124 files changed, 1207 insertions, 873 deletions

diff --git a/Documentation/hwmon/tmp401 b/Documentation/hwmon/tmp401
index 8eb88e974055..711f75e189eb 100644
--- a/Documentation/hwmon/tmp401
+++ b/Documentation/hwmon/tmp401
@@ -20,7 +20,7 @@ Supported chips:
     Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp432.html
   * Texas Instruments TMP435
     Prefix: 'tmp435'
-    Addresses scanned: I2C 0x37, 0x48 - 0x4f
+    Addresses scanned: I2C 0x48 - 0x4f
     Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp435.html
 
 Authors:
diff --git a/Documentation/target/tcmu-design.txt b/Documentation/target/tcmu-design.txt
index 43e94ea6d2ca..263b907517ac 100644
--- a/Documentation/target/tcmu-design.txt
+++ b/Documentation/target/tcmu-design.txt
@@ -15,8 +15,7 @@ Contents:
   a) Discovering and configuring TCMU uio devices
   b) Waiting for events on the device(s)
   c) Managing the command ring
-3) Command filtering and pass_level
-4) A final note
+3) A final note
 
 
 TCM Userspace Design
@@ -324,7 +323,7 @@ int handle_device_events(int fd, void *map)
   /* Process events from cmd ring until we catch up with cmd_head */
   while (ent != (void *)mb + mb->cmdr_off + mb->cmd_head) {
 
-    if (tcmu_hdr_get_op(&ent->hdr) == TCMU_OP_CMD) {
+    if (tcmu_hdr_get_op(ent->hdr.len_op) == TCMU_OP_CMD) {
       uint8_t *cdb = (void *)mb + ent->req.cdb_off;
       bool success = true;
 
@@ -339,8 +338,12 @@ int handle_device_events(int fd, void *map)
         ent->rsp.scsi_status = SCSI_CHECK_CONDITION;
       }
     }
+    else if (tcmu_hdr_get_op(ent->hdr.len_op) != TCMU_OP_PAD) {
+      /* Tell the kernel we didn't handle unknown opcodes */
+      ent->hdr.uflags |= TCMU_UFLAG_UNKNOWN_OP;
+    }
     else {
-      /* Do nothing for PAD entries */
+      /* Do nothing for PAD entries except update cmd_tail */
     }
 
     /* update cmd_tail */
@@ -360,28 +363,6 @@ int handle_device_events(int fd, void *map)
 }
 
 
-Command filtering and pass_level
---------------------------------
-
-TCMU supports a "pass_level" option with valid values of 0 or 1.  When
-the value is 0 (the default), nearly all SCSI commands received for
-the device are passed through to the handler. This allows maximum
-flexibility but increases the amount of code required by the handler,
-to support all mandatory SCSI commands. If pass_level is set to 1,
-then only IO-related commands are presented, and the rest are handled
-by LIO's in-kernel command emulation. The commands presented at level
-1 include all versions of:
-
-READ
-WRITE
-WRITE_VERIFY
-XDWRITEREAD
-WRITE_SAME
-COMPARE_AND_WRITE
-SYNCHRONIZE_CACHE
-UNMAP
-
-
 A final note
 ------------
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 1bbacdaf5cf3..e30871880fdb 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2427,7 +2427,6 @@ L:	linux-security-module@vger.kernel.org
 S:      Supported
 F:      include/linux/capability.h
 F:      include/uapi/linux/capability.h
-F:      security/capability.c
 F:      security/commoncap.c
 F:      kernel/capability.c
 
diff --git a/Makefile b/Makefile
index 92a707859205..aee7e5cb4c15 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
 NAME = Hurr durr I'ma sheep
 
 # *DOCUMENTATION*
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 86217db2937a..992736b5229b 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -223,7 +223,7 @@ dtb-$(CONFIG_SOC_IMX25) += \
         imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dtb \
         imx25-karo-tx25.dtb \
         imx25-pdk.dtb
-dtb-$(CONFIG_SOC_IMX31) += \
+dtb-$(CONFIG_SOC_IMX27) += \
         imx27-apf27.dtb \
         imx27-apf27dev.dtb \
         imx27-eukrea-mbimxsd27-baseboard.dtb \
diff --git a/arch/arm/boot/dts/am335x-boneblack.dts b/arch/arm/boot/dts/am335x-boneblack.dts
index 5c42d259fa68..901739fcb85a 100644
--- a/arch/arm/boot/dts/am335x-boneblack.dts
+++ b/arch/arm/boot/dts/am335x-boneblack.dts
@@ -80,7 +80,3 @@
                 status = "okay";
         };
 };
-
-&rtc {
-        system-power-controller;
-};
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 87fc7a35e802..156d05efcb70 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -654,7 +654,7 @@
         wlcore: wlcore@2 {
                 compatible = "ti,wl1271";
                 reg = <2>;
-                interrupt-parent = <&gpio1>;
+                interrupt-parent = <&gpio0>;
                 interrupts = <31 IRQ_TYPE_LEVEL_HIGH>; /* gpio 31 */
                 ref-clock-frequency = <38400000>;
         };
diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts
index 173ffa479ad3..792394dd0f2a 100644
--- a/arch/arm/boot/dts/exynos4412-trats2.dts
+++ b/arch/arm/boot/dts/exynos4412-trats2.dts
@@ -736,7 +736,7 @@
 
                         display-timings {
                                 timing-0 {
-                                        clock-frequency = <0>;
+                                        clock-frequency = <57153600>;
                                         hactive = <720>;
                                         vactive = <1280>;
                                         hfront-porch = <5>;
diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi
index 6951b66d1ab7..bc215e4b75fd 100644
--- a/arch/arm/boot/dts/imx27.dtsi
+++ b/arch/arm/boot/dts/imx27.dtsi
@@ -533,7 +533,7 @@
 
                         fec: ethernet@1002b000 {
                                 compatible = "fsl,imx27-fec";
-                                reg = <0x1002b000 0x4000>;
+                                reg = <0x1002b000 0x1000>;
                                 interrupts = <50>;
                                 clocks = <&clks IMX27_CLK_FEC_IPG_GATE>,
                                          <&clks IMX27_CLK_FEC_AHB_GATE>;
diff --git a/arch/arm/boot/dts/omap3-devkit8000.dts b/arch/arm/boot/dts/omap3-devkit8000.dts
index 134d3f27a8ec..921de6605f07 100644
--- a/arch/arm/boot/dts/omap3-devkit8000.dts
+++ b/arch/arm/boot/dts/omap3-devkit8000.dts
@@ -110,6 +110,8 @@
         nand@0,0 {
                 reg = <0 0 4>; /* CS0, offset 0, IO size 4 */
                 nand-bus-width = <16>;
+                gpmc,device-width = <2>;
+                ti,nand-ecc-opt = "sw";
 
                 gpmc,sync-clk-ps = <0>;
                 gpmc,cs-on-ns = <0>;
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 0ca4a3eaf65d..fbbb1915c6a9 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -429,7 +429,7 @@ CONFIG_USB_EHCI_EXYNOS=y
 CONFIG_USB_EHCI_TEGRA=y
 CONFIG_USB_EHCI_HCD_STI=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
-CONFIG_USB_ISP1760_HCD=y
+CONFIG_USB_ISP1760=y
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_OHCI_HCD_STI=y
 CONFIG_USB_OHCI_HCD_PLATFORM=y
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index f8ccc21fa032..4e7f40c577e6 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -33,7 +33,9 @@ ret_fast_syscall:
  UNWIND(.fnstart        )
  UNWIND(.cantunwind     )
         disable_irq                             @ disable interrupts
-        ldr     r1, [tsk, #TI_FLAGS]
+        ldr     r1, [tsk, #TI_FLAGS]            @ re-check for syscall tracing
+        tst     r1, #_TIF_SYSCALL_WORK
+        bne     __sys_trace_return
         tst     r1, #_TIF_WORK_MASK
         bne     fast_work_pending
         asm_trace_hardirqs_on
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 213919ba326f..3b8c2833c537 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -304,16 +304,17 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 static int of_pmu_irq_cfg(struct platform_device *pdev)
 {
         int i, irq;
-        int *irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
-
-        if (!irqs)
-                return -ENOMEM;
+        int *irqs;
 
         /* Don't bother with PPIs; they're already affine */
         irq = platform_get_irq(pdev, 0);
         if (irq >= 0 && irq_is_percpu(irq))
                 return 0;
 
+        irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
+        if (!irqs)
+                return -ENOMEM;
+
         for (i = 0; i < pdev->num_resources; ++i) {
                 struct device_node *dn;
                 int cpu;
diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index 4d60005e9277..6d0893a3828e 100644
--- a/arch/arm/mach-imx/gpc.c
+++ b/arch/arm/mach-imx/gpc.c
@@ -280,9 +280,15 @@ void __init imx_gpc_check_dt(void)
         struct device_node *np;
 
         np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-gpc");
-        if (WARN_ON(!np ||
-                    !of_find_property(np, "interrupt-controller", NULL)))
-                pr_warn("Outdated DT detected, system is about to crash!!!\n");
+        if (WARN_ON(!np))
+                return;
+
+        if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL))) {
+                pr_warn("Outdated DT detected, suspend/resume will NOT work\n");
+
+                /* map GPC, so that at least CPUidle and WARs keep working */
+                gpc_base = of_iomap(np, 0);
+        }
 }
 
 #ifdef CONFIG_PM_GENERIC_DOMAINS
@@ -443,6 +449,10 @@ static int imx_gpc_probe(struct platform_device *pdev)
         struct regulator *pu_reg;
         int ret;
 
+        /* bail out if DT too old and doesn't provide the necessary info */
+        if (!of_property_read_bool(pdev->dev.of_node, "#power-domain-cells"))
+                return 0;
+
         pu_reg = devm_regulator_get_optional(&pdev->dev, "pu");
         if (PTR_ERR(pu_reg) == -ENODEV)
                 pu_reg = NULL;
diff --git a/arch/arm/mach-pxa/pxa_cplds_irqs.c b/arch/arm/mach-pxa/pxa_cplds_irqs.c
index f1aeb54fabe3..2385052b0ce1 100644
--- a/arch/arm/mach-pxa/pxa_cplds_irqs.c
+++ b/arch/arm/mach-pxa/pxa_cplds_irqs.c
@@ -107,7 +107,7 @@ static int cplds_probe(struct platform_device *pdev)
         struct resource *res;
         struct cplds *fpga;
         int ret;
-        unsigned int base_irq = 0;
+        int base_irq;
         unsigned long irqflags = 0;
 
         fpga = devm_kzalloc(&pdev->dev, sizeof(*fpga), GFP_KERNEL);
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4e6ef896c619..7186382672b5 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1112,22 +1112,22 @@ void __init sanity_check_meminfo(void)
                         }
 
                         /*
-                         * Find the first non-section-aligned page, and point
+                         * Find the first non-pmd-aligned page, and point
                          * memblock_limit at it. This relies on rounding the
-                         * limit down to be section-aligned, which happens at
-                         * the end of this function.
+                         * limit down to be pmd-aligned, which happens at the
+                         * end of this function.
                          *
                          * With this algorithm, the start or end of almost any
-                         * bank can be non-section-aligned. The only exception
-                         * is that the start of the bank 0 must be section-
+                         * bank can be non-pmd-aligned. The only exception is
+                         * that the start of the bank 0 must be section-
                          * aligned, since otherwise memory would need to be
                          * allocated when mapping the start of bank 0, which
                          * occurs before any free memory is mapped.
                          */
                         if (!memblock_limit) {
-                                if (!IS_ALIGNED(block_start, SECTION_SIZE))
+                                if (!IS_ALIGNED(block_start, PMD_SIZE))
                                         memblock_limit = block_start;
-                                else if (!IS_ALIGNED(block_end, SECTION_SIZE))
+                                else if (!IS_ALIGNED(block_end, PMD_SIZE))
                                         memblock_limit = arm_lowmem_limit;
                         }
 
@@ -1137,12 +1137,12 @@ void __init sanity_check_meminfo(void)
         high_memory = __va(arm_lowmem_limit - 1) + 1;
 
         /*
-         * Round the memblock limit down to a section size.  This
+         * Round the memblock limit down to a pmd size.  This
          * helps to ensure that we will allocate memory from the
-         * last full section, which should be mapped.
+         * last full pmd, which should be mapped.
          */
         if (memblock_limit)
-                memblock_limit = round_down(memblock_limit, SECTION_SIZE);
+                memblock_limit = round_down(memblock_limit, PMD_SIZE);
         if (!memblock_limit)
                 memblock_limit = arm_lowmem_limit;
 
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index d4e162d35b34..7cc3be9fa7c6 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -478,9 +478,16 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 
 int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
 {
-        struct pci_controller *controller = bridge->bus->sysdata;
-
-        ACPI_COMPANION_SET(&bridge->dev, controller->companion);
+        /*
+         * We pass NULL as parent to pci_create_root_bus(), so if it is not NULL
+         * here, pci_create_root_bus() has been called by someone else and
+         * sysdata is likely to be different from what we expect.  Let it go in
+         * that case.
+         */
+        if (!bridge->dev.parent) {
+                struct pci_controller *controller = bridge->bus->sysdata;
+                ACPI_COMPANION_SET(&bridge->dev, controller->companion);
+        }
         return 0;
 }
 
diff --git a/arch/mips/ath79/prom.c b/arch/mips/ath79/prom.c
index e1fe63051136..597899ad5438 100644
--- a/arch/mips/ath79/prom.c
+++ b/arch/mips/ath79/prom.c
@@ -1,6 +1,7 @@
 /*
  *  Atheros AR71XX/AR724X/AR913X specific prom routines
  *
+ *  Copyright (C) 2015 Laurent Fasnacht <l@libres.ch>
  *  Copyright (C) 2008-2010 Gabor Juhos <juhosg@openwrt.org>
  *  Copyright (C) 2008 Imre Kaloz <kaloz@openwrt.org>
  *
@@ -25,12 +26,14 @@ void __init prom_init(void)
 {
         fw_init_cmdline();
 
+#ifdef CONFIG_BLK_DEV_INITRD
         /* Read the initrd address from the firmware environment */
         initrd_start = fw_getenvl("initrd_start");
         if (initrd_start) {
                 initrd_start = KSEG0ADDR(initrd_start);
                 initrd_end = initrd_start + fw_getenvl("initrd_size");
         }
+#endif
 }
 
 void __init prom_free_prom_memory(void)
diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig
index 002680648dcb..b2a577ebce0b 100644
--- a/arch/mips/configs/fuloong2e_defconfig
+++ b/arch/mips/configs/fuloong2e_defconfig
@@ -194,7 +194,7 @@ CONFIG_USB_WUSB_CBAF=m
 CONFIG_USB_C67X00_HCD=m
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_ROOT_HUB_TT=y
-CONFIG_USB_ISP1760_HCD=m
+CONFIG_USB_ISP1760=m
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_UHCI_HCD=m
 CONFIG_USB_R8A66597_HCD=m
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index d2bfbc2e8995..51f57d841662 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -29,7 +29,7 @@
 int kgdb_early_setup;
 #endif
 
-static unsigned long irq_map[NR_IRQS / BITS_PER_LONG];
+static DECLARE_BITMAP(irq_map, NR_IRQS);
 
 int allocate_irqno(void)
 {
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index fd528d7ea278..336708ae5c5b 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -444,7 +444,7 @@ struct plat_smp_ops bmips5000_smp_ops = {
 static void bmips_wr_vec(unsigned long dst, char *start, char *end)
 {
         memcpy((void *)dst, start, end - start);
-        dma_cache_wback((unsigned long)start, end - start);
+        dma_cache_wback(dst, end - start);
         local_flush_icache_range(dst, dst + (end - start));
         instruction_hazard();
 }
diff --git a/arch/mips/lib/strnlen_user.S b/arch/mips/lib/strnlen_user.S
index 7d12c0dded3d..77e64942f004 100644
--- a/arch/mips/lib/strnlen_user.S
+++ b/arch/mips/lib/strnlen_user.S
@@ -34,7 +34,12 @@ LEAF(__strnlen_\func\()_asm)
 FEXPORT(__strnlen_\func\()_nocheck_asm)
         move            v0, a0
         PTR_ADDU        a1, a0                  # stop pointer
-1:      beq             v0, a1, 1f              # limit reached?
+1:
+#ifdef CONFIG_CPU_DADDI_WORKAROUNDS
+        .set            noat
+        li              AT, 1
+#endif
+        beq             v0, a1, 1f              # limit reached?
 .ifeqs "\func", "kernel"
         EX(lb, t0, (v0), .Lfault\@)
 .else
@@ -42,7 +47,13 @@ FEXPORT(__strnlen_\func\()_nocheck_asm)
 .endif
         .set            noreorder
         bnez            t0, 1b
-1:       PTR_ADDIU      v0, 1
+1:
+#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
+         PTR_ADDIU      v0, 1
+#else
+         PTR_ADDU       v0, AT
+        .set            at
+#endif
         .set            reorder
         PTR_SUBU        v0, a0
         jr              ra
diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h
index a6e424d185d0..a6cfdabb6054 100644
--- a/arch/sparc/include/asm/cpudata_64.h
+++ b/arch/sparc/include/asm/cpudata_64.h
@@ -24,7 +24,8 @@ typedef struct {
         unsigned int    icache_line_size;
         unsigned int    ecache_size;
         unsigned int    ecache_line_size;
-        int             core_id;
+        unsigned short  sock_id;
+        unsigned short  core_id;
         int             proc_id;
 } cpuinfo_sparc;
 
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index dc165ebdf05a..2a52c91d2c8a 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -308,12 +308,26 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot)
         "       sllx            %1, 32, %1\n"
         "       or              %0, %1, %0\n"
         "       .previous\n"
+        "       .section        .sun_m7_2insn_patch, \"ax\"\n"
+        "       .word           661b\n"
+        "       sethi           %%uhi(%4), %1\n"
+        "       sethi           %%hi(%4), %0\n"
+        "       .word           662b\n"
+        "       or              %1, %%ulo(%4), %1\n"
+        "       or              %0, %%lo(%4), %0\n"
+        "       .word           663b\n"
+        "       sllx            %1, 32, %1\n"
+        "       or              %0, %1, %0\n"
+        "       .previous\n"
         : "=r" (mask), "=r" (tmp)
         : "i" (_PAGE_PADDR_4U | _PAGE_MODIFIED_4U | _PAGE_ACCESSED_4U |
                _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U |
                _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4U),
           "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V |
                _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V |
+               _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V),
+          "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V |
+               _PAGE_CP_4V | _PAGE_E_4V |
                _PAGE_SPECIAL | _PAGE_PMD_HUGE | _PAGE_SZALL_4V));
 
         return __pte((pte_val(pte) & mask) | (pgprot_val(prot) & ~mask));
@@ -342,9 +356,15 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot)
         "       andn            %0, %4, %0\n"
         "       or              %0, %5, %0\n"
         "       .previous\n"
+        "       .section        .sun_m7_2insn_patch, \"ax\"\n"
+        "       .word           661b\n"
+        "       andn            %0, %6, %0\n"
+        "       or              %0, %5, %0\n"
+        "       .previous\n"
         : "=r" (val)
         : "0" (val), "i" (_PAGE_CP_4U | _PAGE_CV_4U), "i" (_PAGE_E_4U),
-                     "i" (_PAGE_CP_4V | _PAGE_CV_4V), "i" (_PAGE_E_4V));
+                     "i" (_PAGE_CP_4V | _PAGE_CV_4V), "i" (_PAGE_E_4V),
+                     "i" (_PAGE_CP_4V));
 
         return __pgprot(val);
 }
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index ed8f071132e4..d1761df5cca6 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -40,11 +40,12 @@ static inline int pcibus_to_node(struct pci_bus *pbus)
 #ifdef CONFIG_SMP
 #define topology_physical_package_id(cpu)       (cpu_data(cpu).proc_id)
 #define topology_core_id(cpu)                   (cpu_data(cpu).core_id)
-#define topology_core_cpumask(cpu)              (&cpu_core_map[cpu])
+#define topology_core_cpumask(cpu)              (&cpu_core_sib_map[cpu])
 #define topology_thread_cpumask(cpu)            (&per_cpu(cpu_sibling_map, cpu))
 #endif /* CONFIG_SMP */
 
 extern cpumask_t cpu_core_map[NR_CPUS];
+extern cpumask_t cpu_core_sib_map[NR_CPUS];
 static inline const struct cpumask *cpu_coregroup_mask(int cpu)
 {
         return &cpu_core_map[cpu];
diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
index 6fd4436d32f0..ec9c04de3664 100644
--- a/arch/sparc/include/asm/trap_block.h
+++ b/arch/sparc/include/asm/trap_block.h
@@ -79,6 +79,8 @@ struct sun4v_2insn_patch_entry {
 };
 extern struct sun4v_2insn_patch_entry __sun4v_2insn_patch,
         __sun4v_2insn_patch_end;
+extern struct sun4v_2insn_patch_entry __sun_m7_2insn_patch,
+        __sun_m7_2insn_patch_end;
 
 
 #endif /* !(__ASSEMBLY__) */
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index 07cc49e541f4..0f679421b468 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -69,6 +69,8 @@ void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *,
                              struct sun4v_1insn_patch_entry *);
 void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
                              struct sun4v_2insn_patch_entry *);
+void sun_m7_patch_2insn_range(struct sun4v_2insn_patch_entry *,
+                             struct sun4v_2insn_patch_entry *);
 extern unsigned int dcache_parity_tl1_occurred;
 extern unsigned int icache_parity_tl1_occurred;
 
diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c
index 94e392bdee7d..814fb1729b12 100644
--- a/arch/sparc/kernel/leon_pci_grpci2.c
+++ b/arch/sparc/kernel/leon_pci_grpci2.c
@@ -723,7 +723,6 @@ static int grpci2_of_probe(struct platform_device *ofdev)
                 err = -ENOMEM;
                 goto err1;
         }
-        memset(grpci2priv, 0, sizeof(*grpci2priv));
         priv->regs = regs;
         priv->irq = ofdev->archdata.irqs[0]; /* BASE IRQ */
         priv->irq_mode = (capability & STS_IRQMODE) >> STS_IRQMODE_BIT;
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index 26c80e18d7b1..6f80936e0eea 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -614,45 +614,68 @@ static void fill_in_one_cache(cpuinfo_sparc *c, struct mdesc_handle *hp, u64 mp)
         }
 }
 
-static void mark_core_ids(struct mdesc_handle *hp, u64 mp, int core_id)
+static void find_back_node_value(struct mdesc_handle *hp, u64 node,
+                                 char *srch_val,
+                                 void (*func)(struct mdesc_handle *, u64, int),
+                                 u64 val, int depth)
 {
-        u64 a;
-
-        mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_BACK) {
-                u64 t = mdesc_arc_target(hp, a);
-                const char *name;
-                const u64 *id;
+        u64 arc;
 
-                name = mdesc_node_name(hp, t);
-                if (!strcmp(name, "cpu")) {
-                        id = mdesc_get_property(hp, t, "id", NULL);
-                        if (*id < NR_CPUS)
-                                cpu_data(*id).core_id = core_id;
-                } else {
-                        u64 j;
+        /* Since we have an estimate of recursion depth, do a sanity check. */
+        if (depth == 0)
+                return;
 
-                        mdesc_for_each_arc(j, hp, t, MDESC_ARC_TYPE_BACK) {
-                                u64 n = mdesc_arc_target(hp, j);
-                                const char *n_name;
+        mdesc_for_each_arc(arc, hp, node, MDESC_ARC_TYPE_BACK) {
+                u64 n = mdesc_arc_target(hp, arc);
+                const char *name = mdesc_node_name(hp, n);
 
-                                n_name = mdesc_node_name(hp, n);
-                                if (strcmp(n_name, "cpu"))
-                                        continue;
+                if (!strcmp(srch_val, name))
+                        (*func)(hp, n, val);
 
