Merge tag 'v3.0-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into for-linus

Documentation/kernel-parameters.txt

···
 			With this option on every unmap_single operation will
 			result in a hardware IOTLB flush operation as opposed
 			to batching them for performance.
-
+		sp_off [Default Off]
+			By default, super page will be supported if Intel IOMMU
+			has the capability. With this option, super page will
+			not be supported.
 	intremap=	[X86-64, Intel-IOMMU]
 			Format: { on (default) | off | nosid }
 			on	enable Interrupt Remapping (default)

Documentation/virtual/lguest/Makefile

···
 # This creates the demonstration utility "lguest" which runs a Linux guest.
-# Missing headers?  Add "-I../../include -I../../arch/x86/include"
+# Missing headers?  Add "-I../../../include -I../../../arch/x86/include"
 CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE
 
 all: lguest

Documentation/virtual/lguest/lguest.c

···
 #include <linux/virtio_rng.h>
 #include <linux/virtio_ring.h>
 #include <asm/bootparam.h>
-#include "../../include/linux/lguest_launcher.h"
+#include "../../../include/linux/lguest_launcher.h"
 /*L:110
  * We can ignore the 42 include files we need for this program, but I do want
  * to draw attention to the use of kernel-style types.
···
 
 	/* Is it operational */
 	bool running;
-
-	/* Does Guest want an intrrupt on empty? */
-	bool irq_on_empty;
 
 	/* Device-specific data. */
 	void *priv;
···
 
 	/* If they don't want an interrupt, don't send one... */
 	if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT) {
-		/* ... unless they've asked us to force one on empty. */
-		if (!vq->dev->irq_on_empty
-		    || lg_last_avail(vq) != vq->vring.avail->idx)
-			return;
+		return;
 	}
 
 	/* Send the Guest an interrupt tell them we used something up. */
···
 	close(vq->eventfd);
 }
 
-static bool accepted_feature(struct device *dev, unsigned int bit)
-{
-	const u8 *features = get_feature_bits(dev) + dev->feature_len;
-
-	if (dev->feature_len < bit / CHAR_BIT)
-		return false;
-	return features[bit / CHAR_BIT] & (1 << (bit % CHAR_BIT));
-}
-
 static void start_device(struct device *dev)
 {
 	unsigned int i;
···
 	for (i = 0; i < dev->feature_len; i++)
 		verbose(" %02x", get_feature_bits(dev)
 			[dev->feature_len+i]);
-
-	dev->irq_on_empty = accepted_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY);
 
 	for (vq = dev->vq; vq; vq = vq->next) {
 		if (vq->service)
···
 	/* Set up the tun device. */
 	configure_device(ipfd, tapif, ip);
 
-	add_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY);
 	/* Expect Guest to handle everything except UFO */
 	add_feature(dev, VIRTIO_NET_F_CSUM);
 	add_feature(dev, VIRTIO_NET_F_GUEST_CSUM);

Makefile

···
 VERSION = 3
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Sneaky Weasel
 
 # *DOCUMENTATION*

arch/arm/mach-shmobile/board-ap4evb.c

···
 {
 	return !gpio_get_value(GPIO_PORT41);
 }
+/* MERAM */
+static struct sh_mobile_meram_info meram_info = {
+	.addr_mode      = SH_MOBILE_MERAM_MODE1,
+};
+
+static struct resource meram_resources[] = {
+	[0] = {
+		.name   = "MERAM",
+		.start  = 0xe8000000,
+		.end    = 0xe81fffff,
+		.flags  = IORESOURCE_MEM,
+	},
+};
+
+static struct platform_device meram_device = {
+	.name           = "sh_mobile_meram",
+	.id             = 0,
+	.num_resources  = ARRAY_SIZE(meram_resources),
+	.resource       = meram_resources,
+	.dev            = {
+		.platform_data = &meram_info,
+	},
+};
 
 /* SH_MMCIF */
 static struct resource sh_mmcif_resources[] = {
···
 #endif
 	},
 };
+static struct sh_mobile_meram_cfg lcd_meram_cfg = {
+	.icb[0] = {
+		.marker_icb     = 28,
+		.cache_icb      = 24,
+		.meram_offset   = 0x0,
+		.meram_size     = 0x40,
+	},
+	.icb[1] = {
+		.marker_icb     = 29,
+		.cache_icb      = 25,
+		.meram_offset   = 0x40,
+		.meram_size     = 0x40,
+	},
+};
 
 static struct sh_mobile_lcdc_info lcdc_info = {
+	.meram_dev = &meram_info,
 	.ch[0] = {
 		.chan = LCDC_CHAN_MAINLCD,
 		.bpp = 16,
 		.lcd_cfg = ap4evb_lcdc_modes,
 		.num_cfg = ARRAY_SIZE(ap4evb_lcdc_modes),
+		.meram_cfg = &lcd_meram_cfg,
 	}
 };
 
···
 static struct platform_device fsi_ak4643_device = {
 	.name		= "sh_fsi2_a_ak4643",
 };
+static struct sh_mobile_meram_cfg hdmi_meram_cfg = {
+	.icb[0] = {
+		.marker_icb     = 30,
+		.cache_icb      = 26,
+		.meram_offset   = 0x80,
+		.meram_size     = 0x100,
+	},
+	.icb[1] = {
+		.marker_icb     = 31,
+		.cache_icb      = 27,
+		.meram_offset   = 0x180,
+		.meram_size     = 0x100,
+	},
+};
 
 static struct sh_mobile_lcdc_info sh_mobile_lcdc1_info = {
 	.clock_source = LCDC_CLK_EXTERNAL,
+	.meram_dev = &meram_info,
 	.ch[0] = {
 		.chan = LCDC_CHAN_MAINLCD,
 		.bpp = 16,
 		.interface_type = RGB24,
 		.clock_divider = 1,
 		.flags = LCDC_FLAGS_DWPOL,
+		.meram_cfg = &hdmi_meram_cfg,
 	}
 };
 
···
 	&csi2_device,
 	&ceu_device,
 	&ap4evb_camera,
+	&meram_device,
 };
 
 static void __init hdmi_init_pm_clock(void)

arch/arm/mach-shmobile/board-mackerel.c

···
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
+#include <linux/pm_runtime.h>
 #include <linux/smsc911x.h>
 #include <linux/sh_intc.h>
 #include <linux/tca6416_keypad.h>
···
 	},
 };
 
+/* MERAM */
+static struct sh_mobile_meram_info mackerel_meram_info = {
+	.addr_mode	= SH_MOBILE_MERAM_MODE1,
+};
+
+static struct resource meram_resources[] = {
+	[0] = {
+		.name	= "MERAM",
+		.start	= 0xe8000000,
+		.end	= 0xe81fffff,
+		.flags	= IORESOURCE_MEM,
+	},
+};
+
+static struct platform_device meram_device = {
+	.name		= "sh_mobile_meram",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(meram_resources),
+	.resource	= meram_resources,
+	.dev		= {
+		.platform_data = &mackerel_meram_info,
+	},
+};
+
 /* LCDC */
 static struct fb_videomode mackerel_lcdc_modes[] = {
 	{
···
 	return gpio_get_value(GPIO_PORT31);
 }
 
+static struct sh_mobile_meram_cfg lcd_meram_cfg = {
+	.icb[0] = {
+		.marker_icb     = 28,
+		.cache_icb      = 24,
+		.meram_offset   = 0x0,
+		.meram_size     = 0x40,
+	},
+	.icb[1] = {
+		.marker_icb     = 29,
+		.cache_icb      = 25,
+		.meram_offset   = 0x40,
+		.meram_size     = 0x40,
+	},
+};
+
 static struct sh_mobile_lcdc_info lcdc_info = {
+	.meram_dev = &mackerel_meram_info,
 	.clock_source = LCDC_CLK_BUS,
 	.ch[0] = {
 		.chan = LCDC_CHAN_MAINLCD,
···
 			.name = "sh_mobile_lcdc_bl",
 			.max_brightness = 1,
 		},
+		.meram_cfg = &lcd_meram_cfg,
 	}
 };
 
···
 	},
 };
 
+static struct sh_mobile_meram_cfg hdmi_meram_cfg = {
+	.icb[0] = {
+		.marker_icb     = 30,
+		.cache_icb      = 26,
+		.meram_offset   = 0x80,
+		.meram_size     = 0x100,
+	},
+	.icb[1] = {
+		.marker_icb     = 31,
+		.cache_icb      = 27,
+		.meram_offset   = 0x180,
+		.meram_size     = 0x100,
+	},
+};
 /* HDMI */
 static struct sh_mobile_lcdc_info hdmi_lcdc_info = {
+	.meram_dev = &mackerel_meram_info,
 	.clock_source = LCDC_CLK_EXTERNAL,
 	.ch[0] = {
 		.chan = LCDC_CHAN_MAINLCD,
···
 		.interface_type = RGB24,
 		.clock_divider = 1,
 		.flags = LCDC_FLAGS_DWPOL,
+		.meram_cfg = &hdmi_meram_cfg,
 	}
 };
 
···
 }
 
 /* SDHI0 */
+static irqreturn_t mackerel_sdhi0_gpio_cd(int irq, void *arg)
+{
+	struct device *dev = arg;
+	struct sh_mobile_sdhi_info *info = dev->platform_data;
+	struct tmio_mmc_data *pdata = info->pdata;
+
+	tmio_mmc_cd_wakeup(pdata);
+
+	return IRQ_HANDLED;
+}
+
 static struct sh_mobile_sdhi_info sdhi0_info = {
 	.dma_slave_tx	= SHDMA_SLAVE_SDHI0_TX,
 	.dma_slave_rx	= SHDMA_SLAVE_SDHI0_RX,
···
 	&mackerel_camera,
 	&hdmi_lcdc_device,
 	&hdmi_device,
+	&meram_device,
 };
 
 /* Keypad Initialization */
···
 {
 	u32 srcr4;
 	struct clk *clk;
+	int ret;
 
 	sh7372_pinmux_init();
 
···
 	gpio_request(GPIO_FN_SDHID0_2, NULL);
 	gpio_request(GPIO_FN_SDHID0_1, NULL);
 	gpio_request(GPIO_FN_SDHID0_0, NULL);
+
+	ret = request_irq(evt2irq(0x3340), mackerel_sdhi0_gpio_cd,
+			  IRQF_TRIGGER_FALLING, "sdhi0 cd", &sdhi0_device.dev);
+	if (!ret)
+		sdhi0_info.tmio_flags |= TMIO_MMC_HAS_COLD_CD;
+	else
+		pr_err("Cannot get IRQ #%d: %d\n", evt2irq(0x3340), ret);
 
 #if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE)
 	/* enable SDHI1 */

arch/arm/mach-shmobile/clock-sh7372.c

···
        MSTP118, MSTP117, MSTP116, MSTP113,
        MSTP106, MSTP101, MSTP100,
        MSTP223,
+       MSTP218, MSTP217, MSTP216,
        MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
        MSTP329, MSTP328, MSTP323, MSTP322, MSTP314, MSTP313, MSTP312,
        MSTP423, MSTP415, MSTP413, MSTP411, MSTP410, MSTP406, MSTP403,
···
 	[MSTP101] = MSTP(&div4_clks[DIV4_M1], SMSTPCR1, 1, 0), /* VPU */
 	[MSTP100] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 0, 0), /* LCDC0 */
 	[MSTP223] = MSTP(&div6_clks[DIV6_SPU], SMSTPCR2, 23, 0), /* SPU2 */
+	[MSTP218] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 18, 0), /* DMAC1 */
+	[MSTP217] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 17, 0), /* DMAC2 */
+	[MSTP216] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 16, 0), /* DMAC3 */
 	[MSTP207] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 7, 0), /* SCIFA5 */
 	[MSTP206] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 6, 0), /* SCIFB */
 	[MSTP204] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 4, 0), /* SCIFA0 */
···
 	CLKDEV_DEV_ID("sh_mobile_lcdc_fb.0", &mstp_clks[MSTP100]), /* LCDC0 */
 	CLKDEV_DEV_ID("uio_pdrv_genirq.6", &mstp_clks[MSTP223]), /* SPU2DSP0 */
 	CLKDEV_DEV_ID("uio_pdrv_genirq.7", &mstp_clks[MSTP223]), /* SPU2DSP1 */
+	CLKDEV_DEV_ID("sh-dma-engine.0", &mstp_clks[MSTP218]), /* DMAC1 */
+	CLKDEV_DEV_ID("sh-dma-engine.1", &mstp_clks[MSTP217]), /* DMAC2 */
+	CLKDEV_DEV_ID("sh-dma-engine.2", &mstp_clks[MSTP216]), /* DMAC3 */
 	CLKDEV_DEV_ID("sh-sci.5", &mstp_clks[MSTP207]), /* SCIFA5 */
 	CLKDEV_DEV_ID("sh-sci.6", &mstp_clks[MSTP206]), /* SCIFB */
 	CLKDEV_DEV_ID("sh-sci.0", &mstp_clks[MSTP204]), /* SCIFA0 */

arch/arm/mach-tegra/board-harmony-power.c

···
 
 #include <mach/irqs.h>
 
+#include "board-harmony.h"
+
 #define PMC_CTRL		0x0
 #define PMC_CTRL_INTR_LOW	(1 << 17)
 
···
 	.irq_base	= TEGRA_NR_IRQS,
 	.num_subdevs	= ARRAY_SIZE(tps_devs),
 	.subdevs	= tps_devs,
-	.gpio_base	= TEGRA_NR_GPIOS,
+	.gpio_base	= HARMONY_GPIO_TPS6586X(0),
 };
 
 static struct i2c_board_info __initdata harmony_regulators[] = {

arch/arm/mach-tegra/board-harmony.h

···
 #ifndef _MACH_TEGRA_BOARD_HARMONY_H
 #define _MACH_TEGRA_BOARD_HARMONY_H
 
-#define HARMONY_GPIO_WM8903(_x_)	(TEGRA_NR_GPIOS + (_x_))
+#define HARMONY_GPIO_TPS6586X(_x_)	(TEGRA_NR_GPIOS + (_x_))
+#define HARMONY_GPIO_WM8903(_x_)	(HARMONY_GPIO_TPS6586X(4) + (_x_))
 
 #define TEGRA_GPIO_SD2_CD		TEGRA_GPIO_PI5
 #define TEGRA_GPIO_SD2_WP		TEGRA_GPIO_PH1

arch/blackfin/lib/strncpy.S

···
 
 ENTRY(_strncpy)
 	CC = R2 == 0;
-	if CC JUMP 4f;
+	if CC JUMP 6f;
 
 	P2 = R2 ;       /* size */
 	P0 = R0 ;       /* dst*/

arch/ia64/include/asm/unistd.h

···
 #define __NR_clock_adjtime		1328
 #define __NR_syncfs			1329
 #define __NR_setns			1330
+#define __NR_sendmmsg			1331
 
 #ifdef __KERNEL__
 
 
-#define NR_syscalls			307 /* length of syscall table */
+#define NR_syscalls			308 /* length of syscall table */
 
 /*
  * The following defines stop scripts/checksyscalls.sh from complaining about

arch/ia64/kernel/entry.S

···
 	data8 sys_clock_adjtime
 	data8 sys_syncfs
 	data8 sys_setns				// 1330
+	data8 sys_sendmmsg
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
 #endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */

arch/powerpc/platforms/powermac/pic.c

···
 
 static int __init init_pmacpic_syscore(void)
 {
-	register_syscore_ops(&pmacpic_syscore_ops);
+	if (pmac_irq_hw[0])
+		register_syscore_ops(&pmacpic_syscore_ops);
 	return 0;
 }
 

arch/sh/Kconfig

···
 
 config NO_IOPORT
 	def_bool !PCI
-	depends on !SH_CAYMAN && !SH_SH4202_MICRODEV
+	depends on !SH_CAYMAN && !SH_SH4202_MICRODEV && !SH_SHMIN
 
 config IO_TRAPPED
 	bool

arch/sh/boards/mach-ap325rxa/setup.c

···
 	.priv		= &camera_info,
 };
 
-static void dummy_release(struct device *dev)
-{
-}
+static struct platform_device *camera_device;
 
-static struct platform_device camera_device = {
-	.name		= "soc_camera_platform",
-	.dev		= {
-		.platform_data	= &camera_info,
-		.release	= dummy_release,
-	},
-};
+static void ap325rxa_camera_release(struct device *dev)
+{
+	soc_camera_platform_release(&camera_device);
+}
 
 static int ap325rxa_camera_add(struct soc_camera_link *icl,
 			       struct device *dev)
 {
-	if (icl != &camera_link || camera_probe() <= 0)
-		return -ENODEV;
+	int ret = soc_camera_platform_add(icl, dev, &camera_device, &camera_link,
+					  ap325rxa_camera_release, 0);
+	if (ret < 0)
+		return ret;
 
-	camera_info.dev = dev;
+	ret = camera_probe();
+	if (ret < 0)
+		soc_camera_platform_del(icl, camera_device, &camera_link);
 
-	return platform_device_register(&camera_device);
+	return ret;
 }
 
 static void ap325rxa_camera_del(struct soc_camera_link *icl)
 {
-	if (icl != &camera_link)
-		return;
-
-	platform_device_unregister(&camera_device);
-	memset(&camera_device.dev.kobj, 0,
-	       sizeof(camera_device.dev.kobj));
+	soc_camera_platform_del(icl, camera_device, &camera_link);
 }
 #endif /* CONFIG_I2C */
 

arch/sh/boards/mach-ecovec24/setup.c

···
 	},
 	.num_resources	= ARRAY_SIZE(sh_mmcif_resources),
 	.resource	= sh_mmcif_resources,
+	.archdata = {
+		.hwblk_id = HWBLK_MMC,
+	},
 };
 #endif
 

arch/sh/include/asm/pgtable.h

···
 #include <asm/pgtable-2level.h>
 #endif
 #include <asm/page.h>
+#include <asm/mmu.h>
 
 #ifndef __ASSEMBLY__
 #include <asm/addrspace.h>

arch/sh/include/asm/ptrace.h

···
 
 #define user_mode(regs)			(((regs)->sr & 0x40000000)==0)
 #define kernel_stack_pointer(_regs)	((unsigned long)(_regs)->regs[15])
-#define GET_USP(regs) ((regs)->regs[15])
+
+#define GET_FP(regs)	((regs)->regs[14])
+#define GET_USP(regs)	((regs)->regs[15])
 
 extern void show_regs(struct pt_regs *);
 
···
 
 static inline unsigned long profile_pc(struct pt_regs *regs)
 {
-	unsigned long pc = instruction_pointer(regs);
+	unsigned long pc = regs->pc;
 
 	if (virt_addr_uncached(pc))
 		return CAC_ADDR(pc);

arch/sh/include/asm/tlb.h

···
 #include <linux/pagemap.h>
 
 #ifdef CONFIG_MMU
+#include <linux/swap.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>

arch/sh/include/cpu-sh4/cpu/sh7722.h

···
 };
 
 enum {
+	SHDMA_SLAVE_INVALID,
 	SHDMA_SLAVE_SCIF0_TX,
 	SHDMA_SLAVE_SCIF0_RX,
 	SHDMA_SLAVE_SCIF1_TX,

arch/sh/include/cpu-sh4/cpu/sh7724.h

···
 };
 
 enum {
+	SHDMA_SLAVE_INVALID,
 	SHDMA_SLAVE_SCIF0_TX,
 	SHDMA_SLAVE_SCIF0_RX,
 	SHDMA_SLAVE_SCIF1_TX,

arch/sh/include/cpu-sh4/cpu/sh7757.h

···
 };
 
 enum {
+	SHDMA_SLAVE_INVALID,
 	SHDMA_SLAVE_SDHI_TX,
 	SHDMA_SLAVE_SDHI_RX,
 	SHDMA_SLAVE_MMCIF_TX,

arch/sh/kernel/process_32.c

···
 #include <linux/fs.h>
 #include <linux/ftrace.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/prefetch.h>
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/system.h>

arch/sh/mm/consistent.c

···
 	void *addr;
 
 	addr = __in_29bit_mode() ?
-	       (void *)P1SEGADDR((unsigned long)vaddr) : vaddr;
+	       (void *)CAC_ADDR((unsigned long)vaddr) : vaddr;
 
 	switch (direction) {
 	case DMA_FROM_DEVICE:		/* invalidate only */

arch/x86/kernel/Makefile

···
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not profile debug and lowlevel utilities
+CFLAGS_REMOVE_tsc.o = -pg
 CFLAGS_REMOVE_rtc.o = -pg
 CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
 CFLAGS_REMOVE_pvclock.o = -pg
···
 GCOV_PROFILE_vsyscall_64.o	:= n
 GCOV_PROFILE_hpet.o		:= n
 GCOV_PROFILE_tsc.o		:= n
+GCOV_PROFILE_vread_tsc_64.o	:= n
 GCOV_PROFILE_paravirt.o		:= n
 
 # vread_tsc_64 is hot and should be fully optimized:

arch/x86/kernel/process.c

···
 		boot_option_idle_override = IDLE_POLL;
 	} else if (!strcmp(str, "mwait")) {
 		boot_option_idle_override = IDLE_FORCE_MWAIT;
-		WARN_ONCE(1, "\idle=mwait\" will be removed in 2012\"\n");
+		WARN_ONCE(1, "\"idle=mwait\" will be removed in 2012\n");
 	} else if (!strcmp(str, "halt")) {
 		/*
 		 * When the boot option of idle=halt is added, halt is

arch/x86/kernel/smpboot.c

···
 	void *mwait_ptr;
 	struct cpuinfo_x86 *c = __this_cpu_ptr(&cpu_info);
 
-	if (!this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c))
+	if (!(this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c)))
 		return;
 	if (!this_cpu_has(X86_FEATURE_CLFLSH))
 		return;

arch/x86/lguest/boot.c

···
 static void lguest_time_init(void)
 {
 	/* Set up the timer interrupt (0) to go to our simple timer routine */
+	lguest_setup_irq(0);
 	irq_set_handler(0, lguest_time_irq);
 
 	clocksource_register_hz(&lguest_clock, NSEC_PER_SEC);

block/blk-ioc.c

···
 	if (!hlist_empty(&ioc->cic_list)) {
 		struct cfq_io_context *cic;
 
-		cic = list_entry(ioc->cic_list.first, struct cfq_io_context,
+		cic = hlist_entry(ioc->cic_list.first, struct cfq_io_context,
 								cic_list);
 		cic->dtor(ioc);
 	}
···
 	if (!hlist_empty(&ioc->cic_list)) {
 		struct cfq_io_context *cic;
 
-		cic = list_entry(ioc->cic_list.first, struct cfq_io_context,
+		cic = hlist_entry(ioc->cic_list.first, struct cfq_io_context,
 								cic_list);
 		cic->exit(ioc);
 	}

block/cfq-iosched.c

···
 	int nr_cfqq;
 
 	/*
-	 * Per group busy queus average. Useful for workload slice calc. We
+	 * Per group busy queues average. Useful for workload slice calc. We
 	 * create the array for each prio class but at run time it is used
 	 * only for RT and BE class and slot for IDLE class remains unused.
 	 * This is primarily done to avoid confusion and a gcc warning.
···
 #define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
 	blk_add_trace_msg((cfqd)->queue, "cfq%d%c %s " fmt, (cfqq)->pid, \
 			cfq_cfqq_sync((cfqq)) ? 'S' : 'A', \
-			blkg_path(&(cfqq)->cfqg->blkg), ##args);
+			blkg_path(&(cfqq)->cfqg->blkg), ##args)
 
 #define cfq_log_cfqg(cfqd, cfqg, fmt, args...)				\
 	blk_add_trace_msg((cfqd)->queue, "%s " fmt,			\
-				blkg_path(&(cfqg)->blkg), ##args);      \
+				blkg_path(&(cfqg)->blkg), ##args)       \
 
 #else
 #define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
 	blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args)
-#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)		do {} while (0);
+#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)		do {} while (0)
 #endif
 #define cfq_log(cfqd, fmt, args...)	\
 	blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
···
 	return 0;
 
 queue_fail:
-	if (cic)
-		put_io_context(cic->ioc);
-
 	cfq_schedule_dispatch(cfqd);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 	cfq_log(cfqd, "set_request fail");

drivers/block/nbd.c

···
 			if (lo->xmit_timeout)
 				del_timer_sync(&ti);
 		} else
-			result = kernel_recvmsg(sock, &msg, &iov, 1, size, 0);
+			result = kernel_recvmsg(sock, &msg, &iov, 1, size,
+						msg.msg_flags);
 
 		if (signal_pending(current)) {
 			siginfo_t info;
···
 		return -ENOMEM;
 
 	part_shift = 0;
-	if (max_part > 0)
+	if (max_part > 0) {
 		part_shift = fls(max_part);
+
+		/*
+		 * Adjust max_part according to part_shift as it is exported
+		 * to user space so that user can know the max number of
+		 * partition kernel should be able to manage.
+		 *
+		 * Note that -1 is required because partition 0 is reserved
+		 * for the whole disk.
+		 */
+		max_part = (1UL << part_shift) - 1;
+	}
+
+	if ((1UL << part_shift) > DISK_MAX_PARTS)
+		return -EINVAL;
+
+	if (nbds_max > 1UL << (MINORBITS - part_shift))
+		return -EINVAL;
 
 	for (i = 0; i < nbds_max; i++) {
 		struct gendisk *disk = alloc_disk(1 << part_shift);

drivers/block/paride/pcd.c

···
 		strcpy(disk->disk_name, cd->name);	/* umm... */
 		disk->fops = &pcd_bdops;
 		disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
-		disk->events = DISK_EVENT_MEDIA_CHANGE;
 	}
 }
 

drivers/block/virtio_blk.c

···
 #include <linux/virtio.h>
 #include <linux/virtio_blk.h>
 #include <linux/scatterlist.h>
+#include <linux/string_helpers.h>
+#include <scsi/scsi_cmnd.h>
 
 #define PART_BITS 4
 
 static int major, index;
+struct workqueue_struct *virtblk_wq;
 
 struct virtio_blk
 {
···
 	struct list_head reqs;
 
 	mempool_t *pool;
+
+	/* Process context for config space updates */
+	struct work_struct config_work;
 
 	/* What host tells us, plus 2 for header & tailer. */
 	unsigned int sg_elems;
···
 	num = blk_rq_map_sg(q, vbr->req, vblk->sg + out);
 
 	if (vbr->req->cmd_type == REQ_TYPE_BLOCK_PC) {
-		sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, 96);
+		sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
 		sg_set_buf(&vblk->sg[num + out + in++], &vbr->in_hdr,
 			   sizeof(vbr->in_hdr));
 	}
···
 }
 DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL);
 
+static void virtblk_config_changed_work(struct work_struct *work)
+{
+	struct virtio_blk *vblk =
+		container_of(work, struct virtio_blk, config_work);
+	struct virtio_device *vdev = vblk->vdev;
+	struct request_queue *q = vblk->disk->queue;
+	char cap_str_2[10], cap_str_10[10];
+	u64 capacity, size;
+
+	/* Host must always specify the capacity. */
+	vdev->config->get(vdev, offsetof(struct virtio_blk_config, capacity),
+			  &capacity, sizeof(capacity));
+
+	/* If capacity is too big, truncate with warning. */
+	if ((sector_t)capacity != capacity) {
+		dev_warn(&vdev->dev, "Capacity %llu too large: truncating\n",
+			 (unsigned long long)capacity);
+		capacity = (sector_t)-1;
+	}
+
+	size = capacity * queue_logical_block_size(q);
+	string_get_size(size, STRING_UNITS_2, cap_str_2, sizeof(cap_str_2));
+	string_get_size(size, STRING_UNITS_10, cap_str_10, sizeof(cap_str_10));
+
+	dev_notice(&vdev->dev,
+		  "new size: %llu %d-byte logical blocks (%s/%s)\n",
+		  (unsigned long long)capacity,
+		  queue_logical_block_size(q),
+		  cap_str_10, cap_str_2);
+
+	set_capacity(vblk->disk, capacity);
+}
+
+static void virtblk_config_changed(struct virtio_device *vdev)
+{
+	struct virtio_blk *vblk = vdev->priv;
+
+	queue_work(virtblk_wq, &vblk->config_work);
+}
+
 static int __devinit virtblk_probe(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk;
···
 	vblk->vdev = vdev;
 	vblk->sg_elems = sg_elems;
 	sg_init_table(vblk->sg, vblk->sg_elems);
+	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
 
 	/* We expect one virtqueue, for output. */
 	vblk->vq = virtio_find_single_vq(vdev, blk_done, "requests");
···
 {
 	struct virtio_blk *vblk = vdev->priv;
 
+	flush_work(&vblk->config_work);
+
 	/* Nothing should be pending. */
 	BUG_ON(!list_empty(&vblk->reqs));
 
···
  * Use __refdata to avoid this warning.
  */
 static struct virtio_driver __refdata virtio_blk = {
-	.feature_table = features,
-	.feature_table_size = ARRAY_SIZE(features),
-	.driver.name =	KBUILD_MODNAME,
-	.driver.owner =	THIS_MODULE,
-	.id_table =	id_table,
-	.probe =	virtblk_probe,
-	.remove =	__devexit_p(virtblk_remove),
+	.feature_table		= features,
+	.feature_table_size	= ARRAY_SIZE(features),
+	.driver.name		= KBUILD_MODNAME,
+	.driver.owner		= THIS_MODULE,
+	.id_table		= id_table,
+	.probe			= virtblk_probe,
+	.remove			= __devexit_p(virtblk_remove),
+	.config_changed		= virtblk_config_changed,
 };
 
 static int __init init(void)
 {
+	int error;
+
+	virtblk_wq = alloc_workqueue("virtio-blk", 0, 0);
+	if (!virtblk_wq)
+		return -ENOMEM;
+
 	major = register_blkdev(0, "virtblk");
-	if (major < 0)
-		return major;
-	return register_virtio_driver(&virtio_blk);
+	if (major < 0) {
+		error = major;
+		goto out_destroy_workqueue;
+	}
+
+	error = register_virtio_driver(&virtio_blk);
+	if (error)
+		goto out_unregister_blkdev;
+	return 0;
+
+out_unregister_blkdev:
+	unregister_blkdev(major, "virtblk");
+out_destroy_workqueue:
+	destroy_workqueue(virtblk_wq);
+	return error;
 }
 
 static void __exit fini(void)
 {
 	unregister_blkdev(major, "virtblk");
 	unregister_virtio_driver(&virtio_blk);
+	destroy_workqueue(virtblk_wq);
 }
 module_init(init);
 module_exit(fini);

drivers/block/xen-blkback/blkback.c

···
  failed_init:
 	kfree(blkbk->pending_reqs);
 	kfree(blkbk->pending_grant_handles);
-	for (i = 0; i < mmap_pages; i++) {
-		if (blkbk->pending_pages[i])
-			__free_page(blkbk->pending_pages[i]);
+	if (blkbk->pending_pages) {
+		for (i = 0; i < mmap_pages; i++) {
+			if (blkbk->pending_pages[i])
+				__free_page(blkbk->pending_pages[i]);
+		}
+		kfree(blkbk->pending_pages);
 	}
-	kfree(blkbk->pending_pages);
 	kfree(blkbk);
 	blkbk = NULL;
 	return rc;

drivers/block/xen-blkback/xenbus.c

···
 	}
 
 	vbd->bdev = bdev;
-	vbd->size = vbd_sz(vbd);
-
 	if (vbd->bdev->bd_disk == NULL) {
 		DPRINTK("xen_vbd_create: device %08x doesn't exist.\n",
 			vbd->pdevice);
 		xen_vbd_free(vbd);
 		return -ENOENT;
 	}
+	vbd->size = vbd_sz(vbd);
 
 	if (vbd->bdev->bd_disk->flags & GENHD_FL_CD || cdrom)
 		vbd->type |= VDISK_CDROM;

drivers/bluetooth/hci_ldisc.c

···
  *             flags        pointer to flags for data
  *             count        count of received data in bytes
  *     
- * Return Value:    Number of bytes received
+ * Return Value:    None
  */
-static unsigned int hci_uart_tty_receive(struct tty_struct *tty,
-		const u8 *data, char *flags, int count)
+static void hci_uart_tty_receive(struct tty_struct *tty, const u8 *data, char *flags, int count)
 {
 	struct hci_uart *hu = (void *)tty->disc_data;
-	int received;
 
 	if (!hu || tty != hu->tty)
-		return -ENODEV;
+		return;
 
 	if (!test_bit(HCI_UART_PROTO_SET, &hu->flags))
-		return -EINVAL;
+		return;
 
 	spin_lock(&hu->rx_lock);
-	received = hu->proto->recv(hu, (void *) data, count);
-	if (received > 0)
-		hu->hdev->stat.byte_rx += received;
+	hu->proto->recv(hu, (void *) data, count);
+	hu->hdev->stat.byte_rx += count;
 	spin_unlock(&hu->rx_lock);
 
 	tty_unthrottle(tty);
-
-	return received;
 }
 
 static int hci_uart_register_dev(struct hci_uart *hu)

drivers/cdrom/viocd.c

···
 	gendisk->fops = &viocd_fops;
 	gendisk->flags = GENHD_FL_CD | GENHD_FL_REMOVABLE |
 			 GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
-	gendisk->events = DISK_EVENT_MEDIA_CHANGE;
 	set_capacity(gendisk, 0);
 	gendisk->private_data = d;
 	d->viocd_disk = gendisk;

drivers/char/virtio_console.c

···
 	portdev->config.max_nr_ports = 1;
 	if (virtio_has_feature(vdev, VIRTIO_CONSOLE_F_MULTIPORT)) {
 		multiport = true;
-		vdev->features[0] |= 1 << VIRTIO_CONSOLE_F_MULTIPORT;
-
 		vdev->config->get(vdev, offsetof(struct virtio_console_config,
 						 max_nr_ports),
 				  &portdev->config.max_nr_ports,
 				  sizeof(portdev->config.max_nr_ports));
 	}
-
-	/* Let the Host know we support multiple ports.*/
-	vdev->config->finalize_features(vdev);
 
 	err = init_vqs(portdev);
 	if (err < 0) {

drivers/clocksource/sh_cmt.c

···
 #include <linux/ioport.h>
 #include <linux/io.h>
 #include <linux/clk.h>
-#include <linux/pm_runtime.h>
 #include <linux/irq.h>
 #include <linux/err.h>
 #include <linux/clocksource.h>
···
 {
 	int ret;
 
-	/* wake up device and enable clock */
-	pm_runtime_get_sync(&p->pdev->dev);
+	/* enable clock */
 	ret = clk_enable(p->clk);
 	if (ret) {
 		dev_err(&p->pdev->dev, "cannot enable clock\n");
-		pm_runtime_put_sync(&p->pdev->dev);
 		return ret;
 	}
 
···
 	/* disable interrupts in CMT block */
 	sh_cmt_write(p, CMCSR, 0);
 
-	/* stop clock and mark device as idle */
+	/* stop clock */
 	clk_disable(p->clk);
-	pm_runtime_put_sync(&p->pdev->dev);
 }
 
 /* private flags */
···
 
 	if (p) {
 		dev_info(&pdev->dev, "kept as earlytimer\n");
-		pm_runtime_enable(&pdev->dev);
 		return 0;
 	}
 
···
 		kfree(p);
 		platform_set_drvdata(pdev, NULL);
 	}
-
-	if (!is_early_platform_device(pdev))
-		pm_runtime_enable(&pdev->dev);
 	return ret;
 }
 

drivers/clocksource/sh_tmu.c

···
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/clk.h>
-#include <linux/pm_runtime.h>
 #include <linux/irq.h>
 #include <linux/err.h>
 #include <linux/clocksource.h>
···
 {
 	int ret;
 
-	/* wake up device and enable clock */
-	pm_runtime_get_sync(&p->pdev->dev);
+	/* enable clock */
 	ret = clk_enable(p->clk);
 	if (ret) {
 		dev_err(&p->pdev->dev, "cannot enable clock\n");
-		pm_runtime_put_sync(&p->pdev->dev);
 		return ret;
 	}
 
···
 	/* disable interrupts in TMU block */
 	sh_tmu_write(p, TCR, 0x0000);
 
-	/* stop clock and mark device as idle */
+	/* stop clock */
 	clk_disable(p->clk);
-	pm_runtime_put_sync(&p->pdev->dev);
 }
 
 static void sh_tmu_set_next(struct sh_tmu_priv *p, unsigned long delta,
···
 
 	if (p) {
 		dev_info(&pdev->dev, "kept as earlytimer\n");
-		pm_runtime_enable(&pdev->dev);
 		return 0;
 	}
 
···
 		kfree(p);
 		platform_set_drvdata(pdev, NULL);
 	}
-
-	if (!is_early_platform_device(pdev))
-		pm_runtime_enable(&pdev->dev);
 	return ret;
 }
 

drivers/dma/shdma.c

···
 
 		dmae_set_dmars(sh_chan, cfg->mid_rid);
 		dmae_set_chcr(sh_chan, cfg->chcr);
-	} else if ((sh_dmae_readl(sh_chan, CHCR) & 0xf00) != 0x400) {
+	} else {
 		dmae_init(sh_chan);
 	}
 
···
 	/* platform data */
 	shdev->pdata = pdata;
 
+	platform_set_drvdata(pdev, shdev);
+
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_get_sync(&pdev->dev);
 
···
 
 	pm_runtime_put(&pdev->dev);
 
