2.6.27-stable review

@@ -924,6 +924,7 @@ static struct sk_buff *htb_dequeue(struc
 		}
 	}
 	sch->qstats.overlimits++;
+	qdisc_watchdog_cancel(&q->watchdog);
 	qdisc_watchdog_schedule(&q->watchdog, next_event);
 fin:
 	return skb;

@@ -298,6 +298,10 @@ static void fib6_dump_end(struct netlink
 	struct fib6_walker_t *w = (void*)cb->args[2];
 
 	if (w) {
+		if (cb->args[4]) {
+			cb->args[4] = 0;
+			fib6_walker_unlink(w);
+		}
 		cb->args[2] = 0;
 		kfree(w);
 	}

@@ -330,15 +334,12 @@ static int fib6_dump_table(struct fib6_t
 		read_lock_bh(&table->tb6_lock);
 		res = fib6_walk_continue(w);
 		read_unlock_bh(&table->tb6_lock);
-		if (res != 0) {
-			if (res < 0)
-				fib6_walker_unlink(w);
-			goto end;
+		if (res <= 0) {
+			fib6_walker_unlink(w);
+			cb->args[4] = 0;
 		}
-		fib6_walker_unlink(w);
-		cb->args[4] = 0;
 	}
-end:
+
 	return res;
 }
 

@@ -3635,6 +3635,7 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn(c
 {
 	struct sctp_chunk *chunk = arg;
 	struct sctp_fwdtsn_hdr *fwdtsn_hdr;
+	struct sctp_fwdtsn_skip *skip;
 	__u16 len;
 	__u32 tsn;
 

@@ -3664,6 +3665,12 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn(c
 	if (sctp_tsnmap_check(&asoc->peer.tsn_map, tsn) < 0)
 		goto discard_noforce;
 
+	/* Silently discard the chunk if stream-id is not valid */
+	sctp_walk_fwdtsn(skip, chunk) {
+		if (ntohs(skip->stream) >= asoc->c.sinit_max_instreams)
+			goto discard_noforce;
+	}
+
 	sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_FWDTSN, SCTP_U32(tsn));
 	if (len > sizeof(struct sctp_fwdtsn_hdr))
 		sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_FWDTSN,

@@ -3695,6 +3702,7 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn_f
 {
 	struct sctp_chunk *chunk = arg;
 	struct sctp_fwdtsn_hdr *fwdtsn_hdr;
+	struct sctp_fwdtsn_skip *skip;
 	__u16 len;
 	__u32 tsn;
 

@@ -3724,6 +3732,12 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn_f
 	if (sctp_tsnmap_check(&asoc->peer.tsn_map, tsn) < 0)
 		goto gen_shutdown;
 
+	/* Silently discard the chunk if stream-id is not valid */
+	sctp_walk_fwdtsn(skip, chunk) {
+		if (ntohs(skip->stream) >= asoc->c.sinit_max_instreams)
+			goto gen_shutdown;
+	}
+
 	sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_FWDTSN, SCTP_U32(tsn));
 	if (len > sizeof(struct sctp_fwdtsn_hdr))
 		sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_FWDTSN,

@@ -637,8 +637,9 @@ static int u32_change(struct tcf_proto *
 				break;
 
 		n->next = *ins;
-		wmb();
+		tcf_tree_lock(tp);
 		*ins = n;
+		tcf_tree_unlock(tp);
 
 		*arg = (unsigned long)n;
 		return 0;

@@ -214,7 +214,7 @@ static int r6040_phy_read(void __iomem *
 	/* Wait for the read bit to be cleared */
 	while (limit--) {
 		cmd = ioread16(ioaddr + MMDIO);
-		if (cmd & MDIO_READ)
+		if (!(cmd & MDIO_READ))
 			break;
 	}
 

@@ -233,7 +233,7 @@ static void r6040_phy_write(void __iomem
 	/* Wait for the write bit to be cleared */
 	while (limit--) {
 		cmd = ioread16(ioaddr + MMDIO);
-		if (cmd & MDIO_WRITE)
+		if (!(cmd & MDIO_WRITE))
 			break;
 	}
 }

@@ -681,8 +681,10 @@ static irqreturn_t r6040_interrupt(int i
 	struct net_device *dev = dev_id;
 	struct r6040_private *lp = netdev_priv(dev);
 	void __iomem *ioaddr = lp->base;
-	u16 status;
+	u16 misr, status;
 
+	/* Save MIER */
+	misr = ioread16(ioaddr + MIER);
 	/* Mask off RDC MAC interrupt */
 	iowrite16(MSK_INT, ioaddr + MIER);
 	/* Read MISR status and clear */

@@ -702,7 +704,7 @@ static irqreturn_t r6040_interrupt(int i
 			dev->stats.rx_fifo_errors++;
 
 		/* Mask off RX interrupt */
-		iowrite16(ioread16(ioaddr + MIER) & ~RX_INTS, ioaddr + MIER);
+		misr &= ~RX_INTS;
 		netif_rx_schedule(dev, &lp->napi);
 	}
 

@@ -710,6 +712,9 @@ static irqreturn_t r6040_interrupt(int i
 	if (status & TX_INTS)
 		r6040_tx(dev);
 
+	/* Restore RDC MAC interrupt */
+	iowrite16(misr, ioaddr + MIER);
+
 	return IRQ_HANDLED;
 }
 

@@ -49,8 +49,8 @@
 #include <asm/processor.h>
 
 #define DRV_NAME	"r6040"
-#define DRV_VERSION	"0.18"
-#define DRV_RELDATE	"13Jul2008"
+#define DRV_VERSION	"0.19"
+#define DRV_RELDATE	"18Dec2008"
 
 /* PHY CHIP Address */
 #define PHY1_ADDR	1	/* For MAC1 */

@@ -576,10 +576,6 @@ ssize_t tcp_splice_read(struct socket *s
 		else if (!ret) {
 			if (spliced)
 				break;
-			if (flags & SPLICE_F_NONBLOCK) {
-				ret = -EAGAIN;
-				break;
-			}
 			if (sock_flag(sk, SOCK_DONE))
 				break;
 			if (sk->sk_err) {

@@ -597,6 +593,10 @@ ssize_t tcp_splice_read(struct socket *s
 					ret = -ENOTCONN;
 				break;
 			}
+			if (flags & SPLICE_F_NONBLOCK) {
+				ret = -EAGAIN;
+				break;
+			}
 			if (!timeo) {
 				ret = -EAGAIN;
 				break;

@@ -46,6 +46,12 @@ static int usu_probe_thread(void *arg);
 { USB_DEVICE_VER(id_vendor, id_product, bcdDeviceMin,bcdDeviceMax), \
   .driver_info = (flags)|(USB_US_TYPE_STOR<<24) }
 