-                                id = mdesc_get_property(hp, n, "id", NULL);
-                                if (*id < NR_CPUS)
-                                        cpu_data(*id).core_id = core_id;
-                        }
-                }
+                find_back_node_value(hp, n, srch_val, func, val, depth-1);
         }
 }
 
+static void __mark_core_id(struct mdesc_handle *hp, u64 node,
+                           int core_id)
+{
+        const u64 *id = mdesc_get_property(hp, node, "id", NULL);
+
+        if (*id < num_possible_cpus())
+                cpu_data(*id).core_id = core_id;
+}
+
+static void __mark_sock_id(struct mdesc_handle *hp, u64 node,
+                           int sock_id)
+{
+        const u64 *id = mdesc_get_property(hp, node, "id", NULL);
+
+        if (*id < num_possible_cpus())
+                cpu_data(*id).sock_id = sock_id;
+}
+
+static void mark_core_ids(struct mdesc_handle *hp, u64 mp,
+                          int core_id)
+{
+        find_back_node_value(hp, mp, "cpu", __mark_core_id, core_id, 10);
+}
+
+static void mark_sock_ids(struct mdesc_handle *hp, u64 mp,
+                          int sock_id)
+{
+        find_back_node_value(hp, mp, "cpu", __mark_sock_id, sock_id, 10);
+}
+
 static void set_core_ids(struct mdesc_handle *hp)
 {
         int idx;
         u64 mp;
 
         idx = 1;
+
+        /* Identify unique cores by looking for cpus backpointed to by
+         * level 1 instruction caches.
+         */
         mdesc_for_each_node_by_name(hp, mp, "cache") {
                 const u64 *level;
                 const char *type;
@@ -667,11 +690,72 @@ static void set_core_ids(struct mdesc_handle *hp)
                         continue;
 
                 mark_core_ids(hp, mp, idx);
+                idx++;
+        }
+}
+
+static int set_sock_ids_by_cache(struct mdesc_handle *hp, int level)
+{
+        u64 mp;
+        int idx = 1;
+        int fnd = 0;
+
+        /* Identify unique sockets by looking for cpus backpointed to by
+         * shared level n caches.
+         */
+        mdesc_for_each_node_by_name(hp, mp, "cache") {
+                const u64 *cur_lvl;
+
+                cur_lvl = mdesc_get_property(hp, mp, "level", NULL);
+                if (*cur_lvl != level)
+                        continue;
+
+                mark_sock_ids(hp, mp, idx);
+                idx++;
+                fnd = 1;
+        }
+        return fnd;
+}
+
+static void set_sock_ids_by_socket(struct mdesc_handle *hp, u64 mp)
+{
+        int idx = 1;
 
+        mdesc_for_each_node_by_name(hp, mp, "socket") {
+                u64 a;
+
+                mdesc_for_each_arc(a, hp, mp, MDESC_ARC_TYPE_FWD) {
+                        u64 t = mdesc_arc_target(hp, a);
+                        const char *name;
+                        const u64 *id;
+
+                        name = mdesc_node_name(hp, t);
+                        if (strcmp(name, "cpu"))
+                                continue;
+
+                        id = mdesc_get_property(hp, t, "id", NULL);
+                        if (*id < num_possible_cpus())
+                                cpu_data(*id).sock_id = idx;
+                }
                 idx++;
         }
 }
 
+static void set_sock_ids(struct mdesc_handle *hp)
+{
+        u64 mp;
+
+        /* If machine description exposes sockets data use it.
+         * Otherwise fallback to use shared L3 or L2 caches.
+         */
+        mp = mdesc_node_by_name(hp, MDESC_NODE_NULL, "sockets");
+        if (mp != MDESC_NODE_NULL)
+                return set_sock_ids_by_socket(hp, mp);
+
+        if (!set_sock_ids_by_cache(hp, 3))
+                set_sock_ids_by_cache(hp, 2);
+}
+
 static void mark_proc_ids(struct mdesc_handle *hp, u64 mp, int proc_id)
 {
         u64 a;
@@ -707,7 +791,6 @@ static void __set_proc_ids(struct mdesc_handle *hp, const char *exec_unit_name)
                         continue;
 
                 mark_proc_ids(hp, mp, idx);
-
                 idx++;
         }
 }
@@ -900,6 +983,7 @@ void mdesc_fill_in_cpu_data(cpumask_t *mask)
 
         set_core_ids(hp);
         set_proc_ids(hp);
+        set_sock_ids(hp);
 
         mdesc_release(hp);
 
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 6f7251fd2eab..c928bc64b4ba 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -1002,6 +1002,38 @@ static int __init pcibios_init(void)
 subsys_initcall(pcibios_init);
 
 #ifdef CONFIG_SYSFS
+
+#define SLOT_NAME_SIZE  11  /* Max decimal digits + null in u32 */
+
+static void pcie_bus_slot_names(struct pci_bus *pbus)
+{
+        struct pci_dev *pdev;
+        struct pci_bus *bus;
+
+        list_for_each_entry(pdev, &pbus->devices, bus_list) {
+                char name[SLOT_NAME_SIZE];
+                struct pci_slot *pci_slot;
+                const u32 *slot_num;
+                int len;
+
+                slot_num = of_get_property(pdev->dev.of_node,
+                                           "physical-slot#", &len);
+
+                if (slot_num == NULL || len != 4)
+                        continue;
+
+                snprintf(name, sizeof(name), "%u", slot_num[0]);
+                pci_slot = pci_create_slot(pbus, slot_num[0], name, NULL);
+
+                if (IS_ERR(pci_slot))
+                        pr_err("PCI: pci_create_slot returned %ld.\n",
+                               PTR_ERR(pci_slot));
+        }
+
+        list_for_each_entry(bus, &pbus->children, node)
+                pcie_bus_slot_names(bus);
+}
+
 static void pci_bus_slot_names(struct device_node *node, struct pci_bus *bus)
 {
         const struct pci_slot_names {
@@ -1053,18 +1085,29 @@ static int __init of_pci_slot_init(void)
 
         while ((pbus = pci_find_next_bus(pbus)) != NULL) {
                 struct device_node *node;
+                struct pci_dev *pdev;
+
+                pdev = list_first_entry(&pbus->devices, struct pci_dev,
+                                        bus_list);
 
-                if (pbus->self) {
-                        /* PCI->PCI bridge */
-                        node = pbus->self->dev.of_node;
+                if (pdev && pci_is_pcie(pdev)) {
+                        pcie_bus_slot_names(pbus);
                 } else {
-                        struct pci_pbm_info *pbm = pbus->sysdata;
 
-                        /* Host PCI controller */
-                        node = pbm->op->dev.of_node;
-                }
+                        if (pbus->self) {
+
+                                /* PCI->PCI bridge */
+                                node = pbus->self->dev.of_node;
+
+                        } else {
+                                struct pci_pbm_info *pbm = pbus->sysdata;
 
-                pci_bus_slot_names(node, pbus);
+                                /* Host PCI controller */
+                                node = pbm->op->dev.of_node;
+                        }
+
+                        pci_bus_slot_names(node, pbus);
+                }
         }
 
         return 0;
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index c38d19fc27ba..f7b261749383 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -255,6 +255,24 @@ void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
         }
 }
 
+void sun_m7_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
+                             struct sun4v_2insn_patch_entry *end)
+{
+        while (start < end) {
+                unsigned long addr = start->addr;
+
+                *(unsigned int *) (addr +  0) = start->insns[0];
+                wmb();
+                __asm__ __volatile__("flush     %0" : : "r" (addr +  0));
+
+                *(unsigned int *) (addr +  4) = start->insns[1];
+                wmb();
+                __asm__ __volatile__("flush     %0" : : "r" (addr +  4));
+
+                start++;
+        }
+}
+
 static void __init sun4v_patch(void)
 {
         extern void sun4v_hvapi_init(void);
@@ -267,6 +285,9 @@ static void __init sun4v_patch(void)
 
         sun4v_patch_2insn_range(&__sun4v_2insn_patch,
                                 &__sun4v_2insn_patch_end);
+        if (sun4v_chip_type == SUN4V_CHIP_SPARC_M7)
+                sun_m7_patch_2insn_range(&__sun_m7_2insn_patch,
+                                         &__sun_m7_2insn_patch_end);
 
         sun4v_hvapi_init();
 }
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 61139d9924ca..19cd08d18672 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -60,8 +60,12 @@ DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly =
         { [0 ... NR_CPUS-1] = CPU_MASK_NONE };
 
+cpumask_t cpu_core_sib_map[NR_CPUS] __read_mostly = {
+        [0 ... NR_CPUS-1] = CPU_MASK_NONE };
+
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 EXPORT_SYMBOL(cpu_core_map);
+EXPORT_SYMBOL(cpu_core_sib_map);
 
 static cpumask_t smp_commenced_mask;
 
@@ -1243,6 +1247,15 @@ void smp_fill_in_sib_core_maps(void)
                 }
         }
 
+        for_each_present_cpu(i)  {
+                unsigned int j;
+
+                for_each_present_cpu(j)  {
+                        if (cpu_data(i).sock_id == cpu_data(j).sock_id)
+                                cpumask_set_cpu(j, &cpu_core_sib_map[i]);
+                }
+        }
+
         for_each_present_cpu(i) {
                 unsigned int j;
 
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 09243057cb0b..f1a2f688b28a 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -138,6 +138,11 @@ SECTIONS
                 *(.pause_3insn_patch)
                 __pause_3insn_patch_end = .;
         }
+        .sun_m7_2insn_patch : {
+                __sun_m7_2insn_patch = .;
+                *(.sun_m7_2insn_patch)
+                __sun_m7_2insn_patch_end = .;
+        }
         PERCPU_SECTION(SMP_CACHE_BYTES)
 
         . = ALIGN(PAGE_SIZE);
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 4ca0d6ba5ec8..559cb744112c 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -54,6 +54,7 @@
 #include "init_64.h"
 
 unsigned long kern_linear_pte_xor[4] __read_mostly;
+static unsigned long page_cache4v_flag;
 
 /* A bitmap, two bits for every 256MB of physical memory.  These two
  * bits determine what page size we use for kernel linear
@@ -1909,11 +1910,24 @@ static void __init sun4u_linear_pte_xor_finalize(void)
 
 static void __init sun4v_linear_pte_xor_finalize(void)
 {
+        unsigned long pagecv_flag;
+
+        /* Bit 9 of TTE is no longer CV bit on M7 processor and it instead
+         * enables MCD error. Do not set bit 9 on M7 processor.
+         */
+        switch (sun4v_chip_type) {
+        case SUN4V_CHIP_SPARC_M7:
+                pagecv_flag = 0x00;
+                break;
+        default:
+                pagecv_flag = _PAGE_CV_4V;
+                break;
+        }
 #ifndef CONFIG_DEBUG_PAGEALLOC
         if (cpu_pgsz_mask & HV_PGSZ_MASK_256MB) {
                 kern_linear_pte_xor[1] = (_PAGE_VALID | _PAGE_SZ256MB_4V) ^
                         PAGE_OFFSET;
-                kern_linear_pte_xor[1] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+                kern_linear_pte_xor[1] |= (_PAGE_CP_4V | pagecv_flag |
                                            _PAGE_P_4V | _PAGE_W_4V);
         } else {
                 kern_linear_pte_xor[1] = kern_linear_pte_xor[0];
@@ -1922,7 +1936,7 @@ static void __init sun4v_linear_pte_xor_finalize(void)
         if (cpu_pgsz_mask & HV_PGSZ_MASK_2GB) {
                 kern_linear_pte_xor[2] = (_PAGE_VALID | _PAGE_SZ2GB_4V) ^
                         PAGE_OFFSET;
-                kern_linear_pte_xor[2] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+                kern_linear_pte_xor[2] |= (_PAGE_CP_4V | pagecv_flag |
                                            _PAGE_P_4V | _PAGE_W_4V);
         } else {
                 kern_linear_pte_xor[2] = kern_linear_pte_xor[1];
@@ -1931,7 +1945,7 @@ static void __init sun4v_linear_pte_xor_finalize(void)
         if (cpu_pgsz_mask & HV_PGSZ_MASK_16GB) {
                 kern_linear_pte_xor[3] = (_PAGE_VALID | _PAGE_SZ16GB_4V) ^
                         PAGE_OFFSET;
-                kern_linear_pte_xor[3] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+                kern_linear_pte_xor[3] |= (_PAGE_CP_4V | pagecv_flag |
                                            _PAGE_P_4V | _PAGE_W_4V);
         } else {
                 kern_linear_pte_xor[3] = kern_linear_pte_xor[2];
@@ -1958,6 +1972,13 @@ static phys_addr_t __init available_memory(void)
         return available;
 }
 
+#define _PAGE_CACHE_4U  (_PAGE_CP_4U | _PAGE_CV_4U)
+#define _PAGE_CACHE_4V  (_PAGE_CP_4V | _PAGE_CV_4V)
+#define __DIRTY_BITS_4U  (_PAGE_MODIFIED_4U | _PAGE_WRITE_4U | _PAGE_W_4U)
+#define __DIRTY_BITS_4V  (_PAGE_MODIFIED_4V | _PAGE_WRITE_4V | _PAGE_W_4V)
+#define __ACCESS_BITS_4U (_PAGE_ACCESSED_4U | _PAGE_READ_4U | _PAGE_R)
+#define __ACCESS_BITS_4V (_PAGE_ACCESSED_4V | _PAGE_READ_4V | _PAGE_R)
+
 /* We need to exclude reserved regions. This exclusion will include
  * vmlinux and initrd. To be more precise the initrd size could be used to
  * compute a new lower limit because it is freed later during initialization.
@@ -2034,6 +2055,25 @@ void __init paging_init(void)
         memset(swapper_4m_tsb, 0x40, sizeof(swapper_4m_tsb));
 #endif
 
+        /* TTE.cv bit on sparc v9 occupies the same position as TTE.mcde
+         * bit on M7 processor. This is a conflicting usage of the same
+         * bit. Enabling TTE.cv on M7 would turn on Memory Corruption
+         * Detection error on all pages and this will lead to problems
+         * later. Kernel does not run with MCD enabled and hence rest
+         * of the required steps to fully configure memory corruption
+         * detection are not taken. We need to ensure TTE.mcde is not
+         * set on M7 processor. Compute the value of cacheability
+         * flag for use later taking this into consideration.
+         */
+        switch (sun4v_chip_type) {
+        case SUN4V_CHIP_SPARC_M7:
+                page_cache4v_flag = _PAGE_CP_4V;
+                break;
+        default:
+                page_cache4v_flag = _PAGE_CACHE_4V;
+                break;
+        }
+
         if (tlb_type == hypervisor)
                 sun4v_pgprot_init();
         else
@@ -2274,13 +2314,6 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 }
 #endif
 
-#define _PAGE_CACHE_4U  (_PAGE_CP_4U | _PAGE_CV_4U)
-#define _PAGE_CACHE_4V  (_PAGE_CP_4V | _PAGE_CV_4V)
-#define __DIRTY_BITS_4U  (_PAGE_MODIFIED_4U | _PAGE_WRITE_4U | _PAGE_W_4U)
-#define __DIRTY_BITS_4V  (_PAGE_MODIFIED_4V | _PAGE_WRITE_4V | _PAGE_W_4V)
-#define __ACCESS_BITS_4U (_PAGE_ACCESSED_4U | _PAGE_READ_4U | _PAGE_R)
-#define __ACCESS_BITS_4V (_PAGE_ACCESSED_4V | _PAGE_READ_4V | _PAGE_R)
-
 pgprot_t PAGE_KERNEL __read_mostly;
 EXPORT_SYMBOL(PAGE_KERNEL);
 
@@ -2312,8 +2345,7 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
                     _PAGE_P_4U | _PAGE_W_4U);
         if (tlb_type == hypervisor)
                 pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4V |
-                            _PAGE_CP_4V | _PAGE_CV_4V |
-                            _PAGE_P_4V | _PAGE_W_4V);
+                            page_cache4v_flag | _PAGE_P_4V | _PAGE_W_4V);
 
         pte_base |= _PAGE_PMD_HUGE;
 
@@ -2450,14 +2482,14 @@ static void __init sun4v_pgprot_init(void)
         int i;
 
         PAGE_KERNEL = __pgprot (_PAGE_PRESENT_4V | _PAGE_VALID |
-                                _PAGE_CACHE_4V | _PAGE_P_4V |
+                                page_cache4v_flag | _PAGE_P_4V |
                                 __ACCESS_BITS_4V | __DIRTY_BITS_4V |
                                 _PAGE_EXEC_4V);
         PAGE_KERNEL_LOCKED = PAGE_KERNEL;
 
         _PAGE_IE = _PAGE_IE_4V;
         _PAGE_E = _PAGE_E_4V;
-        _PAGE_CACHE = _PAGE_CACHE_4V;
+        _PAGE_CACHE = page_cache4v_flag;
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
         kern_linear_pte_xor[0] = _PAGE_VALID ^ PAGE_OFFSET;
@@ -2465,8 +2497,8 @@ static void __init sun4v_pgprot_init(void)
         kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZ4MB_4V) ^
                 PAGE_OFFSET;
 #endif
-        kern_linear_pte_xor[0] |= (_PAGE_CP_4V | _PAGE_CV_4V |
-                                   _PAGE_P_4V | _PAGE_W_4V);
+        kern_linear_pte_xor[0] |= (page_cache4v_flag | _PAGE_P_4V |
+                                   _PAGE_W_4V);
 
         for (i = 1; i < 4; i++)
                 kern_linear_pte_xor[i] = kern_linear_pte_xor[0];
@@ -2479,12 +2511,12 @@ static void __init sun4v_pgprot_init(void)
                              _PAGE_SZ4MB_4V | _PAGE_SZ512K_4V |
                              _PAGE_SZ64K_4V | _PAGE_SZ8K_4V);
 
-        page_none = _PAGE_PRESENT_4V | _PAGE_ACCESSED_4V | _PAGE_CACHE_4V;
-        page_shared = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+        page_none = _PAGE_PRESENT_4V | _PAGE_ACCESSED_4V | page_cache4v_flag;
+        page_shared = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
                        __ACCESS_BITS_4V | _PAGE_WRITE_4V | _PAGE_EXEC_4V);
-        page_copy   = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+        page_copy   = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
                        __ACCESS_BITS_4V | _PAGE_EXEC_4V);
-        page_readonly = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+        page_readonly = (_PAGE_VALID | _PAGE_PRESENT_4V | page_cache4v_flag |
                          __ACCESS_BITS_4V | _PAGE_EXEC_4V);
 
         page_exec_bit = _PAGE_EXEC_4V;
@@ -2542,7 +2574,7 @@ static unsigned long kern_large_tte(unsigned long paddr)
                _PAGE_EXEC_4U | _PAGE_L_4U | _PAGE_W_4U);
         if (tlb_type == hypervisor)
                 val = (_PAGE_VALID | _PAGE_SZ4MB_4V |
-                       _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_P_4V |
+                       page_cache4v_flag | _PAGE_P_4V |
                        _PAGE_EXEC_4V | _PAGE_W_4V);
 
         return val | paddr;
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index c469490db4a8..3c6bb342a48f 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -140,6 +140,7 @@
 #define MSR_CORE_C3_RESIDENCY           0x000003fc
 #define MSR_CORE_C6_RESIDENCY           0x000003fd
 #define MSR_CORE_C7_RESIDENCY           0x000003fe
+#define MSR_KNL_CORE_C6_RESIDENCY       0x000003ff
 #define MSR_PKG_C2_RESIDENCY            0x0000060d
 #define MSR_PKG_C8_RESIDENCY            0x00000630
 #define MSR_PKG_C9_RESIDENCY            0x00000631
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index d93963340c3c..14a63ed6fe09 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -482,9 +482,16 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 
 int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
 {
-        struct pci_sysdata *sd = bridge->bus->sysdata;
-
-        ACPI_COMPANION_SET(&bridge->dev, sd->companion);
+        /*
+         * We pass NULL as parent to pci_create_root_bus(), so if it is not NULL
+         * here, pci_create_root_bus() has been called by someone else and
+         * sysdata is likely to be different from what we expect.  Let it go in
+         * that case.
+         */
+        if (!bridge->dev.parent) {
+                struct pci_sysdata *sd = bridge->bus->sysdata;
+                ACPI_COMPANION_SET(&bridge->dev, sd->companion);
+        }
         return 0;
 }
 
diff --git a/arch/xtensa/include/asm/dma-mapping.h b/arch/xtensa/include/asm/dma-mapping.h
index 172a02a6ad14..ba78ccf651e7 100644
--- a/arch/xtensa/include/asm/dma-mapping.h
+++ b/arch/xtensa/include/asm/dma-mapping.h
@@ -185,4 +185,17 @@ static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt,
         return -EINVAL;
 }
 
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+                                    dma_addr_t *dma_handle, gfp_t flag,
+                                    struct dma_attrs *attrs)
+{
+        return NULL;
+}
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+                                  void *vaddr, dma_addr_t dma_handle,
+                                  struct dma_attrs *attrs)
+{
+}
+
 #endif  /* _XTENSA_DMA_MAPPING_H */
diff --git a/drivers/bus/mips_cdmm.c b/drivers/bus/mips_cdmm.c
index 5bd792c68f9b..ab3bde16ecb4 100644
--- a/drivers/bus/mips_cdmm.c
+++ b/drivers/bus/mips_cdmm.c
@@ -453,7 +453,7 @@ void __iomem *mips_cdmm_early_probe(unsigned int dev_type)
 
         /* Look for a specific device type */
         for (; drb < bus->drbs; drb += size + 1) {
-                acsr = readl(cdmm + drb * CDMM_DRB_SIZE);
+                acsr = __raw_readl(cdmm + drb * CDMM_DRB_SIZE);
                 type = (acsr & CDMM_ACSR_DEVTYPE) >> CDMM_ACSR_DEVTYPE_SHIFT;
                 if (type == dev_type)
                         return cdmm + drb * CDMM_DRB_SIZE;
@@ -500,7 +500,7 @@ static void mips_cdmm_bus_discover(struct mips_cdmm_bus *bus)
         bus->discovered = true;
         pr_info("cdmm%u discovery (%u blocks)\n", cpu, bus->drbs);
         for (; drb < bus->drbs; drb += size + 1) {
-                acsr = readl(cdmm + drb * CDMM_DRB_SIZE);
+                acsr = __raw_readl(cdmm + drb * CDMM_DRB_SIZE);
                 type = (acsr & CDMM_ACSR_DEVTYPE) >> CDMM_ACSR_DEVTYPE_SHIFT;
                 size = (acsr & CDMM_ACSR_DEVSIZE) >> CDMM_ACSR_DEVSIZE_SHIFT;
                 rev  = (acsr & CDMM_ACSR_DEVREV)  >> CDMM_ACSR_DEVREV_SHIFT;
diff --git a/drivers/gpu/drm/drm_plane_helper.c b/drivers/gpu/drm/drm_plane_helper.c
index 40c1db9ad7c3..2f0ed11024eb 100644
--- a/drivers/gpu/drm/drm_plane_helper.c
+++ b/drivers/gpu/drm/drm_plane_helper.c
@@ -465,6 +465,9 @@ int drm_plane_helper_commit(struct drm_plane *plane,
                 if (!crtc[i])
                         continue;
 
+                if (crtc[i]->cursor == plane)
+                        continue;
+
                 /* There's no other way to figure out whether the crtc is running. */
                 ret = drm_crtc_vblank_get(crtc[i]);
                 if (ret == 0) {
diff --git a/drivers/gpu/drm/nouveau/include/nvif/class.h b/drivers/gpu/drm/nouveau/include/nvif/class.h
index 0b5af0fe8659..64f8b2f687d2 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/class.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/class.h
@@ -14,7 +14,7 @@
 