-	platform_set_drvdata(pdev, shdev);
 	dma_async_device_register(&shdev->common);
 
 	return err;
···
 
 	if (dmars)
 		iounmap(shdev->dmars);
+
+	platform_set_drvdata(pdev, NULL);
 emapdmars:
 	iounmap(shdev->chan_reg);
 	synchronize_rcu();
···
 	if (shdev->dmars)
 		iounmap(shdev->dmars);
 	iounmap(shdev->chan_reg);
+
+	platform_set_drvdata(pdev, NULL);
 
 	synchronize_rcu();
 	kfree(shdev);

drivers/hwmon/coretemp.c

···
 		 * If the TjMax is not plausible, an assumption
 		 * will be used
 		 */
-		if (val > 80 && val < 120) {
+		if (val) {
 			dev_info(dev, "TjMax is %d C.\n", val);
 			return val * 1000;
 		}
···
 
 	/*
 	 * An assumption is made for early CPUs and unreadable MSR.
-	 * NOTE: the given value may not be correct.
+	 * NOTE: the calculated value may not be correct.
 	 */
-
-	switch (c->x86_model) {
-	case 0xe:
-	case 0xf:
-	case 0x16:
-	case 0x1a:
-		dev_warn(dev, "TjMax is assumed as 100 C!\n");
-		return 100000;
-	case 0x17:
-	case 0x1c:		/* Atom CPUs */
-		return adjust_tjmax(c, id, dev);
-	default:
-		dev_warn(dev, "CPU (model=0x%x) is not supported yet,"
-			" using default TjMax of 100C.\n", c->x86_model);
-		return 100000;
-	}
+	return adjust_tjmax(c, id, dev);
 }
 
 static void __devinit get_ucode_rev_on_cpu(void *edx)
···
 	err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
 	if (!err) {
 		val = (eax >> 16) & 0xff;
-		if (val > 80 && val < 120)
+		if (val)
 			return val * 1000;
 	}
 	dev_warn(dev, "Unable to read Pkg-TjMax from CPU:%u\n", cpu);

drivers/hwmon/max6642.c

···
 	if (man_id != 0x4D)
 		return -ENODEV;
 
+	/* sanity check */
+	if (i2c_smbus_read_byte_data(client, 0x04) != 0x4D
+	    || i2c_smbus_read_byte_data(client, 0x06) != 0x4D
+	    || i2c_smbus_read_byte_data(client, 0xff) != 0x4D)
+		return -ENODEV;
+
 	/*
 	 * We read the config and status register, the 4 lower bits in the
 	 * config register should be zero and bit 5, 3, 1 and 0 should be
 	 * zero in the status register.
 	 */
 	reg_config = i2c_smbus_read_byte_data(client, MAX6642_REG_R_CONFIG);
+	if ((reg_config & 0x0f) != 0x00)
+		return -ENODEV;
+
+	/* in between, another round of sanity checks */
+	if (i2c_smbus_read_byte_data(client, 0x04) != reg_config
+	    || i2c_smbus_read_byte_data(client, 0x06) != reg_config
+	    || i2c_smbus_read_byte_data(client, 0xff) != reg_config)
+		return -ENODEV;
+
 	reg_status = i2c_smbus_read_byte_data(client, MAX6642_REG_R_STATUS);
-	if (((reg_config & 0x0f) != 0x00) ||
-	    ((reg_status & 0x2b) != 0x00))
+	if ((reg_status & 0x2b) != 0x00)
 		return -ENODEV;
 
 	strlcpy(info->type, "max6642", I2C_NAME_SIZE);
···
 			    set_temp_max, 0, MAX6642_REG_W_LOCAL_HIGH);
 static SENSOR_DEVICE_ATTR_2(temp2_max, S_IWUSR | S_IRUGO, show_temp_max,
 			    set_temp_max, 1, MAX6642_REG_W_REMOTE_HIGH);
-static SENSOR_DEVICE_ATTR(temp_fault, S_IRUGO, show_alarm, NULL, 2);
+static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 2);
 static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, show_alarm, NULL, 6);
 static SENSOR_DEVICE_ATTR(temp2_max_alarm, S_IRUGO, show_alarm, NULL, 4);
 
···
 	&sensor_dev_attr_temp1_max.dev_attr.attr,
 	&sensor_dev_attr_temp2_max.dev_attr.attr,
 
-	&sensor_dev_attr_temp_fault.dev_attr.attr,
+	&sensor_dev_attr_temp2_fault.dev_attr.attr,
 	&sensor_dev_attr_temp1_max_alarm.dev_attr.attr,
 	&sensor_dev_attr_temp2_max_alarm.dev_attr.attr,
 	NULL

drivers/ide/ide-cd.c

···
 	ide_cd_read_toc(drive, &sense);
 	g->fops = &idecd_ops;
 	g->flags |= GENHD_FL_REMOVABLE | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
-	g->events = DISK_EVENT_MEDIA_CHANGE;
 	add_disk(g);
 	return 0;
 

drivers/input/serio/serport.c

···
  * 'interrupt' routine.
  */
 
-static unsigned int serport_ldisc_receive(struct tty_struct *tty,
-		const unsigned char *cp, char *fp, int count)
+static void serport_ldisc_receive(struct tty_struct *tty, const unsigned char *cp, char *fp, int count)
 {
 	struct serport *serport = (struct serport*) tty->disc_data;
 	unsigned long flags;
 	unsigned int ch_flags;
-	int ret = 0;
 	int i;
 
 	spin_lock_irqsave(&serport->lock, flags);
 
-	if (!test_bit(SERPORT_ACTIVE, &serport->flags)) {
-		ret = -EINVAL;
+	if (!test_bit(SERPORT_ACTIVE, &serport->flags))
 		goto out;
-	}
 
 	for (i = 0; i < count; i++) {
 		switch (fp[i]) {
···
 
 out:
 	spin_unlock_irqrestore(&serport->lock, flags);
-
-	return ret == 0 ? count : ret;
 }
 
 /*

drivers/isdn/gigaset/ser-gigaset.c

···
  *	cflags	buffer containing error flags for received characters (ignored)
  *	count	number of received characters
  */
-static unsigned int
+static void
 gigaset_tty_receive(struct tty_struct *tty, const unsigned char *buf,
 		    char *cflags, int count)
 {
···
 	struct inbuf_t *inbuf;
 
 	if (!cs)
-		return -ENODEV;
+		return;
 	inbuf = cs->inbuf;
 	if (!inbuf) {
 		dev_err(cs->dev, "%s: no inbuf\n", __func__);
 		cs_put(cs);
-		return -EINVAL;
+		return;
 	}
 
 	tail = inbuf->tail;
···
 	gig_dbg(DEBUG_INTR, "%s-->BH", __func__);
 	gigaset_schedule_event(cs);
 	cs_put(cs);
-
-	return count;
 }
 
 /*

drivers/misc/kgdbts.c

···
 		return 1;
 	}
 	/* Readjust the instruction pointer if needed */
-	instruction_pointer_set(&kgdbts_regs, ip + offset);
+	ip += offset;
+#ifdef GDB_ADJUSTS_BREAK_OFFSET
+	instruction_pointer_set(&kgdbts_regs, ip);
+#endif
 	return 0;
 }
 

drivers/misc/ti-st/st_core.c

···
 	pr_debug("%s: done ", __func__);
 }
 
-static unsigned int st_tty_receive(struct tty_struct *tty,
-		const unsigned char *data, char *tty_flags, int count)
+static void st_tty_receive(struct tty_struct *tty, const unsigned char *data,
+			   char *tty_flags, int count)
 {
 #ifdef VERBOSE
 	print_hex_dump(KERN_DEBUG, ">in>", DUMP_PREFIX_NONE,
···
 	 */
 	st_recv(tty->disc_data, data, count);
 	pr_debug("done %s", __func__);
-
-	return count;
 }
 
 /* wake-up function called in from the TTY layer

drivers/net/3c509.c

···
 static int nopnp;
 #endif
 
-static int el3_common_init(struct net_device *dev);
+static int __devinit el3_common_init(struct net_device *dev);
 static void el3_common_remove(struct net_device *dev);
 static ushort id_read_eeprom(int index);
 static ushort read_eeprom(int ioaddr, int index);
···
 static int isa_registered;
 
 #ifdef CONFIG_PNP
-static const struct pnp_device_id el3_pnp_ids[] __devinitconst = {
+static struct pnp_device_id el3_pnp_ids[] = {
 	{ .id = "TCM5090" }, /* 3Com Etherlink III (TP) */
 	{ .id = "TCM5091" }, /* 3Com Etherlink III */
 	{ .id = "TCM5094" }, /* 3Com Etherlink III (combo) */
···
 #endif /* CONFIG_PNP */
 
 #ifdef CONFIG_EISA
-static const struct eisa_device_id el3_eisa_ids[] __devinitconst = {
+static struct eisa_device_id el3_eisa_ids[] = {
 		{ "TCM5090" },
 		{ "TCM5091" },
 		{ "TCM5092" },
···
 #ifdef CONFIG_MCA
 static int el3_mca_probe(struct device *dev);
 
-static const short el3_mca_adapter_ids[] __devinitconst = {
+static short el3_mca_adapter_ids[] __initdata = {
 		0x627c,
 		0x627d,
 		0x62db,
···
 		0x0000
 };
 
-static const char *const el3_mca_adapter_names[] __devinitconst = {
+static char *el3_mca_adapter_names[] __initdata = {
 		"3Com 3c529 EtherLink III (10base2)",
 		"3Com 3c529 EtherLink III (10baseT)",
 		"3Com 3c529 EtherLink III (test mode)",
···
 }
 
 #ifdef CONFIG_MCA
-static int __devinit el3_mca_probe(struct device *device)
+static int __init el3_mca_probe(struct device *device)
 {
 	/* Based on Erik Nygren's ([e-mail]) 3c529 patch,
 	 * heavily modified by Chris Beauregard
···
 #endif /* CONFIG_MCA */
 
 #ifdef CONFIG_EISA
-static int __devinit el3_eisa_probe (struct device *device)
+static int __init el3_eisa_probe (struct device *device)
 {
 	short i;
 	int ioaddr, irq, if_port;

drivers/net/3c59x.c

···
 #endif /* !CONFIG_PM */
 
 #ifdef CONFIG_EISA
-static const struct eisa_device_id vortex_eisa_ids[] __devinitconst = {
+static struct eisa_device_id vortex_eisa_ids[] = {
 	{ "TCM5920", CH_3C592 },
 	{ "TCM5970", CH_3C597 },
 	{ "" }
 };
 MODULE_DEVICE_TABLE(eisa, vortex_eisa_ids);
 
-static int __devinit vortex_eisa_probe(struct device *device)
+static int __init vortex_eisa_probe(struct device *device)
 {
 	void __iomem *ioaddr;
 	struct eisa_device *edev;

drivers/net/caif/caif_serial.c

···
 
 #endif
 
-static unsigned int ldisc_receive(struct tty_struct *tty,
-		const u8 *data, char *flags, int count)
+static void ldisc_receive(struct tty_struct *tty, const u8 *data,
+			char *flags, int count)
 {
 	struct sk_buff *skb = NULL;
 	struct ser_device *ser;
···
 	} else
 		++ser->dev->stats.rx_dropped;
 	update_tty_status(ser);
-
-	return count;
 }
 
 static int handle_tx(struct ser_device *ser)

drivers/net/can/flexcan.c

···
 	mem_size = resource_size(mem);
 	if (!request_mem_region(mem->start, mem_size, pdev->name)) {
 		err = -EBUSY;
-		goto failed_req;
+		goto failed_get;
 	}
 
 	base = ioremap(mem->start, mem_size);
···
 	iounmap(base);
  failed_map:
 	release_mem_region(mem->start, mem_size);
- failed_req:
-	clk_put(clk);
  failed_get:
+	clk_put(clk);
  failed_clock:
 	return err;
 }

drivers/net/can/slcan.c

···
  * in parallel
  */
 
-static unsigned int slcan_receive_buf(struct tty_struct *tty,
+static void slcan_receive_buf(struct tty_struct *tty,
 			      const unsigned char *cp, char *fp, int count)
 {
 	struct slcan *sl = (struct slcan *) tty->disc_data;
-	int bytes = count;
 
 	if (!sl || sl->magic != SLCAN_MAGIC || !netif_running(sl->dev))
-		return -ENODEV;
+		return;
 
 	/* Read the characters out of the buffer */
-	while (bytes--) {
+	while (count--) {
 		if (fp && *fp++) {
 			if (!test_and_set_bit(SLF_ERROR, &sl->flags))
 				sl->dev->stats.rx_errors++;
···
 		}
 		slcan_unesc(sl, *cp++);
 	}
-
-	return count;
 }
 
 /************************************

drivers/net/davinci_emac.c

···
 	ndev = alloc_etherdev(sizeof(struct emac_priv));
 	if (!ndev) {
 		dev_err(&pdev->dev, "error allocating net_device\n");
-		clk_put(emac_clk);
-		return -ENOMEM;
+		rc = -ENOMEM;
+		goto free_clk;
 	}
 
 	platform_set_drvdata(pdev, ndev);
···
 	pdata = pdev->dev.platform_data;
 	if (!pdata) {
 		dev_err(&pdev->dev, "no platform data\n");
-		return -ENODEV;
+		rc = -ENODEV;
+		goto probe_quit;
 	}
 
 	/* MAC addr and PHY mask , RMII enable info from platform_data */
···
 	iounmap(priv->remap_addr);
 
 probe_quit:
-	clk_put(emac_clk);
 	free_netdev(ndev);
+free_clk:
+	clk_put(emac_clk);
 	return rc;
 }
 

drivers/net/depca.c

···
                          "DE422",\
                          ""}
 
-static const char* const depca_signature[] __devinitconst = DEPCA_SIGNATURE;
+static char* __initdata depca_signature[] = DEPCA_SIGNATURE;
 
 enum depca_type {
 	DEPCA, de100, de101, de200, de201, de202, de210, de212, de422, unknown
 };
 
-static const char depca_string[] = "depca";
+static char depca_string[] = "depca";
 
 static int depca_device_remove (struct device *device);
 
 #ifdef CONFIG_EISA
-static const struct eisa_device_id depca_eisa_ids[] __devinitconst = {
+static struct eisa_device_id depca_eisa_ids[] = {
 	{ "DEC4220", de422 },
 	{ "" }
 };
···
 #define DE210_ID 0x628d
 #define DE212_ID 0x6def
 
-static const short depca_mca_adapter_ids[] __devinitconst = {
+static short depca_mca_adapter_ids[] = {
 	DE210_ID,
 	DE212_ID,
 	0x0000
 };
 
-static const char *depca_mca_adapter_name[] = {
+static char *depca_mca_adapter_name[] = {
 	"DEC EtherWORKS MC Adapter (DE210)",
 	"DEC EtherWORKS MC Adapter (DE212)",
 	NULL
 };
 
-static const enum depca_type depca_mca_adapter_type[] = {
+static enum depca_type depca_mca_adapter_type[] = {
 	de210,
 	de212,
 	0
···
 static int load_packet(struct net_device *dev, struct sk_buff *skb);
 static void depca_dbg_open(struct net_device *dev);
 
-static const u_char de1xx_irq[] __devinitconst = { 2, 3, 4, 5, 7, 9, 0 };
-static const u_char de2xx_irq[] __devinitconst = { 5, 9, 10, 11, 15, 0 };
-static const u_char de422_irq[] __devinitconst = { 5, 9, 10, 11, 0 };
+static u_char de1xx_irq[] __initdata = { 2, 3, 4, 5, 7, 9, 0 };
+static u_char de2xx_irq[] __initdata = { 5, 9, 10, 11, 15, 0 };
+static u_char de422_irq[] __initdata = { 5, 9, 10, 11, 0 };
+static u_char *depca_irq;
 
 static int irq;
 static int io;
···
 	.ndo_validate_addr	= eth_validate_addr,
 };
 
-static int __devinit depca_hw_init (struct net_device *dev, struct device *device)
+static int __init depca_hw_init (struct net_device *dev, struct device *device)
 {
 	struct depca_private *lp;
 	int i, j, offset, netRAM, mem_len, status = 0;
···
 	if (dev->irq < 2) {
 		unsigned char irqnum;
 		unsigned long irq_mask, delay;
-		const u_char *depca_irq;
 
 		irq_mask = probe_irq_on();
 
···
 			break;
 
 		default:
-			depca_irq = NULL;
 			break;	/* Not reached */
 		}
 
···
 	}
 }
 
-static int __devinit depca_common_init (u_long ioaddr, struct net_device **devp)
+static int __init depca_common_init (u_long ioaddr, struct net_device **devp)
 {
 	int status = 0;
 
···
 /*
 ** Microchannel bus I/O device probe
 */
-static int __devinit depca_mca_probe(struct device *device)
+static int __init depca_mca_probe(struct device *device)
 {
 	unsigned char pos[2];
 	unsigned char where;
···
 ** ISA bus I/O device probe
 */
 
-static void __devinit depca_platform_probe (void)
+static void __init depca_platform_probe (void)
 {
 	int i;
 	struct platform_device *pldev;
···
 	}
 }
 
-static enum depca_type __devinit depca_shmem_probe (ulong *mem_start)
+static enum depca_type __init depca_shmem_probe (ulong *mem_start)
 {
 	u_long mem_base[] = DEPCA_RAM_BASE_ADDRESSES;
 	enum depca_type adapter = unknown;
···
 */
 
 #ifdef CONFIG_EISA
-static int __devinit depca_eisa_probe (struct device *device)
+static int __init depca_eisa_probe (struct device *device)
 {
 	enum depca_type adapter = unknown;
 	struct eisa_device *edev;
···
 ** and Boot (readb) ROM. This will also give us a clue to the network RAM
 ** base address.
 */
-static int __devinit DepcaSignature(char *name, u_long base_addr)
+static int __init DepcaSignature(char *name, u_long base_addr)
 {
 	u_int i, j, k;
 	void __iomem *ptr;

drivers/net/dm9000.c

···
 
 	irqflags |= IRQF_SHARED;
 
-	if (request_irq(dev->irq, dm9000_interrupt, irqflags, dev->name, dev))
-		return -EAGAIN;
-
 	/* GPIO0 on pre-activate PHY, Reg 1F is not set by reset */
 	iow(db, DM9000_GPR, 0);	/* REG_1F bit0 activate phyxcer */
 	mdelay(1); /* delay needs by DM9000B */
···
 	/* Initialize DM9000 board */
 	dm9000_reset(db);
 	dm9000_init_dm9000(dev);
+
+	if (request_irq(dev->irq, dm9000_interrupt, irqflags, dev->name, dev))
+		return -EAGAIN;
 
 	/* Init driver variable */
 	db->dbug_cnt = 0;

drivers/net/hamradio/6pack.c

···
  * a block of 6pack data has been received, which can now be decapsulated
  * and sent on to some IP layer for further processing.
  */
-static unsigned int sixpack_receive_buf(struct tty_struct *tty,
+static void sixpack_receive_buf(struct tty_struct *tty,
 	const unsigned char *cp, char *fp, int count)
 {
 	struct sixpack *sp;
···
 	int count1;
 
 	if (!count)
-		return 0;
+		return;
 
 	sp = sp_get(tty);
 	if (!sp)
-		return -ENODEV;
+		return;
 
 	memcpy(buf, cp, count < sizeof(buf) ? count : sizeof(buf));
 
···
 
 	sp_put(sp);
 	tty_unthrottle(tty);
-
-	return count1;
 }
 
 /*

drivers/net/hamradio/mkiss.c

···
  * a block of data has been received, which can now be decapsulated
  * and sent on to the AX.25 layer for further processing.
  */
-static unsigned int mkiss_receive_buf(struct tty_struct *tty,
-		const unsigned char *cp, char *fp, int count)
+static void mkiss_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+	char *fp, int count)
 {
 	struct mkiss *ax = mkiss_get(tty);
-	int bytes = count;
 
 	if (!ax)
-		return -ENODEV;
+		return;
 
 	/*
 	 * Argh! mtu change time! - costs us the packet part received
···
 		ax_changedmtu(ax);
 
 	/* Read the characters out of the buffer */
-	while (bytes--) {
+	while (count--) {
 		if (fp != NULL && *fp++) {
 			if (!test_and_set_bit(AXF_ERROR, &ax->flags))
 				ax->dev->stats.rx_errors++;
···
 
 	mkiss_put(ax);
 	tty_unthrottle(tty);
-
-	return count;
 }
 
 /*

drivers/net/hp100.c

···
  *  variables
  */
 #ifdef CONFIG_ISA
-static const char *const hp100_isa_tbl[] __devinitconst = {
+static const char *hp100_isa_tbl[] = {
 	"HWPF150", /* HP J2573 rev A */
 	"HWP1950", /* HP J2573 */
 };
 #endif
 
 #ifdef CONFIG_EISA
-static const struct eisa_device_id hp100_eisa_tbl[] __devinitconst = {
+static struct eisa_device_id hp100_eisa_tbl[] = {
 	{ "HWPF180" }, /* HP J2577 rev A */
 	{ "HWP1920" }, /* HP 27248B */
 	{ "HWP1940" }, /* HP J2577 */
···
 }
 
 #ifdef CONFIG_ISA
-static __devinit int hp100_isa_probe1(struct net_device *dev, int ioaddr)
+static __init int hp100_isa_probe1(struct net_device *dev, int ioaddr)
 {
 	const char *sig;
 	int i;
···
  * EISA and PCI are handled by device infrastructure.
  */
 
-static int  __devinit hp100_isa_probe(struct net_device *dev, int addr)
+static int  __init hp100_isa_probe(struct net_device *dev, int addr)
 {
 	int err = -ENODEV;
 
···
 #endif /* CONFIG_ISA */
 
 #if !defined(MODULE) && defined(CONFIG_ISA)
-struct net_device * __devinit hp100_probe(int unit)
+struct net_device * __init hp100_probe(int unit)
 {
 	struct net_device *dev = alloc_etherdev(sizeof(struct hp100_private));
 	int err;
···
 }
 
 #ifdef CONFIG_EISA
-static int __devinit hp100_eisa_probe (struct device *gendev)
+static int __init hp100_eisa_probe (struct device *gendev)
 {
 	struct net_device *dev = alloc_etherdev(sizeof(struct hp100_private));
 	struct eisa_device *edev = to_eisa_device(gendev);

drivers/net/ibmlana.c

···
 static int ibmlana_io;
 static int startslot;		/* counts through slots when probing multiple devices */
 
-static const short ibmlana_adapter_ids[] __devinitconst = {
+static short ibmlana_adapter_ids[] __initdata = {
 	IBM_LANA_ID,
 	0x0000
 };
 
-static const char *const ibmlana_adapter_names[] __devinitconst = {
+static char *ibmlana_adapter_names[] __devinitdata = {
 	"IBM LAN Adapter/A",
 	NULL
 };

drivers/net/irda/irtty-sir.c

···
  * usbserial:	urb-complete-interrupt / softint
  */
 
-static unsigned int irtty_receive_buf(struct tty_struct *tty,
-		const unsigned char *cp, char *fp, int count)
+static void irtty_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+			      char *fp, int count) 
 {
 	struct sir_dev *dev;
 	struct sirtty_cb *priv = tty->disc_data;
 	int	i;
 
-	IRDA_ASSERT(priv != NULL, return -ENODEV;);
-	IRDA_ASSERT(priv->magic == IRTTY_MAGIC, return -EINVAL;);
+	IRDA_ASSERT(priv != NULL, return;);
+	IRDA_ASSERT(priv->magic == IRTTY_MAGIC, return;);
 
 	if (unlikely(count==0))		/* yes, this happens */
-		return 0;
+		return;
 
 	dev = priv->dev;
 	if (!dev) {
 		IRDA_WARNING("%s(), not ready yet!\n", __func__);
-		return -ENODEV;
+		return;
 	}
 
 	for (i = 0; i < count; i++) {
···
  		if (fp && *fp++) { 
 			IRDA_DEBUG(0, "Framing or parity error!\n");
 			sirdev_receive(dev, NULL, 0);	/* notify sir_dev (updating stats) */
-			return -EINVAL;
+			return;
  		}
 	}
 
 	sirdev_receive(dev, cp, count);
-
-	return count;
 }
 
 /*

drivers/net/irda/smsc-ircc2.c

···
 static void smsc_ircc_sir_wait_hw_transmitter_finish(struct smsc_ircc_cb *self);
 
 /* Probing */
-static int smsc_ircc_look_for_chips(void);
-static const struct smsc_chip * smsc_ircc_probe(unsigned short cfg_base, u8 reg, const struct smsc_chip *chip, char *type);
-static int smsc_superio_flat(const struct smsc_chip *chips, unsigned short cfg_base, char *type);
-static int smsc_superio_paged(const struct smsc_chip *chips, unsigned short cfg_base, char *type);
-static int smsc_superio_fdc(unsigned short cfg_base);
-static int smsc_superio_lpc(unsigned short cfg_base);
+static int __init smsc_ircc_look_for_chips(void);
+static const struct smsc_chip * __init smsc_ircc_probe(unsigned short cfg_base, u8 reg, const struct smsc_chip *chip, char *type);
+static int __init smsc_superio_flat(const struct smsc_chip *chips, unsigned short cfg_base, char *type);
+static int __init smsc_superio_paged(const struct smsc_chip *chips, unsigned short cfg_base, char *type);
+static int __init smsc_superio_fdc(unsigned short cfg_base);
+static int __init smsc_superio_lpc(unsigned short cfg_base);
 #ifdef CONFIG_PCI
-static int preconfigure_smsc_chip(struct smsc_ircc_subsystem_configuration *conf);
-static int preconfigure_through_82801(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf);
-static void preconfigure_ali_port(struct pci_dev *dev,
+static int __init preconfigure_smsc_chip(struct smsc_ircc_subsystem_configuration *conf);
+static int __init preconfigure_through_82801(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf);
+static void __init preconfigure_ali_port(struct pci_dev *dev,
 					 unsigned short port);
-static int preconfigure_through_ali(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf);
-static int smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
+static int __init preconfigure_through_ali(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf);
+static int __init smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
 						    unsigned short ircc_fir,
 						    unsigned short ircc_sir,
 						    unsigned char ircc_dma,
···
 }
 
 /* PNP hotplug support */
-static const struct pnp_device_id smsc_ircc_pnp_table[] __devinitconst = {
+static const struct pnp_device_id smsc_ircc_pnp_table[] = {
 	{ .id = "SMCf010", .driver_data = 0 },
 	/* and presumably others */
 	{ }
···
  *    Try to open driver instance
  *
  */
-static int __devinit smsc_ircc_open(unsigned int fir_base, unsigned int sir_base, u8 dma, u8 irq)
+static int __init smsc_ircc_open(unsigned int fir_base, unsigned int sir_base, u8 dma, u8 irq)
 {
 	struct smsc_ircc_cb *self;
 	struct net_device *dev;
···
 }
 
 
-static int __devinit smsc_access(unsigned short cfg_base, unsigned char reg)
+static int __init smsc_access(unsigned short cfg_base, unsigned char reg)
 {
 	IRDA_DEBUG(1, "%s\n", __func__);
 
···
 	return inb(cfg_base) != reg ? -1 : 0;
 }
 
-static const struct smsc_chip * __devinit smsc_ircc_probe(unsigned short cfg_base, u8 reg, const struct smsc_chip *chip, char *type)
+static const struct smsc_chip * __init smsc_ircc_probe(unsigned short cfg_base, u8 reg, const struct smsc_chip *chip, char *type)
 {
 	u8 devid, xdevid, rev;
 
···
 #ifdef CONFIG_PCI
 #define PCIID_VENDOR_INTEL 0x8086
 #define PCIID_VENDOR_ALI 0x10b9
-static const struct smsc_ircc_subsystem_configuration subsystem_configurations[] __devinitconst = {
+static struct smsc_ircc_subsystem_configuration subsystem_configurations[] __initdata = {
 	/*
 	 * Subsystems needing entries:
 	 * 0x10b9:0x1533 0x103c:0x0850 HP nx9010 family
···
  * (FIR port, SIR port, FIR DMA, FIR IRQ)
  * through the chip configuration port.
  */
-static int __devinit preconfigure_smsc_chip(struct
+static int __init preconfigure_smsc_chip(struct
 					 smsc_ircc_subsystem_configuration
 					 *conf)
 {
···
  * or Intel 82801DB/DBL (ICH4/ICH4-L) LPC Interface Bridge.
  * They all work the same way!
  */
-static int __devinit preconfigure_through_82801(struct pci_dev *dev,
+static int __init preconfigure_through_82801(struct pci_dev *dev,
 					     struct
 					     smsc_ircc_subsystem_configuration
 					     *conf)
···
  * This is based on reverse-engineering since ALi does not
  * provide any data sheet for the 1533 chip.
  */
-static void __devinit preconfigure_ali_port(struct pci_dev *dev,
+static void __init preconfigure_ali_port(struct pci_dev *dev,
 					 unsigned short port)
 {
 	unsigned char reg;
···
 	IRDA_MESSAGE("Activated ALi 1533 ISA bridge port 0x%04x.\n", port);
 }
 
-static int __devinit preconfigure_through_ali(struct pci_dev *dev,
+static int __init preconfigure_through_ali(struct pci_dev *dev,
 					   struct
 					   smsc_ircc_subsystem_configuration
 					   *conf)
···
 	return preconfigure_smsc_chip(conf);
 }
 
-static int __devinit smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
+static int __init smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
 						    unsigned short ircc_fir,
 						    unsigned short ircc_sir,
 						    unsigned char ircc_dma,
···
 	int ret = 0;
 
 	for_each_pci_dev(dev) {
-		const struct smsc_ircc_subsystem_configuration *conf;
+		struct smsc_ircc_subsystem_configuration *conf;
 
 		/*
 		 * Cache the subsystem vendor/device:

drivers/net/ks8842.c

···
 
 	/* check the status */
 	if ((status & RXSR_VALID) && !(status & RXSR_ERROR)) {
-		struct sk_buff *skb = netdev_alloc_skb_ip_align(netdev, len);
+		struct sk_buff *skb = netdev_alloc_skb_ip_align(netdev, len + 3);
 
 		if (skb) {
 

drivers/net/ne3210.c

···
 
 #define NE3210_DEBUG	0x0
 
-static const unsigned char irq_map[] __devinitconst =
-	{ 15, 12, 11, 10, 9, 7, 5, 3 };
-static const unsigned int shmem_map[] __devinitconst =
-	{ 0xff0, 0xfe0, 0xfff0, 0xd8, 0xffe0, 0xffc0, 0xd0, 0x0 };
-static const char *const ifmap[] __devinitconst =
-	{ "UTP", "?", "BNC", "AUI" };
-static const int ifmap_val[] __devinitconst = {
+static unsigned char irq_map[] __initdata = {15, 12, 11, 10, 9, 7, 5, 3};
+static unsigned int shmem_map[] __initdata = {0xff0, 0xfe0, 0xfff0, 0xd8, 0xffe0, 0xffc0, 0xd0, 0x0};
+static const char *ifmap[] __initdata = {"UTP", "?", "BNC", "AUI"};
+static int ifmap_val[] __initdata = {
 		IF_PORT_10BASET,
 		IF_PORT_UNKNOWN,
 		IF_PORT_10BASE2,
 		IF_PORT_AUI,
 };
 
-static int __devinit ne3210_eisa_probe (struct device *device)
+static int __init ne3210_eisa_probe (struct device *device)
 {
 	unsigned long ioaddr, phys_mem;
 	int i, retval, port_index;
···
 	memcpy_toio(shmem, buf, count);
 }
 
-static const struct eisa_device_id ne3210_ids[] __devinitconst = {
+static struct eisa_device_id ne3210_ids[] = {
 	{ "EGL0101" },
 	{ "NVL1801" },
 	{ "" },

drivers/net/ppp_async.c

···
 }
 
 /* May sleep, don't call from interrupt level or with interrupts disabled */
-static unsigned int
+static void
 ppp_asynctty_receive(struct tty_struct *tty, const unsigned char *buf,
 		  char *cflags, int count)
 {
···
 	unsigned long flags;
 
 	if (!ap)
-		return -ENODEV;
+		return;
 	spin_lock_irqsave(&ap->recv_lock, flags);
 	ppp_async_input(ap, buf, cflags, count);
 	spin_unlock_irqrestore(&ap->recv_lock, flags);
···
 		tasklet_schedule(&ap->tsk);
 	ap_put(ap);
 	tty_unthrottle(tty);
-
-	return count;
 }
 
 static void

drivers/net/ppp_synctty.c

···
 }
 
 /* May sleep, don't call from interrupt level or with interrupts disabled */
-static unsigned int
+static void
 ppp_sync_receive(struct tty_struct *tty, const unsigned char *buf,
 		  char *cflags, int count)
 {
···
 	unsigned long flags;
 
 	if (!ap)
-		return -ENODEV;
+		return;
 	spin_lock_irqsave(&ap->recv_lock, flags);
 	ppp_sync_input(ap, buf, cflags, count);
 	spin_unlock_irqrestore(&ap->recv_lock, flags);
···
 		tasklet_schedule(&ap->tsk);
 	sp_put(ap);
 	tty_unthrottle(tty);
-
-	return count;
 }
 
 static void

drivers/net/slip.c

···
  * in parallel
  */
 
-static unsigned int slip_receive_buf(struct tty_struct *tty,
-		const unsigned char *cp, char *fp, int count)
+static void slip_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+							char *fp, int count)
 {
 	struct slip *sl = tty->disc_data;
-	int bytes = count;
 
 	if (!sl || sl->magic != SLIP_MAGIC || !netif_running(sl->dev))
-		return -ENODEV;
+		return;
 
 	/* Read the characters out of the buffer */
-	while (bytes--) {
+	while (count--) {
 		if (fp && *fp++) {
 			if (!test_and_set_bit(SLF_ERROR, &sl->flags))
 				sl->dev->stats.rx_errors++;
···
 #endif
 			slip_unesc(sl, *cp++);
 	}
-
-	return count;
 }
 
 /************************************

drivers/net/smc-mca.c

···
    { 14, 15 }
 };
 
-static const short smc_mca_adapter_ids[] __devinitconst = {
+static short smc_mca_adapter_ids[] __initdata = {
 	0x61c8,
 	0x61c9,
 	0x6fc0,
···
 	0x0000
 };
 
-static const char *const smc_mca_adapter_names[] __devinitconst = {
+static char *smc_mca_adapter_names[] __initdata = {
 	"SMC Ethercard PLUS Elite/A BNC/AUI (WD8013EP/A)",
 	"SMC Ethercard PLUS Elite/A UTP/AUI (WD8013WP/A)",
 	"WD Ethercard PLUS/A (WD8003E/A or WD8003ET/A)",
···
 #endif
 };
 
-static int __devinit ultramca_probe(struct device *gen_dev)
+static int __init ultramca_probe(struct device *gen_dev)
 {
 	unsigned short ioaddr;
 	struct net_device *dev;

drivers/net/tg3.c

···
 			 dma_unmap_addr(txb, mapping),
 			 skb_headlen(skb),
 			 PCI_DMA_TODEVICE);
-	for (i = 0; i <= last; i++) {
+	for (i = 0; i < last; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
 		entry = NEXT_TX(entry);

drivers/net/tokenring/madgemc.c

···
 	return 0;
 }
 
-static const short madgemc_adapter_ids[] __devinitconst = {
+static short madgemc_adapter_ids[] __initdata = {
 	0x002d,
 	0x0000
 };

drivers/net/tulip/de4x5.c

···
 
 static u_char de4x5_irq[] = EISA_ALLOWED_IRQ_LIST;
 
-static int __devinit de4x5_eisa_probe (struct device *gendev)
+static int __init de4x5_eisa_probe (struct device *gendev)
 {
 	struct eisa_device *edev;
 	u_long iobase;
···
 	return 0;
 }
 
-static const struct eisa_device_id de4x5_eisa_ids[] __devinitconst = {
+static struct eisa_device_id de4x5_eisa_ids[] = {
         { "DEC4250", 0 },	/* 0 is the board name index... */
         { "" }
 };

drivers/net/usb/catc.c

···
 	if (!q->dir && q->buf && q->len)
 		memcpy(catc->ctrl_buf, q->buf, q->len);
 
-	if ((status = usb_submit_urb(catc->ctrl_urb, GFP_KERNEL)))
+	if ((status = usb_submit_urb(catc->ctrl_urb, GFP_ATOMIC)))
 		err("submit(ctrl_urb) status %d", status);
 }
 

drivers/net/usb/cdc_ncm.c

···
 #include <linux/usb/usbnet.h>
 #include <linux/usb/cdc.h>
 
-#define	DRIVER_VERSION				"24-May-2011"
+#define	DRIVER_VERSION				"01-June-2011"
 
