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

Pull Ceph updates from Sage Weil:
 "We have a pile of bug fixes from Ilya, including a few patches that
  sync up the CRUSH code with the latest from userspace.

  There is also a long series from Zheng that fixes various issues with
  snapshots, inline data, and directory fsync, some simplification and
  improvement in the cap release code, and a rework of the caching of
  directory contents.

  To top it off there are a few small fixes and cleanups from Benoit and
  Hong"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (40 commits)
  rbd: use GFP_NOIO in rbd_obj_request_create()
  crush: fix a bug in tree bucket decode
  libceph: Fix ceph_tcp_sendpage()'s more boolean usage
  libceph: Remove spurious kunmap() of the zero page
  rbd: queue_depth map option
  rbd: store rbd_options in rbd_device
  rbd: terminate rbd_opts_tokens with Opt_err
  ceph: fix ceph_writepages_start()
  rbd: bump queue_max_segments
  ceph: rework dcache readdir
  crush: sync up with userspace
  crush: fix crash from invalid 'take' argument
  ceph: switch some GFP_NOFS memory allocation to GFP_KERNEL
  ceph: pre-allocate data structure that tracks caps flushing
  ceph: re-send flushing caps (which are revoked) in reconnect stage
  ceph: send TID of the oldest pending caps flush to MDS
  ceph: track pending caps flushing globally
  ceph: track pending caps flushing accurately
  libceph: fix wrong name "Ceph filesystem for Linux"
  ceph: fix directory fsync
  ...

5 files changed, 55 insertions, 16 deletions

diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 30f92cefaa72..9ebee53d3bf5 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -43,9 +43,9 @@ struct ceph_options {
 	int flags;
 	struct ceph_fsid fsid;
 	struct ceph_entity_addr my_addr;
-	int mount_timeout;
-	int osd_idle_ttl;
-	int osd_keepalive_timeout;
+	unsigned long mount_timeout;		/* jiffies */
+	unsigned long osd_idle_ttl;		/* jiffies */
+	unsigned long osd_keepalive_timeout;	/* jiffies */
 
 	/*
 	 * any type that can't be simply compared or doesn't need need
@@ -63,9 +63,9 @@ struct ceph_options {
 /*
  * defaults
  */
-#define CEPH_MOUNT_TIMEOUT_DEFAULT  60
-#define CEPH_OSD_KEEPALIVE_DEFAULT  5
-#define CEPH_OSD_IDLE_TTL_DEFAULT    60
+#define CEPH_MOUNT_TIMEOUT_DEFAULT	msecs_to_jiffies(60 * 1000)
+#define CEPH_OSD_KEEPALIVE_DEFAULT	msecs_to_jiffies(5 * 1000)
+#define CEPH_OSD_IDLE_TTL_DEFAULT	msecs_to_jiffies(60 * 1000)
 
 #define CEPH_MSG_MAX_FRONT_LEN	(16*1024*1024)
 #define CEPH_MSG_MAX_MIDDLE_LEN	(16*1024*1024)
@@ -93,13 +93,9 @@ enum {
 	CEPH_MOUNT_SHUTDOWN,
 };
 
-/*
- * subtract jiffies
- */
-static inline unsigned long time_sub(unsigned long a, unsigned long b)
+static inline unsigned long ceph_timeout_jiffies(unsigned long timeout)
 {
-	BUG_ON(time_after(b, a));
-	return (long)a - (long)b;
+	return timeout ?: MAX_SCHEDULE_TIMEOUT;
 }
 
 struct ceph_mds_client;
@@ -178,6 +174,7 @@ static inline int calc_pages_for(u64 off, u64 len)
 
 extern struct kmem_cache *ceph_inode_cachep;
 extern struct kmem_cache *ceph_cap_cachep;
+extern struct kmem_cache *ceph_cap_flush_cachep;
 extern struct kmem_cache *ceph_dentry_cachep;
 extern struct kmem_cache *ceph_file_cachep;
 
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 61b19c46bdb3..7506b485bb6d 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -249,7 +249,7 @@ extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
 				 struct ceph_msg *msg);
 
 extern void osd_req_op_init(struct ceph_osd_request *osd_req,
-					unsigned int which, u16 opcode);
+			    unsigned int which, u16 opcode, u32 flags);
 
 extern void osd_req_op_raw_data_in_pages(struct ceph_osd_request *,
 					unsigned int which,
diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index 48a1a7d100f1..48b49305716b 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -1,7 +1,11 @@
 #ifndef CEPH_CRUSH_CRUSH_H
 #define CEPH_CRUSH_CRUSH_H
 