+#define COMPLIANT_DEV(id_vendor, id_product, bcdDeviceMin, bcdDeviceMax, \
+		    vendorName, productName, useProtocol, useTransport, \
+		    initFunction, flags) \
+{ USB_DEVICE_VER(id_vendor, id_product, bcdDeviceMin, bcdDeviceMax), \
+  .driver_info = (flags) }
+
 #define USUAL_DEV(useProto, useTrans, useType) \
 { USB_INTERFACE_INFO(USB_CLASS_MASS_STORAGE, useProto, useTrans), \
   .driver_info = ((useType)<<24) }

@@ -57,6 +63,7 @@ struct usb_device_id storage_usb_ids [] 
 
 #undef USUAL_DEV
 #undef UNUSUAL_DEV
+#undef COMPLIANT_DEV
 
 MODULE_DEVICE_TABLE(usb, storage_usb_ids);
 EXPORT_SYMBOL_GPL(storage_usb_ids);

@@ -196,6 +196,14 @@ static int slave_configure(struct scsi_d
 		 * sector in a larger then 1 sector read, since the performance
 		 * impact is negible we set this flag for all USB disks */
 		sdev->last_sector_bug = 1;
+
+		/* Enable last-sector hacks for single-target devices using
+		 * the Bulk-only transport, unless we already know the
+		 * capacity will be decremented or is correct. */
+		if (!(us->fflags & (US_FL_FIX_CAPACITY | US_FL_CAPACITY_OK |
+					US_FL_SCM_MULT_TARG)) &&
+				us->protocol == US_PR_BULK)
+			us->use_last_sector_hacks = 1;
 	} else {
 
 		/* Non-disk-type devices don't need to blacklist any pages

110 lines not on this page · raw message

@@ -27,7 +27,8 @@
 
 /* IMPORTANT NOTE: This file must be included in another file which does
  * the following thing for it to work:
- * The macro UNUSUAL_DEV() must be defined before this file is included
+ * The UNUSUAL_DEV, COMPLIANT_DEV, and USUAL_DEV macros must be defined
+ * before this file is included.
  */
 
 /* If you edit this file, please try to keep it sorted first by VendorID,

@@ -46,6 +47,12 @@
  * <[email protected]>
  */
 
+/* Note: If you add an entry only in order to set the CAPACITY_OK flag,
+ * use the COMPLIANT_DEV macro instead of UNUSUAL_DEV.  This is
+ * because such entries mark devices which actually work correctly,
+ * as opposed to devices that do something strangely or wrongly.
+ */
+
 /* patch submitted by Vivian Bregier <[email protected]>
  */
 UNUSUAL_DEV(  0x03eb, 0x2002, 0x0100, 0x0100,

@@ -692,6 +699,13 @@ UNUSUAL_DEV(  0x0525, 0xa140, 0x0100, 0x
 		US_SC_8070, US_PR_DEVICE, NULL,
 		US_FL_FIX_INQUIRY ),
 
+/* Added by Alan Stern <[email protected]> */
+COMPLIANT_DEV(0x0525, 0xa4a5, 0x0000, 0x9999,
+		"Linux",
+		"File-backed Storage Gadget",
+		US_SC_DEVICE, US_PR_DEVICE, NULL,
+		US_FL_CAPACITY_OK ),
+
 /* Yakumo Mega Image 37
  * Submitted by Stephan Fuhrmann <[email protected]> */
 UNUSUAL_DEV(  0x052b, 0x1801, 0x0100, 0x0100,

@@ -126,6 +126,8 @@ MODULE_PARM_DESC(delay_use, "seconds to 
 { USB_DEVICE_VER(id_vendor, id_product, bcdDeviceMin,bcdDeviceMax), \
   .driver_info = (flags)|(USB_US_TYPE_STOR<<24) }
 
+#define COMPLIANT_DEV	UNUSUAL_DEV
+
 #define USUAL_DEV(useProto, useTrans, useType) \
 { USB_INTERFACE_INFO(USB_CLASS_MASS_STORAGE, useProto, useTrans), \
   .driver_info = (USB_US_TYPE_STOR<<24) }

@@ -134,6 +136,7 @@ static struct usb_device_id storage_usb_
 
 #	include "unusual_devs.h"
 #undef UNUSUAL_DEV
+#undef COMPLIANT_DEV
 #undef USUAL_DEV
 	/* Terminating entry */
 	{ }

@@ -164,6 +167,8 @@ MODULE_DEVICE_TABLE (usb, storage_usb_id
 	.initFunction = init_function,	\
 }
 
+#define COMPLIANT_DEV	UNUSUAL_DEV
+
 #define USUAL_DEV(use_protocol, use_transport, use_type) \
 { \
 	.useProtocol = use_protocol,	\

@@ -173,6 +178,7 @@ MODULE_DEVICE_TABLE (usb, storage_usb_id
 static struct us_unusual_dev us_unusual_dev_list[] = {
 #	include "unusual_devs.h" 
 #	undef UNUSUAL_DEV
+#	undef COMPLIANT_DEV
 #	undef USUAL_DEV
 
 	/* Terminating entry */

@@ -155,6 +155,10 @@ struct us_data {
 #ifdef CONFIG_PM
 	pm_hook			suspend_resume_hook;
 #endif
+
+	/* hacks for READ CAPACITY bug handling */
+	int			use_last_sector_hacks;
+	int			last_sector_retries;
 };
 
 /* Convert between us_data and the corresponding Scsi_Host */

@@ -52,8 +52,9 @@
 	US_FLAG(MAX_SECTORS_MIN,0x00002000)			\
 		/* Sets max_sectors to arch min */		\
 	US_FLAG(BULK_IGNORE_TAG,0x00004000)			\
-		/* Ignore tag mismatch in bulk operations */
-
+		/* Ignore tag mismatch in bulk operations */	\
+	US_FLAG(CAPACITY_OK,	0x00010000)			\
+		/* READ CAPACITY response is correct */
 
 #define US_FLAG(name, value)	US_FL_##name = value ,
 enum { US_DO_ALL_FLAGS };

@@ -59,6 +59,13 @@
 #include "transport.h"
 #include "protocol.h"
 
+/* Vendor IDs for companies that seem to include the READ CAPACITY bug
+ * in all their devices
+ */
+#define VENDOR_ID_NOKIA		0x0421
+#define VENDOR_ID_NIKON		0x04b0
+#define VENDOR_ID_MOTOROLA	0x22b8
+
 /***********************************************************************
  * Host functions 
  ***********************************************************************/

@@ -134,6 +141,22 @@ static int slave_configure(struct scsi_d
 	 * settings can't be overridden via the scsi devinfo mechanism. */
 	if (sdev->type == TYPE_DISK) {
 