 /* CDC NCM subclass 3.2.1 */
 #define USB_CDC_NCM_NDP16_LENGTH_MIN		0x10
···
 	.disconnect = cdc_ncm_disconnect,
 	.suspend = usbnet_suspend,
 	.resume = usbnet_resume,
+	.reset_resume =	usbnet_resume,
 	.supports_autosuspend = 1,
 };
 

drivers/net/virtio_net.c

···
 	 * before it gets out of hand.  Naturally, this wastes entries. */
 	if (capacity < 2+MAX_SKB_FRAGS) {
 		netif_stop_queue(dev);
-		if (unlikely(!virtqueue_enable_cb(vi->svq))) {
+		if (unlikely(!virtqueue_enable_cb_delayed(vi->svq))) {
 			/* More just got used, free them then recheck. */
 			capacity += free_old_xmit_skbs(vi);
 			if (capacity >= 2+MAX_SKB_FRAGS) {

drivers/net/wan/x25_asy.c

···
  * and sent on to some IP layer for further processing.
  */
 
-static unsigned int x25_asy_receive_buf(struct tty_struct *tty,
+static void x25_asy_receive_buf(struct tty_struct *tty,
 				const unsigned char *cp, char *fp, int count)
 {
 	struct x25_asy *sl = tty->disc_data;
-	int bytes = count;
 
 	if (!sl || sl->magic != X25_ASY_MAGIC || !netif_running(sl->dev))
 		return;
 
 
 	/* Read the characters out of the buffer */
-	while (bytes--) {
+	while (count--) {
 		if (fp && *fp++) {
 			if (!test_and_set_bit(SLF_ERROR, &sl->flags))
 				sl->dev->stats.rx_errors++;
···
 		}
 		x25_asy_unesc(sl, *cp++);
 	}
-
-	return count;
 }
 
 /*

drivers/net/wireless/ath/ath9k/Kconfig

···
 config ATH9K_PCI
 	bool "Atheros ath9k PCI/PCIe bus support"
 	depends on ATH9K && PCI
-	default PCI
 	---help---
 	  This option enables the PCI bus support in ath9k.
 

drivers/net/wireless/ath/ath9k/ar9002_calib.c

···
 	if (AR_SREV_9271(ah)) {
 		if (!ar9285_hw_cl_cal(ah, chan))
 			return false;
-	} else if (AR_SREV_9285_12_OR_LATER(ah)) {
+	} else if (AR_SREV_9285(ah) && AR_SREV_9285_12_OR_LATER(ah)) {
 		if (!ar9285_hw_clc(ah, chan))
 			return false;
 	} else {

drivers/net/wireless/ath/ath9k/ar9003_eeprom.c

···
 	case 1:
 		break;
 	case 2:
-		scaledPower -= REDUCE_SCALED_POWER_BY_TWO_CHAIN;
+		if (scaledPower > REDUCE_SCALED_POWER_BY_TWO_CHAIN)
+			scaledPower -= REDUCE_SCALED_POWER_BY_TWO_CHAIN;
+		else
+			scaledPower = 0;
 		break;
 	case 3:
-		scaledPower -= REDUCE_SCALED_POWER_BY_THREE_CHAIN;
+		if (scaledPower > REDUCE_SCALED_POWER_BY_THREE_CHAIN)
+			scaledPower -= REDUCE_SCALED_POWER_BY_THREE_CHAIN;
+		else
+			scaledPower = 0;
 		break;
 	}
 

drivers/net/wireless/ath/ath9k/ar9003_phy.c

···
 		"==== BB update: done ====\n\n");
 }
 EXPORT_SYMBOL(ar9003_hw_bb_watchdog_dbg_info);
+
+void ar9003_hw_disable_phy_restart(struct ath_hw *ah)
+{
+	u32 val;
+
+	/* While receiving unsupported rate frame rx state machine
+	 * gets into a state 0xb and if phy_restart happens in that
+	 * state, BB would go hang. If RXSM is in 0xb state after
+	 * first bb panic, ensure to disable the phy_restart.
+	 */
+	if (!((MS(ah->bb_watchdog_last_status,
+		  AR_PHY_WATCHDOG_RX_OFDM_SM) == 0xb) ||
+	    ah->bb_hang_rx_ofdm))
+		return;
+
+	ah->bb_hang_rx_ofdm = true;
+	val = REG_READ(ah, AR_PHY_RESTART);
+	val &= ~AR_PHY_RESTART_ENA;
+
+	REG_WRITE(ah, AR_PHY_RESTART, val);
+}
+EXPORT_SYMBOL(ar9003_hw_disable_phy_restart);

drivers/net/wireless/ath/ath9k/eeprom_9287.c

···
 	case 1:
 		break;
 	case 2:
-		scaledPower -= REDUCE_SCALED_POWER_BY_TWO_CHAIN;
+		if (scaledPower > REDUCE_SCALED_POWER_BY_TWO_CHAIN)
+			scaledPower -= REDUCE_SCALED_POWER_BY_TWO_CHAIN;
+		else
+			scaledPower = 0;
 		break;
 	case 3:
-		scaledPower -= REDUCE_SCALED_POWER_BY_THREE_CHAIN;
+		if (scaledPower > REDUCE_SCALED_POWER_BY_THREE_CHAIN)
+			scaledPower -= REDUCE_SCALED_POWER_BY_THREE_CHAIN;
+		else
+			scaledPower = 0;
 		break;
 	}
 	scaledPower = max((u16)0, scaledPower);

drivers/net/wireless/ath/ath9k/hw.c

···
 	if (ah->btcoex_hw.enabled)
 		ath9k_hw_btcoex_enable(ah);
 
-	if (AR_SREV_9300_20_OR_LATER(ah))
+	if (AR_SREV_9300_20_OR_LATER(ah)) {
 		ar9003_hw_bb_watchdog_config(ah);
+
+		ar9003_hw_disable_phy_restart(ah);
+	}
 
 	ath9k_hw_apply_gpio_override(ah);
 

drivers/net/wireless/ath/ath9k/hw.h

···
 
 	u32 bb_watchdog_last_status;
 	u32 bb_watchdog_timeout_ms; /* in ms, 0 to disable */
+	u8 bb_hang_rx_ofdm; /* true if bb hang due to rx_ofdm */
 
 	unsigned int paprd_target_power;
 	unsigned int paprd_training_power;
···
 void ar9003_hw_bb_watchdog_config(struct ath_hw *ah);
 void ar9003_hw_bb_watchdog_read(struct ath_hw *ah);
 void ar9003_hw_bb_watchdog_dbg_info(struct ath_hw *ah);
+void ar9003_hw_disable_phy_restart(struct ath_hw *ah);
 void ar9003_paprd_enable(struct ath_hw *ah, bool val);
 void ar9003_paprd_populate_single_table(struct ath_hw *ah,
 					struct ath9k_hw_cal_data *caldata,

drivers/net/wireless/ath/ath9k/main.c

···
 	u32 status = sc->intrstatus;
 	u32 rxmask;
 
-	if (status & ATH9K_INT_FATAL) {
+	if ((status & ATH9K_INT_FATAL) ||
+	    (status & ATH9K_INT_BB_WATCHDOG)) {
 		ath_reset(sc, true);
 		return;
 	}
···
 {
 #define SCHED_INTR (				\
 		ATH9K_INT_FATAL |		\
+		ATH9K_INT_BB_WATCHDOG |		\
 		ATH9K_INT_RXORN |		\
 		ATH9K_INT_RXEOL |		\
 		ATH9K_INT_RX |			\

drivers/net/wireless/ath/ath9k/rc.c

···
 
 	if (WLAN_RC_PHY_HT(rate_table->info[rix].phy)) {
 		rate->flags |= IEEE80211_TX_RC_MCS;
-		if (WLAN_RC_PHY_40(rate_table->info[rix].phy))
+		if (WLAN_RC_PHY_40(rate_table->info[rix].phy) &&
+		    conf_is_ht40(&txrc->hw->conf))
 			rate->flags |= IEEE80211_TX_RC_40_MHZ_WIDTH;
 		if (WLAN_RC_PHY_SGI(rate_table->info[rix].phy))
 			rate->flags |= IEEE80211_TX_RC_SHORT_GI;

drivers/net/wireless/b43/phy_n.c

···
 	int freq;
 	bool avoid = false;
 	u8 length;
-	u16 tmp, core, type, count, max, numb, last, cmd;
+	u16 tmp, core, type, count, max, numb, last = 0, cmd;
 	const u16 *table;
 	bool phy6or5x;
 

drivers/net/wireless/iwlegacy/iwl-4965-lib.c

···
 
 	/* rx_status carries information about the packet to mac80211 */
 	rx_status.mactime = le64_to_cpu(phy_res->timestamp);
+	rx_status.band = (phy_res->phy_flags & RX_RES_PHY_FLAGS_BAND_24_MSK) ?
+				IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ;
 	rx_status.freq =
 		ieee80211_channel_to_frequency(le16_to_cpu(phy_res->channel),
 							rx_status.band);
-	rx_status.band = (phy_res->phy_flags & RX_RES_PHY_FLAGS_BAND_24_MSK) ?
-				IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ;
 	rx_status.rate_idx =
 		iwl4965_hwrate_to_mac80211_idx(rate_n_flags, rx_status.band);
 	rx_status.flag = 0;

drivers/net/wireless/iwlegacy/iwl-4965.c

···
 	s32 temp;
 
 	temp = iwl4965_hw_get_temperature(priv);
-	if (temp < 0)
+	if (IWL_TX_POWER_TEMPERATURE_OUT_OF_RANGE(temp))
 		return;
 
 	if (priv->temperature != temp) {

drivers/net/wireless/iwlwifi/iwl-6000.c

···
 	IWL_DEVICE_6050,
 };
 
+#define IWL_DEVICE_6150						\
+	.fw_name_pre = IWL6050_FW_PRE,				\
+	.ucode_api_max = IWL6050_UCODE_API_MAX,			\
+	.ucode_api_min = IWL6050_UCODE_API_MIN,			\
+	.ops = &iwl6150_ops,					\
+	.eeprom_ver = EEPROM_6150_EEPROM_VERSION,		\
+	.eeprom_calib_ver = EEPROM_6150_TX_POWER_VERSION,	\
+	.base_params = &iwl6050_base_params,			\
+	.need_dc_calib = true,					\
+	.led_mode = IWL_LED_BLINK,				\
+	.internal_wimax_coex = true
+
 struct iwl_cfg iwl6150_bgn_cfg = {
 	.name = "Intel(R) Centrino(R) Wireless-N + WiMAX 6150 BGN",
-	.fw_name_pre = IWL6050_FW_PRE,
-	.ucode_api_max = IWL6050_UCODE_API_MAX,
-	.ucode_api_min = IWL6050_UCODE_API_MIN,
-	.eeprom_ver = EEPROM_6150_EEPROM_VERSION,
-	.eeprom_calib_ver = EEPROM_6150_TX_POWER_VERSION,
-	.ops = &iwl6150_ops,
-	.base_params = &iwl6050_base_params,
+	IWL_DEVICE_6150,
 	.ht_params = &iwl6000_ht_params,
-	.need_dc_calib = true,
-	.led_mode = IWL_LED_RF_STATE,
-	.internal_wimax_coex = true,
+};
+
+struct iwl_cfg iwl6150_bg_cfg = {
+	.name = "Intel(R) Centrino(R) Wireless-N + WiMAX 6150 BG",
+	IWL_DEVICE_6150,
 };
 
 struct iwl_cfg iwl6000_3agn_cfg = {

drivers/net/wireless/iwlwifi/iwl-agn.c

···
 
 /* 6150 WiFi/WiMax Series */
 	{IWL_PCI_DEVICE(0x0885, 0x1305, iwl6150_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0885, 0x1306, iwl6150_bgn_cfg)},
+	{IWL_PCI_DEVICE(0x0885, 0x1307, iwl6150_bg_cfg)},
 	{IWL_PCI_DEVICE(0x0885, 0x1325, iwl6150_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0885, 0x1326, iwl6150_bgn_cfg)},
+	{IWL_PCI_DEVICE(0x0885, 0x1327, iwl6150_bg_cfg)},
 	{IWL_PCI_DEVICE(0x0886, 0x1315, iwl6150_bgn_cfg)},
-	{IWL_PCI_DEVICE(0x0886, 0x1316, iwl6150_bgn_cfg)},
+	{IWL_PCI_DEVICE(0x0886, 0x1317, iwl6150_bg_cfg)},
 
 /* 1000 Series WiFi */
 	{IWL_PCI_DEVICE(0x0083, 0x1205, iwl1000_bgn_cfg)},

drivers/net/wireless/iwlwifi/iwl-agn.h

···
 extern struct iwl_cfg iwl6050_2agn_cfg;
 extern struct iwl_cfg iwl6050_2abg_cfg;
 extern struct iwl_cfg iwl6150_bgn_cfg;
+extern struct iwl_cfg iwl6150_bg_cfg;
 extern struct iwl_cfg iwl1000_bgn_cfg;
 extern struct iwl_cfg iwl1000_bg_cfg;
 extern struct iwl_cfg iwl100_bgn_cfg;

drivers/net/wireless/libertas/cmd.c

···
 	cmd = cmdnode->cmdbuf;
 
 	spin_lock_irqsave(&priv->driver_lock, flags);
+	priv->seqnum++;
+	cmd->seqnum = cpu_to_le16(priv->seqnum);
 	priv->cur_cmd = cmdnode;
 	spin_unlock_irqrestore(&priv->driver_lock, flags);
 
···
 	/* Copy the incoming command to the buffer */
 	memcpy(cmdnode->cmdbuf, in_cmd, in_cmd_size);
 
-	/* Set sequence number, clean result, move to buffer */
-	priv->seqnum++;
+	/* Set command, clean result, move to buffer */
 	cmdnode->cmdbuf->command = cpu_to_le16(command);
 	cmdnode->cmdbuf->size    = cpu_to_le16(in_cmd_size);
-	cmdnode->cmdbuf->seqnum  = cpu_to_le16(priv->seqnum);
 	cmdnode->cmdbuf->result  = 0;
 
 	lbs_deb_host("PREP_CMD: command 0x%04x\n", command);

drivers/net/wireless/mwifiex/sdio.h

···
 /* Rx unit register */
 #define CARD_RX_UNIT_REG		0x63
 
-/* Event header Len*/
-#define MWIFIEX_EVENT_HEADER_LEN           8
+/* Event header len w/o 4 bytes of interface header */
+#define MWIFIEX_EVENT_HEADER_LEN           4
 
 /* Max retry number of CMD53 write */
 #define MAX_WRITE_IOMEM_RETRY		2

drivers/net/wireless/rt2x00/Kconfig

···
 config RT2800USB_RT53XX
        bool "rt2800usb - Include support for rt53xx devices (EXPERIMENTAL)"
        depends on EXPERIMENTAL
-       default y
        ---help---
          This adds support for rt53xx wireless chipset family to the
          rt2800pci driver.

drivers/net/wireless/rtlwifi/pci.c

···
 							 &rx_status,
 							 (u8 *) pdesc, skb);
 
-			pci_unmap_single(rtlpci->pdev,
-					 *((dma_addr_t *) skb->cb),
-					 rtlpci->rxbuffersize,
-					 PCI_DMA_FROMDEVICE);
-
 			skb_put(skb, rtlpriv->cfg->ops->get_desc((u8 *) pdesc,
 							 false,
 							 HW_DESC_RXPKT_LEN));
···
 
 			hdr = rtl_get_hdr(skb);
 			fc = rtl_get_fc(skb);
+
+			/* try for new buffer - if allocation fails, drop
+			 * frame and reuse old buffer
+			 */
+			new_skb = dev_alloc_skb(rtlpci->rxbuffersize);
+			if (unlikely(!new_skb)) {
+				RT_TRACE(rtlpriv, (COMP_INTR | COMP_RECV),
+					 DBG_DMESG,
+					 ("can't alloc skb for rx\n"));
+				goto done;
+			}
+			pci_unmap_single(rtlpci->pdev,
+					 *((dma_addr_t *) skb->cb),
+					 rtlpci->rxbuffersize,
+					 PCI_DMA_FROMDEVICE);
 
 			if (!stats.crc || !stats.hwerror) {
 				memcpy(IEEE80211_SKB_RXCB(skb), &rx_status,
···
 				rtl_lps_leave(hw);
 			}
 
-			new_skb = dev_alloc_skb(rtlpci->rxbuffersize);
-			if (unlikely(!new_skb)) {
-				RT_TRACE(rtlpriv, (COMP_INTR | COMP_RECV),
-					 DBG_DMESG,
-					 ("can't alloc skb for rx\n"));
-				goto done;
-			}
 			skb = new_skb;
-			/*skb->dev = dev; */
 
 			rtlpci->rx_ring[rx_queue_idx].rx_buf[rtlpci->
 							     rx_ring
···
 		       rtlpci->rxringcount);
 
 		rtlpci->rx_ring[rx_queue_idx].idx = 0;
+
+		/* If amsdu_8k is disabled, set buffersize to 4096. This
+		 * change will reduce memory fragmentation.
+		 */
+		if (rtlpci->rxbuffersize > 4096 &&
+		    rtlpriv->rtlhal.disable_amsdu_8k)
+			rtlpci->rxbuffersize = 4096;
 
 		for (i = 0; i < rtlpci->rxringcount; i++) {
 			struct sk_buff *skb =

drivers/net/wireless/wl12xx/conf.h

···
 	/* time to wait on the channel for passive scans (in TUs) */
 	u32 dwell_time_passive;
 
+	/* time to wait on the channel for DFS scans (in TUs) */
+	u32 dwell_time_dfs;
+
 	/* number of probe requests to send on each channel in active scans */
 	u8 num_probe_reqs;
 

drivers/net/wireless/wl12xx/main.c

···
 		.min_dwell_time_active = 8,
 		.max_dwell_time_active = 30,
 		.dwell_time_passive    = 100,
+		.dwell_time_dfs        = 150,
 		.num_probe_reqs        = 2,
 		.rssi_threshold        = -90,
 		.snr_threshold         = 0,

drivers/net/wireless/wl12xx/scan.c

···
 	struct conf_sched_scan_settings *c = &wl->conf.sched_scan;
 	int i, j;
 	u32 flags;
+	bool force_passive = !req->n_ssids;
 
 	for (i = 0, j = start;
 	     i < req->n_channels && j < MAX_CHANNELS_ALL_BANDS;
 	     i++) {
 		flags = req->channels[i]->flags;
 
-		if (!(flags & IEEE80211_CHAN_DISABLED) &&
-		    ((flags & IEEE80211_CHAN_PASSIVE_SCAN) == passive) &&
-		    ((flags & IEEE80211_CHAN_RADAR) == radar) &&
-		    (req->channels[i]->band == band)) {
+		if (force_passive)
+			flags |= IEEE80211_CHAN_PASSIVE_SCAN;
+
+		if ((req->channels[i]->band == band) &&
+		    !(flags & IEEE80211_CHAN_DISABLED) &&
+		    (!!(flags & IEEE80211_CHAN_RADAR) == radar) &&
+		    /* if radar is set, we ignore the passive flag */
+		    (radar ||
+		     !!(flags & IEEE80211_CHAN_PASSIVE_SCAN) == passive)) {
 			wl1271_debug(DEBUG_SCAN, "band %d, center_freq %d ",
 				     req->channels[i]->band,
 				     req->channels[i]->center_freq);
···
 			wl1271_debug(DEBUG_SCAN, "max_power %d",
 				     req->channels[i]->max_power);
 
-			if (flags & IEEE80211_CHAN_PASSIVE_SCAN) {
+			if (flags & IEEE80211_CHAN_RADAR) {
+				channels[j].flags |= SCAN_CHANNEL_FLAGS_DFS;
+				channels[j].passive_duration =
+					cpu_to_le16(c->dwell_time_dfs);
+			}
+			else if (flags & IEEE80211_CHAN_PASSIVE_SCAN) {
 				channels[j].passive_duration =
 					cpu_to_le16(c->dwell_time_passive);
 			} else {
···
 				channels[j].max_duration =
 					cpu_to_le16(c->max_dwell_time_active);
 			}
-			channels[j].tx_power_att = req->channels[j]->max_power;
+			channels[j].tx_power_att = req->channels[i]->max_power;
 			channels[j].channel = req->channels[i]->hw_value;
 
 			j++;
···
 		wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
 						    IEEE80211_BAND_2GHZ,
 						    false, false, idx);
-	idx += cfg->active[0];
+	/*
+	 * 5GHz channels always start at position 14, not immediately
+	 * after the last 2.4GHz channel
+	 */
+	idx = 14;
 
 	cfg->passive[1] =
 		wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
···
 						    false, true, idx);
 	idx += cfg->passive[1];
 
-	cfg->active[1] =
-		wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
-						    IEEE80211_BAND_5GHZ,
-						    false, false, 14);
-	idx += cfg->active[1];
-
 	cfg->dfs =
 		wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
 						    IEEE80211_BAND_5GHZ,
-						    true, false, idx);
+						    true, true, idx);
 	idx += cfg->dfs;
+
+	cfg->active[1] =
+		wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
+						    IEEE80211_BAND_5GHZ,
+						    false, false, idx);
+	idx += cfg->active[1];
 
 	wl1271_debug(DEBUG_SCAN, "    2.4GHz: active %d passive %d",
 		     cfg->active[0], cfg->passive[0]);
 	wl1271_debug(DEBUG_SCAN, "    5GHz: active %d passive %d",
 		     cfg->active[1], cfg->passive[1]);
+	wl1271_debug(DEBUG_SCAN, "    DFS: %d", cfg->dfs);
 
 	return idx;
 }
···
 	struct wl1271_cmd_sched_scan_config *cfg = NULL;
 	struct conf_sched_scan_settings *c = &wl->conf.sched_scan;
 	int i, total_channels, ret;
+	bool force_passive = !req->n_ssids;
 
 	wl1271_debug(DEBUG_CMD, "cmd sched_scan scan config");
 
···
 	for (i = 0; i < SCAN_MAX_CYCLE_INTERVALS; i++)
 		cfg->intervals[i] = cpu_to_le32(req->interval);
 
-	if (req->ssids[0].ssid_len && req->ssids[0].ssid) {
+	if (!force_passive && req->ssids[0].ssid_len && req->ssids[0].ssid) {
 		cfg->filter_type = SCAN_SSID_FILTER_SPECIFIC;
 		cfg->ssid_len = req->ssids[0].ssid_len;
 		memcpy(cfg->ssid, req->ssids[0].ssid,
···
 		goto out;
 	}
 
-	if (cfg->active[0]) {
+	if (!force_passive && cfg->active[0]) {
 		ret = wl1271_cmd_build_probe_req(wl, req->ssids[0].ssid,
 						 req->ssids[0].ssid_len,
 						 ies->ie[IEEE80211_BAND_2GHZ],
···
 		}
 	}
 
-	if (cfg->active[1]) {
+	if (!force_passive && cfg->active[1]) {
 		ret = wl1271_cmd_build_probe_req(wl,  req->ssids[0].ssid,
 						 req->ssids[0].ssid_len,
 						 ies->ie[IEEE80211_BAND_5GHZ],

drivers/net/wireless/wl12xx/scan.h

···
 	SCAN_BSS_TYPE_ANY,
 };
 
+#define SCAN_CHANNEL_FLAGS_DFS		BIT(0)
+#define SCAN_CHANNEL_FLAGS_DFS_ENABLED	BIT(1)
+
 struct conn_scan_ch_params {
 	__le16 min_duration;
 	__le16 max_duration;

drivers/net/wireless/zd1211rw/zd_usb.c

···
 module_init(usb_init);
 module_exit(usb_exit);
 
+static int zd_ep_regs_out_msg(struct usb_device *udev, void *data, int len,
+			      int *actual_length, int timeout)
+{
+	/* In USB 2.0 mode EP_REGS_OUT endpoint is interrupt type. However in
+	 * USB 1.1 mode endpoint is bulk. Select correct type URB by endpoint
+	 * descriptor.
+	 */
+	struct usb_host_endpoint *ep;
+	unsigned int pipe;
+
+	pipe = usb_sndintpipe(udev, EP_REGS_OUT);
+	ep = usb_pipe_endpoint(udev, pipe);
+	if (!ep)
+		return -EINVAL;
+
+	if (usb_endpoint_xfer_int(&ep->desc)) {
+		return usb_interrupt_msg(udev, pipe, data, len,
+					 actual_length, timeout);
+	} else {
+		pipe = usb_sndbulkpipe(udev, EP_REGS_OUT);
+		return usb_bulk_msg(udev, pipe, data, len, actual_length,
+				    timeout);
+	}
+}
+
 static int usb_int_regs_length(unsigned int count)
 {
 	return sizeof(struct usb_int_regs) + count * sizeof(struct reg_data);
···
 
 	udev = zd_usb_to_usbdev(usb);
 	prepare_read_regs_int(usb);
-	r = usb_interrupt_msg(udev, usb_sndintpipe(udev, EP_REGS_OUT),
-			      req, req_len, &actual_req_len, 50 /* ms */);
+	r = zd_ep_regs_out_msg(udev, req, req_len, &actual_req_len, 50 /*ms*/);
 	if (r) {
 		dev_dbg_f(zd_usb_dev(usb),
-			"error in usb_interrupt_msg(). Error number %d\n", r);
+			"error in zd_ep_regs_out_msg(). Error number %d\n", r);
 		goto error;
 	}
 	if (req_len != actual_req_len) {
-		dev_dbg_f(zd_usb_dev(usb), "error in usb_interrupt_msg()\n"
+		dev_dbg_f(zd_usb_dev(usb), "error in zd_ep_regs_out_msg()\n"
 			" req_len %d != actual_req_len %d\n",
 			req_len, actual_req_len);
 		r = -EIO;
···
 		rw->value = cpu_to_le16(ioreqs[i].value);
 	}
 
-	usb_fill_int_urb(urb, udev, usb_sndintpipe(udev, EP_REGS_OUT),
-			 req, req_len, iowrite16v_urb_complete, usb,
-			 ep->desc.bInterval);
+	/* In USB 2.0 mode endpoint is interrupt type. However in USB 1.1 mode
+	 * endpoint is bulk. Select correct type URB by endpoint descriptor.
+	 */
+	if (usb_endpoint_xfer_int(&ep->desc))
+		usb_fill_int_urb(urb, udev, usb_sndintpipe(udev, EP_REGS_OUT),
+				 req, req_len, iowrite16v_urb_complete, usb,
+				 ep->desc.bInterval);
+	else
+		usb_fill_bulk_urb(urb, udev, usb_sndbulkpipe(udev, EP_REGS_OUT),
+				  req, req_len, iowrite16v_urb_complete, usb);
+
 	urb->transfer_flags |= URB_FREE_BUFFER;
 
 	/* Submit previous URB */
···
 	}
 
 	udev = zd_usb_to_usbdev(usb);
-	r = usb_interrupt_msg(udev, usb_sndintpipe(udev, EP_REGS_OUT),
-			      req, req_len, &actual_req_len, 50 /* ms */);
+	r = zd_ep_regs_out_msg(udev, req, req_len, &actual_req_len, 50 /*ms*/);
 	if (r) {
 		dev_dbg_f(zd_usb_dev(usb),
-			"error in usb_interrupt_msg(). Error number %d\n", r);
+			"error in zd_ep_regs_out_msg(). Error number %d\n", r);
 		goto out;
 	}
 	if (req_len != actual_req_len) {
-		dev_dbg_f(zd_usb_dev(usb), "error in usb_interrupt_msg()"
+		dev_dbg_f(zd_usb_dev(usb), "error in zd_ep_regs_out_msg()"
 			" req_len %d != actual_req_len %d\n",
 			req_len, actual_req_len);
 		r = -EIO;

drivers/pci/dmar.c

···
 	{
 #ifdef CONFIG_INTR_REMAP
 		struct acpi_table_dmar *dmar;
-		/*
-		 * for now we will disable dma-remapping when interrupt
-		 * remapping is enabled.
-		 * When support for queued invalidation for IOTLB invalidation
-		 * is added, we will not need this any more.
-		 */
+
 		dmar = (struct acpi_table_dmar *) dmar_tbl;
 		if (ret && cpu_has_x2apic && dmar->flags & 0x1)
 			printk(KERN_INFO

drivers/pci/intel-iommu.c

···
 #define ROOT_SIZE		VTD_PAGE_SIZE
 #define CONTEXT_SIZE		VTD_PAGE_SIZE
 
+#define IS_BRIDGE_HOST_DEVICE(pdev) \
+			    ((pdev->class >> 8) == PCI_CLASS_BRIDGE_HOST)
 #define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY)
 #define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA)
 #define IS_AZALIA(pdev) ((pdev)->vendor == 0x8086 && (pdev)->device == 0x3a3e)
···
 	return (pfn + level_size(level) - 1) & level_mask(level);
 }
 
+static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
+{
+	return  1 << ((lvl - 1) * LEVEL_STRIDE);
+}
+
 /* VT-d pages must always be _smaller_ than MM pages. Otherwise things
    are never going to work. */
 static inline unsigned long dma_to_mm_pfn(unsigned long dma_pfn)
···
 
 static void __init check_tylersburg_isoch(void);
 static int rwbf_quirk;
+
+/*
+ * set to 1 to panic kernel if can't successfully enable VT-d
+ * (used when kernel is launched w/ TXT)
+ */
+static int force_on = 0;
 
 /*
  * 0: Present
···
 	int		iommu_coherency;/* indicate coherency of iommu access */
 	int		iommu_snooping; /* indicate snooping control feature*/
 	int		iommu_count;	/* reference count of iommu */
+	int		iommu_superpage;/* Level of superpages supported:
+					   0 == 4KiB (no superpages), 1 == 2MiB,
+					   2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
 	spinlock_t	iommu_lock;	/* protect iommu set in domain */
 	u64		max_addr;	/* maximum mapped address */
 };
···
 static int dmar_map_gfx = 1;
 static int dmar_forcedac;
 static int intel_iommu_strict;
+static int intel_iommu_superpage = 1;
 
 #define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1))
 static DEFINE_SPINLOCK(device_domain_lock);
···
 			printk(KERN_INFO
 				"Intel-IOMMU: disable batched IOTLB flush\n");
 			intel_iommu_strict = 1;
+		} else if (!strncmp(str, "sp_off", 6)) {
+			printk(KERN_INFO
+				"Intel-IOMMU: disable supported super page\n");
+			intel_iommu_superpage = 0;
 		}
 
 		str += strcspn(str, ",");
···
 	}
 }
 
+static void domain_update_iommu_superpage(struct dmar_domain *domain)
+{
+	int i, mask = 0xf;
+
+	if (!intel_iommu_superpage) {
+		domain->iommu_superpage = 0;
+		return;
+	}
+
+	domain->iommu_superpage = 4; /* 1TiB */
+
+	for_each_set_bit(i, &domain->iommu_bmp, g_num_of_iommus) {
+		mask |= cap_super_page_val(g_iommus[i]->cap);
+		if (!mask) {
+			break;
+		}
+	}
+	domain->iommu_superpage = fls(mask);
+}
+
 /* Some capabilities may be different across iommus */
 static void domain_update_iommu_cap(struct dmar_domain *domain)
 {
 	domain_update_iommu_coherency(domain);
 	domain_update_iommu_snooping(domain);
+	domain_update_iommu_superpage(domain);
 }
 
 static struct intel_iommu *device_to_iommu(int segment, u8 bus, u8 devfn)
···
 }
 
 static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
-				      unsigned long pfn)
+				      unsigned long pfn, int large_level)
 {
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
 	struct dma_pte *parent, *pte = NULL;
 	int level = agaw_to_level(domain->agaw);
-	int offset;
+	int offset, target_level;
 
 	BUG_ON(!domain->pgd);
 	BUG_ON(addr_width < BITS_PER_LONG && pfn >> addr_width);
 	parent = domain->pgd;
+
+	/* Search pte */
+	if (!large_level)
+		target_level = 1;
+	else
+		target_level = large_level;
 
 	while (level > 0) {
 		void *tmp_page;
 
 		offset = pfn_level_offset(pfn, level);
 		pte = &parent[offset];
-		if (level == 1)
+		if (!large_level && (pte->val & DMA_PTE_LARGE_PAGE))
+			break;
+		if (level == target_level)
 			break;
 
 		if (!dma_pte_present(pte)) {
···
 	return pte;
 }
 
+
 /* return address's pte at specific level */
 static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain,
 					 unsigned long pfn,
-					 int level)
+					 int level, int *large_page)
 {
 	struct dma_pte *parent, *pte = NULL;
 	int total = agaw_to_level(domain->agaw);
···
 		if (level == total)
 			return pte;
 
-		if (!dma_pte_present(pte))
+		if (!dma_pte_present(pte)) {
+			*large_page = total;
 			break;
+		}
+
+		if (pte->val & DMA_PTE_LARGE_PAGE) {
+			*large_page = total;
+			return pte;
+		}
+
 		parent = phys_to_virt(dma_pte_addr(pte));
 		total--;
 	}
···
 				unsigned long last_pfn)
 {
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
+	unsigned int large_page = 1;
 	struct dma_pte *first_pte, *pte;
 
 	BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width);
···
 
 	/* we don't need lock here; nobody else touches the iova range */
 	do {
-		first_pte = pte = dma_pfn_level_pte(domain, start_pfn, 1);
+		large_page = 1;
+		first_pte = pte = dma_pfn_level_pte(domain, start_pfn, 1, &large_page);
 		if (!pte) {
-			start_pfn = align_to_level(start_pfn + 1, 2);
+			start_pfn = align_to_level(start_pfn + 1, large_page + 1);
 			continue;
 		}
-		do { 
+		do {
 			dma_clear_pte(pte);
-			start_pfn++;
+			start_pfn += lvl_to_nr_pages(large_page);
 			pte++;
 		} while (start_pfn <= last_pfn && !first_pte_in_page(pte));
 
···
 	int total = agaw_to_level(domain->agaw);
 	int level;
 	unsigned long tmp;
+	int large_page = 2;
 
 	BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width);
 	BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width);
···
 			return;
 
 		do {
-			first_pte = pte = dma_pfn_level_pte(domain, tmp, level);
+			large_page = level;
+			first_pte = pte = dma_pfn_level_pte(domain, tmp, level, &large_page);
+			if (large_page > level)
+				level = large_page + 1;
 			if (!pte) {
 				tmp = align_to_level(tmp + 1, level + 1);
 				continue;
···
 	else
 		domain->iommu_snooping = 0;
 
+	domain->iommu_superpage = fls(cap_super_page_val(iommu->cap));
 	domain->iommu_count = 1;
 	domain->nid = iommu->node;
 
···
 	/* Domain 0 is reserved, so dont process it */
 	if (!domain)
 		return;
+
+	/* Flush any lazy unmaps that may reference this domain */
+	if (!intel_iommu_strict)
+		flush_unmaps_timeout(0);
 
 	domain_remove_dev_info(domain);
 	/* destroy iovas */
···
 	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
 }
 
+/* Return largest possible superpage level for a given mapping */
+static inline int hardware_largepage_caps(struct dmar_domain *domain,
+					  unsigned long iov_pfn,
+					  unsigned long phy_pfn,
+					  unsigned long pages)
+{
+	int support, level = 1;
+	unsigned long pfnmerge;
+
+	support = domain->iommu_superpage;
+
+	/* To use a large page, the virtual *and* physical addresses
+	   must be aligned to 2MiB/1GiB/etc. Lower bits set in either
+	   of them will mean we have to use smaller pages. So just
+	   merge them and check both at once. */
+	pfnmerge = iov_pfn | phy_pfn;
+
+	while (support && !(pfnmerge & ~VTD_STRIDE_MASK)) {
+		pages >>= VTD_STRIDE_SHIFT;
+		if (!pages)
+			break;
+		pfnmerge >>= VTD_STRIDE_SHIFT;
+		level++;
+		support--;
+	}
+	return level;
+}
+
 static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			    struct scatterlist *sg, unsigned long phys_pfn,
 			    unsigned long nr_pages, int prot)
···
 	phys_addr_t uninitialized_var(pteval);
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
 	unsigned long sg_res;
+	unsigned int largepage_lvl = 0;
+	unsigned long lvl_pages = 0;
 
 	BUG_ON(addr_width < BITS_PER_LONG && (iov_pfn + nr_pages - 1) >> addr_width);
 
···
 		pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
 	}
 
-	while (nr_pages--) {
+	while (nr_pages > 0) {
 		uint64_t tmp;
 
 		if (!sg_res) {
···
 			sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + sg->offset;
 			sg->dma_length = sg->length;
 			pteval = page_to_phys(sg_page(sg)) | prot;
+			phys_pfn = pteval >> VTD_PAGE_SHIFT;
 		}
+
 		if (!pte) {
-			first_pte = pte = pfn_to_dma_pte(domain, iov_pfn);
+			largepage_lvl = hardware_largepage_caps(domain, iov_pfn, phys_pfn, sg_res);
+
+			first_pte = pte = pfn_to_dma_pte(domain, iov_pfn, largepage_lvl);
 			if (!pte)
 				return -ENOMEM;
+			/* It is large page*/
+			if (largepage_lvl > 1)
+				pteval |= DMA_PTE_LARGE_PAGE;
+			else
+				pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE;
+
 		}
 		/* We don't need lock here, nobody else
 		 * touches the iova range
···
 			}
 			WARN_ON(1);
 		}
+
+		lvl_pages = lvl_to_nr_pages(largepage_lvl);
+
+		BUG_ON(nr_pages < lvl_pages);
+		BUG_ON(sg_res < lvl_pages);
+
+		nr_pages -= lvl_pages;
+		iov_pfn += lvl_pages;
+		phys_pfn += lvl_pages;
+		pteval += lvl_pages * VTD_PAGE_SIZE;
+		sg_res -= lvl_pages;
+
+		/* If the next PTE would be the first in a new page, then we
+		   need to flush the cache on the entries we've just written.
+		   And then we'll need to recalculate 'pte', so clear it and
+		   let it get set again in the if (!pte) block above.
+
+		   If we're done (!nr_pages) we need to flush the cache too.
+
+		   Also if we've been setting superpages, we may need to
+		   recalculate 'pte' and switch back to smaller pages for the
+		   end of the mapping, if the trailing size is not enough to
+		   use another superpage (i.e. sg_res < lvl_pages). */
 		pte++;
-		if (!nr_pages || first_pte_in_page(pte)) {
+		if (!nr_pages || first_pte_in_page(pte) ||
+		    (largepage_lvl > 1 && sg_res < lvl_pages)) {
 			domain_flush_cache(domain, first_pte,
 					   (void *)pte - (void *)first_pte);
 			pte = NULL;
 		}
-		iov_pfn++;
-		pteval += VTD_PAGE_SIZE;
-		sg_res--;
-		if (!sg_res)
+
+		if (!sg_res && nr_pages)
 			sg = sg_next(sg);
 	}
 	return 0;
···
 	if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)
 		return 0;
 	return iommu_prepare_identity_map(pdev, rmrr->base_address,
-		rmrr->end_address + 1);
+		rmrr->end_address);
 }
 
