Merge 4.4-rc5 into staging-next

We want those fixes in here for testing.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

817 files changed, 9984 insertions, 5222 deletions

diff --git a/Documentation/arm/keystone/Overview.txt b/Documentation/arm/keystone/Overview.txt
index f17bc4c9dff9..400c0c270d2e 100644
--- a/Documentation/arm/keystone/Overview.txt
+++ b/Documentation/arm/keystone/Overview.txt
@@ -49,24 +49,6 @@ specified through DTS. Following are the DTS used:-
 The device tree documentation for the keystone machines are located at
         Documentation/devicetree/bindings/arm/keystone/keystone.txt
 
-Known issues & workaround
--------------------------
-
-Some of the device drivers used on keystone are re-used from that from
-DaVinci and other TI SoCs. These device drivers may use clock APIs directly.
-Some of the keystone specific drivers such as netcp uses run time power
-management API instead to enable clock. As this API has limitations on
-keystone, following workaround is needed to boot Linux.
-
-   Add 'clk_ignore_unused' to the bootargs env variable in u-boot. Otherwise
-   clock frameworks will try to disable clocks that are unused and disable
-   the hardware. This is because netcp related power domain and clock
-   domains are enabled in u-boot as run time power management API currently
-   doesn't enable clocks for netcp due to a limitation. This workaround is
-   expected to be removed in the future when proper API support becomes
-   available. Until then, this work around is needed.
-
-
 Document Author
 ---------------
 Murali Karicheri <m-karicheri2@ti.com>
diff --git a/Documentation/block/null_blk.txt b/Documentation/block/null_blk.txt
index 2f6c6ff7161d..d8880ca30af4 100644
--- a/Documentation/block/null_blk.txt
+++ b/Documentation/block/null_blk.txt
@@ -70,3 +70,6 @@ use_per_node_hctx=[0/1]: Default: 0
      parameter.
   1: The multi-queue block layer is instantiated with a hardware dispatch
      queue for each CPU node in the system.
+
+use_lightnvm=[0/1]: Default: 0
+  Register device with LightNVM. Requires blk-mq to be used.
diff --git a/Documentation/devicetree/bindings/gpio/gpio-mpc8xxx.txt b/Documentation/devicetree/bindings/gpio/gpio-mpc8xxx.txt
index f2455c50533d..120bc4971cf3 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-mpc8xxx.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-mpc8xxx.txt
@@ -11,6 +11,10 @@ Required properties:
       0 = active high
       1 = active low
 
+Optional properties:
+- little-endian : GPIO registers are used as little endian. If not
+                  present registers are used as big endian by default.
+
 Example:
 
 gpio0: gpio@1100 {
diff --git a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
index f5a8ca29aff0..aeea50c84e92 100644
--- a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
+++ b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
@@ -8,6 +8,11 @@ Required properties:
 - phy-mode: See ethernet.txt file in the same directory
 - clocks: a pointer to the reference clock for this device.
 
+Optional properties:
+- tx-csum-limit: maximum mtu supported by port that allow TX checksum.
+  Value is presented in bytes. If not used, by default 1600B is set for
+  "marvell,armada-370-neta" and 9800B for others.
+
 Example:
 
 ethernet@d0070000 {
@@ -15,6 +20,7 @@ ethernet@d0070000 {
         reg = <0xd0070000 0x2500>;
         interrupts = <8>;
         clocks = <&gate_clk 4>;
+        tx-csum-limit = <9800>
         status = "okay";
         phy = <&phy0>;
         phy-mode = "rgmii-id";
diff --git a/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt b/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt
index b38200d2583a..0dfa60d88dd3 100644
--- a/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt
@@ -1,7 +1,9 @@
 * Temperature Sensor ADC (TSADC) on rockchip SoCs
 
 Required properties:
-- compatible : "rockchip,rk3288-tsadc"
+- compatible : should be "rockchip,<name>-tsadc"
+   "rockchip,rk3288-tsadc": found on RK3288 SoCs
+   "rockchip,rk3368-tsadc": found on RK3368 SoCs
 - reg : physical base address of the controller and length of memory mapped
         region.
 - interrupts : The interrupt number to the cpu. The interrupt specifier format
diff --git a/MAINTAINERS b/MAINTAINERS
index 050d0e77a2cf..9bff63cf326e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -318,7 +318,7 @@ M:	Zhang Rui <rui.zhang@intel.com>
 L:      linux-acpi@vger.kernel.org
 W:      https://01.org/linux-acpi
 S:      Supported
-F:      drivers/acpi/video.c
+F:      drivers/acpi/acpi_video.c
 
 ACPI WMI DRIVER
 L:      platform-driver-x86@vger.kernel.org
@@ -1847,7 +1847,7 @@ S:	Supported
 F:      drivers/net/wireless/ath/ath6kl/
 
 WILOCITY WIL6210 WIRELESS DRIVER
-M:      Vladimir Kondratiev <qca_vkondrat@qca.qualcomm.com>
+M:      Maya Erez <qca_merez@qca.qualcomm.com>
 L:      linux-wireless@vger.kernel.org
 L:      wil6210@qca.qualcomm.com
 S:      Supported
@@ -1931,7 +1931,7 @@ S:	Supported
 F:      drivers/i2c/busses/i2c-at91.c
 
 ATMEL ISI DRIVER
-M:      Josh Wu <josh.wu@atmel.com>
+M:      Ludovic Desroches <ludovic.desroches@atmel.com>
 L:      linux-media@vger.kernel.org
 S:      Supported
 F:      drivers/media/platform/soc_camera/atmel-isi.c
@@ -1950,7 +1950,8 @@ S:	Supported
 F:      drivers/net/ethernet/cadence/
 
 ATMEL NAND DRIVER
-M:      Josh Wu <josh.wu@atmel.com>
+M:      Wenyou Yang <wenyou.yang@atmel.com>
+M:      Josh Wu <rainyfeeling@outlook.com>
 L:      linux-mtd@lists.infradead.org
 S:      Supported
 F:      drivers/mtd/nand/atmel_nand*
@@ -2974,6 +2975,7 @@ F:	kernel/cpuset.c
 CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)
 M:      Johannes Weiner <hannes@cmpxchg.org>
 M:      Michal Hocko <mhocko@kernel.org>
+M:      Vladimir Davydov <vdavydov@virtuozzo.com>
 L:      cgroups@vger.kernel.org
 L:      linux-mm@kvack.org
 S:      Maintained
@@ -6366,6 +6368,7 @@ F:	arch/*/include/asm/pmem.h
 LIGHTNVM PLATFORM SUPPORT
 M:      Matias Bjorling <mb@lightnvm.io>
 W:      http://github/OpenChannelSSD
+L:      linux-block@vger.kernel.org
 S:      Maintained
 F:      drivers/lightnvm/
 F:      include/linux/lightnvm.h
@@ -8284,7 +8287,7 @@ F:	include/linux/delayacct.h
 F:      kernel/delayacct.c
 
 PERFORMANCE EVENTS SUBSYSTEM
-M:      Peter Zijlstra <a.p.zijlstra@chello.nl>
+M:      Peter Zijlstra <peterz@infradead.org>
 M:      Ingo Molnar <mingo@redhat.com>
 M:      Arnaldo Carvalho de Melo <acme@kernel.org>
 L:      linux-kernel@vger.kernel.org
@@ -9425,8 +9428,10 @@ F:	include/scsi/sg.h
 
 SCSI SUBSYSTEM
 M:      "James E.J. Bottomley" <JBottomley@odin.com>
-L:      linux-scsi@vger.kernel.org
 T:      git git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi.git
+M:      "Martin K. Petersen" <martin.petersen@oracle.com>
+T:      git git://git.kernel.org/pub/scm/linux/kernel/git/mkp/scsi.git
+L:      linux-scsi@vger.kernel.org
 S:      Maintained
 F:      drivers/scsi/
 F:      include/scsi/
@@ -10901,9 +10906,9 @@ S:	Maintained
 F:      drivers/media/tuners/tua9001*
 
 TULIP NETWORK DRIVERS
-M:      Grant Grundler <grundler@parisc-linux.org>
 L:      netdev@vger.kernel.org
-S:      Maintained
+L:      linux-parisc@vger.kernel.org
+S:      Orphan
 F:      drivers/net/ethernet/dec/tulip/
 
 TUN/TAP driver
diff --git a/Makefile b/Makefile
index 2ffdf9d6f339..bc0165d0f5cf 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc5
 NAME = Blurry Fish Butt
 
 # *DOCUMENTATION*
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index c92c0ef1e9d2..f1ac9818b751 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index cfac24e0e7b6..323486d6ee83 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index 9922a118a15a..66191cd0447e 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig
index f761a7c70761..f68838e8068a 100644
--- a/arch/arc/configs/nsim_hs_defconfig
+++ b/arch/arc/configs/nsim_hs_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig
index dc6f74f41283..96bd1c20fb0b 100644
--- a/arch/arc/configs/nsim_hs_smp_defconfig
+++ b/arch/arc/configs/nsim_hs_smp_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig
index 3fef0a210c56..fcae66683ca0 100644
--- a/arch/arc/configs/nsimosci_hs_defconfig
+++ b/arch/arc/configs/nsimosci_hs_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig
index 51784837daae..b01b659168ea 100644
--- a/arch/arc/configs/nsimosci_hs_smp_defconfig
+++ b/arch/arc/configs/nsimosci_hs_smp_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig
index ef35ef3923dd..a07f20de221b 100644
--- a/arch/arc/configs/vdk_hs38_defconfig
+++ b/arch/arc/configs/vdk_hs38_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_CROSS_MEMORY_ATTACH is not set
diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig
index 634509e5e572..f36c047b33ca 100644
--- a/arch/arc/configs/vdk_hs38_smp_defconfig
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_CROSS_MEMORY_ATTACH is not set
diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h
index ad481c24070d..258b0e5ad332 100644
--- a/arch/arc/include/asm/irqflags-arcv2.h
+++ b/arch/arc/include/asm/irqflags-arcv2.h
@@ -37,6 +37,9 @@
 #define ISA_INIT_STATUS_BITS    (STATUS_IE_MASK | STATUS_AD_MASK | \
                                         (ARCV2_IRQ_DEF_PRIO << 1))
 
+/* SLEEP needs default irq priority (<=) which can interrupt the doze */
+#define ISA_SLEEP_ARG           (0x10 | ARCV2_IRQ_DEF_PRIO)
+
 #ifndef __ASSEMBLY__
 
 /*
diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h
index d8c608174617..c1d36458bfb7 100644
--- a/arch/arc/include/asm/irqflags-compact.h
+++ b/arch/arc/include/asm/irqflags-compact.h
@@ -43,6 +43,8 @@
 
 #define ISA_INIT_STATUS_BITS    STATUS_IE_MASK
 
+#define ISA_SLEEP_ARG           0x3
+
 #ifndef __ASSEMBLY__
 
 /******************************************************************
diff --git a/arch/arc/kernel/ctx_sw.c b/arch/arc/kernel/ctx_sw.c
index c14a5bea0c76..5d446df2c413 100644
--- a/arch/arc/kernel/ctx_sw.c
+++ b/arch/arc/kernel/ctx_sw.c
@@ -58,8 +58,6 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task)
                 "st      sp, [r24]       \n\t"
 #endif
 
-                "sync   \n\t"
-
                 /*
                  * setup _current_task with incoming tsk.
                  * optionally, set r25 to that as well
diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S
index e248594097e7..e6890b1f8650 100644
--- a/arch/arc/kernel/ctx_sw_asm.S
+++ b/arch/arc/kernel/ctx_sw_asm.S
@@ -44,9 +44,6 @@ __switch_to:
         * don't need to do anything special to return it
         */
 
-        /* hardware memory barrier */
-        sync
-
         /*
          * switch to new task, contained in r1
          * Temp reg r3 is required to get the ptr to store val
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 91d5a0f1f3f7..a3f750e76b68 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -44,11 +44,10 @@ SYSCALL_DEFINE0(arc_gettls)
 void arch_cpu_idle(void)
 {
         /* sleep, but enable all interrupts before committing */
-        if (is_isa_arcompact()) {
-                __asm__("sleep 0x3");
-        } else {
-                __asm__("sleep 0x10");
-        }
+        __asm__ __volatile__(
+                "sleep %0       \n"
+                :
+                :"I"(ISA_SLEEP_ARG)); /* can't be "r" has to be embedded const */
 }
 
 asmlinkage void ret_from_fork(void);
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index 93c6ea52b671..7352475451f6 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -986,42 +986,13 @@ int arc_unwind(struct unwind_frame_info *frame)
                                                             (const u8 *)(fde +
                                                                          1) +
                                                             *fde, ptrType);
-                                if (pc >= endLoc)
+                                if (pc >= endLoc) {
                                         fde = NULL;
-                        } else
-                                fde = NULL;
-                }
-                if (fde == NULL) {
-                        for (fde = table->address, tableSize = table->size;
-                             cie = NULL, tableSize > sizeof(*fde)
-                             && tableSize - sizeof(*fde) >= *fde;
-                             tableSize -= sizeof(*fde) + *fde,
-                             fde += 1 + *fde / sizeof(*fde)) {
-                                cie = cie_for_fde(fde, table);
-                                if (cie == &bad_cie) {
                                         cie = NULL;
-                                        break;
                                 }
-                                if (cie == NULL
-                                    || cie == &not_fde
-                                    || (ptrType = fde_pointer_type(cie)) < 0)
-                                        continue;
-                                ptr = (const u8 *)(fde + 2);
-                                startLoc = read_pointer(&ptr,
-                                                        (const u8 *)(fde + 1) +
-                                                        *fde, ptrType);
-                                if (!startLoc)
-                                        continue;
-                                if (!(ptrType & DW_EH_PE_indirect))
-                                        ptrType &=
-                                            DW_EH_PE_FORM | DW_EH_PE_signed;
-                                endLoc =
-                                    startLoc + read_pointer(&ptr,
-                                                            (const u8 *)(fde +
-                                                                         1) +
-                                                            *fde, ptrType);
-                                if (pc >= startLoc && pc < endLoc)
-                                        break;
+                        } else {
+                                fde = NULL;
+                                cie = NULL;
                         }
                 }
         }
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index 0ee739846847..daf2bf52b984 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -619,10 +619,10 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned,
 
                 int dirty = !test_and_set_bit(PG_dc_clean, &page->flags);
                 if (dirty) {
-                        /* wback + inv dcache lines */
+                        /* wback + inv dcache lines (K-mapping) */
                         __flush_dcache_page(paddr, paddr);
 
-                        /* invalidate any existing icache lines */
+                        /* invalidate any existing icache lines (U-mapping) */
                         if (vma->vm_flags & VM_EXEC)
                                 __inv_icache_page(paddr, vaddr);
                 }
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 0365cbbc9179..34e1569a11ee 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -76,6 +76,8 @@ config ARM
         select IRQ_FORCED_THREADING
         select MODULES_USE_ELF_REL
         select NO_BOOTMEM
+        select OF_EARLY_FLATTREE if OF
+        select OF_RESERVED_MEM if OF
         select OLD_SIGACTION
         select OLD_SIGSUSPEND3
         select PERF_USE_VMALLOC
@@ -1822,8 +1824,6 @@ config USE_OF
         bool "Flattened Device Tree support"
         select IRQ_DOMAIN
         select OF
-        select OF_EARLY_FLATTREE
-        select OF_RESERVED_MEM
         help
           Include support for flattened device tree machine descriptions.
 
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index d83ff9c9701e..de8791a4d131 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -74,7 +74,7 @@
                 reg = <0x48240200 0x100>;
                 interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
                 interrupt-parent = <&gic>;
-                clocks = <&dpll_mpu_m2_ck>;
+                clocks = <&mpu_periphclk>;
         };
 
         local_timer: timer@48240600 {
@@ -82,7 +82,7 @@
                 reg = <0x48240600 0x100>;
                 interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>;
                 interrupt-parent = <&gic>;
-                clocks = <&dpll_mpu_m2_ck>;
+                clocks = <&mpu_periphclk>;
         };
 
         l2-cache-controller@48242000 {
diff --git a/arch/arm/boot/dts/am43xx-clocks.dtsi b/arch/arm/boot/dts/am43xx-clocks.dtsi
index cc88728d751d..a38af2bfbfcf 100644
--- a/arch/arm/boot/dts/am43xx-clocks.dtsi
+++ b/arch/arm/boot/dts/am43xx-clocks.dtsi
@@ -259,6 +259,14 @@
                 ti,invert-autoidle-bit;
         };
 
+        mpu_periphclk: mpu_periphclk {
+                #clock-cells = <0>;
+                compatible = "fixed-factor-clock";
+                clocks = <&dpll_mpu_m2_ck>;
+                clock-mult = <1>;
+                clock-div = <2>;
+        };
+
         dpll_ddr_ck: dpll_ddr_ck {
                 #clock-cells = <0>;
                 compatible = "ti,am3-dpll-clock";
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts
index d9ba6b879fc1..00352e761b8c 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15.dts
+++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts
@@ -604,6 +604,7 @@
                 reg = <0x6f>;
                 interrupts-extended = <&crossbar_mpu GIC_SPI 2 IRQ_TYPE_EDGE_RISING>,
                                       <&dra7_pmx_core 0x424>;
+                interrupt-names = "irq", "wakeup";
 
                 pinctrl-names = "default";
                 pinctrl-0 = <&mcp79410_pins_default>;
diff --git a/arch/arm/boot/dts/animeo_ip.dts b/arch/arm/boot/dts/animeo_ip.dts
index 4e0ad3b82796..0962f2fa3f6e 100644
--- a/arch/arm/boot/dts/animeo_ip.dts
+++ b/arch/arm/boot/dts/animeo_ip.dts
@@ -155,21 +155,21 @@
                         label = "keyswitch_in";
                         gpios = <&pioB 1 GPIO_ACTIVE_HIGH>;
                         linux,code = <28>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
 
                 error_in {
                         label = "error_in";
                         gpios = <&pioB 2 GPIO_ACTIVE_HIGH>;
                         linux,code = <29>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
 
                 btn {
                         label = "btn";
                         gpios = <&pioC 23 GPIO_ACTIVE_HIGH>;
                         linux,code = <31>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 };
diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index c6a0e9d7f1a9..e8b7f6726772 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -498,6 +498,7 @@
                                 reg = <0x70000 0x4000>;
                                 interrupts-extended = <&mpic 8>;
                                 clocks = <&gateclk 4>;
+                                tx-csum-limit = <9800>;
                                 status = "disabled";
                         };
 
diff --git a/arch/arm/boot/dts/at91-foxg20.dts b/arch/arm/boot/dts/at91-foxg20.dts
index f89598af4c2b..6bf873e7d96c 100644
--- a/arch/arm/boot/dts/at91-foxg20.dts
+++ b/arch/arm/boot/dts/at91-foxg20.dts
@@ -159,7 +159,7 @@
                         label = "Button";
                         gpios = <&pioC 4 GPIO_ACTIVE_LOW>;
                         linux,code = <0x103>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 };
diff --git a/arch/arm/boot/dts/at91-kizbox.dts b/arch/arm/boot/dts/at91-kizbox.dts
index bf18ece0c027..229e989eb60d 100644
--- a/arch/arm/boot/dts/at91-kizbox.dts
+++ b/arch/arm/boot/dts/at91-kizbox.dts
@@ -24,15 +24,6 @@
         };
 
         clocks {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                ranges;
-
-                main_clock: clock@0 {
-                        compatible = "atmel,osc", "fixed-clock";
-                        clock-frequency = <18432000>;
-                };
-
                 main_xtal {
                         clock-frequency = <18432000>;
                 };
@@ -94,14 +85,14 @@
                         label = "PB_RST";
                         gpios = <&pioB 30 GPIO_ACTIVE_HIGH>;
                         linux,code = <0x100>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
 
                 user {
                         label = "PB_USER";
                         gpios = <&pioB 31 GPIO_ACTIVE_HIGH>;
                         linux,code = <0x101>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 
diff --git a/arch/arm/boot/dts/at91-kizbox2.dts b/arch/arm/boot/dts/at91-kizbox2.dts
index f0b1563cb3f1..50a14568f094 100644
--- a/arch/arm/boot/dts/at91-kizbox2.dts
+++ b/arch/arm/boot/dts/at91-kizbox2.dts
@@ -171,21 +171,21 @@
                         label = "PB_PROG";
                         gpios = <&pioE 27 GPIO_ACTIVE_LOW>;
                         linux,code = <0x102>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
 
                 reset {
                         label = "PB_RST";
                         gpios = <&pioE 29 GPIO_ACTIVE_LOW>;
                         linux,code = <0x100>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
 
                 user {
                         label = "PB_USER";
                         gpios = <&pioE 31 GPIO_ACTIVE_HIGH>;
                         linux,code = <0x101>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 
diff --git a/arch/arm/boot/dts/at91-kizboxmini.dts b/arch/arm/boot/dts/at91-kizboxmini.dts
index 9f72b4932634..9682d105d4d8 100644
--- a/arch/arm/boot/dts/at91-kizboxmini.dts
+++ b/arch/arm/boot/dts/at91-kizboxmini.dts
@@ -98,14 +98,14 @@
                         label = "PB_PROG";
                         gpios = <&pioC 17 GPIO_ACTIVE_LOW>;
                         linux,code = <0x102>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
 
                 reset {
                         label = "PB_RST";
                         gpios = <&pioC 16 GPIO_ACTIVE_LOW>;
                         linux,code = <0x100>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 
diff --git a/arch/arm/boot/dts/at91-qil_a9260.dts b/arch/arm/boot/dts/at91-qil_a9260.dts
index a9aef53ab764..4f2eebf4a560 100644
--- a/arch/arm/boot/dts/at91-qil_a9260.dts
+++ b/arch/arm/boot/dts/at91-qil_a9260.dts
@@ -183,7 +183,7 @@
                         label = "user_pb";
                         gpios = <&pioB 10 GPIO_ACTIVE_LOW>;
                         linux,code = <28>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 
diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
index e07c2b206beb..e74df327cdd3 100644
--- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
@@ -45,6 +45,7 @@
 /dts-v1/;
 #include "sama5d2.dtsi"
 #include "sama5d2-pinfunc.h"
+#include <dt-bindings/mfd/atmel-flexcom.h>
 
 / {
         model = "Atmel SAMA5D2 Xplained";
@@ -59,15 +60,6 @@
         };
 
         clocks {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                ranges;
-
-                main_clock: clock@0 {
-                        compatible = "atmel,osc", "fixed-clock";
-                        clock-frequency = <12000000>;
-                };
-
                 slow_xtal {
                         clock-frequency = <32768>;
                 };
@@ -91,6 +83,22 @@
                         status = "okay";
                 };
 
+                sdmmc0: sdio-host@a0000000 {
+                        bus-width = <8>;
+                        pinctrl-names = "default";
+                        pinctrl-0 = <&pinctrl_sdmmc0_default>;
+                        non-removable;
+                        mmc-ddr-1_8v;
+                        status = "okay";
+                };
+
+                sdmmc1: sdio-host@b0000000 {
+                        bus-width = <4>;
+                        pinctrl-names = "default";
+                        pinctrl-0 = <&pinctrl_sdmmc1_default>;
+                        status = "okay"; /* conflict with qspi0 */
+                };
+
                 apb {
                         spi0: spi@f8000000 {
                                 pinctrl-names = "default";
@@ -176,17 +184,55 @@
                                                         regulator-name = "VDD_SDHC_1V8";
                                                         regulator-min-microvolt = <1800000>;
                                                         regulator-max-microvolt = <1800000>;
+                                                        regulator-always-on;
                                                 };
                                         };
                                 };
                         };
 
+                        flx0: flexcom@f8034000 {
+                                atmel,flexcom-mode = <ATMEL_FLEXCOM_MODE_USART>;
+                                status = "disabled"; /* conflict with ISC_D2 & ISC_D3 data pins */
+
+                                uart5: serial@200 {
+                                        compatible = "atmel,at91sam9260-usart";
+                                        reg = <0x200 0x200>;
+                                        interrupts = <19 IRQ_TYPE_LEVEL_HIGH 7>;
+                                        clocks = <&flx0_clk>;
+                                        clock-names = "usart";
+                                        pinctrl-names = "default";
+                                        pinctrl-0 = <&pinctrl_flx0_default>;
+                                        atmel,fifo-size = <32>;
+                                        status = "okay";
+                                };
+                        };
+
                         uart3: serial@fc008000 {
                                 pinctrl-names = "default";
                                 pinctrl-0 = <&pinctrl_uart3_default>;
                                 status = "okay";
                         };
 
+                        flx4: flexcom@fc018000 {
+                                atmel,flexcom-mode = <ATMEL_FLEXCOM_MODE_TWI>;
+                                status = "okay";
+
+                                i2c2: i2c@600 {
+                                        compatible = "atmel,sama5d2-i2c";
+                                        reg = <0x600 0x200>;
+                                        interrupts = <23 IRQ_TYPE_LEVEL_HIGH 7>;
+                                        dmas = <0>, <0>;
+                                        dma-names = "tx", "rx";
+                                        #address-cells = <1>;
+                                        #size-cells = <0>;
+                                        clocks = <&flx4_clk>;
+                                        pinctrl-names = "default";
+                                        pinctrl-0 = <&pinctrl_flx4_default>;
+                                        atmel,fifo-size = <16>;
+                                        status = "okay";
+                                };
+                        };
+
                         i2c1: i2c@fc028000 {
                                 dmas = <0>, <0>;
                                 pinctrl-names = "default";
@@ -201,6 +247,18 @@
                         };
 
                         pinctrl@fc038000 {
+                                pinctrl_flx0_default: flx0_default {
+                                        pinmux = <PIN_PB28__FLEXCOM0_IO0>,
+                                                 <PIN_PB29__FLEXCOM0_IO1>;
+                                        bias-disable;
+                                };
+
+                                pinctrl_flx4_default: flx4_default {
+                                        pinmux = <PIN_PD12__FLEXCOM4_IO0>,
+                                                 <PIN_PD13__FLEXCOM4_IO1>;
+                                        bias-disable;
+                                };
+
                                 pinctrl_i2c0_default: i2c0_default {
                                         pinmux = <PIN_PD21__TWD0>,
                                                  <PIN_PD22__TWCK0>;
@@ -227,6 +285,46 @@
                                         bias-disable;
                                 };
 
+                                pinctrl_sdmmc0_default: sdmmc0_default {
+                                        cmd_data {
+                                                pinmux = <PIN_PA1__SDMMC0_CMD>,
+                                                         <PIN_PA2__SDMMC0_DAT0>,
+                                                         <PIN_PA3__SDMMC0_DAT1>,
+                                                         <PIN_PA4__SDMMC0_DAT2>,
+                                                         <PIN_PA5__SDMMC0_DAT3>,
+                                                         <PIN_PA6__SDMMC0_DAT4>,
+                                                         <PIN_PA7__SDMMC0_DAT5>,
+                                                         <PIN_PA8__SDMMC0_DAT6>,
+                                                         <PIN_PA9__SDMMC0_DAT7>;
+                                                bias-pull-up;
+                                        };
+
+                                        ck_cd_rstn_vddsel {
+                                                pinmux = <PIN_PA0__SDMMC0_CK>,
+                                                         <PIN_PA10__SDMMC0_RSTN>,
+                                                         <PIN_PA11__SDMMC0_VDDSEL>,
+                                                         <PIN_PA13__SDMMC0_CD>;
+                                                bias-disable;
+                                        };
+                                };
+
+                                pinctrl_sdmmc1_default: sdmmc1_default {
+                                        cmd_data {
+                                                pinmux = <PIN_PA28__SDMMC1_CMD>,
+                                                         <PIN_PA18__SDMMC1_DAT0>,
+                                                         <PIN_PA19__SDMMC1_DAT1>,
+                                                         <PIN_PA20__SDMMC1_DAT2>,
+                                                         <PIN_PA21__SDMMC1_DAT3>;
+                                                bias-pull-up;
+                                        };
+
+                                        conf-ck_cd {
+                                                pinmux = <PIN_PA22__SDMMC1_CK>,
+                                                         <PIN_PA30__SDMMC1_CD>;
+                                                bias-disable;
+                                        };
+                                };
+
                                 pinctrl_spi0_default: spi0_default {
                                         pinmux = <PIN_PA14__SPI0_SPCK>,
                                                  <PIN_PA15__SPI0_MOSI>,
diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
index 8488ac53d22d..ff888d21c786 100644
--- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
@@ -315,7 +315,7 @@
                         label = "PB_USER";
                         gpios = <&pioE 29 GPIO_ACTIVE_LOW>;
                         linux,code = <0x104>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 
diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
index 45371a1b61b3..131614f28e75 100644
--- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
@@ -50,7 +50,6 @@
         compatible = "atmel,sama5d4-xplained", "atmel,sama5d4", "atmel,sama5";
 
         chosen {
-                bootargs = "ignore_loglevel earlyprintk";
                 stdout-path = "serial0:115200n8";
         };
 
@@ -59,15 +58,6 @@
         };
 
         clocks {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                ranges;
-
-                main_clock: clock@0 {
-                        compatible = "atmel,osc", "fixed-clock";
-                        clock-frequency = <12000000>;
-                };
-
                 slow_xtal {
                         clock-frequency = <32768>;
                 };
@@ -235,7 +225,7 @@
                         label = "pb_user1";
                         gpios = <&pioE 8 GPIO_ACTIVE_HIGH>;
                         linux,code = <0x100>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 
diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts
index 6d272c0125e3..2d4a33100af6 100644
--- a/arch/arm/boot/dts/at91-sama5d4ek.dts
+++ b/arch/arm/boot/dts/at91-sama5d4ek.dts
@@ -50,7 +50,6 @@
         compatible = "atmel,sama5d4ek", "atmel,sama5d4", "atmel,sama5";
 
         chosen {
-                bootargs = "ignore_loglevel earlyprintk";
                 stdout-path = "serial0:115200n8";
         };
 
@@ -59,15 +58,6 @@
         };
 
         clocks {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                ranges;
-
-                main_clock: clock@0 {
-                        compatible = "atmel,osc", "fixed-clock";
-                        clock-frequency = <12000000>;
-                };
-
                 slow_xtal {
                         clock-frequency = <32768>;
                 };
@@ -304,7 +294,7 @@
                         label = "pb_user1";
                         gpios = <&pioE 13 GPIO_ACTIVE_HIGH>;
                         linux,code = <0x100>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 
diff --git a/arch/arm/boot/dts/at91rm9200ek.dts b/arch/arm/boot/dts/at91rm9200ek.dts
index 8dab4b75ca97..f90e1c2d3caa 100644
--- a/arch/arm/boot/dts/at91rm9200ek.dts
+++ b/arch/arm/boot/dts/at91rm9200ek.dts
@@ -21,15 +21,6 @@
         };
 
         clocks {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                ranges;
-
-                main_clock: clock@0 {
-                        compatible = "atmel,osc", "fixed-clock";
-                        clock-frequency = <18432000>;
-                };
-
                 slow_xtal {
                         clock-frequency = <32768>;
                 };
diff --git a/arch/arm/boot/dts/at91sam9261ek.dts b/arch/arm/boot/dts/at91sam9261ek.dts
index 2e92ac020f23..55bd51f07fa6 100644
--- a/arch/arm/boot/dts/at91sam9261ek.dts
+++ b/arch/arm/boot/dts/at91sam9261ek.dts
@@ -22,15 +22,6 @@
         };
 
         clocks {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                ranges;
-
-                main_clock: clock@0 {
-                        compatible = "atmel,osc", "fixed-clock";
-                        clock-frequency = <18432000>;
-                };
-
                 slow_xtal {
                         clock-frequency = <32768>;
                 };
@@ -149,7 +140,7 @@
                                         ti,debounce-tol = /bits/ 16 <65535>;
                                         ti,debounce-max = /bits/ 16 <1>;
 
-                                        linux,wakeup;
+                                        wakeup-source;
                                 };
                         };
 
@@ -193,28 +184,28 @@
                         label = "button_0";
                         gpios = <&pioA 27 GPIO_ACTIVE_LOW>;
                         linux,code = <256>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
 
                 button_1 {
                         label = "button_1";
                         gpios = <&pioA 26 GPIO_ACTIVE_LOW>;
                         linux,code = <257>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
 
                 button_2 {
                         label = "button_2";
                         gpios = <&pioA 25 GPIO_ACTIVE_LOW>;
                         linux,code = <258>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
 
                 button_3 {
                         label = "button_3";
                         gpios = <&pioA 24 GPIO_ACTIVE_LOW>;
                         linux,code = <259>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 };
diff --git a/arch/arm/boot/dts/at91sam9263ek.dts b/arch/arm/boot/dts/at91sam9263ek.dts
index 23381276ffb8..59df9d73d276 100644
--- a/arch/arm/boot/dts/at91sam9263ek.dts
+++ b/arch/arm/boot/dts/at91sam9263ek.dts
@@ -22,15 +22,6 @@
         };
 
         clocks {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                ranges;
-
-                main_clock: clock@0 {
-                        compatible = "atmel,osc", "fixed-clock";
-                        clock-frequency = <16367660>;
-                };
-
                 slow_xtal {
                         clock-frequency = <32768>;
                 };
@@ -213,14 +204,14 @@
                         label = "left_click";
                         gpios = <&pioC 5 GPIO_ACTIVE_LOW>;
                         linux,code = <272>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
 
                 right_click {
                         label = "right_click";
                         gpios = <&pioC 4 GPIO_ACTIVE_LOW>;
                         linux,code = <273>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 
diff --git a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
index 57548a2c5a1e..e9cc99b6353a 100644
--- a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
+++ b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
@@ -19,15 +19,6 @@
         };
 
         clocks {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                ranges;
-
-                main_clock: clock@0 {
-                        compatible = "atmel,osc", "fixed-clock";
-                        clock-frequency = <18432000>;
-                };
-
                 slow_xtal {
                         clock-frequency = <32768>;
                 };
@@ -206,14 +197,14 @@
                         label = "Button 3";
                         gpios = <&pioA 30 GPIO_ACTIVE_LOW>;
                         linux,code = <0x103>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
 
                 btn4 {
                         label = "Button 4";
                         gpios = <&pioA 31 GPIO_ACTIVE_LOW>;
                         linux,code = <0x104>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 
diff --git a/arch/arm/boot/dts/at91sam9m10g45ek.dts b/arch/arm/boot/dts/at91sam9m10g45ek.dts
index 9d16ef8453c5..2400c99134f7 100644
--- a/arch/arm/boot/dts/at91sam9m10g45ek.dts
+++ b/arch/arm/boot/dts/at91sam9m10g45ek.dts
@@ -24,15 +24,6 @@
         };
 
         clocks {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                ranges;
-
-                main_clock: clock@0 {
-                        compatible = "atmel,osc", "fixed-clock";
-                        clock-frequency = <12000000>;
-                };
-
                 slow_xtal {
                       clock-frequency = <32768>;
                 };
@@ -323,14 +314,14 @@
                         label = "left_click";
                         gpios = <&pioB 6 GPIO_ACTIVE_LOW>;
                         linux,code = <272>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
 
                 right_click {
                         label = "right_click";
                         gpios = <&pioB 7 GPIO_ACTIVE_LOW>;
                         linux,code = <273>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
 
                 left {
diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts
index acf3451a332d..ca4ddf86817a 100644
--- a/arch/arm/boot/dts/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/at91sam9n12ek.dts
@@ -23,15 +23,6 @@
         };
 
         clocks {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                ranges;
-
-                main_clock: clock@0 {
-                        compatible = "atmel,osc", "fixed-clock";
-                        clock-frequency = <16000000>;
-                };
-
                 slow_xtal {
                         clock-frequency = <32768>;
                 };
@@ -219,7 +210,7 @@
                         label = "Enter";
                         gpios = <&pioB 3 GPIO_ACTIVE_LOW>;
                         linux,code = <28>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 
diff --git a/arch/arm/boot/dts/at91sam9rlek.dts b/arch/arm/boot/dts/at91sam9rlek.dts
index 558c9f220bed..f10566f759cd 100644
--- a/arch/arm/boot/dts/at91sam9rlek.dts
+++ b/arch/arm/boot/dts/at91sam9rlek.dts
@@ -22,15 +22,6 @@
         };
 
         clocks {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                ranges;
-
-                main_clock: clock {
-                        compatible = "atmel,osc", "fixed-clock";
-                        clock-frequency = <12000000>;
-                };
-
                 slow_xtal {
                         clock-frequency = <32768>;
                 };
@@ -225,14 +216,14 @@
                         label = "right_click";
                         gpios = <&pioB 0 GPIO_ACTIVE_LOW>;
                         linux,code = <273>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
 
                 left_click {
                         label = "left_click";
                         gpios = <&pioB 1 GPIO_ACTIVE_LOW>;
                         linux,code = <272>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 
diff --git a/arch/arm/boot/dts/at91sam9x5cm.dtsi b/arch/arm/boot/dts/at91sam9x5cm.dtsi
index 26112ebd15fc..b098ad8cd93a 100644
--- a/arch/arm/boot/dts/at91sam9x5cm.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5cm.dtsi
@@ -13,17 +13,6 @@
         };
 
         clocks {
-                #address-cells = <1>;
-                #size-cells = <1>;
-                ranges;
-
-                main_clock: clock@0 {
-                        compatible = "atmel,osc", "fixed-clock";
-                        clock-frequency = <12000000>;
-                };
-        };
-
-        clocks {
                 slow_xtal {
                         clock-frequency = <32768>;
                 };
diff --git a/arch/arm/boot/dts/berlin2q.dtsi b/arch/arm/boot/dts/berlin2q.dtsi
index 8ea177f375dd..fb1da99996ea 100644
--- a/arch/arm/boot/dts/berlin2q.dtsi
+++ b/arch/arm/boot/dts/berlin2q.dtsi
@@ -118,7 +118,8 @@
                 sdhci0: sdhci@ab0000 {
                         compatible = "mrvl,pxav3-mmc";
                         reg = <0xab0000 0x200>;
-                        clocks = <&chip_clk CLKID_SDIO1XIN>;
+                        clocks = <&chip_clk CLKID_SDIO1XIN>, <&chip_clk CLKID_SDIO>;
+                        clock-names = "io", "core";
                         interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
                         status = "disabled";
                 };
@@ -126,7 +127,8 @@
                 sdhci1: sdhci@ab0800 {
                         compatible = "mrvl,pxav3-mmc";
                         reg = <0xab0800 0x200>;
-                        clocks = <&chip_clk CLKID_SDIO1XIN>;
+                        clocks = <&chip_clk CLKID_SDIO1XIN>, <&chip_clk CLKID_SDIO>;
+                        clock-names = "io", "core";
                         interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
                         status = "disabled";
                 };
@@ -135,7 +137,7 @@
                         compatible = "mrvl,pxav3-mmc";
                         reg = <0xab1000 0x200>;
                         interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
-                        clocks = <&chip_clk CLKID_NFC_ECC>, <&chip_clk CLKID_NFC>;
+                        clocks = <&chip_clk CLKID_NFC_ECC>, <&chip_clk CLKID_SDIO>;
                         clock-names = "io", "core";
                         status = "disabled";
                 };
diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi
index 3c99cfa1a876..eee636de4cd8 100644
--- a/arch/arm/boot/dts/dm816x.dtsi
+++ b/arch/arm/boot/dts/dm816x.dtsi
@@ -218,6 +218,7 @@
                         reg = <0x480c8000 0x2000>;
                         interrupts = <77>;
                         ti,hwmods = "mailbox";
+                        #mbox-cells = <1>;
                         ti,mbox-num-users = <4>;
                         ti,mbox-num-fifos = <12>;
                         mbox_dsp: mbox_dsp {
@@ -279,8 +280,11 @@
                         ti,spi-num-cs = <4>;
                         ti,hwmods = "mcspi1";
                         dmas = <&edma 16 &edma 17
-                                &edma 18 &edma 19>;
-                        dma-names = "tx0", "rx0", "tx1", "rx1";
+                                &edma 18 &edma 19
+                                &edma 20 &edma 21
+                                &edma 22 &edma 23>;
+                        dma-names = "tx0", "rx0", "tx1", "rx1",
+                                    "tx2", "rx2", "tx3", "rx3";
                 };
 
                 mmc1: mmc@48060000 {
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index bc672fb91466..fe99231cbde5 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1459,8 +1459,8 @@
                         interrupt-names = "tx", "rx";
                         dmas = <&sdma_xbar 133>, <&sdma_xbar 132>;
                         dma-names = "tx", "rx";
-                        clocks = <&mcasp3_ahclkx_mux>;
-                        clock-names = "fck";
+                        clocks = <&mcasp3_aux_gfclk_mux>, <&mcasp3_ahclkx_mux>;
+                        clock-names = "fck", "ahclkx";
                         status = "disabled";
                 };
 
diff --git a/arch/arm/boot/dts/k2l-netcp.dtsi b/arch/arm/boot/dts/k2l-netcp.dtsi
index 01aef230773d..5acbd0dcc2ab 100644
--- a/arch/arm/boot/dts/k2l-netcp.dtsi
+++ b/arch/arm/boot/dts/k2l-netcp.dtsi
@@ -137,7 +137,7 @@ netcp: netcp@26000000 {
         /* NetCP address range */
         ranges = <0 0x26000000 0x1000000>;
 
-        clocks = <&papllclk>, <&clkcpgmac>, <&chipclk12>;
+        clocks = <&clkosr>, <&papllclk>, <&clkcpgmac>, <&chipclk12>;
         dma-coherent;
 
         ti,navigator-dmas = <&dma_gbe 0>,
diff --git a/arch/arm/boot/dts/kirkwood-ts219.dtsi b/arch/arm/boot/dts/kirkwood-ts219.dtsi
index c56ab6bbfe3c..0e46560551f4 100644
--- a/arch/arm/boot/dts/kirkwood-ts219.dtsi
+++ b/arch/arm/boot/dts/kirkwood-ts219.dtsi
@@ -40,7 +40,7 @@
                 };
                 poweroff@12100 {
                         compatible = "qnap,power-off";
-                        reg = <0x12000 0x100>;
+                        reg = <0x12100 0x100>;
                         clocks = <&gate_clk 7>;
                 };
                 spi@10600 {
diff --git a/arch/arm/boot/dts/rk3288-veyron-minnie.dts b/arch/arm/boot/dts/rk3288-veyron-minnie.dts
index 8fd8ef2c72da..85f0373df498 100644
--- a/arch/arm/boot/dts/rk3288-veyron-minnie.dts
+++ b/arch/arm/boot/dts/rk3288-veyron-minnie.dts
@@ -86,6 +86,10 @@
         };
 };
 
+&emmc {
+        /delete-property/mmc-hs200-1_8v;
+};
+
 &gpio_keys {
         pinctrl-0 = <&pwr_key_l &ap_lid_int_l &volum_down_l &volum_up_l>;
 
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index 6a79c9c526b8..04ea209f1737 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -452,8 +452,10 @@
                 clock-names = "tsadc", "apb_pclk";
                 resets = <&cru SRST_TSADC>;
                 reset-names = "tsadc-apb";
-                pinctrl-names = "default";
-                pinctrl-0 = <&otp_out>;
+                pinctrl-names = "init", "default", "sleep";
+                pinctrl-0 = <&otp_gpio>;
+                pinctrl-1 = <&otp_out>;
+                pinctrl-2 = <&otp_gpio>;
                 #thermal-sensor-cells = <1>;
                 rockchip,hw-tshut-temp = <95000>;
                 status = "disabled";
@@ -1395,6 +1397,10 @@
                 };
 
                 tsadc {
+                        otp_gpio: otp-gpio {
+                                rockchip,pins = <0 10 RK_FUNC_GPIO &pcfg_pull_none>;
+                        };
+
                         otp_out: otp-out {
                                 rockchip,pins = <0 10 RK_FUNC_1 &pcfg_pull_none>;
                         };
diff --git a/arch/arm/boot/dts/sama5d35ek.dts b/arch/arm/boot/dts/sama5d35ek.dts
index d9a9aca1ccfd..e812f5c1bf70 100644
--- a/arch/arm/boot/dts/sama5d35ek.dts
+++ b/arch/arm/boot/dts/sama5d35ek.dts
@@ -49,7 +49,7 @@
                         label = "pb_user1";
                         gpios = <&pioE 27 GPIO_ACTIVE_HIGH>;
                         linux,code = <0x100>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 };
diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi
index 15bbaf690047..2193637b9cd2 100644
--- a/arch/arm/boot/dts/sama5d4.dtsi
+++ b/arch/arm/boot/dts/sama5d4.dtsi
@@ -1300,7 +1300,7 @@
                         };
 
                         watchdog@fc068640 {
-                                compatible = "atmel,at91sam9260-wdt";
+                                compatible = "atmel,sama5d4-wdt";
                                 reg = <0xfc068640 0x10>;
                                 clocks = <&clk32k>;
                                 status = "disabled";
diff --git a/arch/arm/boot/dts/usb_a9260_common.dtsi b/arch/arm/boot/dts/usb_a9260_common.dtsi
index 12edafefd44a..9beea8976584 100644
--- a/arch/arm/boot/dts/usb_a9260_common.dtsi
+++ b/arch/arm/boot/dts/usb_a9260_common.dtsi
@@ -115,7 +115,7 @@
                         label = "user_pb";
                         gpios = <&pioB 10 GPIO_ACTIVE_LOW>;
                         linux,code = <28>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 
diff --git a/arch/arm/boot/dts/usb_a9263.dts b/arch/arm/boot/dts/usb_a9263.dts
index 68c0de36c339..8cc6edb29694 100644
--- a/arch/arm/boot/dts/usb_a9263.dts
+++ b/arch/arm/boot/dts/usb_a9263.dts
@@ -143,7 +143,7 @@
                         label = "user_pb";
                         gpios = <&pioB 10 GPIO_ACTIVE_LOW>;
                         linux,code = <28>;
-                        gpio-key,wakeup;
+                        wakeup-source;
                 };
         };
 
diff --git a/arch/arm/boot/dts/vf610-colibri.dtsi b/arch/arm/boot/dts/vf610-colibri.dtsi
index 19fe045b8334..2d7eab755210 100644
--- a/arch/arm/boot/dts/vf610-colibri.dtsi
+++ b/arch/arm/boot/dts/vf610-colibri.dtsi
@@ -18,8 +18,3 @@
                 reg = <0x80000000 0x10000000>;
         };
 };
-
-&L2 {
-        arm,data-latency = <2 1 2>;
-        arm,tag-latency = <3 2 3>;
-};
diff --git a/arch/arm/boot/dts/vf610.dtsi b/arch/arm/boot/dts/vf610.dtsi
index 5f8eb1bd782b..58bc6e448be5 100644
--- a/arch/arm/boot/dts/vf610.dtsi
+++ b/arch/arm/boot/dts/vf610.dtsi
@@ -19,7 +19,7 @@
                 reg = <0x40006000 0x1000>;
                 cache-unified;
                 cache-level = <2>;
-                arm,data-latency = <1 1 1>;
+                arm,data-latency = <3 3 3>;
                 arm,tag-latency = <2 2 2>;
         };
 };
diff --git a/arch/arm/boot/dts/vfxxx.dtsi b/arch/arm/boot/dts/vfxxx.dtsi
index 6736bae43a5b..3cd1b27f2697 100644
--- a/arch/arm/boot/dts/vfxxx.dtsi
+++ b/arch/arm/boot/dts/vfxxx.dtsi
@@ -158,7 +158,7 @@
                                 interrupts = <67 IRQ_TYPE_LEVEL_HIGH>;
                                 clocks = <&clks VF610_CLK_DSPI0>;
                                 clock-names = "dspi";
-                                spi-num-chipselects = <5>;
+                                spi-num-chipselects = <6>;
                                 status = "disabled";
                         };
 
@@ -170,7 +170,7 @@
                                 interrupts = <68 IRQ_TYPE_LEVEL_HIGH>;
                                 clocks = <&clks VF610_CLK_DSPI1>;
                                 clock-names = "dspi";
-                                spi-num-chipselects = <5>;
+                                spi-num-chipselects = <4>;
                                 status = "disabled";
                         };
 
@@ -178,8 +178,10 @@
                                 compatible = "fsl,vf610-sai";
                                 reg = <0x40031000 0x1000>;
                                 interrupts = <86 IRQ_TYPE_LEVEL_HIGH>;
-                                clocks = <&clks VF610_CLK_SAI2>;
-                                clock-names = "sai";
+                                clocks = <&clks VF610_CLK_SAI2>,
+                                        <&clks VF610_CLK_SAI2_DIV>,
+                                        <&clks 0>, <&clks 0>;
+                                clock-names = "bus", "mclk1", "mclk2", "mclk3";
                                 dma-names = "tx", "rx";
                                 dmas = <&edma0 0 21>,
                                         <&edma0 0 20>;
@@ -461,6 +463,8 @@
                                 clock-names = "adc";
                                 #io-channel-cells = <1>;
                                 status = "disabled";
+                                fsl,adck-max-frequency = <30000000>, <40000000>,
+                                                        <20000000>;
                         };
 
                         esdhc0: esdhc@400b1000 {
@@ -472,8 +476,6 @@
                                         <&clks VF610_CLK_ESDHC0>;
                                 clock-names = "ipg", "ahb", "per";
                                 status = "disabled";
-                                fsl,adck-max-frequency = <30000000>, <40000000>,
-                                                        <20000000>;
                         };
 
                         esdhc1: esdhc@400b2000 {
diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig
index 1b1e5acd76e2..e4b1be66b3f5 100644
--- a/arch/arm/configs/at91_dt_defconfig
+++ b/arch/arm/configs/at91_dt_defconfig
@@ -125,7 +125,6 @@ CONFIG_POWER_RESET=y
 # CONFIG_HWMON is not set
 CONFIG_WATCHDOG=y
 CONFIG_AT91SAM9X_WATCHDOG=y
-CONFIG_SSB=m
 CONFIG_MFD_ATMEL_HLCDC=y
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig
index a0c57ac88b27..63f7e6ce649a 100644
--- a/arch/arm/configs/sama5_defconfig
+++ b/arch/arm/configs/sama5_defconfig
@@ -129,7 +129,6 @@ CONFIG_GPIO_SYSFS=y
 CONFIG_POWER_SUPPLY=y
 CONFIG_POWER_RESET=y
 # CONFIG_HWMON is not set
-CONFIG_SSB=m
 CONFIG_MFD_ATMEL_FLEXCOM=y
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h
index 6607d976e07d..7da5503c0591 100644
--- a/arch/arm/include/asm/arch_gicv3.h
+++ b/arch/arm/include/asm/arch_gicv3.h
@@ -21,6 +21,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/io.h>
+#include <asm/barrier.h>
 
 #define __ACCESS_CP15(CRn, Op1, CRm, Op2)       p15, Op1, %0, CRn, CRm, Op2
 #define __ACCESS_CP15_64(Op1, CRm)              p15, Op1, %Q0, %R0, CRm
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index be1d07d59ee9..1bd9510de1b9 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -40,6 +40,11 @@ extern void arch_trigger_all_cpu_backtrace(bool);
 #define arch_trigger_all_cpu_backtrace(x) arch_trigger_all_cpu_backtrace(x)
 #endif
 
+static inline int nr_legacy_irqs(void)
+{
+        return NR_IRQS_LEGACY;
+}
+
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index a9c80a2ea1a7..3095df091ff8 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -28,6 +28,18 @@
 unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num);
 unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu);
 
+static inline unsigned long vcpu_get_reg(struct kvm_vcpu *vcpu,
+                                         u8 reg_num)
+{
+        return *vcpu_reg(vcpu, reg_num);
+}
+
+static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
+                                unsigned long val)
+{
+        *vcpu_reg(vcpu, reg_num) = val;
+}
+
 bool kvm_condition_valid(struct kvm_vcpu *vcpu);
 void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr);
 void kvm_inject_undefined(struct kvm_vcpu *vcpu);
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index 7a2a32a1d5a8..ede692ffa32e 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -416,6 +416,7 @@
 #define __NR_execveat                   (__NR_SYSCALL_BASE+387)
 #define __NR_userfaultfd                (__NR_SYSCALL_BASE+388)
 #define __NR_membarrier                 (__NR_SYSCALL_BASE+389)
+#define __NR_mlock2                     (__NR_SYSCALL_BASE+390)
 
 /*
  * The following SWIs are ARM private.
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index 6551d28c27e6..066f7f9ba411 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -17,11 +17,6 @@
 #include <asm/mach/pci.h>
 
 static int debug_pci;
-static resource_size_t (*align_resource)(struct pci_dev *dev,
-                  const struct resource *res,
-                  resource_size_t start,
-                  resource_size_t size,
-                  resource_size_t align) = NULL;
 
 /*
  * We can't use pci_get_device() here since we are
@@ -461,7 +456,6 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw,
                 sys->busnr   = busnr;
                 sys->swizzle = hw->swizzle;
                 sys->map_irq = hw->map_irq;
-                align_resource = hw->align_resource;
                 INIT_LIST_HEAD(&sys->resources);
 
                 if (hw->private_data)
@@ -470,6 +464,8 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw,
                 ret = hw->setup(nr, sys);
 
                 if (ret > 0) {
+                        struct pci_host_bridge *host_bridge;
+
                         ret = pcibios_init_resources(nr, sys);
                         if (ret)  {
                                 kfree(sys);
@@ -491,6 +487,9 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw,
                         busnr = sys->bus->busn_res.end + 1;
 
                         list_add(&sys->node, head);
+
+                        host_bridge = pci_find_host_bridge(sys->bus);
+                        host_bridge->align_resource = hw->align_resource;
                 } else {
                         kfree(sys);
                         if (ret < 0)
@@ -578,14 +577,18 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 {
         struct pci_dev *dev = data;
         resource_size_t start = res->start;
+        struct pci_host_bridge *host_bridge;
 
         if (res->flags & IORESOURCE_IO && start & 0x300)
                 start = (start + 0x3ff) & ~0x3ff;
 
         start = (start + align - 1) & ~(align - 1);
 
-        if (align_resource)
-                return align_resource(dev, res, start, size, align);
+        host_bridge = pci_find_host_bridge(dev->bus);
+
+        if (host_bridge->align_resource)
+                return host_bridge->align_resource(dev, res,
+                                start, size, align);
 
         return start;
 }
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index fde6c88d560c..ac368bb068d1 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -399,6 +399,7 @@
                 CALL(sys_execveat)
                 CALL(sys_userfaultfd)
                 CALL(sys_membarrier)
+                CALL(sys_mlock2)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index eab83b2435b8..e06fd299de08 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -564,17 +564,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
                         vcpu_sleep(vcpu);
 
                 /*
-                 * Disarming the background timer must be done in a
-                 * preemptible context, as this call may sleep.
-                 */
-                kvm_timer_flush_hwstate(vcpu);
-
-                /*
                  * Preparing the interrupts to be injected also
                  * involves poking the GIC, which must be done in a
                  * non-preemptible context.
                  */
                 preempt_disable();
+                kvm_timer_flush_hwstate(vcpu);
                 kvm_vgic_flush_hwstate(vcpu);
 
                 local_irq_disable();
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index 974b1c606d04..3a10c9f1d0a4 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -115,7 +115,7 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
                 trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
                                data);
                 data = vcpu_data_host_to_guest(vcpu, data, len);
-                *vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt) = data;
+                vcpu_set_reg(vcpu, vcpu->arch.mmio_decode.rt, data);
         }
 
         return 0;
@@ -186,7 +186,8 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
         rt = vcpu->arch.mmio_decode.rt;
 
         if (is_write) {
-                data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), len);
+                data = vcpu_data_guest_to_host(vcpu, vcpu_get_reg(vcpu, rt),
+                                               len);
 
                 trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data);
                 mmio_write_buf(data_buf, len, data);
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 6984342da13d..61d96a645ff3 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -98,6 +98,11 @@ static void kvm_flush_dcache_pud(pud_t pud)
         __kvm_flush_dcache_pud(pud);
 }
 
+static bool kvm_is_device_pfn(unsigned long pfn)
+{
+        return !pfn_valid(pfn);
+}
+
 /**
  * stage2_dissolve_pmd() - clear and flush huge PMD entry
  * @kvm:        pointer to kvm structure.
@@ -213,7 +218,7 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
                         kvm_tlb_flush_vmid_ipa(kvm, addr);
 
                         /* No need to invalidate the cache for device mappings */
-                        if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
+                        if (!kvm_is_device_pfn(pte_pfn(old_pte)))
                                 kvm_flush_dcache_pte(old_pte);
 
                         put_page(virt_to_page(pte));
@@ -305,8 +310,7 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
 
         pte = pte_offset_kernel(pmd, addr);
         do {
-                if (!pte_none(*pte) &&
-                    (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
+                if (!pte_none(*pte) && !kvm_is_device_pfn(pte_pfn(*pte)))
                         kvm_flush_dcache_pte(*pte);
         } while (pte++, addr += PAGE_SIZE, addr != end);
 }
@@ -1037,11 +1041,6 @@ static bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
         return kvm_vcpu_dabt_iswrite(vcpu);
 }
 
-static bool kvm_is_device_pfn(unsigned long pfn)
-{
-        return !pfn_valid(pfn);
-}
-
 /**
  * stage2_wp_ptes - write protect PMD range
  * @pmd:        pointer to pmd entry
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 0b556968a6da..a9b3b905e661 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -75,7 +75,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
         unsigned long context_id;
         phys_addr_t target_pc;
 
-        cpu_id = *vcpu_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK;
+        cpu_id = vcpu_get_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK;
         if (vcpu_mode_is_32bit(source_vcpu))
                 cpu_id &= ~((u32) 0);
 
@@ -94,8 +94,8 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
                         return PSCI_RET_INVALID_PARAMS;
         }
 
-        target_pc = *vcpu_reg(source_vcpu, 2);
-        context_id = *vcpu_reg(source_vcpu, 3);
+        target_pc = vcpu_get_reg(source_vcpu, 2);
+        context_id = vcpu_get_reg(source_vcpu, 3);
 
         kvm_reset_vcpu(vcpu);
 
@@ -114,7 +114,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
          * NOTE: We always update r0 (or x0) because for PSCI v0.1
          * the general puspose registers are undefined upon CPU_ON.
          */
-        *vcpu_reg(vcpu, 0) = context_id;
+        vcpu_set_reg(vcpu, 0, context_id);
         vcpu->arch.power_off = false;
         smp_mb();               /* Make sure the above is visible */
 
@@ -134,8 +134,8 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
         struct kvm *kvm = vcpu->kvm;
         struct kvm_vcpu *tmp;
 
-        target_affinity = *vcpu_reg(vcpu, 1);
-        lowest_affinity_level = *vcpu_reg(vcpu, 2);
+        target_affinity = vcpu_get_reg(vcpu, 1);
+        lowest_affinity_level = vcpu_get_reg(vcpu, 2);
 
         /* Determine target affinity mask */
         target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
@@ -209,7 +209,7 @@ int kvm_psci_version(struct kvm_vcpu *vcpu)
 static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 {
         int ret = 1;
-        unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
+        unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
         unsigned long val;
 
         switch (psci_fn) {
@@ -273,13 +273,13 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
                 break;
         }
 
-        *vcpu_reg(vcpu, 0) = val;
+        vcpu_set_reg(vcpu, 0, val);
         return ret;
 }
 
 static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 {
-        unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
+        unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
         unsigned long val;
 
         switch (psci_fn) {
@@ -295,7 +295,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
                 break;
         }
 
-        *vcpu_reg(vcpu, 0) = val;
+        vcpu_set_reg(vcpu, 0, val);
         return 1;
 }
 
diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index 92673006e55c..28656c2b54a0 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -4,7 +4,6 @@ menuconfig ARCH_AT91
         select ARCH_REQUIRE_GPIOLIB
         select COMMON_CLK_AT91
         select PINCTRL
-        select PINCTRL_AT91
         select SOC_BUS
 
 if ARCH_AT91
@@ -17,6 +16,7 @@ config SOC_SAMA5D2
         select HAVE_AT91_USB_CLK
         select HAVE_AT91_H32MX
         select HAVE_AT91_GENERATED_CLK
+        select PINCTRL_AT91PIO4
         help
           Select this if ou are using one of Atmel's SAMA5D2 family SoC.
 
@@ -27,6 +27,7 @@ config SOC_SAMA5D3
         select HAVE_AT91_UTMI
         select HAVE_AT91_SMD
         select HAVE_AT91_USB_CLK
+        select PINCTRL_AT91
         help
           Select this if you are using one of Atmel's SAMA5D3 family SoC.
           This support covers SAMA5D31, SAMA5D33, SAMA5D34, SAMA5D35, SAMA5D36.
@@ -40,6 +41,7 @@ config SOC_SAMA5D4
         select HAVE_AT91_SMD
         select HAVE_AT91_USB_CLK
         select HAVE_AT91_H32MX
+        select PINCTRL_AT91
         help
           Select this if you are using one of Atmel's SAMA5D4 family SoC.
 
@@ -50,6 +52,7 @@ config SOC_AT91RM9200
         select CPU_ARM920T
         select HAVE_AT91_USB_CLK
         select MIGHT_HAVE_PCI
+        select PINCTRL_AT91
         select SOC_SAM_V4_V5
         select SRAM if PM
         help
@@ -65,6 +68,7 @@ config SOC_AT91SAM9
         select HAVE_AT91_UTMI
         select HAVE_FB_ATMEL
         select MEMORY
+        select PINCTRL_AT91
         select SOC_SAM_V4_V5
         select SRAM if PM
         help
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 80e277cfcc8b..23726fb31741 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -41,8 +41,10 @@
  * implementation should be moved down into the pinctrl driver and get
  * called as part of the generic suspend/resume path.
  */
+#ifdef CONFIG_PINCTRL_AT91
 extern void at91_pinctrl_gpio_suspend(void);
 extern void at91_pinctrl_gpio_resume(void);
+#endif
 
 static struct {
         unsigned long uhp_udp_mask;
@@ -151,8 +153,9 @@ static void at91_pm_suspend(suspend_state_t state)
 
 static int at91_pm_enter(suspend_state_t state)
 {
+#ifdef CONFIG_PINCTRL_AT91
         at91_pinctrl_gpio_suspend();
-
+#endif
         switch (state) {
         /*
          * Suspend-to-RAM is like STANDBY plus slow clock mode, so
@@ -192,7 +195,9 @@ static int at91_pm_enter(suspend_state_t state)
 error:
         target_state = PM_SUSPEND_ON;
 
+#ifdef CONFIG_PINCTRL_AT91
         at91_pinctrl_gpio_resume();
+#endif
         return 0;
 }
 
diff --git a/arch/arm/mach-dove/include/mach/entry-macro.S b/arch/arm/mach-dove/include/mach/entry-macro.S
index 72d622baaad3..df1d44bdc375 100644
--- a/arch/arm/mach-dove/include/mach/entry-macro.S
+++ b/arch/arm/mach-dove/include/mach/entry-macro.S
@@ -18,13 +18,13 @@
         @ check low interrupts
         ldr     \irqstat, [\base, #IRQ_CAUSE_LOW_OFF]
         ldr     \tmp, [\base, #IRQ_MASK_LOW_OFF]
-        mov     \irqnr, #31
+        mov     \irqnr, #32
         ands    \irqstat, \irqstat, \tmp
 
         @ if no low interrupts set, check high interrupts
         ldreq   \irqstat, [\base, #IRQ_CAUSE_HIGH_OFF]
         ldreq   \tmp, [\base, #IRQ_MASK_HIGH_OFF]
-        moveq   \irqnr, #63
+        moveq   \irqnr, #64
         andeqs  \irqstat, \irqstat, \tmp
 
         @ find first active interrupt source
diff --git a/arch/arm/mach-exynos/pmu.c b/arch/arm/mach-exynos/pmu.c
index de68938ee6aa..c21e41dad19c 100644
--- a/arch/arm/mach-exynos/pmu.c
+++ b/arch/arm/mach-exynos/pmu.c
@@ -748,8 +748,12 @@ static void exynos5_powerdown_conf(enum sys_powerdown mode)
 void exynos_sys_powerdown_conf(enum sys_powerdown mode)
 {
         unsigned int i;
+        const struct exynos_pmu_data *pmu_data;
+
+        if (!pmu_context)
+                return;
 
-        const struct exynos_pmu_data *pmu_data = pmu_context->pmu_data;
+        pmu_data = pmu_context->pmu_data;
 
         if (pmu_data->powerdown_conf)
                 pmu_data->powerdown_conf(mode);
diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index 8e7976a4c3e7..cfc696b972f3 100644
--- a/arch/arm/mach-imx/gpc.c
+++ b/arch/arm/mach-imx/gpc.c
@@ -177,6 +177,7 @@ static struct irq_chip imx_gpc_chip = {
         .irq_unmask             = imx_gpc_irq_unmask,
         .irq_retrigger          = irq_chip_retrigger_hierarchy,
         .irq_set_wake           = imx_gpc_irq_set_wake,
+        .irq_set_type           = irq_chip_set_type_parent,
 #ifdef CONFIG_SMP
         .irq_set_affinity       = irq_chip_set_affinity_parent,
 #endif
diff --git a/arch/arm/mach-ixp4xx/include/mach/io.h b/arch/arm/mach-ixp4xx/include/mach/io.h
index b02439019963..7a0c13bf4269 100644
--- a/arch/arm/mach-ixp4xx/include/mach/io.h
+++ b/arch/arm/mach-ixp4xx/include/mach/io.h
@@ -143,7 +143,7 @@ static inline void __indirect_writesl(volatile void __iomem *bus_addr,
                 writel(*vaddr++, bus_addr);
 }
 
-static inline unsigned char __indirect_readb(const volatile void __iomem *p)
+static inline u8 __indirect_readb(const volatile void __iomem *p)
 {
         u32 addr = (u32)p;
         u32 n, byte_enables, data;
@@ -166,7 +166,7 @@ static inline void __indirect_readsb(const volatile void __iomem *bus_addr,
                 *vaddr++ = readb(bus_addr);
 }
 
-static inline unsigned short __indirect_readw(const volatile void __iomem *p)
+static inline u16 __indirect_readw(const volatile void __iomem *p)
 {
         u32 addr = (u32)p;
         u32 n, byte_enables, data;
@@ -189,7 +189,7 @@ static inline void __indirect_readsw(const volatile void __iomem *bus_addr,
                 *vaddr++ = readw(bus_addr);
 }
 
-static inline unsigned long __indirect_readl(const volatile void __iomem *p)
+static inline u32 __indirect_readl(const volatile void __iomem *p)
 {
         u32 addr = (__force u32)p;
         u32 data;
@@ -350,7 +350,7 @@ static inline void insl(u32 io_addr, void *p, u32 count)
                                         ((unsigned long)p <= (PIO_MASK + PIO_OFFSET)))
 
 #define ioread8(p)                      ioread8(p)
-static inline unsigned int ioread8(const void __iomem *addr)
+static inline u8 ioread8(const void __iomem *addr)
 {
         unsigned long port = (unsigned long __force)addr;
         if (__is_io_address(port))
@@ -378,7 +378,7 @@ static inline void ioread8_rep(const void __iomem *addr, void *vaddr, u32 count)
 }
 
 #define ioread16(p)                     ioread16(p)
-static inline unsigned int ioread16(const void __iomem *addr)
+static inline u16 ioread16(const void __iomem *addr)
 {
         unsigned long port = (unsigned long __force)addr;
         if (__is_io_address(port))
@@ -407,7 +407,7 @@ static inline void ioread16_rep(const void __iomem *addr, void *vaddr,
 }
 
 #define ioread32(p)                     ioread32(p)
-static inline unsigned int ioread32(const void __iomem *addr)
+static inline u32 ioread32(const void __iomem *addr)
 {
         unsigned long port = (unsigned long __force)addr;
         if (__is_io_address(port))
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 5076d3f334d2..4b4371db5799 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -121,6 +121,7 @@ config ARCH_OMAP2PLUS_TYPICAL
         select NEON if CPU_V7
         select PM
         select REGULATOR
+        select REGULATOR_FIXED_VOLTAGE
         select TWL4030_CORE if ARCH_OMAP3 || ARCH_OMAP4
         select TWL4030_POWER if ARCH_OMAP3 || ARCH_OMAP4
         select VFP
@@ -201,7 +202,6 @@ config MACH_OMAP3_PANDORA
         depends on ARCH_OMAP3
         default y
         select OMAP_PACKAGE_CBB
-        select REGULATOR_FIXED_VOLTAGE if REGULATOR
 
 config MACH_NOKIA_N810
        bool
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 5305ec7341ec..79e1f876d1c9 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -143,9 +143,9 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
                  * Ensure that CPU power state is set to ON to avoid CPU
                  * powerdomain transition on wfi
                  */
-                clkdm_wakeup(cpu1_clkdm);
-                omap_set_pwrdm_state(cpu1_pwrdm, PWRDM_POWER_ON);
-                clkdm_allow_idle(cpu1_clkdm);
+                clkdm_wakeup_nolock(cpu1_clkdm);
+                pwrdm_set_next_pwrst(cpu1_pwrdm, PWRDM_POWER_ON);
+                clkdm_allow_idle_nolock(cpu1_clkdm);
 
                 if (IS_PM44XX_ERRATUM(PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD)) {
                         while (gic_dist_disabled()) {
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index cc8a987149e2..48495ad82aba 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -890,6 +890,36 @@ static int _init_opt_clks(struct omap_hwmod *oh)
         return ret;
 }
 
+static void _enable_optional_clocks(struct omap_hwmod *oh)
+{
+        struct omap_hwmod_opt_clk *oc;
+        int i;
+
+        pr_debug("omap_hwmod: %s: enabling optional clocks\n", oh->name);
+
+        for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
+                if (oc->_clk) {
+                        pr_debug("omap_hwmod: enable %s:%s\n", oc->role,
+                                 __clk_get_name(oc->_clk));
+                        clk_enable(oc->_clk);
+                }
+}
+
+static void _disable_optional_clocks(struct omap_hwmod *oh)
+{
+        struct omap_hwmod_opt_clk *oc;
+        int i;
+
+        pr_debug("omap_hwmod: %s: disabling optional clocks\n", oh->name);
+
+        for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
+                if (oc->_clk) {
+                        pr_debug("omap_hwmod: disable %s:%s\n", oc->role,
+                                 __clk_get_name(oc->_clk));
+                        clk_disable(oc->_clk);
+                }
+}
+
 /**
  * _enable_clocks - enable hwmod main clock and interface clocks
  * @oh: struct omap_hwmod *
@@ -917,6 +947,9 @@ static int _enable_clocks(struct omap_hwmod *oh)
                         clk_enable(os->_clk);
         }
 
+        if (oh->flags & HWMOD_OPT_CLKS_NEEDED)
+                _enable_optional_clocks(oh);
+
         /* The opt clocks are controlled by the device driver. */
 
         return 0;
@@ -948,41 +981,14 @@ static int _disable_clocks(struct omap_hwmod *oh)
                         clk_disable(os->_clk);
         }
 
+        if (oh->flags & HWMOD_OPT_CLKS_NEEDED)
+                _disable_optional_clocks(oh);
+
         /* The opt clocks are controlled by the device driver. */
 
         return 0;
 }
 
-static void _enable_optional_clocks(struct omap_hwmod *oh)
-{
-        struct omap_hwmod_opt_clk *oc;
-        int i;
-
-        pr_debug("omap_hwmod: %s: enabling optional clocks\n", oh->name);
-
-        for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
-                if (oc->_clk) {
-                        pr_debug("omap_hwmod: enable %s:%s\n", oc->role,
-                                 __clk_get_name(oc->_clk));
-                        clk_enable(oc->_clk);
-                }
-}
-
-static void _disable_optional_clocks(struct omap_hwmod *oh)
-{
-        struct omap_hwmod_opt_clk *oc;
-        int i;
-
-        pr_debug("omap_hwmod: %s: disabling optional clocks\n", oh->name);
-
-        for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
-                if (oc->_clk) {
-                        pr_debug("omap_hwmod: disable %s:%s\n", oc->role,
-                                 __clk_get_name(oc->_clk));
-                        clk_disable(oc->_clk);
-                }
-}
-
 /**
  * _omap4_enable_module - enable CLKCTRL modulemode on OMAP4
  * @oh: struct omap_hwmod *
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index ca6df1a73475..76bce11c85a4 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -523,6 +523,8 @@ struct omap_hwmod_omap4_prcm {
  * HWMOD_RECONFIG_IO_CHAIN: omap_hwmod code needs to reconfigure wake-up 
  *     events by calling _reconfigure_io_chain() when a device is enabled
  *     or idled.
+ * HWMOD_OPT_CLKS_NEEDED: The optional clocks are needed for the module to
+ *     operate and they need to be handled at the same time as the main_clk.
  */
 #define HWMOD_SWSUP_SIDLE                       (1 << 0)
 #define HWMOD_SWSUP_MSTANDBY                    (1 << 1)
@@ -538,6 +540,7 @@ struct omap_hwmod_omap4_prcm {
 #define HWMOD_FORCE_MSTANDBY                    (1 << 11)
 #define HWMOD_SWSUP_SIDLE_ACT                   (1 << 12)
 #define HWMOD_RECONFIG_IO_CHAIN                 (1 << 13)
+#define HWMOD_OPT_CLKS_NEEDED                   (1 << 14)
 
 /*
  * omap_hwmod._int_flags definitions
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 51d1ecb384bd..ee4e04434a94 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -1298,6 +1298,44 @@ static struct omap_hwmod dra7xx_mcspi4_hwmod = {
 };
 
 /*
+ * 'mcasp' class
+ *
+ */
+static struct omap_hwmod_class_sysconfig dra7xx_mcasp_sysc = {
+        .sysc_offs      = 0x0004,
+        .sysc_flags     = SYSC_HAS_SIDLEMODE,
+        .idlemodes      = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
+        .sysc_fields    = &omap_hwmod_sysc_type3,
+};
+
+static struct omap_hwmod_class dra7xx_mcasp_hwmod_class = {
+        .name   = "mcasp",
+        .sysc   = &dra7xx_mcasp_sysc,
+};
+
+/* mcasp3 */
+static struct omap_hwmod_opt_clk mcasp3_opt_clks[] = {
+        { .role = "ahclkx", .clk = "mcasp3_ahclkx_mux" },
+};
+
+static struct omap_hwmod dra7xx_mcasp3_hwmod = {
+        .name           = "mcasp3",
+        .class          = &dra7xx_mcasp_hwmod_class,
+        .clkdm_name     = "l4per2_clkdm",
+        .main_clk       = "mcasp3_aux_gfclk_mux",
+        .flags          = HWMOD_OPT_CLKS_NEEDED,
+        .prcm = {
+                .omap4 = {
+                        .clkctrl_offs = DRA7XX_CM_L4PER2_MCASP3_CLKCTRL_OFFSET,
+                        .context_offs = DRA7XX_RM_L4PER2_MCASP3_CONTEXT_OFFSET,
+                        .modulemode   = MODULEMODE_SWCTRL,
+                },
+        },
+        .opt_clks       = mcasp3_opt_clks,
+        .opt_clks_cnt   = ARRAY_SIZE(mcasp3_opt_clks),
+};
+
+/*
  * 'mmc' class
  *
  */
@@ -2566,6 +2604,22 @@ static struct omap_hwmod_ocp_if dra7xx_l3_main_1__hdmi = {
         .user           = OCP_USER_MPU | OCP_USER_SDMA,
 };
 
+/* l4_per2 -> mcasp3 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per2__mcasp3 = {
+        .master         = &dra7xx_l4_per2_hwmod,
+        .slave          = &dra7xx_mcasp3_hwmod,
+        .clk            = "l4_root_clk_div",
+        .user           = OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l3_main_1 -> mcasp3 */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__mcasp3 = {
+        .master         = &dra7xx_l3_main_1_hwmod,
+        .slave          = &dra7xx_mcasp3_hwmod,
+        .clk            = "l3_iclk_div",
+        .user           = OCP_USER_MPU | OCP_USER_SDMA,
+};
+
 /* l4_per1 -> elm */
 static struct omap_hwmod_ocp_if dra7xx_l4_per1__elm = {
         .master         = &dra7xx_l4_per1_hwmod,
@@ -3308,6 +3362,8 @@ static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = {
         &dra7xx_l4_wkup__dcan1,
         &dra7xx_l4_per2__dcan2,
         &dra7xx_l4_per2__cpgmac0,
+        &dra7xx_l4_per2__mcasp3,
+        &dra7xx_l3_main_1__mcasp3,
         &dra7xx_gmac__mdio,
         &dra7xx_l4_cfg__dma_system,
         &dra7xx_l3_main_1__dss,
diff --git a/arch/arm/mach-omap2/omap_hwmod_81xx_data.c b/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
index b1288f56d509..6256052893ec 100644
--- a/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
@@ -144,6 +144,7 @@ static struct omap_hwmod dm81xx_l4_ls_hwmod = {
         .name           = "l4_ls",
         .clkdm_name     = "alwon_l3s_clkdm",
         .class          = &l4_hwmod_class,
+        .flags          = HWMOD_NO_IDLEST,
 };
 
 /*
@@ -155,6 +156,7 @@ static struct omap_hwmod dm81xx_l4_hs_hwmod = {
         .name           = "l4_hs",
         .clkdm_name     = "alwon_l3_med_clkdm",
         .class          = &l4_hwmod_class,
+        .flags          = HWMOD_NO_IDLEST,
 };
 
 /* L3 slow -> L4 ls peripheral interface running at 125MHz */
@@ -850,6 +852,7 @@ static struct omap_hwmod dm816x_emac0_hwmod = {
         .name           = "emac0",
         .clkdm_name     = "alwon_ethernet_clkdm",
         .class          = &dm816x_emac_hwmod_class,
+        .flags          = HWMOD_NO_IDLEST,
 };
 
 static struct omap_hwmod_ocp_if dm81xx_l4_hs__emac0 = {
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 1dfe34654c43..58144779dec4 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -24,9 +24,6 @@
 #include <linux/platform_data/iommu-omap.h>
 #include <linux/platform_data/wkup_m3.h>
 
-#include <asm/siginfo.h>
-#include <asm/signal.h>
-
 #include "common.h"
 #include "common-board-devices.h"
 #include "dss-common.h"
@@ -385,29 +382,6 @@ static void __init omap3_pandora_legacy_init(void)
 }
 #endif /* CONFIG_ARCH_OMAP3 */
 
-#ifdef CONFIG_SOC_TI81XX
-static int fault_fixed_up;
-
-static int t410_abort_handler(unsigned long addr, unsigned int fsr,
-                              struct pt_regs *regs)
-{
-        if ((fsr == 0x406 || fsr == 0xc06) && !fault_fixed_up) {
-                pr_warn("External imprecise Data abort at addr=%#lx, fsr=%#x ignored.\n",
-                        addr, fsr);
-                fault_fixed_up = 1;
-                return 0;
-        }
-
-        return 1;
-}
-
-static void __init t410_abort_init(void)
-{
-        hook_fault_code(16 + 6, t410_abort_handler, SIGBUS, BUS_OBJERR,
-                        "imprecise external abort");
-}
-#endif
-
 #if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5)
 static struct iommu_platform_data omap4_iommu_pdata = {
         .reset_name = "mmu_cache",
@@ -536,9 +510,6 @@ static struct pdata_init pdata_quirks[] __initdata = {
         { "openpandora,omap3-pandora-600mhz", omap3_pandora_legacy_init, },
         { "openpandora,omap3-pandora-1ghz", omap3_pandora_legacy_init, },
 #endif
-#ifdef CONFIG_SOC_TI81XX
-        { "hp,t410", t410_abort_init, },
-#endif
 #ifdef CONFIG_SOC_OMAP5
         { "ti,omap5-uevm", omap5_uevm_legacy_init, },
 #endif
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index 87b98bf92366..2dbd3785ee6f 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -301,11 +301,11 @@ static void omap3_pm_idle(void)
         if (omap_irq_pending())
                 return;
 
-        trace_cpu_idle(1, smp_processor_id());
+        trace_cpu_idle_rcuidle(1, smp_processor_id());
 
         omap_sram_idle();
 
-        trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
+        trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 }
 
 #ifdef CONFIG_SUSPEND
diff --git a/arch/arm/mach-orion5x/include/mach/entry-macro.S b/arch/arm/mach-orion5x/include/mach/entry-macro.S
index 79eb502a1e64..73919a36b577 100644
--- a/arch/arm/mach-orion5x/include/mach/entry-macro.S
+++ b/arch/arm/mach-orion5x/include/mach/entry-macro.S
@@ -21,5 +21,5 @@
         @ find cause bits that are unmasked
         ands    \irqstat, \irqstat, \tmp        @ clear Z flag if any
         clzne   \irqnr, \irqstat                @ calc irqnr
-        rsbne   \irqnr, \irqnr, #31
+        rsbne   \irqnr, \irqnr, #32
         .endm
diff --git a/arch/arm/mach-pxa/ezx.c b/arch/arm/mach-pxa/ezx.c
index 9a9c15bfcd34..7c0d5618be5e 100644
--- a/arch/arm/mach-pxa/ezx.c
+++ b/arch/arm/mach-pxa/ezx.c
@@ -889,6 +889,7 @@ static void __init e680_init(void)
 
         pxa_set_keypad_info(&e680_keypad_platform_data);
 
+        pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
         platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
         platform_add_devices(ARRAY_AND_SIZE(e680_devices));
 }
@@ -956,6 +957,7 @@ static void __init a1200_init(void)
 
         pxa_set_keypad_info(&a1200_keypad_platform_data);
 
+        pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
         platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
         platform_add_devices(ARRAY_AND_SIZE(a1200_devices));
 }
@@ -1148,6 +1150,7 @@ static void __init a910_init(void)
                 platform_device_register(&a910_camera);
         }
 
+        pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
         platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
         platform_add_devices(ARRAY_AND_SIZE(a910_devices));
 }
@@ -1215,6 +1218,7 @@ static void __init e6_init(void)
 
         pxa_set_keypad_info(&e6_keypad_platform_data);
 
+        pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
         platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
         platform_add_devices(ARRAY_AND_SIZE(e6_devices));
 }
@@ -1256,6 +1260,7 @@ static void __init e2_init(void)
 
         pxa_set_keypad_info(&e2_keypad_platform_data);
 
+        pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
         platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
         platform_add_devices(ARRAY_AND_SIZE(e2_devices));
 }
diff --git a/arch/arm/mach-pxa/palm27x.c b/arch/arm/mach-pxa/palm27x.c
index 13eba2b26e0a..8fbfb10047ec 100644
--- a/arch/arm/mach-pxa/palm27x.c
+++ b/arch/arm/mach-pxa/palm27x.c
@@ -344,7 +344,7 @@ void __init palm27x_pwm_init(int bl, int lcd)
 {
         palm_bl_power   = bl;
         palm_lcd_power  = lcd;
-        pwm_add_lookup(palm27x_pwm_lookup, ARRAY_SIZE(palm27x_pwm_lookup));
+        pwm_add_table(palm27x_pwm_lookup, ARRAY_SIZE(palm27x_pwm_lookup));
         platform_device_register(&palm27x_backlight);
 }
 #endif
diff --git a/arch/arm/mach-pxa/palmtc.c b/arch/arm/mach-pxa/palmtc.c
index aebf6de62468..0b5c3876720c 100644
--- a/arch/arm/mach-pxa/palmtc.c
+++ b/arch/arm/mach-pxa/palmtc.c
@@ -169,7 +169,7 @@ static inline void palmtc_keys_init(void) {}
 #if defined(CONFIG_BACKLIGHT_PWM) || defined(CONFIG_BACKLIGHT_PWM_MODULE)
 static struct pwm_lookup palmtc_pwm_lookup[] = {
         PWM_LOOKUP("pxa25x-pwm.1", 0, "pwm-backlight.0", NULL, PALMTC_PERIOD_NS,
-                   PWM_PERIOD_NORMAL),
+                   PWM_POLARITY_NORMAL),
 };
 
 static struct platform_pwm_backlight_data palmtc_backlight_data = {
diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
index a19460e6e7b0..b355fca6cc2e 100644
--- a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
+++ b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
@@ -20,7 +20,7 @@
 #include <plat/cpu.h>
 #include <plat/cpu-freq-core.h>
 
-static struct cpufreq_frequency_table s3c2440_plls_12[] __initdata = {
+static struct cpufreq_frequency_table s3c2440_plls_12[] = {
         { .frequency = 75000000,        .driver_data = PLLVAL(0x75, 3, 3),  },  /* FVco 600.000000 */
         { .frequency = 80000000,        .driver_data = PLLVAL(0x98, 4, 3),  },  /* FVco 640.000000 */
         { .frequency = 90000000,        .driver_data = PLLVAL(0x70, 2, 3),  },  /* FVco 720.000000 */
diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
index 1191b2905625..be9a248b5ce9 100644
--- a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
+++ b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
@@ -20,7 +20,7 @@
 #include <plat/cpu.h>
 #include <plat/cpu-freq-core.h>
 
-static struct cpufreq_frequency_table s3c2440_plls_169344[] __initdata = {
+static struct cpufreq_frequency_table s3c2440_plls_169344[] = {
         { .frequency = 78019200,        .driver_data = PLLVAL(121, 5, 3),       },      /* FVco 624.153600 */
         { .frequency = 84067200,        .driver_data = PLLVAL(131, 5, 3),       },      /* FVco 672.537600 */
         { .frequency = 90115200,        .driver_data = PLLVAL(141, 5, 3),       },      /* FVco 720.921600 */
diff --git a/arch/arm/mach-shmobile/setup-r8a7793.c b/arch/arm/mach-shmobile/setup-r8a7793.c
index 1d2825cb7a65..5fce87f7f254 100644
--- a/arch/arm/mach-shmobile/setup-r8a7793.c
+++ b/arch/arm/mach-shmobile/setup-r8a7793.c
@@ -19,7 +19,7 @@
 #include "common.h"
 #include "rcar-gen2.h"
 
-static const char *r8a7793_boards_compat_dt[] __initconst = {
+static const char * const r8a7793_boards_compat_dt[] __initconst = {
         "renesas,r8a7793",
         NULL,
 };
diff --git a/arch/arm/mach-zx/Kconfig b/arch/arm/mach-zx/Kconfig
index 7fdc5bf24f9b..446334a25cf5 100644
--- a/arch/arm/mach-zx/Kconfig
+++ b/arch/arm/mach-zx/Kconfig
@@ -13,7 +13,7 @@ config SOC_ZX296702
         select ARM_GLOBAL_TIMER
         select HAVE_ARM_SCU if SMP
         select HAVE_ARM_TWD if SMP
-        select PM_GENERIC_DOMAINS
+        select PM_GENERIC_DOMAINS if PM
         help
           Support for ZTE ZX296702 SoC which is a dual core CortexA9MP
 endif
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 9ac16a482ff1..871f21783866 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -49,7 +49,7 @@ config ARM64
         select HAVE_ARCH_AUDITSYSCALL
         select HAVE_ARCH_BITREVERSE
         select HAVE_ARCH_JUMP_LABEL
-        select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP
+        select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
         select HAVE_ARCH_KGDB
         select HAVE_ARCH_SECCOMP_FILTER
         select HAVE_ARCH_TRACEHOOK
@@ -316,6 +316,27 @@ config ARM64_ERRATUM_832075
 
           If unsure, say Y.
 
+config ARM64_ERRATUM_834220
+        bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault"
+        depends on KVM
+        default y
+        help
+          This option adds an alternative code sequence to work around ARM
+          erratum 834220 on Cortex-A57 parts up to r1p2.
+
+          Affected Cortex-A57 parts might report a Stage 2 translation
+          fault as the result of a Stage 1 fault for load crossing a
+          page boundary when there is a permission or device memory
+          alignment fault at Stage 1 and a translation fault at Stage 2.
+
+          The workaround is to verify that the Stage 1 translation
+          doesn't generate a fault before handling the Stage 2 fault.
+          Please note that this does not necessarily enable the workaround,
+          as it depends on the alternative framework, which will only patch
+          the kernel if an affected CPU is detected.
+
+          If unsure, say Y.
+
 config ARM64_ERRATUM_845719
         bool "Cortex-A53: 845719: a load might read incorrect data"
         depends on COMPAT
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
index e81cd48d6245..925552e7b4f3 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
@@ -269,6 +269,7 @@
                         clock-frequency = <0>;  /* Updated by bootloader */
                         voltage-ranges = <1800 1800 3300 3300>;
                         sdhci,auto-cmd12;
+                        little-endian;
                         bus-width = <4>;
                 };
 
@@ -277,6 +278,7 @@
                         reg = <0x0 0x2300000 0x0 0x10000>;
                         interrupts = <0 36 0x4>; /* Level high type */
                         gpio-controller;
+                        little-endian;
                         #gpio-cells = <2>;
                         interrupt-controller;
                         #interrupt-cells = <2>;
@@ -287,6 +289,7 @@
                         reg = <0x0 0x2310000 0x0 0x10000>;
                         interrupts = <0 36 0x4>; /* Level high type */
                         gpio-controller;
+                        little-endian;
                         #gpio-cells = <2>;
                         interrupt-controller;
                         #interrupt-cells = <2>;
@@ -297,6 +300,7 @@
                         reg = <0x0 0x2320000 0x0 0x10000>;
                         interrupts = <0 37 0x4>; /* Level high type */
                         gpio-controller;
+                        little-endian;
                         #gpio-cells = <2>;
                         interrupt-controller;
                         #interrupt-cells = <2>;
@@ -307,6 +311,7 @@
                         reg = <0x0 0x2330000 0x0 0x10000>;
                         interrupts = <0 37 0x4>; /* Level high type */
                         gpio-controller;
+                        little-endian;
                         #gpio-cells = <2>;
                         interrupt-controller;
                         #interrupt-cells = <2>;
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 030cdcb46c6b..2731d3b25ed2 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -77,6 +77,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/stringify.h>
+#include <asm/barrier.h>
 
 /*
  * Low-level accessors
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 11d5bb0fdd54..8f271b83f910 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -29,8 +29,9 @@
 #define ARM64_HAS_PAN                           4
 #define ARM64_HAS_LSE_ATOMICS                   5
 #define ARM64_WORKAROUND_CAVIUM_23154           6
+#define ARM64_WORKAROUND_834220                 7
 
-#define ARM64_NCAPS                             7
+#define ARM64_NCAPS                             8
 
 #ifndef __ASSEMBLY__
 
@@ -46,8 +47,12 @@ enum ftr_type {
 #define FTR_STRICT      true    /* SANITY check strict matching required */
 #define FTR_NONSTRICT   false   /* SANITY check ignored */
 
+#define FTR_SIGNED      true    /* Value should be treated as signed */
+#define FTR_UNSIGNED    false   /* Value should be treated as unsigned */
+
 struct arm64_ftr_bits {
-        bool            strict;   /* CPU Sanity check: strict matching required ? */
+        bool            sign;   /* Value is signed ? */
+        bool            strict; /* CPU Sanity check: strict matching required ? */
         enum ftr_type   type;
         u8              shift;
         u8              width;
@@ -123,6 +128,18 @@ cpuid_feature_extract_field(u64 features, int field)
         return cpuid_feature_extract_field_width(features, field, 4);
 }
 
+static inline unsigned int __attribute_const__
+cpuid_feature_extract_unsigned_field_width(u64 features, int field, int width)
+{
+        return (u64)(features << (64 - width - field)) >> (64 - width);
+}
+
+static inline unsigned int __attribute_const__
+cpuid_feature_extract_unsigned_field(u64 features, int field)
+{
+        return cpuid_feature_extract_unsigned_field_width(features, field, 4);
+}
+
 static inline u64 arm64_ftr_mask(struct arm64_ftr_bits *ftrp)
 {
         return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
@@ -130,7 +147,9 @@ static inline u64 arm64_ftr_mask(struct arm64_ftr_bits *ftrp)
 
 static inline s64 arm64_ftr_value(struct arm64_ftr_bits *ftrp, u64 val)
 {
-        return cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width);
+        return ftrp->sign ?
+                cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width) :
+                cpuid_feature_extract_unsigned_field_width(val, ftrp->shift, ftrp->width);
 }
 
 static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0)
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index e54415ec6935..9732908bfc8a 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -138,16 +138,18 @@ extern struct pmu perf_ops_bp;
 /* Determine number of BRP registers available. */
 static inline int get_num_brps(void)
 {
+        u64 dfr0 = read_system_reg(SYS_ID_AA64DFR0_EL1);
         return 1 +
-                cpuid_feature_extract_field(read_system_reg(SYS_ID_AA64DFR0_EL1),
+                cpuid_feature_extract_unsigned_field(dfr0,
                                                 ID_AA64DFR0_BRPS_SHIFT);
 }
 
 /* Determine number of WRP registers available. */
 static inline int get_num_wrps(void)
 {
+        u64 dfr0 = read_system_reg(SYS_ID_AA64DFR0_EL1);
         return 1 +
-                cpuid_feature_extract_field(read_system_reg(SYS_ID_AA64DFR0_EL1),
+                cpuid_feature_extract_unsigned_field(dfr0,
                                                 ID_AA64DFR0_WRPS_SHIFT);
 }
 
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index 23eb450b820b..8e8d30684392 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -7,4 +7,9 @@ struct pt_regs;
 
 extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
 
+static inline int nr_legacy_irqs(void)
+{
+        return 0;
+}
+
 #endif
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 17e92f05b1fe..25a40213bd9b 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -99,12 +99,22 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
         *vcpu_cpsr(vcpu) |= COMPAT_PSR_T_BIT;
 }
 
-static inline unsigned long *vcpu_reg(const struct kvm_vcpu *vcpu, u8 reg_num)
+/*
+ * vcpu_get_reg and vcpu_set_reg should always be passed a register number
+ * coming from a read of ESR_EL2. Otherwise, it may give the wrong result on
+ * AArch32 with banked registers.
+ */
+static inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu,
+                                         u8 reg_num)
 {
-        if (vcpu_mode_is_32bit(vcpu))
-                return vcpu_reg32(vcpu, reg_num);
+        return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs.regs[reg_num];
+}
 
-        return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.regs[reg_num];
+static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
+                                unsigned long val)
+{
+        if (reg_num != 31)
+                vcpu_gp_regs(vcpu)->regs.regs[reg_num] = val;
 }
 
 /* Get vcpu SPSR for current mode */
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 7e074f93f383..63f52b55defe 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -276,10 +276,14 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
          * hardware updates of the pte (ptep_set_access_flags safely changes
          * valid ptes without going through an invalid entry).
          */
-        if (IS_ENABLED(CONFIG_DEBUG_VM) && IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
-            pte_valid(*ptep)) {
-                BUG_ON(!pte_young(pte));
-                BUG_ON(pte_write(*ptep) && !pte_dirty(pte));
+        if (IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
+            pte_valid(*ptep) && pte_valid(pte)) {
+                VM_WARN_ONCE(!pte_young(pte),
+                             "%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
+                             __func__, pte_val(*ptep), pte_val(pte));
+                VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(pte),
+                             "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx",
+                             __func__, pte_val(*ptep), pte_val(pte));
         }
 
         set_pte(ptep, pte);
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 24926f2504f7..feb6b4efa641 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -75,6 +75,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
                            (1 << MIDR_VARIANT_SHIFT) | 2),
         },
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_834220
+        {
+        /* Cortex-A57 r0p0 - r1p2 */
+                .desc = "ARM erratum 834220",
+                .capability = ARM64_WORKAROUND_834220,
+                MIDR_RANGE(MIDR_CORTEX_A57, 0x00,
+                           (1 << MIDR_VARIANT_SHIFT) | 2),
+        },
+#endif
 #ifdef CONFIG_ARM64_ERRATUM_845719
         {
         /* Cortex-A53 r0p[01234] */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index c8cf89223b5a..0669c63281ea 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -44,8 +44,9 @@ unsigned int compat_elf_hwcap2 __read_mostly;
 
 DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
 
-#define ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
+#define __ARM64_FTR_BITS(SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
         {                                               \
+                .sign = SIGNED,                         \
                 .strict = STRICT,                       \
                 .type = TYPE,                           \
                 .shift = SHIFT,                         \
@@ -53,6 +54,14 @@ DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
                 .safe_val = SAFE_VAL,                   \
         }
 
+/* Define a feature with signed values */
+#define ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
+        __ARM64_FTR_BITS(FTR_SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL)
+
+/* Define a feature with unsigned value */
+#define U_ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
+        __ARM64_FTR_BITS(FTR_UNSIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL)
+
 #define ARM64_FTR_END                                   \
         {                                               \
                 .width = 0,                             \
@@ -99,7 +108,7 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
          * Differing PARange is fine as long as all peripherals and memory are mapped
          * within the minimum PARange of all CPUs
          */
-        ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_PARANGE_SHIFT, 4, 0),
+        U_ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_PARANGE_SHIFT, 4, 0),
         ARM64_FTR_END,
 };
 
@@ -115,18 +124,18 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
 };
 
 static struct arm64_ftr_bits ftr_ctr[] = {
-        ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1),        /* RAO */
+        U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1),      /* RAO */
         ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 3, 0),
-        ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0),  /* CWG */
-        ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),   /* ERG */
-        ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1),   /* DminLine */
+        U_ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0),        /* CWG */
+        U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), /* ERG */
+        U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1), /* DminLine */
         /*
          * Linux can handle differing I-cache policies. Userspace JITs will
          * make use of *minLine
          */
-        ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, 0),     /* L1Ip */
+        U_ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, 0),   /* L1Ip */
         ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 10, 0),        /* RAZ */
-        ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),    /* IminLine */
+        U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),  /* IminLine */
         ARM64_FTR_END,
 };
 
@@ -144,12 +153,12 @@ static struct arm64_ftr_bits ftr_id_mmfr0[] = {
 
 static struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
         ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
-        ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0),
-        ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0),
-        ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_BRPS_SHIFT, 4, 0),
-        ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0),
-        ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0),
-        ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6),
+        U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0),
+        U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0),
+        U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_BRPS_SHIFT, 4, 0),
+        U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0),
+        U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0),
+        U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6),
         ARM64_FTR_END,
 };
 
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index fc5508e0df57..4eeb17198cfa 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -127,7 +127,11 @@ static int __init uefi_init(void)
         table_size = sizeof(efi_config_table_64_t) * efi.systab->nr_tables;
         config_tables = early_memremap(efi_to_phys(efi.systab->tables),
                                        table_size);
-
+        if (config_tables == NULL) {
+                pr_warn("Unable to map EFI config table array.\n");
+                retval = -ENOMEM;
+                goto out;
+        }
         retval = efi_config_parse_tables(config_tables, efi.systab->nr_tables,
                                          sizeof(efi_config_table_64_t), NULL);
 
@@ -209,6 +213,14 @@ void __init efi_init(void)
                          PAGE_ALIGN(params.mmap_size + (params.mmap & ~PAGE_MASK)));
         memmap.phys_map = params.mmap;
         memmap.map = early_memremap(params.mmap, params.mmap_size);
+        if (memmap.map == NULL) {
+                /*
+                * If we are booting via UEFI, the UEFI memory map is the only
+                * description of memory we have, so there is little point in
+                * proceeding if we cannot access it.
+                */
+                panic("Unable to map EFI memory map.\n");
+        }
         memmap.map_end = memmap.map + params.mmap_size;
         memmap.desc_size = params.desc_size;
         memmap.desc_version = params.desc_ver;
@@ -227,7 +239,6 @@ static bool __init efi_virtmap_init(void)
         init_new_context(NULL, &efi_mm);
 
         for_each_efi_memory_desc(&memmap, md) {
-                u64 paddr, npages, size;
                 pgprot_t prot;
 
                 if (!(md->attribute & EFI_MEMORY_RUNTIME))
@@ -235,11 +246,6 @@ static bool __init efi_virtmap_init(void)
                 if (md->virt_addr == 0)
                         return false;
 
-                paddr = md->phys_addr;
-                npages = md->num_pages;
-                memrange_efi_to_native(&paddr, &npages);
-                size = npages << PAGE_SHIFT;
-
                 pr_info("  EFI remap 0x%016llx => %p\n",
                         md->phys_addr, (void *)md->virt_addr);
 
@@ -256,7 +262,8 @@ static bool __init efi_virtmap_init(void)
                 else
                         prot = PAGE_KERNEL;
 
-                create_pgd_mapping(&efi_mm, paddr, md->virt_addr, size,
+                create_pgd_mapping(&efi_mm, md->phys_addr, md->virt_addr,
+                                   md->num_pages << EFI_PAGE_SHIFT, 
                                    __pgprot(pgprot_val(prot) | PTE_NG));
         }
         return true;
@@ -273,12 +280,12 @@ static int __init arm64_enable_runtime_services(void)
 
         if (!efi_enabled(EFI_BOOT)) {
                 pr_info("EFI services will not be available.\n");
-                return -1;
+                return 0;
         }
 
         if (efi_runtime_disabled()) {
                 pr_info("EFI runtime services will be disabled.\n");
-                return -1;
+                return 0;
         }
 
         pr_info("Remapping and enabling EFI services.\n");
@@ -288,7 +295,7 @@ static int __init arm64_enable_runtime_services(void)
                                                    mapsize);
         if (!memmap.map) {
                 pr_err("Failed to remap EFI memory map\n");
-                return -1;
+                return -ENOMEM;
         }
         memmap.map_end = memmap.map + mapsize;
         efi.memmap = &memmap;
@@ -297,13 +304,13 @@ static int __init arm64_enable_runtime_services(void)
                                                    sizeof(efi_system_table_t));
         if (!efi.systab) {
                 pr_err("Failed to remap EFI System Table\n");
-                return -1;
+                return -ENOMEM;
         }
         set_bit(EFI_SYSTEM_TABLES, &efi.flags);
 
         if (!efi_virtmap_init()) {
                 pr_err("No UEFI virtual mapping was installed -- runtime services will not be available\n");
-                return -1;
+                return -ENOMEM;
         }
 
         /* Set up runtime services function pointers */
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 1ee2c3937d4e..71426a78db12 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -5,6 +5,7 @@
  */
 
 #include <asm-generic/vmlinux.lds.h>
+#include <asm/cache.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
@@ -140,7 +141,7 @@ SECTIONS
                 ARM_EXIT_KEEP(EXIT_DATA)
         }
 
-        PERCPU_SECTION(64)
+        PERCPU_SECTION(L1_CACHE_BYTES)
 
         . = ALIGN(PAGE_SIZE);
         __init_end = .;
@@ -158,7 +159,7 @@ SECTIONS
         . = ALIGN(PAGE_SIZE);
         _data = .;
         _sdata = .;
-        RW_DATA_SECTION(64, PAGE_SIZE, THREAD_SIZE)
+        RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
         PECOFF_EDATA_PADDING
         _edata = .;
 
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 68a0759b1375..15f0477b0d2a 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -37,7 +37,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
         int ret;
 
-        trace_kvm_hvc_arm64(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
+        trace_kvm_hvc_arm64(*vcpu_pc(vcpu), vcpu_get_reg(vcpu, 0),
                             kvm_vcpu_hvc_get_imm(vcpu));
 
         ret = kvm_psci_call(vcpu);
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 1599701ef044..86c289832272 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -864,6 +864,10 @@ ENTRY(__kvm_flush_vm_context)
 ENDPROC(__kvm_flush_vm_context)
 
 __kvm_hyp_panic:
+        // Stash PAR_EL1 before corrupting it in __restore_sysregs
+        mrs     x0, par_el1
+        push    x0, xzr
+
         // Guess the context by looking at VTTBR:
         // If zero, then we're already a host.
         // Otherwise restore a minimal host context before panicing.
@@ -898,7 +902,7 @@ __kvm_hyp_panic:
         mrs     x3, esr_el2
         mrs     x4, far_el2
         mrs     x5, hpfar_el2
-        mrs     x6, par_el1
+        pop     x6, xzr         // active context PAR_EL1
         mrs     x7, tpidr_el2
 
         mov     lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
@@ -914,7 +918,7 @@ __kvm_hyp_panic:
 ENDPROC(__kvm_hyp_panic)
 
 __hyp_panic_str:
-        .ascii  "HYP panic:\nPS:%08x PC:%p ESR:%p\nFAR:%p HPFAR:%p PAR:%p\nVCPU:%p\n\0"
+        .ascii  "HYP panic:\nPS:%08x PC:%016x ESR:%08x\nFAR:%016x HPFAR:%016x PAR:%016x\nVCPU:%p\n\0"
 
         .align  2
 
@@ -1015,9 +1019,15 @@ el1_trap:
         b.ne    1f              // Not an abort we care about
 
