Re: Linux 3.4.20

@@ -466,6 +466,10 @@ Note:
 5.3 swappiness
 
 Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
+Please note that unlike the global swappiness, memcg knob set to 0
+really prevents from any swapping even if there is a swap storage
+available. This might lead to memcg OOM killer if there are no file
+pages to reclaim.
 
 Following cgroups' swappiness can't be changed.
 - root cgroup (uses /proc/sys/vm/swappiness).

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 4
-SUBLEVEL = 19
+SUBLEVEL = 20
 EXTRAVERSION =
 NAME = Saber-toothed Squirrel
 

@@ -42,10 +42,10 @@
 #define OMAP_UART_WER_MOD_WKUP	0X7F
 
 /* Enable XON/XOFF flow control on output */
-#define OMAP_UART_SW_TX		0x8
+#define OMAP_UART_SW_TX		0x04
 
 /* Enable XON/XOFF flow control on input */
-#define OMAP_UART_SW_RX		0x2
+#define OMAP_UART_SW_RX		0x04
 
 #define OMAP_UART_SYSC_RESET	0X07
 #define OMAP_UART_TCR_TRIG	0X0F

@@ -156,7 +156,7 @@ typedef struct sigaltstack {
 static inline void sigaddset(sigset_t *set, int _sig)
 {
 	asm ("bfset %0{%1,#1}"
-		: "+od" (*set)
+		: "+o" (*set)
 		: "id" ((_sig - 1) ^ 31)
 		: "cc");
 }

@@ -164,7 +164,7 @@ static inline void sigaddset(sigset_t *set, int _sig)
 static inline void sigdelset(sigset_t *set, int _sig)
 {
 	asm ("bfclr %0{%1,#1}"
-		: "+od" (*set)
+		: "+o" (*set)
 		: "id" ((_sig - 1) ^ 31)
 		: "cc");
 }

@@ -180,7 +180,7 @@ static inline int __gen_sigismember(sigset_t *set, int _sig)
 	int ret;
 	asm ("bfextu %1{%2,#1},%0"
 		: "=d" (ret)
-		: "od" (*set), "id" ((_sig-1) ^ 31)
+		: "o" (*set), "id" ((_sig-1) ^ 31)
 		: "cc");
 	return ret;
 }

@@ -20,7 +20,7 @@
 #define PSW32_MASK_CC		0x00003000UL
 #define PSW32_MASK_PM		0x00000f00UL
 
-#define PSW32_MASK_USER		0x00003F00UL
+#define PSW32_MASK_USER		0x0000FF00UL
 
 #define PSW32_ADDR_AMODE	0x80000000UL
 #define PSW32_ADDR_INSN		0x7FFFFFFFUL

@@ -240,7 +240,7 @@ typedef struct
 #define PSW_MASK_EA		0x00000000UL
 #define PSW_MASK_BA		0x00000000UL
 
-#define PSW_MASK_USER		0x00003F00UL
+#define PSW_MASK_USER		0x0000FF00UL
 
 #define PSW_ADDR_AMODE		0x80000000UL
 #define PSW_ADDR_INSN		0x7FFFFFFFUL

@@ -269,7 +269,7 @@ typedef struct
 #define PSW_MASK_EA		0x0000000100000000UL
 #define PSW_MASK_BA		0x0000000080000000UL
 
-#define PSW_MASK_USER		0x00003F0180000000UL
+#define PSW_MASK_USER		0x0000FF0180000000UL
 
 #define PSW_ADDR_AMODE		0x0000000000000000UL
 #define PSW_ADDR_INSN		0xFFFFFFFFFFFFFFFFUL

@@ -313,6 +313,10 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs)
 	regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) |
 		(__u64)(regs32.psw.mask & PSW32_MASK_USER) << 32 |
 		(__u64)(regs32.psw.addr & PSW32_ADDR_AMODE);
+	/* Check for invalid user address space control. */
+	if ((regs->psw.mask & PSW_MASK_ASC) >= (psw_kernel_bits & PSW_MASK_ASC))
+		regs->psw.mask = (psw_user_bits & PSW_MASK_ASC) |
+			(regs->psw.mask & ~PSW_MASK_ASC);
 	regs->psw.addr = (__u64)(regs32.psw.addr & PSW32_ADDR_INSN);
 	for (i = 0; i < NUM_GPRS; i++)
 		regs->gprs[i] = (__u64) regs32.gprs[i];

@@ -494,7 +498,10 @@ static int setup_frame32(int sig, struct k_sigaction *ka,
 
 	/* Set up registers for signal handler */
 	regs->gprs[15] = (__force __u64) frame;
-	regs->psw.mask |= PSW_MASK_BA;		/* force amode 31 */
+	/* Force 31 bit amode and default user address space control. */
+	regs->psw.mask = PSW_MASK_BA |
+		(psw_user_bits & PSW_MASK_ASC) |
+		(regs->psw.mask & ~PSW_MASK_ASC);
 	regs->psw.addr = (__force __u64) ka->sa.sa_handler;
 
 	regs->gprs[2] = map_signal(sig);

@@ -562,7 +569,10 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info,
 
 	/* Set up registers for signal handler */
 	regs->gprs[15] = (__force __u64) frame;
-	regs->psw.mask |= PSW_MASK_BA;		/* force amode 31 */
+	/* Force 31 bit amode and default user address space control. */
+	regs->psw.mask = PSW_MASK_BA |
+		(psw_user_bits & PSW_MASK_ASC) |
+		(regs->psw.mask & ~PSW_MASK_ASC);
 	regs->psw.addr = (__u64) ka->sa.sa_handler;
 
 	regs->gprs[2] = map_signal(sig);

@@ -148,6 +148,10 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs)
 	/* Use regs->psw.mask instead of psw_user_bits to preserve PER bit. */
 	regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) |
 		(user_sregs.regs.psw.mask & PSW_MASK_USER);
+	/* Check for invalid user address space control. */
+	if ((regs->psw.mask & PSW_MASK_ASC) >= (psw_kernel_bits & PSW_MASK_ASC))
+		regs->psw.mask = (psw_user_bits & PSW_MASK_ASC) |
+			(regs->psw.mask & ~PSW_MASK_ASC);
 	/* Check for invalid amode */
 	if (regs->psw.mask & PSW_MASK_EA)
 		regs->psw.mask |= PSW_MASK_BA;

@@ -294,7 +298,10 @@ static int setup_frame(int sig, struct k_sigaction *ka,
 
 	/* Set up registers for signal handler */
 	regs->gprs[15] = (unsigned long) frame;
-	regs->psw.mask |= PSW_MASK_EA | PSW_MASK_BA;	/* 64 bit amode */
+	/* Force default amode and default user address space control. */
+	regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA |
+		(psw_user_bits & PSW_MASK_ASC) |
+		(regs->psw.mask & ~PSW_MASK_ASC);
 	regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE;
 
 	regs->gprs[2] = map_signal(sig);

@@ -367,7 +374,10 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 
 	/* Set up registers for signal handler */
 	regs->gprs[15] = (unsigned long) frame;
-	regs->psw.mask |= PSW_MASK_EA | PSW_MASK_BA;	/* 64 bit amode */
+	/* Force default amode and default user address space control. */
+	regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA |
+		(psw_user_bits & PSW_MASK_ASC) |
+		(regs->psw.mask & ~PSW_MASK_ASC);
 	regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE;
 
 	regs->gprs[2] = map_signal(sig);

@@ -183,7 +183,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	addr = start;
 	len = (unsigned long) nr_pages << PAGE_SHIFT;
 	end = start + len;
-	if (end < start)
+	if ((end < start) || (end > TASK_SIZE))
 		goto slow_irqon;
 
 	/*

@@ -137,13 +137,18 @@ static void cryptd_queue_worker(struct work_struct *work)
 	struct crypto_async_request *req, *backlog;
 
 	cpu_queue = container_of(work, struct cryptd_cpu_queue, work);
-	/* Only handle one request at a time to avoid hogging crypto
-	 * workqueue. preempt_disable/enable is used to prevent
-	 * being preempted by cryptd_enqueue_request() */
+	/*
+	 * Only handle one request at a time to avoid hogging crypto workqueue.
+	 * preempt_disable/enable is used to prevent being preempted by
+	 * cryptd_enqueue_request(). local_bh_disable/enable is used to prevent
+	 * cryptd_enqueue_request() being accessed from software interrupts.
+	 */
+	local_bh_disable();
 	preempt_disable();
 	backlog = crypto_get_backlog(&cpu_queue->queue);
 	req = crypto_dequeue_request(&cpu_queue->queue);
 	preempt_enable();
+	local_bh_enable();
 
 	if (!req)
 		return;

@@ -1345,12 +1345,15 @@ static int
 acpi_video_bus_get_devices(struct acpi_video_bus *video,
 			   struct acpi_device *device)
 {
-	int status;
+	int status = 0;
 	struct acpi_device *dev;
 
-	status = acpi_video_device_enumerate(video);
-	if (status)
-		return status;
+	/*
+	 * There are systems where video module known to work fine regardless
+	 * of broken _DOD and ignoring returned value here doesn't cause
+	 * any issues later.
+	 */
+	acpi_video_device_enumerate(video);
 
 	list_for_each_entry(dev, &device->children, node) {
 

@@ -175,8 +175,7 @@ struct rbd_device {
 	/* protects updating the header */
 	struct rw_semaphore     header_rwsem;
 	char                    snap_name[RBD_MAX_SNAP_NAME_LEN];
-	u32 cur_snap;	/* index+1 of current snapshot within snap context
-			   0 - for the head */
+	u64                     snap_id;	/* current snapshot id */
 	int read_only;
 
 	struct list_head	node;

@@ -450,7 +449,9 @@ static void rbd_client_release(struct kref *kref)
 	struct rbd_client *rbdc = container_of(kref, struct rbd_client, kref);
 
 	dout("rbd_release_client %p\n", rbdc);
+	spin_lock(&rbd_client_list_lock);
 	list_del(&rbdc->node);
+	spin_unlock(&rbd_client_list_lock);
 
 	ceph_destroy_client(rbdc->client);
 	kfree(rbdc->rbd_opts);

@@ -463,9 +464,7 @@ static void rbd_client_release(struct kref *kref)
  */
 static void rbd_put_client(struct rbd_device *rbd_dev)
 {
-	spin_lock(&rbd_client_list_lock);
 	kref_put(&rbd_dev->rbd_client->kref, rbd_client_release);
-	spin_unlock(&rbd_client_list_lock);
 	rbd_dev->rbd_client = NULL;
 }
 

@@ -498,7 +497,7 @@ static int rbd_header_from_disk(struct rbd_image_header *header,
 
 	snap_count = le32_to_cpu(ondisk->snap_count);
 	header->snapc = kmalloc(sizeof(struct ceph_snap_context) +
-				snap_count * sizeof (*ondisk),
+				snap_count * sizeof(u64),
 				gfp_flags);
 	if (!header->snapc)
 		return -ENOMEM;

@@ -552,21 +551,6 @@ err_snapc:
 	return -ENOMEM;
 }
 
-static int snap_index(struct rbd_image_header *header, int snap_num)
-{
-	return header->total_snaps - snap_num;
-}
-
-static u64 cur_snap_id(struct rbd_device *rbd_dev)
-{
-	struct rbd_image_header *header = &rbd_dev->header;
-
-	if (!rbd_dev->cur_snap)
-		return 0;
-
-	return header->snapc->snaps[snap_index(header, rbd_dev->cur_snap)];
-}
-
 static int snap_by_name(struct rbd_image_header *header, const char *snap_name,
 			u64 *seq, u64 *size)
 {

@@ -605,7 +589,7 @@ static int rbd_header_set_snap(struct rbd_device *dev, u64 *size)
 			snapc->seq = header->snap_seq;
 		else
 			snapc->seq = 0;
-		dev->cur_snap = 0;
+		dev->snap_id = CEPH_NOSNAP;
 		dev->read_only = 0;
 		if (size)
 			*size = header->image_size;

@@ -613,8 +597,7 @@ static int rbd_header_set_snap(struct rbd_device *dev, u64 *size)
 		ret = snap_by_name(header, dev->snap_name, &snapc->seq, size);
 		if (ret < 0)
 			goto done;
-
-		dev->cur_snap = header->total_snaps - ret;
+		dev->snap_id = snapc->seq;
 		dev->read_only = 1;
 	}
 

@@ -1521,7 +1504,7 @@ static void rbd_rq_fn(struct request_queue *q)
 					      coll, cur_seg);
 			else
 				rbd_req_read(rq, rbd_dev,
-					     cur_snap_id(rbd_dev),
+					     rbd_dev->snap_id,
 					     ofs,
 					     op_size, bio,
 					     coll, cur_seg);

@@ -1656,7 +1639,7 @@ static int rbd_header_add_snap(struct rbd_device *dev,
 	struct ceph_mon_client *monc;
 
 	/* we should create a snapshot only if we're pointing at the head */
-	if (dev->cur_snap)
+	if (dev->snap_id != CEPH_NOSNAP)
 		return -EINVAL;
 
 	monc = &dev->rbd_client->client->monc;

@@ -1683,7 +1666,9 @@ static int rbd_header_add_snap(struct rbd_device *dev,
 	if (ret < 0)
 		return ret;
 
-	dev->header.snapc->seq =  new_snapid;
+	down_write(&dev->header_rwsem);
+	dev->header.snapc->seq = new_snapid;
+	up_write(&dev->header_rwsem);
 
 	return 0;
 bad:

@@ -427,9 +427,17 @@ static int intel_overlay_off(struct intel_overlay *overlay)
 	OUT_RING(flip_addr);
 	OUT_RING(MI_WAIT_FOR_EVENT | MI_WAIT_FOR_OVERLAY_FLIP);
 	/* turn overlay off */
-	OUT_RING(MI_OVERLAY_FLIP | MI_OVERLAY_OFF);
-	OUT_RING(flip_addr);
-	OUT_RING(MI_WAIT_FOR_EVENT | MI_WAIT_FOR_OVERLAY_FLIP);
+	if (IS_I830(dev)) {
+		/* Workaround: Don't disable the overlay fully, since otherwise
+		 * it dies on the next OVERLAY_ON cmd. */
+		OUT_RING(MI_NOOP);
+		OUT_RING(MI_NOOP);
+		OUT_RING(MI_NOOP);
+	} else {
+		OUT_RING(MI_OVERLAY_FLIP | MI_OVERLAY_OFF);
+		OUT_RING(flip_addr);
+		OUT_RING(MI_WAIT_FOR_EVENT | MI_WAIT_FOR_OVERLAY_FLIP);
+	}
 	ADVANCE_LP_RING();
 
 	return intel_overlay_do_wait_request(overlay, request,

@@ -1421,7 +1421,7 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode)
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_SETUP, 0, 0);
 			atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0);
 			/* some early dce3.2 boards have a bug in their transmitter control table */
-			if ((rdev->family != CHIP_RV710) || (rdev->family != CHIP_RV730))
+			if ((rdev->family != CHIP_RV710) && (rdev->family != CHIP_RV730))
 				atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0);
 		}
 		if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(encoder)) && connector) {

@@ -749,7 +749,10 @@ static int ttm_get_pages(struct page **pages, unsigned npages, int flags,
 	/* clear the pages coming from the pool if requested */
 	if (flags & TTM_PAGE_FLAG_ZERO_ALLOC) {
 		list_for_each_entry(p, &plist, lru) {
-			clear_page(page_address(p));
+			if (PageHighMem(p))
+				clear_highpage(p);
+			else
+				clear_page(page_address(p));
 		}
 	}
 

@@ -3079,8 +3079,10 @@ static irqreturn_t sky2_intr(int irq, void *dev_id)
 
 	/* Reading this mask interrupts as side effect */
 	status = sky2_read32(hw, B0_Y2_SP_ISRC2);
-	if (status == 0 || status == ~0)
+	if (status == 0 || status == ~0) {
+		sky2_write32(hw, B0_Y2_SP_ICR, 2);
 		return IRQ_NONE;
+	}
 
 	prefetch(&hw->st_le[hw->st_idx]);
 

@@ -73,7 +73,7 @@
 static const int multicast_filter_limit = 32;
 
 #define MAX_READ_REQUEST_SHIFT	12
-#define TX_DMA_BURST	6	/* Maximum PCI burst, '6' is 1024 */
+#define TX_DMA_BURST	7	/* Maximum PCI burst, '7' is unlimited */
 #define SafeMtu		0x1c20	/* ... actually life sucks beyond ~7k */
 #define InterFrameGap	0x03	/* 3 means InterFrameGap = the shortest one */
 

@@ -3488,6 +3488,8 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
 	void __iomem *ioaddr = tp->mmio_addr;
 
 	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_25:
+	case RTL_GIGA_MAC_VER_26:
 	case RTL_GIGA_MAC_VER_29:
 	case RTL_GIGA_MAC_VER_30:
 	case RTL_GIGA_MAC_VER_32:

@@ -4129,6 +4131,9 @@ static void rtl_set_rx_mode(struct net_device *dev)
 		mc_filter[1] = swab32(data);
 	}
 
+	if (tp->mac_version == RTL_GIGA_MAC_VER_35)
+		mc_filter[1] = mc_filter[0] = 0xffffffff;
+
 	RTL_W32(MAR0 + 4, mc_filter[1]);
 	RTL_W32(MAR0 + 0, mc_filter[0]);
 

@@ -110,12 +110,10 @@ enum android_alarm_return_flags {
 #define ANDROID_ALARM_WAIT                  _IO('a', 1)
 
 #define ALARM_IOW(c, type, size)            _IOW('a', (c) | ((type) << 4), size)
-#define ALARM_IOR(c, type, size)            _IOR('a', (c) | ((type) << 4), size)
-
 /* Set alarm */
 #define ANDROID_ALARM_SET(type)             ALARM_IOW(2, type, struct timespec)
 #define ANDROID_ALARM_SET_AND_WAIT(type)    ALARM_IOW(3, type, struct timespec)
-#define ANDROID_ALARM_GET_TIME(type)        ALARM_IOR(4, type, struct timespec)
+#define ANDROID_ALARM_GET_TIME(type)        ALARM_IOW(4, type, struct timespec)
 #define ANDROID_ALARM_SET_RTC               _IOW('a', 5, struct timespec)
 #define ANDROID_ALARM_BASE_CMD(cmd)         (cmd & ~(_IOC(0, 0, 0xf0, 0)))
 #define ANDROID_ALARM_IOCTL_TO_TYPE(cmd)    (_IOC_NR(cmd) >> 4)

@@ -649,19 +649,19 @@ serial_omap_configure_xonxoff
 
 	/*
 	 * IXON Flag:
-	 * Flow control for OMAP.TX
-	 * OMAP.RX should listen for XON/XOFF
+	 * Enable XON/XOFF flow control on output.
+	 * Transmit XON1, XOFF1
 	 */
 	if (termios->c_iflag & IXON)
-		up->efr |= OMAP_UART_SW_RX;
+		up->efr |= OMAP_UART_SW_TX;
 
 	/*
 	 * IXOFF Flag:
-	 * Flow control for OMAP.RX
-	 * OMAP.TX should send XON/XOFF
+	 * Enable XON/XOFF flow control on input.
+	 * Receiver compares XON1, XOFF1.
 	 */
 	if (termios->c_iflag & IXOFF)
-		up->efr |= OMAP_UART_SW_TX;
+		up->efr |= OMAP_UART_SW_RX;
 
 	serial_out(up, UART_EFR, up->efr | UART_EFR_ECB);
 	serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A);

@@ -157,6 +157,7 @@ static void option_instat_callback(struct urb *urb);
 #define NOVATELWIRELESS_PRODUCT_EVDO_EMBEDDED_HIGHSPEED	0x8001
 #define NOVATELWIRELESS_PRODUCT_HSPA_EMBEDDED_FULLSPEED	0x9000
 #define NOVATELWIRELESS_PRODUCT_HSPA_EMBEDDED_HIGHSPEED	0x9001
+#define NOVATELWIRELESS_PRODUCT_E362		0x9010
 #define NOVATELWIRELESS_PRODUCT_G1		0xA001
 #define NOVATELWIRELESS_PRODUCT_G1_M		0xA002
 #define NOVATELWIRELESS_PRODUCT_G2		0xA010

@@ -192,6 +193,9 @@ static void option_instat_callback(struct urb *urb);
 #define DELL_PRODUCT_5730_MINICARD_TELUS	0x8181
 #define DELL_PRODUCT_5730_MINICARD_VZW		0x8182
 
+#define DELL_PRODUCT_5800_MINICARD_VZW		0x8195  /* Novatel E362 */
+#define DELL_PRODUCT_5800_V2_MINICARD_VZW	0x8196  /* Novatel E362 */
+
 #define KYOCERA_VENDOR_ID			0x0c88
 #define KYOCERA_PRODUCT_KPC650			0x17da
 #define KYOCERA_PRODUCT_KPC680			0x180a

@@ -282,6 +286,7 @@ static void option_instat_callback(struct urb *urb);
 /* ALCATEL PRODUCTS */
 #define ALCATEL_VENDOR_ID			0x1bbb
 #define ALCATEL_PRODUCT_X060S_X200		0x0000
+#define ALCATEL_PRODUCT_X220_X500D		0x0017
 
 #define PIRELLI_VENDOR_ID			0x1266
 #define PIRELLI_PRODUCT_C100_1			0x1002

@@ -705,6 +710,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_G2) },
 	/* Novatel Ovation MC551 a.k.a. Verizon USB551L */
 	{ USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_MC551, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_E362, 0xff, 0xff, 0xff) },
 
 	{ USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H01) },
 	{ USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H01A) },

@@ -727,6 +733,8 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5730_MINICARD_SPRINT) },	/* Dell Wireless 5730 Mobile Broadband EVDO/HSPA Mini-Card */
 	{ USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5730_MINICARD_TELUS) },	/* Dell Wireless 5730 Mobile Broadband EVDO/HSPA Mini-Card */
 	{ USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5730_MINICARD_VZW) }, 	/* Dell Wireless 5730 Mobile Broadband EVDO/HSPA Mini-Card */
+	{ USB_DEVICE_AND_INTERFACE_INFO(DELL_VENDOR_ID, DELL_PRODUCT_5800_MINICARD_VZW, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(DELL_VENDOR_ID, DELL_PRODUCT_5800_V2_MINICARD_VZW, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_E100A) },	/* ADU-E100, ADU-310 */
 	{ USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_500A) },
 	{ USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_620UW) },

@@ -1156,6 +1164,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S_X200),
 	  .driver_info = (kernel_ulong_t)&alcatel_x200_blacklist
 	},
+	{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X220_X500D) },
 	{ USB_DEVICE(AIRPLUS_VENDOR_ID, AIRPLUS_PRODUCT_MCD650) },
 	{ USB_DEVICE(TLAYTECH_VENDOR_ID, TLAYTECH_PRODUCT_TEU800) },
 	{ USB_DEVICE(LONGCHEER_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_W14),

@@ -768,7 +768,7 @@ int usb_serial_probe(struct usb_interface *interface,
 
 		if (retval) {
 			dbg("sub driver rejected device");
-			kfree(serial);
+			usb_serial_put(serial);
 			module_put(type->driver.owner);
 			return retval;
 		}

@@ -840,7 +840,7 @@ int usb_serial_probe(struct usb_interface *interface,
 		 */
 		if (num_bulk_in == 0 || num_bulk_out == 0) {
 			dev_info(&interface->dev, "PL-2303 hack: descriptors matched but endpoints did not\n");
-			kfree(serial);
+			usb_serial_put(serial);
 			module_put(type->driver.owner);
 			return -ENODEV;
 		}