 #ifdef CONFIG_DMAR_FLOPPY_WA
···
 		return;
 
 	printk(KERN_INFO "IOMMU: Prepare 0-16MiB unity mapping for LPC\n");
-	ret = iommu_prepare_identity_map(pdev, 0, 16*1024*1024);
+	ret = iommu_prepare_identity_map(pdev, 0, 16*1024*1024 - 1);
 
 	if (ret)
 		printk(KERN_ERR "IOMMU: Failed to create 0-16MiB identity map; "
···
 	if (likely(!iommu_identity_mapping))
 		return 0;
 
+	info = pdev->dev.archdata.iommu;
+	if (info && info != DUMMY_DEVICE_DOMAIN_INFO)
+		return (info->domain == si_domain);
 
-	list_for_each_entry(info, &si_domain->devices, link)
-		if (info->dev == pdev)
-			return 1;
 	return 0;
 }
 
···
 	 * Assume that they will -- if they turn out not to be, then we can 
 	 * take them out of the 1:1 domain later.
 	 */
-	if (!startup)
-		return pdev->dma_mask > DMA_BIT_MASK(32);
+	if (!startup) {
+		/*
+		 * If the device's dma_mask is less than the system's memory
+		 * size then this is not a candidate for identity mapping.
+		 */
+		u64 dma_mask = pdev->dma_mask;
+
+		if (pdev->dev.coherent_dma_mask &&
+		    pdev->dev.coherent_dma_mask < dma_mask)
+			dma_mask = pdev->dev.coherent_dma_mask;
+
+		return dma_mask >= dma_get_required_mask(&pdev->dev);
+	}
 
 	return 1;
 }
···
 		return -EFAULT;
 
 	for_each_pci_dev(pdev) {
+		/* Skip Host/PCI Bridge devices */
+		if (IS_BRIDGE_HOST_DEVICE(pdev))
+			continue;
 		if (iommu_should_identity_map(pdev, 1)) {
 			printk(KERN_INFO "IOMMU: %s identity mapping for device %s\n",
 			       hw ? "hardware" : "software", pci_name(pdev));
···
 	return 0;
 }
 
-static int __init init_dmars(int force_on)
+static int __init init_dmars(void)
 {
 	struct dmar_drhd_unit *drhd;
 	struct dmar_rmrr_unit *rmrr;
···
 	iommu = domain_get_iommu(domain);
 	size = aligned_nrpages(paddr, size);
 
-	iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size),
-				pdev->dma_mask);
+	iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size), dma_mask);
 	if (!iova)
 		goto error;
 
···
 		if (iommu->qi)
 			dmar_reenable_qi(iommu);
 
-	for_each_active_iommu(iommu, drhd) {
+	for_each_iommu(iommu, drhd) {
+		if (drhd->ignored) {
+			/*
+			 * we always have to disable PMRs or DMA may fail on
+			 * this device
+			 */
+			if (force_on)
+				iommu_disable_protect_mem_regions(iommu);
+			continue;
+		}
+	
 		iommu_flush_write_buffer(iommu);
 
 		iommu_set_root_entry(iommu);
···
 					   DMA_CCMD_GLOBAL_INVL);
 		iommu->flush.flush_iotlb(iommu, 0, 0, 0,
 					 DMA_TLB_GLOBAL_FLUSH);
-		iommu_enable_translation(iommu);
+		if (iommu_enable_translation(iommu))
+			return 1;
 		iommu_disable_protect_mem_regions(iommu);
 	}
 
···
 	unsigned long flag;
 
 	if (init_iommu_hw()) {
-		WARN(1, "IOMMU setup failed, DMAR can not resume!\n");
+		if (force_on)
+			panic("tboot: IOMMU setup failed, DMAR can not resume!\n");
+		else
+			WARN(1, "IOMMU setup failed, DMAR can not resume!\n");
 		return;
 	}
 
···
 int __init intel_iommu_init(void)
 {
 	int ret = 0;
-	int force_on = 0;
 
 	/* VT-d is required for a TXT/tboot launch, so enforce that */
 	force_on = tboot_force_iommu();
···
 
 	init_no_remapping_devices();
 
-	ret = init_dmars(force_on);
+	ret = init_dmars();
 	if (ret) {
 		if (force_on)
 			panic("tboot: Failed to initialize DMARs\n");
···
 	spin_lock_irqsave(&device_domain_lock, flags);
 	list_for_each_safe(entry, tmp, &domain->devices) {
 		info = list_entry(entry, struct device_domain_info, link);
-		/* No need to compare PCI domain; it has to be the same */
-		if (info->bus == pdev->bus->number &&
+		if (info->segment == pci_domain_nr(pdev->bus) &&
+		    info->bus == pdev->bus->number &&
 		    info->devfn == pdev->devfn) {
 			list_del(&info->link);
 			list_del(&info->global);
···
 		domain_update_iommu_cap(domain);
 		spin_unlock_irqrestore(&domain->iommu_lock, tmp_flags);
 
-		spin_lock_irqsave(&iommu->lock, tmp_flags);
-		clear_bit(domain->id, iommu->domain_ids);
-		iommu->domains[domain->id] = NULL;
-		spin_unlock_irqrestore(&iommu->lock, tmp_flags);
+		if (!(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) &&
+		    !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY)) {
+			spin_lock_irqsave(&iommu->lock, tmp_flags);
+			clear_bit(domain->id, iommu->domain_ids);
+			iommu->domains[domain->id] = NULL;
+			spin_unlock_irqrestore(&iommu->lock, tmp_flags);
+		}
 	}
 
 	spin_unlock_irqrestore(&device_domain_lock, flags);
···
 	domain->iommu_count = 0;
 	domain->iommu_coherency = 0;
 	domain->iommu_snooping = 0;
+	domain->iommu_superpage = 0;
 	domain->max_addr = 0;
 	domain->nid = -1;
 
···
 	struct dma_pte *pte;
 	u64 phys = 0;
 
-	pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT);
+	pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, 0);
 	if (pte)
 		phys = dma_pte_addr(pte);
 

drivers/pci/iova.c

···
 	curr = iovad->cached32_node;
 	cached_iova = container_of(curr, struct iova, node);
 
-	if (free->pfn_lo >= cached_iova->pfn_lo)
-		iovad->cached32_node = rb_next(&free->node);
+	if (free->pfn_lo >= cached_iova->pfn_lo) {
+		struct rb_node *node = rb_next(&free->node);
+		struct iova *iova = container_of(node, struct iova, node);
+
+		/* only cache if it's below 32bit pfn */
+		if (node && iova->pfn_lo < iovad->dma_32bit_pfn)
+			iovad->cached32_node = node;
+		else
+			iovad->cached32_node = NULL;
+	}
 }
 
 /* Computes the padding size required, to make the

drivers/scsi/scsi_scan.c

···
 		kfree(sdev);
 		goto out;
 	}
-
+	blk_get_queue(sdev->request_queue);
 	sdev->request_queue->queuedata = sdev;
 	scsi_adjust_queue_depth(sdev, 0, sdev->host->cmd_per_lun);
 

drivers/scsi/scsi_sysfs.c

···
 		kfree(evt);
 	}
 
+	blk_put_queue(sdev->request_queue);
 	/* NULL queue means the device can't be used */
 	sdev->request_queue = NULL;
 

drivers/tty/n_gsm.c

···
 	gsm->tty = NULL;
 }
 
-static unsigned int gsmld_receive_buf(struct tty_struct *tty,
-		const unsigned char *cp, char *fp, int count)
+static void gsmld_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+			      char *fp, int count)
 {
 	struct gsm_mux *gsm = tty->disc_data;
 	const unsigned char *dp;
···
 	}
 	/* FASYNC if needed ? */
 	/* If clogged call tty_throttle(tty); */
-
-	return count;
 }
 
 /**

drivers/tty/n_hdlc.c

···
 				    poll_table *wait);
 static int n_hdlc_tty_open(struct tty_struct *tty);
 static void n_hdlc_tty_close(struct tty_struct *tty);
-static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
-		const __u8 *cp, char *fp, int count);
+static void n_hdlc_tty_receive(struct tty_struct *tty, const __u8 *cp,
+			       char *fp, int count);
 static void n_hdlc_tty_wakeup(struct tty_struct *tty);
 
 #define bset(p,b)	((p)[(b) >> 5] |= (1 << ((b) & 0x1f)))
···
  * Called by tty low level driver when receive data is available. Data is
  * interpreted as one HDLC frame.
  */
-static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
-		const __u8 *data, char *flags, int count)
+static void n_hdlc_tty_receive(struct tty_struct *tty, const __u8 *data,
+			       char *flags, int count)
 {
 	register struct n_hdlc *n_hdlc = tty2n_hdlc (tty);
 	register struct n_hdlc_buf *buf;
···
 		
 	/* This can happen if stuff comes in on the backup tty */
 	if (!n_hdlc || tty != n_hdlc->tty)
-		return -ENODEV;
+		return;
 		
 	/* verify line is using HDLC discipline */
 	if (n_hdlc->magic != HDLC_MAGIC) {
 		printk("%s(%d) line not using HDLC discipline\n",
 			__FILE__,__LINE__);
-		return -EINVAL;
+		return;
 	}
 	
 	if ( count>maxframe ) {
 		if (debuglevel >= DEBUG_LEVEL_INFO)	
 			printk("%s(%d) rx count>maxframesize, data discarded\n",
 			       __FILE__,__LINE__);
-		return -EINVAL;
+		return;
 	}
 
 	/* get a free HDLC buffer */	
···
 		if (debuglevel >= DEBUG_LEVEL_INFO)	
 			printk("%s(%d) no more rx buffers, data discarded\n",
 			       __FILE__,__LINE__);
-		return -EINVAL;
+		return;
 	}
 		
 	/* copy received data to HDLC buffer */
···
 	wake_up_interruptible (&tty->read_wait);
 	if (n_hdlc->tty->fasync != NULL)
 		kill_fasync (&n_hdlc->tty->fasync, SIGIO, POLL_IN);
-
-	return count;
 
 }	/* end of n_hdlc_tty_receive() */
 

drivers/tty/n_r3964.c

···
 static void r3964_set_termios(struct tty_struct *tty, struct ktermios *old);
 static unsigned int r3964_poll(struct tty_struct *tty, struct file *file,
 		struct poll_table_struct *wait);
-static unsigned int r3964_receive_buf(struct tty_struct *tty,
-		const unsigned char *cp, char *fp, int count);
+static void r3964_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+		char *fp, int count);
 
 static struct tty_ldisc_ops tty_ldisc_N_R3964 = {
 	.owner = THIS_MODULE,
···
 	return result;
 }
 
-static unsigned int r3964_receive_buf(struct tty_struct *tty,
-		const unsigned char *cp, char *fp, int count)
+static void r3964_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+			char *fp, int count)
 {
 	struct r3964_info *pInfo = tty->disc_data;
 	const unsigned char *p;
···
 		}
 
 	}
-
-	return count;
 }
 
 MODULE_LICENSE("GPL");

drivers/tty/n_tty.c

···
 	return put_user(x, ptr);
 }
 
+/**
+ *	n_tty_set__room	-	receive space
+ *	@tty: terminal
+ *
+ *	Called by the driver to find out how much data it is
+ *	permitted to feed to the line discipline without any being lost
+ *	and thus to manage flow control. Not serialized. Answers for the
+ *	"instant".
+ */
+
+static void n_tty_set_room(struct tty_struct *tty)
+{
+	/* tty->read_cnt is not read locked ? */
+	int	left = N_TTY_BUF_SIZE - tty->read_cnt - 1;
+	int old_left;
+
+	/*
+	 * If we are doing input canonicalization, and there are no
+	 * pending newlines, let characters through without limit, so
+	 * that erase characters will be handled.  Other excess
+	 * characters will be beeped.
+	 */
+	if (left <= 0)
+		left = tty->icanon && !tty->canon_data;
+	old_left = tty->receive_room;
+	tty->receive_room = left;
+
+	/* Did this open up the receive buffer? We may need to flip */
+	if (left && !old_left)
+		schedule_work(&tty->buf.work);
+}
+
 static void put_tty_queue_nolock(unsigned char c, struct tty_struct *tty)
 {
 	if (tty->read_cnt < N_TTY_BUF_SIZE) {
···
 
 	tty->canon_head = tty->canon_data = tty->erasing = 0;
 	memset(&tty->read_flags, 0, sizeof tty->read_flags);
+	n_tty_set_room(tty);
 	check_unthrottle(tty);
 }
 
···
  *	calls one at a time and in order (or using flush_to_ldisc)
  */
 
-static unsigned int n_tty_receive_buf(struct tty_struct *tty,
-		const unsigned char *cp, char *fp, int count)
+static void n_tty_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+			      char *fp, int count)
 {
 	const unsigned char *p;
 	char *f, flags = TTY_NORMAL;
 	int	i;
 	char	buf[64];
 	unsigned long cpuflags;
-	int left;
-	int ret = 0;
 
 	if (!tty->read_buf)
-		return 0;
+		return;
 
 	if (tty->real_raw) {
 		spin_lock_irqsave(&tty->read_lock, cpuflags);
···
 		memcpy(tty->read_buf + tty->read_head, cp, i);
 		tty->read_head = (tty->read_head + i) & (N_TTY_BUF_SIZE-1);
 		tty->read_cnt += i;
-		ret += i;
 		cp += i;
 		count -= i;
 
···
 		memcpy(tty->read_buf + tty->read_head, cp, i);
 		tty->read_head = (tty->read_head + i) & (N_TTY_BUF_SIZE-1);
 		tty->read_cnt += i;
-		ret += i;
 		spin_unlock_irqrestore(&tty->read_lock, cpuflags);
 	} else {
-		ret = count;
 		for (i = count, p = cp, f = fp; i; i--, p++) {
 			if (f)
 				flags = *f++;
···
 			tty->ops->flush_chars(tty);
 	}
 
+	n_tty_set_room(tty);
+
 	if ((!tty->icanon && (tty->read_cnt >= tty->minimum_to_wake)) ||
 		L_EXTPROC(tty)) {
 		kill_fasync(&tty->fasync, SIGIO, POLL_IN);
···
 	 * mode.  We don't want to throttle the driver if we're in
 	 * canonical mode and don't have a newline yet!
 	 */
-	left = N_TTY_BUF_SIZE - tty->read_cnt - 1;
-
-	if (left < TTY_THRESHOLD_THROTTLE)
+	if (tty->receive_room < TTY_THRESHOLD_THROTTLE)
 		tty_throttle(tty);
-
-	return ret;
 }
 
 int is_ignored(int sig)
···
 	if (test_bit(TTY_HW_COOK_IN, &tty->flags)) {
 		tty->raw = 1;
 		tty->real_raw = 1;
+		n_tty_set_room(tty);
 		return;
 	}
 	if (I_ISTRIP(tty) || I_IUCLC(tty) || I_IGNCR(tty) ||
···
 		else
 			tty->real_raw = 0;
 	}
+	n_tty_set_room(tty);
 	/* The termios change make the tty ready for I/O */
 	wake_up_interruptible(&tty->write_wait);
 	wake_up_interruptible(&tty->read_wait);
···
 				retval = -ERESTARTSYS;
 				break;
 			}
+			/* FIXME: does n_tty_set_room need locking ? */
+			n_tty_set_room(tty);
 			timeout = schedule_timeout(timeout);
 			continue;
 		}
···
 		 * longer than TTY_THRESHOLD_UNTHROTTLE in canonical mode,
 		 * we won't get any more characters.
 		 */
-		if (n_tty_chars_in_buffer(tty) <= TTY_THRESHOLD_UNTHROTTLE)
+		if (n_tty_chars_in_buffer(tty) <= TTY_THRESHOLD_UNTHROTTLE) {
+			n_tty_set_room(tty);
 			check_unthrottle(tty);
+		}
 
 		if (b - buf >= minimum)
 			break;
···
 	} else if (test_and_clear_bit(TTY_PUSH, &tty->flags))
 		 goto do_it_again;
 
+	n_tty_set_room(tty);
 	return retval;
 }
 

drivers/tty/tty_buffer.c

···
 		struct tty_buffer *head, *tail = tty->buf.tail;
 		int seen_tail = 0;
 		while ((head = tty->buf.head) != NULL) {
-			int copied;
 			int count;
 			char *char_buf;
 			unsigned char *flag_buf;
···
 			   line discipline as we want to empty the queue */
 			if (test_bit(TTY_FLUSHPENDING, &tty->flags))
 				break;
+			if (!tty->receive_room || seen_tail)
+				break;
+			if (count > tty->receive_room)
+				count = tty->receive_room;
 			char_buf = head->char_buf_ptr + head->read;
 			flag_buf = head->flag_buf_ptr + head->read;
+			head->read += count;
 			spin_unlock_irqrestore(&tty->buf.lock, flags);
-			copied = disc->ops->receive_buf(tty, char_buf,
+			disc->ops->receive_buf(tty, char_buf,
 							flag_buf, count);
 			spin_lock_irqsave(&tty->buf.lock, flags);
-
-			head->read += copied;
-
-			if (copied == 0 || seen_tail) {
-				schedule_work(&tty->buf.work);
-				break;
-			}
 		}
 		clear_bit(TTY_FLUSHING, &tty->flags);
 	}

drivers/tty/vt/selection.c

···
 			continue;
 		}
 		count = sel_buffer_lth - pasted;
-		count = tty->ldisc->ops->receive_buf(tty, sel_buffer + pasted,
+		count = min(count, tty->receive_room);
+		tty->ldisc->ops->receive_buf(tty, sel_buffer + pasted,
 								NULL, count);
 		pasted += count;
 	}

drivers/vhost/net.c

···
 	}
 
 	mutex_lock(&vq->mutex);
-	vhost_disable_notify(vq);
+	vhost_disable_notify(&net->dev, vq);
 
 	if (wmem < sock->sk->sk_sndbuf / 2)
 		tx_poll_stop(net);
···
 				set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
 				break;
 			}
-			if (unlikely(vhost_enable_notify(vq))) {
-				vhost_disable_notify(vq);
+			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
+				vhost_disable_notify(&net->dev, vq);
 				continue;
 			}
 			break;
···
 		return;
 
 	mutex_lock(&vq->mutex);
-	vhost_disable_notify(vq);
+	vhost_disable_notify(&net->dev, vq);
 	vhost_hlen = vq->vhost_hlen;
 	sock_hlen = vq->sock_hlen;
 
···
 			break;
 		/* OK, now we need to know about added descriptors. */
 		if (!headcount) {
-			if (unlikely(vhost_enable_notify(vq))) {
+			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
 				/* They have slipped one in as we were
 				 * doing that: check again. */
-				vhost_disable_notify(vq);
+				vhost_disable_notify(&net->dev, vq);
 				continue;
 			}
 			/* Nothing new?  Wait for eventfd to tell us

drivers/vhost/test.c

···
 		return;
 
 	mutex_lock(&vq->mutex);
-	vhost_disable_notify(vq);
+	vhost_disable_notify(&n->dev, vq);
 
 	for (;;) {
 		head = vhost_get_vq_desc(&n->dev, vq, vq->iov,
···
 			break;
 		/* Nothing new?  Wait for eventfd to tell us they refilled. */
 		if (head == vq->num) {
-			if (unlikely(vhost_enable_notify(vq))) {
-				vhost_disable_notify(vq);
+			if (unlikely(vhost_enable_notify(&n->dev, vq))) {
+				vhost_disable_notify(&n->dev, vq);
 				continue;
 			}
 			break;

drivers/vhost/vhost.c

···
 	VHOST_MEMORY_F_LOG = 0x1,
 };
 
+#define vhost_used_event(vq) ((u16 __user *)&vq->avail->ring[vq->num])
+#define vhost_avail_event(vq) ((u16 __user *)&vq->used->ring[vq->num])
+
 static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
 			    poll_table *pt)
 {
···
 	vq->last_avail_idx = 0;
 	vq->avail_idx = 0;
 	vq->last_used_idx = 0;
+	vq->signalled_used = 0;
+	vq->signalled_used_valid = false;
 	vq->used_flags = 0;
 	vq->log_used = false;
 	vq->log_addr = -1ull;
···
 	return 1;
 }
 
-static int vq_access_ok(unsigned int num,
+static int vq_access_ok(struct vhost_dev *d, unsigned int num,
 			struct vring_desc __user *desc,
 			struct vring_avail __user *avail,
 			struct vring_used __user *used)
 {
+	size_t s = vhost_has_feature(d, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
 	return access_ok(VERIFY_READ, desc, num * sizeof *desc) &&
 	       access_ok(VERIFY_READ, avail,
-			 sizeof *avail + num * sizeof *avail->ring) &&
+			 sizeof *avail + num * sizeof *avail->ring + s) &&
 	       access_ok(VERIFY_WRITE, used,
-			sizeof *used + num * sizeof *used->ring);
+			sizeof *used + num * sizeof *used->ring + s);
 }
 
 /* Can we log writes? */
···
 
 /* Verify access for write logging. */
 /* Caller should have vq mutex and device mutex */
-static int vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base)
+static int vq_log_access_ok(struct vhost_dev *d, struct vhost_virtqueue *vq,
+			    void __user *log_base)
 {
 	struct vhost_memory *mp;
+	size_t s = vhost_has_feature(d, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
 
 	mp = rcu_dereference_protected(vq->dev->memory,
 				       lockdep_is_held(&vq->mutex));
···
 			    vhost_has_feature(vq->dev, VHOST_F_LOG_ALL)) &&
 		(!vq->log_used || log_access_ok(log_base, vq->log_addr,
 					sizeof *vq->used +
-					vq->num * sizeof *vq->used->ring));
+					vq->num * sizeof *vq->used->ring + s));
 }
 
 /* Can we start vq? */
 /* Caller should have vq mutex and device mutex */
 int vhost_vq_access_ok(struct vhost_virtqueue *vq)
 {
-	return vq_access_ok(vq->num, vq->desc, vq->avail, vq->used) &&
-		vq_log_access_ok(vq, vq->log_base);
+	return vq_access_ok(vq->dev, vq->num, vq->desc, vq->avail, vq->used) &&
+		vq_log_access_ok(vq->dev, vq, vq->log_base);
 }
 
 static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
···
 
 	if (r)
 		return r;
+	vq->signalled_used_valid = false;
 	return get_user(vq->last_used_idx, &used->idx);
 }
 
···
 		 * If it is not, we don't as size might not have been setup.
 		 * We will verify when backend is configured. */
 		if (vq->private_data) {
-			if (!vq_access_ok(vq->num,
+			if (!vq_access_ok(d, vq->num,
 				(void __user *)(unsigned long)a.desc_user_addr,
 				(void __user *)(unsigned long)a.avail_user_addr,
 				(void __user *)(unsigned long)a.used_user_addr)) {
···
 			vq = d->vqs + i;
 			mutex_lock(&vq->mutex);
 			/* If ring is inactive, will check when it's enabled. */
-			if (vq->private_data && !vq_log_access_ok(vq, base))
+			if (vq->private_data && !vq_log_access_ok(d, vq, base))
 				r = -EFAULT;
 			else
 				vq->log_base = base;
···
 
 	/* On success, increment avail index. */
 	vq->last_avail_idx++;
+
+	/* Assume notifications from guest are disabled at this point,
+	 * if they aren't we would need to update avail_event index. */
+	BUG_ON(!(vq->used_flags & VRING_USED_F_NO_NOTIFY));
 	return head;
 }
 
···
 			eventfd_signal(vq->log_ctx, 1);
 	}
 	vq->last_used_idx++;
+	/* If the driver never bothers to signal in a very long while,
+	 * used index might wrap around. If that happens, invalidate
+	 * signalled_used index we stored. TODO: make sure driver
+	 * signals at least once in 2^16 and remove this. */
+	if (unlikely(vq->last_used_idx == vq->signalled_used))
+		vq->signalled_used_valid = false;
 	return 0;
 }
 
···
 			    unsigned count)
 {
 	struct vring_used_elem __user *used;
+	u16 old, new;
 	int start;
 
 	start = vq->last_used_idx % vq->num;
···
 			   ((void __user *)used - (void __user *)vq->used),
 			  count * sizeof *used);
 	}
-	vq->last_used_idx += count;
+	old = vq->last_used_idx;
+	new = (vq->last_used_idx += count);
+	/* If the driver never bothers to signal in a very long while,
+	 * used index might wrap around. If that happens, invalidate
+	 * signalled_used index we stored. TODO: make sure driver
+	 * signals at least once in 2^16 and remove this. */
+	if (unlikely((u16)(new - vq->signalled_used) < (u16)(new - old)))
+		vq->signalled_used_valid = false;
 	return 0;
 }
 
···
 	return r;
 }
 
-/* This actually signals the guest, using eventfd. */
-void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
-	__u16 flags;
-
+	__u16 old, new, event;
+	bool v;
 	/* Flush out used index updates. This is paired
 	 * with the barrier that the Guest executes when enabling
 	 * interrupts. */
 	smp_mb();
 
-	if (__get_user(flags, &vq->avail->flags)) {
-		vq_err(vq, "Failed to get flags");
-		return;
+	if (vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY) &&
+	    unlikely(vq->avail_idx == vq->last_avail_idx))
+		return true;
+
+	if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
+		__u16 flags;
+		if (__get_user(flags, &vq->avail->flags)) {
+			vq_err(vq, "Failed to get flags");
+			return true;
+		}
+		return !(flags & VRING_AVAIL_F_NO_INTERRUPT);
 	}
+	old = vq->signalled_used;
+	v = vq->signalled_used_valid;
+	new = vq->signalled_used = vq->last_used_idx;
+	vq->signalled_used_valid = true;
 
-	/* If they don't want an interrupt, don't signal, unless empty. */
-	if ((flags & VRING_AVAIL_F_NO_INTERRUPT) &&
-	    (vq->avail_idx != vq->last_avail_idx ||
-	     !vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY)))
-		return;
+	if (unlikely(!v))
+		return true;
 
+	if (get_user(event, vhost_used_event(vq))) {
+		vq_err(vq, "Failed to get used event idx");
+		return true;
+	}
+	return vring_need_event(event, new, old);
+}
+
+/* This actually signals the guest, using eventfd. */
+void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+{
 	/* Signal the Guest tell them we used something up. */
-	if (vq->call_ctx)
+	if (vq->call_ctx && vhost_notify(dev, vq))
 		eventfd_signal(vq->call_ctx, 1);
 }
 
···
 }
 
 /* OK, now we need to know about added descriptors. */
-bool vhost_enable_notify(struct vhost_virtqueue *vq)
+bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
 	u16 avail_idx;
 	int r;
···
 	if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY))
 		return false;
 	vq->used_flags &= ~VRING_USED_F_NO_NOTIFY;
-	r = put_user(vq->used_flags, &vq->used->flags);
-	if (r) {
-		vq_err(vq, "Failed to enable notification at %p: %d\n",
-		       &vq->used->flags, r);
-		return false;
+	if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
+		r = put_user(vq->used_flags, &vq->used->flags);
+		if (r) {
+			vq_err(vq, "Failed to enable notification at %p: %d\n",
+			       &vq->used->flags, r);
+			return false;
+		}
+	} else {
+		r = put_user(vq->avail_idx, vhost_avail_event(vq));
+		if (r) {
+			vq_err(vq, "Failed to update avail event index at %p: %d\n",
+			       vhost_avail_event(vq), r);
+			return false;
+		}
+	}
+	if (unlikely(vq->log_used)) {
+		void __user *used;
+		/* Make sure data is seen before log. */
+		smp_wmb();
+		used = vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX) ?
+			&vq->used->flags : vhost_avail_event(vq);
+		/* Log used flags or event index entry write. Both are 16 bit
+		 * fields. */
+		log_write(vq->log_base, vq->log_addr +
+			   (used - (void __user *)vq->used),
+			  sizeof(u16));
+		if (vq->log_ctx)
+			eventfd_signal(vq->log_ctx, 1);
 	}
 	/* They could have slipped one in as we were doing that: make
 	 * sure it's written, then check again. */
···
 }
 
 /* We don't need to be notified again. */
-void vhost_disable_notify(struct vhost_virtqueue *vq)
+void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
 	int r;
 
 	if (vq->used_flags & VRING_USED_F_NO_NOTIFY)
 		return;
 	vq->used_flags |= VRING_USED_F_NO_NOTIFY;
-	r = put_user(vq->used_flags, &vq->used->flags);
-	if (r)
-		vq_err(vq, "Failed to enable notification at %p: %d\n",
-		       &vq->used->flags, r);
+	if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
+		r = put_user(vq->used_flags, &vq->used->flags);
+		if (r)
+			vq_err(vq, "Failed to enable notification at %p: %d\n",
+			       &vq->used->flags, r);
+	}
 }

drivers/vhost/vhost.h

···
 	/* Used flags */
 	u16 used_flags;
 
+	/* Last used index value we have signalled on */
+	u16 signalled_used;
+
+	/* Last used index value we have signalled on */
+	bool signalled_used_valid;
+
 	/* Log writes to used structure. */
 	bool log_used;
 	u64 log_addr;
···
 void vhost_add_used_and_signal_n(struct vhost_dev *, struct vhost_virtqueue *,
 			       struct vring_used_elem *heads, unsigned count);
 void vhost_signal(struct vhost_dev *, struct vhost_virtqueue *);
-void vhost_disable_notify(struct vhost_virtqueue *);
-bool vhost_enable_notify(struct vhost_virtqueue *);
+void vhost_disable_notify(struct vhost_dev *, struct vhost_virtqueue *);
+bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
 
 int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
 		    unsigned int log_num, u64 len);
···
 	} while (0)
 
 enum {
-	VHOST_FEATURES = (1 << VIRTIO_F_NOTIFY_ON_EMPTY) |
-			 (1 << VIRTIO_RING_F_INDIRECT_DESC) |
-			 (1 << VHOST_F_LOG_ALL) |
-			 (1 << VHOST_NET_F_VIRTIO_NET_HDR) |
-			 (1 << VIRTIO_NET_F_MRG_RXBUF),
+	VHOST_FEATURES = (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) |
+			 (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
+			 (1ULL << VIRTIO_RING_F_EVENT_IDX) |
+			 (1ULL << VHOST_F_LOG_ALL) |
+			 (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
+			 (1ULL << VIRTIO_NET_F_MRG_RXBUF),
 };
 
 static inline int vhost_has_feature(struct vhost_dev *dev, int bit)

drivers/virtio/virtio_balloon.c

···
 	/* Waiting for host to ack the pages we released. */
 	struct completion acked;
 
-	/* Do we have to tell Host *before* we reuse pages? */
-	bool tell_host_first;
-
 	/* The pages we've told the Host we're not using. */
 	unsigned int num_pages;
 	struct list_head pages;
···
 		vb->num_pages--;
 	}
 
-	if (vb->tell_host_first) {
-		tell_host(vb, vb->deflate_vq);
-		release_pages_by_pfn(vb->pfns, vb->num_pfns);
-	} else {
-		release_pages_by_pfn(vb->pfns, vb->num_pfns);
-		tell_host(vb, vb->deflate_vq);
-	}
+
+	/*
+	 * Note that if
+	 * virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
+	 * is true, we *have* to do it in this order
+	 */
+	tell_host(vb, vb->deflate_vq);
+	release_pages_by_pfn(vb->pfns, vb->num_pfns);
 }
 
 static inline void update_stat(struct virtio_balloon *vb, int idx,
···
 		err = PTR_ERR(vb->thread);
 		goto out_del_vqs;
 	}
-
-	vb->tell_host_first
-		= virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
 
 	return 0;
 

drivers/virtio/virtio_ring.c

···
 	/* Host supports indirect buffers */
 	bool indirect;
 
+	/* Host publishes avail event idx */
+	bool event;
+
 	/* Number of free buffers */
 	unsigned int num_free;
 	/* Head of free buffer list. */
···
 void virtqueue_kick(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 new, old;
 	START_USE(vq);
 	/* Descriptors and available array need to be set before we expose the
 	 * new available array entries. */
 	virtio_wmb();
 
-	vq->vring.avail->idx += vq->num_added;
+	old = vq->vring.avail->idx;
+	new = vq->vring.avail->idx = old + vq->num_added;
 	vq->num_added = 0;
 
 	/* Need to update avail index before checking if we should notify */
 	virtio_mb();
 
-	if (!(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY))
+	if (vq->event ?
+	    vring_need_event(vring_avail_event(&vq->vring), new, old) :
+	    !(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY))
 		/* Prod other side to tell it about changes. */
 		vq->notify(&vq->vq);
 
···
 	ret = vq->data[i];
 	detach_buf(vq, i);
 	vq->last_used_idx++;
+	/* If we expect an interrupt for the next entry, tell host
+	 * by writing event index and flush out the write before
+	 * the read in the next get_buf call. */
+	if (!(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) {
+		vring_used_event(&vq->vring) = vq->last_used_idx;
+		virtio_mb();
+	}
+
 	END_USE(vq);
 	return ret;
 }
···
 
 	/* We optimistically turn back on interrupts, then check if there was
 	 * more to do. */
+	/* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
+	 * either clear the flags bit or point the event index at the next
+	 * entry. Always do both to keep code simple. */
 	vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
+	vring_used_event(&vq->vring) = vq->last_used_idx;
 	virtio_mb();
 	if (unlikely(more_used(vq))) {
 		END_USE(vq);
···
 	return true;
 }
 EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
+
+bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 bufs;
+
+	START_USE(vq);
+
+	/* We optimistically turn back on interrupts, then check if there was
+	 * more to do. */
+	/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
+	 * either clear the flags bit or point the event index at the next
+	 * entry. Always do both to keep code simple. */
+	vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
+	/* TODO: tune this threshold */
+	bufs = (u16)(vq->vring.avail->idx - vq->last_used_idx) * 3 / 4;
+	vring_used_event(&vq->vring) = vq->last_used_idx + bufs;
+	virtio_mb();
+	if (unlikely((u16)(vq->vring.used->idx - vq->last_used_idx) > bufs)) {
+		END_USE(vq);
+		return false;
+	}
+
+	END_USE(vq);
+	return true;
+}
+EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
 
 void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
 {
···
 #endif
 
 	vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC);
+	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
 
 	/* No callback?  Tell other side not to bother us. */
 	if (!callback)
···
 	for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++) {
 		switch (i) {
 		case VIRTIO_RING_F_INDIRECT_DESC:
+			break;
+		case VIRTIO_RING_F_EVENT_IDX:
 			break;
 		default:
 			/* We don't understand this bit. */

fs/autofs4/root.c

···
 	if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
-	dentry_unhash(dentry);
-
 	if (atomic_dec_and_test(&ino->count)) {
 		p_ino = autofs4_dentry_ino(dentry->d_parent);
 		if (p_ino && dentry->d_parent != dentry)

fs/block_dev.c

···
 		 * individual writeable reference is too fragile given the
 		 * way @mode is used in blkdev_get/put().
 		 */
-		if ((disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE) &&
-		    !res && (mode & FMODE_WRITE) && !bdev->bd_write_holder) {
+		if (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder &&
+		    (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) {
 			bdev->bd_write_holder = true;
 			disk_block_events(disk);
 		}

fs/btrfs/btrfs_inode.h

···
 	 */
 	u64 index_cnt;
 
-	/* the start of block group preferred for allocations. */
-	u64 block_group;
-
 	/* the fsync log has some corner cases that mean we have to check
 	 * directories to see if any unlinks have been done before
 	 * the directory was logged.  See tree-log.c for all the

fs/btrfs/ctree.c

···
 {
 	struct btrfs_path *path;
 	path = kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS);
-	if (path)
-		path->reada = 1;
 	return path;
 }
 
