages)
+{
+	struct inode *inode = file->f_dentry->d_inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->osdc;
+	int rc = 0;
+	struct page **pages;
+	struct pagevec pvec;
+	loff_t offset;
+	u64 len;
+
+	dout("readpages %p file %p nr_pages %d\n",
+	     inode, file, nr_pages);
+
+	pages = page_vector_from_list(page_list, &nr_pages);
+	if (IS_ERR(pages))
+		return PTR_ERR(pages);
+
+	/* guess read extent */
+	offset = pages[0]->index << PAGE_CACHE_SHIFT;
+	len = nr_pages << PAGE_CACHE_SHIFT;
+	rc = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout,
+				 offset, &len,
+				 ci->i_truncate_seq, ci->i_truncate_size,
+				 pages, nr_pages);
+	if (rc == -ENOENT)
+		rc = 0;
+	if (rc < 0)
+		goto out;
+
+	/* set uptodate and add to lru in pagevec-sized chunks */
+	pagevec_init(&pvec, 0);
+	for (; !list_empty(page_list) && len > 0;
+	     rc -= PAGE_CACHE_SIZE, len -= PAGE_CACHE_SIZE) {
+		struct page *page =
+			list_entry(page_list->prev, struct page, lru);
+
+		list_del(&page->lru);
+
+		if (rc < (int)PAGE_CACHE_SIZE) {
+			/* zero (remainder of) page */
+			int s = rc < 0 ? 0 : rc;
+			zero_user_segment(page, s, PAGE_CACHE_SIZE);
+		}
+
+		if (add_to_page_cache(page, mapping, page->index, GFP_NOFS)) {
+			page_cache_release(page);
+			dout("readpages %p add_to_page_cache failed %p\n",
+			     inode, page);
+			continue;
+		}
+		dout("readpages %p adding %p idx %lu\n", inode, page,
+		     page->index);
+		flush_dcache_page(page);
+		SetPageUptodate(page);
+		unlock_page(page);
+		if (pagevec_add(&pvec, page) == 0)
+			pagevec_lru_add_file(&pvec);   /* add to lru */
+	}
+	pagevec_lru_add_file(&pvec);
+	rc = 0;
+
+out:
+	kfree(pages);
+	return rc;
+}
+
+/*
+ * Get ref for the oldest snapc for an inode with dirty data... that is, the
+ * only snap context we are allowed to write back.
+ *
+ * Caller holds i_lock.
+ */
+static struct ceph_snap_context *__get_oldest_context(struct inode *inode,
+						      u64 *snap_size)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_snap_context *snapc = NULL;
+	struct ceph_cap_snap *capsnap = NULL;
+
+	list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
+		dout(" cap_snap %p snapc %p has %d dirty pages\n", capsnap,
+		     capsnap->context, capsnap->dirty_pages);
+		if (capsnap->dirty_pages) {
+			snapc = ceph_get_snap_context(capsnap->context);
+			if (snap_size)
+				*snap_size = capsnap->size;
+			break;
+		}
+	}
+	if (!snapc && ci->i_snap_realm) {
+		snapc = ceph_get_snap_context(ci->i_snap_realm->cached_context);
+		dout(" head snapc %p has %d dirty pages\n",
+		     snapc, ci->i_wrbuffer_ref_head);
+	}
+	return snapc;
+}
+
+static struct ceph_snap_context *get_oldest_context(struct inode *inode,
+						    u64 *snap_size)
+{
+	struct ceph_snap_context *snapc = NULL;
+
+	spin_lock(&inode->i_lock);
+	snapc = __get_oldest_context(inode, snap_size);
+	spin_unlock(&inode->i_lock);
+	return snapc;
+}
+
+/*
+ * Write a single page, but leave the page locked.
+ *
+ * If we get a write error, set the page error bit, but still adjust the
+ * dirty page accounting (i.e., page is no longer dirty).
+ */
+static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
+{
+	struct inode *inode;
+	struct ceph_inode_info *ci;
+	struct ceph_client *client;
+	struct ceph_osd_client *osdc;
+	loff_t page_off = page->index << PAGE_CACHE_SHIFT;
+	int len = PAGE_CACHE_SIZE;
+	loff_t i_size;
+	int err = 0;
+	struct ceph_snap_context *snapc;
+	u64 snap_size = 0;
+	long writeback_stat;
+
+	dout("writepage %p idx %lu\n", page, page->index);
+
+	if (!page->mapping || !page->mapping->host) {
+		dout("writepage %p - no mapping\n", page);
+		return -EFAULT;
+	}
+	inode = page->mapping->host;
+	ci = ceph_inode(inode);
+	client = ceph_inode_to_client(inode);
+	osdc = &client->osdc;
+
+	/* verify this is a writeable snap context */
+	snapc = (void *)page->private;
+	if (snapc == NULL) {
+		dout("writepage %p page %p not dirty?\n", inode, page);
+		goto out;
+	}
+	if (snapc != get_oldest_context(inode, &snap_size)) {
+		dout("writepage %p page %p snapc %p not writeable - noop\n",
+		     inode, page, (void *)page->private);
+		/* we should only noop if called by kswapd */
+		WARN_ON((current->flags & PF_MEMALLOC) == 0);
+		goto out;
+	}
+
+	/* is this a partial page at end of file? */
+	if (snap_size)
+		i_size = snap_size;
+	else
+		i_size = i_size_read(inode);
+	if (i_size < page_off + len)
+		len = i_size - page_off;
+
+	dout("writepage %p page %p index %lu on %llu~%u\n",
+	     inode, page, page->index, page_off, len);
+
+	writeback_stat = atomic_long_inc_return(&client->writeback_count);
+	if (writeback_stat >
+	    CONGESTION_ON_THRESH(client->mount_args->congestion_kb))
+		set_bdi_congested(&client->backing_dev_info, BLK_RW_ASYNC);
+
+	set_page_writeback(page);
+	err = ceph_osdc_writepages(osdc, ceph_vino(inode),
+				   &ci->i_layout, snapc,
+				   page_off, len,
+				   ci->i_truncate_seq, ci->i_truncate_size,
+				   &inode->i_mtime,
+				   &page, 1, 0, 0, true);
+	if (err < 0) {
+		dout("writepage setting page/mapping error %d %p\n", err, page);
+		SetPageError(page);
+		mapping_set_error(&inode->i_data, err);
+		if (wbc)
+			wbc->pages_skipped++;
+	} else {
+		dout("writepage cleaned page %p\n", page);
+		err = 0;  /* vfs expects us to return 0 */
+	}
+	page->private = 0;
+	ClearPagePrivate(page);
+	end_page_writeback(page);
+	ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
+	ceph_put_snap_context(snapc);
+out:
+	return err;
+}
+
+static int ceph_writepage(struct page *page, struct writeback_control *wbc)
+{
+	int err;
+	struct inode *inode = page->mapping->host;
+	BUG_ON(!inode);
+	igrab(inode);
+	err = writepage_