@@ -854,7 +854,7 @@ int usb_serial_probe(struct usb_interface *interface,
 		if (num_ports == 0) {
 			dev_err(&interface->dev,
 			    "Generic device with no bulk out, not allowed.\n");
-			kfree(serial);
+			usb_serial_put(serial);
 			module_put(type->driver.owner);
 			return -EIO;
 		}

@@ -1365,8 +1365,8 @@ void xen_evtchn_do_upcall(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	exit_idle();
 	irq_enter();
+	exit_idle();
 
 	__xen_evtchn_do_upcall();
 

@@ -54,7 +54,12 @@
 	(CONGESTION_ON_THRESH(congestion_kb) -				\
 	 (CONGESTION_ON_THRESH(congestion_kb) >> 2))
 
-
+static inline struct ceph_snap_context *page_snap_context(struct page *page)
+{
+	if (PagePrivate(page))
+		return (void *)page->private;
+	return NULL;
+}
 
 /*
  * Dirty a page.  Optimistically adjust accounting, on the assumption

@@ -142,10 +147,9 @@ 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;
+	struct ceph_snap_context *snapc = page_snap_context(page);
 
 	BUG_ON(!PageLocked(page));
-	BUG_ON(!page->private);
 	BUG_ON(!PagePrivate(page));
 	BUG_ON(!page->mapping);
 

@@ -182,7 +186,6 @@ 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;
 }

@@ -202,7 +205,7 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 	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,
+				  (u64) page_offset(page), &len,
 				  ci->i_truncate_seq, ci->i_truncate_size,
 				  &page, 1, 0);
 	if (err == -ENOENT)

@@ -283,7 +286,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
 	int nr_pages = 0;
 	int ret;
 
-	off = page->index << PAGE_CACHE_SHIFT;
+	off = (u64) page_offset(page);
 
 	/* count pages */
 	next_index = page->index;

@@ -423,7 +426,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	struct ceph_inode_info *ci;
 	struct ceph_fs_client *fsc;
 	struct ceph_osd_client *osdc;
-	loff_t page_off = page->index << PAGE_CACHE_SHIFT;
+	loff_t page_off = page_offset(page);
 	int len = PAGE_CACHE_SIZE;
 	loff_t i_size;
 	int err = 0;

@@ -443,7 +446,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	osdc = &fsc->client->osdc;
 
 	/* verify this is a writeable snap context */
-	snapc = (void *)page->private;
+	snapc = page_snap_context(page);
 	if (snapc == NULL) {
 		dout("writepage %p page %p not dirty?\n", inode, page);
 		goto out;

@@ -451,7 +454,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	oldest = get_oldest_context(inode, &snap_size);
 	if (snapc->seq > oldest->seq) {
 		dout("writepage %p page %p snapc %p not writeable - noop\n",
-		     inode, page, (void *)page->private);
+		     inode, page, snapc);
 		/* we should only noop if called by kswapd */
 		WARN_ON((current->flags & PF_MEMALLOC) == 0);
 		ceph_put_snap_context(oldest);

@@ -591,7 +594,7 @@ static void writepages_finish(struct ceph_osd_request *req,
 			clear_bdi_congested(&fsc->backing_dev_info,
 					    BLK_RW_ASYNC);
 
-		ceph_put_snap_context((void *)page->private);
+		ceph_put_snap_context(page_snap_context(page));
 		page->private = 0;
 		ClearPagePrivate(page);
 		dout("unlocking %d %p\n", i, page);

@@ -795,7 +798,7 @@ get_more_pages:
 			}
 
 			/* only if matching snap context */
-			pgsnapc = (void *)page->private;
+			pgsnapc = page_snap_context(page);
 			if (pgsnapc->seq > snapc->seq) {
 				dout("page snapc %p %lld > oldest %p %lld\n",
 				     pgsnapc, pgsnapc->seq, snapc, snapc->seq);

@@ -814,8 +817,7 @@ get_more_pages:
 			/* ok */
 			if (locked_pages == 0) {
 				/* prepare async write request */
-				offset = (unsigned long long)page->index
-					<< PAGE_CACHE_SHIFT;
+				offset = (u64) page_offset(page);
 				len = wsize;
 				req = ceph_osdc_new_request(&fsc->client->osdc,
 					    &ci->i_layout,

@@ -984,7 +986,7 @@ retry_locked:
 	BUG_ON(!ci->i_snap_realm);
 	down_read(&mdsc->snap_rwsem);
 	BUG_ON(!ci->i_snap_realm->cached_context);
-	snapc = (void *)page->private;
+	snapc = page_snap_context(page);
 	if (snapc && snapc != ci->i_head_snapc) {
 		/*
 		 * this page is already dirty in another (older) snap

@@ -1177,7 +1179,7 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct inode *inode = vma->vm_file->f_dentry->d_inode;
 	struct page *page = vmf->page;
 	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
-	loff_t off = page->index << PAGE_CACHE_SHIFT;
+	loff_t off = page_offset(page);
 	loff_t size, len;
 	int ret;
 

@@ -201,6 +201,7 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 	int err = -ENOMEM;
 
 	dout("ceph_fs_debugfs_init\n");
+	BUG_ON(!fsc->client->debugfs_dir);
 	fsc->debugfs_congestion_kb =
 		debugfs_create_file("writeback_congestion_kb",
 				    0600,

@@ -334,10 +334,10 @@ void ceph_put_mds_session(struct ceph_mds_session *s)
 	dout("mdsc put_session %p %d -> %d\n", s,
 	     atomic_read(&s->s_ref), atomic_read(&s->s_ref)-1);
 	if (atomic_dec_and_test(&s->s_ref)) {
-		if (s->s_authorizer)
+		if (s->s_auth.authorizer)
 		     s->s_mdsc->fsc->client->monc.auth->ops->destroy_authorizer(
 			     s->s_mdsc->fsc->client->monc.auth,
-			     s->s_authorizer);
+			     s->s_auth.authorizer);
 		kfree(s);
 	}
 }

@@ -394,11 +394,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	s->s_seq = 0;
 	mutex_init(&s->s_mutex);
 
-	ceph_con_init(mdsc->fsc->client->msgr, &s->s_con);
-	s->s_con.private = s;
-	s->s_con.ops = &mds_con_ops;
-	s->s_con.peer_name.type = CEPH_ENTITY_TYPE_MDS;
-	s->s_con.peer_name.num = cpu_to_le64(mds);
+	ceph_con_init(&s->s_con, s, &mds_con_ops, &mdsc->fsc->client->msgr);
 
 	spin_lock_init(&s->s_gen_ttl_lock);
 	s->s_cap_gen = 0;

@@ -440,7 +436,8 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	mdsc->sessions[mds] = s;
 	atomic_inc(&s->s_ref);  /* one ref to sessions[], one to caller */
 
-	ceph_con_open(&s->s_con, ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
+	ceph_con_open(&s->s_con, CEPH_ENTITY_TYPE_MDS, mds,
+		      ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
 
 	return s;
 

@@ -2532,6 +2529,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 	session->s_seq = 0;
 
 	ceph_con_open(&session->s_con,
+		      CEPH_ENTITY_TYPE_MDS, mds,
 		      ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
 
 	/* replay unsafe requests */

@@ -2636,7 +2634,8 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 		     ceph_mdsmap_is_laggy(newmap, i) ? " (laggy)" : "",
 		     session_state_name(s->s_state));
 
-		if (memcmp(ceph_mdsmap_get_addr(oldmap, i),
+		if (i >= newmap->m_max_mds ||
+		    memcmp(ceph_mdsmap_get_addr(oldmap, i),
 			   ceph_mdsmap_get_addr(newmap, i),
 			   sizeof(struct ceph_entity_addr))) {
 			if (s->s_state == CEPH_MDS_SESSION_OPENING) {

@@ -3395,39 +3394,33 @@ out:
 /*
  * authentication
  */
-static int get_authorizer(struct ceph_connection *con,
-			  void **buf, int *len, int *proto,
-			  void **reply_buf, int *reply_len, int force_new)
+
+/*
+ * Note: returned pointer is the address of a structure that's
+ * managed separately.  Caller must *not* attempt to free it.
+ */
+static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con,
+					int *proto, int force_new)
 {
 	struct ceph_mds_session *s = con->private;
 	struct ceph_mds_client *mdsc = s->s_mdsc;
 	struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
-	int ret = 0;
-
-	if (force_new && s->s_authorizer) {
-		ac->ops->destroy_authorizer(ac, s->s_authorizer);
-		s->s_authorizer = NULL;
-	}
-	if (s->s_authorizer == NULL) {
-		if (ac->ops->create_authorizer) {
-			ret = ac->ops->create_authorizer(
-				ac, CEPH_ENTITY_TYPE_MDS,
-				&s->s_authorizer,
-				&s->s_authorizer_buf,
-				&s->s_authorizer_buf_len,
-				&s->s_authorizer_reply_buf,
-				&s->s_authorizer_reply_buf_len);
-			if (ret)
-				return ret;
-		}
-	}
+	struct ceph_auth_handshake *auth = &s->s_auth;
 
+	if (force_new && auth->authorizer) {
+		if (ac->ops && ac->ops->destroy_authorizer)
+			ac->ops->destroy_authorizer(ac, auth->authorizer);
+		auth->authorizer = NULL;
+	}
+	if (!auth->authorizer && ac->ops && ac->ops->create_authorizer) {
+		int ret = ac->ops->create_authorizer(ac, CEPH_ENTITY_TYPE_MDS,
+							auth);
+		if (ret)
+			return ERR_PTR(ret);
+	}
 	*proto = ac->protocol;
-	*buf = s->s_authorizer_buf;
-	*len = s->s_authorizer_buf_len;
-	*reply_buf = s->s_authorizer_reply_buf;
-	*reply_len = s->s_authorizer_reply_buf_len;
-	return 0;
+
+	return auth;
 }
 
 

@@ -3437,7 +3430,7 @@ static int verify_authorizer_reply(struct ceph_connection *con, int len)
 	struct ceph_mds_client *mdsc = s->s_mdsc;
 	struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
 
-	return ac->ops->verify_authorizer_reply(ac, s->s_authorizer, len);
+	return ac->ops->verify_authorizer_reply(ac, s->s_auth.authorizer, len);
 }
 
 static int invalidate_authorizer(struct ceph_connection *con)

@@ -11,6 +11,7 @@
 #include <linux/ceph/types.h>
 #include <linux/ceph/messenger.h>
 #include <linux/ceph/mdsmap.h>
+#include <linux/ceph/auth.h>
 
 /*
  * Some lock dependencies:

@@ -113,9 +114,7 @@ struct ceph_mds_session {
 
 	struct ceph_connection s_con;
 
-	struct ceph_authorizer *s_authorizer;
-	void             *s_authorizer_buf, *s_authorizer_reply_buf;
-	size_t            s_authorizer_buf_len, s_authorizer_reply_buf_len;
+	struct ceph_auth_handshake s_auth;
 
 	/* protected by s_gen_ttl_lock */
 	spinlock_t        s_gen_ttl_lock;

@@ -225,6 +225,13 @@ sid_to_str(struct cifs_sid *sidptr, char *sidstr)
 }
 
 static void
+cifs_copy_sid(struct cifs_sid *dst, const struct cifs_sid *src)
+{
+	memcpy(dst, src, sizeof(*dst));
+	dst->num_subauth = min_t(u8, src->num_subauth, NUM_SUBAUTHS);
+}
+
+static void
 id_rb_insert(struct rb_root *root, struct cifs_sid *sidptr,
 		struct cifs_sid_id **psidid, char *typestr)
 {

@@ -248,7 +255,7 @@ id_rb_insert(struct rb_root *root, struct cifs_sid *sidptr,
 		}
 	}
 
-	memcpy(&(*psidid)->sid, sidptr, sizeof(struct cifs_sid));
+	cifs_copy_sid(&(*psidid)->sid, sidptr);
 	(*psidid)->time = jiffies - (SID_MAP_RETRY + 1);
 	(*psidid)->refcount = 0;
 

@@ -354,7 +361,7 @@ id_to_sid(unsigned long cid, uint sidtype, struct cifs_sid *ssid)
 	 * any fields of the node after a reference is put .
 	 */
 	if (test_bit(SID_ID_MAPPED, &psidid->state)) {
-		memcpy(ssid, &psidid->sid, sizeof(struct cifs_sid));
+		cifs_copy_sid(ssid, &psidid->sid);
 		psidid->time = jiffies; /* update ts for accessing */
 		goto id_sid_out;
 	}

@@ -370,14 +377,14 @@ id_to_sid(unsigned long cid, uint sidtype, struct cifs_sid *ssid)
 		if (IS_ERR(sidkey)) {
 			rc = -EINVAL;
 			cFYI(1, "%s: Can't map and id to a SID", __func__);
+		} else if (sidkey->datalen < sizeof(struct cifs_sid)) {
+			rc = -EIO;
+			cFYI(1, "%s: Downcall contained malformed key "
+				"(datalen=%hu)", __func__, sidkey->datalen);
 		} else {
 			lsid = (struct cifs_sid *)sidkey->payload.data;
-			memcpy(&psidid->sid, lsid,
-				sidkey->datalen < sizeof(struct cifs_sid) ?
-				sidkey->datalen : sizeof(struct cifs_sid));
-			memcpy(ssid, &psidid->sid,
-				sidkey->datalen < sizeof(struct cifs_sid) ?
-				sidkey->datalen : sizeof(struct cifs_sid));
+			cifs_copy_sid(&psidid->sid, lsid);
+			cifs_copy_sid(ssid, &psidid->sid);
 			set_bit(SID_ID_MAPPED, &psidid->state);
 			key_put(sidkey);
 			kfree(psidid->sidstr);

@@ -396,7 +403,7 @@ id_to_sid(unsigned long cid, uint sidtype, struct cifs_sid *ssid)
 			return rc;
 		}
 		if (test_bit(SID_ID_MAPPED, &psidid->state))
-			memcpy(ssid, &psidid->sid, sizeof(struct cifs_sid));
+			cifs_copy_sid(ssid, &psidid->sid);
 		else
 			rc = -EINVAL;
 	}

@@ -675,8 +682,6 @@ int compare_sids(const struct cifs_sid *ctsid, const struct cifs_sid *cwsid)
 static void copy_sec_desc(const struct cifs_ntsd *pntsd,
 				struct cifs_ntsd *pnntsd, __u32 sidsoffset)
 {
-	int i;
-
 	struct cifs_sid *owner_sid_ptr, *group_sid_ptr;
 	struct cifs_sid *nowner_sid_ptr, *ngroup_sid_ptr;
 

@@ -692,26 +697,14 @@ static void copy_sec_desc(const struct cifs_ntsd *pntsd,
 	owner_sid_ptr = (struct cifs_sid *)((char *)pntsd +
 				le32_to_cpu(pntsd->osidoffset));
 	nowner_sid_ptr = (struct cifs_sid *)((char *)pnntsd + sidsoffset);
-
-	nowner_sid_ptr->revision = owner_sid_ptr->revision;
-	nowner_sid_ptr->num_subauth = owner_sid_ptr->num_subauth;
-	for (i = 0; i < 6; i++)
-		nowner_sid_ptr->authority[i] = owner_sid_ptr->authority[i];
-	for (i = 0; i < 5; i++)
-		nowner_sid_ptr->sub_auth[i] = owner_sid_ptr->sub_auth[i];
+	cifs_copy_sid(nowner_sid_ptr, owner_sid_ptr);
 
 	/* copy group sid */
 	group_sid_ptr = (struct cifs_sid *)((char *)pntsd +
 				le32_to_cpu(pntsd->gsidoffset));
 	ngroup_sid_ptr = (struct cifs_sid *)((char *)pnntsd + sidsoffset +
 					sizeof(struct cifs_sid));
-
-	ngroup_sid_ptr->revision = group_sid_ptr->revision;
-	ngroup_sid_ptr->num_subauth = group_sid_ptr->num_subauth;
-	for (i = 0; i < 6; i++)
-		ngroup_sid_ptr->authority[i] = group_sid_ptr->authority[i];
-	for (i = 0; i < 5; i++)
-		ngroup_sid_ptr->sub_auth[i] = group_sid_ptr->sub_auth[i];
+	cifs_copy_sid(ngroup_sid_ptr, group_sid_ptr);
 
 	return;
 }

@@ -1120,8 +1113,7 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd,
 				kfree(nowner_sid_ptr);
 				return rc;
 			}
-			memcpy(owner_sid_ptr, nowner_sid_ptr,
-					sizeof(struct cifs_sid));
+			cifs_copy_sid(owner_sid_ptr, nowner_sid_ptr);
 			kfree(nowner_sid_ptr);
 			*aclflag = CIFS_ACL_OWNER;
 		}

@@ -1139,8 +1131,7 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd,
 				kfree(ngroup_sid_ptr);
 				return rc;
 			}
-			memcpy(group_sid_ptr, ngroup_sid_ptr,
-					sizeof(struct cifs_sid));
+			cifs_copy_sid(group_sid_ptr, ngroup_sid_ptr);
 			kfree(ngroup_sid_ptr);
 			*aclflag = CIFS_ACL_GROUP;
 		}

@@ -280,6 +280,7 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
 	char *fnek_src;
 	char *cipher_key_bytes_src;
 	char *fn_cipher_key_bytes_src;
+	u8 cipher_code;
 
 	*check_ruid = 0;
 

@@ -421,6 +422,18 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
 	    && !fn_cipher_key_bytes_set)
 		mount_crypt_stat->global_default_fn_cipher_key_bytes =
 			mount_crypt_stat->global_default_cipher_key_size;
+
+	cipher_code = ecryptfs_code_for_cipher_string(
+		mount_crypt_stat->global_default_cipher_name,
+		mount_crypt_stat->global_default_cipher_key_size);
+	if (!cipher_code) {
+		ecryptfs_printk(KERN_ERR,
+				"eCryptfs doesn't support cipher: %s",
+				mount_crypt_stat->global_default_cipher_name);
+		rc = -EINVAL;
+		goto out;
+	}
+
 	mutex_lock(&key_tfm_list_mutex);
 	if (!ecryptfs_tfm_exists(mount_crypt_stat->global_default_cipher_name,
 				 NULL)) {

@@ -506,7 +519,6 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		goto out;
 	}
 
-	s->s_flags = flags;
 	rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs", BDI_CAP_MAP_COPY);
 	if (rc)
 		goto out1;

@@ -542,6 +554,15 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 	}
 
 	ecryptfs_set_superblock_lower(s, path.dentry->d_sb);
+
+	/**
+	 * Set the POSIX ACL flag based on whether they're enabled in the lower
+	 * mount. Force a read-only eCryptfs mount if the lower mount is ro.
+	 * Allow a ro eCryptfs mount even when the lower mount is rw.
+	 */
+	s->s_flags = flags & ~MS_POSIXACL;
+	s->s_flags |= path.dentry->d_sb->s_flags & (MS_RDONLY | MS_POSIXACL);
+
 	s->s_maxbytes = path.dentry->d_sb->s_maxbytes;
 	s->s_blocksize = path.dentry->d_sb->s_blocksize;
 	s->s_magic = ECRYPTFS_SUPER_MAGIC;

@@ -307,8 +307,7 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 			dprintk("%s ERROR: %d Reset session\n", __func__,
 				errorcode);
 			nfs4_schedule_session_recovery(clp->cl_session);
-			exception->retry = 1;
-			break;
+			goto wait_on_recovery;
 #endif /* defined(CONFIG_NFS_V4_1) */
 		case -NFS4ERR_FILE_OPEN:
 			if (exception->timeout > HZ) {

@@ -21,6 +21,7 @@ static bool should_merge(struct fsnotify_event *old, struct fsnotify_event *new)
 			if ((old->path.mnt == new->path.mnt) &&
 			    (old->path.dentry == new->path.dentry))
 				return true;
+			break;
 		case (FSNOTIFY_EVENT_NONE):
 			return true;
 		default:

@@ -1788,8 +1788,9 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 
 	BUG_ON(!th->t_trans_id);
 
-	dquot_initialize(inode);
+	reiserfs_write_unlock(inode->i_sb);
 	err = dquot_alloc_inode(inode);
+	reiserfs_write_lock(inode->i_sb);
 	if (err)
 		goto out_end_trans;
 	if (!dir->i_nlink) {

@@ -1985,8 +1986,10 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 
       out_end_trans:
 	journal_end(th, th->t_super, th->t_blocks_allocated);
+	reiserfs_write_unlock(inode->i_sb);
 	/* Drop can be outside and it needs more credits so it's better to have it outside */
 	dquot_drop(inode);
+	reiserfs_write_lock(inode->i_sb);
 	inode->i_flags |= S_NOQUOTA;
 	make_bad_inode(inode);
 

@@ -3109,10 +3112,9 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
 	/* must be turned off for recursive notify_change calls */
 	ia_valid = attr->ia_valid &= ~(ATTR_KILL_SUID|ATTR_KILL_SGID);
 
-	depth = reiserfs_write_lock_once(inode->i_sb);
 	if (is_quota_modification(inode, attr))
 		dquot_initialize(inode);
-
+	depth = reiserfs_write_lock_once(inode->i_sb);
 	if (attr->ia_valid & ATTR_SIZE) {
 		/* version 2 items will be caught by the s_maxbytes check
 		 ** done for us in vmtruncate

@@ -3176,7 +3178,9 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
 		error = journal_begin(&th, inode->i_sb, jbegin_count);
 		if (error)
 			goto out;
+		reiserfs_write_unlock_once(inode->i_sb, depth);
 		error = dquot_transfer(inode, attr);
+		depth = reiserfs_write_lock_once(inode->i_sb);
 		if (error) {
 			journal_end(&th, inode->i_sb, jbegin_count);
 			goto out;

@@ -1968,7 +1968,9 @@ int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th, struct tree
 		       key2type(&(key->on_disk_key)));
 #endif
 
+	reiserfs_write_unlock(inode->i_sb);
 	retval = dquot_alloc_space_nodirty(inode, pasted_size);
+	reiserfs_write_lock(inode->i_sb);
 	if (retval) {
 		pathrelse(search_path);
 		return retval;

@@ -2061,9 +2063,11 @@ int reiserfs_insert_item(struct reiserfs_transaction_handle *th,
 			       "reiserquota insert_item(): allocating %u id=%u type=%c",
 			       quota_bytes, inode->i_uid, head2type(ih));
 #endif
+		reiserfs_write_unlock(inode->i_sb);
 		/* We can't dirty inode here. It would be immediately written but
 		 * appropriate stat item isn't inserted yet... */
 		retval = dquot_alloc_space_nodirty(inode, quota_bytes);
+		reiserfs_write_lock(inode->i_sb);
 		if (retval) {
 			pathrelse(path);
 			return retval;

@@ -256,7 +256,9 @@ static int finish_unfinished(struct super_block *s)
 			retval = remove_save_link_only(s, &save_link_key, 0);
 			continue;
 		}
+		reiserfs_write_unlock(s);
 		dquot_initialize(inode);
+		reiserfs_write_lock(s);
 
 		if (truncate && S_ISDIR(inode->i_mode)) {
 			/* We got a truncate request for a dir which is impossible.