···
 	u64 search;
 	u64 target;
 	u64 nread = 0;
+	u64 gen;
 	int direction = path->reada;
 	struct extent_buffer *eb;
 	u32 nr;
···
 	nritems = btrfs_header_nritems(node);
 	nr = slot;
 	while (1) {
+		if (!node->map_token) {
+			unsigned long offset = btrfs_node_key_ptr_offset(nr);
+			map_private_extent_buffer(node, offset,
+						  sizeof(struct btrfs_key_ptr),
+						  &node->map_token,
+						  &node->kaddr,
+						  &node->map_start,
+						  &node->map_len, KM_USER1);
+		}
 		if (direction < 0) {
 			if (nr == 0)
 				break;
···
 		search = btrfs_node_blockptr(node, nr);
 		if ((search <= target && target - search <= 65536) ||
 		    (search > target && search - target <= 65536)) {
-			readahead_tree_block(root, search, blocksize,
-				     btrfs_node_ptr_generation(node, nr));
+			gen = btrfs_node_ptr_generation(node, nr);
+			if (node->map_token) {
+				unmap_extent_buffer(node, node->map_token,
+						    KM_USER1);
+				node->map_token = NULL;
+			}
+			readahead_tree_block(root, search, blocksize, gen);
 			nread += blocksize;
 		}
 		nscan++;
 		if ((nread > 65536 || nscan > 32))
 			break;
+	}
+	if (node->map_token) {
+		unmap_extent_buffer(node, node->map_token, KM_USER1);
+		node->map_token = NULL;
 	}
 }
 
···
 		}
 cow_done:
 		BUG_ON(!cow && ins_len);
-		if (level != btrfs_header_level(b))
-			WARN_ON(1);
-		level = btrfs_header_level(b);
 
 		p->nodes[level] = b;
 		if (!p->skip_locking)

fs/btrfs/ctree.h

···
 	 * is required instead of the faster short fsync log commits
 	 */
 	u64 last_trans_log_full_commit;
-	u64 open_ioctl_trans;
 	unsigned long mount_opt:20;
 	unsigned long compress_type:4;
 	u64 max_inline;
···
 	struct super_block *sb;
 	struct inode *btree_inode;
 	struct backing_dev_info bdi;
-	struct mutex trans_mutex;
 	struct mutex tree_log_mutex;
 	struct mutex transaction_kthread_mutex;
 	struct mutex cleaner_mutex;
···
 	struct rw_semaphore subvol_sem;
 	struct srcu_struct subvol_srcu;
 
+	spinlock_t trans_lock;
 	struct list_head trans_list;
 	struct list_head hashers;
 	struct list_head dead_roots;
···
 	atomic_t async_submit_draining;
 	atomic_t nr_async_bios;
 	atomic_t async_delalloc_pages;
+	atomic_t open_ioctl_trans;
 
 	/*
 	 * this is used by the balancing code to wait for all the pending
···
 	int closing;
 	int log_root_recovering;
 	int enospc_unlink;
+	int trans_no_join;
 
 	u64 total_pinned;
 
···
 	struct reloc_control *reloc_ctl;
 
 	spinlock_t delalloc_lock;
-	spinlock_t new_trans_lock;
 	u64 delalloc_bytes;
 
 	/* data_alloc_cluster is only used in ssd mode */
···
 #define BTRFS_MOUNT_USER_SUBVOL_RM_ALLOWED (1 << 14)
 #define BTRFS_MOUNT_ENOSPC_DEBUG	 (1 << 15)
 #define BTRFS_MOUNT_AUTO_DEFRAG		(1 << 16)
+#define BTRFS_MOUNT_INODE_MAP_CACHE	(1 << 17)
 
 #define btrfs_clear_opt(o, opt)		((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)		((o) |= BTRFS_MOUNT_##opt)
···
 void btrfs_block_rsv_release(struct btrfs_root *root,
 			     struct btrfs_block_rsv *block_rsv,
 			     u64 num_bytes);
+int btrfs_truncate_reserve_metadata(struct btrfs_trans_handle *trans,
+				    struct btrfs_root *root,
+				    struct btrfs_block_rsv *rsv);
 int btrfs_set_block_group_ro(struct btrfs_root *root,
 			     struct btrfs_block_group_cache *cache);
 int btrfs_set_block_group_rw(struct btrfs_root *root,
···
 			struct btrfs_root *root,
 			struct extent_buffer *node,
 			struct extent_buffer *parent);
+static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info)
+{
+	/*
+	 * Get synced with close_ctree()
+	 */
+	smp_mb();
+	return fs_info->closing;
+}
+
 /* root-item.c */
 int btrfs_find_root_ref(struct btrfs_root *tree_root,
 			struct btrfs_path *path,
···
 int btrfs_writepages(struct address_space *mapping,
 		     struct writeback_control *wbc);
 int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
-			     struct btrfs_root *new_root,
-			     u64 new_dirid, u64 alloc_hint);
+			     struct btrfs_root *new_root, u64 new_dirid);
 int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
 			 size_t size, struct bio *bio, unsigned long bio_flags);
 

fs/btrfs/delayed-inode.c

···
 	INIT_LIST_HEAD(&head);
 
 	next = item;
+	nitems = 0;
 
 	/*
 	 * count the number of the continuous items that we can insert in batch
···
 	delayed_node = async_node->delayed_node;
 	root = delayed_node->root;
 
-	trans = btrfs_join_transaction(root, 0);
+	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans))
 		goto free_path;
 
···
 	btrfs_set_stack_inode_transid(inode_item, trans->transid);
 	btrfs_set_stack_inode_rdev(inode_item, inode->i_rdev);
 	btrfs_set_stack_inode_flags(inode_item, BTRFS_I(inode)->flags);
-	btrfs_set_stack_inode_block_group(inode_item,
-					  BTRFS_I(inode)->block_group);
+	btrfs_set_stack_inode_block_group(inode_item, 0);
 
 	btrfs_set_stack_timespec_sec(btrfs_inode_atime(inode_item),
 				     inode->i_atime.tv_sec);
···
 			       struct btrfs_root *root, struct inode *inode)
 {
 	struct btrfs_delayed_node *delayed_node;
-	int ret;
+	int ret = 0;
 
 	delayed_node = btrfs_get_or_create_delayed_node(inode);
 	if (IS_ERR(delayed_node))

fs/btrfs/disk-io.c

···
 		vfs_check_frozen(root->fs_info->sb, SB_FREEZE_WRITE);
 		mutex_lock(&root->fs_info->transaction_kthread_mutex);
 
-		spin_lock(&root->fs_info->new_trans_lock);
+		spin_lock(&root->fs_info->trans_lock);
 		cur = root->fs_info->running_transaction;
 		if (!cur) {
-			spin_unlock(&root->fs_info->new_trans_lock);
+			spin_unlock(&root->fs_info->trans_lock);
 			goto sleep;
 		}
 
 		now = get_seconds();
 		if (!cur->blocked &&
 		    (now < cur->start_time || now - cur->start_time < 30)) {
-			spin_unlock(&root->fs_info->new_trans_lock);
+			spin_unlock(&root->fs_info->trans_lock);
 			delay = HZ * 5;
 			goto sleep;
 		}
 		transid = cur->transid;
-		spin_unlock(&root->fs_info->new_trans_lock);
+		spin_unlock(&root->fs_info->trans_lock);
 
-		trans = btrfs_join_transaction(root, 1);
+		trans = btrfs_join_transaction(root);
 		BUG_ON(IS_ERR(trans));
 		if (transid == trans->transid) {
 			ret = btrfs_commit_transaction(trans, root);
···
 	INIT_LIST_HEAD(&fs_info->ordered_operations);
 	INIT_LIST_HEAD(&fs_info->caching_block_groups);
 	spin_lock_init(&fs_info->delalloc_lock);
-	spin_lock_init(&fs_info->new_trans_lock);
+	spin_lock_init(&fs_info->trans_lock);
 	spin_lock_init(&fs_info->ref_cache_lock);
 	spin_lock_init(&fs_info->fs_roots_radix_lock);
 	spin_lock_init(&fs_info->delayed_iput_lock);
···
 	fs_info->max_inline = 8192 * 1024;
 	fs_info->metadata_ratio = 0;
 	fs_info->defrag_inodes = RB_ROOT;
+	fs_info->trans_no_join = 0;
 
 	fs_info->thread_pool_size = min_t(unsigned long,
 					  num_online_cpus() + 2, 8);
···
 	fs_info->do_barriers = 1;
 
 
-	mutex_init(&fs_info->trans_mutex);
 	mutex_init(&fs_info->ordered_operations_mutex);
 	mutex_init(&fs_info->tree_log_mutex);
 	mutex_init(&fs_info->chunk_mutex);
···
 	down_write(&root->fs_info->cleanup_work_sem);
 	up_write(&root->fs_info->cleanup_work_sem);
 
-	trans = btrfs_join_transaction(root, 1);
+	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 	ret = btrfs_commit_transaction(trans, root);
 	BUG_ON(ret);
 	/* run commit again to drop the original snapshot */
-	trans = btrfs_join_transaction(root, 1);
+	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 	btrfs_commit_transaction(trans, root);
···
 
 	WARN_ON(1);
 
-	mutex_lock(&root->fs_info->trans_mutex);
 	mutex_lock(&root->fs_info->transaction_kthread_mutex);
 
+	spin_lock(&root->fs_info->trans_lock);
 	list_splice_init(&root->fs_info->trans_list, &list);
+	root->fs_info->trans_no_join = 1;
+	spin_unlock(&root->fs_info->trans_lock);
+
 	while (!list_empty(&list)) {
 		t = list_entry(list.next, struct btrfs_transaction, list);
 		if (!t)
···
 		t->blocked = 0;
 		if (waitqueue_active(&root->fs_info->transaction_wait))
 			wake_up(&root->fs_info->transaction_wait);
-		mutex_unlock(&root->fs_info->trans_mutex);
 
-		mutex_lock(&root->fs_info->trans_mutex);
 		t->commit_done = 1;
 		if (waitqueue_active(&t->commit_wait))
 			wake_up(&t->commit_wait);
-		mutex_unlock(&root->fs_info->trans_mutex);
-
-		mutex_lock(&root->fs_info->trans_mutex);
 
 		btrfs_destroy_pending_snapshots(t);
 
 		btrfs_destroy_delalloc_inodes(root);
 
-		spin_lock(&root->fs_info->new_trans_lock);
+		spin_lock(&root->fs_info->trans_lock);
 		root->fs_info->running_transaction = NULL;
-		spin_unlock(&root->fs_info->new_trans_lock);
+		spin_unlock(&root->fs_info->trans_lock);
 
 		btrfs_destroy_marked_extents(root, &t->dirty_pages,
 					     EXTENT_DIRTY);
···
 		kmem_cache_free(btrfs_transaction_cachep, t);
 	}
 
+	spin_lock(&root->fs_info->trans_lock);
+	root->fs_info->trans_no_join = 0;
+	spin_unlock(&root->fs_info->trans_lock);
 	mutex_unlock(&root->fs_info->transaction_kthread_mutex);
-	mutex_unlock(&root->fs_info->trans_mutex);
 
 	return 0;
 }

fs/btrfs/extent-tree.c

···
 	 */
 	path->skip_locking = 1;
 	path->search_commit_root = 1;
-	path->reada = 2;
+	path->reada = 1;
 
 	key.objectid = last;
 	key.offset = 0;
···
 	nritems = btrfs_header_nritems(leaf);
 
 	while (1) {
-		smp_mb();
-		if (fs_info->closing > 1) {
+		if (btrfs_fs_closing(fs_info) > 1) {
 			last = (u64)-1;
 			break;
 		}
···
 			if (ret)
 				break;
 
-			caching_ctl->progress = last;
-			btrfs_release_path(path);
-			up_read(&fs_info->extent_commit_sem);
-			mutex_unlock(&caching_ctl->mutex);
-			if (btrfs_transaction_in_commit(fs_info))
-				schedule_timeout(1);
-			else
+			if (need_resched() ||
+			    btrfs_next_leaf(extent_root, path)) {
+				caching_ctl->progress = last;
+				btrfs_release_path(path);
+				up_read(&fs_info->extent_commit_sem);
+				mutex_unlock(&caching_ctl->mutex);
 				cond_resched();
-			goto again;
+				goto again;
+			}
+			leaf = path->nodes[0];
+			nritems = btrfs_header_nritems(leaf);
+			continue;
 		}
 
 		if (key.objectid < block_group->key.objectid) {
···
 			spin_unlock(&data_sinfo->lock);
 alloc:
 			alloc_target = btrfs_get_alloc_profile(root, 1);
-			trans = btrfs_join_transaction(root, 1);
+			trans = btrfs_join_transaction(root);
 			if (IS_ERR(trans))
 				return PTR_ERR(trans);
 
···
 
 		/* commit the current transaction and try again */
 commit_trans:
-		if (!committed && !root->fs_info->open_ioctl_trans) {
+		if (!committed &&
+		    !atomic_read(&root->fs_info->open_ioctl_trans)) {
 			committed = 1;
-			trans = btrfs_join_transaction(root, 1);
+			trans = btrfs_join_transaction(root);
 			if (IS_ERR(trans))
 				return PTR_ERR(trans);
 			ret = btrfs_commit_transaction(trans, root);
···
 		goto out;
 
 	ret = -ENOSPC;
-	trans = btrfs_join_transaction(root, 1);
+	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans))
 		goto out;
 	ret = btrfs_commit_transaction(trans, root);
···
 		if (trans)
 			return -EAGAIN;
 
-		trans = btrfs_join_transaction(root, 1);
+		trans = btrfs_join_transaction(root);
 		BUG_ON(IS_ERR(trans));
 		ret = btrfs_commit_transaction(trans, root);
 		return 0;
···
 	WARN_ON(fs_info->chunk_block_rsv.reserved > 0);
 }
 
+int btrfs_truncate_reserve_metadata(struct btrfs_trans_handle *trans,
+				    struct btrfs_root *root,
+				    struct btrfs_block_rsv *rsv)
+{
+	struct btrfs_block_rsv *trans_rsv = &root->fs_info->trans_block_rsv;
+	u64 num_bytes;
+	int ret;
+
+	/*
+	 * Truncate should be freeing data, but give us 2 items just in case it
+	 * needs to use some space.  We may want to be smarter about this in the
+	 * future.
+	 */
+	num_bytes = btrfs_calc_trans_metadata_size(root, 2);
+
+	/* We already have enough bytes, just return */
+	if (rsv->reserved >= num_bytes)
+		return 0;
+
+	num_bytes -= rsv->reserved;
+
+	/*
+	 * You should have reserved enough space before hand to do this, so this
+	 * should not fail.
+	 */
+	ret = block_rsv_migrate_bytes(trans_rsv, rsv, num_bytes);
+	BUG_ON(ret);
+
+	return 0;
+}
+
 int btrfs_trans_reserve_metadata(struct btrfs_trans_handle *trans,
 				 struct btrfs_root *root,
 				 int num_items)
···
 	struct btrfs_block_rsv *dst_rsv = root->orphan_block_rsv;
 
 	/*
-	 * one for deleting orphan item, one for updating inode and
-	 * two for calling btrfs_truncate_inode_items.
-	 *
-	 * btrfs_truncate_inode_items is a delete operation, it frees
-	 * more space than it uses in most cases. So two units of
-	 * metadata space should be enough for calling it many times.
-	 * If all of the metadata space is used, we can commit
-	 * transaction and use space it freed.
+	 * We need to hold space in order to delete our orphan item once we've
+	 * added it, so this takes the reservation so we can release it later
+	 * when we are truly done with the orphan item.
 	 */
-	u64 num_bytes = btrfs_calc_trans_metadata_size(root, 4);
+	u64 num_bytes = btrfs_calc_trans_metadata_size(root, 1);
 	return block_rsv_migrate_bytes(src_rsv, dst_rsv, num_bytes);
 }
 
 void btrfs_orphan_release_metadata(struct inode *inode)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	u64 num_bytes = btrfs_calc_trans_metadata_size(root, 4);
+	u64 num_bytes = btrfs_calc_trans_metadata_size(root, 1);
 	btrfs_block_rsv_release(root, root->orphan_block_rsv, num_bytes);
 }
 
···
 		if (unlikely(block_group->ro))
 			goto loop;
 
+		spin_lock(&block_group->free_space_ctl->tree_lock);
+		if (cached &&
+		    block_group->free_space_ctl->free_space <
+		    num_bytes + empty_size) {
+			spin_unlock(&block_group->free_space_ctl->tree_lock);
+			goto loop;
+		}
+		spin_unlock(&block_group->free_space_ctl->tree_lock);
+
 		/*
 		 * Ok we want to try and use the cluster allocator, so lets look
 		 * there, unless we are on LOOP_NO_EMPTY_SIZE, since we will
···
 			btrfs_add_free_space(block_group, offset,
 					     search_start - offset);
 		BUG_ON(offset > search_start);
+		btrfs_put_block_group(block_group);
 		break;
 loop:
 		failed_cluster_refill = false;
···
 		ret = -ENOSPC;
 	} else if (!ins->objectid) {
 		ret = -ENOSPC;
-	}
-
-	/* we found what we needed */
-	if (ins->objectid) {
-		if (!(data & BTRFS_BLOCK_GROUP_DATA))
-			trans->block_group = block_group->key.objectid;
-
-		btrfs_put_block_group(block_group);
+	} else if (ins->objectid) {
 		ret = 0;
 	}
 
···
 
 	BUG_ON(cache->ro);
 
-	trans = btrfs_join_transaction(root, 1);
+	trans = btrfs_join_transaction(root);
 	BUG_ON(IS_ERR(trans));
 
 	alloc_flags = update_block_group_flags(root, cache->flags);
···
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
+	path->reada = 1;
 
 	cache_gen = btrfs_super_cache_generation(&root->fs_info->super_copy);
 	if (cache_gen != 0 &&

fs/btrfs/extent_io.c

···
 			if (total_bytes >= max_bytes)
 				break;
 			if (!found) {
-				*start = state->start;
+				*start = max(cur_start, state->start);
 				found = 1;
 			}
 			last = state->end;

fs/btrfs/file.c

···
 	if (!btrfs_test_opt(root, AUTO_DEFRAG))
 		return 0;
 
-	if (root->fs_info->closing)
+	if (btrfs_fs_closing(root->fs_info))
 		return 0;
 
 	if (BTRFS_I(inode)->in_defrag)
···
 	if (!defrag)
 		return -ENOMEM;
 
-	defrag->ino = inode->i_ino;
+	defrag->ino = btrfs_ino(inode);
 	defrag->transid = transid;
 	defrag->root = root->root_key.objectid;
 
···
 		first_ino = defrag->ino + 1;
 		rb_erase(&defrag->rb_node, &fs_info->defrag_inodes);
 
-		if (fs_info->closing)
+		if (btrfs_fs_closing(fs_info))
 			goto next_free;
 
 		spin_unlock(&fs_info->defrag_inodes_lock);
···
 	 * the current transaction, we can bail out now without any
 	 * syncing
 	 */
-	mutex_lock(&root->fs_info->trans_mutex);
+	smp_mb();
 	if (BTRFS_I(inode)->last_trans <=
 	    root->fs_info->last_trans_committed) {
 		BTRFS_I(inode)->last_trans = 0;
-		mutex_unlock(&root->fs_info->trans_mutex);
 		goto out;
 	}
-	mutex_unlock(&root->fs_info->trans_mutex);
 
 	/*
 	 * ok we haven't committed the transaction yet, lets do a commit

fs/btrfs/free-space-cache.c

···
 		return inode;
 
 	spin_lock(&block_group->lock);
-	if (!root->fs_info->closing) {
+	if (!btrfs_fs_closing(root->fs_info)) {
 		block_group->inode = igrab(inode);
 		block_group->iref = 1;
 	}
···
 				spin_lock(&ctl->tree_lock);
 				ret = link_free_space(ctl, e);
 				spin_unlock(&ctl->tree_lock);
-				BUG_ON(ret);
+				if (ret) {
+					printk(KERN_ERR "Duplicate entries in "
+					       "free space cache, dumping\n");
+					kunmap(page);
+					unlock_page(page);
+					page_cache_release(page);
+					goto free_cache;
+				}
 			} else {
 				e->bitmap = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS);
 				if (!e->bitmap) {
···
 				ctl->op->recalc_thresholds(ctl);
 				spin_unlock(&ctl->tree_lock);
 				list_add_tail(&e->list, &bitmaps);
+				if (ret) {
+					printk(KERN_ERR "Duplicate entries in "
+					       "free space cache, dumping\n");
+					kunmap(page);
+					unlock_page(page);
+					page_cache_release(page);
+					goto free_cache;
+				}
 			}
 
 			num_entries--;
···
 	 * If we're unmounting then just return, since this does a search on the
 	 * normal root and not the commit root and we could deadlock.
 	 */
-	smp_mb();
-	if (fs_info->closing)
+	if (btrfs_fs_closing(fs_info))
 		return 0;
 
 	/*
···
 
 	num_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
 		PAGE_CACHE_SHIFT;
+
+	/* Since the first page has all of our checksums and our generation we
+	 * need to calculate the offset into the page that we can start writing
+	 * our entries.
+	 */
+	first_page_offset = (sizeof(u32) * num_pages) + sizeof(u64);
+
 	filemap_write_and_wait(inode->i_mapping);
 	btrfs_wait_ordered_range(inode, inode->i_size &
 				 ~(root->sectorsize - 1), (u64)-1);
+
+	/* make sure we don't overflow that first page */
+	if (first_page_offset + sizeof(struct btrfs_free_space_entry) >= PAGE_CACHE_SIZE) {
+		/* this is really the same as running out of space, where we also return 0 */
+		printk(KERN_CRIT "Btrfs: free space cache was too big for the crc page\n");
+		ret = 0;
+		goto out_update;
+	}
 
 	/* We need a checksum per page. */
 	crc = checksums = kzalloc(sizeof(u32) * num_pages, GFP_NOFS);
···
 		kfree(crc);
 		return -1;
 	}
-
-	/* Since the first page has all of our checksums and our generation we
-	 * need to calculate the offset into the page that we can start writing
-	 * our entries.
-	 */
-	first_page_offset = (sizeof(u32) * num_pages) + sizeof(u64);
 
 	/* Get the cluster for this block_group if it exists */
 	if (block_group && !list_empty(&block_group->cluster_list))
···
 	ret = 1;
 
 out_free:
+	kfree(checksums);
+	kfree(pages);
+
+out_update:
 	if (ret != 1) {
 		invalidate_inode_pages2_range(inode->i_mapping, 0, index);
 		BTRFS_I(inode)->generation = 0;
 	}
-	kfree(checksums);
-	kfree(pages);
 	btrfs_update_inode(trans, root, inode);
 	return ret;
 }
···
 			 * logically.
 			 */
 			if (bitmap) {
-				WARN_ON(info->bitmap);
+				if (info->bitmap) {
+					WARN_ON_ONCE(1);
+					return -EEXIST;
+				}
 				p = &(*p)->rb_right;
 			} else {
-				WARN_ON(!info->bitmap);
+				if (!info->bitmap) {
+					WARN_ON_ONCE(1);
+					return -EEXIST;
+				}
 				p = &(*p)->rb_left;
 			}
 		}
···
 		return inode;
 
 	spin_lock(&root->cache_lock);
-	if (!root->fs_info->closing)
+	if (!btrfs_fs_closing(root->fs_info))
 		root->cache_inode = igrab(inode);
 	spin_unlock(&root->cache_lock);
 
···
 	int ret = 0;
 	u64 root_gen = btrfs_root_generation(&root->root_item);
 
+	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+		return 0;
+
 	/*
 	 * If we're unmounting then just return, since this does a search on the
 	 * normal root and not the commit root and we could deadlock.
 	 */
-	smp_mb();
-	if (fs_info->closing)
+	if (btrfs_fs_closing(fs_info))
 		return 0;
 
 	path = btrfs_alloc_path();
···
 	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
 	struct inode *inode;
 	int ret;
+
+	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+		return 0;
 
 	inode = lookup_free_ino_inode(root, path);
 	if (IS_ERR(inode))

fs/btrfs/inode-map.c

···
 	int slot;
 	int ret;
 
+	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+		return 0;
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
···
 		goto out;
 
 	while (1) {
-		smp_mb();
-		if (fs_info->closing)
+		if (btrfs_fs_closing(fs_info))
 			goto out;
 
 		leaf = path->nodes[0];
···
 	int ret;
 	u64 objectid;
 
+	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+		return;
+
 	spin_lock(&root->cache_lock);
 	if (root->cached != BTRFS_CACHE_NO) {
 		spin_unlock(&root->cache_lock);
···
 
 int btrfs_find_free_ino(struct btrfs_root *root, u64 *objectid)
 {
+	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+		return btrfs_find_free_objectid(root, objectid);
+
 again:
 	*objectid = btrfs_find_ino_for_alloc(root);
 
···
 {
 	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
 	struct btrfs_free_space_ctl *pinned = root->free_ino_pinned;
+
+	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+		return;
+
 again:
 	if (root->cached == BTRFS_CACHE_FINISHED) {
 		__btrfs_add_free_space(ctl, objectid, 1);
···
 	struct btrfs_free_space *info;
 	struct rb_node *n;
 	u64 count;
+
+	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+		return;
 
 	while (1) {
 		n = rb_first(rbroot);
···
 	int prealloc;
 	bool retry = false;
 
+	/* only fs tree and subvol/snap needs ino cache */
+	if (root->root_key.objectid != BTRFS_FS_TREE_OBJECTID &&
+	    (root->root_key.objectid < BTRFS_FIRST_FREE_OBJECTID ||
+	     root->root_key.objectid > BTRFS_LAST_FREE_OBJECTID))
+		return 0;
+
+	/* Don't save inode cache if we are deleting this root */
+	if (btrfs_root_refs(&root->root_item) == 0 &&
+	    root != root->fs_info->tree_root)
+		return 0;
+
+	if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+		return 0;
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
+
 again:
 	inode = lookup_free_ino_inode(root, path);
 	if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) {

fs/btrfs/inode.c

···
 		return -ENOMEM;
 
 	path->leave_spinning = 1;
-	btrfs_set_trans_block_group(trans, inode);
 
 	key.objectid = btrfs_ino(inode);
 	key.offset = start;
···
 		}
 	}
 	if (start == 0) {
-		trans = btrfs_join_transaction(root, 1);
+		trans = btrfs_join_transaction(root);
 		BUG_ON(IS_ERR(trans));
-		btrfs_set_trans_block_group(trans, inode);
 		trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 		/* lets try to make an inline extent */
···
 			    async_extent->start + async_extent->ram_size - 1,
 			    GFP_NOFS);
 
-		trans = btrfs_join_transaction(root, 1);
+		trans = btrfs_join_transaction(root);
 		BUG_ON(IS_ERR(trans));
+		trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 		ret = btrfs_reserve_extent(trans, root,
 					   async_extent->compressed_size,
 					   async_extent->compressed_size,
···
 	int ret = 0;
 
 	BUG_ON(is_free_space_inode(root, inode));
-	trans = btrfs_join_transaction(root, 1);
+	trans = btrfs_join_transaction(root);
 	BUG_ON(IS_ERR(trans));
-	btrfs_set_trans_block_group(trans, inode);
 	trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 	num_bytes = (end - start + blocksize) & ~(blocksize - 1);
···
 	nolock = is_free_space_inode(root, inode);
 
 	if (nolock)
-		trans = btrfs_join_transaction_nolock(root, 1);
+		trans = btrfs_join_transaction_nolock(root);
 	else
-		trans = btrfs_join_transaction(root, 1);
+		trans = btrfs_join_transaction(root);
+
 	BUG_ON(IS_ERR(trans));
+	trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 	cow_start = (u64)-1;
 	cur_offset = start;
···
 {
 	struct btrfs_ordered_sum *sum;
 
-	btrfs_set_trans_block_group(trans, inode);
-
 	list_for_each_entry(sum, list, list) {
 		btrfs_csum_file_blocks(trans,
 		       BTRFS_I(inode)->root->fs_info->csum_root, sum);
···
 		ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent);
 		if (!ret) {
 			if (nolock)
-				trans = btrfs_join_transaction_nolock(root, 1);
+				trans = btrfs_join_transaction_nolock(root);
 			else
-				trans = btrfs_join_transaction(root, 1);
+				trans = btrfs_join_transaction(root);
 			BUG_ON(IS_ERR(trans));
-			btrfs_set_trans_block_group(trans, inode);
 			trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 			ret = btrfs_update_inode(trans, root, inode);
 			BUG_ON(ret);
···
 			 0, &cached_state, GFP_NOFS);
 
 	if (nolock)
-		trans = btrfs_join_transaction_nolock(root, 1);
+		trans = btrfs_join_transaction_nolock(root);
 	else
-		trans = btrfs_join_transaction(root, 1);
+		trans = btrfs_join_transaction(root);
 	BUG_ON(IS_ERR(trans));
-	btrfs_set_trans_block_group(trans, inode);
 	trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 	if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags))
···
 					(u64)-1);
 
 	if (root->orphan_block_rsv || root->orphan_item_inserted) {
-		trans = btrfs_join_transaction(root, 1);
+		trans = btrfs_join_transaction(root);
 		if (!IS_ERR(trans))
 			btrfs_end_transaction(trans, root);
 	}
···
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_key location;
 	int maybe_acls;
-	u64 alloc_group_block;
 	u32 rdev;
 	int ret;
 
 	path = btrfs_alloc_path();
 	BUG_ON(!path);
+	path->leave_spinning = 1;
 	memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));
 
 	ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
···
 	leaf = path->nodes[0];
 	inode_item = btrfs_item_ptr(leaf, path->slots[0],
 				    struct btrfs_inode_item);
+	if (!leaf->map_token)
+		map_private_extent_buffer(leaf, (unsigned long)inode_item,
+					  sizeof(struct btrfs_inode_item),
+					  &leaf->map_token, &leaf->kaddr,
+					  &leaf->map_start, &leaf->map_len,
+					  KM_USER1);
 
 	inode->i_mode = btrfs_inode_mode(leaf, inode_item);
 	inode->i_nlink = btrfs_inode_nlink(leaf, inode_item);
···
 	BTRFS_I(inode)->index_cnt = (u64)-1;
 	BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item);
 
-	alloc_group_block = btrfs_inode_block_group(leaf, inode_item);
-
 	/*
 	 * try to precache a NULL acl entry for files that don't have
 	 * any xattrs or acls
···
 	if (!maybe_acls)
 		cache_no_acl(inode);
 
-	BTRFS_I(inode)->block_group = btrfs_find_block_group(root, 0,
-						alloc_group_block, 0);
+	if (leaf->map_token) {
+		unmap_extent_buffer(leaf, leaf->map_token, KM_USER1);
+		leaf->map_token = NULL;
+	}
+
 	btrfs_free_path(path);
 	inode_item = NULL;
 
···
 	btrfs_set_inode_transid(leaf, item, trans->transid);
 	btrfs_set_inode_rdev(leaf, item, inode->i_rdev);
 	btrfs_set_inode_flags(leaf, item, BTRFS_I(inode)->flags);
-	btrfs_set_inode_block_group(leaf, item, BTRFS_I(inode)->block_group);
+	btrfs_set_inode_block_group(leaf, item, 0);
 
 	if (leaf->map_token) {
 		unmap_extent_buffer(leaf, leaf->map_token, KM_USER1);
···
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	btrfs_set_trans_block_group(trans, dir);
-
 	btrfs_record_unlink_dir(trans, dir, dentry->d_inode, 0);
 
 	ret = btrfs_unlink_inode(trans, root, dir, dentry->d_inode,
···
 	trans = __unlink_start_trans(dir, dentry);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
-
-	btrfs_set_trans_block_group(trans, dir);
 
 	if (unlikely(btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
 		err = btrfs_unlink_subvol(trans, root, dir,
···
 				err = PTR_ERR(trans);
 				break;
 			}
-			btrfs_set_trans_block_group(trans, inode);
 
 			err = btrfs_drop_extents(trans, inode, cur_offset,
 						 cur_offset + hole_size,
···
 	while (1) {
 		trans = btrfs_start_transaction(root, 0);
 		BUG_ON(IS_ERR(trans));
-		btrfs_set_trans_block_group(trans, inode);
 		trans->block_rsv = root->orphan_block_rsv;
 
 		ret = btrfs_block_rsv_check(trans, root,
···
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->reada = 2;
+
+	path->reada = 1;
 
 	if (key_type == BTRFS_DIR_INDEX_KEY) {
 		INIT_LIST_HEAD(&ins_list);
···
 	if (BTRFS_I(inode)->dummy_inode)
 		return 0;
 
-	smp_mb();
-	if (root->fs_info->closing && is_free_space_inode(root, inode))
+	if (btrfs_fs_closing(root->fs_info) && is_free_space_inode(root, inode))
 		nolock = true;
 
 	if (wbc->sync_mode == WB_SYNC_ALL) {
 		if (nolock)
-			trans = btrfs_join_transaction_nolock(root, 1);
+			trans = btrfs_join_transaction_nolock(root);
 		else
-			trans = btrfs_join_transaction(root, 1);
+			trans = btrfs_join_transaction(root);
 		if (IS_ERR(trans))
 			return PTR_ERR(trans);
-		btrfs_set_trans_block_group(trans, inode);
 		if (nolock)
 			ret = btrfs_end_transaction_nolock(trans, root);
 		else
···
 	if (BTRFS_I(inode)->dummy_inode)
 		return;
 
-	trans = btrfs_join_transaction(root, 1);
+	trans = btrfs_join_transaction(root);
 	BUG_ON(IS_ERR(trans));
-	btrfs_set_trans_block_group(trans, inode);
 
 	ret = btrfs_update_inode(trans, root, inode);
 	if (ret && ret == -ENOSPC) {
···
 				       PTR_ERR(trans));
 			return;
 		}
-		btrfs_set_trans_block_group(trans, inode);
 
 		ret = btrfs_update_inode(trans, root, inode);
 		if (ret) {
···
 				     struct btrfs_root *root,
 				     struct inode *dir,
 				     const char *name, int name_len,
-				     u64 ref_objectid, u64 objectid,
-				     u64 alloc_hint, int mode, u64 *index)
+				     u64 ref_objectid, u64 objectid, int mode,
+				     u64 *index)
 {
 	struct inode *inode;
 	struct btrfs_inode_item *inode_item;
···
 		owner = 0;
 	else
 		owner = 1;
-	BTRFS_I(inode)->block_group =
-			btrfs_find_block_group(root, 0, alloc_hint, owner);
 
 	key[0].objectid = objectid;
 	btrfs_set_key_type(&key[0], BTRFS_INODE_ITEM_KEY);
···
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	btrfs_set_trans_block_group(trans, dir);
-
 	err = btrfs_find_free_ino(root, &objectid);
 	if (err)
 		goto out_unlock;
 
 	inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
 				dentry->d_name.len, btrfs_ino(dir), objectid,
-				BTRFS_I(dir)->block_group, mode, &index);
+				mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto out_unlock;
···
 		goto out_unlock;
 	}
 
-	btrfs_set_trans_block_group(trans, inode);
 	err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
 	if (err)
 		drop_inode = 1;
···
 		init_special_inode(inode, inode->i_mode, rdev);
 		btrfs_update_inode(trans, root, inode);
 	}
-	btrfs_update_inode_block_group(trans, inode);
-	btrfs_update_inode_block_group(trans, dir);
 out_unlock:
 	nr = trans->blocks_used;
 	btrfs_end_transaction_throttle(trans, root);
···
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	btrfs_set_trans_block_group(trans, dir);
-
 	err = btrfs_find_free_ino(root, &objectid);
 	if (err)
 		goto out_unlock;
 
 	inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
 				dentry->d_name.len, btrfs_ino(dir), objectid,
-				BTRFS_I(dir)->block_group, mode, &index);
+				mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto out_unlock;
···
 		goto out_unlock;
 	}
 
-	btrfs_set_trans_block_group(trans, inode);
 	err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
 	if (err)
 		drop_inode = 1;
···
 		inode->i_op = &btrfs_file_inode_operations;
 		BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 	}
-	btrfs_update_inode_block_group(trans, inode);
-	btrfs_update_inode_block_group(trans, dir);
 out_unlock:
 	nr = trans->blocks_used;
 	btrfs_end_transaction_throttle(trans, root);
···
 
 	btrfs_inc_nlink(inode);
 	inode->i_ctime = CURRENT_TIME;
-
-	btrfs_set_trans_block_group(trans, dir);
 	ihold(inode);
 
 	err = btrfs_add_nondir(trans, dir, dentry, inode, 1, index);
···
 		drop_inode = 1;
 	} else {
 		struct dentry *parent = dget_parent(dentry);
-		btrfs_update_inode_block_group(trans, dir);
 		err = btrfs_update_inode(trans, root, inode);
 		BUG_ON(err);
 		btrfs_log_new_name(trans, inode, NULL, parent);
···
 	trans = btrfs_start_transaction(root, 5);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
-	btrfs_set_trans_block_group(trans, dir);
 
 	err = btrfs_find_free_ino(root, &objectid);
 	if (err)
···
 
 	inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
 				dentry->d_name.len, btrfs_ino(dir), objectid,
-				BTRFS_I(dir)->block_group, S_IFDIR | mode,
-				&index);
+				S_IFDIR | mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto out_fail;
···
 
 	inode->i_op = &btrfs_dir_inode_operations;
 	inode->i_fop = &btrfs_dir_file_operations;
-	btrfs_set_trans_block_group(trans, inode);
 
 	btrfs_i_size_write(inode, 0);
 	err = btrfs_update_inode(trans, root, inode);
···
 
 	d_instantiate(dentry, inode);
 	drop_on_err = 0;
-	btrfs_update_inode_block_group(trans, inode);
-	btrfs_update_inode_block_group(trans, dir);
 
 out_fail:
 	nr = trans->blocks_used;
···
 
 	if (!path) {
 		path = btrfs_alloc_path();
-		BUG_ON(!path);
+		if (!path) {
+			err = -ENOMEM;
+			goto out;
+		}
+		/*
+		 * Chances are we'll be called again, so go ahead and do
+		 * readahead
+		 */
+		path->reada = 1;
 	}
 
 	ret = btrfs_lookup_file_extent(trans, root, path,
···
 				kunmap(page);
 				free_extent_map(em);
 				em = NULL;
+
 				btrfs_release_path(path);
-				trans = btrfs_join_transaction(root, 1);
+				trans = btrfs_join_transaction(root);
+
 				if (IS_ERR(trans))
 					return ERR_CAST(trans);
 				goto again;
···
 		btrfs_drop_extent_cache(inode, start, start + len - 1, 0);
 	}
 