 #define FERMI_TWOD_A                                                 0x0000902d
 
-#define FERMI_MEMORY_TO_MEMORY_FORMAT_A                              0x0000903d
+#define FERMI_MEMORY_TO_MEMORY_FORMAT_A                              0x00009039
 
 #define KEPLER_INLINE_TO_MEMORY_A                                    0x0000a040
 #define KEPLER_INLINE_TO_MEMORY_B                                    0x0000a140
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm204.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm204.c
index 2f5eadd12a9b..fdb1dcf16a59 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm204.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm204.c
@@ -329,7 +329,6 @@ gm204_gr_init(struct nvkm_object *object)
         nv_mask(priv, 0x419cc0, 0x00000008, 0x00000008);
 
         for (gpc = 0; gpc < priv->gpc_nr; gpc++) {
-        printk(KERN_ERR "ppc %d %d\n", gpc, priv->ppc_nr[gpc]);
                 for (ppc = 0; ppc < priv->ppc_nr[gpc]; ppc++)
                         nv_wr32(priv, PPC_UNIT(gpc, ppc, 0x038), 0xc0000000);
                 nv_wr32(priv, GPC_UNIT(gpc, 0x0420), 0xc0000000);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gf100.c
index e8778c67578e..c61102f70805 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gf100.c
@@ -90,12 +90,14 @@ gf100_devinit_disable(struct nvkm_devinit *devinit)
         return disable;
 }
 
-static int
+int
 gf100_devinit_ctor(struct nvkm_object *parent, struct nvkm_object *engine,
                    struct nvkm_oclass *oclass, void *data, u32 size,
                    struct nvkm_object **pobject)
 {
+        struct nvkm_devinit_impl *impl = (void *)oclass;
         struct nv50_devinit_priv *priv;
+        u64 disable;
         int ret;
 
         ret = nvkm_devinit_create(parent, engine, oclass, &priv);
@@ -103,7 +105,8 @@ gf100_devinit_ctor(struct nvkm_object *parent, struct nvkm_object *engine,
         if (ret)
                 return ret;
 
-        if (nv_rd32(priv, 0x022500) & 0x00000001)
+        disable = impl->disable(&priv->base);
+        if (disable & (1ULL << NVDEV_ENGINE_DISP))
                 priv->base.post = true;
 
         return 0;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
index b345a53e881d..87ca0ece37b4 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
@@ -48,7 +48,7 @@ struct nvkm_oclass *
 gm107_devinit_oclass = &(struct nvkm_devinit_impl) {
         .base.handle = NV_SUBDEV(DEVINIT, 0x07),
         .base.ofuncs = &(struct nvkm_ofuncs) {
-                .ctor = nv50_devinit_ctor,
+                .ctor = gf100_devinit_ctor,
                 .dtor = _nvkm_devinit_dtor,
                 .init = nv50_devinit_init,
                 .fini = _nvkm_devinit_fini,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm204.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm204.c
index 535172c5f1ad..1076fcf0d716 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm204.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm204.c
@@ -161,7 +161,7 @@ struct nvkm_oclass *
 gm204_devinit_oclass = &(struct nvkm_devinit_impl) {
         .base.handle = NV_SUBDEV(DEVINIT, 0x07),
         .base.ofuncs = &(struct nvkm_ofuncs) {
-                .ctor = nv50_devinit_ctor,
+                .ctor = gf100_devinit_ctor,
                 .dtor = _nvkm_devinit_dtor,
                 .init = nv50_devinit_init,
                 .fini = _nvkm_devinit_fini,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h
index b882b65ff3cd..9243521c80ac 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/nv50.h
@@ -15,6 +15,9 @@ int  nv50_devinit_pll_set(struct nvkm_devinit *, u32, u32);
 
 int  gt215_devinit_pll_set(struct nvkm_devinit *, u32, u32);
 
+int  gf100_devinit_ctor(struct nvkm_object *, struct nvkm_object *,
+                        struct nvkm_oclass *, void *, u32,
+                        struct nvkm_object **);
 int  gf100_devinit_pll_set(struct nvkm_devinit *, u32, u32);
 
 u64  gm107_devinit_disable(struct nvkm_devinit *);
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 42b2ea3fdcf3..e597ffc26563 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1798,7 +1798,9 @@ static int radeon_get_shared_nondp_ppll(struct drm_crtc *crtc)
                         if ((crtc->mode.clock == test_crtc->mode.clock) &&
                             (adjusted_clock == test_adjusted_clock) &&
                             (radeon_crtc->ss_enabled == test_radeon_crtc->ss_enabled) &&
-                            (test_radeon_crtc->pll_id != ATOM_PPLL_INVALID))
+                            (test_radeon_crtc->pll_id != ATOM_PPLL_INVALID) &&
+                            (drm_detect_monitor_audio(radeon_connector_edid(test_radeon_crtc->connector)) ==
+                             drm_detect_monitor_audio(radeon_connector_edid(radeon_crtc->connector))))
                                 return test_radeon_crtc->pll_id;
                 }
         }
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index a0c35bbc8546..ba50f3c1c2e0 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -5822,7 +5822,7 @@ static int cik_pcie_gart_enable(struct radeon_device *rdev)
                L2_CACHE_BIGK_FRAGMENT_SIZE(4));
         /* setup context0 */
         WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12);
-        WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1);
+        WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12);
         WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12);
         WREG32(VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR,
                         (u32)(rdev->dummy_page.addr >> 12));
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 05e6d6ef5963..f848acfd3fc8 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2485,7 +2485,7 @@ static int evergreen_pcie_gart_enable(struct radeon_device *rdev)
         WREG32(MC_VM_MB_L1_TLB2_CNTL, tmp);
         WREG32(MC_VM_MB_L1_TLB3_CNTL, tmp);
         WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12);
-        WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1);
+        WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12);
         WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12);
         WREG32(VM_CONTEXT0_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(0) |
                                 RANGE_PROTECTION_FAULT_ENABLE_DEFAULT);
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index 0926739c9fa7..9953356fe263 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -400,7 +400,7 @@ void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable)
         if (enable) {
                 struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 
-                if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+                if (connector && drm_detect_monitor_audio(radeon_connector_edid(connector))) {
                         WREG32(HDMI_INFOFRAME_CONTROL0 + dig->afmt->offset,
                                HDMI_AVI_INFO_SEND | /* enable AVI info frames */
                                HDMI_AVI_INFO_CONT | /* required for audio info values to be updated */
@@ -438,7 +438,8 @@ void evergreen_dp_enable(struct drm_encoder *encoder, bool enable)
         if (!dig || !dig->afmt)
                 return;
 
-        if (enable && drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+        if (enable && connector &&
+            drm_detect_monitor_audio(radeon_connector_edid(connector))) {
                 struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
                 struct radeon_connector *radeon_connector = to_radeon_connector(connector);
                 struct radeon_connector_atom_dig *dig_connector;
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index aba2f428c0a8..64d3a771920d 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1282,7 +1282,7 @@ static int cayman_pcie_gart_enable(struct radeon_device *rdev)
                L2_CACHE_BIGK_FRAGMENT_SIZE(6));
         /* setup context0 */
         WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12);
-        WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1);
+        WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12);
         WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12);
         WREG32(VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR,
                         (u32)(rdev->dummy_page.addr >> 12));
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 25b4ac967742..8f6d862a1882 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1112,7 +1112,7 @@ static int r600_pcie_gart_enable(struct radeon_device *rdev)
         WREG32(MC_VM_L1_TLB_MCB_RD_SEM_CNTL, tmp | ENABLE_SEMAPHORE_MODE);
         WREG32(MC_VM_L1_TLB_MCB_WR_SEM_CNTL, tmp | ENABLE_SEMAPHORE_MODE);
         WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12);
-        WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1);
+        WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12);
         WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12);
         WREG32(VM_CONTEXT0_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(0) |
                                 RANGE_PROTECTION_FAULT_ENABLE_DEFAULT);
diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c
index dcb779647c57..25191f126f3b 100644
--- a/drivers/gpu/drm/radeon/radeon_audio.c
+++ b/drivers/gpu/drm/radeon/radeon_audio.c
@@ -460,9 +460,6 @@ void radeon_audio_detect(struct drm_connector *connector,
         if (!connector || !connector->encoder)
                 return;
 
-        if (!radeon_encoder_is_digital(connector->encoder))
-                return;
-
         rdev = connector->encoder->dev->dev_private;
 
         if (!radeon_audio_chipset_supported(rdev))
@@ -471,26 +468,26 @@ void radeon_audio_detect(struct drm_connector *connector,
         radeon_encoder = to_radeon_encoder(connector->encoder);
         dig = radeon_encoder->enc_priv;
 
-        if (!dig->afmt)
-                return;
-
         if (status == connector_status_connected) {
-                struct radeon_connector *radeon_connector = to_radeon_connector(connector);
+                struct radeon_connector *radeon_connector;
+                int sink_type;
+
+                if (!drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+                        radeon_encoder->audio = NULL;
+                        return;
+                }
+
+                radeon_connector = to_radeon_connector(connector);
+                sink_type = radeon_dp_getsinktype(radeon_connector);
 
                 if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort &&
-                    radeon_dp_getsinktype(radeon_connector) ==
-                    CONNECTOR_OBJECT_ID_DISPLAYPORT)
+                        sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT)
                         radeon_encoder->audio = rdev->audio.dp_funcs;
                 else
                         radeon_encoder->audio = rdev->audio.hdmi_funcs;
 
                 dig->afmt->pin = radeon_audio_get_pin(connector->encoder);
-                if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
-                        radeon_audio_enable(rdev, dig->afmt->pin, 0xf);
-                } else {
-                        radeon_audio_enable(rdev, dig->afmt->pin, 0);
-                        dig->afmt->pin = NULL;
-                }
+                radeon_audio_enable(rdev, dig->afmt->pin, 0xf);
         } else {
                 radeon_audio_enable(rdev, dig->afmt->pin, 0);
                 dig->afmt->pin = NULL;
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index d17d251dbd4f..cebb65e07e1d 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1379,10 +1379,8 @@ out:
         /* updated in get modes as well since we need to know if it's analog or digital */
         radeon_connector_update_scratch_regs(connector, ret);
 
-        if (radeon_audio != 0) {
-                radeon_connector_get_edid(connector);
+        if (radeon_audio != 0)
                 radeon_audio_detect(connector, ret);
-        }
 
 exit:
         pm_runtime_mark_last_busy(connector->dev->dev);
@@ -1719,10 +1717,8 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
 
         radeon_connector_update_scratch_regs(connector, ret);
 
-        if (radeon_audio != 0) {
-                radeon_connector_get_edid(connector);
+        if (radeon_audio != 0)
                 radeon_audio_detect(connector, ret);
-        }
 
 out:
         pm_runtime_mark_last_busy(connector->dev->dev);
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index c54d6313a46d..01ee96acb398 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -921,7 +921,7 @@ static int rv770_pcie_gart_enable(struct radeon_device *rdev)
         WREG32(MC_VM_MB_L1_TLB2_CNTL, tmp);
         WREG32(MC_VM_MB_L1_TLB3_CNTL, tmp);
         WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12);
-        WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1);
+        WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12);
         WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12);
         WREG32(VM_CONTEXT0_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(0) |
                                 RANGE_PROTECTION_FAULT_ENABLE_DEFAULT);
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 5326f753e107..4c679b802bc8 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -4303,7 +4303,7 @@ static int si_pcie_gart_enable(struct radeon_device *rdev)
                L2_CACHE_BIGK_FRAGMENT_SIZE(4));
         /* setup context0 */
         WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12);
-        WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, (rdev->mc.gtt_end >> 12) - 1);
+        WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12);
         WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR, rdev->gart.table_addr >> 12);
         WREG32(VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR,
                         (u32)(rdev->dummy_page.addr >> 12));
diff --git a/drivers/gpu/drm/vgem/Makefile b/drivers/gpu/drm/vgem/Makefile
index 1055cb79096c..3f4c7b842028 100644
--- a/drivers/gpu/drm/vgem/Makefile
+++ b/drivers/gpu/drm/vgem/Makefile
@@ -1,4 +1,4 @@
 ccflags-y := -Iinclude/drm
-vgem-y := vgem_drv.o vgem_dma_buf.o
+vgem-y := vgem_drv.o
 
 obj-$(CONFIG_DRM_VGEM)  += vgem.o
diff --git a/drivers/gpu/drm/vgem/vgem_dma_buf.c b/drivers/gpu/drm/vgem/vgem_dma_buf.c
deleted file mode 100644
index 0254438ad1a6..000000000000
--- a/drivers/gpu/drm/vgem/vgem_dma_buf.c
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * Copyright © 2012 Intel Corporation
- * Copyright © 2014 The Chromium OS Authors
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- *
- * Authors:
- *    Ben Widawsky <ben@bwidawsk.net>
- *
- */
-
-#include <linux/dma-buf.h>
-#include "vgem_drv.h"
-
-struct sg_table *vgem_gem_prime_get_sg_table(struct drm_gem_object *gobj)
-{
-        struct drm_vgem_gem_object *obj = to_vgem_bo(gobj);
-        BUG_ON(obj->pages == NULL);
-
-        return drm_prime_pages_to_sg(obj->pages, obj->base.size / PAGE_SIZE);
-}
-
-int vgem_gem_prime_pin(struct drm_gem_object *gobj)
-{
-        struct drm_vgem_gem_object *obj = to_vgem_bo(gobj);
-        return vgem_gem_get_pages(obj);
-}
-
-void vgem_gem_prime_unpin(struct drm_gem_object *gobj)
-{
-        struct drm_vgem_gem_object *obj = to_vgem_bo(gobj);
-        vgem_gem_put_pages(obj);
-}
-
-void *vgem_gem_prime_vmap(struct drm_gem_object *gobj)
-{
-        struct drm_vgem_gem_object *obj = to_vgem_bo(gobj);
-        BUG_ON(obj->pages == NULL);
-
-        return vmap(obj->pages, obj->base.size / PAGE_SIZE, 0, PAGE_KERNEL);
-}
-
-void vgem_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
-{
-        vunmap(vaddr);
-}
-
-struct drm_gem_object *vgem_gem_prime_import(struct drm_device *dev,
-                                             struct dma_buf *dma_buf)
-{
-        struct drm_vgem_gem_object *obj = NULL;
-        int ret;
-
-        obj = kzalloc(sizeof(*obj), GFP_KERNEL);
-        if (obj == NULL) {
-                ret = -ENOMEM;
-                goto fail;
-        }
-
-        ret = drm_gem_object_init(dev, &obj->base, dma_buf->size);
-        if (ret) {
-                ret = -ENOMEM;
-                goto fail_free;
-        }
-
-        get_dma_buf(dma_buf);
-
-        obj->base.dma_buf = dma_buf;
-        obj->use_dma_buf = true;
-
-        return &obj->base;
-
-fail_free:
-        kfree(obj);
-fail:
-        return ERR_PTR(ret);
-}
diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index cb3b43525b2d..7a207ca547be 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -302,22 +302,13 @@ static const struct file_operations vgem_driver_fops = {
 };
 
 static struct drm_driver vgem_driver = {
-        .driver_features                = DRIVER_GEM | DRIVER_PRIME,
+        .driver_features                = DRIVER_GEM,
         .gem_free_object                = vgem_gem_free_object,
         .gem_vm_ops                     = &vgem_gem_vm_ops,
         .ioctls                         = vgem_ioctls,
         .fops                           = &vgem_driver_fops,
         .dumb_create                    = vgem_gem_dumb_create,
         .dumb_map_offset                = vgem_gem_dumb_map,
-        .prime_handle_to_fd             = drm_gem_prime_handle_to_fd,
-        .prime_fd_to_handle             = drm_gem_prime_fd_to_handle,
-        .gem_prime_export               = drm_gem_prime_export,
-        .gem_prime_import               = vgem_gem_prime_import,
-        .gem_prime_pin                  = vgem_gem_prime_pin,
-        .gem_prime_unpin                = vgem_gem_prime_unpin,
-        .gem_prime_get_sg_table         = vgem_gem_prime_get_sg_table,
-        .gem_prime_vmap                 = vgem_gem_prime_vmap,
-        .gem_prime_vunmap               = vgem_gem_prime_vunmap,
         .name   = DRIVER_NAME,
         .desc   = DRIVER_DESC,
         .date   = DRIVER_DATE,
diff --git a/drivers/gpu/drm/vgem/vgem_drv.h b/drivers/gpu/drm/vgem/vgem_drv.h
index 57ab4d8f41f9..e9f92f7ee275 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.h
+++ b/drivers/gpu/drm/vgem/vgem_drv.h
@@ -43,15 +43,4 @@ struct drm_vgem_gem_object {
 extern void vgem_gem_put_pages(struct drm_vgem_gem_object *obj);
 extern int vgem_gem_get_pages(struct drm_vgem_gem_object *obj);
 
-/* vgem_dma_buf.c */
-extern struct sg_table *vgem_gem_prime_get_sg_table(
-                        struct drm_gem_object *gobj);
-extern int vgem_gem_prime_pin(struct drm_gem_object *gobj);
-extern void vgem_gem_prime_unpin(struct drm_gem_object *gobj);
-extern void *vgem_gem_prime_vmap(struct drm_gem_object *gobj);
-extern void vgem_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
-extern struct drm_gem_object *vgem_gem_prime_import(struct drm_device *dev,
-                                                    struct dma_buf *dma_buf);
-
-
 #endif
diff --git a/drivers/hwmon/nct6683.c b/drivers/hwmon/nct6683.c
index f3830db02d46..37f01702d081 100644
--- a/drivers/hwmon/nct6683.c
+++ b/drivers/hwmon/nct6683.c
@@ -439,6 +439,7 @@ nct6683_create_attr_group(struct device *dev, struct sensor_template_group *tg,
                                  (*t)->dev_attr.attr.name, tg->base + i);
                         if ((*t)->s2) {
                                 a2 = &su->u.a2;
+                                sysfs_attr_init(&a2->dev_attr.attr);
                                 a2->dev_attr.attr.name = su->name;
                                 a2->nr = (*t)->u.s.nr + i;
                                 a2->index = (*t)->u.s.index;
@@ -449,6 +450,7 @@ nct6683_create_attr_group(struct device *dev, struct sensor_template_group *tg,
                                 *attrs = &a2->dev_attr.attr;
                         } else {
                                 a = &su->u.a1;
+                                sysfs_attr_init(&a->dev_attr.attr);
                                 a->dev_attr.attr.name = su->name;
                                 a->index = (*t)->u.index + i;
                                 a->dev_attr.attr.mode =
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index 4fcb48103299..bd1c99deac71 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -995,6 +995,7 @@ nct6775_create_attr_group(struct device *dev, struct sensor_template_group *tg,
                                  (*t)->dev_attr.attr.name, tg->base + i);
                         if ((*t)->s2) {
                                 a2 = &su->u.a2;
+                                sysfs_attr_init(&a2->dev_attr.attr);
                                 a2->dev_attr.attr.name = su->name;
                                 a2->nr = (*t)->u.s.nr + i;
                                 a2->index = (*t)->u.s.index;
@@ -1005,6 +1006,7 @@ nct6775_create_attr_group(struct device *dev, struct sensor_template_group *tg,
                                 *attrs = &a2->dev_attr.attr;
                         } else {
                                 a = &su->u.a1;
+                                sysfs_attr_init(&a->dev_attr.attr);
                                 a->dev_attr.attr.name = su->name;
                                 a->index = (*t)->u.index + i;
                                 a->dev_attr.attr.mode =
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index 112e4d45e4a0..68800115876b 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -239,8 +239,10 @@ static struct ntc_thermistor_platform_data *
 ntc_thermistor_parse_dt(struct platform_device *pdev)
 {
         struct iio_channel *chan;
+        enum iio_chan_type type;
         struct device_node *np = pdev->dev.of_node;
         struct ntc_thermistor_platform_data *pdata;
+        int ret;
 
         if (!np)
                 return NULL;
@@ -253,6 +255,13 @@ ntc_thermistor_parse_dt(struct platform_device *pdev)
         if (IS_ERR(chan))
                 return ERR_CAST(chan);
 
+        ret = iio_get_channel_type(chan, &type);
+        if (ret < 0)
+                return ERR_PTR(ret);
+
+        if (type != IIO_VOLTAGE)
+                return ERR_PTR(-EINVAL);
+
         if (of_property_read_u32(np, "pullup-uv", &pdata->pullup_uv))
                 return ERR_PTR(-ENODEV);
         if (of_property_read_u32(np, "pullup-ohm", &pdata->pullup_ohm))
diff --git a/drivers/hwmon/tmp401.c b/drivers/hwmon/tmp401.c
index 99664ebc738d..ccf4cffe0ee1 100644
--- a/drivers/hwmon/tmp401.c
+++ b/drivers/hwmon/tmp401.c
@@ -44,7 +44,7 @@
 #include <linux/sysfs.h>
 
 /* Addresses to scan */
-static const unsigned short normal_i2c[] = { 0x37, 0x48, 0x49, 0x4a, 0x4c, 0x4d,
+static const unsigned short normal_i2c[] = { 0x48, 0x49, 0x4a, 0x4c, 0x4d,
         0x4e, 0x4f, I2C_CLIENT_END };
 
 enum chips { tmp401, tmp411, tmp431, tmp432, tmp435 };
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 327529ee85eb..3f40319a55da 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -547,11 +547,11 @@ isert_create_pi_ctx(struct fast_reg_descriptor *desc,
         return 0;
 
 err_prot_mr:
-        ib_dereg_mr(desc->pi_ctx->prot_mr);
+        ib_dereg_mr(pi_ctx->prot_mr);
 err_prot_frpl:
-        ib_free_fast_reg_page_list(desc->pi_ctx->prot_frpl);
+        ib_free_fast_reg_page_list(pi_ctx->prot_frpl);
 err_pi_ctx:
-        kfree(desc->pi_ctx);
+        kfree(pi_ctx);
 
         return ret;
 }
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 63953477a07c..eff7bdd7731d 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -429,9 +429,11 @@ static int __multipath_map(struct dm_target *ti, struct request *clone,
                 /* blk-mq request-based interface */
                 *__clone = blk_get_request(bdev_get_queue(bdev),
                                            rq_data_dir(rq), GFP_ATOMIC);
-                if (IS_ERR(*__clone))
+                if (IS_ERR(*__clone)) {
                         /* ENOMEM, requeue */
+                        clear_mapinfo(m, map_context);
                         return r;
+                }
                 (*__clone)->bio = (*__clone)->biotail = NULL;
                 (*__clone)->rq_disk = bdev->bd_disk;
                 (*__clone)->cmd_flags |= REQ_FAILFAST_TRANSPORT;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index d9b00b8565c6..16ba55ad7089 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -820,6 +820,12 @@ void dm_consume_args(struct dm_arg_set *as, unsigned num_args)
 }
 EXPORT_SYMBOL(dm_consume_args);
 
+static bool __table_type_request_based(unsigned table_type)
+{
+        return (table_type == DM_TYPE_REQUEST_BASED ||
+                table_type == DM_TYPE_MQ_REQUEST_BASED);
+}
+
 static int dm_table_set_type(struct dm_table *t)
 {
         unsigned i;
@@ -852,8 +858,7 @@ static int dm_table_set_type(struct dm_table *t)
                  * Determine the type from the live device.
                  * Default to bio-based if device is new.
                  */
-                if (live_md_type == DM_TYPE_REQUEST_BASED ||
-                    live_md_type == DM_TYPE_MQ_REQUEST_BASED)
+                if (__table_type_request_based(live_md_type))
                         request_based = 1;
                 else
                         bio_based = 1;
@@ -903,7 +908,7 @@ static int dm_table_set_type(struct dm_table *t)
                         }
                 t->type = DM_TYPE_MQ_REQUEST_BASED;
 