         /* This is an abort. Check for permission fault */
+alternative_if_not ARM64_WORKAROUND_834220
         and     x2, x1, #ESR_ELx_FSC_TYPE
         cmp     x2, #FSC_PERM
         b.ne    1f              // Not a permission fault
+alternative_else
+        nop                     // Use the permission fault path to
+        nop                     // check for a valid S1 translation,
+        nop                     // regardless of the ESR value.
+alternative_endif
 
         /*
          * Check for Stage-1 page table walk, which is guaranteed
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index 85c57158dcd9..648112e90ed5 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -48,7 +48,7 @@ static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 
         /* Note: These now point to the banked copies */
         *vcpu_spsr(vcpu) = new_spsr_value;
-        *vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
+        *vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
 
         /* Branch to exception vector */
         if (sctlr & (1 << 13))
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 87a64e8db04c..d2650e84faf2 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -78,7 +78,7 @@ static u32 get_ccsidr(u32 csselr)
  * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
  */
 static bool access_dcsw(struct kvm_vcpu *vcpu,
-                        const struct sys_reg_params *p,
+                        struct sys_reg_params *p,
                         const struct sys_reg_desc *r)
 {
         if (!p->is_write)
@@ -94,21 +94,19 @@ static bool access_dcsw(struct kvm_vcpu *vcpu,
  * sys_regs and leave it in complete control of the caches.
  */
 static bool access_vm_reg(struct kvm_vcpu *vcpu,
-                          const struct sys_reg_params *p,
+                          struct sys_reg_params *p,
                           const struct sys_reg_desc *r)
 {
-        unsigned long val;
         bool was_enabled = vcpu_has_cache_enabled(vcpu);
 
         BUG_ON(!p->is_write);
 
-        val = *vcpu_reg(vcpu, p->Rt);
         if (!p->is_aarch32) {
-                vcpu_sys_reg(vcpu, r->reg) = val;
+                vcpu_sys_reg(vcpu, r->reg) = p->regval;
         } else {
                 if (!p->is_32bit)
-                        vcpu_cp15_64_high(vcpu, r->reg) = val >> 32;
-                vcpu_cp15_64_low(vcpu, r->reg) = val & 0xffffffffUL;
+                        vcpu_cp15_64_high(vcpu, r->reg) = upper_32_bits(p->regval);
+                vcpu_cp15_64_low(vcpu, r->reg) = lower_32_bits(p->regval);
         }
 
         kvm_toggle_cache(vcpu, was_enabled);
@@ -122,22 +120,19 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
  * for both AArch64 and AArch32 accesses.
  */
 static bool access_gic_sgi(struct kvm_vcpu *vcpu,
-                           const struct sys_reg_params *p,
+                           struct sys_reg_params *p,
                            const struct sys_reg_desc *r)
 {
-        u64 val;
-
         if (!p->is_write)
                 return read_from_write_only(vcpu, p);
 
-        val = *vcpu_reg(vcpu, p->Rt);
-        vgic_v3_dispatch_sgi(vcpu, val);
+        vgic_v3_dispatch_sgi(vcpu, p->regval);
 
         return true;
 }
 
 static bool trap_raz_wi(struct kvm_vcpu *vcpu,
-                        const struct sys_reg_params *p,
+                        struct sys_reg_params *p,
                         const struct sys_reg_desc *r)
 {
         if (p->is_write)
@@ -147,19 +142,19 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu,
 }
 
 static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
-                           const struct sys_reg_params *p,
+                           struct sys_reg_params *p,
                            const struct sys_reg_desc *r)
 {
         if (p->is_write) {
                 return ignore_write(vcpu, p);
         } else {
-                *vcpu_reg(vcpu, p->Rt) = (1 << 3);
+                p->regval = (1 << 3);
                 return true;
         }
 }
 
 static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
-                                   const struct sys_reg_params *p,
+                                   struct sys_reg_params *p,
                                    const struct sys_reg_desc *r)
 {
         if (p->is_write) {
@@ -167,7 +162,7 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
         } else {
                 u32 val;
                 asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val));
-                *vcpu_reg(vcpu, p->Rt) = val;
+                p->regval = val;
                 return true;
         }
 }
@@ -200,17 +195,17 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
  *   now use the debug registers.
  */
 static bool trap_debug_regs(struct kvm_vcpu *vcpu,
-                            const struct sys_reg_params *p,
+                            struct sys_reg_params *p,
                             const struct sys_reg_desc *r)
 {
         if (p->is_write) {
-                vcpu_sys_reg(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+                vcpu_sys_reg(vcpu, r->reg) = p->regval;
                 vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
         } else {
-                *vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, r->reg);
+                p->regval = vcpu_sys_reg(vcpu, r->reg);
         }
 
-        trace_trap_reg(__func__, r->reg, p->is_write, *vcpu_reg(vcpu, p->Rt));
+        trace_trap_reg(__func__, r->reg, p->is_write, p->regval);
 
         return true;
 }
@@ -225,10 +220,10 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu,
  * hyp.S code switches between host and guest values in future.
  */
 static inline void reg_to_dbg(struct kvm_vcpu *vcpu,
-                              const struct sys_reg_params *p,
+                              struct sys_reg_params *p,
                               u64 *dbg_reg)
 {
-        u64 val = *vcpu_reg(vcpu, p->Rt);
+        u64 val = p->regval;
 
         if (p->is_32bit) {
                 val &= 0xffffffffUL;
@@ -240,19 +235,16 @@ static inline void reg_to_dbg(struct kvm_vcpu *vcpu,
 }
 
 static inline void dbg_to_reg(struct kvm_vcpu *vcpu,
-                              const struct sys_reg_params *p,
+                              struct sys_reg_params *p,
                               u64 *dbg_reg)
 {
-        u64 val = *dbg_reg;
-
+        p->regval = *dbg_reg;
         if (p->is_32bit)
-                val &= 0xffffffffUL;
-
-        *vcpu_reg(vcpu, p->Rt) = val;
+                p->regval &= 0xffffffffUL;
 }
 
 static inline bool trap_bvr(struct kvm_vcpu *vcpu,
-                            const struct sys_reg_params *p,
+                            struct sys_reg_params *p,
                             const struct sys_reg_desc *rd)
 {
         u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];
@@ -294,7 +286,7 @@ static inline void reset_bvr(struct kvm_vcpu *vcpu,
 }
 
 static inline bool trap_bcr(struct kvm_vcpu *vcpu,
-                            const struct sys_reg_params *p,
+                            struct sys_reg_params *p,
                             const struct sys_reg_desc *rd)
 {
         u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg];
@@ -337,7 +329,7 @@ static inline void reset_bcr(struct kvm_vcpu *vcpu,
 }
 
 static inline bool trap_wvr(struct kvm_vcpu *vcpu,
-                            const struct sys_reg_params *p,
+                            struct sys_reg_params *p,
                             const struct sys_reg_desc *rd)
 {
         u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg];
@@ -380,7 +372,7 @@ static inline void reset_wvr(struct kvm_vcpu *vcpu,
 }
 
 static inline bool trap_wcr(struct kvm_vcpu *vcpu,
-                            const struct sys_reg_params *p,
+                            struct sys_reg_params *p,
                             const struct sys_reg_desc *rd)
 {
         u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg];
@@ -687,7 +679,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 };
 
 static bool trap_dbgidr(struct kvm_vcpu *vcpu,
-                        const struct sys_reg_params *p,
+                        struct sys_reg_params *p,
                         const struct sys_reg_desc *r)
 {
         if (p->is_write) {
@@ -697,23 +689,23 @@ static bool trap_dbgidr(struct kvm_vcpu *vcpu,
                 u64 pfr = read_system_reg(SYS_ID_AA64PFR0_EL1);
                 u32 el3 = !!cpuid_feature_extract_field(pfr, ID_AA64PFR0_EL3_SHIFT);
 
-                *vcpu_reg(vcpu, p->Rt) = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) |
-                                          (((dfr >> ID_AA64DFR0_BRPS_SHIFT) & 0xf) << 24) |
-                                          (((dfr >> ID_AA64DFR0_CTX_CMPS_SHIFT) & 0xf) << 20) |
-                                          (6 << 16) | (el3 << 14) | (el3 << 12));
+                p->regval = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) |
+                             (((dfr >> ID_AA64DFR0_BRPS_SHIFT) & 0xf) << 24) |
+                             (((dfr >> ID_AA64DFR0_CTX_CMPS_SHIFT) & 0xf) << 20)
+                             | (6 << 16) | (el3 << 14) | (el3 << 12));
                 return true;
         }
 }
 
 static bool trap_debug32(struct kvm_vcpu *vcpu,
-                         const struct sys_reg_params *p,
+                         struct sys_reg_params *p,
                          const struct sys_reg_desc *r)
 {
         if (p->is_write) {
-                vcpu_cp14(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+                vcpu_cp14(vcpu, r->reg) = p->regval;
                 vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
         } else {
-                *vcpu_reg(vcpu, p->Rt) = vcpu_cp14(vcpu, r->reg);
+                p->regval = vcpu_cp14(vcpu, r->reg);
         }
 
         return true;
@@ -731,7 +723,7 @@ static bool trap_debug32(struct kvm_vcpu *vcpu,
  */
 
 static inline bool trap_xvr(struct kvm_vcpu *vcpu,
-                            const struct sys_reg_params *p,
+                            struct sys_reg_params *p,
                             const struct sys_reg_desc *rd)
 {
         u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];
@@ -740,12 +732,12 @@ static inline bool trap_xvr(struct kvm_vcpu *vcpu,
                 u64 val = *dbg_reg;
 
                 val &= 0xffffffffUL;
-                val |= *vcpu_reg(vcpu, p->Rt) << 32;
+                val |= p->regval << 32;
                 *dbg_reg = val;
 
                 vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
         } else {
-                *vcpu_reg(vcpu, p->Rt) = *dbg_reg >> 32;
+                p->regval = *dbg_reg >> 32;
         }
 
         trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg);
@@ -991,7 +983,7 @@ int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run)
  * Return 0 if the access has been handled, and -1 if not.
  */
 static int emulate_cp(struct kvm_vcpu *vcpu,
-                      const struct sys_reg_params *params,
+                      struct sys_reg_params *params,
                       const struct sys_reg_desc *table,
                       size_t num)
 {
@@ -1062,12 +1054,12 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
 {
         struct sys_reg_params params;
         u32 hsr = kvm_vcpu_get_hsr(vcpu);
+        int Rt = (hsr >> 5) & 0xf;
         int Rt2 = (hsr >> 10) & 0xf;
 
         params.is_aarch32 = true;
         params.is_32bit = false;
         params.CRm = (hsr >> 1) & 0xf;
-        params.Rt = (hsr >> 5) & 0xf;
         params.is_write = ((hsr & 1) == 0);
 
         params.Op0 = 0;
@@ -1076,15 +1068,12 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
         params.CRn = 0;
 
         /*
-         * Massive hack here. Store Rt2 in the top 32bits so we only
-         * have one register to deal with. As we use the same trap
+         * Make a 64-bit value out of Rt and Rt2. As we use the same trap
          * backends between AArch32 and AArch64, we get away with it.
          */
         if (params.is_write) {
-                u64 val = *vcpu_reg(vcpu, params.Rt);
-                val &= 0xffffffff;
-                val |= *vcpu_reg(vcpu, Rt2) << 32;
-                *vcpu_reg(vcpu, params.Rt) = val;
+                params.regval = vcpu_get_reg(vcpu, Rt) & 0xffffffff;
+                params.regval |= vcpu_get_reg(vcpu, Rt2) << 32;
         }
 
         if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
@@ -1095,11 +1084,10 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
         unhandled_cp_access(vcpu, &params);
 
 out:
-        /* Do the opposite hack for the read side */
+        /* Split up the value between registers for the read side */
         if (!params.is_write) {
-                u64 val = *vcpu_reg(vcpu, params.Rt);
-                val >>= 32;
-                *vcpu_reg(vcpu, Rt2) = val;
+                vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval));
+                vcpu_set_reg(vcpu, Rt2, upper_32_bits(params.regval));
         }
 
         return 1;
@@ -1118,21 +1106,24 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
 {
         struct sys_reg_params params;
         u32 hsr = kvm_vcpu_get_hsr(vcpu);
+        int Rt  = (hsr >> 5) & 0xf;
 
         params.is_aarch32 = true;
         params.is_32bit = true;
         params.CRm = (hsr >> 1) & 0xf;
-        params.Rt  = (hsr >> 5) & 0xf;
+        params.regval = vcpu_get_reg(vcpu, Rt);
         params.is_write = ((hsr & 1) == 0);
         params.CRn = (hsr >> 10) & 0xf;
         params.Op0 = 0;
         params.Op1 = (hsr >> 14) & 0x7;
         params.Op2 = (hsr >> 17) & 0x7;
 
-        if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
-                return 1;
-        if (!emulate_cp(vcpu, &params, global, nr_global))
+        if (!emulate_cp(vcpu, &params, target_specific, nr_specific) ||
+            !emulate_cp(vcpu, &params, global, nr_global)) {
+                if (!params.is_write)
+                        vcpu_set_reg(vcpu, Rt, params.regval);
                 return 1;
+        }
 
         unhandled_cp_access(vcpu, &params);
         return 1;
@@ -1175,7 +1166,7 @@ int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
 }
 
 static int emulate_sys_reg(struct kvm_vcpu *vcpu,
-                           const struct sys_reg_params *params)
+                           struct sys_reg_params *params)
 {
         size_t num;
         const struct sys_reg_desc *table, *r;
@@ -1230,6 +1221,8 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
         struct sys_reg_params params;
         unsigned long esr = kvm_vcpu_get_hsr(vcpu);
+        int Rt = (esr >> 5) & 0x1f;
+        int ret;
 
         trace_kvm_handle_sys_reg(esr);
 
@@ -1240,10 +1233,14 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run)
         params.CRn = (esr >> 10) & 0xf;
         params.CRm = (esr >> 1) & 0xf;
         params.Op2 = (esr >> 17) & 0x7;
-        params.Rt = (esr >> 5) & 0x1f;
+        params.regval = vcpu_get_reg(vcpu, Rt);
         params.is_write = !(esr & 1);
 
-        return emulate_sys_reg(vcpu, &params);
+        ret = emulate_sys_reg(vcpu, &params);
+
+        if (!params.is_write)
+                vcpu_set_reg(vcpu, Rt, params.regval);
+        return ret;
 }
 
 /******************************************************************************
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index eaa324e4db4d..dbbb01cfbee9 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -28,7 +28,7 @@ struct sys_reg_params {
         u8      CRn;
         u8      CRm;
         u8      Op2;
-        u8      Rt;
+        u64     regval;
         bool    is_write;
         bool    is_aarch32;
         bool    is_32bit;       /* Only valid if is_aarch32 is true */
@@ -44,7 +44,7 @@ struct sys_reg_desc {
 
         /* Trapped access from guest, if non-NULL. */
         bool (*access)(struct kvm_vcpu *,
-                       const struct sys_reg_params *,
+                       struct sys_reg_params *,
                        const struct sys_reg_desc *);
 
         /* Initialization for vcpu. */
@@ -77,9 +77,9 @@ static inline bool ignore_write(struct kvm_vcpu *vcpu,
 }
 
 static inline bool read_zero(struct kvm_vcpu *vcpu,
-                             const struct sys_reg_params *p)
+                             struct sys_reg_params *p)
 {
-        *vcpu_reg(vcpu, p->Rt) = 0;
+        p->regval = 0;
         return true;
 }
 
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
index 1e4576824165..ed90578fa120 100644
--- a/arch/arm64/kvm/sys_regs_generic_v8.c
+++ b/arch/arm64/kvm/sys_regs_generic_v8.c
@@ -31,13 +31,13 @@
 #include "sys_regs.h"
 
 static bool access_actlr(struct kvm_vcpu *vcpu,
-                         const struct sys_reg_params *p,
+                         struct sys_reg_params *p,
                          const struct sys_reg_desc *r)
 {
         if (p->is_write)
                 return ignore_write(vcpu, p);
 
-        *vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, ACTLR_EL1);
+        p->regval = vcpu_sys_reg(vcpu, ACTLR_EL1);
         return true;
 }
 
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index f636a2639f03..e87f53ff5f58 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -76,13 +76,28 @@ static void flush_context(unsigned int cpu)
                 __flush_icache_all();
 }
 
-static int is_reserved_asid(u64 asid)
+static bool check_update_reserved_asid(u64 asid, u64 newasid)
 {
         int cpu;
-        for_each_possible_cpu(cpu)
-                if (per_cpu(reserved_asids, cpu) == asid)
-                        return 1;
-        return 0;
+        bool hit = false;
+
+        /*
+         * Iterate over the set of reserved ASIDs looking for a match.
+         * If we find one, then we can update our mm to use newasid
+         * (i.e. the same ASID in the current generation) but we can't
+         * exit the loop early, since we need to ensure that all copies
+         * of the old ASID are updated to reflect the mm. Failure to do
+         * so could result in us missing the reserved ASID in a future
+         * generation.
+         */
+        for_each_possible_cpu(cpu) {
+                if (per_cpu(reserved_asids, cpu) == asid) {
+                        hit = true;
+                        per_cpu(reserved_asids, cpu) = newasid;
+                }
+        }
+
+        return hit;
 }
 
 static u64 new_context(struct mm_struct *mm, unsigned int cpu)
@@ -92,12 +107,14 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
         u64 generation = atomic64_read(&asid_generation);
 
         if (asid != 0) {
+                u64 newasid = generation | (asid & ~ASID_MASK);
+
                 /*
                  * If our current ASID was active during a rollover, we
                  * can continue to use it and this was just a false alarm.
                  */
-                if (is_reserved_asid(asid))
-                        return generation | (asid & ~ASID_MASK);
+                if (check_update_reserved_asid(asid, newasid))
+                        return newasid;
 
                 /*
                  * We had a valid ASID in a previous life, so try to re-use
@@ -105,7 +122,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
                  */
                 asid &= ~ASID_MASK;
                 if (!__test_and_set_bit(asid, asid_map))
-                        goto bump_gen;
+                        return newasid;
         }
 
         /*
@@ -129,10 +146,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 set_asid:
         __set_bit(asid, asid_map);
         cur_idx = asid;
-
-bump_gen:
-        asid |= generation;
-        return asid;
+        return asid | generation;
 }
 
 void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 19211c4a8911..92ddac1e8ca2 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -393,16 +393,16 @@ static struct fault_info {
         { do_translation_fault, SIGSEGV, SEGV_MAPERR,   "level 1 translation fault"     },
         { do_translation_fault, SIGSEGV, SEGV_MAPERR,   "level 2 translation fault"     },
         { do_page_fault,        SIGSEGV, SEGV_MAPERR,   "level 3 translation fault"     },
-        { do_bad,               SIGBUS,  0,             "reserved access flag fault"    },
+        { do_bad,               SIGBUS,  0,             "unknown 8"                     },
         { do_page_fault,        SIGSEGV, SEGV_ACCERR,   "level 1 access flag fault"     },
         { do_page_fault,        SIGSEGV, SEGV_ACCERR,   "level 2 access flag fault"     },
         { do_page_fault,        SIGSEGV, SEGV_ACCERR,   "level 3 access flag fault"     },
-        { do_bad,               SIGBUS,  0,             "reserved permission fault"     },
+        { do_bad,               SIGBUS,  0,             "unknown 12"                    },
         { do_page_fault,        SIGSEGV, SEGV_ACCERR,   "level 1 permission fault"      },
         { do_page_fault,        SIGSEGV, SEGV_ACCERR,   "level 2 permission fault"      },
         { do_page_fault,        SIGSEGV, SEGV_ACCERR,   "level 3 permission fault"      },
         { do_bad,               SIGBUS,  0,             "synchronous external abort"    },
-        { do_bad,               SIGBUS,  0,             "asynchronous external abort"   },
+        { do_bad,               SIGBUS,  0,             "unknown 17"                    },
         { do_bad,               SIGBUS,  0,             "unknown 18"                    },
         { do_bad,               SIGBUS,  0,             "unknown 19"                    },
         { do_bad,               SIGBUS,  0,             "synchronous abort (translation table walk)" },
@@ -410,16 +410,16 @@ static struct fault_info {
         { do_bad,               SIGBUS,  0,             "synchronous abort (translation table walk)" },
         { do_bad,               SIGBUS,  0,             "synchronous abort (translation table walk)" },
         { do_bad,               SIGBUS,  0,             "synchronous parity error"      },
-        { do_bad,               SIGBUS,  0,             "asynchronous parity error"     },
+        { do_bad,               SIGBUS,  0,             "unknown 25"                    },
         { do_bad,               SIGBUS,  0,             "unknown 26"                    },
         { do_bad,               SIGBUS,  0,             "unknown 27"                    },
-        { do_bad,               SIGBUS,  0,             "synchronous parity error (translation table walk" },
-        { do_bad,               SIGBUS,  0,             "synchronous parity error (translation table walk" },
-        { do_bad,               SIGBUS,  0,             "synchronous parity error (translation table walk" },
-        { do_bad,               SIGBUS,  0,             "synchronous parity error (translation table walk" },
+        { do_bad,               SIGBUS,  0,             "synchronous parity error (translation table walk)" },
+        { do_bad,               SIGBUS,  0,             "synchronous parity error (translation table walk)" },
+        { do_bad,               SIGBUS,  0,             "synchronous parity error (translation table walk)" },
+        { do_bad,               SIGBUS,  0,             "synchronous parity error (translation table walk)" },
         { do_bad,               SIGBUS,  0,             "unknown 32"                    },
         { do_bad,               SIGBUS,  BUS_ADRALN,    "alignment fault"               },
-        { do_bad,               SIGBUS,  0,             "debug event"                   },
+        { do_bad,               SIGBUS,  0,             "unknown 34"                    },
         { do_bad,               SIGBUS,  0,             "unknown 35"                    },
         { do_bad,               SIGBUS,  0,             "unknown 36"                    },
         { do_bad,               SIGBUS,  0,             "unknown 37"                    },
@@ -433,21 +433,21 @@ static struct fault_info {
         { do_bad,               SIGBUS,  0,             "unknown 45"                    },
         { do_bad,               SIGBUS,  0,             "unknown 46"                    },
         { do_bad,               SIGBUS,  0,             "unknown 47"                    },
-        { do_bad,               SIGBUS,  0,             "unknown 48"                    },
+        { do_bad,               SIGBUS,  0,             "TLB conflict abort"            },
         { do_bad,               SIGBUS,  0,             "unknown 49"                    },
         { do_bad,               SIGBUS,  0,             "unknown 50"                    },
         { do_bad,               SIGBUS,  0,             "unknown 51"                    },
         { do_bad,               SIGBUS,  0,             "implementation fault (lockdown abort)" },
-        { do_bad,               SIGBUS,  0,             "unknown 53"                    },
+        { do_bad,               SIGBUS,  0,             "implementation fault (unsupported exclusive)" },
         { do_bad,               SIGBUS,  0,             "unknown 54"                    },
         { do_bad,               SIGBUS,  0,             "unknown 55"                    },
         { do_bad,               SIGBUS,  0,             "unknown 56"                    },
         { do_bad,               SIGBUS,  0,             "unknown 57"                    },
-        { do_bad,               SIGBUS,  0,             "implementation fault (coprocessor abort)" },
+        { do_bad,               SIGBUS,  0,             "unknown 58"                    },
         { do_bad,               SIGBUS,  0,             "unknown 59"                    },
         { do_bad,               SIGBUS,  0,             "unknown 60"                    },
-        { do_bad,               SIGBUS,  0,             "unknown 61"                    },
-        { do_bad,               SIGBUS,  0,             "unknown 62"                    },
+        { do_bad,               SIGBUS,  0,             "section domain fault"          },
+        { do_bad,               SIGBUS,  0,             "page domain fault"             },
         { do_bad,               SIGBUS,  0,             "unknown 63"                    },
 };
 
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index abb66f84d4ac..873e363048c6 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -64,8 +64,12 @@ EXPORT_SYMBOL(phys_mem_access_prot);
 
 static void __init *early_alloc(unsigned long sz)
 {
-        void *ptr = __va(memblock_alloc(sz, sz));
-        BUG_ON(!ptr);
+        phys_addr_t phys;
+        void *ptr;
+
+        phys = memblock_alloc(sz, sz);
+        BUG_ON(!phys);
+        ptr = __va(phys);
         memset(ptr, 0, sz);
         return ptr;
 }
@@ -81,55 +85,19 @@ static void split_pmd(pmd_t *pmd, pte_t *pte)
         do {
                 /*
                  * Need to have the least restrictive permissions available
-                 * permissions will be fixed up later. Default the new page
-                 * range as contiguous ptes.
+                 * permissions will be fixed up later
                  */
-                set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC_CONT));
+                set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
                 pfn++;
         } while (pte++, i++, i < PTRS_PER_PTE);
 }
 
-/*
- * Given a PTE with the CONT bit set, determine where the CONT range
- * starts, and clear the entire range of PTE CONT bits.
- */
-static void clear_cont_pte_range(pte_t *pte, unsigned long addr)
-{
-        int i;
-
-        pte -= CONT_RANGE_OFFSET(addr);
-        for (i = 0; i < CONT_PTES; i++) {
-                set_pte(pte, pte_mknoncont(*pte));
-                pte++;
-        }
-        flush_tlb_all();
-}
-
-/*
- * Given a range of PTEs set the pfn and provided page protection flags
- */
-static void __populate_init_pte(pte_t *pte, unsigned long addr,
-                                unsigned long end, phys_addr_t phys,
-                                pgprot_t prot)
-{
-        unsigned long pfn = __phys_to_pfn(phys);
-
-        do {
-                /* clear all the bits except the pfn, then apply the prot */
-                set_pte(pte, pfn_pte(pfn, prot));
-                pte++;
-                pfn++;
-                addr += PAGE_SIZE;
-        } while (addr != end);
-}
-
 static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
-                                  unsigned long end, phys_addr_t phys,
+                                  unsigned long end, unsigned long pfn,
                                   pgprot_t prot,
                                   void *(*alloc)(unsigned long size))
 {
         pte_t *pte;
-        unsigned long next;
 
         if (pmd_none(*pmd) || pmd_sect(*pmd)) {
                 pte = alloc(PTRS_PER_PTE * sizeof(pte_t));
@@ -142,27 +110,9 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
 
         pte = pte_offset_kernel(pmd, addr);
         do {
-                next = min(end, (addr + CONT_SIZE) & CONT_MASK);
-                if (((addr | next | phys) & ~CONT_MASK) == 0) {
-                        /* a block of CONT_PTES  */
-                        __populate_init_pte(pte, addr, next, phys,
-                                            __pgprot(pgprot_val(prot) | PTE_CONT));
-                } else {
-                        /*
-                         * If the range being split is already inside of a
-                         * contiguous range but this PTE isn't going to be
-                         * contiguous, then we want to unmark the adjacent
-                         * ranges, then update the portion of the range we
-                         * are interrested in.
-                         */
-                         clear_cont_pte_range(pte, addr);
-                         __populate_init_pte(pte, addr, next, phys, prot);
-                }
-
-                pte += (next - addr) >> PAGE_SHIFT;
-                phys += next - addr;
-                addr = next;
-        } while (addr != end);
+                set_pte(pte, pfn_pte(pfn, prot));
+                pfn++;
+        } while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
 static void split_pud(pud_t *old_pud, pmd_t *pmd)
@@ -223,7 +173,8 @@ static void alloc_init_pmd(struct mm_struct *mm, pud_t *pud,
                                 }
                         }
                 } else {
-                        alloc_init_pte(pmd, addr, next, phys, prot, alloc);
+                        alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys),
+                                       prot, alloc);
                 }
                 phys += next - addr;
         } while (pmd++, addr = next, addr != end);
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index d6a53ef2350b..b162ad70effc 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -139,6 +139,12 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 /* Stack must be multiples of 16B */
 #define STACK_ALIGN(sz) (((sz) + 15) & ~15)
 
+#define _STACK_SIZE \
+        (MAX_BPF_STACK \
+         + 4 /* extra for skb_copy_bits buffer */)
+
+#define STACK_SIZE STACK_ALIGN(_STACK_SIZE)
+
 static void build_prologue(struct jit_ctx *ctx)
 {
         const u8 r6 = bpf2a64[BPF_REG_6];
@@ -150,10 +156,6 @@ static void build_prologue(struct jit_ctx *ctx)
         const u8 rx = bpf2a64[BPF_REG_X];
         const u8 tmp1 = bpf2a64[TMP_REG_1];
         const u8 tmp2 = bpf2a64[TMP_REG_2];
-        int stack_size = MAX_BPF_STACK;
-
-        stack_size += 4; /* extra for skb_copy_bits buffer */
-        stack_size = STACK_ALIGN(stack_size);
 
         /*
          * BPF prog stack layout
@@ -165,12 +167,13 @@ static void build_prologue(struct jit_ctx *ctx)
          *                        | ... | callee saved registers
          *                        +-----+
          *                        |     | x25/x26
-         * BPF fp register => -80:+-----+
+         * BPF fp register => -80:+-----+ <= (BPF_FP)
          *                        |     |
          *                        | ... | BPF prog stack
          *                        |     |
-         *                        |     |
-         * current A64_SP =>      +-----+
+         *                        +-----+ <= (BPF_FP - MAX_BPF_STACK)
+         *                        |RSVD | JIT scratchpad
+         * current A64_SP =>      +-----+ <= (BPF_FP - STACK_SIZE)
          *                        |     |
          *                        | ... | Function call stack
          *                        |     |
@@ -196,7 +199,7 @@ static void build_prologue(struct jit_ctx *ctx)
         emit(A64_MOV(1, fp, A64_SP), ctx);
 
         /* Set up function call stack */
-        emit(A64_SUB_I(1, A64_SP, A64_SP, stack_size), ctx);
+        emit(A64_SUB_I(1, A64_SP, A64_SP, STACK_SIZE), ctx);
 
         /* Clear registers A and X */
         emit_a64_mov_i64(ra, 0, ctx);
@@ -213,13 +216,9 @@ static void build_epilogue(struct jit_ctx *ctx)
         const u8 fp = bpf2a64[BPF_REG_FP];
         const u8 tmp1 = bpf2a64[TMP_REG_1];
         const u8 tmp2 = bpf2a64[TMP_REG_2];
-        int stack_size = MAX_BPF_STACK;
-
-        stack_size += 4; /* extra for skb_copy_bits buffer */
-        stack_size = STACK_ALIGN(stack_size);
 
         /* We're done with BPF stack */
-        emit(A64_ADD_I(1, A64_SP, A64_SP, stack_size), ctx);
+        emit(A64_ADD_I(1, A64_SP, A64_SP, STACK_SIZE), ctx);
 
         /* Restore fs (x25) and x26 */
         emit(A64_POP(fp, A64_R(26), A64_SP), ctx);
@@ -591,7 +590,25 @@ emit_cond_jmp:
         case BPF_ST | BPF_MEM | BPF_H:
         case BPF_ST | BPF_MEM | BPF_B:
         case BPF_ST | BPF_MEM | BPF_DW:
-                goto notyet;
+                /* Load imm to a register then store it */
+                ctx->tmp_used = 1;
+                emit_a64_mov_i(1, tmp2, off, ctx);
+                emit_a64_mov_i(1, tmp, imm, ctx);
+                switch (BPF_SIZE(code)) {
+                case BPF_W:
+                        emit(A64_STR32(tmp, dst, tmp2), ctx);
+                        break;
+                case BPF_H:
+                        emit(A64_STRH(tmp, dst, tmp2), ctx);
+                        break;
+                case BPF_B:
+                        emit(A64_STRB(tmp, dst, tmp2), ctx);
+                        break;
+                case BPF_DW:
+                        emit(A64_STR64(tmp, dst, tmp2), ctx);
+                        break;
+                }
+                break;
 
         /* STX: *(size *)(dst + off) = src */
         case BPF_STX | BPF_MEM | BPF_W:
@@ -658,7 +675,7 @@ emit_cond_jmp:
                         return -EINVAL;
                 }
                 emit_a64_mov_i64(r3, size, ctx);
-                emit(A64_ADD_I(1, r4, fp, MAX_BPF_STACK), ctx);
+                emit(A64_SUB_I(1, r4, fp, STACK_SIZE), ctx);
                 emit_a64_mov_i64(r5, (unsigned long)bpf_load_pointer, ctx);
                 emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
                 emit(A64_MOV(1, A64_FP, A64_SP), ctx);
diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
index 1e9c8b0bf486..170d786807c4 100644
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -14,7 +14,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *
  * ppc:
diff --git a/arch/m68k/coldfire/m54xx.c b/arch/m68k/coldfire/m54xx.c
index f7836c6a6b60..c32f76791f48 100644
--- a/arch/m68k/coldfire/m54xx.c
+++ b/arch/m68k/coldfire/m54xx.c
@@ -98,7 +98,7 @@ static void __init mcf54xx_bootmem_alloc(void)
         memstart = PAGE_ALIGN(_ramstart);
         min_low_pfn = PFN_DOWN(_rambase);
         start_pfn = PFN_DOWN(memstart);
-        max_low_pfn = PFN_DOWN(_ramend);
+        max_pfn = max_low_pfn = PFN_DOWN(_ramend);
         high_memory = (void *)_ramend;
 
         m68k_virt_to_node_shift = fls(_ramend - _rambase - 1) - 6;
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index 0793a7f17417..f9d96bf86910 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -4,7 +4,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls             375
+#define NR_syscalls             376
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT
diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h
index 5e6fae6c275f..36cf129de663 100644
--- a/arch/m68k/include/uapi/asm/unistd.h
+++ b/arch/m68k/include/uapi/asm/unistd.h
@@ -380,5 +380,6 @@
 #define __NR_sendmmsg           372
 #define __NR_userfaultfd        373
 #define __NR_membarrier         374
+#define __NR_mlock2             375
 
 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */
diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c
index 88c27d94a721..76b9113f3092 100644
--- a/arch/m68k/kernel/setup_no.c
+++ b/arch/m68k/kernel/setup_no.c
@@ -238,11 +238,14 @@ void __init setup_arch(char **cmdline_p)
          * Give all the memory to the bootmap allocator, tell it to put the
          * boot mem_map at the start of memory.
          */
+        min_low_pfn = PFN_DOWN(memory_start);
+        max_pfn = max_low_pfn = PFN_DOWN(memory_end);
+
         bootmap_size = init_bootmem_node(
                         NODE_DATA(0),
-                        memory_start >> PAGE_SHIFT, /* map goes here */
-                        PAGE_OFFSET >> PAGE_SHIFT,      /* 0 on coldfire */
-                        memory_end >> PAGE_SHIFT);
+                        min_low_pfn,            /* map goes here */
+                        PFN_DOWN(PAGE_OFFSET),
+                        max_pfn);
         /*
          * Free the usable memory, we have to make sure we do not free
          * the bootmem bitmap so we then reserve it after freeing it :-)
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index 5dd0e80042f5..282cd903f4c4 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -395,3 +395,4 @@ ENTRY(sys_call_table)
         .long sys_sendmmsg
         .long sys_userfaultfd
         .long sys_membarrier
+        .long sys_mlock2                /* 375 */
diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c
index b958916e5eac..8f37fdd80be9 100644
--- a/arch/m68k/mm/motorola.c
+++ b/arch/m68k/mm/motorola.c
@@ -250,7 +250,7 @@ void __init paging_init(void)
         high_memory = phys_to_virt(max_addr);
 
         min_low_pfn = availmem >> PAGE_SHIFT;
-        max_low_pfn = max_addr >> PAGE_SHIFT;
+        max_pfn = max_low_pfn = max_addr >> PAGE_SHIFT;
 
         for (i = 0; i < m68k_num_memory; i++) {
                 addr = m68k_memory[i].addr;
diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c
index a8b942bf7163..2a5f43a68ae3 100644
--- a/arch/m68k/sun3/config.c
+++ b/arch/m68k/sun3/config.c
@@ -118,13 +118,13 @@ static void __init sun3_bootmem_alloc(unsigned long memory_start,
         memory_end = memory_end & PAGE_MASK;
 
         start_page = __pa(memory_start) >> PAGE_SHIFT;
-        num_pages = __pa(memory_end) >> PAGE_SHIFT;
+        max_pfn = num_pages = __pa(memory_end) >> PAGE_SHIFT;
 
         high_memory = (void *)memory_end;
         availmem = memory_start;
 
         m68k_setup_node(0);
-        availmem += init_bootmem_node(NODE_DATA(0), start_page, 0, num_pages);
+        availmem += init_bootmem(start_page, num_pages);
         availmem = (availmem + (PAGE_SIZE-1)) & PAGE_MASK;
 
         free_bootmem(__pa(availmem), memory_end - (availmem));
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index d5fa3eaf39a1..41b1b090f56f 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -1581,7 +1581,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
 
         base = (inst >> 21) & 0x1f;
         op_inst = (inst >> 16) & 0x1f;
-        offset = inst & 0xffff;
+        offset = (int16_t)inst;
         cache = (inst >> 16) & 0x3;
         op = (inst >> 18) & 0x7;
 
diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S
index 7bab3a4e8f7d..7e2210846b8b 100644
--- a/arch/mips/kvm/locore.S
+++ b/arch/mips/kvm/locore.S
@@ -157,9 +157,11 @@ FEXPORT(__kvm_mips_vcpu_run)
 
 FEXPORT(__kvm_mips_load_asid)
         /* Set the ASID for the Guest Kernel */
-        INT_SLL t0, t0, 1       /* with kseg0 @ 0x40000000, kernel */
-                                /* addresses shift to 0x80000000 */
-        bltz    t0, 1f          /* If kernel */
+        PTR_L   t0, VCPU_COP0(k1)
+        LONG_L  t0, COP0_STATUS(t0)
+        andi    t0, KSU_USER | ST0_ERL | ST0_EXL
+        xori    t0, KSU_USER
+        bnez    t0, 1f          /* If kernel */
          INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID  /* (BD)  */
         INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID    /* else user */
 1:
@@ -474,9 +476,11 @@ __kvm_mips_return_to_guest:
         mtc0    t0, CP0_EPC
 
         /* Set the ASID for the Guest Kernel */
-        INT_SLL t0, t0, 1       /* with kseg0 @ 0x40000000, kernel */
-                                /* addresses shift to 0x80000000 */
-        bltz    t0, 1f          /* If kernel */
+        PTR_L   t0, VCPU_COP0(k1)
+        LONG_L  t0, COP0_STATUS(t0)
+        andi    t0, KSU_USER | ST0_ERL | ST0_EXL
+        xori    t0, KSU_USER
+        bnez    t0, 1f          /* If kernel */
          INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID  /* (BD)  */
         INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID    /* else user */
 1:
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 49ff3bfc007e..b9b803facdbf 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -279,7 +279,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 
         if (!gebase) {
                 err = -ENOMEM;
-                goto out_free_cpu;
+                goto out_uninit_cpu;
         }
         kvm_debug("Allocated %d bytes for KVM Exception Handlers @ %p\n",
                   ALIGN(size, PAGE_SIZE), gebase);
@@ -343,6 +343,9 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 out_free_gebase:
         kfree(gebase);
 
+out_uninit_cpu:
+        kvm_vcpu_uninit(vcpu);
+
 out_free_cpu:
         kfree(vcpu);
 
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index d8117be729a2..730d394ce5f0 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -145,7 +145,7 @@ static void *mips_dma_alloc_coherent(struct device *dev, size_t size,
 
         gfp = massage_gfp_flags(dev, gfp);
 
-        if (IS_ENABLED(CONFIG_DMA_CMA) && !(gfp & GFP_ATOMIC))
+        if (IS_ENABLED(CONFIG_DMA_CMA) && gfpflags_allow_blocking(gfp))
                 page = dma_alloc_from_contiguous(dev,
                                         count, get_order(size));
         if (!page)
diff --git a/arch/mips/pci/pci-rt2880.c b/arch/mips/pci/pci-rt2880.c
index 8a978022630b..dbbeccc3d714 100644
--- a/arch/mips/pci/pci-rt2880.c
+++ b/arch/mips/pci/pci-rt2880.c
@@ -11,6 +11,7 @@
  *  by the Free Software Foundation.
  */
 
+#include <linux/delay.h>
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <linux/io.h>
@@ -232,8 +233,7 @@ static int rt288x_pci_probe(struct platform_device *pdev)
         ioport_resource.end = RT2880_PCI_IO_BASE + RT2880_PCI_IO_SIZE - 1;
 
         rt2880_pci_reg_write(0, RT2880_PCI_REG_PCICFG_ADDR);
-        for (i = 0; i < 0xfffff; i++)
-                ;
+        udelay(1);
 
         rt2880_pci_reg_write(0x79, RT2880_PCI_REG_ARBCTL);
         rt2880_pci_reg_write(0x07FF0001, RT2880_PCI_REG_BAR0SETUP_ADDR);
diff --git a/arch/mips/pmcs-msp71xx/msp_setup.c b/arch/mips/pmcs-msp71xx/msp_setup.c
index 4f925e06c414..78b2ef49dbc7 100644
--- a/arch/mips/pmcs-msp71xx/msp_setup.c
+++ b/arch/mips/pmcs-msp71xx/msp_setup.c
@@ -10,6 +10,8 @@
  * option) any later version.
  */
 
+#include <linux/delay.h>
+
 #include <asm/bootinfo.h>
 #include <asm/cacheflush.h>
 #include <asm/idle.h>
@@ -77,7 +79,7 @@ void msp7120_reset(void)
          */
 
         /* Wait a bit for the DDRC to settle */
-        for (i = 0; i < 100000000; i++);
+        mdelay(125);
 
 #if defined(CONFIG_PMC_MSP7120_GW)
         /*
diff --git a/arch/mips/sni/reset.c b/arch/mips/sni/reset.c
index 244f9427625b..db8f88b6a3af 100644
--- a/arch/mips/sni/reset.c
+++ b/arch/mips/sni/reset.c
@@ -3,6 +3,8 @@
  *
  *  Reset a SNI machine.
  */
+#include <linux/delay.h>
+
 #include <asm/io.h>
 #include <asm/reboot.h>
 #include <asm/sni.h>
@@ -32,9 +34,9 @@ void sni_machine_restart(char *command)
         for (;;) {
                 for (i = 0; i < 100; i++) {
                         kb_wait();
-                        for (j = 0; j < 100000 ; j++)
-                                /* nothing */;
+                        udelay(50);
                         outb_p(0xfe, 0x64);      /* pulse reset low */
+                        udelay(50);
                 }
         }
 }
diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig
index 4434b54e1d87..78ae5552fdb8 100644
--- a/arch/mn10300/Kconfig
+++ b/arch/mn10300/Kconfig
@@ -1,6 +1,7 @@
 config MN10300
         def_bool y
         select HAVE_OPROFILE
+        select HAVE_UID16
         select GENERIC_IRQ_SHOW
         select ARCH_WANT_IPC_PARSE_VERSION
         select HAVE_ARCH_TRACEHOOK
@@ -37,9 +38,6 @@ config HIGHMEM
 config NUMA
         def_bool n
 
-config UID16
-        def_bool y
-
 config RWSEM_GENERIC_SPINLOCK
         def_bool y
 
diff --git a/arch/nios2/mm/cacheflush.c b/arch/nios2/mm/cacheflush.c
index 223cdcc8203f..87bf88ed04c6 100644
--- a/arch/nios2/mm/cacheflush.c
+++ b/arch/nios2/mm/cacheflush.c
@@ -23,22 +23,6 @@ static void __flush_dcache(unsigned long start, unsigned long end)
         end += (cpuinfo.dcache_line_size - 1);
         end &= ~(cpuinfo.dcache_line_size - 1);
 
-        for (addr = start; addr < end; addr += cpuinfo.dcache_line_size) {
-                __asm__ __volatile__ ("   flushda 0(%0)\n"
-                                        : /* Outputs */
-                                        : /* Inputs  */ "r"(addr)
-                                        /* : No clobber */);
-        }
-}
-
-static void __flush_dcache_all(unsigned long start, unsigned long end)
-{
-        unsigned long addr;
-
-        start &= ~(cpuinfo.dcache_line_size - 1);
-        end += (cpuinfo.dcache_line_size - 1);
-        end &= ~(cpuinfo.dcache_line_size - 1);
-
         if (end > start + cpuinfo.dcache_size)
                 end = start + cpuinfo.dcache_size;
 
@@ -112,7 +96,7 @@ static void flush_aliases(struct address_space *mapping, struct page *page)
 
 void flush_cache_all(void)
 {
-        __flush_dcache_all(0, cpuinfo.dcache_size);
+        __flush_dcache(0, cpuinfo.dcache_size);
         __flush_icache(0, cpuinfo.icache_size);
 }
 
@@ -182,7 +166,7 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page)
          */
         unsigned long start = (unsigned long)page_address(page);
 
-        __flush_dcache_all(start, start + PAGE_SIZE);
+        __flush_dcache(start, start + PAGE_SIZE);
 }
 
 void flush_dcache_page(struct page *page)
@@ -268,7 +252,7 @@ void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
 {
         flush_cache_page(vma, user_vaddr, page_to_pfn(page));
         memcpy(dst, src, len);
-        __flush_dcache_all((unsigned long)src, (unsigned long)src + len);
+        __flush_dcache((unsigned long)src, (unsigned long)src + len);
         if (vma->vm_flags & VM_EXEC)
                 __flush_icache((unsigned long)src, (unsigned long)src + len);
 }
@@ -279,7 +263,7 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
 {
         flush_cache_page(vma, user_vaddr, page_to_pfn(page));
         memcpy(dst, src, len);
-        __flush_dcache_all((unsigned long)dst, (unsigned long)dst + len);
+        __flush_dcache((unsigned long)dst, (unsigned long)dst + len);
         if (vma->vm_flags & VM_EXEC)
                 __flush_icache((unsigned long)dst, (unsigned long)dst + len);
 }
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index d8534f95915a..291cee28ccb6 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -372,7 +372,8 @@ static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
  */
 #ifdef CONFIG_HUGETLB_PAGE
 #define pte_huge(pte)           (pte_val(pte) & _PAGE_HUGE)
-#define pte_mkhuge(pte)         (__pte(pte_val(pte) | _PAGE_HUGE))
+#define pte_mkhuge(pte)         (__pte(pte_val(pte) | \
+                                 (parisc_requires_coherency() ? 0 : _PAGE_HUGE)))
 #else
 #define pte_huge(pte)           (0)
 #define pte_mkhuge(pte)         (pte)
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index 33170384d3ac..35bdccbb2036 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -360,8 +360,9 @@
 #define __NR_execveat           (__NR_Linux + 342)
 #define __NR_membarrier         (__NR_Linux + 343)
 #define __NR_userfaultfd        (__NR_Linux + 344)
+#define __NR_mlock2             (__NR_Linux + 345)
 
-#define __NR_Linux_syscalls     (__NR_userfaultfd + 1)
+#define __NR_Linux_syscalls     (__NR_mlock2 + 1)
 
 
 #define __IGNORE_select         /* newselect */
diff --git a/arch/parisc/kernel/pci.c b/arch/parisc/kernel/pci.c
index 64f2764a8cef..c99f3dde455c 100644
--- a/arch/parisc/kernel/pci.c
+++ b/arch/parisc/kernel/pci.c
@@ -171,24 +171,6 @@ void pcibios_set_master(struct pci_dev *dev)
 }
 
 
-void __init pcibios_init_bus(struct pci_bus *bus)
-{
-        struct pci_dev *dev = bus->self;
-        unsigned short bridge_ctl;
-
-        /* We deal only with pci controllers and pci-pci bridges. */
-        if (!dev || (dev->class >> 8) != PCI_CLASS_BRIDGE_PCI)
-                return;
-
-        /* PCI-PCI bridge - set the cache line and default latency
-           (32) for primary and secondary buses. */
-        pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER, 32);
-
-        pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &bridge_ctl);
-        bridge_ctl |= PCI_BRIDGE_CTL_PARITY | PCI_BRIDGE_CTL_SERR;
-        pci_write_config_word(dev, PCI_BRIDGE_CONTROL, bridge_ctl);
-}
-
 /*
  * pcibios align resources() is called every time generic PCI code
  * wants to generate a new address. The process of looking for
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 78c3ef8c348d..d4ffcfbc9885 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -440,6 +440,7 @@
         ENTRY_COMP(execveat)
         ENTRY_SAME(membarrier)
         ENTRY_SAME(userfaultfd)
+        ENTRY_SAME(mlock2)              /* 345 */
 
 
 .ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b))
diff --git a/arch/powerpc/boot/dts/sbc8641d.dts b/arch/powerpc/boot/dts/sbc8641d.dts
index 631ede72e226..68f0ed7626bd 100644
--- a/arch/powerpc/boot/dts/sbc8641d.dts
+++ b/arch/powerpc/boot/dts/sbc8641d.dts
@@ -227,23 +227,15 @@
                                 reg = <0x520 0x20>;
 
                                 phy0: ethernet-phy@1f {
-                                        interrupt-parent = <&mpic>;
-                                        interrupts = <10 1>;
                                         reg = <0x1f>;
                                 };
                                 phy1: ethernet-phy@0 {
-                                        interrupt-parent = <&mpic>;
-                                        interrupts = <10 1>;
                                         reg = <0>;
                                 };
                                 phy2: ethernet-phy@1 {
-                                        interrupt-parent = <&mpic>;
-                                        interrupts = <10 1>;
                                         reg = <1>;
                                 };
                                 phy3: ethernet-phy@2 {
-                                        interrupt-parent = <&mpic>;
-                                        interrupts = <10 1>;
                                         reg = <2>;
                                 };
                                 tbi0: tbi-phy@11 {
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index a908ada8e0a5..2220f7a60def 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -108,6 +108,7 @@
 #define MSR_TS_T        __MASK(MSR_TS_T_LG)     /*  Transaction Transactional */
 #define MSR_TS_MASK     (MSR_TS_T | MSR_TS_S)   /* Transaction State bits */
 #define MSR_TM_ACTIVE(x) (((x) & MSR_TS_MASK) != 0) /* Transaction active? */
+#define MSR_TM_RESV(x) (((x) & MSR_TS_MASK) == MSR_TS_MASK) /* Reserved */
 #define MSR_TM_TRANSACTIONAL(x) (((x) & MSR_TS_MASK) == MSR_TS_T)
 #define MSR_TM_SUSPENDED(x)     (((x) & MSR_TS_MASK) == MSR_TS_S)
 
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 80dfe8965df9..8d14feb40f12 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -590,16 +590,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
         eeh_ops->configure_bridge(pe);
         eeh_pe_restore_bars(pe);
 
-        /*
-         * If it's PHB PE, the frozen state on all available PEs should have
-         * been cleared by the PHB reset. Otherwise, we unfreeze the PE and its
-         * child PEs because they might be in frozen state.
-         */
-        if (!(pe->type & EEH_PE_PHB)) {
-                rc = eeh_clear_pe_frozen_state(pe, false);
-                if (rc)
-                        return rc;
-        }
+        /* Clear frozen state */
+        rc = eeh_clear_pe_frozen_state(pe, false);
+        if (rc)
+                return rc;
 
         /* Give the system 5 seconds to finish running the user-space
          * hotplug shutdown scripts, e.g. ifdown for ethernet.  Yes,
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 75b6676c1a0b..646bf4d222c1 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -551,6 +551,24 @@ static void tm_reclaim_thread(struct thread_struct *thr,
                 msr_diff &= MSR_FP | MSR_VEC | MSR_VSX | MSR_FE0 | MSR_FE1;
         }
 
+        /*
+         * Use the current MSR TM suspended bit to track if we have
+         * checkpointed state outstanding.
+         * On signal delivery, we'd normally reclaim the checkpointed
+         * state to obtain stack pointer (see:get_tm_stackpointer()).
+         * This will then directly return to userspace without going
+         * through __switch_to(). However, if the stack frame is bad,
+         * we need to exit this thread which calls __switch_to() which
+         * will again attempt to reclaim the already saved tm state.
+         * Hence we need to check that we've not already reclaimed
+         * this state.
+         * We do this using the current MSR, rather tracking it in
+         * some specific thread_struct bit, as it has the additional
+         * benifit of checking for a potential TM bad thing exception.
+         */
+        if (!MSR_TM_SUSPENDED(mfmsr()))
+                return;
+
         tm_reclaim(thr, thr->regs->msr, cause);
 
         /* Having done the reclaim, we now have the checkpointed
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 0dbee465af7a..ef7c24e84a62 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -875,6 +875,15 @@ static long restore_tm_user_regs(struct pt_regs *regs,
                 return 1;
 #endif /* CONFIG_SPE */
 
+        /* Get the top half of the MSR from the user context */
+        if (__get_user(msr_hi, &tm_sr->mc_gregs[PT_MSR]))
+                return 1;
+        msr_hi <<= 32;
+        /* If TM bits are set to the reserved value, it's an invalid context */
+        if (MSR_TM_RESV(msr_hi))
+                return 1;
+        /* Pull in the MSR TM bits from the user context */
+        regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr_hi & MSR_TS_MASK);
         /* Now, recheckpoint.  This loads up all of the checkpointed (older)
          * registers, including FP and V[S]Rs.  After recheckpointing, the
          * transactional versions should be loaded.
@@ -884,11 +893,6 @@ static long restore_tm_user_regs(struct pt_regs *regs,
         current->thread.tm_texasr |= TEXASR_FS;
         /* This loads the checkpointed FP/VEC state, if used */
         tm_recheckpoint(&current->thread, msr);
-        /* Get the top half of the MSR */
-        if (__get_user(msr_hi, &tm_sr->mc_gregs[PT_MSR]))
-                return 1;
-        /* Pull in MSR TM from user context */
-        regs->msr = (regs->msr & ~MSR_TS_MASK) | ((msr_hi<<32) & MSR_TS_MASK);
 
         /* This loads the speculative FP/VEC state, if used */
         if (msr & MSR_FP) {
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 20756dfb9f34..c676ecec0869 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -438,6 +438,10 @@ static long restore_tm_sigcontexts(struct pt_regs *regs,
 
         /* get MSR separately, transfer the LE bit if doing signal return */
         err |= __get_user(msr, &sc->gp_regs[PT_MSR]);
+        /* Don't allow reserved mode. */
+        if (MSR_TM_RESV(msr))
+                return -EINVAL;
+
         /* pull in MSR TM from user context */
         regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK);
 
diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c
index 6ccfb6c1c707..0a00e2aed393 100644
--- a/arch/powerpc/platforms/powernv/opal-irqchip.c
+++ b/arch/powerpc/platforms/powernv/opal-irqchip.c
@@ -43,11 +43,34 @@ static unsigned int opal_irq_count;
 static unsigned int *opal_irqs;
 
 static void opal_handle_irq_work(struct irq_work *work);
-static __be64 last_outstanding_events;
+static u64 last_outstanding_events;
 static struct irq_work opal_event_irq_work = {
         .func = opal_handle_irq_work,
 };
 
+void opal_handle_events(uint64_t events)
+{
+        int virq, hwirq = 0;
+        u64 mask = opal_event_irqchip.mask;
+
+        if (!in_irq() && (events & mask)) {
+                last_outstanding_events = events;
+                irq_work_queue(&opal_event_irq_work);
+                return;
+        }
+
+        while (events & mask) {
+                hwirq = fls64(events) - 1;
+                if (BIT_ULL(hwirq) & mask) {
+                        virq = irq_find_mapping(opal_event_irqchip.domain,
+                                                hwirq);
+                        if (virq)
+                                generic_handle_irq(virq);
+                }
+                events &= ~BIT_ULL(hwirq);
+        }
+}
+
 static void opal_event_mask(struct irq_data *d)
 {
         clear_bit(d->hwirq, &opal_event_irqchip.mask);
@@ -55,12 +78,12 @@ static void opal_event_mask(struct irq_data *d)
 
 static void opal_event_unmask(struct irq_data *d)
 {
+        __be64 events;
+
         set_bit(d->hwirq, &opal_event_irqchip.mask);
 
-        opal_poll_events(&last_outstanding_events);
-        if (last_outstanding_events & opal_event_irqchip.mask)
-                /* Need to retrigger the interrupt */
-                irq_work_queue(&opal_event_irq_work);
+        opal_poll_events(&events);
+        opal_handle_events(be64_to_cpu(events));
 }
 
 static int opal_event_set_type(struct irq_data *d, unsigned int flow_type)
@@ -96,29 +119,6 @@ static int opal_event_map(struct irq_domain *d, unsigned int irq,
         return 0;
 }
 
-void opal_handle_events(uint64_t events)
-{
-        int virq, hwirq = 0;
-        u64 mask = opal_event_irqchip.mask;
-
-        if (!in_irq() && (events & mask)) {
-                last_outstanding_events = events;
-                irq_work_queue(&opal_event_irq_work);
-                return;
-        }
-
-        while (events & mask) {
-                hwirq = fls64(events) - 1;
-                if (BIT_ULL(hwirq) & mask) {
-                        virq = irq_find_mapping(opal_event_irqchip.domain,
-                                                hwirq);
-                        if (virq)
-                                generic_handle_irq(virq);
-                }
-                events &= ~BIT_ULL(hwirq);
-        }
-}
-
 static irqreturn_t opal_interrupt(int irq, void *data)
 {
         __be64 events;
@@ -131,7 +131,7 @@ static irqreturn_t opal_interrupt(int irq, void *data)
 
 static void opal_handle_irq_work(struct irq_work *work)
 {
-        opal_handle_events(be64_to_cpu(last_outstanding_events));
+        opal_handle_events(last_outstanding_events);
 }
 
 static int opal_event_match(struct irq_domain *h, struct device_node *node,
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 373e32346d68..6a75352f453c 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1030,8 +1030,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
                                    src_id, 0);
 
         /* sending vcpu invalid */
-        if (src_id >= KVM_MAX_VCPUS ||
-            kvm_get_vcpu(vcpu->kvm, src_id) == NULL)
+        if (kvm_get_vcpu_by_id(vcpu->kvm, src_id) == NULL)
                 return -EINVAL;
 
         if (sclp.has_sigpif)
@@ -1110,6 +1109,10 @@ static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
         trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
                                    irq->u.emerg.code, 0);
 
+        /* sending vcpu invalid */
+        if (kvm_get_vcpu_by_id(vcpu->kvm, irq->u.emerg.code) == NULL)
+                return -EINVAL;
+
         set_bit(irq->u.emerg.code, li->sigp_emerg_pending);
         set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
         atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 8fe2f1c722dc..846589281b04 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -342,12 +342,16 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
                 r = 0;
                 break;
         case KVM_CAP_S390_VECTOR_REGISTERS:
-                if (MACHINE_HAS_VX) {
+                mutex_lock(&kvm->lock);
+                if (atomic_read(&kvm->online_vcpus)) {
+                        r = -EBUSY;
+                } else if (MACHINE_HAS_VX) {
                         set_kvm_facility(kvm->arch.model.fac->mask, 129);
                         set_kvm_facility(kvm->arch.model.fac->list, 129);
                         r = 0;
                 } else
                         r = -EINVAL;
+                mutex_unlock(&kvm->lock);
                 VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s",
                          r ? "(not available)" : "(success)");
                 break;
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 77191b85ea7a..d76b51cb4b62 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -660,7 +660,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 
         kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
 
-        if (!MACHINE_HAS_PFMF)
+        if (!test_kvm_facility(vcpu->kvm, 8))
                 return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
 
         if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index da690b69f9fe..77c22d685c7a 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -291,12 +291,8 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code,
                            u16 cpu_addr, u32 parameter, u64 *status_reg)
 {
         int rc;
-        struct kvm_vcpu *dst_vcpu;
+        struct kvm_vcpu *dst_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr);
 
-        if (cpu_addr >= KVM_MAX_VCPUS)
-                return SIGP_CC_NOT_OPERATIONAL;
-
-        dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
         if (!dst_vcpu)
                 return SIGP_CC_NOT_OPERATIONAL;
 
@@ -478,7 +474,7 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu)
         trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr);
 
         if (order_code == SIGP_EXTERNAL_CALL) {
-                dest_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+                dest_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr);
                 BUG_ON(dest_vcpu == NULL);
 
                 kvm_s390_vcpu_wakeup(dest_vcpu);
diff --git a/arch/sh/include/uapi/asm/unistd_64.h b/arch/sh/include/uapi/asm/unistd_64.h
index e6820c86e8c7..47ebd5b5ed55 100644
--- a/arch/sh/include/uapi/asm/unistd_64.h
+++ b/arch/sh/include/uapi/asm/unistd_64.h
@@ -278,7 +278,7 @@
 #define __NR_fsetxattr          256
 #define __NR_getxattr           257
 #define __NR_lgetxattr          258
-#define __NR_fgetxattr          269
+#define __NR_fgetxattr          259
 #define __NR_listxattr          260
 #define __NR_llistxattr         261
 #define __NR_flistxattr         262
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 7cfd7f153966..4dca18347ee9 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -10,7 +10,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *
  * ppc:
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index b0da5aedb336..3091267c5cc3 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -9,7 +9,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/perf_event.h>
diff --git a/arch/tile/kernel/perf_event.c b/arch/tile/kernel/perf_event.c
index bb509cee3b59..8767060d70fb 100644
--- a/arch/tile/kernel/perf_event.c
+++ b/arch/tile/kernel/perf_event.c
@@ -21,7 +21,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  */
diff --git a/arch/um/Makefile b/arch/um/Makefile
index 25ed4098640e..e3abe6f3156d 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -131,7 +131,7 @@ export LDS_ELF_FORMAT := $(ELF_FORMAT)
 # The wrappers will select whether using "malloc" or the kernel allocator.
 LINK_WRAPS = -Wl,--wrap,malloc -Wl,--wrap,free -Wl,--wrap,calloc
 
-LD_FLAGS_CMDLINE = $(foreach opt,$(LDFLAGS),-Wl,$(opt)) -lrt
+LD_FLAGS_CMDLINE = $(foreach opt,$(LDFLAGS),-Wl,$(opt))
 
 # Used by link-vmlinux.sh which has special support for um link
 export CFLAGS_vmlinux := $(LINK-y) $(LINK_WRAPS) $(LD_FLAGS_CMDLINE)
diff --git a/arch/um/drivers/net_user.c b/arch/um/drivers/net_user.c
index e697a4136707..e9f8445861dc 100644
--- a/arch/um/drivers/net_user.c
+++ b/arch/um/drivers/net_user.c
@@ -249,21 +249,23 @@ void close_addr(unsigned char *addr, unsigned char *netmask, void *arg)
 
 char *split_if_spec(char *str, ...)
 {
-        char **arg, *end;
+        char **arg, *end, *ret = NULL;
         va_list ap;
 
         va_start(ap, str);
         while ((arg = va_arg(ap, char **)) != NULL) {
                 if (*str == '\0')
-                        return NULL;
+                        goto out;
                 end = strchr(str, ',');
                 if (end != str)
                         *arg = str;
                 if (end == NULL)
-                        return NULL;
+                        goto out;
                 *end++ = '\0';
                 str = end;
         }
+        ret = str;
+out:
         va_end(ap);
-        return str;
+        return ret;
 }
diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c
index 57acbd67d85d..fc8be0e3a4ff 100644
--- a/arch/um/kernel/signal.c
+++ b/arch/um/kernel/signal.c
@@ -69,7 +69,7 @@ void do_signal(struct pt_regs *regs)
         struct ksignal ksig;
         int handled_sig = 0;
 
-        while (get_signal(&ksig)) {
+        if (get_signal(&ksig)) {
                 handled_sig = 1;
                 /* Whee!  Actually deliver the signal.  */
                 handle_signal(&ksig, regs);
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 0033e96c3f09..9011a88353de 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -23,7 +23,6 @@
 #include <stdarg.h>
 #include <linux/types.h>
 #include <linux/edd.h>
-#include <asm/boot.h>
 #include <asm/setup.h>
 #include "bitops.h"
 #include "ctype.h"
diff --git a/arch/x86/boot/video-mode.c b/arch/x86/boot/video-mode.c
index aa8a96b052e3..95c7a818c0ed 100644
--- a/arch/x86/boot/video-mode.c
+++ b/arch/x86/boot/video-mode.c
@@ -19,6 +19,8 @@
 #include "video.h"
 #include "vesa.h"
 
+#include <uapi/asm/boot.h>
+
 /*
  * Common variables
  */
diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c
index 05111bb8d018..77780e386e9b 100644
--- a/arch/x86/boot/video.c
+++ b/arch/x86/boot/video.c
@@ -13,6 +13,8 @@
  * Select video mode
  */
 
+#include <uapi/asm/boot.h>
+
 #include "boot.h"
 #include "video.h"
 #include "vesa.h"
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 53616ca03244..a55697d19824 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -509,6 +509,17 @@ END(irq_entries_start)
          * tracking that we're in kernel mode.
          */
         SWAPGS
+
+        /*
+         * We need to tell lockdep that IRQs are off.  We can't do this until
+         * we fix gsbase, and we should do it before enter_from_user_mode
+         * (which can take locks).  Since TRACE_IRQS_OFF idempotent,
+         * the simplest way to handle it is to just call it twice if
+         * we enter from user mode.  There's no reason to optimize this since
+         * TRACE_IRQS_OFF is a no-op if lockdep is off.
+         */
+        TRACE_IRQS_OFF
+
 #ifdef CONFIG_CONTEXT_TRACKING
         call enter_from_user_mode
 #endif
@@ -1049,12 +1060,18 @@ ENTRY(error_entry)
         SWAPGS
 
 .Lerror_entry_from_usermode_after_swapgs:
+        /*
+         * We need to tell lockdep that IRQs are off.  We can't do this until
+         * we fix gsbase, and we should do it before enter_from_user_mode
+         * (which can take locks).
+         */
+        TRACE_IRQS_OFF
 #ifdef CONFIG_CONTEXT_TRACKING
         call enter_from_user_mode
 #endif
+        ret
 
 .Lerror_entry_done:
-
         TRACE_IRQS_OFF
         ret
 
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index c5b7fb2774d0..cc071c6f7d4d 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -9,19 +9,21 @@
 #define PAGE_SIZE       (_AC(1,UL) << PAGE_SHIFT)
 #define PAGE_MASK       (~(PAGE_SIZE-1))
 
+#define PMD_PAGE_SIZE           (_AC(1, UL) << PMD_SHIFT)
+#define PMD_PAGE_MASK           (~(PMD_PAGE_SIZE-1))
+
+#define PUD_PAGE_SIZE           (_AC(1, UL) << PUD_SHIFT)
+#define PUD_PAGE_MASK           (~(PUD_PAGE_SIZE-1))
+
 #define __PHYSICAL_MASK         ((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1))
 #define __VIRTUAL_MASK          ((1UL << __VIRTUAL_MASK_SHIFT) - 1)
 
-/* Cast PAGE_MASK to a signed type so that it is sign-extended if
+/* Cast *PAGE_MASK to a signed type so that it is sign-extended if
    virtual addresses are 32-bits but physical addresses are larger
    (ie, 32-bit PAE). */
 #define PHYSICAL_PAGE_MASK      (((signed long)PAGE_MASK) & __PHYSICAL_MASK)
-
-#define PMD_PAGE_SIZE           (_AC(1, UL) << PMD_SHIFT)
-#define PMD_PAGE_MASK           (~(PMD_PAGE_SIZE-1))
-
-#define PUD_PAGE_SIZE           (_AC(1, UL) << PUD_SHIFT)
-#define PUD_PAGE_MASK           (~(PUD_PAGE_SIZE-1))
+#define PHYSICAL_PMD_PAGE_MASK  (((signed long)PMD_PAGE_MASK) & __PHYSICAL_MASK)
+#define PHYSICAL_PUD_PAGE_MASK  (((signed long)PUD_PAGE_MASK) & __PHYSICAL_MASK)
 
 #define HPAGE_SHIFT             PMD_SHIFT
 #define HPAGE_SIZE              (_AC(1,UL) << HPAGE_SHIFT)
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index dd5b0aa9dd2f..a471cadb9630 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -279,17 +279,14 @@ static inline pmdval_t native_pmd_val(pmd_t pmd)
 static inline pudval_t pud_pfn_mask(pud_t pud)
 {
         if (native_pud_val(pud) & _PAGE_PSE)
-                return PUD_PAGE_MASK & PHYSICAL_PAGE_MASK;
+                return PHYSICAL_PUD_PAGE_MASK;
         else
                 return PTE_PFN_MASK;
 }
 
 static inline pudval_t pud_flags_mask(pud_t pud)
 {
-        if (native_pud_val(pud) & _PAGE_PSE)
-                return ~(PUD_PAGE_MASK & (pudval_t)PHYSICAL_PAGE_MASK);
-        else
-                return ~PTE_PFN_MASK;
+        return ~pud_pfn_mask(pud);
 }
 
 static inline pudval_t pud_flags(pud_t pud)
@@ -300,17 +297,14 @@ static inline pudval_t pud_flags(pud_t pud)
 static inline pmdval_t pmd_pfn_mask(pmd_t pmd)
 {
         if (native_pmd_val(pmd) & _PAGE_PSE)
-                return PMD_PAGE_MASK & PHYSICAL_PAGE_MASK;
+                return PHYSICAL_PMD_PAGE_MASK;
         else
                 return PTE_PFN_MASK;
 }
 
 static inline pmdval_t pmd_flags_mask(pmd_t pmd)
 {
-        if (native_pmd_val(pmd) & _PAGE_PSE)
-                return ~(PMD_PAGE_MASK & (pmdval_t)PHYSICAL_PAGE_MASK);
-        else
-                return ~PTE_PFN_MASK;
+        return ~pmd_pfn_mask(pmd);
 }
 
 static inline pmdval_t pmd_flags(pmd_t pmd)
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 48d34d28f5a6..cd0fc0cc78bc 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -1,7 +1,6 @@
 #ifndef _ASM_X86_PLATFORM_H
 #define _ASM_X86_PLATFORM_H
 
-#include <asm/pgtable_types.h>
 #include <asm/bootparam.h>
 
 struct mpc_bus;
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 7fc27f1cca58..b3e94ef461fd 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -698,3 +698,4 @@ int __init microcode_init(void)
         return error;
 
 }
+late_initcall(microcode_init);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 4562cf070c27..2bf79d7c97df 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -5,7 +5,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  *
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 499f533dd3cc..d0e35ebb2adb 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -5,7 +5,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  *
@@ -387,7 +387,7 @@ struct cpu_hw_events {
 /* Check flags and event code/umask, and set the HSW N/A flag */
 #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \
         __EVENT_CONSTRAINT(code, n,                     \
-                          INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \
+                          INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
                           HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW)
 
 
@@ -627,6 +627,7 @@ struct x86_perf_task_context {
         u64 lbr_from[MAX_LBR_ENTRIES];
         u64 lbr_to[MAX_LBR_ENTRIES];
         u64 lbr_info[MAX_LBR_ENTRIES];
+        int tos;
         int lbr_callstack_users;
         int lbr_stack_state;
 };
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index f63360be2238..e2a430021e46 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -232,7 +232,7 @@ static struct event_constraint intel_hsw_event_constraints[] = {
         FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
         FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
         FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
-        INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.* */
+        INTEL_UEVENT_CONSTRAINT(0x148, 0x4),    /* L1D_PEND_MISS.PENDING */
         INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
         INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
         /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index 377e8f8ed391..a316ca96f1b6 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -298,7 +298,7 @@ static bool __match_event(struct perf_event *a, struct perf_event *b)
 static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event)
 {
         if (event->attach_state & PERF_ATTACH_TASK)
-                return perf_cgroup_from_task(event->hw.target);
+                return perf_cgroup_from_task(event->hw.target, event->ctx);
 
         return event->cgrp;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index bfd0b717e944..659f01e165d5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -239,7 +239,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
         }
 
         mask = x86_pmu.lbr_nr - 1;
-        tos = intel_pmu_lbr_tos();
+        tos = task_ctx->tos;
         for (i = 0; i < tos; i++) {
                 lbr_idx = (tos - i) & mask;
                 wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
@@ -247,6 +247,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
                 if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
                         wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
         }
+        wrmsrl(x86_pmu.lbr_tos, tos);
         task_ctx->lbr_stack_state = LBR_NONE;
 }
 
@@ -270,6 +271,7 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
                 if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
                         rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
         }
+        task_ctx->tos = tos;
         task_ctx->lbr_stack_state = LBR_VALID;
 }
 
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index dc5fa6a1e8d6..3512ba607361 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -1,7 +1,7 @@
 /*
  * x86 specific code for irq_work
  *
- * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/kernel.h>
diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c
index 4f00b63d7ff3..14415aff1813 100644
--- a/arch/x86/kernel/pmem.c
+++ b/arch/x86/kernel/pmem.c
@@ -4,10 +4,22 @@
  */
 #include <linux/platform_device.h>
 #include <linux/module.h>
+#include <linux/ioport.h>
+
+static int found(u64 start, u64 end, void *data)
+{
+        return 1;
+}
 
 static __init int register_e820_pmem(void)
 {
+        char *pmem = "Persistent Memory (legacy)";
         struct platform_device *pdev;
+        int rc;
+
+        rc = walk_iomem_res(pmem, IORESOURCE_MEM, 0, -1, NULL, found);
+        if (rc <= 0)
+                return 0;
 
         /*
          * See drivers/nvdimm/e820.c for the implementation, this is
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 29db25f9a745..d2bbe343fda7 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1250,8 +1250,6 @@ void __init setup_arch(char **cmdline_p)
         if (efi_enabled(EFI_BOOT))
                 efi_apply_memmap_quirks();
 #endif
-
-        microcode_init();
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index b7ffb7c00075..cb6282c3638f 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -690,12 +690,15 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
         signal_setup_done(failed, ksig, stepping);
 }
 
-#ifdef CONFIG_X86_32
-#define NR_restart_syscall      __NR_restart_syscall
-#else /* !CONFIG_X86_32 */
-#define NR_restart_syscall      \
-        test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : __NR_restart_syscall
-#endif /* CONFIG_X86_32 */
+static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
+{
+#if defined(CONFIG_X86_32) || !defined(CONFIG_X86_64)
+        return __NR_restart_syscall;
+#else /* !CONFIG_X86_32 && CONFIG_X86_64 */
+        return test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall :
+                __NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT);
+#endif /* CONFIG_X86_32 || !CONFIG_X86_64 */
+}
 
 /*
  * Note that 'init' is a special process: it doesn't get signals it doesn't
@@ -724,7 +727,7 @@ void do_signal(struct pt_regs *regs)
                         break;
 
                 case -ERESTART_RESTARTBLOCK:
-                        regs->ax = NR_restart_syscall;
+                        regs->ax = get_nr_restart_syscall(regs);
                         regs->ip -= 2;
                         break;
                 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 892ee2e5ecbc..fbabe4fcc7fb 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -509,7 +509,7 @@ void __inquire_remote_apic(int apicid)
  */
 #define UDELAY_10MS_DEFAULT 10000
 
-static unsigned int init_udelay = INT_MAX;
+static unsigned int init_udelay = UINT_MAX;
 
 static int __init cpu_init_udelay(char *str)
 {
@@ -522,14 +522,15 @@ early_param("cpu_init_udelay", cpu_init_udelay);
 static void __init smp_quirk_init_udelay(void)
 {
         /* if cmdline changed it from default, leave it alone */
-        if (init_udelay != INT_MAX)
+        if (init_udelay != UINT_MAX)
                 return;
 
         /* if modern processor, use no delay */
         if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
-            ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF)))
+            ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) {
                 init_udelay = 0;
-
+                return;
+        }
         /* else, use legacy delay */
         init_udelay = UDELAY_10MS_DEFAULT;
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 87acc5221740..af823a388c19 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -7394,11 +7394,6 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 
         switch (type) {
         case VMX_VPID_EXTENT_ALL_CONTEXT:
-                if (get_vmcs12(vcpu)->virtual_processor_id == 0) {
-                        nested_vmx_failValid(vcpu,
-                                VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
-                        return 1;
-                }
                 __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
                 nested_vmx_succeed(vcpu);
                 break;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 00462bd63129..eed32283d22c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2763,6 +2763,26 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
         return 0;
 }
 
+static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu)
+{
+        return (!lapic_in_kernel(vcpu) ||
+                kvm_apic_accept_pic_intr(vcpu));
+}
+
+/*
+ * if userspace requested an interrupt window, check that the
+ * interrupt window is open.
+ *
+ * No need to exit to userspace if we already have an interrupt queued.
+ */
+static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
+{
+        return kvm_arch_interrupt_allowed(vcpu) &&
+                !kvm_cpu_has_interrupt(vcpu) &&
+                !kvm_event_needs_reinjection(vcpu) &&
+                kvm_cpu_accept_dm_intr(vcpu);
+}
+
 static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
                                     struct kvm_interrupt *irq)
 {
@@ -2786,6 +2806,7 @@ static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
                 return -EEXIST;
 
         vcpu->arch.pending_external_vector = irq->irq;
+        kvm_make_request(KVM_REQ_EVENT, vcpu);
         return 0;
 }
 
@@ -5910,23 +5931,10 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt)
         return emulator_write_emulated(ctxt, rip, instruction, 3, NULL);
 }
 
-/*
- * Check if userspace requested an interrupt window, and that the
- * interrupt window is open.
- *
- * No need to exit to userspace if we already have an interrupt queued.
- */
 static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu)
 {
-        if (!vcpu->run->request_interrupt_window || pic_in_kernel(vcpu->kvm))
-                return false;
-
-        if (kvm_cpu_has_interrupt(vcpu))
-                return false;
-
-        return (irqchip_split(vcpu->kvm)
-                ? kvm_apic_accept_pic_intr(vcpu)
-                : kvm_arch_interrupt_allowed(vcpu));
+        return vcpu->run->request_interrupt_window &&
+                likely(!pic_in_kernel(vcpu->kvm));
 }
 
 static void post_kvm_run_save(struct kvm_vcpu *vcpu)
@@ -5937,17 +5945,9 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
         kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0;
         kvm_run->cr8 = kvm_get_cr8(vcpu);
         kvm_run->apic_base = kvm_get_apic_base(vcpu);
-        if (!irqchip_in_kernel(vcpu->kvm))
-                kvm_run->ready_for_interrupt_injection =
-                        kvm_arch_interrupt_allowed(vcpu) &&
-                        !kvm_cpu_has_interrupt(vcpu) &&
-                        !kvm_event_needs_reinjection(vcpu);
-        else if (!pic_in_kernel(vcpu->kvm))
-                kvm_run->ready_for_interrupt_injection =
-                        kvm_apic_accept_pic_intr(vcpu) &&
-                        !kvm_cpu_has_interrupt(vcpu);
-        else
-                kvm_run->ready_for_interrupt_injection = 1;
+        kvm_run->ready_for_interrupt_injection =
+                pic_in_kernel(vcpu->kvm) ||
+                kvm_vcpu_ready_for_interrupt_injection(vcpu);
 }
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu)
@@ -6360,8 +6360,10 @@ void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
 static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 {
         int r;
-        bool req_int_win = !lapic_in_kernel(vcpu) &&
-                vcpu->run->request_interrupt_window;
+        bool req_int_win =
+                dm_request_for_irq_injection(vcpu) &&
+                kvm_cpu_accept_dm_intr(vcpu);
+
         bool req_immediate_exit = false;
 
         if (vcpu->requests) {
@@ -6663,7 +6665,8 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
                 if (kvm_cpu_has_pending_timer(vcpu))
                         kvm_inject_pending_timer_irqs(vcpu);
 
-                if (dm_request_for_irq_injection(vcpu)) {
+                if (dm_request_for_irq_injection(vcpu) &&
+                        kvm_vcpu_ready_for_interrupt_injection(vcpu)) {
                         r = 0;
                         vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
                         ++vcpu->stat.request_irq_exits;
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 1202d5ca2fb5..b2fd67da1701 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -101,19 +101,19 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
         switch (type) {
         case REG_TYPE_RM:
                 regno = X86_MODRM_RM(insn->modrm.value);
-                if (X86_REX_B(insn->rex_prefix.value) == 1)
+                if (X86_REX_B(insn->rex_prefix.value))
                         regno += 8;
                 break;
 
         case REG_TYPE_INDEX:
                 regno = X86_SIB_INDEX(insn->sib.value);
-                if (X86_REX_X(insn->rex_prefix.value) == 1)
+                if (X86_REX_X(insn->rex_prefix.value))
                         regno += 8;
                 break;
 
         case REG_TYPE_BASE:
                 regno = X86_SIB_BASE(insn->sib.value);
-                if (X86_REX_B(insn->rex_prefix.value) == 1)
+                if (X86_REX_B(insn->rex_prefix.value))
                         regno += 8;
                 break;
 
diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c
index 7bcf06a7cd12..6eb3c8af96e2 100644
--- a/arch/x86/pci/bus_numa.c
+++ b/arch/x86/pci/bus_numa.c
@@ -50,18 +50,9 @@ void x86_pci_root_bus_resources(int bus, struct list_head *resources)
         if (!found)
                 pci_add_resource(resources, &info->busn);
 
-        list_for_each_entry(root_res, &info->resources, list) {
-                struct resource *res;
-                struct resource *root;
+        list_for_each_entry(root_res, &info->resources, list)
+                pci_add_resource(resources, &root_res->res);
 
-                res = &root_res->res;
-                pci_add_resource(resources, res);
-                if (res->flags & IORESOURCE_IO)
-                        root = &ioport_resource;
-                else
-                        root = &iomem_resource;
-                insert_resource(root, res);
-        }
         return;
 
 default_resources:
diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c
index 06934a8a4872..e5f854ce2d72 100644
--- a/arch/x86/um/signal.c
+++ b/arch/x86/um/signal.c
@@ -211,7 +211,7 @@ static int copy_sc_from_user(struct pt_regs *regs,
                 if (err)
                         return 1;
 
-                err = convert_fxsr_from_user(&fpx, sc.fpstate);
+                err = convert_fxsr_from_user(&fpx, (void *)sc.fpstate);
                 if (err)
                         return 1;
 
@@ -227,7 +227,7 @@ static int copy_sc_from_user(struct pt_regs *regs,
         {
                 struct user_i387_struct fp;
 
-                err = copy_from_user(&fp, sc.fpstate,
+                err = copy_from_user(&fp, (void *)sc.fpstate,
                                      sizeof(struct user_i387_struct));
                 if (err)
                         return 1;
@@ -291,7 +291,7 @@ static int copy_sc_to_user(struct sigcontext __user *to,
 #endif
 #undef PUTREG
         sc.oldmask = mask;
-        sc.fpstate = to_fp;
+        sc.fpstate = (unsigned long)to_fp;
 
         err = copy_to_user(to, &sc, sizeof(struct sigcontext));
         if (err)
@@ -468,12 +468,10 @@ long sys_sigreturn(void)
         struct sigframe __user *frame = (struct sigframe __user *)(sp - 8);
         sigset_t set;
         struct sigcontext __user *sc = &frame->sc;
-        unsigned long __user *oldmask = &sc->oldmask;
-        unsigned long __user *extramask = frame->extramask;
         int sig_size = (_NSIG_WORDS - 1) * sizeof(unsigned long);
 
-        if (copy_from_user(&set.sig[0], oldmask, sizeof(set.sig[0])) ||
-            copy_from_user(&set.sig[1], extramask, sig_size))
+        if (copy_from_user(&set.sig[0], (void *)sc->oldmask, sizeof(set.sig[0])) ||
+            copy_from_user(&set.sig[1], frame->extramask, sig_size))
                 goto segfault;
 
         set_current_blocked(&set);
@@ -505,6 +503,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig,
 {
         struct rt_sigframe __user *frame;
         int err = 0, sig = ksig->sig;
+        unsigned long fp_to;
 
         frame = (struct rt_sigframe __user *)
                 round_down(stack_top - sizeof(struct rt_sigframe), 16);
@@ -526,7 +525,10 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig,
         err |= __save_altstack(&frame->uc.uc_stack, PT_REGS_SP(regs));
         err |= copy_sc_to_user(&frame->uc.uc_mcontext, &frame->fpstate, regs,
                                set->sig[0]);
-        err |= __put_user(&frame->fpstate, &frame->uc.uc_mcontext.fpstate);
+
+        fp_to = (unsigned long)&frame->fpstate;
+
+        err |= __put_user(fp_to, &frame->uc.uc_mcontext.fpstate);
         if (sizeof(*set) == 16) {
                 err |= __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]);
                 err |= __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 5bcdfc10c23a..5a37188b559f 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1127,15 +1127,15 @@ void blkcg_exit_queue(struct request_queue *q)
  * of the main cic data structures.  For now we allow a task to change
  * its cgroup only if it's the only owner of its ioc.
  */
-static int blkcg_can_attach(struct cgroup_subsys_state *css,
-                            struct cgroup_taskset *tset)
+static int blkcg_can_attach(struct cgroup_taskset *tset)
 {
         struct task_struct *task;
+        struct cgroup_subsys_state *dst_css;
         struct io_context *ioc;
         int ret = 0;
 
         /* task_lock() is needed to avoid races with exit_io_context() */
-        cgroup_taskset_for_each(task, tset) {
+        cgroup_taskset_for_each(task, dst_css, tset) {
                 task_lock(task);
                 ioc = task->io_context;
                 if (ioc && atomic_read(&ioc->nr_tasks) > 1)
diff --git a/block/blk-core.c b/block/blk-core.c
index 5131993b23a1..3636be469fa2 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2114,7 +2114,8 @@ blk_qc_t submit_bio(int rw, struct bio *bio)
 EXPORT_SYMBOL(submit_bio);
 
 /**
- * blk_rq_check_limits - Helper function to check a request for the queue limit
+ * blk_cloned_rq_check_limits - Helper function to check a cloned request
+ *                              for new the queue limits
  * @q:  the queue
  * @rq: the request being checked
  *
@@ -2125,20 +2126,13 @@ EXPORT_SYMBOL(submit_bio);
  *    after it is inserted to @q, it should be checked against @q before
  *    the insertion using this generic function.
  *
- *    This function should also be useful for request stacking drivers
- *    in some cases below, so export this function.
  *    Request stacking drivers like request-based dm may change the queue
- *    limits while requests are in the queue (e.g. dm's table swapping).
- *    Such request stacking drivers should check those requests against
- *    the new queue limits again when they dispatch those requests,
- *    although such checkings are also done against the old queue limits
- *    when submitting requests.
+ *    limits when retrying requests on other queues. Those requests need
+ *    to be checked against the new queue limits again during dispatch.
  */
-int blk_rq_check_limits(struct request_queue *q, struct request *rq)
+static int blk_cloned_rq_check_limits(struct request_queue *q,
+                                      struct request *rq)
 {
-        if (!rq_mergeable(rq))
-                return 0;
-
         if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, rq->cmd_flags)) {
                 printk(KERN_ERR "%s: over max size limit.\n", __func__);
                 return -EIO;
@@ -2158,7 +2152,6 @@ int blk_rq_check_limits(struct request_queue *q, struct request *rq)
 
         return 0;
 }
-EXPORT_SYMBOL_GPL(blk_rq_check_limits);
 
 /**
  * blk_insert_cloned_request - Helper for stacking drivers to submit a request
@@ -2170,7 +2163,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
         unsigned long flags;
         int where = ELEVATOR_INSERT_BACK;
 
-        if (blk_rq_check_limits(q, rq))
+        if (blk_cloned_rq_check_limits(q, rq))
                 return -EIO;
 
         if (rq->rq_disk &&
@@ -3412,6 +3405,9 @@ int blk_pre_runtime_suspend(struct request_queue *q)
 {
         int ret = 0;
 
+        if (!q->dev)
+                return ret;
+
         spin_lock_irq(q->queue_lock);
         if (q->nr_pending) {
                 ret = -EBUSY;
@@ -3439,6 +3435,9 @@ EXPORT_SYMBOL(blk_pre_runtime_suspend);
  */
 void blk_post_runtime_suspend(struct request_queue *q, int err)
 {
+        if (!q->dev)
+                return;
+
         spin_lock_irq(q->queue_lock);
         if (!err) {
                 q->rpm_status = RPM_SUSPENDED;
@@ -3463,6 +3462,9 @@ EXPORT_SYMBOL(blk_post_runtime_suspend);
  */
 void blk_pre_runtime_resume(struct request_queue *q)
 {
+        if (!q->dev)
+                return;
+
         spin_lock_irq(q->queue_lock);
         q->rpm_status = RPM_RESUMING;
         spin_unlock_irq(q->queue_lock);
@@ -3485,6 +3487,9 @@ EXPORT_SYMBOL(blk_pre_runtime_resume);
  */
 void blk_post_runtime_resume(struct request_queue *q, int err)
 {
+        if (!q->dev)
+                return;
+
         spin_lock_irq(q->queue_lock);
         if (!err) {
                 q->rpm_status = RPM_ACTIVE;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index de5716d8e525..e01405a3e8b3 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -76,6 +76,9 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
         struct bio_vec bv, bvprv, *bvprvp = NULL;
         struct bvec_iter iter;
         unsigned seg_size = 0, nsegs = 0, sectors = 0;
+        unsigned front_seg_size = bio->bi_seg_front_size;
+        bool do_split = true;
+        struct bio *new = NULL;
 
         bio_for_each_segment(bv, bio, iter) {
                 if (sectors + (bv.bv_len >> 9) > queue_max_sectors(q))
@@ -98,8 +101,11 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 
                         seg_size += bv.bv_len;
                         bvprv = bv;
-                        bvprvp = &bv;
+                        bvprvp = &bvprv;
                         sectors += bv.bv_len >> 9;
+
+                        if (nsegs == 1 && seg_size > front_seg_size)
+                                front_seg_size = seg_size;
                         continue;
                 }
 new_segment:
@@ -108,16 +114,29 @@ new_segment:
 
                 nsegs++;
                 bvprv = bv;
-                bvprvp = &bv;
+                bvprvp = &bvprv;
                 seg_size = bv.bv_len;
                 sectors += bv.bv_len >> 9;
+
+                if (nsegs == 1 && seg_size > front_seg_size)
+                        front_seg_size = seg_size;
         }
 
-        *segs = nsegs;
-        return NULL;
+        do_split = false;
 split:
         *segs = nsegs;
-        return bio_split(bio, sectors, GFP_NOIO, bs);
+
+        if (do_split) {
+                new = bio_split(bio, sectors, GFP_NOIO, bs);
+                if (new)
+                        bio = new;
+        }
+
+        bio->bi_seg_front_size = front_seg_size;
+        if (seg_size > bio->bi_seg_back_size)
+                bio->bi_seg_back_size = seg_size;
+
+        return do_split ? new : NULL;
 }
 
 void blk_queue_split(struct request_queue *q, struct bio **bio,
@@ -412,6 +431,12 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
         if (sg)
                 sg_mark_end(sg);
 
+        /*
+         * Something must have been wrong if the figured number of
+         * segment is bigger than number of req's physical segments
+         */
+        WARN_ON(nsegs > rq->nr_phys_segments);
+
         return nsegs;
 }
 EXPORT_SYMBOL(blk_rq_map_sg);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 3ae09de62f19..6d6f8feb48c0 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1291,15 +1291,16 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
                 blk_mq_bio_to_request(rq, bio);
 
                 /*
-                 * we do limited pluging. If bio can be merged, do merge.
+                 * We do limited pluging. If the bio can be merged, do that.
                  * Otherwise the existing request in the plug list will be
                  * issued. So the plug list will have one request at most
                  */
                 if (plug) {
                         /*
                          * The plug list might get flushed before this. If that
-                         * happens, same_queue_rq is invalid and plug list is empty
-                         **/
+                         * happens, same_queue_rq is invalid and plug list is
+                         * empty
+                         */
                         if (same_queue_rq && !list_empty(&plug->mq_list)) {
                                 old_rq = same_queue_rq;
                                 list_del_init(&old_rq->queuelist);
@@ -1380,12 +1381,15 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
                 blk_mq_bio_to_request(rq, bio);
                 if (!request_count)
                         trace_block_plug(q);
-                else if (request_count >= BLK_MAX_REQUEST_COUNT) {
+
+                blk_mq_put_ctx(data.ctx);
+
+                if (request_count >= BLK_MAX_REQUEST_COUNT) {
                         blk_flush_plug_list(plug, false);
                         trace_block_plug(q);
                 }
+
                 list_add_tail(&rq->queuelist, &plug->mq_list);
-                blk_mq_put_ctx(data.ctx);
                 return cookie;
         }
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 7d8f129a1516..dd4973583978 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -91,7 +91,8 @@ void blk_set_default_limits(struct queue_limits *lim)
         lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
         lim->virt_boundary_mask = 0;
         lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
-        lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
+        lim->max_sectors = lim->max_dev_sectors = lim->max_hw_sectors =
+                BLK_SAFE_MAX_SECTORS;
         lim->chunk_sectors = 0;
         lim->max_write_same_sectors = 0;
         lim->max_discard_sectors = 0;
@@ -127,6 +128,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
         lim->max_hw_sectors = UINT_MAX;
         lim->max_segment_size = UINT_MAX;
         lim->max_sectors = UINT_MAX;
+        lim->max_dev_sectors = UINT_MAX;
         lim->max_write_same_sectors = UINT_MAX;
 }
 EXPORT_SYMBOL(blk_set_stacking_limits);
@@ -214,8 +216,8 @@ void blk_queue_bounce_limit(struct request_queue *q, u64 max_addr)
 EXPORT_SYMBOL(blk_queue_bounce_limit);
 
 /**
- * blk_limits_max_hw_sectors - set hard and soft limit of max sectors for request
- * @limits: the queue limits
+ * blk_queue_max_hw_sectors - set max sectors for a request for this queue
+ * @q:  the request queue for the device
  * @max_hw_sectors:  max hardware sectors in the usual 512b unit
  *
  * Description:
@@ -224,13 +226,19 @@ EXPORT_SYMBOL(blk_queue_bounce_limit);
  *    the device driver based upon the capabilities of the I/O
  *    controller.
  *
+ *    max_dev_sectors is a hard limit imposed by the storage device for
+ *    READ/WRITE requests. It is set by the disk driver.
+ *
  *    max_sectors is a soft limit imposed by the block layer for
  *    filesystem type requests.  This value can be overridden on a
  *    per-device basis in /sys/block/<device>/queue/max_sectors_kb.
  *    The soft limit can not exceed max_hw_sectors.
  **/
-void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_sectors)
+void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
 {
+        struct queue_limits *limits = &q->limits;
+        unsigned int max_sectors;
+
         if ((max_hw_sectors << 9) < PAGE_CACHE_SIZE) {
                 max_hw_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
                 printk(KERN_INFO "%s: set to minimum %d\n",
@@ -238,22 +246,9 @@ void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_
         }
 
         limits->max_hw_sectors = max_hw_sectors;
-        limits->max_sectors = min_t(unsigned int, max_hw_sectors,
-                                    BLK_DEF_MAX_SECTORS);
-}
-EXPORT_SYMBOL(blk_limits_max_hw_sectors);
-
-/**
- * blk_queue_max_hw_sectors - set max sectors for a request for this queue
- * @q:  the request queue for the device
- * @max_hw_sectors:  max hardware sectors in the usual 512b unit
- *
- * Description:
- *    See description for blk_limits_max_hw_sectors().
- **/
-void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
-{
-        blk_limits_max_hw_sectors(&q->limits, max_hw_sectors);
+        max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors);
+        max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS);
+        limits->max_sectors = max_sectors;
 }
 EXPORT_SYMBOL(blk_queue_max_hw_sectors);
 
@@ -527,6 +522,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
         t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
         t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
+        t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors);
         t->max_write_same_sectors = min(t->max_write_same_sectors,
                                         b->max_write_same_sectors);
         t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 565b8dac5782..e140cc487ce1 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -205,6 +205,9 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
         if (ret < 0)
                 return ret;
 
+        max_hw_sectors_kb = min_not_zero(max_hw_sectors_kb, (unsigned long)
+                                         q->limits.max_dev_sectors >> 1);
+
         if (max_sectors_kb > max_hw_sectors_kb || max_sectors_kb < page_kb)
                 return -EINVAL;
 
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 246dfb16c3d9..aa40aa93381b 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -158,11 +158,13 @@ void blk_abort_request(struct request *req)
 {
         if (blk_mark_rq_complete(req))
                 return;
-        blk_delete_timer(req);
-        if (req->q->mq_ops)
+
+        if (req->q->mq_ops) {
                 blk_mq_rq_timed_out(req, false);
-        else
+        } else {
+                blk_delete_timer(req);
                 blk_rq_timed_out(req);
+        }
 }
 EXPORT_SYMBOL_GPL(blk_abort_request);
 
diff --git a/block/noop-iosched.c b/block/noop-iosched.c
index 3de89d4690f3..a163c487cf38 100644
--- a/block/noop-iosched.c
+++ b/block/noop-iosched.c
@@ -21,10 +21,10 @@ static void noop_merged_requests(struct request_queue *q, struct request *rq,
 static int noop_dispatch(struct request_queue *q, int force)
 {
         struct noop_data *nd = q->elevator->elevator_data;
+        struct request *rq;
 
-        if (!list_empty(&nd->queue)) {
-                struct request *rq;
-                rq = list_entry(nd->queue.next, struct request, queuelist);
+        rq = list_first_entry_or_null(&nd->queue, struct request, queuelist);
+        if (rq) {
                 list_del_init(&rq->queuelist);
                 elv_dispatch_sort(q, rq);
                 return 1;
@@ -46,7 +46,7 @@ noop_former_request(struct request_queue *q, struct request *rq)
 
         if (rq->queuelist.prev == &nd->queue)
                 return NULL;
-        return list_entry(rq->queuelist.prev, struct request, queuelist);
+        return list_prev_entry(rq, queuelist);
 }
 
 static struct request *
@@ -56,7 +56,7 @@ noop_latter_request(struct request_queue *q, struct request *rq)
 
         if (rq->queuelist.next == &nd->queue)
                 return NULL;
-        return list_entry(rq->queuelist.next, struct request, queuelist);
+        return list_next_entry(rq, queuelist);
 }
 
 static int noop_init_queue(struct request_queue *q, struct elevator_type *e)
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 3b030157ec85..746935a5973c 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -397,7 +397,7 @@ static int drop_partitions(struct gendisk *disk, struct block_device *bdev)
         struct hd_struct *part;
         int res;
 
-        if (bdev->bd_part_count)
+        if (bdev->bd_part_count || bdev->bd_super)
                 return -EBUSY;
         res = invalidate_partition(disk, 0);
         if (res)
diff --git a/block/partitions/mac.c b/block/partitions/mac.c
index c2c48ec64b27..621317ac4d59 100644
--- a/block/partitions/mac.c
+++ b/block/partitions/mac.c
@@ -32,7 +32,7 @@ int mac_partition(struct parsed_partitions *state)
         Sector sect;
         unsigned char *data;
         int slot, blocks_in_map;
-        unsigned secsize;
+        unsigned secsize, datasize, partoffset;
 #ifdef CONFIG_PPC_PMAC
         int found_root = 0;
         int found_root_goodness = 0;
@@ -50,10 +50,14 @@ int mac_partition(struct parsed_partitions *state)
         }
         secsize = be16_to_cpu(md->block_size);
         put_dev_sector(sect);
-        data = read_part_sector(state, secsize/512, &sect);
+        datasize = round_down(secsize, 512);
+        data = read_part_sector(state, datasize / 512, &sect);
         if (!data)
                 return -1;
-        part = (struct mac_partition *) (data + secsize%512);
+        partoffset = secsize % 512;
+        if (partoffset + sizeof(*part) > datasize)
+                return -1;
+        part = (struct mac_partition *) (data + partoffset);
         if (be16_to_cpu(part->signature) != MAC_PARTITION_MAGIC) {
                 put_dev_sector(sect);
                 return 0;               /* not a MacOS disk */
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 0aa6fdfb448a..6d4d4569447e 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -125,7 +125,7 @@ static int aead_wait_for_data(struct sock *sk, unsigned flags)
         if (flags & MSG_DONTWAIT)
                 return -EAGAIN;
 
-        set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+        sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 
         for (;;) {
                 if (signal_pending(current))
@@ -139,7 +139,7 @@ static int aead_wait_for_data(struct sock *sk, unsigned flags)
         }
         finish_wait(sk_sleep(sk), &wait);
 
-        clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+        sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 
         return err;
 }
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index af31a0ee4057..ca9efe17db1a 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -212,7 +212,7 @@ static int skcipher_wait_for_wmem(struct sock *sk, unsigned flags)
         if (flags & MSG_DONTWAIT)
                 return -EAGAIN;
 
-        set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+        sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
         for (;;) {
                 if (signal_pending(current))
@@ -258,7 +258,7 @@ static int skcipher_wait_for_data(struct sock *sk, unsigned flags)
                 return -EAGAIN;
         }
 
-        set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+        sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 
         for (;;) {
                 if (signal_pending(current))
@@ -272,7 +272,7 @@ static int skcipher_wait_for_data(struct sock *sk, unsigned flags)
         }
         finish_wait(sk_sleep(sk), &wait);
 
-        clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+        sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 
         return err;
 }
diff --git a/drivers/Makefile b/drivers/Makefile
index 73d039156ea7..795d0ca714bf 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -63,6 +63,7 @@ obj-$(CONFIG_FB_I810)           += video/fbdev/i810/
 obj-$(CONFIG_FB_INTEL)          += video/fbdev/intelfb/
 
 obj-$(CONFIG_PARPORT)           += parport/
+obj-$(CONFIG_NVM)               += lightnvm/
 obj-y                           += base/ block/ misc/ mfd/ nfc/
 obj-$(CONFIG_LIBNVDIMM)         += nvdimm/
 obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/
@@ -70,7 +71,6 @@ obj-$(CONFIG_NUBUS)		+= nubus/
 obj-y                           += macintosh/
 obj-$(CONFIG_IDE)               += ide/
 obj-$(CONFIG_SCSI)              += scsi/
-obj-$(CONFIG_NVM)               += lightnvm/
 obj-y                           += nvme/
 obj-$(CONFIG_ATA)               += ata/
 obj-$(CONFIG_TARGET_CORE)       += target/
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 25dbb76c02cc..5eef4cb4f70e 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -58,10 +58,10 @@ config ACPI_CCA_REQUIRED
         bool
 
 config ACPI_DEBUGGER
-        bool "In-kernel debugger (EXPERIMENTAL)"
+        bool "AML debugger interface (EXPERIMENTAL)"
         select ACPI_DEBUG
         help
-          Enable in-kernel debugging facilities: statistics, internal
+          Enable in-kernel debugging of AML facilities: statistics, internal
           object dump, single step control method execution.
           This is still under development, currently enabling this only
           results in the compilation of the ACPICA debugger files.
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index f7dab53b352a..e7ed39bab97d 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -233,11 +233,12 @@ static bool add_spa(struct acpi_nfit_desc *acpi_desc,
                 struct nfit_table_prev *prev,
                 struct acpi_nfit_system_address *spa)
 {
+        size_t length = min_t(size_t, sizeof(*spa), spa->header.length);
         struct device *dev = acpi_desc->dev;
         struct nfit_spa *nfit_spa;
 
         list_for_each_entry(nfit_spa, &prev->spas, list) {
-                if (memcmp(nfit_spa->spa, spa, sizeof(*spa)) == 0) {
+                if (memcmp(nfit_spa->spa, spa, length) == 0) {
                         list_move_tail(&nfit_spa->list, &acpi_desc->spas);
                         return true;
                 }
@@ -259,11 +260,12 @@ static bool add_memdev(struct acpi_nfit_desc *acpi_desc,
                 struct nfit_table_prev *prev,
                 struct acpi_nfit_memory_map *memdev)
 {
+        size_t length = min_t(size_t, sizeof(*memdev), memdev->header.length);
         struct device *dev = acpi_desc->dev;
         struct nfit_memdev *nfit_memdev;
 
         list_for_each_entry(nfit_memdev, &prev->memdevs, list)
-                if (memcmp(nfit_memdev->memdev, memdev, sizeof(*memdev)) == 0) {
+                if (memcmp(nfit_memdev->memdev, memdev, length) == 0) {
                         list_move_tail(&nfit_memdev->list, &acpi_desc->memdevs);
                         return true;
                 }
@@ -284,11 +286,12 @@ static bool add_dcr(struct acpi_nfit_desc *acpi_desc,
                 struct nfit_table_prev *prev,
                 struct acpi_nfit_control_region *dcr)
 {
+        size_t length = min_t(size_t, sizeof(*dcr), dcr->header.length);
         struct device *dev = acpi_desc->dev;
         struct nfit_dcr *nfit_dcr;
 
         list_for_each_entry(nfit_dcr, &prev->dcrs, list)
-                if (memcmp(nfit_dcr->dcr, dcr, sizeof(*dcr)) == 0) {
+                if (memcmp(nfit_dcr->dcr, dcr, length) == 0) {
                         list_move_tail(&nfit_dcr->list, &acpi_desc->dcrs);
                         return true;
                 }
@@ -308,11 +311,12 @@ static bool add_bdw(struct acpi_nfit_desc *acpi_desc,
                 struct nfit_table_prev *prev,
                 struct acpi_nfit_data_region *bdw)
 {
+        size_t length = min_t(size_t, sizeof(*bdw), bdw->header.length);
         struct device *dev = acpi_desc->dev;
         struct nfit_bdw *nfit_bdw;
 
         list_for_each_entry(nfit_bdw, &prev->bdws, list)
-                if (memcmp(nfit_bdw->bdw, bdw, sizeof(*bdw)) == 0) {
+                if (memcmp(nfit_bdw->bdw, bdw, length) == 0) {
                         list_move_tail(&nfit_bdw->list, &acpi_desc->bdws);
                         return true;
                 }
@@ -332,11 +336,12 @@ static bool add_idt(struct acpi_nfit_desc *acpi_desc,
                 struct nfit_table_prev *prev,
                 struct acpi_nfit_interleave *idt)
 {
+        size_t length = min_t(size_t, sizeof(*idt), idt->header.length);
         struct device *dev = acpi_desc->dev;
         struct nfit_idt *nfit_idt;
 
         list_for_each_entry(nfit_idt, &prev->idts, list)
-                if (memcmp(nfit_idt->idt, idt, sizeof(*idt)) == 0) {
+                if (memcmp(nfit_idt->idt, idt, length) == 0) {
                         list_move_tail(&nfit_idt->list, &acpi_desc->idts);
                         return true;
                 }
@@ -356,11 +361,12 @@ static bool add_flush(struct acpi_nfit_desc *acpi_desc,
                 struct nfit_table_prev *prev,
                 struct acpi_nfit_flush_address *flush)
 {
+        size_t length = min_t(size_t, sizeof(*flush), flush->header.length);
         struct device *dev = acpi_desc->dev;
         struct nfit_flush *nfit_flush;
 
         list_for_each_entry(nfit_flush, &prev->flushes, list)
-                if (memcmp(nfit_flush->flush, flush, sizeof(*flush)) == 0) {
+                if (memcmp(nfit_flush->flush, flush, length) == 0) {
                         list_move_tail(&nfit_flush->list, &acpi_desc->flushes);
                         return true;
                 }
@@ -655,7 +661,7 @@ static ssize_t revision_show(struct device *dev,
         struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
         struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
 