-	trans = btrfs_join_transaction(root, 0);
+	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans))
 		return ERR_CAST(trans);
 
···
 		 * to make sure the current transaction stays open
 		 * while we look for nocow cross refs
 		 */
-		trans = btrfs_join_transaction(root, 0);
+		trans = btrfs_join_transaction(root);
 		if (IS_ERR(trans))
 			goto must_cow;
 
···
 
 	BUG_ON(!ordered);
 
-	trans = btrfs_join_transaction(root, 1);
+	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans)) {
 		err = -ENOMEM;
 		goto out;
···
 static int btrfs_truncate(struct inode *inode)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_block_rsv *rsv;
 	int ret;
 	int err = 0;
 	struct btrfs_trans_handle *trans;
···
 	btrfs_wait_ordered_range(inode, inode->i_size & (~mask), (u64)-1);
 	btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
 
-	trans = btrfs_start_transaction(root, 5);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
+	/*
+	 * Yes ladies and gentelment, this is indeed ugly.  The fact is we have
+	 * 3 things going on here
+	 *
+	 * 1) We need to reserve space for our orphan item and the space to
+	 * delete our orphan item.  Lord knows we don't want to have a dangling
+	 * orphan item because we didn't reserve space to remove it.
+	 *
+	 * 2) We need to reserve space to update our inode.
+	 *
+	 * 3) We need to have something to cache all the space that is going to
+	 * be free'd up by the truncate operation, but also have some slack
+	 * space reserved in case it uses space during the truncate (thank you
+	 * very much snapshotting).
+	 *
+	 * And we need these to all be seperate.  The fact is we can use alot of
+	 * space doing the truncate, and we have no earthly idea how much space
+	 * we will use, so we need the truncate reservation to be seperate so it
+	 * doesn't end up using space reserved for updating the inode or
+	 * removing the orphan item.  We also need to be able to stop the
+	 * transaction and start a new one, which means we need to be able to
+	 * update the inode several times, and we have no idea of knowing how
+	 * many times that will be, so we can't just reserve 1 item for the
+	 * entirety of the opration, so that has to be done seperately as well.
+	 * Then there is the orphan item, which does indeed need to be held on
+	 * to for the whole operation, and we need nobody to touch this reserved
+	 * space except the orphan code.
+	 *
+	 * So that leaves us with
+	 *
+	 * 1) root->orphan_block_rsv - for the orphan deletion.
+	 * 2) rsv - for the truncate reservation, which we will steal from the
+	 * transaction reservation.
+	 * 3) fs_info->trans_block_rsv - this will have 1 items worth left for
+	 * updating the inode.
+	 */
+	rsv = btrfs_alloc_block_rsv(root);
+	if (!rsv)
+		return -ENOMEM;
+	btrfs_add_durable_block_rsv(root->fs_info, rsv);
 
-	btrfs_set_trans_block_group(trans, inode);
+	trans = btrfs_start_transaction(root, 4);
+	if (IS_ERR(trans)) {
+		err = PTR_ERR(trans);
+		goto out;
+	}
+
+	/*
+	 * Reserve space for the truncate process.  Truncate should be adding
+	 * space, but if there are snapshots it may end up using space.
+	 */
+	ret = btrfs_truncate_reserve_metadata(trans, root, rsv);
+	BUG_ON(ret);
 
 	ret = btrfs_orphan_add(trans, inode);
 	if (ret) {
 		btrfs_end_transaction(trans, root);
-		return ret;
+		goto out;
 	}
 
 	nr = trans->blocks_used;
 	btrfs_end_transaction(trans, root);
 	btrfs_btree_balance_dirty(root, nr);
 
-	/* Now start a transaction for the truncate */
-	trans = btrfs_start_transaction(root, 0);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
-	btrfs_set_trans_block_group(trans, inode);
-	trans->block_rsv = root->orphan_block_rsv;
+	/*
+	 * Ok so we've already migrated our bytes over for the truncate, so here
+	 * just reserve the one slot we need for updating the inode.
+	 */
+	trans = btrfs_start_transaction(root, 1);
+	if (IS_ERR(trans)) {
+		err = PTR_ERR(trans);
+		goto out;
+	}
+	trans->block_rsv = rsv;
 
 	/*
 	 * setattr is responsible for setting the ordered_data_close flag,
···
 
 	while (1) {
 		if (!trans) {
-			trans = btrfs_start_transaction(root, 0);
-			if (IS_ERR(trans))
-				return PTR_ERR(trans);
-			btrfs_set_trans_block_group(trans, inode);
-			trans->block_rsv = root->orphan_block_rsv;
-		}
+			trans = btrfs_start_transaction(root, 3);
+			if (IS_ERR(trans)) {
+				err = PTR_ERR(trans);
+				goto out;
+			}
 
-		ret = btrfs_block_rsv_check(trans, root,
-					    root->orphan_block_rsv, 0, 5);
-		if (ret == -EAGAIN) {
-			ret = btrfs_commit_transaction(trans, root);
-			if (ret)
-				return ret;
-			trans = NULL;
-			continue;
-		} else if (ret) {
-			err = ret;
-			break;
+			ret = btrfs_truncate_reserve_metadata(trans, root,
+							      rsv);
+			BUG_ON(ret);
+
+			trans->block_rsv = rsv;
 		}
 
 		ret = btrfs_truncate_inode_items(trans, root, inode,
···
 			break;
 		}
 
+		trans->block_rsv = &root->fs_info->trans_block_rsv;
 		ret = btrfs_update_inode(trans, root, inode);
 		if (ret) {
 			err = ret;
···
 	}
 
 	if (ret == 0 && inode->i_nlink > 0) {
+		trans->block_rsv = root->orphan_block_rsv;
 		ret = btrfs_orphan_del(trans, inode);
 		if (ret)
 			err = ret;
···
 		ret = btrfs_orphan_del(NULL, inode);
 	}
 
+	trans->block_rsv = &root->fs_info->trans_block_rsv;
 	ret = btrfs_update_inode(trans, root, inode);
 	if (ret && !err)
 		err = ret;
 
 	nr = trans->blocks_used;
 	ret = btrfs_end_transaction_throttle(trans, root);
+	btrfs_btree_balance_dirty(root, nr);
+
+out:
+	btrfs_free_block_rsv(root, rsv);
+
 	if (ret && !err)
 		err = ret;
-	btrfs_btree_balance_dirty(root, nr);
 
 	return err;
 }
···
  * create a new subvolume directory/inode (helper for the ioctl).
  */
 int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
-			     struct btrfs_root *new_root,
-			     u64 new_dirid, u64 alloc_hint)
+			     struct btrfs_root *new_root, u64 new_dirid)
 {
 	struct inode *inode;
 	int err;
 	u64 index = 0;
 
 	inode = btrfs_new_inode(trans, new_root, NULL, "..", 2, new_dirid,
-				new_dirid, alloc_hint, S_IFDIR | 0700, &index);
+				new_dirid, S_IFDIR | 0700, &index);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 	inode->i_op = &btrfs_dir_inode_operations;
···
 		spin_lock(&root->fs_info->ordered_extent_lock);
 		list_del_init(&BTRFS_I(inode)->ordered_operations);
 		spin_unlock(&root->fs_info->ordered_extent_lock);
-	}
-
-	if (root == root->fs_info->tree_root) {
-		struct btrfs_block_group_cache *block_group;
-
-		block_group = btrfs_lookup_block_group(root->fs_info,
-						BTRFS_I(inode)->block_group);
-		if (block_group && block_group->inode == inode) {
-			spin_lock(&block_group->lock);
-			block_group->inode = NULL;
-			spin_unlock(&block_group->lock);
-			btrfs_put_block_group(block_group);
-		} else if (block_group) {
-			btrfs_put_block_group(block_group);
-		}
 	}
 
 	spin_lock(&root->orphan_lock);
···
                 goto out_notrans;
         }
 
-	btrfs_set_trans_block_group(trans, new_dir);
-
 	if (dest != root)
 		btrfs_record_root_in_trans(trans, dest);
 
···
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	btrfs_set_trans_block_group(trans, dir);
-
 	err = btrfs_find_free_ino(root, &objectid);
 	if (err)
 		goto out_unlock;
 
 	inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
 				dentry->d_name.len, btrfs_ino(dir), objectid,
-				BTRFS_I(dir)->block_group, S_IFLNK|S_IRWXUGO,
-				&index);
+				S_IFLNK|S_IRWXUGO, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto out_unlock;
···
 		goto out_unlock;
 	}
 
-	btrfs_set_trans_block_group(trans, inode);
 	err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
 	if (err)
 		drop_inode = 1;
···
 		inode->i_op = &btrfs_file_inode_operations;
 		BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 	}
-	btrfs_update_inode_block_group(trans, inode);
-	btrfs_update_inode_block_group(trans, dir);
 	if (drop_inode)
 		goto out_unlock;
 

fs/btrfs/ioctl.c

···
 		ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
 	}
 
-	trans = btrfs_join_transaction(root, 1);
+	trans = btrfs_join_transaction(root);
 	BUG_ON(IS_ERR(trans));
 
 	ret = btrfs_update_inode(trans, root, inode);
···
 
 	btrfs_record_root_in_trans(trans, new_root);
 
-	ret = btrfs_create_subvol_root(trans, new_root, new_dirid,
-				       BTRFS_I(dir)->block_group);
+	ret = btrfs_create_subvol_root(trans, new_root, new_dirid);
 	/*
 	 * insert the directory item
 	 */
···
 	struct btrfs_file_extent_item *extent;
 	int type;
 	int ret;
+	u64 ino = btrfs_ino(inode);
 
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
 
-	min_key.objectid = inode->i_ino;
+	min_key.objectid = ino;
 	min_key.type = BTRFS_EXTENT_DATA_KEY;
 	min_key.offset = *off;
 
-	max_key.objectid = inode->i_ino;
+	max_key.objectid = ino;
 	max_key.type = (u8)-1;
 	max_key.offset = (u64)-1;
 
···
 					   path, 0, newer_than);
 		if (ret != 0)
 			goto none;
-		if (min_key.objectid != inode->i_ino)
+		if (min_key.objectid != ino)
 			goto none;
 		if (min_key.type != BTRFS_EXTENT_DATA_KEY)
 			goto none;
···
 	if (ret)
 		goto out;
 
-	mutex_lock(&root->fs_info->trans_mutex);
-	root->fs_info->open_ioctl_trans++;
-	mutex_unlock(&root->fs_info->trans_mutex);
+	atomic_inc(&root->fs_info->open_ioctl_trans);
 
 	ret = -ENOMEM;
-	trans = btrfs_start_ioctl_transaction(root, 0);
+	trans = btrfs_start_ioctl_transaction(root);
 	if (IS_ERR(trans))
 		goto out_drop;
 
···
 	return 0;
 
 out_drop:
-	mutex_lock(&root->fs_info->trans_mutex);
-	root->fs_info->open_ioctl_trans--;
-	mutex_unlock(&root->fs_info->trans_mutex);
+	atomic_dec(&root->fs_info->open_ioctl_trans);
 	mnt_drop_write(file->f_path.mnt);
 out:
 	return ret;
···
 
 	btrfs_end_transaction(trans, root);
 
-	mutex_lock(&root->fs_info->trans_mutex);
-	root->fs_info->open_ioctl_trans--;
-	mutex_unlock(&root->fs_info->trans_mutex);
+	atomic_dec(&root->fs_info->open_ioctl_trans);
 
 	mnt_drop_write(file->f_path.mnt);
 	return 0;

fs/btrfs/relocation.c

···
 		err = -ENOMEM;
 		goto out;
 	}
+	path1->reada = 1;
+	path2->reada = 2;
 
 	node = alloc_backref_node(cache);
 	if (!node) {
···
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
+	path->reada = 1;
 
 	reloc_root = root->reloc_root;
 	root_item = &reloc_root->root_item;
···
 	u64 num_bytes = 0;
 	int ret;
 
-	mutex_lock(&root->fs_info->trans_mutex);
+	spin_lock(&root->fs_info->trans_lock);
 	rc->merging_rsv_size += root->nodesize * (BTRFS_MAX_LEVEL - 1) * 2;
 	rc->merging_rsv_size += rc->nodes_relocated * 2;
-	mutex_unlock(&root->fs_info->trans_mutex);
+	spin_unlock(&root->fs_info->trans_lock);
 again:
 	if (!err) {
 		num_bytes = rc->merging_rsv_size;
···
 			err = ret;
 	}
 
-	trans = btrfs_join_transaction(rc->extent_root, 1);
+	trans = btrfs_join_transaction(rc->extent_root);
 	if (IS_ERR(trans)) {
 		if (!err)
 			btrfs_block_rsv_release(rc->extent_root,
···
 	int ret;
 again:
 	root = rc->extent_root;
-	mutex_lock(&root->fs_info->trans_mutex);
+	spin_lock(&root->fs_info->trans_lock);
 	list_splice_init(&rc->reloc_roots, &reloc_roots);
-	mutex_unlock(&root->fs_info->trans_mutex);
+	spin_unlock(&root->fs_info->trans_lock);
 
 	while (!list_empty(&reloc_roots)) {
 		found = 1;
···
 		goto out;
 	}
 
-	trans = btrfs_join_transaction(root, 0);
+	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans)) {
 		btrfs_free_path(path);
 		ret = PTR_ERR(trans);
···
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
+	path->reada = 1;
 
 	root = read_fs_root(rc->extent_root->fs_info, ref_root);
 	if (IS_ERR(root)) {
···
 static void set_reloc_control(struct reloc_control *rc)
 {
 	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
-	mutex_lock(&fs_info->trans_mutex);
+	spin_lock(&fs_info->trans_lock);
 	fs_info->reloc_ctl = rc;
-	mutex_unlock(&fs_info->trans_mutex);
+	spin_unlock(&fs_info->trans_lock);
 }
 
 static void unset_reloc_control(struct reloc_control *rc)
 {
 	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
-	mutex_lock(&fs_info->trans_mutex);
+	spin_lock(&fs_info->trans_lock);
 	fs_info->reloc_ctl = NULL;
-	mutex_unlock(&fs_info->trans_mutex);
+	spin_unlock(&fs_info->trans_lock);
 }
 
 static int check_extent_flags(u64 flags)
···
 	rc->create_reloc_tree = 1;
 	set_reloc_control(rc);
 
-	trans = btrfs_join_transaction(rc->extent_root, 1);
+	trans = btrfs_join_transaction(rc->extent_root);
 	BUG_ON(IS_ERR(trans));
 	btrfs_commit_transaction(trans, rc->extent_root);
 	return 0;
···
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
+	path->reada = 1;
 
 	ret = prepare_to_relocate(rc);
 	if (ret) {
···
 	btrfs_block_rsv_release(rc->extent_root, rc->block_rsv, (u64)-1);
 
 	/* get rid of pinned extents */
-	trans = btrfs_join_transaction(rc->extent_root, 1);
+	trans = btrfs_join_transaction(rc->extent_root);
 	if (IS_ERR(trans))
 		err = PTR_ERR(trans);
 	else
···
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
+	path->reada = -1;
 
 	key.objectid = BTRFS_TREE_RELOC_OBJECTID;
 	key.type = BTRFS_ROOT_ITEM_KEY;
···
 
 	set_reloc_control(rc);
 
-	trans = btrfs_join_transaction(rc->extent_root, 1);
+	trans = btrfs_join_transaction(rc->extent_root);
 	if (IS_ERR(trans)) {
 		unset_reloc_control(rc);
 		err = PTR_ERR(trans);
···
 
 	unset_reloc_control(rc);
 
-	trans = btrfs_join_transaction(rc->extent_root, 1);
+	trans = btrfs_join_transaction(rc->extent_root);
 	if (IS_ERR(trans))
 		err = PTR_ERR(trans);
 	else

fs/btrfs/scrub.c

···
 	}
 }
 
+static void scrub_free_bio(struct bio *bio)
+{
+	int i;
+	struct page *last_page = NULL;
+
+	if (!bio)
+		return;
+
+	for (i = 0; i < bio->bi_vcnt; ++i) {
+		if (bio->bi_io_vec[i].bv_page == last_page)
+			continue;
+		last_page = bio->bi_io_vec[i].bv_page;
+		__free_page(last_page);
+	}
+	bio_put(bio);
+}
+
 static noinline_for_stack void scrub_free_dev(struct scrub_dev *sdev)
 {
 	int i;
-	int j;
-	struct page *last_page;
 
 	if (!sdev)
 		return;
 
 	for (i = 0; i < SCRUB_BIOS_PER_DEV; ++i) {
 		struct scrub_bio *sbio = sdev->bios[i];
-		struct bio *bio;
 
 		if (!sbio)
 			break;
 
-		bio = sbio->bio;
-		if (bio) {
-			last_page = NULL;
-			for (j = 0; j < bio->bi_vcnt; ++j) {
-				if (bio->bi_io_vec[j].bv_page == last_page)
-					continue;
-				last_page = bio->bi_io_vec[j].bv_page;
-				__free_page(last_page);
-			}
-			bio_put(bio);
-		}
+		scrub_free_bio(sbio->bio);
 		kfree(sbio);
 	}
 
···
 {
 	struct scrub_dev *sdev;
 	int		i;
-	int		j;
-	int		ret;
 	struct btrfs_fs_info *fs_info = dev->dev_root->fs_info;
 
 	sdev = kzalloc(sizeof(*sdev), GFP_NOFS);
···
 		goto nomem;
 	sdev->dev = dev;
 	for (i = 0; i < SCRUB_BIOS_PER_DEV; ++i) {
-		struct bio *bio;
 		struct scrub_bio *sbio;
 
 		sbio = kzalloc(sizeof(*sbio), GFP_NOFS);
···
 			goto nomem;
 		sdev->bios[i] = sbio;
 
-		bio = bio_kmalloc(GFP_NOFS, SCRUB_PAGES_PER_BIO);
-		if (!bio)
-			goto nomem;
-
 		sbio->index = i;
 		sbio->sdev = sdev;
-		sbio->bio = bio;
 		sbio->count = 0;
 		sbio->work.func = scrub_checksum;
-		bio->bi_private = sdev->bios[i];
-		bio->bi_end_io = scrub_bio_end_io;
-		bio->bi_sector = 0;
-		bio->bi_bdev = dev->bdev;
-		bio->bi_size = 0;
-
-		for (j = 0; j < SCRUB_PAGES_PER_BIO; ++j) {
-			struct page *page;
-			page = alloc_page(GFP_NOFS);
-			if (!page)
-				goto nomem;
-
-			ret = bio_add_page(bio, page, PAGE_SIZE, 0);
-			if (!ret)
-				goto nomem;
-		}
-		WARN_ON(bio->bi_vcnt != SCRUB_PAGES_PER_BIO);
 
 		if (i != SCRUB_BIOS_PER_DEV-1)
 			sdev->bios[i]->next_free = i + 1;
···
 	int ret;
 	DECLARE_COMPLETION_ONSTACK(complete);
 
-	/* we are going to wait on this IO */
-	rw |= REQ_SYNC;
-
 	bio = bio_alloc(GFP_NOFS, 1);
 	bio->bi_bdev = bdev;
 	bio->bi_sector = sector;
···
 	bio->bi_private = &complete;
 	submit_bio(rw, bio);
 
+	/* this will also unplug the queue */
 	wait_for_completion(&complete);
 
 	ret = !test_bit(BIO_UPTODATE, &bio->bi_flags);
···
 	struct btrfs_fs_info *fs_info = sdev->dev->dev_root->fs_info;
 
 	sbio->err = err;
+	sbio->bio = bio;
 
 	btrfs_queue_worker(&fs_info->scrub_workers, &sbio->work);
 }
···
 	}
 
 out:
+	scrub_free_bio(sbio->bio);
+	sbio->bio = NULL;
 	spin_lock(&sdev->list_lock);
 	sbio->next_free = sdev->first_free;
 	sdev->first_free = sbio->index;
···
 static int scrub_submit(struct scrub_dev *sdev)
 {
 	struct scrub_bio *sbio;
+	struct bio *bio;
+	int i;
 
 	if (sdev->curr == -1)
 		return 0;
 
 	sbio = sdev->bios[sdev->curr];
 
-	sbio->bio->bi_sector = sbio->physical >> 9;
-	sbio->bio->bi_size = sbio->count * PAGE_SIZE;
-	sbio->bio->bi_next = NULL;
-	sbio->bio->bi_flags |= 1 << BIO_UPTODATE;
-	sbio->bio->bi_comp_cpu = -1;
-	sbio->bio->bi_bdev = sdev->dev->bdev;
+	bio = bio_alloc(GFP_NOFS, sbio->count);
+	if (!bio)
+		goto nomem;
+
+	bio->bi_private = sbio;
+	bio->bi_end_io = scrub_bio_end_io;
+	bio->bi_bdev = sdev->dev->bdev;
+	bio->bi_sector = sbio->physical >> 9;
+
+	for (i = 0; i < sbio->count; ++i) {
+		struct page *page;
+		int ret;
+
+		page = alloc_page(GFP_NOFS);
+		if (!page)
+			goto nomem;
+
+		ret = bio_add_page(bio, page, PAGE_SIZE, 0);
+		if (!ret) {
+			__free_page(page);
+			goto nomem;
+		}
+	}
+
 	sbio->err = 0;
 	sdev->curr = -1;
 	atomic_inc(&sdev->in_flight);
 
-	submit_bio(0, sbio->bio);
+	submit_bio(READ, bio);
 
 	return 0;
+
+nomem:
+	scrub_free_bio(bio);
+
+	return -ENOMEM;
 }
 
 static int scrub_page(struct scrub_dev *sdev, u64 logical, u64 len,
···
 		sbio->logical = logical;
 	} else if (sbio->physical + sbio->count * PAGE_SIZE != physical ||
 		   sbio->logical + sbio->count * PAGE_SIZE != logical) {
-		scrub_submit(sdev);
+		int ret;
+
+		ret = scrub_submit(sdev);
+		if (ret)
+			return ret;
 		goto again;
 	}
 	sbio->spag[sbio->count].flags = flags;
···
 		memcpy(sbio->spag[sbio->count].csum, csum, sdev->csum_size);
 	}
 	++sbio->count;
-	if (sbio->count == SCRUB_PAGES_PER_BIO || force)
-		scrub_submit(sdev);
+	if (sbio->count == SCRUB_PAGES_PER_BIO || force) {
+		int ret;
+
+		ret = scrub_submit(sdev);
+		if (ret)
+			return ret;
+	}
 
 	return 0;
 }
···
 	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_root *csum_root = fs_info->csum_root;
 	struct btrfs_extent_item *extent;
+	struct blk_plug plug;
 	u64 flags;
 	int ret;
 	int slot;
···
 	 * the scrub. This might currently (crc32) end up to be about 1MB
 	 */
 	start_stripe = 0;
+	blk_start_plug(&plug);
 again:
 	logical = base + offset + start_stripe * increment;
 	for (i = start_stripe; i < nstripes; ++i) {
···
 	scrub_submit(sdev);
 
 out:
+	blk_finish_plug(&plug);
 	btrfs_free_path(path);
 	return ret < 0 ? ret : 0;
 }
···
 	int ret;
 	struct btrfs_device *dev;
 
-	if (root->fs_info->closing)
+	if (btrfs_fs_closing(root->fs_info))
 		return -EINVAL;
 
 	/*

fs/btrfs/super.c

···
 	Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
 	Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
 	Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed,
-	Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, Opt_err,
+	Opt_enospc_debug, Opt_subvolrootid, Opt_defrag,
+	Opt_inode_cache, Opt_err,
 };
 
 static match_table_t tokens = {
···
 	{Opt_enospc_debug, "enospc_debug"},
 	{Opt_subvolrootid, "subvolrootid=%d"},
 	{Opt_defrag, "autodefrag"},
+	{Opt_inode_cache, "inode_cache"},
 	{Opt_err, NULL},
 };
 
···
 		case Opt_space_cache:
 			printk(KERN_INFO "btrfs: enabling disk space caching\n");
 			btrfs_set_opt(info->mount_opt, SPACE_CACHE);
+			break;
+		case Opt_inode_cache:
+			printk(KERN_INFO "btrfs: enabling inode map caching\n");
+			btrfs_set_opt(info->mount_opt, INODE_MAP_CACHE);
 			break;
 		case Opt_clear_cache:
 			printk(KERN_INFO "btrfs: force clearing of disk cache\n");

fs/btrfs/transaction.c

···
 {
 	WARN_ON(atomic_read(&transaction->use_count) == 0);
 	if (atomic_dec_and_test(&transaction->use_count)) {
+		BUG_ON(!list_empty(&transaction->list));
 		memset(transaction, 0, sizeof(*transaction));
 		kmem_cache_free(btrfs_transaction_cachep, transaction);
 	}
···
 /*
  * either allocate a new transaction or hop into the existing one
  */
-static noinline int join_transaction(struct btrfs_root *root)
+static noinline int join_transaction(struct btrfs_root *root, int nofail)
 {
 	struct btrfs_transaction *cur_trans;
+
+	spin_lock(&root->fs_info->trans_lock);
+	if (root->fs_info->trans_no_join) {
+		if (!nofail) {
+			spin_unlock(&root->fs_info->trans_lock);
+			return -EBUSY;
+		}
+	}
+
 	cur_trans = root->fs_info->running_transaction;
-	if (!cur_trans) {
-		cur_trans = kmem_cache_alloc(btrfs_transaction_cachep,
-					     GFP_NOFS);
-		if (!cur_trans)
-			return -ENOMEM;
-		root->fs_info->generation++;
-		atomic_set(&cur_trans->num_writers, 1);
-		cur_trans->num_joined = 0;
-		cur_trans->transid = root->fs_info->generation;
-		init_waitqueue_head(&cur_trans->writer_wait);
-		init_waitqueue_head(&cur_trans->commit_wait);
-		cur_trans->in_commit = 0;
-		cur_trans->blocked = 0;
-		atomic_set(&cur_trans->use_count, 1);
-		cur_trans->commit_done = 0;
-		cur_trans->start_time = get_seconds();
-
-		cur_trans->delayed_refs.root = RB_ROOT;
-		cur_trans->delayed_refs.num_entries = 0;
-		cur_trans->delayed_refs.num_heads_ready = 0;
-		cur_trans->delayed_refs.num_heads = 0;
-		cur_trans->delayed_refs.flushing = 0;
-		cur_trans->delayed_refs.run_delayed_start = 0;
-		spin_lock_init(&cur_trans->delayed_refs.lock);
-
-		INIT_LIST_HEAD(&cur_trans->pending_snapshots);
-		list_add_tail(&cur_trans->list, &root->fs_info->trans_list);
-		extent_io_tree_init(&cur_trans->dirty_pages,
-				     root->fs_info->btree_inode->i_mapping);
-		spin_lock(&root->fs_info->new_trans_lock);
-		root->fs_info->running_transaction = cur_trans;
-		spin_unlock(&root->fs_info->new_trans_lock);
-	} else {
+	if (cur_trans) {
+		atomic_inc(&cur_trans->use_count);
 		atomic_inc(&cur_trans->num_writers);
 		cur_trans->num_joined++;
+		spin_unlock(&root->fs_info->trans_lock);
+		return 0;
 	}
+	spin_unlock(&root->fs_info->trans_lock);
+
+	cur_trans = kmem_cache_alloc(btrfs_transaction_cachep, GFP_NOFS);
+	if (!cur_trans)
+		return -ENOMEM;
+	spin_lock(&root->fs_info->trans_lock);
+	if (root->fs_info->running_transaction) {
+		kmem_cache_free(btrfs_transaction_cachep, cur_trans);
+		cur_trans = root->fs_info->running_transaction;
+		atomic_inc(&cur_trans->use_count);
+		atomic_inc(&cur_trans->num_writers);
+		cur_trans->num_joined++;
+		spin_unlock(&root->fs_info->trans_lock);
+		return 0;
+	}
+	atomic_set(&cur_trans->num_writers, 1);
+	cur_trans->num_joined = 0;
+	init_waitqueue_head(&cur_trans->writer_wait);
+	init_waitqueue_head(&cur_trans->commit_wait);
+	cur_trans->in_commit = 0;
+	cur_trans->blocked = 0;
+	/*
+	 * One for this trans handle, one so it will live on until we
+	 * commit the transaction.
+	 */
+	atomic_set(&cur_trans->use_count, 2);
+	cur_trans->commit_done = 0;
+	cur_trans->start_time = get_seconds();
+
+	cur_trans->delayed_refs.root = RB_ROOT;
+	cur_trans->delayed_refs.num_entries = 0;
+	cur_trans->delayed_refs.num_heads_ready = 0;
+	cur_trans->delayed_refs.num_heads = 0;
+	cur_trans->delayed_refs.flushing = 0;
+	cur_trans->delayed_refs.run_delayed_start = 0;
+	spin_lock_init(&cur_trans->commit_lock);
+	spin_lock_init(&cur_trans->delayed_refs.lock);
+
+	INIT_LIST_HEAD(&cur_trans->pending_snapshots);
+	list_add_tail(&cur_trans->list, &root->fs_info->trans_list);
+	extent_io_tree_init(&cur_trans->dirty_pages,
+			     root->fs_info->btree_inode->i_mapping);
+	root->fs_info->generation++;
+	cur_trans->transid = root->fs_info->generation;
+	root->fs_info->running_transaction = cur_trans;
+	spin_unlock(&root->fs_info->trans_lock);
 
 	return 0;
 }
···
  * to make sure the old root from before we joined the transaction is deleted
  * when the transaction commits
  */
-static noinline int record_root_in_trans(struct btrfs_trans_handle *trans,
-					 struct btrfs_root *root)
+int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *root)
 {
 	if (root->ref_cows && root->last_trans < trans->transid) {
 		WARN_ON(root == root->fs_info->extent_root);
 		WARN_ON(root->commit_root != root->node);
 
+		spin_lock(&root->fs_info->fs_roots_radix_lock);
+		if (root->last_trans == trans->transid) {
+			spin_unlock(&root->fs_info->fs_roots_radix_lock);
+			return 0;
+		}
+		root->last_trans = trans->transid;
 		radix_tree_tag_set(&root->fs_info->fs_roots_radix,
 			   (unsigned long)root->root_key.objectid,
 			   BTRFS_ROOT_TRANS_TAG);
-		root->last_trans = trans->transid;
+		spin_unlock(&root->fs_info->fs_roots_radix_lock);
 		btrfs_init_reloc_root(trans, root);
 	}
-	return 0;
-}
-
-int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *root)
-{
-	if (!root->ref_cows)
-		return 0;
-
-	mutex_lock(&root->fs_info->trans_mutex);
-	if (root->last_trans == trans->transid) {
-		mutex_unlock(&root->fs_info->trans_mutex);
-		return 0;
-	}
-
-	record_root_in_trans(trans, root);
-	mutex_unlock(&root->fs_info->trans_mutex);
 	return 0;
 }
 
···
 {
 	struct btrfs_transaction *cur_trans;
 
+	spin_lock(&root->fs_info->trans_lock);
 	cur_trans = root->fs_info->running_transaction;
 	if (cur_trans && cur_trans->blocked) {
 		DEFINE_WAIT(wait);
 		atomic_inc(&cur_trans->use_count);
+		spin_unlock(&root->fs_info->trans_lock);
 		while (1) {
 			prepare_to_wait(&root->fs_info->transaction_wait, &wait,
 					TASK_UNINTERRUPTIBLE);
 			if (!cur_trans->blocked)
 				break;
-			mutex_unlock(&root->fs_info->trans_mutex);
 			schedule();
-			mutex_lock(&root->fs_info->trans_mutex);
 		}
 		finish_wait(&root->fs_info->transaction_wait, &wait);
 		put_transaction(cur_trans);
+	} else {
+		spin_unlock(&root->fs_info->trans_lock);
 	}
 }
 
···
 
 static int may_wait_transaction(struct btrfs_root *root, int type)
 {
-	if (!root->fs_info->log_root_recovering &&
-	    ((type == TRANS_START && !root->fs_info->open_ioctl_trans) ||
-	     type == TRANS_USERSPACE))
+	if (root->fs_info->log_root_recovering)
+		return 0;
+
+	if (type == TRANS_USERSPACE)
 		return 1;
+
+	if (type == TRANS_START &&
+	    !atomic_read(&root->fs_info->open_ioctl_trans))
+		return 1;
+
 	return 0;
 }
 
···
 
 	if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
 		return ERR_PTR(-EROFS);
+
+	if (current->journal_info) {
+		WARN_ON(type != TRANS_JOIN && type != TRANS_JOIN_NOLOCK);
+		h = current->journal_info;
+		h->use_count++;
+		h->orig_rsv = h->block_rsv;
+		h->block_rsv = NULL;
+		goto got_it;
+	}
 again:
 	h = kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS);
 	if (!h)
 		return ERR_PTR(-ENOMEM);
 
-	if (type != TRANS_JOIN_NOLOCK)
-		mutex_lock(&root->fs_info->trans_mutex);
 	if (may_wait_transaction(root, type))
 		wait_current_trans(root);
 
-	ret = join_transaction(root);
+	do {
+		ret = join_transaction(root, type == TRANS_JOIN_NOLOCK);
+		if (ret == -EBUSY)
+			wait_current_trans(root);
+	} while (ret == -EBUSY);
+
 	if (ret < 0) {
 		kmem_cache_free(btrfs_trans_handle_cachep, h);
-		if (type != TRANS_JOIN_NOLOCK)
-			mutex_unlock(&root->fs_info->trans_mutex);
 		return ERR_PTR(ret);
 	}
 
 	cur_trans = root->fs_info->running_transaction;
-	atomic_inc(&cur_trans->use_count);
-	if (type != TRANS_JOIN_NOLOCK)
-		mutex_unlock(&root->fs_info->trans_mutex);
 
 	h->transid = cur_trans->transid;
 	h->transaction = cur_trans;
 	h->blocks_used = 0;
-	h->block_group = 0;
 	h->bytes_reserved = 0;
 	h->delayed_ref_updates = 0;
+	h->use_count = 1;
 	h->block_rsv = NULL;
+	h->orig_rsv = NULL;
 
 	smp_mb();
 	if (cur_trans->blocked && may_wait_transaction(root, type)) {
···
 		}
 	}
 
-	if (type != TRANS_JOIN_NOLOCK)
-		mutex_lock(&root->fs_info->trans_mutex);
-	record_root_in_trans(h, root);
-	if (type != TRANS_JOIN_NOLOCK)
-		mutex_unlock(&root->fs_info->trans_mutex);
+got_it:
+	btrfs_record_root_in_trans(h, root);
 
 	if (!current->journal_info && type != TRANS_USERSPACE)
 		current->journal_info = h;
···
 {
 	return start_transaction(root, num_items, TRANS_START);
 }
-struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root,
-						   int num_blocks)
+struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root)
 {
 	return start_transaction(root, 0, TRANS_JOIN);
 }
 
-struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root,
-							  int num_blocks)
+struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root)
 {
 	return start_transaction(root, 0, TRANS_JOIN_NOLOCK);
 }
 
-struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *r,
-							 int num_blocks)
+struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root)
 {
-	return start_transaction(r, 0, TRANS_USERSPACE);
+	return start_transaction(root, 0, TRANS_USERSPACE);
 }
 
 /* wait for a transaction commit to be fully complete */
···
 				    struct btrfs_transaction *commit)
 {
 	DEFINE_WAIT(wait);
-	mutex_lock(&root->fs_info->trans_mutex);
 	while (!commit->commit_done) {
 		prepare_to_wait(&commit->commit_wait, &wait,
 				TASK_UNINTERRUPTIBLE);
 		if (commit->commit_done)
 			break;
-		mutex_unlock(&root->fs_info->trans_mutex);
 		schedule();
-		mutex_lock(&root->fs_info->trans_mutex);
 	}
-	mutex_unlock(&root->fs_info->trans_mutex);
 	finish_wait(&commit->commit_wait, &wait);
 	return 0;
 }
···
 	struct btrfs_transaction *cur_trans = NULL, *t;
 	int ret;
 
-	mutex_lock(&root->fs_info->trans_mutex);
-
 	ret = 0;
 	if (transid) {
 		if (transid <= root->fs_info->last_trans_committed)
-			goto out_unlock;
+			goto out;
 