-        } else if (hybrid && list_empty(devices) && live_md_type != DM_TYPE_NONE) {
+        } else if (list_empty(devices) && __table_type_request_based(live_md_type)) {
                 /* inherit live MD type */
                 t->type = live_md_type;
 
@@ -925,10 +930,7 @@ struct target_type *dm_table_get_immutable_target_type(struct dm_table *t)
 
 bool dm_table_request_based(struct dm_table *t)
 {
-        unsigned table_type = dm_table_get_type(t);
-
-        return (table_type == DM_TYPE_REQUEST_BASED ||
-                table_type == DM_TYPE_MQ_REQUEST_BASED);
+        return __table_type_request_based(dm_table_get_type(t));
 }
 
 bool dm_table_mq_request_based(struct dm_table *t)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index a930b72314ac..2caf492890d6 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1082,13 +1082,11 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
         dm_put(md);
 }
 
-static void free_rq_clone(struct request *clone, bool must_be_mapped)
+static void free_rq_clone(struct request *clone)
 {
         struct dm_rq_target_io *tio = clone->end_io_data;
         struct mapped_device *md = tio->md;
 
-        WARN_ON_ONCE(must_be_mapped && !clone->q);
-
         blk_rq_unprep_clone(clone);
 
         if (md->type == DM_TYPE_MQ_REQUEST_BASED)
@@ -1132,7 +1130,7 @@ static void dm_end_request(struct request *clone, int error)
                         rq->sense_len = clone->sense_len;
         }
 
-        free_rq_clone(clone, true);
+        free_rq_clone(clone);
         if (!rq->q->mq_ops)
                 blk_end_request_all(rq, error);
         else
@@ -1151,7 +1149,7 @@ static void dm_unprep_request(struct request *rq)
         }
 
         if (clone)
-                free_rq_clone(clone, false);
+                free_rq_clone(clone);
 }
 
 /*
@@ -1164,6 +1162,7 @@ static void old_requeue_request(struct request *rq)
 
         spin_lock_irqsave(q->queue_lock, flags);
         blk_requeue_request(q, rq);
+        blk_run_queue_async(q);
         spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
@@ -1724,8 +1723,7 @@ static int dm_merge_bvec(struct request_queue *q,
         struct mapped_device *md = q->queuedata;
         struct dm_table *map = dm_get_live_table_fast(md);
         struct dm_target *ti;
-        sector_t max_sectors;
-        int max_size = 0;
+        sector_t max_sectors, max_size = 0;
 
         if (unlikely(!map))
                 goto out;
@@ -1740,8 +1738,16 @@ static int dm_merge_bvec(struct request_queue *q,
         max_sectors = min(max_io_len(bvm->bi_sector, ti),
                           (sector_t) queue_max_sectors(q));
         max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size;
-        if (unlikely(max_size < 0)) /* this shouldn't _ever_ happen */
-                max_size = 0;
+
+        /*
+         * FIXME: this stop-gap fix _must_ be cleaned up (by passing a sector_t
+         * to the targets' merge function since it holds sectors not bytes).
+         * Just doing this as an interim fix for stable@ because the more
+         * comprehensive cleanup of switching to sector_t will impact every
+         * DM target that implements a ->merge hook.
+         */
+        if (max_size > INT_MAX)
+                max_size = INT_MAX;
 
         /*
          * merge_bvec_fn() returns number of bytes
@@ -1749,7 +1755,7 @@ static int dm_merge_bvec(struct request_queue *q,
          * max is precomputed maximal io size
          */
         if (max_size && ti->type->merge)
-                max_size = ti->type->merge(ti, bvm, biovec, max_size);
+                max_size = ti->type->merge(ti, bvm, biovec, (int) max_size);
         /*
          * If the target doesn't support merge method and some of the devices
          * provided their merge_bvec method (we know this by looking for the
@@ -1971,8 +1977,8 @@ static int map_request(struct dm_rq_target_io *tio, struct request *rq,
                         dm_kill_unmapped_request(rq, r);
                         return r;
                 }
-                if (IS_ERR(clone))
-                        return DM_MAPIO_REQUEUE;
+                if (r != DM_MAPIO_REMAPPED)
+                        return r;
                 if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
                         /* -ENOMEM */
                         ti->type->release_clone_rq(clone);
@@ -2753,13 +2759,15 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
         if (dm_table_get_type(map) == DM_TYPE_REQUEST_BASED) {
                 /* clone request is allocated at the end of the pdu */
                 tio->clone = (void *)blk_mq_rq_to_pdu(rq) + sizeof(struct dm_rq_target_io);
-                if (!clone_rq(rq, md, tio, GFP_ATOMIC))
-                        return BLK_MQ_RQ_QUEUE_BUSY;
+                (void) clone_rq(rq, md, tio, GFP_ATOMIC);
                 queue_kthread_work(&md->kworker, &tio->work);
         } else {
                 /* Direct call is fine since .queue_rq allows allocations */
-                if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE)
-                        dm_requeue_unmapped_original_request(md, rq);
+                if (map_request(tio, rq, md) == DM_MAPIO_REQUEUE) {
+                        /* Undo dm_start_request() before requeuing */
+                        rq_completed(md, rq_data_dir(rq), false);
+                        return BLK_MQ_RQ_QUEUE_BUSY;
+                }
         }
 
         return BLK_MQ_RQ_QUEUE_OK;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 593a02476c78..27506302eb7a 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4211,12 +4211,12 @@ action_store(struct mddev *mddev, const char *page, size_t len)
         if (!mddev->pers || !mddev->pers->sync_request)
                 return -EINVAL;
 
-        if (cmd_match(page, "frozen"))
-                set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
-        else
-                clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 
         if (cmd_match(page, "idle") || cmd_match(page, "frozen")) {
+                if (cmd_match(page, "frozen"))
+                        set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+                else
+                        clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
                 flush_workqueue(md_misc_wq);
                 if (mddev->sync_thread) {
                         set_bit(MD_RECOVERY_INTR, &mddev->recovery);
@@ -4229,16 +4229,17 @@ action_store(struct mddev *mddev, const char *page, size_t len)
                    test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
                 return -EBUSY;
         else if (cmd_match(page, "resync"))
-                set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+                clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
         else if (cmd_match(page, "recover")) {
+                clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
                 set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-                set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
         } else if (cmd_match(page, "reshape")) {
                 int err;
                 if (mddev->pers->start_reshape == NULL)
                         return -EINVAL;
                 err = mddev_lock(mddev);
                 if (!err) {
+                        clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
                         err = mddev->pers->start_reshape(mddev);
                         mddev_unlock(mddev);
                 }
@@ -4250,6 +4251,7 @@ action_store(struct mddev *mddev, const char *page, size_t len)
                         set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
                 else if (!cmd_match(page, "repair"))
                         return -EINVAL;
+                clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
                 set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
                 set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
         }
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index b9f2b9cc6060..553d54b87052 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -749,6 +749,7 @@ static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
 static bool stripe_can_batch(struct stripe_head *sh)
 {
         return test_bit(STRIPE_BATCH_READY, &sh->state) &&
+                !test_bit(STRIPE_BITMAP_PENDING, &sh->state) &&
                 is_full_stripe_write(sh);
 }
 
@@ -837,6 +838,15 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh
                     < IO_THRESHOLD)
                         md_wakeup_thread(conf->mddev->thread);
 
+        if (test_and_clear_bit(STRIPE_BIT_DELAY, &sh->state)) {
+                int seq = sh->bm_seq;
+                if (test_bit(STRIPE_BIT_DELAY, &sh->batch_head->state) &&
+                    sh->batch_head->bm_seq > seq)
+                        seq = sh->batch_head->bm_seq;
+                set_bit(STRIPE_BIT_DELAY, &sh->batch_head->state);
+                sh->batch_head->bm_seq = seq;
+        }
+
         atomic_inc(&sh->count);
 unlock_out:
         unlock_two_stripes(head, sh);
@@ -2987,14 +2997,32 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx,
         pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
                 (unsigned long long)(*bip)->bi_iter.bi_sector,
                 (unsigned long long)sh->sector, dd_idx);
-        spin_unlock_irq(&sh->stripe_lock);
 
         if (conf->mddev->bitmap && firstwrite) {
+                /* Cannot hold spinlock over bitmap_startwrite,
+                 * but must ensure this isn't added to a batch until
+                 * we have added to the bitmap and set bm_seq.
+                 * So set STRIPE_BITMAP_PENDING to prevent
+                 * batching.
+                 * If multiple add_stripe_bio() calls race here they
+                 * much all set STRIPE_BITMAP_PENDING.  So only the first one
+                 * to complete "bitmap_startwrite" gets to set
+                 * STRIPE_BIT_DELAY.  This is important as once a stripe
+                 * is added to a batch, STRIPE_BIT_DELAY cannot be changed
+                 * any more.
+                 */
+                set_bit(STRIPE_BITMAP_PENDING, &sh->state);
+                spin_unlock_irq(&sh->stripe_lock);
                 bitmap_startwrite(conf->mddev->bitmap, sh->sector,
                                   STRIPE_SECTORS, 0);
-                sh->bm_seq = conf->seq_flush+1;
-                set_bit(STRIPE_BIT_DELAY, &sh->state);
+                spin_lock_irq(&sh->stripe_lock);
+                clear_bit(STRIPE_BITMAP_PENDING, &sh->state);
+                if (!sh->batch_head) {
+                        sh->bm_seq = conf->seq_flush+1;
+                        set_bit(STRIPE_BIT_DELAY, &sh->state);
+                }
         }
+        spin_unlock_irq(&sh->stripe_lock);
 
         if (stripe_can_batch(sh))
                 stripe_add_to_batch_list(conf, sh);
@@ -3392,6 +3420,8 @@ static void handle_stripe_fill(struct stripe_head *sh,
         set_bit(STRIPE_HANDLE, &sh->state);
 }
 
+static void break_stripe_batch_list(struct stripe_head *head_sh,
+                                    unsigned long handle_flags);
 /* handle_stripe_clean_event
  * any written block on an uptodate or failed drive can be returned.
  * Note that if we 'wrote' to a failed drive, it will be UPTODATE, but
@@ -3405,7 +3435,6 @@ static void handle_stripe_clean_event(struct r5conf *conf,
         int discard_pending = 0;
         struct stripe_head *head_sh = sh;
         bool do_endio = false;
-        int wakeup_nr = 0;
 
         for (i = disks; i--; )
                 if (sh->dev[i].written) {
@@ -3494,44 +3523,8 @@ unhash:
                 if (atomic_dec_and_test(&conf->pending_full_writes))
                         md_wakeup_thread(conf->mddev->thread);
 
-        if (!head_sh->batch_head || !do_endio)
-                return;
-        for (i = 0; i < head_sh->disks; i++) {
-                if (test_and_clear_bit(R5_Overlap, &head_sh->dev[i].flags))
-                        wakeup_nr++;
-        }
-        while (!list_empty(&head_sh->batch_list)) {
-                int i;
-                sh = list_first_entry(&head_sh->batch_list,
-                                      struct stripe_head, batch_list);
-                list_del_init(&sh->batch_list);
-
-                set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG,
-                              head_sh->state & ~((1 << STRIPE_ACTIVE) |
-                                                 (1 << STRIPE_PREREAD_ACTIVE) |
-                                                 STRIPE_EXPAND_SYNC_FLAG));
-                sh->check_state = head_sh->check_state;
-                sh->reconstruct_state = head_sh->reconstruct_state;
-                for (i = 0; i < sh->disks; i++) {
-                        if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
-                                wakeup_nr++;
-                        sh->dev[i].flags = head_sh->dev[i].flags;
-                }
-
-                spin_lock_irq(&sh->stripe_lock);
-                sh->batch_head = NULL;
-                spin_unlock_irq(&sh->stripe_lock);
-                if (sh->state & STRIPE_EXPAND_SYNC_FLAG)
-                        set_bit(STRIPE_HANDLE, &sh->state);
-                release_stripe(sh);
-        }
-
-        spin_lock_irq(&head_sh->stripe_lock);
-        head_sh->batch_head = NULL;
-        spin_unlock_irq(&head_sh->stripe_lock);
-        wake_up_nr(&conf->wait_for_overlap, wakeup_nr);
-        if (head_sh->state & STRIPE_EXPAND_SYNC_FLAG)
-                set_bit(STRIPE_HANDLE, &head_sh->state);
+        if (head_sh->batch_head && do_endio)
+                break_stripe_batch_list(head_sh, STRIPE_EXPAND_SYNC_FLAGS);
 }
 
 static void handle_stripe_dirtying(struct r5conf *conf,
@@ -4172,9 +4165,13 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 
 static int clear_batch_ready(struct stripe_head *sh)
 {
+        /* Return '1' if this is a member of batch, or
+         * '0' if it is a lone stripe or a head which can now be
+         * handled.
+         */
         struct stripe_head *tmp;
         if (!test_and_clear_bit(STRIPE_BATCH_READY, &sh->state))
-                return 0;
+                return (sh->batch_head && sh->batch_head != sh);
         spin_lock(&sh->stripe_lock);
         if (!sh->batch_head) {
                 spin_unlock(&sh->stripe_lock);
@@ -4202,38 +4199,65 @@ static int clear_batch_ready(struct stripe_head *sh)
         return 0;
 }
 
-static void check_break_stripe_batch_list(struct stripe_head *sh)
+static void break_stripe_batch_list(struct stripe_head *head_sh,
+                                    unsigned long handle_flags)
 {
-        struct stripe_head *head_sh, *next;
+        struct stripe_head *sh, *next;
         int i;
-
-        if (!test_and_clear_bit(STRIPE_BATCH_ERR, &sh->state))
-                return;
-
-        head_sh = sh;
+        int do_wakeup = 0;
 
         list_for_each_entry_safe(sh, next, &head_sh->batch_list, batch_list) {
 
                 list_del_init(&sh->batch_list);
 
-                set_mask_bits(&sh->state, ~STRIPE_EXPAND_SYNC_FLAG,
-                              head_sh->state & ~((1 << STRIPE_ACTIVE) |
-                                                 (1 << STRIPE_PREREAD_ACTIVE) |
-                                                 (1 << STRIPE_DEGRADED) |
-                                                 STRIPE_EXPAND_SYNC_FLAG));
+                WARN_ON_ONCE(sh->state & ((1 << STRIPE_ACTIVE) |
+                                          (1 << STRIPE_SYNCING) |
+                                          (1 << STRIPE_REPLACED) |
+                                          (1 << STRIPE_PREREAD_ACTIVE) |
+                                          (1 << STRIPE_DELAYED) |
+                                          (1 << STRIPE_BIT_DELAY) |
+                                          (1 << STRIPE_FULL_WRITE) |
+                                          (1 << STRIPE_BIOFILL_RUN) |
+                                          (1 << STRIPE_COMPUTE_RUN)  |
+                                          (1 << STRIPE_OPS_REQ_PENDING) |
+                                          (1 << STRIPE_DISCARD) |
+                                          (1 << STRIPE_BATCH_READY) |
+                                          (1 << STRIPE_BATCH_ERR) |
+                                          (1 << STRIPE_BITMAP_PENDING)));
+                WARN_ON_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) |
+                                              (1 << STRIPE_REPLACED)));
+
+                set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
+                                            (1 << STRIPE_DEGRADED)),
+                              head_sh->state & (1 << STRIPE_INSYNC));
+
                 sh->check_state = head_sh->check_state;
                 sh->reconstruct_state = head_sh->reconstruct_state;
-                for (i = 0; i < sh->disks; i++)
+                for (i = 0; i < sh->disks; i++) {
+                        if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
+                                do_wakeup = 1;
                         sh->dev[i].flags = head_sh->dev[i].flags &
                                 (~((1 << R5_WriteError) | (1 << R5_Overlap)));
-
+                }
                 spin_lock_irq(&sh->stripe_lock);
                 sh->batch_head = NULL;
                 spin_unlock_irq(&sh->stripe_lock);
-
-                set_bit(STRIPE_HANDLE, &sh->state);
+                if (handle_flags == 0 ||
+                    sh->state & handle_flags)
+                        set_bit(STRIPE_HANDLE, &sh->state);
                 release_stripe(sh);
         }
+        spin_lock_irq(&head_sh->stripe_lock);
+        head_sh->batch_head = NULL;
+        spin_unlock_irq(&head_sh->stripe_lock);
+        for (i = 0; i < head_sh->disks; i++)
+                if (test_and_clear_bit(R5_Overlap, &head_sh->dev[i].flags))
+                        do_wakeup = 1;
+        if (head_sh->state & handle_flags)
+                set_bit(STRIPE_HANDLE, &head_sh->state);
+
+        if (do_wakeup)
+                wake_up(&head_sh->raid_conf->wait_for_overlap);
 }
 
 static void handle_stripe(struct stripe_head *sh)
@@ -4258,7 +4282,8 @@ static void handle_stripe(struct stripe_head *sh)
                 return;
         }
 
-        check_break_stripe_batch_list(sh);
+        if (test_and_clear_bit(STRIPE_BATCH_ERR, &sh->state))
+                break_stripe_batch_list(sh, 0);
 
         if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) && !sh->batch_head) {
                 spin_lock(&sh->stripe_lock);
@@ -4312,6 +4337,7 @@ static void handle_stripe(struct stripe_head *sh)
         if (s.failed > conf->max_degraded) {
                 sh->check_state = 0;
                 sh->reconstruct_state = 0;
+                break_stripe_batch_list(sh, 0);
                 if (s.to_read+s.to_write+s.written)
                         handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
                 if (s.syncing + s.replacing)
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 7dc0dd86074b..896d603ad0da 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -337,9 +337,12 @@ enum {
         STRIPE_ON_RELEASE_LIST,
         STRIPE_BATCH_READY,
         STRIPE_BATCH_ERR,
+        STRIPE_BITMAP_PENDING,  /* Being added to bitmap, don't add
+                                 * to batch yet.
+                                 */
 };
 
-#define STRIPE_EXPAND_SYNC_FLAG \
+#define STRIPE_EXPAND_SYNC_FLAGS \
         ((1 << STRIPE_EXPAND_SOURCE) |\
         (1 << STRIPE_EXPAND_READY) |\
         (1 << STRIPE_EXPANDING) |\
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index a6dcbf850c1f..6f9ffb9026cd 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -2358,11 +2358,11 @@ static int be_evt_queues_create(struct be_adapter *adapter)
                                     adapter->cfg_num_qs);
 
         for_all_evt_queues(adapter, eqo, i) {
+                int numa_node = dev_to_node(&adapter->pdev->dev);
                 if (!zalloc_cpumask_var(&eqo->affinity_mask, GFP_KERNEL))
                         return -ENOMEM;
-                cpumask_set_cpu_local_first(i, dev_to_node(&adapter->pdev->dev),
-                                            eqo->affinity_mask);
-
+                cpumask_set_cpu(cpumask_local_spread(i, numa_node),
+                                eqo->affinity_mask);
                 netif_napi_add(adapter->netdev, &eqo->napi, be_poll,
                                BE_NAPI_WEIGHT);
                 napi_hash_add(&eqo->napi);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 32f5ec737472..cf467a9f6cc7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1501,17 +1501,13 @@ static int mlx4_en_init_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
 {
         struct mlx4_en_rx_ring *ring = priv->rx_ring[ring_idx];
         int numa_node = priv->mdev->dev->numa_node;
-        int ret = 0;
 
         if (!zalloc_cpumask_var(&ring->affinity_mask, GFP_KERNEL))
                 return -ENOMEM;
 
-        ret = cpumask_set_cpu_local_first(ring_idx, numa_node,
-                                          ring->affinity_mask);
-        if (ret)
-                free_cpumask_var(ring->affinity_mask);
-
-        return ret;
+        cpumask_set_cpu(cpumask_local_spread(ring_idx, numa_node),
+                        ring->affinity_mask);
+        return 0;
 }
 
 static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index f7bf312fb443..7bed3a88579f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -144,9 +144,9 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
         ring->queue_index = queue_index;
 
         if (queue_index < priv->num_tx_rings_p_up)
-                cpumask_set_cpu_local_first(queue_index,
-                                            priv->mdev->dev->numa_node,
-                                            &ring->affinity_mask);
+                cpumask_set_cpu(cpumask_local_spread(queue_index,
+                                                     priv->mdev->dev->numa_node),
+                                &ring->affinity_mask);
 
         *pring = ring;
         return 0;
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 9bb9ad6d4a1b..28f328136f0d 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -2897,7 +2897,7 @@ static ssize_t hotkey_wakeup_reason_show(struct device *dev,
         return snprintf(buf, PAGE_SIZE, "%d\n", hotkey_wakeup_reason);
 }
 
-static DEVICE_ATTR_RO(hotkey_wakeup_reason);
+static DEVICE_ATTR(wakeup_reason, S_IRUGO, hotkey_wakeup_reason_show, NULL);
 
 static void hotkey_wakeup_reason_notify_change(void)
 {
@@ -2913,7 +2913,8 @@ static ssize_t hotkey_wakeup_hotunplug_complete_show(struct device *dev,
         return snprintf(buf, PAGE_SIZE, "%d\n", hotkey_autosleep_ack);
 }
 
-static DEVICE_ATTR_RO(hotkey_wakeup_hotunplug_complete);
+static DEVICE_ATTR(wakeup_hotunplug_complete, S_IRUGO,
+                   hotkey_wakeup_hotunplug_complete_show, NULL);
 
 static void hotkey_wakeup_hotunplug_complete_notify_change(void)
 {
@@ -2978,8 +2979,8 @@ static struct attribute *hotkey_attributes[] __initdata = {
         &dev_attr_hotkey_enable.attr,
         &dev_attr_hotkey_bios_enabled.attr,
         &dev_attr_hotkey_bios_mask.attr,
-        &dev_attr_hotkey_wakeup_reason.attr,
-        &dev_attr_hotkey_wakeup_hotunplug_complete.attr,
+        &dev_attr_wakeup_reason.attr,
+        &dev_attr_wakeup_hotunplug_complete.attr,
         &dev_attr_hotkey_mask.attr,
         &dev_attr_hotkey_all_mask.attr,
         &dev_attr_hotkey_recommended_mask.attr,
@@ -4393,12 +4394,13 @@ static ssize_t wan_enable_store(struct device *dev,
                         attr, buf, count);
 }
 
-static DEVICE_ATTR_RW(wan_enable);
+static DEVICE_ATTR(wwan_enable, S_IWUSR | S_IRUGO,
+                   wan_enable_show, wan_enable_store);
 
 /* --------------------------------------------------------------------- */
 
 static struct attribute *wan_attributes[] = {
-        &dev_attr_wan_enable.attr,
+        &dev_attr_wwan_enable.attr,
         NULL
 };
 
@@ -8138,7 +8140,8 @@ static ssize_t fan_pwm1_enable_store(struct device *dev,
         return count;
 }
 
-static DEVICE_ATTR_RW(fan_pwm1_enable);
+static DEVICE_ATTR(pwm1_enable, S_IWUSR | S_IRUGO,
+                   fan_pwm1_enable_show, fan_pwm1_enable_store);
 
 /* sysfs fan pwm1 ------------------------------------------------------ */
 static ssize_t fan_pwm1_show(struct device *dev,
@@ -8198,7 +8201,7 @@ static ssize_t fan_pwm1_store(struct device *dev,
         return (rc) ? rc : count;
 }
 
-static DEVICE_ATTR_RW(fan_pwm1);
+static DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, fan_pwm1_show, fan_pwm1_store);
 
 /* sysfs fan fan1_input ------------------------------------------------ */
 static ssize_t fan_fan1_input_show(struct device *dev,
@@ -8215,7 +8218,7 @@ static ssize_t fan_fan1_input_show(struct device *dev,
         return snprintf(buf, PAGE_SIZE, "%u\n", speed);
 }
 