+		/* Some vendors seem to put the READ CAPACITY bug into
+		 * all their devices -- primarily makers of cell phones
+		 * and digital cameras.  Since these devices always use
+		 * flash media and can be expected to have an even number
+		 * of sectors, we will always enable the CAPACITY_HEURISTICS
+		 * flag unless told otherwise. */
+		switch (le16_to_cpu(us->pusb_dev->descriptor.idVendor)) {
+		case VENDOR_ID_NOKIA:
+		case VENDOR_ID_NIKON:
+		case VENDOR_ID_MOTOROLA:
+			if (!(us->fflags & (US_FL_FIX_CAPACITY |
+					US_FL_CAPACITY_OK)))
+				us->fflags |= US_FL_CAPACITY_HEURISTICS;
+			break;
+		}
+
 		/* Disk-type devices use MODE SENSE(6) if the protocol
 		 * (SubClass) is Transparent SCSI, otherwise they use
 		 * MODE SENSE(10). */

@@ -9882,6 +9882,7 @@ static struct snd_pci_quirk alc262_cfg_t
 	SND_PCI_QUIRK(0x10cf, 0x142d, "Fujitsu Lifebook E8410", ALC262_FUJITSU),
 	SND_PCI_QUIRK(0x144d, 0xc032, "Samsung Q1 Ultra", ALC262_ULTRA),
 	SND_PCI_QUIRK(0x144d, 0xc039, "Samsung Q1U EL", ALC262_ULTRA),
+	SND_PCI_QUIRK(0x144d, 0xc510, "Samsung Q45", ALC262_HIPPO),
 	SND_PCI_QUIRK(0x17aa, 0x384e, "Lenovo 3000 y410", ALC262_LENOVO_3000),
 	SND_PCI_QUIRK(0x17ff, 0x0560, "Benq ED8", ALC262_BENQ_ED8),
 	SND_PCI_QUIRK(0x17ff, 0x058d, "Benq T31-16", ALC262_BENQ_T31),

79 lines not on this page · raw message

@@ -1075,7 +1075,7 @@ static int stir421x_patch_device(struct 
 {
 	unsigned int i;
 	int ret;
-	char stir421x_fw_name[11];
+	char stir421x_fw_name[12];
 	const struct firmware *fw;
 	const unsigned char *fw_version_ptr; /* pointer to version string */
 	unsigned long fw_version = 0;

@@ -1141,7 +1141,8 @@ static int kill_something_info(int sig, 
 		struct task_struct * p;
 
 		for_each_process(p) {
-			if (p->pid > 1 && !same_thread_group(p, current)) {
+			if (task_pid_vnr(p) > 1 &&
+					!same_thread_group(p, current)) {
 				int err = group_send_sig_info(sig, info, p);
 				++count;
 				if (err != -EPERM)

@@ -121,7 +121,7 @@ int idr_pre_get(struct idr *idp, gfp_t g
 {
 	while (idp->id_free_cnt < IDR_FREE_MAX) {
 		struct idr_layer *new;
-		new = kmem_cache_alloc(idr_layer_cache, gfp_mask);
+		new = kmem_cache_zalloc(idr_layer_cache, gfp_mask);
 		if (new == NULL)
 			return (0);
 		move_to_free_list(idp, new);

@@ -623,16 +623,10 @@ void *idr_replace(struct idr *idp, void 
 }
 EXPORT_SYMBOL(idr_replace);
 
-static void idr_cache_ctor(void *idr_layer)
-{
-	memset(idr_layer, 0, sizeof(struct idr_layer));
-}
-
 void __init idr_init_cache(void)
 {
 	idr_layer_cache = kmem_cache_create("idr_layer_cache",
-				sizeof(struct idr_layer), 0, SLAB_PANIC,
-				idr_cache_ctor);
+				sizeof(struct idr_layer), 0, SLAB_PANIC, NULL);
 }
 
 /**

@@ -53,6 +53,7 @@ static struct usb_device_id p54u_table[]
 	{USB_DEVICE(0x050d, 0x7050)},	/* Belkin F5D7050 ver 1000 */
 	{USB_DEVICE(0x0572, 0x2000)},	/* Cohiba Proto board */
 	{USB_DEVICE(0x0572, 0x2002)},	/* Cohiba Proto board */
+	{USB_DEVICE(0x06b9, 0x0121)},	/* Thomson SpeedTouch 121g */
 	{USB_DEVICE(0x0707, 0xee13)},   /* SMC 2862W-G version 2 */
 	{USB_DEVICE(0x083a, 0x4521)},   /* Siemens Gigaset USB Adapter 54 version 2 */
 	{USB_DEVICE(0x0846, 0x4240)},	/* Netgear WG111 (v2) */

@@ -33,6 +33,11 @@ struct endpoint_state {
 struct pcie_link_state {
 	struct list_head sibiling;
 	struct pci_dev *pdev;
+	bool downstream_has_switch;
+
+	struct pcie_link_state *parent;
+	struct list_head children;
+	struct list_head link;
 
 	/* ASPM state */
 	unsigned int support_state;

@@ -125,7 +130,7 @@ static void pcie_set_clock_pm(struct pci
 	link_state->clk_pm_enabled = !!enable;
 }
 
-static void pcie_check_clock_pm(struct pci_dev *pdev)
+static void pcie_check_clock_pm(struct pci_dev *pdev, int blacklist)
 {
 	int pos;
 	u32 reg32;

@@ -149,10 +154,26 @@ static void pcie_check_clock_pm(struct p
 		if (!(reg16 & PCI_EXP_LNKCTL_CLKREQ_EN))
 			enabled = 0;
 	}
-	link_state->clk_pm_capable = capable;
 	link_state->clk_pm_enabled = enabled;
 	link_state->bios_clk_state = enabled;
-	pcie_set_clock_pm(pdev, policy_to_clkpm_state(pdev));
+	if (!blacklist) {
+		link_state->clk_pm_capable = capable;
+		pcie_set_clock_pm(pdev, policy_to_clkpm_state(pdev));
+	} else {
+		link_state->clk_pm_capable = 0;
+		pcie_set_clock_pm(pdev, 0);
+	}
+}
+
+static bool pcie_aspm_downstream_has_switch(struct pci_dev *pdev)
+{
+	struct pci_dev *child_dev;
+
+	list_for_each_entry(child_dev, &pdev->subordinate->devices, bus_list) {
+		if (child_dev->pcie_type == PCI_EXP_TYPE_UPSTREAM)
+			return true;
+	}
+	return false;
 }
 
 /*

@@ -419,9 +440,9 @@ static unsigned int pcie_aspm_check_stat
 {
 	struct pci_dev *child_dev;
 
-	/* If no child, disable the link */
+	/* If no child, ignore the link */
 	if (list_empty(&pdev->subordinate->devices))
-		return 0;
+		return state;
 	list_for_each_entry(child_dev, &pdev->subordinate->devices, bus_list) {
 		if (child_dev->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) {
 			/*

@@ -462,6 +483,9 @@ static void __pcie_aspm_config_link(stru
 	int valid = 1;
 	struct pcie_link_state *link_state = pdev->link_state;
 
+	/* If no child, disable the link */
+	if (list_empty(&pdev->subordinate->devices))
+		state = 0;
 	/*
 	 * if the downstream component has pci bridge function, don't do ASPM
 	 * now

@@ -493,20 +517,52 @@ static void __pcie_aspm_config_link(stru
 	link_state->enabled_state = state;
 }
 