 		/* find specified transaction */
+		spin_lock(&root->fs_info->trans_lock);
 		list_for_each_entry(t, &root->fs_info->trans_list, list) {
 			if (t->transid == transid) {
 				cur_trans = t;
+				atomic_inc(&cur_trans->use_count);
 				break;
 			}
 			if (t->transid > transid)
 				break;
 		}
+		spin_unlock(&root->fs_info->trans_lock);
 		ret = -EINVAL;
 		if (!cur_trans)
-			goto out_unlock;  /* bad transid */
+			goto out;  /* bad transid */
 	} else {
 		/* find newest transaction that is committing | committed */
+		spin_lock(&root->fs_info->trans_lock);
 		list_for_each_entry_reverse(t, &root->fs_info->trans_list,
 					    list) {
 			if (t->in_commit) {
 				if (t->commit_done)
-					goto out_unlock;
+					goto out;
 				cur_trans = t;
+				atomic_inc(&cur_trans->use_count);
 				break;
 			}
 		}
+		spin_unlock(&root->fs_info->trans_lock);
 		if (!cur_trans)
-			goto out_unlock;  /* nothing committing|committed */
+			goto out;  /* nothing committing|committed */
 	}
-
-	atomic_inc(&cur_trans->use_count);
-	mutex_unlock(&root->fs_info->trans_mutex);
 
 	wait_for_commit(root, cur_trans);
 
-	mutex_lock(&root->fs_info->trans_mutex);
 	put_transaction(cur_trans);
 	ret = 0;
-out_unlock:
-	mutex_unlock(&root->fs_info->trans_mutex);
+out:
 	return ret;
 }
 
 void btrfs_throttle(struct btrfs_root *root)
 {
-	mutex_lock(&root->fs_info->trans_mutex);
-	if (!root->fs_info->open_ioctl_trans)
+	if (!atomic_read(&root->fs_info->open_ioctl_trans))
 		wait_current_trans(root);
-	mutex_unlock(&root->fs_info->trans_mutex);
 }
 
 static int should_end_transaction(struct btrfs_trans_handle *trans,
···
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	int updates;
 
+	smp_mb();
 	if (cur_trans->blocked || cur_trans->delayed_refs.flushing)
 		return 1;
 
···
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	struct btrfs_fs_info *info = root->fs_info;
 	int count = 0;
+
+	if (--trans->use_count) {
+		trans->block_rsv = trans->orig_rsv;
+		return 0;
+	}
 
 	while (count < 4) {
 		unsigned long cur = trans->delayed_ref_updates;
···
 
 	btrfs_trans_release_metadata(trans, root);
 
-	if (lock && !root->fs_info->open_ioctl_trans &&
-	    should_end_transaction(trans, root))
+	if (lock && !atomic_read(&root->fs_info->open_ioctl_trans) &&
+	    should_end_transaction(trans, root)) {
 		trans->transaction->blocked = 1;
+		smp_wmb();
+	}
 
 	if (lock && cur_trans->blocked && !cur_trans->in_commit) {
 		if (throttle)
···
  */
 int btrfs_add_dead_root(struct btrfs_root *root)
 {
-	mutex_lock(&root->fs_info->trans_mutex);
+	spin_lock(&root->fs_info->trans_lock);
 	list_add(&root->root_list, &root->fs_info->dead_roots);
-	mutex_unlock(&root->fs_info->trans_mutex);
+	spin_unlock(&root->fs_info->trans_lock);
 	return 0;
 }
 
···
 	int ret;
 	int err = 0;
 
+	spin_lock(&fs_info->fs_roots_radix_lock);
 	while (1) {
 		ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix,
 						 (void **)gang, 0,
···
 			radix_tree_tag_clear(&fs_info->fs_roots_radix,
 					(unsigned long)root->root_key.objectid,
 					BTRFS_ROOT_TRANS_TAG);
+			spin_unlock(&fs_info->fs_roots_radix_lock);
 
 			btrfs_free_log(trans, root);
 			btrfs_update_reloc_root(trans, root);
···
 			err = btrfs_update_root(trans, fs_info->tree_root,
 						&root->root_key,
 						&root->root_item);
+			spin_lock(&fs_info->fs_roots_radix_lock);
 			if (err)
 				break;
 		}
 	}
+	spin_unlock(&fs_info->fs_roots_radix_lock);
 	return err;
 }
 
···
 		btrfs_btree_balance_dirty(info->tree_root, nr);
 		cond_resched();
 
-		if (root->fs_info->closing || ret != -EAGAIN)
+		if (btrfs_fs_closing(root->fs_info) || ret != -EAGAIN)
 			break;
 	}
 	root->defrag_running = 0;
···
 	parent = dget_parent(dentry);
 	parent_inode = parent->d_inode;
 	parent_root = BTRFS_I(parent_inode)->root;
-	record_root_in_trans(trans, parent_root);
+	btrfs_record_root_in_trans(trans, parent_root);
 
 	/*
 	 * insert the directory item
···
 	ret = btrfs_update_inode(trans, parent_root, parent_inode);
 	BUG_ON(ret);
 
-	record_root_in_trans(trans, root);
+	btrfs_record_root_in_trans(trans, root);
 	btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
 	memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
 	btrfs_check_and_init_root_item(new_root_item);
···
 int btrfs_transaction_in_commit(struct btrfs_fs_info *info)
 {
 	int ret = 0;
-	spin_lock(&info->new_trans_lock);
+	spin_lock(&info->trans_lock);
 	if (info->running_transaction)
 		ret = info->running_transaction->in_commit;
-	spin_unlock(&info->new_trans_lock);
+	spin_unlock(&info->trans_lock);
 	return ret;
 }
 
 int btrfs_transaction_blocked(struct btrfs_fs_info *info)
 {
 	int ret = 0;
-	spin_lock(&info->new_trans_lock);
+	spin_lock(&info->trans_lock);
 	if (info->running_transaction)
 		ret = info->running_transaction->blocked;
-	spin_unlock(&info->new_trans_lock);
+	spin_unlock(&info->trans_lock);
 	return ret;
 }
 
···
 				    &wait);
 			break;
 		}
-		mutex_unlock(&root->fs_info->trans_mutex);
 		schedule();
-		mutex_lock(&root->fs_info->trans_mutex);
 		finish_wait(&root->fs_info->transaction_blocked_wait, &wait);
 	}
 }
···
 				    &wait);
 			break;
 		}
-		mutex_unlock(&root->fs_info->trans_mutex);
 		schedule();
-		mutex_lock(&root->fs_info->trans_mutex);
 		finish_wait(&root->fs_info->transaction_wait,
 			    &wait);
 	}
···
 
 	INIT_DELAYED_WORK(&ac->work, do_async_commit);
 	ac->root = root;
-	ac->newtrans = btrfs_join_transaction(root, 0);
+	ac->newtrans = btrfs_join_transaction(root);
 	if (IS_ERR(ac->newtrans)) {
 		int err = PTR_ERR(ac->newtrans);
 		kfree(ac);
···
 	}
 
 	/* take transaction reference */
-	mutex_lock(&root->fs_info->trans_mutex);
 	cur_trans = trans->transaction;
 	atomic_inc(&cur_trans->use_count);
-	mutex_unlock(&root->fs_info->trans_mutex);
 
 	btrfs_end_transaction(trans, root);
 	schedule_delayed_work(&ac->work, 0);
 
 	/* wait for transaction to start and unblock */
-	mutex_lock(&root->fs_info->trans_mutex);
 	if (wait_for_unblock)
 		wait_current_trans_commit_start_and_unblock(root, cur_trans);
 	else
 		wait_current_trans_commit_start(root, cur_trans);
 	put_transaction(cur_trans);
-	mutex_unlock(&root->fs_info->trans_mutex);
 
 	return 0;
 }
···
 	ret = btrfs_run_delayed_refs(trans, root, 0);
 	BUG_ON(ret);
 
-	mutex_lock(&root->fs_info->trans_mutex);
+	spin_lock(&cur_trans->commit_lock);
 	if (cur_trans->in_commit) {
+		spin_unlock(&cur_trans->commit_lock);
 		atomic_inc(&cur_trans->use_count);
-		mutex_unlock(&root->fs_info->trans_mutex);
 		btrfs_end_transaction(trans, root);
 
 		ret = wait_for_commit(root, cur_trans);
 		BUG_ON(ret);
 
-		mutex_lock(&root->fs_info->trans_mutex);
 		put_transaction(cur_trans);
-		mutex_unlock(&root->fs_info->trans_mutex);
 
 		return 0;
 	}
 
 	trans->transaction->in_commit = 1;
 	trans->transaction->blocked = 1;
+	spin_unlock(&cur_trans->commit_lock);
 	wake_up(&root->fs_info->transaction_blocked_wait);
 
+	spin_lock(&root->fs_info->trans_lock);
 	if (cur_trans->list.prev != &root->fs_info->trans_list) {
 		prev_trans = list_entry(cur_trans->list.prev,
 					struct btrfs_transaction, list);
 		if (!prev_trans->commit_done) {
 			atomic_inc(&prev_trans->use_count);
-			mutex_unlock(&root->fs_info->trans_mutex);
+			spin_unlock(&root->fs_info->trans_lock);
 
 			wait_for_commit(root, prev_trans);
 
-			mutex_lock(&root->fs_info->trans_mutex);
 			put_transaction(prev_trans);
+		} else {
+			spin_unlock(&root->fs_info->trans_lock);
 		}
+	} else {
+		spin_unlock(&root->fs_info->trans_lock);
 	}
 
 	if (now < cur_trans->start_time || now - cur_trans->start_time < 1)
···
 
 	do {
 		int snap_pending = 0;
+
 		joined = cur_trans->num_joined;
 		if (!list_empty(&trans->transaction->pending_snapshots))
 			snap_pending = 1;
 
 		WARN_ON(cur_trans != trans->transaction);
-		mutex_unlock(&root->fs_info->trans_mutex);
 
 		if (flush_on_commit || snap_pending) {
 			btrfs_start_delalloc_inodes(root, 1);
···
 		prepare_to_wait(&cur_trans->writer_wait, &wait,
 				TASK_UNINTERRUPTIBLE);
 
-		smp_mb();
 		if (atomic_read(&cur_trans->num_writers) > 1)
 			schedule_timeout(MAX_SCHEDULE_TIMEOUT);
 		else if (should_grow)
 			schedule_timeout(1);
 
-		mutex_lock(&root->fs_info->trans_mutex);
 		finish_wait(&cur_trans->writer_wait, &wait);
+		spin_lock(&root->fs_info->trans_lock);
+		root->fs_info->trans_no_join = 1;
+		spin_unlock(&root->fs_info->trans_lock);
 	} while (atomic_read(&cur_trans->num_writers) > 1 ||
 		 (should_grow && cur_trans->num_joined != joined));
 
···
 	btrfs_prepare_extent_commit(trans, root);
 
 	cur_trans = root->fs_info->running_transaction;
-	spin_lock(&root->fs_info->new_trans_lock);
-	root->fs_info->running_transaction = NULL;
-	spin_unlock(&root->fs_info->new_trans_lock);
 
 	btrfs_set_root_node(&root->fs_info->tree_root->root_item,
 			    root->fs_info->tree_root->node);
···
 	       sizeof(root->fs_info->super_copy));
 
 	trans->transaction->blocked = 0;
+	spin_lock(&root->fs_info->trans_lock);
+	root->fs_info->running_transaction = NULL;
+	root->fs_info->trans_no_join = 0;
+	spin_unlock(&root->fs_info->trans_lock);
 
 	wake_up(&root->fs_info->transaction_wait);
 
-	mutex_unlock(&root->fs_info->trans_mutex);
 	ret = btrfs_write_and_wait_transaction(trans, root);
 	BUG_ON(ret);
 	write_ctree_super(trans, root, 0);
···
 
 	btrfs_finish_extent_commit(trans, root);
 
-	mutex_lock(&root->fs_info->trans_mutex);
-
 	cur_trans->commit_done = 1;
 
 	root->fs_info->last_trans_committed = cur_trans->transid;
 
 	wake_up(&cur_trans->commit_wait);
 
+	spin_lock(&root->fs_info->trans_lock);
 	list_del_init(&cur_trans->list);
+	spin_unlock(&root->fs_info->trans_lock);
+
 	put_transaction(cur_trans);
 	put_transaction(cur_trans);
 
 	trace_btrfs_transaction_commit(root);
-
-	mutex_unlock(&root->fs_info->trans_mutex);
 
 	btrfs_scrub_continue(root);
 
···
 	LIST_HEAD(list);
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
-	mutex_lock(&fs_info->trans_mutex);
+	spin_lock(&fs_info->trans_lock);
 	list_splice_init(&fs_info->dead_roots, &list);
-	mutex_unlock(&fs_info->trans_mutex);
+	spin_unlock(&fs_info->trans_lock);
 
 	while (!list_empty(&list)) {
 		root = list_entry(list.next, struct btrfs_root, root_list);

fs/btrfs/transaction.h

···
 	 * transaction can end
 	 */
 	atomic_t num_writers;
+	atomic_t use_count;
 
 	unsigned long num_joined;
+
+	spinlock_t commit_lock;
 	int in_commit;
-	atomic_t use_count;
 	int commit_done;
 	int blocked;
 	struct list_head list;
···
 
 struct btrfs_trans_handle {
 	u64 transid;
-	u64 block_group;
 	u64 bytes_reserved;
+	unsigned long use_count;
 	unsigned long blocks_reserved;
 	unsigned long blocks_used;
 	unsigned long delayed_ref_updates;
 	struct btrfs_transaction *transaction;
 	struct btrfs_block_rsv *block_rsv;
+	struct btrfs_block_rsv *orig_rsv;
 };
 
 struct btrfs_pending_snapshot {
···
 	struct list_head list;
 };
 
-static inline void btrfs_set_trans_block_group(struct btrfs_trans_handle *trans,
-					       struct inode *inode)
-{
-	trans->block_group = BTRFS_I(inode)->block_group;
-}
-
-static inline void btrfs_update_inode_block_group(
-					  struct btrfs_trans_handle *trans,
-					  struct inode *inode)
-{
-	BTRFS_I(inode)->block_group = trans->block_group;
-}
-
 static inline void btrfs_set_inode_last_trans(struct btrfs_trans_handle *trans,
 					      struct inode *inode)
 {
···
 				 struct btrfs_root *root);
 struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
 						   int num_items);
-struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root,
-						  int num_blocks);
-struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root,
-							  int num_blocks);
-struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *r,
-							 int num_blocks);
+struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root);
+struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root);
+struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root);
 int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid);
 int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans,
 				     struct btrfs_root *root);

fs/btrfs/volumes.c

···
 		BUG_ON(!new_device);
 		memcpy(new_device, device, sizeof(*new_device));
 		new_device->name = kstrdup(device->name, GFP_NOFS);
-		BUG_ON(!new_device->name);
+		BUG_ON(device->name && !new_device->name);
 		new_device->bdev = NULL;
 		new_device->writeable = 0;
 		new_device->in_fs_metadata = 0;

fs/btrfs/xattr.c

···
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	btrfs_set_trans_block_group(trans, inode);
-
 	ret = do_setxattr(trans, inode, name, value, size, flags);
 	if (ret)
 		goto out;

fs/namei.c

···
 	if (error)
 		goto out;
 
+	shrink_dcache_parent(dentry);
 	error = dir->i_op->rmdir(dir, dentry);
 	if (error)
 		goto out;
···
 	if (d_mountpoint(old_dentry) || d_mountpoint(new_dentry))
 		goto out;
 
+	if (target)
+		shrink_dcache_parent(new_dentry);
 	error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
 	if (error)
 		goto out;

fs/partitions/check.c

···
 				   struct device_attribute *attr, char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
-	struct gendisk *disk = dev_to_disk(dev);
-	unsigned int alignment = 0;
-
-	if (disk->queue)
-		alignment = queue_limit_discard_alignment(&disk->queue->limits,
-								p->start_sect);
-	return sprintf(buf, "%u\n", alignment);
+	return sprintf(buf, "%u\n", p->discard_alignment);
 }
 
 ssize_t part_stat_show(struct device *dev,
···
 	p->start_sect = start;
 	p->alignment_offset =
 		queue_limit_alignment_offset(&disk->queue->limits, start);
+	p->discard_alignment =
+		queue_limit_discard_alignment(&disk->queue->limits, start);
 	p->nr_sects = len;
 	p->partno = partno;
 	p->policy = get_disk_ro(disk);

fs/ubifs/io.c

···
 	ubifs_assert(wbuf->size % c->min_io_size == 0);
 	ubifs_assert(mutex_is_locked(&wbuf->io_mutex));
 	ubifs_assert(!c->ro_media && !c->ro_mount);
+	ubifs_assert(!c->space_fixup);
 	if (c->leb_size - wbuf->offs >= c->max_write_size)
 		ubifs_assert(!((wbuf->offs + wbuf->size) % c->max_write_size));
 
···
 	ubifs_assert(lnum >= 0 && lnum < c->leb_cnt && offs >= 0);
 	ubifs_assert(offs % c->min_io_size == 0 && offs < c->leb_size);
 	ubifs_assert(!c->ro_media && !c->ro_mount);
+	ubifs_assert(!c->space_fixup);
 
 	if (c->ro_error)
 		return -EROFS;

fs/ubifs/journal.c

···
 
 out_release:
 	release_head(c, BASEHD);
+	kfree(dent);
 out_ro:
 	ubifs_ro_mode(c, err);
 	if (last_reference)

fs/ubifs/orphan.c

···
 		if (IS_ERR(sleb)) {
 			if (PTR_ERR(sleb) == -EUCLEAN)
 				sleb = ubifs_recover_leb(c, lnum, 0,
-							 c->sbuf, 0);
+							 c->sbuf, -1);
 			if (IS_ERR(sleb)) {
 				err = PTR_ERR(sleb);
 				break;

fs/ubifs/recovery.c

···
 }
 
 /**
- * drop_last_node - drop the last node or group of nodes.
+ * drop_last_group - drop the last group of nodes.
  * @sleb: scanned LEB information
  * @offs: offset of dropped nodes is returned here
- * @grouped: non-zero if whole group of nodes have to be dropped
  *
  * This is a helper function for 'ubifs_recover_leb()' which drops the last
- * node of the scanned LEB or the last group of nodes if @grouped is not zero.
- * This function returns %1 if a node was dropped and %0 otherwise.
+ * group of nodes of the scanned LEB.
  */
-static int drop_last_node(struct ubifs_scan_leb *sleb, int *offs, int grouped)
+static void drop_last_group(struct ubifs_scan_leb *sleb, int *offs)
 {
-	int dropped = 0;
-
 	while (!list_empty(&sleb->nodes)) {
 		struct ubifs_scan_node *snod;
 		struct ubifs_ch *ch;
···
 				  list);
 		ch = snod->node;
 		if (ch->group_type != UBIFS_IN_NODE_GROUP)
-			return dropped;
-		dbg_rcvry("dropping node at %d:%d", sleb->lnum, snod->offs);
+			break;
+
+		dbg_rcvry("dropping grouped node at %d:%d",
+			  sleb->lnum, snod->offs);
 		*offs = snod->offs;
 		list_del(&snod->list);
 		kfree(snod);
 		sleb->nodes_cnt -= 1;
-		dropped = 1;
-		if (!grouped)
-			break;
 	}
-	return dropped;
+}
+
+/**
+ * drop_last_node - drop the last node.
+ * @sleb: scanned LEB information
+ * @offs: offset of dropped nodes is returned here
+ * @grouped: non-zero if whole group of nodes have to be dropped
+ *
+ * This is a helper function for 'ubifs_recover_leb()' which drops the last
+ * node of the scanned LEB.
+ */
+static void drop_last_node(struct ubifs_scan_leb *sleb, int *offs)
+{
+	struct ubifs_scan_node *snod;
+
+	if (!list_empty(&sleb->nodes)) {
+		snod = list_entry(sleb->nodes.prev, struct ubifs_scan_node,
+				  list);
+
+		dbg_rcvry("dropping last node at %d:%d", sleb->lnum, snod->offs);
+		*offs = snod->offs;
+		list_del(&snod->list);
+		kfree(snod);
+		sleb->nodes_cnt -= 1;
+	}
 }
 
 /**
···
  * @lnum: LEB number
  * @offs: offset
  * @sbuf: LEB-sized buffer to use
- * @grouped: nodes may be grouped for recovery
+ * @jhead: journal head number this LEB belongs to (%-1 if the LEB does not
+ *         belong to any journal head)
  *
  * This function does a scan of a LEB, but caters for errors that might have
  * been caused by the unclean unmount from which we are attempting to recover.
···
  * found, and a negative error code in case of failure.
  */
 struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
-					 int offs, void *sbuf, int grouped)
+					 int offs, void *sbuf, int jhead)
 {
 	int ret = 0, err, len = c->leb_size - offs, start = offs, min_io_unit;
+	int grouped = jhead == -1 ? 0 : c->jheads[jhead].grouped;
 	struct ubifs_scan_leb *sleb;
 	void *buf = sbuf + offs;
 
-	dbg_rcvry("%d:%d", lnum, offs);
+	dbg_rcvry("%d:%d, jhead %d, grouped %d", lnum, offs, jhead, grouped);
 
 	sleb = ubifs_start_scan(c, lnum, offs, sbuf);
 	if (IS_ERR(sleb))
···
 		 * Scan quietly until there is an error from which we cannot
 		 * recover
 		 */
-		ret = ubifs_scan_a_node(c, buf, len, lnum, offs, 0);
+		ret = ubifs_scan_a_node(c, buf, len, lnum, offs, 1);
 		if (ret == SCANNED_A_NODE) {
 			/* A valid node, and not a padding node */
 			struct ubifs_ch *ch = buf;
···
 		 * If nodes are grouped, always drop the incomplete group at
 		 * the end.
 		 */
-		drop_last_node(sleb, &offs, 1);
+		drop_last_group(sleb, &offs);
 
-	/*
-	 * While we are in the middle of the same min. I/O unit keep dropping
-	 * nodes. So basically, what we want is to make sure that the last min.
-	 * I/O unit where we saw the corruption is dropped completely with all
-	 * the uncorrupted node which may possibly sit there.
-	 *
-	 * In other words, let's name the min. I/O unit where the corruption
-	 * starts B, and the previous min. I/O unit A. The below code tries to
-	 * deal with a situation when half of B contains valid nodes or the end
-	 * of a valid node, and the second half of B contains corrupted data or
-	 * garbage. This means that UBIFS had been writing to B just before the
-	 * power cut happened. I do not know how realistic is this scenario
-	 * that half of the min. I/O unit had been written successfully and the
-	 * other half not, but this is possible in our 'failure mode emulation'
-	 * infrastructure at least.
-	 *
-	 * So what is the problem, why we need to drop those nodes? Whey can't
-	 * we just clean-up the second half of B by putting a padding node
-	 * there? We can, and this works fine with one exception which was
-	 * reproduced with power cut emulation testing and happens extremely
-	 * rarely. The description follows, but it is worth noting that that is
-	 * only about the GC head, so we could do this trick only if the bud
-	 * belongs to the GC head, but it does not seem to be worth an
-	 * additional "if" statement.
-	 *
-	 * So, imagine the file-system is full, we run GC which is moving valid
-	 * nodes from LEB X to LEB Y (obviously, LEB Y is the current GC head
-	 * LEB). The @c->gc_lnum is -1, which means that GC will retain LEB X
-	 * and will try to continue. Imagine that LEB X is currently the
-	 * dirtiest LEB, and the amount of used space in LEB Y is exactly the
-	 * same as amount of free space in LEB X.
-	 *
-	 * And a power cut happens when nodes are moved from LEB X to LEB Y. We
-	 * are here trying to recover LEB Y which is the GC head LEB. We find
-	 * the min. I/O unit B as described above. Then we clean-up LEB Y by
-	 * padding min. I/O unit. And later 'ubifs_rcvry_gc_commit()' function
-	 * fails, because it cannot find a dirty LEB which could be GC'd into
-	 * LEB Y! Even LEB X does not match because the amount of valid nodes
-	 * there does not fit the free space in LEB Y any more! And this is
-	 * because of the padding node which we added to LEB Y. The
-	 * user-visible effect of this which I once observed and analysed is
-	 * that we cannot mount the file-system with -ENOSPC error.
-	 *
-	 * So obviously, to make sure that situation does not happen we should
-	 * free min. I/O unit B in LEB Y completely and the last used min. I/O
-	 * unit in LEB Y should be A. This is basically what the below code
-	 * tries to do.
-	 */
-	while (min_io_unit == round_down(offs, c->min_io_size) &&
-	       min_io_unit != offs &&
-	       drop_last_node(sleb, &offs, grouped));
+	if (jhead == GCHD) {
+		/*
+		 * If this LEB belongs to the GC head then while we are in the
+		 * middle of the same min. I/O unit keep dropping nodes. So
+		 * basically, what we want is to make sure that the last min.
+		 * I/O unit where we saw the corruption is dropped completely
+		 * with all the uncorrupted nodes which may possibly sit there.
+		 *
+		 * In other words, let's name the min. I/O unit where the
+		 * corruption starts B, and the previous min. I/O unit A. The
+		 * below code tries to deal with a situation when half of B
+		 * contains valid nodes or the end of a valid node, and the
+		 * second half of B contains corrupted data or garbage. This
+		 * means that UBIFS had been writing to B just before the power
+		 * cut happened. I do not know how realistic is this scenario
+		 * that half of the min. I/O unit had been written successfully
+		 * and the other half not, but this is possible in our 'failure
+		 * mode emulation' infrastructure at least.
+		 *
+		 * So what is the problem, why we need to drop those nodes? Why
+		 * can't we just clean-up the second half of B by putting a
+		 * padding node there? We can, and this works fine with one
+		 * exception which was reproduced with power cut emulation
+		 * testing and happens extremely rarely.
+		 *
+		 * Imagine the file-system is full, we run GC which starts
+		 * moving valid nodes from LEB X to LEB Y (obviously, LEB Y is
+		 * the current GC head LEB). The @c->gc_lnum is -1, which means
+		 * that GC will retain LEB X and will try to continue. Imagine
+		 * that LEB X is currently the dirtiest LEB, and the amount of
+		 * used space in LEB Y is exactly the same as amount of free
+		 * space in LEB X.
+		 *
+		 * And a power cut happens when nodes are moved from LEB X to
+		 * LEB Y. We are here trying to recover LEB Y which is the GC
+		 * head LEB. We find the min. I/O unit B as described above.
+		 * Then we clean-up LEB Y by padding min. I/O unit. And later
+		 * 'ubifs_rcvry_gc_commit()' function fails, because it cannot
+		 * find a dirty LEB which could be GC'd into LEB Y! Even LEB X
+		 * does not match because the amount of valid nodes there does
+		 * not fit the free space in LEB Y any more! And this is
+		 * because of the padding node which we added to LEB Y. The
+		 * user-visible effect of this which I once observed and
+		 * analysed is that we cannot mount the file-system with
+		 * -ENOSPC error.
+		 *
+		 * So obviously, to make sure that situation does not happen we
+		 * should free min. I/O unit B in LEB Y completely and the last
+		 * used min. I/O unit in LEB Y should be A. This is basically
+		 * what the below code tries to do.
+		 */
+		while (offs > min_io_unit)
+			drop_last_node(sleb, &offs);
+	}
 
 	buf = sbuf + offs;
 	len = c->leb_size - offs;
···
 		}
 		ubifs_scan_destroy(sleb);
 	}
-	return ubifs_recover_leb(c, lnum, offs, sbuf, 0);
+	return ubifs_recover_leb(c, lnum, offs, sbuf, -1);
 }
 
 /**

fs/ubifs/replay.c

···
 		 * these LEBs could possibly be written to at the power cut
 		 * time.
 		 */
-		sleb = ubifs_recover_leb(c, lnum, offs, c->sbuf,
-					 b->bud->jhead != GCHD);
+		sleb = ubifs_recover_leb(c, lnum, offs, c->sbuf, b->bud->jhead);
 	else
 		sleb = ubifs_scan(c, lnum, offs, c->sbuf, 0);
 	if (IS_ERR(sleb))

fs/ubifs/shrinker.c

···
 	long clean_zn_cnt = atomic_long_read(&ubifs_clean_zn_cnt);
 
 	if (nr == 0)
-		return clean_zn_cnt;
+		/*
+		 * Due to the way UBIFS updates the clean znode counter it may
+		 * temporarily be negative.
+		 */
+		return clean_zn_cnt >= 0 ? clean_zn_cnt : 1;
 
 	if (!clean_zn_cnt) {
 		/*

fs/ubifs/super.c

···
 
 		c->jheads[i].wbuf.sync_callback = &bud_wbuf_callback;
 		c->jheads[i].wbuf.jhead = i;
+		c->jheads[i].grouped = 1;
 	}
 
 	c->jheads[BASEHD].wbuf.dtype = UBI_SHORTTERM;
 	/*
 	 * Garbage Collector head likely contains long-term data and
-	 * does not need to be synchronized by timer.
+	 * does not need to be synchronized by timer. Also GC head nodes are
+	 * not grouped.
 	 */
 	c->jheads[GCHD].wbuf.dtype = UBI_LONGTERM;
 	c->jheads[GCHD].wbuf.no_timer = 1;
+	c->jheads[GCHD].grouped = 0;
 
 	return 0;
 }
···
 	if ((c->mst_node->flags & cpu_to_le32(UBIFS_MST_DIRTY)) != 0) {
 		ubifs_msg("recovery needed");
 		c->need_recovery = 1;
-		if (!c->ro_mount) {
-			err = ubifs_recover_inl_heads(c, c->sbuf);
-			if (err)
-				goto out_master;
-		}
-	} else if (!c->ro_mount) {
+	}
+
+	if (c->need_recovery && !c->ro_mount) {
+		err = ubifs_recover_inl_heads(c, c->sbuf);
+		if (err)
+			goto out_master;
+	}
+
+	err = ubifs_lpt_init(c, 1, !c->ro_mount);
+	if (err)
+		goto out_master;
+
+	if (!c->ro_mount && c->space_fixup) {
+		err = ubifs_fixup_free_space(c);
+		if (err)
+			goto out_master;
+	}
+
+	if (!c->ro_mount) {
 		/*
 		 * Set the "dirty" flag so that if we reboot uncleanly we
 		 * will notice this immediately on the next mount.
···
 		c->mst_node->flags |= cpu_to_le32(UBIFS_MST_DIRTY);
 		err = ubifs_write_master(c);
 		if (err)
-			goto out_master;
+			goto out_lpt;
 	}
-
-	err = ubifs_lpt_init(c, 1, !c->ro_mount);
-	if (err)
-		goto out_lpt;
 
 	err = dbg_check_idx_size(c, c->bi.old_idx_sz);
 	if (err)
···
 		}
 	} else
 		ubifs_assert(c->lst.taken_empty_lebs > 0);
-
-	if (!c->ro_mount && c->space_fixup) {
-		err = ubifs_fixup_free_space(c);
-		if (err)
-			goto out_infos;
-	}
 
 	err = dbg_check_filesystem(c);
 	if (err)

fs/ubifs/tnc.c

···
  */
 void ubifs_tnc_close(struct ubifs_info *c)
 {
-	long clean_freed;
-
 	tnc_destroy_cnext(c);
 	if (c->zroot.znode) {
-		clean_freed = ubifs_destroy_tnc_subtree(c->zroot.znode);
-		atomic_long_sub(clean_freed, &ubifs_clean_zn_cnt);
+		long n;
+
+		ubifs_destroy_tnc_subtree(c->zroot.znode);
+		n = atomic_long_read(&c->clean_zn_cnt);
+		atomic_long_sub(n, &ubifs_clean_zn_cnt);
 	}
 	kfree(c->gap_lebs);
 	kfree(c->ilebs);

fs/ubifs/ubifs.h

···
  * struct ubifs_jhead - journal head.
  * @wbuf: head's write-buffer
  * @buds_list: list of bud LEBs belonging to this journal head
+ * @grouped: non-zero if UBIFS groups nodes when writing to this journal head
  *
  * Note, the @buds list is protected by the @c->buds_lock.
  */
 struct ubifs_jhead {
 	struct ubifs_wbuf wbuf;
 	struct list_head buds_list;
+	unsigned int grouped:1;
 };
 
 /**
···
 int ubifs_recover_master_node(struct ubifs_info *c);
 int ubifs_write_rcvrd_mst_node(struct ubifs_info *c);
 struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
-					 int offs, void *sbuf, int grouped);
+					 int offs, void *sbuf, int jhead);
 struct ubifs_scan_leb *ubifs_recover_log_leb(struct ubifs_info *c, int lnum,
 					     int offs, void *sbuf);
 int ubifs_recover_inl_heads(const struct ubifs_info *c, void *sbuf);

include/asm-generic/unistd.h

···
 __SYSCALL(__NR_syncfs, sys_syncfs)
 #define __NR_setns 268
 __SYSCALL(__NR_setns, sys_setns)
+#define __NR_sendmmsg 269
+__SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
 
 #undef __NR_syscalls
-#define __NR_syscalls 269
+#define __NR_syscalls 270
 
 /*
  * All syscalls below here should go away really,

include/linux/blkdev.h

···
 #define blk_get_integrity(a)			(0)
 #define blk_integrity_compare(a, b)		(0)
 #define blk_integrity_register(a, b)		(0)
-#define blk_integrity_unregister(a)		do { } while (0);
-#define blk_queue_max_integrity_segments(a, b)	do { } while (0);
+#define blk_integrity_unregister(a)		do { } while (0)
+#define blk_queue_max_integrity_segments(a, b)	do { } while (0)
 #define queue_max_integrity_segments(a)		(0)
 #define blk_integrity_merge_rq(a, b, c)		(0)
 #define blk_integrity_merge_bio(a, b, c)	(0)

include/linux/dma_remapping.h

···
 #define VTD_PAGE_MASK		(((u64)-1) << VTD_PAGE_SHIFT)
 #define VTD_PAGE_ALIGN(addr)	(((addr) + VTD_PAGE_SIZE - 1) & VTD_PAGE_MASK)
 
+#define VTD_STRIDE_SHIFT        (9)
+#define VTD_STRIDE_MASK         (((u64)-1) << VTD_STRIDE_SHIFT)
+
 #define DMA_PTE_READ (1)
 #define DMA_PTE_WRITE (2)
+#define DMA_PTE_LARGE_PAGE (1 << 7)
 #define DMA_PTE_SNP (1 << 11)
 
 #define CONTEXT_TT_MULTI_LEVEL	0

include/linux/genhd.h

···
 	sector_t start_sect;
 	sector_t nr_sects;
 	sector_t alignment_offset;
+	unsigned int discard_alignment;
 	struct device __dev;
 	struct kobject *holder_dir;
 	int policy, partno;

include/linux/ieee80211.h

···
 #define WLAN_CAPABILITY_ESS		(1<<0)
 #define WLAN_CAPABILITY_IBSS		(1<<1)
 
-/* A mesh STA sets the ESS and IBSS capability bits to zero */
-#define WLAN_CAPABILITY_IS_MBSS(cap)	\
+/*
+ * A mesh STA sets the ESS and IBSS capability bits to zero.
+ * however, this holds true for p2p probe responses (in the p2p_find
+ * phase) as well.
+ */
+#define WLAN_CAPABILITY_IS_STA_BSS(cap)	\
 	(!((cap) & (WLAN_CAPABILITY_ESS | WLAN_CAPABILITY_IBSS)))
 
 #define WLAN_CAPABILITY_CF_POLLABLE	(1<<2)

include/linux/if_packet.h

···
 #define TP_STATUS_COPY		0x2
 #define TP_STATUS_LOSING	0x4
 #define TP_STATUS_CSUMNOTREADY	0x8
+#define TP_STATUS_VLAN_VALID   0x10 /* auxdata has valid tp_vlan_tci */
 