-static DEVICE_ATTR_RO(fan_fan1_input);
+static DEVICE_ATTR(fan1_input, S_IRUGO, fan_fan1_input_show, NULL);
 
 /* sysfs fan fan2_input ------------------------------------------------ */
 static ssize_t fan_fan2_input_show(struct device *dev,
@@ -8232,7 +8235,7 @@ static ssize_t fan_fan2_input_show(struct device *dev,
         return snprintf(buf, PAGE_SIZE, "%u\n", speed);
 }
 
-static DEVICE_ATTR_RO(fan_fan2_input);
+static DEVICE_ATTR(fan2_input, S_IRUGO, fan_fan2_input_show, NULL);
 
 /* sysfs fan fan_watchdog (hwmon driver) ------------------------------- */
 static ssize_t fan_fan_watchdog_show(struct device_driver *drv,
@@ -8265,8 +8268,8 @@ static DRIVER_ATTR(fan_watchdog, S_IWUSR | S_IRUGO,
 
 /* --------------------------------------------------------------------- */
 static struct attribute *fan_attributes[] = {
-        &dev_attr_fan_pwm1_enable.attr, &dev_attr_fan_pwm1.attr,
-        &dev_attr_fan_fan1_input.attr,
+        &dev_attr_pwm1_enable.attr, &dev_attr_pwm1.attr,
+        &dev_attr_fan1_input.attr,
         NULL, /* for fan2_input */
         NULL
 };
@@ -8400,7 +8403,7 @@ static int __init fan_init(struct ibm_init_struct *iibm)
                 if (tp_features.second_fan) {
                         /* attach second fan tachometer */
                         fan_attributes[ARRAY_SIZE(fan_attributes)-2] =
-                                        &dev_attr_fan_fan2_input.attr;
+                                        &dev_attr_fan2_input.attr;
                 }
                 rc = sysfs_create_group(&tpacpi_sensors_pdev->dev.kobj,
                                          &fan_attr_group);
@@ -8848,7 +8851,7 @@ static ssize_t thinkpad_acpi_pdev_name_show(struct device *dev,
         return snprintf(buf, PAGE_SIZE, "%s\n", TPACPI_NAME);
 }
 
-static DEVICE_ATTR_RO(thinkpad_acpi_pdev_name);
+static DEVICE_ATTR(name, S_IRUGO, thinkpad_acpi_pdev_name_show, NULL);
 
 /* --------------------------------------------------------------------- */
 
@@ -9390,8 +9393,7 @@ static void thinkpad_acpi_module_exit(void)
                 hwmon_device_unregister(tpacpi_hwmon);
 
         if (tp_features.sensors_pdev_attrs_registered)
-                device_remove_file(&tpacpi_sensors_pdev->dev,
-                                   &dev_attr_thinkpad_acpi_pdev_name);
+                device_remove_file(&tpacpi_sensors_pdev->dev, &dev_attr_name);
         if (tpacpi_sensors_pdev)
                 platform_device_unregister(tpacpi_sensors_pdev);
         if (tpacpi_pdev)
@@ -9512,8 +9514,7 @@ static int __init thinkpad_acpi_module_init(void)
                 thinkpad_acpi_module_exit();
                 return ret;
         }
-        ret = device_create_file(&tpacpi_sensors_pdev->dev,
-                                 &dev_attr_thinkpad_acpi_pdev_name);
+        ret = device_create_file(&tpacpi_sensors_pdev->dev, &dev_attr_name);
         if (ret) {
                 pr_err("unable to create sysfs hwmon device attributes\n");
                 thinkpad_acpi_module_exit();
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 68c2002e78bf..5c9e680aa375 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -1020,8 +1020,7 @@ static void tcm_qla2xxx_depend_tpg(struct work_struct *work)
         struct se_portal_group *se_tpg = &base_tpg->se_tpg;
         struct scsi_qla_host *base_vha = base_tpg->lport->qla_vha;
 
-        if (!configfs_depend_item(se_tpg->se_tpg_tfo->tf_subsys,
-                                  &se_tpg->tpg_group.cg_item)) {
+        if (!target_depend_item(&se_tpg->tpg_group.cg_item)) {
                 atomic_set(&base_tpg->lport_tpg_enabled, 1);
                 qlt_enable_vha(base_vha);
         }
@@ -1037,8 +1036,7 @@ static void tcm_qla2xxx_undepend_tpg(struct work_struct *work)
 
         if (!qlt_stop_phase1(base_vha->vha_tgt.qla_tgt)) {
                 atomic_set(&base_tpg->lport_tpg_enabled, 0);
-                configfs_undepend_item(se_tpg->se_tpg_tfo->tf_subsys,
-                                       &se_tpg->tpg_group.cg_item);
+                target_undepend_item(&se_tpg->tpg_group.cg_item);
         }
         complete(&base_tpg->tpg_base_comp);
 }
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 34871a628b11..74e6114ff18f 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -230,7 +230,7 @@ int iscsit_access_np(struct iscsi_np *np, struct iscsi_portal_group *tpg)
          * Here we serialize access across the TIQN+TPG Tuple.
          */
         ret = down_interruptible(&tpg->np_login_sem);
-        if ((ret != 0) || signal_pending(current))
+        if (ret != 0)
                 return -1;
 
         spin_lock_bh(&tpg->tpg_state_lock);
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 8ce94ff744e6..70d799dfab03 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -346,6 +346,7 @@ static int iscsi_login_zero_tsih_s1(
         if (IS_ERR(sess->se_sess)) {
                 iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
                                 ISCSI_LOGIN_STATUS_NO_RESOURCES);
+                kfree(sess->sess_ops);
                 kfree(sess);
                 return -ENOMEM;
         }
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index e8a240818353..5e3295fe404d 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -161,10 +161,7 @@ struct iscsi_portal_group *iscsit_get_tpg_from_np(
 int iscsit_get_tpg(
         struct iscsi_portal_group *tpg)
 {
-        int ret;
-
-        ret = mutex_lock_interruptible(&tpg->tpg_access_lock);
-        return ((ret != 0) || signal_pending(current)) ? -1 : 0;
+        return mutex_lock_interruptible(&tpg->tpg_access_lock);
 }
 
 void iscsit_put_tpg(struct iscsi_portal_group *tpg)
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index 75cbde1f7c5b..4f8d4d459aa4 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -704,7 +704,7 @@ target_alua_state_check(struct se_cmd *cmd)
 
         if (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)
                 return 0;
-        if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+        if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
                 return 0;
 
         if (!port)
@@ -2377,7 +2377,7 @@ ssize_t core_alua_store_secondary_write_metadata(
 
 int core_setup_alua(struct se_device *dev)
 {
-        if (dev->transport->transport_type != TRANSPORT_PLUGIN_PHBA_PDEV &&
+        if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) &&
             !(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) {
                 struct t10_alua_lu_gp_member *lu_gp_mem;
 
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index ddaf76a4ac2a..e7b0430a0575 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -212,10 +212,6 @@ static struct config_group *target_core_register_fabric(
 
         pr_debug("Target_Core_ConfigFS: REGISTER -> Allocated Fabric:"
                         " %s\n", tf->tf_group.cg_item.ci_name);
-        /*
-         * Setup tf_ops.tf_subsys pointer for usage with configfs_depend_item()
-         */
-        tf->tf_ops.tf_subsys = tf->tf_subsys;
         tf->tf_fabric = &tf->tf_group.cg_item;
         pr_debug("Target_Core_ConfigFS: REGISTER -> Set tf->tf_fabric"
                         " for %s\n", name);
@@ -291,10 +287,17 @@ static struct configfs_subsystem target_core_fabrics = {
         },
 };
 
-struct configfs_subsystem *target_core_subsystem[] = {
-        &target_core_fabrics,
-        NULL,
-};
+int target_depend_item(struct config_item *item)
+{
+        return configfs_depend_item(&target_core_fabrics, item);
+}
+EXPORT_SYMBOL(target_depend_item);
+
+void target_undepend_item(struct config_item *item)
+{
+        return configfs_undepend_item(&target_core_fabrics, item);
+}
+EXPORT_SYMBOL(target_undepend_item);
 
 /*##############################################################################
 // Start functions called by external Target Fabrics Modules
@@ -467,7 +470,6 @@ int target_register_template(const struct target_core_fabric_ops *fo)
          * struct target_fabric_configfs->tf_cit_tmpl
          */
         tf->tf_module = fo->module;
-        tf->tf_subsys = target_core_subsystem[0];
         snprintf(tf->tf_name, TARGET_FABRIC_NAME_SIZE, "%s", fo->name);
 
         tf->tf_ops = *fo;
@@ -809,7 +811,7 @@ static ssize_t target_core_dev_pr_show_attr_res_holder(struct se_device *dev,
 {
         int ret;
 
-        if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+        if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
                 return sprintf(page, "Passthrough\n");
 
         spin_lock(&dev->dev_reservation_lock);
@@ -960,7 +962,7 @@ SE_DEV_PR_ATTR_RO(res_pr_type);
 static ssize_t target_core_dev_pr_show_attr_res_type(
                 struct se_device *dev, char *page)
 {
-        if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+        if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
                 return sprintf(page, "SPC_PASSTHROUGH\n");
         else if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
                 return sprintf(page, "SPC2_RESERVATIONS\n");
@@ -973,7 +975,7 @@ SE_DEV_PR_ATTR_RO(res_type);
 static ssize_t target_core_dev_pr_show_attr_res_aptpl_active(
                 struct se_device *dev, char *page)
 {
-        if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+        if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
                 return 0;
 
         return sprintf(page, "APTPL Bit Status: %s\n",
@@ -988,7 +990,7 @@ SE_DEV_PR_ATTR_RO(res_aptpl_active);
 static ssize_t target_core_dev_pr_show_attr_res_aptpl_metadata(
                 struct se_device *dev, char *page)
 {
-        if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+        if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
                 return 0;
 
         return sprintf(page, "Ready to process PR APTPL metadata..\n");
@@ -1035,7 +1037,7 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata(
         u16 port_rpti = 0, tpgt = 0;
         u8 type = 0, scope;
 
-        if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+        if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
                 return 0;
         if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
                 return 0;
@@ -2870,7 +2872,7 @@ static int __init target_core_init_configfs(void)
 {
         struct config_group *target_cg, *hba_cg = NULL, *alua_cg = NULL;
         struct config_group *lu_gp_cg = NULL;
-        struct configfs_subsystem *subsys;
+        struct configfs_subsystem *subsys = &target_core_fabrics;
         struct t10_alua_lu_gp *lu_gp;
         int ret;
 
@@ -2878,7 +2880,6 @@ static int __init target_core_init_configfs(void)
                 " Engine: %s on %s/%s on "UTS_RELEASE"\n",
                 TARGET_CORE_VERSION, utsname()->sysname, utsname()->machine);
 
-        subsys = target_core_subsystem[0];
         config_group_init(&subsys->su_group);
         mutex_init(&subsys->su_mutex);
 
@@ -3008,13 +3009,10 @@ out_global:
 
 static void __exit target_core_exit_configfs(void)
 {
-        struct configfs_subsystem *subsys;
         struct config_group *hba_cg, *alua_cg, *lu_gp_cg;
         struct config_item *item;
         int i;
 
-        subsys = target_core_subsystem[0];
-
         lu_gp_cg = &alua_lu_gps_group;
         for (i = 0; lu_gp_cg->default_groups[i]; i++) {
                 item = &lu_gp_cg->default_groups[i]->cg_item;
@@ -3045,8 +3043,8 @@ static void __exit target_core_exit_configfs(void)
          * We expect subsys->su_group.default_groups to be released
          * by configfs subsystem provider logic..
          */
-        configfs_unregister_subsystem(subsys);
-        kfree(subsys->su_group.default_groups);
+        configfs_unregister_subsystem(&target_core_fabrics);
+        kfree(target_core_fabrics.su_group.default_groups);
 
         core_alua_free_lu_gp(default_lu_gp);
         default_lu_gp = NULL;
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 7faa6aef9a4d..ce5f768181ff 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -33,6 +33,7 @@
 #include <linux/kthread.h>
 #include <linux/in.h>
 #include <linux/export.h>
+#include <asm/unaligned.h>
 #include <net/sock.h>
 #include <net/tcp.h>
 #include <scsi/scsi.h>
@@ -527,7 +528,7 @@ static void core_export_port(
         list_add_tail(&port->sep_list, &dev->dev_sep_list);
         spin_unlock(&dev->se_port_lock);
 
-        if (dev->transport->transport_type != TRANSPORT_PLUGIN_PHBA_PDEV &&
+        if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH) &&
             !(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)) {
                 tg_pt_gp_mem = core_alua_allocate_tg_pt_gp_mem(port);
                 if (IS_ERR(tg_pt_gp_mem) || !tg_pt_gp_mem) {
@@ -1603,7 +1604,7 @@ int target_configure_device(struct se_device *dev)
          * anything virtual (IBLOCK, FILEIO, RAMDISK), but not for TCM/pSCSI
          * passthrough because this is being provided by the backend LLD.
          */
-        if (dev->transport->transport_type != TRANSPORT_PLUGIN_PHBA_PDEV) {
+        if (!(dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)) {
                 strncpy(&dev->t10_wwn.vendor[0], "LIO-ORG", 8);
                 strncpy(&dev->t10_wwn.model[0],
                         dev->transport->inquiry_prod, 16);
@@ -1707,3 +1708,76 @@ void core_dev_release_virtual_lun0(void)
                 target_free_device(g_lun0_dev);
         core_delete_hba(hba);
 }
+
+/*
+ * Common CDB parsing for kernel and user passthrough.
+ */
+sense_reason_t
+passthrough_parse_cdb(struct se_cmd *cmd,
+        sense_reason_t (*exec_cmd)(struct se_cmd *cmd))
+{
+        unsigned char *cdb = cmd->t_task_cdb;
+
+        /*
+         * Clear a lun set in the cdb if the initiator talking to use spoke
+         * and old standards version, as we can't assume the underlying device
+         * won't choke up on it.
+         */
+        switch (cdb[0]) {
+        case READ_10: /* SBC - RDProtect */
+        case READ_12: /* SBC - RDProtect */
+        case READ_16: /* SBC - RDProtect */
+        case SEND_DIAGNOSTIC: /* SPC - SELF-TEST Code */
+        case VERIFY: /* SBC - VRProtect */
+        case VERIFY_16: /* SBC - VRProtect */
+        case WRITE_VERIFY: /* SBC - VRProtect */
+        case WRITE_VERIFY_12: /* SBC - VRProtect */
+        case MAINTENANCE_IN: /* SPC - Parameter Data Format for SA RTPG */
+                break;
+        default:
+                cdb[1] &= 0x1f; /* clear logical unit number */
+                break;
+        }
+
+        /*
+         * For REPORT LUNS we always need to emulate the response, for everything
+         * else, pass it up.
+         */
+        if (cdb[0] == REPORT_LUNS) {
+                cmd->execute_cmd = spc_emulate_report_luns;
+                return TCM_NO_SENSE;
+        }
+
+        /* Set DATA_CDB flag for ops that should have it */
+        switch (cdb[0]) {
+        case READ_6:
+        case READ_10:
+        case READ_12:
+        case READ_16:
+        case WRITE_6:
+        case WRITE_10:
+        case WRITE_12:
+        case WRITE_16:
+        case WRITE_VERIFY:
+        case WRITE_VERIFY_12:
+        case 0x8e: /* WRITE_VERIFY_16 */
+        case COMPARE_AND_WRITE:
+        case XDWRITEREAD_10:
+                cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
+                break;
+        case VARIABLE_LENGTH_CMD:
+                switch (get_unaligned_be16(&cdb[8])) {
+                case READ_32:
+                case WRITE_32:
+                case 0x0c: /* WRITE_VERIFY_32 */
+                case XDWRITEREAD_32:
+                        cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
+                        break;
+                }
+        }
+
+        cmd->execute_cmd = exec_cmd;
+
+        return TCM_NO_SENSE;
+}
+EXPORT_SYMBOL(passthrough_parse_cdb);
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index f7e6e51aed36..3f27bfd816d8 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -958,7 +958,6 @@ static struct se_subsystem_api fileio_template = {
         .inquiry_prod           = "FILEIO",
         .inquiry_rev            = FD_VERSION,
         .owner                  = THIS_MODULE,
-        .transport_type         = TRANSPORT_PLUGIN_VHBA_PDEV,
         .attach_hba             = fd_attach_hba,
         .detach_hba             = fd_detach_hba,
         .alloc_device           = fd_alloc_device,
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 1b7947c2510f..8c965683789f 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -904,7 +904,6 @@ static struct se_subsystem_api iblock_template = {
         .inquiry_prod           = "IBLOCK",
         .inquiry_rev            = IBLOCK_VERSION,
         .owner                  = THIS_MODULE,
-        .transport_type         = TRANSPORT_PLUGIN_VHBA_PDEV,
         .attach_hba             = iblock_attach_hba,
         .detach_hba             = iblock_detach_hba,
         .alloc_device           = iblock_alloc_device,
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index 874a9bc988d8..68bd7f5d9f73 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -4,9 +4,6 @@
 /* target_core_alua.c */
 extern struct t10_alua_lu_gp *default_lu_gp;
 
-/* target_core_configfs.c */
-extern struct configfs_subsystem *target_core_subsystem[];
-
 /* target_core_device.c */
 extern struct mutex g_device_mutex;
 extern struct list_head g_device_list;
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index c1aa9655e96e..a15411c79ae9 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -1367,41 +1367,26 @@ void core_scsi3_free_all_registrations(
 
 static int core_scsi3_tpg_depend_item(struct se_portal_group *tpg)
 {
-        return configfs_depend_item(tpg->se_tpg_tfo->tf_subsys,
-                        &tpg->tpg_group.cg_item);
+        return target_depend_item(&tpg->tpg_group.cg_item);
 }
 
 static void core_scsi3_tpg_undepend_item(struct se_portal_group *tpg)
 {
-        configfs_undepend_item(tpg->se_tpg_tfo->tf_subsys,
-                        &tpg->tpg_group.cg_item);
-
+        target_undepend_item(&tpg->tpg_group.cg_item);
         atomic_dec_mb(&tpg->tpg_pr_ref_count);
 }
 
 static int core_scsi3_nodeacl_depend_item(struct se_node_acl *nacl)
 {
-        struct se_portal_group *tpg = nacl->se_tpg;
-
         if (nacl->dynamic_node_acl)
                 return 0;
-
-        return configfs_depend_item(tpg->se_tpg_tfo->tf_subsys,
-                        &nacl->acl_group.cg_item);
+        return target_depend_item(&nacl->acl_group.cg_item);
 }
 
 static void core_scsi3_nodeacl_undepend_item(struct se_node_acl *nacl)
 {
-        struct se_portal_group *tpg = nacl->se_tpg;
-
-        if (nacl->dynamic_node_acl) {
-                atomic_dec_mb(&nacl->acl_pr_ref_count);
-                return;
-        }
-
-        configfs_undepend_item(tpg->se_tpg_tfo->tf_subsys,
-                        &nacl->acl_group.cg_item);
-
+        if (!nacl->dynamic_node_acl)
+                target_undepend_item(&nacl->acl_group.cg_item);
         atomic_dec_mb(&nacl->acl_pr_ref_count);
 }
 
@@ -1419,8 +1404,7 @@ static int core_scsi3_lunacl_depend_item(struct se_dev_entry *se_deve)
         nacl = lun_acl->se_lun_nacl;
         tpg = nacl->se_tpg;
 
-        return configfs_depend_item(tpg->se_tpg_tfo->tf_subsys,
-                        &lun_acl->se_lun_group.cg_item);
+        return target_depend_item(&lun_acl->se_lun_group.cg_item);
 }
 
 static void core_scsi3_lunacl_undepend_item(struct se_dev_entry *se_deve)
@@ -1438,9 +1422,7 @@ static void core_scsi3_lunacl_undepend_item(struct se_dev_entry *se_deve)
         nacl = lun_acl->se_lun_nacl;
         tpg = nacl->se_tpg;
 
-        configfs_undepend_item(tpg->se_tpg_tfo->tf_subsys,
-                        &lun_acl->se_lun_group.cg_item);
-
+        target_undepend_item(&lun_acl->se_lun_group.cg_item);
         atomic_dec_mb(&se_deve->pr_ref_count);
 }
 
@@ -4111,7 +4093,7 @@ target_check_reservation(struct se_cmd *cmd)
                 return 0;
         if (dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE)
                 return 0;
-        if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+        if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
                 return 0;
 
         spin_lock(&dev->dev_reservation_lock);
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index f6c954c4635f..ecc5eaef13d6 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -521,6 +521,7 @@ static int pscsi_configure_device(struct se_device *dev)
                                         " pdv_host_id: %d\n", pdv->pdv_host_id);
                                 return -EINVAL;
                         }
+                        pdv->pdv_lld_host = sh;
                 }
         } else {
                 if (phv->phv_mode == PHV_VIRTUAL_HOST_ID) {
@@ -603,6 +604,8 @@ static void pscsi_free_device(struct se_device *dev)
                 if ((phv->phv_mode == PHV_LLD_SCSI_HOST_NO) &&
                     (phv->phv_lld_host != NULL))
                         scsi_host_put(phv->phv_lld_host);
+                else if (pdv->pdv_lld_host)
+                        scsi_host_put(pdv->pdv_lld_host);
 
                 if ((sd->type == TYPE_DISK) || (sd->type == TYPE_ROM))
                         scsi_device_put(sd);
@@ -970,64 +973,13 @@ fail:
         return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 }
 
-/*
- * Clear a lun set in the cdb if the initiator talking to use spoke
- * and old standards version, as we can't assume the underlying device
- * won't choke up on it.
- */
-static inline void pscsi_clear_cdb_lun(unsigned char *cdb)
-{
-        switch (cdb[0]) {
-        case READ_10: /* SBC - RDProtect */
-        case READ_12: /* SBC - RDProtect */
-        case READ_16: /* SBC - RDProtect */
-        case SEND_DIAGNOSTIC: /* SPC - SELF-TEST Code */
-        case VERIFY: /* SBC - VRProtect */
-        case VERIFY_16: /* SBC - VRProtect */
-        case WRITE_VERIFY: /* SBC - VRProtect */
-        case WRITE_VERIFY_12: /* SBC - VRProtect */
-        case MAINTENANCE_IN: /* SPC - Parameter Data Format for SA RTPG */
-                break;
-        default:
-                cdb[1] &= 0x1f; /* clear logical unit number */
-                break;
-        }
-}
-
 static sense_reason_t
 pscsi_parse_cdb(struct se_cmd *cmd)
 {
-        unsigned char *cdb = cmd->t_task_cdb;
-
         if (cmd->se_cmd_flags & SCF_BIDI)
                 return TCM_UNSUPPORTED_SCSI_OPCODE;
 