+static struct pcie_link_state *get_root_port_link(struct pcie_link_state *link)
+{
+	struct pcie_link_state *root_port_link = link;
+	while (root_port_link->parent)
+		root_port_link = root_port_link->parent;
+	return root_port_link;
+}
+
+/* check the whole hierarchy, and configure each link in the hierarchy */
 static void __pcie_aspm_configure_link_state(struct pci_dev *pdev,
 	unsigned int state)
 {
 	struct pcie_link_state *link_state = pdev->link_state;
+	struct pcie_link_state *root_port_link = get_root_port_link(link_state);
+	struct pcie_link_state *leaf;
 
-	if (link_state->support_state == 0)
-		return;
 	state &= PCIE_LINK_STATE_L0S|PCIE_LINK_STATE_L1;
 
-	/* state 0 means disabling aspm */
-	state = pcie_aspm_check_state(pdev, state);
+	/* check all links who have specific root port link */
+	list_for_each_entry(leaf, &link_list, sibiling) {
+		if (!list_empty(&leaf->children) ||
+			get_root_port_link(leaf) != root_port_link)
+			continue;
+		state = pcie_aspm_check_state(leaf->pdev, state);
+	}
+	/* check root port link too in case it hasn't children */
+	state = pcie_aspm_check_state(root_port_link->pdev, state);
+
 	if (link_state->enabled_state == state)
 		return;
-	__pcie_aspm_config_link(pdev, state);
+
+	/*
+	 * we must change the hierarchy. See comments in
+	 * __pcie_aspm_config_link for the order
+	 **/
+	if (state & PCIE_LINK_STATE_L1) {
+		list_for_each_entry(leaf, &link_list, sibiling) {
+			if (get_root_port_link(leaf) == root_port_link)
+				__pcie_aspm_config_link(leaf->pdev, state);
+		}
+	} else {
+		list_for_each_entry_reverse(leaf, &link_list, sibiling) {
+			if (get_root_port_link(leaf) == root_port_link)
+				__pcie_aspm_config_link(leaf->pdev, state);
+		}
+	}
 }
 
 /*

@@ -570,6 +626,7 @@ void pcie_aspm_init_link_state(struct pc
 	unsigned int state;
 	struct pcie_link_state *link_state;
 	int error = 0;
+	int blacklist;
 
 	if (aspm_disabled || !pdev->is_pcie || pdev->link_state)
 		return;

@@ -580,29 +637,58 @@ void pcie_aspm_init_link_state(struct pc
 	if (list_empty(&pdev->subordinate->devices))
 		goto out;
 
-	if (pcie_aspm_sanity_check(pdev))
-		goto out;
+	blacklist = !!pcie_aspm_sanity_check(pdev);
 
 	mutex_lock(&aspm_lock);
 
 	link_state = kzalloc(sizeof(*link_state), GFP_KERNEL);
 	if (!link_state)
 		goto unlock_out;
-	pdev->link_state = link_state;
 
-	pcie_aspm_configure_common_clock(pdev);
-
-	pcie_aspm_cap_init(pdev);
+	link_state->downstream_has_switch = pcie_aspm_downstream_has_switch(pdev);
+	INIT_LIST_HEAD(&link_state->children);
+	INIT_LIST_HEAD(&link_state->link);
+	if (pdev->bus->self) {/* this is a switch */
+		struct pcie_link_state *parent_link_state;
+
+		parent_link_state = pdev->bus->parent->self->link_state;
+		if (!parent_link_state) {
+			kfree(link_state);
+			goto unlock_out;
+		}
+		list_add(&link_state->link, &parent_link_state->children);
+		link_state->parent = parent_link_state;
+	}
 
-	/* config link state to avoid BIOS error */
-	state = pcie_aspm_check_state(pdev, policy_to_aspm_state(pdev));
-	__pcie_aspm_config_link(pdev, state);
+	pdev->link_state = link_state;
 
-	pcie_check_clock_pm(pdev);
+	if (!blacklist) {
+		pcie_aspm_configure_common_clock(pdev);
+		pcie_aspm_cap_init(pdev);
+	} else {
+		link_state->enabled_state = PCIE_LINK_STATE_L0S|PCIE_LINK_STATE_L1;
+		link_state->bios_aspm_state = 0;
+		/* Set support state to 0, so we will disable ASPM later */
+		link_state->support_state = 0;
+	}
 
 	link_state->pdev = pdev;
 	list_add(&link_state->sibiling, &link_list);
 
+	if (link_state->downstream_has_switch) {
+		/*
+		 * If link has switch, delay the link config. The leaf link
+		 * initialization will config the whole hierarchy. but we must
+		 * make sure BIOS doesn't set unsupported link state
+		 **/
+		state = pcie_aspm_check_state(pdev, link_state->bios_aspm_state);
+		__pcie_aspm_config_link(pdev, state);
+	} else
+		__pcie_aspm_configure_link_state(pdev,
+			policy_to_aspm_state(pdev));
+
+	pcie_check_clock_pm(pdev, blacklist);
+
 unlock_out:
 	if (error)
 		free_link_state(pdev);

@@ -635,6 +721,7 @@ void pcie_aspm_exit_link_state(struct pc
 	/* All functions are removed, so just disable ASPM for the link */
 	__pcie_aspm_config_one_dev(parent, 0);
 	list_del(&link_state->sibiling);
+	list_del(&link_state->link);
 	/* Clock PM is for endpoint device */
 
 	free_link_state(parent);

@@ -2113,6 +2113,7 @@ static struct usb_device_id rt73usb_devi
 	/* Linksys */
 	{ USB_DEVICE(0x13b1, 0x0020), USB_DEVICE_DATA(&rt73usb_ops) },
 	{ USB_DEVICE(0x13b1, 0x0023), USB_DEVICE_DATA(&rt73usb_ops) },
+	{ USB_DEVICE(0x13b1, 0x0028), USB_DEVICE_DATA(&rt73usb_ops) },
 	/* MSI */
 	{ USB_DEVICE(0x0db0, 0x6877), USB_DEVICE_DATA(&rt73usb_ops) },
 	{ USB_DEVICE(0x0db0, 0x6874), USB_DEVICE_DATA(&rt73usb_ops) },

@@ -270,6 +270,7 @@ long keyctl_join_session_keyring(const c
 
 	/* join the session */
 	ret = join_session_keyring(name);
+	kfree(name);
 
  error:
 	return ret;

@@ -904,7 +904,7 @@ xpc_update_partition_info_sn2(struct xpc
 	dev_dbg(xpc_part, "  remote_vars_pa = 0x%016lx\n",
 		part_sn2->remote_vars_pa);
 
-	part->last_heartbeat = remote_vars->heartbeat;
+	part->last_heartbeat = remote_vars->heartbeat - 1;
 	dev_dbg(xpc_part, "  last_heartbeat = 0x%016lx\n",
 		part->last_heartbeat);
 