 /* Tx ring - header status */
 #define TP_STATUS_AVAILABLE	0x0

include/linux/mtd/physmap.h

···
 #include <linux/mtd/partitions.h>
 
 struct map_info;
+struct platform_device;
 
 struct physmap_flash_data {
 	unsigned int		width;

include/linux/tty_ldisc.h

···
  * 	tty device.  It is solely the responsibility of the line
  * 	discipline to handle poll requests.
  *
- * unsigned int (*receive_buf)(struct tty_struct *, const unsigned char *cp,
+ * void	(*receive_buf)(struct tty_struct *, const unsigned char *cp,
  * 		       char *fp, int count);
  *
  * 	This function is called by the low-level tty driver to send
···
  * 	processing.  <cp> is a pointer to the buffer of input
  * 	character received by the device.  <fp> is a pointer to a
  * 	pointer of flag bytes which indicate whether a character was
- * 	received with a parity error, etc. Returns the amount of bytes
- * 	received.
+ * 	received with a parity error, etc.
  * 
  * void	(*write_wakeup)(struct tty_struct *);
  *
···
 	/*
 	 * The following routines are called from below.
 	 */
-	unsigned int (*receive_buf)(struct tty_struct *,
-			const unsigned char *cp, char *fp, int count);
+	void	(*receive_buf)(struct tty_struct *, const unsigned char *cp,
+			       char *fp, int count);
 	void	(*write_wakeup)(struct tty_struct *);
 	void	(*dcd_change)(struct tty_struct *, unsigned int,
 				struct pps_event_time *);

include/linux/virtio.h

···
  *	This re-enables callbacks; it returns "false" if there are pending
  *	buffers in the queue, to detect a possible race between the driver
  *	checking for more work, and enabling callbacks.
+ * virtqueue_enable_cb_delayed: restart callbacks after disable_cb.
+ *	vq: the struct virtqueue we're talking about.
+ *	This re-enables callbacks but hints to the other side to delay
+ *	interrupts until most of the available buffers have been processed;
+ *	it returns "false" if there are many pending buffers in the queue,
+ *	to detect a possible race between the driver checking for more work,
+ *	and enabling callbacks.
  * virtqueue_detach_unused_buf: detach first unused buffer
  * 	vq: the struct virtqueue we're talking about.
  * 	Returns NULL or the "data" token handed to add_buf
···
 void virtqueue_disable_cb(struct virtqueue *vq);
 
 bool virtqueue_enable_cb(struct virtqueue *vq);
+
+bool virtqueue_enable_cb_delayed(struct virtqueue *vq);
 
 void *virtqueue_detach_unused_buf(struct virtqueue *vq);
 

include/linux/virtio_9p.h

···
 #ifndef _LINUX_VIRTIO_9P_H
 #define _LINUX_VIRTIO_9P_H
 /* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 #include <linux/types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>

include/linux/virtio_balloon.h

···
 #ifndef _LINUX_VIRTIO_BALLOON_H
 #define _LINUX_VIRTIO_BALLOON_H
 /* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
 

include/linux/virtio_blk.h

···
 #ifndef _LINUX_VIRTIO_BLK_H
 #define _LINUX_VIRTIO_BLK_H
 /* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 #include <linux/types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>

include/linux/virtio_config.h

···
 #ifndef _LINUX_VIRTIO_CONFIG_H
 #define _LINUX_VIRTIO_CONFIG_H
 /* This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
- * anyone can use the definitions to implement compatible drivers/servers. */
+ * anyone can use the definitions to implement compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 
 /* Virtio devices use a standardized configuration space to define their
  * features and pass configuration information, but each implementation can

include/linux/virtio_console.h

···
 #include <linux/virtio_config.h>
 /*
  * This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
- * anyone can use the definitions to implement compatible drivers/servers.
+ * anyone can use the definitions to implement compatible drivers/servers:
+ *
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
  *
  * Copyright (C) Red Hat, Inc., 2009, 2010, 2011
  * Copyright (C) Amit Shah <[e-mail]>, 2009, 2010, 2011

include/linux/virtio_ids.h

···
  *
  * This header is BSD licensed so anyone can use the definitions to implement
  * compatible drivers/servers.
- */
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 
 #define VIRTIO_ID_NET		1 /* virtio net */
 #define VIRTIO_ID_BLOCK		2 /* virtio block */

include/linux/virtio_net.h

···
 #ifndef _LINUX_VIRTIO_NET_H
 #define _LINUX_VIRTIO_NET_H
 /* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 #include <linux/types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>

include/linux/virtio_pci.h

···
  *
  * This header is BSD licensed so anyone can use the definitions to implement
  * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
  */
 
 #ifndef _LINUX_VIRTIO_PCI_H

include/linux/virtio_ring.h

···
  * This header is BSD licensed so anyone can use the definitions to implement
  * compatible drivers/servers.
  *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
  * Copyright Rusty Russell IBM Corporation 2007. */
 #include <linux/types.h>
 
···
 
 /* We support indirect buffer descriptors */
 #define VIRTIO_RING_F_INDIRECT_DESC	28
+
+/* The Guest publishes the used index for which it expects an interrupt
+ * at the end of the avail ring. Host should ignore the avail->flags field. */
+/* The Host publishes the avail index for which it expects a kick
+ * at the end of the used ring. Guest should ignore the used->flags field. */
+#define VIRTIO_RING_F_EVENT_IDX		29
 
 /* Virtio ring descriptors: 16 bytes.  These can chain together via "next". */
 struct vring_desc {
···
  *	__u16 avail_flags;
  *	__u16 avail_idx;
  *	__u16 available[num];
+ *	__u16 used_event_idx;
  *
  *	// Padding to the next align boundary.
  *	char pad[];
···
  *	__u16 used_flags;
  *	__u16 used_idx;
  *	struct vring_used_elem used[num];
+ *	__u16 avail_event_idx;
  * };
  */
+/* We publish the used event index at the end of the available ring, and vice
+ * versa. They are at the end for backwards compatibility. */
+#define vring_used_event(vr) ((vr)->avail->ring[(vr)->num])
+#define vring_avail_event(vr) (*(__u16 *)&(vr)->used->ring[(vr)->num])
+
 static inline void vring_init(struct vring *vr, unsigned int num, void *p,
 			      unsigned long align)
 {
···
 {
 	return ((sizeof(struct vring_desc) * num + sizeof(__u16) * (2 + num)
 		 + align - 1) & ~(align - 1))
-		+ sizeof(__u16) * 2 + sizeof(struct vring_used_elem) * num;
+		+ sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num;
+}
+
+/* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */
+/* Assuming a given event_idx value from the other size, if
+ * we have just incremented index from old to new_idx,
+ * should we trigger an event? */
+static inline int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old)
+{
+	/* Note: Xen has similar logic for notification hold-off
+	 * in include/xen/interface/io/ring.h with req_event and req_prod
+	 * corresponding to event_idx + 1 and new_idx respectively.
+	 * Note also that req_event and req_prod in Xen start at 1,
+	 * event indexes in virtio start at 0. */
+	return (__u16)(new_idx - event_idx - 1) < (__u16)(new_idx - old);
 }
 
 #ifdef __KERNEL__

include/net/sctp/command.h

···
 	SCTP_CMD_UPDATE_INITTAG, /* Update peer inittag */
 	SCTP_CMD_SEND_MSG,	 /* Send the whole use message */
 	SCTP_CMD_SEND_NEXT_ASCONF, /* Send the next ASCONF after ACK */
+	SCTP_CMD_PURGE_ASCONF_QUEUE, /* Purge all asconf queues.*/
 	SCTP_CMD_LAST
 } sctp_verb_t;
 

include/net/sctp/structs.h

···
 struct sctp_chunk *sctp_assoc_lookup_asconf_ack(
 					const struct sctp_association *asoc,
 					__be32 serial);
-
+void sctp_asconf_queue_teardown(struct sctp_association *asoc);
 
 int sctp_cmp_addr_exact(const union sctp_addr *ss1,
 			const union sctp_addr *ss2);

include/trace/events/net.h

···
 TRACE_EVENT(net_dev_xmit,
 
 	TP_PROTO(struct sk_buff *skb,
-		 int rc),
+		 int rc,
+		 struct net_device *dev,
+		 unsigned int skb_len),
 
-	TP_ARGS(skb, rc),
+	TP_ARGS(skb, rc, dev, skb_len),
 
 	TP_STRUCT__entry(
 		__field(	void *,		skbaddr		)
 		__field(	unsigned int,	len		)
 		__field(	int,		rc		)
-		__string(	name,		skb->dev->name	)
+		__string(	name,		dev->name	)
 	),
 
 	TP_fast_assign(
 		__entry->skbaddr = skb;
-		__entry->len = skb->len;
+		__entry->len = skb_len;
 		__entry->rc = rc;
-		__assign_str(name, skb->dev->name);
+		__assign_str(name, dev->name);
 	),
 
 	TP_printk("dev=%s skbaddr=%p len=%u rc=%d",

kernel/rcutree.c

···
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 	kthread_bind(t, cpu);
-	set_task_state(t, TASK_INTERRUPTIBLE);
 	per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
 	WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL);
 	per_cpu(rcu_cpu_kthread_task, cpu) = t;
···
 		if (IS_ERR(t))
 			return PTR_ERR(t);
 		raw_spin_lock_irqsave(&rnp->lock, flags);
-		set_task_state(t, TASK_INTERRUPTIBLE);
 		rnp->node_kthread_task = t;
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		sp.sched_priority = 99;
···
 	return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index);
 }
 
+static void rcu_wake_one_boost_kthread(struct rcu_node *rnp);
+
 /*
  * Spawn all kthreads -- called as soon as the scheduler is running.
  */
···
 {
 	int cpu;
 	struct rcu_node *rnp;
+	struct task_struct *t;
 
 	rcu_kthreads_spawnable = 1;
 	for_each_possible_cpu(cpu) {
 		per_cpu(rcu_cpu_has_work, cpu) = 0;
-		if (cpu_online(cpu))
+		if (cpu_online(cpu)) {
 			(void)rcu_spawn_one_cpu_kthread(cpu);
+			t = per_cpu(rcu_cpu_kthread_task, cpu);
+			if (t)
+				wake_up_process(t);
+		}
 	}
 	rnp = rcu_get_root(rcu_state);
 	(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+	if (rnp->node_kthread_task)
+		wake_up_process(rnp->node_kthread_task);
 	if (NUM_RCU_NODES > 1) {
-		rcu_for_each_leaf_node(rcu_state, rnp)
+		rcu_for_each_leaf_node(rcu_state, rnp) {
 			(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+			t = rnp->node_kthread_task;
+			if (t)
+				wake_up_process(t);
+			rcu_wake_one_boost_kthread(rnp);
+		}
 	}
 	return 0;
 }
···
 	raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
 }
 
-static void __cpuinit rcu_online_cpu(int cpu)
+static void __cpuinit rcu_prepare_cpu(int cpu)
 {
 	rcu_init_percpu_data(cpu, &rcu_sched_state, 0);
 	rcu_init_percpu_data(cpu, &rcu_bh_state, 0);
 	rcu_preempt_init_percpu_data(cpu);
 }
 
-static void __cpuinit rcu_online_kthreads(int cpu)
+static void __cpuinit rcu_prepare_kthreads(int cpu)
 {
 	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;
···
 		if (rnp->node_kthread_task == NULL)
 			(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
 	}
+}
+
+/*
+ * kthread_create() creates threads in TASK_UNINTERRUPTIBLE state,
+ * but the RCU threads are woken on demand, and if demand is low this
+ * could be a while triggering the hung task watchdog.
+ *
+ * In order to avoid this, poke all tasks once the CPU is fully
+ * up and running.
+ */
+static void __cpuinit rcu_online_kthreads(int cpu)
+{
+	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
+	struct rcu_node *rnp = rdp->mynode;
+	struct task_struct *t;
+
+	t = per_cpu(rcu_cpu_kthread_task, cpu);
+	if (t)
+		wake_up_process(t);
+
+	t = rnp->node_kthread_task;
+	if (t)
+		wake_up_process(t);
+
+	rcu_wake_one_boost_kthread(rnp);
 }
 
 /*
···
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		rcu_online_cpu(cpu);
-		rcu_online_kthreads(cpu);
+		rcu_prepare_cpu(cpu);
+		rcu_prepare_kthreads(cpu);
 		break;
 	case CPU_ONLINE:
+		rcu_online_kthreads(cpu);
 	case CPU_DOWN_FAILED:
 		rcu_node_kthread_setaffinity(rnp, -1);
 		rcu_cpu_kthread_setrt(cpu, 1);

kernel/rcutree_plugin.h

···
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 	raw_spin_lock_irqsave(&rnp->lock, flags);
-	set_task_state(t, TASK_INTERRUPTIBLE);
 	rnp->boost_kthread_task = t;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	sp.sched_priority = RCU_KTHREAD_PRIO;
 	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 	return 0;
+}
+
+static void __cpuinit rcu_wake_one_boost_kthread(struct rcu_node *rnp)
+{
+	if (rnp->boost_kthread_task)
+		wake_up_process(rnp->boost_kthread_task);
 }
 
 #else /* #ifdef CONFIG_RCU_BOOST */
···
 						 int rnp_index)
 {
 	return 0;
+}
+
+static void __cpuinit rcu_wake_one_boost_kthread(struct rcu_node *rnp)
+{
 }
 
 #endif /* #else #ifdef CONFIG_RCU_BOOST */

lib/Kconfig.debug

···
 	bool "Verbose BUG() reporting (adds 70K)" if DEBUG_KERNEL && EXPERT
 	depends on BUG
 	depends on ARM || AVR32 || M32R || M68K || SPARC32 || SPARC64 || \
-		   FRV || SUPERH || GENERIC_BUG || BLACKFIN || MN10300
+		   FRV || SUPERH || GENERIC_BUG || BLACKFIN || MN10300 || TILE
 	default y
 	help
 	  Say Y here to make BUG() panics output the file name and line number

mm/hugetlb.c

···
 	 */
 	chg = vma_needs_reservation(h, vma, addr);
 	if (chg < 0)
-		return ERR_PTR(chg);
+		return ERR_PTR(-VM_FAULT_OOM);
 	if (chg)
 		if (hugetlb_get_quota(inode->i_mapping, chg))
-			return ERR_PTR(-ENOSPC);
+			return ERR_PTR(-VM_FAULT_SIGBUS);
 
 	spin_lock(&hugetlb_lock);
 	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);

mm/page_alloc.c

···
 
 	if (should_fail_alloc_page(gfp_mask, order))
 		return NULL;
-#ifndef CONFIG_ZONE_DMA
-	if (WARN_ON_ONCE(gfp_mask & __GFP_DMA))
-		return NULL;
-#endif
 
 	/*
 	 * Check the zones suitable for the gfp_mask contain at least one

net/8021q/vlan_dev.c

···
 		u64_stats_update_begin(&stats->syncp);
 		stats->tx_packets++;
 		stats->tx_bytes += len;
-		u64_stats_update_begin(&stats->syncp);
+		u64_stats_update_end(&stats->syncp);
 	} else {
 		this_cpu_inc(vlan_dev_info(dev)->vlan_pcpu_stats->tx_dropped);
 	}

net/bluetooth/l2cap_core.c

···
 		if (c->psm == psm) {
 			/* Exact match. */
 			if (!bacmp(&bt_sk(sk)->src, src)) {
-				read_unlock_bh(&chan_list_lock);
+				read_unlock(&chan_list_lock);
 				return c;
 			}
 

net/caif/chnl_net.c

···
 	struct chnl_net *dev = NULL;
 	struct list_head *list_node;
 	struct list_head *_tmp;
-	/* May be called with or without RTNL lock held */
-	int islocked = rtnl_is_locked();
-	if (!islocked)
-		rtnl_lock();
+
+	rtnl_lock();
 	list_for_each_safe(list_node, _tmp, &chnl_net_list) {
 		dev = list_entry(list_node, struct chnl_net, list_field);
 		if (dev->state == CAIF_SHUTDOWN)
 			dev_close(dev->netdev);
 	}
-	if (!islocked)
-		rtnl_unlock();
+	rtnl_unlock();
 }
 static DECLARE_WORK(close_worker, close_work);
 

net/core/dev.c

···
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	int rc = NETDEV_TX_OK;
+	unsigned int skb_len;
 
 	if (likely(!skb->next)) {
 		u32 features;
···
 			}
 		}
 
+		skb_len = skb->len;
 		rc = ops->ndo_start_xmit(skb, dev);
-		trace_net_dev_xmit(skb, rc);
+		trace_net_dev_xmit(skb, rc, dev, skb_len);
 		if (rc == NETDEV_TX_OK)
 			txq_trans_update(txq);
 		return rc;
···
 		if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
 			skb_dst_drop(nskb);
 
+		skb_len = nskb->len;
 		rc = ops->ndo_start_xmit(nskb, dev);
-		trace_net_dev_xmit(nskb, rc);
+		trace_net_dev_xmit(nskb, rc, dev, skb_len);
 		if (unlikely(rc != NETDEV_TX_OK)) {
 			if (rc & ~NETDEV_TX_MASK)
 				goto out_kfree_gso_skb;

net/ipv4/af_inet.c

···
 	if (addr_len < sizeof(struct sockaddr_in))
 		goto out;
 
+	if (addr->sin_family != AF_INET)
+		goto out;
+
 	chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);
 
 	/* Not specified by any standard per-se, however it breaks too

net/ipv4/ip_options.c

···
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <asm/uaccess.h>
+#include <asm/unaligned.h>
 #include <linux/skbuff.h>
 #include <linux/ip.h>
 #include <linux/icmp.h>
···
 				goto error;
 			}
 			if (optptr[2] <= optlen) {
-				__be32 *timeptr = NULL;
+				unsigned char *timeptr = NULL;
 				if (optptr[2]+3 > optptr[1]) {
 					pp_ptr = optptr + 2;
 					goto error;
···
 				      case IPOPT_TS_TSONLY:
 					opt->ts = optptr - iph;
 					if (skb)
-						timeptr = (__be32*)&optptr[optptr[2]-1];
+						timeptr = &optptr[optptr[2]-1];
 					opt->ts_needtime = 1;
 					optptr[2] += 4;
 					break;
···
 					opt->ts = optptr - iph;
 					if (rt)  {
 						memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4);
-						timeptr = (__be32*)&optptr[optptr[2]+3];
+						timeptr = &optptr[optptr[2]+3];
 					}
 					opt->ts_needaddr = 1;
 					opt->ts_needtime = 1;
···
 						if (inet_addr_type(net, addr) == RTN_UNICAST)
 							break;
 						if (skb)
-							timeptr = (__be32*)&optptr[optptr[2]+3];
+							timeptr = &optptr[optptr[2]+3];
 					}
 					opt->ts_needtime = 1;
 					optptr[2] += 8;
···
 				}
 				if (timeptr) {
 					struct timespec tv;
-					__be32  midtime;
+					u32  midtime;
 					getnstimeofday(&tv);
-					midtime = htonl((tv.tv_sec % 86400) * MSEC_PER_SEC + tv.tv_nsec / NSEC_PER_MSEC);
-					memcpy(timeptr, &midtime, sizeof(__be32));
+					midtime = (tv.tv_sec % 86400) * MSEC_PER_SEC + tv.tv_nsec / NSEC_PER_MSEC;
+					put_unaligned_be32(midtime, timeptr);
 					opt->is_changed = 1;
 				}
 			} else {

net/mac80211/mlme.c

···
 		WARN_ON(!ieee80211_set_channel_type(local, sdata, channel_type));
 	}
 
+	ieee80211_stop_queues_by_reason(&sdata->local->hw,
+					IEEE80211_QUEUE_STOP_REASON_CSA);
+
 	/* channel_type change automatically detected */
 	ieee80211_hw_config(local, 0);
 
···
 						 channel_type);
 		rcu_read_unlock();
 	}
+
+	ieee80211_wake_queues_by_reason(&sdata->local->hw,
+					IEEE80211_QUEUE_STOP_REASON_CSA);
 
 	ht_opmode = le16_to_cpu(hti->operation_mode);
 
···
 		local->hw.conf.flags &= ~IEEE80211_CONF_PS;
 		config_changed |= IEEE80211_CONF_CHANGE_PS;
 	}
+	local->ps_sdata = NULL;
 
 	ieee80211_hw_config(local, config_changed);
 

net/mac80211/scan.c

···
 #include <linux/if_arp.h>
 #include <linux/rtnetlink.h>
 #include <linux/pm_qos_params.h>
-#include <linux/slab.h>
 #include <net/sch_generic.h>
 #include <linux/slab.h>
 #include <net/mac80211.h>

net/packet/af_packet.c

···
 			getnstimeofday(&ts);
 		h.h2->tp_sec = ts.tv_sec;
 		h.h2->tp_nsec = ts.tv_nsec;
-		h.h2->tp_vlan_tci = vlan_tx_tag_get(skb);
+		if (vlan_tx_tag_present(skb)) {
+			h.h2->tp_vlan_tci = vlan_tx_tag_get(skb);
+			status |= TP_STATUS_VLAN_VALID;
+		} else {
+			h.h2->tp_vlan_tci = 0;
+		}
 		hdrlen = sizeof(*h.h2);
 		break;
 	default:
···
 		aux.tp_snaplen = skb->len;
 		aux.tp_mac = 0;
 		aux.tp_net = skb_network_offset(skb);
-		aux.tp_vlan_tci = vlan_tx_tag_get(skb);
-
+		if (vlan_tx_tag_present(skb)) {
+			aux.tp_vlan_tci = vlan_tx_tag_get(skb);
+			aux.tp_status |= TP_STATUS_VLAN_VALID;
+		} else {
+			aux.tp_vlan_tci = 0;
+		}
 		put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux);
 	}
 

net/sctp/associola.c

···
 
 	asoc->peer.transport_count = 0;
 
-	/* Free any cached ASCONF_ACK chunk. */
-	sctp_assoc_free_asconf_acks(asoc);
-
-	/* Free the ASCONF queue. */
-	sctp_assoc_free_asconf_queue(asoc);
-
-	/* Free any cached ASCONF chunk. */
-	if (asoc->addip_last_asconf)
-		sctp_chunk_free(asoc->addip_last_asconf);
+	sctp_asconf_queue_teardown(asoc);
 
 	/* AUTH - Free the endpoint shared keys */
 	sctp_auth_destroy_keys(&asoc->endpoint_shared_keys);
···
 	}
 
 	return NULL;
+}
+
+void sctp_asconf_queue_teardown(struct sctp_association *asoc)
+{
+	/* Free any cached ASCONF_ACK chunk. */
+	sctp_assoc_free_asconf_acks(asoc);
+
+	/* Free the ASCONF queue. */
+	sctp_assoc_free_asconf_queue(asoc);
+
+	/* Free any cached ASCONF chunk. */
+	if (asoc->addip_last_asconf)
+		sctp_chunk_free(asoc->addip_last_asconf);
 }

net/sctp/sm_sideeffect.c

···
 		case SCTP_CMD_SEND_NEXT_ASCONF:
 			sctp_cmd_send_asconf(asoc);
 			break;
+		case SCTP_CMD_PURGE_ASCONF_QUEUE:
+			sctp_asconf_queue_teardown(asoc);
+			break;
 		default:
 			pr_warn("Impossible command: %u, %p\n",
 				cmd->verb, cmd->obj.ptr);

net/sctp/sm_statefuns.c

···
 		return SCTP_DISPOSITION_CONSUME;
 	}
 
-	/* For now, fail any unsent/unacked data.  Consider the optional
-	 * choice of resending of this data.
+	/* For now, stop pending T3-rtx and SACK timers, fail any unsent/unacked
+	 * data. Consider the optional choice of resending of this data.
 	 */
+	sctp_add_cmd_sf(commands, SCTP_CMD_T3_RTX_TIMERS_STOP, SCTP_NULL());
+	sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
+			SCTP_TO(SCTP_EVENT_TIMEOUT_SACK));
 	sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_OUTQUEUE, SCTP_NULL());
+
+	/* Stop pending T4-rto timer, teardown ASCONF queue, ASCONF-ACK queue
+	 * and ASCONF-ACK cache.
+	 */
+	sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
+			SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO));
+	sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_ASCONF_QUEUE, SCTP_NULL());
 
 	repl = sctp_make_cookie_ack(new_asoc, chunk);
 	if (!repl)

net/wireless/nl80211.c

···
 	i = 0;
 	if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) {
 		nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS], tmp) {
+			request->ssids[i].ssid_len = nla_len(attr);
 			if (request->ssids[i].ssid_len > IEEE80211_MAX_SSID_LEN) {
 				err = -EINVAL;
 				goto out_free;
 			}
 			memcpy(request->ssids[i].ssid, nla_data(attr), nla_len(attr));
-			request->ssids[i].ssid_len = nla_len(attr);
 			i++;
 		}
 	}
···
 	if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) {
 		nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS],
 				    tmp) {
+			request->ssids[i].ssid_len = nla_len(attr);
 			if (request->ssids[i].ssid_len >
 			    IEEE80211_MAX_SSID_LEN) {
 				err = -EINVAL;
···
 			}
 			memcpy(request->ssids[i].ssid, nla_data(attr),
 			       nla_len(attr));
-			request->ssids[i].ssid_len = nla_len(attr);
 			i++;
 		}
 	}

net/wireless/scan.c

···
 	return memcmp(ssidie + 2, ssid, ssid_len) == 0;
 }
 
+static bool is_mesh_bss(struct cfg80211_bss *a)
+{
+	const u8 *ie;
+
+	if (!WLAN_CAPABILITY_IS_STA_BSS(a->capability))
+		return false;
+
+	ie = cfg80211_find_ie(WLAN_EID_MESH_ID,
+			      a->information_elements,
+			      a->len_information_elements);
+	if (!ie)
+		return false;
+
+	ie = cfg80211_find_ie(WLAN_EID_MESH_CONFIG,
+			      a->information_elements,
+			      a->len_information_elements);
+	if (!ie)
+		return false;
+
+	return true;
+}
+
 static bool is_mesh(struct cfg80211_bss *a,
 		    const u8 *meshid, size_t meshidlen,
 		    const u8 *meshcfg)
 {
 	const u8 *ie;
 
-	if (!WLAN_CAPABILITY_IS_MBSS(a->capability))
+	if (!WLAN_CAPABILITY_IS_STA_BSS(a->capability))
 		return false;
 
 	ie = cfg80211_find_ie(WLAN_EID_MESH_ID,
···
 	if (a->channel != b->channel)
 		return b->channel->center_freq - a->channel->center_freq;
 
-	if (WLAN_CAPABILITY_IS_MBSS(a->capability | b->capability)) {
+	if (is_mesh_bss(a) && is_mesh_bss(b)) {
 		r = cmp_ies(WLAN_EID_MESH_ID,
 			    a->information_elements,
 			    a->len_information_elements,
···
 		    struct cfg80211_internal_bss *res)
 {
 	struct cfg80211_internal_bss *found = NULL;
-	const u8 *meshid, *meshcfg;
 
 	/*
 	 * The reference to "res" is donated to this function.
···
 	}
 
 	res->ts = jiffies;
-
-	if (WLAN_CAPABILITY_IS_MBSS(res->pub.capability)) {
-		/* must be mesh, verify */
-		meshid = cfg80211_find_ie(WLAN_EID_MESH_ID,
-					  res->pub.information_elements,
-					  res->pub.len_information_elements);
-		meshcfg = cfg80211_find_ie(WLAN_EID_MESH_CONFIG,
-					   res->pub.information_elements,
-					   res->pub.len_information_elements);
-		if (!meshid || !meshcfg ||
-		    meshcfg[1] != sizeof(struct ieee80211_meshconf_ie)) {
-			/* bogus mesh */
-			kref_put(&res->ref, bss_release);
-			return NULL;
-		}
-	}
 
 	spin_lock_bh(&dev->bss_lock);
 

security/apparmor/lsm.c

···
 			sa.aad.op = OP_SETPROCATTR;
 			sa.aad.info = name;
 			sa.aad.error = -EINVAL;
-			return aa_audit(AUDIT_APPARMOR_DENIED, NULL, GFP_KERNEL,
+			return aa_audit(AUDIT_APPARMOR_DENIED,
+					__aa_current_profile(), GFP_KERNEL,
 					&sa, NULL);
 		}
 	} else if (strcmp(name, "exec") == 0) {

sound/pci/asihpi/hpidspcd.c

···
 	    HPI_VER_MINOR(HPI_VER) * 100 + HPI_VER_RELEASE(HPI_VER)))
 
 /***********************************************************************/
-#include "linux/pci.h"
+#include <linux/pci.h>
 /*-------------------------------------------------------------------*/
 short hpi_dsp_code_open(u32 adapter, struct dsp_code *ps_dsp_code,
 	u32 *pos_error_code)

sound/pci/fm801.c

···
 	sprintf(chip->tea.bus_info, "PCI:%s", pci_name(pci));
 	if ((tea575x_tuner & TUNER_TYPE_MASK) > 0 &&
 	    (tea575x_tuner & TUNER_TYPE_MASK) < 4) {
-		if (snd_tea575x_init(&chip->tea))
+		if (snd_tea575x_init(&chip->tea)) {
 			snd_printk(KERN_ERR "TEA575x radio not found\n");
-	} else if ((tea575x_tuner & TUNER_TYPE_MASK) == 0)
+			snd_fm801_free(chip);
+			return -ENODEV;
+		}
+	} else if ((tea575x_tuner & TUNER_TYPE_MASK) == 0) {
 		/* autodetect tuner connection */
 		for (tea575x_tuner = 1; tea575x_tuner <= 3; tea575x_tuner++) {
 			chip->tea575x_tuner = tea575x_tuner;
···
 				break;
 			}
 		}
+		if (tea575x_tuner == 4) {
+			snd_printk(KERN_ERR "TEA575x radio not found\n");
+			snd_fm801_free(chip);
+			return -ENODEV;
+		}
+	}
 	strlcpy(chip->tea.card, snd_fm801_tea575x_gpios[(tea575x_tuner & TUNER_TYPE_MASK) - 1].name, sizeof(chip->tea.card));
 #endif
 

sound/pci/hda/patch_analog.c

···
 				hda_nid_t hp)
 {
 	struct ad198x_spec *spec = codec->spec;
-	snd_hda_codec_write(codec, front, 0, AC_VERB_SET_EAPD_BTLENABLE,
+	if (snd_hda_query_pin_caps(codec, front) & AC_PINCAP_EAPD)
+		snd_hda_codec_write(codec, front, 0, AC_VERB_SET_EAPD_BTLENABLE,
 			    !spec->inv_eapd ? 0x00 : 0x02);
-	snd_hda_codec_write(codec, hp, 0, AC_VERB_SET_EAPD_BTLENABLE,
+	if (snd_hda_query_pin_caps(codec, hp) & AC_PINCAP_EAPD)
+		snd_hda_codec_write(codec, hp, 0, AC_VERB_SET_EAPD_BTLENABLE,
 			    !spec->inv_eapd ? 0x00 : 0x02);
 }
 
···
 	case 0x11d4184a:
 	case 0x11d4194a:
 	case 0x11d4194b:
+	case 0x11d41988:
+	case 0x11d4198b:
+	case 0x11d4989a:
+	case 0x11d4989b:
 		ad198x_power_eapd_write(codec, 0x12, 0x11);
 		break;
 	case 0x11d41981:
···
 		break;
 	case 0x11d41986:
 		ad198x_power_eapd_write(codec, 0x1b, 0x1a);
-		break;
-	case 0x11d41988:
-	case 0x11d4198b:
-	case 0x11d4989a:
-	case 0x11d4989b:
-		ad198x_power_eapd_write(codec, 0x29, 0x22);
 		break;
 	}
 }

sound/soc/codecs/cx20442.c

···
 }
 
 /* Line discipline .receive_buf() */
-static unsigned int v253_receive(struct tty_struct *tty,
-				 const unsigned char *cp, char *fp, int count)
+static void v253_receive(struct tty_struct *tty,
+				const unsigned char *cp, char *fp, int count)
 {
 	struct snd_soc_codec *codec = tty->disc_data;
 	struct cx20442_priv *cx20442;
 
 	if (!codec)
-		return count;
+		return;
 
 	cx20442 = snd_soc_codec_get_drvdata(codec);
 
···
 		codec->hw_write = (hw_write_t)tty->ops->write;
 		codec->card->pop_time = 1;
 	}
-
-	return count;
 }
 
 /* Line discipline .write_wakeup() */

sound/soc/codecs/wm_hubs.c

···
 SOC_SINGLE_TLV("IN1L Volume", WM8993_LEFT_LINE_INPUT_1_2_VOLUME, 0, 31, 0,
 	       inpga_tlv),
 SOC_SINGLE("IN1L Switch", WM8993_LEFT_LINE_INPUT_1_2_VOLUME, 7, 1, 1),
-SOC_SINGLE("IN1L ZC Switch", WM8993_LEFT_LINE_INPUT_1_2_VOLUME, 7, 1, 0),
+SOC_SINGLE("IN1L ZC Switch", WM8993_LEFT_LINE_INPUT_1_2_VOLUME, 6, 1, 0),
 
 SOC_SINGLE_TLV("IN1R Volume", WM8993_RIGHT_LINE_INPUT_1_2_VOLUME, 0, 31, 0,
 	       inpga_tlv),
 SOC_SINGLE("IN1R Switch", WM8993_RIGHT_LINE_INPUT_1_2_VOLUME, 7, 1, 1),
-SOC_SINGLE("IN1R ZC Switch", WM8993_RIGHT_LINE_INPUT_1_2_VOLUME, 7, 1, 0),
+SOC_SINGLE("IN1R ZC Switch", WM8993_RIGHT_LINE_INPUT_1_2_VOLUME, 6, 1, 0),
 
 
 SOC_SINGLE_TLV("IN2L Volume", WM8993_LEFT_LINE_INPUT_3_4_VOLUME, 0, 31, 0,
 	       inpga_tlv),
 SOC_SINGLE("IN2L Switch", WM8993_LEFT_LINE_INPUT_3_4_VOLUME, 7, 1, 1),
-SOC_SINGLE("IN2L ZC Switch", WM8993_LEFT_LINE_INPUT_3_4_VOLUME, 7, 1, 0),
+SOC_SINGLE("IN2L ZC Switch", WM8993_LEFT_LINE_INPUT_3_4_VOLUME, 6, 1, 0),
 
 SOC_SINGLE_TLV("IN2R Volume", WM8993_RIGHT_LINE_INPUT_3_4_VOLUME, 0, 31, 0,
 	       inpga_tlv),
 SOC_SINGLE("IN2R Switch", WM8993_RIGHT_LINE_INPUT_3_4_VOLUME, 7, 1, 1),
-SOC_SINGLE("IN2R ZC Switch", WM8993_RIGHT_LINE_INPUT_3_4_VOLUME, 7, 1, 0),
+SOC_SINGLE("IN2R ZC Switch", WM8993_RIGHT_LINE_INPUT_3_4_VOLUME, 6, 1, 0),
 
 SOC_SINGLE_TLV("MIXINL IN2L Volume", WM8993_INPUT_MIXER3, 7, 1, 0,
 	       inmix_sw_tlv),

sound/soc/soc-dapm.c

···
 }
 
 static int dapm_is_shared_kcontrol(struct snd_soc_dapm_context *dapm,
+	struct snd_soc_dapm_widget *kcontrolw,
 	const struct snd_kcontrol_new *kcontrol_new,
 	struct snd_kcontrol **kcontrol)
 {
···
 	*kcontrol = NULL;
 
 	list_for_each_entry(w, &dapm->card->widgets, list) {
+		if (w == kcontrolw || w->dapm != kcontrolw->dapm)
+			continue;
 		for (i = 0; i < w->num_kcontrols; i++) {
 			if (&w->kcontrol_news[i] == kcontrol_new) {
 				if (w->kcontrols)
···
 		return -EINVAL;
 	}
 
-	shared = dapm_is_shared_kcontrol(dapm, &w->kcontrol_news[0],
+	shared = dapm_is_shared_kcontrol(dapm, w, &w->kcontrol_news[0],
 					 &kcontrol);
 	if (kcontrol) {
 		wlist = kcontrol->private_data;

sound/usb/6fire/firmware.c

···
 	ret = usb6fire_fw_ihex_init(fw, rec);
 	if (ret < 0) {
 		kfree(rec);
+		release_firmware(fw);
 		snd_printk(KERN_ERR PREFIX "error validating ezusb "
 				"firmware %s.\n", fwname);
 		return ret;

sound/usb/quirks.c

···
 static int snd_usb_cm6206_boot_quirk(struct usb_device *dev)
 {
 	int err, reg;
-	int val[] = {0x200c, 0x3000, 0xf800, 0x143f, 0x0000, 0x3000};
+	int val[] = {0x2004, 0x3000, 0xf800, 0x143f, 0x0000, 0x3000};
 
 	for (reg = 0; reg < ARRAY_SIZE(val); reg++) {
 		err = snd_usb_cm106_write_int_reg(dev, reg, val[reg]);

tools/testing/ktest/ktest.pl

···
 
 sub reboot_to {
     if ($reboot_type eq "grub") {
-	run_ssh "'(echo \"savedefault --default=$grub_number --once\" | grub --batch; reboot)'";
+	run_ssh "'(echo \"savedefault --default=$grub_number --once\" | grub --batch && reboot)'";
 	return;
     }
 
···
 	or dodie "Failed to read $config";
 
     while (<IN>) {
-	if (/^(.*?(CONFIG\S*)(=.*| is not set))/) {
+	if (/^((CONFIG\S*)=.*)/) {
 	    $config_ignore{$2} = $1;
 	}
     }
···
 	if (!$found) {
 	    # try the other half
 	    doprint "Top half produced no set configs, trying bottom half\n";
-	    @tophalf = @start_list[$half .. $#start_list];
+	    @tophalf = @start_list[$half + 1 .. $#start_list];
 	    create_config @tophalf;
 	    read_current_config \%current_config;
 	    foreach my $config (@tophalf) {
···
 	# remove half the configs we are looking at and see if
 	# they are good.
 	$half = int($#start_list / 2);
-    } while ($half > 0);
+    } while ($#start_list > 0);
 
     # we found a single config, try it again unless we are running manually
 

tools/virtio/virtio_test.c

···
 		.val = 'h',
 	},
 	{
+		.name = "event-idx",
+		.val = 'E',
+	},
+	{
+		.name = "no-event-idx",
+		.val = 'e',
+	},
+	{
 		.name = "indirect",
 		.val = 'I',
 	},
···
 
 static void help()
 {
-	fprintf(stderr, "Usage: virtio_test [--help] [--no-indirect]\n");
+	fprintf(stderr, "Usage: virtio_test [--help]"
+		" [--no-indirect]"
+		" [--no-event-idx]"
+		"\n");
 }
 
 int main(int argc, char **argv)
 {
 	struct vdev_info dev;
-	unsigned long long features = 1ULL << VIRTIO_RING_F_INDIRECT_DESC;
+	unsigned long long features = (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
+		(1ULL << VIRTIO_RING_F_EVENT_IDX);
 	int o;
 
 	for (;;) {
···
 		case '?':
 			help();
 			exit(2);
+		case 'e':
+			features &= ~(1ULL << VIRTIO_RING_F_EVENT_IDX);
+			break;
 		case 'h':
 			help();
 			goto done;