@@ -1292,7 +1294,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 				kfree(qf_names[i]);
 #endif
 		err = -EINVAL;
-		goto out_err;
+		goto out_unlock;
 	}
 #ifdef CONFIG_QUOTA
 	handle_quota_files(s, qf_names, &qfmt);

@@ -1336,7 +1338,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 	if (blocks) {
 		err = reiserfs_resize(s, blocks);
 		if (err != 0)
-			goto out_err;
+			goto out_unlock;
 	}
 
 	if (*mount_flags & MS_RDONLY) {

@@ -1346,9 +1348,15 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 			/* it is read-only already */
 			goto out_ok;
 
+		/*
+		 * Drop write lock. Quota will retake it when needed and lock
+		 * ordering requires calling dquot_suspend() without it.
+		 */
+		reiserfs_write_unlock(s);
 		err = dquot_suspend(s, -1);
 		if (err < 0)
 			goto out_err;
+		reiserfs_write_lock(s);
 
 		/* try to remount file system with read-only permissions */
 		if (sb_umount_state(rs) == REISERFS_VALID_FS

@@ -1358,7 +1366,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 
 		err = journal_begin(&th, s, 10);
 		if (err)
-			goto out_err;
+			goto out_unlock;
 
 		/* Mounting a rw partition read-only. */
 		reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1);

@@ -1373,7 +1381,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 
 		if (reiserfs_is_journal_aborted(journal)) {
 			err = journal->j_errno;
-			goto out_err;
+			goto out_unlock;
 		}
 
 		handle_data_mode(s, mount_options);

@@ -1382,7 +1390,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 		s->s_flags &= ~MS_RDONLY;	/* now it is safe to call journal_begin */
 		err = journal_begin(&th, s, 10);
 		if (err)
-			goto out_err;
+			goto out_unlock;
 
 		/* Mount a partition which is read-only, read-write */
 		reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1);

@@ -1399,11 +1407,17 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 	SB_JOURNAL(s)->j_must_wait = 1;
 	err = journal_end(&th, s, 10);
 	if (err)
-		goto out_err;
+		goto out_unlock;
 	s->s_dirt = 0;
 
 	if (!(*mount_flags & MS_RDONLY)) {
+		/*
+		 * Drop write lock. Quota will retake it when needed and lock
+		 * ordering requires calling dquot_resume() without it.
+		 */
+		reiserfs_write_unlock(s);
 		dquot_resume(s, -1);
+		reiserfs_write_lock(s);
 		finish_unfinished(s);
 		reiserfs_xattr_init(s, *mount_flags);
 	}

@@ -1413,9 +1427,10 @@ out_ok:
 	reiserfs_write_unlock(s);
 	return 0;
 
+out_unlock:
+	reiserfs_write_unlock(s);
 out_err:
 	kfree(new_opts);
-	reiserfs_write_unlock(s);
 	return err;
 }
 

@@ -2049,13 +2064,15 @@ static int reiserfs_write_dquot(struct dquot *dquot)
 			  REISERFS_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
 	if (ret)
 		goto out;
+	reiserfs_write_unlock(dquot->dq_sb);
 	ret = dquot_commit(dquot);
+	reiserfs_write_lock(dquot->dq_sb);
 	err =
 	    journal_end(&th, dquot->dq_sb,
 			REISERFS_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
 	if (!ret && err)
 		ret = err;
-      out:
+out:
 	reiserfs_write_unlock(dquot->dq_sb);
 	return ret;
 }

@@ -2071,13 +2088,15 @@ static int reiserfs_acquire_dquot(struct dquot *dquot)
 			  REISERFS_QUOTA_INIT_BLOCKS(dquot->dq_sb));
 	if (ret)
 		goto out;
+	reiserfs_write_unlock(dquot->dq_sb);
 	ret = dquot_acquire(dquot);
+	reiserfs_write_lock(dquot->dq_sb);
 	err =
 	    journal_end(&th, dquot->dq_sb,
 			REISERFS_QUOTA_INIT_BLOCKS(dquot->dq_sb));
 	if (!ret && err)
 		ret = err;
-      out:
+out:
 	reiserfs_write_unlock(dquot->dq_sb);
 	return ret;
 }

@@ -2091,19 +2110,21 @@ static int reiserfs_release_dquot(struct dquot *dquot)
 	ret =
 	    journal_begin(&th, dquot->dq_sb,
 			  REISERFS_QUOTA_DEL_BLOCKS(dquot->dq_sb));
+	reiserfs_write_unlock(dquot->dq_sb);
 	if (ret) {
 		/* Release dquot anyway to avoid endless cycle in dqput() */
 		dquot_release(dquot);
 		goto out;
 	}
 	ret = dquot_release(dquot);
+	reiserfs_write_lock(dquot->dq_sb);
 	err =
 	    journal_end(&th, dquot->dq_sb,
 			REISERFS_QUOTA_DEL_BLOCKS(dquot->dq_sb));
 	if (!ret && err)
 		ret = err;
-      out:
 	reiserfs_write_unlock(dquot->dq_sb);
+out:
 	return ret;
 }
 

@@ -2128,11 +2149,13 @@ static int reiserfs_write_info(struct super_block *sb, int type)
 	ret = journal_begin(&th, sb, 2);
 	if (ret)
 		goto out;
+	reiserfs_write_unlock(sb);
 	ret = dquot_commit_info(sb, type);
+	reiserfs_write_lock(sb);
 	err = journal_end(&th, sb, 2);
 	if (!ret && err)
 		ret = err;
-      out:
+out:
 	reiserfs_write_unlock(sb);
 	return ret;
 }

@@ -2157,8 +2180,11 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
 	struct reiserfs_transaction_handle th;
 	int opt = type == USRQUOTA ? REISERFS_USRQUOTA : REISERFS_GRPQUOTA;
 
-	if (!(REISERFS_SB(sb)->s_mount_opt & (1 << opt)))
-		return -EINVAL;
+	reiserfs_write_lock(sb);
+	if (!(REISERFS_SB(sb)->s_mount_opt & (1 << opt))) {
+		err = -EINVAL;
+		goto out;
+	}
 
 	/* Quotafile not on the same filesystem? */
 	if (path->dentry->d_sb != sb) {

@@ -2200,8 +2226,10 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
 		if (err)
 			goto out;
 	}
-	err = dquot_quota_on(sb, type, format_id, path);
+	reiserfs_write_unlock(sb);
+	return dquot_quota_on(sb, type, format_id, path);
 out:
+	reiserfs_write_unlock(sb);
 	return err;
 }
 

@@ -2275,7 +2303,9 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type,
 		tocopy = sb->s_blocksize - offset < towrite ?
 		    sb->s_blocksize - offset : towrite;
 		tmp_bh.b_state = 0;
+		reiserfs_write_lock(sb);
 		err = reiserfs_get_block(inode, blk, &tmp_bh, GET_BLOCK_CREATE);
+		reiserfs_write_unlock(sb);
 		if (err)
 			goto out;
 		if (offset || tocopy != sb->s_blocksize)

@@ -2291,10 +2321,12 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type,
 		flush_dcache_page(bh->b_page);
 		set_buffer_uptodate(bh);
 		unlock_buffer(bh);
+		reiserfs_write_lock(sb);
 		reiserfs_prepare_for_journal(sb, bh, 1);
 		journal_mark_dirty(current->journal_info, sb, bh);
 		if (!journal_quota)
 			reiserfs_add_ordered_list(inode, bh);
+		reiserfs_write_unlock(sb);
 		brelse(bh);
 		offset = 0;
 		towrite -= tocopy;

@@ -681,8 +681,16 @@ int ubifs_find_free_leb_for_idx(struct ubifs_info *c)
 	if (!lprops) {
 		lprops = ubifs_fast_find_freeable(c);
 		if (!lprops) {
-			ubifs_assert(c->freeable_cnt == 0);
-			if (c->lst.empty_lebs - c->lst.taken_empty_lebs > 0) {
+			/*
+			 * The first condition means the following: go scan the
+			 * LPT if there are uncategorized lprops, which means
+			 * there may be freeable LEBs there (UBIFS does not
+			 * store the information about freeable LEBs in the
+			 * master node).
+			 */
+			if (c->in_a_category_cnt != c->main_lebs ||
+			    c->lst.empty_lebs - c->lst.taken_empty_lebs > 0) {
+				ubifs_assert(c->freeable_cnt == 0);
 				lprops = scan_for_leb_for_idx(c);
 				if (IS_ERR(lprops)) {
 					err = PTR_ERR(lprops);

@@ -300,8 +300,11 @@ void ubifs_add_to_cat(struct ubifs_info *c, struct ubifs_lprops *lprops,
 	default:
 		ubifs_assert(0);
 	}
+
 	lprops->flags &= ~LPROPS_CAT_MASK;
 	lprops->flags |= cat;
+	c->in_a_category_cnt += 1;
+	ubifs_assert(c->in_a_category_cnt <= c->main_lebs);
 }
 
 /**

@@ -334,6 +337,9 @@ static void ubifs_remove_from_cat(struct ubifs_info *c,
 	default:
 		ubifs_assert(0);
 	}
+
+	c->in_a_category_cnt -= 1;
+	ubifs_assert(c->in_a_category_cnt >= 0);
 }
 
 /**

@@ -1184,6 +1184,8 @@ struct ubifs_debug_info;
  * @freeable_list: list of freeable non-index LEBs (free + dirty == @leb_size)
  * @frdi_idx_list: list of freeable index LEBs (free + dirty == @leb_size)
  * @freeable_cnt: number of freeable LEBs in @freeable_list
+ * @in_a_category_cnt: count of lprops which are in a certain category, which
+ *                     basically meants that they were loaded from the flash
  *
  * @ltab_lnum: LEB number of LPT's own lprops table
  * @ltab_offs: offset of LPT's own lprops table

@@ -1413,6 +1415,7 @@ struct ubifs_info {
 	struct list_head freeable_list;
 	struct list_head frdi_idx_list;
 	int freeable_cnt;
+	int in_a_category_cnt;
 
 	int ltab_lnum;
 	int ltab_offs;

@@ -1165,9 +1165,14 @@ xfs_buf_bio_end_io(
 {
 	xfs_buf_t		*bp = (xfs_buf_t *)bio->bi_private;
 
-	xfs_buf_ioerror(bp, -error);
+	/*
+	 * don't overwrite existing errors - otherwise we can lose errors on
+	 * buffers that require multiple bios to complete.
+	 */
+	if (!bp->b_error)
+		xfs_buf_ioerror(bp, -error);
 
-	if (!error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
+	if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
 		invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp));
 
 	_xfs_buf_ioend(bp, 1);

@@ -1243,6 +1248,11 @@ next_chunk:
 		if (size)
 			goto next_chunk;
 	} else {
+		/*
+		 * This is guaranteed not to be the last io reference count
+		 * because the caller (xfs_buf_iorequest) holds a count itself.
+		 */
+		atomic_dec(&bp->b_io_remaining);
 		xfs_buf_ioerror(bp, EIO);
 		bio_put(bio);
 	}

@@ -14,6 +14,14 @@
 struct ceph_auth_client;
 struct ceph_authorizer;
 
+struct ceph_auth_handshake {
+	struct ceph_authorizer *authorizer;
+	void *authorizer_buf;
+	size_t authorizer_buf_len;
+	void *authorizer_reply_buf;
+	size_t authorizer_reply_buf_len;
+};
+
 struct ceph_auth_client_ops {
 	const char *name;
 

@@ -43,9 +51,7 @@ struct ceph_auth_client_ops {
 	 * the response to authenticate the service.
 	 */
 	int (*create_authorizer)(struct ceph_auth_client *ac, int peer_type,
-				 struct ceph_authorizer **a,
-				 void **buf, size_t *len,
-				 void **reply_buf, size_t *reply_len);
+				 struct ceph_auth_handshake *auth);
 	int (*verify_authorizer_reply)(struct ceph_auth_client *ac,
 				       struct ceph_authorizer *a, size_t len);
 	void (*destroy_authorizer)(struct ceph_auth_client *ac,

@@ -132,7 +132,7 @@ struct ceph_client {
 	u32 supported_features;
 	u32 required_features;
 
-	struct ceph_messenger *msgr;   /* messenger instance */
+	struct ceph_messenger msgr;   /* messenger instance */
 	struct ceph_mon_client monc;
 	struct ceph_osd_client osdc;
 

@@ -25,15 +25,12 @@ struct ceph_connection_operations {
 	void (*dispatch) (struct ceph_connection *con, struct ceph_msg *m);
 
 	/* authorize an outgoing connection */
-	int (*get_authorizer) (struct ceph_connection *con,
-			       void **buf, int *len, int *proto,
-			       void **reply_buf, int *reply_len, int force_new);
+	struct ceph_auth_handshake *(*get_authorizer) (
+				struct ceph_connection *con,
+			       int *proto, int force_new);
 	int (*verify_authorizer_reply) (struct ceph_connection *con, int len);
 	int (*invalidate_authorizer)(struct ceph_connection *con);
 
-	/* protocol version mismatch */
-	void (*bad_proto) (struct ceph_connection *con);
-
 	/* there was some error on the socket (disconnect, whatever) */
 	void (*fault) (struct ceph_connection *con);
 

@@ -53,6 +50,7 @@ struct ceph_messenger {
 	struct ceph_entity_inst inst;    /* my name+address */
 	struct ceph_entity_addr my_enc_addr;
 
+	atomic_t stopping;
 	bool nocrc;
 
 	/*

@@ -80,7 +78,10 @@ struct ceph_msg {
 	unsigned nr_pages;              /* size of page array */
 	unsigned page_alignment;        /* io offset in first page */
 	struct ceph_pagelist *pagelist; /* instead of pages */
+
+	struct ceph_connection *con;
 	struct list_head list_head;
+
 	struct kref kref;
 	struct bio  *bio;		/* instead of pages/pagelist */
 	struct bio  *bio_iter;		/* bio iterator */

@@ -106,23 +107,6 @@ struct ceph_msg_pos {
 #define MAX_DELAY_INTERVAL	(5 * 60 * HZ)
 
 /*
- * ceph_connection state bit flags
- */
-#define LOSSYTX         0  /* we can close channel or drop messages on errors */
-#define CONNECTING	1
-#define NEGOTIATING	2
-#define KEEPALIVE_PENDING      3
-#define WRITE_PENDING	4  /* we have data ready to send */
-#define STANDBY		8  /* no outgoing messages, socket closed.  we keep
-			    * the ceph_connection around to maintain shared
-			    * state with the peer. */
-#define CLOSED		10 /* we've closed the connection */
-#define SOCK_CLOSED	11 /* socket state changed to closed */
-#define OPENING         13 /* open connection w/ (possibly new) peer */
-#define DEAD            14 /* dead, about to kfree */
-#define BACKOFF         15
-
-/*
  * A single connection with another host.
  *
  * We maintain a queue of outgoing messages, and some session state to

@@ -131,18 +115,22 @@ struct ceph_msg_pos {
  */
 struct ceph_connection {
 	void *private;
-	atomic_t nref;
 
 	const struct ceph_connection_operations *ops;
 
 	struct ceph_messenger *msgr;
+
+	atomic_t sock_state;
 	struct socket *sock;
-	unsigned long state;	/* connection state (see flags above) */
+	struct ceph_entity_addr peer_addr; /* peer address */
+	struct ceph_entity_addr peer_addr_for_me;
+
+	unsigned long flags;
+	unsigned long state;
 	const char *error_msg;  /* error message, if any */
 
-	struct ceph_entity_addr peer_addr; /* peer address */
 	struct ceph_entity_name peer_name; /* peer name */
-	struct ceph_entity_addr peer_addr_for_me;
+
 	unsigned peer_features;
 	u32 connect_seq;      /* identify the most recent connection
 				 attempt for this connection, client */

@@ -163,16 +151,8 @@ struct ceph_connection {
 
 	/* connection negotiation temps */
 	char in_banner[CEPH_BANNER_MAX_LEN];
-	union {
-		struct {  /* outgoing connection */
-			struct ceph_msg_connect out_connect;
-			struct ceph_msg_connect_reply in_reply;
-		};
-		struct {  /* incoming */
-			struct ceph_msg_connect in_connect;
-			struct ceph_msg_connect_reply out_reply;
-		};
-	};
+	struct ceph_msg_connect out_connect;
+	struct ceph_msg_connect_reply in_reply;
 	struct ceph_entity_addr actual_peer_addr;
 
 	/* message out temps */

@@ -215,24 +195,26 @@ extern int ceph_msgr_init(void);
 extern void ceph_msgr_exit(void);
 extern void ceph_msgr_flush(void);
 
-extern struct ceph_messenger *ceph_messenger_create(
-	struct ceph_entity_addr *myaddr,
-	u32 features, u32 required);
-extern void ceph_messenger_destroy(struct ceph_messenger *);
+extern void ceph_messenger_init(struct ceph_messenger *msgr,
+			struct ceph_entity_addr *myaddr,
+			u32 supported_features,
+			u32 required_features,
+			bool nocrc);
 
-extern void ceph_con_init(struct ceph_messenger *msgr,
-			  struct ceph_connection *con);
+extern void ceph_con_init(struct ceph_connection *con, void *private,
+			const struct ceph_connection_operations *ops,
+			struct ceph_messenger *msgr);
 extern void ceph_con_open(struct ceph_connection *con,
+			  __u8 entity_type, __u64 entity_num,
 			  struct ceph_entity_addr *addr);
 extern bool ceph_con_opened(struct ceph_connection *con);
 extern void ceph_con_close(struct ceph_connection *con);
 extern void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg);
-extern void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg);
-extern void ceph_con_revoke_message(struct ceph_connection *con,
-				  struct ceph_msg *msg);
+
+extern void ceph_msg_revoke(struct ceph_msg *msg);
+extern void ceph_msg_revoke_incoming(struct ceph_msg *msg);
+
 extern void ceph_con_keepalive(struct ceph_connection *con);
-extern struct ceph_connection *ceph_con_get(struct ceph_connection *con);
-extern void ceph_con_put(struct ceph_connection *con);
 
 extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
 				     bool can_fail);

@@ -70,7 +70,7 @@ struct ceph_mon_client {
 	bool hunting;
 	int cur_mon;                       /* last monitor i contacted */
 	unsigned long sub_sent, sub_renew_after;
-	struct ceph_connection *con;
+	struct ceph_connection con;
 	bool have_fsid;
 
 	/* pending generic requests */

@@ -11,10 +11,11 @@
 struct ceph_msgpool {
 	const char *name;
 	mempool_t *pool;
+	int type;               /* preallocated message type */
 	int front_len;          /* preallocated payload size */
 };
 
-extern int ceph_msgpool_init(struct ceph_msgpool *pool,
+extern int ceph_msgpool_init(struct ceph_msgpool *pool, int type,
 			     int front_len, int size, bool blocking,
 			     const char *name);
 extern void ceph_msgpool_destroy(struct ceph_msgpool *pool);

@@ -6,9 +6,10 @@
 #include <linux/mempool.h>
 #include <linux/rbtree.h>
 
-#include "types.h"
-#include "osdmap.h"
-#include "messenger.h"
+#include <linux/ceph/types.h>
+#include <linux/ceph/osdmap.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/auth.h>
 
 /* 
  * Maximum object name size 

@@ -40,9 +41,7 @@ struct ceph_osd {
 	struct list_head o_requests;
 	struct list_head o_linger_requests;
 	struct list_head o_osd_lru;
-	struct ceph_authorizer *o_authorizer;
-	void *o_authorizer_buf, *o_authorizer_reply_buf;
-	size_t o_authorizer_buf_len, o_authorizer_reply_buf_len;
+	struct ceph_auth_handshake o_auth;
 	unsigned long lru_ttl;
 	int o_marked_for_keepalive;
 	struct list_head o_keepalive_item;

@@ -208,7 +207,7 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc,
 extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
 				 struct ceph_msg *msg);
 
-extern void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
+extern int ceph_calc_raw_layout(struct ceph_osd_client *osdc,
 			struct ceph_file_layout *layout,
 			u64 snapid,
 			u64 off, u64 *plen, u64 *bno,

@@ -111,9 +111,9 @@ extern struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 extern void ceph_osdmap_destroy(struct ceph_osdmap *map);
 
 /* calculate mapping of a file extent to an object */
-extern void ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
-					  u64 off, u64 *plen,
-					  u64 *bno, u64 *oxoff, u64 *oxlen);
+extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
+					 u64 off, u64 *plen,
+					 u64 *bno, u64 *oxoff, u64 *oxlen);
 
 /* calculate mapping of object to a placement group */
 extern int ceph_calc_object_layout(struct ceph_object_layout *ol,

@@ -168,7 +168,7 @@ struct crush_map {
 
 
 /* crush.c */
-extern int crush_get_bucket_item_weight(struct crush_bucket *b, int pos);
+extern int crush_get_bucket_item_weight(const struct crush_bucket *b, int pos);
 extern void crush_calc_parents(struct crush_map *map);
 extern void crush_destroy_bucket_uniform(struct crush_bucket_uniform *b);
 extern void crush_destroy_bucket_list(struct crush_bucket_list *b);

@@ -177,4 +177,9 @@ extern void crush_destroy_bucket_straw(struct crush_bucket_straw *b);
 extern void crush_destroy_bucket(struct crush_bucket *b);
 extern void crush_destroy(struct crush_map *map);
 
+static inline int crush_calc_tree_node(int i)
+{
+	return ((i+1) << 1)-1;
+}
+
 #endif

@@ -10,11 +10,11 @@
 
 #include "crush.h"
 
-extern int crush_find_rule(struct crush_map *map, int pool, int type, int size);
-extern int crush_do_rule(struct crush_map *map,
+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,
 			 int ruleno,
 			 int x, int *result, int result_max,
 			 int forcefeed,    /* -1 for none */
-			 __u32 *weights);
+			 const __u32 *weights);
 
 #endif

@@ -2273,12 +2273,17 @@ static void layout_symtab(struct module *mod, struct load_info *info)
 	src = (void *)info->hdr + symsect->sh_offset;
 	nsrc = symsect->sh_size / sizeof(*src);
 
+	/* strtab always starts with a nul, so offset 0 is the empty string. */
+	strtab_size = 1;
+
 	/* Compute total space required for the core symbols' strtab. */
-	for (ndst = i = strtab_size = 1; i < nsrc; ++i, ++src)
-		if (is_core_symbol(src, info->sechdrs, info->hdr->e_shnum)) {
-			strtab_size += strlen(&info->strtab[src->st_name]) + 1;
+	for (ndst = i = 0; i < nsrc; i++) {
+		if (i == 0 ||
+		    is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum)) {
+			strtab_size += strlen(&info->strtab[src[i].st_name])+1;
 			ndst++;
 		}
+	}
 
 	/* Append room for core symbols at end of core part. */
 	info->symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1);

@@ -2312,15 +2317,15 @@ static void add_kallsyms(struct module *mod, const struct load_info *info)
 	mod->core_symtab = dst = mod->module_core + info->symoffs;
 	mod->core_strtab = s = mod->module_core + info->stroffs;
 	src = mod->symtab;
-	*dst = *src;
 	*s++ = 0;
-	for (ndst = i = 1; i < mod->num_symtab; ++i, ++src) {
-		if (!is_core_symbol(src, info->sechdrs, info->hdr->e_shnum))
-			continue;
-
-		dst[ndst] = *src;
-		dst[ndst++].st_name = s - mod->core_strtab;
-		s += strlcpy(s, &mod->strtab[src->st_name], KSYM_NAME_LEN) + 1;
+	for (ndst = i = 0; i < mod->num_symtab; i++) {
+		if (i == 0 ||
+		    is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum)) {
+			dst[ndst] = src[i];
+			dst[ndst++].st_name = s - mod->core_strtab;
+			s += strlcpy(s, &mod->strtab[src[i].st_name],
+				     KSYM_NAME_LEN) + 1;
+		}
 	}
 	mod->core_num_syms = ndst;
 }

@@ -1489,17 +1489,26 @@ static int mem_cgroup_count_children(struct mem_cgroup *memcg)
 u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
 {
 	u64 limit;
-	u64 memsw;
 
 	limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
-	limit += total_swap_pages << PAGE_SHIFT;
 