@@ -61,27 +61,23 @@ struct clocksource *clock;
 
 #ifdef CONFIG_GENERIC_TIME
 /**
- * __get_nsec_offset - Returns nanoseconds since last call to periodic_hook
+ * clocksource_forward_now - update clock to the current time
  *
- * private function, must hold xtime_lock lock when being
- * called. Returns the number of nanoseconds since the
- * last call to update_wall_time() (adjusted by NTP scaling)
+ * Forward the current clock to update its state since the last call to
+ * update_wall_time(). This is useful before significant clock changes,
+ * as it avoids having to deal with this time offset explicitly.
  */
-static inline s64 __get_nsec_offset(void)
+static void clocksource_forward_now(void)
 {
 	cycle_t cycle_now, cycle_delta;
-	s64 ns_offset;
+	s64 nsec;
 
-	/* read clocksource: */
 	cycle_now = clocksource_read(clock);
-
-	/* calculate the delta since the last update_wall_time: */
 	cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
+	clock->cycle_last = cycle_now;
 
-	/* convert to nanoseconds: */
-	ns_offset = cyc2ns(clock, cycle_delta);
-
-	return ns_offset;
+	nsec = cyc2ns(clock, cycle_delta);
+	timespec_add_ns(&xtime, nsec);
 }
 
 /**

@@ -92,6 +88,7 @@ static inline s64 __get_nsec_offset(void
  */
 void getnstimeofday(struct timespec *ts)
 {
+	cycle_t cycle_now, cycle_delta;
 	unsigned long seq;
 	s64 nsecs;
 

@@ -101,7 +98,15 @@ void getnstimeofday(struct timespec *ts)
 		seq = read_seqbegin(&xtime_lock);
 
 		*ts = xtime;
-		nsecs = __get_nsec_offset();
+
+		/* read clocksource: */
+		cycle_now = clocksource_read(clock);
+
+		/* calculate the delta since the last update_wall_time: */
+		cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
+
+		/* convert to nanoseconds: */
+		nsecs = cyc2ns(clock, cycle_delta);
 
 	} while (read_seqretry(&xtime_lock, seq));
 

@@ -134,22 +139,22 @@ EXPORT_SYMBOL(do_gettimeofday);
  */
 int do_settimeofday(struct timespec *tv)
 {
+	struct timespec ts_delta;
 	unsigned long flags;
-	time_t wtm_sec, sec = tv->tv_sec;
-	long wtm_nsec, nsec = tv->tv_nsec;
 
 	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
 		return -EINVAL;
 
 	write_seqlock_irqsave(&xtime_lock, flags);
 
-	nsec -= __get_nsec_offset();
+	clocksource_forward_now();
+
+	ts_delta.tv_sec = tv->tv_sec - xtime.tv_sec;
+	ts_delta.tv_nsec = tv->tv_nsec - xtime.tv_nsec;
+	wall_to_monotonic = timespec_sub(wall_to_monotonic, ts_delta);
 
-	wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
-	wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);
+	xtime = *tv;
 
-	set_normalized_timespec(&xtime, sec, nsec);
-	set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
 	update_xtime_cache(0);
 
 	clock->error = 0;

@@ -175,22 +180,17 @@ EXPORT_SYMBOL(do_settimeofday);
 static void change_clocksource(void)
 {
 	struct clocksource *new;
-	cycle_t now;
-	u64 nsec;
 
 	new = clocksource_get_next();
 
 	if (clock == new)
 		return;
 
-	new->cycle_last = 0;
-	now = clocksource_read(new);
-	nsec =  __get_nsec_offset();
-	timespec_add_ns(&xtime, nsec);
+	clocksource_forward_now();
 
 	clock = new;
-	clock->cycle_last = now;
-
+	clock->cycle_last = 0;
+	clock->cycle_last = clocksource_read(new);
 	clock->error = 0;
 	clock->xtime_nsec = 0;
 	clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);

@@ -205,8 +205,8 @@ static void change_clocksource(void)
 	 */
 }
 #else
+static inline void clocksource_forward_now(void) { }
 static inline void change_clocksource(void) { }
-static inline s64 __get_nsec_offset(void) { return 0; }
 #endif
 
 /**

@@ -268,8 +268,6 @@ void __init timekeeping_init(void)
 
 /* time in seconds when suspend began */
 static unsigned long timekeeping_suspend_time;
-/* xtime offset when we went into suspend */
-static s64 timekeeping_suspend_nsecs;
 
 /**
  * timekeeping_resume - Resumes the generic timekeeping subsystem.

@@ -295,8 +293,6 @@ static int timekeeping_resume(struct sys
 		wall_to_monotonic.tv_sec -= sleep_length;
 		total_sleep_time += sleep_length;
 	}
-	/* Make sure that we have the correct xtime reference */
-	timespec_add_ns(&xtime, timekeeping_suspend_nsecs);
 	update_xtime_cache(0);
 	/* re-base the last cycle value */
 	clock->cycle_last = 0;

@@ -322,8 +318,7 @@ static int timekeeping_suspend(struct sy
 	timekeeping_suspend_time = read_persistent_clock();
 
 	write_seqlock_irqsave(&xtime_lock, flags);
-	/* Get the current xtime offset */
-	timekeeping_suspend_nsecs = __get_nsec_offset();
+	clocksource_forward_now();
 	timekeeping_suspended = 1;
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 

@@ -464,10 +459,10 @@ void update_wall_time(void)
 	 */
 	while (offset >= clock->cycle_interval) {
 		/* accumulate one interval */
-		clock->xtime_nsec += clock->xtime_interval;
-		clock->cycle_last += clock->cycle_interval;
 		offset -= clock->cycle_interval;
+		clock->cycle_last += clock->cycle_interval;
 
+		clock->xtime_nsec += clock->xtime_interval;
 		if (clock->xtime_nsec >= (u64)NSEC_PER_SEC << clock->shift) {
 			clock->xtime_nsec -= (u64)NSEC_PER_SEC << clock->shift;
 			xtime.tv_sec++;

@@ -180,6 +180,7 @@ static struct vrm_model vrm_models[] = {
 	{X86_VENDOR_AMD, 0x6, ANY, ANY, 90},		/* Athlon Duron etc */
 	{X86_VENDOR_AMD, 0xF, 0x3F, ANY, 24},		/* Athlon 64, Opteron */
 	{X86_VENDOR_AMD, 0xF, ANY, ANY, 25},		/* NPT family 0Fh */
+	{X86_VENDOR_AMD, 0x10, ANY, ANY, 25},		/* NPT family 10h */
 	{X86_VENDOR_INTEL, 0x6, 0x9, ANY, 13},		/* Pentium M (130 nm) */
 	{X86_VENDOR_INTEL, 0x6, 0xB, ANY, 85},		/* Tualatin */
 	{X86_VENDOR_INTEL, 0x6, 0xD, ANY, 13},		/* Pentium M (90 nm) */