-        return sprintf(buf, "%d\n", acpi_desc->nfit->header.revision);
+        return sprintf(buf, "%d\n", acpi_desc->acpi_header.revision);
 }
 static DEVICE_ATTR_RO(revision);
 
@@ -1652,7 +1658,6 @@ int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz)
 
         data = (u8 *) acpi_desc->nfit;
         end = data + sz;
-        data += sizeof(struct acpi_table_nfit);
         while (!IS_ERR_OR_NULL(data))
                 data = add_table(acpi_desc, &prev, data, end);
 
@@ -1748,13 +1753,29 @@ static int acpi_nfit_add(struct acpi_device *adev)
                 return PTR_ERR(acpi_desc);
         }
 
-        acpi_desc->nfit = (struct acpi_table_nfit *) tbl;
+        /*
+         * Save the acpi header for later and then skip it,
+         * making nfit point to the first nfit table header.
+         */
+        acpi_desc->acpi_header = *tbl;
+        acpi_desc->nfit = (void *) tbl + sizeof(struct acpi_table_nfit);
+        sz -= sizeof(struct acpi_table_nfit);
 
         /* Evaluate _FIT and override with that if present */
         status = acpi_evaluate_object(adev->handle, "_FIT", NULL, &buf);
         if (ACPI_SUCCESS(status) && buf.length > 0) {
-                acpi_desc->nfit = (struct acpi_table_nfit *)buf.pointer;
-                sz = buf.length;
+                union acpi_object *obj;
+                /*
+                 * Adjust for the acpi_object header of the _FIT
+                 */
+                obj = buf.pointer;
+                if (obj->type == ACPI_TYPE_BUFFER) {
+                        acpi_desc->nfit =
+                                (struct acpi_nfit_header *)obj->buffer.pointer;
+                        sz = obj->buffer.length;
+                } else
+                        dev_dbg(dev, "%s invalid type %d, ignoring _FIT\n",
+                                 __func__, (int) obj->type);
         }
 
         rc = acpi_nfit_init(acpi_desc, sz);
@@ -1777,7 +1798,8 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
 {
         struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(&adev->dev);
         struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
-        struct acpi_table_nfit *nfit_saved;
+        struct acpi_nfit_header *nfit_saved;
+        union acpi_object *obj;
         struct device *dev = &adev->dev;
         acpi_status status;
         int ret;
@@ -1808,12 +1830,19 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
         }
 
         nfit_saved = acpi_desc->nfit;
-        acpi_desc->nfit = (struct acpi_table_nfit *)buf.pointer;
-        ret = acpi_nfit_init(acpi_desc, buf.length);
-        if (!ret) {
-                /* Merge failed, restore old nfit, and exit */
-                acpi_desc->nfit = nfit_saved;
-                dev_err(dev, "failed to merge updated NFIT\n");
+        obj = buf.pointer;
+        if (obj->type == ACPI_TYPE_BUFFER) {
+                acpi_desc->nfit =
+                        (struct acpi_nfit_header *)obj->buffer.pointer;
+                ret = acpi_nfit_init(acpi_desc, obj->buffer.length);
+                if (ret) {
+                        /* Merge failed, restore old nfit, and exit */
+                        acpi_desc->nfit = nfit_saved;
+                        dev_err(dev, "failed to merge updated NFIT\n");
+                }
+        } else {
+                /* Bad _FIT, restore old nfit */
+                dev_err(dev, "Invalid _FIT\n");
         }
         kfree(buf.pointer);
 
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index 2ea5c0797c8f..3d549a383659 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -96,7 +96,8 @@ struct nfit_mem {
 
 struct acpi_nfit_desc {
         struct nvdimm_bus_descriptor nd_desc;
-        struct acpi_table_nfit *nfit;
+        struct acpi_table_header acpi_header;
+        struct acpi_nfit_header *nfit;
         struct mutex spa_map_mutex;
         struct mutex init_mutex;
         struct list_head spa_maps;
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 850d7bf0c873..ae3fe4e64203 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -768,6 +768,13 @@ static void pci_acpi_root_add_resources(struct acpi_pci_root_info *info)
                 else
                         continue;
 
+                /*
+                 * Some legacy x86 host bridge drivers use iomem_resource and
+                 * ioport_resource as default resource pool, skip it.
+                 */
+                if (res == root)
+                        continue;
+
                 conflict = insert_resource_conflict(root, res);
                 if (conflict) {
                         dev_info(&info->bridge->dev,
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index ff02bb4218fc..cdfbcc54821f 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -314,16 +314,6 @@ static const struct pci_device_id ahci_pci_tbl[] = {
         { PCI_VDEVICE(INTEL, 0x1f37), board_ahci_avn }, /* Avoton RAID */
         { PCI_VDEVICE(INTEL, 0x1f3e), board_ahci_avn }, /* Avoton RAID */
         { PCI_VDEVICE(INTEL, 0x1f3f), board_ahci_avn }, /* Avoton RAID */
-        { PCI_VDEVICE(INTEL, 0xa182), board_ahci }, /* Lewisburg AHCI*/
-        { PCI_VDEVICE(INTEL, 0xa202), board_ahci }, /* Lewisburg AHCI*/
-        { PCI_VDEVICE(INTEL, 0xa184), board_ahci }, /* Lewisburg RAID*/
-        { PCI_VDEVICE(INTEL, 0xa204), board_ahci }, /* Lewisburg RAID*/
-        { PCI_VDEVICE(INTEL, 0xa186), board_ahci }, /* Lewisburg RAID*/
-        { PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/
-        { PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/
-        { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* Lewisburg RAID*/
-        { PCI_VDEVICE(INTEL, 0xa18e), board_ahci }, /* Lewisburg RAID*/
-        { PCI_VDEVICE(INTEL, 0xa20e), board_ahci }, /* Lewisburg RAID*/
         { PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Wellsburg RAID */
         { PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Wellsburg RAID */
         { PCI_VDEVICE(INTEL, 0x8d02), board_ahci }, /* Wellsburg AHCI */
@@ -350,10 +340,22 @@ static const struct pci_device_id ahci_pci_tbl[] = {
         { PCI_VDEVICE(INTEL, 0x9d03), board_ahci }, /* Sunrise Point-LP AHCI */
         { PCI_VDEVICE(INTEL, 0x9d05), board_ahci }, /* Sunrise Point-LP RAID */
         { PCI_VDEVICE(INTEL, 0x9d07), board_ahci }, /* Sunrise Point-LP RAID */
+        { PCI_VDEVICE(INTEL, 0xa102), board_ahci }, /* Sunrise Point-H AHCI */
         { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H AHCI */
         { PCI_VDEVICE(INTEL, 0xa105), board_ahci }, /* Sunrise Point-H RAID */
+        { PCI_VDEVICE(INTEL, 0xa106), board_ahci }, /* Sunrise Point-H RAID */
         { PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */
         { PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */
+        { PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/
+        { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* Lewisburg RAID*/
+        { PCI_VDEVICE(INTEL, 0xa182), board_ahci }, /* Lewisburg AHCI*/
+        { PCI_VDEVICE(INTEL, 0xa184), board_ahci }, /* Lewisburg RAID*/
+        { PCI_VDEVICE(INTEL, 0xa186), board_ahci }, /* Lewisburg RAID*/
+        { PCI_VDEVICE(INTEL, 0xa18e), board_ahci }, /* Lewisburg RAID*/
+        { PCI_VDEVICE(INTEL, 0xa202), board_ahci }, /* Lewisburg AHCI*/
+        { PCI_VDEVICE(INTEL, 0xa204), board_ahci }, /* Lewisburg RAID*/
+        { PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/
+        { PCI_VDEVICE(INTEL, 0xa20e), board_ahci }, /* Lewisburg RAID*/
 
         /* JMicron 360/1/3/5/6, match class to avoid IDE function */
         { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c
index 8490d37aee2a..f7a7fa81740e 100644
--- a/drivers/ata/ahci_mvebu.c
+++ b/drivers/ata/ahci_mvebu.c
@@ -62,6 +62,7 @@ static void ahci_mvebu_regret_option(struct ahci_host_priv *hpriv)
         writel(0x80, hpriv->mmio + AHCI_VENDOR_SPECIFIC_0_DATA);
 }
 
+#ifdef CONFIG_PM_SLEEP
 static int ahci_mvebu_suspend(struct platform_device *pdev, pm_message_t state)
 {
         return ahci_platform_suspend_host(&pdev->dev);
@@ -81,6 +82,10 @@ static int ahci_mvebu_resume(struct platform_device *pdev)
 
         return ahci_platform_resume_host(&pdev->dev);
 }
+#else
+#define ahci_mvebu_suspend NULL
+#define ahci_mvebu_resume NULL
+#endif
 
 static const struct ata_port_info ahci_mvebu_port_info = {
         .flags     = AHCI_FLAG_COMMON,
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 096064cd6c52..4665512dae44 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -1273,6 +1273,15 @@ static int ahci_exec_polled_cmd(struct ata_port *ap, int pmp,
         ata_tf_to_fis(tf, pmp, is_cmd, fis);
         ahci_fill_cmd_slot(pp, 0, cmd_fis_len | flags | (pmp << 12));
 
+        /* set port value for softreset of Port Multiplier */
+        if (pp->fbs_enabled && pp->fbs_last_dev != pmp) {
+                tmp = readl(port_mmio + PORT_FBS);
+                tmp &= ~(PORT_FBS_DEV_MASK | PORT_FBS_DEC);
+                tmp |= pmp << PORT_FBS_DEV_OFFSET;
+                writel(tmp, port_mmio + PORT_FBS);
+                pp->fbs_last_dev = pmp;
+        }
+
         /* issue & wait */
         writel(1, port_mmio + PORT_CMD_ISSUE);
 
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index cb0508af1459..961acc788f44 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -1505,12 +1505,20 @@ static const char *ata_err_string(unsigned int err_mask)
 unsigned int ata_read_log_page(struct ata_device *dev, u8 log,
                                u8 page, void *buf, unsigned int sectors)
 {
+        unsigned long ap_flags = dev->link->ap->flags;
         struct ata_taskfile tf;
         unsigned int err_mask;
         bool dma = false;
 
         DPRINTK("read log page - log 0x%x, page 0x%x\n", log, page);
 
+        /*
+         * Return error without actually issuing the command on controllers
+         * which e.g. lockup on a read log page.
+         */
+        if (ap_flags & ATA_FLAG_NO_LOG_PAGE)
+                return AC_ERR_DEV;
+
 retry:
         ata_tf_init(dev, &tf);
         if (dev->dma_mode && ata_id_has_read_log_dma_ext(dev->id) &&
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index 5389579c5120..a723ae929783 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -45,7 +45,8 @@ enum {
         SATA_FSL_MAX_PRD_DIRECT = 16,   /* Direct PRDT entries */
 
         SATA_FSL_HOST_FLAGS     = (ATA_FLAG_SATA | ATA_FLAG_PIO_DMA |
-                                ATA_FLAG_PMP | ATA_FLAG_NCQ | ATA_FLAG_AN),
+                                   ATA_FLAG_PMP | ATA_FLAG_NCQ |
+                                   ATA_FLAG_AN | ATA_FLAG_NO_LOG_PAGE),
 
         SATA_FSL_MAX_CMDS       = SATA_FSL_QUEUE_DEPTH,
         SATA_FSL_CMD_HDR_SIZE   = 16,   /* 4 DWORDS */
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index dea6edcbf145..29bcff086bce 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -630,6 +630,9 @@ static void sil_dev_config(struct ata_device *dev)
         unsigned int n, quirks = 0;
         unsigned char model_num[ATA_ID_PROD_LEN + 1];
 
+        /* This controller doesn't support trim */
+        dev->horkage |= ATA_HORKAGE_NOTRIM;
+
         ata_id_c_string(dev->id, model_num, ATA_ID_PROD, sizeof(model_num));
 
         for (n = 0; sil_blacklist[n].product; n++)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 2804aed3f416..25425d3f2575 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -303,6 +303,10 @@ static int memory_subsys_offline(struct device *dev)
         if (mem->state == MEM_OFFLINE)
                 return 0;
 
+        /* Can't offline block with non-present sections */
+        if (mem->section_count != sections_per_block)
+                return -EINVAL;
+
         return memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
 }
 
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index e03b1ad25a90..167418e73445 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1775,10 +1775,10 @@ int genpd_dev_pm_attach(struct device *dev)
         }
 
         pd = of_genpd_get_from_provider(&pd_args);
+        of_node_put(pd_args.np);
         if (IS_ERR(pd)) {
                 dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
                         __func__, PTR_ERR(pd));
-                of_node_put(dev->of_node);
                 return -EPROBE_DEFER;
         }
 
@@ -1796,7 +1796,6 @@ int genpd_dev_pm_attach(struct device *dev)
         if (ret < 0) {
                 dev_err(dev, "failed to add to PM domain %s: %d",
                         pd->name, ret);
-                of_node_put(dev->of_node);
                 goto out;
         }
 
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index e60dd12e23aa..1e937ac5f456 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -160,9 +160,6 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
                 struct gpd_timing_data *td;
                 s64 constraint_ns;
 
-                if (!pdd->dev->driver)
-                        continue;
-
                 /*
                  * Check if the device is allowed to be off long enough for the
                  * domain to turn off and on (that's how much time it will
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index a28a562f7b7f..3457ac8c03e2 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3810,7 +3810,6 @@ static int mtip_block_initialize(struct driver_data *dd)
         sector_t capacity;
         unsigned int index = 0;
         struct kobject *kobj;
-        unsigned char thd_name[16];
 
         if (dd->disk)
                 goto skip_create_disk; /* hw init done, before rebuild */
@@ -3958,10 +3957,9 @@ skip_create_disk:
         }
 
 start_service_thread:
-        sprintf(thd_name, "mtip_svc_thd_%02d", index);
         dd->mtip_svc_handler = kthread_create_on_node(mtip_service_thread,
-                                                dd, dd->numa_node, "%s",
-                                                thd_name);
+                                                dd, dd->numa_node,
+                                                "mtip_svc_thd_%02d", index);
 
         if (IS_ERR(dd->mtip_svc_handler)) {
                 dev_err(&dd->pdev->dev, "service thread failed to start\n");
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 6255d1c4bba4..8162475d96b5 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -8,6 +8,7 @@
 #include <linux/slab.h>
 #include <linux/blk-mq.h>
 #include <linux/hrtimer.h>
+#include <linux/lightnvm.h>
 
 struct nullb_cmd {
         struct list_head list;
@@ -17,6 +18,7 @@ struct nullb_cmd {
         struct bio *bio;
         unsigned int tag;
         struct nullb_queue *nq;
+        struct hrtimer timer;
 };
 
 struct nullb_queue {
@@ -39,23 +41,14 @@ struct nullb {
 
         struct nullb_queue *queues;
         unsigned int nr_queues;
+        char disk_name[DISK_NAME_LEN];
 };
 
 static LIST_HEAD(nullb_list);
 static struct mutex lock;
 static int null_major;
 static int nullb_indexes;
-
-struct completion_queue {
-        struct llist_head list;
-        struct hrtimer timer;
-};
-
-/*
- * These are per-cpu for now, they will need to be configured by the
- * complete_queues parameter and appropriately mapped.
- */
-static DEFINE_PER_CPU(struct completion_queue, completion_queues);
+static struct kmem_cache *ppa_cache;
 
 enum {
         NULL_IRQ_NONE           = 0,
@@ -119,6 +112,10 @@ static int nr_devices = 2;
 module_param(nr_devices, int, S_IRUGO);
 MODULE_PARM_DESC(nr_devices, "Number of devices to register");
 
+static bool use_lightnvm;
+module_param(use_lightnvm, bool, S_IRUGO);
+MODULE_PARM_DESC(use_lightnvm, "Register as a LightNVM device");
+
 static int irqmode = NULL_IRQ_SOFTIRQ;
 
 static int null_set_irqmode(const char *str, const struct kernel_param *kp)
@@ -135,8 +132,8 @@ static const struct kernel_param_ops null_irqmode_param_ops = {
 device_param_cb(irqmode, &null_irqmode_param_ops, &irqmode, S_IRUGO);
 MODULE_PARM_DESC(irqmode, "IRQ completion handler. 0-none, 1-softirq, 2-timer");
 
-static int completion_nsec = 10000;
-module_param(completion_nsec, int, S_IRUGO);
+static unsigned long completion_nsec = 10000;
+module_param(completion_nsec, ulong, S_IRUGO);
 MODULE_PARM_DESC(completion_nsec, "Time in ns to complete a request in hardware. Default: 10,000ns");
 
 static int hw_queue_depth = 64;
@@ -173,6 +170,8 @@ static void free_cmd(struct nullb_cmd *cmd)
         put_tag(cmd->nq, cmd->tag);
 }
 
+static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer);
+
 static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq)
 {
         struct nullb_cmd *cmd;
@@ -183,6 +182,11 @@ static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq)
                 cmd = &nq->cmds[tag];
                 cmd->tag = tag;
                 cmd->nq = nq;
+                if (irqmode == NULL_IRQ_TIMER) {
+                        hrtimer_init(&cmd->timer, CLOCK_MONOTONIC,
+                                     HRTIMER_MODE_REL);
+                        cmd->timer.function = null_cmd_timer_expired;
+                }
                 return cmd;
         }
 
@@ -213,6 +217,8 @@ static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, int can_wait)
 
 static void end_cmd(struct nullb_cmd *cmd)
 {
+        struct request_queue *q = NULL;
+
         switch (queue_mode)  {
         case NULL_Q_MQ:
                 blk_mq_end_request(cmd->rq, 0);
@@ -223,55 +229,37 @@ static void end_cmd(struct nullb_cmd *cmd)
                 break;
         case NULL_Q_BIO:
                 bio_endio(cmd->bio);
-                break;
+                goto free_cmd;
         }
 
+        if (cmd->rq)
+                q = cmd->rq->q;
+
+        /* Restart queue if needed, as we are freeing a tag */
+        if (q && !q->mq_ops && blk_queue_stopped(q)) {
+                unsigned long flags;
+
+                spin_lock_irqsave(q->queue_lock, flags);
+                if (blk_queue_stopped(q))
+                        blk_start_queue(q);
+                spin_unlock_irqrestore(q->queue_lock, flags);
+        }
+free_cmd:
         free_cmd(cmd);
 }
 
 static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
 {
-        struct completion_queue *cq;
-        struct llist_node *entry;
-        struct nullb_cmd *cmd;
-
-        cq = &per_cpu(completion_queues, smp_processor_id());
-
-        while ((entry = llist_del_all(&cq->list)) != NULL) {
-                entry = llist_reverse_order(entry);
-                do {
-                        struct request_queue *q = NULL;
-
-                        cmd = container_of(entry, struct nullb_cmd, ll_list);
-                        entry = entry->next;
-                        if (cmd->rq)
-                                q = cmd->rq->q;
-                        end_cmd(cmd);
-
-                        if (q && !q->mq_ops && blk_queue_stopped(q)) {
-                                spin_lock(q->queue_lock);
-                                if (blk_queue_stopped(q))
-                                        blk_start_queue(q);
-                                spin_unlock(q->queue_lock);
-                        }
-                } while (entry);
-        }
+        end_cmd(container_of(timer, struct nullb_cmd, timer));
 
         return HRTIMER_NORESTART;
 }
 
 static void null_cmd_end_timer(struct nullb_cmd *cmd)
 {
-        struct completion_queue *cq = &per_cpu(completion_queues, get_cpu());
+        ktime_t kt = ktime_set(0, completion_nsec);
 
-        cmd->ll_list.next = NULL;
-        if (llist_add(&cmd->ll_list, &cq->list)) {
-                ktime_t kt = ktime_set(0, completion_nsec);
-
-                hrtimer_start(&cq->timer, kt, HRTIMER_MODE_REL_PINNED);
-        }
-
-        put_cpu();
+        hrtimer_start(&cmd->timer, kt, HRTIMER_MODE_REL);
 }
 
 static void null_softirq_done_fn(struct request *rq)
@@ -369,6 +357,10 @@ static int null_queue_rq(struct blk_mq_hw_ctx *hctx,
 {
         struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
 
+        if (irqmode == NULL_IRQ_TIMER) {
+                hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+                cmd->timer.function = null_cmd_timer_expired;
+        }
         cmd->rq = bd->rq;
         cmd->nq = hctx->driver_data;
 
@@ -427,15 +419,157 @@ static void null_del_dev(struct nullb *nullb)
 {
         list_del_init(&nullb->list);
 
-        del_gendisk(nullb->disk);
+        if (use_lightnvm)
+                nvm_unregister(nullb->disk_name);
+        else
+                del_gendisk(nullb->disk);
         blk_cleanup_queue(nullb->q);
         if (queue_mode == NULL_Q_MQ)
                 blk_mq_free_tag_set(&nullb->tag_set);
-        put_disk(nullb->disk);
+        if (!use_lightnvm)
+                put_disk(nullb->disk);
         cleanup_queues(nullb);
         kfree(nullb);
 }
 
+#ifdef CONFIG_NVM
+
+static void null_lnvm_end_io(struct request *rq, int error)
+{
+        struct nvm_rq *rqd = rq->end_io_data;
+        struct nvm_dev *dev = rqd->dev;
+
+        dev->mt->end_io(rqd, error);
+
+        blk_put_request(rq);
+}
+
+static int null_lnvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
+{
+        struct request_queue *q = dev->q;
+        struct request *rq;
+        struct bio *bio = rqd->bio;
+
+        rq = blk_mq_alloc_request(q, bio_rw(bio), GFP_KERNEL, 0);
+        if (IS_ERR(rq))
+                return -ENOMEM;
+
+        rq->cmd_type = REQ_TYPE_DRV_PRIV;
+        rq->__sector = bio->bi_iter.bi_sector;
+        rq->ioprio = bio_prio(bio);
+
+        if (bio_has_data(bio))
+                rq->nr_phys_segments = bio_phys_segments(q, bio);
+
+        rq->__data_len = bio->bi_iter.bi_size;
+        rq->bio = rq->biotail = bio;
+
+        rq->end_io_data = rqd;
+
+        blk_execute_rq_nowait(q, NULL, rq, 0, null_lnvm_end_io);
+
+        return 0;
+}
+
+static int null_lnvm_id(struct nvm_dev *dev, struct nvm_id *id)
+{
+        sector_t size = gb * 1024 * 1024 * 1024ULL;
+        sector_t blksize;
+        struct nvm_id_group *grp;
+
+        id->ver_id = 0x1;
+        id->vmnt = 0;
+        id->cgrps = 1;
+        id->cap = 0x3;
+        id->dom = 0x1;
+
+        id->ppaf.blk_offset = 0;
+        id->ppaf.blk_len = 16;
+        id->ppaf.pg_offset = 16;
+        id->ppaf.pg_len = 16;
+        id->ppaf.sect_offset = 32;
+        id->ppaf.sect_len = 8;
+        id->ppaf.pln_offset = 40;
+        id->ppaf.pln_len = 8;
+        id->ppaf.lun_offset = 48;
+        id->ppaf.lun_len = 8;
+        id->ppaf.ch_offset = 56;
+        id->ppaf.ch_len = 8;
+
+        do_div(size, bs); /* convert size to pages */
+        do_div(size, 256); /* concert size to pgs pr blk */
+        grp = &id->groups[0];
+        grp->mtype = 0;
+        grp->fmtype = 0;
+        grp->num_ch = 1;
+        grp->num_pg = 256;
+        blksize = size;
+        do_div(size, (1 << 16));
+        grp->num_lun = size + 1;
+        do_div(blksize, grp->num_lun);
+        grp->num_blk = blksize;
+        grp->num_pln = 1;
+
+        grp->fpg_sz = bs;
+        grp->csecs = bs;
+        grp->trdt = 25000;
+        grp->trdm = 25000;
+        grp->tprt = 500000;
+        grp->tprm = 500000;
+        grp->tbet = 1500000;
+        grp->tbem = 1500000;
+        grp->mpos = 0x010101; /* single plane rwe */
+        grp->cpar = hw_queue_depth;
+
+        return 0;
+}
+
+static void *null_lnvm_create_dma_pool(struct nvm_dev *dev, char *name)
+{
+        mempool_t *virtmem_pool;
+
+        virtmem_pool = mempool_create_slab_pool(64, ppa_cache);
+        if (!virtmem_pool) {
+                pr_err("null_blk: Unable to create virtual memory pool\n");
+                return NULL;
+        }
+
+        return virtmem_pool;
+}
+
+static void null_lnvm_destroy_dma_pool(void *pool)
+{
+        mempool_destroy(pool);
+}
+
+static void *null_lnvm_dev_dma_alloc(struct nvm_dev *dev, void *pool,
+                                gfp_t mem_flags, dma_addr_t *dma_handler)
+{
+        return mempool_alloc(pool, mem_flags);
+}
+
+static void null_lnvm_dev_dma_free(void *pool, void *entry,
+                                                        dma_addr_t dma_handler)
+{
+        mempool_free(entry, pool);
+}
+
+static struct nvm_dev_ops null_lnvm_dev_ops = {
+        .identity               = null_lnvm_id,
+        .submit_io              = null_lnvm_submit_io,
+
+        .create_dma_pool        = null_lnvm_create_dma_pool,
+        .destroy_dma_pool       = null_lnvm_destroy_dma_pool,
+        .dev_dma_alloc          = null_lnvm_dev_dma_alloc,
+        .dev_dma_free           = null_lnvm_dev_dma_free,
+
+        /* Simulate nvme protocol restriction */
+        .max_phys_sect          = 64,
+};
+#else
+static struct nvm_dev_ops null_lnvm_dev_ops;
+#endif /* CONFIG_NVM */
+
 static int null_open(struct block_device *bdev, fmode_t mode)
 {
         return 0;
@@ -575,11 +709,6 @@ static int null_add_dev(void)
         queue_flag_set_unlocked(QUEUE_FLAG_NONROT, nullb->q);
         queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, nullb->q);
 
-        disk = nullb->disk = alloc_disk_node(1, home_node);
-        if (!disk) {
-                rv = -ENOMEM;
-                goto out_cleanup_blk_queue;
-        }
 
         mutex_lock(&lock);
         list_add_tail(&nullb->list, &nullb_list);
@@ -589,6 +718,21 @@ static int null_add_dev(void)
         blk_queue_logical_block_size(nullb->q, bs);
         blk_queue_physical_block_size(nullb->q, bs);
 
+        sprintf(nullb->disk_name, "nullb%d", nullb->index);
+
+        if (use_lightnvm) {
+                rv = nvm_register(nullb->q, nullb->disk_name,
+                                                        &null_lnvm_dev_ops);
+                if (rv)
+                        goto out_cleanup_blk_queue;
+                goto done;
+        }
+
+        disk = nullb->disk = alloc_disk_node(1, home_node);
+        if (!disk) {
+                rv = -ENOMEM;
+                goto out_cleanup_lightnvm;
+        }
         size = gb * 1024 * 1024 * 1024ULL;
         set_capacity(disk, size >> 9);
 
@@ -598,10 +742,15 @@ static int null_add_dev(void)
         disk->fops              = &null_fops;
         disk->private_data      = nullb;
         disk->queue             = nullb->q;
-        sprintf(disk->disk_name, "nullb%d", nullb->index);
+        strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
+
         add_disk(disk);
+done:
         return 0;
 
+out_cleanup_lightnvm:
+        if (use_lightnvm)
+                nvm_unregister(nullb->disk_name);
 out_cleanup_blk_queue:
         blk_cleanup_queue(nullb->q);
 out_cleanup_tags:
@@ -617,7 +766,9 @@ out:
 
 static int __init null_init(void)
 {
+        int ret = 0;
         unsigned int i;
+        struct nullb *nullb;
 
         if (bs > PAGE_SIZE) {
                 pr_warn("null_blk: invalid block size\n");
@@ -625,6 +776,18 @@ static int __init null_init(void)
                 bs = PAGE_SIZE;
         }
 
+        if (use_lightnvm && bs != 4096) {
+                pr_warn("null_blk: LightNVM only supports 4k block size\n");
+                pr_warn("null_blk: defaults block size to 4k\n");
+                bs = 4096;
+        }
+
+        if (use_lightnvm && queue_mode != NULL_Q_MQ) {
+                pr_warn("null_blk: LightNVM only supported for blk-mq\n");
+                pr_warn("null_blk: defaults queue mode to blk-mq\n");
+                queue_mode = NULL_Q_MQ;
+        }
+
         if (queue_mode == NULL_Q_MQ && use_per_node_hctx) {
                 if (submit_queues < nr_online_nodes) {
                         pr_warn("null_blk: submit_queues param is set to %u.",
@@ -638,32 +801,38 @@ static int __init null_init(void)
 
         mutex_init(&lock);
 
-        /* Initialize a separate list for each CPU for issuing softirqs */
-        for_each_possible_cpu(i) {
-                struct completion_queue *cq = &per_cpu(completion_queues, i);
-
-                init_llist_head(&cq->list);
-
-                if (irqmode != NULL_IRQ_TIMER)
-                        continue;
-
-                hrtimer_init(&cq->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-                cq->timer.function = null_cmd_timer_expired;
-        }
-
         null_major = register_blkdev(0, "nullb");
         if (null_major < 0)
                 return null_major;
 
-        for (i = 0; i < nr_devices; i++) {
-                if (null_add_dev()) {
-                        unregister_blkdev(null_major, "nullb");
-                        return -EINVAL;
+        if (use_lightnvm) {
+                ppa_cache = kmem_cache_create("ppa_cache", 64 * sizeof(u64),
+                                                                0, 0, NULL);
+                if (!ppa_cache) {
+                        pr_err("null_blk: unable to create ppa cache\n");
+                        ret = -ENOMEM;
+                        goto err_ppa;
                 }
         }
 
+        for (i = 0; i < nr_devices; i++) {
+                ret = null_add_dev();
+                if (ret)
+                        goto err_dev;
+        }
+
         pr_info("null: module loaded\n");
         return 0;
+
+err_dev:
+        while (!list_empty(&nullb_list)) {
+                nullb = list_entry(nullb_list.next, struct nullb, list);
+                null_del_dev(nullb);
+        }
+        kmem_cache_destroy(ppa_cache);
+err_ppa:
+        unregister_blkdev(null_major, "nullb");
+        return ret;
 }
 
 static void __exit null_exit(void)
@@ -678,6 +847,8 @@ static void __exit null_exit(void)
                 null_del_dev(nullb);
         }
         mutex_unlock(&lock);
+
+        kmem_cache_destroy(ppa_cache);
 }
 
 module_init(null_init);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 235708c7c46e..81ea69fee7ca 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -3442,6 +3442,7 @@ static void rbd_queue_workfn(struct work_struct *work)
                 goto err_rq;
         }
         img_request->rq = rq;
+        snapc = NULL; /* img_request consumes a ref */
 
         if (op_type == OBJ_OP_DISCARD)
                 result = rbd_img_request_fill(img_request, OBJ_REQUEST_NODATA,
diff --git a/drivers/bus/omap-ocp2scp.c b/drivers/bus/omap-ocp2scp.c
index 9f1856948758..bf500e0e7362 100644
--- a/drivers/bus/omap-ocp2scp.c
+++ b/drivers/bus/omap-ocp2scp.c
@@ -117,7 +117,7 @@ static struct platform_driver omap_ocp2scp_driver = {
 
 module_platform_driver(omap_ocp2scp_driver);
 
-MODULE_ALIAS("platform: omap-ocp2scp");
+MODULE_ALIAS("platform:omap-ocp2scp");
 MODULE_AUTHOR("Texas Instruments Inc.");
 MODULE_DESCRIPTION("OMAP OCP2SCP driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 55fe9020459f..4cc72fa017c7 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -1230,14 +1230,14 @@ static int smi_start_processing(void       *send_info,
 
         new_smi->intf = intf;
 
-        /* Try to claim any interrupts. */
-        if (new_smi->irq_setup)
-                new_smi->irq_setup(new_smi);
-
         /* Set up the timer that drives the interface. */
         setup_timer(&new_smi->si_timer, smi_timeout, (long)new_smi);
         smi_mod_timer(new_smi, jiffies + SI_TIMEOUT_JIFFIES);
 
+        /* Try to claim any interrupts. */
+        if (new_smi->irq_setup)
+                new_smi->irq_setup(new_smi);
+
         /*
          * Check if the user forcefully enabled the daemon.
          */
diff --git a/drivers/clk/clk-gpio.c b/drivers/clk/clk-gpio.c
index 10819e248414..335322dc403f 100644
--- a/drivers/clk/clk-gpio.c
+++ b/drivers/clk/clk-gpio.c
@@ -209,6 +209,8 @@ EXPORT_SYMBOL_GPL(clk_register_gpio_mux);
 
 struct clk_gpio_delayed_register_data {
         const char *gpio_name;
+        int num_parents;
+        const char **parent_names;
         struct device_node *node;
         struct mutex lock;
         struct clk *clk;
@@ -222,8 +224,6 @@ static struct clk *of_clk_gpio_delayed_register_get(
 {
         struct clk_gpio_delayed_register_data *data = _data;
         struct clk *clk;
-        const char **parent_names;
-        int i, num_parents;
         int gpio;
         enum of_gpio_flags of_flags;
 
@@ -248,26 +248,14 @@ static struct clk *of_clk_gpio_delayed_register_get(
                 return ERR_PTR(gpio);
         }
 
-        num_parents = of_clk_get_parent_count(data->node);
-
-        parent_names = kcalloc(num_parents, sizeof(char *), GFP_KERNEL);
-        if (!parent_names) {
-                clk = ERR_PTR(-ENOMEM);
-                goto out;
-        }
-
-        for (i = 0; i < num_parents; i++)
-                parent_names[i] = of_clk_get_parent_name(data->node, i);
-
-        clk = data->clk_register_get(data->node->name, parent_names,
-                        num_parents, gpio, of_flags & OF_GPIO_ACTIVE_LOW);
+        clk = data->clk_register_get(data->node->name, data->parent_names,
+                        data->num_parents, gpio, of_flags & OF_GPIO_ACTIVE_LOW);
         if (IS_ERR(clk))
                 goto out;
 
         data->clk = clk;
 out:
         mutex_unlock(&data->lock);
-        kfree(parent_names);
 
         return clk;
 }
@@ -296,11 +284,24 @@ static void __init of_gpio_clk_setup(struct device_node *node,
                                 unsigned gpio, bool active_low))
 {
         struct clk_gpio_delayed_register_data *data;
+        const char **parent_names;
+        int i, num_parents;
 
         data = kzalloc(sizeof(*data), GFP_KERNEL);
         if (!data)
                 return;
 
+        num_parents = of_clk_get_parent_count(node);
+
+        parent_names = kcalloc(num_parents, sizeof(char *), GFP_KERNEL);
+        if (!parent_names)
+                return;
+
+        for (i = 0; i < num_parents; i++)
+                parent_names[i] = of_clk_get_parent_name(node, i);
+
+        data->num_parents = num_parents;
+        data->parent_names = parent_names;
         data->node = node;
         data->gpio_name = gpio_name;
         data->clk_register_get = clk_register_get;
diff --git a/drivers/clk/clk-qoriq.c b/drivers/clk/clk-qoriq.c
index 1ab0fb81c6a0..7bc1c4527ae4 100644
--- a/drivers/clk/clk-qoriq.c
+++ b/drivers/clk/clk-qoriq.c
@@ -778,8 +778,10 @@ static struct clk * __init create_one_cmux(struct clockgen *cg, int idx)
          */
         clksel = (cg_in(cg, hwc->reg) & CLKSEL_MASK) >> CLKSEL_SHIFT;
         div = get_pll_div(cg, hwc, clksel);
-        if (!div)
+        if (!div) {
+                kfree(hwc);
                 return NULL;
+        }
 
         pct80_rate = clk_get_rate(div->clk);
         pct80_rate *= 8;
diff --git a/drivers/clk/clk-scpi.c b/drivers/clk/clk-scpi.c
index 0b501a9fef92..cd0f2726f5e0 100644
--- a/drivers/clk/clk-scpi.c
+++ b/drivers/clk/clk-scpi.c
@@ -292,6 +292,7 @@ static int scpi_clocks_probe(struct platform_device *pdev)
                 ret = scpi_clk_add(dev, child, match);
                 if (ret) {
                         scpi_clocks_remove(pdev);
+                        of_node_put(child);
                         return ret;
                 }
         }
diff --git a/drivers/clk/imx/clk-pllv1.c b/drivers/clk/imx/clk-pllv1.c
index 8564e4342c7d..82fe3662b5f6 100644
--- a/drivers/clk/imx/clk-pllv1.c
+++ b/drivers/clk/imx/clk-pllv1.c
@@ -52,7 +52,7 @@ static unsigned long clk_pllv1_recalc_rate(struct clk_hw *hw,
                 unsigned long parent_rate)
 {
         struct clk_pllv1 *pll = to_clk_pllv1(hw);
-        long long ll;
+        unsigned long long ull;
         int mfn_abs;
         unsigned int mfi, mfn, mfd, pd;
         u32 reg;
@@ -94,16 +94,16 @@ static unsigned long clk_pllv1_recalc_rate(struct clk_hw *hw,
         rate = parent_rate * 2;
         rate /= pd + 1;
 
-        ll = (unsigned long long)rate * mfn_abs;
+        ull = (unsigned long long)rate * mfn_abs;
 
-        do_div(ll, mfd + 1);
+        do_div(ull, mfd + 1);
 
         if (mfn_is_negative(pll, mfn))
-                ll = -ll;
+                ull = (rate * mfi) - ull;
+        else
+                ull = (rate * mfi) + ull;
 
-        ll = (rate * mfi) + ll;
-
-        return ll;
+        return ull;
 }
 
 static struct clk_ops clk_pllv1_ops = {
diff --git a/drivers/clk/imx/clk-pllv2.c b/drivers/clk/imx/clk-pllv2.c
index b18f875eac6a..4aeda56ce372 100644
--- a/drivers/clk/imx/clk-pllv2.c
+++ b/drivers/clk/imx/clk-pllv2.c
@@ -79,7 +79,7 @@ static unsigned long __clk_pllv2_recalc_rate(unsigned long parent_rate,
 {
         long mfi, mfn, mfd, pdf, ref_clk;
         unsigned long dbl;
-        s64 temp;
+        u64 temp;
 
         dbl = dp_ctl & MXC_PLL_DP_CTL_DPDCK0_2_EN;
 
@@ -98,8 +98,9 @@ static unsigned long __clk_pllv2_recalc_rate(unsigned long parent_rate,
         temp = (u64) ref_clk * abs(mfn);
         do_div(temp, mfd + 1);
         if (mfn < 0)
-                temp = -temp;
-        temp = (ref_clk * mfi) + temp;
+                temp = (ref_clk * mfi) - temp;
+        else
+                temp = (ref_clk * mfi) + temp;
 
         return temp;
 }
@@ -126,7 +127,7 @@ static int __clk_pllv2_set_rate(unsigned long rate, unsigned long parent_rate,
 {
         u32 reg;
         long mfi, pdf, mfn, mfd = 999999;
-        s64 temp64;
+        u64 temp64;
         unsigned long quad_parent_rate;
 
         quad_parent_rate = 4 * parent_rate;
diff --git a/drivers/clk/imx/clk-vf610.c b/drivers/clk/imx/clk-vf610.c
index d1b1c95177bb..0a94d9661d91 100644
--- a/drivers/clk/imx/clk-vf610.c
+++ b/drivers/clk/imx/clk-vf610.c
@@ -335,22 +335,22 @@ static void __init vf610_clocks_init(struct device_node *ccm_node)
         clk[VF610_CLK_SAI0_SEL] = imx_clk_mux("sai0_sel", CCM_CSCMR1, 0, 2, sai_sels, 4);
         clk[VF610_CLK_SAI0_EN] = imx_clk_gate("sai0_en", "sai0_sel", CCM_CSCDR1, 16);
         clk[VF610_CLK_SAI0_DIV] = imx_clk_divider("sai0_div", "sai0_en", CCM_CSCDR1, 0, 4);
-        clk[VF610_CLK_SAI0] = imx_clk_gate2("sai0", "sai0_div", CCM_CCGR0, CCM_CCGRx_CGn(15));
+        clk[VF610_CLK_SAI0] = imx_clk_gate2("sai0", "ipg_bus", CCM_CCGR0, CCM_CCGRx_CGn(15));
 
         clk[VF610_CLK_SAI1_SEL] = imx_clk_mux("sai1_sel", CCM_CSCMR1, 2, 2, sai_sels, 4);
         clk[VF610_CLK_SAI1_EN] = imx_clk_gate("sai1_en", "sai1_sel", CCM_CSCDR1, 17);
         clk[VF610_CLK_SAI1_DIV] = imx_clk_divider("sai1_div", "sai1_en", CCM_CSCDR1, 4, 4);
-        clk[VF610_CLK_SAI1] = imx_clk_gate2("sai1", "sai1_div", CCM_CCGR1, CCM_CCGRx_CGn(0));
+        clk[VF610_CLK_SAI1] = imx_clk_gate2("sai1", "ipg_bus", CCM_CCGR1, CCM_CCGRx_CGn(0));
 
         clk[VF610_CLK_SAI2_SEL] = imx_clk_mux("sai2_sel", CCM_CSCMR1, 4, 2, sai_sels, 4);
         clk[VF610_CLK_SAI2_EN] = imx_clk_gate("sai2_en", "sai2_sel", CCM_CSCDR1, 18);
         clk[VF610_CLK_SAI2_DIV] = imx_clk_divider("sai2_div", "sai2_en", CCM_CSCDR1, 8, 4);
-        clk[VF610_CLK_SAI2] = imx_clk_gate2("sai2", "sai2_div", CCM_CCGR1, CCM_CCGRx_CGn(1));
+        clk[VF610_CLK_SAI2] = imx_clk_gate2("sai2", "ipg_bus", CCM_CCGR1, CCM_CCGRx_CGn(1));
 
         clk[VF610_CLK_SAI3_SEL] = imx_clk_mux("sai3_sel", CCM_CSCMR1, 6, 2, sai_sels, 4);
         clk[VF610_CLK_SAI3_EN] = imx_clk_gate("sai3_en", "sai3_sel", CCM_CSCDR1, 19);
         clk[VF610_CLK_SAI3_DIV] = imx_clk_divider("sai3_div", "sai3_en", CCM_CSCDR1, 12, 4);
-        clk[VF610_CLK_SAI3] = imx_clk_gate2("sai3", "sai3_div", CCM_CCGR1, CCM_CCGRx_CGn(2));
+        clk[VF610_CLK_SAI3] = imx_clk_gate2("sai3", "ipg_bus", CCM_CCGR1, CCM_CCGRx_CGn(2));
 
         clk[VF610_CLK_NFC_SEL] = imx_clk_mux("nfc_sel", CCM_CSCMR1, 12, 2, nfc_sels, 4);
         clk[VF610_CLK_NFC_EN] = imx_clk_gate("nfc_en", "nfc_sel", CCM_CSCDR2, 9);
diff --git a/drivers/clk/mmp/clk-mmp2.c b/drivers/clk/mmp/clk-mmp2.c
index 09d2832fbd78..71fd29348f28 100644
--- a/drivers/clk/mmp/clk-mmp2.c
+++ b/drivers/clk/mmp/clk-mmp2.c
@@ -9,6 +9,7 @@
  * warranty of any kind, whether express or implied.
  */
 
+#include <linux/clk.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
diff --git a/drivers/clk/mmp/clk-pxa168.c b/drivers/clk/mmp/clk-pxa168.c
index 93e967c0f972..75244915df05 100644
--- a/drivers/clk/mmp/clk-pxa168.c
+++ b/drivers/clk/mmp/clk-pxa168.c
@@ -9,6 +9,7 @@
  * warranty of any kind, whether express or implied.
  */
 
+#include <linux/clk.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
diff --git a/drivers/clk/mmp/clk-pxa910.c b/drivers/clk/mmp/clk-pxa910.c
index 993abcdb32cc..37ba04ba1368 100644
--- a/drivers/clk/mmp/clk-pxa910.c
+++ b/drivers/clk/mmp/clk-pxa910.c
@@ -9,6 +9,7 @@
  * warranty of any kind, whether express or implied.
  */
 
+#include <linux/clk.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
diff --git a/drivers/clk/sunxi/clk-a10-pll2.c b/drivers/clk/sunxi/clk-a10-pll2.c
index 5484c31ec568..0ee1f363e4be 100644
--- a/drivers/clk/sunxi/clk-a10-pll2.c
+++ b/drivers/clk/sunxi/clk-a10-pll2.c
@@ -41,15 +41,10 @@
 
 #define SUN4I_PLL2_OUTPUTS              4
 
-struct sun4i_pll2_data {
-        u32     post_div_offset;
-        u32     pre_div_flags;
-};
-
 static DEFINE_SPINLOCK(sun4i_a10_pll2_lock);
 
 static void __init sun4i_pll2_setup(struct device_node *node,
-                                    struct sun4i_pll2_data *data)
+                                    int post_div_offset)
 {
         const char *clk_name = node->name, *parent;
         struct clk **clks, *base_clk, *prediv_clk;
@@ -76,7 +71,7 @@ static void __init sun4i_pll2_setup(struct device_node *node,
                                           parent, 0, reg,
                                           SUN4I_PLL2_PRE_DIV_SHIFT,
                                           SUN4I_PLL2_PRE_DIV_WIDTH,
-                                          data->pre_div_flags,
+                                          CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO,
                                           &sun4i_a10_pll2_lock);
         if (!prediv_clk) {
                 pr_err("Couldn't register the prediv clock\n");
@@ -127,7 +122,7 @@ static void __init sun4i_pll2_setup(struct device_node *node,
          */
         val = readl(reg);
         val &= ~(SUN4I_PLL2_POST_DIV_MASK << SUN4I_PLL2_POST_DIV_SHIFT);
-        val |= (SUN4I_PLL2_POST_DIV_VALUE - data->post_div_offset) << SUN4I_PLL2_POST_DIV_SHIFT;
+        val |= (SUN4I_PLL2_POST_DIV_VALUE - post_div_offset) << SUN4I_PLL2_POST_DIV_SHIFT;
         writel(val, reg);
 
         of_property_read_string_index(node, "clock-output-names",
@@ -191,25 +186,17 @@ err_unmap:
         iounmap(reg);
 }
 
-static struct sun4i_pll2_data sun4i_a10_pll2_data = {
-        .pre_div_flags  = CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO,
-};
-
 static void __init sun4i_a10_pll2_setup(struct device_node *node)
 {
-        sun4i_pll2_setup(node, &sun4i_a10_pll2_data);
+        sun4i_pll2_setup(node, 0);
 }
 
 CLK_OF_DECLARE(sun4i_a10_pll2, "allwinner,sun4i-a10-pll2-clk",
                sun4i_a10_pll2_setup);
 
-static struct sun4i_pll2_data sun5i_a13_pll2_data = {
-        .post_div_offset        = 1,
-};
-
 static void __init sun5i_a13_pll2_setup(struct device_node *node)
 {
-        sun4i_pll2_setup(node, &sun5i_a13_pll2_data);
+        sun4i_pll2_setup(node, 1);
 }
 
 CLK_OF_DECLARE(sun5i_a13_pll2, "allwinner,sun5i-a13-pll2-clk",
diff --git a/drivers/clk/ti/clk-816x.c b/drivers/clk/ti/clk-816x.c
index 1dfad0c712cd..2a5d84fdddc5 100644
--- a/drivers/clk/ti/clk-816x.c
+++ b/drivers/clk/ti/clk-816x.c
@@ -20,6 +20,8 @@ static struct ti_dt_clk dm816x_clks[] = {
         DT_CLK(NULL, "sys_clkin", "sys_clkin_ck"),
         DT_CLK(NULL, "timer_sys_ck", "sys_clkin_ck"),
         DT_CLK(NULL, "sys_32k_ck", "sys_32k_ck"),
+        DT_CLK(NULL, "timer_32k_ck", "sysclk18_ck"),
+        DT_CLK(NULL, "timer_ext_ck", "tclkin_ck"),
         DT_CLK(NULL, "mpu_ck", "mpu_ck"),
         DT_CLK(NULL, "timer1_fck", "timer1_fck"),
         DT_CLK(NULL, "timer2_fck", "timer2_fck"),
diff --git a/drivers/clk/ti/clkt_dpll.c b/drivers/clk/ti/clkt_dpll.c
index 9023ca9caf84..b5cc6f66ae5d 100644
--- a/drivers/clk/ti/clkt_dpll.c
+++ b/drivers/clk/ti/clkt_dpll.c
@@ -240,7 +240,7 @@ u8 omap2_init_dpll_parent(struct clk_hw *hw)
  */
 unsigned long omap2_get_dpll_rate(struct clk_hw_omap *clk)
 {
-        long long dpll_clk;
+        u64 dpll_clk;
         u32 dpll_mult, dpll_div, v;
         struct dpll_data *dd;
 
@@ -262,7 +262,7 @@ unsigned long omap2_get_dpll_rate(struct clk_hw_omap *clk)
         dpll_div = v & dd->div1_mask;
         dpll_div >>= __ffs(dd->div1_mask);
 
-        dpll_clk = (long long)clk_get_rate(dd->clk_ref) * dpll_mult;
+        dpll_clk = (u64)clk_get_rate(dd->clk_ref) * dpll_mult;
         do_div(dpll_clk, dpll_div + 1);
 
         return dpll_clk;
diff --git a/drivers/clk/ti/divider.c b/drivers/clk/ti/divider.c
index 5b1726829e6d..df2558350fc1 100644
--- a/drivers/clk/ti/divider.c
+++ b/drivers/clk/ti/divider.c
@@ -214,7 +214,6 @@ static int ti_clk_divider_set_rate(struct clk_hw *hw, unsigned long rate,
 {
         struct clk_divider *divider;
         unsigned int div, value;
-        unsigned long flags = 0;
         u32 val;
 
         if (!hw || !rate)
@@ -228,9 +227,6 @@ static int ti_clk_divider_set_rate(struct clk_hw *hw, unsigned long rate,
         if (value > div_mask(divider))
                 value = div_mask(divider);
 
-        if (divider->lock)
-                spin_lock_irqsave(divider->lock, flags);
-
         if (divider->flags & CLK_DIVIDER_HIWORD_MASK) {
                 val = div_mask(divider) << (divider->shift + 16);
         } else {
@@ -240,9 +236,6 @@ static int ti_clk_divider_set_rate(struct clk_hw *hw, unsigned long rate,
         val |= value << divider->shift;
         ti_clk_ll_ops->clk_writel(val, divider->reg);
 
-        if (divider->lock)
-                spin_unlock_irqrestore(divider->lock, flags);
-
         return 0;
 }
 
@@ -256,8 +249,7 @@ static struct clk *_register_divider(struct device *dev, const char *name,
                                      const char *parent_name,
                                      unsigned long flags, void __iomem *reg,
                                      u8 shift, u8 width, u8 clk_divider_flags,
-                                     const struct clk_div_table *table,
-                                     spinlock_t *lock)
+                                     const struct clk_div_table *table)
 {
         struct clk_divider *div;
         struct clk *clk;
@@ -288,7 +280,6 @@ static struct clk *_register_divider(struct device *dev, const char *name,
         div->shift = shift;
         div->width = width;
         div->flags = clk_divider_flags;
-        div->lock = lock;
         div->hw.init = &init;
         div->table = table;
 
@@ -421,7 +412,7 @@ struct clk *ti_clk_register_divider(struct ti_clk *setup)
 
         clk = _register_divider(NULL, setup->name, div->parent,
                                 flags, (void __iomem *)reg, div->bit_shift,
-                                width, div_flags, table, NULL);
+                                width, div_flags, table);
 
         if (IS_ERR(clk))
                 kfree(table);
@@ -584,8 +575,7 @@ static void __init of_ti_divider_clk_setup(struct device_node *node)
                 goto cleanup;
 
         clk = _register_divider(NULL, node->name, parent_name, flags, reg,
-                                shift, width, clk_divider_flags, table,
-                                NULL);
+                                shift, width, clk_divider_flags, table);
 
         if (!IS_ERR(clk)) {
                 of_clk_add_provider(node, of_clk_src_simple_get, clk);
diff --git a/drivers/clk/ti/fapll.c b/drivers/clk/ti/fapll.c
index f4b2e9888bdf..66a0d0ed8b55 100644
--- a/drivers/clk/ti/fapll.c
+++ b/drivers/clk/ti/fapll.c
@@ -168,7 +168,7 @@ static unsigned long ti_fapll_recalc_rate(struct clk_hw *hw,
 {
         struct fapll_data *fd = to_fapll(hw);
         u32 fapll_n, fapll_p, v;
-        long long rate;
+        u64 rate;
 
         if (ti_fapll_clock_is_bypass(fd))
                 return parent_rate;
@@ -314,7 +314,7 @@ static unsigned long ti_fapll_synth_recalc_rate(struct clk_hw *hw,
 {
         struct fapll_synth *synth = to_synth(hw);
         u32 synth_div_m;
-        long long rate;
+        u64 rate;
 
         /* The audio_pll_clk1 is hardwired to produce 32.768KiHz clock */
         if (!synth->div)
diff --git a/drivers/clk/ti/mux.c b/drivers/clk/ti/mux.c
index 69f08a1d047d..dab9ba88b9d6 100644
--- a/drivers/clk/ti/mux.c
+++ b/drivers/clk/ti/mux.c
@@ -69,7 +69,6 @@ static int ti_clk_mux_set_parent(struct clk_hw *hw, u8 index)
 {
         struct clk_mux *mux = to_clk_mux(hw);
         u32 val;
-        unsigned long flags = 0;
 
         if (mux->table) {
                 index = mux->table[index];
@@ -81,9 +80,6 @@ static int ti_clk_mux_set_parent(struct clk_hw *hw, u8 index)
                         index++;
         }
 
-        if (mux->lock)
-                spin_lock_irqsave(mux->lock, flags);
-
         if (mux->flags & CLK_MUX_HIWORD_MASK) {
                 val = mux->mask << (mux->shift + 16);
         } else {
@@ -93,9 +89,6 @@ static int ti_clk_mux_set_parent(struct clk_hw *hw, u8 index)
         val |= index << mux->shift;
         ti_clk_ll_ops->clk_writel(val, mux->reg);
 
-        if (mux->lock)
-                spin_unlock_irqrestore(mux->lock, flags);
-
         return 0;
 }
 
@@ -109,7 +102,7 @@ static struct clk *_register_mux(struct device *dev, const char *name,
                                  const char **parent_names, u8 num_parents,
                                  unsigned long flags, void __iomem *reg,
                                  u8 shift, u32 mask, u8 clk_mux_flags,
-                                 u32 *table, spinlock_t *lock)
+                                 u32 *table)
 {
         struct clk_mux *mux;
         struct clk *clk;
@@ -133,7 +126,6 @@ static struct clk *_register_mux(struct device *dev, const char *name,
         mux->shift = shift;
         mux->mask = mask;
         mux->flags = clk_mux_flags;
-        mux->lock = lock;
         mux->table = table;
         mux->hw.init = &init;
 
@@ -175,7 +167,7 @@ struct clk *ti_clk_register_mux(struct ti_clk *setup)
 
         return _register_mux(NULL, setup->name, mux->parents, mux->num_parents,
                              flags, (void __iomem *)reg, mux->bit_shift, mask,
-                             mux_flags, NULL, NULL);
+                             mux_flags, NULL);
 }
 
 /**
@@ -227,8 +219,7 @@ static void of_mux_clk_setup(struct device_node *node)
         mask = (1 << fls(mask)) - 1;
 
         clk = _register_mux(NULL, node->name, parent_names, num_parents,
-                            flags, reg, shift, mask, clk_mux_flags, NULL,
-                            NULL);
+                            flags, reg, shift, mask, clk_mux_flags, NULL);
 
         if (!IS_ERR(clk))
                 of_clk_add_provider(node, of_clk_src_simple_get, clk);
diff --git a/drivers/clocksource/mmio.c b/drivers/clocksource/mmio.c
index 1593ade2a815..c4f7d7a9b689 100644
--- a/drivers/clocksource/mmio.c
+++ b/drivers/clocksource/mmio.c
@@ -55,7 +55,7 @@ int __init clocksource_mmio_init(void __iomem *base, const char *name,
 {
         struct clocksource_mmio *cs;
 
-        if (bits > 32 || bits < 16)
+        if (bits > 64 || bits < 16)
                 return -EINVAL;
 
         cs = kzalloc(sizeof(struct clocksource_mmio), GFP_KERNEL);
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 8014c2307332..235a1ba73d92 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -202,7 +202,7 @@ config ARM_SA1110_CPUFREQ
 
 config ARM_SCPI_CPUFREQ
         tristate "SCPI based CPUfreq driver"
-        depends on ARM_BIG_LITTLE_CPUFREQ && ARM_SCPI_PROTOCOL
+        depends on ARM_BIG_LITTLE_CPUFREQ && ARM_SCPI_PROTOCOL && COMMON_CLK_SCPI
         help
           This adds the CPUfreq driver support for ARM big.LITTLE platforms
           using SCPI protocol for CPU power management.
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index e8cb334094b0..7c0bdfb1a2ca 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -98,10 +98,11 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
         policy->max = cpu->perf_caps.highest_perf;
         policy->cpuinfo.min_freq = policy->min;
         policy->cpuinfo.max_freq = policy->max;
+        policy->shared_type = cpu->shared_type;
 
         if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY)
                 cpumask_copy(policy->cpus, cpu->shared_cpu_map);
-        else {
+        else if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL) {
                 /* Support only SW_ANY for now. */
                 pr_debug("Unsupported CPU co-ord type\n");
                 return -EFAULT;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 7c48e7316d91..8412ce5f93a7 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -976,10 +976,14 @@ static int cpufreq_init_policy(struct cpufreq_policy *policy)
 
         new_policy.governor = gov;
 
-        /* Use the default policy if its valid. */
-        if (cpufreq_driver->setpolicy)
-                cpufreq_parse_governor(gov->name, &new_policy.policy, NULL);
-
+        /* Use the default policy if there is no last_policy. */
+        if (cpufreq_driver->setpolicy) {
+                if (policy->last_policy)
+                        new_policy.policy = policy->last_policy;
+                else
+                        cpufreq_parse_governor(gov->name, &new_policy.policy,
+                                               NULL);
+        }
         /* set default policy */
         return cpufreq_set_policy(policy, &new_policy);
 }
@@ -1330,6 +1334,8 @@ static void cpufreq_offline_prepare(unsigned int cpu)
                 if (has_target())
                         strncpy(policy->last_governor, policy->governor->name,
                                 CPUFREQ_NAME_LEN);
+                else
+                        policy->last_policy = policy->policy;
         } else if (cpu == policy->cpu) {
                 /* Nominate new CPU */
                 policy->cpu = cpumask_any(policy->cpus);
@@ -1401,13 +1407,10 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
         }
 
         cpumask_clear_cpu(cpu, policy->real_cpus);
+        remove_cpu_dev_symlink(policy, cpu);
 
-        if (cpumask_empty(policy->real_cpus)) {
+        if (cpumask_empty(policy->real_cpus))
                 cpufreq_policy_free(policy, true);
-                return;
-        }
-
-        remove_cpu_dev_symlink(policy, cpu);
 }
 
 static void handle_update(struct work_struct *work)
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 001a532e342e..4d07cbd2b23c 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1101,6 +1101,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
             policy->max >= policy->cpuinfo.max_freq) {
                 pr_debug("intel_pstate: set performance\n");
                 limits = &performance_limits;
+                if (hwp_active)
+                        intel_pstate_hwp_set();
                 return 0;
         }
 
@@ -1108,7 +1110,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
         limits = &powersave_limits;
         limits->min_policy_pct = (policy->min * 100) / policy->cpuinfo.max_freq;
         limits->min_policy_pct = clamp_t(int, limits->min_policy_pct, 0 , 100);
-        limits->max_policy_pct = (policy->max * 100) / policy->cpuinfo.max_freq;
+        limits->max_policy_pct = DIV_ROUND_UP(policy->max * 100,
+                                              policy->cpuinfo.max_freq);
         limits->max_policy_pct = clamp_t(int, limits->max_policy_pct, 0 , 100);
 
         /* Normalize user input to [min_policy_pct, max_policy_pct] */
@@ -1120,6 +1123,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
                                    limits->max_sysfs_pct);
         limits->max_perf_pct = max(limits->min_policy_pct,
                                    limits->max_perf_pct);
+        limits->max_perf = round_up(limits->max_perf, 8);
 
         /* Make sure min_perf_pct <= max_perf_pct */
         limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct);
diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c
index 733aa5153e74..68ef8fd9482f 100644
--- a/drivers/cpufreq/s3c24xx-cpufreq.c
+++ b/drivers/cpufreq/s3c24xx-cpufreq.c
@@ -648,7 +648,7 @@ late_initcall(s3c_cpufreq_initcall);
  *
  * Register the given set of PLLs with the system.
  */
-int __init s3c_plltab_register(struct cpufreq_frequency_table *plls,
+int s3c_plltab_register(struct cpufreq_frequency_table *plls,
                                unsigned int plls_no)
 {
         struct cpufreq_frequency_table *vals;
diff --git a/drivers/crypto/nx/nx-aes-ccm.c b/drivers/crypto/nx/nx-aes-ccm.c
index 73ef49922788..7038f364acb5 100644
--- a/drivers/crypto/nx/nx-aes-ccm.c
+++ b/drivers/crypto/nx/nx-aes-ccm.c
@@ -409,7 +409,7 @@ static int ccm_nx_decrypt(struct aead_request   *req,
                 processed += to_process;
         } while (processed < nbytes);
 
-        rc = memcmp(csbcpb->cpb.aes_ccm.out_pat_or_mac, priv->oauth_tag,
+        rc = crypto_memneq(csbcpb->cpb.aes_ccm.out_pat_or_mac, priv->oauth_tag,
                     authsize) ? -EBADMSG : 0;
 out:
         spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
diff --git a/drivers/crypto/nx/nx-aes-gcm.c b/drivers/crypto/nx/nx-aes-gcm.c
index eee624f589b6..abd465f479c4 100644
--- a/drivers/crypto/nx/nx-aes-gcm.c
+++ b/drivers/crypto/nx/nx-aes-gcm.c
@@ -21,6 +21,7 @@
 
 #include <crypto/internal/aead.h>
 #include <crypto/aes.h>
+#include <crypto/algapi.h>
 #include <crypto/scatterwalk.h>
 #include <linux/module.h>
 #include <linux/types.h>
@@ -418,7 +419,7 @@ mac:
                         itag, req->src, req->assoclen + nbytes,
                         crypto_aead_authsize(crypto_aead_reqtfm(req)),
                         SCATTERWALK_FROM_SG);
-                rc = memcmp(itag, otag,
+                rc = crypto_memneq(itag, otag,
                             crypto_aead_authsize(crypto_aead_reqtfm(req))) ?
                      -EBADMSG : 0;
         }
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 46f531e19ccf..b6f9f42e2985 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -977,7 +977,7 @@ static void ipsec_esp_decrypt_swauth_done(struct device *dev,
                 } else
                         oicv = (char *)&edesc->link_tbl[0];
 
-                err = memcmp(oicv, icv, authsize) ? -EBADMSG : 0;
+                err = crypto_memneq(oicv, icv, authsize) ? -EBADMSG : 0;
         }
 
         kfree(edesc);
diff --git a/drivers/fpga/fpga-mgr.c b/drivers/fpga/fpga-mgr.c
index a24f5cb877e0..953dc9195937 100644
--- a/drivers/fpga/fpga-mgr.c
+++ b/drivers/fpga/fpga-mgr.c
@@ -122,12 +122,10 @@ int fpga_mgr_firmware_load(struct fpga_manager *mgr, u32 flags,
         }
 
         ret = fpga_mgr_buf_load(mgr, flags, fw->data, fw->size);
-        if (ret)
-                return ret;
 
         release_firmware(fw);
 
-        return 0;
+        return ret;
 }
 EXPORT_SYMBOL_GPL(fpga_mgr_firmware_load);
 
@@ -256,7 +254,6 @@ int fpga_mgr_register(struct device *dev, const char *name,
                       void *priv)
 {
         struct fpga_manager *mgr;
-        const char *dt_label;
         int id, ret;
 
         if (!mops || !mops->write_init || !mops->write ||
@@ -300,11 +297,9 @@ int fpga_mgr_register(struct device *dev, const char *name,
         mgr->dev.id = id;
         dev_set_drvdata(dev, mgr);
 
-        dt_label = of_get_property(mgr->dev.of_node, "label", NULL);
-        if (dt_label)
-                ret = dev_set_name(&mgr->dev, "%s", dt_label);
-        else
-                ret = dev_set_name(&mgr->dev, "fpga%d", id);
+        ret = dev_set_name(&mgr->dev, "fpga%d", id);
+        if (ret)
+                goto error_device;
 
         ret = device_add(&mgr->dev);
         if (ret)
diff --git a/drivers/gpio/gpio-74xx-mmio.c b/drivers/gpio/gpio-74xx-mmio.c
index 6ed7c0fb3378..6b186829087c 100644
--- a/drivers/gpio/gpio-74xx-mmio.c
+++ b/drivers/gpio/gpio-74xx-mmio.c
@@ -113,13 +113,16 @@ static int mmio_74xx_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 
 static int mmio_74xx_gpio_probe(struct platform_device *pdev)
 {
-        const struct of_device_id *of_id =
-                of_match_device(mmio_74xx_gpio_ids, &pdev->dev);
+        const struct of_device_id *of_id;
         struct mmio_74xx_gpio_priv *priv;
         struct resource *res;
         void __iomem *dat;
         int err;
 
+        of_id = of_match_device(mmio_74xx_gpio_ids, &pdev->dev);
+        if (!of_id)
+                return -ENODEV;
+
         priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
         if (!priv)
                 return -ENOMEM;
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index 56d2d026e62e..f7fbb46d5d79 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -1122,8 +1122,6 @@ static int omap_gpio_chip_init(struct gpio_bank *bank, struct irq_chip *irqc)
         /* MPUIO is a bit different, reading IRQ status clears it */
         if (bank->is_mpuio) {
                 irqc->irq_ack = dummy_irq_chip.irq_ack;
-                irqc->irq_mask = irq_gc_mask_set_bit;
-                irqc->irq_unmask = irq_gc_mask_clr_bit;
                 if (!bank->regs->wkup_en)
                         irqc->irq_set_wake = NULL;
         }
diff --git a/drivers/gpio/gpio-palmas.c b/drivers/gpio/gpio-palmas.c
index 171a6389f9ce..52b447c071cb 100644
--- a/drivers/gpio/gpio-palmas.c
+++ b/drivers/gpio/gpio-palmas.c
@@ -167,6 +167,8 @@ static int palmas_gpio_probe(struct platform_device *pdev)
         const struct palmas_device_data *dev_data;
 
         match = of_match_device(of_palmas_gpio_match, &pdev->dev);
+        if (!match)
+                return -ENODEV;
         dev_data = match->data;
         if (!dev_data)
                 dev_data = &palmas_dev_data;
diff --git a/drivers/gpio/gpio-syscon.c b/drivers/gpio/gpio-syscon.c
index 045a952576c7..7b25fdf64802 100644
--- a/drivers/gpio/gpio-syscon.c
+++ b/drivers/gpio/gpio-syscon.c
@@ -187,11 +187,15 @@ MODULE_DEVICE_TABLE(of, syscon_gpio_ids);
 static int syscon_gpio_probe(struct platform_device *pdev)
 {
         struct device *dev = &pdev->dev;
-        const struct of_device_id *of_id = of_match_device(syscon_gpio_ids, dev);
+        const struct of_device_id *of_id;
         struct syscon_gpio_priv *priv;
         struct device_node *np = dev->of_node;
         int ret;
 
+        of_id = of_match_device(syscon_gpio_ids, dev);
+        if (!of_id)
+                return -ENODEV;
+
         priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
         if (!priv)
                 return -ENOMEM;
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 027e5f47dd28..896bf29776b0 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -375,6 +375,60 @@ static int tegra_gpio_irq_set_wake(struct irq_data *d, unsigned int enable)
 }
 #endif
 
+#ifdef  CONFIG_DEBUG_FS
+
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+static int dbg_gpio_show(struct seq_file *s, void *unused)
+{
+        int i;
+        int j;
+
+        for (i = 0; i < tegra_gpio_bank_count; i++) {
+                for (j = 0; j < 4; j++) {
+                        int gpio = tegra_gpio_compose(i, j, 0);
+                        seq_printf(s,
+                                "%d:%d %02x %02x %02x %02x %02x %02x %06x\n",
+                                i, j,
+                                tegra_gpio_readl(GPIO_CNF(gpio)),
+                                tegra_gpio_readl(GPIO_OE(gpio)),
+                                tegra_gpio_readl(GPIO_OUT(gpio)),
+                                tegra_gpio_readl(GPIO_IN(gpio)),
+                                tegra_gpio_readl(GPIO_INT_STA(gpio)),
+                                tegra_gpio_readl(GPIO_INT_ENB(gpio)),
+                                tegra_gpio_readl(GPIO_INT_LVL(gpio)));
+                }
+        }
+        return 0;
+}
+
+static int dbg_gpio_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, dbg_gpio_show, &inode->i_private);
+}
+
+static const struct file_operations debug_fops = {
+        .open           = dbg_gpio_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+};
+
+static void tegra_gpio_debuginit(void)
+{
+        (void) debugfs_create_file("tegra_gpio", S_IRUGO,
+                                        NULL, NULL, &debug_fops);
+}
+
+#else
+
+static inline void tegra_gpio_debuginit(void)
+{
+}
+
+#endif
+
 static struct irq_chip tegra_gpio_irq_chip = {
         .name           = "GPIO",
         .irq_ack        = tegra_gpio_irq_ack,
@@ -519,6 +573,8 @@ static int tegra_gpio_probe(struct platform_device *pdev)
                         spin_lock_init(&bank->lvl_lock[j]);
         }
 
+        tegra_gpio_debuginit();
+
         return 0;
 }
 
@@ -536,52 +592,3 @@ static int __init tegra_gpio_init(void)
         return platform_driver_register(&tegra_gpio_driver);
 }
 postcore_initcall(tegra_gpio_init);
-
-#ifdef  CONFIG_DEBUG_FS
-
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-
-static int dbg_gpio_show(struct seq_file *s, void *unused)
-{
-        int i;
-        int j;
-
-        for (i = 0; i < tegra_gpio_bank_count; i++) {
-                for (j = 0; j < 4; j++) {
-                        int gpio = tegra_gpio_compose(i, j, 0);
-                        seq_printf(s,
-                                "%d:%d %02x %02x %02x %02x %02x %02x %06x\n",
-                                i, j,
-                                tegra_gpio_readl(GPIO_CNF(gpio)),
-                                tegra_gpio_readl(GPIO_OE(gpio)),
-                                tegra_gpio_readl(GPIO_OUT(gpio)),
-                                tegra_gpio_readl(GPIO_IN(gpio)),
-                                tegra_gpio_readl(GPIO_INT_STA(gpio)),
-                                tegra_gpio_readl(GPIO_INT_ENB(gpio)),
-                                tegra_gpio_readl(GPIO_INT_LVL(gpio)));
-                }
-        }
-        return 0;
-}
-
-static int dbg_gpio_open(struct inode *inode, struct file *file)
-{
-        return single_open(file, dbg_gpio_show, &inode->i_private);
-}
-
-static const struct file_operations debug_fops = {
-        .open           = dbg_gpio_open,
-        .read           = seq_read,
-        .llseek         = seq_lseek,
-        .release        = single_release,
-};
-
-static int __init tegra_gpio_debuginit(void)
-{
-        (void) debugfs_create_file("tegra_gpio", S_IRUGO,
-                                        NULL, NULL, &debug_fops);
-        return 0;
-}
-late_initcall(tegra_gpio_debuginit);
-#endif
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index a18f00fc1bb8..2a91f3287e3b 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -233,7 +233,7 @@ static struct gpio_desc *gpio_name_to_desc(const char * const name)
                 for (i = 0; i != chip->ngpio; ++i) {
                         struct gpio_desc *gpio = &chip->desc[i];
 
-                        if (!gpio->name)
+                        if (!gpio->name || !name)
                                 continue;
 
                         if (!strcmp(gpio->name, name)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 306f75700bf8..5a5f04d0902d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -496,6 +496,7 @@ struct amdgpu_bo_va_mapping {
 
 /* bo virtual addresses in a specific vm */
 struct amdgpu_bo_va {
+        struct mutex                    mutex;
         /* protected by bo being reserved */
         struct list_head                bo_list;
         struct fence                    *last_pt_update;
@@ -538,6 +539,7 @@ struct amdgpu_bo {
         /* Constant after initialization */
         struct amdgpu_device            *adev;
         struct drm_gem_object           gem_base;
+        struct amdgpu_bo                *parent;
 
         struct ttm_bo_kmap_obj          dma_buf_vmap;
         pid_t                           pid;
@@ -928,8 +930,6 @@ struct amdgpu_vm_id {
 };
 
 struct amdgpu_vm {
-        struct mutex            mutex;
-
         struct rb_root          va;
 
         /* protecting invalidated */
@@ -956,6 +956,8 @@ struct amdgpu_vm {
         struct amdgpu_vm_id     ids[AMDGPU_MAX_RINGS];
         /* for interval tree */
         spinlock_t              it_lock;
+        /* protecting freed */
+        spinlock_t              freed_lock;
 };
 
 struct amdgpu_vm_manager {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 3afcf0237c25..4f352ec9dec4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -222,6 +222,8 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
                                 }
 
                                 p->uf.bo = gem_to_amdgpu_bo(gobj);
+                                amdgpu_bo_ref(p->uf.bo);
+                                drm_gem_object_unreference_unlocked(gobj);
                                 p->uf.offset = fence_data->offset;
                         } else {
                                 ret = -EINVAL;
@@ -487,7 +489,7 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bo
                         amdgpu_ib_free(parser->adev, &parser->ibs[i]);
         kfree(parser->ibs);
         if (parser->uf.bo)
-                drm_gem_object_unreference_unlocked(&parser->uf.bo->gem_base);
+                amdgpu_bo_unref(&parser->uf.bo);
 }
 
 static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p,
@@ -776,7 +778,7 @@ static int amdgpu_cs_free_job(struct amdgpu_job *job)
                         amdgpu_ib_free(job->adev, &job->ibs[i]);
         kfree(job->ibs);
         if (job->uf.bo)
-                drm_gem_object_unreference_unlocked(&job->uf.bo->gem_base);
+                amdgpu_bo_unref(&job->uf.bo);
         return 0;
 }
 
@@ -784,8 +786,6 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 {
         struct amdgpu_device *adev = dev->dev_private;
         union drm_amdgpu_cs *cs = data;
-        struct amdgpu_fpriv *fpriv = filp->driver_priv;
-        struct amdgpu_vm *vm = &fpriv->vm;
         struct amdgpu_cs_parser parser = {};
         bool reserved_buffers = false;
         int i, r;
@@ -803,7 +803,6 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
                 r = amdgpu_cs_handle_lockup(adev, r);
                 return r;
         }
-        mutex_lock(&vm->mutex);
         r = amdgpu_cs_parser_relocs(&parser);
         if (r == -ENOMEM)
                 DRM_ERROR("Not enough memory for command submission!\n");
@@ -888,7 +887,6 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 out:
         amdgpu_cs_parser_fini(&parser, r, reserved_buffers);
-        mutex_unlock(&vm->mutex);
         r = amdgpu_cs_handle_lockup(adev, r);
         return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index e173a5a02f0d..5580d3420c3a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -73,6 +73,8 @@ static void amdgpu_flip_work_func(struct work_struct *__work)
         struct drm_crtc *crtc = &amdgpuCrtc->base;
         unsigned long flags;
         unsigned i;
+        int vpos, hpos, stat, min_udelay;
+        struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id];
 
         amdgpu_flip_wait_fence(adev, &work->excl);
         for (i = 0; i < work->shared_count; ++i)
@@ -81,6 +83,41 @@ static void amdgpu_flip_work_func(struct work_struct *__work)
         /* We borrow the event spin lock for protecting flip_status */
         spin_lock_irqsave(&crtc->dev->event_lock, flags);
 
+        /* If this happens to execute within the "virtually extended" vblank
+         * interval before the start of the real vblank interval then it needs
+         * to delay programming the mmio flip until the real vblank is entered.
+         * This prevents completing a flip too early due to the way we fudge
+         * our vblank counter and vblank timestamps in order to work around the
+         * problem that the hw fires vblank interrupts before actual start of
+         * vblank (when line buffer refilling is done for a frame). It
+         * complements the fudging logic in amdgpu_get_crtc_scanoutpos() for
+         * timestamping and amdgpu_get_vblank_counter_kms() for vblank counts.
+         *
+         * In practice this won't execute very often unless on very fast
+         * machines because the time window for this to happen is very small.
+         */
+        for (;;) {
+                /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank
+                 * start in hpos, and to the "fudged earlier" vblank start in
+                 * vpos.
+                 */
+                stat = amdgpu_get_crtc_scanoutpos(adev->ddev, work->crtc_id,
+                                                  GET_DISTANCE_TO_VBLANKSTART,
+                                                  &vpos, &hpos, NULL, NULL,
+                                                  &crtc->hwmode);
+
+                if ((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
+                    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE) ||
+                    !(vpos >= 0 && hpos <= 0))
+                        break;
+
+                /* Sleep at least until estimated real start of hw vblank */
+                spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+                min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5);
+                usleep_range(min_udelay, 2 * min_udelay);
+                spin_lock_irqsave(&crtc->dev->event_lock, flags);
+        };
+
         /* do the flip (mmio) */
         adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base);
         /* set the flip status */
@@ -109,7 +146,7 @@ static void amdgpu_unpin_work_func(struct work_struct *__work)
         } else
                 DRM_ERROR("failed to reserve buffer after flip\n");
 
-        drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base);
+        amdgpu_bo_unref(&work->old_rbo);
         kfree(work->shared);
         kfree(work);
 }
@@ -148,8 +185,8 @@ int amdgpu_crtc_page_flip(struct drm_crtc *crtc,
         obj = old_amdgpu_fb->obj;
 
         /* take a reference to the old object */
-        drm_gem_object_reference(obj);
         work->old_rbo = gem_to_amdgpu_bo(obj);
+        amdgpu_bo_ref(work->old_rbo);
 
         new_amdgpu_fb = to_amdgpu_framebuffer(fb);
         obj = new_amdgpu_fb->obj;
@@ -222,7 +259,7 @@ pflip_cleanup:
         amdgpu_bo_unreserve(new_rbo);
 
 cleanup:
-        drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base);
+        amdgpu_bo_unref(&work->old_rbo);
         fence_put(work->excl);
         for (i = 0; i < work->shared_count; ++i)
                 fence_put(work->shared[i]);
@@ -712,6 +749,15 @@ bool amdgpu_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
  * \param dev Device to query.
  * \param pipe Crtc to query.
  * \param flags Flags from caller (DRM_CALLED_FROM_VBLIRQ or 0).
+ *              For driver internal use only also supports these flags:
+ *
+ *              USE_REAL_VBLANKSTART to use the real start of vblank instead
+ *              of a fudged earlier start of vblank.
+ *
+ *              GET_DISTANCE_TO_VBLANKSTART to return distance to the
+ *              fudged earlier start of vblank in *vpos and the distance
+ *              to true start of vblank in *hpos.
+ *
  * \param *vpos Location where vertical scanout position should be stored.
  * \param *hpos Location where horizontal scanout position should go.
  * \param *stime Target location for timestamp taken immediately before
@@ -776,10 +822,40 @@ int amdgpu_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
                 vbl_end = 0;
         }
 
+        /* Called from driver internal vblank counter query code? */
+        if (flags & GET_DISTANCE_TO_VBLANKSTART) {
+            /* Caller wants distance from real vbl_start in *hpos */
+            *hpos = *vpos - vbl_start;
+        }
+
+        /* Fudge vblank to start a few scanlines earlier to handle the
+         * problem that vblank irqs fire a few scanlines before start
+         * of vblank. Some driver internal callers need the true vblank
+         * start to be used and signal this via the USE_REAL_VBLANKSTART flag.
+         *
+         * The cause of the "early" vblank irq is that the irq is triggered
+         * by the line buffer logic when the line buffer read position enters
+         * the vblank, whereas our crtc scanout position naturally lags the
+         * line buffer read position.
+         */
+        if (!(flags & USE_REAL_VBLANKSTART))
+                vbl_start -= adev->mode_info.crtcs[pipe]->lb_vblank_lead_lines;
+
         /* Test scanout position against vblank region. */
         if ((*vpos < vbl_start) && (*vpos >= vbl_end))
                 in_vbl = false;
 
+        /* In vblank? */
+        if (in_vbl)
+            ret |= DRM_SCANOUTPOS_IN_VBLANK;
+
+        /* Called from driver internal vblank counter query code? */
+        if (flags & GET_DISTANCE_TO_VBLANKSTART) {
+                /* Caller wants distance from fudged earlier vbl_start */
+                *vpos -= vbl_start;
+                return ret;
+        }
+
         /* Check if inside vblank area and apply corrective offsets:
          * vpos will then be >=0 in video scanout area, but negative
          * within vblank area, counting down the number of lines until
@@ -795,32 +871,6 @@ int amdgpu_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
         /* Correct for shifted end of vbl at vbl_end. */
         *vpos = *vpos - vbl_end;
 
-        /* In vblank? */
-        if (in_vbl)
-                ret |= DRM_SCANOUTPOS_IN_VBLANK;
-
-        /* Is vpos outside nominal vblank area, but less than
-         * 1/100 of a frame height away from start of vblank?
-         * If so, assume this isn't a massively delayed vblank
-         * interrupt, but a vblank interrupt that fired a few
-         * microseconds before true start of vblank. Compensate
-         * by adding a full frame duration to the final timestamp.
-         * Happens, e.g., on ATI R500, R600.
-         *
-         * We only do this if DRM_CALLED_FROM_VBLIRQ.
-         */
-        if ((flags & DRM_CALLED_FROM_VBLIRQ) && !in_vbl) {
-                vbl_start = mode->crtc_vdisplay;
-                vtotal = mode->crtc_vtotal;
-
-                if (vbl_start - *vpos < vtotal / 100) {
-                        *vpos -= vtotal;
-
-                        /* Signal this correction as "applied". */
-                        ret |= 0x8;
-                }
-        }
-
         return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 00c5b580f56c..9c253c535d26 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -115,12 +115,9 @@ int amdgpu_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_pri
         struct amdgpu_vm *vm = &fpriv->vm;
         struct amdgpu_bo_va *bo_va;
         int r;
-        mutex_lock(&vm->mutex);
         r = amdgpu_bo_reserve(rbo, false);
-        if (r) {
-                mutex_unlock(&vm->mutex);
+        if (r)
                 return r;
-        }
 
         bo_va = amdgpu_vm_bo_find(vm, rbo);
         if (!bo_va) {
@@ -129,7 +126,6 @@ int amdgpu_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_pri
                 ++bo_va->ref_count;
         }
         amdgpu_bo_unreserve(rbo);
-        mutex_unlock(&vm->mutex);
         return 0;
 }
 
@@ -142,10 +138,8 @@ void amdgpu_gem_object_close(struct drm_gem_object *obj,
         struct amdgpu_vm *vm = &fpriv->vm;
         struct amdgpu_bo_va *bo_va;
         int r;
-        mutex_lock(&vm->mutex);
         r = amdgpu_bo_reserve(rbo, true);
         if (r) {
-                mutex_unlock(&vm->mutex);
                 dev_err(adev->dev, "leaking bo va because "
                         "we fail to reserve bo (%d)\n", r);
                 return;
@@ -157,7 +151,6 @@ void amdgpu_gem_object_close(struct drm_gem_object *obj,
                 }
         }
         amdgpu_bo_unreserve(rbo);
-        mutex_unlock(&vm->mutex);
 }
 
 static int amdgpu_gem_handle_lockup(struct amdgpu_device *adev, int r)
@@ -242,8 +235,9 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
             AMDGPU_GEM_USERPTR_REGISTER))
                 return -EINVAL;
 
-        if (!(args->flags & AMDGPU_GEM_USERPTR_ANONONLY) ||
-                   !(args->flags & AMDGPU_GEM_USERPTR_REGISTER)) {
+        if (!(args->flags & AMDGPU_GEM_USERPTR_READONLY) && (
+             !(args->flags & AMDGPU_GEM_USERPTR_ANONONLY) ||
+             !(args->flags & AMDGPU_GEM_USERPTR_REGISTER))) {
 
                 /* if we want to write to it we must require anonymous
                    memory and install a MMU notifier */
@@ -483,6 +477,14 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
                 if (domain == AMDGPU_GEM_DOMAIN_CPU)
                         goto error_unreserve;
         }
+        list_for_each_entry(entry, &duplicates, head) {
+                domain = amdgpu_mem_type_to_domain(entry->bo->mem.mem_type);
+                /* if anything is swapped out don't swap it in here,
+                   just abort and wait for the next CS */
+                if (domain == AMDGPU_GEM_DOMAIN_CPU)
+                        goto error_unreserve;
+        }
+
         r = amdgpu_vm_update_page_directory(adev, bo_va->vm);
         if (r)
                 goto error_unreserve;
@@ -553,7 +555,6 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
         gobj = drm_gem_object_lookup(dev, filp, args->handle);
         if (gobj == NULL)
                 return -ENOENT;
-        mutex_lock(&fpriv->vm.mutex);
         rbo = gem_to_amdgpu_bo(gobj);
         INIT_LIST_HEAD(&list);
         INIT_LIST_HEAD(&duplicates);
@@ -568,7 +569,6 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
         }
         r = ttm_eu_reserve_buffers(&ticket, &list, true, &duplicates);
         if (r) {
-                mutex_unlock(&fpriv->vm.mutex);
                 drm_gem_object_unreference_unlocked(gobj);
                 return r;
         }
@@ -577,7 +577,6 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
         if (!bo_va) {
                 ttm_eu_backoff_reservation(&ticket, &list);
                 drm_gem_object_unreference_unlocked(gobj);
-                mutex_unlock(&fpriv->vm.mutex);
                 return -ENOENT;
         }
 
@@ -602,7 +601,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
         ttm_eu_backoff_reservation(&ticket, &list);
         if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE))
                 amdgpu_gem_va_update_vm(adev, bo_va, args->operation);
-        mutex_unlock(&fpriv->vm.mutex);
+
         drm_gem_object_unreference_unlocked(gobj);
         return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 1618e2294a16..e23843f4d877 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -611,13 +611,59 @@ void amdgpu_driver_preclose_kms(struct drm_device *dev,
 u32 amdgpu_get_vblank_counter_kms(struct drm_device *dev, unsigned int pipe)
 {
         struct amdgpu_device *adev = dev->dev_private;
+        int vpos, hpos, stat;
+        u32 count;
 
         if (pipe >= adev->mode_info.num_crtc) {
                 DRM_ERROR("Invalid crtc %u\n", pipe);
                 return -EINVAL;
         }
 
-        return amdgpu_display_vblank_get_counter(adev, pipe);
+        /* The hw increments its frame counter at start of vsync, not at start
+         * of vblank, as is required by DRM core vblank counter handling.
+         * Cook the hw count here to make it appear to the caller as if it
+         * incremented at start of vblank. We measure distance to start of
+         * vblank in vpos. vpos therefore will be >= 0 between start of vblank
+         * and start of vsync, so vpos >= 0 means to bump the hw frame counter
+         * result by 1 to give the proper appearance to caller.
+         */
+        if (adev->mode_info.crtcs[pipe]) {
+                /* Repeat readout if needed to provide stable result if
+                 * we cross start of vsync during the queries.
+                 */
+                do {
+                        count = amdgpu_display_vblank_get_counter(adev, pipe);
+                        /* Ask amdgpu_get_crtc_scanoutpos to return vpos as
+                         * distance to start of vblank, instead of regular
+                         * vertical scanout pos.
+                         */
+                        stat = amdgpu_get_crtc_scanoutpos(
+                                dev, pipe, GET_DISTANCE_TO_VBLANKSTART,
+                                &vpos, &hpos, NULL, NULL,
+                                &adev->mode_info.crtcs[pipe]->base.hwmode);
+                } while (count != amdgpu_display_vblank_get_counter(adev, pipe));
+
+                if (((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
+                    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE))) {
+                        DRM_DEBUG_VBL("Query failed! stat %d\n", stat);
+                } else {
+                        DRM_DEBUG_VBL("crtc %d: dist from vblank start %d\n",
+                                      pipe, vpos);
+
+                        /* Bump counter if we are at >= leading edge of vblank,
+                         * but before vsync where vpos would turn negative and
+                         * the hw counter really increments.
+                         */
+                        if (vpos >= 0)
+                                count++;
+                }
+        } else {
+                /* Fallback to use value as is. */
+                count = amdgpu_display_vblank_get_counter(adev, pipe);
+                DRM_DEBUG_VBL("NULL mode info! Returned count may be wrong.\n");
+        }
+
+        return count;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index b62c1710cab6..064ebb347074 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -407,6 +407,7 @@ struct amdgpu_crtc {
         u32 line_time;
         u32 wm_low;
         u32 wm_high;
+        u32 lb_vblank_lead_lines;
         struct drm_display_mode hw_mode;
 };
 
@@ -528,6 +529,10 @@ struct amdgpu_framebuffer {
 #define ENCODER_MODE_IS_DP(em) (((em) == ATOM_ENCODER_MODE_DP) || \
                                 ((em) == ATOM_ENCODER_MODE_DP_MST))
 
+/* Driver internal use only flags of amdgpu_get_crtc_scanoutpos() */
+#define USE_REAL_VBLANKSTART            (1 << 30)
+#define GET_DISTANCE_TO_VBLANKSTART     (1 << 31)
+
 void amdgpu_link_encoder_connector(struct drm_device *dev);
 
 struct drm_connector *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 0d524384ff79..c3ce103b6a33 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -100,6 +100,7 @@ static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
         list_del_init(&bo->list);
         mutex_unlock(&bo->adev->gem.mutex);
         drm_gem_object_release(&bo->gem_base);
+        amdgpu_bo_unref(&bo->parent);
         kfree(bo->metadata);
         kfree(bo);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index d4bac5f49939..8a1752ff3d8e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -587,9 +587,13 @@ static int amdgpu_ttm_backend_bind(struct ttm_tt *ttm,
         uint32_t flags = amdgpu_ttm_tt_pte_flags(gtt->adev, ttm, bo_mem);
         int r;
 
-        if (gtt->userptr)
-                amdgpu_ttm_tt_pin_userptr(ttm);
-
+        if (gtt->userptr) {
+                r = amdgpu_ttm_tt_pin_userptr(ttm);
+                if (r) {
+                        DRM_ERROR("failed to pin userptr\n");
+                        return r;
+                }
+        }
         gtt->offset = (unsigned long)(bo_mem->start << PAGE_SHIFT);
         if (!ttm->num_pages) {
                 WARN(1, "nothing to bind %lu pages for mreg %p back %p!\n",
@@ -797,11 +801,12 @@ uint32_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm,
         if (mem && mem->mem_type != TTM_PL_SYSTEM)
                 flags |= AMDGPU_PTE_VALID;
 
-        if (mem && mem->mem_type == TTM_PL_TT)
+        if (mem && mem->mem_type == TTM_PL_TT) {
                 flags |= AMDGPU_PTE_SYSTEM;
 
-        if (!ttm || ttm->caching_state == tt_cached)
-                flags |= AMDGPU_PTE_SNOOPED;
+                if (ttm->caching_state == tt_cached)
+                        flags |= AMDGPU_PTE_SNOOPED;
+        }
 
         if (adev->asic_type >= CHIP_TOPAZ)
                 flags |= AMDGPU_PTE_EXECUTABLE;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 03f0c3bae516..a745eeeb5d82 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -392,7 +392,10 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
         ib->ptr[ib->length_dw++] = 0x00000001; /* session cmd */
         ib->ptr[ib->length_dw++] = handle;
 
-        ib->ptr[ib->length_dw++] = 0x00000030; /* len */
+        if ((ring->adev->vce.fw_version >> 24) >= 52)
+                ib->ptr[ib->length_dw++] = 0x00000040; /* len */
+        else
+                ib->ptr[ib->length_dw++] = 0x00000030; /* len */
         ib->ptr[ib->length_dw++] = 0x01000001; /* create cmd */
         ib->ptr[ib->length_dw++] = 0x00000000;
         ib->ptr[ib->length_dw++] = 0x00000042;
@@ -404,6 +407,12 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
         ib->ptr[ib->length_dw++] = 0x00000100;
         ib->ptr[ib->length_dw++] = 0x0000000c;
         ib->ptr[ib->length_dw++] = 0x00000000;
+        if ((ring->adev->vce.fw_version >> 24) >= 52) {
+                ib->ptr[ib->length_dw++] = 0x00000000;
+                ib->ptr[ib->length_dw++] = 0x00000000;
+                ib->ptr[ib->length_dw++] = 0x00000000;
+                ib->ptr[ib->length_dw++] = 0x00000000;
+        }
 
         ib->ptr[ib->length_dw++] = 0x00000014; /* len */
         ib->ptr[ib->length_dw++] = 0x05000005; /* feedback buffer */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 159ce54bbd8d..b53d273eb7a1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -885,17 +885,21 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
         struct amdgpu_bo_va_mapping *mapping;
         int r;
 
+        spin_lock(&vm->freed_lock);
         while (!list_empty(&vm->freed)) {
                 mapping = list_first_entry(&vm->freed,
                         struct amdgpu_bo_va_mapping, list);
                 list_del(&mapping->list);
-
+                spin_unlock(&vm->freed_lock);
                 r = amdgpu_vm_bo_update_mapping(adev, vm, mapping, 0, 0, NULL);
                 kfree(mapping);
                 if (r)
                         return r;
 
+                spin_lock(&vm->freed_lock);
         }
+        spin_unlock(&vm->freed_lock);
+
         return 0;
 
 }
@@ -922,8 +926,9 @@ int amdgpu_vm_clear_invalids(struct amdgpu_device *adev,
                 bo_va = list_first_entry(&vm->invalidated,
                         struct amdgpu_bo_va, vm_status);
                 spin_unlock(&vm->status_lock);
-
+                mutex_lock(&bo_va->mutex);
                 r = amdgpu_vm_bo_update(adev, bo_va, NULL);
+                mutex_unlock(&bo_va->mutex);
                 if (r)
                         return r;
 
@@ -967,7 +972,7 @@ struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
         INIT_LIST_HEAD(&bo_va->valids);
         INIT_LIST_HEAD(&bo_va->invalids);
         INIT_LIST_HEAD(&bo_va->vm_status);
-
+        mutex_init(&bo_va->mutex);
         list_add_tail(&bo_va->bo_list, &bo->va);
 
         return bo_va;
@@ -1045,7 +1050,9 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
         mapping->offset = offset;
         mapping->flags = flags;
 
+        mutex_lock(&bo_va->mutex);
         list_add(&mapping->list, &bo_va->invalids);
+        mutex_unlock(&bo_va->mutex);
         spin_lock(&vm->it_lock);
         interval_tree_insert(&mapping->it, &vm->va);
         spin_unlock(&vm->it_lock);
@@ -1076,6 +1083,11 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
                 if (r)
                         goto error_free;
 
+                /* Keep a reference to the page table to avoid freeing
+                 * them up in the wrong order.
+                 */
+                pt->parent = amdgpu_bo_ref(vm->page_directory);
+
                 r = amdgpu_vm_clear_bo(adev, pt);
                 if (r) {
                         amdgpu_bo_unref(&pt);
@@ -1121,7 +1133,7 @@ int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
         bool valid = true;
 
         saddr /= AMDGPU_GPU_PAGE_SIZE;
-
+        mutex_lock(&bo_va->mutex);
         list_for_each_entry(mapping, &bo_va->valids, list) {
                 if (mapping->it.start == saddr)
                         break;
@@ -1135,20 +1147,25 @@ int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
                                 break;
                 }
 
-                if (&mapping->list == &bo_va->invalids)
+                if (&mapping->list == &bo_va->invalids) {
+                        mutex_unlock(&bo_va->mutex);
                         return -ENOENT;
+                }
         }
-
+        mutex_unlock(&bo_va->mutex);
         list_del(&mapping->list);
         spin_lock(&vm->it_lock);
         interval_tree_remove(&mapping->it, &vm->va);
         spin_unlock(&vm->it_lock);
         trace_amdgpu_vm_bo_unmap(bo_va, mapping);
 
-        if (valid)
+        if (valid) {
+                spin_lock(&vm->freed_lock);
                 list_add(&mapping->list, &vm->freed);
-        else
+                spin_unlock(&vm->freed_lock);
+        } else {
                 kfree(mapping);
+        }
 
         return 0;
 }
@@ -1181,7 +1198,9 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
                 interval_tree_remove(&mapping->it, &vm->va);
                 spin_unlock(&vm->it_lock);
                 trace_amdgpu_vm_bo_unmap(bo_va, mapping);
+                spin_lock(&vm->freed_lock);
                 list_add(&mapping->list, &vm->freed);
+                spin_unlock(&vm->freed_lock);
         }
         list_for_each_entry_safe(mapping, next, &bo_va->invalids, list) {
                 list_del(&mapping->list);
@@ -1190,8 +1209,8 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
                 spin_unlock(&vm->it_lock);
                 kfree(mapping);
         }
-
         fence_put(bo_va->last_pt_update);
+        mutex_destroy(&bo_va->mutex);
         kfree(bo_va);
 }
 
@@ -1236,13 +1255,13 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
                 vm->ids[i].id = 0;
                 vm->ids[i].flushed_updates = NULL;
         }
-        mutex_init(&vm->mutex);
         vm->va = RB_ROOT;
         spin_lock_init(&vm->status_lock);
         INIT_LIST_HEAD(&vm->invalidated);
         INIT_LIST_HEAD(&vm->cleared);
         INIT_LIST_HEAD(&vm->freed);
         spin_lock_init(&vm->it_lock);
+        spin_lock_init(&vm->freed_lock);
         pd_size = amdgpu_vm_directory_size(adev);
         pd_entries = amdgpu_vm_num_pdes(adev);
 
@@ -1320,7 +1339,6 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
                 fence_put(vm->ids[i].flushed_updates);
         }
 
-        mutex_destroy(&vm->mutex);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index cb0f7747e3dc..4dcc8fba5792 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -1250,7 +1250,7 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev,
         u32 pixel_period;
         u32 line_time = 0;
         u32 latency_watermark_a = 0, latency_watermark_b = 0;
-        u32 tmp, wm_mask;
+        u32 tmp, wm_mask, lb_vblank_lead_lines = 0;
 
         if (amdgpu_crtc->base.enabled && num_heads && mode) {
                 pixel_period = 1000000 / (u32)mode->clock;
@@ -1333,6 +1333,7 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev,
                     (adev->mode_info.disp_priority == 2)) {
                         DRM_DEBUG_KMS("force priority to high\n");
                 }
+                lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
         }
 
         /* select wm A */
@@ -1357,6 +1358,8 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev,
         amdgpu_crtc->line_time = line_time;
         amdgpu_crtc->wm_high = latency_watermark_a;
         amdgpu_crtc->wm_low = latency_watermark_b;
+        /* Save number of lines the linebuffer leads before the scanout */
+        amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 5af3721851d6..8f1e51128b33 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -1238,7 +1238,7 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev,
         u32 pixel_period;
         u32 line_time = 0;
         u32 latency_watermark_a = 0, latency_watermark_b = 0;
-        u32 tmp, wm_mask;
+        u32 tmp, wm_mask, lb_vblank_lead_lines = 0;
 
         if (amdgpu_crtc->base.enabled && num_heads && mode) {
                 pixel_period = 1000000 / (u32)mode->clock;
@@ -1321,6 +1321,7 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev,
                     (adev->mode_info.disp_priority == 2)) {
                         DRM_DEBUG_KMS("force priority to high\n");
                 }
+                lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
         }
 
         /* select wm A */
@@ -1345,6 +1346,8 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev,
         amdgpu_crtc->line_time = line_time;
         amdgpu_crtc->wm_high = latency_watermark_a;
         amdgpu_crtc->wm_low = latency_watermark_b;
+        /* Save number of lines the linebuffer leads before the scanout */
+        amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 4f7b49a6dc50..42d954dc436d 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -1193,7 +1193,7 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev,
         u32 pixel_period;
         u32 line_time = 0;
         u32 latency_watermark_a = 0, latency_watermark_b = 0;
-        u32 tmp, wm_mask;
+        u32 tmp, wm_mask, lb_vblank_lead_lines = 0;
 
         if (amdgpu_crtc->base.enabled && num_heads && mode) {
                 pixel_period = 1000000 / (u32)mode->clock;
@@ -1276,6 +1276,7 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev,
                     (adev->mode_info.disp_priority == 2)) {
                         DRM_DEBUG_KMS("force priority to high\n");
                 }
+                lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
         }
 
         /* select wm A */
@@ -1302,6 +1303,8 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev,
         amdgpu_crtc->line_time = line_time;
         amdgpu_crtc->wm_high = latency_watermark_a;
         amdgpu_crtc->wm_low = latency_watermark_b;
+        /* Save number of lines the linebuffer leads before the scanout */
+        amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 7427d8cd4c43..ed8abb58a785 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -513,7 +513,7 @@ static int gmc_v7_0_gart_enable(struct amdgpu_device *adev)
         WREG32(mmVM_L2_CNTL3, tmp);
         /* setup context0 */
         WREG32(mmVM_CONTEXT0_PAGE_TABLE_START_ADDR, adev->mc.gtt_start >> 12);
-        WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, (adev->mc.gtt_end >> 12) - 1);
+        WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, adev->mc.gtt_end >> 12);
         WREG32(mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR, adev->gart.table_addr >> 12);
         WREG32(mmVM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR,
                         (u32)(adev->dummy_page.addr >> 12));
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index cb0e50ebb528..d39028440814 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -657,7 +657,7 @@ static int gmc_v8_0_gart_enable(struct amdgpu_device *adev)
         WREG32(mmVM_L2_CNTL4, tmp);
         /* setup context0 */
         WREG32(mmVM_CONTEXT0_PAGE_TABLE_START_ADDR, adev->mc.gtt_start >> 12);
-        WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, (adev->mc.gtt_end >> 12) - 1);
+        WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, adev->mc.gtt_end >> 12);
         WREG32(mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR, adev->gart.table_addr >> 12);
         WREG32(mmVM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR,
                         (u32)(adev->dummy_page.addr >> 12));
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 6a52db6ad8d7..370c6c9d81c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -40,6 +40,9 @@
 