-	memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
 	/*
-	 * If memsw is finite and limits the amount of swap space available
-	 * to this memcg, return that limit.
+	 * Do not consider swap space if we cannot swap due to swappiness
 	 */
-	return min(limit, memsw);
+	if (mem_cgroup_swappiness(memcg)) {
+		u64 memsw;
+
+		limit += total_swap_pages << PAGE_SHIFT;
+		memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
+
+		/*
+		 * If memsw is finite and limits the amount of swap space
+		 * available to this memcg, return that limit.
+		 */
+		limit = min(limit, memsw);
+	}
+
+	return limit;
 }
 
 static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg,

@@ -595,7 +595,7 @@ static void shmem_evict_inode(struct inode *inode)
 		kfree(xattr->name);
 		kfree(xattr);
 	}
-	BUG_ON(inode->i_blocks);
+	WARN_ON(inode->i_blocks);
 	shmem_free_inode(inode->i_sb);
 	end_writeback(inode);
 }

@@ -3128,6 +3128,8 @@ static int kswapd(void *p)
 						&balanced_classzone_idx);
 		}
 	}
+
+	current->reclaim_state = NULL;
 	return 0;
 }
 

@@ -59,9 +59,7 @@ static int handle_reply(struct ceph_auth_client *ac, int result,
  */
 static int ceph_auth_none_create_authorizer(
 	struct ceph_auth_client *ac, int peer_type,
-	struct ceph_authorizer **a,
-	void **buf, size_t *len,
-	void **reply_buf, size_t *reply_len)
+	struct ceph_auth_handshake *auth)
 {
 	struct ceph_auth_none_info *ai = ac->private;
 	struct ceph_none_authorizer *au = &ai->au;

@@ -82,11 +80,12 @@ static int ceph_auth_none_create_authorizer(
 		dout("built authorizer len %d\n", au->buf_len);
 	}
 
-	*a = (struct ceph_authorizer *)au;
-	*buf = au->buf;
-	*len = au->buf_len;
-	*reply_buf = au->reply_buf;
-	*reply_len = sizeof(au->reply_buf);
+	auth->authorizer = (struct ceph_authorizer *) au;
+	auth->authorizer_buf = au->buf;
+	auth->authorizer_buf_len = au->buf_len;
+	auth->authorizer_reply_buf = au->reply_buf;
+	auth->authorizer_reply_buf_len = sizeof (au->reply_buf);
+
 	return 0;
 
 bad2:

@@ -526,9 +526,7 @@ static int ceph_x_handle_reply(struct ceph_auth_client *ac, int result,
 
 static int ceph_x_create_authorizer(
 	struct ceph_auth_client *ac, int peer_type,
-	struct ceph_authorizer **a,
-	void **buf, size_t *len,
-	void **reply_buf, size_t *reply_len)
+	struct ceph_auth_handshake *auth)
 {
 	struct ceph_x_authorizer *au;
 	struct ceph_x_ticket_handler *th;

@@ -548,11 +546,12 @@ static int ceph_x_create_authorizer(
 		return ret;
 	}
 
-	*a = (struct ceph_authorizer *)au;
-	*buf = au->buf->vec.iov_base;
-	*len = au->buf->vec.iov_len;
-	*reply_buf = au->reply_buf;
-	*reply_len = sizeof(au->reply_buf);
+	auth->authorizer = (struct ceph_authorizer *) au;
+	auth->authorizer_buf = au->buf->vec.iov_base;
+	auth->authorizer_buf_len = au->buf->vec.iov_len;
+	auth->authorizer_reply_buf = au->reply_buf;
+	auth->authorizer_reply_buf_len = sizeof (au->reply_buf);
+
 	return 0;
 }
 

@@ -83,7 +83,6 @@ int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid)
 			return -1;
 		}
 	} else {
-		pr_info("client%lld fsid %pU\n", ceph_client_id(client), fsid);
 		memcpy(&client->fsid, fsid, sizeof(*fsid));
 	}
 	return 0;

@@ -468,19 +467,15 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
 	/* msgr */
 	if (ceph_test_opt(client, MYIP))
 		myaddr = &client->options->my_addr;
-	client->msgr = ceph_messenger_create(myaddr,
-					     client->supported_features,
-					     client->required_features);
-	if (IS_ERR(client->msgr)) {
-		err = PTR_ERR(client->msgr);
-		goto fail;
-	}
-	client->msgr->nocrc = ceph_test_opt(client, NOCRC);
+	ceph_messenger_init(&client->msgr, myaddr,
+		client->supported_features,
+		client->required_features,
+		ceph_test_opt(client, NOCRC));
 
 	/* subsystems */
 	err = ceph_monc_init(&client->monc, client);
 	if (err < 0)
-		goto fail_msgr;
+		goto fail;
 	err = ceph_osdc_init(&client->osdc, client);
 	if (err < 0)
 		goto fail_monc;

@@ -489,8 +484,6 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
 
 fail_monc:
 	ceph_monc_stop(&client->monc);
-fail_msgr:
-	ceph_messenger_destroy(client->msgr);
 fail:
 	kfree(client);
 	return ERR_PTR(err);

@@ -501,22 +494,15 @@ void ceph_destroy_client(struct ceph_client *client)
 {
 	dout("destroy_client %p\n", client);
 
+	atomic_set(&client->msgr.stopping, 1);
+
 	/* unmount */
 	ceph_osdc_stop(&client->osdc);
 
-	/*
-	 * make sure osd connections close out before destroying the
-	 * auth module, which is needed to free those connections'
-	 * ceph_authorizers.
-	 */
-	ceph_msgr_flush();
-
 	ceph_monc_stop(&client->monc);
 
 	ceph_debugfs_client_cleanup(client);
 
-	ceph_messenger_destroy(client->msgr);
-
 	ceph_destroy_options(client->options);
 
 	kfree(client);

@@ -26,9 +26,9 @@ const char *crush_bucket_alg_name(int alg)
  * @b: bucket pointer
  * @p: item index in bucket
  */
-int crush_get_bucket_item_weight(struct crush_bucket *b, int p)
+int crush_get_bucket_item_weight(const struct crush_bucket *b, int p)
 {
-	if (p >= b->size)
+	if ((__u32)p >= b->size)
 		return 0;
 
 	switch (b->alg) {

@@ -37,9 +37,7 @@ int crush_get_bucket_item_weight(struct crush_bucket *b, int p)
 	case CRUSH_BUCKET_LIST:
 		return ((struct crush_bucket_list *)b)->item_weights[p];
 	case CRUSH_BUCKET_TREE:
-		if (p & 1)
-			return ((struct crush_bucket_tree *)b)->node_weights[p];
-		return 0;
+		return ((struct crush_bucket_tree *)b)->node_weights[crush_calc_tree_node(p)];
 	case CRUSH_BUCKET_STRAW:
 		return ((struct crush_bucket_straw *)b)->item_weights[p];
 	}

@@ -87,6 +85,8 @@ void crush_destroy_bucket_list(struct crush_bucket_list *b)
 
 void crush_destroy_bucket_tree(struct crush_bucket_tree *b)
 {
+	kfree(b->h.perm);
+	kfree(b->h.items);
 	kfree(b->node_weights);
 	kfree(b);
 }

@@ -124,10 +124,9 @@ void crush_destroy_bucket(struct crush_bucket *b)
  */
 void crush_destroy(struct crush_map *map)
 {
-	int b;
-
 	/* buckets */
 	if (map->buckets) {
+		__s32 b;
 		for (b = 0; b < map->max_buckets; b++) {
 			if (map->buckets[b] == NULL)
 				continue;

@@ -138,6 +137,7 @@ void crush_destroy(struct crush_map *map)
 
 	/* rules */
 	if (map->rules) {
+		__u32 b;
 		for (b = 0; b < map->max_rules; b++)
 			kfree(map->rules[b]);
 		kfree(map->rules);

@@ -32,9 +32,9 @@
  * @type: storage ruleset type (user defined)
  * @size: output set size
  */
-int crush_find_rule(struct crush_map *map, int ruleset, int type, int size)
+int crush_find_rule(const struct crush_map *map, int ruleset, int type, int size)
 {
-	int i;
+	__u32 i;
 
 	for (i = 0; i < map->max_rules; i++) {
 		if (map->rules[i] &&

@@ -72,7 +72,7 @@ static int bucket_perm_choose(struct crush_bucket *bucket,
 	unsigned i, s;
 
 	/* start a new permutation if @x has changed */
-	if (bucket->perm_x != x || bucket->perm_n == 0) {
+	if (bucket->perm_x != (__u32)x || bucket->perm_n == 0) {
 		dprintk("bucket %d new x=%d\n", bucket->id, x);
 		bucket->perm_x = x;
 

@@ -152,8 +152,8 @@ static int bucket_list_choose(struct crush_bucket_list *bucket,
 			return bucket->h.items[i];
 	}
 
-	BUG_ON(1);
-	return 0;
+	dprintk("bad list sums for bucket %d\n", bucket->h.id);
+	return bucket->h.items[0];
 }
 
 

@@ -219,7 +219,7 @@ static int bucket_tree_choose(struct crush_bucket_tree *bucket,
 static int bucket_straw_choose(struct crush_bucket_straw *bucket,
 			       int x, int r)
 {
-	int i;
+	__u32 i;
 	int high = 0;
 	__u64 high_draw = 0;
 	__u64 draw;

@@ -239,6 +239,7 @@ static int bucket_straw_choose(struct crush_bucket_straw *bucket,
 static int crush_bucket_choose(struct crush_bucket *in, int x, int r)
 {
 	dprintk(" crush_bucket_choose %d x=%d r=%d\n", in->id, x, r);
+	BUG_ON(in->size == 0);
 	switch (in->alg) {
 	case CRUSH_BUCKET_UNIFORM:
 		return bucket_uniform_choose((struct crush_bucket_uniform *)in,

@@ -253,7 +254,7 @@ static int crush_bucket_choose(struct crush_bucket *in, int x, int r)
 		return bucket_straw_choose((struct crush_bucket_straw *)in,
 					   x, r);
 	default:
-		BUG_ON(1);
+		dprintk("unknown bucket %d alg %d\n", in->id, in->alg);
 		return in->items[0];
 	}
 }

@@ -262,7 +263,7 @@ static int crush_bucket_choose(struct crush_bucket *in, int x, int r)
  * true if device is marked "out" (failed, fully offloaded)
  * of the cluster
  */
-static int is_out(struct crush_map *map, __u32 *weight, int item, int x)
+static int is_out(const struct crush_map *map, const __u32 *weight, int item, int x)
 {
 	if (weight[item] >= 0x10000)
 		return 0;

@@ -287,16 +288,16 @@ static int is_out(struct crush_map *map, __u32 *weight, int item, int x)
  * @recurse_to_leaf: true if we want one device under each item of given type
  * @out2: second output vector for leaf items (if @recurse_to_leaf)
  */
-static int crush_choose(struct crush_map *map,
+static int crush_choose(const struct crush_map *map,
 			struct crush_bucket *bucket,
-			__u32 *weight,
+			const __u32 *weight,
 			int x, int numrep, int type,
 			int *out, int outpos,
 			int firstn, int recurse_to_leaf,
 			int *out2)
 {
 	int rep;
-	int ftotal, flocal;
+	unsigned int ftotal, flocal;
 	int retry_descent, retry_bucket, skip_rep;
 	struct crush_bucket *in = bucket;
 	int r;

@@ -304,7 +305,7 @@ static int crush_choose(struct crush_map *map,
 	int item = 0;
 	int itemtype;
 	int collide, reject;
-	const int orig_tries = 5; /* attempts before we fall back to search */
+	const unsigned int orig_tries = 5; /* attempts before we fall back to search */
 
 	dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d\n", recurse_to_leaf ? "_LEAF" : "",
 		bucket->id, x, outpos, numrep);

@@ -325,7 +326,7 @@ static int crush_choose(struct crush_map *map,
 				r = rep;
 				if (in->alg == CRUSH_BUCKET_UNIFORM) {
 					/* be careful */
-					if (firstn || numrep >= in->size)
+					if (firstn || (__u32)numrep >= in->size)
 						/* r' = r + f_total */
 						r += ftotal;
 					else if (in->size % numrep == 0)

@@ -354,7 +355,11 @@ static int crush_choose(struct crush_map *map,
 					item = bucket_perm_choose(in, x, r);
 				else
 					item = crush_bucket_choose(in, x, r);
-				BUG_ON(item >= map->max_devices);
+				if (item >= map->max_devices) {
+					dprintk("   bad item %d\n", item);
+					skip_rep = 1;
+					break;
+				}
 
 				/* desired type? */
 				if (item < 0)

@@ -365,8 +370,12 @@ static int crush_choose(struct crush_map *map,
 
 				/* keep going? */
 				if (itemtype != type) {
-					BUG_ON(item >= 0 ||
-					       (-1-item) >= map->max_buckets);
+					if (item >= 0 ||
+					    (-1-item) >= map->max_buckets) {
+						dprintk("   bad item type %d\n", type);
+						skip_rep = 1;
+						break;
+					}
 					in = map->buckets[-1-item];
 					retry_bucket = 1;
 					continue;

@@ -415,7 +424,7 @@ reject:
 					if (collide && flocal < 3)
 						/* retry locally a few times */
 						retry_bucket = 1;
-					else if (flocal < in->size + orig_tries)
+					else if (flocal <= in->size + orig_tries)
 						/* exhaustive bucket search */
 						retry_bucket = 1;
 					else if (ftotal < 20)

@@ -425,7 +434,7 @@ reject:
 						/* else give up */
 						skip_rep = 1;
 					dprintk("  reject %d  collide %d  "
-						"ftotal %d  flocal %d\n",
+						"ftotal %u  flocal %u\n",
 						reject, collide, ftotal,
 						flocal);
 				}

@@ -456,9 +465,9 @@ reject:
  * @result_max: maximum result size
  * @force: force initial replica choice; -1 for none
  */
-int crush_do_rule(struct crush_map *map,
+int crush_do_rule(const struct crush_map *map,
 		  int ruleno, int x, int *result, int result_max,
-		  int force, __u32 *weight)
+		  int force, const __u32 *weight)
 {
 	int result_len;
 	int force_context[CRUSH_MAX_DEPTH];

@@ -473,12 +482,15 @@ int crush_do_rule(struct crush_map *map,
 	int osize;
 	int *tmp;
 	struct crush_rule *rule;
-	int step;
+	__u32 step;
 	int i, j;
 	int numrep;
 	int firstn;
 
-	BUG_ON(ruleno >= map->max_rules);
+	if ((__u32)ruleno >= map->max_rules) {
+		dprintk(" bad ruleno %d\n", ruleno);
+		return 0;
+	}
 
 	rule = map->rules[ruleno];
 	result_len = 0;

@@ -488,7 +500,8 @@ int crush_do_rule(struct crush_map *map,
 	/*
 	 * determine hierarchical context of force, if any.  note
 	 * that this may or may not correspond to the specific types
-	 * referenced by the crush rule.
+	 * referenced by the crush rule.  it will also only affect
+	 * the first descent (TAKE).
 	 */
 	if (force >= 0 &&
 	    force < map->max_devices &&

@@ -527,7 +540,8 @@ int crush_do_rule(struct crush_map *map,
 			firstn = 1;
 		case CRUSH_RULE_CHOOSE_LEAF_INDEP:
 		case CRUSH_RULE_CHOOSE_INDEP:
-			BUG_ON(wsize == 0);
+			if (wsize == 0)
+				break;
 
 			recurse_to_leaf =
 				rule->steps[step].op ==

@@ -596,7 +610,9 @@ int crush_do_rule(struct crush_map *map,
 			break;
 
 		default:
-			BUG_ON(1);
+			dprintk(" unknown op %d at step %d\n",
+				curstep->op, step);
+			break;
 		}
 	}
 	return result_len;

@@ -466,6 +466,7 @@ void ceph_key_destroy(struct key *key) {
 	struct ceph_crypto_key *ckey = key->payload.data;
 
 	ceph_crypto_key_destroy(ckey);
+	kfree(ckey);
 }
 
 struct key_type key_type_ceph = {

@@ -16,7 +16,8 @@ struct ceph_crypto_key {
 
 static inline void ceph_crypto_key_destroy(struct ceph_crypto_key *key)
 {
-	kfree(key->key);
+	if (key)
+		kfree(key->key);
 }
 
 extern int ceph_crypto_key_clone(struct ceph_crypto_key *dst,

@@ -189,6 +189,9 @@ int ceph_debugfs_client_init(struct ceph_client *client)
 	snprintf(name, sizeof(name), "%pU.client%lld", &client->fsid,
 		 client->monc.auth->global_id);
 
+	dout("ceph_debugfs_client_init %p %s\n", client, name);
+
+	BUG_ON(client->debugfs_dir);
 	client->debugfs_dir = debugfs_create_dir(name, ceph_debugfs_dir);
 	if (!client->debugfs_dir)
 		goto out;

@@ -234,6 +237,7 @@ out:
 
 void ceph_debugfs_client_cleanup(struct ceph_client *client)
 {
+	dout("ceph_debugfs_client_cleanup %p\n", client);
 	debugfs_remove(client->debugfs_osdmap);
 	debugfs_remove(client->debugfs_monmap);
 	debugfs_remove(client->osdc.debugfs_file);

@@ -29,6 +29,74 @@
  * the sender.
  */
 
+/*
+ * We track the state of the socket on a given connection using
+ * values defined below.  The transition to a new socket state is
+ * handled by a function which verifies we aren't coming from an
+ * unexpected state.
+ *
+ *      --------
+ *      | NEW* |  transient initial state
+ *      --------
+ *          | con_sock_state_init()
+ *          v
+ *      ----------
+ *      | CLOSED |  initialized, but no socket (and no
+ *      ----------  TCP connection)
+ *       ^      \
+ *       |       \ con_sock_state_connecting()
+ *       |        ----------------------
+ *       |                              \
+ *       + con_sock_state_closed()       \
+ *       |+---------------------------    \
+ *       | \                          \    \
+ *       |  -----------                \    \
+ *       |  | CLOSING |  socket event;  \    \
+ *       |  -----------  await close     \    \
+ *       |       ^                        \   |
+ *       |       |                         \  |
+ *       |       + con_sock_state_closing() \ |
+ *       |      / \                         | |
+ *       |     /   ---------------          | |
+ *       |    /                   \         v v
+ *       |   /                    --------------
+ *       |  /    -----------------| CONNECTING |  socket created, TCP
+ *       |  |   /                 --------------  connect initiated
+ *       |  |   | con_sock_state_connected()
+ *       |  |   v
+ *      -------------
+ *      | CONNECTED |  TCP connection established
+ *      -------------
+ *
+ * State values for ceph_connection->sock_state; NEW is assumed to be 0.
+ */
+
+#define CON_SOCK_STATE_NEW		0	/* -> CLOSED */
+#define CON_SOCK_STATE_CLOSED		1	/* -> CONNECTING */
+#define CON_SOCK_STATE_CONNECTING	2	/* -> CONNECTED or -> CLOSING */
+#define CON_SOCK_STATE_CONNECTED	3	/* -> CLOSING or -> CLOSED */
+#define CON_SOCK_STATE_CLOSING		4	/* -> CLOSED */
+
+/*
+ * connection states
+ */
+#define CON_STATE_CLOSED        1  /* -> PREOPEN */
+#define CON_STATE_PREOPEN       2  /* -> CONNECTING, CLOSED */
+#define CON_STATE_CONNECTING    3  /* -> NEGOTIATING, CLOSED */
+#define CON_STATE_NEGOTIATING   4  /* -> OPEN, CLOSED */
+#define CON_STATE_OPEN          5  /* -> STANDBY, CLOSED */
+#define CON_STATE_STANDBY       6  /* -> PREOPEN, CLOSED */
+
+/*
+ * ceph_connection flag bits
+ */
+#define CON_FLAG_LOSSYTX           0  /* we can close channel or drop
+				       * messages on errors */
+#define CON_FLAG_KEEPALIVE_PENDING 1  /* we need to send a keepalive */
+#define CON_FLAG_WRITE_PENDING	   2  /* we have data ready to send */
+#define CON_FLAG_SOCK_CLOSED	   3  /* socket state changed to closed */
+#define CON_FLAG_BACKOFF           4  /* need to retry queuing delayed work */
+
 /* static tag bytes (protocol control messages) */
 static char tag_msg = CEPH_MSGR_TAG_MSG;
 static char tag_ack = CEPH_MSGR_TAG_ACK;

@@ -147,72 +215,130 @@ void ceph_msgr_flush(void)
 }
 EXPORT_SYMBOL(ceph_msgr_flush);
 
+/* Connection socket state transition functions */
+
+static void con_sock_state_init(struct ceph_connection *con)
+{
+	int old_state;
+
+	old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CLOSED);
+	if (WARN_ON(old_state != CON_SOCK_STATE_NEW))
+		printk("%s: unexpected old state %d\n", __func__, old_state);
+	dout("%s con %p sock %d -> %d\n", __func__, con, old_state,
+	     CON_SOCK_STATE_CLOSED);
+}
+
+static void con_sock_state_connecting(struct ceph_connection *con)
+{
+	int old_state;
+
+	old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CONNECTING);
+	if (WARN_ON(old_state != CON_SOCK_STATE_CLOSED))
+		printk("%s: unexpected old state %d\n", __func__, old_state);
+	dout("%s con %p sock %d -> %d\n", __func__, con, old_state,
+	     CON_SOCK_STATE_CONNECTING);
+}
+
+static void con_sock_state_connected(struct ceph_connection *con)
+{
+	int old_state;
+
+	old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CONNECTED);
+	if (WARN_ON(old_state != CON_SOCK_STATE_CONNECTING))
+		printk("%s: unexpected old state %d\n", __func__, old_state);
+	dout("%s con %p sock %d -> %d\n", __func__, con, old_state,
+	     CON_SOCK_STATE_CONNECTED);
+}
+
+static void con_sock_state_closing(struct ceph_connection *con)
+{
+	int old_state;
+
+	old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CLOSING);
+	if (WARN_ON(old_state != CON_SOCK_STATE_CONNECTING &&
+			old_state != CON_SOCK_STATE_CONNECTED &&
+			old_state != CON_SOCK_STATE_CLOSING))
+		printk("%s: unexpected old state %d\n", __func__, old_state);
+	dout("%s con %p sock %d -> %d\n", __func__, con, old_state,
+	     CON_SOCK_STATE_CLOSING);
+}
+
+static void con_sock_state_closed(struct ceph_connection *con)
+{
+	int old_state;
+
+	old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CLOSED);
+	if (WARN_ON(old_state != CON_SOCK_STATE_CONNECTED &&
+		    old_state != CON_SOCK_STATE_CLOSING &&
+		    old_state != CON_SOCK_STATE_CONNECTING &&
+		    old_state != CON_SOCK_STATE_CLOSED))
+		printk("%s: unexpected old state %d\n", __func__, old_state);
+	dout("%s con %p sock %d -> %d\n", __func__, con, old_state,
+	     CON_SOCK_STATE_CLOSED);
+}
 
 /*
  * socket callback functions
  */
 
 /* data available on socket, or listen socket received a connect */
-static void ceph_data_ready(struct sock *sk, int count_unused)
+static void ceph_sock_data_ready(struct sock *sk, int count_unused)
 {
 	struct ceph_connection *con = sk->sk_user_data;
+	if (atomic_read(&con->msgr->stopping)) {
+		return;
+	}
 
 	if (sk->sk_state != TCP_CLOSE_WAIT) {
-		dout("ceph_data_ready on %p state = %lu, queueing work\n",
+		dout("%s on %p state = %lu, queueing work\n", __func__,
 		     con, con->state);
 		queue_con(con);
 	}
 }
 
 /* socket has buffer space for writing */
-static void ceph_write_space(struct sock *sk)
+static void ceph_sock_write_space(struct sock *sk)
 {
 	struct ceph_connection *con = sk->sk_user_data;
 