@@ -729,7 +729,7 @@ ath9k_hw_eeprom_set_board_values(struct 
 					  AR_AN_TOP2_LOCALBIAS,
 					  AR_AN_TOP2_LOCALBIAS_S,
 					  pModal->local_bias);
-		DPRINTF(ah->ah_sc, ATH_DBG_ANY, "ForceXPAon: %d\n",
+		DPRINTF(ah->ah_sc, ATH_DBG_EEPROM, "ForceXPAon: %d\n",
 			pModal->force_xpaon);
 		REG_RMW_FIELD(ah, AR_PHY_XPA_CFG, AR_PHY_FORCE_XPA_CFG,
 			      pModal->force_xpaon);

@@ -576,7 +576,7 @@ static ssize_t read_rbu_image_type(struc
 {
 	int size = 0;
 	if (!pos)
-		size = sprintf(buffer, "%s\n", image_type);
+		size = scnprintf(buffer, count, "%s\n", image_type);
 	return size;
 }
 

@@ -648,7 +648,7 @@ static ssize_t read_rbu_packet_size(stru
 	int size = 0;
 	if (!pos) {
 		spin_lock(&rbu_data.lock);
-		size = sprintf(buffer, "%lu\n", rbu_data.packetsize);
+		size = scnprintf(buffer, count, "%lu\n", rbu_data.packetsize);
 		spin_unlock(&rbu_data.lock);
 	}
 	return size;

@@ -1153,7 +1153,7 @@ static int __init abituguru3_dmi_detect(
 
 static inline int abituguru3_dmi_detect(void)
 {
-	return -ENODEV;
+	return 1;
 }
 
 #endif /* CONFIG_DMI */

@@ -710,9 +710,18 @@ int is_hugepage_only_range(struct mm_str
 			   unsigned long len)
 {
 	struct slice_mask mask, available;
+	unsigned int psize = mm->context.user_psize;
 
 	mask = slice_range_to_mask(addr, len);
-	available = slice_mask_for_size(mm, mm->context.user_psize);
+	available = slice_mask_for_size(mm, psize);
+#ifdef CONFIG_PPC_64K_PAGES
+	/* We need to account for 4k slices too */
+	if (psize == MMU_PAGE_64K) {
+		struct slice_mask compat_mask;
+		compat_mask = slice_mask_for_size(mm, MMU_PAGE_4K);
+		or_mask(available, compat_mask);
+	}
+#endif
 
 #if 0 /* too verbose */
 	slice_dbg("is_hugepage_only_range(mm=%p, addr=%lx, len=%lx)\n",

@@ -872,9 +872,10 @@ int write_cache_pages(struct address_spa
 	int done = 0;
 	struct pagevec pvec;
 	int nr_pages;
+	pgoff_t uninitialized_var(writeback_index);
 	pgoff_t index;
 	pgoff_t end;		/* Inclusive */
-	int scanned = 0;
+	int cycled;
 	int range_whole = 0;
 
 	if (wbc->nonblocking && bdi_write_congested(bdi)) {

@@ -884,14 +885,19 @@ int write_cache_pages(struct address_spa
 
 	pagevec_init(&pvec, 0);
 	if (wbc->range_cyclic) {
-		index = mapping->writeback_index; /* Start from prev offset */
+		writeback_index = mapping->writeback_index; /* prev offset */
+		index = writeback_index;
+		if (index == 0)
+			cycled = 1;
+		else
+			cycled = 0;
 		end = -1;
 	} else {
 		index = wbc->range_start >> PAGE_CACHE_SHIFT;
 		end = wbc->range_end >> PAGE_CACHE_SHIFT;
 		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
 			range_whole = 1;
-		scanned = 1;
+		cycled = 1; /* ignore range_cyclic tests */
 	}
 retry:
 	while (!done && (index <= end) &&

@@ -900,7 +906,6 @@ retry:
 					      min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
 		unsigned i;
 
-		scanned = 1;
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 

@@ -918,7 +923,11 @@ retry:
 				continue;
 			}
 
-			if (!wbc->range_cyclic && page->index > end) {
+			if (page->index > end) {
+				/*
+				 * can't be range_cyclic (1st pass) because
+				 * end == -1 in that case.
+				 */
 				done = 1;
 				unlock_page(page);
 				continue;

@@ -949,13 +958,15 @@ retry:
 		pagevec_release(&pvec);
 		cond_resched();
 	}
-	if (!scanned && !done) {
+	if (!cycled) {
 		/*
+		 * range_cyclic:
 		 * We hit the last page and there is more work to be done: wrap
 		 * back to the start of the file
 		 */
-		scanned = 1;
+		cycled = 1;
 		index = 0;
+		end = writeback_index - 1;
 		goto retry;
 	}
 	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))

@@ -875,6 +875,7 @@ int write_cache_pages(struct address_spa
 	pgoff_t uninitialized_var(writeback_index);
 	pgoff_t index;
 	pgoff_t end;		/* Inclusive */
+	pgoff_t done_index;
 	int cycled;
 	int range_whole = 0;
 

@@ -900,6 +901,7 @@ int write_cache_pages(struct address_spa
 		cycled = 1; /* ignore range_cyclic tests */
 	}
 retry:
+	done_index = index;
 	while (!done && (index <= end) &&
 	       (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
 					      PAGECACHE_TAG_DIRTY,

@@ -909,6 +911,8 @@ retry:
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
+			done_index = page->index + 1;
+
 			/*
 			 * At this point we hold neither mapping->tree_lock nor
 			 * lock on the page itself: the page may be truncated or

@@ -970,7 +974,7 @@ retry:
 		goto retry;
 	}
 	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
-		mapping->writeback_index = index;
+		mapping->writeback_index = done_index;
 
 	if (wbc->range_cont)
 		wbc->range_start = index << PAGE_CACHE_SHIFT;

@@ -948,11 +948,26 @@ retry:
 
 			ret = (*writepage)(page, wbc, data);
 
-			if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE)) {
-				unlock_page(page);
-				ret = 0;
-			}
-			if (ret || (--(wbc->nr_to_write) <= 0))
+			if (unlikely(ret)) {
+				if (ret == AOP_WRITEPAGE_ACTIVATE) {
+					unlock_page(page);
+					ret = 0;
+				} else {
+					/*
+					 * done_index is set past this page,
+					 * so media errors will not choke
+					 * background writeout for the entire
+					 * file. This has consequences for
+					 * range_cyclic semantics (ie. it may
+					 * not be suitable for data integrity
+					 * writeout).
+					 */
+					done = 1;
+					break;
+				}
+ 			}
+
+			if (--(wbc->nr_to_write) <= 0)
 				done = 1;
 			if (wbc->nonblocking && bdi_write_congested(bdi)) {
 				wbc->encountered_congestion = 1;

@@ -209,7 +209,7 @@ int __filemap_fdatawrite_range(struct ad
 	int ret;
 	struct writeback_control wbc = {
 		.sync_mode = sync_mode,
-		.nr_to_write = mapping->nrpages * 2,
+		.nr_to_write = LONG_MAX,
 		.range_start = start,
 		.range_end = end,
 	};