 #define GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT     0x04
 #define GRBM_GFX_INDEX__VCE_INSTANCE_MASK       0x10
+#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR0         0x8616
+#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR1         0x8617
+#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR2         0x8618
 
 #define VCE_V3_0_FW_SIZE        (384 * 1024)
 #define VCE_V3_0_STACK_SIZE     (64 * 1024)
@@ -130,9 +133,11 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
 
                 /* set BUSY flag */
                 WREG32_P(mmVCE_STATUS, 1, ~1);
-
-                WREG32_P(mmVCE_VCPU_CNTL, VCE_VCPU_CNTL__CLK_EN_MASK,
-                        ~VCE_VCPU_CNTL__CLK_EN_MASK);
+                if (adev->asic_type >= CHIP_STONEY)
+                        WREG32_P(mmVCE_VCPU_CNTL, 1, ~0x200001);
+                else
+                        WREG32_P(mmVCE_VCPU_CNTL, VCE_VCPU_CNTL__CLK_EN_MASK,
+                                ~VCE_VCPU_CNTL__CLK_EN_MASK);
 
                 WREG32_P(mmVCE_SOFT_RESET,
                          VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK,
@@ -391,8 +396,12 @@ static void vce_v3_0_mc_resume(struct amdgpu_device *adev, int idx)
         WREG32(mmVCE_LMI_SWAP_CNTL, 0);
         WREG32(mmVCE_LMI_SWAP_CNTL1, 0);
         WREG32(mmVCE_LMI_VM_CTRL, 0);
-
-        WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR, (adev->vce.gpu_addr >> 8));
+        if (adev->asic_type >= CHIP_STONEY) {
+                WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR0, (adev->vce.gpu_addr >> 8));
+                WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR1, (adev->vce.gpu_addr >> 8));
+                WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR2, (adev->vce.gpu_addr >> 8));
+        } else
+                WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR, (adev->vce.gpu_addr >> 8));
         offset = AMDGPU_VCE_FIRMWARE_OFFSET;
         size = VCE_V3_0_FW_SIZE;
         WREG32(mmVCE_VCPU_CACHE_OFFSET0, offset & 0x7fffffff);
@@ -576,6 +585,11 @@ static int vce_v3_0_process_interrupt(struct amdgpu_device *adev,
                                       struct amdgpu_iv_entry *entry)
 {
         DRM_DEBUG("IH: VCE\n");
+
+        WREG32_P(mmVCE_SYS_INT_STATUS,
+                VCE_SYS_INT_STATUS__VCE_SYS_INT_TRAP_INTERRUPT_INT_MASK,
+                ~VCE_SYS_INT_STATUS__VCE_SYS_INT_TRAP_INTERRUPT_INT_MASK);
+
         switch (entry->src_data) {
         case 0:
                 amdgpu_fence_process(&adev->vce.ring[0]);
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index ea30d6ad4c13..3a4820e863ec 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -30,8 +30,7 @@
 #define CREATE_TRACE_POINTS
 #include "gpu_sched_trace.h"
 
-static struct amd_sched_job *
-amd_sched_entity_pop_job(struct amd_sched_entity *entity);
+static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity);
 static void amd_sched_wakeup(struct amd_gpu_scheduler *sched);
 
 struct kmem_cache *sched_fence_slab;
@@ -64,36 +63,36 @@ static void amd_sched_rq_remove_entity(struct amd_sched_rq *rq,
 }
 
 /**
- * Select next job from a specified run queue with round robin policy.
- * Return NULL if nothing available.
+ * Select an entity which could provide a job to run
+ *
+ * @rq          The run queue to check.
+ *
+ * Try to find a ready entity, returns NULL if none found.
  */
-static struct amd_sched_job *
-amd_sched_rq_select_job(struct amd_sched_rq *rq)
+static struct amd_sched_entity *
+amd_sched_rq_select_entity(struct amd_sched_rq *rq)
 {
         struct amd_sched_entity *entity;
-        struct amd_sched_job *sched_job;
 
         spin_lock(&rq->lock);
 
         entity = rq->current_entity;
         if (entity) {
                 list_for_each_entry_continue(entity, &rq->entities, list) {
-                        sched_job = amd_sched_entity_pop_job(entity);
-                        if (sched_job) {
+                        if (amd_sched_entity_is_ready(entity)) {
                                 rq->current_entity = entity;
                                 spin_unlock(&rq->lock);
-                                return sched_job;
+                                return entity;
                         }
                 }
         }
 
         list_for_each_entry(entity, &rq->entities, list) {
 
-                sched_job = amd_sched_entity_pop_job(entity);
-                if (sched_job) {
+                if (amd_sched_entity_is_ready(entity)) {
                         rq->current_entity = entity;
                         spin_unlock(&rq->lock);
-                        return sched_job;
+                        return entity;
                 }
 
                 if (entity == rq->current_entity)
@@ -177,6 +176,24 @@ static bool amd_sched_entity_is_idle(struct amd_sched_entity *entity)
 }
 
 /**
+ * Check if entity is ready
+ *
+ * @entity      The pointer to a valid scheduler entity
+ *
+ * Return true if entity could provide a job.
+ */
+static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity)
+{
+        if (kfifo_is_empty(&entity->job_queue))
+                return false;
+
+        if (ACCESS_ONCE(entity->dependency))
+                return false;
+
+        return true;
+}
+
+/**
  * Destroy a context entity
  *
  * @sched       Pointer to scheduler instance
@@ -211,32 +228,53 @@ static void amd_sched_entity_wakeup(struct fence *f, struct fence_cb *cb)
         amd_sched_wakeup(entity->sched);
 }
 
+static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity)
+{
+        struct amd_gpu_scheduler *sched = entity->sched;
+        struct fence * fence = entity->dependency;
+        struct amd_sched_fence *s_fence;
+
+        if (fence->context == entity->fence_context) {
+                /* We can ignore fences from ourself */
+                fence_put(entity->dependency);
+                return false;
+        }
+
+        s_fence = to_amd_sched_fence(fence);
+        if (s_fence && s_fence->sched == sched) {
+                /* Fence is from the same scheduler */
+                if (test_bit(AMD_SCHED_FENCE_SCHEDULED_BIT, &fence->flags)) {
+                        /* Ignore it when it is already scheduled */
+                        fence_put(entity->dependency);
+                        return false;
+                }
+
+                /* Wait for fence to be scheduled */
+                entity->cb.func = amd_sched_entity_wakeup;
+                list_add_tail(&entity->cb.node, &s_fence->scheduled_cb);
+                return true;
+        }
+
+        if (!fence_add_callback(entity->dependency, &entity->cb,
+                                amd_sched_entity_wakeup))
+                return true;
+
+        fence_put(entity->dependency);
+        return false;
+}
+
 static struct amd_sched_job *
 amd_sched_entity_pop_job(struct amd_sched_entity *entity)
 {
         struct amd_gpu_scheduler *sched = entity->sched;
         struct amd_sched_job *sched_job;
 
-        if (ACCESS_ONCE(entity->dependency))
-                return NULL;
-
         if (!kfifo_out_peek(&entity->job_queue, &sched_job, sizeof(sched_job)))
                 return NULL;
 
-        while ((entity->dependency = sched->ops->dependency(sched_job))) {
-
-                if (entity->dependency->context == entity->fence_context) {
-                        /* We can ignore fences from ourself */
-                        fence_put(entity->dependency);
-                        continue;
-                }
-
-                if (fence_add_callback(entity->dependency, &entity->cb,
-                                       amd_sched_entity_wakeup))
-                        fence_put(entity->dependency);
-                else
+        while ((entity->dependency = sched->ops->dependency(sched_job)))
+                if (amd_sched_entity_add_dependency_cb(entity))
                         return NULL;
-        }
 
         return sched_job;
 }
@@ -250,6 +288,7 @@ amd_sched_entity_pop_job(struct amd_sched_entity *entity)
  */
 static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
 {
+        struct amd_gpu_scheduler *sched = sched_job->sched;
         struct amd_sched_entity *entity = sched_job->s_entity;
         bool added, first = false;
 
@@ -264,7 +303,7 @@ static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
 
         /* first job wakes up scheduler */
         if (first)
-                amd_sched_wakeup(sched_job->sched);
+                amd_sched_wakeup(sched);
 
         return added;
 }
@@ -280,9 +319,9 @@ void amd_sched_entity_push_job(struct amd_sched_job *sched_job)
 {
         struct amd_sched_entity *entity = sched_job->s_entity;
 
+        trace_amd_sched_job(sched_job);
         wait_event(entity->sched->job_scheduled,
                    amd_sched_entity_in(sched_job));
-        trace_amd_sched_job(sched_job);
 }
 
 /**
@@ -304,22 +343,22 @@ static void amd_sched_wakeup(struct amd_gpu_scheduler *sched)
 }
 
 /**
- * Select next to run
+ * Select next entity to process
 */
-static struct amd_sched_job *
-amd_sched_select_job(struct amd_gpu_scheduler *sched)
+static struct amd_sched_entity *
+amd_sched_select_entity(struct amd_gpu_scheduler *sched)
 {
-        struct amd_sched_job *sched_job;
+        struct amd_sched_entity *entity;
 
         if (!amd_sched_ready(sched))
                 return NULL;
 
         /* Kernel run queue has higher priority than normal run queue*/
-        sched_job = amd_sched_rq_select_job(&sched->kernel_rq);
-        if (sched_job == NULL)
-                sched_job = amd_sched_rq_select_job(&sched->sched_rq);
+        entity = amd_sched_rq_select_entity(&sched->kernel_rq);
+        if (entity == NULL)
+                entity = amd_sched_rq_select_entity(&sched->sched_rq);
 
-        return sched_job;
+        return entity;
 }
 
 static void amd_sched_process_job(struct fence *f, struct fence_cb *cb)
@@ -381,13 +420,16 @@ static int amd_sched_main(void *param)
                 unsigned long flags;
 
                 wait_event_interruptible(sched->wake_up_worker,
-                        kthread_should_stop() ||
-                        (sched_job = amd_sched_select_job(sched)));
+                        (entity = amd_sched_select_entity(sched)) ||
+                        kthread_should_stop());
 
+                if (!entity)
+                        continue;
+
+                sched_job = amd_sched_entity_pop_job(entity);
                 if (!sched_job)
                         continue;
 
-                entity = sched_job->s_entity;
                 s_fence = sched_job->s_fence;
 
                 if (sched->timeout != MAX_SCHEDULE_TIMEOUT) {
@@ -400,6 +442,7 @@ static int amd_sched_main(void *param)
 
                 atomic_inc(&sched->hw_rq_count);
                 fence = sched->ops->run_job(sched_job);
+                amd_sched_fence_scheduled(s_fence);
                 if (fence) {
                         r = fence_add_callback(fence, &s_fence->cb,
                                                amd_sched_process_job);
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
index 939692b14f4b..a0f0ae53aacd 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
@@ -27,6 +27,8 @@
 #include <linux/kfifo.h>
 #include <linux/fence.h>
 
+#define AMD_SCHED_FENCE_SCHEDULED_BIT   FENCE_FLAG_USER_BITS
+
 struct amd_gpu_scheduler;
 struct amd_sched_rq;
 
@@ -68,6 +70,7 @@ struct amd_sched_rq {
 struct amd_sched_fence {
         struct fence                    base;
         struct fence_cb                 cb;
+        struct list_head                scheduled_cb;
         struct amd_gpu_scheduler        *sched;
         spinlock_t                      lock;
         void                            *owner;
@@ -134,7 +137,7 @@ void amd_sched_entity_push_job(struct amd_sched_job *sched_job);
 
 struct amd_sched_fence *amd_sched_fence_create(
         struct amd_sched_entity *s_entity, void *owner);
+void amd_sched_fence_scheduled(struct amd_sched_fence *fence);
 void amd_sched_fence_signal(struct amd_sched_fence *fence);
 
-
 #endif
diff --git a/drivers/gpu/drm/amd/scheduler/sched_fence.c b/drivers/gpu/drm/amd/scheduler/sched_fence.c
index 8d2130b9ff05..87c78eecea64 100644
--- a/drivers/gpu/drm/amd/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/amd/scheduler/sched_fence.c
@@ -35,6 +35,8 @@ struct amd_sched_fence *amd_sched_fence_create(struct amd_sched_entity *s_entity
         fence = kmem_cache_zalloc(sched_fence_slab, GFP_KERNEL);
         if (fence == NULL)
                 return NULL;
+
+        INIT_LIST_HEAD(&fence->scheduled_cb);
         fence->owner = owner;
         fence->sched = s_entity->sched;
         spin_lock_init(&fence->lock);
@@ -55,6 +57,17 @@ void amd_sched_fence_signal(struct amd_sched_fence *fence)
                 FENCE_TRACE(&fence->base, "was already signaled\n");
 }
 
+void amd_sched_fence_scheduled(struct amd_sched_fence *s_fence)
+{
+        struct fence_cb *cur, *tmp;
+
+        set_bit(AMD_SCHED_FENCE_SCHEDULED_BIT, &s_fence->base.flags);
+        list_for_each_entry_safe(cur, tmp, &s_fence->scheduled_cb, node) {
+                list_del_init(&cur->node);
+                cur->func(&s_fence->base, cur);
+        }
+}
+
 static const char *amd_sched_fence_get_driver_name(struct fence *fence)
 {
         return "amd_sched";
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 9362609df38a..7dd6728dd092 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -160,6 +160,11 @@ int drm_setmaster_ioctl(struct drm_device *dev, void *data,
                 goto out_unlock;
         }
 
+        if (!file_priv->allowed_master) {
+                ret = drm_new_set_master(dev, file_priv);
+                goto out_unlock;
+        }
+
         file_priv->minor->master = drm_master_get(file_priv->master);
         file_priv->is_master = 1;
         if (dev->driver->master_set) {
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index c59ce4d0ef75..6b5625e66119 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -126,6 +126,60 @@ static int drm_cpu_valid(void)
 }
 
 /**
+ * drm_new_set_master - Allocate a new master object and become master for the
+ * associated master realm.
+ *
+ * @dev: The associated device.
+ * @fpriv: File private identifying the client.
+ *
+ * This function must be called with dev::struct_mutex held.
+ * Returns negative error code on failure. Zero on success.
+ */
+int drm_new_set_master(struct drm_device *dev, struct drm_file *fpriv)
+{
+        struct drm_master *old_master;
+        int ret;
+
+        lockdep_assert_held_once(&dev->master_mutex);
+
+        /* create a new master */
+        fpriv->minor->master = drm_master_create(fpriv->minor);
+        if (!fpriv->minor->master)
+                return -ENOMEM;
+
+        /* take another reference for the copy in the local file priv */
+        old_master = fpriv->master;
+        fpriv->master = drm_master_get(fpriv->minor->master);
+
+        if (dev->driver->master_create) {
+                ret = dev->driver->master_create(dev, fpriv->master);
+                if (ret)
+                        goto out_err;
+        }
+        if (dev->driver->master_set) {
+                ret = dev->driver->master_set(dev, fpriv, true);
+                if (ret)
+                        goto out_err;
+        }
+
+        fpriv->is_master = 1;
+        fpriv->allowed_master = 1;
+        fpriv->authenticated = 1;
+        if (old_master)
+                drm_master_put(&old_master);
+
+        return 0;
+
+out_err:
+        /* drop both references and restore old master on failure */
+        drm_master_put(&fpriv->minor->master);
+        drm_master_put(&fpriv->master);
+        fpriv->master = old_master;
+
+        return ret;
+}
+
+/**
  * Called whenever a process opens /dev/drm.
  *
  * \param filp file pointer.
@@ -189,35 +243,9 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor)
         mutex_lock(&dev->master_mutex);
         if (drm_is_primary_client(priv) && !priv->minor->master) {
                 /* create a new master */
-                priv->minor->master = drm_master_create(priv->minor);
-                if (!priv->minor->master) {
-                        ret = -ENOMEM;
+                ret = drm_new_set_master(dev, priv);
+                if (ret)
                         goto out_close;
-                }
-
-                priv->is_master = 1;
-                /* take another reference for the copy in the local file priv */
-                priv->master = drm_master_get(priv->minor->master);
-                priv->authenticated = 1;
-
-                if (dev->driver->master_create) {
-                        ret = dev->driver->master_create(dev, priv->master);
-                        if (ret) {
-                                /* drop both references if this fails */
-                                drm_master_put(&priv->minor->master);
-                                drm_master_put(&priv->master);
-                                goto out_close;
-                        }
-                }
-                if (dev->driver->master_set) {
-                        ret = dev->driver->master_set(dev, priv, true);
-                        if (ret) {
-                                /* drop both references if this fails */
-                                drm_master_put(&priv->minor->master);
-                                drm_master_put(&priv->master);
-                                goto out_close;
-                        }
-                }
         } else if (drm_is_primary_client(priv)) {
                 /* get a reference to the master */
                 priv->master = drm_master_get(priv->minor->master);
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 2151ea551d3b..607f493ae801 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -980,7 +980,8 @@ static void send_vblank_event(struct drm_device *dev,
                 struct drm_pending_vblank_event *e,
                 unsigned long seq, struct timeval *now)
 {
-        WARN_ON_SMP(!spin_is_locked(&dev->event_lock));
+        assert_spin_locked(&dev->event_lock);
+
         e->event.sequence = seq;
         e->event.tv_sec = now->tv_sec;
         e->event.tv_usec = now->tv_usec;
@@ -993,6 +994,57 @@ static void send_vblank_event(struct drm_device *dev,
 }
 
 /**
+ * drm_arm_vblank_event - arm vblank event after pageflip
+ * @dev: DRM device
+ * @pipe: CRTC index
+ * @e: the event to prepare to send
+ *
+ * A lot of drivers need to generate vblank events for the very next vblank
+ * interrupt. For example when the page flip interrupt happens when the page
+ * flip gets armed, but not when it actually executes within the next vblank
+ * period. This helper function implements exactly the required vblank arming
+ * behaviour.
+ *
+ * Caller must hold event lock. Caller must also hold a vblank reference for
+ * the event @e, which will be dropped when the next vblank arrives.
+ *
+ * This is the legacy version of drm_crtc_arm_vblank_event().
+ */
+void drm_arm_vblank_event(struct drm_device *dev, unsigned int pipe,
+                          struct drm_pending_vblank_event *e)
+{
+        assert_spin_locked(&dev->event_lock);
+
+        e->pipe = pipe;
+        e->event.sequence = drm_vblank_count(dev, pipe);
+        list_add_tail(&e->base.link, &dev->vblank_event_list);
+}
+EXPORT_SYMBOL(drm_arm_vblank_event);
+
+/**
+ * drm_crtc_arm_vblank_event - arm vblank event after pageflip
+ * @crtc: the source CRTC of the vblank event
+ * @e: the event to send
+ *
+ * A lot of drivers need to generate vblank events for the very next vblank
+ * interrupt. For example when the page flip interrupt happens when the page
+ * flip gets armed, but not when it actually executes within the next vblank
+ * period. This helper function implements exactly the required vblank arming
+ * behaviour.
+ *
+ * Caller must hold event lock. Caller must also hold a vblank reference for
+ * the event @e, which will be dropped when the next vblank arrives.
+ *
+ * This is the native KMS version of drm_arm_vblank_event().
+ */
+void drm_crtc_arm_vblank_event(struct drm_crtc *crtc,
+                               struct drm_pending_vblank_event *e)
+{
+        drm_arm_vblank_event(crtc->dev, drm_crtc_index(crtc), e);
+}
+EXPORT_SYMBOL(drm_crtc_arm_vblank_event);
+
+/**
  * drm_send_vblank_event - helper to send vblank event after pageflip
  * @dev: DRM device
  * @pipe: CRTC index
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index a3b22bdacd44..8aab974b0564 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2734,6 +2734,8 @@ static const char *power_domain_str(enum intel_display_power_domain domain)
                 return "AUX_C";
         case POWER_DOMAIN_AUX_D:
                 return "AUX_D";
+        case POWER_DOMAIN_GMBUS:
+                return "GMBUS";
         case POWER_DOMAIN_INIT:
                 return "INIT";
         default:
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 95bb27de774f..a01e51581c4c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -199,6 +199,7 @@ enum intel_display_power_domain {
         POWER_DOMAIN_AUX_B,
         POWER_DOMAIN_AUX_C,
         POWER_DOMAIN_AUX_D,
+        POWER_DOMAIN_GMBUS,
         POWER_DOMAIN_INIT,
 
         POWER_DOMAIN_NUM,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 91bb1fc27420..32e6aade6223 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1210,8 +1210,16 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
         if (i915_gem_request_completed(req, true))
                 return 0;
 
-        timeout_expire = timeout ?
-                jiffies + nsecs_to_jiffies_timeout((u64)*timeout) : 0;
+        timeout_expire = 0;
+        if (timeout) {
+                if (WARN_ON(*timeout < 0))
+                        return -EINVAL;
+
+                if (*timeout == 0)
+                        return -ETIME;
+
+                timeout_expire = jiffies + nsecs_to_jiffies_timeout(*timeout);
+        }
 
         if (INTEL_INFO(dev_priv)->gen >= 6)
                 gen6_rps_boost(dev_priv, rps, req->emitted_jiffies);
diff --git a/drivers/gpu/drm/i915/i915_gem_fence.c b/drivers/gpu/drm/i915/i915_gem_fence.c
index 40a10b25956c..f010391b87f5 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence.c
@@ -642,11 +642,10 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev)
                 }
 
                 /* check for L-shaped memory aka modified enhanced addressing */
-                if (IS_GEN4(dev)) {
-                        uint32_t ddc2 = I915_READ(DCC2);
-
-                        if (!(ddc2 & DCC2_MODIFIED_ENHANCED_DISABLE))
-                                dev_priv->quirks |= QUIRK_PIN_SWIZZLED_PAGES;
+                if (IS_GEN4(dev) &&
+                    !(I915_READ(DCC2) & DCC2_MODIFIED_ENHANCED_DISABLE)) {
+                        swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN;
+                        swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN;
                 }
 
                 if (dcc == 0xffffffff) {
@@ -675,16 +674,35 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev)
                  * matching, which was the case for the swizzling required in
                  * the table above, or from the 1-ch value being less than
                  * the minimum size of a rank.
+                 *
+                 * Reports indicate that the swizzling actually
+                 * varies depending upon page placement inside the
+                 * channels, i.e. we see swizzled pages where the
+                 * banks of memory are paired and unswizzled on the
+                 * uneven portion, so leave that as unknown.
                  */
-                if (I915_READ16(C0DRB3) != I915_READ16(C1DRB3)) {
-                        swizzle_x = I915_BIT_6_SWIZZLE_NONE;
-                        swizzle_y = I915_BIT_6_SWIZZLE_NONE;
-                } else {
+                if (I915_READ16(C0DRB3) == I915_READ16(C1DRB3)) {
                         swizzle_x = I915_BIT_6_SWIZZLE_9_10;
                         swizzle_y = I915_BIT_6_SWIZZLE_9;
                 }
         }
 
+        if (swizzle_x == I915_BIT_6_SWIZZLE_UNKNOWN ||
+            swizzle_y == I915_BIT_6_SWIZZLE_UNKNOWN) {
+                /* Userspace likes to explode if it sees unknown swizzling,
+                 * so lie. We will finish the lie when reporting through
+                 * the get-tiling-ioctl by reporting the physical swizzle
+                 * mode as unknown instead.
+                 *
+                 * As we don't strictly know what the swizzling is, it may be
+                 * bit17 dependent, and so we need to also prevent the pages
+                 * from being moved.
+                 */
+                dev_priv->quirks |= QUIRK_PIN_SWIZZLED_PAGES;
+                swizzle_x = I915_BIT_6_SWIZZLE_NONE;
+                swizzle_y = I915_BIT_6_SWIZZLE_NONE;
+        }
+
         dev_priv->mm.bit_6_swizzle_x = swizzle_x;
         dev_priv->mm.bit_6_swizzle_y = swizzle_y;
 }
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 71860f8680f9..22e86d2e408d 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5194,11 +5194,31 @@ static enum intel_display_power_domain port_to_power_domain(enum port port)
         case PORT_E:
                 return POWER_DOMAIN_PORT_DDI_E_2_LANES;
         default:
-                WARN_ON_ONCE(1);
+                MISSING_CASE(port);
                 return POWER_DOMAIN_PORT_OTHER;
         }
 }
 
+static enum intel_display_power_domain port_to_aux_power_domain(enum port port)
+{
+        switch (port) {
+        case PORT_A:
+                return POWER_DOMAIN_AUX_A;
+        case PORT_B:
+                return POWER_DOMAIN_AUX_B;
+        case PORT_C:
+                return POWER_DOMAIN_AUX_C;
+        case PORT_D:
+                return POWER_DOMAIN_AUX_D;
+        case PORT_E:
+                /* FIXME: Check VBT for actual wiring of PORT E */
+                return POWER_DOMAIN_AUX_D;
+        default:
+                MISSING_CASE(port);
+                return POWER_DOMAIN_AUX_A;
+        }
+}
+
 #define for_each_power_domain(domain, mask)                             \
         for ((domain) = 0; (domain) < POWER_DOMAIN_NUM; (domain)++)     \
                 if ((1 << (domain)) & (mask))
@@ -5230,6 +5250,36 @@ intel_display_port_power_domain(struct intel_encoder *intel_encoder)
         }
 }
 
+enum intel_display_power_domain
+intel_display_port_aux_power_domain(struct intel_encoder *intel_encoder)
+{
+        struct drm_device *dev = intel_encoder->base.dev;
+        struct intel_digital_port *intel_dig_port;
+
+        switch (intel_encoder->type) {
+        case INTEL_OUTPUT_UNKNOWN:
+        case INTEL_OUTPUT_HDMI:
+                /*
+                 * Only DDI platforms should ever use these output types.
+                 * We can get here after the HDMI detect code has already set
+                 * the type of the shared encoder. Since we can't be sure
+                 * what's the status of the given connectors, play safe and
+                 * run the DP detection too.
+                 */
+                WARN_ON_ONCE(!HAS_DDI(dev));
+        case INTEL_OUTPUT_DISPLAYPORT:
+        case INTEL_OUTPUT_EDP:
+                intel_dig_port = enc_to_dig_port(&intel_encoder->base);
+                return port_to_aux_power_domain(intel_dig_port->port);
+        case INTEL_OUTPUT_DP_MST:
+                intel_dig_port = enc_to_mst(&intel_encoder->base)->primary;
+                return port_to_aux_power_domain(intel_dig_port->port);
+        default:
+                MISSING_CASE(intel_encoder->type);
+                return POWER_DOMAIN_AUX_A;
+        }
+}
+
 static unsigned long get_crtc_power_domains(struct drm_crtc *crtc)
 {
         struct drm_device *dev = crtc->dev;
@@ -12460,7 +12510,6 @@ intel_pipe_config_compare(struct drm_device *dev,
         if (INTEL_INFO(dev)->gen < 8) {
                 PIPE_CONF_CHECK_M_N(dp_m_n);
 
-                PIPE_CONF_CHECK_I(has_drrs);
                 if (current_config->has_drrs)
                         PIPE_CONF_CHECK_M_N(dp_m2_n2);
         } else
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 09bdd94ca3ba..78b8ec84d576 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -277,7 +277,7 @@ static void pps_lock(struct intel_dp *intel_dp)
          * See vlv_power_sequencer_reset() why we need
          * a power domain reference here.
          */
-        power_domain = intel_display_port_power_domain(encoder);
+        power_domain = intel_display_port_aux_power_domain(encoder);
         intel_display_power_get(dev_priv, power_domain);
 
         mutex_lock(&dev_priv->pps_mutex);
@@ -293,7 +293,7 @@ static void pps_unlock(struct intel_dp *intel_dp)
 
         mutex_unlock(&dev_priv->pps_mutex);
 
-        power_domain = intel_display_port_power_domain(encoder);
+        power_domain = intel_display_port_aux_power_domain(encoder);
         intel_display_power_put(dev_priv, power_domain);
 }
 
@@ -816,8 +816,6 @@ intel_dp_aux_ch(struct intel_dp *intel_dp,
 
         intel_dp_check_edp(intel_dp);
 
-        intel_aux_display_runtime_get(dev_priv);
-
         /* Try to wait for any previous AUX channel activity */
         for (try = 0; try < 3; try++) {
                 status = I915_READ_NOTRACE(ch_ctl);
@@ -926,7 +924,6 @@ done:
         ret = recv_bytes;
 out:
         pm_qos_update_request(&dev_priv->pm_qos, PM_QOS_DEFAULT_VALUE);
-        intel_aux_display_runtime_put(dev_priv);
 
         if (vdd)
                 edp_panel_vdd_off(intel_dp, false);
@@ -1784,7 +1781,7 @@ static bool edp_panel_vdd_on(struct intel_dp *intel_dp)
         if (edp_have_panel_vdd(intel_dp))
                 return need_to_disable;
 
-        power_domain = intel_display_port_power_domain(intel_encoder);
+        power_domain = intel_display_port_aux_power_domain(intel_encoder);
         intel_display_power_get(dev_priv, power_domain);
 
         DRM_DEBUG_KMS("Turning eDP port %c VDD on\n",
@@ -1874,7 +1871,7 @@ static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp)
         if ((pp & POWER_TARGET_ON) == 0)
                 intel_dp->last_power_cycle = jiffies;
 
-        power_domain = intel_display_port_power_domain(intel_encoder);
+        power_domain = intel_display_port_aux_power_domain(intel_encoder);
         intel_display_power_put(dev_priv, power_domain);
 }
 
@@ -2025,7 +2022,7 @@ static void edp_panel_off(struct intel_dp *intel_dp)
         wait_panel_off(intel_dp);
 
         /* We got a reference when we enabled the VDD. */
-        power_domain = intel_display_port_power_domain(intel_encoder);
+        power_domain = intel_display_port_aux_power_domain(intel_encoder);
         intel_display_power_put(dev_priv, power_domain);
 }
 
@@ -4765,26 +4762,6 @@ intel_dp_unset_edid(struct intel_dp *intel_dp)
         intel_dp->has_audio = false;
 }
 
-static enum intel_display_power_domain
-intel_dp_power_get(struct intel_dp *dp)
-{
-        struct intel_encoder *encoder = &dp_to_dig_port(dp)->base;
-        enum intel_display_power_domain power_domain;
-
-        power_domain = intel_display_port_power_domain(encoder);
-        intel_display_power_get(to_i915(encoder->base.dev), power_domain);
-
-        return power_domain;
-}
-
-static void
-intel_dp_power_put(struct intel_dp *dp,
-                   enum intel_display_power_domain power_domain)
-{
-        struct intel_encoder *encoder = &dp_to_dig_port(dp)->base;
-        intel_display_power_put(to_i915(encoder->base.dev), power_domain);
-}
-
 static enum drm_connector_status
 intel_dp_detect(struct drm_connector *connector, bool force)
 {
@@ -4808,7 +4785,8 @@ intel_dp_detect(struct drm_connector *connector, bool force)
                 return connector_status_disconnected;
         }
 
-        power_domain = intel_dp_power_get(intel_dp);
+        power_domain = intel_display_port_aux_power_domain(intel_encoder);
+        intel_display_power_get(to_i915(dev), power_domain);
 
         /* Can't disconnect eDP, but you can close the lid... */
         if (is_edp(intel_dp))
@@ -4853,7 +4831,7 @@ intel_dp_detect(struct drm_connector *connector, bool force)
         }
 
 out:
-        intel_dp_power_put(intel_dp, power_domain);
+        intel_display_power_put(to_i915(dev), power_domain);
         return status;
 }
 
@@ -4862,6 +4840,7 @@ intel_dp_force(struct drm_connector *connector)
 {
         struct intel_dp *intel_dp = intel_attached_dp(connector);
         struct intel_encoder *intel_encoder = &dp_to_dig_port(intel_dp)->base;
+        struct drm_i915_private *dev_priv = to_i915(intel_encoder->base.dev);
         enum intel_display_power_domain power_domain;
 
         DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
@@ -4871,11 +4850,12 @@ intel_dp_force(struct drm_connector *connector)
         if (connector->status != connector_status_connected)
                 return;
 
-        power_domain = intel_dp_power_get(intel_dp);
+        power_domain = intel_display_port_aux_power_domain(intel_encoder);
+        intel_display_power_get(dev_priv, power_domain);
 
         intel_dp_set_edid(intel_dp);
 
-        intel_dp_power_put(intel_dp, power_domain);
+        intel_display_power_put(dev_priv, power_domain);
 
         if (intel_encoder->type != INTEL_OUTPUT_EDP)
                 intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT;
@@ -5091,7 +5071,7 @@ static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp)
          * indefinitely.
          */
         DRM_DEBUG_KMS("VDD left on by BIOS, adjusting state tracking\n");
-        power_domain = intel_display_port_power_domain(&intel_dig_port->base);
+        power_domain = intel_display_port_aux_power_domain(&intel_dig_port->base);
         intel_display_power_get(dev_priv, power_domain);
 
         edp_panel_vdd_schedule_off(intel_dp);
@@ -5153,7 +5133,8 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
         enum intel_display_power_domain power_domain;
         enum irqreturn ret = IRQ_NONE;
 
-        if (intel_dig_port->base.type != INTEL_OUTPUT_EDP)
+        if (intel_dig_port->base.type != INTEL_OUTPUT_EDP &&
+            intel_dig_port->base.type != INTEL_OUTPUT_HDMI)
                 intel_dig_port->base.type = INTEL_OUTPUT_DISPLAYPORT;
 
         if (long_hpd && intel_dig_port->base.type == INTEL_OUTPUT_EDP) {
@@ -5172,7 +5153,7 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
                       port_name(intel_dig_port->port),
                       long_hpd ? "long" : "short");
 
-        power_domain = intel_display_port_power_domain(intel_encoder);
+        power_domain = intel_display_port_aux_power_domain(intel_encoder);
         intel_display_power_get(dev_priv, power_domain);
 
         if (long_hpd) {
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 0598932ce623..f2a1142bff34 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1169,6 +1169,8 @@ void hsw_enable_ips(struct intel_crtc *crtc);
 void hsw_disable_ips(struct intel_crtc *crtc);
 enum intel_display_power_domain
 intel_display_port_power_domain(struct intel_encoder *intel_encoder);
+enum intel_display_power_domain
+intel_display_port_aux_power_domain(struct intel_encoder *intel_encoder);
 void intel_mode_from_pipe_config(struct drm_display_mode *mode,
                                  struct intel_crtc_state *pipe_config);
 void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc);
@@ -1377,8 +1379,6 @@ void intel_display_power_get(struct drm_i915_private *dev_priv,
                              enum intel_display_power_domain domain);
 void intel_display_power_put(struct drm_i915_private *dev_priv,
                              enum intel_display_power_domain domain);
-void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv);
-void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_get(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_put(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 9eafa191cee2..81cdd9ff3892 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1335,21 +1335,17 @@ intel_hdmi_set_edid(struct drm_connector *connector, bool force)
 {
         struct drm_i915_private *dev_priv = to_i915(connector->dev);
         struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
-        struct intel_encoder *intel_encoder =
-                &hdmi_to_dig_port(intel_hdmi)->base;
-        enum intel_display_power_domain power_domain;
         struct edid *edid = NULL;
         bool connected = false;
 
-        power_domain = intel_display_port_power_domain(intel_encoder);
-        intel_display_power_get(dev_priv, power_domain);
+        intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
 
         if (force)
                 edid = drm_get_edid(connector,
                                     intel_gmbus_get_adapter(dev_priv,
                                     intel_hdmi->ddc_bus));
 
-        intel_display_power_put(dev_priv, power_domain);
+        intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS);
 
         to_intel_connector(connector)->detect_edid = edid;
         if (edid && edid->input & DRM_EDID_INPUT_DIGITAL) {
@@ -1383,6 +1379,8 @@ intel_hdmi_detect(struct drm_connector *connector, bool force)
         DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
                       connector->base.id, connector->name);
 
+        intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
+
         while (!live_status && --retry) {
                 live_status = intel_digital_port_connected(dev_priv,
                                 hdmi_to_dig_port(intel_hdmi));
@@ -1402,6 +1400,8 @@ intel_hdmi_detect(struct drm_connector *connector, bool force)
         } else
                 status = connector_status_disconnected;
 
+        intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS);
+
         return status;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 1369fc41d039..8324654037b6 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -483,7 +483,7 @@ gmbus_xfer(struct i2c_adapter *adapter,
         int i = 0, inc, try = 0;
         int ret = 0;
 
-        intel_aux_display_runtime_get(dev_priv);
+        intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS);
         mutex_lock(&dev_priv->gmbus_mutex);
 
         if (bus->force_bit) {
@@ -595,7 +595,9 @@ timeout:
 
 out:
         mutex_unlock(&dev_priv->gmbus_mutex);
-        intel_aux_display_runtime_put(dev_priv);
+
+        intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS);
+
         return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index d89c1d0aa1b7..7e23d65c9b24 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -362,6 +362,7 @@ static void hsw_set_power_well(struct drm_i915_private *dev_priv,
         BIT(POWER_DOMAIN_AUX_C) |                       \
         BIT(POWER_DOMAIN_AUDIO) |                       \
         BIT(POWER_DOMAIN_VGA) |                         \
+        BIT(POWER_DOMAIN_GMBUS) |                       \
         BIT(POWER_DOMAIN_INIT))
 #define BXT_DISPLAY_POWERWELL_1_POWER_DOMAINS (         \
         BXT_DISPLAY_POWERWELL_2_POWER_DOMAINS |         \
@@ -1483,6 +1484,7 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
         BIT(POWER_DOMAIN_AUX_B) |                       \
         BIT(POWER_DOMAIN_AUX_C) |                       \
         BIT(POWER_DOMAIN_AUX_D) |                       \
+        BIT(POWER_DOMAIN_GMBUS) |                       \
         BIT(POWER_DOMAIN_INIT))
 #define HSW_DISPLAY_POWER_DOMAINS (                             \
         (POWER_DOMAIN_MASK & ~HSW_ALWAYS_ON_POWER_DOMAINS) |    \
@@ -1845,6 +1847,8 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv)
         i915.disable_power_well = sanitize_disable_power_well_option(dev_priv,
                                                      i915.disable_power_well);
 
+        BUILD_BUG_ON(POWER_DOMAIN_NUM > 31);
+
         mutex_init(&power_domains->lock);
 
         /*
@@ -2064,36 +2068,6 @@ void intel_power_domains_init_hw(struct drm_i915_private *dev_priv)
 }
 
 /**
- * intel_aux_display_runtime_get - grab an auxiliary power domain reference
- * @dev_priv: i915 device instance
- *
- * This function grabs a power domain reference for the auxiliary power domain
- * (for access to the GMBUS and DP AUX blocks) and ensures that it and all its
- * parents are powered up. Therefore users should only grab a reference to the
- * innermost power domain they need.
- *
- * Any power domain reference obtained by this function must have a symmetric
- * call to intel_aux_display_runtime_put() to release the reference again.
- */
-void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv)
-{
-        intel_runtime_pm_get(dev_priv);
-}
-
-/**
- * intel_aux_display_runtime_put - release an auxiliary power domain reference
- * @dev_priv: i915 device instance
- *
- * This function drops the auxiliary power domain reference obtained by
- * intel_aux_display_runtime_get() and might power down the corresponding
- * hardware block right away if this is the last reference.
- */
-void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv)
-{
-        intel_runtime_pm_put(dev_priv);
-}
-
-/**
  * intel_runtime_pm_get - grab a runtime pm reference
  * @dev_priv: i915 device instance
  *
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 64f16ea779ef..7b990b4e96d2 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -63,8 +63,7 @@ static void imx_drm_driver_lastclose(struct drm_device *drm)
 #if IS_ENABLED(CONFIG_DRM_IMX_FB_HELPER)
         struct imx_drm_device *imxdrm = drm->dev_private;
 
-        if (imxdrm->fbhelper)
-                drm_fbdev_cma_restore_mode(imxdrm->fbhelper);
+        drm_fbdev_cma_restore_mode(imxdrm->fbhelper);
 #endif
 }
 
@@ -340,7 +339,7 @@ err_kms:
  * imx_drm_add_crtc - add a new crtc
  */
 int imx_drm_add_crtc(struct drm_device *drm, struct drm_crtc *crtc,
-                struct imx_drm_crtc **new_crtc,
+                struct imx_drm_crtc **new_crtc, struct drm_plane *primary_plane,
                 const struct imx_drm_crtc_helper_funcs *imx_drm_helper_funcs,
                 struct device_node *port)
 {
@@ -379,7 +378,7 @@ int imx_drm_add_crtc(struct drm_device *drm, struct drm_crtc *crtc,
         drm_crtc_helper_add(crtc,
                         imx_drm_crtc->imx_drm_helper_funcs.crtc_helper_funcs);
 
-        drm_crtc_init(drm, crtc,
+        drm_crtc_init_with_planes(drm, crtc, primary_plane, NULL,
                         imx_drm_crtc->imx_drm_helper_funcs.crtc_funcs);
 
         return 0;
diff --git a/drivers/gpu/drm/imx/imx-drm.h b/drivers/gpu/drm/imx/imx-drm.h
index 28e776d8d9d2..83284b4d4be1 100644
--- a/drivers/gpu/drm/imx/imx-drm.h
+++ b/drivers/gpu/drm/imx/imx-drm.h
@@ -9,6 +9,7 @@ struct drm_display_mode;
 struct drm_encoder;
 struct drm_fbdev_cma;
 struct drm_framebuffer;
+struct drm_plane;
 struct imx_drm_crtc;
 struct platform_device;
 
@@ -24,7 +25,7 @@ struct imx_drm_crtc_helper_funcs {
 };
 
 int imx_drm_add_crtc(struct drm_device *drm, struct drm_crtc *crtc,
-                struct imx_drm_crtc **new_crtc,
+                struct imx_drm_crtc **new_crtc, struct drm_plane *primary_plane,
                 const struct imx_drm_crtc_helper_funcs *imx_helper_funcs,
                 struct device_node *port);
 int imx_drm_remove_crtc(struct imx_drm_crtc *);
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index e671ad369416..f9597146dc67 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -721,6 +721,7 @@ static const struct of_device_id imx_tve_dt_ids[] = {
         { .compatible = "fsl,imx53-tve", },
         { /* sentinel */ }
 };
+MODULE_DEVICE_TABLE(of, imx_tve_dt_ids);
 
 static struct platform_driver imx_tve_driver = {
         .probe          = imx_tve_probe,
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index 7bc8301fafff..4ab841eebee1 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -212,7 +212,8 @@ static void ipu_crtc_handle_pageflip(struct ipu_crtc *ipu_crtc)
 
         spin_lock_irqsave(&drm->event_lock, flags);
         if (ipu_crtc->page_flip_event)
-                drm_send_vblank_event(drm, -1, ipu_crtc->page_flip_event);
+                drm_crtc_send_vblank_event(&ipu_crtc->base,
+                                           ipu_crtc->page_flip_event);
         ipu_crtc->page_flip_event = NULL;
         imx_drm_crtc_vblank_put(ipu_crtc->imx_crtc);
         spin_unlock_irqrestore(&drm->event_lock, flags);
@@ -349,7 +350,6 @@ static int ipu_crtc_init(struct ipu_crtc *ipu_crtc,
         struct ipu_soc *ipu = dev_get_drvdata(ipu_crtc->dev->parent);
         int dp = -EINVAL;
         int ret;
-        int id;
 
         ret = ipu_get_resources(ipu_crtc, pdata);
         if (ret) {
@@ -358,18 +358,23 @@ static int ipu_crtc_init(struct ipu_crtc *ipu_crtc,
                 return ret;
         }
 
+        if (pdata->dp >= 0)
+                dp = IPU_DP_FLOW_SYNC_BG;
+        ipu_crtc->plane[0] = ipu_plane_init(drm, ipu, pdata->dma[0], dp, 0,
+                                            DRM_PLANE_TYPE_PRIMARY);
+        if (IS_ERR(ipu_crtc->plane[0])) {
+                ret = PTR_ERR(ipu_crtc->plane[0]);
+                goto err_put_resources;
+        }
+
         ret = imx_drm_add_crtc(drm, &ipu_crtc->base, &ipu_crtc->imx_crtc,
-                        &ipu_crtc_helper_funcs, ipu_crtc->dev->of_node);
+                        &ipu_crtc->plane[0]->base, &ipu_crtc_helper_funcs,
+                        ipu_crtc->dev->of_node);
         if (ret) {
                 dev_err(ipu_crtc->dev, "adding crtc failed with %d.\n", ret);
                 goto err_put_resources;
         }
 
-        if (pdata->dp >= 0)
-                dp = IPU_DP_FLOW_SYNC_BG;
-        id = imx_drm_crtc_id(ipu_crtc->imx_crtc);
-        ipu_crtc->plane[0] = ipu_plane_init(ipu_crtc->base.dev, ipu,
-                                            pdata->dma[0], dp, BIT(id), true);
         ret = ipu_plane_get_resources(ipu_crtc->plane[0]);
         if (ret) {
                 dev_err(ipu_crtc->dev, "getting plane 0 resources failed with %d.\n",
@@ -379,10 +384,10 @@ static int ipu_crtc_init(struct ipu_crtc *ipu_crtc,
 
         /* If this crtc is using the DP, add an overlay plane */
         if (pdata->dp >= 0 && pdata->dma[1] > 0) {
-                ipu_crtc->plane[1] = ipu_plane_init(ipu_crtc->base.dev, ipu,
-                                                    pdata->dma[1],
-                                                    IPU_DP_FLOW_SYNC_FG,
-                                                    BIT(id), false);
+                ipu_crtc->plane[1] = ipu_plane_init(drm, ipu, pdata->dma[1],
+                                                IPU_DP_FLOW_SYNC_FG,
+                                                drm_crtc_mask(&ipu_crtc->base),
+                                                DRM_PLANE_TYPE_OVERLAY);
                 if (IS_ERR(ipu_crtc->plane[1]))
                         ipu_crtc->plane[1] = NULL;
         }
@@ -407,28 +412,6 @@ err_put_resources:
         return ret;
 }
 
-static struct device_node *ipu_drm_get_port_by_id(struct device_node *parent,
-                                                  int port_id)
-{
-        struct device_node *port;
-        int id, ret;
-
-        port = of_get_child_by_name(parent, "port");
-        while (port) {
-                ret = of_property_read_u32(port, "reg", &id);
-                if (!ret && id == port_id)
-                        return port;
-
-                do {
-                        port = of_get_next_child(parent, port);
-                        if (!port)
-                                return NULL;
-                } while (of_node_cmp(port->name, "port"));
-        }
-
-        return NULL;
-}
-
 static int ipu_drm_bind(struct device *dev, struct device *master, void *data)
 {
         struct ipu_client_platformdata *pdata = dev->platform_data;
@@ -470,23 +453,11 @@ static const struct component_ops ipu_crtc_ops = {
 static int ipu_drm_probe(struct platform_device *pdev)
 {
         struct device *dev = &pdev->dev;
-        struct ipu_client_platformdata *pdata = dev->platform_data;
         int ret;
 
         if (!dev->platform_data)
                 return -EINVAL;
 
-        if (!dev->of_node) {
-                /* Associate crtc device with the corresponding DI port node */
-                dev->of_node = ipu_drm_get_port_by_id(dev->parent->of_node,
-                                                      pdata->di + 2);
-                if (!dev->of_node) {
-                        dev_err(dev, "missing port@%d node in %s\n",
-                                pdata->di + 2, dev->parent->of_node->full_name);
-                        return -ENODEV;
-                }
-        }
-
         ret = dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
         if (ret)
                 return ret;
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c
index 575f4c84388f..e2ff410bab74 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.c
+++ b/drivers/gpu/drm/imx/ipuv3-plane.c
@@ -381,7 +381,7 @@ static struct drm_plane_funcs ipu_plane_funcs = {
 
 struct ipu_plane *ipu_plane_init(struct drm_device *dev, struct ipu_soc *ipu,
                                  int dma, int dp, unsigned int possible_crtcs,
-                                 bool priv)
+                                 enum drm_plane_type type)
 {
         struct ipu_plane *ipu_plane;
         int ret;
@@ -399,10 +399,9 @@ struct ipu_plane *ipu_plane_init(struct drm_device *dev, struct ipu_soc *ipu,
         ipu_plane->dma = dma;
         ipu_plane->dp_flow = dp;
 
-        ret = drm_plane_init(dev, &ipu_plane->base, possible_crtcs,
-                             &ipu_plane_funcs, ipu_plane_formats,
-                             ARRAY_SIZE(ipu_plane_formats),
-                             priv);
+        ret = drm_universal_plane_init(dev, &ipu_plane->base, possible_crtcs,
+                                       &ipu_plane_funcs, ipu_plane_formats,
+                                       ARRAY_SIZE(ipu_plane_formats), type);
         if (ret) {
                 DRM_ERROR("failed to initialize plane\n");
                 kfree(ipu_plane);
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.h b/drivers/gpu/drm/imx/ipuv3-plane.h
index 9b5eff18f5b8..3a443b413c60 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.h
+++ b/drivers/gpu/drm/imx/ipuv3-plane.h
@@ -34,7 +34,7 @@ struct ipu_plane {
 
 struct ipu_plane *ipu_plane_init(struct drm_device *dev, struct ipu_soc *ipu,
                                  int dma, int dp, unsigned int possible_crtcs,
-                                 bool priv);
+                                 enum drm_plane_type type);
 
 /* Init IDMAC, DMFC, DP */
 int ipu_plane_mode_set(struct ipu_plane *plane, struct drm_crtc *crtc,
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index b4deb9cf9d71..2e9b9f1b5cd2 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -54,7 +54,11 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector)
 
         if (imxpd->panel && imxpd->panel->funcs &&
             imxpd->panel->funcs->get_modes) {
+                struct drm_display_info *di = &connector->display_info;
+
                 num_modes = imxpd->panel->funcs->get_modes(imxpd->panel);
+                if (!imxpd->bus_format && di->num_bus_formats)
+                        imxpd->bus_format = di->bus_formats[0];
                 if (num_modes > 0)
                         return num_modes;
         }
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
index 8f760002e401..913192c94876 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
@@ -159,7 +159,6 @@ struct nvkm_device_func {
 struct nvkm_device_quirk {
         u8 tv_pin_mask;
         u8 tv_gpio;
-        bool War00C800_0;
 };
 
 struct nvkm_device_chip {
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/instmem.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/instmem.h
index 28bc202f9753..40f845e31272 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/instmem.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/instmem.h
@@ -7,6 +7,7 @@ struct nvkm_instmem {
         const struct nvkm_instmem_func *func;
         struct nvkm_subdev subdev;
 
+        spinlock_t lock;
         struct list_head list;
         u32 reserved;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index 8b8332e46f24..d5e6938cc6bc 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -367,6 +367,7 @@ static int nouveau_rom_call(acpi_handle rom_handle, uint8_t *bios,
                 return -ENODEV;
         }
         obj = (union acpi_object *)buffer.pointer;
+        len = min(len, (int)obj->buffer.length);
         memcpy(bios+offset, obj->buffer.pointer, len);
         kfree(buffer.pointer);
         return len;
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index db6bc6760545..64c8d932d5f1 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -829,7 +829,6 @@ nouveau_finish_page_flip(struct nouveau_channel *chan,
         struct drm_device *dev = drm->dev;
         struct nouveau_page_flip_state *s;
         unsigned long flags;
-        int crtcid = -1;
 
         spin_lock_irqsave(&dev->event_lock, flags);
 
@@ -841,15 +840,19 @@ nouveau_finish_page_flip(struct nouveau_channel *chan,
 
         s = list_first_entry(&fctx->flip, struct nouveau_page_flip_state, head);
         if (s->event) {
-                /* Vblank timestamps/counts are only correct on >= NV-50 */
-                if (drm->device.info.family >= NV_DEVICE_INFO_V0_TESLA)
-                        crtcid = s->crtc;
+                if (drm->device.info.family < NV_DEVICE_INFO_V0_TESLA) {
+                        drm_arm_vblank_event(dev, s->crtc, s->event);
+                } else {
+                        drm_send_vblank_event(dev, s->crtc, s->event);
 
-                drm_send_vblank_event(dev, crtcid, s->event);
+                        /* Give up ownership of vblank for page-flipped crtc */
+                        drm_vblank_put(dev, s->crtc);
+                }
+        }
+        else {
+                /* Give up ownership of vblank for page-flipped crtc */
+                drm_vblank_put(dev, s->crtc);
         }
-
-        /* Give up ownership of vblank for page-flipped crtc */
-        drm_vblank_put(dev, s->crtc);
 
         list_del(&s->head);
         if (ps)
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.h b/drivers/gpu/drm/nouveau/nouveau_drm.h
index 3050042e6c6d..a02813e994ec 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.h
@@ -39,6 +39,7 @@
 
 #include <nvif/client.h>
 #include <nvif/device.h>
+#include <nvif/ioctl.h>
 
 #include <drmP.h>
 
@@ -65,9 +66,10 @@ struct nouveau_drm_tile {
 };
 
 enum nouveau_drm_object_route {
-        NVDRM_OBJECT_NVIF = 0,
+        NVDRM_OBJECT_NVIF = NVIF_IOCTL_V0_OWNER_NVIF,
         NVDRM_OBJECT_USIF,
         NVDRM_OBJECT_ABI16,
+        NVDRM_OBJECT_ANY = NVIF_IOCTL_V0_OWNER_ANY,
 };
 
 enum nouveau_drm_notify_route {
diff --git a/drivers/gpu/drm/nouveau/nouveau_usif.c b/drivers/gpu/drm/nouveau/nouveau_usif.c
index 89dc4ce63490..6ae1b3494bcd 100644
--- a/drivers/gpu/drm/nouveau/nouveau_usif.c
+++ b/drivers/gpu/drm/nouveau/nouveau_usif.c
@@ -313,7 +313,10 @@ usif_ioctl(struct drm_file *filp, void __user *user, u32 argc)
         if (nvif_unpack(argv->v0, 0, 0, true)) {
                 /* block access to objects not created via this interface */
                 owner = argv->v0.owner;
-                argv->v0.owner = NVDRM_OBJECT_USIF;
+                if (argv->v0.object == 0ULL)
+                        argv->v0.owner = NVDRM_OBJECT_ANY; /* except client */
+                else
+                        argv->v0.owner = NVDRM_OBJECT_USIF;
         } else
                 goto done;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
index e3c783d0e2ab..62ad0300cfa5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/pci.c
@@ -259,12 +259,6 @@ nvkm_device_pci_10de_0df4[] = {
 };
 
 static const struct nvkm_device_pci_vendor
-nvkm_device_pci_10de_0fcd[] = {
-        { 0x17aa, 0x3801, NULL, { .War00C800_0 = true } }, /* Lenovo Y510P */
-        {}
-};
-
-static const struct nvkm_device_pci_vendor
 nvkm_device_pci_10de_0fd2[] = {
         { 0x1028, 0x0595, "GeForce GT 640M LE" },
         { 0x1028, 0x05b2, "GeForce GT 640M LE" },
@@ -684,7 +678,6 @@ nvkm_device_pci_10de_1189[] = {
 static const struct nvkm_device_pci_vendor
 nvkm_device_pci_10de_1199[] = {
         { 0x1458, 0xd001, "GeForce GTX 760" },
-        { 0x1462, 0x1106, "GeForce GTX 780M", { .War00C800_0 = true } }, /* Medion Erazer X7827 */
         {}
 };
 
@@ -695,14 +688,6 @@ nvkm_device_pci_10de_11e3[] = {
 };
 
 static const struct nvkm_device_pci_vendor
-nvkm_device_pci_10de_11fc[] = {
-        { 0x1179, 0x0001, NULL, { .War00C800_0 = true } }, /* Toshiba Tecra W50 */
-        { 0x17aa, 0x2211, NULL, { .War00C800_0 = true } }, /* Lenovo W541 */
-        { 0x17aa, 0x221e, NULL, { .War00C800_0 = true } }, /* Lenovo W541 */
-        {}
-};
-
-static const struct nvkm_device_pci_vendor
 nvkm_device_pci_10de_1247[] = {
         { 0x1043, 0x212a, "GeForce GT 635M" },
         { 0x1043, 0x212b, "GeForce GT 635M" },
@@ -1356,7 +1341,7 @@ nvkm_device_pci_10de[] = {
         { 0x0fc6, "GeForce GTX 650" },
         { 0x0fc8, "GeForce GT 740" },
         { 0x0fc9, "GeForce GT 730" },
-        { 0x0fcd, "GeForce GT 755M", nvkm_device_pci_10de_0fcd },
+        { 0x0fcd, "GeForce GT 755M" },
         { 0x0fce, "GeForce GT 640M LE" },
         { 0x0fd1, "GeForce GT 650M" },
         { 0x0fd2, "GeForce GT 640M", nvkm_device_pci_10de_0fd2 },
@@ -1490,7 +1475,7 @@ nvkm_device_pci_10de[] = {
         { 0x11e2, "GeForce GTX 765M" },
         { 0x11e3, "GeForce GTX 760M", nvkm_device_pci_10de_11e3 },
         { 0x11fa, "Quadro K4000" },
-        { 0x11fc, "Quadro K2100M", nvkm_device_pci_10de_11fc },
+        { 0x11fc, "Quadro K2100M" },
         { 0x1200, "GeForce GTX 560 Ti" },
         { 0x1201, "GeForce GTX 560" },
         { 0x1203, "GeForce GTX 460 SE v2" },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c
index b5b875928aba..74de7a96c22a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf117.c
@@ -207,6 +207,8 @@ gf117_grctx_generate_attrib(struct gf100_grctx *info)
                         const u32 b =  beta * gr->ppc_tpc_nr[gpc][ppc];
                         const u32 t = timeslice_mode;
                         const u32 o = PPC_UNIT(gpc, ppc, 0);
+                        if (!(gr->ppc_mask[gpc] & (1 << ppc)))
+                                continue;
                         mmio_skip(info, o + 0xc0, (t << 28) | (b << 16) | ++bo);
                         mmio_wr32(info, o + 0xc0, (t << 28) | (b << 16) | --bo);
                         bo += grctx->attrib_nr_max * gr->ppc_tpc_nr[gpc][ppc];
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpc.fuc b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpc.fuc
index 194afe910d21..7dacb3cc0668 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpc.fuc
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpc.fuc
@@ -52,10 +52,12 @@ mmio_list_base:
 #endif
 
 #ifdef INCLUDE_CODE
+#define gpc_addr(reg,addr)                                                    /*
+*/      imm32(reg,addr)                                                       /*
+*/      or reg NV_PGRAPH_GPCX_GPCCS_MMIO_CTRL_BASE_ENABLE
 #define gpc_wr32(addr,reg)                                                    /*
+*/      gpc_addr($r14,addr)                                                   /*
 */      mov b32 $r15 reg                                                      /*
-*/      imm32($r14, addr)                                                     /*
-*/      or $r14 NV_PGRAPH_GPCX_GPCCS_MMIO_CTRL_BASE_ENABLE                    /*
 */      call(nv_wr32)
 
 // reports an exception to the host
@@ -161,7 +163,7 @@ init:
 
 #if NV_PGRAPH_GPCX_UNK__SIZE > 0
         // figure out which, and how many, UNKs are actually present
-        imm32($r14, 0x500c30)
+        gpc_addr($r14, 0x500c30)
         clear b32 $r2
         clear b32 $r3
         clear b32 $r4
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgf117.fuc3.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgf117.fuc3.h
index 64d07df4b8b1..bb820ff28621 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgf117.fuc3.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgf117.fuc3.h
@@ -314,7 +314,7 @@ uint32_t gf117_grgpc_code[] = {
         0x03f01200,
         0x0002d000,
         0x17f104bd,
-        0x10fe0542,
+        0x10fe0545,
         0x0007f100,
         0x0003f007,
         0xbd0000d0,
@@ -338,184 +338,184 @@ uint32_t gf117_grgpc_code[] = {
         0x02d00103,
         0xf104bd00,
         0xf00c30e7,
-        0x24bd50e3,
-        0x44bd34bd,
-/* 0x0430: init_unk_loop */
-        0xb06821f4,
-        0x0bf400f6,
-        0x01f7f00f,
-        0xfd04f2bb,
-        0x30b6054f,
-/* 0x0445: init_unk_next */
-        0x0120b601,
-        0xb004e0b6,
-        0x1bf40126,
-/* 0x0451: init_unk_done */
-        0x070380e2,
-        0xf1080480,
-        0xf0010027,
-        0x22cf0223,
-        0x9534bd00,
-        0x07f10825,
-        0x03f0c000,
-        0x0005d001,
-        0x07f104bd,
-        0x03f0c100,
-        0x0005d001,
-        0x0e9804bd,
-        0x010f9800,
-        0x015021f5,
-        0xbb002fbb,
-        0x0e98003f,
-        0x020f9801,
-        0x015021f5,
-        0xfd050e98,
-        0x2ebb00ef,
-        0x003ebb00,
-        0x98020e98,
-        0x21f5030f,
-        0x0e980150,
-        0x00effd07,
-        0xbb002ebb,
-        0x35b6003e,
-        0x0007f102,
-        0x0103f0d3,
-        0xbd0003d0,
-        0x0825b604,
-        0xb60635b6,
-        0x30b60120,
-        0x0824b601,
-        0xb90834b6,
-        0x21f5022f,
-        0x2fbb02d3,
-        0x003fbb00,
-        0x010007f1,
-        0xd00203f0,
+        0xe5f050e3,
+        0xbd24bd01,
+/* 0x0433: init_unk_loop */
+        0xf444bd34,
+        0xf6b06821,
+        0x0f0bf400,
+        0xbb01f7f0,
+        0x4ffd04f2,
+        0x0130b605,
+/* 0x0448: init_unk_next */
+        0xb60120b6,
+        0x26b004e0,
+        0xe21bf401,
+/* 0x0454: init_unk_done */
+        0x80070380,
+        0x27f10804,
+        0x23f00100,
+        0x0022cf02,
+        0x259534bd,
+        0x0007f108,
+        0x0103f0c0,
+        0xbd0005d0,
+        0x0007f104,
+        0x0103f0c1,
+        0xbd0005d0,
+        0x000e9804,
+        0xf5010f98,
+        0xbb015021,
+        0x3fbb002f,
+        0x010e9800,
+        0xf5020f98,
+        0x98015021,
+        0xeffd050e,
+        0x002ebb00,
+        0x98003ebb,
+        0x0f98020e,
+        0x5021f503,
+        0x070e9801,
+        0xbb00effd,
+        0x3ebb002e,
+        0x0235b600,
+        0xd30007f1,
+        0xd00103f0,
         0x04bd0003,
-        0x29f024bd,
-        0x0007f11f,
-        0x0203f008,
-        0xbd0002d0,
-/* 0x0505: main */
-        0x0031f404,
-        0xf00028f4,
-        0x21f424d7,
-        0xf401f439,
-        0xf404e4b0,
-        0x81fe1e18,
-        0x0627f001,
-        0x12fd20bd,
-        0x01e4b604,
-        0xfe051efd,
-        0x21f50018,
-        0x0ef405fa,
-/* 0x0535: main_not_ctx_xfer */
-        0x10ef94d3,
-        0xf501f5f0,
-        0xf4037e21,
-/* 0x0542: ih */
-        0x80f9c60e,
-        0xf90188fe,
-        0xf990f980,
-        0xf9b0f9a0,
-        0xf9e0f9d0,
-        0xf104bdf0,
-        0xf00200a7,
-        0xaacf00a3,
-        0x04abc400,
-        0xf02c0bf4,
-        0xe7f124d7,
-        0xe3f01a00,
-        0x00eecf00,
-        0x1900f7f1,
-        0xcf00f3f0,
-        0x21f400ff,
-        0x01e7f004,
-        0x1d0007f1,
-        0xd00003f0,
-        0x04bd000e,
-/* 0x0590: ih_no_fifo */
-        0x010007f1,
-        0xd00003f0,
-        0x04bd000a,
-        0xe0fcf0fc,
-        0xb0fcd0fc,
-        0x90fca0fc,
-        0x88fe80fc,
-        0xf480fc00,
-        0x01f80032,
-/* 0x05b4: hub_barrier_done */
-        0x9801f7f0,
-        0xfebb040e,
-        0x02ffb904,
-        0x9418e7f1,
-        0xf440e3f0,
-        0x00f89d21,
-/* 0x05cc: ctx_redswitch */
-        0xf120f7f0,
+        0xb60825b6,
+        0x20b60635,
+        0x0130b601,
+        0xb60824b6,
+        0x2fb90834,
+        0xd321f502,
+        0x002fbb02,
+        0xf1003fbb,
+        0xf0010007,
+        0x03d00203,
+        0xbd04bd00,
+        0x1f29f024,
+        0x080007f1,
+        0xd00203f0,
+        0x04bd0002,
+/* 0x0508: main */
+        0xf40031f4,
+        0xd7f00028,
+        0x3921f424,
+        0xb0f401f4,
+        0x18f404e4,
+        0x0181fe1e,
+        0xbd0627f0,
+        0x0412fd20,
+        0xfd01e4b6,
+        0x18fe051e,
+        0xfd21f500,
+        0xd30ef405,
+/* 0x0538: main_not_ctx_xfer */
+        0xf010ef94,
+        0x21f501f5,
+        0x0ef4037e,
+/* 0x0545: ih */
+        0xfe80f9c6,
+        0x80f90188,
+        0xa0f990f9,
+        0xd0f9b0f9,
+        0xf0f9e0f9,
+        0xa7f104bd,
+        0xa3f00200,
+        0x00aacf00,
+        0xf404abc4,
+        0xd7f02c0b,
+        0x00e7f124,
+        0x00e3f01a,
+        0xf100eecf,
+        0xf01900f7,
+        0xffcf00f3,
+        0x0421f400,
+        0xf101e7f0,
+        0xf01d0007,
+        0x0ed00003,
+/* 0x0593: ih_no_fifo */
+        0xf104bd00,
+        0xf0010007,
+        0x0ad00003,
+        0xfc04bd00,
+        0xfce0fcf0,
+        0xfcb0fcd0,
+        0xfc90fca0,
+        0x0088fe80,
+        0x32f480fc,
+/* 0x05b7: hub_barrier_done */
+        0xf001f800,
+        0x0e9801f7,
+        0x04febb04,
+        0xf102ffb9,
+        0xf09418e7,
+        0x21f440e3,
+/* 0x05cf: ctx_redswitch */
+        0xf000f89d,
+        0x07f120f7,
+        0x03f08500,
+        0x000fd001,
+        0xe7f004bd,
+/* 0x05e1: ctx_redswitch_delay */
+        0x01e2b608,
+        0xf1fd1bf4,
+        0xf10800f5,
+        0xf10200f5,
         0xf0850007,
         0x0fd00103,
-        0xf004bd00,
-/* 0x05de: ctx_redswitch_delay */
-        0xe2b608e7,
-        0xfd1bf401,
-        0x0800f5f1,
-        0x0200f5f1,
-        0x850007f1,
-        0xd00103f0,
-        0x04bd000f,
-/* 0x05fa: ctx_xfer */
-        0x07f100f8,
-        0x03f08100,
-        0x000fd002,
-        0x11f404bd,
-        0xcc21f507,
-/* 0x060d: ctx_xfer_not_load */
-        0x6a21f505,
-        0xf124bd02,
-        0xf047fc07,
-        0x02d00203,
-        0xf004bd00,
-        0x20b6012c,
-        0xfc07f103,
-        0x0203f04a,
-        0xbd0002d0,
-        0x01acf004,
-        0xf102a5f0,
-        0xf00000b7,
-        0x0c9850b3,
-        0x0fc4b604,
-        0x9800bcbb,
-        0x0d98000c,
-        0x00e7f001,
-        0x016f21f5,
-        0xf101acf0,
-        0xf04000b7,
-        0x0c9850b3,
-        0x0fc4b604,
-        0x9800bcbb,
-        0x0d98010c,
-        0x060f9802,
-        0x0800e7f1,
-        0x016f21f5,
+        0xf804bd00,
+/* 0x05fd: ctx_xfer */
+        0x0007f100,
+        0x0203f081,
+        0xbd000fd0,
+        0x0711f404,
+        0x05cf21f5,
+/* 0x0610: ctx_xfer_not_load */
+        0x026a21f5,
+        0x07f124bd,
+        0x03f047fc,
+        0x0002d002,
+        0x2cf004bd,
+        0x0320b601,
+        0x4afc07f1,
+        0xd00203f0,
+        0x04bd0002,
         0xf001acf0,
-        0xb7f104a5,
-        0xb3f03000,
+        0xb7f102a5,
+        0xb3f00000,
         0x040c9850,
         0xbb0fc4b6,
         0x0c9800bc,
-        0x030d9802,
-        0xf1080f98,
-        0xf50200e7,
-        0xf5016f21,
-        0xf4025e21,
-        0x12f40601,
-/* 0x06a9: ctx_xfer_post */
-        0x7f21f507,
-/* 0x06ad: ctx_xfer_done */
-        0xb421f502,
-        0x0000f805,
-        0x00000000,
+        0x010d9800,
+        0xf500e7f0,
+        0xf0016f21,
+        0xb7f101ac,
+        0xb3f04000,
+        0x040c9850,
+        0xbb0fc4b6,
+        0x0c9800bc,
+        0x020d9801,
+        0xf1060f98,
+        0xf50800e7,
+        0xf0016f21,
+        0xa5f001ac,
+        0x00b7f104,
+        0x50b3f030,
+        0xb6040c98,
+        0xbcbb0fc4,
+        0x020c9800,
+        0x98030d98,
+        0xe7f1080f,
+        0x21f50200,
+        0x21f5016f,
+        0x01f4025e,
+        0x0712f406,
+/* 0x06ac: ctx_xfer_post */
+        0x027f21f5,
+/* 0x06b0: ctx_xfer_done */
+        0x05b721f5,
+        0x000000f8,
         0x00000000,
         0x00000000,
         0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk104.fuc3.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk104.fuc3.h
index 2f596433c222..911976d20940 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk104.fuc3.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk104.fuc3.h
@@ -314,7 +314,7 @@ uint32_t gk104_grgpc_code[] = {
         0x03f01200,
         0x0002d000,
         0x17f104bd,
-        0x10fe0542,
+        0x10fe0545,
         0x0007f100,
         0x0003f007,
         0xbd0000d0,
@@ -338,184 +338,184 @@ uint32_t gk104_grgpc_code[] = {
         0x02d00103,
         0xf104bd00,
         0xf00c30e7,
-        0x24bd50e3,
-        0x44bd34bd,
-/* 0x0430: init_unk_loop */
-        0xb06821f4,
-        0x0bf400f6,
-        0x01f7f00f,
-        0xfd04f2bb,
-        0x30b6054f,
-/* 0x0445: init_unk_next */
-        0x0120b601,
-        0xb004e0b6,
-        0x1bf40126,
-/* 0x0451: init_unk_done */
-        0x070380e2,
-        0xf1080480,
-        0xf0010027,
-        0x22cf0223,
-        0x9534bd00,
-        0x07f10825,
-        0x03f0c000,
-        0x0005d001,
-        0x07f104bd,
-        0x03f0c100,
-        0x0005d001,
-        0x0e9804bd,
-        0x010f9800,
-        0x015021f5,
-        0xbb002fbb,
-        0x0e98003f,
-        0x020f9801,
-        0x015021f5,
-        0xfd050e98,
-        0x2ebb00ef,
-        0x003ebb00,
-        0x98020e98,
-        0x21f5030f,
-        0x0e980150,
-        0x00effd07,
-        0xbb002ebb,
-        0x35b6003e,
-        0x0007f102,
-        0x0103f0d3,
-        0xbd0003d0,
-        0x0825b604,
-        0xb60635b6,
-        0x30b60120,
-        0x0824b601,
-        0xb90834b6,
-        0x21f5022f,
-        0x2fbb02d3,
-        0x003fbb00,
-        0x010007f1,
-        0xd00203f0,
+        0xe5f050e3,
+        0xbd24bd01,
+/* 0x0433: init_unk_loop */
+        0xf444bd34,
+        0xf6b06821,
+        0x0f0bf400,
+        0xbb01f7f0,
+        0x4ffd04f2,
+        0x0130b605,
+/* 0x0448: init_unk_next */
+        0xb60120b6,
+        0x26b004e0,
+        0xe21bf401,
+/* 0x0454: init_unk_done */
+        0x80070380,
+        0x27f10804,
+        0x23f00100,
+        0x0022cf02,
+        0x259534bd,
+        0x0007f108,
+        0x0103f0c0,
+        0xbd0005d0,
+        0x0007f104,
+        0x0103f0c1,
+        0xbd0005d0,
+        0x000e9804,
+        0xf5010f98,
+        0xbb015021,
+        0x3fbb002f,
+        0x010e9800,
+        0xf5020f98,
+        0x98015021,
+        0xeffd050e,
+        0x002ebb00,
+        0x98003ebb,
+        0x0f98020e,
+        0x5021f503,
+        0x070e9801,
+        0xbb00effd,
+        0x3ebb002e,
+        0x0235b600,
+        0xd30007f1,
+        0xd00103f0,
         0x04bd0003,
-        0x29f024bd,
-        0x0007f11f,
-        0x0203f008,
-        0xbd0002d0,
-/* 0x0505: main */
-        0x0031f404,
-        0xf00028f4,
-        0x21f424d7,
-        0xf401f439,
-        0xf404e4b0,
-        0x81fe1e18,
-        0x0627f001,
-        0x12fd20bd,
-        0x01e4b604,
-        0xfe051efd,
-        0x21f50018,
-        0x0ef405fa,
-/* 0x0535: main_not_ctx_xfer */
-        0x10ef94d3,
-        0xf501f5f0,
-        0xf4037e21,
-/* 0x0542: ih */
-        0x80f9c60e,
-        0xf90188fe,
-        0xf990f980,
-        0xf9b0f9a0,
-        0xf9e0f9d0,
-        0xf104bdf0,
-        0xf00200a7,
-        0xaacf00a3,
-        0x04abc400,
-        0xf02c0bf4,
-        0xe7f124d7,
-        0xe3f01a00,
-        0x00eecf00,
-        0x1900f7f1,
-        0xcf00f3f0,
-        0x21f400ff,
-        0x01e7f004,
-        0x1d0007f1,
-        0xd00003f0,
-        0x04bd000e,
-/* 0x0590: ih_no_fifo */
-        0x010007f1,
-        0xd00003f0,
-        0x04bd000a,
-        0xe0fcf0fc,
-        0xb0fcd0fc,
-        0x90fca0fc,
-        0x88fe80fc,
-        0xf480fc00,
-        0x01f80032,
-/* 0x05b4: hub_barrier_done */
-        0x9801f7f0,
-        0xfebb040e,
-        0x02ffb904,
-        0x9418e7f1,
-        0xf440e3f0,
-        0x00f89d21,
-/* 0x05cc: ctx_redswitch */
-        0xf120f7f0,
+        0xb60825b6,
+        0x20b60635,
+        0x0130b601,
+        0xb60824b6,
+        0x2fb90834,
+        0xd321f502,
+        0x002fbb02,
+        0xf1003fbb,
+        0xf0010007,
+        0x03d00203,
+        0xbd04bd00,
+        0x1f29f024,
+        0x080007f1,
+        0xd00203f0,
+        0x04bd0002,
+/* 0x0508: main */
+        0xf40031f4,
+        0xd7f00028,
+        0x3921f424,
+        0xb0f401f4,
+        0x18f404e4,
+        0x0181fe1e,
+        0xbd0627f0,
+        0x0412fd20,
+        0xfd01e4b6,
+        0x18fe051e,
+        0xfd21f500,
+        0xd30ef405,
+/* 0x0538: main_not_ctx_xfer */
+        0xf010ef94,
+        0x21f501f5,
+        0x0ef4037e,
+/* 0x0545: ih */
+        0xfe80f9c6,
+        0x80f90188,
+        0xa0f990f9,
+        0xd0f9b0f9,
+        0xf0f9e0f9,
+        0xa7f104bd,
+        0xa3f00200,
+        0x00aacf00,
+        0xf404abc4,
+        0xd7f02c0b,
+        0x00e7f124,
+        0x00e3f01a,
+        0xf100eecf,
+        0xf01900f7,
+        0xffcf00f3,
+        0x0421f400,
+        0xf101e7f0,
+        0xf01d0007,
+        0x0ed00003,
+/* 0x0593: ih_no_fifo */
+        0xf104bd00,
+        0xf0010007,
+        0x0ad00003,
+        0xfc04bd00,
+        0xfce0fcf0,
+        0xfcb0fcd0,
+        0xfc90fca0,
+        0x0088fe80,
+        0x32f480fc,
+/* 0x05b7: hub_barrier_done */
+        0xf001f800,
+        0x0e9801f7,
+        0x04febb04,
+        0xf102ffb9,
+        0xf09418e7,
+        0x21f440e3,
+/* 0x05cf: ctx_redswitch */
+        0xf000f89d,
+        0x07f120f7,
+        0x03f08500,
+        0x000fd001,
+        0xe7f004bd,
+/* 0x05e1: ctx_redswitch_delay */
+        0x01e2b608,
+        0xf1fd1bf4,
+        0xf10800f5,
+        0xf10200f5,
         0xf0850007,
         0x0fd00103,
-        0xf004bd00,
-/* 0x05de: ctx_redswitch_delay */
-        0xe2b608e7,
-        0xfd1bf401,
-        0x0800f5f1,
-        0x0200f5f1,
-        0x850007f1,
-        0xd00103f0,
-        0x04bd000f,
-/* 0x05fa: ctx_xfer */
-        0x07f100f8,
-        0x03f08100,
-        0x000fd002,
-        0x11f404bd,
-        0xcc21f507,
-/* 0x060d: ctx_xfer_not_load */
-        0x6a21f505,
-        0xf124bd02,
-        0xf047fc07,
-        0x02d00203,
-        0xf004bd00,
-        0x20b6012c,
-        0xfc07f103,
-        0x0203f04a,
-        0xbd0002d0,
-        0x01acf004,
-        0xf102a5f0,
-        0xf00000b7,
-        0x0c9850b3,
-        0x0fc4b604,
-        0x9800bcbb,
-        0x0d98000c,
-        0x00e7f001,
-        0x016f21f5,
-        0xf101acf0,
-        0xf04000b7,
-        0x0c9850b3,
-        0x0fc4b604,
-        0x9800bcbb,
-        0x0d98010c,
-        0x060f9802,
-        0x0800e7f1,
-        0x016f21f5,
+        0xf804bd00,
+/* 0x05fd: ctx_xfer */
+        0x0007f100,
+        0x0203f081,
+        0xbd000fd0,
+        0x0711f404,
+        0x05cf21f5,
+/* 0x0610: ctx_xfer_not_load */
+        0x026a21f5,
+        0x07f124bd,
+        0x03f047fc,
+        0x0002d002,
+        0x2cf004bd,
+        0x0320b601,
+        0x4afc07f1,
+        0xd00203f0,
+        0x04bd0002,
         0xf001acf0,
-        0xb7f104a5,
-        0xb3f03000,
+        0xb7f102a5,
+        0xb3f00000,
         0x040c9850,
         0xbb0fc4b6,
         0x0c9800bc,
-        0x030d9802,
-        0xf1080f98,
-        0xf50200e7,
-        0xf5016f21,
-        0xf4025e21,
-        0x12f40601,
-/* 0x06a9: ctx_xfer_post */
-        0x7f21f507,
-/* 0x06ad: ctx_xfer_done */
-        0xb421f502,
-        0x0000f805,
-        0x00000000,
+        0x010d9800,
+        0xf500e7f0,
+        0xf0016f21,
+        0xb7f101ac,
+        0xb3f04000,
+        0x040c9850,
+        0xbb0fc4b6,
+        0x0c9800bc,
+        0x020d9801,
+        0xf1060f98,
+        0xf50800e7,
+        0xf0016f21,
+        0xa5f001ac,
+        0x00b7f104,
+        0x50b3f030,
+        0xb6040c98,
+        0xbcbb0fc4,
+        0x020c9800,
+        0x98030d98,
+        0xe7f1080f,
+        0x21f50200,
+        0x21f5016f,
+        0x01f4025e,
+        0x0712f406,
+/* 0x06ac: ctx_xfer_post */
+        0x027f21f5,
+/* 0x06b0: ctx_xfer_done */
+        0x05b721f5,
+        0x000000f8,
         0x00000000,
         0x00000000,
         0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk110.fuc3.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk110.fuc3.h
index ee8e54db8fc9..1c6e11b05df2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk110.fuc3.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk110.fuc3.h
@@ -314,7 +314,7 @@ uint32_t gk110_grgpc_code[] = {
         0x03f01200,
         0x0002d000,
         0x17f104bd,
-        0x10fe0542,
+        0x10fe0545,
         0x0007f100,
         0x0003f007,
         0xbd0000d0,
@@ -338,184 +338,184 @@ uint32_t gk110_grgpc_code[] = {
         0x02d00103,
         0xf104bd00,
         0xf00c30e7,
-        0x24bd50e3,
-        0x44bd34bd,
-/* 0x0430: init_unk_loop */
-        0xb06821f4,
-        0x0bf400f6,
-        0x01f7f00f,
-        0xfd04f2bb,
-        0x30b6054f,
-/* 0x0445: init_unk_next */
-        0x0120b601,
-        0xb004e0b6,
-        0x1bf40226,
-/* 0x0451: init_unk_done */
-        0x070380e2,
-        0xf1080480,
-        0xf0010027,
-        0x22cf0223,
-        0x9534bd00,
-        0x07f10825,
-        0x03f0c000,
-        0x0005d001,
-        0x07f104bd,
-        0x03f0c100,
-        0x0005d001,
-        0x0e9804bd,
-        0x010f9800,
-        0x015021f5,
-        0xbb002fbb,
-        0x0e98003f,
-        0x020f9801,
-        0x015021f5,
-        0xfd050e98,
-        0x2ebb00ef,
-        0x003ebb00,
-        0x98020e98,
-        0x21f5030f,
-        0x0e980150,
-        0x00effd07,
-        0xbb002ebb,
-        0x35b6003e,
-        0x0007f102,
-        0x0103f0d3,
-        0xbd0003d0,
-        0x0825b604,
-        0xb60635b6,
-        0x30b60120,
-        0x0824b601,
-        0xb90834b6,
-        0x21f5022f,
-        0x2fbb02d3,
-        0x003fbb00,
-        0x010007f1,
-        0xd00203f0,
+        0xe5f050e3,
+        0xbd24bd01,
+/* 0x0433: init_unk_loop */
+        0xf444bd34,
+        0xf6b06821,
+        0x0f0bf400,
+        0xbb01f7f0,
+        0x4ffd04f2,
+        0x0130b605,
+/* 0x0448: init_unk_next */
+        0xb60120b6,
+        0x26b004e0,
+        0xe21bf402,
+/* 0x0454: init_unk_done */
+        0x80070380,
+        0x27f10804,
+        0x23f00100,
+        0x0022cf02,
+        0x259534bd,
+        0x0007f108,
+        0x0103f0c0,
+        0xbd0005d0,
+        0x0007f104,
+        0x0103f0c1,
+        0xbd0005d0,
+        0x000e9804,
+        0xf5010f98,
+        0xbb015021,
+        0x3fbb002f,
+        0x010e9800,
+        0xf5020f98,
+        0x98015021,
+        0xeffd050e,
+        0x002ebb00,
+        0x98003ebb,
+        0x0f98020e,
+        0x5021f503,
+        0x070e9801,
+        0xbb00effd,
+        0x3ebb002e,
+        0x0235b600,
+        0xd30007f1,
+        0xd00103f0,
         0x04bd0003,
-        0x29f024bd,
-        0x0007f11f,
-        0x0203f030,
-        0xbd0002d0,
-/* 0x0505: main */
-        0x0031f404,
-        0xf00028f4,
-        0x21f424d7,
-        0xf401f439,
-        0xf404e4b0,
-        0x81fe1e18,
-        0x0627f001,
-        0x12fd20bd,
-        0x01e4b604,
-        0xfe051efd,
-        0x21f50018,
-        0x0ef405fa,
-/* 0x0535: main_not_ctx_xfer */
-        0x10ef94d3,
-        0xf501f5f0,
-        0xf4037e21,
-/* 0x0542: ih */
-        0x80f9c60e,
-        0xf90188fe,
-        0xf990f980,
-        0xf9b0f9a0,
-        0xf9e0f9d0,
-        0xf104bdf0,
-        0xf00200a7,
-        0xaacf00a3,
-        0x04abc400,
-        0xf02c0bf4,
-        0xe7f124d7,
-        0xe3f01a00,
-        0x00eecf00,
-        0x1900f7f1,
-        0xcf00f3f0,
-        0x21f400ff,
-        0x01e7f004,
-        0x1d0007f1,
-        0xd00003f0,
-        0x04bd000e,
-/* 0x0590: ih_no_fifo */
-        0x010007f1,
-        0xd00003f0,
-        0x04bd000a,
-        0xe0fcf0fc,
-        0xb0fcd0fc,
-        0x90fca0fc,
-        0x88fe80fc,
-        0xf480fc00,
-        0x01f80032,
-/* 0x05b4: hub_barrier_done */
-        0x9801f7f0,
-        0xfebb040e,
-        0x02ffb904,
-        0x9418e7f1,
-        0xf440e3f0,
-        0x00f89d21,
-/* 0x05cc: ctx_redswitch */
-        0xf120f7f0,
+        0xb60825b6,
+        0x20b60635,
+        0x0130b601,
+        0xb60824b6,
+        0x2fb90834,
+        0xd321f502,
+        0x002fbb02,
+        0xf1003fbb,
+        0xf0010007,
+        0x03d00203,
+        0xbd04bd00,
+        0x1f29f024,
+        0x300007f1,
+        0xd00203f0,
+        0x04bd0002,
+/* 0x0508: main */
+        0xf40031f4,
+        0xd7f00028,
+        0x3921f424,
+        0xb0f401f4,
+        0x18f404e4,
+        0x0181fe1e,
+        0xbd0627f0,
+        0x0412fd20,
+        0xfd01e4b6,
+        0x18fe051e,
+        0xfd21f500,
+        0xd30ef405,
+/* 0x0538: main_not_ctx_xfer */
+        0xf010ef94,
+        0x21f501f5,
+        0x0ef4037e,
+/* 0x0545: ih */
+        0xfe80f9c6,
+        0x80f90188,
+        0xa0f990f9,
+        0xd0f9b0f9,
+        0xf0f9e0f9,
+        0xa7f104bd,
+        0xa3f00200,
+        0x00aacf00,
+        0xf404abc4,
+        0xd7f02c0b,
+        0x00e7f124,
+        0x00e3f01a,
+        0xf100eecf,
+        0xf01900f7,
+        0xffcf00f3,
+        0x0421f400,
+        0xf101e7f0,
+        0xf01d0007,
+        0x0ed00003,
+/* 0x0593: ih_no_fifo */
+        0xf104bd00,
+        0xf0010007,
+        0x0ad00003,
+        0xfc04bd00,
+        0xfce0fcf0,
+        0xfcb0fcd0,
+        0xfc90fca0,
+        0x0088fe80,
+        0x32f480fc,
+/* 0x05b7: hub_barrier_done */
+        0xf001f800,
+        0x0e9801f7,
+        0x04febb04,
+        0xf102ffb9,
+        0xf09418e7,
+        0x21f440e3,
+/* 0x05cf: ctx_redswitch */
+        0xf000f89d,
+        0x07f120f7,
+        0x03f08500,
+        0x000fd001,
+        0xe7f004bd,
+/* 0x05e1: ctx_redswitch_delay */
+        0x01e2b608,
+        0xf1fd1bf4,
+        0xf10800f5,
+        0xf10200f5,
         0xf0850007,
         0x0fd00103,
-        0xf004bd00,
-/* 0x05de: ctx_redswitch_delay */
-        0xe2b608e7,
-        0xfd1bf401,
-        0x0800f5f1,
-        0x0200f5f1,
-        0x850007f1,
-        0xd00103f0,
-        0x04bd000f,
-/* 0x05fa: ctx_xfer */
-        0x07f100f8,
-        0x03f08100,
-        0x000fd002,
-        0x11f404bd,
-        0xcc21f507,
-/* 0x060d: ctx_xfer_not_load */
-        0x6a21f505,
-        0xf124bd02,
-        0xf047fc07,
-        0x02d00203,
-        0xf004bd00,
-        0x20b6012c,
-        0xfc07f103,
-        0x0203f04a,
-        0xbd0002d0,
-        0x01acf004,
-        0xf102a5f0,
-        0xf00000b7,
-        0x0c9850b3,
-        0x0fc4b604,
-        0x9800bcbb,
-        0x0d98000c,
-        0x00e7f001,
-        0x016f21f5,
-        0xf101acf0,
-        0xf04000b7,
-        0x0c9850b3,
-        0x0fc4b604,
-        0x9800bcbb,
-        0x0d98010c,
-        0x060f9802,
-        0x0800e7f1,
-        0x016f21f5,
+        0xf804bd00,
+/* 0x05fd: ctx_xfer */
+        0x0007f100,
+        0x0203f081,
+        0xbd000fd0,
+        0x0711f404,
+        0x05cf21f5,
+/* 0x0610: ctx_xfer_not_load */
+        0x026a21f5,
+        0x07f124bd,
+        0x03f047fc,
+        0x0002d002,
+        0x2cf004bd,
+        0x0320b601,
+        0x4afc07f1,
+        0xd00203f0,
+        0x04bd0002,
         0xf001acf0,
-        0xb7f104a5,
-        0xb3f03000,
+        0xb7f102a5,
+        0xb3f00000,
         0x040c9850,
         0xbb0fc4b6,
         0x0c9800bc,
-        0x030d9802,
-        0xf1080f98,
-        0xf50200e7,
-        0xf5016f21,
-        0xf4025e21,
-        0x12f40601,
-/* 0x06a9: ctx_xfer_post */
-        0x7f21f507,
-/* 0x06ad: ctx_xfer_done */
-        0xb421f502,
-        0x0000f805,
-        0x00000000,
+        0x010d9800,
+        0xf500e7f0,
+        0xf0016f21,
+        0xb7f101ac,
+        0xb3f04000,
+        0x040c9850,
+        0xbb0fc4b6,
+        0x0c9800bc,
+        0x020d9801,
+        0xf1060f98,
+        0xf50800e7,
+        0xf0016f21,
+        0xa5f001ac,
+        0x00b7f104,
+        0x50b3f030,
+        0xb6040c98,
+        0xbcbb0fc4,
+        0x020c9800,
+        0x98030d98,
+        0xe7f1080f,
+        0x21f50200,
+        0x21f5016f,
+        0x01f4025e,
+        0x0712f406,
+/* 0x06ac: ctx_xfer_post */
+        0x027f21f5,
+/* 0x06b0: ctx_xfer_done */
+        0x05b721f5,
+        0x000000f8,
         0x00000000,
         0x00000000,
         0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk208.fuc5.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk208.fuc5.h
index fbcc342f896f..84af7ec6a78e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk208.fuc5.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgk208.fuc5.h
@@ -276,7 +276,7 @@ uint32_t gk208_grgpc_code[] = {
         0x02020014,
         0xf6120040,
         0x04bd0002,
-        0xfe048141,
+        0xfe048441,
         0x00400010,
         0x0000f607,
         0x040204bd,
@@ -295,165 +295,165 @@ uint32_t gk208_grgpc_code[] = {
         0x01c90080,
         0xbd0002f6,
         0x0c308e04,
-        0xbd24bd50,
-/* 0x0383: init_unk_loop */
-        0x7e44bd34,
-        0xb0000065,
-        0x0bf400f6,
-        0xbb010f0e,
-        0x4ffd04f2,
-        0x0130b605,
-/* 0x0398: init_unk_next */
-        0xb60120b6,
-        0x26b004e0,
-        0xe21bf401,
-/* 0x03a4: init_unk_done */
-        0xb50703b5,
-        0x00820804,
-        0x22cf0201,
-        0x9534bd00,
-        0x00800825,
-        0x05f601c0,
-        0x8004bd00,
-        0xf601c100,
-        0x04bd0005,
-        0x98000e98,
-        0x207e010f,
-        0x2fbb0001,
-        0x003fbb00,
-        0x98010e98,
-        0x207e020f,
-        0x0e980001,
-        0x00effd05,
-        0xbb002ebb,
-        0x0e98003e,
-        0x030f9802,
-        0x0001207e,
-        0xfd070e98,
-        0x2ebb00ef,
-        0x003ebb00,
-        0x800235b6,
-        0xf601d300,
-        0x04bd0003,
-        0xb60825b6,
-        0x20b60635,
-        0x0130b601,
-        0xb60824b6,
-        0x2fb20834,
-        0x0002687e,
-        0xbb002fbb,
-        0x0080003f,
-        0x03f60201,
-        0xbd04bd00,
-        0x1f29f024,
-        0x02300080,
-        0xbd0002f6,
-/* 0x0445: main */
-        0x0031f404,
-        0x0d0028f4,
-        0x00377e24,
-        0xf401f400,
-        0xf404e4b0,
-        0x81fe1d18,
-        0xbd060201,
-        0x0412fd20,
-        0xfd01e4b6,
-        0x18fe051e,
-        0x05187e00,
-        0xd40ef400,
-/* 0x0474: main_not_ctx_xfer */
-        0xf010ef94,
-        0xf87e01f5,
-        0x0ef40002,
-/* 0x0481: ih */
-        0xfe80f9c7,
-        0x80f90188,
-        0xa0f990f9,
-        0xd0f9b0f9,
-        0xf0f9e0f9,
-        0x004a04bd,
-        0x00aacf02,
-        0xf404abc4,
-        0x240d1f0b,
-        0xcf1a004e,
-        0x004f00ee,
-        0x00ffcf19,
-        0x0000047e,
-        0x0040010e,
-        0x000ef61d,
-/* 0x04be: ih_no_fifo */
-        0x004004bd,
-        0x000af601,
-        0xf0fc04bd,
-        0xd0fce0fc,
-        0xa0fcb0fc,
-        0x80fc90fc,
-        0xfc0088fe,
-        0x0032f480,
-/* 0x04de: hub_barrier_done */
-        0x010f01f8,
-        0xbb040e98,
-        0xffb204fe,
-        0x4094188e,
-        0x00008f7e,
-/* 0x04f2: ctx_redswitch */
-        0x200f00f8,
+        0x01e5f050,
+        0x34bd24bd,
+/* 0x0386: init_unk_loop */
+        0x657e44bd,
+        0xf6b00000,
+        0x0e0bf400,
+        0xf2bb010f,
+        0x054ffd04,
+/* 0x039b: init_unk_next */
+        0xb60130b6,
+        0xe0b60120,
+        0x0126b004,
+/* 0x03a7: init_unk_done */
+        0xb5e21bf4,
+        0x04b50703,
+        0x01008208,
+        0x0022cf02,
+        0x259534bd,
+        0xc0008008,
+        0x0005f601,
+        0x008004bd,
+        0x05f601c1,
+        0x9804bd00,
+        0x0f98000e,
+        0x01207e01,
+        0x002fbb00,
+        0x98003fbb,
+        0x0f98010e,
+        0x01207e02,
+        0x050e9800,
+        0xbb00effd,
+        0x3ebb002e,
+        0x020e9800,
+        0x7e030f98,
+        0x98000120,
+        0xeffd070e,
+        0x002ebb00,
+        0xb6003ebb,
+        0x00800235,
+        0x03f601d3,
+        0xb604bd00,
+        0x35b60825,
+        0x0120b606,
+        0xb60130b6,
+        0x34b60824,
+        0x7e2fb208,
+        0xbb000268,
+        0x3fbb002f,
+        0x01008000,
+        0x0003f602,
+        0x24bd04bd,
+        0x801f29f0,
+        0xf6023000,
+        0x04bd0002,
+/* 0x0448: main */
+        0xf40031f4,
+        0x240d0028,
+        0x0000377e,
+        0xb0f401f4,
+        0x18f404e4,
+        0x0181fe1d,
+        0x20bd0602,
+        0xb60412fd,
+        0x1efd01e4,
+        0x0018fe05,
+        0x00051b7e,
+/* 0x0477: main_not_ctx_xfer */
+        0x94d40ef4,
+        0xf5f010ef,
+        0x02f87e01,
+        0xc70ef400,
+/* 0x0484: ih */
+        0x88fe80f9,
+        0xf980f901,
+        0xf9a0f990,
+        0xf9d0f9b0,
+        0xbdf0f9e0,
+        0x02004a04,
+        0xc400aacf,
+        0x0bf404ab,
+        0x4e240d1f,
+        0xeecf1a00,
+        0x19004f00,
+        0x7e00ffcf,
+        0x0e000004,
+        0x1d004001,
+        0xbd000ef6,
+/* 0x04c1: ih_no_fifo */
+        0x01004004,
+        0xbd000af6,
+        0xfcf0fc04,
+        0xfcd0fce0,
+        0xfca0fcb0,
+        0xfe80fc90,
+        0x80fc0088,
+        0xf80032f4,
+/* 0x04e1: hub_barrier_done */
+        0x98010f01,
+        0xfebb040e,
+        0x8effb204,
+        0x7e409418,
+        0xf800008f,
+/* 0x04f5: ctx_redswitch */
+        0x80200f00,
+        0xf6018500,
+        0x04bd000f,
+/* 0x0502: ctx_redswitch_delay */
+        0xe2b6080e,
+        0xfd1bf401,
+        0x0800f5f1,
+        0x0200f5f1,
         0x01850080,
         0xbd000ff6,
-/* 0x04ff: ctx_redswitch_delay */
-        0xb6080e04,
-        0x1bf401e2,
-        0x00f5f1fd,
-        0x00f5f108,
-        0x85008002,
-        0x000ff601,
-        0x00f804bd,
-/* 0x0518: ctx_xfer */
-        0x02810080,
-        0xbd000ff6,
-        0x0711f404,
-        0x0004f27e,
-/* 0x0528: ctx_xfer_not_load */
-        0x0002167e,
-        0xfc8024bd,
-        0x02f60247,
-        0xf004bd00,
-        0x20b6012c,
-        0x4afc8003,
+/* 0x051b: ctx_xfer */
+        0x8000f804,
+        0xf6028100,
+        0x04bd000f,
+        0x7e0711f4,
+/* 0x052b: ctx_xfer_not_load */
+        0x7e0004f5,
+        0xbd000216,
+        0x47fc8024,
         0x0002f602,
-        0xacf004bd,
-        0x02a5f001,
-        0x5000008b,
-        0xb6040c98,
-        0xbcbb0fc4,
-        0x000c9800,
-        0x0e010d98,
-        0x013d7e00,
-        0x01acf000,
-        0x5040008b,
-        0xb6040c98,
-        0xbcbb0fc4,
-        0x010c9800,
-        0x98020d98,
-        0x004e060f,
-        0x013d7e08,
-        0x01acf000,
-        0x8b04a5f0,
-        0x98503000,
+        0x2cf004bd,
+        0x0320b601,
+        0x024afc80,
+        0xbd0002f6,
+        0x01acf004,
+        0x8b02a5f0,
+        0x98500000,
         0xc4b6040c,
         0x00bcbb0f,
-        0x98020c98,
-        0x0f98030d,
-        0x02004e08,
+        0x98000c98,
+        0x000e010d,
         0x00013d7e,
-        0x00020a7e,
-        0xf40601f4,
-/* 0x05b2: ctx_xfer_post */
-        0x277e0712,
-/* 0x05b6: ctx_xfer_done */
-        0xde7e0002,
-        0x00f80004,
-        0x00000000,
+        0x8b01acf0,
+        0x98504000,
+        0xc4b6040c,
+        0x00bcbb0f,
+        0x98010c98,
+        0x0f98020d,
+        0x08004e06,
+        0x00013d7e,
+        0xf001acf0,
+        0x008b04a5,
+        0x0c985030,
+        0x0fc4b604,
+        0x9800bcbb,
+        0x0d98020c,
+        0x080f9803,
+        0x7e02004e,
+        0x7e00013d,
+        0xf400020a,
+        0x12f40601,
+/* 0x05b5: ctx_xfer_post */
+        0x02277e07,
+/* 0x05b9: ctx_xfer_done */
+        0x04e17e00,
+        0x0000f800,
         0x00000000,
         0x00000000,
         0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgm107.fuc5.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgm107.fuc5.h
index 51f5c3c6e966..11bf363a6ae9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgm107.fuc5.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/gpcgm107.fuc5.h
@@ -289,7 +289,7 @@ uint32_t gm107_grgpc_code[] = {
         0x020014fe,
         0x12004002,
         0xbd0002f6,
-        0x05b04104,
+        0x05b34104,
         0x400010fe,
         0x00f60700,
         0x0204bd00,
@@ -308,259 +308,259 @@ uint32_t gm107_grgpc_code[] = {
         0xc900800f,
         0x0002f601,
         0x308e04bd,
-        0x24bd500c,
-        0x44bd34bd,
-/* 0x03b0: init_unk_loop */
-        0x0000657e,
-        0xf400f6b0,
-        0x010f0e0b,
-        0xfd04f2bb,
-        0x30b6054f,
-/* 0x03c5: init_unk_next */
-        0x0120b601,
-        0xb004e0b6,
-        0x1bf40226,
-/* 0x03d1: init_unk_done */
-        0x0703b5e2,
-        0x820804b5,
-        0xcf020100,
-        0x34bd0022,
-        0x80082595,
-        0xf601c000,
+        0xe5f0500c,
+        0xbd24bd01,
+/* 0x03b3: init_unk_loop */
+        0x7e44bd34,
+        0xb0000065,
+        0x0bf400f6,
+        0xbb010f0e,
+        0x4ffd04f2,
+        0x0130b605,
+/* 0x03c8: init_unk_next */
+        0xb60120b6,
+        0x26b004e0,
+        0xe21bf402,
+/* 0x03d4: init_unk_done */
+        0xb50703b5,
+        0x00820804,
+        0x22cf0201,
+        0x9534bd00,
+        0x00800825,
+        0x05f601c0,
+        0x8004bd00,
+        0xf601c100,
         0x04bd0005,
-        0x01c10080,
-        0xbd0005f6,
-        0x000e9804,
-        0x7e010f98,
-        0xbb000120,
-        0x3fbb002f,
-        0x010e9800,
-        0x7e020f98,
-        0x98000120,
-        0xeffd050e,
-        0x002ebb00,
-        0x98003ebb,
-        0x0f98020e,
-        0x01207e03,
-        0x070e9800,
-        0xbb00effd,
-        0x3ebb002e,
-        0x0235b600,
-        0x01d30080,
-        0xbd0003f6,
-        0x0825b604,
-        0xb60635b6,
-        0x30b60120,
-        0x0824b601,
-        0xb20834b6,
-        0x02687e2f,
-        0x002fbb00,
-        0x0f003fbb,
-        0x8effb23f,
-        0xf0501d60,
-        0x8f7e01e5,
-        0x0c0f0000,
-        0xa88effb2,
-        0xe5f0501d,
-        0x008f7e01,
-        0x03147e00,
-        0xb23f0f00,
-        0x1d608eff,
-        0x01e5f050,
-        0x00008f7e,
-        0xffb2000f,
-        0x501d9c8e,
-        0x7e01e5f0,
-        0x0f00008f,
-        0x03147e01,
-        0x8effb200,
+        0x98000e98,
+        0x207e010f,
+        0x2fbb0001,
+        0x003fbb00,
+        0x98010e98,
+        0x207e020f,
+        0x0e980001,
+        0x00effd05,
+        0xbb002ebb,
+        0x0e98003e,
+        0x030f9802,
+        0x0001207e,
+        0xfd070e98,
+        0x2ebb00ef,
+        0x003ebb00,
+        0x800235b6,
+        0xf601d300,
+        0x04bd0003,
+        0xb60825b6,
+        0x20b60635,
+        0x0130b601,
+        0xb60824b6,
+        0x2fb20834,
+        0x0002687e,
+        0xbb002fbb,
+        0x3f0f003f,
+        0x501d608e,
+        0xb201e5f0,
+        0x008f7eff,
+        0x8e0c0f00,
         0xf0501da8,
-        0x8f7e01e5,
-        0xff0f0000,
-        0x988effb2,
+        0xffb201e5,
+        0x00008f7e,
+        0x0003147e,
+        0x608e3f0f,
         0xe5f0501d,
-        0x008f7e01,
-        0xb2020f00,
-        0x1da88eff,
+        0x7effb201,
+        0x0f00008f,
+        0x1d9c8e00,
         0x01e5f050,
-        0x00008f7e,
+        0x8f7effb2,
+        0x010f0000,
         0x0003147e,
-        0x85050498,
-        0x98504000,
-        0x64b60406,
-        0x0056bb0f,
-/* 0x04e0: tpc_strand_init_tpc_loop */
-        0x05705eb8,
-        0x00657e00,
-        0xbdf6b200,
-/* 0x04ed: tpc_strand_init_idx_loop */
-        0x605eb874,
-        0x7fb20005,
-        0x00008f7e,
-        0x05885eb8,
-        0x082f9500,
-        0x00008f7e,
-        0x058c5eb8,
-        0x082f9500,
+        0x501da88e,
+        0xb201e5f0,
+        0x008f7eff,
+        0x8eff0f00,
+        0xf0501d98,
+        0xffb201e5,
         0x00008f7e,
-        0x05905eb8,
-        0x00657e00,
-        0x06f5b600,
-        0xb601f0b6,
-        0x2fbb08f4,
-        0x003fbb00,
-        0xb60170b6,
-        0x1bf40162,
-        0x0050b7bf,
-        0x0142b608,
-        0x0fa81bf4,
-        0x8effb23f,
-        0xf0501d60,
-        0x8f7e01e5,
-        0x0d0f0000,
-        0xa88effb2,
+        0xa88e020f,
         0xe5f0501d,
-        0x008f7e01,
-        0x03147e00,
-        0x01008000,
-        0x0003f602,
-        0x24bd04bd,
-        0x801f29f0,
-        0xf6023000,
-        0x04bd0002,
-/* 0x0574: main */
-        0xf40031f4,
-        0x240d0028,
-        0x0000377e,
-        0xb0f401f4,
-        0x18f404e4,
-        0x0181fe1d,
-        0x20bd0602,
-        0xb60412fd,
-        0x1efd01e4,
-        0x0018fe05,
-        0x0006477e,
-/* 0x05a3: main_not_ctx_xfer */
-        0x94d40ef4,
-        0xf5f010ef,
-        0x02f87e01,
-        0xc70ef400,
-/* 0x05b0: ih */
-        0x88fe80f9,
-        0xf980f901,
-        0xf9a0f990,
-        0xf9d0f9b0,
-        0xbdf0f9e0,
-        0x02004a04,
-        0xc400aacf,
-        0x0bf404ab,
-        0x4e240d1f,
-        0xeecf1a00,
-        0x19004f00,
-        0x7e00ffcf,
-        0x0e000004,
-        0x1d004001,
-        0xbd000ef6,
-/* 0x05ed: ih_no_fifo */
-        0x01004004,
-        0xbd000af6,
-        0xfcf0fc04,
-        0xfcd0fce0,
-        0xfca0fcb0,
-        0xfe80fc90,
-        0x80fc0088,
-        0xf80032f4,
-/* 0x060d: hub_barrier_done */
-        0x98010f01,
-        0xfebb040e,
-        0x8effb204,
-        0x7e409418,
-        0xf800008f,
-/* 0x0621: ctx_redswitch */
-        0x80200f00,
+        0x7effb201,
+        0x7e00008f,
+        0x98000314,
+        0x00850504,
+        0x06985040,
+        0x0f64b604,
+/* 0x04e3: tpc_strand_init_tpc_loop */
+        0xb80056bb,
+        0x0005705e,
+        0x0000657e,
+        0x74bdf6b2,
+/* 0x04f0: tpc_strand_init_idx_loop */
+        0x05605eb8,
+        0x7e7fb200,
+        0xb800008f,
+        0x0005885e,
+        0x7e082f95,
+        0xb800008f,
+        0x00058c5e,
+        0x7e082f95,
+        0xb800008f,
+        0x0005905e,
+        0x0000657e,
+        0xb606f5b6,
+        0xf4b601f0,
+        0x002fbb08,
+        0xb6003fbb,
+        0x62b60170,
+        0xbf1bf401,
+        0x080050b7,
+        0xf40142b6,
+        0x3f0fa81b,
+        0x501d608e,
+        0xb201e5f0,
+        0x008f7eff,
+        0x8e0d0f00,
+        0xf0501da8,
+        0xffb201e5,
+        0x00008f7e,
+        0x0003147e,
+        0x02010080,
+        0xbd0003f6,
+        0xf024bd04,
+        0x00801f29,
+        0x02f60230,
+/* 0x0577: main */
+        0xf404bd00,
+        0x28f40031,
+        0x7e240d00,
+        0xf4000037,
+        0xe4b0f401,
+        0x1d18f404,
+        0x020181fe,
+        0xfd20bd06,
+        0xe4b60412,
+        0x051efd01,
+        0x7e0018fe,
+        0xf400064a,
+/* 0x05a6: main_not_ctx_xfer */
+        0xef94d40e,
+        0x01f5f010,
+        0x0002f87e,
+/* 0x05b3: ih */
+        0xf9c70ef4,
+        0x0188fe80,
+        0x90f980f9,
+        0xb0f9a0f9,
+        0xe0f9d0f9,
+        0x04bdf0f9,
+        0xcf02004a,
+        0xabc400aa,
+        0x1f0bf404,
+        0x004e240d,
+        0x00eecf1a,
+        0xcf19004f,
+        0x047e00ff,
+        0x010e0000,
+        0xf61d0040,
+        0x04bd000e,
+/* 0x05f0: ih_no_fifo */
+        0xf6010040,
+        0x04bd000a,
+        0xe0fcf0fc,
+        0xb0fcd0fc,
+        0x90fca0fc,
+        0x88fe80fc,
+        0xf480fc00,
+        0x01f80032,
+/* 0x0610: hub_barrier_done */
+        0x0e98010f,
+        0x04febb04,
+        0x188effb2,
+        0x8f7e4094,
+        0x00f80000,
+/* 0x0624: ctx_redswitch */
+        0x0080200f,
+        0x0ff60185,
+        0x0e04bd00,
+/* 0x0631: ctx_redswitch_delay */
+        0x01e2b608,
+        0xf1fd1bf4,
+        0xf10800f5,
+        0x800200f5,
         0xf6018500,
         0x04bd000f,
-/* 0x062e: ctx_redswitch_delay */
-        0xe2b6080e,
-        0xfd1bf401,
-        0x0800f5f1,
-        0x0200f5f1,
-        0x01850080,
-        0xbd000ff6,
-/* 0x0647: ctx_xfer */
-        0x8000f804,
-        0xf6028100,
-        0x04bd000f,
-        0xc48effb2,
-        0xe5f0501d,
-        0x008f7e01,
-        0x0711f400,
-        0x0006217e,
-/* 0x0664: ctx_xfer_not_load */
-        0x0002167e,
-        0xfc8024bd,
-        0x02f60247,
-        0xf004bd00,
-        0x20b6012c,
-        0x4afc8003,
+/* 0x064a: ctx_xfer */
+        0x008000f8,
+        0x0ff60281,
+        0x8e04bd00,
+        0xf0501dc4,
+        0xffb201e5,
+        0x00008f7e,
+        0x7e0711f4,
+/* 0x0667: ctx_xfer_not_load */
+        0x7e000624,
+        0xbd000216,
+        0x47fc8024,
         0x0002f602,
-        0x0c0f04bd,
-        0xa88effb2,
-        0xe5f0501d,
-        0x008f7e01,
-        0x03147e00,
-        0xb23f0f00,
-        0x1d608eff,
-        0x01e5f050,
+        0x2cf004bd,
+        0x0320b601,
+        0x024afc80,
+        0xbd0002f6,
+        0x8e0c0f04,
+        0xf0501da8,
+        0xffb201e5,
         0x00008f7e,
-        0xffb2000f,
-        0x501d9c8e,
-        0x7e01e5f0,
+        0x0003147e,
+        0x608e3f0f,
+        0xe5f0501d,
+        0x7effb201,
         0x0f00008f,
-        0x03147e01,
-        0x01fcf000,
-        0xb203f0b6,
-        0x1da88eff,
+        0x1d9c8e00,
         0x01e5f050,
-        0x00008f7e,
-        0xf001acf0,
-        0x008b02a5,
-        0x0c985000,
-        0x0fc4b604,
-        0x9800bcbb,
-        0x0d98000c,
-        0x7e000e01,
-        0xf000013d,
-        0x008b01ac,
-        0x0c985040,
-        0x0fc4b604,
-        0x9800bcbb,
-        0x0d98010c,
-        0x060f9802,
-        0x7e08004e,
-        0xf000013d,
+        0x8f7effb2,
+        0x010f0000,
+        0x0003147e,
+        0xb601fcf0,
+        0xa88e03f0,
+        0xe5f0501d,
+        0x7effb201,
+        0xf000008f,
         0xa5f001ac,
-        0x30008b04,
+        0x00008b02,
         0x040c9850,
         0xbb0fc4b6,
         0x0c9800bc,
-        0x030d9802,
-        0x4e080f98,
-        0x3d7e0200,
-        0x0a7e0001,
-        0x147e0002,
-        0x01f40003,
-        0x1a12f406,
-/* 0x073c: ctx_xfer_post */
-        0x0002277e,
-        0xffb20d0f,
-        0x501da88e,
-        0x7e01e5f0,
-        0x7e00008f,
-/* 0x0753: ctx_xfer_done */
-        0x7e000314,
-        0xf800060d,
-        0x00000000,
+        0x010d9800,
+        0x3d7e000e,
+        0xacf00001,
+        0x40008b01,
+        0x040c9850,
+        0xbb0fc4b6,
+        0x0c9800bc,
+        0x020d9801,
+        0x4e060f98,
+        0x3d7e0800,
+        0xacf00001,
+        0x04a5f001,
+        0x5030008b,
+        0xb6040c98,
+        0xbcbb0fc4,
+        0x020c9800,
+        0x98030d98,
+        0x004e080f,
+        0x013d7e02,
+        0x020a7e00,
+        0x03147e00,
+        0x0601f400,
+/* 0x073f: ctx_xfer_post */
+        0x7e1a12f4,
+        0x0f000227,
+        0x1da88e0d,
+        0x01e5f050,
+        0x8f7effb2,
+        0x147e0000,
+/* 0x0756: ctx_xfer_done */
+        0x107e0003,
+        0x00f80006,
         0x00000000,
         0x00000000,
         0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index dda7a7d224c9..9f5dfc85147a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -143,7 +143,7 @@ gf100_gr_zbc_depth_get(struct gf100_gr *gr, int format,
 static int
 gf100_fermi_mthd_zbc_color(struct nvkm_object *object, void *data, u32 size)
 {
-        struct gf100_gr *gr = (void *)object->engine;
+        struct gf100_gr *gr = gf100_gr(nvkm_gr(object->engine));
         union {
                 struct fermi_a_zbc_color_v0 v0;
         } *args = data;
@@ -189,7 +189,7 @@ gf100_fermi_mthd_zbc_color(struct nvkm_object *object, void *data, u32 size)
 static int
 gf100_fermi_mthd_zbc_depth(struct nvkm_object *object, void *data, u32 size)
 {
-        struct gf100_gr *gr = (void *)object->engine;
+        struct gf100_gr *gr = gf100_gr(nvkm_gr(object->engine));
         union {
                 struct fermi_a_zbc_depth_v0 v0;
         } *args = data;
@@ -1530,6 +1530,8 @@ gf100_gr_oneinit(struct nvkm_gr *base)
                 gr->ppc_nr[i]  = gr->func->ppc_nr;
                 for (j = 0; j < gr->ppc_nr[i]; j++) {
                         u8 mask = nvkm_rd32(device, GPC_UNIT(i, 0x0c30 + (j * 4)));
+                        if (mask)
+                                gr->ppc_mask[i] |= (1 << j);
                         gr->ppc_tpc_nr[i][j] = hweight8(mask);
                 }
         }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
index 4611961b1187..02e78b8d93f6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
@@ -97,6 +97,7 @@ struct gf100_gr {
         u8 tpc_nr[GPC_MAX];
         u8 tpc_total;
         u8 ppc_nr[GPC_MAX];
+        u8 ppc_mask[GPC_MAX];
         u8 ppc_tpc_nr[GPC_MAX][4];
 
         struct nvkm_memory *unk4188b4;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c
index 895ba74057d4..1d7dd38292b3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/base.c
@@ -97,7 +97,9 @@ static void *
 nvkm_instobj_dtor(struct nvkm_memory *memory)
 {
         struct nvkm_instobj *iobj = nvkm_instobj(memory);
+        spin_lock(&iobj->imem->lock);
         list_del(&iobj->head);
+        spin_unlock(&iobj->imem->lock);
         nvkm_memory_del(&iobj->parent);
         return iobj;
 }
@@ -190,7 +192,9 @@ nvkm_instobj_new(struct nvkm_instmem *imem, u32 size, u32 align, bool zero,
                 nvkm_memory_ctor(&nvkm_instobj_func_slow, &iobj->memory);
                 iobj->parent = memory;
                 iobj->imem = imem;
+                spin_lock(&iobj->imem->lock);
                 list_add_tail(&iobj->head, &imem->list);
+                spin_unlock(&iobj->imem->lock);
                 memory = &iobj->memory;
         }
 