 	/* only queue to workqueue if there is data we want to write,
 	 * and there is sufficient space in the socket buffer to accept
-	 * more data.  clear SOCK_NOSPACE so that ceph_write_space()
+	 * more data.  clear SOCK_NOSPACE so that ceph_sock_write_space()
 	 * doesn't get called again until try_write() fills the socket
 	 * buffer. See net/ipv4/tcp_input.c:tcp_check_space()
 	 * and net/core/stream.c:sk_stream_write_space().
 	 */
-	if (test_bit(WRITE_PENDING, &con->state)) {
+	if (test_bit(CON_FLAG_WRITE_PENDING, &con->flags)) {
 		if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) {
-			dout("ceph_write_space %p queueing write work\n", con);
+			dout("%s %p queueing write work\n", __func__, con);
 			clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 			queue_con(con);
 		}
 	} else {
-		dout("ceph_write_space %p nothing to write\n", con);
+		dout("%s %p nothing to write\n", __func__, con);
 	}
 }
 
 /* socket's state has changed */
-static void ceph_state_change(struct sock *sk)
+static void ceph_sock_state_change(struct sock *sk)
 {
 	struct ceph_connection *con = sk->sk_user_data;
 
-	dout("ceph_state_change %p state = %lu sk_state = %u\n",
+	dout("%s %p state = %lu sk_state = %u\n", __func__,
 	     con, con->state, sk->sk_state);
 
-	if (test_bit(CLOSED, &con->state))
-		return;
-
 	switch (sk->sk_state) {
 	case TCP_CLOSE:
-		dout("ceph_state_change TCP_CLOSE\n");
+		dout("%s TCP_CLOSE\n", __func__);
 	case TCP_CLOSE_WAIT:
-		dout("ceph_state_change TCP_CLOSE_WAIT\n");
-		if (test_and_set_bit(SOCK_CLOSED, &con->state) == 0) {
-			if (test_bit(CONNECTING, &con->state))
-				con->error_msg = "connection failed";
-			else
-				con->error_msg = "socket closed";
-			queue_con(con);
-		}
+		dout("%s TCP_CLOSE_WAIT\n", __func__);
+		con_sock_state_closing(con);
+		set_bit(CON_FLAG_SOCK_CLOSED, &con->flags);
+		queue_con(con);
 		break;
 	case TCP_ESTABLISHED:
-		dout("ceph_state_change TCP_ESTABLISHED\n");
+		dout("%s TCP_ESTABLISHED\n", __func__);
+		con_sock_state_connected(con);
 		queue_con(con);
 		break;
 	default:	/* Everything else is uninteresting */

@@ -228,9 +354,9 @@ static void set_sock_callbacks(struct socket *sock,
 {
 	struct sock *sk = sock->sk;
 	sk->sk_user_data = con;
-	sk->sk_data_ready = ceph_data_ready;
-	sk->sk_write_space = ceph_write_space;
-	sk->sk_state_change = ceph_state_change;
+	sk->sk_data_ready = ceph_sock_data_ready;
+	sk->sk_write_space = ceph_sock_write_space;
+	sk->sk_state_change = ceph_sock_state_change;
 }
 
 

@@ -262,6 +388,7 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 
 	dout("connect %s\n", ceph_pr_addr(&con->peer_addr.in_addr));
 
+	con_sock_state_connecting(con);
 	ret = sock->ops->connect(sock, (struct sockaddr *)paddr, sizeof(*paddr),
 				 O_NONBLOCK);
 	if (ret == -EINPROGRESS) {

@@ -277,7 +404,6 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 		return ret;
 	}
 	con->sock = sock;
-
 	return 0;
 }
 

@@ -333,16 +459,24 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
  */
 static int con_close_socket(struct ceph_connection *con)
 {
-	int rc;
+	int rc = 0;
 
 	dout("con_close_socket on %p sock %p\n", con, con->sock);
-	if (!con->sock)
-		return 0;
-	set_bit(SOCK_CLOSED, &con->state);
-	rc = con->sock->ops->shutdown(con->sock, SHUT_RDWR);
-	sock_release(con->sock);
-	con->sock = NULL;
-	clear_bit(SOCK_CLOSED, &con->state);
+	if (con->sock) {
+		rc = con->sock->ops->shutdown(con->sock, SHUT_RDWR);
+		sock_release(con->sock);
+		con->sock = NULL;
+	}
+
+	/*
+	 * Forcibly clear the SOCK_CLOSED flag.  It gets set
+	 * independent of the connection mutex, and we could have
+	 * received a socket close event before we had the chance to
+	 * shut the socket down.
+	 */
+	clear_bit(CON_FLAG_SOCK_CLOSED, &con->flags);
+
+	con_sock_state_closed(con);
 	return rc;
 }
 

@@ -353,6 +487,10 @@ static int con_close_socket(struct ceph_connection *con)
 static void ceph_msg_remove(struct ceph_msg *msg)
 {
 	list_del_init(&msg->list_head);
+	BUG_ON(msg->con == NULL);
+	msg->con->ops->put(msg->con);
+	msg->con = NULL;
+
 	ceph_msg_put(msg);
 }
 static void ceph_msg_remove_list(struct list_head *head)

@@ -372,8 +510,11 @@ static void reset_connection(struct ceph_connection *con)
 	ceph_msg_remove_list(&con->out_sent);
 
 	if (con->in_msg) {
+		BUG_ON(con->in_msg->con != con);
+		con->in_msg->con = NULL;
 		ceph_msg_put(con->in_msg);
 		con->in_msg = NULL;
+		con->ops->put(con);
 	}
 
 	con->connect_seq = 0;

@@ -391,32 +532,44 @@ static void reset_connection(struct ceph_connection *con)
  */
 void ceph_con_close(struct ceph_connection *con)
 {
+	mutex_lock(&con->mutex);
 	dout("con_close %p peer %s\n", con,
 	     ceph_pr_addr(&con->peer_addr.in_addr));
-	set_bit(CLOSED, &con->state);  /* in case there's queued work */
-	clear_bit(STANDBY, &con->state);  /* avoid connect_seq bump */
-	clear_bit(LOSSYTX, &con->state);  /* so we retry next connect */
-	clear_bit(KEEPALIVE_PENDING, &con->state);
-	clear_bit(WRITE_PENDING, &con->state);
-	mutex_lock(&con->mutex);
+	con->state = CON_STATE_CLOSED;
+
+	clear_bit(CON_FLAG_LOSSYTX, &con->flags); /* so we retry next connect */
+	clear_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags);
+	clear_bit(CON_FLAG_WRITE_PENDING, &con->flags);
+	clear_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags);
+	clear_bit(CON_FLAG_BACKOFF, &con->flags);
+
 	reset_connection(con);
 	con->peer_global_seq = 0;
 	cancel_delayed_work(&con->work);
+	con_close_socket(con);
 	mutex_unlock(&con->mutex);
-	queue_con(con);
 }
 EXPORT_SYMBOL(ceph_con_close);
 
 /*
  * Reopen a closed connection, with a new peer address.
  */
-void ceph_con_open(struct ceph_connection *con, struct ceph_entity_addr *addr)
+void ceph_con_open(struct ceph_connection *con,
+		   __u8 entity_type, __u64 entity_num,
+		   struct ceph_entity_addr *addr)
 {
+	mutex_lock(&con->mutex);
 	dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr));
-	set_bit(OPENING, &con->state);
-	clear_bit(CLOSED, &con->state);
+
+	BUG_ON(con->state != CON_STATE_CLOSED);
+	con->state = CON_STATE_PREOPEN;
+
+	con->peer_name.type = (__u8) entity_type;
+	con->peer_name.num = cpu_to_le64(entity_num);
+
 	memcpy(&con->peer_addr, addr, sizeof(*addr));
 	con->delay = 0;      /* reset backoff memory */
+	mutex_unlock(&con->mutex);
 	queue_con(con);
 }
 EXPORT_SYMBOL(ceph_con_open);

@@ -430,42 +583,26 @@ bool ceph_con_opened(struct ceph_connection *con)
 }
 
 /*
- * generic get/put
- */
-struct ceph_connection *ceph_con_get(struct ceph_connection *con)
-{
-	int nref = __atomic_add_unless(&con->nref, 1, 0);
-
-	dout("con_get %p nref = %d -> %d\n", con, nref, nref + 1);
-
-	return nref ? con : NULL;
-}
-
-void ceph_con_put(struct ceph_connection *con)
-{
-	int nref = atomic_dec_return(&con->nref);
-
-	BUG_ON(nref < 0);
-	if (nref == 0) {
-		BUG_ON(con->sock);
-		kfree(con);
-	}
-	dout("con_put %p nref = %d -> %d\n", con, nref + 1, nref);
-}
-
-/*
  * initialize a new connection.
  */
-void ceph_con_init(struct ceph_messenger *msgr, struct ceph_connection *con)
+void ceph_con_init(struct ceph_connection *con, void *private,
+	const struct ceph_connection_operations *ops,
+	struct ceph_messenger *msgr)
 {
 	dout("con_init %p\n", con);
 	memset(con, 0, sizeof(*con));
-	atomic_set(&con->nref, 1);
+	con->private = private;
+	con->ops = ops;
 	con->msgr = msgr;
+
+	con_sock_state_init(con);
+
 	mutex_init(&con->mutex);
 	INIT_LIST_HEAD(&con->out_queue);
 	INIT_LIST_HEAD(&con->out_sent);
 	INIT_DELAYED_WORK(&con->work, con_work);
+
+	con->state = CON_STATE_CLOSED;
 }
 EXPORT_SYMBOL(ceph_con_init);
 

@@ -486,14 +623,14 @@ static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt)
 	return ret;
 }
 
-static void ceph_con_out_kvec_reset(struct ceph_connection *con)
+static void con_out_kvec_reset(struct ceph_connection *con)
 {
 	con->out_kvec_left = 0;
 	con->out_kvec_bytes = 0;
 	con->out_kvec_cur = &con->out_kvec[0];
 }
 
-static void ceph_con_out_kvec_add(struct ceph_connection *con,
+static void con_out_kvec_add(struct ceph_connection *con,
 				size_t size, void *data)
 {
 	int index;

@@ -507,6 +644,53 @@ static void ceph_con_out_kvec_add(struct ceph_connection *con,
 	con->out_kvec_bytes += size;
 }
 
+#ifdef CONFIG_BLOCK
+static void init_bio_iter(struct bio *bio, struct bio **iter, int *seg)
+{
+	if (!bio) {
+		*iter = NULL;
+		*seg = 0;
+		return;
+	}
+	*iter = bio;
+	*seg = bio->bi_idx;
+}
+
+static void iter_bio_next(struct bio **bio_iter, int *seg)
+{
+	if (*bio_iter == NULL)
+		return;
+
+	BUG_ON(*seg >= (*bio_iter)->bi_vcnt);
+
+	(*seg)++;
+	if (*seg == (*bio_iter)->bi_vcnt)
+		init_bio_iter((*bio_iter)->bi_next, bio_iter, seg);
+}
+#endif
+
+static void prepare_write_message_data(struct ceph_connection *con)
+{
+	struct ceph_msg *msg = con->out_msg;
+
+	BUG_ON(!msg);
+	BUG_ON(!msg->hdr.data_len);
+
+	/* initialize page iterator */
+	con->out_msg_pos.page = 0;
+	if (msg->pages)
+		con->out_msg_pos.page_pos = msg->page_alignment;
+	else
+		con->out_msg_pos.page_pos = 0;
+#ifdef CONFIG_BLOCK
+	if (msg->bio)
+		init_bio_iter(msg->bio, &msg->bio_iter, &msg->bio_seg);
+#endif
+	con->out_msg_pos.data_pos = 0;
+	con->out_msg_pos.did_page_crc = false;
+	con->out_more = 1;  /* data + footer will follow */
+}
+
 /*
  * Prepare footer for currently outgoing message, and finish things
  * off.  Assumes out_kvec* are already valid.. we just add on to the end.

@@ -516,6 +700,8 @@ static void prepare_write_message_footer(struct ceph_connection *con)
 	struct ceph_msg *m = con->out_msg;
 	int v = con->out_kvec_left;
 
+	m->footer.flags |= CEPH_MSG_FOOTER_COMPLETE;
+
 	dout("prepare_write_message_footer %p\n", con);
 	con->out_kvec_is_msg = true;
 	con->out_kvec[v].iov_base = &m->footer;

@@ -534,7 +720,7 @@ static void prepare_write_message(struct ceph_connection *con)
 	struct ceph_msg *m;
 	u32 crc;
 
-	ceph_con_out_kvec_reset(con);
+	con_out_kvec_reset(con);
 	con->out_kvec_is_msg = true;
 	con->out_msg_done = false;
 

@@ -542,14 +728,16 @@ static void prepare_write_message(struct ceph_connection *con)
 	 * TCP packet that's a good thing. */
 	if (con->in_seq > con->in_seq_acked) {
 		con->in_seq_acked = con->in_seq;
-		ceph_con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
+		con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
 		con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
-		ceph_con_out_kvec_add(con, sizeof (con->out_temp_ack),
+		con_out_kvec_add(con, sizeof (con->out_temp_ack),
 			&con->out_temp_ack);
 	}
 
+	BUG_ON(list_empty(&con->out_queue));
 	m = list_first_entry(&con->out_queue, struct ceph_msg, list_head);
 	con->out_msg = m;
+	BUG_ON(m->con != con);
 
 	/* put message on sent list */
 	ceph_msg_get(m);

@@ -572,18 +760,18 @@ static void prepare_write_message(struct ceph_connection *con)
 	BUG_ON(le32_to_cpu(m->hdr.front_len) != m->front.iov_len);
 
 	/* tag + hdr + front + middle */
-	ceph_con_out_kvec_add(con, sizeof (tag_msg), &tag_msg);
-	ceph_con_out_kvec_add(con, sizeof (m->hdr), &m->hdr);
-	ceph_con_out_kvec_add(con, m->front.iov_len, m->front.iov_base);
+	con_out_kvec_add(con, sizeof (tag_msg), &tag_msg);
+	con_out_kvec_add(con, sizeof (m->hdr), &m->hdr);
+	con_out_kvec_add(con, m->front.iov_len, m->front.iov_base);
 
 	if (m->middle)
-		ceph_con_out_kvec_add(con, m->middle->vec.iov_len,
+		con_out_kvec_add(con, m->middle->vec.iov_len,
 			m->middle->vec.iov_base);
 
 	/* fill in crc (except data pages), footer */
 	crc = crc32c(0, &m->hdr, offsetof(struct ceph_msg_header, crc));
 	con->out_msg->hdr.crc = cpu_to_le32(crc);
-	con->out_msg->footer.flags = CEPH_MSG_FOOTER_COMPLETE;
+	con->out_msg->footer.flags = 0;
 
 	crc = crc32c(0, m->front.iov_base, m->front.iov_len);
 	con->out_msg->footer.front_crc = cpu_to_le32(crc);

@@ -593,28 +781,19 @@ static void prepare_write_message(struct ceph_connection *con)
 		con->out_msg->footer.middle_crc = cpu_to_le32(crc);
 	} else
 		con->out_msg->footer.middle_crc = 0;
-	con->out_msg->footer.data_crc = 0;
-	dout("prepare_write_message front_crc %u data_crc %u\n",
+	dout("%s front_crc %u middle_crc %u\n", __func__,
 	     le32_to_cpu(con->out_msg->footer.front_crc),
 	     le32_to_cpu(con->out_msg->footer.middle_crc));
 
 	/* is there a data payload? */
-	if (le32_to_cpu(m->hdr.data_len) > 0) {
-		/* initialize page iterator */
-		con->out_msg_pos.page = 0;
-		if (m->pages)
-			con->out_msg_pos.page_pos = m->page_alignment;
-		else
-			con->out_msg_pos.page_pos = 0;
-		con->out_msg_pos.data_pos = 0;
-		con->out_msg_pos.did_page_crc = false;
-		con->out_more = 1;  /* data + footer will follow */
-	} else {
+	con->out_msg->footer.data_crc = 0;
+	if (m->hdr.data_len)
+		prepare_write_message_data(con);
+	else
 		/* no, queue up footer too and be done */
 		prepare_write_message_footer(con);
-	}
 
-	set_bit(WRITE_PENDING, &con->state);
+	set_bit(CON_FLAG_WRITE_PENDING, &con->flags);
 }
 
 /*

@@ -626,16 +805,16 @@ static void prepare_write_ack(struct ceph_connection *con)
 	     con->in_seq_acked, con->in_seq);
 	con->in_seq_acked = con->in_seq;
 
-	ceph_con_out_kvec_reset(con);
+	con_out_kvec_reset(con);
 
-	ceph_con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
+	con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
 
 	con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
-	ceph_con_out_kvec_add(con, sizeof (con->out_temp_ack),
+	con_out_kvec_add(con, sizeof (con->out_temp_ack),
 				&con->out_temp_ack);
 
 	con->out_more = 1;  /* more will follow.. eventually.. */
-	set_bit(WRITE_PENDING, &con->state);
+	set_bit(CON_FLAG_WRITE_PENDING, &con->flags);
 }
 
 /*

@@ -644,63 +823,60 @@ static void prepare_write_ack(struct ceph_connection *con)
 static void prepare_write_keepalive(struct ceph_connection *con)
 {
 	dout("prepare_write_keepalive %p\n", con);
-	ceph_con_out_kvec_reset(con);
-	ceph_con_out_kvec_add(con, sizeof (tag_keepalive), &tag_keepalive);
-	set_bit(WRITE_PENDING, &con->state);
+	con_out_kvec_reset(con);
+	con_out_kvec_add(con, sizeof (tag_keepalive), &tag_keepalive);
+	set_bit(CON_FLAG_WRITE_PENDING, &con->flags);
 }
 
 /*
  * Connection negotiation.
  */
 
-static int prepare_connect_authorizer(struct ceph_connection *con)
+static struct ceph_auth_handshake *get_connect_authorizer(struct ceph_connection *con,
+						int *auth_proto)
 {
-	void *auth_buf;
-	int auth_len = 0;
-	int auth_protocol = 0;
+	struct ceph_auth_handshake *auth;
+
+	if (!con->ops->get_authorizer) {
+		con->out_connect.authorizer_protocol = CEPH_AUTH_UNKNOWN;
+		con->out_connect.authorizer_len = 0;
+		return NULL;
+	}
 
+	/* Can't hold the mutex while getting authorizer */
 	mutex_unlock(&con->mutex);
-	if (con->ops->get_authorizer)
-		con->ops->get_authorizer(con, &auth_buf, &auth_len,
-					 &auth_protocol, &con->auth_reply_buf,
-					 &con->auth_reply_buf_len,
-					 con->auth_retry);
+	auth = con->ops->get_authorizer(con, auth_proto, con->auth_retry);
 	mutex_lock(&con->mutex);
 
-	if (test_bit(CLOSED, &con->state) ||
-	    test_bit(OPENING, &con->state))
-		return -EAGAIN;
+	if (IS_ERR(auth))
+		return auth;
+	if (con->state != CON_STATE_NEGOTIATING)
+		return ERR_PTR(-EAGAIN);
 
-	con->out_connect.authorizer_protocol = cpu_to_le32(auth_protocol);
-	con->out_connect.authorizer_len = cpu_to_le32(auth_len);
-
-	if (auth_len)
-		ceph_con_out_kvec_add(con, auth_len, auth_buf);
-
-	return 0;
+	con->auth_reply_buf = auth->authorizer_reply_buf;
+	con->auth_reply_buf_len = auth->authorizer_reply_buf_len;
+	return auth;
 }
 
 /*
  * We connected to a peer and are saying hello.
  */
-static void prepare_write_banner(struct ceph_messenger *msgr,
-				 struct ceph_connection *con)
+static void prepare_write_banner(struct ceph_connection *con)
 {
-	ceph_con_out_kvec_reset(con);
-	ceph_con_out_kvec_add(con, strlen(CEPH_BANNER), CEPH_BANNER);
-	ceph_con_out_kvec_add(con, sizeof (msgr->my_enc_addr),
-					&msgr->my_enc_addr);
+	con_out_kvec_add(con, strlen(CEPH_BANNER), CEPH_BANNER);
+	con_out_kvec_add(con, sizeof (con->msgr->my_enc_addr),
+					&con->msgr->my_enc_addr);
 
 	con->out_more = 0;
-	set_bit(WRITE_PENDING, &con->state);
+	set_bit(CON_FLAG_WRITE_PENDING, &con->flags);
 }
 
-static int prepare_write_connect(struct ceph_messenger *msgr,
-				 struct ceph_connection *con,
-				 int include_banner)
+static int prepare_write_connect(struct ceph_connection *con)
 {
 	unsigned global_seq = get_global_seq(con->msgr, 0);
 	int proto;
+	int auth_proto;
+	struct ceph_auth_handshake *auth;
 
 	switch (con->peer_name.type) {
 	case CEPH_ENTITY_TYPE_MON:

@@ -719,23 +895,32 @@ static int prepare_write_connect(struct ceph_messenger *msgr,
 	dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con,
 	     con->connect_seq, global_seq, proto);
 
-	con->out_connect.features = cpu_to_le64(msgr->supported_features);
+	con->out_connect.features = cpu_to_le64(con->msgr->supported_features);
 	con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT);
 	con->out_connect.connect_seq = cpu_to_le32(con->connect_seq);
 	con->out_connect.global_seq = cpu_to_le32(global_seq);
 	con->out_connect.protocol_version = cpu_to_le32(proto);
 	con->out_connect.flags = 0;
 
-	if (include_banner)
-		prepare_write_banner(msgr, con);
-	else
-		ceph_con_out_kvec_reset(con);
-	ceph_con_out_kvec_add(con, sizeof (con->out_connect), &con->out_connect);
+	auth_proto = CEPH_AUTH_UNKNOWN;
+	auth = get_connect_authorizer(con, &auth_proto);
+	if (IS_ERR(auth))
+		return PTR_ERR(auth);
+
+	con->out_connect.authorizer_protocol = cpu_to_le32(auth_proto);
+	con->out_connect.authorizer_len = auth ?
+		cpu_to_le32(auth->authorizer_buf_len) : 0;
+
+	con_out_kvec_add(con, sizeof (con->out_connect),
+					&con->out_connect);
+	if (auth && auth->authorizer_buf_len)
+		con_out_kvec_add(con, auth->authorizer_buf_len,
+					auth->authorizer_buf);
 
 	con->out_more = 0;
-	set_bit(WRITE_PENDING, &con->state);
+	set_bit(CON_FLAG_WRITE_PENDING, &con->flags);
 
-	return prepare_connect_authorizer(con);
+	return 0;
 }
 
 /*

@@ -781,30 +966,34 @@ out:
 	return ret;  /* done! */
 }
 
-#ifdef CONFIG_BLOCK
-static void init_bio_iter(struct bio *bio, struct bio **iter, int *seg)
+static void out_msg_pos_next(struct ceph_connection *con, struct page *page,
+			size_t len, size_t sent, bool in_trail)
 {
-	if (!bio) {
-		*iter = NULL;
-		*seg = 0;
-		return;
-	}
-	*iter = bio;
-	*seg = bio->bi_idx;
-}
+	struct ceph_msg *msg = con->out_msg;
 
-static void iter_bio_next(struct bio **bio_iter, int *seg)
-{
-	if (*bio_iter == NULL)
-		return;
+	BUG_ON(!msg);
+	BUG_ON(!sent);
 
-	BUG_ON(*seg >= (*bio_iter)->bi_vcnt);
+	con->out_msg_pos.data_pos += sent;
+	con->out_msg_pos.page_pos += sent;
+	if (sent < len)
+		return;
 