@@ -967,8 +967,10 @@ retry:
 				}
  			}
 
-			if (--(wbc->nr_to_write) <= 0)
-				done = 1;
+			if (wbc->sync_mode == WB_SYNC_NONE) {
+				if (--wbc->nr_to_write <= 0)
+					done = 1;
+			}
 			if (wbc->nonblocking && bdi_write_congested(bdi)) {
 				wbc->encountered_congestion = 1;
 				done = 1;

@@ -902,11 +902,14 @@ int write_cache_pages(struct address_spa
 	}
 retry:
 	done_index = index;
-	while (!done && (index <= end) &&
-	       (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
-					      PAGECACHE_TAG_DIRTY,
-					      min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
-		unsigned i;
+	while (!done && (index <= end)) {
+		int i;
+
+		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+			      PAGECACHE_TAG_DIRTY,
+			      min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+		if (nr_pages == 0)
+			break;
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];

@@ -922,7 +925,16 @@ retry:
 			 */
 			lock_page(page);
 
+			/*
+			 * Page truncated or invalidated. We can freely skip it
+			 * then, even for data integrity operations: the page
+			 * has disappeared concurrently, so there could be no
+			 * real expectation of this data interity operation
+			 * even if there is now a new, dirty page at the same
+			 * pagecache address.
+			 */
 			if (unlikely(page->mapping != mapping)) {
+continue_unlock:
 				unlock_page(page);
 				continue;
 			}

@@ -933,18 +945,15 @@ retry:
 				 * end == -1 in that case.
 				 */
 				done = 1;
-				unlock_page(page);
-				continue;
+				goto continue_unlock;
 			}
 
 			if (wbc->sync_mode != WB_SYNC_NONE)
 				wait_on_page_writeback(page);
 
 			if (PageWriteback(page) ||
-			    !clear_page_dirty_for_io(page)) {
-				unlock_page(page);
-				continue;
-			}
+			    !clear_page_dirty_for_io(page))
+				goto continue_unlock;
 
 			ret = (*writepage)(page, wbc, data);
 

@@ -968,7 +977,8 @@ retry:
  			}
 
 			if (wbc->sync_mode == WB_SYNC_NONE) {
-				if (--wbc->nr_to_write <= 0)
+				wbc->nr_to_write--;
+				if (wbc->nr_to_write <= 0)
 					done = 1;
 			}
 			if (wbc->nonblocking && bdi_write_congested(bdi)) {

@@ -948,11 +948,20 @@ continue_unlock:
 				goto continue_unlock;
 			}
 
-			if (wbc->sync_mode != WB_SYNC_NONE)
-				wait_on_page_writeback(page);
+			if (!PageDirty(page)) {
+				/* someone wrote it for us */
+				goto continue_unlock;
+			}
+
+			if (PageWriteback(page)) {
+				if (wbc->sync_mode != WB_SYNC_NONE)
+					wait_on_page_writeback(page);
+				else
+					goto continue_unlock;
+			}
 
-			if (PageWriteback(page) ||
-			    !clear_page_dirty_for_io(page))
+			BUG_ON(PageWriteback(page));
+			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
 			ret = (*writepage)(page, wbc, data);

@@ -914,15 +914,24 @@ retry:
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
-			done_index = page->index + 1;
-
 			/*
-			 * At this point we hold neither mapping->tree_lock nor
-			 * lock on the page itself: the page may be truncated or
-			 * invalidated (changing page->mapping to NULL), or even
-			 * swizzled back from swapper_space to tmpfs file
-			 * mapping
+			 * At this point, the page may be truncated or
+			 * invalidated (changing page->mapping to NULL), or
+			 * even swizzled back from swapper_space to tmpfs file
+			 * mapping. However, page->index will not change
+			 * because we have a reference on the page.
 			 */
+			if (page->index > end) {
+				/*
+				 * can't be range_cyclic (1st pass) because
+				 * end == -1 in that case.
+				 */
+				done = 1;
+				break;
+			}
+
+			done_index = page->index + 1;
+
 			lock_page(page);
 
 			/*

@@ -939,15 +948,6 @@ continue_unlock:
 				continue;
 			}
 
-			if (page->index > end) {
-				/*
-				 * can't be range_cyclic (1st pass) because
-				 * end == -1 in that case.
-				 */
-				done = 1;
-				goto continue_unlock;
-			}
-
 			if (!PageDirty(page)) {
 				/* someone wrote it for us */
 				goto continue_unlock;

@@ -987,12 +987,15 @@ continue_unlock:
 
 			if (wbc->sync_mode == WB_SYNC_NONE) {
 				wbc->nr_to_write--;
-				if (wbc->nr_to_write <= 0)
+				if (wbc->nr_to_write <= 0) {
 					done = 1;
+					break;
+				}
 			}
 			if (wbc->nonblocking && bdi_write_congested(bdi)) {
 				wbc->encountered_congestion = 1;
 				done = 1;
+				break;
 			}
 		}
 		pagevec_release(&pvec);

@@ -287,7 +287,7 @@ int do_sync_mapping_range(struct address
 
 	if (flags & SYNC_FILE_RANGE_WRITE) {
 		ret = __filemap_fdatawrite_range(mapping, offset, endbyte,
-						WB_SYNC_NONE);
+						WB_SYNC_ALL);
 		if (ret < 0)
 			goto out;
 	}

@@ -1304,7 +1304,8 @@ generic_file_aio_read(struct kiocb *iocb
 			goto out; /* skip atime */
 		size = i_size_read(inode);
 		if (pos < size) {
-			retval = filemap_write_and_wait(mapping);
+			retval = filemap_write_and_wait_range(mapping, pos,
+					pos + iov_length(iov, nr_segs) - 1);
 			if (!retval) {
 				retval = mapping->a_ops->direct_IO(READ, iocb,
 							iov, pos, nr_segs);

@@ -2117,18 +2118,10 @@ generic_file_direct_write(struct kiocb *
 	if (count != ocount)
 		*nr_segs = iov_shorten((struct iovec *)iov, *nr_segs, count);
 
-	/*
-	 * Unmap all mmappings of the file up-front.
-	 *
-	 * This will cause any pte dirty bits to be propagated into the
-	 * pageframes for the subsequent filemap_write_and_wait().
-	 */
 	write_len = iov_length(iov, *nr_segs);
 	end = (pos + write_len - 1) >> PAGE_CACHE_SHIFT;
-	if (mapping_mapped(mapping))
-		unmap_mapping_range(mapping, pos, write_len, 0);
 
-	written = filemap_write_and_wait(mapping);
+	written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1);
 	if (written)
 		goto out;
 