-        pscsi_clear_cdb_lun(cdb);
-
-        /*
-         * For REPORT LUNS we always need to emulate the response, for everything
-         * else the default for pSCSI is to pass the command to the underlying
-         * LLD / physical hardware.
-         */
-        switch (cdb[0]) {
-        case REPORT_LUNS:
-                cmd->execute_cmd = spc_emulate_report_luns;
-                return 0;
-        case READ_6:
-        case READ_10:
-        case READ_12:
-        case READ_16:
-        case WRITE_6:
-        case WRITE_10:
-        case WRITE_12:
-        case WRITE_16:
-        case WRITE_VERIFY:
-                cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
-                /* FALLTHROUGH*/
-        default:
-                cmd->execute_cmd = pscsi_execute_cmd;
-                return 0;
-        }
+        return passthrough_parse_cdb(cmd, pscsi_execute_cmd);
 }
 
 static sense_reason_t
@@ -1189,7 +1141,7 @@ static struct configfs_attribute *pscsi_backend_dev_attrs[] = {
 static struct se_subsystem_api pscsi_template = {
         .name                   = "pscsi",
         .owner                  = THIS_MODULE,
-        .transport_type         = TRANSPORT_PLUGIN_PHBA_PDEV,
+        .transport_flags        = TRANSPORT_FLAG_PASSTHROUGH,
         .attach_hba             = pscsi_attach_hba,
         .detach_hba             = pscsi_detach_hba,
         .pmode_enable_hba       = pscsi_pmode_enable_hba,
diff --git a/drivers/target/target_core_pscsi.h b/drivers/target/target_core_pscsi.h
index 1bd757dff8ee..820d3052b775 100644
--- a/drivers/target/target_core_pscsi.h
+++ b/drivers/target/target_core_pscsi.h
@@ -45,6 +45,7 @@ struct pscsi_dev_virt {
         int     pdv_lun_id;
         struct block_device *pdv_bd;
         struct scsi_device *pdv_sd;
+        struct Scsi_Host *pdv_lld_host;
 } ____cacheline_aligned;
 
 typedef enum phv_modes {
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index a263bf5fab8d..d16489b6a1a4 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -733,7 +733,6 @@ static struct se_subsystem_api rd_mcp_template = {
         .name                   = "rd_mcp",
         .inquiry_prod           = "RAMDISK-MCP",
         .inquiry_rev            = RD_MCP_VERSION,
-        .transport_type         = TRANSPORT_PLUGIN_VHBA_VDEV,
         .attach_hba             = rd_attach_hba,
         .detach_hba             = rd_detach_hba,
         .alloc_device           = rd_alloc_device,
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 8855781ac653..733824e3825f 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -568,7 +568,7 @@ sbc_compare_and_write(struct se_cmd *cmd)
          * comparision using SGLs at cmd->t_bidi_data_sg..
          */
         rc = down_interruptible(&dev->caw_sem);
-        if ((rc != 0) || signal_pending(current)) {
+        if (rc != 0) {
                 cmd->transport_complete_callback = NULL;
                 return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
         }
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 3fe5cb240b6f..675f2d9d1f14 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1196,7 +1196,7 @@ transport_check_alloc_task_attr(struct se_cmd *cmd)
          * Check if SAM Task Attribute emulation is enabled for this
          * struct se_device storage object
          */
-        if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+        if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
                 return 0;
 
         if (cmd->sam_task_attr == TCM_ACA_TAG) {
@@ -1770,7 +1770,7 @@ static int target_write_prot_action(struct se_cmd *cmd)
                                                    sectors, 0, NULL, 0);
                 if (unlikely(cmd->pi_err)) {
                         spin_lock_irq(&cmd->t_state_lock);
-                        cmd->transport_state &= ~CMD_T_BUSY|CMD_T_SENT;
+                        cmd->transport_state &= ~(CMD_T_BUSY|CMD_T_SENT);
                         spin_unlock_irq(&cmd->t_state_lock);
                         transport_generic_request_failure(cmd, cmd->pi_err);
                         return -1;
@@ -1787,7 +1787,7 @@ static bool target_handle_task_attr(struct se_cmd *cmd)
 {
         struct se_device *dev = cmd->se_dev;
 
-        if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+        if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
                 return false;
 
         /*
@@ -1868,7 +1868,7 @@ void target_execute_cmd(struct se_cmd *cmd)
 
         if (target_handle_task_attr(cmd)) {
                 spin_lock_irq(&cmd->t_state_lock);
-                cmd->transport_state &= ~CMD_T_BUSY|CMD_T_SENT;
+                cmd->transport_state &= ~(CMD_T_BUSY | CMD_T_SENT);
                 spin_unlock_irq(&cmd->t_state_lock);
                 return;
         }
@@ -1912,7 +1912,7 @@ static void transport_complete_task_attr(struct se_cmd *cmd)
 {
         struct se_device *dev = cmd->se_dev;
 
-        if (dev->transport->transport_type == TRANSPORT_PLUGIN_PHBA_PDEV)
+        if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
                 return;
 
         if (cmd->sam_task_attr == TCM_SIMPLE_TAG) {
@@ -1957,8 +1957,7 @@ static void transport_complete_qf(struct se_cmd *cmd)
         case DMA_TO_DEVICE:
                 if (cmd->se_cmd_flags & SCF_BIDI) {
                         ret = cmd->se_tfo->queue_data_in(cmd);
-                        if (ret < 0)
-                                break;
+                        break;
                 }
                 /* Fall through for DMA_TO_DEVICE */
         case DMA_NONE:
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index dbc872a6c981..07d2996d8c1f 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -71,13 +71,6 @@ struct tcmu_hba {
         u32 host_id;
 };
 
-/* User wants all cmds or just some */
-enum passthru_level {
-        TCMU_PASS_ALL = 0,
-        TCMU_PASS_IO,
-        TCMU_PASS_INVALID,
-};
-
 #define TCMU_CONFIG_LEN 256
 
 struct tcmu_dev {
@@ -89,7 +82,6 @@ struct tcmu_dev {
 #define TCMU_DEV_BIT_OPEN 0
 #define TCMU_DEV_BIT_BROKEN 1
         unsigned long flags;
-        enum passthru_level pass_level;
 
         struct uio_info uio_info;
 
@@ -683,8 +675,6 @@ static struct se_device *tcmu_alloc_device(struct se_hba *hba, const char *name)
         setup_timer(&udev->timeout, tcmu_device_timedout,
                 (unsigned long)udev);
 
-        udev->pass_level = TCMU_PASS_ALL;
-
         return &udev->se_dev;
 }
 
@@ -948,13 +938,13 @@ static void tcmu_free_device(struct se_device *dev)
 }
 
 enum {
-        Opt_dev_config, Opt_dev_size, Opt_err, Opt_pass_level,
+        Opt_dev_config, Opt_dev_size, Opt_hw_block_size, Opt_err,
 };
 
 static match_table_t tokens = {
         {Opt_dev_config, "dev_config=%s"},
         {Opt_dev_size, "dev_size=%u"},
-        {Opt_pass_level, "pass_level=%u"},
+        {Opt_hw_block_size, "hw_block_size=%u"},
         {Opt_err, NULL}
 };
 
@@ -965,7 +955,7 @@ static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev,
         char *orig, *ptr, *opts, *arg_p;
         substring_t args[MAX_OPT_ARGS];
         int ret = 0, token;
-        int arg;
+        unsigned long tmp_ul;
 
         opts = kstrdup(page, GFP_KERNEL);
         if (!opts)
@@ -998,15 +988,23 @@ static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev,
                         if (ret < 0)
                                 pr_err("kstrtoul() failed for dev_size=\n");
                         break;
-                case Opt_pass_level:
-                        match_int(args, &arg);
-                        if (arg >= TCMU_PASS_INVALID) {
-                                pr_warn("TCMU: Invalid pass_level: %d\n", arg);
+                case Opt_hw_block_size:
+                        arg_p = match_strdup(&args[0]);
+                        if (!arg_p) {
+                                ret = -ENOMEM;
                                 break;
                         }
-
-                        pr_debug("TCMU: Setting pass_level to %d\n", arg);
-                        udev->pass_level = arg;
+                        ret = kstrtoul(arg_p, 0, &tmp_ul);
+                        kfree(arg_p);
+                        if (ret < 0) {
+                                pr_err("kstrtoul() failed for hw_block_size=\n");
+                                break;
+                        }
+                        if (!tmp_ul) {
+                                pr_err("hw_block_size must be nonzero\n");
+                                break;
+                        }
+                        dev->dev_attrib.hw_block_size = tmp_ul;
                         break;
                 default:
                         break;
@@ -1024,8 +1022,7 @@ static ssize_t tcmu_show_configfs_dev_params(struct se_device *dev, char *b)
 
         bl = sprintf(b + bl, "Config: %s ",
                      udev->dev_config[0] ? udev->dev_config : "NULL");
-        bl += sprintf(b + bl, "Size: %zu PassLevel: %u\n",
-                      udev->dev_size, udev->pass_level);
+        bl += sprintf(b + bl, "Size: %zu\n", udev->dev_size);
 
         return bl;
 }
@@ -1039,20 +1036,6 @@ static sector_t tcmu_get_blocks(struct se_device *dev)
 }
 
 static sense_reason_t
-tcmu_execute_rw(struct se_cmd *se_cmd, struct scatterlist *sgl, u32 sgl_nents,
-                enum dma_data_direction data_direction)
-{
-        int ret;
-
-        ret = tcmu_queue_cmd(se_cmd);
-
-        if (ret != 0)
-                return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-        else
-                return TCM_NO_SENSE;
-}
-
-static sense_reason_t
 tcmu_pass_op(struct se_cmd *se_cmd)
 {
         int ret = tcmu_queue_cmd(se_cmd);
@@ -1063,91 +1046,29 @@ tcmu_pass_op(struct se_cmd *se_cmd)
                 return TCM_NO_SENSE;
 }
 
-static struct sbc_ops tcmu_sbc_ops = {
-        .execute_rw = tcmu_execute_rw,
-        .execute_sync_cache     = tcmu_pass_op,
-        .execute_write_same     = tcmu_pass_op,
-        .execute_write_same_unmap = tcmu_pass_op,
-        .execute_unmap          = tcmu_pass_op,
-};
-
 static sense_reason_t
 tcmu_parse_cdb(struct se_cmd *cmd)
 {
-        unsigned char *cdb = cmd->t_task_cdb;
-        struct tcmu_dev *udev = TCMU_DEV(cmd->se_dev);
-        sense_reason_t ret;
-
-        switch (udev->pass_level) {
-        case TCMU_PASS_ALL:
-                /* We're just like pscsi, then */
-                /*
-                 * For REPORT LUNS we always need to emulate the response, for everything
-                 * else, pass it up.
-                 */
-                switch (cdb[0]) {
-                case REPORT_LUNS:
-                        cmd->execute_cmd = spc_emulate_report_luns;
-                        break;
-                case READ_6:
-                case READ_10:
-                case READ_12:
-                case READ_16:
-                case WRITE_6:
-                case WRITE_10:
-                case WRITE_12:
-                case WRITE_16:
-                case WRITE_VERIFY:
-                        cmd->se_cmd_flags |= SCF_SCSI_DATA_CDB;
-                        /* FALLTHROUGH */
-                default:
-                        cmd->execute_cmd = tcmu_pass_op;
-                }
-                ret = TCM_NO_SENSE;
-                break;
-        case TCMU_PASS_IO:
-                ret = sbc_parse_cdb(cmd, &tcmu_sbc_ops);
-                break;
-        default:
-                pr_err("Unknown tcm-user pass level %d\n", udev->pass_level);
-                ret = TCM_CHECK_CONDITION_ABORT_CMD;
-        }
-
-        return ret;
+        return passthrough_parse_cdb(cmd, tcmu_pass_op);
 }
 
-DEF_TB_DEFAULT_ATTRIBS(tcmu);
+DEF_TB_DEV_ATTRIB_RO(tcmu, hw_pi_prot_type);
+TB_DEV_ATTR_RO(tcmu, hw_pi_prot_type);
+
+DEF_TB_DEV_ATTRIB_RO(tcmu, hw_block_size);
+TB_DEV_ATTR_RO(tcmu, hw_block_size);
+
+DEF_TB_DEV_ATTRIB_RO(tcmu, hw_max_sectors);
+TB_DEV_ATTR_RO(tcmu, hw_max_sectors);
+
+DEF_TB_DEV_ATTRIB_RO(tcmu, hw_queue_depth);
+TB_DEV_ATTR_RO(tcmu, hw_queue_depth);
 
 static struct configfs_attribute *tcmu_backend_dev_attrs[] = {
-        &tcmu_dev_attrib_emulate_model_alias.attr,
-        &tcmu_dev_attrib_emulate_dpo.attr,
-        &tcmu_dev_attrib_emulate_fua_write.attr,
-        &tcmu_dev_attrib_emulate_fua_read.attr,
-        &tcmu_dev_attrib_emulate_write_cache.attr,
-        &tcmu_dev_attrib_emulate_ua_intlck_ctrl.attr,
-        &tcmu_dev_attrib_emulate_tas.attr,
-        &tcmu_dev_attrib_emulate_tpu.attr,
-        &tcmu_dev_attrib_emulate_tpws.attr,
-        &tcmu_dev_attrib_emulate_caw.attr,
-        &tcmu_dev_attrib_emulate_3pc.attr,
-        &tcmu_dev_attrib_pi_prot_type.attr,
         &tcmu_dev_attrib_hw_pi_prot_type.attr,
-        &tcmu_dev_attrib_pi_prot_format.attr,
-        &tcmu_dev_attrib_enforce_pr_isids.attr,
-        &tcmu_dev_attrib_is_nonrot.attr,
-        &tcmu_dev_attrib_emulate_rest_reord.attr,
-        &tcmu_dev_attrib_force_pr_aptpl.attr,
         &tcmu_dev_attrib_hw_block_size.attr,
-        &tcmu_dev_attrib_block_size.attr,
         &tcmu_dev_attrib_hw_max_sectors.attr,
-        &tcmu_dev_attrib_optimal_sectors.attr,
         &tcmu_dev_attrib_hw_queue_depth.attr,
-        &tcmu_dev_attrib_queue_depth.attr,
-        &tcmu_dev_attrib_max_unmap_lba_count.attr,
-        &tcmu_dev_attrib_max_unmap_block_desc_count.attr,
-        &tcmu_dev_attrib_unmap_granularity.attr,
-        &tcmu_dev_attrib_unmap_granularity_alignment.attr,
-        &tcmu_dev_attrib_max_write_same_len.attr,
         NULL,
 };
 
@@ -1156,7 +1077,7 @@ static struct se_subsystem_api tcmu_template = {
         .inquiry_prod           = "USER",
         .inquiry_rev            = TCMU_VERSION,
         .owner                  = THIS_MODULE,
-        .transport_type         = TRANSPORT_PLUGIN_VHBA_PDEV,
+        .transport_flags        = TRANSPORT_FLAG_PASSTHROUGH,
         .attach_hba             = tcmu_attach_hba,
         .detach_hba             = tcmu_detach_hba,
         .alloc_device           = tcmu_alloc_device,
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index a600ff15dcfd..8fd680ac941b 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -58,7 +58,6 @@ static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op
                                         bool src)
 {
         struct se_device *se_dev;
-        struct configfs_subsystem *subsys = target_core_subsystem[0];
         unsigned char tmp_dev_wwn[XCOPY_NAA_IEEE_REGEX_LEN], *dev_wwn;
         int rc;
 
@@ -90,8 +89,7 @@ static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op
                                 " se_dev\n", xop->src_dev);
                 }
 
-                rc = configfs_depend_item(subsys,
-                                &se_dev->dev_group.cg_item);
+                rc = target_depend_item(&se_dev->dev_group.cg_item);
                 if (rc != 0) {
                         pr_err("configfs_depend_item attempt failed:"
                                 " %d for se_dev: %p\n", rc, se_dev);
@@ -99,8 +97,8 @@ static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op
                         return rc;
                 }
 
-                pr_debug("Called configfs_depend_item for subsys: %p se_dev: %p"
-                        " se_dev->se_dev_group: %p\n", subsys, se_dev,
+                pr_debug("Called configfs_depend_item for se_dev: %p"
+                        " se_dev->se_dev_group: %p\n", se_dev,
                         &se_dev->dev_group);
 
                 mutex_unlock(&g_device_mutex);
@@ -373,7 +371,6 @@ static int xcopy_pt_get_cmd_state(struct se_cmd *se_cmd)
 
 static void xcopy_pt_undepend_remotedev(struct xcopy_op *xop)
 {
-        struct configfs_subsystem *subsys = target_core_subsystem[0];
         struct se_device *remote_dev;
 
         if (xop->op_origin == XCOL_SOURCE_RECV_OP)
@@ -381,11 +378,11 @@ static void xcopy_pt_undepend_remotedev(struct xcopy_op *xop)
         else
                 remote_dev = xop->src_dev;
 
-        pr_debug("Calling configfs_undepend_item for subsys: %p"
+        pr_debug("Calling configfs_undepend_item for"
                   " remote_dev: %p remote_dev->dev_group: %p\n",
-                  subsys, remote_dev, &remote_dev->dev_group.cg_item);
+                  remote_dev, &remote_dev->dev_group.cg_item);
 
-        configfs_undepend_item(subsys, &remote_dev->dev_group.cg_item);
+        target_undepend_item(&remote_dev->dev_group.cg_item);
 }
 
 static void xcopy_pt_release_cmd(struct se_cmd *se_cmd)
diff --git a/drivers/tty/mips_ejtag_fdc.c b/drivers/tty/mips_ejtag_fdc.c
index 04d9e23d1ee1..358323c83b4f 100644
--- a/drivers/tty/mips_ejtag_fdc.c
+++ b/drivers/tty/mips_ejtag_fdc.c
@@ -174,13 +174,13 @@ struct mips_ejtag_fdc_tty {
 static inline void mips_ejtag_fdc_write(struct mips_ejtag_fdc_tty *priv,
                                         unsigned int offs, unsigned int data)
 {
-        iowrite32(data, priv->reg + offs);
+        __raw_writel(data, priv->reg + offs);
 }
 
 static inline unsigned int mips_ejtag_fdc_read(struct mips_ejtag_fdc_tty *priv,
                                                unsigned int offs)
 {
-        return ioread32(priv->reg + offs);
+        return __raw_readl(priv->reg + offs);
 }
 
 /* Encoding of byte stream in FDC words */
@@ -347,9 +347,9 @@ static void mips_ejtag_fdc_console_write(struct console *c, const char *s,
                 s += inc[word.bytes - 1];
 
                 /* Busy wait until there's space in fifo */
-                while (ioread32(regs + REG_FDSTAT) & REG_FDSTAT_TXF)
+                while (__raw_readl(regs + REG_FDSTAT) & REG_FDSTAT_TXF)
                         ;
-                iowrite32(word.word, regs + REG_FDTX(c->index));
+                __raw_writel(word.word, regs + REG_FDTX(c->index));
         }
 out:
         local_irq_restore(flags);
@@ -1227,7 +1227,7 @@ static int kgdbfdc_read_char(void)
 
                 /* Read next word from KGDB channel */
                 do {
-                        stat = ioread32(regs + REG_FDSTAT);
+                        stat = __raw_readl(regs + REG_FDSTAT);
 
                         /* No data waiting? */
                         if (stat & REG_FDSTAT_RXE)
@@ -1236,7 +1236,7 @@ static int kgdbfdc_read_char(void)
                         /* Read next word */
                         channel = (stat & REG_FDSTAT_RXCHAN) >>
                                         REG_FDSTAT_RXCHAN_SHIFT;
-                        data = ioread32(regs + REG_FDRX);
+                        data = __raw_readl(regs + REG_FDRX);
                 } while (channel != CONFIG_MIPS_EJTAG_FDC_KGDB_CHAN);
 
                 /* Decode into rbuf */
@@ -1266,9 +1266,10 @@ static void kgdbfdc_push_one(void)
                 return;
 
         /* Busy wait until there's space in fifo */
-        while (ioread32(regs + REG_FDSTAT) & REG_FDSTAT_TXF)
+        while (__raw_readl(regs + REG_FDSTAT) & REG_FDSTAT_TXF)
                 ;
-        iowrite32(word.word, regs + REG_FDTX(CONFIG_MIPS_EJTAG_FDC_KGDB_CHAN));
+        __raw_writel(word.word,
+                     regs + REG_FDTX(CONFIG_MIPS_EJTAG_FDC_KGDB_CHAN));
 }
 
 /* flush the whole write buffer to the TX FIFO */
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 5e19bb53b3a9..ea32b386797f 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1409,8 +1409,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs,
                          * dependency now.
                          */
                         se_tpg = &tpg->se_tpg;
-                        ret = configfs_depend_item(se_tpg->se_tpg_tfo->tf_subsys,
-                                                   &se_tpg->tpg_group.cg_item);
+                        ret = target_depend_item(&se_tpg->tpg_group.cg_item);
                         if (ret) {
                                 pr_warn("configfs_depend_item() failed: %d\n", ret);
                                 kfree(vs_tpg);
@@ -1513,8 +1512,7 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs,
                  * to allow vhost-scsi WWPN se_tpg->tpg_group shutdown to occur.
                  */
                 se_tpg = &tpg->se_tpg;
-                configfs_undepend_item(se_tpg->se_tpg_tfo->tf_subsys,
-                                       &se_tpg->tpg_group.cg_item);
+                target_undepend_item(&se_tpg->tpg_group.cg_item);
         }
         if (match) {
                 for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 241ef68d2893..cd46e4158830 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -918,7 +918,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
                         total_size = total_mapping_size(elf_phdata,
                                                         loc->elf_ex.e_phnum);
                         if (!total_size) {
-                                error = -EINVAL;
+                                retval = -EINVAL;
                                 goto out_free_dentry;
                         }
                 }
diff --git a/fs/dcache.c b/fs/dcache.c
index 656ce522a218..37b5afdaf698 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1239,13 +1239,13 @@ ascend:
                 /* might go back up the wrong parent if we have had a rename. */
                 if (need_seqretry(&rename_lock, seq))
                         goto rename_retry;
-                next = child->d_child.next;
-                while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) {
+                /* go into the first sibling still alive */
+                do {
+                        next = child->d_child.next;
                         if (next == &this_parent->d_subdirs)
                                 goto ascend;
                         child = list_entry(next, struct dentry, d_child);
-                        next = next->next;
-                }
+                } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
                 rcu_read_unlock();
                 goto resume;
         }
diff --git a/fs/omfs/bitmap.c b/fs/omfs/bitmap.c
index 082234581d05..83f4e76511c2 100644
--- a/fs/omfs/bitmap.c
+++ b/fs/omfs/bitmap.c
@@ -159,7 +159,7 @@ int omfs_allocate_range(struct super_block *sb,
         goto out;
 
 found:
-        *return_block = i * bits_per_entry + bit;
+        *return_block = (u64) i * bits_per_entry + bit;
         *return_size = run;
         ret = set_run(sb, i, bits_per_entry, bit, run, 1);
 
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index 138321b0c6c2..3d935c81789a 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -306,7 +306,8 @@ static const struct super_operations omfs_sops = {
  */
 static int omfs_get_imap(struct super_block *sb)
 {
-        unsigned int bitmap_size, count, array_size;
+        unsigned int bitmap_size, array_size;
+        int count;
         struct omfs_sb_info *sbi = OMFS_SB(sb);
         struct buffer_head *bh;
         unsigned long **ptr;
@@ -359,7 +360,7 @@ nomem:
 }
 
 enum {
-        Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask
+        Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask, Opt_err
 };
 
 static const match_table_t tokens = {
@@ -368,6 +369,7 @@ static const match_table_t tokens = {
         {Opt_umask, "umask=%o"},
         {Opt_dmask, "dmask=%o"},
         {Opt_fmask, "fmask=%o"},
+        {Opt_err, NULL},
 };
 
 static int parse_options(char *options, struct omfs_sb_info *sbi)
@@ -548,8 +550,10 @@ static int omfs_fill_super(struct super_block *sb, void *data, int silent)
         }
 
         sb->s_root = d_make_root(root);
-        if (!sb->s_root)
+        if (!sb->s_root) {
+                ret = -ENOMEM;
                 goto out_brelse_bh2;
+        }
         printk(KERN_DEBUG "omfs: Mounted volume %s\n", omfs_rb->r_name);
 
         ret = 0;
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 04e79d57bca6..e9d401ce93bb 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -574,8 +574,8 @@ xfs_attr_shortform_add(xfs_da_args_t *args, int forkoff)
  * After the last attribute is removed revert to original inode format,
  * making all literal area available to the data fork once more.
  */
-STATIC void
-xfs_attr_fork_reset(
+void
+xfs_attr_fork_remove(
         struct xfs_inode        *ip,
         struct xfs_trans        *tp)
 {
@@ -641,7 +641,7 @@ xfs_attr_shortform_remove(xfs_da_args_t *args)
             (mp->m_flags & XFS_MOUNT_ATTR2) &&
             (dp->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
             !(args->op_flags & XFS_DA_OP_ADDNAME)) {
-                xfs_attr_fork_reset(dp, args->trans);
+                xfs_attr_fork_remove(dp, args->trans);
         } else {
                 xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
                 dp->i_d.di_forkoff = xfs_attr_shortform_bytesfit(dp, totsize);
@@ -905,7 +905,7 @@ xfs_attr3_leaf_to_shortform(
         if (forkoff == -1) {
                 ASSERT(dp->i_mount->m_flags & XFS_MOUNT_ATTR2);
                 ASSERT(dp->i_d.di_format != XFS_DINODE_FMT_BTREE);
-                xfs_attr_fork_reset(dp, args->trans);
+                xfs_attr_fork_remove(dp, args->trans);
                 goto out;
         }
 