-	(*seg)++;
-	if (*seg == (*bio_iter)->bi_vcnt)
-		init_bio_iter((*bio_iter)->bi_next, bio_iter, seg);
-}
+	BUG_ON(sent != len);
+	con->out_msg_pos.page_pos = 0;
+	con->out_msg_pos.page++;
+	con->out_msg_pos.did_page_crc = false;
+	if (in_trail)
+		list_move_tail(&page->lru,
+			       &msg->trail->head);
+	else if (msg->pagelist)
+		list_move_tail(&page->lru,
+			       &msg->pagelist->head);
+#ifdef CONFIG_BLOCK
+	else if (msg->bio)
+		iter_bio_next(&msg->bio_iter, &msg->bio_seg);
 #endif
+}
 
 /*
  * Write as much message data payload as we can.  If we finish, queue

@@ -821,41 +1010,36 @@ static int write_partial_msg_pages(struct ceph_connection *con)
 	bool do_datacrc = !con->msgr->nocrc;
 	int ret;
 	int total_max_write;
-	int in_trail = 0;
-	size_t trail_len = (msg->trail ? msg->trail->length : 0);
+	bool in_trail = false;
+	const size_t trail_len = (msg->trail ? msg->trail->length : 0);
+	const size_t trail_off = data_len - trail_len;
 
 	dout("write_partial_msg_pages %p msg %p page %d/%d offset %d\n",
-	     con, con->out_msg, con->out_msg_pos.page, con->out_msg->nr_pages,
+	     con, msg, con->out_msg_pos.page, msg->nr_pages,
 	     con->out_msg_pos.page_pos);
 
-#ifdef CONFIG_BLOCK
-	if (msg->bio && !msg->bio_iter)
-		init_bio_iter(msg->bio, &msg->bio_iter, &msg->bio_seg);
-#endif
-
+	/*
+	 * Iterate through each page that contains data to be
+	 * written, and send as much as possible for each.
+	 *
+	 * If we are calculating the data crc (the default), we will
+	 * need to map the page.  If we have no pages, they have
+	 * been revoked, so use the zero page.
+	 */
 	while (data_len > con->out_msg_pos.data_pos) {
 		struct page *page = NULL;
 		int max_write = PAGE_SIZE;
 		int bio_offset = 0;
 
-		total_max_write = data_len - trail_len -
-			con->out_msg_pos.data_pos;
-
-		/*
-		 * if we are calculating the data crc (the default), we need
-		 * to map the page.  if our pages[] has been revoked, use the
-		 * zero page.
-		 */
-
-		/* have we reached the trail part of the data? */
-		if (con->out_msg_pos.data_pos >= data_len - trail_len) {
-			in_trail = 1;
+		in_trail = in_trail || con->out_msg_pos.data_pos >= trail_off;
+		if (!in_trail)
+			total_max_write = trail_off - con->out_msg_pos.data_pos;
 
+		if (in_trail) {
 			total_max_write = data_len - con->out_msg_pos.data_pos;
 
 			page = list_first_entry(&msg->trail->head,
 						struct page, lru);
-			max_write = PAGE_SIZE;
 		} else if (msg->pages) {
 			page = msg->pages[con->out_msg_pos.page];
 		} else if (msg->pagelist) {

@@ -878,52 +1062,32 @@ static int write_partial_msg_pages(struct ceph_connection *con)
 
 		if (do_datacrc && !con->out_msg_pos.did_page_crc) {
 			void *base;
-			u32 crc;
-			u32 tmpcrc = le32_to_cpu(con->out_msg->footer.data_crc);
+			u32 crc = le32_to_cpu(msg->footer.data_crc);
 			char *kaddr;
 
 			kaddr = kmap(page);
 			BUG_ON(kaddr == NULL);
 			base = kaddr + con->out_msg_pos.page_pos + bio_offset;
-			crc = crc32c(tmpcrc, base, len);
-			con->out_msg->footer.data_crc = cpu_to_le32(crc);
+			crc = crc32c(crc, base, len);
+			kunmap(page);
+			msg->footer.data_crc = cpu_to_le32(crc);
 			con->out_msg_pos.did_page_crc = true;
 		}
 		ret = ceph_tcp_sendpage(con->sock, page,
 				      con->out_msg_pos.page_pos + bio_offset,
 				      len, 1);
-
-		if (do_datacrc)
-			kunmap(page);
-
 		if (ret <= 0)
 			goto out;
 
-		con->out_msg_pos.data_pos += ret;
-		con->out_msg_pos.page_pos += ret;
-		if (ret == len) {
-			con->out_msg_pos.page_pos = 0;
-			con->out_msg_pos.page++;
-			con->out_msg_pos.did_page_crc = false;
-			if (in_trail)
-				list_move_tail(&page->lru,
-					       &msg->trail->head);
-			else if (msg->pagelist)
-				list_move_tail(&page->lru,
-					       &msg->pagelist->head);
-#ifdef CONFIG_BLOCK
-			else if (msg->bio)
-				iter_bio_next(&msg->bio_iter, &msg->bio_seg);
-#endif
-		}
+		out_msg_pos_next(con, page, len, (size_t) ret, in_trail);
 	}
 
 	dout("write_partial_msg_pages %p msg %p done\n", con, msg);
 
 	/* prepare and queue up footer, too */
 	if (!do_datacrc)
-		con->out_msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC;
-	ceph_con_out_kvec_reset(con);
+		msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC;
+	con_out_kvec_reset(con);
 	prepare_write_message_footer(con);
 	ret = 1;
 out:

@@ -992,11 +1156,10 @@ static int prepare_read_message(struct ceph_connection *con)
 
 
 static int read_partial(struct ceph_connection *con,
-			int *to, int size, void *object)
+			int end, int size, void *object)
 {
-	*to += size;
-	while (con->in_base_pos < *to) {
-		int left = *to - con->in_base_pos;
+	while (con->in_base_pos < end) {
+		int left = end - con->in_base_pos;
 		int have = size - left;
 		int ret = ceph_tcp_recvmsg(con->sock, object + have, left);
 		if (ret <= 0)

@@ -1012,37 +1175,52 @@ static int read_partial(struct ceph_connection *con,
  */
 static int read_partial_banner(struct ceph_connection *con)
 {
-	int ret, to = 0;
+	int size;
+	int end;
+	int ret;
 
 	dout("read_partial_banner %p at %d\n", con, con->in_base_pos);
 
 	/* peer's banner */
-	ret = read_partial(con, &to, strlen(CEPH_BANNER), con->in_banner);
+	size = strlen(CEPH_BANNER);
+	end = size;
+	ret = read_partial(con, end, size, con->in_banner);
 	if (ret <= 0)
 		goto out;
-	ret = read_partial(con, &to, sizeof(con->actual_peer_addr),
-			   &con->actual_peer_addr);
+
+	size = sizeof (con->actual_peer_addr);
+	end += size;
+	ret = read_partial(con, end, size, &con->actual_peer_addr);
 	if (ret <= 0)
 		goto out;
-	ret = read_partial(con, &to, sizeof(con->peer_addr_for_me),
-			   &con->peer_addr_for_me);
+
+	size = sizeof (con->peer_addr_for_me);
+	end += size;
+	ret = read_partial(con, end, size, &con->peer_addr_for_me);
 	if (ret <= 0)
 		goto out;
+
 out:
 	return ret;
 }
 
 static int read_partial_connect(struct ceph_connection *con)
 {
-	int ret, to = 0;
+	int size;
+	int end;
+	int ret;
 
 	dout("read_partial_connect %p at %d\n", con, con->in_base_pos);
 
-	ret = read_partial(con, &to, sizeof(con->in_reply), &con->in_reply);
+	size = sizeof (con->in_reply);
+	end = size;
+	ret = read_partial(con, end, size, &con->in_reply);
 	if (ret <= 0)
 		goto out;
-	ret = read_partial(con, &to, le32_to_cpu(con->in_reply.authorizer_len),
-			   con->auth_reply_buf);
+
+	size = le32_to_cpu(con->in_reply.authorizer_len);
+	end += size;
+	ret = read_partial(con, end, size, con->auth_reply_buf);
 	if (ret <= 0)
 		goto out;
 

@@ -1321,20 +1499,14 @@ static int process_banner(struct ceph_connection *con)
 		     ceph_pr_addr(&con->msgr->inst.addr.in_addr));
 	}
 
-	set_bit(NEGOTIATING, &con->state);
-	prepare_read_connect(con);
 	return 0;
 }
 
 static void fail_protocol(struct ceph_connection *con)
 {
 	reset_connection(con);
-	set_bit(CLOSED, &con->state);  /* in case there's queued work */
-
-	mutex_unlock(&con->mutex);
-	if (con->ops->bad_proto)
-		con->ops->bad_proto(con);
-	mutex_lock(&con->mutex);
+	BUG_ON(con->state != CON_STATE_NEGOTIATING);
+	con->state = CON_STATE_CLOSED;
 }
 
 static int process_connect(struct ceph_connection *con)

@@ -1377,7 +1549,8 @@ static int process_connect(struct ceph_connection *con)
 			return -1;
 		}
 		con->auth_retry = 1;
-		ret = prepare_write_connect(con->msgr, con, 0);
+		con_out_kvec_reset(con);
+		ret = prepare_write_connect(con);
 		if (ret < 0)
 			return ret;
 		prepare_read_connect(con);

@@ -1392,12 +1565,15 @@ static int process_connect(struct ceph_connection *con)
 		 * dropped messages.
 		 */
 		dout("process_connect got RESET peer seq %u\n",
-		     le32_to_cpu(con->in_connect.connect_seq));
+		     le32_to_cpu(con->in_reply.connect_seq));
 		pr_err("%s%lld %s connection reset\n",
 		       ENTITY_NAME(con->peer_name),
 		       ceph_pr_addr(&con->peer_addr.in_addr));
 		reset_connection(con);
-		prepare_write_connect(con->msgr, con, 0);
+		con_out_kvec_reset(con);
+		ret = prepare_write_connect(con);
+		if (ret < 0)
+			return ret;
 		prepare_read_connect(con);
 
 		/* Tell ceph about it. */

@@ -1406,8 +1582,7 @@ static int process_connect(struct ceph_connection *con)
 		if (con->ops->peer_reset)
 			con->ops->peer_reset(con);
 		mutex_lock(&con->mutex);
-		if (test_bit(CLOSED, &con->state) ||
-		    test_bit(OPENING, &con->state))
+		if (con->state != CON_STATE_NEGOTIATING)
 			return -EAGAIN;
 		break;
 

@@ -1416,11 +1591,14 @@ static int process_connect(struct ceph_connection *con)
 		 * If we sent a smaller connect_seq than the peer has, try
 		 * again with a larger value.
 		 */
-		dout("process_connect got RETRY my seq = %u, peer_seq = %u\n",
+		dout("process_connect got RETRY_SESSION my seq %u, peer %u\n",
 		     le32_to_cpu(con->out_connect.connect_seq),
-		     le32_to_cpu(con->in_connect.connect_seq));
-		con->connect_seq = le32_to_cpu(con->in_connect.connect_seq);
-		prepare_write_connect(con->msgr, con, 0);
+		     le32_to_cpu(con->in_reply.connect_seq));
+		con->connect_seq = le32_to_cpu(con->in_reply.connect_seq);
+		con_out_kvec_reset(con);
+		ret = prepare_write_connect(con);
+		if (ret < 0)
+			return ret;
 		prepare_read_connect(con);
 		break;
 

@@ -1431,10 +1609,13 @@ static int process_connect(struct ceph_connection *con)
 		 */
 		dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n",
 		     con->peer_global_seq,
-		     le32_to_cpu(con->in_connect.global_seq));
+		     le32_to_cpu(con->in_reply.global_seq));
 		get_global_seq(con->msgr,
-			       le32_to_cpu(con->in_connect.global_seq));
-		prepare_write_connect(con->msgr, con, 0);
+			       le32_to_cpu(con->in_reply.global_seq));
+		con_out_kvec_reset(con);
+		ret = prepare_write_connect(con);
+		if (ret < 0)
+			return ret;
 		prepare_read_connect(con);
 		break;
 

@@ -1449,7 +1630,10 @@ static int process_connect(struct ceph_connection *con)
 			fail_protocol(con);
 			return -1;
 		}
-		clear_bit(CONNECTING, &con->state);
+
+		BUG_ON(con->state != CON_STATE_NEGOTIATING);
+		con->state = CON_STATE_OPEN;
+
 		con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq);
 		con->connect_seq++;
 		con->peer_features = server_feat;

@@ -1461,7 +1645,9 @@ static int process_connect(struct ceph_connection *con)
 			le32_to_cpu(con->in_reply.connect_seq));
 
 		if (con->in_reply.flags & CEPH_MSG_CONNECT_LOSSY)
-			set_bit(LOSSYTX, &con->state);
+			set_bit(CON_FLAG_LOSSYTX, &con->flags);
+
+		con->delay = 0;      /* reset backoff memory */
 
 		prepare_read_tag(con);
 		break;

@@ -1491,10 +1677,10 @@ static int process_connect(struct ceph_connection *con)
  */
 static int read_partial_ack(struct ceph_connection *con)
 {
-	int to = 0;
+	int size = sizeof (con->in_temp_ack);
+	int end = size;
 
-	return read_partial(con, &to, sizeof(con->in_temp_ack),
-			    &con->in_temp_ack);
+	return read_partial(con, end, size, &con->in_temp_ack);
 }
 
 

@@ -1547,10 +1733,7 @@ static int read_partial_message_section(struct ceph_connection *con,
 	return 1;
 }
 
-static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con,
-				struct ceph_msg_header *hdr,
-				int *skip);
-
+static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip);
 
 static int read_partial_message_pages(struct ceph_connection *con,
 				      struct page **pages,

@@ -1593,9 +1776,6 @@ static int read_partial_message_bio(struct ceph_connection *con,
 	void *p;
 	int ret, left;
 
-	if (IS_ERR(bv))
-		return PTR_ERR(bv);
-
 	left = min((int)(data_len - con->in_msg_pos.data_pos),
 		   (int)(bv->bv_len - con->in_msg_pos.page_pos));
 

@@ -1627,26 +1807,22 @@ static int read_partial_message_bio(struct ceph_connection *con,
 static int read_partial_message(struct ceph_connection *con)
 {
 	struct ceph_msg *m = con->in_msg;
+	int size;
+	int end;
 	int ret;
-	int to, left;
 	unsigned front_len, middle_len, data_len;
 	bool do_datacrc = !con->msgr->nocrc;
-	int skip;
 	u64 seq;
 	u32 crc;
 
 	dout("read_partial_message con %p msg %p\n", con, m);
 
 	/* header */
-	while (con->in_base_pos < sizeof(con->in_hdr)) {
-		left = sizeof(con->in_hdr) - con->in_base_pos;
-		ret = ceph_tcp_recvmsg(con->sock,
-				       (char *)&con->in_hdr + con->in_base_pos,
-				       left);
-		if (ret <= 0)
-			return ret;
-		con->in_base_pos += ret;
-	}
+	size = sizeof (con->in_hdr);
+	end = size;
+	ret = read_partial(con, end, size, &con->in_hdr);
+	if (ret <= 0)
+		return ret;
 
 	crc = crc32c(0, &con->in_hdr, offsetof(struct ceph_msg_header, crc));
 	if (cpu_to_le32(crc) != con->in_hdr.crc) {

@@ -1686,10 +1862,13 @@ static int read_partial_message(struct ceph_connection *con)
 
 	/* allocate message? */
 	if (!con->in_msg) {
+		int skip = 0;
+
 		dout("got hdr type %d front %d data %d\n", con->in_hdr.type,
 		     con->in_hdr.front_len, con->in_hdr.data_len);
-		skip = 0;
-		con->in_msg = ceph_alloc_msg(con, &con->in_hdr, &skip);
+		ret = ceph_con_in_msg_alloc(con, &skip);
+		if (ret < 0)
+			return ret;
 		if (skip) {
 			/* skip this message */
 			dout("alloc_msg said skip message\n");

@@ -1700,11 +1879,9 @@ static int read_partial_message(struct ceph_connection *con)
 			con->in_seq++;
 			return 0;
 		}
-		if (!con->in_msg) {
-			con->error_msg =
-				"error allocating memory for incoming message";
-			return -ENOMEM;
-		}
+
+		BUG_ON(!con->in_msg);
+		BUG_ON(con->in_msg->con != con);
 		m = con->in_msg;
 		m->front.iov_len = 0;    /* haven't read it yet */
 		if (m->middle)

@@ -1716,6 +1893,11 @@ static int read_partial_message(struct ceph_connection *con)
 		else
 			con->in_msg_pos.page_pos = 0;
 		con->in_msg_pos.data_pos = 0;
+
+#ifdef CONFIG_BLOCK
+		if (m->bio)
+			init_bio_iter(m->bio, &m->bio_iter, &m->bio_seg);
+#endif
 	}
 
 	/* front */

@@ -1732,10 +1914,6 @@ static int read_partial_message(struct ceph_connection *con)
 		if (ret <= 0)
 			return ret;
 	}
-#ifdef CONFIG_BLOCK
-	if (m->bio && !m->bio_iter)
-		init_bio_iter(m->bio, &m->bio_iter, &m->bio_seg);
-#endif
 
 	/* (page) data */
 	while (con->in_msg_pos.data_pos < data_len) {

@@ -1746,7 +1924,7 @@ static int read_partial_message(struct ceph_connection *con)
 				return ret;
 #ifdef CONFIG_BLOCK
 		} else if (m->bio) {
-
+			BUG_ON(!m->bio_iter);
 			ret = read_partial_message_bio(con,
 						 &m->bio_iter, &m->bio_seg,
 						 data_len, do_datacrc);

@@ -1759,16 +1937,12 @@ static int read_partial_message(struct ceph_connection *con)
 	}
 
 	/* footer */
-	to = sizeof(m->hdr) + sizeof(m->footer);
-	while (con->in_base_pos < to) {
-		left = to - con->in_base_pos;
-		ret = ceph_tcp_recvmsg(con->sock, (char *)&m->footer +
-				       (con->in_base_pos - sizeof(m->hdr)),
-				       left);
-		if (ret <= 0)
-			return ret;
-		con->in_base_pos += ret;
-	}
+	size = sizeof (m->footer);
+	end += size;
+	ret = read_partial(con, end, size, &m->footer);
+	if (ret <= 0)
+		return ret;
+
 	dout("read_partial_message got msg %p %d (%u) + %d (%u) + %d (%u)\n",
 	     m, front_len, m->footer.front_crc, middle_len,
 	     m->footer.middle_crc, data_len, m->footer.data_crc);

@@ -1804,8 +1978,11 @@ static void process_message(struct ceph_connection *con)
 {
 	struct ceph_msg *msg;
 
+	BUG_ON(con->in_msg->con != con);
+	con->in_msg->con = NULL;
 	msg = con->in_msg;
 	con->in_msg = NULL;
+	con->ops->put(con);
 
 	/* if first message, set peer_name */
 	if (con->peer_name.type == 0)

@@ -1825,7 +2002,6 @@ static void process_message(struct ceph_connection *con)
 	con->ops->dispatch(con, msg);
 
 	mutex_lock(&con->mutex);
-	prepare_read_tag(con);
 }
 
 

@@ -1835,21 +2011,21 @@ static void process_message(struct ceph_connection *con)
  */
 static int try_write(struct ceph_connection *con)
 {
-	struct ceph_messenger *msgr = con->msgr;
 	int ret = 1;
 
-	dout("try_write start %p state %lu nref %d\n", con, con->state,
-	     atomic_read(&con->nref));
+	dout("try_write start %p state %lu\n", con, con->state);
 
 more:
 	dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes);
 
 	/* open the socket first? */
-	if (con->sock == NULL) {
-		prepare_write_connect(msgr, con, 1);
+	if (con->state == CON_STATE_PREOPEN) {
+		BUG_ON(con->sock);
+		con->state = CON_STATE_CONNECTING;
+
+		con_out_kvec_reset(con);
+		prepare_write_banner(con);
 		prepare_read_banner(con);
-		set_bit(CONNECTING, &con->state);
-		clear_bit(NEGOTIATING, &con->state);
 
 		BUG_ON(con->in_msg);
 		con->in_tag = CEPH_MSGR_TAG_READY;

@@ -1896,7 +2072,7 @@ more_kvec:
 	}
 
 do_next:
-	if (!test_bit(CONNECTING, &con->state)) {
+	if (con->state == CON_STATE_OPEN) {
 		/* is anything else pending? */
 		if (!list_empty(&con->out_queue)) {
 			prepare_write_message(con);

@@ -1906,14 +2082,15 @@ do_next:
 			prepare_write_ack(con);
 			goto more;
 		}
-		if (test_and_clear_bit(KEEPALIVE_PENDING, &con->state)) {
+		if (test_and_clear_bit(CON_FLAG_KEEPALIVE_PENDING,
+				       &con->flags)) {
 			prepare_write_keepalive(con);
 			goto more;
 		}
 	}
 
 	/* Nothing to do! */
-	clear_bit(WRITE_PENDING, &con->state);
+	clear_bit(CON_FLAG_WRITE_PENDING, &con->flags);
 	dout("try_write nothing else to write.\n");
 	ret = 0;
 out:

@@ -1930,38 +2107,46 @@ static int try_read(struct ceph_connection *con)
 {
 	int ret = -1;
 
-	if (!con->sock)
-		return 0;
-
-	if (test_bit(STANDBY, &con->state))
+more:
+	dout("try_read start on %p state %lu\n", con, con->state);
+	if (con->state != CON_STATE_CONNECTING &&
+	    con->state != CON_STATE_NEGOTIATING &&
+	    con->state != CON_STATE_OPEN)
 		return 0;
 
-	dout("try_read start on %p\n", con);
+	BUG_ON(!con->sock);
 
-more:
 	dout("try_read tag %d in_base_pos %d\n", (int)con->in_tag,
 	     con->in_base_pos);
 
-	/*
-	 * process_connect and process_message drop and re-take
-	 * con->mutex.  make sure we handle a racing close or reopen.
-	 */
-	if (test_bit(CLOSED, &con->state) ||
-	    test_bit(OPENING, &con->state)) {
-		ret = -EAGAIN;
+	if (con->state == CON_STATE_CONNECTING) {
+		dout("try_read connecting\n");
+		ret = read_partial_banner(con);
+		if (ret <= 0)
+			goto out;
+		ret = process_banner(con);
+		if (ret < 0)
+			goto out;
+
+		BUG_ON(con->state != CON_STATE_CONNECTING);
+		con->state = CON_STATE_NEGOTIATING;
+
+		/*
+		 * Received banner is good, exchange connection info.
+		 * Do not reset out_kvec, as sending our banner raced
+		 * with receiving peer banner after connect completed.
+		 */
+		ret = prepare_write_connect(con);
+		if (ret < 0)
+			goto out;
+		prepare_read_connect(con);
+
+		/* Send connection info before awaiting response */
 		goto out;
 	}
 
-	if (test_bit(CONNECTING, &con->state)) {
-		if (!test_bit(NEGOTIATING, &con->state)) {
-			dout("try_read connecting\n");
-			ret = read_partial_banner(con);
-			if (ret <= 0)
-				goto out;
-			ret = process_banner(con);
-			if (ret < 0)
-				goto out;
-		}
+	if (con->state == CON_STATE_NEGOTIATING) {
+		dout("try_read negotiating\n");
 		ret = read_partial_connect(con);
 		if (ret <= 0)
 			goto out;

@@ -1971,6 +2156,8 @@ more:
 		goto more;
 	}
 
+	BUG_ON(con->state != CON_STATE_OPEN);
+
 	if (con->in_base_pos < 0) {
 		/*
 		 * skipping + discarding content.