-#include <linux/types.h>
+#ifdef __KERNEL__
+# include <linux/types.h>
+#else
+# include "crush_compat.h"
+#endif
 
 /*
  * CRUSH is a pseudo-random data distribution algorithm that
@@ -20,7 +24,11 @@
 #define CRUSH_MAGIC 0x00010000ul   /* for detecting algorithm revisions */
 
 #define CRUSH_MAX_DEPTH 10  /* max crush hierarchy depth */
+#define CRUSH_MAX_RULESET (1<<8)  /* max crush ruleset number */
+#define CRUSH_MAX_RULES CRUSH_MAX_RULESET  /* should be the same as max rulesets */
 
+#define CRUSH_MAX_DEVICE_WEIGHT (100u * 0x10000u)
+#define CRUSH_MAX_BUCKET_WEIGHT (65535u * 0x10000u)
 
 #define CRUSH_ITEM_UNDEF  0x7ffffffe  /* undefined result (internal use only) */
 #define CRUSH_ITEM_NONE   0x7fffffff  /* no result */
@@ -108,6 +116,15 @@ enum {
 };
 extern const char *crush_bucket_alg_name(int alg);
 
+/*
+ * although tree was a legacy algorithm, it has been buggy, so
+ * exclude it.
+ */
+#define CRUSH_LEGACY_ALLOWED_BUCKET_ALGS (	\
+		(1 << CRUSH_BUCKET_UNIFORM) |	\
+		(1 << CRUSH_BUCKET_LIST) |	\
+		(1 << CRUSH_BUCKET_STRAW))
+
 struct crush_bucket {
 	__s32 id;        /* this'll be negative */
 	__u16 type;      /* non-zero; type=0 is reserved for devices */
@@ -174,7 +191,7 @@ struct crush_map {
 	/* choose local attempts using a fallback permutation before
 	 * re-descent */
 	__u32 choose_local_fallback_tries;
-	/* choose attempts before giving up */ 
+	/* choose attempts before giving up */
 	__u32 choose_total_tries;
 	/* attempt chooseleaf inner descent once for firstn mode; on
 	 * reject retry outer descent.  Note that this does *not*
@@ -187,6 +204,25 @@ struct crush_map {
 	 * that want to limit reshuffling, a value of 3 or 4 will make the
 	 * mappings line up a bit better with previous mappings. */
 	__u8 chooseleaf_vary_r;
+
+#ifndef __KERNEL__
+	/*
+	 * version 0 (original) of straw_calc has various flaws.  version 1
+	 * fixes a few of them.
+	 */
+	__u8 straw_calc_version;
+
+	/*
+	 * allowed bucket algs is a bitmask, here the bit positions
+	 * are CRUSH_BUCKET_*.  note that these are *bits* and
+	 * CRUSH_BUCKET_* values are not, so we need to or together (1
+	 * << CRUSH_BUCKET_WHATEVER).  The 0th bit is not used to
+	 * minimize confusion (bucket type values start at 1).
+	 */
+	__u32 allowed_bucket_algs;
+
+	__u32 *choose_tries;
+#endif
 };
 
 
diff --git a/include/linux/crush/hash.h b/include/linux/crush/hash.h
index 91e884230d5d..d1d90258242e 100644
--- a/include/linux/crush/hash.h
+++ b/include/linux/crush/hash.h
@@ -1,6 +1,12 @@
 #ifndef CEPH_CRUSH_HASH_H
 #define CEPH_CRUSH_HASH_H
 
+#ifdef __KERNEL__
+# include <linux/types.h>
+#else
+# include "crush_compat.h"
+#endif
+
 #define CRUSH_HASH_RJENKINS1   0
 
 #define CRUSH_HASH_DEFAULT CRUSH_HASH_RJENKINS1
diff --git a/include/linux/crush/mapper.h b/include/linux/crush/mapper.h
index eab367446eea..5dfd5b1125d2 100644
--- a/include/linux/crush/mapper.h
+++ b/include/linux/crush/mapper.h
@@ -8,7 +8,7 @@
  * LGPL2
  */
 
-#include <linux/crush/crush.h>
+#include "crush.h"
 
 extern int crush_find_rule(const struct crush_map *map, int ruleset, int type, int size);
 extern int crush_do_rule(const struct crush_map *map,