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index 025c4b820c03..882c8d338891 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -53,7 +53,7 @@ int	xfs_attr_shortform_remove(struct xfs_da_args *args);
 int     xfs_attr_shortform_list(struct xfs_attr_list_context *context);
 int     xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp);
 int     xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes);
-
+void    xfs_attr_fork_remove(struct xfs_inode *ip, struct xfs_trans *tp);
 
 /*
  * Internal routines when attribute fork size == XFS_LBSIZE(mp).
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index aeffeaaac0ec..f1026e86dabc 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3224,12 +3224,24 @@ xfs_bmap_extsize_align(
                 align_alen += temp;
                 align_off -= temp;
         }
+
+        /* Same adjustment for the end of the requested area. */
+        temp = (align_alen % extsz);
+        if (temp)
+                align_alen += extsz - temp;
+
         /*
-         * Same adjustment for the end of the requested area.
+         * For large extent hint sizes, the aligned extent might be larger than
+         * MAXEXTLEN. In that case, reduce the size by an extsz so that it pulls
+         * the length back under MAXEXTLEN. The outer allocation loops handle
+         * short allocation just fine, so it is safe to do this. We only want to
+         * do it when we are forced to, though, because it means more allocation
+         * operations are required.
          */
-        if ((temp = (align_alen % extsz))) {
-                align_alen += extsz - temp;
-        }
+        while (align_alen > MAXEXTLEN)
+                align_alen -= extsz;
+        ASSERT(align_alen <= MAXEXTLEN);
+
         /*
          * If the previous block overlaps with this proposed allocation
          * then move the start forward without adjusting the length.
@@ -3318,7 +3330,9 @@ xfs_bmap_extsize_align(
                         return -EINVAL;
         } else {
                 ASSERT(orig_off >= align_off);
-                ASSERT(orig_end <= align_off + align_alen);
+                /* see MAXEXTLEN handling above */
+                ASSERT(orig_end <= align_off + align_alen ||
+                       align_alen + extsz > MAXEXTLEN);
         }
 
 #ifdef DEBUG
@@ -4099,13 +4113,6 @@ xfs_bmapi_reserve_delalloc(
         /* Figure out the extent size, adjust alen */
         extsz = xfs_get_extsz_hint(ip);
         if (extsz) {
-                /*
-                 * Make sure we don't exceed a single extent length when we
-                 * align the extent by reducing length we are going to
-                 * allocate by the maximum amount extent size aligment may
-                 * require.
-                 */
-                alen = XFS_FILBLKS_MIN(len, MAXEXTLEN - (2 * extsz - 1));
                 error = xfs_bmap_extsize_align(mp, got, prev, extsz, rt, eof,
                                                1, 0, &aoff, &alen);
                 ASSERT(!error);
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 07349a183a11..1c9e75521250 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -376,7 +376,7 @@ xfs_ialloc_ag_alloc(
          */
         newlen = args.mp->m_ialloc_inos;
         if (args.mp->m_maxicount &&
-            percpu_counter_read(&args.mp->m_icount) + newlen >
+            percpu_counter_read_positive(&args.mp->m_icount) + newlen >
                                                         args.mp->m_maxicount)
                 return -ENOSPC;
         args.minlen = args.maxlen = args.mp->m_ialloc_blks;
@@ -1339,10 +1339,13 @@ xfs_dialloc(
          * If we have already hit the ceiling of inode blocks then clear
          * okalloc so we scan all available agi structures for a free
          * inode.
+         *
+         * Read rough value of mp->m_icount by percpu_counter_read_positive,
+         * which will sacrifice the preciseness but improve the performance.
          */
         if (mp->m_maxicount &&
-            percpu_counter_read(&mp->m_icount) + mp->m_ialloc_inos >
-                                                        mp->m_maxicount) {
+            percpu_counter_read_positive(&mp->m_icount) + mp->m_ialloc_inos
+                                                        > mp->m_maxicount) {
                 noroom = 1;
                 okalloc = 0;
         }
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index f9c1c64782d3..3fbf167cfb4c 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -380,23 +380,31 @@ xfs_attr3_root_inactive(
         return error;
 }
 
+/*
+ * xfs_attr_inactive kills all traces of an attribute fork on an inode. It
+ * removes both the on-disk and in-memory inode fork. Note that this also has to
+ * handle the condition of inodes without attributes but with an attribute fork
+ * configured, so we can't use xfs_inode_hasattr() here.
+ *
+ * The in-memory attribute fork is removed even on error.
+ */
 int
-xfs_attr_inactive(xfs_inode_t *dp)
+xfs_attr_inactive(
+        struct xfs_inode        *dp)
 {
-        xfs_trans_t *trans;
-        xfs_mount_t *mp;
-        int error;
+        struct xfs_trans        *trans;
+        struct xfs_mount        *mp;
+        int                     cancel_flags = 0;
+        int                     lock_mode = XFS_ILOCK_SHARED;
+        int                     error = 0;
 
         mp = dp->i_mount;
         ASSERT(! XFS_NOT_DQATTACHED(mp, dp));
 
-        xfs_ilock(dp, XFS_ILOCK_SHARED);
-        if (!xfs_inode_hasattr(dp) ||
-            dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
-                xfs_iunlock(dp, XFS_ILOCK_SHARED);
-                return 0;
-        }
-        xfs_iunlock(dp, XFS_ILOCK_SHARED);
+        xfs_ilock(dp, lock_mode);
+        if (!XFS_IFORK_Q(dp))
+                goto out_destroy_fork;
+        xfs_iunlock(dp, lock_mode);
 
         /*
          * Start our first transaction of the day.
@@ -408,13 +416,18 @@ xfs_attr_inactive(xfs_inode_t *dp)
          * the inode in every transaction to let it float upward through
          * the log.
          */
+        lock_mode = 0;
         trans = xfs_trans_alloc(mp, XFS_TRANS_ATTRINVAL);
         error = xfs_trans_reserve(trans, &M_RES(mp)->tr_attrinval, 0, 0);
-        if (error) {
-                xfs_trans_cancel(trans, 0);
-                return error;
-        }
-        xfs_ilock(dp, XFS_ILOCK_EXCL);
+        if (error)
+                goto out_cancel;
+
+        lock_mode = XFS_ILOCK_EXCL;
+        cancel_flags = XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT;
+        xfs_ilock(dp, lock_mode);
+
+        if (!XFS_IFORK_Q(dp))
+                goto out_cancel;
 
         /*
          * No need to make quota reservations here. We expect to release some
@@ -422,29 +435,31 @@ xfs_attr_inactive(xfs_inode_t *dp)
          */
         xfs_trans_ijoin(trans, dp, 0);
 
-        /*
-         * Decide on what work routines to call based on the inode size.
-         */
-        if (!xfs_inode_hasattr(dp) ||
-            dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
-                error = 0;
-                goto out;
+        /* invalidate and truncate the attribute fork extents */
+        if (dp->i_d.di_aformat != XFS_DINODE_FMT_LOCAL) {
+                error = xfs_attr3_root_inactive(&trans, dp);
+                if (error)
+                        goto out_cancel;
+
+                error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
+                if (error)
+                        goto out_cancel;
         }
-        error = xfs_attr3_root_inactive(&trans, dp);
-        if (error)
-                goto out;
 
-        error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
-        if (error)
-                goto out;
+        /* Reset the attribute fork - this also destroys the in-core fork */
+        xfs_attr_fork_remove(dp, trans);
 
         error = xfs_trans_commit(trans, XFS_TRANS_RELEASE_LOG_RES);
-        xfs_iunlock(dp, XFS_ILOCK_EXCL);
-
+        xfs_iunlock(dp, lock_mode);
         return error;
 
-out:
-        xfs_trans_cancel(trans, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
-        xfs_iunlock(dp, XFS_ILOCK_EXCL);
+out_cancel:
+        xfs_trans_cancel(trans, cancel_flags);
+out_destroy_fork:
+        /* kill the in-core attr fork before we drop the inode lock */
+        if (dp->i_afp)
+                xfs_idestroy_fork(dp, XFS_ATTR_FORK);
+        if (lock_mode)
+                xfs_iunlock(dp, lock_mode);
         return error;
 }
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 8121e75352ee..3b7591224f4a 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -124,7 +124,7 @@ xfs_iozero(
                 status = 0;
         } while (count);
 
-        return (-status);
+        return status;
 }
 
 int
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index d6ebc85192b7..539a85fddbc2 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1946,21 +1946,17 @@ xfs_inactive(
         /*
          * If there are attributes associated with the file then blow them away
          * now.  The code calls a routine that recursively deconstructs the
-         * attribute fork.  We need to just commit the current transaction
-         * because we can't use it for xfs_attr_inactive().
+         * attribute fork. If also blows away the in-core attribute fork.
          */
-        if (ip->i_d.di_anextents > 0) {
-                ASSERT(ip->i_d.di_forkoff != 0);
-
+        if (XFS_IFORK_Q(ip)) {
                 error = xfs_attr_inactive(ip);
                 if (error)
                         return;
         }
 
-        if (ip->i_afp)
-                xfs_idestroy_fork(ip, XFS_ATTR_FORK);
-
+        ASSERT(!ip->i_afp);
         ASSERT(ip->i_d.di_anextents == 0);
+        ASSERT(ip->i_d.di_forkoff == 0);
 
         /*
          * Free the inode.
@@ -2883,7 +2879,13 @@ xfs_rename_alloc_whiteout(
         if (error)
                 return error;
 
-        /* Satisfy xfs_bumplink that this is a real tmpfile */
+        /*
+         * Prepare the tmpfile inode as if it were created through the VFS.
+         * Otherwise, the link increment paths will complain about nlink 0->1.
+         * Drop the link count as done by d_tmpfile(), complete the inode setup
+         * and flag it as linkable.
+         */
+        drop_nlink(VFS_I(tmpfile));
         xfs_finish_inode_setup(tmpfile);
         VFS_I(tmpfile)->i_state |= I_LINKABLE;
 
@@ -3151,7 +3153,7 @@ xfs_rename(
          * intermediate state on disk.
          */
         if (wip) {
-                ASSERT(wip->i_d.di_nlink == 0);
+                ASSERT(VFS_I(wip)->i_nlink == 0 && wip->i_d.di_nlink == 0);
                 error = xfs_bumplink(tp, wip);
                 if (error)
                         goto out_trans_abort;
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 2ce7ee3b4ec1..6f23fbdfb365 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1084,14 +1084,18 @@ xfs_log_sbcount(xfs_mount_t *mp)
         return xfs_sync_sb(mp, true);
 }
 
+/*
+ * Deltas for the inode count are +/-64, hence we use a large batch size
+ * of 128 so we don't need to take the counter lock on every update.
+ */
+#define XFS_ICOUNT_BATCH        128
 int
 xfs_mod_icount(
         struct xfs_mount        *mp,
         int64_t                 delta)
 {
-        /* deltas are +/-64, hence the large batch size of 128. */
-        __percpu_counter_add(&mp->m_icount, delta, 128);
-        if (percpu_counter_compare(&mp->m_icount, 0) < 0) {
+        __percpu_counter_add(&mp->m_icount, delta, XFS_ICOUNT_BATCH);
+        if (__percpu_counter_compare(&mp->m_icount, 0, XFS_ICOUNT_BATCH) < 0) {
                 ASSERT(0);
                 percpu_counter_add(&mp->m_icount, -delta);
                 return -EINVAL;
@@ -1113,6 +1117,14 @@ xfs_mod_ifree(
         return 0;
 }
 
+/*
+ * Deltas for the block count can vary from 1 to very large, but lock contention
+ * only occurs on frequent small block count updates such as in the delayed
+ * allocation path for buffered writes (page a time updates). Hence we set
+ * a large batch count (1024) to minimise global counter updates except when
+ * we get near to ENOSPC and we have to be very accurate with our updates.
+ */
+#define XFS_FDBLOCKS_BATCH      1024
 int
 xfs_mod_fdblocks(
         struct xfs_mount        *mp,
@@ -1151,25 +1163,19 @@ xfs_mod_fdblocks(
          * Taking blocks away, need to be more accurate the closer we
          * are to zero.
          *
-         * batch size is set to a maximum of 1024 blocks - if we are
-         * allocating of freeing extents larger than this then we aren't
-         * going to be hammering the counter lock so a lock per update
-         * is not a problem.
-         *
          * If the counter has a value of less than 2 * max batch size,
          * then make everything serialise as we are real close to
          * ENOSPC.
          */
-#define __BATCH 1024
-        if (percpu_counter_compare(&mp->m_fdblocks, 2 * __BATCH) < 0)
+        if (__percpu_counter_compare(&mp->m_fdblocks, 2 * XFS_FDBLOCKS_BATCH,
+                                     XFS_FDBLOCKS_BATCH) < 0)
                 batch = 1;
         else
-                batch = __BATCH;
-#undef __BATCH
+                batch = XFS_FDBLOCKS_BATCH;
 
         __percpu_counter_add(&mp->m_fdblocks, delta, batch);
-        if (percpu_counter_compare(&mp->m_fdblocks,
-                                   XFS_ALLOC_SET_ASIDE(mp)) >= 0) {
+        if (__percpu_counter_compare(&mp->m_fdblocks, XFS_ALLOC_SET_ASIDE(mp),
+                                     XFS_FDBLOCKS_BATCH) >= 0) {
                 /* we had space! */
                 return 0;
         }
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 27e285b92b5f..59915ea5373c 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -151,10 +151,8 @@ static inline unsigned int cpumask_any_but(const struct cpumask *mask,
         return 1;
 }
 
-static inline int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp)
+static inline unsigned int cpumask_local_spread(unsigned int i, int node)
 {
-        set_bit(0, cpumask_bits(dstp));
-
         return 0;
 }
 
@@ -208,7 +206,7 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 
 int cpumask_next_and(int n, const struct cpumask *, const struct cpumask *);
 int cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
-int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp);
+unsigned int cpumask_local_spread(unsigned int i, int node);
 
 /**
  * for_each_cpu - iterate over every cpu in a mask
diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 50e50095c8d1..84a109449610 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -41,7 +41,12 @@ void percpu_counter_destroy(struct percpu_counter *fbc);
 void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
 void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch);
 s64 __percpu_counter_sum(struct percpu_counter *fbc);
-int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs);
+int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch);
+
+static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
+{
+        return __percpu_counter_compare(fbc, rhs, percpu_counter_batch);
+}
 
 static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 {
@@ -116,6 +121,12 @@ static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
                 return 0;
 }
 
+static inline int
+__percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch)
+{
+        return percpu_counter_compare(fbc, rhs);
+}
+
 static inline void
 percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 {
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index d61be7297b2c..5f1225706993 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -1,9 +1,7 @@
 #ifndef TARGET_CORE_BACKEND_H
 #define TARGET_CORE_BACKEND_H
 
-#define TRANSPORT_PLUGIN_PHBA_PDEV              1
-#define TRANSPORT_PLUGIN_VHBA_PDEV              2
-#define TRANSPORT_PLUGIN_VHBA_VDEV              3
+#define TRANSPORT_FLAG_PASSTHROUGH              1
 
 struct target_backend_cits {
         struct config_item_type tb_dev_cit;
@@ -22,7 +20,7 @@ struct se_subsystem_api {
         char inquiry_rev[4];
         struct module *owner;
 
-        u8 transport_type;
+        u8 transport_flags;
 
         int (*attach_hba)(struct se_hba *, u32);
         void (*detach_hba)(struct se_hba *);
@@ -138,5 +136,7 @@ int	se_dev_set_queue_depth(struct se_device *, u32);
 int     se_dev_set_max_sectors(struct se_device *, u32);
 int     se_dev_set_optimal_sectors(struct se_device *, u32);
 int     se_dev_set_block_size(struct se_device *, u32);
+sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd,
+        sense_reason_t (*exec_cmd)(struct se_cmd *cmd));
 
 #endif /* TARGET_CORE_BACKEND_H */
diff --git a/include/target/target_core_configfs.h b/include/target/target_core_configfs.h
index 25bb04c4209e..b99c01170392 100644
--- a/include/target/target_core_configfs.h
+++ b/include/target/target_core_configfs.h
@@ -40,8 +40,6 @@ struct target_fabric_configfs {
         struct config_item      *tf_fabric;
         /* Passed from fabric modules */
         struct config_item_type *tf_fabric_cit;
-        /* Pointer to target core subsystem */
-        struct configfs_subsystem *tf_subsys;
         /* Pointer to fabric's struct module */
         struct module *tf_module;
         struct target_core_fabric_ops tf_ops;
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 17c7f5ac7ea0..0f4dc3768587 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -4,7 +4,6 @@
 struct target_core_fabric_ops {
         struct module *module;
         const char *name;
-        struct configfs_subsystem *tf_subsys;
         char *(*get_fabric_name)(void);
         u8 (*get_fabric_proto_ident)(struct se_portal_group *);
         char *(*tpg_get_wwn)(struct se_portal_group *);
@@ -109,6 +108,9 @@ struct target_core_fabric_ops {
 int target_register_template(const struct target_core_fabric_ops *fo);
 void target_unregister_template(const struct target_core_fabric_ops *fo);
 
+int target_depend_item(struct config_item *item);
+void target_undepend_item(struct config_item *item);
+
 struct se_session *transport_init_session(enum target_prot_op);
 int transport_alloc_session_tags(struct se_session *, unsigned int,
                 unsigned int);
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 81ea59812117..f7554fd7fc62 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -140,19 +140,42 @@ DEFINE_EVENT(kmem_free, kfree,
         TP_ARGS(call_site, ptr)
 );
 
-DEFINE_EVENT(kmem_free, kmem_cache_free,
+DEFINE_EVENT_CONDITION(kmem_free, kmem_cache_free,
 
         TP_PROTO(unsigned long call_site, const void *ptr),
 
-        TP_ARGS(call_site, ptr)
+        TP_ARGS(call_site, ptr),
+
+        /*
+         * This trace can be potentially called from an offlined cpu.
+         * Since trace points use RCU and RCU should not be used from
+         * offline cpus, filter such calls out.
+         * While this trace can be called from a preemptable section,
+         * it has no impact on the condition since tasks can migrate
+         * only from online cpus to other online cpus. Thus its safe
+         * to use raw_smp_processor_id.
+         */
+        TP_CONDITION(cpu_online(raw_smp_processor_id()))
 );
 
-TRACE_EVENT(mm_page_free,
+TRACE_EVENT_CONDITION(mm_page_free,
 
         TP_PROTO(struct page *page, unsigned int order),
 
         TP_ARGS(page, order),
 
+
+        /*
+         * This trace can be potentially called from an offlined cpu.
+         * Since trace points use RCU and RCU should not be used from
+         * offline cpus, filter such calls out.
+         * While this trace can be called from a preemptable section,
+         * it has no impact on the condition since tasks can migrate
+         * only from online cpus to other online cpus. Thus its safe
+         * to use raw_smp_processor_id.
+         */
+        TP_CONDITION(cpu_online(raw_smp_processor_id())),
+
         TP_STRUCT__entry(
                 __field(        unsigned long,  pfn             )
                 __field(        unsigned int,   order           )
@@ -253,12 +276,35 @@ DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked,
         TP_ARGS(page, order, migratetype)
 );
 
-DEFINE_EVENT_PRINT(mm_page, mm_page_pcpu_drain,
+TRACE_EVENT_CONDITION(mm_page_pcpu_drain,
 
         TP_PROTO(struct page *page, unsigned int order, int migratetype),
 
         TP_ARGS(page, order, migratetype),
 
+        /*
+         * This trace can be potentially called from an offlined cpu.
+         * Since trace points use RCU and RCU should not be used from
+         * offline cpus, filter such calls out.
+         * While this trace can be called from a preemptable section,
+         * it has no impact on the condition since tasks can migrate
+         * only from online cpus to other online cpus. Thus its safe
+         * to use raw_smp_processor_id.
+         */
+        TP_CONDITION(cpu_online(raw_smp_processor_id())),
+
+        TP_STRUCT__entry(
+                __field(        unsigned long,  pfn             )
+                __field(        unsigned int,   order           )
+                __field(        int,            migratetype     )
+        ),
+
+        TP_fast_assign(
+                __entry->pfn            = page ? page_to_pfn(page) : -1UL;
+                __entry->order          = order;
+                __entry->migratetype    = migratetype;
+        ),
+
         TP_printk("page=%p pfn=%lu order=%d migratetype=%d",
                 pfn_to_page(__entry->pfn), __entry->pfn,
                 __entry->order, __entry->migratetype)
diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h
index 984169a819ee..d7f1cbc3766c 100644
--- a/include/uapi/linux/virtio_balloon.h
+++ b/include/uapi/linux/virtio_balloon.h
@@ -26,6 +26,7 @@
  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  * SUCH DAMAGE. */
 #include <linux/types.h>
+#include <linux/virtio_types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
 
diff --git a/kernel/module.c b/kernel/module.c
index 42a1d2afb217..cfc9e843a924 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3370,6 +3370,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
         module_bug_cleanup(mod);
         mutex_unlock(&module_mutex);
 
+        blocking_notifier_call_chain(&module_notify_list,
+                                     MODULE_STATE_GOING, mod);
+
         /* we can't deallocate the module until we clear memory protection */
         unset_module_init_ro_nx(mod);
         unset_module_core_ro_nx(mod);
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 830dd5dec40f..5f627084f2e9 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -139,64 +139,42 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
 #endif
 
 /**
- * cpumask_set_cpu_local_first - set i'th cpu with local numa cpu's first
- *
+ * cpumask_local_spread - select the i'th cpu with local numa cpu's first
  * @i: index number
- * @numa_node: local numa_node
- * @dstp: cpumask with the relevant cpu bit set according to the policy
+ * @node: local numa_node
  *
- * This function sets the cpumask according to a numa aware policy.
- * cpumask could be used as an affinity hint for the IRQ related to a
- * queue. When the policy is to spread queues across cores - local cores
- * first.
+ * This function selects an online CPU according to a numa aware policy;
+ * local cpus are returned first, followed by non-local ones, then it
+ * wraps around.
  *
- * Returns 0 on success, -ENOMEM for no memory, and -EAGAIN when failed to set
- * the cpu bit and need to re-call the function.
+ * It's not very efficient, but useful for setup.
  */
-int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp)
+unsigned int cpumask_local_spread(unsigned int i, int node)
 {
-        cpumask_var_t mask;
         int cpu;
-        int ret = 0;
-
-        if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
-                return -ENOMEM;
 
+        /* Wrap: we always want a cpu. */
         i %= num_online_cpus();
 