@@ -2519,7 +2512,8 @@ generic_file_buffered_write(struct kiocb
 	 * the file data here, to try to honour O_DIRECT expectations.
 	 */
 	if (unlikely(file->f_flags & O_DIRECT) && written)
-		status = filemap_write_and_wait(mapping);
+		status = filemap_write_and_wait_range(mapping,
+					pos, pos + written - 1);
 
 	return written ? written : status;
 }

@@ -421,9 +421,6 @@ __writeback_single_inode(struct inode *i
  * If we're a pdlfush thread, then implement pdflush collision avoidance
  * against the entire list.
  *
- * WB_SYNC_HOLD is a hack for sys_sync(): reattach the inode to sb->s_dirty so
- * that it can be located for waiting on in __writeback_single_inode().
- *
  * If `bdi' is non-zero then we're being asked to writeback a specific queue.
  * This function assumes that the blockdev superblock's inodes are backed by
  * a variety of queues, so all inodes are searched.  For other superblocks,

@@ -499,10 +496,6 @@ void generic_sync_sb_inodes(struct super
 		__iget(inode);
 		pages_skipped = wbc->pages_skipped;
 		__writeback_single_inode(inode, wbc);
-		if (wbc->sync_mode == WB_SYNC_HOLD) {
-			inode->dirtied_when = jiffies;
-			list_move(&inode->i_list, &sb->s_dirty);
-		}
 		if (current_is_pdflush())
 			writeback_release(bdi);
 		if (wbc->pages_skipped != pages_skipped) {

@@ -588,8 +581,7 @@ restart:
 
 /*
  * writeback and wait upon the filesystem's dirty inodes.  The caller will
- * do this in two passes - one to write, and one to wait.  WB_SYNC_HOLD is
- * used to park the written inodes on sb->s_dirty for the wait pass.
+ * do this in two passes - one to write, and one to wait.
  *
  * A finite limit is set on the number of pages which will be written.
  * To prevent infinite livelock of sys_sync().

@@ -600,7 +592,7 @@ restart:
 void sync_inodes_sb(struct super_block *sb, int wait)
 {
 	struct writeback_control wbc = {
-		.sync_mode	= wait ? WB_SYNC_ALL : WB_SYNC_HOLD,
+		.sync_mode	= wait ? WB_SYNC_ALL : WB_SYNC_NONE,
 		.range_start	= 0,
 		.range_end	= LLONG_MAX,
 	};

@@ -30,7 +30,6 @@ static inline int task_is_pdflush(struct
 enum writeback_sync_modes {
 	WB_SYNC_NONE,	/* Don't wait on anything */
 	WB_SYNC_ALL,	/* Wait on every mapping */
-	WB_SYNC_HOLD,	/* Hold the inode on sb_dirty for sys_sync() */
 };
 
 /*

@@ -440,6 +440,7 @@ void generic_sync_sb_inodes(struct super
 				struct writeback_control *wbc)
 {
 	const unsigned long start = jiffies;	/* livelock avoidance */
+	int sync = wbc->sync_mode == WB_SYNC_ALL;
 
 	spin_lock(&inode_lock);
 	if (!wbc->for_kupdate || list_empty(&sb->s_io))

@@ -516,7 +517,49 @@ void generic_sync_sb_inodes(struct super
 		if (!list_empty(&sb->s_more_io))
 			wbc->more_io = 1;
 	}
-	spin_unlock(&inode_lock);
+
+	if (sync) {
+		struct inode *inode, *old_inode = NULL;
+
+		/*
+		 * Data integrity sync. Must wait for all pages under writeback,
+		 * because there may have been pages dirtied before our sync
+		 * call, but which had writeout started before we write it out.
+		 * In which case, the inode may not be on the dirty list, but
+		 * we still have to wait for that writeout.
+		 */
+		list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+			struct address_space *mapping;
+
+			if (inode->i_state & (I_FREEING|I_WILL_FREE))
+				continue;
+			mapping = inode->i_mapping;
+			if (mapping->nrpages == 0)
+				continue;
+			__iget(inode);
+			spin_unlock(&inode_lock);
+			/*
+			 * We hold a reference to 'inode' so it couldn't have
+			 * been removed from s_inodes list while we dropped the
+			 * inode_lock.  We cannot iput the inode now as we can
+			 * be holding the last reference and we cannot iput it
+			 * under inode_lock. So we keep the reference and iput
+			 * it later.
+			 */
+			iput(old_inode);
+			old_inode = inode;
+
+			filemap_fdatawait(mapping);
+
+			cond_resched();
+
+			spin_lock(&inode_lock);
+		}
+		spin_unlock(&inode_lock);
+		iput(old_inode);
+	} else
+		spin_unlock(&inode_lock);
+
 	return;		/* Leave any unwritten inodes on s_io */
 }
 EXPORT_SYMBOL_GPL(generic_sync_sb_inodes);

@@ -596,13 +639,16 @@ void sync_inodes_sb(struct super_block *
 		.range_start	= 0,
 		.range_end	= LLONG_MAX,
 	};
-	unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
-	unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
 
-	wbc.nr_to_write = nr_dirty + nr_unstable +
-			(inodes_stat.nr_inodes - inodes_stat.nr_unused) +
-			nr_dirty + nr_unstable;
-	wbc.nr_to_write += wbc.nr_to_write / 2;		/* Bit more for luck */
+	if (!wait) {
+		unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
+		unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
+
+		wbc.nr_to_write = nr_dirty + nr_unstable +
+			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
+	} else
+		wbc.nr_to_write = LONG_MAX; /* doesn't actually matter */
+
 	sync_sb_inodes(sb, &wbc);
 }
 

@@ -652,18 +652,6 @@ void sync_inodes_sb(struct super_block *
 	sync_sb_inodes(sb, &wbc);
 }
 
-/*
- * Rather lame livelock avoidance.
- */
-static void set_sb_syncing(int val)
-{
-	struct super_block *sb;
-	spin_lock(&sb_lock);
-	list_for_each_entry_reverse(sb, &super_blocks, s_list)
-		sb->s_syncing = val;
-	spin_unlock(&sb_lock);
-}
-
 /**
  * sync_inodes - writes all inodes to disk
  * @wait: wait for completion

@@ -690,9 +678,6 @@ static void __sync_inodes(int wait)
 	spin_lock(&sb_lock);
 restart:
 	list_for_each_entry(sb, &super_blocks, s_list) {
-		if (sb->s_syncing)
-			continue;
-		sb->s_syncing = 1;
 		sb->s_count++;
 		spin_unlock(&sb_lock);
 		down_read(&sb->s_umount);

@@ -710,13 +695,10 @@ restart:
 
 void sync_inodes(int wait)
 {
-	set_sb_syncing(0);
 	__sync_inodes(0);
 
-	if (wait) {
-		set_sb_syncing(0);
+	if (wait)
 		__sync_inodes(1);
-	}
 }
 
 /**

@@ -1080,7 +1080,6 @@ struct super_block {
 	struct rw_semaphore	s_umount;
 	struct mutex		s_lock;
 	int			s_count;
-	int			s_syncing;
 	int			s_need_sync_fs;
 	atomic_t		s_active;
 #ifdef CONFIG_SECURITY