@@ -309,5 +313,6 @@ nvkm_instmem_ctor(const struct nvkm_instmem_func *func,
 {
         nvkm_subdev_ctor(&nvkm_instmem, device, index, 0, &imem->subdev);
         imem->func = func;
+        spin_lock_init(&imem->lock);
         INIT_LIST_HEAD(&imem->list);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk104.c
index d942fa7b9f18..86f9f3b13f71 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk104.c
@@ -81,9 +81,7 @@ gk104_pmu_pgob(struct nvkm_pmu *pmu, bool enable)
         nvkm_mask(device, 0x000200, 0x00001000, 0x00001000);
         nvkm_rd32(device, 0x000200);
 
-        if ( nvkm_boolopt(device->cfgopt, "War00C800_0",
-            device->quirk ? device->quirk->War00C800_0 : false)) {
-                nvkm_info(&pmu->subdev, "hw bug workaround enabled\n");
+        if (nvkm_boolopt(device->cfgopt, "War00C800_0", true)) {
                 switch (device->chipset) {
                 case 0xe4:
                         magic(device, 0x04000000);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk104.c
index b61509e26ec9..b735173a18ff 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/volt/gk104.c
@@ -59,7 +59,7 @@ gk104_volt_set(struct nvkm_volt *base, u32 uv)
         duty = (uv - bios->base) * div / bios->pwm_range;
 
         nvkm_wr32(device, 0x20340, div);
-        nvkm_wr32(device, 0x20344, 0x8000000 | duty);
+        nvkm_wr32(device, 0x20344, 0x80000000 | duty);
 
         return 0;
 }
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 248953d2fdb7..f81fb2641097 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -4173,11 +4173,7 @@ void cik_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
         control |= ib->length_dw | (vm_id << 24);
 
         radeon_ring_write(ring, header);
-        radeon_ring_write(ring,
-#ifdef __BIG_ENDIAN
-                          (2 << 0) |
-#endif
-                          (ib->gpu_addr & 0xFFFFFFFC));
+        radeon_ring_write(ring, (ib->gpu_addr & 0xFFFFFFFC));
         radeon_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFFFF);
         radeon_ring_write(ring, control);
 }
@@ -8472,7 +8468,7 @@ restart_ih:
         if (queue_dp)
                 schedule_work(&rdev->dp_work);
         if (queue_hotplug)
-                schedule_work(&rdev->hotplug_work);
+                schedule_delayed_work(&rdev->hotplug_work, 0);
         if (queue_reset) {
                 rdev->needs_reset = true;
                 wake_up_all(&rdev->fence_queue);
@@ -9630,6 +9626,9 @@ static void dce8_program_watermarks(struct radeon_device *rdev,
                     (rdev->disp_priority == 2)) {
                         DRM_DEBUG_KMS("force priority to high\n");
                 }
+
+                /* Save number of lines the linebuffer leads before the scanout */
+                radeon_crtc->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
         }
 
         /* select wm A */
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 7f33767d7ed6..2ad462896896 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -2372,6 +2372,9 @@ static void evergreen_program_watermarks(struct radeon_device *rdev,
                 c.full = dfixed_div(c, a);
                 priority_b_mark = dfixed_trunc(c);
                 priority_b_cnt |= priority_b_mark & PRIORITY_MARK_MASK;
+
+                /* Save number of lines the linebuffer leads before the scanout */
+                radeon_crtc->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
         }
 
         /* select wm A */
@@ -5344,7 +5347,7 @@ restart_ih:
         if (queue_dp)
                 schedule_work(&rdev->dp_work);
         if (queue_hotplug)
-                schedule_work(&rdev->hotplug_work);
+                schedule_delayed_work(&rdev->hotplug_work, 0);
         if (queue_hdmi)
                 schedule_work(&rdev->audio_work);
         if (queue_thermal && rdev->pm.dpm_enabled)
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 238b13f045c1..9e7e2bf03b81 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -806,7 +806,7 @@ int r100_irq_process(struct radeon_device *rdev)
                 status = r100_irq_ack(rdev);
         }
         if (queue_hotplug)
-                schedule_work(&rdev->hotplug_work);
+                schedule_delayed_work(&rdev->hotplug_work, 0);
         if (rdev->msi_enabled) {
                 switch (rdev->family) {
                 case CHIP_RS400:
@@ -3217,6 +3217,9 @@ void r100_bandwidth_update(struct radeon_device *rdev)
         uint32_t pixel_bytes1 = 0;
         uint32_t pixel_bytes2 = 0;
 
+        /* Guess line buffer size to be 8192 pixels */
+        u32 lb_size = 8192;
+
         if (!rdev->mode_info.mode_config_initialized)
                 return;
 
@@ -3631,6 +3634,13 @@ void r100_bandwidth_update(struct radeon_device *rdev)
                 DRM_DEBUG_KMS("GRPH2_BUFFER_CNTL from to %x\n",
                           (unsigned int)RREG32(RADEON_GRPH2_BUFFER_CNTL));
         }
+
+        /* Save number of lines the linebuffer leads before the scanout */
+        if (mode1)
+            rdev->mode_info.crtcs[0]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode1->crtc_hdisplay);
+
+        if (mode2)
+            rdev->mode_info.crtcs[1]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode2->crtc_hdisplay);
 }
 
 int r100_ring_test(struct radeon_device *rdev, struct radeon_ring *ring)
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 4ea5b10ff5f4..cc2fdf0be37a 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -4276,7 +4276,7 @@ restart_ih:
                 WREG32(IH_RB_RPTR, rptr);
         }
         if (queue_hotplug)
-                schedule_work(&rdev->hotplug_work);
+                schedule_delayed_work(&rdev->hotplug_work, 0);
         if (queue_hdmi)
                 schedule_work(&rdev->audio_work);
         if (queue_thermal && rdev->pm.dpm_enabled)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index b6cbd816537e..87db64983ea8 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -2414,7 +2414,7 @@ struct radeon_device {
         struct r600_ih ih; /* r6/700 interrupt ring */
         struct radeon_rlc rlc;
         struct radeon_mec mec;
-        struct work_struct hotplug_work;
+        struct delayed_work hotplug_work;
         struct work_struct dp_work;
         struct work_struct audio_work;
         int num_crtc; /* number of crtcs */
diff --git a/drivers/gpu/drm/radeon/radeon_agp.c b/drivers/gpu/drm/radeon/radeon_agp.c
index fe994aac3b04..c77d349c561c 100644
--- a/drivers/gpu/drm/radeon/radeon_agp.c
+++ b/drivers/gpu/drm/radeon/radeon_agp.c
@@ -54,6 +54,9 @@ static struct radeon_agpmode_quirk radeon_agpmode_quirk_list[] = {
         /* Intel 82855PM host bridge / Mobility 9600 M10 RV350 Needs AGPMode 1 (lp #195051) */
         { PCI_VENDOR_ID_INTEL, 0x3340, PCI_VENDOR_ID_ATI, 0x4e50,
                 PCI_VENDOR_ID_IBM, 0x0550, 1},
+        /* Intel 82855PM host bridge / RV250/M9 GL [Mobility FireGL 9000/Radeon 9000] needs AGPMode 1 (Thinkpad T40p) */
+        { PCI_VENDOR_ID_INTEL, 0x3340, PCI_VENDOR_ID_ATI, 0x4c66,
+                PCI_VENDOR_ID_IBM, 0x054d, 1},
         /* Intel 82855PM host bridge / Mobility M7 needs AGPMode 1 */
         { PCI_VENDOR_ID_INTEL, 0x3340, PCI_VENDOR_ID_ATI, 0x4c57,
                 PCI_VENDOR_ID_IBM, 0x0530, 1},
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 5a2cafb4f1bc..340f3f549f29 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1234,13 +1234,32 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
         if (r < 0)
                 return connector_status_disconnected;
 
+        if (radeon_connector->detected_hpd_without_ddc) {
+                force = true;
+                radeon_connector->detected_hpd_without_ddc = false;
+        }
+
         if (!force && radeon_check_hpd_status_unchanged(connector)) {
                 ret = connector->status;
                 goto exit;
         }
 
-        if (radeon_connector->ddc_bus)
+        if (radeon_connector->ddc_bus) {
                 dret = radeon_ddc_probe(radeon_connector, false);
+
+                /* Sometimes the pins required for the DDC probe on DVI
+                 * connectors don't make contact at the same time that the ones
+                 * for HPD do. If the DDC probe fails even though we had an HPD
+                 * signal, try again later */
+                if (!dret && !force &&
+                    connector->status != connector_status_connected) {
+                        DRM_DEBUG_KMS("hpd detected without ddc, retrying in 1 second\n");
+                        radeon_connector->detected_hpd_without_ddc = true;
+                        schedule_delayed_work(&rdev->hotplug_work,
+                                              msecs_to_jiffies(1000));
+                        goto exit;
+                }
+        }
         if (dret) {
                 radeon_connector->detected_by_load = false;
                 radeon_connector_free_edid(connector);
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index a8d9927ed9eb..1eca0acac016 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -322,7 +322,9 @@ void radeon_crtc_handle_vblank(struct radeon_device *rdev, int crtc_id)
          * to complete in this vblank?
          */
         if (update_pending &&
-            (DRM_SCANOUTPOS_VALID & radeon_get_crtc_scanoutpos(rdev->ddev, crtc_id, 0,
+            (DRM_SCANOUTPOS_VALID & radeon_get_crtc_scanoutpos(rdev->ddev,
+                                                               crtc_id,
+                                                               USE_REAL_VBLANKSTART,
                                                                &vpos, &hpos, NULL, NULL,
                                                                &rdev->mode_info.crtcs[crtc_id]->base.hwmode)) &&
             ((vpos >= (99 * rdev->mode_info.crtcs[crtc_id]->base.hwmode.crtc_vdisplay)/100) ||
@@ -401,6 +403,8 @@ static void radeon_flip_work_func(struct work_struct *__work)
         struct drm_crtc *crtc = &radeon_crtc->base;
         unsigned long flags;
         int r;
+        int vpos, hpos, stat, min_udelay;
+        struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id];
 
         down_read(&rdev->exclusive_lock);
         if (work->fence) {
@@ -437,6 +441,41 @@ static void radeon_flip_work_func(struct work_struct *__work)
         /* set the proper interrupt */
         radeon_irq_kms_pflip_irq_get(rdev, radeon_crtc->crtc_id);
 
+        /* If this happens to execute within the "virtually extended" vblank
+         * interval before the start of the real vblank interval then it needs
+         * to delay programming the mmio flip until the real vblank is entered.
+         * This prevents completing a flip too early due to the way we fudge
+         * our vblank counter and vblank timestamps in order to work around the
+         * problem that the hw fires vblank interrupts before actual start of
+         * vblank (when line buffer refilling is done for a frame). It
+         * complements the fudging logic in radeon_get_crtc_scanoutpos() for
+         * timestamping and radeon_get_vblank_counter_kms() for vblank counts.
+         *
+         * In practice this won't execute very often unless on very fast
+         * machines because the time window for this to happen is very small.
+         */
+        for (;;) {
+                /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank
+                 * start in hpos, and to the "fudged earlier" vblank start in
+                 * vpos.
+                 */
+                stat = radeon_get_crtc_scanoutpos(rdev->ddev, work->crtc_id,
+                                                  GET_DISTANCE_TO_VBLANKSTART,
+                                                  &vpos, &hpos, NULL, NULL,
+                                                  &crtc->hwmode);
+
+                if ((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
+                    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE) ||
+                    !(vpos >= 0 && hpos <= 0))
+                        break;
+
+                /* Sleep at least until estimated real start of hw vblank */
+                spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+                min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5);
+                usleep_range(min_udelay, 2 * min_udelay);
+                spin_lock_irqsave(&crtc->dev->event_lock, flags);
+        };
+
         /* do the flip (mmio) */
         radeon_page_flip(rdev, radeon_crtc->crtc_id, work->base);
 
@@ -1768,6 +1807,15 @@ bool radeon_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
  * \param dev Device to query.
  * \param crtc Crtc to query.
  * \param flags Flags from caller (DRM_CALLED_FROM_VBLIRQ or 0).
+ *              For driver internal use only also supports these flags:
+ *
+ *              USE_REAL_VBLANKSTART to use the real start of vblank instead
+ *              of a fudged earlier start of vblank.
+ *
+ *              GET_DISTANCE_TO_VBLANKSTART to return distance to the
+ *              fudged earlier start of vblank in *vpos and the distance
+ *              to true start of vblank in *hpos.
+ *
  * \param *vpos Location where vertical scanout position should be stored.
  * \param *hpos Location where horizontal scanout position should go.
  * \param *stime Target location for timestamp taken immediately before
@@ -1911,10 +1959,40 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
                 vbl_end = 0;
         }
 
+        /* Called from driver internal vblank counter query code? */
+        if (flags & GET_DISTANCE_TO_VBLANKSTART) {
+            /* Caller wants distance from real vbl_start in *hpos */
+            *hpos = *vpos - vbl_start;
+        }
+
+        /* Fudge vblank to start a few scanlines earlier to handle the
+         * problem that vblank irqs fire a few scanlines before start
+         * of vblank. Some driver internal callers need the true vblank
+         * start to be used and signal this via the USE_REAL_VBLANKSTART flag.
+         *
+         * The cause of the "early" vblank irq is that the irq is triggered
+         * by the line buffer logic when the line buffer read position enters
+         * the vblank, whereas our crtc scanout position naturally lags the
+         * line buffer read position.
+         */
+        if (!(flags & USE_REAL_VBLANKSTART))
+                vbl_start -= rdev->mode_info.crtcs[pipe]->lb_vblank_lead_lines;
+
         /* Test scanout position against vblank region. */
         if ((*vpos < vbl_start) && (*vpos >= vbl_end))
                 in_vbl = false;
 
+        /* In vblank? */
+        if (in_vbl)
+            ret |= DRM_SCANOUTPOS_IN_VBLANK;
+
+        /* Called from driver internal vblank counter query code? */
+        if (flags & GET_DISTANCE_TO_VBLANKSTART) {
+                /* Caller wants distance from fudged earlier vbl_start */
+                *vpos -= vbl_start;
+                return ret;
+        }
+
         /* Check if inside vblank area and apply corrective offsets:
          * vpos will then be >=0 in video scanout area, but negative
          * within vblank area, counting down the number of lines until
@@ -1930,31 +2008,5 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
         /* Correct for shifted end of vbl at vbl_end. */
         *vpos = *vpos - vbl_end;
 
-        /* In vblank? */
-        if (in_vbl)
-                ret |= DRM_SCANOUTPOS_IN_VBLANK;
-
-        /* Is vpos outside nominal vblank area, but less than
-         * 1/100 of a frame height away from start of vblank?
-         * If so, assume this isn't a massively delayed vblank
-         * interrupt, but a vblank interrupt that fired a few
-         * microseconds before true start of vblank. Compensate
-         * by adding a full frame duration to the final timestamp.
-         * Happens, e.g., on ATI R500, R600.
-         *
-         * We only do this if DRM_CALLED_FROM_VBLIRQ.
-         */
-        if ((flags & DRM_CALLED_FROM_VBLIRQ) && !in_vbl) {
-                vbl_start = mode->crtc_vdisplay;
-                vtotal = mode->crtc_vtotal;
-
-                if (vbl_start - *vpos < vtotal / 100) {
-                        *vpos -= vtotal;
-
-                        /* Signal this correction as "applied". */
-                        ret |= 0x8;
-                }
-        }
-
         return ret;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index 171d3e43c30c..979f3bf65f2c 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -74,7 +74,7 @@ irqreturn_t radeon_driver_irq_handler_kms(int irq, void *arg)
 static void radeon_hotplug_work_func(struct work_struct *work)
 {
         struct radeon_device *rdev = container_of(work, struct radeon_device,
-                                                  hotplug_work);
+                                                  hotplug_work.work);
         struct drm_device *dev = rdev->ddev;
         struct drm_mode_config *mode_config = &dev->mode_config;
         struct drm_connector *connector;
@@ -302,7 +302,7 @@ int radeon_irq_kms_init(struct radeon_device *rdev)
                 }
         }
 
-        INIT_WORK(&rdev->hotplug_work, radeon_hotplug_work_func);
+        INIT_DELAYED_WORK(&rdev->hotplug_work, radeon_hotplug_work_func);
         INIT_WORK(&rdev->dp_work, radeon_dp_work_func);
         INIT_WORK(&rdev->audio_work, r600_audio_update_hdmi);
 
@@ -310,7 +310,7 @@ int radeon_irq_kms_init(struct radeon_device *rdev)
         r = drm_irq_install(rdev->ddev, rdev->ddev->pdev->irq);
         if (r) {
                 rdev->irq.installed = false;
-                flush_work(&rdev->hotplug_work);
+                flush_delayed_work(&rdev->hotplug_work);
                 return r;
         }
 
@@ -333,7 +333,7 @@ void radeon_irq_kms_fini(struct radeon_device *rdev)
                 rdev->irq.installed = false;
                 if (rdev->msi_enabled)
                         pci_disable_msi(rdev->pdev);
-                flush_work(&rdev->hotplug_work);
+                flush_delayed_work(&rdev->hotplug_work);
         }
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 0ec6fcca16d3..d290a8a09036 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -755,6 +755,8 @@ void radeon_driver_preclose_kms(struct drm_device *dev,
  */
 u32 radeon_get_vblank_counter_kms(struct drm_device *dev, int crtc)
 {
+        int vpos, hpos, stat;
+        u32 count;
         struct radeon_device *rdev = dev->dev_private;
 
         if (crtc < 0 || crtc >= rdev->num_crtc) {
@@ -762,7 +764,53 @@ u32 radeon_get_vblank_counter_kms(struct drm_device *dev, int crtc)
                 return -EINVAL;
         }
 
-        return radeon_get_vblank_counter(rdev, crtc);
+        /* The hw increments its frame counter at start of vsync, not at start
+         * of vblank, as is required by DRM core vblank counter handling.
+         * Cook the hw count here to make it appear to the caller as if it
+         * incremented at start of vblank. We measure distance to start of
+         * vblank in vpos. vpos therefore will be >= 0 between start of vblank
+         * and start of vsync, so vpos >= 0 means to bump the hw frame counter
+         * result by 1 to give the proper appearance to caller.
+         */
+        if (rdev->mode_info.crtcs[crtc]) {
+                /* Repeat readout if needed to provide stable result if
+                 * we cross start of vsync during the queries.
+                 */
+                do {
+                        count = radeon_get_vblank_counter(rdev, crtc);
+                        /* Ask radeon_get_crtc_scanoutpos to return vpos as
+                         * distance to start of vblank, instead of regular
+                         * vertical scanout pos.
+                         */
+                        stat = radeon_get_crtc_scanoutpos(
+                                dev, crtc, GET_DISTANCE_TO_VBLANKSTART,
+                                &vpos, &hpos, NULL, NULL,
+                                &rdev->mode_info.crtcs[crtc]->base.hwmode);
+                } while (count != radeon_get_vblank_counter(rdev, crtc));
+
+                if (((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
+                    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE))) {
+                        DRM_DEBUG_VBL("Query failed! stat %d\n", stat);
+                }
+                else {
+                        DRM_DEBUG_VBL("crtc %d: dist from vblank start %d\n",
+                                      crtc, vpos);
+
+                        /* Bump counter if we are at >= leading edge of vblank,
+                         * but before vsync where vpos would turn negative and
+                         * the hw counter really increments.
+                         */
+                        if (vpos >= 0)
+                                count++;
+                }
+        }
+        else {
+            /* Fallback to use value as is. */
+            count = radeon_get_vblank_counter(rdev, crtc);
+            DRM_DEBUG_VBL("NULL mode info! Returned count may be wrong.\n");
+        }
+
+        return count;
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 830e171c3a9e..bba112628b47 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -367,6 +367,7 @@ struct radeon_crtc {
         u32 line_time;
         u32 wm_low;
         u32 wm_high;
+        u32 lb_vblank_lead_lines;
         struct drm_display_mode hw_mode;
         enum radeon_output_csc output_csc;
 };
@@ -553,6 +554,7 @@ struct radeon_connector {
         void *con_priv;
         bool dac_load_detect;
         bool detected_by_load; /* if the connection status was determined by load */
+        bool detected_hpd_without_ddc; /* if an HPD signal was detected on DVI, but ddc probing failed */
         uint16_t connector_object_id;
         struct radeon_hpd hpd;
         struct radeon_router router;
@@ -686,6 +688,9 @@ struct atom_voltage_table
         struct atom_voltage_table_entry entries[MAX_VOLTAGE_ENTRIES];
 };
 
+/* Driver internal use only flags of radeon_get_crtc_scanoutpos() */
+#define USE_REAL_VBLANKSTART            (1 << 30)
+#define GET_DISTANCE_TO_VBLANKSTART     (1 << 31)
 
 extern void
 radeon_add_atom_connector(struct drm_device *dev,
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index f4f03dcc1530..59abebd6b5dc 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -1756,7 +1756,9 @@ static bool radeon_pm_in_vbl(struct radeon_device *rdev)
          */
         for (crtc = 0; (crtc < rdev->num_crtc) && in_vbl; crtc++) {
                 if (rdev->pm.active_crtcs & (1 << crtc)) {
-                        vbl_status = radeon_get_crtc_scanoutpos(rdev->ddev, crtc, 0,
+                        vbl_status = radeon_get_crtc_scanoutpos(rdev->ddev,
+                                                                crtc,
+                                                                USE_REAL_VBLANKSTART,
                                                                 &vpos, &hpos, NULL, NULL,
                                                                 &rdev->mode_info.crtcs[crtc]->base.hwmode);
                         if ((vbl_status & DRM_SCANOUTPOS_VALID) &&
diff --git a/drivers/gpu/drm/radeon/radeon_vce.c b/drivers/gpu/drm/radeon/radeon_vce.c
index 574f62bbd215..7eb1ae758906 100644
--- a/drivers/gpu/drm/radeon/radeon_vce.c
+++ b/drivers/gpu/drm/radeon/radeon_vce.c
@@ -361,31 +361,31 @@ int radeon_vce_get_create_msg(struct radeon_device *rdev, int ring,
 
         /* stitch together an VCE create msg */
         ib.length_dw = 0;
-        ib.ptr[ib.length_dw++] = 0x0000000c; /* len */
-        ib.ptr[ib.length_dw++] = 0x00000001; /* session cmd */
-        ib.ptr[ib.length_dw++] = handle;
-
-        ib.ptr[ib.length_dw++] = 0x00000030; /* len */
-        ib.ptr[ib.length_dw++] = 0x01000001; /* create cmd */
-        ib.ptr[ib.length_dw++] = 0x00000000;
-        ib.ptr[ib.length_dw++] = 0x00000042;
-        ib.ptr[ib.length_dw++] = 0x0000000a;
-        ib.ptr[ib.length_dw++] = 0x00000001;
-        ib.ptr[ib.length_dw++] = 0x00000080;
-        ib.ptr[ib.length_dw++] = 0x00000060;
-        ib.ptr[ib.length_dw++] = 0x00000100;
-        ib.ptr[ib.length_dw++] = 0x00000100;
-        ib.ptr[ib.length_dw++] = 0x0000000c;
-        ib.ptr[ib.length_dw++] = 0x00000000;
-
-        ib.ptr[ib.length_dw++] = 0x00000014; /* len */
-        ib.ptr[ib.length_dw++] = 0x05000005; /* feedback buffer */
-        ib.ptr[ib.length_dw++] = upper_32_bits(dummy);
-        ib.ptr[ib.length_dw++] = dummy;
-        ib.ptr[ib.length_dw++] = 0x00000001;
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x0000000c); /* len */
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000001); /* session cmd */
+        ib.ptr[ib.length_dw++] = cpu_to_le32(handle);
+
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000030); /* len */
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x01000001); /* create cmd */
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000000);
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000042);
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x0000000a);
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000001);
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000080);
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000060);
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000100);
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000100);
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x0000000c);
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000000);
+
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000014); /* len */
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x05000005); /* feedback buffer */
+        ib.ptr[ib.length_dw++] = cpu_to_le32(upper_32_bits(dummy));
+        ib.ptr[ib.length_dw++] = cpu_to_le32(dummy);
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000001);
 
         for (i = ib.length_dw; i < ib_size_dw; ++i)
-                ib.ptr[i] = 0x0;
+                ib.ptr[i] = cpu_to_le32(0x0);
 
         r = radeon_ib_schedule(rdev, &ib, NULL, false);
         if (r) {
@@ -428,21 +428,21 @@ int radeon_vce_get_destroy_msg(struct radeon_device *rdev, int ring,
 
         /* stitch together an VCE destroy msg */
         ib.length_dw = 0;
-        ib.ptr[ib.length_dw++] = 0x0000000c; /* len */
-        ib.ptr[ib.length_dw++] = 0x00000001; /* session cmd */
-        ib.ptr[ib.length_dw++] = handle;
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x0000000c); /* len */
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000001); /* session cmd */
+        ib.ptr[ib.length_dw++] = cpu_to_le32(handle);
 
-        ib.ptr[ib.length_dw++] = 0x00000014; /* len */
-        ib.ptr[ib.length_dw++] = 0x05000005; /* feedback buffer */
-        ib.ptr[ib.length_dw++] = upper_32_bits(dummy);
-        ib.ptr[ib.length_dw++] = dummy;
-        ib.ptr[ib.length_dw++] = 0x00000001;
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000014); /* len */
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x05000005); /* feedback buffer */
+        ib.ptr[ib.length_dw++] = cpu_to_le32(upper_32_bits(dummy));
+        ib.ptr[ib.length_dw++] = cpu_to_le32(dummy);
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000001);
 
-        ib.ptr[ib.length_dw++] = 0x00000008; /* len */
-        ib.ptr[ib.length_dw++] = 0x02000001; /* destroy cmd */
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x00000008); /* len */
+        ib.ptr[ib.length_dw++] = cpu_to_le32(0x02000001); /* destroy cmd */
 
         for (i = ib.length_dw; i < ib_size_dw; ++i)
-                ib.ptr[i] = 0x0;
+                ib.ptr[i] = cpu_to_le32(0x0);
 
         r = radeon_ib_schedule(rdev, &ib, NULL, false);
         if (r) {
@@ -699,12 +699,12 @@ bool radeon_vce_semaphore_emit(struct radeon_device *rdev,
 {
         uint64_t addr = semaphore->gpu_addr;
 
-        radeon_ring_write(ring, VCE_CMD_SEMAPHORE);
-        radeon_ring_write(ring, (addr >> 3) & 0x000FFFFF);
-        radeon_ring_write(ring, (addr >> 23) & 0x000FFFFF);
-        radeon_ring_write(ring, 0x01003000 | (emit_wait ? 1 : 0));
+        radeon_ring_write(ring, cpu_to_le32(VCE_CMD_SEMAPHORE));
+        radeon_ring_write(ring, cpu_to_le32((addr >> 3) & 0x000FFFFF));
+        radeon_ring_write(ring, cpu_to_le32((addr >> 23) & 0x000FFFFF));
+        radeon_ring_write(ring, cpu_to_le32(0x01003000 | (emit_wait ? 1 : 0)));
         if (!emit_wait)
-                radeon_ring_write(ring, VCE_CMD_END);
+                radeon_ring_write(ring, cpu_to_le32(VCE_CMD_END));
 
         return true;
 }
@@ -719,10 +719,10 @@ bool radeon_vce_semaphore_emit(struct radeon_device *rdev,
 void radeon_vce_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 {
         struct radeon_ring *ring = &rdev->ring[ib->ring];
-        radeon_ring_write(ring, VCE_CMD_IB);
-        radeon_ring_write(ring, ib->gpu_addr);
-        radeon_ring_write(ring, upper_32_bits(ib->gpu_addr));
-        radeon_ring_write(ring, ib->length_dw);
+        radeon_ring_write(ring, cpu_to_le32(VCE_CMD_IB));
+        radeon_ring_write(ring, cpu_to_le32(ib->gpu_addr));
+        radeon_ring_write(ring, cpu_to_le32(upper_32_bits(ib->gpu_addr)));
+        radeon_ring_write(ring, cpu_to_le32(ib->length_dw));
 }
 
 /**
@@ -738,12 +738,12 @@ void radeon_vce_fence_emit(struct radeon_device *rdev,
         struct radeon_ring *ring = &rdev->ring[fence->ring];
         uint64_t addr = rdev->fence_drv[fence->ring].gpu_addr;
 
-        radeon_ring_write(ring, VCE_CMD_FENCE);
-        radeon_ring_write(ring, addr);
-        radeon_ring_write(ring, upper_32_bits(addr));
-        radeon_ring_write(ring, fence->seq);
-        radeon_ring_write(ring, VCE_CMD_TRAP);
-        radeon_ring_write(ring, VCE_CMD_END);
+        radeon_ring_write(ring, cpu_to_le32(VCE_CMD_FENCE));
+        radeon_ring_write(ring, cpu_to_le32(addr));
+        radeon_ring_write(ring, cpu_to_le32(upper_32_bits(addr)));
+        radeon_ring_write(ring, cpu_to_le32(fence->seq));
+        radeon_ring_write(ring, cpu_to_le32(VCE_CMD_TRAP));
+        radeon_ring_write(ring, cpu_to_le32(VCE_CMD_END));
 }
 
 /**
@@ -765,7 +765,7 @@ int radeon_vce_ring_test(struct radeon_device *rdev, struct radeon_ring *ring)
                           ring->idx, r);
                 return r;
         }
-        radeon_ring_write(ring, VCE_CMD_END);
+        radeon_ring_write(ring, cpu_to_le32(VCE_CMD_END));
         radeon_ring_unlock_commit(rdev, ring, false);
 
         for (i = 0; i < rdev->usec_timeout; i++) {
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 97a904835759..6244f4e44e9a 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -813,7 +813,7 @@ int rs600_irq_process(struct radeon_device *rdev)
                 status = rs600_irq_ack(rdev);
         }
         if (queue_hotplug)
-                schedule_work(&rdev->hotplug_work);
+                schedule_delayed_work(&rdev->hotplug_work, 0);
         if (queue_hdmi)
                 schedule_work(&rdev->audio_work);
         if (rdev->msi_enabled) {
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 516ca27cfa12..6bc44c24e837 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -207,6 +207,9 @@ void rs690_line_buffer_adjust(struct radeon_device *rdev,
 {
         u32 tmp;
 
+        /* Guess line buffer size to be 8192 pixels */
+        u32 lb_size = 8192;
+
         /*
          * Line Buffer Setup
          * There is a single line buffer shared by both display controllers.
@@ -243,6 +246,13 @@ void rs690_line_buffer_adjust(struct radeon_device *rdev,
                 tmp |= V_006520_DC_LB_MEMORY_SPLIT_D1_1Q_D2_3Q;
         }
         WREG32(R_006520_DC_LB_MEMORY_SPLIT, tmp);
+
+        /* Save number of lines the linebuffer leads before the scanout */
+        if (mode1)
+                rdev->mode_info.crtcs[0]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode1->crtc_hdisplay);
+
+        if (mode2)
+                rdev->mode_info.crtcs[1]->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode2->crtc_hdisplay);
 }
 
 struct rs690_watermark {
diff --git a/drivers/gpu/drm/radeon/rv730_dpm.c b/drivers/gpu/drm/radeon/rv730_dpm.c
index 3f5e1cf138ba..d37ba2cb886e 100644
--- a/drivers/gpu/drm/radeon/rv730_dpm.c
+++ b/drivers/gpu/drm/radeon/rv730_dpm.c
@@ -464,7 +464,7 @@ void rv730_stop_dpm(struct radeon_device *rdev)
         result = rv770_send_msg_to_smc(rdev, PPSMC_MSG_TwoLevelsDisabled);
 
         if (result != PPSMC_Result_OK)
-                DRM_ERROR("Could not force DPM to low\n");
+                DRM_DEBUG("Could not force DPM to low\n");
 
         WREG32_P(GENERAL_PWRMGT, 0, ~GLOBAL_PWRMGT_EN);
 
diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c
index b9c770745a7a..e830c8935db0 100644
--- a/drivers/gpu/drm/radeon/rv770_dpm.c
+++ b/drivers/gpu/drm/radeon/rv770_dpm.c
@@ -193,7 +193,7 @@ void rv770_stop_dpm(struct radeon_device *rdev)
         result = rv770_send_msg_to_smc(rdev, PPSMC_MSG_TwoLevelsDisabled);
 
         if (result != PPSMC_Result_OK)
-                DRM_ERROR("Could not force DPM to low.\n");
+                DRM_DEBUG("Could not force DPM to low.\n");
 
         WREG32_P(GENERAL_PWRMGT, 0, ~GLOBAL_PWRMGT_EN);
 
@@ -1418,7 +1418,7 @@ int rv770_resume_smc(struct radeon_device *rdev)
 int rv770_set_sw_state(struct radeon_device *rdev)
 {
         if (rv770_send_msg_to_smc(rdev, PPSMC_MSG_SwitchToSwState) != PPSMC_Result_OK)
-                return -EINVAL;
+                DRM_DEBUG("rv770_set_sw_state failed\n");
         return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 07037e32dea3..f878d6962da5 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2376,6 +2376,9 @@ static void dce6_program_watermarks(struct radeon_device *rdev,
                 c.full = dfixed_div(c, a);
                 priority_b_mark = dfixed_trunc(c);
                 priority_b_cnt |= priority_b_mark & PRIORITY_MARK_MASK;
+
+                /* Save number of lines the linebuffer leads before the scanout */
+                radeon_crtc->lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
         }
 
         /* select wm A */
@@ -6848,7 +6851,7 @@ restart_ih:
         if (queue_dp)
                 schedule_work(&rdev->dp_work);
         if (queue_hotplug)
-                schedule_work(&rdev->hotplug_work);
+                schedule_delayed_work(&rdev->hotplug_work, 0);
         if (queue_thermal && rdev->pm.dpm_enabled)
                 schedule_work(&rdev->pm.dpm.thermal.work);
         rdev->ih.rptr = rptr;
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
index 8caea0a33dd8..d908321b94ce 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
@@ -67,6 +67,7 @@ static int rockchip_drm_gem_object_mmap(struct drm_gem_object *obj,
          * VM_PFNMAP flag that was set by drm_gem_mmap_obj()/drm_gem_mmap().
          */
         vma->vm_flags &= ~VM_PFNMAP;
+        vma->vm_pgoff = 0;
 
         ret = dma_mmap_attrs(drm->dev, vma, rk_obj->kvaddr, rk_obj->dma_addr,
                              obj->size, &rk_obj->dma_attrs);
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 5d8ae5e49c44..03c47eeadc81 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -374,6 +374,7 @@ static const struct of_device_id vop_driver_dt_match[] = {
           .data = &rk3288_vop },
         {},
 };
+MODULE_DEVICE_TABLE(of, vop_driver_dt_match);
 
 static inline void vop_writel(struct vop *vop, uint32_t offset, uint32_t v)
 {
@@ -959,8 +960,8 @@ static int vop_update_plane_event(struct drm_plane *plane,
         val = (dest.y2 - dest.y1 - 1) << 16;
         val |= (dest.x2 - dest.x1 - 1) & 0xffff;
         VOP_WIN_SET(vop, win, dsp_info, val);
-        val = (dsp_sty - 1) << 16;
-        val |= (dsp_stx - 1) & 0xffff;
+        val = dsp_sty << 16;
+        val |= dsp_stx & 0xffff;
         VOP_WIN_SET(vop, win, dsp_st, val);
         VOP_WIN_SET(vop, win, rb_swap, rb_swap);
 
@@ -1289,7 +1290,7 @@ static void vop_win_state_complete(struct vop_win *vop_win,
 
         if (state->event) {
                 spin_lock_irqsave(&drm->event_lock, flags);
-                drm_send_vblank_event(drm, -1, state->event);
+                drm_crtc_send_vblank_event(crtc, state->event);
                 spin_unlock_irqrestore(&drm->event_lock, flags);
         }
 
@@ -1575,32 +1576,25 @@ static int vop_initial(struct vop *vop)
                 return PTR_ERR(vop->dclk);
         }
 
-        ret = clk_prepare(vop->hclk);
-        if (ret < 0) {
-                dev_err(vop->dev, "failed to prepare hclk\n");
-                return ret;
-        }
-
         ret = clk_prepare(vop->dclk);
         if (ret < 0) {
                 dev_err(vop->dev, "failed to prepare dclk\n");
-                goto err_unprepare_hclk;
+                return ret;
         }
 
-        ret = clk_prepare(vop->aclk);
+        /* Enable both the hclk and aclk to setup the vop */
+        ret = clk_prepare_enable(vop->hclk);
         if (ret < 0) {
-                dev_err(vop->dev, "failed to prepare aclk\n");
+                dev_err(vop->dev, "failed to prepare/enable hclk\n");
                 goto err_unprepare_dclk;
         }
 
-        /*
-         * enable hclk, so that we can config vop register.
-         */
-        ret = clk_enable(vop->hclk);
+        ret = clk_prepare_enable(vop->aclk);
         if (ret < 0) {
-                dev_err(vop->dev, "failed to prepare aclk\n");
-                goto err_unprepare_aclk;
+                dev_err(vop->dev, "failed to prepare/enable aclk\n");
+                goto err_disable_hclk;
         }
+
         /*
          * do hclk_reset, reset all vop registers.
          */
@@ -1608,7 +1602,7 @@ static int vop_initial(struct vop *vop)
         if (IS_ERR(ahb_rst)) {
                 dev_err(vop->dev, "failed to get ahb reset\n");
                 ret = PTR_ERR(ahb_rst);
-                goto err_disable_hclk;
+                goto err_disable_aclk;
         }
         reset_control_assert(ahb_rst);
         usleep_range(10, 20);
@@ -1634,26 +1628,25 @@ static int vop_initial(struct vop *vop)
         if (IS_ERR(vop->dclk_rst)) {
                 dev_err(vop->dev, "failed to get dclk reset\n");
                 ret = PTR_ERR(vop->dclk_rst);
-                goto err_unprepare_aclk;
+                goto err_disable_aclk;
         }
         reset_control_assert(vop->dclk_rst);
         usleep_range(10, 20);
         reset_control_deassert(vop->dclk_rst);
 
         clk_disable(vop->hclk);
+        clk_disable(vop->aclk);
 
         vop->is_enabled = false;
 
         return 0;
 
+err_disable_aclk:
+        clk_disable_unprepare(vop->aclk);
 err_disable_hclk:
-        clk_disable(vop->hclk);
-err_unprepare_aclk:
-        clk_unprepare(vop->aclk);
+        clk_disable_unprepare(vop->hclk);
 err_unprepare_dclk:
         clk_unprepare(vop->dclk);
-err_unprepare_hclk:
-        clk_unprepare(vop->hclk);
         return ret;
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_lock.c b/drivers/gpu/drm/ttm/ttm_lock.c
index 6a954544727f..f154fb1929bd 100644
--- a/drivers/gpu/drm/ttm/ttm_lock.c
+++ b/drivers/gpu/drm/ttm/ttm_lock.c
@@ -180,7 +180,7 @@ int ttm_write_lock(struct ttm_lock *lock, bool interruptible)
                         spin_unlock(&lock->lock);
                 }
         } else
-                wait_event(lock->queue, __ttm_read_lock(lock));
+                wait_event(lock->queue, __ttm_write_lock(lock));
 
         return ret;
 }
diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c
index f545913a56c7..578fe0a9324c 100644
--- a/drivers/gpu/drm/virtio/virtgpu_display.c
+++ b/drivers/gpu/drm/virtio/virtgpu_display.c
@@ -412,7 +412,7 @@ static const struct drm_connector_funcs virtio_gpu_connector_funcs = {
         .save = virtio_gpu_conn_save,
         .restore = virtio_gpu_conn_restore,
         .detect = virtio_gpu_conn_detect,
-        .fill_modes = drm_helper_probe_single_connector_modes,
+        .fill_modes = drm_helper_probe_single_connector_modes_nomerge,
         .destroy = virtio_gpu_conn_destroy,
         .reset = drm_atomic_helper_connector_reset,
         .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index a09cf8529b9f..c49812b80dd0 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -1233,6 +1233,7 @@ static void vmw_master_drop(struct drm_device *dev,
 
         vmw_fp->locked_master = drm_master_get(file_priv->master);
         ret = ttm_vt_lock(&vmaster->lock, false, vmw_fp->tfile);
+        vmw_kms_legacy_hotspot_clear(dev_priv);
         if (unlikely((ret != 0))) {
                 DRM_ERROR("Unable to lock TTM at VT switch.\n");
                 drm_master_put(&vmw_fp->locked_master);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index a8ae9dfb83b7..469cdd520615 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -925,6 +925,7 @@ int vmw_kms_present(struct vmw_private *dev_priv,
                     uint32_t num_clips);
 int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
                                 struct drm_file *file_priv);
+void vmw_kms_legacy_hotspot_clear(struct vmw_private *dev_priv);
 
 int vmw_dumb_create(struct drm_file *file_priv,
                     struct drm_device *dev,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
index a8baf5f5e765..b6a0806b06bf 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
@@ -390,7 +390,7 @@ void *vmw_fifo_reserve_dx(struct vmw_private *dev_priv, uint32_t bytes,
         else if (ctx_id == SVGA3D_INVALID_ID)
                 ret = vmw_local_fifo_reserve(dev_priv, bytes);
         else {
-                WARN_ON("Command buffer has not been allocated.\n");
+                WARN(1, "Command buffer has not been allocated.\n");
                 ret = NULL;
         }
         if (IS_ERR_OR_NULL(ret)) {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 9fcd7f82995c..9b4bb9e74d73 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -133,13 +133,19 @@ void vmw_cursor_update_position(struct vmw_private *dev_priv,
         vmw_mmio_write(++count, fifo_mem + SVGA_FIFO_CURSOR_COUNT);
 }
 
-int vmw_du_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv,
-                           uint32_t handle, uint32_t width, uint32_t height)
+
+/*
+ * vmw_du_crtc_cursor_set2 - Driver cursor_set2 callback.
+ */
+int vmw_du_crtc_cursor_set2(struct drm_crtc *crtc, struct drm_file *file_priv,
+                            uint32_t handle, uint32_t width, uint32_t height,
+                            int32_t hot_x, int32_t hot_y)
 {
         struct vmw_private *dev_priv = vmw_priv(crtc->dev);
         struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
         struct vmw_surface *surface = NULL;
         struct vmw_dma_buffer *dmabuf = NULL;
+        s32 hotspot_x, hotspot_y;
         int ret;
 
         /*
@@ -151,6 +157,8 @@ int vmw_du_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv,
          */
         drm_modeset_unlock_crtc(crtc);
         drm_modeset_lock_all(dev_priv->dev);
+        hotspot_x = hot_x + du->hotspot_x;
+        hotspot_y = hot_y + du->hotspot_y;
 
         /* A lot of the code assumes this */
         if (handle && (width != 64 || height != 64)) {
@@ -187,31 +195,34 @@ int vmw_du_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv,
                 vmw_dmabuf_unreference(&du->cursor_dmabuf);
 
         /* setup new image */
+        ret = 0;
         if (surface) {
                 /* vmw_user_surface_lookup takes one reference */
                 du->cursor_surface = surface;
 
                 du->cursor_surface->snooper.crtc = crtc;
                 du->cursor_age = du->cursor_surface->snooper.age;
-                vmw_cursor_update_image(dev_priv, surface->snooper.image,
-                                        64, 64, du->hotspot_x, du->hotspot_y);
+                ret = vmw_cursor_update_image(dev_priv, surface->snooper.image,
+                                              64, 64, hotspot_x, hotspot_y);
         } else if (dmabuf) {
                 /* vmw_user_surface_lookup takes one reference */
                 du->cursor_dmabuf = dmabuf;
 
                 ret = vmw_cursor_update_dmabuf(dev_priv, dmabuf, width, height,
-                                               du->hotspot_x, du->hotspot_y);
+                                               hotspot_x, hotspot_y);
         } else {
                 vmw_cursor_update_position(dev_priv, false, 0, 0);
-                ret = 0;
                 goto out;
         }
 
-        vmw_cursor_update_position(dev_priv, true,
-                                   du->cursor_x + du->hotspot_x,
-                                   du->cursor_y + du->hotspot_y);
+        if (!ret) {
+                vmw_cursor_update_position(dev_priv, true,
+                                           du->cursor_x + hotspot_x,
+                                           du->cursor_y + hotspot_y);
+                du->core_hotspot_x = hot_x;
+                du->core_hotspot_y = hot_y;
+        }
 
-        ret = 0;
 out:
         drm_modeset_unlock_all(dev_priv->dev);
         drm_modeset_lock_crtc(crtc, crtc->cursor);
@@ -239,8 +250,10 @@ int vmw_du_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
         drm_modeset_lock_all(dev_priv->dev);
 
         vmw_cursor_update_position(dev_priv, shown,
-                                   du->cursor_x + du->hotspot_x,
-                                   du->cursor_y + du->hotspot_y);
+                                   du->cursor_x + du->hotspot_x +
+                                   du->core_hotspot_x,
+                                   du->cursor_y + du->hotspot_y +
+                                   du->core_hotspot_y);
 
         drm_modeset_unlock_all(dev_priv->dev);
         drm_modeset_lock_crtc(crtc, crtc->cursor);
@@ -334,6 +347,29 @@ err_unreserve:
         ttm_bo_unreserve(bo);
 }
 
+/**
+ * vmw_kms_legacy_hotspot_clear - Clear legacy hotspots
+ *
+ * @dev_priv: Pointer to the device private struct.
+ *
+ * Clears all legacy hotspots.
+ */
+void vmw_kms_legacy_hotspot_clear(struct vmw_private *dev_priv)
+{
+        struct drm_device *dev = dev_priv->dev;
+        struct vmw_display_unit *du;
+        struct drm_crtc *crtc;
+
+        drm_modeset_lock_all(dev);
+        drm_for_each_crtc(crtc, dev) {
+                du = vmw_crtc_to_du(crtc);
+
+                du->hotspot_x = 0;
+                du->hotspot_y = 0;
+        }
+        drm_modeset_unlock_all(dev);
+}
+
 void vmw_kms_cursor_post_execbuf(struct vmw_private *dev_priv)
 {
         struct drm_device *dev = dev_priv->dev;
@@ -351,7 +387,9 @@ void vmw_kms_cursor_post_execbuf(struct vmw_private *dev_priv)
                 du->cursor_age = du->cursor_surface->snooper.age;
                 vmw_cursor_update_image(dev_priv,
                                         du->cursor_surface->snooper.image,
-                                        64, 64, du->hotspot_x, du->hotspot_y);
+                                        64, 64,
+                                        du->hotspot_x + du->core_hotspot_x,
+                                        du->hotspot_y + du->core_hotspot_y);
         }
 
         mutex_unlock(&dev->mode_config.mutex);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
index 782df7ca9794..edd81503516d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
@@ -159,6 +159,8 @@ struct vmw_display_unit {
 
         int hotspot_x;
         int hotspot_y;
+        s32 core_hotspot_x;
+        s32 core_hotspot_y;
 
         unsigned unit;
 
@@ -193,8 +195,9 @@ void vmw_du_crtc_restore(struct drm_crtc *crtc);
 void vmw_du_crtc_gamma_set(struct drm_crtc *crtc,
                            u16 *r, u16 *g, u16 *b,
                            uint32_t start, uint32_t size);
-int vmw_du_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv,
-                           uint32_t handle, uint32_t width, uint32_t height);
+int vmw_du_crtc_cursor_set2(struct drm_crtc *crtc, struct drm_file *file_priv,
+                            uint32_t handle, uint32_t width, uint32_t height,
+                            int32_t hot_x, int32_t hot_y);
 int vmw_du_crtc_cursor_move(struct drm_crtc *crtc, int x, int y);
 int vmw_du_connector_dpms(struct drm_connector *connector, int mode);
 void vmw_du_connector_save(struct drm_connector *connector);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index bb63e4d795fa..52caecb4502e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -297,7 +297,7 @@ static int vmw_ldu_crtc_set_config(struct drm_mode_set *set)
 static struct drm_crtc_funcs vmw_legacy_crtc_funcs = {
         .save = vmw_du_crtc_save,
         .restore = vmw_du_crtc_restore,
-        .cursor_set = vmw_du_crtc_cursor_set,
+        .cursor_set2 = vmw_du_crtc_cursor_set2,
         .cursor_move = vmw_du_crtc_cursor_move,
         .gamma_set = vmw_du_crtc_gamma_set,
         .destroy = vmw_ldu_crtc_destroy,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
index b96d1ab610c5..13926ff192e3 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
@@ -533,7 +533,7 @@ out_no_fence:
 static struct drm_crtc_funcs vmw_screen_object_crtc_funcs = {
         .save = vmw_du_crtc_save,
         .restore = vmw_du_crtc_restore,
-        .cursor_set = vmw_du_crtc_cursor_set,
+        .cursor_set2 = vmw_du_crtc_cursor_set2,
         .cursor_move = vmw_du_crtc_cursor_move,
         .gamma_set = vmw_du_crtc_gamma_set,
         .destroy = vmw_sou_crtc_destroy,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index b1fc1c02792d..f823fc3efed7 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -1043,7 +1043,7 @@ out_finish:
 static struct drm_crtc_funcs vmw_stdu_crtc_funcs = {
         .save = vmw_du_crtc_save,
         .restore = vmw_du_crtc_restore,
-        .cursor_set = vmw_du_crtc_cursor_set,
+        .cursor_set2 = vmw_du_crtc_cursor_set2,
         .cursor_move = vmw_du_crtc_cursor_move,
         .gamma_set = vmw_du_crtc_gamma_set,
         .destroy = vmw_stdu_crtc_destroy,
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index ba47b30d28fa..f2e13eb8339f 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -28,6 +28,7 @@
 #include <linux/irqchip/chained_irq.h>
 #include <linux/irqdomain.h>
 #include <linux/of_device.h>
+#include <linux/of_graph.h>
 
 #include <drm/drm_fourcc.h>
 
@@ -993,12 +994,26 @@ static void platform_device_unregister_children(struct platform_device *pdev)
 struct ipu_platform_reg {
         struct ipu_client_platformdata pdata;
         const char *name;
-        int reg_offset;
 };
 
+/* These must be in the order of the corresponding device tree port nodes */
 static const struct ipu_platform_reg client_reg[] = {
         {
                 .pdata = {
+                        .csi = 0,
+                        .dma[0] = IPUV3_CHANNEL_CSI0,
+                        .dma[1] = -EINVAL,
+                },
+                .name = "imx-ipuv3-camera",
+        }, {
+                .pdata = {
+                        .csi = 1,
+                        .dma[0] = IPUV3_CHANNEL_CSI1,
+                        .dma[1] = -EINVAL,
+                },
+                .name = "imx-ipuv3-camera",
+        }, {
+                .pdata = {
                         .di = 0,
                         .dc = 5,
                         .dp = IPU_DP_FLOW_SYNC_BG,
@@ -1015,22 +1030,6 @@ static const struct ipu_platform_reg client_reg[] = {
                         .dma[1] = -EINVAL,
                 },
                 .name = "imx-ipuv3-crtc",
-        }, {
-                .pdata = {
-                        .csi = 0,
-                        .dma[0] = IPUV3_CHANNEL_CSI0,
-                        .dma[1] = -EINVAL,
-                },
-                .reg_offset = IPU_CM_CSI0_REG_OFS,
-                .name = "imx-ipuv3-camera",
-        }, {
-                .pdata = {
-                        .csi = 1,
-                        .dma[0] = IPUV3_CHANNEL_CSI1,
-                        .dma[1] = -EINVAL,
-                },
-                .reg_offset = IPU_CM_CSI1_REG_OFS,
-                .name = "imx-ipuv3-camera",
         },
 };
 
@@ -1051,22 +1050,30 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base)
         for (i = 0; i < ARRAY_SIZE(client_reg); i++) {
                 const struct ipu_platform_reg *reg = &client_reg[i];
                 struct platform_device *pdev;
-                struct resource res;
-
-                if (reg->reg_offset) {
-                        memset(&res, 0, sizeof(res));
-                        res.flags = IORESOURCE_MEM;
-                        res.start = ipu_base + ipu->devtype->cm_ofs + reg->reg_offset;
-                        res.end = res.start + PAGE_SIZE - 1;
-                        pdev = platform_device_register_resndata(dev, reg->name,
-                                id++, &res, 1, &reg->pdata, sizeof(reg->pdata));
-                } else {
-                        pdev = platform_device_register_data(dev, reg->name,
-                                id++, &reg->pdata, sizeof(reg->pdata));
+
+                pdev = platform_device_alloc(reg->name, id++);
+                if (!pdev) {
+                        ret = -ENOMEM;
+                        goto err_register;
+                }
+
+                pdev->dev.parent = dev;
+
+                /* Associate subdevice with the corresponding port node */
+                pdev->dev.of_node = of_graph_get_port_by_id(dev->of_node, i);
+                if (!pdev->dev.of_node) {
+                        dev_err(dev, "missing port@%d node in %s\n", i,
+                                dev->of_node->full_name);
+                        ret = -ENODEV;
+                        goto err_register;
                 }
 
-                if (IS_ERR(pdev)) {
-                        ret = PTR_ERR(pdev);
+                ret = platform_device_add_data(pdev, &reg->pdata,
+                                               sizeof(reg->pdata));
+                if (!ret)
+                        ret = platform_device_add(pdev);
+                if (ret) {
+                        platform_device_put(pdev);
                         goto err_register;
                 }
         }
diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c
index 3166e4bc4eb6..9abcaa53bd25 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -395,8 +395,10 @@ int vga_get(struct pci_dev *pdev, unsigned int rsrc, int interruptible)
                 set_current_state(interruptible ?
                                   TASK_INTERRUPTIBLE :
                                   TASK_UNINTERRUPTIBLE);
-                if (signal_pending(current)) {
-                        rc = -EINTR;
+                if (interruptible && signal_pending(current)) {
+                        __set_current_state(TASK_RUNNING);
+                        remove_wait_queue(&vga_wait_queue, &wait);
+                        rc = -ERESTARTSYS;
                         break;
                 }
                 schedule();
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index ac1feea51be3..8b78a7f1f779 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -316,11 +316,6 @@
 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001       0xa001
 
 #define USB_VENDOR_ID_ELAN              0x04f3
-#define USB_DEVICE_ID_ELAN_TOUCHSCREEN  0x0089
-#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B     0x009b
-#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_0103     0x0103
-#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_010c     0x010c
-#define USB_DEVICE_ID_ELAN_TOUCHSCREEN_016F     0x016f
 
 #define USB_VENDOR_ID_ELECOM            0x056e
 #define USB_DEVICE_ID_ELECOM_BM084      0x0061
@@ -609,6 +604,7 @@
 #define USB_DEVICE_ID_LOGITECH_HARMONY_FIRST  0xc110
 #define USB_DEVICE_ID_LOGITECH_HARMONY_LAST 0xc14f
 #define USB_DEVICE_ID_LOGITECH_HARMONY_PS3 0x0306
+#define USB_DEVICE_ID_LOGITECH_KEYBOARD_G710_PLUS 0xc24d
 #define USB_DEVICE_ID_LOGITECH_MOUSE_C01A       0xc01a
 #define USB_DEVICE_ID_LOGITECH_MOUSE_C05A       0xc05a
 #define USB_DEVICE_ID_LOGITECH_MOUSE_C06A       0xc06a
diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c
index c20ac76c0a8c..c690fae02cf8 100644
--- a/drivers/hid/hid-lg.c
+++ b/drivers/hid/hid-lg.c
@@ -665,8 +665,9 @@ static int lg_probe(struct hid_device *hdev, const struct hid_device_id *id)
         struct lg_drv_data *drv_data;
         int ret;
 
-        /* Only work with the 1st interface (G29 presents multiple) */
-        if (iface_num != 0) {
+        /* G29 only work with the 1st interface */
+        if ((hdev->product == USB_DEVICE_ID_LOGITECH_G29_WHEEL) &&
+            (iface_num != 0)) {
                 dbg_hid("%s: ignoring ifnum %d\n", __func__, iface_num);
                 return -ENODEV;
         }
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 94bb137abe32..7dd0953cd70f 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -72,11 +72,7 @@ static const struct hid_blacklist {
         { USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL },
         { USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET },
         { USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_WIIU, HID_QUIRK_MULTI_INPUT },
-        { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN, HID_QUIRK_ALWAYS_POLL },
-        { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_009B, HID_QUIRK_ALWAYS_POLL },
-        { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_0103, HID_QUIRK_ALWAYS_POLL },
-        { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_010c, HID_QUIRK_ALWAYS_POLL },
-        { USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ELAN_TOUCHSCREEN_016F, HID_QUIRK_ALWAYS_POLL },
+        { USB_VENDOR_ID_ELAN, HID_ANY_ID, HID_QUIRK_ALWAYS_POLL },
         { USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700, HID_QUIRK_NOGET },
         { USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER, HID_QUIRK_NO_INIT_REPORTS },
         { USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET },
@@ -84,6 +80,7 @@ static const struct hid_blacklist {
         { USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0B4A, HID_QUIRK_ALWAYS_POLL },
         { USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL },
         { USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_C077, HID_QUIRK_ALWAYS_POLL },
+        { USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_KEYBOARD_G710_PLUS, HID_QUIRK_NOGET },
         { USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C01A, HID_QUIRK_ALWAYS_POLL },
         { USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C05A, HID_QUIRK_ALWAYS_POLL },
         { USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C06A, HID_QUIRK_ALWAYS_POLL },
@@ -339,7 +336,8 @@ static const struct hid_blacklist *usbhid_exists_squirk(const u16 idVendor,
 
         for (; hid_blacklist[n].idVendor; n++)
                 if (hid_blacklist[n].idVendor == idVendor &&
-                                hid_blacklist[n].idProduct == idProduct)
+                        (hid_blacklist[n].idProduct == (__u16) HID_ANY_ID ||
+                                hid_blacklist[n].idProduct == idProduct))
                         bl_entry = &hid_blacklist[n];
 
         if (bl_entry != NULL)
diff --git a/drivers/iio/adc/qcom-spmi-vadc.c b/drivers/iio/adc/qcom-spmi-vadc.c
index 0c4618b4d515..c2babe50a0d8 100644
--- a/drivers/iio/adc/qcom-spmi-vadc.c
+++ b/drivers/iio/adc/qcom-spmi-vadc.c
@@ -839,8 +839,10 @@ static int vadc_get_dt_data(struct vadc_priv *vadc, struct device_node *node)
 
         for_each_available_child_of_node(node, child) {
                 ret = vadc_get_dt_channel_data(vadc->dev, &prop, child);
-                if (ret)
+                if (ret) {
+                        of_node_put(child);
                         return ret;
+                }
 
                 vadc->chan_props[index] = prop;
 
diff --git a/drivers/iio/dummy/iio_simple_dummy_events.c b/drivers/iio/dummy/iio_simple_dummy_events.c
index bfbf1c56bd22..6eb600ff7056 100644
--- a/drivers/iio/dummy/iio_simple_dummy_events.c
+++ b/drivers/iio/dummy/iio_simple_dummy_events.c
@@ -159,7 +159,7 @@ static irqreturn_t iio_simple_dummy_get_timestamp(int irq, void *private)
         struct iio_dummy_state *st = iio_priv(indio_dev);
 
         st->event_timestamp = iio_get_time_ns();
-        return IRQ_HANDLED;
+        return IRQ_WAKE_THREAD;
 }
 
 /**
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index a4b164a478c4..139ae916225f 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -303,7 +303,7 @@ static int iio_scan_mask_set(struct iio_dev *indio_dev,
         if (trialmask == NULL)
                 return -ENOMEM;
         if (!indio_dev->masklength) {
-                WARN_ON("Trying to set scanmask prior to registering buffer\n");
+                WARN(1, "Trying to set scanmask prior to registering buffer\n");
                 goto err_invalid_mask;
         }
         bitmap_copy(trialmask, buffer->scan_mask, indio_dev->masklength);
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index d0a84febd435..8966f85ca4cd 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -664,7 +664,7 @@ int __iio_device_attr_init(struct device_attribute *dev_attr,
                         break;
                 case IIO_SEPARATE:
                         if (!chan->indexed) {
-                                WARN_ON("Differential channels must be indexed\n");
+                                WARN(1, "Differential channels must be indexed\n");
                                 ret = -EINVAL;
                                 goto error_free_full_postfix;
                         }
diff --git a/drivers/iio/light/apds9960.c b/drivers/iio/light/apds9960.c
index 7d269ef9e062..f6a07dc32ae4 100644
--- a/drivers/iio/light/apds9960.c
+++ b/drivers/iio/light/apds9960.c
@@ -453,6 +453,7 @@ static int apds9960_set_power_state(struct apds9960_data *data, bool on)
                         usleep_range(data->als_adc_int_us,
                                      APDS9960_MAX_INT_TIME_IN_US);
         } else {
+                pm_runtime_mark_last_busy(dev);
                 ret = pm_runtime_put_autosuspend(dev);
         }
 
diff --git a/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c b/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c
index be8ccef735f8..29ac262f591b 100644
--- a/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c
+++ b/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c
@@ -140,10 +140,10 @@ static int lidar_get_measurement(struct lidar_data *data, u16 *reg)
                 if (ret < 0)
                         break;
 
-                /* return 0 since laser is likely pointed out of range */
+                /* return -EINVAL since laser is likely pointed out of range */
                 if (ret & LIDAR_REG_STATUS_INVALID) {
                         *reg = 0;
-                        ret = 0;
+                        ret = -EINVAL;
                         break;
                 }
 
@@ -209,7 +209,7 @@ static irqreturn_t lidar_trigger_handler(int irq, void *private)
         if (!ret) {
                 iio_push_to_buffers_with_timestamp(indio_dev, data->buffer,
                                                    iio_get_time_ns());
-        } else {
+        } else if (ret != -EINVAL) {
                 dev_err(&data->client->dev, "cannot read LIDAR measurement");
         }
 
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 944cd90417bc..d2d5d004f16d 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1126,10 +1126,7 @@ static bool validate_ipv4_net_dev(struct net_device *net_dev,
 
         rcu_read_lock();
         err = fib_lookup(dev_net(net_dev), &fl4, &res, 0);
-        if (err)
-                return false;
-
-        ret = FIB_RES_DEV(res) == net_dev;
+        ret = err == 0 && FIB_RES_DEV(res) == net_dev;
         rcu_read_unlock();
 
         return ret;
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index 8d8af7a41a30..2281de122038 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -1811,6 +1811,11 @@ static int validate_mad(const struct ib_mad_hdr *mad_hdr,
                 if (qp_num == 0)
                         valid = 1;
         } else {
+                /* CM attributes other than ClassPortInfo only use Send method */
+                if ((mad_hdr->mgmt_class == IB_MGMT_CLASS_CM) &&
+                    (mad_hdr->attr_id != IB_MGMT_CLASSPORTINFO_ATTR_ID) &&
+                    (mad_hdr->method != IB_MGMT_METHOD_SEND))
+                        goto out;
                 /* Filter GSI packets sent to QP0 */
                 if (qp_num != 0)
                         valid = 1;
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 2aba774f835b..a95a32ba596e 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -512,7 +512,7 @@ static int ib_nl_get_path_rec_attrs_len(ib_sa_comp_mask comp_mask)
         return len;
 }
 
-static int ib_nl_send_msg(struct ib_sa_query *query)
+static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask)
 {
         struct sk_buff *skb = NULL;
         struct nlmsghdr *nlh;
@@ -526,7 +526,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query)
         if (len <= 0)
                 return -EMSGSIZE;
 
-        skb = nlmsg_new(len, GFP_KERNEL);
+        skb = nlmsg_new(len, gfp_mask);
         if (!skb)
                 return -ENOMEM;
 
@@ -544,7 +544,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query)
         /* Repair the nlmsg header length */
         nlmsg_end(skb, nlh);
 
-        ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, GFP_KERNEL);
+        ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, gfp_mask);
         if (!ret)
                 ret = len;
         else
@@ -553,7 +553,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query)
         return ret;
 }
 
-static int ib_nl_make_request(struct ib_sa_query *query)
+static int ib_nl_make_request(struct ib_sa_query *query, gfp_t gfp_mask)
 {
         unsigned long flags;
         unsigned long delay;
@@ -562,25 +562,27 @@ static int ib_nl_make_request(struct ib_sa_query *query)
         INIT_LIST_HEAD(&query->list);
         query->seq = (u32)atomic_inc_return(&ib_nl_sa_request_seq);
 
+        /* Put the request on the list first.*/
         spin_lock_irqsave(&ib_nl_request_lock, flags);
-        ret = ib_nl_send_msg(query);
-        if (ret <= 0) {
-                ret = -EIO;
-                goto request_out;
-        } else {
-                ret = 0;
-        }
-
         delay = msecs_to_jiffies(sa_local_svc_timeout_ms);
         query->timeout = delay + jiffies;
         list_add_tail(&query->list, &ib_nl_request_list);
         /* Start the timeout if this is the only request */
         if (ib_nl_request_list.next == &query->list)
                 queue_delayed_work(ib_nl_wq, &ib_nl_timed_work, delay);
-
-request_out:
         spin_unlock_irqrestore(&ib_nl_request_lock, flags);
 
+        ret = ib_nl_send_msg(query, gfp_mask);
+        if (ret <= 0) {
+                ret = -EIO;
+                /* Remove the request */
+                spin_lock_irqsave(&ib_nl_request_lock, flags);
+                list_del(&query->list);
+                spin_unlock_irqrestore(&ib_nl_request_lock, flags);
+        } else {
+                ret = 0;
+        }
+
         return ret;
 }
 
@@ -1108,7 +1110,7 @@ static int send_mad(struct ib_sa_query *query, int timeout_ms, gfp_t gfp_mask)
 
         if (query->flags & IB_SA_ENABLE_LOCAL_SERVICE) {
                 if (!ibnl_chk_listeners(RDMA_NL_GROUP_LS)) {
-                        if (!ib_nl_make_request(query))
+                        if (!ib_nl_make_request(query, gfp_mask))
                                 return id;
                 }
                 ib_sa_disable_local_svc(query);
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 94816aeb95a0..1c02deab068f 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -62,9 +62,11 @@ static struct uverbs_lock_class rule_lock_class = { .name = "RULE-uobj" };
  * The ib_uobject locking scheme is as follows:
  *
  * - ib_uverbs_idr_lock protects the uverbs idrs themselves, so it
- *   needs to be held during all idr operations.  When an object is
+ *   needs to be held during all idr write operations.  When an object is
  *   looked up, a reference must be taken on the object's kref before
- *   dropping this lock.
+ *   dropping this lock.  For read operations, the rcu_read_lock()
+ *   and rcu_write_lock() but similarly the kref reference is grabbed
+ *   before the rcu_read_unlock().
  *
  * - Each object also has an rwsem.  This rwsem must be held for
  *   reading while an operation that uses the object is performed.
@@ -96,7 +98,7 @@ static void init_uobj(struct ib_uobject *uobj, u64 user_handle,
 
 static void release_uobj(struct kref *kref)
 {
-        kfree(container_of(kref, struct ib_uobject, ref));
+        kfree_rcu(container_of(kref, struct ib_uobject, ref), rcu);
 }
 
 static void put_uobj(struct ib_uobject *uobj)
@@ -145,7 +147,7 @@ static struct ib_uobject *__idr_get_uobj(struct idr *idr, int id,
 {
         struct ib_uobject *uobj;
 
-        spin_lock(&ib_uverbs_idr_lock);
+        rcu_read_lock();
         uobj = idr_find(idr, id);
         if (uobj) {
                 if (uobj->context == context)
@@ -153,7 +155,7 @@ static struct ib_uobject *__idr_get_uobj(struct idr *idr, int id,
                 else
                         uobj = NULL;
         }
-        spin_unlock(&ib_uverbs_idr_lock);
+        rcu_read_unlock();
 
         return uobj;
 }
@@ -2446,6 +2448,7 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file,
         int                             i, sg_ind;
         int                             is_ud;
         ssize_t                         ret = -EINVAL;
+        size_t                          next_size;
 
         if (copy_from_user(&cmd, buf, sizeof cmd))
                 return -EFAULT;
@@ -2490,7 +2493,8 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file,
                                 goto out_put;
                         }
 
-                        ud = alloc_wr(sizeof(*ud), user_wr->num_sge);
+                        next_size = sizeof(*ud);
+                        ud = alloc_wr(next_size, user_wr->num_sge);
                         if (!ud) {
                                 ret = -ENOMEM;
                                 goto out_put;
@@ -2511,7 +2515,8 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file,
                            user_wr->opcode == IB_WR_RDMA_READ) {
                         struct ib_rdma_wr *rdma;
 
-                        rdma = alloc_wr(sizeof(*rdma), user_wr->num_sge);
+                        next_size = sizeof(*rdma);
+                        rdma = alloc_wr(next_size, user_wr->num_sge);
                         if (!rdma) {
                                 ret = -ENOMEM;
                                 goto out_put;
@@ -2525,7 +2530,8 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file,
                            user_wr->opcode == IB_WR_ATOMIC_FETCH_AND_ADD) {
                         struct ib_atomic_wr *atomic;
 
-                        atomic = alloc_wr(sizeof(*atomic), user_wr->num_sge);
+                        next_size = sizeof(*atomic);
+                        atomic = alloc_wr(next_size, user_wr->num_sge);
                         if (!atomic) {
                                 ret = -ENOMEM;
                                 goto out_put;
@@ -2540,7 +2546,8 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file,
                 } else if (user_wr->opcode == IB_WR_SEND ||
                            user_wr->opcode == IB_WR_SEND_WITH_IMM ||
                            user_wr->opcode == IB_WR_SEND_WITH_INV) {
-                        next = alloc_wr(sizeof(*next), user_wr->num_sge);
+                        next_size = sizeof(*next);
+                        next = alloc_wr(next_size, user_wr->num_sge);
                         if (!next) {
                                 ret = -ENOMEM;
                                 goto out_put;
@@ -2572,7 +2579,7 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file,
 
                 if (next->num_sge) {
                         next->sg_list = (void *) next +
-                                ALIGN(sizeof *next, sizeof (struct ib_sge));
+                                ALIGN(next_size, sizeof(struct ib_sge));
                         if (copy_from_user(next->sg_list,
                                            buf + sizeof cmd +
                                            cmd.wr_count * cmd.wqe_size +
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 043a60ee6836..545906dec26d 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1516,7 +1516,7 @@ EXPORT_SYMBOL(ib_map_mr_sg);
  * @sg_nents:      number of entries in sg
  * @set_page:      driver page assignment function pointer
  *
- * Core service helper for drivers to covert the largest
+ * Core service helper for drivers to convert the largest
  * prefix of given sg list to a page vector. The sg list
  * prefix converted is the prefix that meet the requirements
  * of ib_map_mr_sg.
@@ -1533,7 +1533,7 @@ int ib_sg_to_pages(struct ib_mr *mr,
         u64 last_end_dma_addr = 0, last_page_addr = 0;
         unsigned int last_page_off = 0;
         u64 page_mask = ~((u64)mr->page_size - 1);
-        int i;
+        int i, ret;
 
         mr->iova = sg_dma_address(&sgl[0]);
         mr->length = 0;
@@ -1544,27 +1544,29 @@ int ib_sg_to_pages(struct ib_mr *mr,
                 u64 end_dma_addr = dma_addr + dma_len;
                 u64 page_addr = dma_addr & page_mask;
 
-                if (i && page_addr != dma_addr) {
-                        if (last_end_dma_addr != dma_addr) {
-                                /* gap */
-                                goto done;
-
-                        } else if (last_page_off + dma_len <= mr->page_size) {
-                                /* chunk this fragment with the last */
-                                mr->length += dma_len;
-                                last_end_dma_addr += dma_len;
-                                last_page_off += dma_len;
-                                continue;
-                        } else {
-                                /* map starting from the next page */
-                                page_addr = last_page_addr + mr->page_size;
-                                dma_len -= mr->page_size - last_page_off;
-                        }
+                /*
+                 * For the second and later elements, check whether either the
+                 * end of element i-1 or the start of element i is not aligned
+                 * on a page boundary.
+                 */
+                if (i && (last_page_off != 0 || page_addr != dma_addr)) {
+                        /* Stop mapping if there is a gap. */
+                        if (last_end_dma_addr != dma_addr)
+                                break;
+
+                        /*
+                         * Coalesce this element with the last. If it is small
+                         * enough just update mr->length. Otherwise start
+                         * mapping from the next page.
+                         */
+                        goto next_page;
                 }
 
                 do {
-                        if (unlikely(set_page(mr, page_addr)))
-                                goto done;
+                        ret = set_page(mr, page_addr);
+                        if (unlikely(ret < 0))
+                                return i ? : ret;
+next_page:
                         page_addr += mr->page_size;
                 } while (page_addr < end_dma_addr);
 
@@ -1574,7 +1576,6 @@ int ib_sg_to_pages(struct ib_mr *mr,
                 last_page_off = end_dma_addr & ~page_mask;
         }
 
-done:
         return i;
 }
 EXPORT_SYMBOL(ib_sg_to_pages);
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index f567160a4a56..97d6878f9938 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -456,7 +456,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
         props->max_qp_wr           = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE;
         props->max_sge             = min(dev->dev->caps.max_sq_sg,
                                          dev->dev->caps.max_rq_sg);
-        props->max_sge_rd = props->max_sge;
+        props->max_sge_rd          = MLX4_MAX_SGE_RD;
         props->max_cq              = dev->dev->quotas.cq;
         props->max_cqe             = dev->dev->caps.max_cqes;
         props->max_mr              = dev->dev->quotas.mpt;
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index a2e4ca56da44..13eaaf45288f 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -34,6 +34,7 @@
 #include <linux/log2.h>
 #include <linux/slab.h>
 #include <linux/netdevice.h>
+#include <linux/vmalloc.h>
 
 #include <rdma/ib_cache.h>
 #include <rdma/ib_pack.h>
@@ -795,8 +796,14 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
                 if (err)
                         goto err_mtt;
 
-                qp->sq.wrid  = kmalloc(qp->sq.wqe_cnt * sizeof (u64), gfp);
-                qp->rq.wrid  = kmalloc(qp->rq.wqe_cnt * sizeof (u64), gfp);
+                qp->sq.wrid = kmalloc(qp->sq.wqe_cnt * sizeof(u64), gfp);
+                if (!qp->sq.wrid)
+                        qp->sq.wrid = __vmalloc(qp->sq.wqe_cnt * sizeof(u64),
+                                                gfp, PAGE_KERNEL);
+                qp->rq.wrid = kmalloc(qp->rq.wqe_cnt * sizeof(u64), gfp);
+                if (!qp->rq.wrid)
+                        qp->rq.wrid = __vmalloc(qp->rq.wqe_cnt * sizeof(u64),
+                                                gfp, PAGE_KERNEL);
                 if (!qp->sq.wrid || !qp->rq.wrid) {
                         err = -ENOMEM;
                         goto err_wrid;
@@ -886,8 +893,8 @@ err_wrid:
                 if (qp_has_rq(init_attr))
                         mlx4_ib_db_unmap_user(to_mucontext(pd->uobject->context), &qp->db);
         } else {
-                kfree(qp->sq.wrid);
-                kfree(qp->rq.wrid);
+                kvfree(qp->sq.wrid);
+                kvfree(qp->rq.wrid);
         }
 
 err_mtt:
@@ -1062,8 +1069,8 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
                                               &qp->db);
                 ib_umem_release(qp->umem);
         } else {
-                kfree(qp->sq.wrid);
-                kfree(qp->rq.wrid);
+                kvfree(qp->sq.wrid);
+                kvfree(qp->rq.wrid);
                 if (qp->mlx4_ib_qp_type & (MLX4_IB_QPT_PROXY_SMI_OWNER |
                     MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI))
                         free_proxy_bufs(&dev->ib_dev, qp);
diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c
index dce5dfe3a70e..8d133c40fa0e 100644
--- a/drivers/infiniband/hw/mlx4/srq.c
+++ b/drivers/infiniband/hw/mlx4/srq.c
@@ -34,6 +34,7 @@
 #include <linux/mlx4/qp.h>
 #include <linux/mlx4/srq.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 
 #include "mlx4_ib.h"
 #include "user.h"
@@ -172,8 +173,12 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd,
 
                 srq->wrid = kmalloc(srq->msrq.max * sizeof (u64), GFP_KERNEL);
                 if (!srq->wrid) {
-                        err = -ENOMEM;
-                        goto err_mtt;
+                        srq->wrid = __vmalloc(srq->msrq.max * sizeof(u64),
+                                              GFP_KERNEL, PAGE_KERNEL);
+                        if (!srq->wrid) {
+                                err = -ENOMEM;
+                                goto err_mtt;
+                        }
                 }
         }
 
@@ -204,7 +209,7 @@ err_wrid:
         if (pd->uobject)
                 mlx4_ib_db_unmap_user(to_mucontext(pd->uobject->context), &srq->db);
         else
-                kfree(srq->wrid);
+                kvfree(srq->wrid);
 
 err_mtt:
         mlx4_mtt_cleanup(dev->dev, &srq->mtt);
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index ec8993a7b3be..6000f7aeede9 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -381,7 +381,19 @@ static void __cache_work_func(struct mlx5_cache_ent *ent)
                         }
                 }
         } else if (ent->cur > 2 * ent->limit) {
-                if (!someone_adding(cache) &&
+                /*
+                 * The remove_keys() logic is performed as garbage collection
+                 * task. Such task is intended to be run when no other active
+                 * processes are running.
+                 *
+                 * The need_resched() will return TRUE if there are user tasks
+                 * to be activated in near future.
+                 *
+                 * In such case, we don't execute remove_keys() and postpone
+                 * the garbage collection work to try to run in next cycle,
+                 * in order to free CPU resources to other tasks.
+                 */
+                if (!need_resched() && !someone_adding(cache) &&
                     time_after(jiffies, cache->last_add + 300 * HZ)) {
                         remove_keys(dev, i, 1);
                         if (ent->cur > ent->limit)
diff --git a/drivers/infiniband/hw/qib/qib_qsfp.c b/drivers/infiniband/hw/qib/qib_qsfp.c
index 5e27f76805e2..4c7c3c84a741 100644
--- a/drivers/infiniband/hw/qib/qib_qsfp.c
+++ b/drivers/infiniband/hw/qib/qib_qsfp.c
@@ -292,7 +292,7 @@ int qib_refresh_qsfp_cache(struct qib_pportdata *ppd, struct qib_qsfp_cache *cp)
                 qib_dev_porterr(ppd->dd, ppd->port,
                                 "QSFP byte0 is 0x%02X, S/B 0x0C/D\n", peek[0]);
 
-        if ((peek[2] & 2) == 0) {
+        if ((peek[2] & 4) == 0) {
                 /*
                  * If cable is paged, rather than "flat memory", we need to
                  * set the page to zero, Even if it already appears to be zero.
@@ -538,7 +538,7 @@ int qib_qsfp_dump(struct qib_pportdata *ppd, char *buf, int len)
         sofar += scnprintf(buf + sofar, len - sofar, "Date:%.*s\n",
                            QSFP_DATE_LEN, cd.date);
         sofar += scnprintf(buf + sofar, len - sofar, "Lot:%.*s\n",
-                           QSFP_LOT_LEN, cd.date);
+                           QSFP_LOT_LEN, cd.lot);
 
         while (bidx < QSFP_DEFAULT_HDR_CNT) {
                 int iidx;
diff --git a/drivers/infiniband/hw/qib/qib_verbs.h b/drivers/infiniband/hw/qib/qib_verbs.h
index 2baf5ad251ed..bc803f33d5f6 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.h
+++ b/drivers/infiniband/hw/qib/qib_verbs.h
@@ -329,9 +329,9 @@ struct qib_sge {
 struct qib_mr {
         struct ib_mr ibmr;
         struct ib_umem *umem;
-        struct qib_mregion mr;  /* must be last */
         u64 *pages;
         u32 npages;
+        struct qib_mregion mr;  /* must be last */
 };
 
 /*
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index a93070210109..42f4da620f2e 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -1293,7 +1293,7 @@ u8 iser_check_task_pi_status(struct iscsi_iser_task *iser_task,
                 if (mr_status.fail_status & IB_MR_CHECK_SIG_STATUS) {
                         sector_t sector_off = mr_status.sig_err.sig_err_offset;
 
-                        do_div(sector_off, sector_size + 8);
+                        sector_div(sector_off, sector_size + 8);
                         *sector = scsi_get_lba(iser_task->sc) + sector_off;
 
                         pr_err("PI error found type %d at sector %llx "
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index dfbbbb28090b..8a51c3b5d657 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -157,16 +157,9 @@ isert_create_qp(struct isert_conn *isert_conn,
         attr.recv_cq = comp->cq;
         attr.cap.max_send_wr = ISERT_QP_MAX_REQ_DTOS;
         attr.cap.max_recv_wr = ISERT_QP_MAX_RECV_DTOS + 1;
-        /*
-         * FIXME: Use devattr.max_sge - 2 for max_send_sge as
-         * work-around for RDMA_READs with ConnectX-2.
-         *
-         * Also, still make sure to have at least two SGEs for
-         * outgoing control PDU responses.
-         */
-        attr.cap.max_send_sge = max(2, device->dev_attr.max_sge - 2);
-        isert_conn->max_sge = attr.cap.max_send_sge;
-
+        attr.cap.max_send_sge = device->dev_attr.max_sge;
+        isert_conn->max_sge = min(device->dev_attr.max_sge,
+                                  device->dev_attr.max_sge_rd);
         attr.cap.max_recv_sge = 1;
         attr.sq_sig_type = IB_SIGNAL_REQ_WR;
         attr.qp_type = IB_QPT_RC;
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 9909022dc6c3..3db9a659719b 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -488,7 +488,7 @@ static int srp_create_ch_ib(struct srp_rdma_ch *ch)
         struct ib_qp *qp;
         struct ib_fmr_pool *fmr_pool = NULL;
         struct srp_fr_pool *fr_pool = NULL;
-        const int m = 1 + dev->use_fast_reg;
+        const int m = dev->use_fast_reg ? 3 : 1;
         struct ib_cq_init_attr cq_attr = {};
         int ret;
 
@@ -994,16 +994,16 @@ static int srp_connect_ch(struct srp_rdma_ch *ch, bool multich)
 
         ret = srp_lookup_path(ch);
         if (ret)
-                return ret;
+                goto out;
 
         while (1) {
                 init_completion(&ch->done);
                 ret = srp_send_req(ch, multich);
                 if (ret)
-                        return ret;
+                        goto out;
                 ret = wait_for_completion_interruptible(&ch->done);
                 if (ret < 0)
-                        return ret;
+                        goto out;
 
                 /*
                  * The CM event handling code will set status to
@@ -1011,15 +1011,16 @@ static int srp_connect_ch(struct srp_rdma_ch *ch, bool multich)
                  * back, or SRP_DLID_REDIRECT if we get a lid/qp
                  * redirect REJ back.
                  */
-                switch (ch->status) {
+                ret = ch->status;
+                switch (ret) {
                 case 0:
                         ch->connected = true;
-                        return 0;
+                        goto out;
 
                 case SRP_PORT_REDIRECT:
                         ret = srp_lookup_path(ch);
                         if (ret)
-                                return ret;
+                                goto out;
                         break;
 
                 case SRP_DLID_REDIRECT:
@@ -1028,13 +1029,16 @@ static int srp_connect_ch(struct srp_rdma_ch *ch, bool multich)
                 case SRP_STALE_CONN:
                         shost_printk(KERN_ERR, target->scsi_host, PFX
                                      "giving up on stale connection\n");
-                        ch->status = -ECONNRESET;
-                        return ch->status;
+                        ret = -ECONNRESET;
+                        goto out;
 
                 default:
-                        return ch->status;
+                        goto out;
                 }
         }
+
+out:
+        return ret <= 0 ? ret : -ENODEV;
 }
 
 static int srp_inv_rkey(struct srp_rdma_ch *ch, u32 rkey)
@@ -1309,7 +1313,7 @@ reset_state:
 }
 
 static int srp_map_finish_fr(struct srp_map_state *state,
-                             struct srp_rdma_ch *ch)
+                             struct srp_rdma_ch *ch, int sg_nents)
 {
         struct srp_target_port *target = ch->target;
         struct srp_device *dev = target->srp_host->srp_dev;
@@ -1324,10 +1328,10 @@ static int srp_map_finish_fr(struct srp_map_state *state,
 
         WARN_ON_ONCE(!dev->use_fast_reg);
 
-        if (state->sg_nents == 0)
+        if (sg_nents == 0)
                 return 0;
 
-        if (state->sg_nents == 1 && target->global_mr) {
+        if (sg_nents == 1 && target->global_mr) {
                 srp_map_desc(state, sg_dma_address(state->sg),
                              sg_dma_len(state->sg),
                              target->global_mr->rkey);
@@ -1341,8 +1345,7 @@ static int srp_map_finish_fr(struct srp_map_state *state,
         rkey = ib_inc_rkey(desc->mr->rkey);
         ib_update_fast_reg_key(desc->mr, rkey);
 
-        n = ib_map_mr_sg(desc->mr, state->sg, state->sg_nents,
-                         dev->mr_page_size);
+        n = ib_map_mr_sg(desc->mr, state->sg, sg_nents, dev->mr_page_size);
         if (unlikely(n < 0))
                 return n;
 
@@ -1448,16 +1451,15 @@ static int srp_map_sg_fr(struct srp_map_state *state, struct srp_rdma_ch *ch,
         state->fr.next = req->fr_list;
         state->fr.end = req->fr_list + ch->target->cmd_sg_cnt;
         state->sg = scat;
-        state->sg_nents = scsi_sg_count(req->scmnd);
 
-        while (state->sg_nents) {
+        while (count) {
                 int i, n;
 
-                n = srp_map_finish_fr(state, ch);
+                n = srp_map_finish_fr(state, ch, count);
                 if (unlikely(n < 0))
                         return n;
 
-                state->sg_nents -= n;
+                count -= n;
                 for (i = 0; i < n; i++)
                         state->sg = sg_next(state->sg);
         }
@@ -1517,10 +1519,12 @@ static int srp_map_idb(struct srp_rdma_ch *ch, struct srp_request *req,
 
         if (dev->use_fast_reg) {
                 state.sg = idb_sg;
-                state.sg_nents = 1;
                 sg_set_buf(idb_sg, req->indirect_desc, idb_len);
                 idb_sg->dma_address = req->indirect_dma_addr; /* hack! */
-                ret = srp_map_finish_fr(&state, ch);
+#ifdef CONFIG_NEED_SG_DMA_LENGTH
+                idb_sg->dma_length = idb_sg->length;          /* hack^2 */
+#endif
+                ret = srp_map_finish_fr(&state, ch, 1);
                 if (ret < 0)
                         return ret;
         } else if (dev->use_fmr) {
@@ -1655,7 +1659,7 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_rdma_ch *ch,
                         return ret;
                 req->nmdesc++;
         } else {
-                idb_rkey = target->global_mr->rkey;
+                idb_rkey = cpu_to_be32(target->global_mr->rkey);
         }
 
         indirect_hdr->table_desc.va = cpu_to_be64(req->indirect_dma_addr);
diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h
index 87a2a919dc43..f6af531f9f32 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.h
+++ b/drivers/infiniband/ulp/srp/ib_srp.h
@@ -300,10 +300,7 @@ struct srp_map_state {
         dma_addr_t              base_dma_addr;
         u32                     dma_len;
         u32                     total_len;
-        union {
-                unsigned int    npages;
-                int             sg_nents;
-        };
+        unsigned int            npages;
         unsigned int            nmdesc;
         unsigned int            ndesc;
 };
diff --git a/drivers/irqchip/irq-versatile-fpga.c b/drivers/irqchip/irq-versatile-fpga.c
index 598ab3f0e0ac..cadf104e3074 100644
--- a/drivers/irqchip/irq-versatile-fpga.c
+++ b/drivers/irqchip/irq-versatile-fpga.c
@@ -210,7 +210,12 @@ int __init fpga_irq_of_init(struct device_node *node,
                 parent_irq = -1;
         }
 
+#ifdef CONFIG_ARCH_VERSATILE
+        fpga_irq_init(base, node->name, IRQ_SIC_START, parent_irq, valid_mask,
+                                  node);
+#else
         fpga_irq_init(base, node->name, 0, parent_irq, valid_mask, node);
+#endif
 
         writel(clear_mask, base + IRQ_ENABLE_CLEAR);
         writel(clear_mask, base + FIQ_ENABLE_CLEAR);
diff --git a/drivers/isdn/hisax/config.c b/drivers/isdn/hisax/config.c
index b33f53b3ca93..bf04d2a3cf4a 100644
--- a/drivers/isdn/hisax/config.c
+++ b/drivers/isdn/hisax/config.c
@@ -1896,7 +1896,7 @@ static void EChannel_proc_rcv(struct hisax_d_if *d_if)
                                 ptr--;
                                 *ptr++ = '\n';
                                 *ptr = 0;
-                                HiSax_putstatus(cs, NULL, "%s", cs->dlog);
+                                HiSax_putstatus(cs, NULL, cs->dlog);
                         } else
                                 HiSax_putstatus(cs, "LogEcho: ",
                                                 "warning Frame too big (%d)",
diff --git a/drivers/isdn/hisax/hfc_pci.c b/drivers/isdn/hisax/hfc_pci.c
index 4a4825528188..90449e1e91e5 100644
--- a/drivers/isdn/hisax/hfc_pci.c
+++ b/drivers/isdn/hisax/hfc_pci.c
@@ -901,7 +901,7 @@ Begin:
                                         ptr--;
                                         *ptr++ = '\n';
                                         *ptr = 0;
-                                        HiSax_putstatus(cs, NULL, "%s", cs->dlog);
+                                        HiSax_putstatus(cs, NULL, cs->dlog);
                                 } else
                                         HiSax_putstatus(cs, "LogEcho: ", "warning Frame too big (%d)", total - 3);
                         }
diff --git a/drivers/isdn/hisax/hfc_sx.c b/drivers/isdn/hisax/hfc_sx.c
index b1fad81f0722..13b2151c10f5 100644
--- a/drivers/isdn/hisax/hfc_sx.c
+++ b/drivers/isdn/hisax/hfc_sx.c
@@ -674,7 +674,7 @@ receive_emsg(struct IsdnCardState *cs)
                                         ptr--;
                                         *ptr++ = '\n';
                                         *ptr = 0;
-                                        HiSax_putstatus(cs, NULL, "%s", cs->dlog);
+                                        HiSax_putstatus(cs, NULL, cs->dlog);
                                 } else
                                         HiSax_putstatus(cs, "LogEcho: ", "warning Frame too big (%d)", skb->len);
                         }
diff --git a/drivers/isdn/hisax/q931.c b/drivers/isdn/hisax/q931.c
index b420f8bd862e..ba4beb25d872 100644
--- a/drivers/isdn/hisax/q931.c
+++ b/drivers/isdn/hisax/q931.c
@@ -1179,7 +1179,7 @@ LogFrame(struct IsdnCardState *cs, u_char *buf, int size)
                 dp--;
                 *dp++ = '\n';
                 *dp = 0;
-                HiSax_putstatus(cs, NULL, "%s", cs->dlog);
+                HiSax_putstatus(cs, NULL, cs->dlog);
         } else
                 HiSax_putstatus(cs, "LogFrame: ", "warning Frame too big (%d)", size);
 }
@@ -1246,7 +1246,7 @@ dlogframe(struct IsdnCardState *cs, struct sk_buff *skb, int dir)
         }
         if (finish) {
                 *dp = 0;
-                HiSax_putstatus(cs, NULL, "%s", cs->dlog);
+                HiSax_putstatus(cs, NULL, cs->dlog);
                 return;
         }
         if ((0xfe & buf[0]) == PROTO_DIS_N0) {  /* 1TR6 */
@@ -1509,5 +1509,5 @@ dlogframe(struct IsdnCardState *cs, struct sk_buff *skb, int dir)
                 dp += sprintf(dp, "Unknown protocol %x!", buf[0]);
         }
         *dp = 0;
-        HiSax_putstatus(cs, NULL, "%s", cs->dlog);
+        HiSax_putstatus(cs, NULL, cs->dlog);
 }
diff --git a/drivers/lightnvm/Kconfig b/drivers/lightnvm/Kconfig
index a16bf56d3f28..85a339030e4b 100644
--- a/drivers/lightnvm/Kconfig
+++ b/drivers/lightnvm/Kconfig
@@ -18,6 +18,7 @@ if NVM
 
 config NVM_DEBUG
         bool "Open-Channel SSD debugging support"
+        default n
         ---help---
         Exposes a debug management interface to create/remove targets at:
 