@@ -2004,7 +2191,8 @@ more:
 			prepare_read_ack(con);
 			break;
 		case CEPH_MSGR_TAG_CLOSE:
-			set_bit(CLOSED, &con->state);   /* fixme */
+			con_close_socket(con);
+			con->state = CON_STATE_CLOSED;
 			goto out;
 		default:
 			goto bad_tag;

@@ -2027,6 +2215,8 @@ more:
 		if (con->in_tag == CEPH_MSGR_TAG_READY)
 			goto more;
 		process_message(con);
+		if (con->state == CON_STATE_OPEN)
+			prepare_read_tag(con);
 		goto more;
 	}
 	if (con->in_tag == CEPH_MSGR_TAG_ACK) {

@@ -2055,12 +2245,6 @@ bad_tag:
  */
 static void queue_con(struct ceph_connection *con)
 {
-	if (test_bit(DEAD, &con->state)) {
-		dout("queue_con %p ignoring: DEAD\n",
-		     con);
-		return;
-	}
-
 	if (!con->ops->get(con)) {
 		dout("queue_con %p ref count 0\n", con);
 		return;

@@ -2085,7 +2269,26 @@ static void con_work(struct work_struct *work)
 
 	mutex_lock(&con->mutex);
 restart:
-	if (test_and_clear_bit(BACKOFF, &con->state)) {
+	if (test_and_clear_bit(CON_FLAG_SOCK_CLOSED, &con->flags)) {
+		switch (con->state) {
+		case CON_STATE_CONNECTING:
+			con->error_msg = "connection failed";
+			break;
+		case CON_STATE_NEGOTIATING:
+			con->error_msg = "negotiation failed";
+			break;
+		case CON_STATE_OPEN:
+			con->error_msg = "socket closed";
+			break;
+		default:
+			dout("unrecognized con state %d\n", (int)con->state);
+			con->error_msg = "unrecognized con state";
+			BUG();
+		}
+		goto fault;
+	}
+
+	if (test_and_clear_bit(CON_FLAG_BACKOFF, &con->flags)) {
 		dout("con_work %p backing off\n", con);
 		if (queue_delayed_work(ceph_msgr_wq, &con->work,
 				       round_jiffies_relative(con->delay))) {

@@ -2093,41 +2296,42 @@ restart:
 			mutex_unlock(&con->mutex);
 			return;
 		} else {
-			con->ops->put(con);
 			dout("con_work %p FAILED to back off %lu\n", con,
 			     con->delay);
+			set_bit(CON_FLAG_BACKOFF, &con->flags);
 		}
+		goto done;
 	}
 
-	if (test_bit(STANDBY, &con->state)) {
+	if (con->state == CON_STATE_STANDBY) {
 		dout("con_work %p STANDBY\n", con);
 		goto done;
 	}
-	if (test_bit(CLOSED, &con->state)) { /* e.g. if we are replaced */
-		dout("con_work CLOSED\n");
-		con_close_socket(con);
+	if (con->state == CON_STATE_CLOSED) {
+		dout("con_work %p CLOSED\n", con);
+		BUG_ON(con->sock);
 		goto done;
 	}
-	if (test_and_clear_bit(OPENING, &con->state)) {
-		/* reopen w/ new peer */
+	if (con->state == CON_STATE_PREOPEN) {
 		dout("con_work OPENING\n");
-		con_close_socket(con);
+		BUG_ON(con->sock);
 	}
 
-	if (test_and_clear_bit(SOCK_CLOSED, &con->state))
-		goto fault;
-
 	ret = try_read(con);
 	if (ret == -EAGAIN)
 		goto restart;
-	if (ret < 0)
+	if (ret < 0) {
+		con->error_msg = "socket error on read";
 		goto fault;
+	}
 
 	ret = try_write(con);
 	if (ret == -EAGAIN)
 		goto restart;
-	if (ret < 0)
+	if (ret < 0) {
+		con->error_msg = "socket error on write";
 		goto fault;
+	}
 
 done:
 	mutex_unlock(&con->mutex);

@@ -2136,7 +2340,6 @@ done_unlocked:
 	return;
 
 fault:
-	mutex_unlock(&con->mutex);
 	ceph_fault(con);     /* error/fault path */
 	goto done_unlocked;
 }

@@ -2147,26 +2350,31 @@ fault:
  * exponential backoff
  */
 static void ceph_fault(struct ceph_connection *con)
+	__releases(con->mutex)
 {
 	pr_err("%s%lld %s %s\n", ENTITY_NAME(con->peer_name),
 	       ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg);
 	dout("fault %p state %lu to peer %s\n",
 	     con, con->state, ceph_pr_addr(&con->peer_addr.in_addr));
 
-	if (test_bit(LOSSYTX, &con->state)) {
-		dout("fault on LOSSYTX channel\n");
-		goto out;
-	}
-
-	mutex_lock(&con->mutex);
-	if (test_bit(CLOSED, &con->state))
-		goto out_unlock;
+	BUG_ON(con->state != CON_STATE_CONNECTING &&
+	       con->state != CON_STATE_NEGOTIATING &&
+	       con->state != CON_STATE_OPEN);
 
 	con_close_socket(con);
 
+	if (test_bit(CON_FLAG_LOSSYTX, &con->flags)) {
+		dout("fault on LOSSYTX channel, marking CLOSED\n");
+		con->state = CON_STATE_CLOSED;
+		goto out_unlock;
+	}
+
 	if (con->in_msg) {
+		BUG_ON(con->in_msg->con != con);
+		con->in_msg->con = NULL;
 		ceph_msg_put(con->in_msg);
 		con->in_msg = NULL;
+		con->ops->put(con);
 	}
 
 	/* Requeue anything that hasn't been acked */

@@ -2175,12 +2383,13 @@ static void ceph_fault(struct ceph_connection *con)
 	/* If there are no messages queued or keepalive pending, place
 	 * the connection in a STANDBY state */
 	if (list_empty(&con->out_queue) &&
-	    !test_bit(KEEPALIVE_PENDING, &con->state)) {
+	    !test_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags)) {
 		dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con);
-		clear_bit(WRITE_PENDING, &con->state);
-		set_bit(STANDBY, &con->state);
+		clear_bit(CON_FLAG_WRITE_PENDING, &con->flags);
+		con->state = CON_STATE_STANDBY;
 	} else {
 		/* retry after a delay. */
+		con->state = CON_STATE_PREOPEN;
 		if (con->delay == 0)
 			con->delay = BASE_DELAY_INTERVAL;
 		else if (con->delay < MAX_DELAY_INTERVAL)

@@ -2201,13 +2410,12 @@ static void ceph_fault(struct ceph_connection *con)
 			 * that when con_work restarts we schedule the
 			 * delay then.
 			 */
-			set_bit(BACKOFF, &con->state);
+			set_bit(CON_FLAG_BACKOFF, &con->flags);
 		}
 	}
 
 out_unlock:
 	mutex_unlock(&con->mutex);
-out:
 	/*
 	 * in case we faulted due to authentication, invalidate our
 	 * current tickets so that we can get new ones.

@@ -2224,18 +2432,14 @@ out:
 
 
 /*
- * create a new messenger instance
+ * initialize a new messenger instance
  */
-struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr,
-					     u32 supported_features,
-					     u32 required_features)
+void ceph_messenger_init(struct ceph_messenger *msgr,
+			struct ceph_entity_addr *myaddr,
+			u32 supported_features,
+			u32 required_features,
+			bool nocrc)
 {
-	struct ceph_messenger *msgr;
-
-	msgr = kzalloc(sizeof(*msgr), GFP_KERNEL);
-	if (msgr == NULL)
-		return ERR_PTR(-ENOMEM);
-
 	msgr->supported_features = supported_features;
 	msgr->required_features = required_features;
 

@@ -2248,30 +2452,23 @@ struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr,
 	msgr->inst.addr.type = 0;
 	get_random_bytes(&msgr->inst.addr.nonce, sizeof(msgr->inst.addr.nonce));
 	encode_my_addr(msgr);
+	msgr->nocrc = nocrc;
 
-	dout("messenger_create %p\n", msgr);
-	return msgr;
-}
-EXPORT_SYMBOL(ceph_messenger_create);
+	atomic_set(&msgr->stopping, 0);
 
-void ceph_messenger_destroy(struct ceph_messenger *msgr)
-{
-	dout("destroy %p\n", msgr);
-	kfree(msgr);
-	dout("destroyed messenger %p\n", msgr);
+	dout("%s %p\n", __func__, msgr);
 }
-EXPORT_SYMBOL(ceph_messenger_destroy);
+EXPORT_SYMBOL(ceph_messenger_init);
 
 static void clear_standby(struct ceph_connection *con)
 {
 	/* come back from STANDBY? */
-	if (test_and_clear_bit(STANDBY, &con->state)) {
-		mutex_lock(&con->mutex);
+	if (con->state == CON_STATE_STANDBY) {
 		dout("clear_standby %p and ++connect_seq\n", con);
+		con->state = CON_STATE_PREOPEN;
 		con->connect_seq++;
-		WARN_ON(test_bit(WRITE_PENDING, &con->state));
-		WARN_ON(test_bit(KEEPALIVE_PENDING, &con->state));
-		mutex_unlock(&con->mutex);
+		WARN_ON(test_bit(CON_FLAG_WRITE_PENDING, &con->flags));
+		WARN_ON(test_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags));
 	}
 }
 

@@ -2280,21 +2477,24 @@ static void clear_standby(struct ceph_connection *con)
  */
 void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
 {
-	if (test_bit(CLOSED, &con->state)) {
-		dout("con_send %p closed, dropping %p\n", con, msg);
-		ceph_msg_put(msg);
-		return;
-	}
-
 	/* set src+dst */
 	msg->hdr.src = con->msgr->inst.name;
-
 	BUG_ON(msg->front.iov_len != le32_to_cpu(msg->hdr.front_len));
-
 	msg->needs_out_seq = true;
 
-	/* queue */
 	mutex_lock(&con->mutex);
+
+	if (con->state == CON_STATE_CLOSED) {
+		dout("con_send %p closed, dropping %p\n", con, msg);
+		ceph_msg_put(msg);
+		mutex_unlock(&con->mutex);
+		return;
+	}
+
+	BUG_ON(msg->con != NULL);
+	msg->con = con->ops->get(con);
+	BUG_ON(msg->con == NULL);
+
 	BUG_ON(!list_empty(&msg->list_head));
 	list_add_tail(&msg->list_head, &con->out_queue);
 	dout("----- %p to %s%lld %d=%s len %d+%d+%d -----\n", msg,

@@ -2303,12 +2503,13 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
 	     le32_to_cpu(msg->hdr.front_len),
 	     le32_to_cpu(msg->hdr.middle_len),
 	     le32_to_cpu(msg->hdr.data_len));
+
+	clear_standby(con);
 	mutex_unlock(&con->mutex);
 
 	/* if there wasn't anything waiting to send before, queue
 	 * new work */
-	clear_standby(con);
-	if (test_and_set_bit(WRITE_PENDING, &con->state) == 0)
+	if (test_and_set_bit(CON_FLAG_WRITE_PENDING, &con->flags) == 0)
 		queue_con(con);
 }
 EXPORT_SYMBOL(ceph_con_send);

@@ -2316,24 +2517,34 @@ EXPORT_SYMBOL(ceph_con_send);
 /*
  * Revoke a message that was previously queued for send
  */
-void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg)
+void ceph_msg_revoke(struct ceph_msg *msg)
 {
+	struct ceph_connection *con = msg->con;
+
+	if (!con)
+		return;		/* Message not in our possession */
+
 	mutex_lock(&con->mutex);
 	if (!list_empty(&msg->list_head)) {
-		dout("con_revoke %p msg %p - was on queue\n", con, msg);
+		dout("%s %p msg %p - was on queue\n", __func__, con, msg);
 		list_del_init(&msg->list_head);
-		ceph_msg_put(msg);
+		BUG_ON(msg->con == NULL);
+		msg->con->ops->put(msg->con);
+		msg->con = NULL;
 		msg->hdr.seq = 0;
+
+		ceph_msg_put(msg);
 	}
 	if (con->out_msg == msg) {
-		dout("con_revoke %p msg %p - was sending\n", con, msg);
+		dout("%s %p msg %p - was sending\n", __func__, con, msg);
 		con->out_msg = NULL;
 		if (con->out_kvec_is_msg) {
 			con->out_skip = con->out_kvec_bytes;
 			con->out_kvec_is_msg = false;
 		}
-		ceph_msg_put(msg);
 		msg->hdr.seq = 0;
+
+		ceph_msg_put(msg);
 	}
 	mutex_unlock(&con->mutex);
 }

@@ -2341,17 +2552,27 @@ void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg)
 /*
  * Revoke a message that we may be reading data into
  */
-void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg)
+void ceph_msg_revoke_incoming(struct ceph_msg *msg)
 {
+	struct ceph_connection *con;
+
+	BUG_ON(msg == NULL);
+	if (!msg->con) {
+		dout("%s msg %p null con\n", __func__, msg);
+
+		return;		/* Message not in our possession */
+	}
+
+	con = msg->con;
 	mutex_lock(&con->mutex);
-	if (con->in_msg && con->in_msg == msg) {
+	if (con->in_msg == msg) {
 		unsigned front_len = le32_to_cpu(con->in_hdr.front_len);
 		unsigned middle_len = le32_to_cpu(con->in_hdr.middle_len);
 		unsigned data_len = le32_to_cpu(con->in_hdr.data_len);
 
 		/* skip rest of message */
-		dout("con_revoke_pages %p msg %p revoked\n", con, msg);
-			con->in_base_pos = con->in_base_pos -
+		dout("%s %p msg %p revoked\n", __func__, con, msg);
+		con->in_base_pos = con->in_base_pos -
 				sizeof(struct ceph_msg_header) -
 				front_len -
 				middle_len -

@@ -2362,8 +2583,8 @@ void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg)
 		con->in_tag = CEPH_MSGR_TAG_READY;
 		con->in_seq++;
 	} else {
-		dout("con_revoke_pages %p msg %p pages %p no-op\n",
-		     con, con->in_msg, msg);
+		dout("%s %p in_msg %p msg %p no-op\n",
+		     __func__, con, con->in_msg, msg);
 	}
 	mutex_unlock(&con->mutex);
 }

@@ -2374,9 +2595,11 @@ void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg)
 void ceph_con_keepalive(struct ceph_connection *con)
 {
 	dout("con_keepalive %p\n", con);
+	mutex_lock(&con->mutex);
 	clear_standby(con);
-	if (test_and_set_bit(KEEPALIVE_PENDING, &con->state) == 0 &&
-	    test_and_set_bit(WRITE_PENDING, &con->state) == 0)
+	mutex_unlock(&con->mutex);
+	if (test_and_set_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags) == 0 &&
+	    test_and_set_bit(CON_FLAG_WRITE_PENDING, &con->flags) == 0)
 		queue_con(con);
 }
 EXPORT_SYMBOL(ceph_con_keepalive);

@@ -2395,6 +2618,8 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
 	if (m == NULL)
 		goto out;
 	kref_init(&m->kref);
+
+	m->con = NULL;
 	INIT_LIST_HEAD(&m->list_head);
 
 	m->hdr.tid = 0;

@@ -2490,46 +2715,78 @@ static int ceph_alloc_middle(struct ceph_connection *con, struct ceph_msg *msg)
 }
 
 /*
- * Generic message allocator, for incoming messages.
+ * Allocate a message for receiving an incoming message on a
+ * connection, and save the result in con->in_msg.  Uses the
+ * connection's private alloc_msg op if available.
+ *
+ * Returns 0 on success, or a negative error code.
+ *
+ * On success, if we set *skip = 1:
+ *  - the next message should be skipped and ignored.
+ *  - con->in_msg == NULL
+ * or if we set *skip = 0:
+ *  - con->in_msg is non-null.
+ * On error (ENOMEM, EAGAIN, ...),
+ *  - con->in_msg == NULL
  */
-static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con,
-				struct ceph_msg_header *hdr,
-				int *skip)
+static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip)
 {
+	struct ceph_msg_header *hdr = &con->in_hdr;
 	int type = le16_to_cpu(hdr->type);
 	int front_len = le32_to_cpu(hdr->front_len);
 	int middle_len = le32_to_cpu(hdr->middle_len);
-	struct ceph_msg *msg = NULL;
-	int ret;
+	int ret = 0;
+
+	BUG_ON(con->in_msg != NULL);
 
 	if (con->ops->alloc_msg) {
+		struct ceph_msg *msg;
+
 		mutex_unlock(&con->mutex);
 		msg = con->ops->alloc_msg(con, hdr, skip);
 		mutex_lock(&con->mutex);
-		if (!msg || *skip)
-			return NULL;
+		if (con->state != CON_STATE_OPEN) {
+			if (msg)
+				ceph_msg_put(msg);
+			return -EAGAIN;
+		}
+		con->in_msg = msg;
+		if (con->in_msg) {
+			con->in_msg->con = con->ops->get(con);
+			BUG_ON(con->in_msg->con == NULL);
+		}
+		if (*skip) {
+			con->in_msg = NULL;
+			return 0;
+		}
+		if (!con->in_msg) {
+			con->error_msg =
+				"error allocating memory for incoming message";
+			return -ENOMEM;
+		}
 	}
-	if (!msg) {
-		*skip = 0;
-		msg = ceph_msg_new(type, front_len, GFP_NOFS, false);
-		if (!msg) {
+	if (!con->in_msg) {
+		con->in_msg = ceph_msg_new(type, front_len, GFP_NOFS, false);
+		if (!con->in_msg) {
 			pr_err("unable to allocate msg type %d len %d\n",
 			       type, front_len);
-			return NULL;
+			return -ENOMEM;
 		}
-		msg->page_alignment = le16_to_cpu(hdr->data_off);
+		con->in_msg->con = con->ops->get(con);
+		BUG_ON(con->in_msg->con == NULL);
+		con->in_msg->page_alignment = le16_to_cpu(hdr->data_off);
 	}
-	memcpy(&msg->hdr, &con->in_hdr, sizeof(con->in_hdr));
+	memcpy(&con->in_msg->hdr, &con->in_hdr, sizeof(con->in_hdr));
 
-	if (middle_len && !msg->middle) {
-		ret = ceph_alloc_middle(con, msg);
+	if (middle_len && !con->in_msg->middle) {
+		ret = ceph_alloc_middle(con, con->in_msg);
 		if (ret < 0) {
-			ceph_msg_put(msg);
-			return NULL;
+			ceph_msg_put(con->in_msg);
+			con->in_msg = NULL;
 		}
 	}
 
-	return msg;
+	return ret;
 }
 
 

@@ -106,9 +106,9 @@ static void __send_prepared_auth_request(struct ceph_mon_client *monc, int len)
 	monc->pending_auth = 1;
 	monc->m_auth->front.iov_len = len;
 	monc->m_auth->hdr.front_len = cpu_to_le32(len);
-	ceph_con_revoke(monc->con, monc->m_auth);
+	ceph_msg_revoke(monc->m_auth);
 	ceph_msg_get(monc->m_auth);  /* keep our ref */
-	ceph_con_send(monc->con, monc->m_auth);
+	ceph_con_send(&monc->con, monc->m_auth);
 }
 
 /*

@@ -117,8 +117,11 @@ static void __send_prepared_auth_request(struct ceph_mon_client *monc, int len)
 static void __close_session(struct ceph_mon_client *monc)
 {
 	dout("__close_session closing mon%d\n", monc->cur_mon);
-	ceph_con_revoke(monc->con, monc->m_auth);
-	ceph_con_close(monc->con);
+	ceph_msg_revoke(monc->m_auth);
+	ceph_msg_revoke_incoming(monc->m_auth_reply);
+	ceph_msg_revoke(monc->m_subscribe);
+	ceph_msg_revoke_incoming(monc->m_subscribe_ack);
+	ceph_con_close(&monc->con);
 	monc->cur_mon = -1;
 	monc->pending_auth = 0;
 	ceph_auth_reset(monc->auth);

@@ -142,9 +145,8 @@ static int __open_session(struct ceph_mon_client *monc)
 		monc->want_next_osdmap = !!monc->want_next_osdmap;
 
 		dout("open_session mon%d opening\n", monc->cur_mon);
-		monc->con->peer_name.type = CEPH_ENTITY_TYPE_MON;
-		monc->con->peer_name.num = cpu_to_le64(monc->cur_mon);
-		ceph_con_open(monc->con,
+		ceph_con_open(&monc->con,
+			      CEPH_ENTITY_TYPE_MON, monc->cur_mon,
 			      &monc->monmap->mon_inst[monc->cur_mon].addr);
 
 		/* initiatiate authentication handshake */

@@ -226,8 +228,8 @@ static void __send_subscribe(struct ceph_mon_client *monc)
 
 		msg->front.iov_len = p - msg->front.iov_base;
 		msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
-		ceph_con_revoke(monc->con, msg);
-		ceph_con_send(monc->con, ceph_msg_get(msg));
+		ceph_msg_revoke(msg);
+		ceph_con_send(&monc->con, ceph_msg_get(msg));
 
 		monc->sub_sent = jiffies | 1;  /* never 0 */
 	}

@@ -247,7 +249,7 @@ static void handle_subscribe_ack(struct ceph_mon_client *monc,
 	if (monc->hunting) {
 		pr_info("mon%d %s session established\n",
 			monc->cur_mon,
-			ceph_pr_addr(&monc->con->peer_addr.in_addr));
+			ceph_pr_addr(&monc->con.peer_addr.in_addr));
 		monc->hunting = false;
 	}
 	dout("handle_subscribe_ack after %d seconds\n", seconds);

@@ -309,6 +311,17 @@ int ceph_monc_open_session(struct ceph_mon_client *monc)
 EXPORT_SYMBOL(ceph_monc_open_session);
 
 /*
+ * We require the fsid and global_id in order to initialize our
+ * debugfs dir.
+ */
+static bool have_debugfs_info(struct ceph_mon_client *monc)
+{
+	dout("have_debugfs_info fsid %d globalid %lld\n",
+	     (int)monc->client->have_fsid, monc->auth->global_id);
+	return monc->client->have_fsid && monc->auth->global_id > 0;
+}
+
+/*
  * The monitor responds with mount ack indicate mount success.  The
  * included client ticket allows the client to talk to MDSs and OSDs.
  */

@@ -318,9 +331,12 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc,
 	struct ceph_client *client = monc->client;
 	struct ceph_monmap *monmap = NULL, *old = monc->monmap;
 	void *p, *end;
+	int had_debugfs_info, init_debugfs = 0;
 
 	mutex_lock(&monc->mutex);
 
+	had_debugfs_info = have_debugfs_info(monc);
+
 	dout("handle_monmap\n");
 	p = msg->front.iov_base;
 	end = p + msg->front.iov_len;

@@ -342,12 +358,22 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc,
 
 	if (!client->have_fsid) {
 		client->have_fsid = true;
+		if (!had_debugfs_info && have_debugfs_info(monc)) {
+			pr_info("client%lld fsid %pU\n",
+				ceph_client_id(monc->client),
+				&monc->client->fsid);
+			init_debugfs = 1;
+		}
 		mutex_unlock(&monc->mutex);
-		/*
-		 * do debugfs initialization without mutex to avoid
-		 * creating a locking dependency
-		 */
-		ceph_debugfs_client_init(client);
+
+		if (init_debugfs) {
+			/*
+			 * do debugfs initialization without mutex to avoid
+			 * creating a locking dependency
+			 */
+			ceph_debugfs_client_init(monc->client);
+		}
+
 		goto out_unlocked;
 	}
 out:

@@ -439,6 +465,7 @@ static struct ceph_msg *get_generic_reply(struct ceph_connection *con,
 		m = NULL;
 	} else {
 		dout("get_generic_reply %lld got %p\n", tid, req->reply);
+		*skip = 0;
 		m = ceph_msg_get(req->reply);
 		/*
 		 * we don't need to track the connection reading into