-        if (numa_node == -1 || !cpumask_of_node(numa_node)) {
-                /* Use all online cpu's for non numa aware system */
-                cpumask_copy(mask, cpu_online_mask);
+        if (node == -1) {
+                for_each_cpu(cpu, cpu_online_mask)
+                        if (i-- == 0)
+                                return cpu;
         } else {
-                int n;
-
-                cpumask_and(mask,
-                            cpumask_of_node(numa_node), cpu_online_mask);
-
-                n = cpumask_weight(mask);
-                if (i >= n) {
-                        i -= n;
-
-                        /* If index > number of local cpu's, mask out local
-                         * cpu's
-                         */
-                        cpumask_andnot(mask, cpu_online_mask, mask);
+                /* NUMA first. */
+                for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask)
+                        if (i-- == 0)
+                                return cpu;
+
+                for_each_cpu(cpu, cpu_online_mask) {
+                        /* Skip NUMA nodes, done above. */
+                        if (cpumask_test_cpu(cpu, cpumask_of_node(node)))
+                                continue;
+
+                        if (i-- == 0)
+                                return cpu;
                 }
         }
-
-        for_each_cpu(cpu, mask) {
-                if (--i < 0)
-                        goto out;
-        }
-
-        ret = -EAGAIN;
-
-out:
-        free_cpumask_var(mask);
-
-        if (!ret)
-                cpumask_set_cpu(cpu, dstp);
-
-        return ret;
+        BUG();
 }
-EXPORT_SYMBOL(cpumask_set_cpu_local_first);
+EXPORT_SYMBOL(cpumask_local_spread);
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 48144cdae819..f051d69f0910 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -197,13 +197,13 @@ static int percpu_counter_hotcpu_callback(struct notifier_block *nb,
  * Compare counter against given value.
  * Return 1 if greater, 0 if equal and -1 if less
  */
-int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
+int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch)
 {
         s64     count;
 
         count = percpu_counter_read(fbc);
         /* Check to see if rough count will be sufficient for comparison */
-        if (abs(count - rhs) > (percpu_counter_batch*num_online_cpus())) {
+        if (abs(count - rhs) > (batch * num_online_cpus())) {
                 if (count > rhs)
                         return 1;
                 else
@@ -218,7 +218,7 @@ int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
         else
                 return 0;
 }
-EXPORT_SYMBOL(percpu_counter_compare);
+EXPORT_SYMBOL(__percpu_counter_compare);
 
 static int __init percpu_counter_startup(void)
 {
diff --git a/scripts/gdb/linux/modules.py b/scripts/gdb/linux/modules.py
index a1504c4f1900..25db8cff44a2 100644
--- a/scripts/gdb/linux/modules.py
+++ b/scripts/gdb/linux/modules.py
@@ -73,18 +73,11 @@ class LxLsmod(gdb.Command):
                 "        " if utils.get_long_type().sizeof == 8 else ""))
 
         for module in module_list():
-            ref = 0
-            module_refptr = module['refptr']
-            for cpu in cpus.cpu_list("cpu_possible_mask"):
-                refptr = cpus.per_cpu(module_refptr, cpu)
-                ref += refptr['incs']
-                ref -= refptr['decs']
-
             gdb.write("{address} {name:<19} {size:>8}  {ref}".format(
                 address=str(module['module_core']).split()[0],
                 name=module['name'].string(),
                 size=str(module['core_size']),
-                ref=str(ref)))
+                ref=str(module['refcnt']['counter'])))
 
             source_list = module['source_list']
             t = self._module_use_type.get_type().pointer()
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 1c8678775f40..ac0db1679f09 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -4926,9 +4926,12 @@ int snd_hda_gen_parse_auto_config(struct hda_codec *codec,
  dig_only:
         parse_digital(codec);
 
-        if (spec->power_down_unused || codec->power_save_node)
+        if (spec->power_down_unused || codec->power_save_node) {
                 if (!codec->power_filter)
                         codec->power_filter = snd_hda_gen_path_power_filter;
+                if (!codec->patch_ops.stream_pm)
+                        codec->patch_ops.stream_pm = snd_hda_gen_stream_pm;
+        }
 
         if (!spec->no_analog && spec->beep_nid) {
                 err = snd_hda_attach_beep_device(codec, spec->beep_nid);
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 34040d26c94f..fea198c58196 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2089,6 +2089,8 @@ static const struct pci_device_id azx_ids[] = {
           .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
         { PCI_DEVICE(0x1002, 0xaab0),
           .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+        { PCI_DEVICE(0x1002, 0xaac8),
+          .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
         /* VIA VT8251/VT8237A */
         { PCI_DEVICE(0x1106, 0x3288),
           .driver_data = AZX_DRIVER_VIA | AZX_DCAPS_POSFIX_VIA },
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 31f8f13be907..464168426465 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -884,6 +884,7 @@ static struct alc_codec_rename_pci_table rename_pci_tbl[] = {
         { 0x10ec0275, 0x1028, 0, "ALC3260" },
         { 0x10ec0899, 0x1028, 0, "ALC3861" },
         { 0x10ec0298, 0x1028, 0, "ALC3266" },
+        { 0x10ec0256, 0x1028, 0, "ALC3246" },
         { 0x10ec0670, 0x1025, 0, "ALC669X" },
         { 0x10ec0676, 0x1025, 0, "ALC679X" },
         { 0x10ec0282, 0x1043, 0, "ALC3229" },
@@ -4227,6 +4228,11 @@ static void alc_fixup_headset_mode_alc662(struct hda_codec *codec,
         if (action == HDA_FIXUP_ACT_PRE_PROBE) {
                 spec->parse_flags |= HDA_PINCFG_HEADSET_MIC;
                 spec->gen.hp_mic = 1; /* Mic-in is same pin as headphone */
+
+                /* Disable boost for mic-in permanently. (This code is only called
+                   from quirks that guarantee that the headphone is at NID 0x1b.) */
+                snd_hda_codec_write(codec, 0x1b, 0, AC_VERB_SET_AMP_GAIN_MUTE, 0x7000);
+                snd_hda_override_wcaps(codec, 0x1b, get_wcaps(codec, 0x1b) & ~AC_WCAP_IN_AMP);
         } else
                 alc_fixup_headset_mode(codec, fix, action);
 }
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 43c99ce4a520..6833c74ed6ff 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -4403,7 +4403,6 @@ static const struct hda_codec_ops stac_patch_ops = {
 #ifdef CONFIG_PM
         .suspend = stac_suspend,
 #endif
-        .stream_pm = snd_hda_gen_stream_pm,
         .reboot_notify = stac_shutup,
 };
 
@@ -4697,7 +4696,8 @@ static int patch_stac92hd71bxx(struct hda_codec *codec)
                 return err;
 
         spec = codec->spec;
-        codec->power_save_node = 1;
+        /* disabled power_save_node since it causes noises on a Dell machine */
+        /* codec->power_save_node = 1; */
         spec->linear_tone_beep = 0;
         spec->gen.own_eapd_ctl = 1;
         spec->gen.power_down_unused = 1;
diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c
index d51703e30523..0a4ad5feb82e 100644
--- a/sound/pci/hda/thinkpad_helper.c
+++ b/sound/pci/hda/thinkpad_helper.c
@@ -72,7 +72,6 @@ static void hda_fixup_thinkpad_acpi(struct hda_codec *codec,
                 if (led_set_func(TPACPI_LED_MUTE, false) >= 0) {
                         old_vmaster_hook = spec->vmaster_mute.hook;
                         spec->vmaster_mute.hook = update_tpacpi_mute_led;
-                        spec->vmaster_mute_enum = 1;
                         removefunc = false;
                 }
                 if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0) {
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 46facfc9aec1..29175346cc4f 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1118,6 +1118,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip)
         case USB_ID(0x045E, 0x075D): /* MS Lifecam Cinema  */
         case USB_ID(0x045E, 0x076D): /* MS Lifecam HD-5000 */
         case USB_ID(0x045E, 0x0772): /* MS Lifecam Studio */
+        case USB_ID(0x045E, 0x0779): /* MS Lifecam HD-3000 */
         case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */
                 return true;
         }
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index bac98ca3d4ca..323b65edfc97 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -52,6 +52,7 @@ unsigned int skip_c0;
 unsigned int skip_c1;
 unsigned int do_nhm_cstates;
 unsigned int do_snb_cstates;
+unsigned int do_knl_cstates;
 unsigned int do_pc2;
 unsigned int do_pc3;
 unsigned int do_pc6;
@@ -91,6 +92,7 @@ unsigned int do_gfx_perf_limit_reasons;
 unsigned int do_ring_perf_limit_reasons;
 unsigned int crystal_hz;
 unsigned long long tsc_hz;
+int base_cpu;
 
 #define RAPL_PKG                (1 << 0)
                                         /* 0x610 MSR_PKG_POWER_LIMIT */
@@ -316,7 +318,7 @@ void print_header(void)
 
         if (do_nhm_cstates)
                 outp += sprintf(outp, "  CPU%%c1");
-        if (do_nhm_cstates && !do_slm_cstates)
+        if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
                 outp += sprintf(outp, "  CPU%%c3");
         if (do_nhm_cstates)
                 outp += sprintf(outp, "  CPU%%c6");
@@ -546,7 +548,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
         if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
                 goto done;
 
-        if (do_nhm_cstates && !do_slm_cstates)
+        if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates)
                 outp += sprintf(outp, "%8.2f", 100.0 * c->c3/t->tsc);
         if (do_nhm_cstates)
                 outp += sprintf(outp, "%8.2f", 100.0 * c->c6/t->tsc);
@@ -1018,14 +1020,17 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
         if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
                 return 0;
 
-        if (do_nhm_cstates && !do_slm_cstates) {
+        if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) {
                 if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
                         return -6;
         }
 
-        if (do_nhm_cstates) {
+        if (do_nhm_cstates && !do_knl_cstates) {
                 if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6))
                         return -7;
+        } else if (do_knl_cstates) {
+                if (get_msr(cpu, MSR_KNL_CORE_C6_RESIDENCY, &c->c6))
+                        return -7;
         }
 
         if (do_snb_cstates)
@@ -1150,7 +1155,7 @@ dump_nhm_platform_info(void)
         unsigned long long msr;
         unsigned int ratio;
 
-        get_msr(0, MSR_NHM_PLATFORM_INFO, &msr);
+        get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr);
 
         fprintf(stderr, "cpu0: MSR_NHM_PLATFORM_INFO: 0x%08llx\n", msr);
 
@@ -1162,7 +1167,7 @@ dump_nhm_platform_info(void)
         fprintf(stderr, "%d * %.0f = %.0f MHz base frequency\n",
                 ratio, bclk, ratio * bclk);
 
-        get_msr(0, MSR_IA32_POWER_CTL, &msr);
+        get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr);
         fprintf(stderr, "cpu0: MSR_IA32_POWER_CTL: 0x%08llx (C1E auto-promotion: %sabled)\n",
                 msr, msr & 0x2 ? "EN" : "DIS");
 
@@ -1175,7 +1180,7 @@ dump_hsw_turbo_ratio_limits(void)
         unsigned long long msr;
         unsigned int ratio;
 
-        get_msr(0, MSR_TURBO_RATIO_LIMIT2, &msr);
+        get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT2, &msr);
 
         fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT2: 0x%08llx\n", msr);
 
@@ -1197,7 +1202,7 @@ dump_ivt_turbo_ratio_limits(void)
         unsigned long long msr;
         unsigned int ratio;
 
-        get_msr(0, MSR_TURBO_RATIO_LIMIT1, &msr);
+        get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT1, &msr);
 
         fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", msr);
 
@@ -1249,7 +1254,7 @@ dump_nhm_turbo_ratio_limits(void)
         unsigned long long msr;
         unsigned int ratio;
 
-        get_msr(0, MSR_TURBO_RATIO_LIMIT, &msr);
+        get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT, &msr);
 
         fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n", msr);
 
@@ -1296,11 +1301,72 @@ dump_nhm_turbo_ratio_limits(void)
 }
 
 static void
+dump_knl_turbo_ratio_limits(void)
+{
+        int cores;
+        unsigned int ratio;
+        unsigned long long msr;
+        int delta_cores;
+        int delta_ratio;
+        int i;
+
+        get_msr(base_cpu, MSR_NHM_TURBO_RATIO_LIMIT, &msr);
+
+        fprintf(stderr, "cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x%08llx\n",
+        msr);
+
+        /**
+         * Turbo encoding in KNL is as follows:
+         * [7:0] -- Base value of number of active cores of bucket 1.
+         * [15:8] -- Base value of freq ratio of bucket 1.
+         * [20:16] -- +ve delta of number of active cores of bucket 2.
+         * i.e. active cores of bucket 2 =
+         * active cores of bucket 1 + delta
+         * [23:21] -- Negative delta of freq ratio of bucket 2.
+         * i.e. freq ratio of bucket 2 =
+         * freq ratio of bucket 1 - delta
+         * [28:24]-- +ve delta of number of active cores of bucket 3.
+         * [31:29]-- -ve delta of freq ratio of bucket 3.
+         * [36:32]-- +ve delta of number of active cores of bucket 4.
+         * [39:37]-- -ve delta of freq ratio of bucket 4.
+         * [44:40]-- +ve delta of number of active cores of bucket 5.
+         * [47:45]-- -ve delta of freq ratio of bucket 5.
+         * [52:48]-- +ve delta of number of active cores of bucket 6.
+         * [55:53]-- -ve delta of freq ratio of bucket 6.
+         * [60:56]-- +ve delta of number of active cores of bucket 7.
+         * [63:61]-- -ve delta of freq ratio of bucket 7.
+         */
+        cores = msr & 0xFF;
+        ratio = (msr >> 8) && 0xFF;
+        if (ratio > 0)
+                fprintf(stderr,
+                        "%d * %.0f = %.0f MHz max turbo %d active cores\n",
+                        ratio, bclk, ratio * bclk, cores);
+
+        for (i = 16; i < 64; i = i + 8) {
+                delta_cores = (msr >> i) & 0x1F;
+                delta_ratio = (msr >> (i + 5)) && 0x7;
+                if (!delta_cores || !delta_ratio)
+                        return;
+                cores = cores + delta_cores;
+                ratio = ratio - delta_ratio;
+
+                /** -ve ratios will make successive ratio calculations
+                 * negative. Hence return instead of carrying on.
+                 */
+                if (ratio > 0)
+                        fprintf(stderr,
+                                "%d * %.0f = %.0f MHz max turbo %d active cores\n",
+                                ratio, bclk, ratio * bclk, cores);
+        }
+}
+
+static void
 dump_nhm_cst_cfg(void)
 {
         unsigned long long msr;
 
-        get_msr(0, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
+        get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
 
 #define SNB_C1_AUTO_UNDEMOTE              (1UL << 27)
 #define SNB_C3_AUTO_UNDEMOTE              (1UL << 28)
@@ -1381,12 +1447,41 @@ int parse_int_file(const char *fmt, ...)
 }
 
 /*
- * cpu_is_first_sibling_in_core(cpu)
- * return 1 if given CPU is 1st HT sibling in the core
+ * get_cpu_position_in_core(cpu)
+ * return the position of the CPU among its HT siblings in the core
+ * return -1 if the sibling is not in list
  */
-int cpu_is_first_sibling_in_core(int cpu)
+int get_cpu_position_in_core(int cpu)
 {
-        return cpu == parse_int_file("/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
+        char path[64];
+        FILE *filep;
+        int this_cpu;
+        char character;
+        int i;
+
+        sprintf(path,
+                "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list",
+                cpu);
+        filep = fopen(path, "r");
+        if (filep == NULL) {
+                perror(path);
+                exit(1);
+        }
+
+        for (i = 0; i < topo.num_threads_per_core; i++) {
+                fscanf(filep, "%d", &this_cpu);
+                if (this_cpu == cpu) {
+                        fclose(filep);
+                        return i;
+                }
+
+                /* Account for no separator after last thread*/
+                if (i != (topo.num_threads_per_core - 1))
+                        fscanf(filep, "%c", &character);
+        }
+
+        fclose(filep);
+        return -1;
 }
 
 /*
@@ -1412,25 +1507,31 @@ int get_num_ht_siblings(int cpu)
 {
         char path[80];
         FILE *filep;
-        int sib1, sib2;
-        int matches;
+        int sib1;
+        int matches = 0;
         char character;
+        char str[100];
+        char *ch;
 
         sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
         filep = fopen_or_die(path, "r");
+
         /*
          * file format:
-         * if a pair of number with a character between: 2 siblings (eg. 1-2, or 1,4)
-         * otherwinse 1 sibling (self).
+         * A ',' separated or '-' separated set of numbers
+         * (eg 1-2 or 1,3,4,5)
          */
-        matches = fscanf(filep, "%d%c%d\n", &sib1, &character, &sib2);
+        fscanf(filep, "%d%c\n", &sib1, &character);
+        fseek(filep, 0, SEEK_SET);
+        fgets(str, 100, filep);
+        ch = strchr(str, character);
+        while (ch != NULL) {
+                matches++;
+                ch = strchr(ch+1, character);
+        }
 
         fclose(filep);
-
-        if (matches == 3)
-                return 2;
-        else
-                return 1;
+        return matches+1;
 }
 
 /*
@@ -1594,8 +1695,10 @@ restart:
 void check_dev_msr()
 {
         struct stat sb;
+        char pathname[32];
 
-        if (stat("/dev/cpu/0/msr", &sb))
+        sprintf(pathname, "/dev/cpu/%d/msr", base_cpu);
+        if (stat(pathname, &sb))
                 if (system("/sbin/modprobe msr > /dev/null 2>&1"))
                         err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" ");
 }
@@ -1608,6 +1711,7 @@ void check_permissions()
         cap_user_data_t cap_data = &cap_data_data;
         extern int capget(cap_user_header_t hdrp, cap_user_data_t datap);
         int do_exit = 0;
+        char pathname[32];
 
         /* check for CAP_SYS_RAWIO */
         cap_header->pid = getpid();
@@ -1622,7 +1726,8 @@ void check_permissions()
         }
 
         /* test file permissions */
-        if (euidaccess("/dev/cpu/0/msr", R_OK)) {
+        sprintf(pathname, "/dev/cpu/%d/msr", base_cpu);
+        if (euidaccess(pathname, R_OK)) {
                 do_exit++;
                 warn("/dev/cpu/0/msr open failed, try chown or chmod +r /dev/cpu/*/msr");
         }
@@ -1704,7 +1809,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
         default:
                 return 0;
         }
-        get_msr(0, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
+        get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
 
         pkg_cstate_limit = pkg_cstate_limits[msr & 0xF];
 
@@ -1753,6 +1858,21 @@ int has_hsw_turbo_ratio_limit(unsigned int family, unsigned int model)
         }
 }
 
+int has_knl_turbo_ratio_limit(unsigned int family, unsigned int model)
+{
+        if (!genuine_intel)
+                return 0;
+
+        if (family != 6)
+                return 0;
+
+        switch (model) {
+        case 0x57:      /* Knights Landing */
+                return 1;
+        default:
+                return 0;
+        }
+}
 static void
 dump_cstate_pstate_config_info(family, model)
 {
@@ -1770,6 +1890,9 @@ dump_cstate_pstate_config_info(family, model)
         if (has_nhm_turbo_ratio_limit(family, model))
                 dump_nhm_turbo_ratio_limits();
 
+        if (has_knl_turbo_ratio_limit(family, model))
+                dump_knl_turbo_ratio_limits();
+
         dump_nhm_cst_cfg();
 }
 
@@ -1801,7 +1924,7 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p)
         if (get_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS, &msr))
                 return 0;
 
-        switch (msr & 0x7) {
+        switch (msr & 0xF) {
         case ENERGY_PERF_BIAS_PERFORMANCE:
                 epb_string = "performance";
                 break;
@@ -1925,7 +2048,7 @@ double get_tdp(model)
         unsigned long long msr;
 
         if (do_rapl & RAPL_PKG_POWER_INFO)
-                if (!get_msr(0, MSR_PKG_POWER_INFO, &msr))
+                if (!get_msr(base_cpu, MSR_PKG_POWER_INFO, &msr))
                         return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units;
 
         switch (model) {
@@ -1950,6 +2073,7 @@ rapl_dram_energy_units_probe(int  model, double rapl_energy_units)
         case 0x3F:      /* HSX */
         case 0x4F:      /* BDX */
         case 0x56:      /* BDX-DE */
+        case 0x57:      /* KNL */
                 return (rapl_dram_energy_units = 15.3 / 1000000);
         default:
                 return (rapl_energy_units);
@@ -1991,6 +2115,7 @@ void rapl_probe(unsigned int family, unsigned int model)
         case 0x3F:      /* HSX */
         case 0x4F:      /* BDX */
         case 0x56:      /* BDX-DE */
+        case 0x57:      /* KNL */
                 do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
                 break;
         case 0x2D:
@@ -2006,7 +2131,7 @@ void rapl_probe(unsigned int family, unsigned int model)
         }
 
         /* units on package 0, verify later other packages match */
-        if (get_msr(0, MSR_RAPL_POWER_UNIT, &msr))
+        if (get_msr(base_cpu, MSR_RAPL_POWER_UNIT, &msr))
                 return;
 
         rapl_power_units = 1.0 / (1 << (msr & 0xF));
@@ -2331,6 +2456,17 @@ int is_slm(unsigned int family, unsigned int model)
         return 0;
 }
 
+int is_knl(unsigned int family, unsigned int model)
+{
+        if (!genuine_intel)
+                return 0;
+        switch (model) {
+        case 0x57:      /* KNL */
+                return 1;
+        }
+        return 0;
+}
+
 #define SLM_BCLK_FREQS 5
 double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0};
 
@@ -2340,7 +2476,7 @@ double slm_bclk(void)
         unsigned int i;
         double freq;
 
-        if (get_msr(0, MSR_FSB_FREQ, &msr))
+        if (get_msr(base_cpu, MSR_FSB_FREQ, &msr))
                 fprintf(stderr, "SLM BCLK: unknown\n");
 
         i = msr & 0xf;
@@ -2408,7 +2544,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
         if (!do_nhm_platform_info)
                 goto guess;
 
-        if (get_msr(0, MSR_IA32_TEMPERATURE_TARGET, &msr))
+        if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr))
                 goto guess;
 
         target_c_local = (msr >> 16) & 0xFF;
@@ -2541,6 +2677,7 @@ void process_cpuid()
         do_c8_c9_c10 = has_hsw_msrs(family, model);
         do_skl_residency = has_skl_msrs(family, model);
         do_slm_cstates = is_slm(family, model);
+        do_knl_cstates  = is_knl(family, model);
         bclk = discover_bclk(family, model);
 
         rapl_probe(family, model);
@@ -2755,13 +2892,9 @@ int initialize_counters(int cpu_id)
 
         my_package_id = get_physical_package_id(cpu_id);
         my_core_id = get_core_id(cpu_id);
-
-        if (cpu_is_first_sibling_in_core(cpu_id)) {
-                my_thread_id = 0;
+        my_thread_id = get_cpu_position_in_core(cpu_id);
+        if (!my_thread_id)
                 topo.num_cores++;
-        } else {
-                my_thread_id = 1;
-        }
 
         init_counter(EVEN_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id);
         init_counter(ODD_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id);
@@ -2785,13 +2918,24 @@ void setup_all_buffers(void)
         for_all_proc_cpus(initialize_counters);
 }
 
+void set_base_cpu(void)
+{
+        base_cpu = sched_getcpu();
+        if (base_cpu < 0)
+                err(-ENODEV, "No valid cpus found");
+
+        if (debug > 1)
+                fprintf(stderr, "base_cpu = %d\n", base_cpu);
+}
+
 void turbostat_init()
 {
+        setup_all_buffers();
+        set_base_cpu();
         check_dev_msr();
         check_permissions();
         process_cpuid();
 
-        setup_all_buffers();
 
         if (debug)
                 for_all_cpus(print_epb, ODD_COUNTERS);
@@ -2870,7 +3014,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-        fprintf(stderr, "turbostat version 4.5 2 Apr, 2015"
+        fprintf(stderr, "turbostat version 4.7 27-May, 2015"
                 " - Len Brown <lenb@kernel.org>\n");
 }