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index f659e605a406..8f41b245cd55 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -74,7 +74,7 @@ EXPORT_SYMBOL(nvm_unregister_target);
 void *nvm_dev_dma_alloc(struct nvm_dev *dev, gfp_t mem_flags,
                                                         dma_addr_t *dma_handler)
 {
-        return dev->ops->dev_dma_alloc(dev->q, dev->ppalist_pool, mem_flags,
+        return dev->ops->dev_dma_alloc(dev, dev->ppalist_pool, mem_flags,
                                                                 dma_handler);
 }
 EXPORT_SYMBOL(nvm_dev_dma_alloc);
@@ -97,15 +97,47 @@ static struct nvmm_type *nvm_find_mgr_type(const char *name)
         return NULL;
 }
 
+struct nvmm_type *nvm_init_mgr(struct nvm_dev *dev)
+{
+        struct nvmm_type *mt;
+        int ret;
+
+        lockdep_assert_held(&nvm_lock);
+
+        list_for_each_entry(mt, &nvm_mgrs, list) {
+                ret = mt->register_mgr(dev);
+                if (ret < 0) {
+                        pr_err("nvm: media mgr failed to init (%d) on dev %s\n",
+                                                                ret, dev->name);
+                        return NULL; /* initialization failed */
+                } else if (ret > 0)
+                        return mt;
+        }
+
+        return NULL;
+}
+
 int nvm_register_mgr(struct nvmm_type *mt)
 {
+        struct nvm_dev *dev;
         int ret = 0;
 
         down_write(&nvm_lock);
-        if (nvm_find_mgr_type(mt->name))
+        if (nvm_find_mgr_type(mt->name)) {
                 ret = -EEXIST;
-        else
+                goto finish;
+        } else {
                 list_add(&mt->list, &nvm_mgrs);
+        }
+
+        /* try to register media mgr if any device have none configured */
+        list_for_each_entry(dev, &nvm_devices, devices) {
+                if (dev->mt)
+                        continue;
+
+                dev->mt = nvm_init_mgr(dev);
+        }
+finish:
         up_write(&nvm_lock);
 
         return ret;
@@ -160,11 +192,6 @@ int nvm_erase_blk(struct nvm_dev *dev, struct nvm_block *blk)
 }
 EXPORT_SYMBOL(nvm_erase_blk);
 
-static void nvm_core_free(struct nvm_dev *dev)
-{
-        kfree(dev);
-}
-
 static int nvm_core_init(struct nvm_dev *dev)
 {
         struct nvm_id *id = &dev->identity;
@@ -179,12 +206,21 @@ static int nvm_core_init(struct nvm_dev *dev)
         dev->sec_size = grp->csecs;
         dev->oob_size = grp->sos;
         dev->sec_per_pg = grp->fpg_sz / grp->csecs;
-        dev->addr_mode = id->ppat;
-        dev->addr_format = id->ppaf;
+        memcpy(&dev->ppaf, &id->ppaf, sizeof(struct nvm_addr_format));
 
         dev->plane_mode = NVM_PLANE_SINGLE;
         dev->max_rq_size = dev->ops->max_phys_sect * dev->sec_size;
 
+        if (grp->mtype != 0) {
+                pr_err("nvm: memory type not supported\n");
+                return -EINVAL;
+        }
+
+        if (grp->fmtype != 0 && grp->fmtype != 1) {
+                pr_err("nvm: flash type not supported\n");
+                return -EINVAL;
+        }
+
         if (grp->mpos & 0x020202)
                 dev->plane_mode = NVM_PLANE_DOUBLE;
         if (grp->mpos & 0x040404)
@@ -213,21 +249,17 @@ static void nvm_free(struct nvm_dev *dev)
 
         if (dev->mt)
                 dev->mt->unregister_mgr(dev);
-
-        nvm_core_free(dev);
 }
 
 static int nvm_init(struct nvm_dev *dev)
 {
-        struct nvmm_type *mt;
-        int ret = 0;
+        int ret = -EINVAL;
 
         if (!dev->q || !dev->ops)
-                return -EINVAL;
+                return ret;
 
-        if (dev->ops->identity(dev->q, &dev->identity)) {
+        if (dev->ops->identity(dev, &dev->identity)) {
                 pr_err("nvm: device could not be identified\n");
-                ret = -EINVAL;
                 goto err;
         }
 
@@ -251,29 +283,12 @@ static int nvm_init(struct nvm_dev *dev)
                 goto err;
         }
 
-        /* register with device with a supported manager */
-        list_for_each_entry(mt, &nvm_mgrs, list) {
-                ret = mt->register_mgr(dev);
-                if (ret < 0)
-                        goto err; /* initialization failed */
-                if (ret > 0) {
-                        dev->mt = mt;
-                        break; /* successfully initialized */
-                }
-        }
-
-        if (!ret) {
-                pr_info("nvm: no compatible manager found.\n");
-                return 0;
-        }
-
         pr_info("nvm: registered %s [%u/%u/%u/%u/%u/%u]\n",
                         dev->name, dev->sec_per_pg, dev->nr_planes,
                         dev->pgs_per_blk, dev->blks_per_lun, dev->nr_luns,
                         dev->nr_chnls);
         return 0;
 err:
-        nvm_free(dev);
         pr_err("nvm: failed to initialize nvm\n");
         return ret;
 }
@@ -308,22 +323,27 @@ int nvm_register(struct request_queue *q, char *disk_name,
         if (ret)
                 goto err_init;
 
-        down_write(&nvm_lock);
-        list_add(&dev->devices, &nvm_devices);
-        up_write(&nvm_lock);
+        if (dev->ops->max_phys_sect > 256) {
+                pr_info("nvm: max sectors supported is 256.\n");
+                ret = -EINVAL;
+                goto err_init;
+        }
 
         if (dev->ops->max_phys_sect > 1) {
-                dev->ppalist_pool = dev->ops->create_dma_pool(dev->q,
-                                                                "ppalist");
+                dev->ppalist_pool = dev->ops->create_dma_pool(dev, "ppalist");
                 if (!dev->ppalist_pool) {
                         pr_err("nvm: could not create ppa pool\n");
-                        return -ENOMEM;
+                        ret = -ENOMEM;
+                        goto err_init;
                 }
-        } else if (dev->ops->max_phys_sect > 256) {
-                pr_info("nvm: max sectors supported is 256.\n");
-                return -EINVAL;
         }
 
+        /* register device with a supported media manager */
+        down_write(&nvm_lock);
+        dev->mt = nvm_init_mgr(dev);
+        list_add(&dev->devices, &nvm_devices);
+        up_write(&nvm_lock);
+
         return 0;
 err_init:
         kfree(dev);
@@ -333,19 +353,22 @@ EXPORT_SYMBOL(nvm_register);
 
 void nvm_unregister(char *disk_name)
 {
-        struct nvm_dev *dev = nvm_find_nvm_dev(disk_name);
+        struct nvm_dev *dev;
 
+        down_write(&nvm_lock);
+        dev = nvm_find_nvm_dev(disk_name);
         if (!dev) {
                 pr_err("nvm: could not find device %s to unregister\n",
                                                                 disk_name);
+                up_write(&nvm_lock);
                 return;
         }
 
-        nvm_exit(dev);
-
-        down_write(&nvm_lock);
         list_del(&dev->devices);
         up_write(&nvm_lock);
+
+        nvm_exit(dev);
+        kfree(dev);
 }
 EXPORT_SYMBOL(nvm_unregister);
 
@@ -358,38 +381,24 @@ static int nvm_create_target(struct nvm_dev *dev,
 {
         struct nvm_ioctl_create_simple *s = &create->conf.s;
         struct request_queue *tqueue;
-        struct nvmm_type *mt;
         struct gendisk *tdisk;
         struct nvm_tgt_type *tt;
         struct nvm_target *t;
         void *targetdata;
-        int ret = 0;
 
         if (!dev->mt) {
-                /* register with device with a supported NVM manager */
-                list_for_each_entry(mt, &nvm_mgrs, list) {
-                        ret = mt->register_mgr(dev);
-                        if (ret < 0)
-                                return ret; /* initialization failed */
-                        if (ret > 0) {
-                                dev->mt = mt;
-                                break; /* successfully initialized */
-                        }
-                }
-
-                if (!ret) {
-                        pr_info("nvm: no compatible nvm manager found.\n");
-                        return -ENODEV;
-                }
+                pr_info("nvm: device has no media manager registered.\n");
+                return -ENODEV;
         }
 
+        down_write(&nvm_lock);
         tt = nvm_find_target_type(create->tgttype);
         if (!tt) {
                 pr_err("nvm: target type %s not found\n", create->tgttype);
+                up_write(&nvm_lock);
                 return -EINVAL;
         }
 
-        down_write(&nvm_lock);
         list_for_each_entry(t, &dev->online_targets, list) {
                 if (!strcmp(create->tgtname, t->disk->disk_name)) {
                         pr_err("nvm: target name already exists.\n");
@@ -457,11 +466,11 @@ static void nvm_remove_target(struct nvm_target *t)
         lockdep_assert_held(&nvm_lock);
 
         del_gendisk(tdisk);
+        blk_cleanup_queue(q);
+
         if (tt->exit)
                 tt->exit(tdisk->private_data);
 
-        blk_cleanup_queue(q);
-
         put_disk(tdisk);
 
         list_del(&t->list);
@@ -473,7 +482,9 @@ static int __nvm_configure_create(struct nvm_ioctl_create *create)
         struct nvm_dev *dev;
         struct nvm_ioctl_create_simple *s;
 
+        down_write(&nvm_lock);
         dev = nvm_find_nvm_dev(create->dev);
+        up_write(&nvm_lock);
         if (!dev) {
                 pr_err("nvm: device not found\n");
                 return -EINVAL;
@@ -532,7 +543,9 @@ static int nvm_configure_show(const char *val)
                 return -EINVAL;
         }
 
+        down_write(&nvm_lock);
         dev = nvm_find_nvm_dev(devname);
+        up_write(&nvm_lock);
         if (!dev) {
                 pr_err("nvm: device not found\n");
                 return -EINVAL;
@@ -541,7 +554,7 @@ static int nvm_configure_show(const char *val)
         if (!dev->mt)
                 return 0;
 
-        dev->mt->free_blocks_print(dev);
+        dev->mt->lun_info_print(dev);
 
         return 0;
 }
@@ -677,8 +690,10 @@ static long nvm_ioctl_info(struct file *file, void __user *arg)
         info->tgtsize = tgt_iter;
         up_write(&nvm_lock);
 
-        if (copy_to_user(arg, info, sizeof(struct nvm_ioctl_info)))
+        if (copy_to_user(arg, info, sizeof(struct nvm_ioctl_info))) {
+                kfree(info);
                 return -EFAULT;
+        }
 
         kfree(info);
         return 0;
@@ -721,8 +736,11 @@ static long nvm_ioctl_get_devices(struct file *file, void __user *arg)
 
         devices->nr_devices = i;
 
-        if (copy_to_user(arg, devices, sizeof(struct nvm_ioctl_get_devices)))
+        if (copy_to_user(arg, devices,
+                         sizeof(struct nvm_ioctl_get_devices))) {
+                kfree(devices);
                 return -EFAULT;
+        }
 
         kfree(devices);
         return 0;
diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c
index ae1fb2bdc5f4..f434e89e1c7a 100644
--- a/drivers/lightnvm/gennvm.c
+++ b/drivers/lightnvm/gennvm.c
@@ -60,23 +60,27 @@ static int gennvm_luns_init(struct nvm_dev *dev, struct gen_nvm *gn)
                 lun->vlun.lun_id = i % dev->luns_per_chnl;
                 lun->vlun.chnl_id = i / dev->luns_per_chnl;
                 lun->vlun.nr_free_blocks = dev->blks_per_lun;
+                lun->vlun.nr_inuse_blocks = 0;
+                lun->vlun.nr_bad_blocks = 0;
         }
         return 0;
 }
 
-static int gennvm_block_bb(u32 lun_id, void *bb_bitmap, unsigned int nr_blocks,
+static int gennvm_block_bb(struct ppa_addr ppa, int nr_blocks, u8 *blks,
                                                                 void *private)
 {
         struct gen_nvm *gn = private;
-        struct gen_lun *lun = &gn->luns[lun_id];
+        struct nvm_dev *dev = gn->dev;
+        struct gen_lun *lun;
         struct nvm_block *blk;
         int i;
 
-        if (unlikely(bitmap_empty(bb_bitmap, nr_blocks)))
-                return 0;
+        lun = &gn->luns[(dev->nr_luns * ppa.g.ch) + ppa.g.lun];
+
+        for (i = 0; i < nr_blocks; i++) {
+                if (blks[i] == 0)
+                        continue;
 
-        i = -1;
-        while ((i = find_next_bit(bb_bitmap, nr_blocks, i + 1)) < nr_blocks) {
                 blk = &lun->vlun.blocks[i];
                 if (!blk) {
                         pr_err("gennvm: BB data is out of bounds.\n");
@@ -84,6 +88,7 @@ static int gennvm_block_bb(u32 lun_id, void *bb_bitmap, unsigned int nr_blocks,
                 }
 
                 list_move_tail(&blk->list, &lun->bb_list);
+                lun->vlun.nr_bad_blocks++;
         }
 
         return 0;
@@ -136,6 +141,7 @@ static int gennvm_block_map(u64 slba, u32 nlb, __le64 *entries, void *private)
                         list_move_tail(&blk->list, &lun->used_list);
                         blk->type = 1;
                         lun->vlun.nr_free_blocks--;
+                        lun->vlun.nr_inuse_blocks++;
                 }
         }
 
@@ -164,22 +170,32 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn)
                         block->id = cur_block_id++;
 
                         /* First block is reserved for device */
-                        if (unlikely(lun_iter == 0 && blk_iter == 0))
+                        if (unlikely(lun_iter == 0 && blk_iter == 0)) {
+                                lun->vlun.nr_free_blocks--;
                                 continue;
+                        }
 
                         list_add_tail(&block->list, &lun->free_list);
                 }
 
                 if (dev->ops->get_bb_tbl) {
-                        ret = dev->ops->get_bb_tbl(dev->q, lun->vlun.id,
-                                        dev->blks_per_lun, gennvm_block_bb, gn);
+                        struct ppa_addr ppa;
+
+                        ppa.ppa = 0;
+                        ppa.g.ch = lun->vlun.chnl_id;
+                        ppa.g.lun = lun->vlun.id;
+                        ppa = generic_to_dev_addr(dev, ppa);
+
+                        ret = dev->ops->get_bb_tbl(dev, ppa,
+                                                dev->blks_per_lun,
+                                                gennvm_block_bb, gn);
                         if (ret)
                                 pr_err("gennvm: could not read BB table\n");
                 }
         }
 
         if (dev->ops->get_l2p_tbl) {
-                ret = dev->ops->get_l2p_tbl(dev->q, 0, dev->total_pages,
+                ret = dev->ops->get_l2p_tbl(dev, 0, dev->total_pages,
                                                         gennvm_block_map, dev);
                 if (ret) {
                         pr_err("gennvm: could not read L2P table.\n");
@@ -190,15 +206,27 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn)
         return 0;
 }
 
+static void gennvm_free(struct nvm_dev *dev)
+{
+        gennvm_blocks_free(dev);
+        gennvm_luns_free(dev);
+        kfree(dev->mp);
+        dev->mp = NULL;
+}
+
 static int gennvm_register(struct nvm_dev *dev)
 {
         struct gen_nvm *gn;
         int ret;
 
+        if (!try_module_get(THIS_MODULE))
+                return -ENODEV;
+
         gn = kzalloc(sizeof(struct gen_nvm), GFP_KERNEL);
         if (!gn)
                 return -ENOMEM;
 
+        gn->dev = dev;
         gn->nr_luns = dev->nr_luns;
         dev->mp = gn;
 
@@ -216,16 +244,15 @@ static int gennvm_register(struct nvm_dev *dev)
 
         return 1;
 err:
-        kfree(gn);
+        gennvm_free(dev);
+        module_put(THIS_MODULE);
         return ret;
 }
 
 static void gennvm_unregister(struct nvm_dev *dev)
 {
-        gennvm_blocks_free(dev);
-        gennvm_luns_free(dev);
-        kfree(dev->mp);
-        dev->mp = NULL;
+        gennvm_free(dev);
+        module_put(THIS_MODULE);
 }
 
 static struct nvm_block *gennvm_get_blk(struct nvm_dev *dev,
@@ -240,23 +267,21 @@ static struct nvm_block *gennvm_get_blk(struct nvm_dev *dev,
         if (list_empty(&lun->free_list)) {
                 pr_err_ratelimited("gennvm: lun %u have no free pages available",
                                                                 lun->vlun.id);
-                spin_unlock(&vlun->lock);
                 goto out;
         }
 
-        while (!is_gc && lun->vlun.nr_free_blocks < lun->reserved_blocks) {
-                spin_unlock(&vlun->lock);
+        if (!is_gc && lun->vlun.nr_free_blocks < lun->reserved_blocks)
                 goto out;
-        }
 
         blk = list_first_entry(&lun->free_list, struct nvm_block, list);
         list_move_tail(&blk->list, &lun->used_list);
         blk->type = 1;
 
         lun->vlun.nr_free_blocks--;
+        lun->vlun.nr_inuse_blocks++;
 
-        spin_unlock(&vlun->lock);
 out:
+        spin_unlock(&vlun->lock);
         return blk;
 }
 
@@ -271,16 +296,21 @@ static void gennvm_put_blk(struct nvm_dev *dev, struct nvm_block *blk)
         case 1:
                 list_move_tail(&blk->list, &lun->free_list);
                 lun->vlun.nr_free_blocks++;
+                lun->vlun.nr_inuse_blocks--;
                 blk->type = 0;
                 break;
         case 2:
                 list_move_tail(&blk->list, &lun->bb_list);
+                lun->vlun.nr_bad_blocks++;
+                lun->vlun.nr_inuse_blocks--;
                 break;
         default:
                 WARN_ON_ONCE(1);
                 pr_err("gennvm: erroneous block type (%lu -> %u)\n",
                                                         blk->id, blk->type);
                 list_move_tail(&blk->list, &lun->bb_list);
+                lun->vlun.nr_bad_blocks++;
+                lun->vlun.nr_inuse_blocks--;
         }
 
         spin_unlock(&vlun->lock);
@@ -292,10 +322,10 @@ static void gennvm_addr_to_generic_mode(struct nvm_dev *dev, struct nvm_rq *rqd)
 
         if (rqd->nr_pages > 1) {
                 for (i = 0; i < rqd->nr_pages; i++)
-                        rqd->ppa_list[i] = addr_to_generic_mode(dev,
+                        rqd->ppa_list[i] = dev_to_generic_addr(dev,
                                                         rqd->ppa_list[i]);
         } else {
-                rqd->ppa_addr = addr_to_generic_mode(dev, rqd->ppa_addr);
+                rqd->ppa_addr = dev_to_generic_addr(dev, rqd->ppa_addr);
         }
 }
 
@@ -305,10 +335,10 @@ static void gennvm_generic_to_addr_mode(struct nvm_dev *dev, struct nvm_rq *rqd)
 
         if (rqd->nr_pages > 1) {
                 for (i = 0; i < rqd->nr_pages; i++)
-                        rqd->ppa_list[i] = generic_to_addr_mode(dev,
+                        rqd->ppa_list[i] = generic_to_dev_addr(dev,
                                                         rqd->ppa_list[i]);
         } else {
-                rqd->ppa_addr = generic_to_addr_mode(dev, rqd->ppa_addr);
+                rqd->ppa_addr = generic_to_dev_addr(dev, rqd->ppa_addr);
         }
 }
 
@@ -321,7 +351,7 @@ static int gennvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
         gennvm_generic_to_addr_mode(dev, rqd);
 
         rqd->dev = dev;
-        return dev->ops->submit_io(dev->q, rqd);
+        return dev->ops->submit_io(dev, rqd);
 }
 
 static void gennvm_blk_set_type(struct nvm_dev *dev, struct ppa_addr *ppa,
@@ -354,10 +384,10 @@ static void gennvm_mark_blk_bad(struct nvm_dev *dev, struct nvm_rq *rqd)
 {
         int i;
 
-        if (!dev->ops->set_bb)
+        if (!dev->ops->set_bb_tbl)
                 return;
 
-        if (dev->ops->set_bb(dev->q, rqd, 1))
+        if (dev->ops->set_bb_tbl(dev, rqd, 1))
                 return;
 
         gennvm_addr_to_generic_mode(dev, rqd);
@@ -425,7 +455,7 @@ static int gennvm_erase_blk(struct nvm_dev *dev, struct nvm_block *blk,
 
         gennvm_generic_to_addr_mode(dev, &rqd);
 
-        ret = dev->ops->erase_block(dev->q, &rqd);
+        ret = dev->ops->erase_block(dev, &rqd);
 
         if (plane_cnt)
                 nvm_dev_dma_free(dev, rqd.ppa_list, rqd.dma_ppa_list);
@@ -440,15 +470,24 @@ static struct nvm_lun *gennvm_get_lun(struct nvm_dev *dev, int lunid)
         return &gn->luns[lunid].vlun;
 }
 
-static void gennvm_free_blocks_print(struct nvm_dev *dev)
+static void gennvm_lun_info_print(struct nvm_dev *dev)
 {
         struct gen_nvm *gn = dev->mp;
         struct gen_lun *lun;
         unsigned int i;
 
-        gennvm_for_each_lun(gn, lun, i)
-                pr_info("%s: lun%8u\t%u\n",
-                                        dev->name, i, lun->vlun.nr_free_blocks);
+
+        gennvm_for_each_lun(gn, lun, i) {
+                spin_lock(&lun->vlun.lock);
+
+                pr_info("%s: lun%8u\t%u\t%u\t%u\n",
+                                dev->name, i,
+                                lun->vlun.nr_free_blocks,
+                                lun->vlun.nr_inuse_blocks,
+                                lun->vlun.nr_bad_blocks);
+
+                spin_unlock(&lun->vlun.lock);
+        }
 }
 
 static struct nvmm_type gennvm = {
@@ -466,7 +505,7 @@ static struct nvmm_type gennvm = {
         .erase_blk      = gennvm_erase_blk,
 
         .get_lun        = gennvm_get_lun,
-        .free_blocks_print = gennvm_free_blocks_print,
+        .lun_info_print = gennvm_lun_info_print,
 };
 
 static int __init gennvm_module_init(void)
diff --git a/drivers/lightnvm/gennvm.h b/drivers/lightnvm/gennvm.h
index d23bd3501ddc..9c24b5b32dac 100644
--- a/drivers/lightnvm/gennvm.h
+++ b/drivers/lightnvm/gennvm.h
@@ -35,6 +35,8 @@ struct gen_lun {
 };
 
 struct gen_nvm {
+        struct nvm_dev *dev;
+
         int nr_luns;
         struct gen_lun *luns;
 };
diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c
index 7ba64c87ba1c..134e4faba482 100644
--- a/drivers/lightnvm/rrpc.c
+++ b/drivers/lightnvm/rrpc.c
@@ -123,12 +123,42 @@ static u64 block_to_addr(struct rrpc *rrpc, struct rrpc_block *rblk)
         return blk->id * rrpc->dev->pgs_per_blk;
 }
 
+static struct ppa_addr linear_to_generic_addr(struct nvm_dev *dev,
+                                                        struct ppa_addr r)
+{
+        struct ppa_addr l;
+        int secs, pgs, blks, luns;
+        sector_t ppa = r.ppa;
+
+        l.ppa = 0;
+
+        div_u64_rem(ppa, dev->sec_per_pg, &secs);
+        l.g.sec = secs;
+
+        sector_div(ppa, dev->sec_per_pg);
+        div_u64_rem(ppa, dev->sec_per_blk, &pgs);
+        l.g.pg = pgs;
+
+        sector_div(ppa, dev->pgs_per_blk);
+        div_u64_rem(ppa, dev->blks_per_lun, &blks);
+        l.g.blk = blks;
+
+        sector_div(ppa, dev->blks_per_lun);
+        div_u64_rem(ppa, dev->luns_per_chnl, &luns);
+        l.g.lun = luns;
+
+        sector_div(ppa, dev->luns_per_chnl);
+        l.g.ch = ppa;
+
+        return l;
+}
+
 static struct ppa_addr rrpc_ppa_to_gaddr(struct nvm_dev *dev, u64 addr)
 {
         struct ppa_addr paddr;
 
         paddr.ppa = addr;
-        return __linear_to_generic_addr(dev, paddr);
+        return linear_to_generic_addr(dev, paddr);
 }
 
 /* requires lun->lock taken */
@@ -152,7 +182,7 @@ static struct rrpc_block *rrpc_get_blk(struct rrpc *rrpc, struct rrpc_lun *rlun,
         struct nvm_block *blk;
         struct rrpc_block *rblk;
 
-        blk = nvm_get_blk(rrpc->dev, rlun->parent, 0);
+        blk = nvm_get_blk(rrpc->dev, rlun->parent, flags);
         if (!blk)
                 return NULL;
 
@@ -172,6 +202,20 @@ static void rrpc_put_blk(struct rrpc *rrpc, struct rrpc_block *rblk)
         nvm_put_blk(rrpc->dev, rblk->parent);
 }
 
+static void rrpc_put_blks(struct rrpc *rrpc)
+{
+        struct rrpc_lun *rlun;
+        int i;
+
+        for (i = 0; i < rrpc->nr_luns; i++) {
+                rlun = &rrpc->luns[i];
+                if (rlun->cur)
+                        rrpc_put_blk(rrpc, rlun->cur);
+                if (rlun->gc_cur)
+                        rrpc_put_blk(rrpc, rlun->gc_cur);
+        }
+}
+
 static struct rrpc_lun *get_next_lun(struct rrpc *rrpc)
 {
         int next = atomic_inc_return(&rrpc->next_lun);
@@ -972,7 +1016,7 @@ static int rrpc_map_init(struct rrpc *rrpc)
                 return 0;
 
         /* Bring up the mapping table from device */
-        ret = dev->ops->get_l2p_tbl(dev->q, 0, dev->total_pages,
+        ret = dev->ops->get_l2p_tbl(dev, 0, dev->total_pages,
                                                         rrpc_l2p_update, rrpc);
         if (ret) {
                 pr_err("nvm: rrpc: could not read L2P table.\n");
@@ -1194,18 +1238,21 @@ static int rrpc_luns_configure(struct rrpc *rrpc)
 
                 rblk = rrpc_get_blk(rrpc, rlun, 0);
                 if (!rblk)
-                        return -EINVAL;
+                        goto err;
 
                 rrpc_set_lun_cur(rlun, rblk);
 
                 /* Emergency gc block */
                 rblk = rrpc_get_blk(rrpc, rlun, 1);
                 if (!rblk)
-                        return -EINVAL;
+                        goto err;
                 rlun->gc_cur = rblk;
         }
 
         return 0;
+err:
+        rrpc_put_blks(rrpc);
+        return -EINVAL;
 }
 
 static struct nvm_tgt_type tt_rrpc;
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 917d47e290ae..3147c8d09ea8 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -112,7 +112,8 @@ struct iv_tcw_private {
  * and encrypts / decrypts at the same time.
  */
 enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID,
-             DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD };
+             DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD,
+             DM_CRYPT_EXIT_THREAD};
 
 /*
  * The fields in here must be read only after initialization.
@@ -1203,20 +1204,18 @@ continue_locked:
                 if (!RB_EMPTY_ROOT(&cc->write_tree))
                         goto pop_from_list;
 
+                if (unlikely(test_bit(DM_CRYPT_EXIT_THREAD, &cc->flags))) {
+                        spin_unlock_irq(&cc->write_thread_wait.lock);
+                        break;
+                }
+
                 __set_current_state(TASK_INTERRUPTIBLE);
                 __add_wait_queue(&cc->write_thread_wait, &wait);
 
                 spin_unlock_irq(&cc->write_thread_wait.lock);
 
-                if (unlikely(kthread_should_stop())) {
-                        set_task_state(current, TASK_RUNNING);
-                        remove_wait_queue(&cc->write_thread_wait, &wait);
-                        break;
-                }
-
                 schedule();
 
-                set_task_state(current, TASK_RUNNING);
                 spin_lock_irq(&cc->write_thread_wait.lock);
                 __remove_wait_queue(&cc->write_thread_wait, &wait);
                 goto continue_locked;
@@ -1531,8 +1530,13 @@ static void crypt_dtr(struct dm_target *ti)
         if (!cc)
                 return;
 
-        if (cc->write_thread)
+        if (cc->write_thread) {
+                spin_lock_irq(&cc->write_thread_wait.lock);
+                set_bit(DM_CRYPT_EXIT_THREAD, &cc->flags);
+                wake_up_locked(&cc->write_thread_wait);
+                spin_unlock_irq(&cc->write_thread_wait.lock);
                 kthread_stop(cc->write_thread);
+        }
 
         if (cc->io_queue)
                 destroy_workqueue(cc->io_queue);
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index aaa6caa46a9f..cfa29f574c2a 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1537,32 +1537,34 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
                 struct block_device **bdev, fmode_t *mode)
 {
         struct multipath *m = ti->private;
-        struct pgpath *pgpath;
         unsigned long flags;
         int r;
 
-        r = 0;
-
         spin_lock_irqsave(&m->lock, flags);
 
         if (!m->current_pgpath)
                 __choose_pgpath(m, 0);
 
-        pgpath = m->current_pgpath;
-
-        if (pgpath) {
-                *bdev = pgpath->path.dev->bdev;
-                *mode = pgpath->path.dev->mode;
+        if (m->current_pgpath) {
+                if (!m->queue_io) {
+                        *bdev = m->current_pgpath->path.dev->bdev;
+                        *mode = m->current_pgpath->path.dev->mode;
+                        r = 0;
+                } else {
+                        /* pg_init has not started or completed */
+                        r = -ENOTCONN;
+                }
+        } else {
+                /* No path is available */
+                if (m->queue_if_no_path)
+                        r = -ENOTCONN;
+                else
+                        r = -EIO;
         }
 
-        if ((pgpath && m->queue_io) || (!pgpath && m->queue_if_no_path))
-                r = -ENOTCONN;
-        else if (!*bdev)
-                r = -EIO;
-
         spin_unlock_irqrestore(&m->lock, flags);
 
-        if (r == -ENOTCONN && !fatal_signal_pending(current)) {
+        if (r == -ENOTCONN) {
                 spin_lock_irqsave(&m->lock, flags);
                 if (!m->current_pg) {
                         /* Path status changed, redo selection */
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 1fa45695b68a..c219a053c7f6 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -1207,6 +1207,12 @@ static int __reserve_metadata_snap(struct dm_pool_metadata *pmd)
         dm_block_t held_root;
 
         /*
+         * We commit to ensure the btree roots which we increment in a
+         * moment are up to date.
+         */
+        __commit_transaction(pmd);
+
+        /*
          * Copy the superblock.
          */
         dm_sm_inc_block(pmd->metadata_sm, THIN_SUPERBLOCK_LOCATION);
@@ -1538,7 +1544,7 @@ static int __remove(struct dm_thin_device *td, dm_block_t block)
 static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_t end)
 {
         int r;
-        unsigned count;
+        unsigned count, total_count = 0;
         struct dm_pool_metadata *pmd = td->pmd;
         dm_block_t keys[1] = { td->id };
         __le64 value;
@@ -1561,11 +1567,29 @@ static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_
         if (r)
                 return r;
 
-        r = dm_btree_remove_leaves(&pmd->bl_info, mapping_root, &begin, end, &mapping_root, &count);
-        if (r)
-                return r;
+        /*
+         * Remove leaves stops at the first unmapped entry, so we have to
+         * loop round finding mapped ranges.
+         */
+        while (begin < end) {
+                r = dm_btree_lookup_next(&pmd->bl_info, mapping_root, &begin, &begin, &value);
+                if (r == -ENODATA)
+                        break;
+
+                if (r)
+                        return r;
+
+                if (begin >= end)
+                        break;
+
+                r = dm_btree_remove_leaves(&pmd->bl_info, mapping_root, &begin, end, &mapping_root, &count);
+                if (r)
+                        return r;
+
+                total_count += count;
+        }
 
-        td->mapped_blocks -= count;
+        td->mapped_blocks -= total_count;
         td->changed = 1;
 
         /*
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 3897b90bd462..63903a5a5d9e 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -2432,6 +2432,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
         case PM_WRITE:
                 if (old_mode != new_mode)
                         notify_of_pool_mode_change(pool, "write");
+                pool->pf.error_if_no_space = pt->requested_pf.error_if_no_space;
                 dm_pool_metadata_read_write(pool->pmd);
                 pool->process_bio = process_bio;
                 pool->process_discard = process_discard_bio;
@@ -4249,10 +4250,9 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
         struct thin_c *tc = ti->private;
         struct pool *pool = tc->pool;
-        struct queue_limits *pool_limits = dm_get_queue_limits(pool->pool_md);
 
-        if (!pool_limits->discard_granularity)
-                return; /* pool's discard support is disabled */
+        if (!pool->pf.discard_enabled)
+                return;
 
         limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
         limits->max_discard_sectors = 2048 * 1024 * 16; /* 16G */
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 6e15f3565892..5df40480228b 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -591,7 +591,7 @@ retry:
 
 out:
         dm_put_live_table(md, *srcu_idx);
-        if (r == -ENOTCONN) {
+        if (r == -ENOTCONN && !fatal_signal_pending(current)) {
                 msleep(10);
                 goto retry;
         }
@@ -603,9 +603,10 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
 {
         struct mapped_device *md = bdev->bd_disk->private_data;
         struct dm_target *tgt;
+        struct block_device *tgt_bdev = NULL;
         int srcu_idx, r;
 
-        r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx);
+        r = dm_get_live_table_for_ioctl(md, &tgt, &tgt_bdev, &mode, &srcu_idx);
         if (r < 0)
                 return r;
 
@@ -620,7 +621,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
                         goto out;
         }
 
-        r =  __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+        r =  __blkdev_driver_ioctl(tgt_bdev, mode, cmd, arg);
 out:
         dm_put_live_table(md, srcu_idx);
         return r;
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index c573402033b2..b1ced58eb5e1 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -63,6 +63,11 @@ int lower_bound(struct btree_node *n, uint64_t key)
         return bsearch(n, key, 0);
 }
 
+static int upper_bound(struct btree_node *n, uint64_t key)
+{
+        return bsearch(n, key, 1);
+}
+
 void inc_children(struct dm_transaction_manager *tm, struct btree_node *n,
                   struct dm_btree_value_type *vt)
 {
@@ -252,6 +257,16 @@ static void pop_frame(struct del_stack *s)
         dm_tm_unlock(s->tm, f->b);
 }
 
+static void unlock_all_frames(struct del_stack *s)
+{
+        struct frame *f;
+
+        while (unprocessed_frames(s)) {
+                f = s->spine + s->top--;
+                dm_tm_unlock(s->tm, f->b);
+        }
+}
+
 int dm_btree_del(struct dm_btree_info *info, dm_block_t root)
 {
         int r;
@@ -308,9 +323,13 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root)
                         pop_frame(s);
                 }
         }
-
 out:
+        if (r) {
+                /* cleanup all frames of del_stack */
+                unlock_all_frames(s);
+        }
         kfree(s);
+
         return r;
 }
 EXPORT_SYMBOL_GPL(dm_btree_del);
@@ -392,6 +411,82 @@ int dm_btree_lookup(struct dm_btree_info *info, dm_block_t root,
 }
 EXPORT_SYMBOL_GPL(dm_btree_lookup);
 
+static int dm_btree_lookup_next_single(struct dm_btree_info *info, dm_block_t root,
+                                       uint64_t key, uint64_t *rkey, void *value_le)
+{
+        int r, i;
+        uint32_t flags, nr_entries;
+        struct dm_block *node;
+        struct btree_node *n;
+
+        r = bn_read_lock(info, root, &node);
+        if (r)
+                return r;
+
+        n = dm_block_data(node);
+        flags = le32_to_cpu(n->header.flags);
+        nr_entries = le32_to_cpu(n->header.nr_entries);
+
+        if (flags & INTERNAL_NODE) {
+                i = lower_bound(n, key);
+                if (i < 0 || i >= nr_entries) {
+                        r = -ENODATA;
+                        goto out;
+                }
+
+                r = dm_btree_lookup_next_single(info, value64(n, i), key, rkey, value_le);
+                if (r == -ENODATA && i < (nr_entries - 1)) {
+                        i++;
+                        r = dm_btree_lookup_next_single(info, value64(n, i), key, rkey, value_le);
+                }
+
+        } else {
+                i = upper_bound(n, key);
+                if (i < 0 || i >= nr_entries) {
+                        r = -ENODATA;
+                        goto out;
+                }
+
+                *rkey = le64_to_cpu(n->keys[i]);
+                memcpy(value_le, value_ptr(n, i), info->value_type.size);
+        }
+out:
+        dm_tm_unlock(info->tm, node);
+        return r;
+}
+
+int dm_btree_lookup_next(struct dm_btree_info *info, dm_block_t root,
+                         uint64_t *keys, uint64_t *rkey, void *value_le)
+{
+        unsigned level;
+        int r = -ENODATA;
+        __le64 internal_value_le;
+        struct ro_spine spine;
+
+        init_ro_spine(&spine, info);
+        for (level = 0; level < info->levels - 1u; level++) {
+                r = btree_lookup_raw(&spine, root, keys[level],
+                                     lower_bound, rkey,
+                                     &internal_value_le, sizeof(uint64_t));
+                if (r)
+                        goto out;
+
+                if (*rkey != keys[level]) {
+                        r = -ENODATA;
+                        goto out;
+                }
+
+                root = le64_to_cpu(internal_value_le);
+        }
+
+        r = dm_btree_lookup_next_single(info, root, keys[level], rkey, value_le);
+out:
+        exit_ro_spine(&spine);
+        return r;
+}
+
+EXPORT_SYMBOL_GPL(dm_btree_lookup_next);
+
 /*
  * Splits a node by creating a sibling node and shifting half the nodes
  * contents across.  Assumes there is a parent node, and it has room for
@@ -473,8 +568,10 @@ static int btree_split_sibling(struct shadow_spine *s, unsigned parent_index,
 
         r = insert_at(sizeof(__le64), pn, parent_index + 1,
                       le64_to_cpu(rn->keys[0]), &location);
-        if (r)
+        if (r) {
+                unlock_block(s->info, right);
                 return r;
+        }
 
         if (key < le64_to_cpu(rn->keys[0])) {
                 unlock_block(s->info, right);
diff --git a/drivers/md/persistent-data/dm-btree.h b/drivers/md/persistent-data/dm-btree.h
index 11d8cf78621d..c74301fa5a37 100644
--- a/drivers/md/persistent-data/dm-btree.h
+++ b/drivers/md/persistent-data/dm-btree.h
@@ -110,6 +110,13 @@ int dm_btree_lookup(struct dm_btree_info *info, dm_block_t root,
                     uint64_t *keys, void *value_le);
 
 /*
+ * Tries to find the first key where the bottom level key is >= to that
+ * given.  Useful for skipping empty sections of the btree.
+ */
+int dm_btree_lookup_next(struct dm_btree_info *info, dm_block_t root,
+                         uint64_t *keys, uint64_t *rkey, void *value_le);
+
+/*
  * Insertion (or overwrite an existing value).  O(ln(n))
  */
 int dm_btree_insert(struct dm_btree_info *info, dm_block_t root,
@@ -135,9 +142,10 @@ int dm_btree_remove(struct dm_btree_info *info, dm_block_t root,
                     uint64_t *keys, dm_block_t *new_root);
 
 /*
- * Removes values between 'keys' and keys2, where keys2 is keys with the
- * final key replaced with 'end_key'.  'end_key' is the one-past-the-end
- * value.  'keys' may be altered.
+ * Removes a _contiguous_ run of values starting from 'keys' and not
+ * reaching keys2 (where keys2 is keys with the final key replaced with
+ * 'end_key').  'end_key' is the one-past-the-end value.  'keys' may be
+ * altered.
  */
 int dm_btree_remove_leaves(struct dm_btree_info *info, dm_block_t root,
                            uint64_t *keys, uint64_t end_key,
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 53091295fce9..fca6dbcf9a47 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -136,7 +136,7 @@ static int brb_push(struct bop_ring_buffer *brb,
         return 0;
 }
 
-static int brb_pop(struct bop_ring_buffer *brb, struct block_op *result)
+static int brb_peek(struct bop_ring_buffer *brb, struct block_op *result)
 {
         struct block_op *bop;
 
@@ -147,6 +147,17 @@ static int brb_pop(struct bop_ring_buffer *brb, struct block_op *result)
         result->type = bop->type;
         result->block = bop->block;
 
+        return 0;
+}
+
+static int brb_pop(struct bop_ring_buffer *brb)
+{
+        struct block_op *bop;
+
+        if (brb_empty(brb))
+                return -ENODATA;
+
+        bop = brb->bops + brb->begin;
         brb->begin = brb_next(brb, brb->begin);
 
         return 0;
@@ -211,7 +222,7 @@ static int apply_bops(struct sm_metadata *smm)
         while (!brb_empty(&smm->uncommitted)) {
                 struct block_op bop;
 
-                r = brb_pop(&smm->uncommitted, &bop);
+                r = brb_peek(&smm->uncommitted, &bop);
                 if (r) {
                         DMERR("bug in bop ring buffer");
                         break;
@@ -220,6 +231,8 @@ static int apply_bops(struct sm_metadata *smm)
                 r = commit_bop(smm, &bop);
                 if (r)
                         break;
+
+                brb_pop(&smm->uncommitted);
         }
 
         return r;
@@ -683,7 +696,6 @@ static struct dm_space_map bootstrap_ops = {
 static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
 {
         int r, i;
-        enum allocation_event ev;
         struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
         dm_block_t old_len = smm->ll.nr_blocks;
 
@@ -705,11 +717,12 @@ static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
          * allocate any new blocks.
          */
         do {
-                for (i = old_len; !r && i < smm->begin; i++) {
-                        r = sm_ll_inc(&smm->ll, i, &ev);
-                        if (r)
-                                goto out;
-                }
+                for (i = old_len; !r && i < smm->begin; i++)
+                        r = add_bop(smm, BOP_INC, i);
+
+                if (r)
+                        goto out;
+
                 old_len = smm->begin;
 
                 r = apply_bops(smm);
@@ -754,7 +767,6 @@ int dm_sm_metadata_create(struct dm_space_map *sm,
 {
         int r;
         dm_block_t i;
-        enum allocation_event ev;
         struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
 
         smm->begin = superblock + 1;
@@ -782,7 +794,7 @@ int dm_sm_metadata_create(struct dm_space_map *sm,
          * allocated blocks that they were built from.
          */
         for (i = superblock; !r && i < smm->begin; i++)
-                r = sm_ll_inc(&smm->ll, i, &ev);
+                r = add_bop(smm, BOP_INC, i);
 
         if (r)
                 return r;
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index d2e75c88f4d2..f40909793490 100644
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -497,6 +497,7 @@ static u64 calculate_sr(struct cxl_context *ctx)
 {
         u64 sr = 0;
 
+        set_endian(sr);
         if (ctx->master)
                 sr |= CXL_PSL_SR_An_MP;
         if (mfspr(SPRN_LPCR) & LPCR_TC)
@@ -506,7 +507,6 @@ static u64 calculate_sr(struct cxl_context *ctx)
                 sr |= CXL_PSL_SR_An_HV;
         } else {
                 sr |= CXL_PSL_SR_An_PR | CXL_PSL_SR_An_R;
-                set_endian(sr);
                 sr &= ~(CXL_PSL_SR_An_HV);
                 if (!test_tsk_thread_flag(current, TIF_32BIT))
                         sr |= CXL_PSL_SR_An_SF;
diff --git a/drivers/net/can/bfin_can.c b/drivers/net/can/bfin_can.c
index 57dadd52b428..1deb8ff90a89 100644
--- a/drivers/net/can/bfin_can.c
+++ b/drivers/net/can/bfin_can.c
@@ -501,8 +501,6 @@ static int bfin_can_err(struct net_device *dev, u16 isrc, u16 status)
                         cf->data[2] |= CAN_ERR_PROT_FORM;
                 else if (status & SER)
                         cf->data[2] |= CAN_ERR_PROT_STUFF;
-                else
-                        cf->data[2] |= CAN_ERR_PROT_UNSPEC;
         }
 
         priv->can.state = state;
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index 5d214d135332..f91b094288da 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -962,7 +962,6 @@ static int c_can_handle_bus_err(struct net_device *dev,
          * type of the last error to occur on the CAN bus
          */
         cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR;
-        cf->data[2] |= CAN_ERR_PROT_UNSPEC;
 
         switch (lec_type) {
         case LEC_STUFF_ERROR:
@@ -975,8 +974,7 @@ static int c_can_handle_bus_err(struct net_device *dev,
                 break;
         case LEC_ACK_ERROR:
                 netdev_dbg(dev, "ack error\n");
-                cf->data[3] |= (CAN_ERR_PROT_LOC_ACK |
-                                CAN_ERR_PROT_LOC_ACK_DEL);
+                cf->data[3] = CAN_ERR_PROT_LOC_ACK;
                 break;
         case LEC_BIT1_ERROR:
                 netdev_dbg(dev, "bit1 error\n");
@@ -988,8 +986,7 @@ static int c_can_handle_bus_err(struct net_device *dev,
                 break;
         case LEC_CRC_ERROR:
                 netdev_dbg(dev, "CRC error\n");
-                cf->data[3] |= (CAN_ERR_PROT_LOC_CRC_SEQ |
-                                CAN_ERR_PROT_LOC_CRC_DEL);
+                cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
                 break;
         default:
                 break;
diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c
index 70a8cbb29e75..1e37313054f3 100644
--- a/drivers/net/can/cc770/cc770.c
+++ b/drivers/net/can/cc770/cc770.c
@@ -578,7 +578,7 @@ static int cc770_err(struct net_device *dev, u8 status)
                                 cf->data[2] |= CAN_ERR_PROT_BIT0;
                                 break;
                         case STAT_LEC_CRC:
-                                cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ;
+                                cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
                                 break;
                         }
                 }
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 868fe945e35a..41c0fc9f3b14 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -535,13 +535,13 @@ static void do_bus_err(struct net_device *dev,
         if (reg_esr & FLEXCAN_ESR_ACK_ERR) {
                 netdev_dbg(dev, "ACK_ERR irq\n");
                 cf->can_id |= CAN_ERR_ACK;
-                cf->data[3] |= CAN_ERR_PROT_LOC_ACK;
+                cf->data[3] = CAN_ERR_PROT_LOC_ACK;
                 tx_errors = 1;
         }
         if (reg_esr & FLEXCAN_ESR_CRC_ERR) {
                 netdev_dbg(dev, "CRC_ERR irq\n");
                 cf->data[2] |= CAN_ERR_PROT_BIT;
-                cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ;
+                cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
                 rx_errors = 1;
         }
         if (reg_esr & FLEXCAN_ESR_FRM_ERR) {
diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c
index c1e85368a198..5d04f5464faf 100644
--- a/drivers/net/can/janz-ican3.c
+++ b/drivers/net/can/janz-ican3.c
@@ -1096,7 +1096,6 @@ static int ican3_handle_cevtind(struct ican3_dev *mod, struct ican3_msg *msg)
                         cf->data[2] |= CAN_ERR_PROT_STUFF;
                         break;
                 default:
-                        cf->data[2] |= CAN_ERR_PROT_UNSPEC;
                         cf->data[3] = ecc & ECC_SEG;
                         break;
                 }
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index ef655177bb5e..39cf911f7a1e 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -487,7 +487,6 @@ static int m_can_handle_lec_err(struct net_device *dev,
          * type of the last error to occur on the CAN bus
          */
         cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR;
-        cf->data[2] |= CAN_ERR_PROT_UNSPEC;
 
         switch (lec_type) {
         case LEC_STUFF_ERROR:
@@ -500,8 +499,7 @@ static int m_can_handle_lec_err(struct net_device *dev,
                 break;
         case LEC_ACK_ERROR:
                 netdev_dbg(dev, "ack error\n");
-                cf->data[3] |= (CAN_ERR_PROT_LOC_ACK |
-                                CAN_ERR_PROT_LOC_ACK_DEL);
+                cf->data[3] = CAN_ERR_PROT_LOC_ACK;
                 break;
         case LEC_BIT1_ERROR:
                 netdev_dbg(dev, "bit1 error\n");
@@ -513,8 +511,7 @@ static int m_can_handle_lec_err(struct net_device *dev,
                 break;
         case LEC_CRC_ERROR:
                 netdev_dbg(dev, "CRC error\n");
-                cf->data[3] |= (CAN_ERR_PROT_LOC_CRC_SEQ |
-                                CAN_ERR_PROT_LOC_CRC_DEL);
+                cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
                 break;
         default:
                 break;
diff --git a/drivers/net/can/pch_can.c b/drivers/net/can/pch_can.c
index e187ca783da0..c1317889d3d8 100644
--- a/drivers/net/can/pch_can.c
+++ b/drivers/net/can/pch_can.c
@@ -559,8 +559,7 @@ static void pch_can_error(struct net_device *ndev, u32 status)
                 stats->rx_errors++;
                 break;
         case PCH_CRC_ERR:
-                cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ |
-                               CAN_ERR_PROT_LOC_CRC_DEL;
+                cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
                 priv->can.can_stats.bus_error++;
                 stats->rx_errors++;
                 break;
diff --git a/drivers/net/can/rcar_can.c b/drivers/net/can/rcar_can.c
index 7bd54191f962..bc46be39549d 100644
--- a/drivers/net/can/rcar_can.c
+++ b/drivers/net/can/rcar_can.c
@@ -241,17 +241,16 @@ static void rcar_can_error(struct net_device *ndev)
                 u8 ecsr;
 
                 netdev_dbg(priv->ndev, "Bus error interrupt:\n");
-                if (skb) {
+                if (skb)
                         cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT;
-                        cf->data[2] = CAN_ERR_PROT_UNSPEC;
-                }
+
                 ecsr = readb(&priv->regs->ecsr);
                 if (ecsr & RCAR_CAN_ECSR_ADEF) {
                         netdev_dbg(priv->ndev, "ACK Delimiter Error\n");
                         tx_errors++;
                         writeb(~RCAR_CAN_ECSR_ADEF, &priv->regs->ecsr);
                         if (skb)
-                                cf->data[3] |= CAN_ERR_PROT_LOC_ACK_DEL;
+                                cf->data[3] = CAN_ERR_PROT_LOC_ACK_DEL;
                 }
                 if (ecsr & RCAR_CAN_ECSR_BE0F) {
                         netdev_dbg(priv->ndev, "Bit Error (dominant)\n");
@@ -272,7 +271,7 @@ static void rcar_can_error(struct net_device *ndev)
                         rx_errors++;
                         writeb(~RCAR_CAN_ECSR_CEF, &priv->regs->ecsr);
                         if (skb)
-                                cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ;
+                                cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
                 }
                 if (ecsr & RCAR_CAN_ECSR_AEF) {
                         netdev_dbg(priv->ndev, "ACK Error\n");
@@ -280,7 +279,7 @@ static void rcar_can_error(struct net_device *ndev)
                         writeb(~RCAR_CAN_ECSR_AEF, &priv->regs->ecsr);
                         if (skb) {
                                 cf->can_id |= CAN_ERR_ACK;
-                                cf->data[3] |= CAN_ERR_PROT_LOC_ACK;
+                                cf->data[3] = CAN_ERR_PROT_LOC_ACK;
                         }
                 }
                 if (ecsr & RCAR_CAN_ECSR_FEF) {
diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c
index 7b92e911a616..8dda3b703d39 100644
--- a/drivers/net/can/sja1000/sja1000.c
+++ b/drivers/net/can/sja1000/sja1000.c
@@ -218,6 +218,9 @@ static void sja1000_start(struct net_device *dev)
         priv->write_reg(priv, SJA1000_RXERR, 0x0);
         priv->read_reg(priv, SJA1000_ECC);
 
+        /* clear interrupt flags */
+        priv->read_reg(priv, SJA1000_IR);
+
         /* leave reset mode */
         set_normal_mode(dev);
 }
@@ -446,7 +449,6 @@ static int sja1000_err(struct net_device *dev, uint8_t isrc, uint8_t status)
                         cf->data[2] |= CAN_ERR_PROT_STUFF;
                         break;
                 default:
-                        cf->data[2] |= CAN_ERR_PROT_UNSPEC;
                         cf->data[3] = ecc & ECC_SEG;
                         break;
                 }
diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c
index d9a42c646783..68ef0a4cd821 100644
--- a/drivers/net/can/sun4i_can.c
+++ b/drivers/net/can/sun4i_can.c
@@ -575,7 +575,6 @@ static int sun4i_can_err(struct net_device *dev, u8 isrc, u8 status)
                                 cf->data[2] |= CAN_ERR_PROT_STUFF;
                                 break;
                         default:
-                                cf->data[2] |= CAN_ERR_PROT_UNSPEC;
                                 cf->data[3] = (ecc & SUN4I_STA_ERR_SEG_CODE)
                                                >> 16;
                                 break;
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index cf345cbfe819..680d1ff07a55 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -722,7 +722,6 @@ static int ti_hecc_error(struct net_device *ndev, int int_status,
         if (err_status & HECC_BUS_ERROR) {
                 ++priv->can.can_stats.bus_error;
                 cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT;
-                cf->data[2] |= CAN_ERR_PROT_UNSPEC;
                 if (err_status & HECC_CANES_FE) {
                         hecc_set_bit(priv, HECC_CANES, HECC_CANES_FE);
                         cf->data[2] |= CAN_ERR_PROT_FORM;
@@ -737,13 +736,11 @@ static int ti_hecc_error(struct net_device *ndev, int int_status,
                 }
                 if (err_status & HECC_CANES_CRCE) {
                         hecc_set_bit(priv, HECC_CANES, HECC_CANES_CRCE);
-                        cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ |
-                                        CAN_ERR_PROT_LOC_CRC_DEL;
+                        cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
                 }
                 if (err_status & HECC_CANES_ACKE) {
                         hecc_set_bit(priv, HECC_CANES, HECC_CANES_ACKE);
-                        cf->data[3] |= CAN_ERR_PROT_LOC_ACK |
-                                        CAN_ERR_PROT_LOC_ACK_DEL;
+                        cf->data[3] = CAN_ERR_PROT_LOC_ACK;
                 }
         }
 
diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index 2d390384ef3b..fc5b75675cd8 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -377,7 +377,6 @@ static void ems_usb_rx_err(struct ems_usb *dev, struct ems_cpc_msg *msg)
                         cf->data[2] |= CAN_ERR_PROT_STUFF;
                         break;
                 default:
-                        cf->data[2] |= CAN_ERR_PROT_UNSPEC;
                         cf->data[3] = ecc & SJA1000_ECC_SEG;
                         break;
                 }
diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c
index 0e5a4493ba4f..113e64fcd73b 100644
--- a/drivers/net/can/usb/esd_usb2.c
+++ b/drivers/net/can/usb/esd_usb2.c
@@ -282,7 +282,6 @@ static void esd_usb2_rx_event(struct esd_usb2_net_priv *priv,
                                 cf->data[2] |= CAN_ERR_PROT_STUFF;
                                 break;
                         default:
-                                cf->data[2] |= CAN_ERR_PROT_UNSPEC;
                                 cf->data[3] = ecc & SJA1000_ECC_SEG;
                                 break;
                         }
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 8b17a9065b0b..022bfa13ebfa 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -944,10 +944,9 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev,
                         cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT;
 
                         if (es->leaf.error_factor & M16C_EF_ACKE)
-                                cf->data[3] |= (CAN_ERR_PROT_LOC_ACK);
+                                cf->data[3] = CAN_ERR_PROT_LOC_ACK;
                         if (es->leaf.error_factor & M16C_EF_CRCE)
-                                cf->data[3] |= (CAN_ERR_PROT_LOC_CRC_SEQ |
-                                                CAN_ERR_PROT_LOC_CRC_DEL);
+                                cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
                         if (es->leaf.error_factor & M16C_EF_FORME)
                                 cf->data[2] |= CAN_ERR_PROT_FORM;
                         if (es->leaf.error_factor & M16C_EF_STFE)
diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c
index de95b1ccba3e..a731720f1d13 100644
--- a/drivers/net/can/usb/usb_8dev.c
+++ b/drivers/net/can/usb/usb_8dev.c
@@ -401,9 +401,7 @@ static void usb_8dev_rx_err_msg(struct usb_8dev_priv *priv,
                 tx_errors = 1;
                 break;
         case USB_8DEV_STATUSMSG_CRC:
-                cf->data[2] |= CAN_ERR_PROT_UNSPEC;
-                cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ |
-                               CAN_ERR_PROT_LOC_CRC_DEL;
+                cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
                 rx_errors = 1;
                 break;
         case USB_8DEV_STATUSMSG_BIT0:
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index fc55e8e0351d..51670b322409 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -608,17 +608,15 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
 
         /* Check for error interrupt */
         if (isr & XCAN_IXR_ERROR_MASK) {
-                if (skb) {
+                if (skb)
                         cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR;
-                        cf->data[2] |= CAN_ERR_PROT_UNSPEC;
-                }
 
                 /* Check for Ack error interrupt */
                 if (err_status & XCAN_ESR_ACKER_MASK) {
                         stats->tx_errors++;
                         if (skb) {
                                 cf->can_id |= CAN_ERR_ACK;
-                                cf->data[3] |= CAN_ERR_PROT_LOC_ACK;
+                                cf->data[3] = CAN_ERR_PROT_LOC_ACK;
                         }
                 }
 
@@ -654,8 +652,7 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
                         stats->rx_errors++;
                         if (skb) {
                                 cf->can_id |= CAN_ERR_PROT;
-                                cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ |
-                                                CAN_ERR_PROT_LOC_CRC_DEL;
+                                cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
                         }
                 }
                         priv->can.can_stats.bus_error++;
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 955d06b9cdba..31c5e476fd64 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -29,6 +29,7 @@ source "drivers/net/ethernet/apm/Kconfig"
 source "drivers/net/ethernet/apple/Kconfig"
 source "drivers/net/ethernet/arc/Kconfig"
 source "drivers/net/ethernet/atheros/Kconfig"
+source "drivers/net/ethernet/aurora/Kconfig"
 source "drivers/net/ethernet/cadence/Kconfig"
 source "drivers/net/ethernet/adi/Kconfig"
 source "drivers/net/ethernet/broadcom/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 4a2ee98738f0..071f84eb6f3f 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_NET_XGENE) += apm/
 obj-$(CONFIG_NET_VENDOR_APPLE) += apple/
 obj-$(CONFIG_NET_VENDOR_ARC) += arc/
 obj-$(CONFIG_NET_VENDOR_ATHEROS) += atheros/
+obj-$(CONFIG_NET_VENDOR_AURORA) += aurora/
 obj-$(CONFIG_NET_CADENCE) += cadence/
 obj-$(CONFIG_NET_BFIN) += adi/
 obj-$(CONFIG_NET_VENDOR_BROADCOM) += broadcom/
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index 991412ce6f48..9147a0107c44 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -450,12 +450,12 @@ static netdev_tx_t xgene_enet_start_xmit(struct sk_buff *skb,
                 return NETDEV_TX_OK;
         }
 
-        pdata->ring_ops->wr_cmd(tx_ring, count);
         skb_tx_timestamp(skb);
 
         pdata->stats.tx_packets++;
         pdata->stats.tx_bytes += skb->len;
 
+        pdata->ring_ops->wr_cmd(tx_ring, count);
         return NETDEV_TX_OK;
 }
 
@@ -688,10 +688,10 @@ static int xgene_enet_open(struct net_device *ndev)
         mac_ops->tx_enable(pdata);
         mac_ops->rx_enable(pdata);
 
+        xgene_enet_napi_enable(pdata);
         ret = xgene_enet_register_irq(ndev);
         if (ret)
                 return ret;
-        xgene_enet_napi_enable(pdata);
 
         if (pdata->phy_mode == PHY_INTERFACE_MODE_RGMII)
                 phy_start(pdata->phy_dev);
@@ -715,13 +715,13 @@ static int xgene_enet_close(struct net_device *ndev)
         else
                 cancel_delayed_work_sync(&pdata->link_work);
 
-        xgene_enet_napi_disable(pdata);
-        xgene_enet_free_irq(ndev);
-        xgene_enet_process_ring(pdata->rx_ring, -1);
-
         mac_ops->tx_disable(pdata);
         mac_ops->rx_disable(pdata);
 
+        xgene_enet_free_irq(ndev);
+        xgene_enet_napi_disable(pdata);
+        xgene_enet_process_ring(pdata->rx_ring, -1);
+
         return 0;
 }
 
@@ -1474,15 +1474,15 @@ static int xgene_enet_probe(struct platform_device *pdev)
         }
         ndev->hw_features = ndev->features;
 
-        ret = register_netdev(ndev);
+        ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64));
         if (ret) {
-                netdev_err(ndev, "Failed to register netdev\n");
+                netdev_err(ndev, "No usable DMA configuration\n");
                 goto err;
         }
 
-        ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64));
+        ret = register_netdev(ndev);
         if (ret) {
-                netdev_err(ndev, "No usable DMA configuration\n");
+                netdev_err(ndev, "Failed to register netdev\n");
                 goto err;
         }
 
@@ -1490,14 +1490,17 @@ static int xgene_enet_probe(struct platform_device *pdev)
         if (ret)
                 goto err;
 
-        xgene_enet_napi_add(pdata);
         mac_ops = pdata->mac_ops;
-        if (pdata->phy_mode == PHY_INTERFACE_MODE_RGMII)
+        if (pdata->phy_mode == PHY_INTERFACE_MODE_RGMII) {
                 ret = xgene_enet_mdio_config(pdata);
-        else
+                if (ret)
+                        goto err;
+        } else {
                 INIT_DELAYED_WORK(&pdata->link_work, mac_ops->link_state);
+        }
 
-        return ret;
+        xgene_enet_napi_add(pdata);
+        return 0;
 err:
         unregister_netdev(ndev);
         free_netdev(ndev);
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index c8af3ce3ea38..bd377a6b067d 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1534,6 +1534,8 @@ static const struct pci_device_id alx_pci_tbl[] = {
           .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
         { PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_E2200),
           .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
+        { PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_E2400),
+          .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
         { PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_AR8162),
           .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
         { PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_AR8171) },
diff --git a/drivers/net/ethernet/atheros/alx/reg.h b/drivers/net/ethernet/atheros/alx/reg.h
index af006b44b2a6..0959e6824cb6 100644
--- a/drivers/net/ethernet/atheros/alx/reg.h
+++ b/drivers/net/ethernet/atheros/alx/reg.h
@@ -37,6 +37,7 @@
 
 #define ALX_DEV_ID_AR8161                               0x1091
 #define ALX_DEV_ID_E2200                                0xe091
+#define ALX_DEV_ID_E2400                                0xe0a1
 #define ALX_DEV_ID_AR8162                               0x1090
 #define ALX_DEV_ID_AR8171                               0x10A1
 #define ALX_DEV_ID_AR8172                               0x10A0
diff --git a/drivers/net/ethernet/aurora/Kconfig b/drivers/net/ethernet/aurora/Kconfig
new file mode 100644
index 000000000000..a3c7106fdf85
--- /dev/null
+++ b/drivers/net/ethernet/aurora/Kconfig
@@ -0,0 +1,20 @@
+config NET_VENDOR_AURORA
+        bool "Aurora VLSI devices"
+        help
+          If you have a network (Ethernet) device belonging to this class,
+          say Y.
+
+          Note that the answer to this question doesn't directly affect the
+          kernel: saying N will just cause the configurator to skip all
+          questions about Aurora devices. If you say Y, you will be asked
+          for your specific device in the following questions.
+
+if NET_VENDOR_AURORA
+
+config AURORA_NB8800
+        tristate "Aurora AU-NB8800 support"
+        select PHYLIB
+        help
+         Support for the AU-NB8800 gigabit Ethernet controller.
+
+endif
diff --git a/drivers/net/ethernet/aurora/Makefile b/drivers/net/ethernet/aurora/Makefile
new file mode 100644
index 000000000000..6cb528a2fc26
--- /dev/null
+++ b/drivers/net/ethernet/aurora/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_AURORA_NB8800) += nb8800.o
diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
new file mode 100644
index 000000000000..ecc4a334c507
--- /dev/null
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -0,0 +1,1552 @@
+/*
+ * Copyright (C) 2015 Mans Rullgard <mans@mansr.com>
+ *
+ * Mostly rewritten, based on driver from Sigma Designs.  Original
+ * copyright notice below.
+ *
+ *
+ * Driver for tangox SMP864x/SMP865x/SMP867x/SMP868x builtin Ethernet Mac.
+ *
+ * Copyright (C) 2005 Maxime Bizon <mbizon@freebox.fr>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/etherdevice.h>
+#include <linux/delay.h>
+#include <linux/ethtool.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/of_device.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include <linux/dma-mapping.h>
+#include <linux/phy.h>
+#include <linux/cache.h>
+#include <linux/jiffies.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <asm/barrier.h>
+
+#include "nb8800.h"
+
+static void nb8800_tx_done(struct net_device *dev);
+static int nb8800_dma_stop(struct net_device *dev);
+
+static inline u8 nb8800_readb(struct nb8800_priv *priv, int reg)
+{
+        return readb_relaxed(priv->base + reg);
+}
+
+static inline u32 nb8800_readl(struct nb8800_priv *priv, int reg)
+{
+        return readl_relaxed(priv->base + reg);
+}
+
+static inline void nb8800_writeb(struct nb8800_priv *priv, int reg, u8 val)
+{
+        writeb_relaxed(val, priv->base + reg);
+}
+
+static inline void nb8800_writew(struct nb8800_priv *priv, int reg, u16 val)
+{
+        writew_relaxed(val, priv->base + reg);
+}
+
+static inline void nb8800_writel(struct nb8800_priv *priv, int reg, u32 val)
+{
+        writel_relaxed(val, priv->base + reg);
+}
+
+static inline void nb8800_maskb(struct nb8800_priv *priv, int reg,
+                                u32 mask, u32 val)
+{
+        u32 old = nb8800_readb(priv, reg);
+        u32 new = (old & ~mask) | (val & mask);
+
+        if (new != old)
+                nb8800_writeb(priv, reg, new);
+}
+
+static inline void nb8800_maskl(struct nb8800_priv *priv, int reg,
+                                u32 mask, u32 val)
+{
+        u32 old = nb8800_readl(priv, reg);
+        u32 new = (old & ~mask) | (val & mask);
+
+        if (new != old)
+                nb8800_writel(priv, reg, new);
+}
+
+static inline void nb8800_modb(struct nb8800_priv *priv, int reg, u8 bits,
+                               bool set)
+{
+        nb8800_maskb(priv, reg, bits, set ? bits : 0);
+}
+
+static inline void nb8800_setb(struct nb8800_priv *priv, int reg, u8 bits)
+{
+        nb8800_maskb(priv, reg, bits, bits);
+}
+
+static inline void nb8800_clearb(struct nb8800_priv *priv, int reg, u8 bits)
+{
+        nb8800_maskb(priv, reg, bits, 0);
+}
+
+static inline void nb8800_modl(struct nb8800_priv *priv, int reg, u32 bits,
+                               bool set)
+{
+        nb8800_maskl(priv, reg, bits, set ? bits : 0);
+}
+
+static inline void nb8800_setl(struct nb8800_priv *priv, int reg, u32 bits)
+{
+        nb8800_maskl(priv, reg, bits, bits);
+}
+
+static inline void nb8800_clearl(struct nb8800_priv *priv, int reg, u32 bits)
+{
+        nb8800_maskl(priv, reg, bits, 0);
+}
+
+static int nb8800_mdio_wait(struct mii_bus *bus)
+{
+        struct nb8800_priv *priv = bus->priv;
+        u32 val;
+
+        return readl_poll_timeout_atomic(priv->base + NB8800_MDIO_CMD,
+                                         val, !(val & MDIO_CMD_GO), 1, 1000);
+}
+
+static int nb8800_mdio_cmd(struct mii_bus *bus, u32 cmd)
+{
+        struct nb8800_priv *priv = bus->priv;
+        int err;
+
+        err = nb8800_mdio_wait(bus);
+        if (err)
+                return err;
+
+        nb8800_writel(priv, NB8800_MDIO_CMD, cmd);
+        udelay(10);
+        nb8800_writel(priv, NB8800_MDIO_CMD, cmd | MDIO_CMD_GO);
+
+        return nb8800_mdio_wait(bus);
+}
+
+static int nb8800_mdio_read(struct mii_bus *bus, int phy_id, int reg)
+{
+        struct nb8800_priv *priv = bus->priv;
+        u32 val;
+        int err;
+
+        err = nb8800_mdio_cmd(bus, MDIO_CMD_ADDR(phy_id) | MDIO_CMD_REG(reg));
+        if (err)
+                return err;
+
+        val = nb8800_readl(priv, NB8800_MDIO_STS);
+        if (val & MDIO_STS_ERR)
+                return 0xffff;
+
+        return val & 0xffff;
+}
+
+static int nb8800_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 val)
+{
+        u32 cmd = MDIO_CMD_ADDR(phy_id) | MDIO_CMD_REG(reg) |
+                MDIO_CMD_DATA(val) | MDIO_CMD_WR;
+
+        return nb8800_mdio_cmd(bus, cmd);
+}
+
+static void nb8800_mac_tx(struct net_device *dev, bool enable)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+
+        while (nb8800_readl(priv, NB8800_TXC_CR) & TCR_EN)
+                cpu_relax();
+
+        nb8800_modb(priv, NB8800_TX_CTL1, TX_EN, enable);
+}
+
+static void nb8800_mac_rx(struct net_device *dev, bool enable)
+{
+        nb8800_modb(netdev_priv(dev), NB8800_RX_CTL, RX_EN, enable);
+}
+
+static void nb8800_mac_af(struct net_device *dev, bool enable)
+{
+        nb8800_modb(netdev_priv(dev), NB8800_RX_CTL, RX_AF_EN, enable);
+}
+
+static void nb8800_start_rx(struct net_device *dev)
+{
+        nb8800_setl(netdev_priv(dev), NB8800_RXC_CR, RCR_EN);
+}
+
+static int nb8800_alloc_rx(struct net_device *dev, unsigned int i, bool napi)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        struct nb8800_rx_desc *rxd = &priv->rx_descs[i];
+        struct nb8800_rx_buf *rxb = &priv->rx_bufs[i];
+        int size = L1_CACHE_ALIGN(RX_BUF_SIZE);
+        dma_addr_t dma_addr;
+        struct page *page;
+        unsigned long offset;
+        void *data;
+
+        data = napi ? napi_alloc_frag(size) : netdev_alloc_frag(size);
+        if (!data)
+                return -ENOMEM;
+
+        page = virt_to_head_page(data);
+        offset = data - page_address(page);
+
+        dma_addr = dma_map_page(&dev->dev, page, offset, RX_BUF_SIZE,
+                                DMA_FROM_DEVICE);
+
+        if (dma_mapping_error(&dev->dev, dma_addr)) {
+                skb_free_frag(data);
+                return -ENOMEM;
+        }
+
+        rxb->page = page;
+        rxb->offset = offset;
+        rxd->desc.s_addr = dma_addr;
+
+        return 0;
+}
+
+static void nb8800_receive(struct net_device *dev, unsigned int i,
+                           unsigned int len)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        struct nb8800_rx_desc *rxd = &priv->rx_descs[i];
+        struct page *page = priv->rx_bufs[i].page;
+        int offset = priv->rx_bufs[i].offset;
+        void *data = page_address(page) + offset;
+        dma_addr_t dma = rxd->desc.s_addr;
+        struct sk_buff *skb;
+        unsigned int size;
+        int err;
+
+        size = len <= RX_COPYBREAK ? len : RX_COPYHDR;
+
+        skb = napi_alloc_skb(&priv->napi, size);
+        if (!skb) {
+                netdev_err(dev, "rx skb allocation failed\n");
+                dev->stats.rx_dropped++;
+                return;
+        }
+
+        if (len <= RX_COPYBREAK) {
+                dma_sync_single_for_cpu(&dev->dev, dma, len, DMA_FROM_DEVICE);
+                memcpy(skb_put(skb, len), data, len);
+                dma_sync_single_for_device(&dev->dev, dma, len,
+                                           DMA_FROM_DEVICE);
+        } else {
+                err = nb8800_alloc_rx(dev, i, true);
+                if (err) {
+                        netdev_err(dev, "rx buffer allocation failed\n");
+                        dev->stats.rx_dropped++;
+                        return;
+                }
+
+                dma_unmap_page(&dev->dev, dma, RX_BUF_SIZE, DMA_FROM_DEVICE);
+                memcpy(skb_put(skb, RX_COPYHDR), data, RX_COPYHDR);
+                skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
+                                offset + RX_COPYHDR, len - RX_COPYHDR,
+                                RX_BUF_SIZE);
+        }
+
+        skb->protocol = eth_type_trans(skb, dev);
+        napi_gro_receive(&priv->napi, skb);
+}
+
+static void nb8800_rx_error(struct net_device *dev, u32 report)
+{
+        if (report & RX_LENGTH_ERR)
+                dev->stats.rx_length_errors++;
+
+        if (report & RX_FCS_ERR)
+                dev->stats.rx_crc_errors++;
+
+        if (report & RX_FIFO_OVERRUN)
+                dev->stats.rx_fifo_errors++;
+
+        if (report & RX_ALIGNMENT_ERROR)
+                dev->stats.rx_frame_errors++;
+
+        dev->stats.rx_errors++;
+}
+
+static int nb8800_poll(struct napi_struct *napi, int budget)
+{
+        struct net_device *dev = napi->dev;
+        struct nb8800_priv *priv = netdev_priv(dev);
+        struct nb8800_rx_desc *rxd;
+        unsigned int last = priv->rx_eoc;
+        unsigned int next;
+        int work = 0;
+
+        nb8800_tx_done(dev);
+
+again:
+        while (work < budget) {
+                struct nb8800_rx_buf *rxb;
+                unsigned int len;
+
+                next = (last + 1) % RX_DESC_COUNT;
+
+                rxb = &priv->rx_bufs[next];
+                rxd = &priv->rx_descs[next];
+
+                if (!rxd->report)
+                        break;
+
+                len = RX_BYTES_TRANSFERRED(rxd->report);
+
+                if (IS_RX_ERROR(rxd->report))
+                        nb8800_rx_error(dev, rxd->report);
+                else
+                        nb8800_receive(dev, next, len);
+
+                dev->stats.rx_packets++;
+                dev->stats.rx_bytes += len;
+
+                if (rxd->report & RX_MULTICAST_PKT)
+                        dev->stats.multicast++;
+
+                rxd->report = 0;
+                last = next;
+                work++;
+        }
+
+        if (work) {
+                priv->rx_descs[last].desc.config |= DESC_EOC;
+                wmb();  /* ensure new EOC is written before clearing old */
+                priv->rx_descs[priv->rx_eoc].desc.config &= ~DESC_EOC;
+                priv->rx_eoc = last;
+                nb8800_start_rx(dev);
+        }
+
+        if (work < budget) {
+                nb8800_writel(priv, NB8800_RX_ITR, priv->rx_itr_irq);
+
+                /* If a packet arrived after we last checked but
+                 * before writing RX_ITR, the interrupt will be
+                 * delayed, so we retrieve it now.
+                 */
+                if (priv->rx_descs[next].report)
+                        goto again;
+
+                napi_complete_done(napi, work);
+        }
+
+        return work;
+}
+
+static void __nb8800_tx_dma_start(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        struct nb8800_tx_buf *txb;
+        u32 txc_cr;
+
+        txb = &priv->tx_bufs[priv->tx_queue];
+        if (!txb->ready)
+                return;
+
+        txc_cr = nb8800_readl(priv, NB8800_TXC_CR);
+        if (txc_cr & TCR_EN)
+                return;
+
+        nb8800_writel(priv, NB8800_TX_DESC_ADDR, txb->dma_desc);
+        wmb();          /* ensure desc addr is written before starting DMA */
+        nb8800_writel(priv, NB8800_TXC_CR, txc_cr | TCR_EN);
+
+        priv->tx_queue = (priv->tx_queue + txb->chain_len) % TX_DESC_COUNT;
+}
+
+static void nb8800_tx_dma_start(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+
+        spin_lock_irq(&priv->tx_lock);
+        __nb8800_tx_dma_start(dev);
+        spin_unlock_irq(&priv->tx_lock);
+}
+
+static void nb8800_tx_dma_start_irq(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+
+        spin_lock(&priv->tx_lock);
+        __nb8800_tx_dma_start(dev);
+        spin_unlock(&priv->tx_lock);
+}
+
+static int nb8800_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        struct nb8800_tx_desc *txd;
+        struct nb8800_tx_buf *txb;
+        struct nb8800_dma_desc *desc;
+        dma_addr_t dma_addr;
+        unsigned int dma_len;
+        unsigned int align;
+        unsigned int next;
+
+        if (atomic_read(&priv->tx_free) <= NB8800_DESC_LOW) {
+                netif_stop_queue(dev);
+                return NETDEV_TX_BUSY;
+        }
+
+        align = (8 - (uintptr_t)skb->data) & 7;
+
+        dma_len = skb->len - align;
+        dma_addr = dma_map_single(&dev->dev, skb->data + align,
+                                  dma_len, DMA_TO_DEVICE);
+
+        if (dma_mapping_error(&dev->dev, dma_addr)) {
+                netdev_err(dev, "tx dma mapping error\n");
+                kfree_skb(skb);
+                dev->stats.tx_dropped++;
+                return NETDEV_TX_OK;
+        }
+
+        if (atomic_dec_return(&priv->tx_free) <= NB8800_DESC_LOW) {
+                netif_stop_queue(dev);
+                skb->xmit_more = 0;
+        }
+
+        next = priv->tx_next;
+        txb = &priv->tx_bufs[next];
+        txd = &priv->tx_descs[next];
+        desc = &txd->desc[0];
+
+        next = (next + 1) % TX_DESC_COUNT;
+
+        if (align) {
+                memcpy(txd->buf, skb->data, align);
+
+                desc->s_addr =
+                        txb->dma_desc + offsetof(struct nb8800_tx_desc, buf);
+                desc->n_addr = txb->dma_desc + sizeof(txd->desc[0]);
+                desc->config = DESC_BTS(2) | DESC_DS | align;
+
+                desc++;
+        }
+
+        desc->s_addr = dma_addr;
+        desc->n_addr = priv->tx_bufs[next].dma_desc;
+        desc->config = DESC_BTS(2) | DESC_DS | DESC_EOF | dma_len;
+
+        if (!skb->xmit_more)
+                desc->config |= DESC_EOC;
+
+        txb->skb = skb;
+        txb->dma_addr = dma_addr;
+        txb->dma_len = dma_len;
+
+        if (!priv->tx_chain) {
+                txb->chain_len = 1;
+                priv->tx_chain = txb;
+        } else {
+                priv->tx_chain->chain_len++;
+        }
+
+        netdev_sent_queue(dev, skb->len);
+
+        priv->tx_next = next;
+
+        if (!skb->xmit_more) {
+                smp_wmb();
+                priv->tx_chain->ready = true;
+                priv->tx_chain = NULL;
+                nb8800_tx_dma_start(dev);
+        }
+
+        return NETDEV_TX_OK;
+}
+
+static void nb8800_tx_error(struct net_device *dev, u32 report)
+{
+        if (report & TX_LATE_COLLISION)
+                dev->stats.collisions++;
+
+        if (report & TX_PACKET_DROPPED)
+                dev->stats.tx_dropped++;
+
+        if (report & TX_FIFO_UNDERRUN)
+                dev->stats.tx_fifo_errors++;
+
+        dev->stats.tx_errors++;
+}
+
+static void nb8800_tx_done(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        unsigned int limit = priv->tx_next;
+        unsigned int done = priv->tx_done;
+        unsigned int packets = 0;
+        unsigned int len = 0;
+
+        while (done != limit) {
+                struct nb8800_tx_desc *txd = &priv->tx_descs[done];
+                struct nb8800_tx_buf *txb = &priv->tx_bufs[done];
+                struct sk_buff *skb;
+
+                if (!txd->report)
+                        break;
+
+                skb = txb->skb;
+                len += skb->len;
+
+                dma_unmap_single(&dev->dev, txb->dma_addr, txb->dma_len,
+                                 DMA_TO_DEVICE);
+
+                if (IS_TX_ERROR(txd->report)) {
+                        nb8800_tx_error(dev, txd->report);
+                        kfree_skb(skb);
+                } else {
+                        consume_skb(skb);
+                }
+
+                dev->stats.tx_packets++;
+                dev->stats.tx_bytes += TX_BYTES_TRANSFERRED(txd->report);
+                dev->stats.collisions += TX_EARLY_COLLISIONS(txd->report);
+
+                txb->skb = NULL;
+                txb->ready = false;
+                txd->report = 0;
+
+                done = (done + 1) % TX_DESC_COUNT;
+                packets++;
+        }
+
+        if (packets) {
+                smp_mb__before_atomic();
+                atomic_add(packets, &priv->tx_free);
+                netdev_completed_queue(dev, packets, len);
+                netif_wake_queue(dev);
+                priv->tx_done = done;
+        }
+}
+
+static irqreturn_t nb8800_irq(int irq, void *dev_id)
+{
+        struct net_device *dev = dev_id;
+        struct nb8800_priv *priv = netdev_priv(dev);
+        irqreturn_t ret = IRQ_NONE;
+        u32 val;
+
+        /* tx interrupt */
+        val = nb8800_readl(priv, NB8800_TXC_SR);
+        if (val) {
+                nb8800_writel(priv, NB8800_TXC_SR, val);
+
+                if (val & TSR_DI)
+                        nb8800_tx_dma_start_irq(dev);
+
+                if (val & TSR_TI)
+                        napi_schedule_irqoff(&priv->napi);
+
+                if (unlikely(val & TSR_DE))
+                        netdev_err(dev, "TX DMA error\n");
+
+                /* should never happen with automatic status retrieval */
+                if (unlikely(val & TSR_TO))
+                        netdev_err(dev, "TX Status FIFO overflow\n");
+
+                ret = IRQ_HANDLED;
+        }
+
+        /* rx interrupt */
+        val = nb8800_readl(priv, NB8800_RXC_SR);
+        if (val) {
+                nb8800_writel(priv, NB8800_RXC_SR, val);
+
+                if (likely(val & (RSR_RI | RSR_DI))) {
+                        nb8800_writel(priv, NB8800_RX_ITR, priv->rx_itr_poll);
+                        napi_schedule_irqoff(&priv->napi);
+                }
+
+                if (unlikely(val & RSR_DE))
+                        netdev_err(dev, "RX DMA error\n");
+
+                /* should never happen with automatic status retrieval */
+                if (unlikely(val & RSR_RO))
+                        netdev_err(dev, "RX Status FIFO overflow\n");
+
+                ret = IRQ_HANDLED;
+        }
+
+        return ret;
+}
+
+static void nb8800_mac_config(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        bool gigabit = priv->speed == SPEED_1000;
+        u32 mac_mode_mask = RGMII_MODE | HALF_DUPLEX | GMAC_MODE;
+        u32 mac_mode = 0;
+        u32 slot_time;
+        u32 phy_clk;
+        u32 ict;
+
+        if (!priv->duplex)
+                mac_mode |= HALF_DUPLEX;
+
+        if (gigabit) {
+                if (priv->phy_mode == PHY_INTERFACE_MODE_RGMII)
+                        mac_mode |= RGMII_MODE;
+
+                mac_mode |= GMAC_MODE;
+                phy_clk = 125000000;
+
+                /* Should be 512 but register is only 8 bits */
+                slot_time = 255;
+        } else {
+                phy_clk = 25000000;
+                slot_time = 128;
+        }
+
+        ict = DIV_ROUND_UP(phy_clk, clk_get_rate(priv->clk));
+
+        nb8800_writeb(priv, NB8800_IC_THRESHOLD, ict);
+        nb8800_writeb(priv, NB8800_SLOT_TIME, slot_time);
+        nb8800_maskb(priv, NB8800_MAC_MODE, mac_mode_mask, mac_mode);
+}
+
+static void nb8800_pause_config(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        struct phy_device *phydev = priv->phydev;
+        u32 rxcr;
+
+        if (priv->pause_aneg) {
+                if (!phydev || !phydev->link)
+                        return;
+
+                priv->pause_rx = phydev->pause;
+                priv->pause_tx = phydev->pause ^ phydev->asym_pause;
+        }
+
+        nb8800_modb(priv, NB8800_RX_CTL, RX_PAUSE_EN, priv->pause_rx);
+
+        rxcr = nb8800_readl(priv, NB8800_RXC_CR);
+        if (!!(rxcr & RCR_FL) == priv->pause_tx)
+                return;
+
+        if (netif_running(dev)) {
+                napi_disable(&priv->napi);
+                netif_tx_lock_bh(dev);
+                nb8800_dma_stop(dev);
+                nb8800_modl(priv, NB8800_RXC_CR, RCR_FL, priv->pause_tx);
+                nb8800_start_rx(dev);
+                netif_tx_unlock_bh(dev);
+                napi_enable(&priv->napi);
+        } else {
+                nb8800_modl(priv, NB8800_RXC_CR, RCR_FL, priv->pause_tx);
+        }
+}
+
+static void nb8800_link_reconfigure(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        struct phy_device *phydev = priv->phydev;
+        int change = 0;
+
+        if (phydev->link) {
+                if (phydev->speed != priv->speed) {
+                        priv->speed = phydev->speed;
+                        change = 1;
+                }
+
+                if (phydev->duplex != priv->duplex) {
+                        priv->duplex = phydev->duplex;
+                        change = 1;
+                }
+
+                if (change)
+                        nb8800_mac_config(dev);
+
+                nb8800_pause_config(dev);
+        }
+
+        if (phydev->link != priv->link) {
+                priv->link = phydev->link;
+                change = 1;
+        }
+
+        if (change)
+                phy_print_status(priv->phydev);
+}
+
+static void nb8800_update_mac_addr(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        int i;
+
+        for (i = 0; i < ETH_ALEN; i++)
+                nb8800_writeb(priv, NB8800_SRC_ADDR(i), dev->dev_addr[i]);
+
+        for (i = 0; i < ETH_ALEN; i++)
+                nb8800_writeb(priv, NB8800_UC_ADDR(i), dev->dev_addr[i]);
+}
+
+static int nb8800_set_mac_address(struct net_device *dev, void *addr)
+{
+        struct sockaddr *sock = addr;
+
+        if (netif_running(dev))
+                return -EBUSY;
+
+        ether_addr_copy(dev->dev_addr, sock->sa_data);
+        nb8800_update_mac_addr(dev);
+
+        return 0;
+}
+
+static void nb8800_mc_init(struct net_device *dev, int val)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+
+        nb8800_writeb(priv, NB8800_MC_INIT, val);
+        readb_poll_timeout_atomic(priv->base + NB8800_MC_INIT, val, !val,
+                                  1, 1000);
+}
+
+static void nb8800_set_rx_mode(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        struct netdev_hw_addr *ha;
+        int i;
+
+        if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) {
+                nb8800_mac_af(dev, false);
+                return;
+        }
+
+        nb8800_mac_af(dev, true);
+        nb8800_mc_init(dev, 0);
+
+        netdev_for_each_mc_addr(ha, dev) {
+                for (i = 0; i < ETH_ALEN; i++)
+                        nb8800_writeb(priv, NB8800_MC_ADDR(i), ha->addr[i]);
+
+                nb8800_mc_init(dev, 0xff);
+        }
+}
+
+#define RX_DESC_SIZE (RX_DESC_COUNT * sizeof(struct nb8800_rx_desc))
+#define TX_DESC_SIZE (TX_DESC_COUNT * sizeof(struct nb8800_tx_desc))
+
+static void nb8800_dma_free(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        unsigned int i;
+
+        if (priv->rx_bufs) {
+                for (i = 0; i < RX_DESC_COUNT; i++)
+                        if (priv->rx_bufs[i].page)
+                                put_page(priv->rx_bufs[i].page);
+
+                kfree(priv->rx_bufs);
+                priv->rx_bufs = NULL;
+        }
+
+        if (priv->tx_bufs) {
+                for (i = 0; i < TX_DESC_COUNT; i++)
+                        kfree_skb(priv->tx_bufs[i].skb);
+
+                kfree(priv->tx_bufs);
+                priv->tx_bufs = NULL;
+        }
+
+        if (priv->rx_descs) {
+                dma_free_coherent(dev->dev.parent, RX_DESC_SIZE, priv->rx_descs,
+                                  priv->rx_desc_dma);
+                priv->rx_descs = NULL;
+        }
+
+        if (priv->tx_descs) {
+                dma_free_coherent(dev->dev.parent, TX_DESC_SIZE, priv->tx_descs,
+                                  priv->tx_desc_dma);
+                priv->tx_descs = NULL;
+        }
+}
+
+static void nb8800_dma_reset(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        struct nb8800_rx_desc *rxd;
+        struct nb8800_tx_desc *txd;
+        unsigned int i;
+
+        for (i = 0; i < RX_DESC_COUNT; i++) {
+                dma_addr_t rx_dma = priv->rx_desc_dma + i * sizeof(*rxd);
+
+                rxd = &priv->rx_descs[i];
+                rxd->desc.n_addr = rx_dma + sizeof(*rxd);
+                rxd->desc.r_addr =
+                        rx_dma + offsetof(struct nb8800_rx_desc, report);
+                rxd->desc.config = priv->rx_dma_config;
+                rxd->report = 0;
+        }
+
+        rxd->desc.n_addr = priv->rx_desc_dma;
+        rxd->desc.config |= DESC_EOC;
+
+        priv->rx_eoc = RX_DESC_COUNT - 1;
+
+        for (i = 0; i < TX_DESC_COUNT; i++) {
+                struct nb8800_tx_buf *txb = &priv->tx_bufs[i];
+                dma_addr_t r_dma = txb->dma_desc +
+                        offsetof(struct nb8800_tx_desc, report);
+
+                txd = &priv->tx_descs[i];
+                txd->desc[0].r_addr = r_dma;
+                txd->desc[1].r_addr = r_dma;
+                txd->report = 0;
+        }
+
+        priv->tx_next = 0;
+        priv->tx_queue = 0;
+        priv->tx_done = 0;
+        atomic_set(&priv->tx_free, TX_DESC_COUNT);
+
+        nb8800_writel(priv, NB8800_RX_DESC_ADDR, priv->rx_desc_dma);
+
+        wmb();          /* ensure all setup is written before starting */
+}
+
+static int nb8800_dma_init(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        unsigned int n_rx = RX_DESC_COUNT;
+        unsigned int n_tx = TX_DESC_COUNT;
+        unsigned int i;
+        int err;
+
+        priv->rx_descs = dma_alloc_coherent(dev->dev.parent, RX_DESC_SIZE,
+                                            &priv->rx_desc_dma, GFP_KERNEL);
+        if (!priv->rx_descs)
+                goto err_out;
+
+        priv->rx_bufs = kcalloc(n_rx, sizeof(*priv->rx_bufs), GFP_KERNEL);
+        if (!priv->rx_bufs)
+                goto err_out;
+
+        for (i = 0; i < n_rx; i++) {
+                err = nb8800_alloc_rx(dev, i, false);
+                if (err)
+                        goto err_out;
+        }
+
+        priv->tx_descs = dma_alloc_coherent(dev->dev.parent, TX_DESC_SIZE,
+                                            &priv->tx_desc_dma, GFP_KERNEL);
+        if (!priv->tx_descs)
+                goto err_out;
+
+        priv->tx_bufs = kcalloc(n_tx, sizeof(*priv->tx_bufs), GFP_KERNEL);
+        if (!priv->tx_bufs)
+                goto err_out;
+
+        for (i = 0; i < n_tx; i++)
+                priv->tx_bufs[i].dma_desc =
+                        priv->tx_desc_dma + i * sizeof(struct nb8800_tx_desc);
+
+        nb8800_dma_reset(dev);
+
+        return 0;
+
+err_out:
+        nb8800_dma_free(dev);
+
+        return -ENOMEM;
+}
+
+static int nb8800_dma_stop(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        struct nb8800_tx_buf *txb = &priv->tx_bufs[0];
+        struct nb8800_tx_desc *txd = &priv->tx_descs[0];
+        int retry = 5;
+        u32 txcr;
+        u32 rxcr;
+        int err;
+        unsigned int i;
+
+        /* wait for tx to finish */
+        err = readl_poll_timeout_atomic(priv->base + NB8800_TXC_CR, txcr,
+                                        !(txcr & TCR_EN) &&
+                                        priv->tx_done == priv->tx_next,
+                                        1000, 1000000);
+        if (err)
+                return err;
+
+        /* The rx DMA only stops if it reaches the end of chain.
+         * To make this happen, we set the EOC flag on all rx
+         * descriptors, put the device in loopback mode, and send
+         * a few dummy frames.  The interrupt handler will ignore
+         * these since NAPI is disabled and no real frames are in
+         * the tx queue.
+         */
+
+        for (i = 0; i < RX_DESC_COUNT; i++)
+                priv->rx_descs[i].desc.config |= DESC_EOC;
+
+        txd->desc[0].s_addr =
+                txb->dma_desc + offsetof(struct nb8800_tx_desc, buf);
+        txd->desc[0].config = DESC_BTS(2) | DESC_DS | DESC_EOF | DESC_EOC | 8;
+        memset(txd->buf, 0, sizeof(txd->buf));
+
+        nb8800_mac_af(dev, false);
+        nb8800_setb(priv, NB8800_MAC_MODE, LOOPBACK_EN);
+
+        do {
+                nb8800_writel(priv, NB8800_TX_DESC_ADDR, txb->dma_desc);
+                wmb();
+                nb8800_writel(priv, NB8800_TXC_CR, txcr | TCR_EN);
+
+                err = readl_poll_timeout_atomic(priv->base + NB8800_RXC_CR,
+                                                rxcr, !(rxcr & RCR_EN),
+                                                1000, 100000);
+        } while (err && --retry);
+
+        nb8800_mac_af(dev, true);
+        nb8800_clearb(priv, NB8800_MAC_MODE, LOOPBACK_EN);
+        nb8800_dma_reset(dev);
+
+        return retry ? 0 : -ETIMEDOUT;
+}
+
+static void nb8800_pause_adv(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        u32 adv = 0;
+
+        if (!priv->phydev)
+                return;
+
+        if (priv->pause_rx)
+                adv |= ADVERTISED_Pause | ADVERTISED_Asym_Pause;
+        if (priv->pause_tx)
+                adv ^= ADVERTISED_Asym_Pause;
+
+        priv->phydev->supported |= adv;
+        priv->phydev->advertising |= adv;
+}
+
+static int nb8800_open(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        int err;
+
+        /* clear any pending interrupts */
+        nb8800_writel(priv, NB8800_RXC_SR, 0xf);
+        nb8800_writel(priv, NB8800_TXC_SR, 0xf);
+
+        err = nb8800_dma_init(dev);
+        if (err)
+                return err;
+
+        err = request_irq(dev->irq, nb8800_irq, 0, dev_name(&dev->dev), dev);
+        if (err)
+                goto err_free_dma;
+
+        nb8800_mac_rx(dev, true);
+        nb8800_mac_tx(dev, true);
+
+        priv->phydev = of_phy_connect(dev, priv->phy_node,
+                                      nb8800_link_reconfigure, 0,
+                                      priv->phy_mode);
+        if (!priv->phydev)
+                goto err_free_irq;
+
+        nb8800_pause_adv(dev);
+
+        netdev_reset_queue(dev);
+        napi_enable(&priv->napi);
+        netif_start_queue(dev);
+
+        nb8800_start_rx(dev);
+        phy_start(priv->phydev);
+
+        return 0;
+
+err_free_irq:
+        free_irq(dev->irq, dev);
+err_free_dma:
+        nb8800_dma_free(dev);
+
+        return err;
+}
+
+static int nb8800_stop(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+
+        phy_stop(priv->phydev);
+
+        netif_stop_queue(dev);
+        napi_disable(&priv->napi);
+
+        nb8800_dma_stop(dev);
+        nb8800_mac_rx(dev, false);
+        nb8800_mac_tx(dev, false);
+
+        phy_disconnect(priv->phydev);
+        priv->phydev = NULL;
+
+        free_irq(dev->irq, dev);
+
+        nb8800_dma_free(dev);
+
+        return 0;
+}
+
+static int nb8800_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+
+        return phy_mii_ioctl(priv->phydev, rq, cmd);
+}
+
+static const struct net_device_ops nb8800_netdev_ops = {
+        .ndo_open               = nb8800_open,
+        .ndo_stop               = nb8800_stop,
+        .ndo_start_xmit         = nb8800_xmit,
+        .ndo_set_mac_address    = nb8800_set_mac_address,
+        .ndo_set_rx_mode        = nb8800_set_rx_mode,
+        .ndo_do_ioctl           = nb8800_ioctl,
+        .ndo_change_mtu         = eth_change_mtu,
+        .ndo_validate_addr      = eth_validate_addr,
+};
+
+static int nb8800_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+
+        if (!priv->phydev)
+                return -ENODEV;
+
+        return phy_ethtool_gset(priv->phydev, cmd);
+}
+
+static int nb8800_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+
+        if (!priv->phydev)
+                return -ENODEV;
+
+        return phy_ethtool_sset(priv->phydev, cmd);
+}
+
+static int nb8800_nway_reset(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+
+        if (!priv->phydev)
+                return -ENODEV;
+
+        return genphy_restart_aneg(priv->phydev);
+}
+
+static void nb8800_get_pauseparam(struct net_device *dev,
+                                  struct ethtool_pauseparam *pp)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+
+        pp->autoneg = priv->pause_aneg;
+        pp->rx_pause = priv->pause_rx;
+        pp->tx_pause = priv->pause_tx;
+}
+
+static int nb8800_set_pauseparam(struct net_device *dev,
+                                 struct ethtool_pauseparam *pp)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+
+        priv->pause_aneg = pp->autoneg;
+        priv->pause_rx = pp->rx_pause;
+        priv->pause_tx = pp->tx_pause;
+
+        nb8800_pause_adv(dev);
+
+        if (!priv->pause_aneg)
+                nb8800_pause_config(dev);
+        else if (priv->phydev)
+                phy_start_aneg(priv->phydev);
+
+        return 0;
+}
+
+static const char nb8800_stats_names[][ETH_GSTRING_LEN] = {
+        "rx_bytes_ok",
+        "rx_frames_ok",
+        "rx_undersize_frames",
+        "rx_fragment_frames",
+        "rx_64_byte_frames",
+        "rx_127_byte_frames",
+        "rx_255_byte_frames",
+        "rx_511_byte_frames",
+        "rx_1023_byte_frames",
+        "rx_max_size_frames",
+        "rx_oversize_frames",
+        "rx_bad_fcs_frames",
+        "rx_broadcast_frames",
+        "rx_multicast_frames",
+        "rx_control_frames",
+        "rx_pause_frames",
+        "rx_unsup_control_frames",
+        "rx_align_error_frames",
+        "rx_overrun_frames",
+        "rx_jabber_frames",
+        "rx_bytes",
+        "rx_frames",
+
+        "tx_bytes_ok",
+        "tx_frames_ok",
+        "tx_64_byte_frames",
+        "tx_127_byte_frames",
+        "tx_255_byte_frames",
+        "tx_511_byte_frames",
+        "tx_1023_byte_frames",
+        "tx_max_size_frames",
+        "tx_oversize_frames",
+        "tx_broadcast_frames",
+        "tx_multicast_frames",
+        "tx_control_frames",
+        "tx_pause_frames",
+        "tx_underrun_frames",
+        "tx_single_collision_frames",
+        "tx_multi_collision_frames",
+        "tx_deferred_collision_frames",
+        "tx_late_collision_frames",
+        "tx_excessive_collision_frames",
+        "tx_bytes",
+        "tx_frames",
+        "tx_collisions",
+};
+
+#define NB8800_NUM_STATS ARRAY_SIZE(nb8800_stats_names)
+
+static int nb8800_get_sset_count(struct net_device *dev, int sset)
+{
+        if (sset == ETH_SS_STATS)
+                return NB8800_NUM_STATS;
+
+        return -EOPNOTSUPP;
+}
+
+static void nb8800_get_strings(struct net_device *dev, u32 sset, u8 *buf)
+{
+        if (sset == ETH_SS_STATS)
+                memcpy(buf, &nb8800_stats_names, sizeof(nb8800_stats_names));
+}
+
+static u32 nb8800_read_stat(struct net_device *dev, int index)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+
+        nb8800_writeb(priv, NB8800_STAT_INDEX, index);
+
+        return nb8800_readl(priv, NB8800_STAT_DATA);
+}
+
+static void nb8800_get_ethtool_stats(struct net_device *dev,
+                                     struct ethtool_stats *estats, u64 *st)
+{
+        unsigned int i;
+        u32 rx, tx;
+
+        for (i = 0; i < NB8800_NUM_STATS / 2; i++) {
+                rx = nb8800_read_stat(dev, i);
+                tx = nb8800_read_stat(dev, i | 0x80);
+                st[i] = rx;
+                st[i + NB8800_NUM_STATS / 2] = tx;
+        }
+}
+
+static const struct ethtool_ops nb8800_ethtool_ops = {
+        .get_settings           = nb8800_get_settings,
+        .set_settings           = nb8800_set_settings,
+        .nway_reset             = nb8800_nway_reset,
+        .get_link               = ethtool_op_get_link,
+        .get_pauseparam         = nb8800_get_pauseparam,
+        .set_pauseparam         = nb8800_set_pauseparam,
+        .get_sset_count         = nb8800_get_sset_count,
+        .get_strings            = nb8800_get_strings,
+        .get_ethtool_stats      = nb8800_get_ethtool_stats,
+};
+
+static int nb8800_hw_init(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        u32 val;
+
+        val = TX_RETRY_EN | TX_PAD_EN | TX_APPEND_FCS;
+        nb8800_writeb(priv, NB8800_TX_CTL1, val);
+
+        /* Collision retry count */
+        nb8800_writeb(priv, NB8800_TX_CTL2, 5);
+
+        val = RX_PAD_STRIP | RX_AF_EN;
+        nb8800_writeb(priv, NB8800_RX_CTL, val);
+
+        /* Chosen by fair dice roll */
+        nb8800_writeb(priv, NB8800_RANDOM_SEED, 4);
+
+        /* TX cycles per deferral period */
+        nb8800_writeb(priv, NB8800_TX_SDP, 12);
+
+        /* The following three threshold values have been
+         * experimentally determined for good results.
+         */
+
+        /* RX/TX FIFO threshold for partial empty (64-bit entries) */
+        nb8800_writeb(priv, NB8800_PE_THRESHOLD, 0);
+
+        /* RX/TX FIFO threshold for partial full (64-bit entries) */
+        nb8800_writeb(priv, NB8800_PF_THRESHOLD, 255);
+
+        /* Buffer size for transmit (64-bit entries) */
+        nb8800_writeb(priv, NB8800_TX_BUFSIZE, 64);
+
+        /* Configure tx DMA */
+
+        val = nb8800_readl(priv, NB8800_TXC_CR);
+        val &= TCR_LE;          /* keep endian setting */
+        val |= TCR_DM;          /* DMA descriptor mode */
+        val |= TCR_RS;          /* automatically store tx status  */
+        val |= TCR_DIE;         /* interrupt on DMA chain completion */
+        val |= TCR_TFI(7);      /* interrupt after 7 frames transmitted */
+        val |= TCR_BTS(2);      /* 32-byte bus transaction size */
+        nb8800_writel(priv, NB8800_TXC_CR, val);
+
+        /* TX complete interrupt after 10 ms or 7 frames (see above) */
+        val = clk_get_rate(priv->clk) / 100;
+        nb8800_writel(priv, NB8800_TX_ITR, val);
+
+        /* Configure rx DMA */
+
+        val = nb8800_readl(priv, NB8800_RXC_CR);
+        val &= RCR_LE;          /* keep endian setting */
+        val |= RCR_DM;          /* DMA descriptor mode */
+        val |= RCR_RS;          /* automatically store rx status */
+        val |= RCR_DIE;         /* interrupt at end of DMA chain */
+        val |= RCR_RFI(7);      /* interrupt after 7 frames received */
+        val |= RCR_BTS(2);      /* 32-byte bus transaction size */
+        nb8800_writel(priv, NB8800_RXC_CR, val);
+
+        /* The rx interrupt can fire before the DMA has completed
+         * unless a small delay is added.  50 us is hopefully enough.
+         */
+        priv->rx_itr_irq = clk_get_rate(priv->clk) / 20000;
+
+        /* In NAPI poll mode we want to disable interrupts, but the
+         * hardware does not permit this.  Delay 10 ms instead.
+         */
+        priv->rx_itr_poll = clk_get_rate(priv->clk) / 100;
+
+        nb8800_writel(priv, NB8800_RX_ITR, priv->rx_itr_irq);
+
+        priv->rx_dma_config = RX_BUF_SIZE | DESC_BTS(2) | DESC_DS | DESC_EOF;
+
+        /* Flow control settings */
+
+        /* Pause time of 0.1 ms */
+        val = 100000 / 512;
+        nb8800_writeb(priv, NB8800_PQ1, val >> 8);
+        nb8800_writeb(priv, NB8800_PQ2, val & 0xff);
+
+        /* Auto-negotiate by default */
+        priv->pause_aneg = true;
+        priv->pause_rx = true;
+        priv->pause_tx = true;
+
+        nb8800_mc_init(dev, 0);
+
+        return 0;
+}
+
+static int nb8800_tangox_init(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        u32 pad_mode = PAD_MODE_MII;
+
+        switch (priv->phy_mode) {
+        case PHY_INTERFACE_MODE_MII:
+        case PHY_INTERFACE_MODE_GMII:
+                pad_mode = PAD_MODE_MII;
+                break;
+
+        case PHY_INTERFACE_MODE_RGMII:
+                pad_mode = PAD_MODE_RGMII;
+                break;
+
+        case PHY_INTERFACE_MODE_RGMII_TXID:
+                pad_mode = PAD_MODE_RGMII | PAD_MODE_GTX_CLK_DELAY;
+                break;
+
+        default:
+                dev_err(dev->dev.parent, "unsupported phy mode %s\n",
+                        phy_modes(priv->phy_mode));
+                return -EINVAL;
+        }
+
+        nb8800_writeb(priv, NB8800_TANGOX_PAD_MODE, pad_mode);
+
+        return 0;
+}
+
+static int nb8800_tangox_reset(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        int clk_div;
+
+        nb8800_writeb(priv, NB8800_TANGOX_RESET, 0);
+        usleep_range(1000, 10000);
+        nb8800_writeb(priv, NB8800_TANGOX_RESET, 1);
+
+        wmb();          /* ensure reset is cleared before proceeding */
+
+        clk_div = DIV_ROUND_UP(clk_get_rate(priv->clk), 2 * MAX_MDC_CLOCK);
+        nb8800_writew(priv, NB8800_TANGOX_MDIO_CLKDIV, clk_div);
+
+        return 0;
+}
+
+static const struct nb8800_ops nb8800_tangox_ops = {
+        .init   = nb8800_tangox_init,
+        .reset  = nb8800_tangox_reset,
+};
+
+static int nb8800_tango4_init(struct net_device *dev)
+{
+        struct nb8800_priv *priv = netdev_priv(dev);
+        int err;
+
+        err = nb8800_tangox_init(dev);
+        if (err)
+                return err;
+
+        /* On tango4 interrupt on DMA completion per frame works and gives
+         * better performance despite generating more rx interrupts.
+         */
+
+        /* Disable unnecessary interrupt on rx completion */
+        nb8800_clearl(priv, NB8800_RXC_CR, RCR_RFI(7));
+
+        /* Request interrupt on descriptor DMA completion */
+        priv->rx_dma_config |= DESC_ID;
+
+        return 0;
+}
+
+static const struct nb8800_ops nb8800_tango4_ops = {
+        .init   = nb8800_tango4_init,
+        .reset  = nb8800_tangox_reset,
+};
+
+static const struct of_device_id nb8800_dt_ids[] = {
+        {
+                .compatible = "aurora,nb8800",
+        },
+        {
+                .compatible = "sigma,smp8642-ethernet",
+                .data = &nb8800_tangox_ops,
+        },
+        {
+                .compatible = "sigma,smp8734-ethernet",
+                .data = &nb8800_tango4_ops,
+        },
+        { }
+};
+
+static int nb8800_probe(struct platform_device *pdev)
+{
+        const struct of_device_id *match;
+        const struct nb8800_ops *ops = NULL;
+        struct nb8800_priv *priv;
+        struct resource *res;
+        struct net_device *dev;
+        struct mii_bus *bus;
+        const unsigned char *mac;
+        void __iomem *base;
+        int irq;
+        int ret;
+
+        match = of_match_device(nb8800_dt_ids, &pdev->dev);
+        if (match)
+                ops = match->data;
+
+        irq = platform_get_irq(pdev, 0);
+        if (irq <= 0) {
+                dev_err(&pdev->dev, "No IRQ\n");
+                return -EINVAL;
+        }
+
+        res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+        base = devm_ioremap_resource(&pdev->dev, res);
+        if (IS_ERR(base))
+                return PTR_ERR(base);
+
+        dev_dbg(&pdev->dev, "AU-NB8800 Ethernet at %pa\n", &res->start);
+
+        dev = alloc_etherdev(sizeof(*priv));
+        if (!dev)
+                return -ENOMEM;
+
+        platform_set_drvdata(pdev, dev);
+        SET_NETDEV_DEV(dev, &pdev->dev);
+
+        priv = netdev_priv(dev);
+        priv->base = base;
+
+        priv->phy_mode = of_get_phy_mode(pdev->dev.of_node);
+        if (priv->phy_mode < 0)
+                priv->phy_mode = PHY_INTERFACE_MODE_RGMII;
+
+        priv->clk = devm_clk_get(&pdev->dev, NULL);
+        if (IS_ERR(priv->clk)) {
+                dev_err(&pdev->dev, "failed to get clock\n");
+                ret = PTR_ERR(priv->clk);
+                goto err_free_dev;
+        }
+
+        ret = clk_prepare_enable(priv->clk);
+        if (ret)
+                goto err_free_dev;
+
+        spin_lock_init(&priv->tx_lock);
+
+        if (ops && ops->reset) {
+                ret = ops->reset(dev);
+                if (ret)
+                        goto err_free_dev;
+        }
+
+        bus = devm_mdiobus_alloc(&pdev->dev);
+        if (!bus) {
+                ret = -ENOMEM;
+                goto err_disable_clk;
+        }
+
+        bus->name = "nb8800-mii";
+        bus->read = nb8800_mdio_read;
+        bus->write = nb8800_mdio_write;
+        bus->parent = &pdev->dev;
+        snprintf(bus->id, MII_BUS_ID_SIZE, "%lx.nb8800-mii",
+                 (unsigned long)res->start);
+        bus->priv = priv;
+
+        ret = of_mdiobus_register(bus, pdev->dev.of_node);
+        if (ret) {
+                dev_err(&pdev->dev, "failed to register MII bus\n");
+                goto err_disable_clk;
+        }
+
+        priv->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
+        if (!priv->phy_node) {
+                dev_err(&pdev->dev, "no PHY specified\n");
+                ret = -ENODEV;
+                goto err_free_bus;
+        }
+
+        priv->mii_bus = bus;
+
+        ret = nb8800_hw_init(dev);
+        if (ret)
+                goto err_free_bus;
+
+        if (ops && ops->init) {
+                ret = ops->init(dev);
+                if (ret)
+                        goto err_free_bus;
+        }
+
+        dev->netdev_ops = &nb8800_netdev_ops;
+        dev->ethtool_ops = &nb8800_ethtool_ops;
+        dev->flags |= IFF_MULTICAST;
+        dev->irq = irq;
+
+        mac = of_get_mac_address(pdev->dev.of_node);
+        if (mac)
+                ether_addr_copy(dev->dev_addr, mac);
+
+        if (!is_valid_ether_addr(dev->dev_addr))
+                eth_hw_addr_random(dev);
+
+        nb8800_update_mac_addr(dev);
+
+        netif_carrier_off(dev);
+
+        ret = register_netdev(dev);
+        if (ret) {
+                netdev_err(dev, "failed to register netdev\n");
+                goto err_free_dma;
+        }
+
+        netif_napi_add(dev, &priv->napi, nb8800_poll, NAPI_POLL_WEIGHT);
+
+        netdev_info(dev, "MAC address %pM\n", dev->dev_addr);
+
+        return 0;
+
+err_free_dma:
+        nb8800_dma_free(dev);
+err_free_bus:
+        mdiobus_unregister(bus);
+err_disable_clk:
+        clk_disable_unprepare(priv->clk);
+err_free_dev:
+        free_netdev(dev);
+
+        return ret;
+}
+
+static int nb8800_remove(struct platform_device *pdev)
+{
+        struct net_device *ndev = platform_get_drvdata(pdev);
+        struct nb8800_priv *priv = netdev_priv(ndev);
+
+        unregister_netdev(ndev);
+
+        mdiobus_unregister(priv->mii_bus);
+
+        clk_disable_unprepare(priv->clk);
+
+        nb8800_dma_free(ndev);
+        free_netdev(ndev);
+
+        return 0;
+}
+
+static struct platform_driver nb8800_driver = {
+        .driver = {
+                .name           = "nb8800",
+                .of_match_table = nb8800_dt_ids,
+        },
+        .probe  = nb8800_probe,
+        .remove = nb8800_remove,
+};
+
+module_platform_driver(nb8800_driver);
+
+MODULE_DESCRIPTION("Aurora AU-NB8800 Ethernet driver");
+MODULE_AUTHOR("Mans Rullgard <mans@mansr.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/aurora/nb8800.h b/drivers/net/ethernet/aurora/nb8800.h
new file mode 100644
index 000000000000..e5adbc2aac9f
--- /dev/null
+++ b/drivers/net/ethernet/aurora/nb8800.h
@@ -0,0 +1,316 @@
+#ifndef _NB8800_H_
+#define _NB8800_H_
+
+#include <linux/types.h>
+#include <linux/skbuff.h>
+#include <linux/phy.h>
+#include <linux/clk.h>
+#include <linux/bitops.h>
+
+#define RX_DESC_COUNT                   256
+#define TX_DESC_COUNT                   256
+
+#define NB8800_DESC_LOW                 4
+
+#define RX_BUF_SIZE                     1552
+
+#define RX_COPYBREAK                    256
+#define RX_COPYHDR                      128
+
+#define MAX_MDC_CLOCK                   2500000
+
+/* Stargate Solutions SSN8800 core registers */
+#define NB8800_TX_CTL1                  0x000
+#define TX_TPD                          BIT(5)
+#define TX_APPEND_FCS                   BIT(4)
+#define TX_PAD_EN                       BIT(3)
+#define TX_RETRY_EN                     BIT(2)
+#define TX_EN                           BIT(0)
+
+#define NB8800_TX_CTL2                  0x001
+
+#define NB8800_RX_CTL                   0x004
+#define RX_BC_DISABLE                   BIT(7)
+#define RX_RUNT                         BIT(6)
+#define RX_AF_EN                        BIT(5)
+#define RX_PAUSE_EN                     BIT(3)
+#define RX_SEND_CRC                     BIT(2)
+#define RX_PAD_STRIP                    BIT(1)
+#define RX_EN                           BIT(0)
+
+#define NB8800_RANDOM_SEED              0x008
+#define NB8800_TX_SDP                   0x14
+#define NB8800_TX_TPDP1                 0x18
+#define NB8800_TX_TPDP2                 0x19
+#define NB8800_SLOT_TIME                0x1c
+
+#define NB8800_MDIO_CMD                 0x020
+#define MDIO_CMD_GO                     BIT(31)
+#define MDIO_CMD_WR                     BIT(26)
+#define MDIO_CMD_ADDR(x)                ((x) << 21)
+#define MDIO_CMD_REG(x)                 ((x) << 16)
+#define MDIO_CMD_DATA(x)                ((x) <<  0)
+
+#define NB8800_MDIO_STS                 0x024
+#define MDIO_STS_ERR                    BIT(31)
+
+#define NB8800_MC_ADDR(i)               (0x028 + (i))
+#define NB8800_MC_INIT                  0x02e
+#define NB8800_UC_ADDR(i)               (0x03c + (i))
+
+#define NB8800_MAC_MODE                 0x044
+#define RGMII_MODE                      BIT(7)
+#define HALF_DUPLEX                     BIT(4)
+#define BURST_EN                        BIT(3)
+#define LOOPBACK_EN                     BIT(2)
+#define GMAC_MODE                       BIT(0)
+
+#define NB8800_IC_THRESHOLD             0x050
+#define NB8800_PE_THRESHOLD             0x051
+#define NB8800_PF_THRESHOLD             0x052
+#define NB8800_TX_BUFSIZE               0x054
+#define NB8800_FIFO_CTL                 0x056
+#define NB8800_PQ1                      0x060
+#define NB8800_PQ2                      0x061
+#define NB8800_SRC_ADDR(i)              (0x06a + (i))
+#define NB8800_STAT_DATA                0x078
+#define NB8800_STAT_INDEX               0x07c
+#define NB8800_STAT_CLEAR               0x07d
+
+#define NB8800_SLEEP_MODE               0x07e
+#define SLEEP_MODE                      BIT(0)
+
+#define NB8800_WAKEUP                   0x07f
+#define WAKEUP                          BIT(0)
+
+/* Aurora NB8800 host interface registers */
+#define NB8800_TXC_CR                   0x100
+#define TCR_LK                          BIT(12)
+#define TCR_DS                          BIT(11)
+#define TCR_BTS(x)                      (((x) & 0x7) << 8)
+#define TCR_DIE                         BIT(7)
+#define TCR_TFI(x)                      (((x) & 0x7) << 4)
+#define TCR_LE                          BIT(3)
+#define TCR_RS                          BIT(2)
+#define TCR_DM                          BIT(1)
+#define TCR_EN                          BIT(0)
+
+#define NB8800_TXC_SR                   0x104
+#define TSR_DE                          BIT(3)
+#define TSR_DI                          BIT(2)
+#define TSR_TO                          BIT(1)
+#define TSR_TI                          BIT(0)
+
+#define NB8800_TX_SAR                   0x108
+#define NB8800_TX_DESC_ADDR             0x10c
+
+#define NB8800_TX_REPORT_ADDR           0x110
+#define TX_BYTES_TRANSFERRED(x)         (((x) >> 16) & 0xffff)
+#define TX_FIRST_DEFERRAL               BIT(7)
+#define TX_EARLY_COLLISIONS(x)          (((x) >> 3) & 0xf)
+#define TX_LATE_COLLISION               BIT(2)
+#define TX_PACKET_DROPPED               BIT(1)
+#define TX_FIFO_UNDERRUN                BIT(0)
+#define IS_TX_ERROR(r)                  ((r) & 0x07)
+
+#define NB8800_TX_FIFO_SR               0x114
+#define NB8800_TX_ITR                   0x118
+
+#define NB8800_RXC_CR                   0x200
+#define RCR_FL                          BIT(13)
+#define RCR_LK                          BIT(12)
+#define RCR_DS                          BIT(11)
+#define RCR_BTS(x)                      (((x) & 7) << 8)
+#define RCR_DIE                         BIT(7)
+#define RCR_RFI(x)                      (((x) & 7) << 4)
+#define RCR_LE                          BIT(3)
+#define RCR_RS                          BIT(2)
+#define RCR_DM                          BIT(1)
+#define RCR_EN                          BIT(0)
+
+#define NB8800_RXC_SR                   0x204
+#define RSR_DE                          BIT(3)
+#define RSR_DI                          BIT(2)
+#define RSR_RO                          BIT(1)
+#define RSR_RI                          BIT(0)
+
+#define NB8800_RX_SAR                   0x208
+#define NB8800_RX_DESC_ADDR             0x20c
+
+#define NB8800_RX_REPORT_ADDR           0x210
+#define RX_BYTES_TRANSFERRED(x)         (((x) >> 16) & 0xFFFF)
+#define RX_MULTICAST_PKT                BIT(9)
+#define RX_BROADCAST_PKT                BIT(8)
+#define RX_LENGTH_ERR                   BIT(7)
+#define RX_FCS_ERR                      BIT(6)
+#define RX_RUNT_PKT                     BIT(5)
+#define RX_FIFO_OVERRUN                 BIT(4)
+#define RX_LATE_COLLISION               BIT(3)
+#define RX_ALIGNMENT_ERROR              BIT(2)
+#define RX_ERROR_MASK                   0xfc
+#define IS_RX_ERROR(r)                  ((r) & RX_ERROR_MASK)
+
+#define NB8800_RX_FIFO_SR               0x214
+#define NB8800_RX_ITR                   0x218
+
+/* Sigma Designs SMP86xx additional registers */
+#define NB8800_TANGOX_PAD_MODE          0x400
+#define PAD_MODE_MASK                   0x7
+#define PAD_MODE_MII                    0x0
+#define PAD_MODE_RGMII                  0x1
+#define PAD_MODE_GTX_CLK_INV            BIT(3)
+#define PAD_MODE_GTX_CLK_DELAY          BIT(4)
+
+#define NB8800_TANGOX_MDIO_CLKDIV       0x420
+#define NB8800_TANGOX_RESET             0x424
+
+/* Hardware DMA descriptor */
+struct nb8800_dma_desc {
+        u32                             s_addr; /* start address */
+        u32                             n_addr; /* next descriptor address */
+        u32                             r_addr; /* report address */
+        u32                             config;
+} __aligned(8);
+
+#define DESC_ID                         BIT(23)
+#define DESC_EOC                        BIT(22)
+#define DESC_EOF                        BIT(21)
+#define DESC_LK                         BIT(20)
+#define DESC_DS                         BIT(19)
+#define DESC_BTS(x)                     (((x) & 0x7) << 16)
+
+/* DMA descriptor and associated data for rx.
+ * Allocated from coherent memory.
+ */
+struct nb8800_rx_desc {
+        /* DMA descriptor */
+        struct nb8800_dma_desc          desc;
+
+        /* Status report filled in by hardware */
+        u32                             report;
+};
+
+/* Address of buffer on rx ring */
+struct nb8800_rx_buf {
+        struct page                     *page;
+        unsigned long                   offset;
+};
+
+/* DMA descriptors and associated data for tx.
+ * Allocated from coherent memory.
+ */
+struct nb8800_tx_desc {
+        /* DMA descriptor.  The second descriptor is used if packet
+         * data is unaligned.
+         */
+        struct nb8800_dma_desc          desc[2];
+
+        /* Status report filled in by hardware */
+        u32                             report;
+
+        /* Bounce buffer for initial unaligned part of packet */
+        u8                              buf[8] __aligned(8);
+};
+
+/* Packet in tx queue */
+struct nb8800_tx_buf {
+        /* Currently queued skb */
+        struct sk_buff                  *skb;
+
+        /* DMA address of the first descriptor */
+        dma_addr_t                      dma_desc;
+
+        /* DMA address of packet data */
+        dma_addr_t                      dma_addr;
+
+        /* Length of DMA mapping, less than skb->len if alignment
+         * buffer is used.
+         */
+        unsigned int                    dma_len;
+
+        /* Number of packets in chain starting here */
+        unsigned int                    chain_len;
+
+        /* Packet chain ready to be submitted to hardware */
+        bool                            ready;
+};
+
+struct nb8800_priv {
+        struct napi_struct              napi;
+
+        void __iomem                    *base;
+
+        /* RX DMA descriptors */
+        struct nb8800_rx_desc           *rx_descs;
+
+        /* RX buffers referenced by DMA descriptors */
+        struct nb8800_rx_buf            *rx_bufs;
+
+        /* Current end of chain */
+        u32                             rx_eoc;
+
+        /* Value for rx interrupt time register in NAPI interrupt mode */
+        u32                             rx_itr_irq;
+
+        /* Value for rx interrupt time register in NAPI poll mode */
+        u32                             rx_itr_poll;
+
+        /* Value for config field of rx DMA descriptors */
+        u32                             rx_dma_config;
+
+        /* TX DMA descriptors */
+        struct nb8800_tx_desc           *tx_descs;
+
+        /* TX packet queue */
+        struct nb8800_tx_buf            *tx_bufs;
+
+        /* Number of free tx queue entries */
+        atomic_t                        tx_free;
+
+        /* First free tx queue entry */
+        u32                             tx_next;
+
+        /* Next buffer to transmit */
+        u32                             tx_queue;
+
+        /* Start of current packet chain */
+        struct nb8800_tx_buf            *tx_chain;
+
+        /* Next buffer to reclaim */
+        u32                             tx_done;
+
+        /* Lock for DMA activation */
+        spinlock_t                      tx_lock;
+
+        struct mii_bus                  *mii_bus;
+        struct device_node              *phy_node;
+        struct phy_device               *phydev;
+
+        /* PHY connection type from DT */
+        int                             phy_mode;
+
+        /* Current link status */
+        int                             speed;
+        int                             duplex;
+        int                             link;
+
+        /* Pause settings */
+        bool                            pause_aneg;
+        bool                            pause_rx;
+        bool                            pause_tx;
+
+        /* DMA base address of rx descriptors, see rx_descs above */
+        dma_addr_t                      rx_desc_dma;
+
+        /* DMA base address of tx descriptors, see tx_descs above */
+        dma_addr_t                      tx_desc_dma;
+
+        struct clk                      *clk;
+};
+
+struct nb8800_ops {
+        int                             (*init)(struct net_device *dev);
+        int                             (*reset)(struct net_device *dev);
+};
+
+#endif /* _NB8800_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index c9b036789184..2e611dc5f162 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -10139,8 +10139,8 @@ static void __bnx2x_del_vxlan_port(struct bnx2x *bp, u16 port)
                 DP(BNX2X_MSG_SP, "Invalid vxlan port\n");
                 return;
         }
-        bp->vxlan_dst_port--;
-        if (bp->vxlan_dst_port)
+        bp->vxlan_dst_port_count--;
+        if (bp->vxlan_dst_port_count)
                 return;
 