@@ -461,7 +488,7 @@ static int do_generic_request(struct ceph_mon_client *monc,
 	req->request->hdr.tid = cpu_to_le64(req->tid);
 	__insert_generic_request(monc, req);
 	monc->num_generic_requests++;
-	ceph_con_send(monc->con, ceph_msg_get(req->request));
+	ceph_con_send(&monc->con, ceph_msg_get(req->request));
 	mutex_unlock(&monc->mutex);
 
 	err = wait_for_completion_interruptible(&req->completion);

@@ -684,8 +711,9 @@ static void __resend_generic_request(struct ceph_mon_client *monc)
 
 	for (p = rb_first(&monc->generic_request_tree); p; p = rb_next(p)) {
 		req = rb_entry(p, struct ceph_mon_generic_request, node);
-		ceph_con_revoke(monc->con, req->request);
-		ceph_con_send(monc->con, ceph_msg_get(req->request));
+		ceph_msg_revoke(req->request);
+		ceph_msg_revoke_incoming(req->reply);
+		ceph_con_send(&monc->con, ceph_msg_get(req->request));
 	}
 }
 

@@ -705,7 +733,7 @@ static void delayed_work(struct work_struct *work)
 		__close_session(monc);
 		__open_session(monc);  /* continue hunting */
 	} else {
-		ceph_con_keepalive(monc->con);
+		ceph_con_keepalive(&monc->con);
 
 		__validate_auth(monc);
 

@@ -760,19 +788,12 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl)
 		goto out;
 
 	/* connection */
-	monc->con = kmalloc(sizeof(*monc->con), GFP_KERNEL);
-	if (!monc->con)
-		goto out_monmap;
-	ceph_con_init(monc->client->msgr, monc->con);
-	monc->con->private = monc;
-	monc->con->ops = &mon_con_ops;
-
 	/* authentication */
 	monc->auth = ceph_auth_init(cl->options->name,
 				    cl->options->key);
 	if (IS_ERR(monc->auth)) {
 		err = PTR_ERR(monc->auth);
-		goto out_con;
+		goto out_monmap;
 	}
 	monc->auth->want_keys =
 		CEPH_ENTITY_TYPE_AUTH | CEPH_ENTITY_TYPE_MON |

@@ -801,6 +822,9 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl)
 	if (!monc->m_auth)
 		goto out_auth_reply;
 
+	ceph_con_init(&monc->con, monc, &mon_con_ops,
+		      &monc->client->msgr);
+
 	monc->cur_mon = -1;
 	monc->hunting = true;
 	monc->sub_renew_after = jiffies;

@@ -824,8 +848,6 @@ out_subscribe_ack:
 	ceph_msg_put(monc->m_subscribe_ack);
 out_auth:
 	ceph_auth_destroy(monc->auth);
-out_con:
-	monc->con->ops->put(monc->con);
 out_monmap:
 	kfree(monc->monmap);
 out:

@@ -841,12 +863,16 @@ void ceph_monc_stop(struct ceph_mon_client *monc)
 	mutex_lock(&monc->mutex);
 	__close_session(monc);
 
-	monc->con->private = NULL;
-	monc->con->ops->put(monc->con);
-	monc->con = NULL;
-
 	mutex_unlock(&monc->mutex);
 
+	/*
+	 * flush msgr queue before we destroy ourselves to ensure that:
+	 *  - any work that references our embedded con is finished.
+	 *  - any osd_client or other work that may reference an authorizer
+	 *    finishes before we shut down the auth subsystem.
+	 */
+	ceph_msgr_flush();
+
 	ceph_auth_destroy(monc->auth);
 
 	ceph_msg_put(monc->m_auth);

@@ -863,8 +889,10 @@ static void handle_auth_reply(struct ceph_mon_client *monc,
 {
 	int ret;
 	int was_auth = 0;
+	int had_debugfs_info, init_debugfs = 0;
 
 	mutex_lock(&monc->mutex);
+	had_debugfs_info = have_debugfs_info(monc);
 	if (monc->auth->ops)
 		was_auth = monc->auth->ops->is_authenticated(monc->auth);
 	monc->pending_auth = 0;

@@ -880,14 +908,29 @@ static void handle_auth_reply(struct ceph_mon_client *monc,
 	} else if (!was_auth && monc->auth->ops->is_authenticated(monc->auth)) {
 		dout("authenticated, starting session\n");
 
-		monc->client->msgr->inst.name.type = CEPH_ENTITY_TYPE_CLIENT;
-		monc->client->msgr->inst.name.num =
+		monc->client->msgr.inst.name.type = CEPH_ENTITY_TYPE_CLIENT;
+		monc->client->msgr.inst.name.num =
 					cpu_to_le64(monc->auth->global_id);
 
 		__send_subscribe(monc);
 		__resend_generic_request(monc);
 	}
+
+	if (!had_debugfs_info && have_debugfs_info(monc)) {
+		pr_info("client%lld fsid %pU\n",
+			ceph_client_id(monc->client),
+			&monc->client->fsid);
+		init_debugfs = 1;
+	}
 	mutex_unlock(&monc->mutex);
+
+	if (init_debugfs) {
+		/*
+		 * do debugfs initialization without mutex to avoid
+		 * creating a locking dependency
+		 */
+		ceph_debugfs_client_init(monc->client);
+	}
 }
 
 static int __validate_auth(struct ceph_mon_client *monc)

@@ -992,6 +1035,8 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
 	case CEPH_MSG_MDS_MAP:
 	case CEPH_MSG_OSD_MAP:
 		m = ceph_msg_new(type, front_len, GFP_NOFS, false);
+		if (!m)
+			return NULL;	/* ENOMEM--return skip == 0 */
 		break;
 	}
 

@@ -1021,7 +1066,7 @@ static void mon_fault(struct ceph_connection *con)
 	if (!monc->hunting)
 		pr_info("mon%d %s session lost, "
 			"hunting for new mon\n", monc->cur_mon,
-			ceph_pr_addr(&monc->con->peer_addr.in_addr));
+			ceph_pr_addr(&monc->con.peer_addr.in_addr));
 
 	__close_session(monc);
 	if (!monc->hunting) {

@@ -1036,9 +1081,23 @@ out:
 	mutex_unlock(&monc->mutex);
 }
 
+/*
+ * We can ignore refcounting on the connection struct, as all references
+ * will come from the messenger workqueue, which is drained prior to
+ * mon_client destruction.
+ */
+static struct ceph_connection *con_get(struct ceph_connection *con)
+{
+	return con;
+}
+
+static void con_put(struct ceph_connection *con)
+{
+}
+
 static const struct ceph_connection_operations mon_con_ops = {
-	.get = ceph_con_get,
-	.put = ceph_con_put,
+	.get = con_get,
+	.put = con_put,
 	.dispatch = dispatch,
 	.fault = mon_fault,
 	.alloc_msg = mon_alloc_msg,

@@ -12,7 +12,7 @@ static void *msgpool_alloc(gfp_t gfp_mask, void *arg)
 	struct ceph_msgpool *pool = arg;
 	struct ceph_msg *msg;
 
-	msg = ceph_msg_new(0, pool->front_len, gfp_mask, true);
+	msg = ceph_msg_new(pool->type, pool->front_len, gfp_mask, true);
 	if (!msg) {
 		dout("msgpool_alloc %s failed\n", pool->name);
 	} else {

@@ -32,10 +32,11 @@ static void msgpool_free(void *element, void *arg)
 	ceph_msg_put(msg);
 }
 
-int ceph_msgpool_init(struct ceph_msgpool *pool,
+int ceph_msgpool_init(struct ceph_msgpool *pool, int type,
 		      int front_len, int size, bool blocking, const char *name)
 {
 	dout("msgpool %s init\n", name);
+	pool->type = type;
 	pool->front_len = front_len;
 	pool->pool = mempool_create(size, msgpool_alloc, msgpool_free, pool);
 	if (!pool->pool)

@@ -61,7 +62,7 @@ struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool,
 		WARN_ON(1);
 
 		/* try to alloc a fresh message */
-		return ceph_msg_new(0, front_len, GFP_NOFS, false);
+		return ceph_msg_new(pool->type, front_len, GFP_NOFS, false);
 	}
 
 	msg = mempool_alloc(pool->pool, GFP_NOFS);

@@ -52,7 +52,7 @@ static int op_has_extent(int op)
 		op == CEPH_OSD_OP_WRITE);
 }
 
-void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
+int ceph_calc_raw_layout(struct ceph_osd_client *osdc,
 			struct ceph_file_layout *layout,
 			u64 snapid,
 			u64 off, u64 *plen, u64 *bno,

@@ -62,12 +62,15 @@ void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
 	struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base;
 	u64 orig_len = *plen;
 	u64 objoff, objlen;    /* extent in object */
+	int r;
 
 	reqhead->snapid = cpu_to_le64(snapid);
 
 	/* object extent? */
-	ceph_calc_file_object_mapping(layout, off, plen, bno,
-				      &objoff, &objlen);
+	r = ceph_calc_file_object_mapping(layout, off, plen, bno,
+					  &objoff, &objlen);
+	if (r < 0)
+		return r;
 	if (*plen < orig_len)
 		dout(" skipping last %llu, final file extent %llu~%llu\n",
 		     orig_len - *plen, off, *plen);

@@ -83,7 +86,7 @@ void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
 
 	dout("calc_layout bno=%llx %llu~%llu (%d pages)\n",
 	     *bno, objoff, objlen, req->r_num_pages);
-
+	return 0;
 }
 EXPORT_SYMBOL(ceph_calc_raw_layout);
 

@@ -112,20 +115,25 @@ EXPORT_SYMBOL(ceph_calc_raw_layout);
  *
  * fill osd op in request message.
  */
-static void calc_layout(struct ceph_osd_client *osdc,
-			struct ceph_vino vino,
-			struct ceph_file_layout *layout,
-			u64 off, u64 *plen,
-			struct ceph_osd_request *req,
-			struct ceph_osd_req_op *op)
+static int calc_layout(struct ceph_osd_client *osdc,
+		       struct ceph_vino vino,
+		       struct ceph_file_layout *layout,
+		       u64 off, u64 *plen,
+		       struct ceph_osd_request *req,
+		       struct ceph_osd_req_op *op)
 {
 	u64 bno;
+	int r;
 
-	ceph_calc_raw_layout(osdc, layout, vino.snap, off,
-			     plen, &bno, req, op);
+	r = ceph_calc_raw_layout(osdc, layout, vino.snap, off,
+				 plen, &bno, req, op);
+	if (r < 0)
+		return r;
 
 	snprintf(req->r_oid, sizeof(req->r_oid), "%llx.%08llx", vino.ino, bno);
 	req->r_oid_len = strlen(req->r_oid);
+
+	return r;
 }
 
 /*

@@ -139,15 +147,14 @@ void ceph_osdc_release_request(struct kref *kref)
 
 	if (req->r_request)
 		ceph_msg_put(req->r_request);
-	if (req->r_reply)
-		ceph_msg_put(req->r_reply);
 	if (req->r_con_filling_msg) {
-		dout("release_request revoking pages %p from con %p\n",
+		dout("%s revoking pages %p from con %p\n", __func__,
 		     req->r_pages, req->r_con_filling_msg);
-		ceph_con_revoke_message(req->r_con_filling_msg,
-				      req->r_reply);
-		ceph_con_put(req->r_con_filling_msg);
+		ceph_msg_revoke_incoming(req->r_reply);
+		req->r_con_filling_msg->ops->put(req->r_con_filling_msg);
 	}
+	if (req->r_reply)
+		ceph_msg_put(req->r_reply);
 	if (req->r_own_pages)
 		ceph_release_page_vector(req->r_pages,
 					 req->r_num_pages);

@@ -243,6 +250,7 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 		}
 		ceph_pagelist_init(req->r_trail);
 	}
+
 	/* create request message; allow space for oid */
 	msg_size += MAX_OBJ_NAME_SIZE;
 	if (snapc)

@@ -256,7 +264,6 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 		return NULL;
 	}
 
-	msg->hdr.type = cpu_to_le16(CEPH_MSG_OSD_OP);
 	memset(msg->front.iov_base, 0, msg->front.iov_len);
 
 	req->r_request = msg;

@@ -278,7 +285,7 @@ static void osd_req_encode_op(struct ceph_osd_request *req,
 {
 	dst->op = cpu_to_le16(src->op);
 
-	switch (dst->op) {
+	switch (src->op) {
 	case CEPH_OSD_OP_READ:
 	case CEPH_OSD_OP_WRITE:
 		dst->extent.offset =

@@ -624,7 +631,7 @@ static void osd_reset(struct ceph_connection *con)
 /*
  * Track open sessions with osds.
  */
-static struct ceph_osd *create_osd(struct ceph_osd_client *osdc)
+static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum)
 {
 	struct ceph_osd *osd;
 

@@ -634,15 +641,13 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc)
 
 	atomic_set(&osd->o_ref, 1);
 	osd->o_osdc = osdc;
+	osd->o_osd = onum;
 	INIT_LIST_HEAD(&osd->o_requests);
 	INIT_LIST_HEAD(&osd->o_linger_requests);
 	INIT_LIST_HEAD(&osd->o_osd_lru);
 	osd->o_incarnation = 1;
 
-	ceph_con_init(osdc->client->msgr, &osd->o_con);
-	osd->o_con.private = osd;
-	osd->o_con.ops = &osd_con_ops;
-	osd->o_con.peer_name.type = CEPH_ENTITY_TYPE_OSD;
+	ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr);
 
 	INIT_LIST_HEAD(&osd->o_keepalive_item);
 	return osd;

@@ -664,11 +669,11 @@ static void put_osd(struct ceph_osd *osd)
 {
 	dout("put_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref),
 	     atomic_read(&osd->o_ref) - 1);
-	if (atomic_dec_and_test(&osd->o_ref)) {
+	if (atomic_dec_and_test(&osd->o_ref) && osd->o_auth.authorizer) {
 		struct ceph_auth_client *ac = osd->o_osdc->client->monc.auth;
 
-		if (osd->o_authorizer)
-			ac->ops->destroy_authorizer(ac, osd->o_authorizer);
+		if (ac->ops && ac->ops->destroy_authorizer)
+			ac->ops->destroy_authorizer(ac, osd->o_auth.authorizer);
 		kfree(osd);
 	}
 }

@@ -752,7 +757,8 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
 		ret = -EAGAIN;
 	} else {
 		ceph_con_close(&osd->o_con);
-		ceph_con_open(&osd->o_con, &osdc->osdmap->osd_addr[osd->o_osd]);
+		ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd,
+			      &osdc->osdmap->osd_addr[osd->o_osd]);
 		osd->o_incarnation++;
 	}
 	return ret;

@@ -841,13 +847,19 @@ static void register_request(struct ceph_osd_client *osdc,
 static void __unregister_request(struct ceph_osd_client *osdc,
 				 struct ceph_osd_request *req)
 {
+	if (RB_EMPTY_NODE(&req->r_node)) {
+		dout("__unregister_request %p tid %lld not registered\n",
+			req, req->r_tid);
+		return;
+	}
+
 	dout("__unregister_request %p tid %lld\n", req, req->r_tid);
 	rb_erase(&req->r_node, &osdc->requests);
 	osdc->num_requests--;
 
 	if (req->r_osd) {
 		/* make sure the original request isn't in flight. */
-		ceph_con_revoke(&req->r_osd->o_con, req->r_request);
+		ceph_msg_revoke(req->r_request);
 
 		list_del_init(&req->r_osd_item);
 		if (list_empty(&req->r_osd->o_requests) &&

@@ -874,7 +886,7 @@ static void __unregister_request(struct ceph_osd_client *osdc,
 static void __cancel_request(struct ceph_osd_request *req)
 {
 	if (req->r_sent && req->r_osd) {
-		ceph_con_revoke(&req->r_osd->o_con, req->r_request);
+		ceph_msg_revoke(req->r_request);
 		req->r_sent = 0;
 	}
 }

@@ -884,7 +896,9 @@ static void __register_linger_request(struct ceph_osd_client *osdc,
 {
 	dout("__register_linger_request %p\n", req);
 	list_add_tail(&req->r_linger_item, &osdc->req_linger);
-	list_add_tail(&req->r_linger_osd, &req->r_osd->o_linger_requests);
+	if (req->r_osd)
+		list_add_tail(&req->r_linger_osd,
+			      &req->r_osd->o_linger_requests);
 }
 
 static void __unregister_linger_request(struct ceph_osd_client *osdc,

@@ -992,18 +1006,18 @@ static int __map_request(struct ceph_osd_client *osdc,
 	req->r_osd = __lookup_osd(osdc, o);
 	if (!req->r_osd && o >= 0) {
 		err = -ENOMEM;
-		req->r_osd = create_osd(osdc);
+		req->r_osd = create_osd(osdc, o);
 		if (!req->r_osd) {
 			list_move(&req->r_req_lru_item, &osdc->req_notarget);
 			goto out;
 		}
 
 		dout("map_request osd %p is osd%d\n", req->r_osd, o);
-		req->r_osd->o_osd = o;
-		req->r_osd->o_con.peer_name.num = cpu_to_le64(o);
 		__insert_osd(osdc, req->r_osd);
 
-		ceph_con_open(&req->r_osd->o_con, &osdc->osdmap->osd_addr[o]);
+		ceph_con_open(&req->r_osd->o_con,
+			      CEPH_ENTITY_TYPE_OSD, o,
+			      &osdc->osdmap->osd_addr[o]);
 	}
 
 	if (req->r_osd) {

@@ -1210,7 +1224,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg,
 	if (req->r_con_filling_msg == con && req->r_reply == msg) {
 		dout(" dropping con_filling_msg ref %p\n", con);
 		req->r_con_filling_msg = NULL;
-		ceph_con_put(con);
+		con->ops->put(con);
 	}
 
 	if (!req->r_got_reply) {

@@ -1298,8 +1312,9 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend)
 
 	dout("kick_requests %s\n", force_resend ? " (force resend)" : "");
 	mutex_lock(&osdc->request_mutex);
-	for (p = rb_first(&osdc->requests); p; p = rb_next(p)) {
+	for (p = rb_first(&osdc->requests); p; ) {
 		req = rb_entry(p, struct ceph_osd_request, r_node);
+		p = rb_next(p);
 		err = __map_request(osdc, req, force_resend);
 		if (err < 0)
 			continue;  /* error */

@@ -1307,10 +1322,23 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend)
 			dout("%p tid %llu maps to no osd\n", req, req->r_tid);
 			needmap++;  /* request a newer map */
 		} else if (err > 0) {
-			dout("%p tid %llu requeued on osd%d\n", req, req->r_tid,
-			     req->r_osd ? req->r_osd->o_osd : -1);
-			if (!req->r_linger)
+			if (!req->r_linger) {
+				dout("%p tid %llu requeued on osd%d\n", req,
+				     req->r_tid,
+				     req->r_osd ? req->r_osd->o_osd : -1);
 				req->r_flags |= CEPH_OSD_FLAG_RETRY;
+			}
+		}
+		if (req->r_linger && list_empty(&req->r_linger_item)) {
+			/*
+			 * register as a linger so that we will
+			 * re-submit below and get a new tid
+			 */
+			dout("%p tid %llu restart on osd%d\n",
+			     req, req->r_tid,
+			     req->r_osd ? req->r_osd->o_osd : -1);
+			__register_linger_request(osdc, req);
+			__unregister_request(osdc, req);
 		}
 	}
 

@@ -1385,7 +1413,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 			     epoch, maplen);
 			newmap = osdmap_apply_incremental(&p, next,
 							  osdc->osdmap,
-							  osdc->client->msgr);
+							  &osdc->client->msgr);
 			if (IS_ERR(newmap)) {
 				err = PTR_ERR(newmap);
 				goto bad;

@@ -1833,11 +1861,12 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
 	if (!osdc->req_mempool)
 		goto out;
 
-	err = ceph_msgpool_init(&osdc->msgpool_op, OSD_OP_FRONT_LEN, 10, true,
+	err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP,
+				OSD_OP_FRONT_LEN, 10, true,
 				"osd_op");
 	if (err < 0)
 		goto out_mempool;
-	err = ceph_msgpool_init(&osdc->msgpool_op_reply,
+	err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY,
 				OSD_OPREPLY_FRONT_LEN, 10, true,
 				"osd_op_reply");
 	if (err < 0)

@@ -2019,10 +2048,10 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 	}
 
 	if (req->r_con_filling_msg) {
-		dout("get_reply revoking msg %p from old con %p\n",
+		dout("%s revoking msg %p from old con %p\n", __func__,
 		     req->r_reply, req->r_con_filling_msg);
-		ceph_con_revoke_message(req->r_con_filling_msg, req->r_reply);
-		ceph_con_put(req->r_con_filling_msg);
+		ceph_msg_revoke_incoming(req->r_reply);
+		req->r_con_filling_msg->ops->put(req->r_con_filling_msg);
 		req->r_con_filling_msg = NULL;
 	}
 

@@ -2057,7 +2086,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
 #endif
 	}
 	*skip = 0;
-	req->r_con_filling_msg = ceph_con_get(con);
+	req->r_con_filling_msg = con->ops->get(con);
 	dout("get_reply tid %lld %p\n", tid, m);
 
 out:

@@ -2074,6 +2103,7 @@ static struct ceph_msg *alloc_msg(struct ceph_connection *con,
 	int type = le16_to_cpu(hdr->type);
 	int front = le32_to_cpu(hdr->front_len);
 
+	*skip = 0;
 	switch (type) {
 	case CEPH_MSG_OSD_MAP:
 	case CEPH_MSG_WATCH_NOTIFY:

@@ -2108,37 +2138,32 @@ static void put_osd_con(struct ceph_connection *con)
 /*
  * authentication
  */
-static int get_authorizer(struct ceph_connection *con,
-			  void **buf, int *len, int *proto,
-			  void **reply_buf, int *reply_len, int force_new)
+/*
+ * Note: returned pointer is the address of a structure that's
+ * managed separately.  Caller must *not* attempt to free it.
+ */
+static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con,
+					int *proto, int force_new)
 {
 	struct ceph_osd *o = con->private;
 	struct ceph_osd_client *osdc = o->o_osdc;
 	struct ceph_auth_client *ac = osdc->client->monc.auth;
-	int ret = 0;
+	struct ceph_auth_handshake *auth = &o->o_auth;
 
-	if (force_new && o->o_authorizer) {
-		ac->ops->destroy_authorizer(ac, o->o_authorizer);
-		o->o_authorizer = NULL;
-	}
-	if (o->o_authorizer == NULL) {
-		ret = ac->ops->create_authorizer(
-			ac, CEPH_ENTITY_TYPE_OSD,
-			&o->o_authorizer,
-			&o->o_authorizer_buf,
-			&o->o_authorizer_buf_len,
-			&o->o_authorizer_reply_buf,
-			&o->o_authorizer_reply_buf_len);
+	if (force_new && auth->authorizer) {
+		if (ac->ops && ac->ops->destroy_authorizer)
+			ac->ops->destroy_authorizer(ac, auth->authorizer);
+		auth->authorizer = NULL;
+	}
+	if (!auth->authorizer && ac->ops && ac->ops->create_authorizer) {
+		int ret = ac->ops->create_authorizer(ac, CEPH_ENTITY_TYPE_OSD,
+							auth);
 		if (ret)
-			return ret;
+			return ERR_PTR(ret);
 	}
-
 	*proto = ac->protocol;
-	*buf = o->o_authorizer_buf;
-	*len = o->o_authorizer_buf_len;
-	*reply_buf = o->o_authorizer_reply_buf;
-	*reply_len = o->o_authorizer_reply_buf_len;
-	return 0;
+
+	return auth;
 }