         if (netif_running(bp->dev)) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index db15c5ee09c5..bdf094fb6ef9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3625,6 +3625,7 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp)
                 pf->fw_fid = le16_to_cpu(resp->fid);
                 pf->port_id = le16_to_cpu(resp->port_id);
                 memcpy(pf->mac_addr, resp->perm_mac_address, ETH_ALEN);
+                memcpy(bp->dev->dev_addr, pf->mac_addr, ETH_ALEN);
                 pf->max_rsscos_ctxs = le16_to_cpu(resp->max_rsscos_ctx);
                 pf->max_cp_rings = le16_to_cpu(resp->max_cmpl_rings);
                 pf->max_tx_rings = le16_to_cpu(resp->max_tx_rings);
@@ -3648,8 +3649,11 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 
                 vf->fw_fid = le16_to_cpu(resp->fid);
                 memcpy(vf->mac_addr, resp->perm_mac_address, ETH_ALEN);
-                if (!is_valid_ether_addr(vf->mac_addr))
-                        random_ether_addr(vf->mac_addr);
+                if (is_valid_ether_addr(vf->mac_addr))
+                        /* overwrite netdev dev_adr with admin VF MAC */
+                        memcpy(bp->dev->dev_addr, vf->mac_addr, ETH_ALEN);
+                else
+                        random_ether_addr(bp->dev->dev_addr);
 
                 vf->max_rsscos_ctxs = le16_to_cpu(resp->max_rsscos_ctx);
                 vf->max_cp_rings = le16_to_cpu(resp->max_cmpl_rings);
@@ -3880,6 +3884,8 @@ static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 #endif
 }
 
+static int bnxt_cfg_rx_mode(struct bnxt *);
+
 static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init)
 {
         int rc = 0;
@@ -3946,11 +3952,9 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init)
                 bp->vnic_info[0].rx_mask |=
                                 CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS;
 
-        rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0);
-        if (rc) {
-                netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %x\n", rc);
+        rc = bnxt_cfg_rx_mode(bp);
+        if (rc)
                 goto err_out;
-        }
 
         rc = bnxt_hwrm_set_coal(bp);
         if (rc)
@@ -4865,7 +4869,7 @@ static void bnxt_set_rx_mode(struct net_device *dev)
         }
 }
 
-static void bnxt_cfg_rx_mode(struct bnxt *bp)
+static int bnxt_cfg_rx_mode(struct bnxt *bp)
 {
         struct net_device *dev = bp->dev;
         struct bnxt_vnic_info *vnic = &bp->vnic_info[0];
@@ -4914,6 +4918,7 @@ static void bnxt_cfg_rx_mode(struct bnxt *bp)
                         netdev_err(bp->dev, "HWRM vnic filter failure rc: %x\n",
                                    rc);
                         vnic->uc_filter_count = i;
+                        return rc;
                 }
         }
 
@@ -4922,6 +4927,8 @@ skip_uc:
         if (rc)
                 netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %x\n",
                            rc);
+
+        return rc;
 }
 
 static netdev_features_t bnxt_fix_features(struct net_device *dev,
@@ -5212,13 +5219,27 @@ init_err:
 static int bnxt_change_mac_addr(struct net_device *dev, void *p)
 {
         struct sockaddr *addr = p;
+        struct bnxt *bp = netdev_priv(dev);
+        int rc = 0;
 
         if (!is_valid_ether_addr(addr->sa_data))
                 return -EADDRNOTAVAIL;
 
+#ifdef CONFIG_BNXT_SRIOV
+        if (BNXT_VF(bp) && is_valid_ether_addr(bp->vf.mac_addr))
+                return -EADDRNOTAVAIL;
+#endif
+
+        if (ether_addr_equal(addr->sa_data, dev->dev_addr))
+                return 0;
+
         memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
+        if (netif_running(dev)) {
+                bnxt_close_nic(bp, false, false);
+                rc = bnxt_open_nic(bp, false, false);
+        }
 
-        return 0;
+        return rc;
 }
 
 /* rtnl_lock held */
@@ -5686,15 +5707,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
         bnxt_set_tpa_flags(bp);
         bnxt_set_ring_params(bp);
         dflt_rings = netif_get_num_default_rss_queues();
-        if (BNXT_PF(bp)) {
-                memcpy(dev->dev_addr, bp->pf.mac_addr, ETH_ALEN);
+        if (BNXT_PF(bp))
                 bp->pf.max_irqs = max_irqs;
-        } else {
 #if defined(CONFIG_BNXT_SRIOV)
-                memcpy(dev->dev_addr, bp->vf.mac_addr, ETH_ALEN);
+        else
                 bp->vf.max_irqs = max_irqs;
 #endif
-        }
         bnxt_get_max_rings(bp, &max_rx_rings, &max_tx_rings);
         bp->rx_nr_rings = min_t(int, dflt_rings, max_rx_rings);
         bp->tx_nr_rings_per_tc = min_t(int, dflt_rings, max_tx_rings);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index f4cf68861069..7a9af2887d8e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -804,10 +804,9 @@ void bnxt_update_vf_mac(struct bnxt *bp)
         if (!is_valid_ether_addr(resp->perm_mac_address))
                 goto update_vf_mac_exit;
 
-        if (ether_addr_equal(resp->perm_mac_address, bp->vf.mac_addr))
-                goto update_vf_mac_exit;
-
-        memcpy(bp->vf.mac_addr, resp->perm_mac_address, ETH_ALEN);
+        if (!ether_addr_equal(resp->perm_mac_address, bp->vf.mac_addr))
+                memcpy(bp->vf.mac_addr, resp->perm_mac_address, ETH_ALEN);
+        /* overwrite netdev dev_adr with admin VF MAC */
         memcpy(bp->dev->dev_addr, bp->vf.mac_addr, ETH_ALEN);
 update_vf_mac_exit:
         mutex_unlock(&bp->hwrm_cmd_lock);
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 88c1e1a834f8..169059c92f80 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -1682,6 +1682,8 @@ static void macb_init_hw(struct macb *bp)
         macb_set_hwaddr(bp);
 
         config = macb_mdc_clk_div(bp);
+        if (bp->phy_interface == PHY_INTERFACE_MODE_SGMII)
+                config |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL);
         config |= MACB_BF(RBOF, NET_IP_ALIGN);  /* Make eth data aligned */
         config |= MACB_BIT(PAE);                /* PAuse Enable */
         config |= MACB_BIT(DRFCS);              /* Discard Rx FCS */
@@ -2416,6 +2418,8 @@ static int macb_init(struct platform_device *pdev)
         /* Set MII management clock divider */
         val = macb_mdc_clk_div(bp);
         val |= macb_dbw(bp);
+        if (bp->phy_interface == PHY_INTERFACE_MODE_SGMII)
+                val |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL);
         macb_writel(bp, NCFGR, val);
 
         return 0;
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 6e1faea00ca8..d83b0db77821 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -215,12 +215,17 @@
 /* GEM specific NCFGR bitfields. */
 #define GEM_GBE_OFFSET          10 /* Gigabit mode enable */
 #define GEM_GBE_SIZE            1
+#define GEM_PCSSEL_OFFSET       11
+#define GEM_PCSSEL_SIZE         1
 #define GEM_CLK_OFFSET          18 /* MDC clock division */
 #define GEM_CLK_SIZE            3
 #define GEM_DBW_OFFSET          21 /* Data bus width */
 #define GEM_DBW_SIZE            2
 #define GEM_RXCOEN_OFFSET       24
 #define GEM_RXCOEN_SIZE         1
+#define GEM_SGMIIEN_OFFSET      27
+#define GEM_SGMIIEN_SIZE        1
+
 
 /* Constants for data bus width. */
 #define GEM_DBW32               0 /* 32 bit AMBA AHB data bus width */
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index d3950b20feb9..39ca6744a4e6 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -120,10 +120,9 @@
  * Calculated for SCLK of 700Mhz
  * value written should be a 1/16th of what is expected
  *
- * 1 tick per 0.05usec = value of 2.2
- * This 10% would be covered in CQ timer thresh value
+ * 1 tick per 0.025usec
  */
-#define NICPF_CLK_PER_INT_TICK          2
+#define NICPF_CLK_PER_INT_TICK          1
 
 /* Time to wait before we decide that a SQ is stuck.
  *
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index c561fdcb79a7..4b7fd63ae57c 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -37,6 +37,7 @@ struct nicpf {
 #define NIC_GET_BGX_FROM_VF_LMAC_MAP(map)       ((map >> 4) & 0xF)
 #define NIC_GET_LMAC_FROM_VF_LMAC_MAP(map)      (map & 0xF)
         u8                      vf_lmac_map[MAX_LMAC];
+        u8                      lmac_cnt;
         struct delayed_work     dwork;
         struct workqueue_struct *check_link;
         u8                      link[MAX_LMAC];
@@ -279,6 +280,7 @@ static void nic_set_lmac_vf_mapping(struct nicpf *nic)
         u64 lmac_credit;
 
         nic->num_vf_en = 0;
+        nic->lmac_cnt = 0;
 
         for (bgx = 0; bgx < NIC_MAX_BGX; bgx++) {
                 if (!(bgx_map & (1 << bgx)))
@@ -288,6 +290,7 @@ static void nic_set_lmac_vf_mapping(struct nicpf *nic)
                         nic->vf_lmac_map[next_bgx_lmac++] =
                                                 NIC_SET_VF_LMAC_MAP(bgx, lmac);
                 nic->num_vf_en += lmac_cnt;
+                nic->lmac_cnt += lmac_cnt;
 
                 /* Program LMAC credits */
                 lmac_credit = (1ull << 1); /* channel credit enable */
@@ -715,6 +718,13 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
         case NIC_MBOX_MSG_CFG_DONE:
                 /* Last message of VF config msg sequence */
                 nic->vf_enabled[vf] = true;
+                if (vf >= nic->lmac_cnt)
+                        goto unlock;
+
+                bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+                lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+
+                bgx_lmac_rx_tx_enable(nic->node, bgx, lmac, true);
                 goto unlock;
         case NIC_MBOX_MSG_SHUTDOWN:
                 /* First msg in VF teardown sequence */
@@ -722,6 +732,14 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
                 if (vf >= nic->num_vf_en)
                         nic->sqs_used[vf - nic->num_vf_en] = false;
                 nic->pqs_vf[vf] = 0;
+
+                if (vf >= nic->lmac_cnt)
+                        break;
+
+                bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+                lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+
+                bgx_lmac_rx_tx_enable(nic->node, bgx, lmac, false);
                 break;
         case NIC_MBOX_MSG_ALLOC_SQS:
                 nic_alloc_sqs(nic, &mbx.sqs_alloc);
@@ -940,7 +958,7 @@ static void nic_poll_for_link(struct work_struct *work)
 
         mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE;
 
-        for (vf = 0; vf < nic->num_vf_en; vf++) {
+        for (vf = 0; vf < nic->lmac_cnt; vf++) {
                 /* Poll only if VF is UP */
                 if (!nic->vf_enabled[vf])
                         continue;
@@ -1074,8 +1092,7 @@ static void nic_remove(struct pci_dev *pdev)
 
         if (nic->check_link) {
                 /* Destroy work Queue */
-                cancel_delayed_work(&nic->dwork);
-                flush_workqueue(nic->check_link);
+                cancel_delayed_work_sync(&nic->dwork);
                 destroy_workqueue(nic->check_link);
         }
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index af54c10945c2..a12b2e38cf61 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -112,6 +112,13 @@ static int nicvf_get_settings(struct net_device *netdev,
 
         cmd->supported = 0;
         cmd->transceiver = XCVR_EXTERNAL;
+
+        if (!nic->link_up) {
+                cmd->duplex = DUPLEX_UNKNOWN;
+                ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN);
+                return 0;
+        }
+
         if (nic->speed <= 1000) {
                 cmd->port = PORT_MII;
                 cmd->autoneg = AUTONEG_ENABLE;
@@ -125,6 +132,13 @@ static int nicvf_get_settings(struct net_device *netdev,
         return 0;
 }
 
+static u32 nicvf_get_link(struct net_device *netdev)
+{
+        struct nicvf *nic = netdev_priv(netdev);
+
+        return nic->link_up;
+}
+
 static void nicvf_get_drvinfo(struct net_device *netdev,
                               struct ethtool_drvinfo *info)
 {
@@ -660,7 +674,7 @@ static int nicvf_set_channels(struct net_device *dev,
 
 static const struct ethtool_ops nicvf_ethtool_ops = {
         .get_settings           = nicvf_get_settings,
-        .get_link               = ethtool_op_get_link,
+        .get_link               = nicvf_get_link,
         .get_drvinfo            = nicvf_get_drvinfo,
         .get_msglevel           = nicvf_get_msglevel,
         .set_msglevel           = nicvf_set_msglevel,
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 7f709cbdcd87..dde8dc720cd3 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1057,6 +1057,7 @@ int nicvf_stop(struct net_device *netdev)
 
         netif_carrier_off(netdev);
         netif_tx_stop_all_queues(nic->netdev);
+        nic->link_up = false;
 
         /* Teardown secondary qsets first */
         if (!nic->sqs_mode) {
@@ -1211,9 +1212,6 @@ int nicvf_open(struct net_device *netdev)
         nic->drv_stats.txq_stop = 0;
         nic->drv_stats.txq_wake = 0;
 
-        netif_carrier_on(netdev);
-        netif_tx_start_all_queues(netdev);
-
         return 0;
 cleanup:
         nicvf_disable_intr(nic, NICVF_INTR_MBOX, 0);
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index e404ea837727..206b6a71a545 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -592,7 +592,7 @@ void nicvf_cmp_queue_config(struct nicvf *nic, struct queue_set *qs,
         /* Set threshold value for interrupt generation */
         nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_THRESH, qidx, cq->thresh);
         nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_CFG2,
-                              qidx, nic->cq_coalesce_usecs);
+                              qidx, CMP_QUEUE_TIMER_THRESH);
 }
 
 /* Configures transmit queue */
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index fb4957d09914..033e8306e91c 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -76,7 +76,7 @@
 #define CMP_QSIZE               CMP_QUEUE_SIZE2
 #define CMP_QUEUE_LEN           (1ULL << (CMP_QSIZE + 10))
 #define CMP_QUEUE_CQE_THRESH    0
-#define CMP_QUEUE_TIMER_THRESH  220 /* 10usec */
+#define CMP_QUEUE_TIMER_THRESH  80 /* ~2usec */
 
 #define RBDR_SIZE               RBDR_SIZE0
 #define RCV_BUF_COUNT           (1ULL << (RBDR_SIZE + 13))
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 180aa9fabf48..9df26c2263bc 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -186,6 +186,23 @@ void bgx_set_lmac_mac(int node, int bgx_idx, int lmacid, const u8 *mac)
 }
 EXPORT_SYMBOL(bgx_set_lmac_mac);
 
+void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable)
+{
+        struct bgx *bgx = bgx_vnic[(node * MAX_BGX_PER_CN88XX) + bgx_idx];
+        u64 cfg;
+
+        if (!bgx)
+                return;
+
+        cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG);
+        if (enable)
+                cfg |= CMR_PKT_RX_EN | CMR_PKT_TX_EN;
+        else
+                cfg &= ~(CMR_PKT_RX_EN | CMR_PKT_TX_EN);
+        bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg);
+}
+EXPORT_SYMBOL(bgx_lmac_rx_tx_enable);
+
 static void bgx_sgmii_change_link_state(struct lmac *lmac)
 {
         struct bgx *bgx = lmac->bgx;
@@ -612,6 +629,8 @@ static void bgx_poll_for_link(struct work_struct *work)
                 lmac->last_duplex = 1;
         } else {
                 lmac->link_up = 0;
+                lmac->last_speed = SPEED_UNKNOWN;
+                lmac->last_duplex = DUPLEX_UNKNOWN;
         }
 
         if (lmac->last_link != lmac->link_up) {
@@ -654,8 +673,7 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
         }
 
         /* Enable lmac */
-        bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG,
-                       CMR_EN | CMR_PKT_RX_EN | CMR_PKT_TX_EN);
+        bgx_reg_modify(bgx, lmacid, BGX_CMRX_CFG, CMR_EN);
 
         /* Restore default cfg, incase low level firmware changed it */
         bgx_reg_write(bgx, lmacid, BGX_CMRX_RX_DMAC_CTL, 0x03);
@@ -695,8 +713,7 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
         lmac = &bgx->lmac[lmacid];
         if (lmac->check_link) {
                 /* Destroy work queue */
-                cancel_delayed_work(&lmac->dwork);
-                flush_workqueue(lmac->check_link);
+                cancel_delayed_work_sync(&lmac->dwork);
                 destroy_workqueue(lmac->check_link);
         }
 
@@ -1009,6 +1026,9 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
         struct bgx *bgx = NULL;
         u8 lmac;
 
+        /* Load octeon mdio driver */
+        octeon_mdiobus_force_mod_depencency();
+
         bgx = devm_kzalloc(dev, sizeof(*bgx), GFP_KERNEL);
         if (!bgx)
                 return -ENOMEM;
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index 07b7ec66c60d..149e179363a1 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -182,6 +182,8 @@ enum MCAST_MODE {
 #define BCAST_ACCEPT    1
 #define CAM_ACCEPT      1
 
+void octeon_mdiobus_force_mod_depencency(void);
+void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable);
 void bgx_add_dmac_addr(u64 dmac, int node, int bgx_idx, int lmac);
 unsigned bgx_get_map(int node);
 int bgx_get_lmac_count(int node, int bgx);
diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index ed41559bae77..b553409e04ad 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -98,8 +98,7 @@ static int csr0 = 0x01A00000 | 0x4800;
 #elif defined(__mips__)
 static int csr0 = 0x00200000 | 0x4000;
 #else
-#warning Processor architecture undefined!
-static int csr0 = 0x00A00000 | 0x4800;
+static int csr0;
 #endif
 
 /* Operational parameters that usually are not changed. */
@@ -1982,6 +1981,12 @@ static int __init tulip_init (void)
         pr_info("%s", version);
 #endif
 
+        if (!csr0) {
+                pr_warn("tulip: unknown CPU architecture, using default csr0\n");
+                /* default to 8 longword cache line alignment */
+                csr0 = 0x00A00000 | 0x4800;
+        }
+
         /* copy module parms into globals */
         tulip_rx_copybreak = rx_copybreak;
         tulip_max_interrupt_work = max_interrupt_work;
diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c
index 9beb3d34d4ba..3c0e4d5c5fef 100644
--- a/drivers/net/ethernet/dec/tulip/winbond-840.c
+++ b/drivers/net/ethernet/dec/tulip/winbond-840.c
@@ -907,7 +907,7 @@ static void init_registers(struct net_device *dev)
 #elif defined(CONFIG_SPARC) || defined (CONFIG_PARISC) || defined(CONFIG_ARM)
         i |= 0x4800;
 #else
-#warning Processor architecture undefined
+        dev_warn(&dev->dev, "unknown CPU architecture, using default csr0 setting\n");
         i |= 0x4800;
 #endif
         iowrite32(i, ioaddr + PCIBusCfg);
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index ff76d4e9dc1b..bee32a9d9876 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -7,7 +7,8 @@ config NET_VENDOR_FREESCALE
         default y
         depends on FSL_SOC || QUICC_ENGINE || CPM1 || CPM2 || PPC_MPC512x || \
                    M523x || M527x || M5272 || M528x || M520x || M532x || \
-                   ARCH_MXC || ARCH_MXS || (PPC_MPC52xx && PPC_BESTCOMM)
+                   ARCH_MXC || ARCH_MXS || (PPC_MPC52xx && PPC_BESTCOMM) || \
+                   ARCH_LAYERSCAPE
         ---help---
           If you have a network (Ethernet) card belonging to this class, say Y.
 
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 3e6b9b437497..7cf898455e60 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -647,9 +647,9 @@ static int gfar_parse_group(struct device_node *np,
         if (model && strcasecmp(model, "FEC")) {
                 gfar_irq(grp, RX)->irq = irq_of_parse_and_map(np, 1);
                 gfar_irq(grp, ER)->irq = irq_of_parse_and_map(np, 2);
-                if (gfar_irq(grp, TX)->irq == NO_IRQ ||
-                    gfar_irq(grp, RX)->irq == NO_IRQ ||
-                    gfar_irq(grp, ER)->irq == NO_IRQ)
+                if (!gfar_irq(grp, TX)->irq ||
+                    !gfar_irq(grp, RX)->irq ||
+                    !gfar_irq(grp, ER)->irq)
                         return -EINVAL;
         }
 
diff --git a/drivers/net/ethernet/freescale/gianfar_ptp.c b/drivers/net/ethernet/freescale/gianfar_ptp.c
index 664d0c261269..b40fba929d65 100644
--- a/drivers/net/ethernet/freescale/gianfar_ptp.c
+++ b/drivers/net/ethernet/freescale/gianfar_ptp.c
@@ -467,7 +467,7 @@ static int gianfar_ptp_probe(struct platform_device *dev)
 
         etsects->irq = platform_get_irq(dev, 0);
 
-        if (etsects->irq == NO_IRQ) {
+        if (etsects->irq < 0) {
                 pr_err("irq not in device tree\n");
                 goto no_node;
         }
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
index 639263d5e833..7781e80896a6 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -627,8 +627,10 @@ static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev)
 
                 /* verify the skb head is not shared */
                 err = skb_cow_head(skb, 0);
-                if (err)
+                if (err) {
+                        dev_kfree_skb(skb);
                         return NETDEV_TX_OK;
+                }
 
                 /* locate vlan header */
                 vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index e84c7f2634d3..ed622fa29dfa 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -36,7 +36,7 @@
 
 /* Registers */
 #define MVNETA_RXQ_CONFIG_REG(q)                (0x1400 + ((q) << 2))
-#define      MVNETA_RXQ_HW_BUF_ALLOC            BIT(1)
+#define      MVNETA_RXQ_HW_BUF_ALLOC            BIT(0)
 #define      MVNETA_RXQ_PKT_OFFSET_ALL_MASK     (0xf    << 8)
 #define      MVNETA_RXQ_PKT_OFFSET_MASK(offs)   ((offs) << 8)
 #define MVNETA_RXQ_THRESHOLD_REG(q)             (0x14c0 + ((q) << 2))
@@ -62,6 +62,7 @@
 #define MVNETA_WIN_SIZE(w)                      (0x2204 + ((w) << 3))
 #define MVNETA_WIN_REMAP(w)                     (0x2280 + ((w) << 2))
 #define MVNETA_BASE_ADDR_ENABLE                 0x2290
+#define MVNETA_ACCESS_PROTECT_ENABLE            0x2294
 #define MVNETA_PORT_CONFIG                      0x2400
 #define      MVNETA_UNI_PROMISC_MODE            BIT(0)
 #define      MVNETA_DEF_RXQ(q)                  ((q) << 1)
@@ -159,7 +160,7 @@
 
 #define MVNETA_INTR_ENABLE                       0x25b8
 #define      MVNETA_TXQ_INTR_ENABLE_ALL_MASK     0x0000ff00
-#define      MVNETA_RXQ_INTR_ENABLE_ALL_MASK     0xff000000  // note: neta says it's 0x000000FF
+#define      MVNETA_RXQ_INTR_ENABLE_ALL_MASK     0x000000ff
 
 #define MVNETA_RXQ_CMD                           0x2680
 #define      MVNETA_RXQ_DISABLE_SHIFT            8
@@ -242,6 +243,7 @@
 #define MVNETA_VLAN_TAG_LEN             4
 
 #define MVNETA_CPU_D_CACHE_LINE_SIZE    32
+#define MVNETA_TX_CSUM_DEF_SIZE         1600
 #define MVNETA_TX_CSUM_MAX_SIZE         9800
 #define MVNETA_ACC_MODE_EXT             1
 
@@ -1579,12 +1581,16 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
                 }
 
                 skb = build_skb(data, pp->frag_size > PAGE_SIZE ? 0 : pp->frag_size);
-                if (!skb)
-                        goto err_drop_frame;
 
+                /* After refill old buffer has to be unmapped regardless
+                 * the skb is successfully built or not.
+                 */
                 dma_unmap_single(dev->dev.parent, phys_addr,
                                  MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE);
 
+                if (!skb)
+                        goto err_drop_frame;
+
                 rcvd_pkts++;
                 rcvd_bytes += rx_bytes;
 
@@ -3191,6 +3197,7 @@ static void mvneta_conf_mbus_windows(struct mvneta_port *pp,
         }
 
         mvreg_write(pp, MVNETA_BASE_ADDR_ENABLE, win_enable);
+        mvreg_write(pp, MVNETA_ACCESS_PROTECT_ENABLE, win_protect);
 }
 
 /* Power up the port */
@@ -3250,6 +3257,7 @@ static int mvneta_probe(struct platform_device *pdev)
         char hw_mac_addr[ETH_ALEN];
         const char *mac_from;
         const char *managed;
+        int tx_csum_limit;
         int phy_mode;
         int err;
         int cpu;
@@ -3350,8 +3358,21 @@ static int mvneta_probe(struct platform_device *pdev)
                 }
         }
 
-        if (of_device_is_compatible(dn, "marvell,armada-370-neta"))
-                pp->tx_csum_limit = 1600;
+        if (!of_property_read_u32(dn, "tx-csum-limit", &tx_csum_limit)) {
+                if (tx_csum_limit < 0 ||
+                    tx_csum_limit > MVNETA_TX_CSUM_MAX_SIZE) {
+                        tx_csum_limit = MVNETA_TX_CSUM_DEF_SIZE;
+                        dev_info(&pdev->dev,
+                                 "Wrong TX csum limit in DT, set to %dB\n",
+                                 MVNETA_TX_CSUM_DEF_SIZE);
+                }
+        } else if (of_device_is_compatible(dn, "marvell,armada-370-neta")) {
+                tx_csum_limit = MVNETA_TX_CSUM_DEF_SIZE;
+        } else {
+                tx_csum_limit = MVNETA_TX_CSUM_MAX_SIZE;
+        }
+
+        pp->tx_csum_limit = tx_csum_limit;
 
         pp->tx_ring_size = MVNETA_MAX_TXD;
         pp->rx_ring_size = MVNETA_MAX_RXD;
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 2177e56ed0be..d48d5793407d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -1010,7 +1010,7 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave,
                 if (!(smp->mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED &&
                       smp->method == IB_MGMT_METHOD_GET) || network_view) {
                         mlx4_err(dev, "Unprivileged slave %d is trying to execute a Subnet MGMT MAD, class 0x%x, method 0x%x, view=%s for attr 0x%x. Rejecting\n",
-                                 slave, smp->method, smp->mgmt_class,
+                                 slave, smp->mgmt_class, smp->method,
                                  network_view ? "Network" : "Host",
                                  be16_to_cpu(smp->attr_id));
                         return -EPERM;
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index b159ef8303cc..057665180f13 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -1326,7 +1326,7 @@ static int lpc_eth_drv_probe(struct platform_device *pdev)
         /* Get platform resources */
         res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
         irq = platform_get_irq(pdev, 0);
-        if ((!res) || (irq < 0) || (irq >= NR_IRQS)) {
+        if (!res || irq < 0) {
                 dev_err(&pdev->dev, "error getting resources.\n");
                 ret = -ENXIO;
                 goto err_exit;
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index ee8d1ec61fab..ed5da4d47668 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1225,7 +1225,7 @@ static int ravb_open(struct net_device *ndev)
         /* Device init */
         error = ravb_dmac_init(ndev);
         if (error)
-                goto out_free_irq;
+                goto out_free_irq2;
         ravb_emac_init(ndev);
 
         /* Initialise PTP Clock driver */
@@ -1243,9 +1243,11 @@ static int ravb_open(struct net_device *ndev)
 out_ptp_stop:
         /* Stop PTP Clock driver */
         ravb_ptp_stop(ndev);
+out_free_irq2:
+        if (priv->chip_id == RCAR_GEN3)
+                free_irq(priv->emac_irq, ndev);
 out_free_irq:
         free_irq(ndev->irq, ndev);
-        free_irq(priv->emac_irq, ndev);
 out_napi_off:
         napi_disable(&priv->napi[RAVB_NC]);
         napi_disable(&priv->napi[RAVB_BE]);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
index 7f6f4a4fcc70..58c05acc2aab 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
@@ -299,16 +299,17 @@ static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
         if (IS_PHY_IF_MODE_GBIT(dwmac->interface)) {
                 const char *rs;
 
+                dwmac->tx_retime_src = TX_RETIME_SRC_CLKGEN;
+
                 err = of_property_read_string(np, "st,tx-retime-src", &rs);
                 if (err < 0) {
                         dev_warn(dev, "Use internal clock source\n");
-                        dwmac->tx_retime_src = TX_RETIME_SRC_CLKGEN;
-                } else if (!strcasecmp(rs, "clk_125")) {
-                        dwmac->tx_retime_src = TX_RETIME_SRC_CLK_125;
-                } else if (!strcasecmp(rs, "txclk")) {
-                        dwmac->tx_retime_src = TX_RETIME_SRC_TXCLK;
+                } else {
+                        if (!strcasecmp(rs, "clk_125"))
+                                dwmac->tx_retime_src = TX_RETIME_SRC_CLK_125;
+                        else if (!strcasecmp(rs, "txclk"))
+                                dwmac->tx_retime_src = TX_RETIME_SRC_TXCLK;
                 }
-
                 dwmac->speed = SPEED_1000;
         }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 64d8aa4e0cad..3c6549aee11d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -185,7 +185,7 @@ static void stmmac_clk_csr_set(struct stmmac_priv *priv)
                         priv->clk_csr = STMMAC_CSR_100_150M;
                 else if ((clk_rate >= CSR_F_150M) && (clk_rate < CSR_F_250M))
                         priv->clk_csr = STMMAC_CSR_150_250M;
-                else if ((clk_rate >= CSR_F_250M) && (clk_rate < CSR_F_300M))
+                else if ((clk_rate >= CSR_F_250M) && (clk_rate <= CSR_F_300M))
                         priv->clk_csr = STMMAC_CSR_250_300M;
         }
 }
@@ -2232,6 +2232,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 
                         frame_len = priv->hw->desc->get_rx_frame_len(p, coe);
 
+                        /*  check if frame_len fits the preallocated memory */
+                        if (frame_len > priv->dma_buf_sz) {
+                                priv->dev->stats.rx_length_errors++;
+                                break;
+                        }
+
                         /* ACS is set; GMAC core strips PAD/FCS for IEEE 802.3
                          * Type frames (LLC/LLC-SNAP)
                          */
@@ -3102,6 +3108,7 @@ int stmmac_resume(struct net_device *ndev)
         init_dma_desc_rings(ndev, GFP_ATOMIC);
         stmmac_hw_setup(ndev, false);
         stmmac_init_tx_coalesce(priv);
+        stmmac_set_rx_mode(ndev);
 
         napi_enable(&priv->napi);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index ebf6abc4853f..bba670c42e37 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -138,7 +138,6 @@ int stmmac_mdio_reset(struct mii_bus *bus)
 
 #ifdef CONFIG_OF
         if (priv->device->of_node) {
-                int reset_gpio, active_low;
 
                 if (data->reset_gpio < 0) {
                         struct device_node *np = priv->device->of_node;
@@ -154,24 +153,23 @@ int stmmac_mdio_reset(struct mii_bus *bus)
                                                 "snps,reset-active-low");
                         of_property_read_u32_array(np,
                                 "snps,reset-delays-us", data->delays, 3);
-                }
 
-                reset_gpio = data->reset_gpio;
-                active_low = data->active_low;
+                        if (gpio_request(data->reset_gpio, "mdio-reset"))
+                                return 0;
+                }
 
-                if (!gpio_request(reset_gpio, "mdio-reset")) {
-                        gpio_direction_output(reset_gpio, active_low ? 1 : 0);
-                        if (data->delays[0])
-                                msleep(DIV_ROUND_UP(data->delays[0], 1000));
+                gpio_direction_output(data->reset_gpio,
+                                      data->active_low ? 1 : 0);
+                if (data->delays[0])
+                        msleep(DIV_ROUND_UP(data->delays[0], 1000));
 
-                        gpio_set_value(reset_gpio, active_low ? 0 : 1);
-                        if (data->delays[1])
-                                msleep(DIV_ROUND_UP(data->delays[1], 1000));
+                gpio_set_value(data->reset_gpio, data->active_low ? 0 : 1);
+                if (data->delays[1])
+                        msleep(DIV_ROUND_UP(data->delays[1], 1000));
 
-                        gpio_set_value(reset_gpio, active_low ? 1 : 0);
-                        if (data->delays[2])
-                                msleep(DIV_ROUND_UP(data->delays[2], 1000));
-                }
+                gpio_set_value(data->reset_gpio, data->active_low ? 1 : 0);
+                if (data->delays[2])
+                        msleep(DIV_ROUND_UP(data->delays[2], 1000));
         }
 #endif
 
diff --git a/drivers/net/ethernet/ti/cpsw-common.c b/drivers/net/ethernet/ti/cpsw-common.c
index c08be62bceba..1562ab4151e1 100644
--- a/drivers/net/ethernet/ti/cpsw-common.c
+++ b/drivers/net/ethernet/ti/cpsw-common.c
@@ -78,6 +78,9 @@ static int cpsw_am33xx_cm_get_macid(struct device *dev, u16 offset, int slave,
 
 int ti_cm_get_macid(struct device *dev, int slave, u8 *mac_addr)
 {
+        if (of_machine_is_compatible("ti,dm8148"))
+                return cpsw_am33xx_cm_get_macid(dev, 0x630, slave, mac_addr);
+
         if (of_machine_is_compatible("ti,am33xx"))
                 return cpsw_am33xx_cm_get_macid(dev, 0x630, slave, mac_addr);
 
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 54036ae0a388..0fc521941c71 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -498,7 +498,7 @@ static void macvtap_sock_write_space(struct sock *sk)
         wait_queue_head_t *wqueue;
 
         if (!sock_writeable(sk) ||
-            !test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags))
+            !test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags))
                 return;
 
         wqueue = sk_sleep(sk);
@@ -585,7 +585,7 @@ static unsigned int macvtap_poll(struct file *file, poll_table * wait)
                 mask |= POLLIN | POLLRDNORM;
 
         if (sock_writeable(&q->sk) ||
-            (!test_and_set_bit(SOCK_ASYNC_NOSPACE, &q->sock.flags) &&
+            (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &q->sock.flags) &&
              sock_writeable(&q->sk)))
                 mask |= POLLOUT | POLLWRNORM;
 
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 07a6119121c3..3ce5d9514623 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -614,7 +614,7 @@ static struct mdio_device_id __maybe_unused broadcom_tbl[] = {
         { PHY_ID_BCM5461, 0xfffffff0 },
         { PHY_ID_BCM54616S, 0xfffffff0 },
         { PHY_ID_BCM5464, 0xfffffff0 },
-        { PHY_ID_BCM5482, 0xfffffff0 },
+        { PHY_ID_BCM5481, 0xfffffff0 },
         { PHY_ID_BCM5482, 0xfffffff0 },
         { PHY_ID_BCM50610, 0xfffffff0 },
         { PHY_ID_BCM50610M, 0xfffffff0 },
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 48ce6ef400fe..47cd306dbb3c 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -448,7 +448,8 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
                 mdiobus_write(phydev->bus, mii_data->phy_id,
                               mii_data->reg_num, val);
 
-                if (mii_data->reg_num == MII_BMCR &&
+                if (mii_data->phy_id == phydev->addr &&
+                    mii_data->reg_num == MII_BMCR &&
                     val & BMCR_RESET)
                         return phy_init_hw(phydev);
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index b1878faea397..f0db770e8b2f 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1040,7 +1040,7 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
                 mask |= POLLIN | POLLRDNORM;
 
         if (sock_writeable(sk) ||
-            (!test_and_set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+            (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
              sock_writeable(sk)))
                 mask |= POLLOUT | POLLWRNORM;
 
@@ -1488,7 +1488,7 @@ static void tun_sock_write_space(struct sock *sk)
         if (!sock_writeable(sk))
                 return;
 
-        if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags))
+        if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags))
                 return;
 
         wqueue = sk_sleep(sk);
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index a187f08113ec..3b1ba8237768 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -691,7 +691,6 @@ static void cdc_ncm_free(struct cdc_ncm_ctx *ctx)
 
 int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags)
 {
-        const struct usb_cdc_union_desc *union_desc = NULL;
         struct cdc_ncm_ctx *ctx;
         struct usb_driver *driver;
         u8 *buf;
@@ -725,15 +724,16 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
         /* parse through descriptors associated with control interface */
         cdc_parse_cdc_header(&hdr, intf, buf, len);
 
-        ctx->data = usb_ifnum_to_if(dev->udev,
-                                    hdr.usb_cdc_union_desc->bSlaveInterface0);
+        if (hdr.usb_cdc_union_desc)
+                ctx->data = usb_ifnum_to_if(dev->udev,
+                                            hdr.usb_cdc_union_desc->bSlaveInterface0);
         ctx->ether_desc = hdr.usb_cdc_ether_desc;
         ctx->func_desc = hdr.usb_cdc_ncm_desc;
         ctx->mbim_desc = hdr.usb_cdc_mbim_desc;
         ctx->mbim_extended_desc = hdr.usb_cdc_mbim_extended_desc;
 
         /* some buggy devices have an IAD but no CDC Union */
-        if (!union_desc && intf->intf_assoc && intf->intf_assoc->bInterfaceCount == 2) {
+        if (!hdr.usb_cdc_union_desc && intf->intf_assoc && intf->intf_assoc->bInterfaceCount == 2) {
                 ctx->data = usb_ifnum_to_if(dev->udev, intf->cur_altsetting->desc.bInterfaceNumber + 1);
                 dev_dbg(&intf->dev, "CDC Union missing - got slave from IAD\n");
         }
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 34799eaace41..9a5be8b85186 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -725,6 +725,7 @@ static const struct usb_device_id products[] = {
         {QMI_FIXED_INTF(0x2357, 0x9000, 4)},    /* TP-LINK MA260 */
         {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},    /* Telit LE920 */
         {QMI_FIXED_INTF(0x1bc7, 0x1201, 2)},    /* Telit LE920 */
+        {QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)},    /* XS Stick W100-2 from 4G Systems */
         {QMI_FIXED_INTF(0x0b3c, 0xc000, 4)},    /* Olivetti Olicard 100 */
         {QMI_FIXED_INTF(0x0b3c, 0xc001, 4)},    /* Olivetti Olicard 120 */
         {QMI_FIXED_INTF(0x0b3c, 0xc002, 4)},    /* Olivetti Olicard 140 */
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d8838dedb7a4..f94ab786088f 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -140,6 +140,12 @@ struct virtnet_info {
 
         /* CPU hot plug notifier */
         struct notifier_block nb;
+
+        /* Control VQ buffers: protected by the rtnl lock */
+        struct virtio_net_ctrl_hdr ctrl_hdr;
+        virtio_net_ctrl_ack ctrl_status;
+        u8 ctrl_promisc;
+        u8 ctrl_allmulti;
 };
 
 struct padded_vnet_hdr {
@@ -976,31 +982,30 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
                                  struct scatterlist *out)
 {
         struct scatterlist *sgs[4], hdr, stat;
-        struct virtio_net_ctrl_hdr ctrl;
-        virtio_net_ctrl_ack status = ~0;
         unsigned out_num = 0, tmp;
 
         /* Caller should know better */
         BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ));
 
-        ctrl.class = class;
-        ctrl.cmd = cmd;
+        vi->ctrl_status = ~0;
+        vi->ctrl_hdr.class = class;
+        vi->ctrl_hdr.cmd = cmd;
         /* Add header */
-        sg_init_one(&hdr, &ctrl, sizeof(ctrl));
+        sg_init_one(&hdr, &vi->ctrl_hdr, sizeof(vi->ctrl_hdr));
         sgs[out_num++] = &hdr;
 
         if (out)
                 sgs[out_num++] = out;
 
         /* Add return status. */
-        sg_init_one(&stat, &status, sizeof(status));
+        sg_init_one(&stat, &vi->ctrl_status, sizeof(vi->ctrl_status));
         sgs[out_num] = &stat;
 
         BUG_ON(out_num + 1 > ARRAY_SIZE(sgs));
         virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC);
 
         if (unlikely(!virtqueue_kick(vi->cvq)))
-                return status == VIRTIO_NET_OK;
+                return vi->ctrl_status == VIRTIO_NET_OK;
 
         /* Spin for a response, the kick causes an ioport write, trapping
          * into the hypervisor, so the request should be handled immediately.
@@ -1009,7 +1014,7 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd,
                !virtqueue_is_broken(vi->cvq))
                 cpu_relax();
 
-        return status == VIRTIO_NET_OK;
+        return vi->ctrl_status == VIRTIO_NET_OK;
 }
 
 static int virtnet_set_mac_address(struct net_device *dev, void *p)
@@ -1151,7 +1156,6 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 {
         struct virtnet_info *vi = netdev_priv(dev);
         struct scatterlist sg[2];
-        u8 promisc, allmulti;
         struct virtio_net_ctrl_mac *mac_data;
         struct netdev_hw_addr *ha;
         int uc_count;
@@ -1163,22 +1167,22 @@ static void virtnet_set_rx_mode(struct net_device *dev)
         if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX))
                 return;
 
-        promisc = ((dev->flags & IFF_PROMISC) != 0);
-        allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
+        vi->ctrl_promisc = ((dev->flags & IFF_PROMISC) != 0);
+        vi->ctrl_allmulti = ((dev->flags & IFF_ALLMULTI) != 0);
 
-        sg_init_one(sg, &promisc, sizeof(promisc));
+        sg_init_one(sg, &vi->ctrl_promisc, sizeof(vi->ctrl_promisc));
 
         if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
                                   VIRTIO_NET_CTRL_RX_PROMISC, sg))
                 dev_warn(&dev->dev, "Failed to %sable promisc mode.\n",
-                         promisc ? "en" : "dis");
+                         vi->ctrl_promisc ? "en" : "dis");
 
-        sg_init_one(sg, &allmulti, sizeof(allmulti));
+        sg_init_one(sg, &vi->ctrl_allmulti, sizeof(vi->ctrl_allmulti));
 
         if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX,
                                   VIRTIO_NET_CTRL_RX_ALLMULTI, sg))
                 dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n",
-                         allmulti ? "en" : "dis");
+                         vi->ctrl_allmulti ? "en" : "dis");
 
         uc_count = netdev_uc_count(dev);
         mc_count = netdev_mc_count(dev);
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 899ea4288197..417903715437 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -587,6 +587,12 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx,
                                                 &adapter->pdev->dev,
                                                 rbi->skb->data, rbi->len,
                                                 PCI_DMA_FROMDEVICE);
+                                if (dma_mapping_error(&adapter->pdev->dev,
+                                                      rbi->dma_addr)) {
+                                        dev_kfree_skb_any(rbi->skb);
+                                        rq->stats.rx_buf_alloc_failure++;
+                                        break;
+                                }
                         } else {
                                 /* rx buffer skipped by the device */
                         }
@@ -605,13 +611,18 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx,
                                                 &adapter->pdev->dev,
                                                 rbi->page, 0, PAGE_SIZE,
                                                 PCI_DMA_FROMDEVICE);
+                                if (dma_mapping_error(&adapter->pdev->dev,
+                                                      rbi->dma_addr)) {
+                                        put_page(rbi->page);
+                                        rq->stats.rx_buf_alloc_failure++;
+                                        break;
+                                }
                         } else {
                                 /* rx buffers skipped by the device */
                         }
                         val = VMXNET3_RXD_BTYPE_BODY << VMXNET3_RXD_BTYPE_SHIFT;
                 }
 
-                BUG_ON(rbi->dma_addr == 0);
                 gd->rxd.addr = cpu_to_le64(rbi->dma_addr);
                 gd->dword[2] = cpu_to_le32((!ring->gen << VMXNET3_RXD_GEN_SHIFT)
                                            | val | rbi->len);
@@ -655,7 +666,7 @@ vmxnet3_append_frag(struct sk_buff *skb, struct Vmxnet3_RxCompDesc *rcd,
 }
 
 
-static void
+static int
 vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
                 struct vmxnet3_tx_queue *tq, struct pci_dev *pdev,
                 struct vmxnet3_adapter *adapter)
@@ -715,6 +726,8 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
                 tbi->dma_addr = dma_map_single(&adapter->pdev->dev,
                                 skb->data + buf_offset, buf_size,
                                 PCI_DMA_TODEVICE);
+                if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr))
+                        return -EFAULT;
 
                 tbi->len = buf_size;
 
@@ -755,6 +768,8 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
                         tbi->dma_addr = skb_frag_dma_map(&adapter->pdev->dev, frag,
                                                          buf_offset, buf_size,
                                                          DMA_TO_DEVICE);
+                        if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr))
+                                return -EFAULT;
 
                         tbi->len = buf_size;
 
@@ -782,6 +797,8 @@ vmxnet3_map_pkt(struct sk_buff *skb, struct vmxnet3_tx_ctx *ctx,
         /* set the last buf_info for the pkt */
         tbi->skb = skb;
         tbi->sop_idx = ctx->sop_txd - tq->tx_ring.base;
+
+        return 0;
 }
 
 
@@ -1020,7 +1037,8 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
         }
 
         /* fill tx descs related to addr & len */
-        vmxnet3_map_pkt(skb, &ctx, tq, adapter->pdev, adapter);
+        if (vmxnet3_map_pkt(skb, &ctx, tq, adapter->pdev, adapter))
+                goto unlock_drop_pkt;
 
         /* setup the EOP desc */
         ctx.eop_txd->dword[3] = cpu_to_le32(VMXNET3_TXD_CQ | VMXNET3_TXD_EOP);
@@ -1231,6 +1249,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
                 struct vmxnet3_rx_buf_info *rbi;
                 struct sk_buff *skb, *new_skb = NULL;
                 struct page *new_page = NULL;
+                dma_addr_t new_dma_addr;
                 int num_to_alloc;
                 struct Vmxnet3_RxDesc *rxd;
                 u32 idx, ring_idx;
@@ -1287,6 +1306,21 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
                                 skip_page_frags = true;
                                 goto rcd_done;
                         }
+                        new_dma_addr = dma_map_single(&adapter->pdev->dev,
+                                                      new_skb->data, rbi->len,
+                                                      PCI_DMA_FROMDEVICE);
+                        if (dma_mapping_error(&adapter->pdev->dev,
+                                              new_dma_addr)) {
+                                dev_kfree_skb(new_skb);
+                                /* Skb allocation failed, do not handover this
+                                 * skb to stack. Reuse it. Drop the existing pkt
+                                 */
+                                rq->stats.rx_buf_alloc_failure++;
+                                ctx->skb = NULL;
+                                rq->stats.drop_total++;
+                                skip_page_frags = true;
+                                goto rcd_done;
+                        }
 
                         dma_unmap_single(&adapter->pdev->dev, rbi->dma_addr,
                                          rbi->len,
@@ -1303,9 +1337,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 
                         /* Immediate refill */
                         rbi->skb = new_skb;
-                        rbi->dma_addr = dma_map_single(&adapter->pdev->dev,
-                                                       rbi->skb->data, rbi->len,
-                                                       PCI_DMA_FROMDEVICE);
+                        rbi->dma_addr = new_dma_addr;
                         rxd->addr = cpu_to_le64(rbi->dma_addr);
                         rxd->len = rbi->len;
                         if (adapter->version == 2 &&
@@ -1348,6 +1380,19 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
                                         skip_page_frags = true;
                                         goto rcd_done;
                                 }
+                                new_dma_addr = dma_map_page(&adapter->pdev->dev
+                                                        , rbi->page,
+                                                        0, PAGE_SIZE,
+                                                        PCI_DMA_FROMDEVICE);
+                                if (dma_mapping_error(&adapter->pdev->dev,
+                                                      new_dma_addr)) {
+                                        put_page(new_page);
+                                        rq->stats.rx_buf_alloc_failure++;
+                                        dev_kfree_skb(ctx->skb);
+                                        ctx->skb = NULL;
+                                        skip_page_frags = true;
+                                        goto rcd_done;
+                                }
 
                                 dma_unmap_page(&adapter->pdev->dev,
                                                rbi->dma_addr, rbi->len,
@@ -1357,10 +1402,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq,
 
                                 /* Immediate refill */
                                 rbi->page = new_page;
-                                rbi->dma_addr = dma_map_page(&adapter->pdev->dev
-                                                        , rbi->page,
-                                                        0, PAGE_SIZE,
-                                                        PCI_DMA_FROMDEVICE);
+                                rbi->dma_addr = new_dma_addr;
                                 rxd->addr = cpu_to_le64(rbi->dma_addr);
                                 rxd->len = rbi->len;
                         }
@@ -2167,7 +2209,8 @@ vmxnet3_set_mc(struct net_device *netdev)
                                                         PCI_DMA_TODEVICE);
                         }
 
-                        if (new_table_pa) {
+                        if (!dma_mapping_error(&adapter->pdev->dev,
+                                               new_table_pa)) {
                                 new_mode |= VMXNET3_RXM_MCAST;
                                 rxConf->mfTablePA = cpu_to_le64(new_table_pa);
                         } else {
@@ -3075,6 +3118,11 @@ vmxnet3_probe_device(struct pci_dev *pdev,
         adapter->adapter_pa = dma_map_single(&adapter->pdev->dev, adapter,
                                              sizeof(struct vmxnet3_adapter),
                                              PCI_DMA_TODEVICE);
+        if (dma_mapping_error(&adapter->pdev->dev, adapter->adapter_pa)) {
+                dev_err(&pdev->dev, "Failed to map dma\n");
+                err = -EFAULT;
+                goto err_dma_map;
+        }
         adapter->shared = dma_alloc_coherent(
                                 &adapter->pdev->dev,
                                 sizeof(struct Vmxnet3_DriverShared),
@@ -3233,6 +3281,7 @@ err_alloc_queue_desc:
 err_alloc_shared:
         dma_unmap_single(&adapter->pdev->dev, adapter->adapter_pa,
                          sizeof(struct vmxnet3_adapter), PCI_DMA_TODEVICE);
+err_dma_map:
         free_netdev(netdev);
         return err;
 }
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 92fa3e1ea65c..4f9748457f5a 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -907,7 +907,6 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev,
                        struct nlattr *tb[], struct nlattr *data[])
 {
         struct net_vrf *vrf = netdev_priv(dev);
-        int err;
 
         if (!data || !data[IFLA_VRF_TABLE])
                 return -EINVAL;
@@ -916,15 +915,7 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev,
 
         dev->priv_flags |= IFF_L3MDEV_MASTER;
 
-        err = register_netdevice(dev);
-        if (err < 0)
-                goto out_fail;
-
-        return 0;
-
-out_fail:
-        free_netdev(dev);
-        return err;
+        return register_netdevice(dev);
 }
 
 static size_t vrf_nl_getsize(const struct net_device *dev)
diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c
index e92aaf615901..89541cc90e87 100644
--- a/drivers/net/wan/hdlc_fr.c
+++ b/drivers/net/wan/hdlc_fr.c
@@ -1075,11 +1075,10 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type)
 
         used = pvc_is_used(pvc);
 
-        if (type == ARPHRD_ETHER) {
+        if (type == ARPHRD_ETHER)
                 dev = alloc_netdev(0, "pvceth%d", NET_NAME_UNKNOWN,
                                    ether_setup);
-                dev->priv_flags &= ~IFF_TX_SKB_SHARING;
-        } else
+        else
                 dev = alloc_netdev(0, "pvc%d", NET_NAME_UNKNOWN, pvc_setup);
 
         if (!dev) {
@@ -1088,9 +1087,10 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type)
                 return -ENOBUFS;
         }
 
-        if (type == ARPHRD_ETHER)
+        if (type == ARPHRD_ETHER) {
+                dev->priv_flags &= ~IFF_TX_SKB_SHARING;
                 eth_hw_addr_random(dev);
-        else {
+        } else {
                 *(__be16*)dev->dev_addr = htons(dlci);
                 dlci_to_q922(dev->broadcast, dlci);
         }
diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c
index 5c47b011a9d7..cd39025d2abf 100644
--- a/drivers/net/wan/x25_asy.c
+++ b/drivers/net/wan/x25_asy.c
@@ -549,16 +549,12 @@ static void x25_asy_receive_buf(struct tty_struct *tty,
 
 static int x25_asy_open_tty(struct tty_struct *tty)
 {
-        struct x25_asy *sl = tty->disc_data;
+        struct x25_asy *sl;
         int err;
 
         if (tty->ops->write == NULL)
                 return -EOPNOTSUPP;
 
-        /* First make sure we're not already connected. */
-        if (sl && sl->magic == X25_ASY_MAGIC)
-                return -EEXIST;
-
         /* OK.  Find a free X.25 channel to use. */
         sl = x25_asy_alloc();
         if (sl == NULL)
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index aa9bd92ac4ed..0947cc271e69 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -51,6 +51,7 @@ MODULE_PARM_DESC(rawmode, "Use raw 802.11 frame datapath");
 static const struct ath10k_hw_params ath10k_hw_params_list[] = {
         {
                 .id = QCA988X_HW_2_0_VERSION,
+                .dev_id = QCA988X_2_0_DEVICE_ID,
                 .name = "qca988x hw2.0",
                 .patch_load_addr = QCA988X_HW_2_0_PATCH_LOAD_ADDR,
                 .uart_pin = 7,
@@ -69,6 +70,25 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
         },
         {
                 .id = QCA6174_HW_2_1_VERSION,
+                .dev_id = QCA6164_2_1_DEVICE_ID,
+                .name = "qca6164 hw2.1",
+                .patch_load_addr = QCA6174_HW_2_1_PATCH_LOAD_ADDR,
+                .uart_pin = 6,
+                .otp_exe_param = 0,
+                .channel_counters_freq_hz = 88000,
+                .max_probe_resp_desc_thres = 0,
+                .fw = {
+                        .dir = QCA6174_HW_2_1_FW_DIR,
+                        .fw = QCA6174_HW_2_1_FW_FILE,
+                        .otp = QCA6174_HW_2_1_OTP_FILE,
+                        .board = QCA6174_HW_2_1_BOARD_DATA_FILE,
+                        .board_size = QCA6174_BOARD_DATA_SZ,
+                        .board_ext_size = QCA6174_BOARD_EXT_DATA_SZ,
+                },
+        },
+        {
+                .id = QCA6174_HW_2_1_VERSION,
+                .dev_id = QCA6174_2_1_DEVICE_ID,
                 .name = "qca6174 hw2.1",
                 .patch_load_addr = QCA6174_HW_2_1_PATCH_LOAD_ADDR,
                 .uart_pin = 6,
@@ -86,6 +106,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
         },
         {
                 .id = QCA6174_HW_3_0_VERSION,
+                .dev_id = QCA6174_2_1_DEVICE_ID,
                 .name = "qca6174 hw3.0",
                 .patch_load_addr = QCA6174_HW_3_0_PATCH_LOAD_ADDR,
                 .uart_pin = 6,
@@ -103,6 +124,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
         },
         {
                 .id = QCA6174_HW_3_2_VERSION,
+                .dev_id = QCA6174_2_1_DEVICE_ID,
                 .name = "qca6174 hw3.2",
                 .patch_load_addr = QCA6174_HW_3_0_PATCH_LOAD_ADDR,
                 .uart_pin = 6,
@@ -121,6 +143,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
         },
         {
                 .id = QCA99X0_HW_2_0_DEV_VERSION,
+                .dev_id = QCA99X0_2_0_DEVICE_ID,
                 .name = "qca99x0 hw2.0",
                 .patch_load_addr = QCA99X0_HW_2_0_PATCH_LOAD_ADDR,
                 .uart_pin = 7,
@@ -139,10 +162,31 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
         },
         {
                 .id = QCA9377_HW_1_0_DEV_VERSION,
+                .dev_id = QCA9377_1_0_DEVICE_ID,
                 .name = "qca9377 hw1.0",
                 .patch_load_addr = QCA9377_HW_1_0_PATCH_LOAD_ADDR,
-                .uart_pin = 7,
+                .uart_pin = 6,
                 .otp_exe_param = 0,
+                .channel_counters_freq_hz = 88000,
+                .max_probe_resp_desc_thres = 0,
+                .fw = {
+                        .dir = QCA9377_HW_1_0_FW_DIR,
+                        .fw = QCA9377_HW_1_0_FW_FILE,
+                        .otp = QCA9377_HW_1_0_OTP_FILE,
+                        .board = QCA9377_HW_1_0_BOARD_DATA_FILE,
+                        .board_size = QCA9377_BOARD_DATA_SZ,
+                        .board_ext_size = QCA9377_BOARD_EXT_DATA_SZ,
+                },
+        },
+        {
+                .id = QCA9377_HW_1_1_DEV_VERSION,
+                .dev_id = QCA9377_1_0_DEVICE_ID,
+                .name = "qca9377 hw1.1",
+                .patch_load_addr = QCA9377_HW_1_0_PATCH_LOAD_ADDR,
+                .uart_pin = 6,
+                .otp_exe_param = 0,
+                .channel_counters_freq_hz = 88000,
+                .max_probe_resp_desc_thres = 0,
                 .fw = {
                         .dir = QCA9377_HW_1_0_FW_DIR,
                         .fw = QCA9377_HW_1_0_FW_FILE,
@@ -1263,7 +1307,8 @@ static int ath10k_init_hw_params(struct ath10k *ar)
         for (i = 0; i < ARRAY_SIZE(ath10k_hw_params_list); i++) {
                 hw_params = &ath10k_hw_params_list[i];
 
-                if (hw_params->id == ar->target_version)
+                if (hw_params->id == ar->target_version &&
+                    hw_params->dev_id == ar->dev_id)
                         break;
         }
 
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 018c64f4fd25..858d75f49a9f 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -636,6 +636,7 @@ struct ath10k {
 
         struct ath10k_hw_params {
                 u32 id;
+                u16 dev_id;
                 const char *name;
                 u32 patch_load_addr;
                 int uart_pin;
diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h
index 39966a05c1cc..713c2bcea178 100644
--- a/drivers/net/wireless/ath/ath10k/hw.h
+++ b/drivers/net/wireless/ath/ath10k/hw.h
@@ -22,6 +22,12 @@
 
 #define ATH10K_FW_DIR                   "ath10k"
 
+#define QCA988X_2_0_DEVICE_ID   (0x003c)
+#define QCA6164_2_1_DEVICE_ID   (0x0041)
+#define QCA6174_2_1_DEVICE_ID   (0x003e)
+#define QCA99X0_2_0_DEVICE_ID   (0x0040)
+#define QCA9377_1_0_DEVICE_ID   (0x0042)
+
 /* QCA988X 1.0 definitions (unsupported) */
 #define QCA988X_HW_1_0_CHIP_ID_REV      0x0
 
@@ -42,6 +48,10 @@
 #define QCA6174_HW_3_0_VERSION          0x05020000
 #define QCA6174_HW_3_2_VERSION          0x05030000
 
+/* QCA9377 target BMI version signatures */
+#define QCA9377_HW_1_0_DEV_VERSION      0x05020000
+#define QCA9377_HW_1_1_DEV_VERSION      0x05020001
+
 enum qca6174_pci_rev {
         QCA6174_PCI_REV_1_1 = 0x11,
         QCA6174_PCI_REV_1_3 = 0x13,
@@ -60,6 +70,11 @@ enum qca6174_chip_id_rev {
         QCA6174_HW_3_2_CHIP_ID_REV = 10,
 };
 
+enum qca9377_chip_id_rev {
+        QCA9377_HW_1_0_CHIP_ID_REV = 0x0,
+        QCA9377_HW_1_1_CHIP_ID_REV = 0x1,
+};
+
 #define QCA6174_HW_2_1_FW_DIR           "ath10k/QCA6174/hw2.1"
 #define QCA6174_HW_2_1_FW_FILE          "firmware.bin"
 #define QCA6174_HW_2_1_OTP_FILE         "otp.bin"
@@ -85,8 +100,6 @@ enum qca6174_chip_id_rev {
 #define QCA99X0_HW_2_0_PATCH_LOAD_ADDR  0x1234
 
 /* QCA9377 1.0 definitions */
-#define QCA9377_HW_1_0_DEV_VERSION     0x05020001
-#define QCA9377_HW_1_0_CHIP_ID_REV     0x1
 #define QCA9377_HW_1_0_FW_DIR          ATH10K_FW_DIR "/QCA9377/hw1.0"
 #define QCA9377_HW_1_0_FW_FILE         "firmware.bin"
 #define QCA9377_HW_1_0_OTP_FILE        "otp.bin"
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index a7411fe90cc4..95a55405ebf0 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -4225,7 +4225,7 @@ static int ath10k_config(struct ieee80211_hw *hw, u32 changed)
 
 static u32 get_nss_from_chainmask(u16 chain_mask)
 {
-        if ((chain_mask & 0x15) == 0x15)
+        if ((chain_mask & 0xf) == 0xf)
                 return 4;
         else if ((chain_mask & 0x7) == 0x7)
                 return 3;
diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index 3fca200b986c..930785a724e1 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -57,12 +57,6 @@ MODULE_PARM_DESC(reset_mode, "0: auto, 1: warm only (default: 0)");
 #define ATH10K_PCI_TARGET_WAIT 3000
 #define ATH10K_PCI_NUM_WARM_RESET_ATTEMPTS 3
 
-#define QCA988X_2_0_DEVICE_ID   (0x003c)
-#define QCA6164_2_1_DEVICE_ID   (0x0041)
-#define QCA6174_2_1_DEVICE_ID   (0x003e)
-#define QCA99X0_2_0_DEVICE_ID   (0x0040)
-#define QCA9377_1_0_DEVICE_ID   (0x0042)
-
 static const struct pci_device_id ath10k_pci_id_table[] = {
         { PCI_VDEVICE(ATHEROS, QCA988X_2_0_DEVICE_ID) }, /* PCI-E QCA988X V2 */
         { PCI_VDEVICE(ATHEROS, QCA6164_2_1_DEVICE_ID) }, /* PCI-E QCA6164 V2.1 */
@@ -92,7 +86,9 @@ static const struct ath10k_pci_supp_chip ath10k_pci_supp_chips[] = {
         { QCA6174_2_1_DEVICE_ID, QCA6174_HW_3_2_CHIP_ID_REV },
 
         { QCA99X0_2_0_DEVICE_ID, QCA99X0_HW_2_0_CHIP_ID_REV },
+
         { QCA9377_1_0_DEVICE_ID, QCA9377_HW_1_0_CHIP_ID_REV },
+        { QCA9377_1_0_DEVICE_ID, QCA9377_HW_1_1_CHIP_ID_REV },
 };
 
 static void ath10k_pci_buffer_cleanup(struct ath10k *ar);
@@ -111,8 +107,9 @@ static void ath10k_pci_htc_tx_cb(struct ath10k_ce_pipe *ce_state);
 static void ath10k_pci_htc_rx_cb(struct ath10k_ce_pipe *ce_state);
 static void ath10k_pci_htt_tx_cb(struct ath10k_ce_pipe *ce_state);
 static void ath10k_pci_htt_rx_cb(struct ath10k_ce_pipe *ce_state);
+static void ath10k_pci_htt_htc_rx_cb(struct ath10k_ce_pipe *ce_state);
 
-static const struct ce_attr host_ce_config_wlan[] = {
+static struct ce_attr host_ce_config_wlan[] = {
         /* CE0: host->target HTC control and raw streams */
         {
                 .flags = CE_ATTR_FLAGS,
@@ -128,7 +125,7 @@ static const struct ce_attr host_ce_config_wlan[] = {
                 .src_nentries = 0,
                 .src_sz_max = 2048,
                 .dest_nentries = 512,
-                .recv_cb = ath10k_pci_htc_rx_cb,
+                .recv_cb = ath10k_pci_htt_htc_rx_cb,
         },
 
         /* CE2: target->host WMI */
@@ -217,7 +214,7 @@ static const struct ce_attr host_ce_config_wlan[] = {
 };
 
 /* Target firmware's Copy Engine configuration. */
-static const struct ce_pipe_config target_ce_config_wlan[] = {
+static struct ce_pipe_config target_ce_config_wlan[] = {
         /* CE0: host->target HTC control and raw streams */
         {
                 .pipenum = __cpu_to_le32(0),
@@ -330,7 +327,7 @@ static const struct ce_pipe_config target_ce_config_wlan[] = {
  * This table is derived from the CE_PCI TABLE, above.
  * It is passed to the Target at startup for use by firmware.
  */
-static const struct service_to_pipe target_service_to_ce_map_wlan[] = {
+static struct service_to_pipe target_service_to_ce_map_wlan[] = {
         {
                 __cpu_to_le32(ATH10K_HTC_SVC_ID_WMI_DATA_VO),
                 __cpu_to_le32(PIPEDIR_OUT),     /* out = UL = host -> target */
@@ -1208,6 +1205,16 @@ static void ath10k_pci_htc_rx_cb(struct ath10k_ce_pipe *ce_state)
         ath10k_pci_process_rx_cb(ce_state, ath10k_htc_rx_completion_handler);
 }
 
+static void ath10k_pci_htt_htc_rx_cb(struct ath10k_ce_pipe *ce_state)
+{
+        /* CE4 polling needs to be done whenever CE pipe which transports
+         * HTT Rx (target->host) is processed.
+         */
+        ath10k_ce_per_engine_service(ce_state->ar, 4);
+
+        ath10k_pci_process_rx_cb(ce_state, ath10k_htc_rx_completion_handler);
+}
+
 /* Called by lower (CE) layer when a send to HTT Target completes. */
 static void ath10k_pci_htt_tx_cb(struct ath10k_ce_pipe *ce_state)
 {
@@ -2027,6 +2034,29 @@ static int ath10k_pci_init_config(struct ath10k *ar)
         return 0;
 }
 
+static void ath10k_pci_override_ce_config(struct ath10k *ar)
+{
+        struct ce_attr *attr;
+        struct ce_pipe_config *config;
+
+        /* For QCA6174 we're overriding the Copy Engine 5 configuration,
+         * since it is currently used for other feature.
+         */
+
+        /* Override Host's Copy Engine 5 configuration */
+        attr = &host_ce_config_wlan[5];
+        attr->src_sz_max = 0;
+        attr->dest_nentries = 0;
+
+        /* Override Target firmware's Copy Engine configuration */
+        config = &target_ce_config_wlan[5];
+        config->pipedir = __cpu_to_le32(PIPEDIR_OUT);
+        config->nbytes_max = __cpu_to_le32(2048);
+
+        /* Map from service/endpoint to Copy Engine */
+        target_service_to_ce_map_wlan[15].pipenum = __cpu_to_le32(1);
+}
+
 static int ath10k_pci_alloc_pipes(struct ath10k *ar)
 {
         struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
@@ -3020,6 +3050,9 @@ static int ath10k_pci_probe(struct pci_dev *pdev,
                 goto err_core_destroy;
         }
 
+        if (QCA_REV_6174(ar))
+                ath10k_pci_override_ce_config(ar);
+
         ret = ath10k_pci_alloc_pipes(ar);
         if (ret) {
                 ath10k_err(ar, "failed to allocate copy engine pipes: %d\n",
diff --git a/drivers/net/wireless/iwlwifi/iwl-7000.c b/drivers/net/wireless/iwlwifi/iwl-7000.c
index 1a73c7a1da77..bf88ec3a65fa 100644
--- a/drivers/net/wireless/iwlwifi/iwl-7000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-7000.c
@@ -69,7 +69,7 @@
 #include "iwl-agn-hw.h"
 
 /* Highest firmware API version supported */
-#define IWL7260_UCODE_API_MAX   17
+#define IWL7260_UCODE_API_MAX   19
 
 /* Oldest version we won't warn about */
 #define IWL7260_UCODE_API_OK    13
diff --git a/drivers/net/wireless/iwlwifi/iwl-8000.c b/drivers/net/wireless/iwlwifi/iwl-8000.c
index 0116e5a4c393..9bcc0bf937d8 100644
--- a/drivers/net/wireless/iwlwifi/iwl-8000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-8000.c
@@ -69,7 +69,7 @@
 #include "iwl-agn-hw.h"
 
 /* Highest firmware API version supported */
-#define IWL8000_UCODE_API_MAX   17
+#define IWL8000_UCODE_API_MAX   19
 
 /* Oldest version we won't warn about */
 #define IWL8000_UCODE_API_OK    13
diff --git a/drivers/net/wireless/iwlwifi/mvm/d3.c b/drivers/net/wireless/iwlwifi/mvm/d3.c
index 85ae902df7c0..29ae58ebf223 100644
--- a/drivers/net/wireless/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/iwlwifi/mvm/d3.c
@@ -309,9 +309,9 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
          * to transmit packets to the AP, i.e. the PTK.
          */
         if (key->flags & IEEE80211_KEY_FLAG_PAIRWISE) {
-                key->hw_key_idx = 0;
                 mvm->ptk_ivlen = key->iv_len;
                 mvm->ptk_icvlen = key->icv_len;
+                ret = iwl_mvm_set_sta_key(mvm, vif, sta, key, 0);
         } else {
                 /*
                  * firmware only supports TSC/RSC for a single key,
@@ -319,12 +319,11 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
                  * with new ones -- this relies on mac80211 doing
                  * list_add_tail().
                  */
-                key->hw_key_idx = 1;
                 mvm->gtk_ivlen = key->iv_len;
                 mvm->gtk_icvlen = key->icv_len;
+                ret = iwl_mvm_set_sta_key(mvm, vif, sta, key, 1);
         }
 
-        ret = iwl_mvm_set_sta_key(mvm, vif, sta, key, true);
         data->error = ret != 0;
 out_unlock:
         mutex_unlock(&mvm->mutex);
@@ -772,9 +771,6 @@ static int iwl_mvm_switch_to_d3(struct iwl_mvm *mvm)
          */
         set_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status);
 
-        /* We reprogram keys and shouldn't allocate new key indices */
-        memset(mvm->fw_key_table, 0, sizeof(mvm->fw_key_table));
-
         mvm->ptk_ivlen = 0;
         mvm->ptk_icvlen = 0;
         mvm->ptk_ivlen = 0;
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index 1fb684693040..e88afac51c5d 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -2941,6 +2941,7 @@ static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
 {
         struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
         int ret;
+        u8 key_offset;
 
         if (iwlwifi_mod_params.sw_crypto) {
                 IWL_DEBUG_MAC80211(mvm, "leave - hwcrypto disabled\n");
@@ -3006,10 +3007,14 @@ static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
                         break;
                 }
 
+                /* in HW restart reuse the index, otherwise request a new one */
+                if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))
+                        key_offset = key->hw_key_idx;
+                else
+                        key_offset = STA_KEY_IDX_INVALID;
+
                 IWL_DEBUG_MAC80211(mvm, "set hwcrypto key\n");
-                ret = iwl_mvm_set_sta_key(mvm, vif, sta, key,
-                                          test_bit(IWL_MVM_STATUS_IN_HW_RESTART,
-                                                   &mvm->status));
+                ret = iwl_mvm_set_sta_key(mvm, vif, sta, key, key_offset);
                 if (ret) {
                         IWL_WARN(mvm, "set key failed\n");
                         /*
diff --git a/drivers/net/wireless/iwlwifi/mvm/sta.c b/drivers/net/wireless/iwlwifi/mvm/sta.c
index 300a249486e4..354acbde088e 100644
--- a/drivers/net/wireless/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/iwlwifi/mvm/sta.c
@@ -1201,7 +1201,8 @@ static int iwl_mvm_set_fw_key_idx(struct iwl_mvm *mvm)
         return max_offs;
 }
 
-static u8 iwl_mvm_get_key_sta_id(struct ieee80211_vif *vif,
+static u8 iwl_mvm_get_key_sta_id(struct iwl_mvm *mvm,
+                                 struct ieee80211_vif *vif,
                                  struct ieee80211_sta *sta)
 {
         struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
@@ -1218,8 +1219,21 @@ static u8 iwl_mvm_get_key_sta_id(struct ieee80211_vif *vif,
          * station ID, then use AP's station ID.
          */
         if (vif->type == NL80211_IFTYPE_STATION &&
-            mvmvif->ap_sta_id != IWL_MVM_STATION_COUNT)
-                return mvmvif->ap_sta_id;
+            mvmvif->ap_sta_id != IWL_MVM_STATION_COUNT) {
+                u8 sta_id = mvmvif->ap_sta_id;
+
+                sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[sta_id],
+                                                lockdep_is_held(&mvm->mutex));
+                /*
+                 * It is possible that the 'sta' parameter is NULL,
+                 * for example when a GTK is removed - the sta_id will then
+                 * be the AP ID, and no station was passed by mac80211.
+                 */
+                if (IS_ERR_OR_NULL(sta))
+                        return IWL_MVM_STATION_COUNT;
+
+                return sta_id;
+        }
 
         return IWL_MVM_STATION_COUNT;
 }
@@ -1227,7 +1241,8 @@ static u8 iwl_mvm_get_key_sta_id(struct ieee80211_vif *vif,
 static int iwl_mvm_send_sta_key(struct iwl_mvm *mvm,
                                 struct iwl_mvm_sta *mvm_sta,
                                 struct ieee80211_key_conf *keyconf, bool mcast,
-                                u32 tkip_iv32, u16 *tkip_p1k, u32 cmd_flags)
+                                u32 tkip_iv32, u16 *tkip_p1k, u32 cmd_flags,
+                                u8 key_offset)
 {
         struct iwl_mvm_add_sta_key_cmd cmd = {};
         __le16 key_flags;
@@ -1269,7 +1284,7 @@ static int iwl_mvm_send_sta_key(struct iwl_mvm *mvm,
         if (mcast)
                 key_flags |= cpu_to_le16(STA_KEY_MULTICAST);
 
-        cmd.key_offset = keyconf->hw_key_idx;
+        cmd.key_offset = key_offset;
         cmd.key_flags = key_flags;
         cmd.sta_id = sta_id;
 
@@ -1360,6 +1375,7 @@ static int __iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
                                  struct ieee80211_vif *vif,
                                  struct ieee80211_sta *sta,
                                  struct ieee80211_key_conf *keyconf,
+                                 u8 key_offset,
                                  bool mcast)
 {
         struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta);
@@ -1375,17 +1391,17 @@ static int __iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
                 ieee80211_get_key_rx_seq(keyconf, 0, &seq);
                 ieee80211_get_tkip_rx_p1k(keyconf, addr, seq.tkip.iv32, p1k);
                 ret = iwl_mvm_send_sta_key(mvm, mvm_sta, keyconf, mcast,
-                                           seq.tkip.iv32, p1k, 0);
+                                           seq.tkip.iv32, p1k, 0, key_offset);
                 break;
         case WLAN_CIPHER_SUITE_CCMP:
         case WLAN_CIPHER_SUITE_WEP40:
         case WLAN_CIPHER_SUITE_WEP104:
                 ret = iwl_mvm_send_sta_key(mvm, mvm_sta, keyconf, mcast,
-                                           0, NULL, 0);
+                                           0, NULL, 0, key_offset);
                 break;
         default:
                 ret = iwl_mvm_send_sta_key(mvm, mvm_sta, keyconf, mcast,
-                                           0, NULL, 0);
+                                           0, NULL, 0, key_offset);
         }
 
         return ret;
@@ -1433,7 +1449,7 @@ int iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
                         struct ieee80211_vif *vif,
                         struct ieee80211_sta *sta,
                         struct ieee80211_key_conf *keyconf,
-                        bool have_key_offset)
+                        u8 key_offset)
 {
         bool mcast = !(keyconf->flags & IEEE80211_KEY_FLAG_PAIRWISE);
         u8 sta_id;
@@ -1443,7 +1459,7 @@ int iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
         lockdep_assert_held(&mvm->mutex);
 
         /* Get the station id from the mvm local station table */
-        sta_id = iwl_mvm_get_key_sta_id(vif, sta);
+        sta_id = iwl_mvm_get_key_sta_id(mvm, vif, sta);
         if (sta_id == IWL_MVM_STATION_COUNT) {
                 IWL_ERR(mvm, "Failed to find station id\n");
                 return -EINVAL;
@@ -1470,18 +1486,25 @@ int iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
         if (WARN_ON_ONCE(iwl_mvm_sta_from_mac80211(sta)->vif != vif))
                 return -EINVAL;
 
-        if (!have_key_offset) {
-                /*
-                 * The D3 firmware hardcodes the PTK offset to 0, so we have to
-                 * configure it there. As a result, this workaround exists to
-                 * let the caller set the key offset (hw_key_idx), see d3.c.
-                 */
-                keyconf->hw_key_idx = iwl_mvm_set_fw_key_idx(mvm);
-                if (keyconf->hw_key_idx == STA_KEY_IDX_INVALID)
+        /* If the key_offset is not pre-assigned, we need to find a
+         * new offset to use.  In normal cases, the offset is not
+         * pre-assigned, but during HW_RESTART we want to reuse the
+         * same indices, so we pass them when this function is called.
+         *
+         * In D3 entry, we need to hardcoded the indices (because the
+         * firmware hardcodes the PTK offset to 0).  In this case, we
+         * need to make sure we don't overwrite the hw_key_idx in the
+         * keyconf structure, because otherwise we cannot configure
+         * the original ones back when resuming.
+         */
+        if (key_offset == STA_KEY_IDX_INVALID) {
+                key_offset  = iwl_mvm_set_fw_key_idx(mvm);
+                if (key_offset == STA_KEY_IDX_INVALID)
                         return -ENOSPC;
+                keyconf->hw_key_idx = key_offset;
         }
 
-        ret = __iwl_mvm_set_sta_key(mvm, vif, sta, keyconf, mcast);
+        ret = __iwl_mvm_set_sta_key(mvm, vif, sta, keyconf, key_offset, mcast);
         if (ret) {
                 __clear_bit(keyconf->hw_key_idx, mvm->fw_key_table);
                 goto end;
@@ -1495,7 +1518,8 @@ int iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
          */
         if (keyconf->cipher == WLAN_CIPHER_SUITE_WEP40 ||
             keyconf->cipher == WLAN_CIPHER_SUITE_WEP104) {
-                ret = __iwl_mvm_set_sta_key(mvm, vif, sta, keyconf, !mcast);
+                ret = __iwl_mvm_set_sta_key(mvm, vif, sta, keyconf,
+                                            key_offset, !mcast);
                 if (ret) {
                         __clear_bit(keyconf->hw_key_idx, mvm->fw_key_table);
                         __iwl_mvm_remove_sta_key(mvm, sta_id, keyconf, mcast);
@@ -1521,7 +1545,7 @@ int iwl_mvm_remove_sta_key(struct iwl_mvm *mvm,
         lockdep_assert_held(&mvm->mutex);
 
         /* Get the station id from the mvm local station table */
-        sta_id = iwl_mvm_get_key_sta_id(vif, sta);
+        sta_id = iwl_mvm_get_key_sta_id(mvm, vif, sta);
 
         IWL_DEBUG_WEP(mvm, "mvm remove dynamic key: idx=%d sta=%d\n",
                       keyconf->keyidx, sta_id);
@@ -1547,24 +1571,6 @@ int iwl_mvm_remove_sta_key(struct iwl_mvm *mvm,
                 return 0;
         }
 
-        /*
-         * It is possible that the 'sta' parameter is NULL, and thus
-         * there is a need to retrieve the sta from the local station table,
-         * for example when a GTK is removed (where the sta_id will then be
-         * the AP ID, and no station was passed by mac80211.)
-         */
-        if (!sta) {
-                sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[sta_id],
-                                                lockdep_is_held(&mvm->mutex));
-                if (!sta) {
-                        IWL_ERR(mvm, "Invalid station id\n");
-                        return -EINVAL;
-                }
-        }
-
-        if (WARN_ON_ONCE(iwl_mvm_sta_from_mac80211(sta)->vif != vif))
-                return -EINVAL;
-
         ret = __iwl_mvm_remove_sta_key(mvm, sta_id, keyconf, mcast);
         if (ret)
                 return ret;
@@ -1584,7 +1590,7 @@ void iwl_mvm_update_tkip_key(struct iwl_mvm *mvm,
                              u16 *phase1key)
 {
         struct iwl_mvm_sta *mvm_sta;
-        u8 sta_id = iwl_mvm_get_key_sta_id(vif, sta);
+        u8 sta_id = iwl_mvm_get_key_sta_id(mvm, vif, sta);
         bool mcast = !(keyconf->flags & IEEE80211_KEY_FLAG_PAIRWISE);
 
         if (WARN_ON_ONCE(sta_id == IWL_MVM_STATION_COUNT))
@@ -1602,7 +1608,7 @@ void iwl_mvm_update_tkip_key(struct iwl_mvm *mvm,
 
         mvm_sta = iwl_mvm_sta_from_mac80211(sta);
         iwl_mvm_send_sta_key(mvm, mvm_sta, keyconf, mcast,
-                             iv32, phase1key, CMD_ASYNC);
+                             iv32, phase1key, CMD_ASYNC, keyconf->hw_key_idx);
         rcu_read_unlock();
 }
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/sta.h b/drivers/net/wireless/iwlwifi/mvm/sta.h
index eedb215eba3f..0631cc0a6d3c 100644
--- a/drivers/net/wireless/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/iwlwifi/mvm/sta.h
@@ -365,8 +365,8 @@ int iwl_mvm_rm_sta_id(struct iwl_mvm *mvm,
 int iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
                         struct ieee80211_vif *vif,
                         struct ieee80211_sta *sta,
-                        struct ieee80211_key_conf *key,
-                        bool have_key_offset);
+                        struct ieee80211_key_conf *keyconf,
+                        u8 key_offset);
 int iwl_mvm_remove_sta_key(struct iwl_mvm *mvm,
                            struct ieee80211_vif *vif,
                            struct ieee80211_sta *sta,
diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c
index 644b58bc5226..639761fb2bfb 100644
--- a/drivers/net/wireless/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/iwlwifi/pcie/drv.c
@@ -423,14 +423,21 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 /* 8000 Series */
         {IWL_PCI_DEVICE(0x24F3, 0x0010, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x1010, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x0130, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x1130, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x0132, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x1132, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x0110, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x01F0, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x0012, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x1012, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x1110, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x0050, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x0250, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x1050, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x0150, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x1150, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F4, 0x0030, iwl8260_2ac_cfg)},
-        {IWL_PCI_DEVICE(0x24F4, 0x1130, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F4, 0x1030, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0xC010, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0xC110, iwl8260_2ac_cfg)},
@@ -438,18 +445,28 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
         {IWL_PCI_DEVICE(0x24F3, 0xC050, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0xD050, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x8010, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x8110, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x9010, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x9110, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F4, 0x8030, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F4, 0x9030, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x8130, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x9130, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x8132, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x9132, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x8050, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x8150, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x9050, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x9150, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x0004, iwl8260_2n_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x0044, iwl8260_2n_cfg)},
         {IWL_PCI_DEVICE(0x24F5, 0x0010, iwl4165_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F6, 0x0030, iwl4165_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x0810, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x0910, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x0850, iwl8260_2ac_cfg)},
         {IWL_PCI_DEVICE(0x24F3, 0x0950, iwl8260_2ac_cfg)},
+        {IWL_PCI_DEVICE(0x24F3, 0x0930, iwl8260_2ac_cfg)},
 #endif /* CONFIG_IWLMVM */
 
         {0}
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
index 6e9418ed90c2..bbb789f8990b 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c
@@ -2272,7 +2272,7 @@ void rtl8821ae_enable_interrupt(struct ieee80211_hw *hw)
         struct rtl_priv *rtlpriv = rtl_priv(hw);
         struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 
-        if (!rtlpci->int_clear)
+        if (rtlpci->int_clear)
                 rtl8821ae_clear_interrupt(hw);/*clear it here first*/
 
         rtl_write_dword(rtlpriv, REG_HIMR, rtlpci->irq_mask[0] & 0xFFFFFFFF);
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
index 8ee141a55bc5..142bdff4ed60 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c
@@ -448,7 +448,7 @@ MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n");
 MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 1)\n");
 MODULE_PARM_DESC(debug, "Set debug level (0-5) (default 0)");
 MODULE_PARM_DESC(disable_watchdog, "Set to 1 to disable the watchdog (default 0)\n");
-MODULE_PARM_DESC(int_clear, "Set to 1 to disable interrupt clear before set (default 0)\n");
+MODULE_PARM_DESC(int_clear, "Set to 0 to disable interrupt clear before set (default 1)\n");
 
 static SIMPLE_DEV_PM_OPS(rtlwifi_pm_ops, rtl_pci_suspend, rtl_pci_resume);
 
diff --git a/drivers/nvme/host/Makefile b/drivers/nvme/host/Makefile
index 219dc206fa5f..a5fe23952586 100644
--- a/drivers/nvme/host/Makefile
+++ b/drivers/nvme/host/Makefile
@@ -1,4 +1,5 @@
 
 obj-$(CONFIG_BLK_DEV_NVME)     += nvme.o
 
-nvme-y          += pci.o scsi.o lightnvm.o
+lightnvm-$(CONFIG_NVM)  := lightnvm.o
+nvme-y          += pci.o scsi.o $(lightnvm-y)
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index e0b7b95813bc..15f2acb4d5cd 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -22,8 +22,6 @@
 
 #include "nvme.h"
 
-#ifdef CONFIG_NVM
-
 #include <linux/nvme.h>
 #include <linux/bitops.h>
 #include <linux/lightnvm.h>
@@ -93,7 +91,7 @@ struct nvme_nvm_l2ptbl {
         __le16                  cdw14[6];
 };
 
-struct nvme_nvm_bbtbl {
+struct nvme_nvm_getbbtbl {
         __u8                    opcode;
         __u8                    flags;
         __u16                   command_id;
@@ -101,10 +99,23 @@ struct nvme_nvm_bbtbl {
         __u64                   rsvd[2];
         __le64                  prp1;
         __le64                  prp2;
-        __le32                  prp1_len;
-        __le32                  prp2_len;
-        __le32                  lbb;
-        __u32                   rsvd11[3];
+        __le64                  spba;
+        __u32                   rsvd4[4];
+};
+
+struct nvme_nvm_setbbtbl {
+        __u8                    opcode;
+        __u8                    flags;
+        __u16                   command_id;
+        __le32                  nsid;
+        __le64                  rsvd[2];
+        __le64                  prp1;
+        __le64                  prp2;
+        __le64                  spba;
+        __le16                  nlb;
+        __u8                    value;
+        __u8                    rsvd3;
+        __u32                   rsvd4[3];
 };
 
 struct nvme_nvm_erase_blk {
@@ -129,8 +140,8 @@ struct nvme_nvm_command {
                 struct nvme_nvm_hb_rw hb_rw;
                 struct nvme_nvm_ph_rw ph_rw;
                 struct nvme_nvm_l2ptbl l2p;
-                struct nvme_nvm_bbtbl get_bb;
-                struct nvme_nvm_bbtbl set_bb;
+                struct nvme_nvm_getbbtbl get_bb;
+                struct nvme_nvm_setbbtbl set_bb;
                 struct nvme_nvm_erase_blk erase;
         };
 };
@@ -142,11 +153,13 @@ struct nvme_nvm_id_group {
         __u8                    num_ch;
         __u8                    num_lun;
         __u8                    num_pln;
+        __u8                    rsvd1;
         __le16                  num_blk;
         __le16                  num_pg;
         __le16                  fpg_sz;
         __le16                  csecs;
         __le16                  sos;
+        __le16                  rsvd2;
         __le32                  trdt;
         __le32                  trdm;
         __le32                  tprt;
@@ -154,8 +167,9 @@ struct nvme_nvm_id_group {
         __le32                  tbet;
         __le32                  tbem;
         __le32                  mpos;
+        __le32                  mccap;
         __le16                  cpar;
-        __u8                    reserved[913];
+        __u8                    reserved[906];
 } __packed;
 
 struct nvme_nvm_addr_format {
@@ -178,15 +192,28 @@ struct nvme_nvm_id {
         __u8                    ver_id;
         __u8                    vmnt;
         __u8                    cgrps;
-        __u8                    res[5];
+        __u8                    res;
         __le32                  cap;
         __le32                  dom;
         struct nvme_nvm_addr_format ppaf;
-        __u8                    ppat;
-        __u8                    resv[223];
+        __u8                    resv[228];
         struct nvme_nvm_id_group groups[4];
 } __packed;
 
+struct nvme_nvm_bb_tbl {
+        __u8    tblid[4];
+        __le16  verid;
+        __le16  revid;
+        __le32  rvsd1;
+        __le32  tblks;
+        __le32  tfact;
+        __le32  tgrown;
+        __le32  tdresv;
+        __le32  thresv;
+        __le32  rsvd2[8];
+        __u8    blk[0];
+};
+
 /*
  * Check we didn't inadvertently grow the command struct
  */
@@ -195,12 +222,14 @@ static inline void _nvme_nvm_check_size(void)
         BUILD_BUG_ON(sizeof(struct nvme_nvm_identity) != 64);
         BUILD_BUG_ON(sizeof(struct nvme_nvm_hb_rw) != 64);
         BUILD_BUG_ON(sizeof(struct nvme_nvm_ph_rw) != 64);
-        BUILD_BUG_ON(sizeof(struct nvme_nvm_bbtbl) != 64);
+        BUILD_BUG_ON(sizeof(struct nvme_nvm_getbbtbl) != 64);
+        BUILD_BUG_ON(sizeof(struct nvme_nvm_setbbtbl) != 64);
         BUILD_BUG_ON(sizeof(struct nvme_nvm_l2ptbl) != 64);
         BUILD_BUG_ON(sizeof(struct nvme_nvm_erase_blk) != 64);
         BUILD_BUG_ON(sizeof(struct nvme_nvm_id_group) != 960);
         BUILD_BUG_ON(sizeof(struct nvme_nvm_addr_format) != 128);
         BUILD_BUG_ON(sizeof(struct nvme_nvm_id) != 4096);
+        BUILD_BUG_ON(sizeof(struct nvme_nvm_bb_tbl) != 512);
 }
 
 static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
@@ -234,6 +263,7 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
                 dst->tbet = le32_to_cpu(src->tbet);
                 dst->tbem = le32_to_cpu(src->tbem);
                 dst->mpos = le32_to_cpu(src->mpos);
+                dst->mccap = le32_to_cpu(src->mccap);
 
                 dst->cpar = le16_to_cpu(src->cpar);
         }
@@ -241,9 +271,10 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
         return 0;
 }
 
-static int nvme_nvm_identity(struct request_queue *q, struct nvm_id *nvm_id)
+static int nvme_nvm_identity(struct nvm_dev *nvmdev, struct nvm_id *nvm_id)
 {
-        struct nvme_ns *ns = q->queuedata;
+        struct nvme_ns *ns = nvmdev->q->queuedata;
+        struct nvme_dev *dev = ns->dev;
         struct nvme_nvm_id *nvme_nvm_id;
         struct nvme_nvm_command c = {};
         int ret;
@@ -256,8 +287,8 @@ static int nvme_nvm_identity(struct request_queue *q, struct nvm_id *nvm_id)
         if (!nvme_nvm_id)
                 return -ENOMEM;
 
-        ret = nvme_submit_sync_cmd(q, (struct nvme_command *)&c, nvme_nvm_id,
-                                                sizeof(struct nvme_nvm_id));
+        ret = nvme_submit_sync_cmd(dev->admin_q, (struct nvme_command *)&c,
+                                nvme_nvm_id, sizeof(struct nvme_nvm_id));
         if (ret) {
                 ret = -EIO;
                 goto out;
@@ -268,6 +299,8 @@ static int nvme_nvm_identity(struct request_queue *q, struct nvm_id *nvm_id)
         nvm_id->cgrps = nvme_nvm_id->cgrps;
         nvm_id->cap = le32_to_cpu(nvme_nvm_id->cap);
         nvm_id->dom = le32_to_cpu(nvme_nvm_id->dom);
+        memcpy(&nvm_id->ppaf, &nvme_nvm_id->ppaf,
+                                        sizeof(struct nvme_nvm_addr_format));
 
         ret = init_grps(nvm_id, nvme_nvm_id);
 out:
@@ -275,13 +308,13 @@ out:
         return ret;
 }
 
-static int nvme_nvm_get_l2p_tbl(struct request_queue *q, u64 slba, u32 nlb,
+static int nvme_nvm_get_l2p_tbl(struct nvm_dev *nvmdev, u64 slba, u32 nlb,
                                 nvm_l2p_update_fn *update_l2p, void *priv)
 {
-        struct nvme_ns *ns = q->queuedata;
+        struct nvme_ns *ns = nvmdev->q->queuedata;
         struct nvme_dev *dev = ns->dev;
         struct nvme_nvm_command c = {};
-        u32 len = queue_max_hw_sectors(q) << 9;
+        u32 len = queue_max_hw_sectors(dev->admin_q) << 9;
         u32 nlb_pr_rq = len / sizeof(u64);
         u64 cmd_slba = slba;
         void *entries;
@@ -299,8 +332,8 @@ static int nvme_nvm_get_l2p_tbl(struct request_queue *q, u64 slba, u32 nlb,
                 c.l2p.slba = cpu_to_le64(cmd_slba);
                 c.l2p.nlb = cpu_to_le32(cmd_nlb);
 
-                ret = nvme_submit_sync_cmd(q, (struct nvme_command *)&c,
-                                                                entries, len);
+                ret = nvme_submit_sync_cmd(dev->admin_q,
+                                (struct nvme_command *)&c, entries, len);
                 if (ret) {
                         dev_err(dev->dev, "L2P table transfer failed (%d)\n",
                                                                         ret);
@@ -322,43 +355,84 @@ out:
         return ret;
 }
 
-static int nvme_nvm_get_bb_tbl(struct request_queue *q, int lunid,
-                                unsigned int nr_blocks,
-                                nvm_bb_update_fn *update_bbtbl, void *priv)
+static int nvme_nvm_get_bb_tbl(struct nvm_dev *nvmdev, struct ppa_addr ppa,
+                                int nr_blocks, nvm_bb_update_fn *update_bbtbl,
+                                void *priv)
 {
+        struct request_queue *q = nvmdev->q;
         struct nvme_ns *ns = q->queuedata;
         struct nvme_dev *dev = ns->dev;
         struct nvme_nvm_command c = {};
-        void *bb_bitmap;
-        u16 bb_bitmap_size;
+        struct nvme_nvm_bb_tbl *bb_tbl;
+        int tblsz = sizeof(struct nvme_nvm_bb_tbl) + nr_blocks;
         int ret = 0;
 
         c.get_bb.opcode = nvme_nvm_admin_get_bb_tbl;
         c.get_bb.nsid = cpu_to_le32(ns->ns_id);
-        c.get_bb.lbb = cpu_to_le32(lunid);
-        bb_bitmap_size = ((nr_blocks >> 15) + 1) * PAGE_SIZE;
-        bb_bitmap = kmalloc(bb_bitmap_size, GFP_KERNEL);
-        if (!bb_bitmap)
-                return -ENOMEM;
+        c.get_bb.spba = cpu_to_le64(ppa.ppa);
 
-        bitmap_zero(bb_bitmap, nr_blocks);
+        bb_tbl = kzalloc(tblsz, GFP_KERNEL);
+        if (!bb_tbl)
+                return -ENOMEM;
 
-        ret = nvme_submit_sync_cmd(q, (struct nvme_command *)&c, bb_bitmap,
-                                                                bb_bitmap_size);
+        ret = nvme_submit_sync_cmd(dev->admin_q, (struct nvme_command *)&c,
+                                                                bb_tbl, tblsz);
         if (ret) {
                 dev_err(dev->dev, "get bad block table failed (%d)\n", ret);
                 ret = -EIO;
                 goto out;
         }
 
-        ret = update_bbtbl(lunid, bb_bitmap, nr_blocks, priv);
+        if (bb_tbl->tblid[0] != 'B' || bb_tbl->tblid[1] != 'B' ||
+                bb_tbl->tblid[2] != 'L' || bb_tbl->tblid[3] != 'T') {
+                dev_err(dev->dev, "bbt format mismatch\n");
+                ret = -EINVAL;
+                goto out;
+        }
+
+        if (le16_to_cpu(bb_tbl->verid) != 1) {
+                ret = -EINVAL;
+                dev_err(dev->dev, "bbt version not supported\n");
+                goto out;
+        }
+
+        if (le32_to_cpu(bb_tbl->tblks) != nr_blocks) {
+                ret = -EINVAL;
+                dev_err(dev->dev, "bbt unsuspected blocks returned (%u!=%u)",
+                                        le32_to_cpu(bb_tbl->tblks), nr_blocks);
+                goto out;
+        }
+
+        ppa = dev_to_generic_addr(nvmdev, ppa);
+        ret = update_bbtbl(ppa, nr_blocks, bb_tbl->blk, priv);
         if (ret) {
                 ret = -EINTR;
                 goto out;
         }
 
 out:
-        kfree(bb_bitmap);
+        kfree(bb_tbl);
+        return ret;
+}
+
+static int nvme_nvm_set_bb_tbl(struct nvm_dev *nvmdev, struct nvm_rq *rqd,
+                                                                int type)
+{
+        struct nvme_ns *ns = nvmdev->q->queuedata;
+        struct nvme_dev *dev = ns->dev;
+        struct nvme_nvm_command c = {};
+        int ret = 0;
+
+        c.set_bb.opcode = nvme_nvm_admin_set_bb_tbl;
+        c.set_bb.nsid = cpu_to_le32(ns->ns_id);
+        c.set_bb.spba = cpu_to_le64(rqd->ppa_addr.ppa);
+        c.set_bb.nlb = cpu_to_le16(rqd->nr_pages - 1);
+        c.set_bb.value = type;
+
+        ret = nvme_submit_sync_cmd(dev->admin_q, (struct nvme_command *)&c,
+                                                                NULL, 0);
+        if (ret)
+                dev_err(dev->dev, "set bad block table failed (%d)\n", ret);
         return ret;
 }
 
@@ -381,7 +455,7 @@ static void nvme_nvm_end_io(struct request *rq, int error)
         struct nvm_rq *rqd = rq->end_io_data;
         struct nvm_dev *dev = rqd->dev;
 
-        if (dev->mt->end_io(rqd, error))
+        if (dev->mt && dev->mt->end_io(rqd, error))
                 pr_err("nvme: err status: %x result: %lx\n",
                                 rq->errors, (unsigned long)rq->special);
 
@@ -389,8 +463,9 @@ static void nvme_nvm_end_io(struct request *rq, int error)
         blk_mq_free_request(rq);
 }
 
-static int nvme_nvm_submit_io(struct request_queue *q, struct nvm_rq *rqd)
+static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 {
+        struct request_queue *q = dev->q;
         struct nvme_ns *ns = q->queuedata;
         struct request *rq;
         struct bio *bio = rqd->bio;
@@ -428,8 +503,9 @@ static int nvme_nvm_submit_io(struct request_queue *q, struct nvm_rq *rqd)
         return 0;
 }
 
-static int nvme_nvm_erase_block(struct request_queue *q, struct nvm_rq *rqd)
+static int nvme_nvm_erase_block(struct nvm_dev *dev, struct nvm_rq *rqd)
 {
+        struct request_queue *q = dev->q;
         struct nvme_ns *ns = q->queuedata;
         struct nvme_nvm_command c = {};
 
@@ -441,9 +517,9 @@ static int nvme_nvm_erase_block(struct request_queue *q, struct nvm_rq *rqd)
         return nvme_submit_sync_cmd(q, (struct nvme_command *)&c, NULL, 0);
 }
 
-static void *nvme_nvm_create_dma_pool(struct request_queue *q, char *name)
+static void *nvme_nvm_create_dma_pool(struct nvm_dev *nvmdev, char *name)
 {
-        struct nvme_ns *ns = q->queuedata;
+        struct nvme_ns *ns = nvmdev->q->queuedata;
         struct nvme_dev *dev = ns->dev;
 
         return dma_pool_create(name, dev->dev, PAGE_SIZE, PAGE_SIZE, 0);
@@ -456,7 +532,7 @@ static void nvme_nvm_destroy_dma_pool(void *pool)
         dma_pool_destroy(dma_pool);
 }
 
-static void *nvme_nvm_dev_dma_alloc(struct request_queue *q, void *pool,
+static void *nvme_nvm_dev_dma_alloc(struct nvm_dev *dev, void *pool,
                                     gfp_t mem_flags, dma_addr_t *dma_handler)
 {
         return dma_pool_alloc(pool, mem_flags, dma_handler);
@@ -474,6 +550,7 @@ static struct nvm_dev_ops nvme_nvm_dev_ops = {
         .get_l2p_tbl            = nvme_nvm_get_l2p_tbl,
 
         .get_bb_tbl             = nvme_nvm_get_bb_tbl,
+        .set_bb_tbl             = nvme_nvm_set_bb_tbl,
 
         .submit_io              = nvme_nvm_submit_io,
         .erase_block            = nvme_nvm_erase_block,
@@ -496,31 +573,27 @@ void nvme_nvm_unregister(struct request_queue *q, char *disk_name)
         nvm_unregister(disk_name);
 }
 
+/* move to shared place when used in multiple places. */
+#define PCI_VENDOR_ID_CNEX 0x1d1d
+#define PCI_DEVICE_ID_CNEX_WL 0x2807
+#define PCI_DEVICE_ID_CNEX_QEMU 0x1f1f
+
 int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id)
 {
         struct nvme_dev *dev = ns->dev;
         struct pci_dev *pdev = to_pci_dev(dev->dev);
 
         /* QEMU NVMe simulator - PCI ID + Vendor specific bit */
-        if (pdev->vendor == PCI_VENDOR_ID_INTEL && pdev->device == 0x5845 &&
+        if (pdev->vendor == PCI_VENDOR_ID_CNEX &&
+                                pdev->device == PCI_DEVICE_ID_CNEX_QEMU &&
                                                         id->vs[0] == 0x1)
                 return 1;
 
         /* CNEX Labs - PCI ID + Vendor specific bit */
-        if (pdev->vendor == 0x1d1d && pdev->device == 0x2807 &&
+        if (pdev->vendor == PCI_VENDOR_ID_CNEX &&
+                                pdev->device == PCI_DEVICE_ID_CNEX_WL &&
                                                         id->vs[0] == 0x1)
                 return 1;
 
         return 0;
 }
-#else
-int nvme_nvm_register(struct request_queue *q, char *disk_name)
-{
-        return 0;
-}
-void nvme_nvm_unregister(struct request_queue *q, char *disk_name) {};
-int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id)
-{
-        return 0;
-}
-#endif /* CONFIG_NVM */
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index fdb4e5bad9ac..044253dca30a 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -136,8 +136,22 @@ int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr);
 int nvme_sg_io32(struct nvme_ns *ns, unsigned long arg);
 int nvme_sg_get_version_num(int __user *ip);
 
+#ifdef CONFIG_NVM
 int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id);
 int nvme_nvm_register(struct request_queue *q, char *disk_name);
 void nvme_nvm_unregister(struct request_queue *q, char *disk_name);
+#else
+static inline int nvme_nvm_register(struct request_queue *q, char *disk_name)
+{
+        return 0;
+}
+
+static inline void nvme_nvm_unregister(struct request_queue *q, char *disk_name) {};
+
+static inline int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id)
+{
+        return 0;
+}
+#endif /* CONFIG_NVM */
 
 #endif /* _NVME_H */
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 8187df204695..9e294ff4e652 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -896,19 +896,28 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
                         goto retry_cmd;
                 }
                 if (blk_integrity_rq(req)) {
-                        if (blk_rq_count_integrity_sg(req->q, req->bio) != 1)
+                        if (blk_rq_count_integrity_sg(req->q, req->bio) != 1) {
+                                dma_unmap_sg(dev->dev, iod->sg, iod->nents,
+                                                dma_dir);
                                 goto error_cmd;
+                        }
 
                         sg_init_table(iod->meta_sg, 1);
                         if (blk_rq_map_integrity_sg(
-                                        req->q, req->bio, iod->meta_sg) != 1)
+                                        req->q, req->bio, iod->meta_sg) != 1) {
+                                dma_unmap_sg(dev->dev, iod->sg, iod->nents,
+                                                dma_dir);
                                 goto error_cmd;
+                        }
 
                         if (rq_data_dir(req))
                                 nvme_dif_remap(req, nvme_dif_prep);
 
-                        if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg, 1, dma_dir))
+                        if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg, 1, dma_dir)) {
+                                dma_unmap_sg(dev->dev, iod->sg, iod->nents,
+                                                dma_dir);
                                 goto error_cmd;
+                        }
                 }
         }
 
@@ -968,7 +977,8 @@ static void __nvme_process_cq(struct nvme_queue *nvmeq, unsigned int *tag)
         if (head == nvmeq->cq_head && phase == nvmeq->cq_phase)
                 return;
 
-        writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
+        if (likely(nvmeq->cq_vector >= 0))
+                writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
         nvmeq->cq_head = head;
         nvmeq->cq_phase = phase;
 
@@ -1727,9 +1737,13 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
         u32 aqa;
         u64 cap = lo_hi_readq(&dev->bar->cap);
         struct nvme_queue *nvmeq;
-        unsigned page_shift = PAGE_SHIFT;
+        /*
+         * default to a 4K page size, with the intention to update this
+         * path in the future to accomodate architectures with differing
+         * kernel and IO page sizes.
+         */
+        unsigned page_shift = 12;
         unsigned dev_page_min = NVME_CAP_MPSMIN(cap) + 12;
-        unsigned dev_page_max = NVME_CAP_MPSMAX(cap) + 12;
 
         if (page_shift < dev_page_min) {
                 dev_err(dev->dev,
@@ -1738,13 +1752,6 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
                                 1 << page_shift);
                 return -ENODEV;
         }
-        if (page_shift > dev_page_max) {
-                dev_info(dev->dev,
-                                "Device maximum page size (%u) smaller than "
-                                "host (%u); enabling work-around\n",
-                                1 << dev_page_max, 1 << page_shift);
-                page_shift = dev_page_max;
-        }
 
         dev->subsystem = readl(&dev->bar->vs) >= NVME_VS(1, 1) ?
                                                 NVME_CAP_NSSRC(cap) : 0;
@@ -2268,7 +2275,7 @@ static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
         if (dev->max_hw_sectors) {
                 blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors);
                 blk_queue_max_segments(ns->queue,
-                        ((dev->max_hw_sectors << 9) / dev->page_size) + 1);
+                        (dev->max_hw_sectors / (dev->page_size >> 9)) + 1);
         }
         if (dev->stripe_size)
                 blk_queue_chunk_sectors(ns->queue, dev->stripe_size >> 9);
@@ -2701,6 +2708,18 @@ static int nvme_dev_map(struct nvme_dev *dev)
         dev->q_depth = min_t(int, NVME_CAP_MQES(cap) + 1, NVME_Q_DEPTH);
         dev->db_stride = 1 << NVME_CAP_STRIDE(cap);
         dev->dbs = ((void __iomem *)dev->bar) + 4096;
+
+        /*
+         * Temporary fix for the Apple controller found in the MacBook8,1 and
+         * some MacBook7,1 to avoid controller resets and data loss.
+         */
+        if (pdev->vendor == PCI_VENDOR_ID_APPLE && pdev->device == 0x2001) {
+                dev->q_depth = 2;
+                dev_warn(dev->dev, "detected Apple NVMe controller, set "
+                        "queue depth=%u to work around controller resets\n",
+                        dev->q_depth);
+        }
+
         if (readl(&dev->bar->vs) >= NVME_VS(1, 2))
                 dev->cmb = nvme_map_cmb(dev);
 
@@ -2787,6 +2806,10 @@ static void nvme_del_queue_end(struct nvme_queue *nvmeq)
 {
         struct nvme_delq_ctx *dq = nvmeq->cmdinfo.ctx;
         nvme_put_dq(dq);
+
+        spin_lock_irq(&nvmeq->q_lock);
+        nvme_process_cq(nvmeq);
+        spin_unlock_irq(&nvmeq->q_lock);
 }
 
 static int adapter_async_del_queue(struct nvme_queue *nvmeq, u8 opcode,
diff --git a/drivers/of/address.c b/drivers/of/address.c
index cd53fe4a0c86..9582c5703b3c 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -485,9 +485,10 @@ static int of_translate_one(struct device_node *parent, struct of_bus *bus,
         int rone;
         u64 offset = OF_BAD_ADDR;
 
-        /* Normally, an absence of a "ranges" property means we are
+        /*
+         * Normally, an absence of a "ranges" property means we are
          * crossing a non-translatable boundary, and thus the addresses
-         * below the current not cannot be converted to CPU physical ones.
+         * below the current cannot be converted to CPU physical ones.
          * Unfortunately, while this is very clear in the spec, it's not
          * what Apple understood, and they do have things like /uni-n or
          * /ht nodes with no "ranges" property and a lot of perfectly
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index d2430298a309..655f79db7899 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/initrd.h>
 #include <linux/memblock.h>
+#include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/of_reserved_mem.h>
@@ -436,6 +437,8 @@ static void *kernel_tree_alloc(u64 size, u64 align)
         return kzalloc(size, GFP_KERNEL);
 }
 
+static DEFINE_MUTEX(of_fdt_unflatten_mutex);
+
 /**
  * of_fdt_unflatten_tree - create tree of device_nodes from flat blob
  *
@@ -447,7 +450,9 @@ static void *kernel_tree_alloc(u64 size, u64 align)
 void of_fdt_unflatten_tree(const unsigned long *blob,
                         struct device_node **mynodes)
 {
+        mutex_lock(&of_fdt_unflatten_mutex);
         __unflatten_device_tree(blob, mynodes, &kernel_tree_alloc);
+        mutex_unlock(&of_fdt_unflatten_mutex);
 }
 EXPORT_SYMBOL_GPL(of_fdt_unflatten_tree);
 
@@ -1041,7 +1046,7 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size)
 int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base,
                                         phys_addr_t size, bool nomap)
 {
-        pr_err("Reserved memory not supported, ignoring range 0x%pa - 0x%pa%s\n",
+        pr_err("Reserved memory not supported, ignoring range %pa - %pa%s\n",
                   &base, &size, nomap ? " (nomap)" : "");
         return -ENOSYS;
 }
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 902b89be7217..4fa916dffc91 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -53,7 +53,7 @@ EXPORT_SYMBOL_GPL(irq_of_parse_and_map);
  * Returns a pointer to the interrupt parent node, or NULL if the interrupt
  * parent could not be determined.
  */
-static struct device_node *of_irq_find_parent(struct device_node *child)
+struct device_node *of_irq_find_parent(struct device_node *child)
 {
         struct device_node *p;
         const __be32 *parp;
@@ -77,6 +77,7 @@ static struct device_node *of_irq_find_parent(struct device_node *child)
 
         return p;
 }
+EXPORT_SYMBOL_GPL(of_irq_find_parent);
 
 /**
  * of_irq_parse_raw - Low level interrupt tree parsing
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index be77e75c587d..1a3556a9e9ea 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -206,7 +206,13 @@ static int __init __rmem_cmp(const void *a, const void *b)
 {
         const struct reserved_mem *ra = a, *rb = b;
 
-        return ra->base - rb->base;
+        if (ra->base < rb->base)
+                return -1;
+
+        if (ra->base > rb->base)
+                return 1;
+
+        return 0;
 }
 
 static void __init __rmem_check_for_overlap(void)
diff --git a/drivers/parisc/iommu-helpers.h b/drivers/parisc/iommu-helpers.h
index 761e77bfce5d..e56f1569f6c3 100644
--- a/drivers/parisc/iommu-helpers.h
+++ b/drivers/parisc/iommu-helpers.h
@@ -104,7 +104,11 @@ iommu_coalesce_chunks(struct ioc *ioc, struct device *dev,
         struct scatterlist *contig_sg;     /* contig chunk head */
         unsigned long dma_offset, dma_len; /* start/len of DMA stream */
         unsigned int n_mappings = 0;
-        unsigned int max_seg_size = dma_get_max_seg_size(dev);
+        unsigned int max_seg_size = min(dma_get_max_seg_size(dev),
+                                        (unsigned)DMA_CHUNK_SIZE);
+        unsigned int max_seg_boundary = dma_get_seg_boundary(dev) + 1;
+        if (max_seg_boundary)   /* check if the addition above didn't overflow */
+                max_seg_size = min(max_seg_size, max_seg_boundary);
 
         while (nents > 0) {
 
@@ -138,14 +142,11 @@ iommu_coalesce_chunks(struct ioc *ioc, struct device *dev,
 
                         /*
                         ** First make sure current dma stream won't
-                        ** exceed DMA_CHUNK_SIZE if we coalesce the
+                        ** exceed max_seg_size if we coalesce the
                         ** next entry.
                         */   
-                        if(unlikely(ALIGN(dma_len + dma_offset + startsg->length,
-                                            IOVP_SIZE) > DMA_CHUNK_SIZE))
-                                break;
-
-                        if (startsg->length + dma_len > max_seg_size)
+                        if (unlikely(ALIGN(dma_len + dma_offset + startsg->length, IOVP_SIZE) >
+                                     max_seg_size))
                                 break;
 
                         /*
diff --git a/drivers/pci/host/pcie-altera.c b/drivers/pci/host/pcie-altera.c
index e5dda38bdde5..99da549d5d06 100644
--- a/drivers/pci/host/pcie-altera.c
+++ b/drivers/pci/host/pcie-altera.c
@@ -55,8 +55,10 @@
 #define TLP_CFG_DW2(bus, devfn, offset) \
                                 (((bus) << 24) | ((devfn) << 16) | (offset))
 #define TLP_REQ_ID(bus, devfn)          (((bus) << 8) | (devfn))
+#define TLP_COMP_STATUS(s)              (((s) >> 12) & 7)
 #define TLP_HDR_SIZE                    3
 #define TLP_LOOP                        500
+#define RP_DEVFN                        0
 
 #define INTX_NUM                        4
 
@@ -166,34 +168,41 @@ static bool altera_pcie_valid_config(struct altera_pcie *pcie,
 
 static int tlp_read_packet(struct altera_pcie *pcie, u32 *value)
 {
-        u8 loop;
+        int i;
         bool sop = 0;
         u32 ctrl;
         u32 reg0, reg1;
+        u32 comp_status = 1;
 
         /*
          * Minimum 2 loops to read TLP headers and 1 loop to read data
          * payload.
          */
-        for (loop = 0; loop < TLP_LOOP; loop++) {
+        for (i = 0; i < TLP_LOOP; i++) {
                 ctrl = cra_readl(pcie, RP_RXCPL_STATUS);
                 if ((ctrl & RP_RXCPL_SOP) || (ctrl & RP_RXCPL_EOP) || sop) {
                         reg0 = cra_readl(pcie, RP_RXCPL_REG0);
                         reg1 = cra_readl(pcie, RP_RXCPL_REG1);
 
-                        if (ctrl & RP_RXCPL_SOP)
+                        if (ctrl & RP_RXCPL_SOP) {
                                 sop = true;
+                                comp_status = TLP_COMP_STATUS(reg1);
+                        }
 
                         if (ctrl & RP_RXCPL_EOP) {
+                                if (comp_status)
+                                        return PCIBIOS_DEVICE_NOT_FOUND;
+
                                 if (value)
                                         *value = reg0;
+
                                 return PCIBIOS_SUCCESSFUL;
                         }
                 }
                 udelay(5);
         }
 
-        return -ENOENT;
+        return PCIBIOS_DEVICE_NOT_FOUND;
 }
 
 static void tlp_write_packet(struct altera_pcie *pcie, u32 *headers,
@@ -233,7 +242,7 @@ static int tlp_cfg_dword_read(struct altera_pcie *pcie, u8 bus, u32 devfn,
         else
                 headers[0] = TLP_CFG_DW0(TLP_FMTTYPE_CFGRD1);
 
-        headers[1] = TLP_CFG_DW1(TLP_REQ_ID(pcie->root_bus_nr, devfn),
+        headers[1] = TLP_CFG_DW1(TLP_REQ_ID(pcie->root_bus_nr, RP_DEVFN),
                                         TLP_READ_TAG, byte_en);
         headers[2] = TLP_CFG_DW2(bus, devfn, where);
 
@@ -253,7 +262,7 @@ static int tlp_cfg_dword_write(struct altera_pcie *pcie, u8 bus, u32 devfn,
         else
                 headers[0] = TLP_CFG_DW0(TLP_FMTTYPE_CFGWR1);
 
-        headers[1] = TLP_CFG_DW1(TLP_REQ_ID(pcie->root_bus_nr, devfn),
+        headers[1] = TLP_CFG_DW1(TLP_REQ_ID(pcie->root_bus_nr, RP_DEVFN),
                                         TLP_WRITE_TAG, byte_en);
         headers[2] = TLP_CFG_DW2(bus, devfn, where);
 
@@ -458,7 +467,7 @@ static int altera_pcie_init_irq_domain(struct altera_pcie *pcie)
         struct device_node *node = dev->of_node;
 
         /* Setup INTx */
-        pcie->irq_domain = irq_domain_add_linear(node, INTX_NUM,
+        pcie->irq_domain = irq_domain_add_linear(node, INTX_NUM + 1,
                                         &intx_domain_ops, pcie);
         if (!pcie->irq_domain) {
                 dev_err(dev, "Failed to get a INTx IRQ domain\n");
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index 540f077c37ea..02a7452bdf23 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -440,7 +440,6 @@ int dw_pcie_host_init(struct pcie_port *pp)
                                          ret, pp->io);
                                 continue;
                         }
-                        pp->io_base = pp->io->start;
                         break;
                 case IORESOURCE_MEM:
                         pp->mem = win->res;
diff --git a/drivers/pci/host/pcie-hisi.c b/drivers/pci/host/pcie-hisi.c
index 35457ecd8e70..163671a4f798 100644
--- a/drivers/pci/host/pcie-hisi.c
+++ b/drivers/pci/host/pcie-hisi.c
@@ -111,7 +111,7 @@ static struct pcie_host_ops hisi_pcie_host_ops = {
         .link_up = hisi_pcie_link_up,
 };
 
-static int __init hisi_add_pcie_port(struct pcie_port *pp,
+static int hisi_add_pcie_port(struct pcie_port *pp,
                                      struct platform_device *pdev)
 {
         int ret;
@@ -139,7 +139,7 @@ static int __init hisi_add_pcie_port(struct pcie_port *pp,
         return 0;
 }
 
-static int __init hisi_pcie_probe(struct platform_device *pdev)
+static int hisi_pcie_probe(struct platform_device *pdev)
 {
         struct hisi_pcie *hisi_pcie;
         struct pcie_port *pp;
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 53e463244bb7..7eaa4c87fec7 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -54,7 +54,7 @@ static int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
         struct irq_domain *domain;
 
         domain = pci_msi_get_domain(dev);
-        if (domain)
+        if (domain && irq_domain_is_hierarchy(domain))
                 return pci_msi_domain_alloc_irqs(domain, dev, nvec, type);
 
         return arch_setup_msi_irqs(dev, nvec, type);
@@ -65,7 +65,7 @@ static void pci_msi_teardown_msi_irqs(struct pci_dev *dev)
         struct irq_domain *domain;
 
         domain = pci_msi_get_domain(dev);
-        if (domain)
+        if (domain && irq_domain_is_hierarchy(domain))
                 pci_msi_domain_free_irqs(domain, dev);
         else
                 arch_teardown_msi_irqs(dev);
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 4446fcb5effd..d7ffd66814bb 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -1146,9 +1146,21 @@ static int pci_pm_runtime_suspend(struct device *dev)
         pci_dev->state_saved = false;
         pci_dev->no_d3cold = false;
         error = pm->runtime_suspend(dev);
-        suspend_report_result(pm->runtime_suspend, error);
-        if (error)
+        if (error) {
+                /*
+                 * -EBUSY and -EAGAIN is used to request the runtime PM core
+                 * to schedule a new suspend, so log the event only with debug
+                 * log level.
+                 */
+                if (error == -EBUSY || error == -EAGAIN)
+                        dev_dbg(dev, "can't suspend now (%pf returned %d)\n",
+                                pm->runtime_suspend, error);
+                else
+                        dev_err(dev, "can't suspend (%pf returned %d)\n",
+                                pm->runtime_suspend, error);
+
                 return error;
+        }
         if (!pci_dev->d3cold_allowed)
                 pci_dev->no_d3cold = true;
 
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 92618686604c..eead54cd01b2 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -216,7 +216,10 @@ static ssize_t numa_node_store(struct device *dev,
         if (ret)
                 return ret;
 
-        if (node >= MAX_NUMNODES || !node_online(node))
+        if ((node < 0 && node != NUMA_NO_NODE) || node >= MAX_NUMNODES)
+                return -EINVAL;
+
+        if (node != NUMA_NO_NODE && !node_online(node))
                 return -EINVAL;
 
         add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index fd2f03fa53f3..d390fc1475ec 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -337,6 +337,4 @@ static inline int pci_dev_specific_reset(struct pci_dev *dev, int probe)
 }
 #endif
 
-struct pci_host_bridge *pci_find_host_bridge(struct pci_bus *bus);
-
 #endif /* DRIVERS_PCI_H */
diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index b422e4ed73f4..312c78b27a32 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -5,8 +5,6 @@
 config PINCTRL
         bool
 
-if PINCTRL
-
 menu "Pin controllers"
         depends on PINCTRL
 
@@ -274,5 +272,3 @@ config PINCTRL_TB10X
         select GPIOLIB
 
 endmenu
-
-endif
diff --git a/drivers/pinctrl/freescale/pinctrl-imx1-core.c b/drivers/pinctrl/freescale/pinctrl-imx1-core.c
index 88a7fac11bd4..acaf84cadca3 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx1-core.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx1-core.c
@@ -538,8 +538,10 @@ static int imx1_pinctrl_parse_functions(struct device_node *np,
                 func->groups[i] = child->name;
                 grp = &info->groups[grp_index++];
                 ret = imx1_pinctrl_parse_groups(child, grp, info, i++);
-                if (ret == -ENOMEM)
+                if (ret == -ENOMEM) {
+                        of_node_put(child);
                         return ret;
+                }
         }
 
         return 0;
@@ -582,8 +584,10 @@ static int imx1_pinctrl_parse_dt(struct platform_device *pdev,
 
         for_each_child_of_node(np, child) {
                 ret = imx1_pinctrl_parse_functions(child, info, ifunc++);
-                if (ret == -ENOMEM)
+                if (ret == -ENOMEM) {
+                        of_node_put(child);
                         return -ENOMEM;
+                }
         }
 
         return 0;
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index f307f1d27d64..5c717275a7fa 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -747,7 +747,7 @@ static int mtk_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
         reg_addr =  mtk_get_port(pctl, offset) + pctl->devdata->dir_offset;
         bit = BIT(offset & 0xf);
         regmap_read(pctl->regmap1, reg_addr, &read_val);
-        return !!(read_val & bit);
+        return !(read_val & bit);
 }
 
 static int mtk_gpio_get(struct gpio_chip *chip, unsigned offset)
@@ -757,12 +757,8 @@ static int mtk_gpio_get(struct gpio_chip *chip, unsigned offset)
         unsigned int read_val = 0;
         struct mtk_pinctrl *pctl = dev_get_drvdata(chip->dev);
 
-        if (mtk_gpio_get_direction(chip, offset))
-                reg_addr = mtk_get_port(pctl, offset) +
-                        pctl->devdata->dout_offset;
-        else
-                reg_addr = mtk_get_port(pctl, offset) +
-                        pctl->devdata->din_offset;
+        reg_addr = mtk_get_port(pctl, offset) +
+                pctl->devdata->din_offset;
 
         bit = BIT(offset & 0xf);
         regmap_read(pctl->regmap1, reg_addr, &read_val);
@@ -997,6 +993,7 @@ static struct gpio_chip mtk_gpio_chip = {
         .owner                  = THIS_MODULE,
         .request                = gpiochip_generic_request,
         .free                   = gpiochip_generic_free,
+        .get_direction          = mtk_gpio_get_direction,
         .direction_input        = mtk_gpio_direction_input,
         .direction_output       = mtk_gpio_direction_output,
         .get                    = mtk_gpio_get,
diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
index d809c9eaa323..19a3c3bc2f1f 100644
--- a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
@@ -672,7 +672,7 @@ static int pm8xxx_gpio_probe(struct platform_device *pdev)
                 return -ENOMEM;
 
         pctrl->dev = &pdev->dev;
-        pctrl->npins = (unsigned)of_device_get_match_data(&pdev->dev);
+        pctrl->npins = (unsigned long)of_device_get_match_data(&pdev->dev);
 
         pctrl->regmap = dev_get_regmap(pdev->dev.parent, NULL);
         if (!pctrl->regmap) {
diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
index 8982027de8e8..b868ef1766a0 100644
--- a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
+++ b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
@@ -763,7 +763,7 @@ static int pm8xxx_mpp_probe(struct platform_device *pdev)
                 return -ENOMEM;
 
         pctrl->dev = &pdev->dev;
-        pctrl->npins = (unsigned)of_device_get_match_data(&pdev->dev);
+        pctrl->npins = (unsigned long)of_device_get_match_data(&pdev->dev);
 
         pctrl->regmap = dev_get_regmap(pdev->dev.parent, NULL);
         if (!pctrl->regmap) {
diff --git a/drivers/pinctrl/sh-pfc/pfc-sh7734.c b/drivers/pinctrl/sh-pfc/pfc-sh7734.c
index e7deb51de7dc..9842bb106796 100644
--- a/drivers/pinctrl/sh-pfc/pfc-sh7734.c
+++ b/drivers/pinctrl/sh-pfc/pfc-sh7734.c
@@ -31,11 +31,11 @@
         PORT_GP_12(5, fn, sfx)
 
 #undef _GP_DATA
-#define _GP_DATA(bank, pin, name, sfx)                                  \
+#define _GP_DATA(bank, pin, name, sfx, cfg)                             \
         PINMUX_DATA(name##_DATA, name##_FN, name##_IN, name##_OUT)
 
-#define _GP_INOUTSEL(bank, pin, name, sfx)      name##_IN, name##_OUT
-#define _GP_INDT(bank, pin, name, sfx)          name##_DATA
+#define _GP_INOUTSEL(bank, pin, name, sfx, cfg) name##_IN, name##_OUT
+#define _GP_INDT(bank, pin, name, sfx, cfg)     name##_DATA
 #define GP_INOUTSEL(bank)       PORT_GP_32_REV(bank, _GP_INOUTSEL, unused)
 #define GP_INDT(bank)           PORT_GP_32_REV(bank, _GP_INDT, unused)
 
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 8b3130f22b42..9e03d158f411 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -1478,6 +1478,8 @@ module_init(remoteproc_init);
 
 static void __exit remoteproc_exit(void)
 {
+        ida_destroy(&rproc_dev_index);
+
         rproc_exit_debugfs();
 }
 module_exit(remoteproc_exit);
diff --git a/drivers/remoteproc/remoteproc_debugfs.c b/drivers/remoteproc/remoteproc_debugfs.c
index 9d30809bb407..916af5096f57 100644
--- a/drivers/remoteproc/remoteproc_debugfs.c
+++ b/drivers/remoteproc/remoteproc_debugfs.c
@@ -156,7 +156,7 @@ rproc_recovery_write(struct file *filp, const char __user *user_buf,
         char buf[10];
         int ret;
 
-        if (count > sizeof(buf))
+        if (count < 1 || count > sizeof(buf))
                 return count;
 
         ret = copy_from_user(buf, user_buf, count);
diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index 188006c55ce0..aa705bb4748c 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -15,9 +15,6 @@
 #include <linux/i2c.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
-#include <linux/of_irq.h>
-#include <linux/pm_wakeirq.h>
 #include <linux/rtc/ds1307.h>
 #include <linux/rtc.h>
 #include <linux/slab.h>
@@ -117,7 +114,6 @@ struct ds1307 {
 #define HAS_ALARM       1               /* bit 1 == irq claimed */
         struct i2c_client       *client;
         struct rtc_device       *rtc;
-        int                     wakeirq;
         s32 (*read_block_data)(const struct i2c_client *client, u8 command,
                                u8 length, u8 *values);
         s32 (*write_block_data)(const struct i2c_client *client, u8 command,
@@ -1138,7 +1134,10 @@ read_rtc:
                                 bin2bcd(tmp));
         }
 
-        device_set_wakeup_capable(&client->dev, want_irq);
+        if (want_irq) {
+                device_set_wakeup_capable(&client->dev, true);
+                set_bit(HAS_ALARM, &ds1307->flags);
+        }
         ds1307->rtc = devm_rtc_device_register(&client->dev, client->name,
                                 rtc_ops, THIS_MODULE);
         if (IS_ERR(ds1307->rtc)) {
@@ -1146,43 +1145,19 @@ read_rtc:
         }
 
         if (want_irq) {
-                struct device_node *node = client->dev.of_node;
-
                 err = devm_request_threaded_irq(&client->dev,
                                                 client->irq, NULL, irq_handler,
                                                 IRQF_SHARED | IRQF_ONESHOT,
                                                 ds1307->rtc->name, client);
                 if (err) {
                         client->irq = 0;
+                        device_set_wakeup_capable(&client->dev, false);
+                        clear_bit(HAS_ALARM, &ds1307->flags);
                         dev_err(&client->dev, "unable to request IRQ!\n");
-                        goto no_irq;
-                }
-
-                set_bit(HAS_ALARM, &ds1307->flags);
-                dev_dbg(&client->dev, "got IRQ %d\n", client->irq);
-
-                /* Currently supported by OF code only! */
-                if (!node)
-                        goto no_irq;
-
-                err = of_irq_get(node, 1);
-                if (err <= 0) {
-                        if (err == -EPROBE_DEFER)
-                                goto exit;
-                        goto no_irq;
-                }
-                ds1307->wakeirq = err;
-
-                err = dev_pm_set_dedicated_wake_irq(&client->dev,
-                                                    ds1307->wakeirq);
-                if (err) {
-                        dev_err(&client->dev, "unable to setup wakeIRQ %d!\n",
-                                err);
-                        goto exit;
-                }
+                } else
+                        dev_dbg(&client->dev, "got IRQ %d\n", client->irq);
         }
 
-no_irq:
         if (chip->nvram_size) {
 
                 ds1307->nvram = devm_kzalloc(&client->dev,
@@ -1226,9 +1201,6 @@ static int ds1307_remove(struct i2c_client *client)
 {
         struct ds1307 *ds1307 = i2c_get_clientdata(client);
 
-        if (ds1307->wakeirq)
-                dev_pm_clear_wake_irq(&client->dev);
-
         if (test_and_clear_bit(HAS_NVRAM, &ds1307->flags))
                 sysfs_remove_bin_file(&client->dev.kobj, ds1307->nvram);
 
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 5f692ae40749..64eed87d34a8 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -364,6 +364,7 @@ config SCSI_HPSA
         tristate "HP Smart Array SCSI driver"
         depends on PCI && SCSI
         select CHECK_SIGNATURE
+        select SCSI_SAS_ATTRS
         help
           This driver supports HP Smart Array Controllers (circa 2009).
           It is a SCSI alternative to the cciss driver, which is a block
@@ -499,6 +500,7 @@ config SCSI_ADVANSYS
         tristate "AdvanSys SCSI support"
         depends on SCSI
         depends on ISA || EISA || PCI
+        depends on ISA_DMA_API || !ISA
         help
           This is a driver for all SCSI host adapters manufactured by
           AdvanSys. It is documented in the kernel source in
diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c
index 519f9a4b3dad..febbd83e2ecd 100644
--- a/drivers/scsi/advansys.c
+++ b/drivers/scsi/advansys.c
@@ -7803,7 +7803,7 @@ adv_build_req(struct asc_board *boardp, struct scsi_cmnd *scp,
                 return ASC_BUSY;
         }
         scsiqp->sense_addr = cpu_to_le32(sense_addr);
-        scsiqp->sense_len = cpu_to_le32(SCSI_SENSE_BUFFERSIZE);
+        scsiqp->sense_len = SCSI_SENSE_BUFFERSIZE;
 
         /* Build ADV_SCSI_REQ_Q */
 
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 323982fd00c3..82ac1cd818ac 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -333,6 +333,17 @@ static void scsi_host_dev_release(struct device *dev)
                 kfree(queuedata);
         }
 
+        if (shost->shost_state == SHOST_CREATED) {
+                /*
+                 * Free the shost_dev device name here if scsi_host_alloc()
+                 * and scsi_host_put() have been called but neither
+                 * scsi_host_add() nor scsi_host_remove() has been called.
+                 * This avoids that the memory allocated for the shost_dev
+                 * name is leaked.
+                 */
+                kfree(dev_name(&shost->shost_dev));
+        }
+
         scsi_destroy_command_freelist(shost);
         if (shost_use_blk_mq(shost)) {
                 if (shost->tag_set.tags)
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 6a8f95808ee0..a3860367b568 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -8671,7 +8671,7 @@ static void hpsa_disable_rld_caching(struct ctlr_info *h)
         if ((rc != 0)  || (c->err_info->CommandStatus != 0))
                 goto errout;
 
-        if (*options && HPSA_DIAG_OPTS_DISABLE_RLD_CACHING)
+        if (*options & HPSA_DIAG_OPTS_DISABLE_RLD_CACHING)
                 goto out;
 
 errout:
diff --git a/drivers/scsi/mpt3sas/Kconfig b/drivers/scsi/mpt3sas/Kconfig
index 29061467cc17..b736dbc80485 100644
--- a/drivers/scsi/mpt3sas/Kconfig
+++ b/drivers/scsi/mpt3sas/Kconfig
@@ -71,3 +71,12 @@ config SCSI_MPT3SAS_MAX_SGE
         MAX_PHYS_SEGMENTS in most kernels.  However in SuSE kernels this
         can be 256. However, it may decreased down to 16.  Decreasing this
         parameter will reduce memory requirements on a per controller instance.
+
+config SCSI_MPT2SAS
+        tristate "Legacy MPT2SAS config option"
+        default n
+        select SCSI_MPT3SAS
+        depends on PCI && SCSI
+        ---help---
+        Dummy config option for backwards compatiblity: configure the MPT3SAS
+        driver instead.
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index d95206b7e116..9ab77b06434d 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -3905,8 +3905,7 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
          * We do not expose raid functionality to upper layer for warpdrive.
          */
         if (!ioc->is_warpdrive && !scsih_is_raid(&scmd->device->sdev_gendev)
-            && (sas_device_priv_data->flags & MPT_DEVICE_TLR_ON) &&
-            scmd->cmd_len != 32)
+            && sas_is_tlr_enabled(scmd->device) && scmd->cmd_len != 32)
                 mpi_control |= MPI2_SCSIIO_CONTROL_TLR_ON;
 
         smid = mpt3sas_base_get_smid_scsiio(ioc, ioc->scsi_io_cb_idx, scmd);
diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c
index 90fdf0e859e3..675e7fab0796 100644
--- a/drivers/scsi/mvsas/mv_init.c
+++ b/drivers/scsi/mvsas/mv_init.c
@@ -758,7 +758,7 @@ mvs_store_interrupt_coalescing(struct device *cdev,
                         struct device_attribute *attr,
                         const char *buffer, size_t size)
 {
-        int val = 0;
+        unsigned int val = 0;
         struct mvs_info *mvi = NULL;
         struct Scsi_Host *shost = class_to_shost(cdev);
         struct sas_ha_struct *sha = SHOST_TO_SAS_HA(shost);
@@ -766,7 +766,7 @@ mvs_store_interrupt_coalescing(struct device *cdev,
         if (buffer == NULL)
                 return size;
 
-        if (sscanf(buffer, "%d", &val) != 1)
+        if (sscanf(buffer, "%u", &val) != 1)
                 return -EINVAL;
 
         if (val >= 0x10000) {
diff --git a/drivers/scsi/qla2xxx/qla_nx.c b/drivers/scsi/qla2xxx/qla_nx.c
index eb0cc5475c45..b6b4cfdd7620 100644
--- a/drivers/scsi/qla2xxx/qla_nx.c
+++ b/drivers/scsi/qla2xxx/qla_nx.c
@@ -433,7 +433,7 @@ qla82xx_pci_get_crb_addr_2M(struct qla_hw_data *ha, ulong off_in,
         if (off_in < QLA82XX_PCI_CRBSPACE)
                 return -1;
 
-        *off_out = (void __iomem *)(off_in - QLA82XX_PCI_CRBSPACE);
+        off_in -= QLA82XX_PCI_CRBSPACE;
 
         /* Try direct map */
         m = &crb_128M_2M_map[CRB_BLK(off_in)].sub_block[CRB_SUBBLK(off_in)];
@@ -443,6 +443,7 @@ qla82xx_pci_get_crb_addr_2M(struct qla_hw_data *ha, ulong off_in,
                 return 0;
         }
         /* Not in direct map, use crb window */
+        *off_out = (void __iomem *)off_in;
         return 1;
 }
 
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 3ba2e9564b9a..81af294f15a7 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -902,7 +902,7 @@ static ssize_t tcm_qla2xxx_tpg_fabric_prot_type_show(struct config_item *item,
         return sprintf(page, "%d\n", tpg->tpg_attrib.fabric_prot_type);
 }
 
-CONFIGFS_ATTR_WO(tcm_qla2xxx_tpg_, enable);
+CONFIGFS_ATTR(tcm_qla2xxx_tpg_, enable);
 CONFIGFS_ATTR_RO(tcm_qla2xxx_tpg_, dynamic_sessions);
 CONFIGFS_ATTR(tcm_qla2xxx_tpg_, fabric_prot_type);
 
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index dfcc45bb03b1..d09d60293c27 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -465,8 +465,9 @@ static const struct opcode_info_t opcode_info_arr[SDEB_I_LAST_ELEMENT + 1] = {
              0} },
         {0, 0, 0, F_INV_OP | FF_RESPOND, NULL, NULL, /* MAINT OUT */
             {0,  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
-        {0, 0, 0, F_INV_OP | FF_RESPOND, NULL, NULL, /* VERIFY */
-            {0,  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
+        {0, 0x2f, 0, F_D_OUT_MAYBE | FF_DIRECT_IO, NULL, NULL, /* VERIFY(10) */
+            {10,  0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xc7,
+             0, 0, 0, 0, 0, 0} },
         {1, 0x7f, 0x9, F_SA_HIGH | F_D_IN | FF_DIRECT_IO, resp_read_dt0,
             vl_iarr, {32,  0xc7, 0, 0, 0, 0, 0x1f, 0x18, 0x0, 0x9, 0xfe, 0,
                       0xff, 0xff, 0xff, 0xff} },/* VARIABLE LENGTH, READ(32) */
@@ -477,8 +478,8 @@ static const struct opcode_info_t opcode_info_arr[SDEB_I_LAST_ELEMENT + 1] = {
             {10,  0x13, 0xff, 0xff, 0, 0, 0, 0xff, 0xff, 0xc7, 0, 0, 0, 0, 0,
              0} },
 /* 20 */
-        {0, 0, 0, F_INV_OP | FF_RESPOND, NULL, NULL, /* ALLOW REMOVAL */
-            {0,  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
+        {0, 0x1e, 0, 0, NULL, NULL, /* ALLOW REMOVAL */
+            {6,  0, 0, 0, 0x3, 0xc7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
         {0, 0x1, 0, 0, resp_start_stop, NULL, /* REWIND ?? */
             {6,  0x1, 0, 0, 0, 0xc7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0} },
         {0, 0, 0, F_INV_OP | FF_RESPOND, NULL, NULL, /* ATA_PT */
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 83245391e956..054923e3393c 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -701,9 +701,12 @@ static int scsi_probe_lun(struct scsi_device *sdev, unsigned char *inq_result,
          * strings.
          */
         if (sdev->inquiry_len < 36) {
-                sdev_printk(KERN_INFO, sdev,
-                            "scsi scan: INQUIRY result too short (%d),"
-                            " using 36\n", sdev->inquiry_len);
+                if (!sdev->host->short_inquiry) {
+                        shost_printk(KERN_INFO, sdev->host,
+                                    "scsi scan: INQUIRY result too short (%d),"
+                                    " using 36\n", sdev->inquiry_len);
+                        sdev->host->short_inquiry = 1;
+                }
                 sdev->inquiry_len = 36;
         }
 
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 8d2312239ae0..21930c9ac9cd 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -1102,6 +1102,14 @@ void __scsi_remove_device(struct scsi_device *sdev)
 {
         struct device *dev = &sdev->sdev_gendev;
 
+        /*
+         * This cleanup path is not reentrant and while it is impossible
+         * to get a new reference with scsi_device_get() someone can still
+         * hold a previously acquired one.
+         */
+        if (sdev->sdev_state == SDEV_DEL)
+                return;
+
         if (sdev->is_visible) {
                 if (scsi_device_set_state(sdev, SDEV_CANCEL) != 0)
                         return;
@@ -1110,7 +1118,9 @@ void __scsi_remove_device(struct scsi_device *sdev)
                 device_unregister(&sdev->sdev_dev);
                 transport_remove_device(dev);
                 scsi_dh_remove_device(sdev);
-        }
+                device_del(dev);
+        } else
+                put_device(&sdev->sdev_dev);
 
         /*
          * Stop accepting new requests and wait until all queuecommand() and
@@ -1121,16 +1131,6 @@ void __scsi_remove_device(struct scsi_device *sdev)
         blk_cleanup_queue(sdev->request_queue);
         cancel_work_sync(&sdev->requeue_work);
 
-        /*
-         * Remove the device after blk_cleanup_queue() has been called such
-         * a possible bdi_register() call with the same name occurs after
-         * blk_cleanup_queue() has called bdi_destroy().
-         */
-        if (sdev->is_visible)
-                device_del(dev);
-        else
-                put_device(&sdev->sdev_dev);
-
         if (sdev->host->hostt->slave_destroy)
                 sdev->host->hostt->slave_destroy(sdev);
         transport_destroy_device(dev);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 54519804c46a..3d22fc3e3c1a 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -638,11 +638,24 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
         unsigned int max_blocks = 0;
 
         q->limits.discard_zeroes_data = 0;
-        q->limits.discard_alignment = sdkp->unmap_alignment *
-                logical_block_size;
-        q->limits.discard_granularity =
-                max(sdkp->physical_block_size,
-                    sdkp->unmap_granularity * logical_block_size);
+
+        /*
+         * When LBPRZ is reported, discard alignment and granularity
+         * must be fixed to the logical block size. Otherwise the block
+         * layer will drop misaligned portions of the request which can
+         * lead to data corruption. If LBPRZ is not set, we honor the
+         * device preference.
+         */
+        if (sdkp->lbprz) {
+                q->limits.discard_alignment = 0;
+                q->limits.discard_granularity = 1;
+        } else {
+                q->limits.discard_alignment = sdkp->unmap_alignment *
+                        logical_block_size;
+                q->limits.discard_granularity =
+                        max(sdkp->physical_block_size,
+                            sdkp->unmap_granularity * logical_block_size);
+        }
 
         sdkp->provisioning_mode = mode;
 
@@ -2321,11 +2334,8 @@ got_data:
                 }
         }
 
-        if (sdkp->capacity > 0xffffffff) {
+        if (sdkp->capacity > 0xffffffff)
                 sdp->use_16_for_rw = 1;
-                sdkp->max_xfer_blocks = SD_MAX_XFER_BLOCKS;
-        } else
-                sdkp->max_xfer_blocks = SD_DEF_XFER_BLOCKS;
 
         /* Rescale capacity to 512-byte units */
         if (sector_size == 4096)
@@ -2642,7 +2652,6 @@ static void sd_read_block_limits(struct scsi_disk *sdkp)
 {
         unsigned int sector_sz = sdkp->device->sector_size;
         const int vpd_len = 64;
-        u32 max_xfer_length;
         unsigned char *buffer = kmalloc(vpd_len, GFP_KERNEL);
 
         if (!buffer ||
@@ -2650,14 +2659,11 @@ static void sd_read_block_limits(struct scsi_disk *sdkp)
             scsi_get_vpd_page(sdkp->device, 0xb0, buffer, vpd_len))
                 goto out;
 
-        max_xfer_length = get_unaligned_be32(&buffer[8]);
-        if (max_xfer_length)
-                sdkp->max_xfer_blocks = max_xfer_length;
-
         blk_queue_io_min(sdkp->disk->queue,
                          get_unaligned_be16(&buffer[6]) * sector_sz);
-        blk_queue_io_opt(sdkp->disk->queue,
-                         get_unaligned_be32(&buffer[12]) * sector_sz);
+
+        sdkp->max_xfer_blocks = get_unaligned_be32(&buffer[8]);
+        sdkp->opt_xfer_blocks = get_unaligned_be32(&buffer[12]);
 
         if (buffer[3] == 0x3c) {
                 unsigned int lba_count, desc_count;
@@ -2806,6 +2812,11 @@ static int sd_try_extended_inquiry(struct scsi_device *sdp)
         return 0;
 }
 
+static inline u32 logical_to_sectors(struct scsi_device *sdev, u32 blocks)
+{
+        return blocks << (ilog2(sdev->sector_size) - 9);
+}
+
 /**
  *      sd_revalidate_disk - called the first time a new disk is seen,
  *      performs disk spin up, read_capacity, etc.
@@ -2815,8 +2826,9 @@ static int sd_revalidate_disk(struct gendisk *disk)
 {
         struct scsi_disk *sdkp = scsi_disk(disk);
         struct scsi_device *sdp = sdkp->device;
+        struct request_queue *q = sdkp->disk->queue;
         unsigned char *buffer;
-        unsigned int max_xfer;
+        unsigned int dev_max, rw_max;
 
         SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp,
                                       "sd_revalidate_disk\n"));
@@ -2864,11 +2876,26 @@ static int sd_revalidate_disk(struct gendisk *disk)
          */
         sd_set_flush_flag(sdkp);
 
-        max_xfer = sdkp->max_xfer_blocks;
-        max_xfer <<= ilog2(sdp->sector_size) - 9;
+        /* Initial block count limit based on CDB TRANSFER LENGTH field size. */
+        dev_max = sdp->use_16_for_rw ? SD_MAX_XFER_BLOCKS : SD_DEF_XFER_BLOCKS;
+
+        /* Some devices report a maximum block count for READ/WRITE requests. */
+        dev_max = min_not_zero(dev_max, sdkp->max_xfer_blocks);
+        q->limits.max_dev_sectors = logical_to_sectors(sdp, dev_max);
+
+        /*
+         * Use the device's preferred I/O size for reads and writes
+         * unless the reported value is unreasonably large (or garbage).
+         */
+        if (sdkp->opt_xfer_blocks && sdkp->opt_xfer_blocks <= dev_max &&
+            sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS)
+                rw_max = q->limits.io_opt =
+                        logical_to_sectors(sdp, sdkp->opt_xfer_blocks);
+        else
+                rw_max = BLK_DEF_MAX_SECTORS;
 
-        sdkp->disk->queue->limits.max_sectors =
-                min_not_zero(queue_max_hw_sectors(sdkp->disk->queue), max_xfer);
+        /* Combine with controller limits */
+        q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q));
 
         set_capacity(disk, sdkp->capacity);
         sd_config_write_same(sdkp);
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 63ba5ca7f9a1..5f2a84aff29f 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -67,6 +67,7 @@ struct scsi_disk {
         atomic_t        openers;
         sector_t        capacity;       /* size in 512-byte sectors */
         u32             max_xfer_blocks;
+        u32             opt_xfer_blocks;
         u32             max_ws_blocks;
         u32             max_unmap_blocks;
         u32             unmap_granularity;
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index e0a1e52a04e7..2e522951b619 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -4083,6 +4083,7 @@ static int create_one_cdev(struct scsi_tape *tape, int mode, int rew)
         }
         cdev->owner = THIS_MODULE;
         cdev->ops = &st_fops;
+        STm->cdevs[rew] = cdev;
 
         error = cdev_add(cdev, cdev_devno, 1);
         if (error) {
@@ -4091,7 +4092,6 @@ static int create_one_cdev(struct scsi_tape *tape, int mode, int rew)
                 pr_err("st%d: Device not attached.\n", dev_num);
                 goto out_free;
         }
-        STm->cdevs[rew] = cdev;
 
         i = mode << (4 - ST_NBR_MODE_BITS);
         snprintf(name, 10, "%s%s%s", rew ? "n" : "",
@@ -4110,8 +4110,9 @@ static int create_one_cdev(struct scsi_tape *tape, int mode, int rew)
         return 0;
 out_free:
         cdev_del(STm->cdevs[rew]);
-        STm->cdevs[rew] = NULL;
 out:
+        STm->cdevs[rew] = NULL;
+        STm->devs[rew] = NULL;
         return error;
 }
 
diff --git a/drivers/soc/mediatek/Kconfig b/drivers/soc/mediatek/Kconfig
index 9d5068248aa0..0a4ea809a61b 100644
--- a/drivers/soc/mediatek/Kconfig
+++ b/drivers/soc/mediatek/Kconfig
@@ -23,6 +23,7 @@ config MTK_PMIC_WRAP
 config MTK_SCPSYS
         bool "MediaTek SCPSYS Support"
         depends on ARCH_MEDIATEK || COMPILE_TEST
+        default ARM64 && ARCH_MEDIATEK
         select REGMAP
         select MTK_INFRACFG
         select PM_GENERIC_DOMAINS if PM
diff --git a/drivers/soc/ti/knav_qmss_queue.c b/drivers/soc/ti/knav_qmss_queue.c
index f3a0b6a4b54e..8c03a80b482d 100644
--- a/drivers/soc/ti/knav_qmss_queue.c
+++ b/drivers/soc/ti/knav_qmss_queue.c
@@ -1179,7 +1179,7 @@ static int knav_queue_setup_link_ram(struct knav_device *kdev)
 
                 block++;
                 if (!block->size)
-                        return 0;
+                        continue;
 
                 dev_dbg(kdev->dev, "linkram1: phys:%x, virt:%p, size:%x\n",
                         block->phys, block->virt, block->size);
@@ -1519,9 +1519,9 @@ static int knav_queue_load_pdsp(struct knav_device *kdev,
 
         for (i = 0; i < ARRAY_SIZE(knav_acc_firmwares); i++) {
                 if (knav_acc_firmwares[i]) {
-                        ret = request_firmware(&fw,
-                                               knav_acc_firmwares[i],
-                                               kdev->dev);
+                        ret = request_firmware_direct(&fw,
+                                                      knav_acc_firmwares[i],
+                                                      kdev->dev);
                         if (!ret) {
                                 found = true;
                                 break;
diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c
index 06858e04ec59..bf9a610e5b89 100644
--- a/drivers/spi/spi-bcm63xx.c
+++ b/drivers/spi/spi-bcm63xx.c
@@ -562,8 +562,8 @@ static int bcm63xx_spi_probe(struct platform_device *pdev)
                 goto out_clk_disable;
         }
 
-        dev_info(dev, "at 0x%08x (irq %d, FIFOs size %d)\n",
-                 r->start, irq, bs->fifo_size);
+        dev_info(dev, "at %pr (irq %d, FIFOs size %d)\n",
+                 r, irq, bs->fifo_size);
 
         return 0;
 
diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c
index 563954a61424..7840067062a8 100644
--- a/drivers/spi/spi-mt65xx.c
+++ b/drivers/spi/spi-mt65xx.c
@@ -410,7 +410,7 @@ static int mtk_spi_setup(struct spi_device *spi)
         if (!spi->controller_data)
                 spi->controller_data = (void *)&mtk_default_chip_info;
 
-        if (mdata->dev_comp->need_pad_sel)
+        if (mdata->dev_comp->need_pad_sel && gpio_is_valid(spi->cs_gpio))
                 gpio_direction_output(spi->cs_gpio, !(spi->mode & SPI_CS_HIGH));
 
         return 0;
@@ -632,13 +632,23 @@ static int mtk_spi_probe(struct platform_device *pdev)
                         goto err_put_master;
                 }
 
-                for (i = 0; i < master->num_chipselect; i++) {
-                        ret = devm_gpio_request(&pdev->dev, master->cs_gpios[i],
-                                                dev_name(&pdev->dev));
-                        if (ret) {
-                                dev_err(&pdev->dev,
-                                        "can't get CS GPIO %i\n", i);
-                                goto err_put_master;
+                if (!master->cs_gpios && master->num_chipselect > 1) {
+                        dev_err(&pdev->dev,
+                                "cs_gpios not specified and num_chipselect > 1\n");
+                        ret = -EINVAL;
+                        goto err_put_master;
+                }
+
+                if (master->cs_gpios) {
+                        for (i = 0; i < master->num_chipselect; i++) {
+                                ret = devm_gpio_request(&pdev->dev,
+                                                        master->cs_gpios[i],
+                                                        dev_name(&pdev->dev));
+                                if (ret) {
+                                        dev_err(&pdev->dev,
+                                                "can't get CS GPIO %i\n", i);
+                                        goto err_put_master;
+                                }
                         }
                 }
         }
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index 94af80676684..5e5fd77e2711 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -1171,19 +1171,31 @@ err_no_rxchan:
 static int pl022_dma_autoprobe(struct pl022 *pl022)
 {
         struct device *dev = &pl022->adev->dev;
+        struct dma_chan *chan;
+        int err;
 
         /* automatically configure DMA channels from platform, normally using DT */
-        pl022->dma_rx_channel = dma_request_slave_channel(dev, "rx");
-        if (!pl022->dma_rx_channel)
+        chan = dma_request_slave_channel_reason(dev, "rx");
+        if (IS_ERR(chan)) {
+                err = PTR_ERR(chan);
                 goto err_no_rxchan;
+        }
+
+        pl022->dma_rx_channel = chan;
 
-        pl022->dma_tx_channel = dma_request_slave_channel(dev, "tx");
-        if (!pl022->dma_tx_channel)
+        chan = dma_request_slave_channel_reason(dev, "tx");
+        if (IS_ERR(chan)) {
+                err = PTR_ERR(chan);
                 goto err_no_txchan;
+        }
+
+        pl022->dma_tx_channel = chan;
 
         pl022->dummypage = kmalloc(PAGE_SIZE, GFP_KERNEL);
-        if (!pl022->dummypage)
+        if (!pl022->dummypage) {
+                err = -ENOMEM;
                 goto err_no_dummypage;
+        }
 
         return 0;
 
@@ -1194,7 +1206,7 @@ err_no_txchan:
         dma_release_channel(pl022->dma_rx_channel);
         pl022->dma_rx_channel = NULL;
 err_no_rxchan:
-        return -ENODEV;
+        return err;
 }
                 
 static void terminate_dma(struct pl022 *pl022)
@@ -2236,6 +2248,10 @@ static int pl022_probe(struct amba_device *adev, const struct amba_id *id)
 
         /* Get DMA channels, try autoconfiguration first */
         status = pl022_dma_autoprobe(pl022);
+        if (status == -EPROBE_DEFER) {
+                dev_dbg(dev, "deferring probe to get DMA channel\n");
+                goto err_no_irq;
+        }
 
         /* If that failed, use channels from platform_info */
         if (status == 0)
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index e2415be209d5..2b0a8ec3affb 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -376,6 +376,7 @@ static void spi_drv_shutdown(struct device *dev)
 
 /**
  * __spi_register_driver - register a SPI driver
+ * @owner: owner module of the driver to register
  * @sdrv: the driver to register
  * Context: can sleep
  *
@@ -2130,6 +2131,7 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message)
          * Set transfer tx_nbits and rx_nbits as single transfer default
          * (SPI_NBITS_SINGLE) if it is not set for this transfer.
          */
+        message->frame_length = 0;
         list_for_each_entry(xfer, &message->transfers, transfer_list) {
                 message->frame_length += xfer->len;
                 if (!xfer->bits_per_word)
diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h
index f5d741f25ffd..485ab2670918 100644
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h
+++ b/drivers/staging/lustre/include/linux/libcfs/libcfs_ioctl.h
@@ -110,7 +110,6 @@ struct libcfs_ioctl_handler {
 #define IOC_LIBCFS_CLEAR_DEBUG       _IOWR('e', 31, long)
 #define IOC_LIBCFS_MARK_DEBUG         _IOWR('e', 32, long)
 #define IOC_LIBCFS_MEMHOG                 _IOWR('e', 36, long)
-#define IOC_LIBCFS_PING_TEST           _IOWR('e', 37, long)
 /* lnet ioctls */
 #define IOC_LIBCFS_GET_NI                 _IOWR('e', 50, long)
 #define IOC_LIBCFS_FAIL_NID             _IOWR('e', 51, long)
diff --git a/drivers/staging/lustre/lustre/libcfs/module.c b/drivers/staging/lustre/lustre/libcfs/module.c
index 96d9d4651a51..75247e920994 100644
--- a/drivers/staging/lustre/lustre/libcfs/module.c
+++ b/drivers/staging/lustre/lustre/libcfs/module.c
@@ -274,23 +274,6 @@ static int libcfs_ioctl_int(struct cfs_psdev_file *pfile, unsigned long cmd,
                 }
                 break;
 
-        case IOC_LIBCFS_PING_TEST: {
-                extern void (kping_client)(struct libcfs_ioctl_data *);
-                void (*ping)(struct libcfs_ioctl_data *);
-
-                CDEBUG(D_IOCTL, "doing %d pings to nid %s (%s)\n",
-                       data->ioc_count, libcfs_nid2str(data->ioc_nid),
-                       libcfs_nid2str(data->ioc_nid));
-                ping = symbol_get(kping_client);
-                if (!ping)
-                        CERROR("symbol_get failed\n");
-                else {
-                        ping(data);
-                        symbol_put(kping_client);
-                }
-                return 0;
-        }
-
         default: {
                 struct libcfs_ioctl_handler *hand;
 
diff --git a/drivers/staging/lustre/lustre/obdecho/echo_client.c b/drivers/staging/lustre/lustre/obdecho/echo_client.c
index 14ac56bb0d77..46822183b9f5 100644
--- a/drivers/staging/lustre/lustre/obdecho/echo_client.c
+++ b/drivers/staging/lustre/lustre/obdecho/echo_client.c
@@ -1270,6 +1270,7 @@ static int
 echo_copyout_lsm(struct lov_stripe_md *lsm, void *_ulsm, int ulsm_nob)
 {
         struct lov_stripe_md *ulsm = _ulsm;
+        struct lov_oinfo **p;
         int nob, i;
 
         nob = offsetof(struct lov_stripe_md, lsm_oinfo[lsm->lsm_stripe_count]);
@@ -1279,9 +1280,10 @@ echo_copyout_lsm(struct lov_stripe_md *lsm, void *_ulsm, int ulsm_nob)
         if (copy_to_user(ulsm, lsm, sizeof(*ulsm)))
                 return -EFAULT;
 
-        for (i = 0; i < lsm->lsm_stripe_count; i++) {
-                if (copy_to_user(ulsm->lsm_oinfo[i], lsm->lsm_oinfo[i],
-                                      sizeof(lsm->lsm_oinfo[0])))
+        for (i = 0, p = lsm->lsm_oinfo; i < lsm->lsm_stripe_count; i++, p++) {
+                struct lov_oinfo __user *up;
+                if (get_user(up, ulsm->lsm_oinfo + i) ||
+                    copy_to_user(up, *p, sizeof(struct lov_oinfo)))
                         return -EFAULT;
         }
         return 0;
@@ -1289,9 +1291,10 @@ echo_copyout_lsm(struct lov_stripe_md *lsm, void *_ulsm, int ulsm_nob)
 
 static int
 echo_copyin_lsm(struct echo_device *ed, struct lov_stripe_md *lsm,
-                 void *ulsm, int ulsm_nob)
+                struct lov_stripe_md __user *ulsm, int ulsm_nob)
 {
         struct echo_client_obd *ec = ed->ed_ec;
+        struct lov_oinfo **p;
         int                  i;
 
         if (ulsm_nob < sizeof(*lsm))
@@ -1306,11 +1309,10 @@ echo_copyin_lsm(struct echo_device *ed, struct lov_stripe_md *lsm,
             ((__u64)lsm->lsm_stripe_size * lsm->lsm_stripe_count > ~0UL))
                 return -EINVAL;
 
-        for (i = 0; i < lsm->lsm_stripe_count; i++) {
-                if (copy_from_user(lsm->lsm_oinfo[i],
-                                       ((struct lov_stripe_md *)ulsm)-> \
-                                       lsm_oinfo[i],
-                                       sizeof(lsm->lsm_oinfo[0])))
+        for (i = 0, p = lsm->lsm_oinfo; i < lsm->lsm_stripe_count; i++, p++) {
+                struct lov_oinfo __user *up;
+                if (get_user(up, ulsm->lsm_oinfo + i) ||
+                    copy_from_user(*p, up, sizeof(struct lov_oinfo)))
                         return -EFAULT;
         }
         return 0;
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 342a07c58d89..72204fbf2bb1 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -4074,6 +4074,17 @@ reject:
         return iscsit_add_reject(conn, ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf);
 }
 
+static bool iscsi_target_check_conn_state(struct iscsi_conn *conn)
+{
+        bool ret;
+
+        spin_lock_bh(&conn->state_lock);
+        ret = (conn->conn_state != TARG_CONN_STATE_LOGGED_IN);
+        spin_unlock_bh(&conn->state_lock);
+
+        return ret;
+}
+
 int iscsi_target_rx_thread(void *arg)
 {
         int ret, rc;
@@ -4091,7 +4102,7 @@ int iscsi_target_rx_thread(void *arg)
          * incoming iscsi/tcp socket I/O, and/or failing the connection.
          */
         rc = wait_for_completion_interruptible(&conn->rx_login_comp);
-        if (rc < 0)
+        if (rc < 0 || iscsi_target_check_conn_state(conn))
                 return 0;
 
         if (conn->conn_transport->transport_type == ISCSI_INFINIBAND) {
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 5c964c09c89f..9fc9117d0f22 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -388,6 +388,7 @@ err:
         if (login->login_complete) {
                 if (conn->rx_thread && conn->rx_thread_active) {
                         send_sig(SIGINT, conn->rx_thread, 1);
+                        complete(&conn->rx_login_comp);
                         kthread_stop(conn->rx_thread);
                 }
                 if (conn->tx_thread && conn->tx_thread_active) {
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index 51d1734d5390..2cbea2af7cd0 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -208,7 +208,7 @@ int iscsi_create_default_params(struct iscsi_param_list **param_list_ptr)
         if (!pl) {
                 pr_err("Unable to allocate memory for"
                                 " struct iscsi_param_list.\n");
-                return -1 ;
+                return -ENOMEM;
         }
         INIT_LIST_HEAD(&pl->param_list);
         INIT_LIST_HEAD(&pl->extra_response_list);
@@ -578,7 +578,7 @@ int iscsi_copy_param_list(
         param_list = kzalloc(sizeof(struct iscsi_param_list), GFP_KERNEL);
         if (!param_list) {
                 pr_err("Unable to allocate memory for struct iscsi_param_list.\n");
-                return -1;
+                return -ENOMEM;
         }
         INIT_LIST_HEAD(&param_list->param_list);
         INIT_LIST_HEAD(&param_list->extra_response_list);
@@ -629,7 +629,7 @@ int iscsi_copy_param_list(
 
 err_out:
         iscsi_release_param_list(param_list);
-        return -1;
+        return -ENOMEM;
 }
 
 static void iscsi_release_extra_responses(struct iscsi_param_list *param_list)
@@ -729,7 +729,7 @@ static int iscsi_add_notunderstood_response(
         if (!extra_response) {
                 pr_err("Unable to allocate memory for"
                         " struct iscsi_extra_response.\n");
-                return -1;
+                return -ENOMEM;
         }
         INIT_LIST_HEAD(&extra_response->er_list);
 
@@ -1370,7 +1370,7 @@ int iscsi_decode_text_input(
         tmpbuf = kzalloc(length + 1, GFP_KERNEL);
         if (!tmpbuf) {
                 pr_err("Unable to allocate %u + 1 bytes for tmpbuf.\n", length);
-                return -1;
+                return -ENOMEM;
         }
 
         memcpy(tmpbuf, textbuf, length);
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 0b4b2a67d9f9..98698d875742 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -371,7 +371,8 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o
         return 0;
 }
 
-static sense_reason_t xdreadwrite_callback(struct se_cmd *cmd, bool success)
+static sense_reason_t xdreadwrite_callback(struct se_cmd *cmd, bool success,
+                                           int *post_ret)
 {
         unsigned char *buf, *addr;
         struct scatterlist *sg;
@@ -437,7 +438,8 @@ sbc_execute_rw(struct se_cmd *cmd)
                                cmd->data_direction);
 }
 
-static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success)
+static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success,
+                                             int *post_ret)
 {
         struct se_device *dev = cmd->se_dev;
 
@@ -447,8 +449,10 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success)
          * sent to the backend driver.
          */
         spin_lock_irq(&cmd->t_state_lock);
-        if ((cmd->transport_state & CMD_T_SENT) && !cmd->scsi_status)
+        if ((cmd->transport_state & CMD_T_SENT) && !cmd->scsi_status) {
                 cmd->se_cmd_flags |= SCF_COMPARE_AND_WRITE_POST;
+                *post_ret = 1;
+        }
         spin_unlock_irq(&cmd->t_state_lock);
 
         /*
@@ -460,7 +464,8 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success)
         return TCM_NO_SENSE;
 }
 
-static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool success)
+static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool success,
+                                                 int *post_ret)
 {
         struct se_device *dev = cmd->se_dev;
         struct scatterlist *write_sg = NULL, *sg;
@@ -556,11 +561,11 @@ static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool succes
 
                 if (block_size < PAGE_SIZE) {
                         sg_set_page(&write_sg[i], m.page, block_size,
-                                    block_size);
+                                    m.piter.sg->offset + block_size);
                 } else {
                         sg_miter_next(&m);
                         sg_set_page(&write_sg[i], m.page, block_size,
-                                    0);
+                                    m.piter.sg->offset);
                 }
                 len -= block_size;
                 i++;
diff --git a/drivers/target/target_core_stat.c b/drivers/target/target_core_stat.c
index 273c72b2b83d..81a6b3e07687 100644
--- a/drivers/target/target_core_stat.c
+++ b/drivers/target/target_core_stat.c
@@ -246,7 +246,7 @@ static ssize_t target_stat_lu_prod_show(struct config_item *item, char *page)
         char str[sizeof(dev->t10_wwn.model)+1];
 
         /* scsiLuProductId */
-        for (i = 0; i < sizeof(dev->t10_wwn.vendor); i++)
+        for (i = 0; i < sizeof(dev->t10_wwn.model); i++)
                 str[i] = ISPRINT(dev->t10_wwn.model[i]) ?
                         dev->t10_wwn.model[i] : ' ';
         str[i] = '\0';
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 5b2820312310..28fb3016370f 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -130,6 +130,9 @@ void core_tmr_abort_task(
                 if (tmr->ref_task_tag != ref_tag)
                         continue;
 
+                if (!kref_get_unless_zero(&se_cmd->cmd_kref))
+                        continue;
+
                 printk("ABORT_TASK: Found referenced %s task_tag: %llu\n",
                         se_cmd->se_tfo->get_fabric_name(), ref_tag);
 
@@ -139,13 +142,15 @@ void core_tmr_abort_task(
                                " skipping\n", ref_tag);
                         spin_unlock(&se_cmd->t_state_lock);
                         spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
+
+                        target_put_sess_cmd(se_cmd);
+
                         goto out;
                 }
                 se_cmd->transport_state |= CMD_T_ABORTED;
                 spin_unlock(&se_cmd->t_state_lock);
 
                 list_del_init(&se_cmd->se_cmd_list);
-                kref_get(&se_cmd->cmd_kref);
                 spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
                 cancel_work_sync(&se_cmd->work);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 5bacc7b5ed6d..4fdcee2006d1 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1658,7 +1658,7 @@ bool target_stop_cmd(struct se_cmd *cmd, unsigned long *flags)
 void transport_generic_request_failure(struct se_cmd *cmd,
                 sense_reason_t sense_reason)
 {
-        int ret = 0;
+        int ret = 0, post_ret = 0;
 
         pr_debug("-----[ Storage Engine Exception for cmd: %p ITT: 0x%08llx"
                 " CDB: 0x%02x\n", cmd, cmd->tag, cmd->t_task_cdb[0]);
@@ -1680,7 +1680,7 @@ void transport_generic_request_failure(struct se_cmd *cmd,
          */
         if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) &&
              cmd->transport_complete_callback)
-                cmd->transport_complete_callback(cmd, false);
+                cmd->transport_complete_callback(cmd, false, &post_ret);
 
         switch (sense_reason) {
         case TCM_NON_EXISTENT_LUN:
@@ -2068,11 +2068,13 @@ static void target_complete_ok_work(struct work_struct *work)
          */
         if (cmd->transport_complete_callback) {
                 sense_reason_t rc;
+                bool caw = (cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE);
+                bool zero_dl = !(cmd->data_length);
+                int post_ret = 0;
 
-                rc = cmd->transport_complete_callback(cmd, true);
-                if (!rc && !(cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE_POST)) {
-                        if ((cmd->se_cmd_flags & SCF_COMPARE_AND_WRITE) &&
-                            !cmd->data_length)
+                rc = cmd->transport_complete_callback(cmd, true, &post_ret);
+                if (!rc && !post_ret) {
+                        if (caw && zero_dl)
                                 goto queue_rsp;
 
                         return;
@@ -2507,23 +2509,24 @@ out:
 EXPORT_SYMBOL(target_get_sess_cmd);
 
 static void target_release_cmd_kref(struct kref *kref)
-                __releases(&se_cmd->se_sess->sess_cmd_lock)
 {
         struct se_cmd *se_cmd = container_of(kref, struct se_cmd, cmd_kref);
         struct se_session *se_sess = se_cmd->se_sess;
+        unsigned long flags;
 
+        spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
         if (list_empty(&se_cmd->se_cmd_list)) {
-                spin_unlock(&se_sess->sess_cmd_lock);
+                spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
                 se_cmd->se_tfo->release_cmd(se_cmd);
                 return;
         }
         if (se_sess->sess_tearing_down && se_cmd->cmd_wait_set) {
-                spin_unlock(&se_sess->sess_cmd_lock);
+                spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
                 complete(&se_cmd->cmd_wait_comp);
                 return;
         }
         list_del(&se_cmd->se_cmd_list);
-        spin_unlock(&se_sess->sess_cmd_lock);
+        spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
         se_cmd->se_tfo->release_cmd(se_cmd);
 }
@@ -2539,8 +2542,7 @@ int target_put_sess_cmd(struct se_cmd *se_cmd)
                 se_cmd->se_tfo->release_cmd(se_cmd);
                 return 1;
         }
-        return kref_put_spinlock_irqsave(&se_cmd->cmd_kref, target_release_cmd_kref,
-                        &se_sess->sess_cmd_lock);
+        return kref_put(&se_cmd->cmd_kref, target_release_cmd_kref);
 }
 EXPORT_SYMBOL(target_put_sess_cmd);
 
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 937cebf76633..5e6d6cb348fc 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -638,7 +638,7 @@ static int tcmu_check_expired_cmd(int id, void *p, void *data)
         if (test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags))
                 return 0;
 
-        if (!time_after(cmd->deadline, jiffies))
+        if (!time_after(jiffies, cmd->deadline))
                 return 0;
 
         set_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags);
@@ -1101,8 +1101,6 @@ tcmu_parse_cdb(struct se_cmd *cmd)
 
 static const struct target_backend_ops tcmu_ops = {
         .name                   = "user",
-        .inquiry_prod           = "USER",
-        .inquiry_rev            = TCMU_VERSION,
         .owner                  = THIS_MODULE,
         .transport_flags        = TRANSPORT_FLAG_PASSTHROUGH,
         .attach_hba             = tcmu_attach_hba,
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index c463c89b90ef..8cc4ac64a91c 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -382,7 +382,7 @@ endmenu
 
 config QCOM_SPMI_TEMP_ALARM
         tristate "Qualcomm SPMI PMIC Temperature Alarm"
-        depends on OF && (SPMI || COMPILE_TEST) && IIO
+        depends on OF && SPMI && IIO
         select REGMAP_SPMI
         help
           This enables a thermal sysfs driver for Qualcomm plug-and-play (QPNP)
diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
index c8fe3cac2e0e..c5547bd711db 100644
--- a/drivers/thermal/imx_thermal.c
+++ b/drivers/thermal/imx_thermal.c
@@ -55,6 +55,7 @@
 #define TEMPSENSE2_PANIC_VALUE_SHIFT    16
 #define TEMPSENSE2_PANIC_VALUE_MASK     0xfff0000
 
+#define OCOTP_MEM0                      0x0480
 #define OCOTP_ANA1                      0x04e0
 
 /* The driver supports 1 passive trip point and 1 critical trip point */
@@ -64,12 +65,6 @@ enum imx_thermal_trip {
         IMX_TRIP_NUM,
 };
 
-/*
- * It defines the temperature in millicelsius for passive trip point
- * that will trigger cooling action when crossed.
- */
-#define IMX_TEMP_PASSIVE                85000
-
 #define IMX_POLLING_DELAY               2000 /* millisecond */
 #define IMX_PASSIVE_DELAY               1000
 
@@ -100,12 +95,14 @@ struct imx_thermal_data {
         u32 c1, c2; /* See formula in imx_get_sensor_data() */
         int temp_passive;
         int temp_critical;
+        int temp_max;
         int alarm_temp;
         int last_temp;
         bool irq_enabled;
         int irq;
         struct clk *thermal_clk;
         const struct thermal_soc_data *socdata;
+        const char *temp_grade;
 };
 
 static void imx_set_panic_temp(struct imx_thermal_data *data,
@@ -285,10 +282,12 @@ static int imx_set_trip_temp(struct thermal_zone_device *tz, int trip,
 {
         struct imx_thermal_data *data = tz->devdata;
 
+        /* do not allow changing critical threshold */
         if (trip == IMX_TRIP_CRITICAL)
                 return -EPERM;
 
-        if (temp < 0 || temp > IMX_TEMP_PASSIVE)
+        /* do not allow passive to be set higher than critical */
+        if (temp < 0 || temp > data->temp_critical)
                 return -EINVAL;
 
         data->temp_passive = temp;
@@ -404,17 +403,39 @@ static int imx_get_sensor_data(struct platform_device *pdev)
         data->c1 = temp64;
         data->c2 = n1 * data->c1 + 1000 * t1;
 
-        /*
-         * Set the default passive cooling trip point,
-         * can be changed from userspace.
-         */
-        data->temp_passive = IMX_TEMP_PASSIVE;
+        /* use OTP for thermal grade */
+        ret = regmap_read(map, OCOTP_MEM0, &val);
+        if (ret) {
+                dev_err(&pdev->dev, "failed to read temp grade: %d\n", ret);
+                return ret;
+        }
+
+        /* The maximum die temp is specified by the Temperature Grade */
+        switch ((val >> 6) & 0x3) {
+        case 0: /* Commercial (0 to 95C) */
+                data->temp_grade = "Commercial";
+                data->temp_max = 95000;
+                break;
+        case 1: /* Extended Commercial (-20 to 105C) */
+                data->temp_grade = "Extended Commercial";
+                data->temp_max = 105000;
+                break;
+        case 2: /* Industrial (-40 to 105C) */
+                data->temp_grade = "Industrial";
+                data->temp_max = 105000;
+                break;
+        case 3: /* Automotive (-40 to 125C) */
+                data->temp_grade = "Automotive";
+                data->temp_max = 125000;
+                break;
+        }
 
         /*
-         * The maximum die temperature set to 20 C higher than
-         * IMX_TEMP_PASSIVE.
+         * Set the critical trip point at 5C under max
+         * Set the passive trip point at 10C under max (can change via sysfs)
          */
-        data->temp_critical = 1000 * 20 + data->temp_passive;
+        data->temp_critical = data->temp_max - (1000 * 5);
+        data->temp_passive = data->temp_max - (1000 * 10);
 
         return 0;
 }
@@ -551,6 +572,11 @@ static int imx_thermal_probe(struct platform_device *pdev)
                 return ret;
         }
 
+        dev_info(&pdev->dev, "%s CPU temperature grade - max:%dC"
+                 " critical:%dC passive:%dC\n", data->temp_grade,
+                 data->temp_max / 1000, data->temp_critical / 1000,
+                 data->temp_passive / 1000);
+
         /* Enable measurements at ~ 10 Hz */
         regmap_write(map, TEMPSENSE1 + REG_CLR, TEMPSENSE1_MEASURE_FREQ);
         measure_freq = DIV_ROUND_UP(32768, 10); /* 10 Hz */
diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c
index 42b7d4253b94..be4eedcb839a 100644
--- a/drivers/thermal/of-thermal.c
+++ b/drivers/thermal/of-thermal.c
@@ -964,7 +964,7 @@ void of_thermal_destroy_zones(void)
 
         np = of_find_node_by_name(NULL, "thermal-zones");
         if (!np) {
-                pr_err("unable to find thermal zones\n");
+                pr_debug("unable to find thermal zones\n");
                 return;
         }
 
diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c
index f0fbea386869..1246aa6fcab0 100644
--- a/drivers/thermal/power_allocator.c
+++ b/drivers/thermal/power_allocator.c
@@ -174,7 +174,6 @@ static void estimate_pid_constants(struct thermal_zone_device *tz,
 /**
  * pid_controller() - PID controller
  * @tz: thermal zone we are operating in
- * @current_temp:       the current temperature in millicelsius
  * @control_temp:       the target temperature in millicelsius
  * @max_allocatable_power:      maximum allocatable power for this thermal zone
  *
@@ -191,7 +190,6 @@ static void estimate_pid_constants(struct thermal_zone_device *tz,
  * Return: The power budget for the next period.
  */
 static u32 pid_controller(struct thermal_zone_device *tz,
-                          int current_temp,
                           int control_temp,
                           u32 max_allocatable_power)
 {
@@ -211,7 +209,7 @@ static u32 pid_controller(struct thermal_zone_device *tz,
                                        true);
         }
 
-        err = control_temp - current_temp;
+        err = control_temp - tz->temperature;
         err = int_to_frac(err);
 
         /* Calculate the proportional term */
@@ -332,7 +330,6 @@ static void divvy_up_power(u32 *req_power, u32 *max_power, int num_actors,
 }
 
 static int allocate_power(struct thermal_zone_device *tz,
-                          int current_temp,
                           int control_temp)
 {
         struct thermal_instance *instance;
@@ -418,8 +415,7 @@ static int allocate_power(struct thermal_zone_device *tz,
                 i++;
         }
 
-        power_range = pid_controller(tz, current_temp, control_temp,
-                                     max_allocatable_power);
+        power_range = pid_controller(tz, control_temp, max_allocatable_power);
 
         divvy_up_power(weighted_req_power, max_power, num_actors,
                        total_weighted_req_power, power_range, granted_power,
@@ -444,8 +440,8 @@ static int allocate_power(struct thermal_zone_device *tz,
         trace_thermal_power_allocator(tz, req_power, total_req_power,
                                       granted_power, total_granted_power,
                                       num_actors, power_range,
-                                      max_allocatable_power, current_temp,
-                                      control_temp - current_temp);
+                                      max_allocatable_power, tz->temperature,
+                                      control_temp - tz->temperature);
 
         kfree(req_power);
 unlock:
@@ -612,7 +608,7 @@ static void power_allocator_unbind(struct thermal_zone_device *tz)
 static int power_allocator_throttle(struct thermal_zone_device *tz, int trip)
 {
         int ret;
-        int switch_on_temp, control_temp, current_temp;
+        int switch_on_temp, control_temp;
         struct power_allocator_params *params = tz->governor_data;
 
         /*
@@ -622,15 +618,9 @@ static int power_allocator_throttle(struct thermal_zone_device *tz, int trip)
         if (trip != params->trip_max_desired_temperature)
                 return 0;
 
-        ret = thermal_zone_get_temp(tz, &current_temp);
-        if (ret) {
-                dev_warn(&tz->device, "Failed to get temperature: %d\n", ret);
-                return ret;
-        }
-
         ret = tz->ops->get_trip_temp(tz, params->trip_switch_on,
                                      &switch_on_temp);
-        if (!ret && (current_temp < switch_on_temp)) {
+        if (!ret && (tz->temperature < switch_on_temp)) {
                 tz->passive = 0;
                 reset_pid_controller(params);
                 allow_maximum_power(tz);
@@ -648,7 +638,7 @@ static int power_allocator_throttle(struct thermal_zone_device *tz, int trip)
                 return ret;
         }
 
-        return allocate_power(tz, current_temp, control_temp);
+        return allocate_power(tz, control_temp);
 }
 
 static struct thermal_governor thermal_gov_power_allocator = {
diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c
index 5d4ae7d705e0..13d01edc7a04 100644
--- a/drivers/thermal/rcar_thermal.c
+++ b/drivers/thermal/rcar_thermal.c
@@ -361,6 +361,24 @@ static irqreturn_t rcar_thermal_irq(int irq, void *data)
 /*
  *              platform functions
  */
+static int rcar_thermal_remove(struct platform_device *pdev)
+{
+        struct rcar_thermal_common *common = platform_get_drvdata(pdev);
+        struct device *dev = &pdev->dev;
+        struct rcar_thermal_priv *priv;
+
+        rcar_thermal_for_each_priv(priv, common) {
+                if (rcar_has_irq_support(priv))
+                        rcar_thermal_irq_disable(priv);
+                thermal_zone_device_unregister(priv->zone);
+        }
+
+        pm_runtime_put(dev);
+        pm_runtime_disable(dev);
+
+        return 0;
+}
+
 static int rcar_thermal_probe(struct platform_device *pdev)
 {
         struct rcar_thermal_common *common;
@@ -377,6 +395,8 @@ static int rcar_thermal_probe(struct platform_device *pdev)
         if (!common)
                 return -ENOMEM;
 
+        platform_set_drvdata(pdev, common);
+
         INIT_LIST_HEAD(&common->head);
         spin_lock_init(&common->lock);
         common->dev = dev;
@@ -454,43 +474,16 @@ static int rcar_thermal_probe(struct platform_device *pdev)
                 rcar_thermal_common_write(common, ENR, enr_bits);
         }
 
-        platform_set_drvdata(pdev, common);
-
         dev_info(dev, "%d sensor probed\n", i);
 
         return 0;
 
 error_unregister:
-        rcar_thermal_for_each_priv(priv, common) {
-                if (rcar_has_irq_support(priv))
-                        rcar_thermal_irq_disable(priv);
-                thermal_zone_device_unregister(priv->zone);
-        }
-
-        pm_runtime_put(dev);
-        pm_runtime_disable(dev);
+        rcar_thermal_remove(pdev);
 
         return ret;
 }
 
-static int rcar_thermal_remove(struct platform_device *pdev)
-{
-        struct rcar_thermal_common *common = platform_get_drvdata(pdev);
-        struct device *dev = &pdev->dev;
-        struct rcar_thermal_priv *priv;
-
-        rcar_thermal_for_each_priv(priv, common) {
-                if (rcar_has_irq_support(priv))
-                        rcar_thermal_irq_disable(priv);
-                thermal_zone_device_unregister(priv->zone);
-        }
-
-        pm_runtime_put(dev);
-        pm_runtime_disable(dev);
-
-        return 0;
-}
-
 static const struct of_device_id rcar_thermal_dt_ids[] = {
         { .compatible = "renesas,rcar-thermal", },
         {},
diff --git a/drivers/thermal/rockchip_thermal.c b/drivers/thermal/rockchip_thermal.c
index 9787e8aa509f..e845841ab036 100644
--- a/drivers/thermal/rockchip_thermal.c
+++ b/drivers/thermal/rockchip_thermal.c
@@ -1,6 +1,9 @@
 /*
  * Copyright (c) 2014, Fuzhou Rockchip Electronics Co., Ltd
  *
+ * Copyright (c) 2015, Fuzhou Rockchip Electronics Co., Ltd
+ * Caesar Wang <wxt@rock-chips.com>
+ *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
  * version 2, as published by the Free Software Foundation.
@@ -45,17 +48,50 @@ enum tshut_polarity {
 };
 
 /**
- * The system has three Temperature Sensors.  channel 0 is reserved,
- * channel 1 is for CPU, and channel 2 is for GPU.
+ * The system has two Temperature Sensors.
+ * sensor0 is for CPU, and sensor1 is for GPU.
  */
 enum sensor_id {
-        SENSOR_CPU = 1,
+        SENSOR_CPU = 0,
         SENSOR_GPU,
 };
 
+/**
+* The conversion table has the adc value and temperature.
+* ADC_DECREMENT is the adc value decremnet.(e.g. v2_code_table)
+* ADC_INCREMNET is the adc value incremnet.(e.g. v3_code_table)
+*/
+enum adc_sort_mode {
+        ADC_DECREMENT = 0,
+        ADC_INCREMENT,
+};
+
+/**
+ * The max sensors is two in rockchip SoCs.
+ * Two sensors: CPU and GPU sensor.
+ */
+#define SOC_MAX_SENSORS 2
+
+struct chip_tsadc_table {
+        const struct tsadc_table *id;
+
+        /* the array table size*/
+        unsigned int length;
+
+        /* that analogic mask data */
+        u32 data_mask;
+
+        /* the sort mode is adc value that increment or decrement in table */
+        enum adc_sort_mode mode;
+};
+
 struct rockchip_tsadc_chip {
+        /* The sensor id of chip correspond to the ADC channel */
+        int chn_id[SOC_MAX_SENSORS];
+        int chn_num;
+
         /* The hardware-controlled tshut property */
-        long tshut_temp;
+        int tshut_temp;
         enum tshut_mode tshut_mode;
         enum tshut_polarity tshut_polarity;
 
@@ -65,37 +101,40 @@ struct rockchip_tsadc_chip {
         void (*control)(void __iomem *reg, bool on);
 
         /* Per-sensor methods */
-        int (*get_temp)(int chn, void __iomem *reg, int *temp);
-        void (*set_tshut_temp)(int chn, void __iomem *reg, long temp);
+        int (*get_temp)(struct chip_tsadc_table table,
+                        int chn, void __iomem *reg, int *temp);
+        void (*set_tshut_temp)(struct chip_tsadc_table table,
+                               int chn, void __iomem *reg, int temp);
         void (*set_tshut_mode)(int chn, void __iomem *reg, enum tshut_mode m);
+
+        /* Per-table methods */
+        struct chip_tsadc_table table;
 };
 
 struct rockchip_thermal_sensor {
         struct rockchip_thermal_data *thermal;
         struct thermal_zone_device *tzd;
-        enum sensor_id id;
+        int id;
 };
 
-#define NUM_SENSORS     2 /* Ignore unused sensor 0 */
-
 struct rockchip_thermal_data {
         const struct rockchip_tsadc_chip *chip;
         struct platform_device *pdev;
         struct reset_control *reset;
 
-        struct rockchip_thermal_sensor sensors[NUM_SENSORS];
+        struct rockchip_thermal_sensor sensors[SOC_MAX_SENSORS];
 
         struct clk *clk;
         struct clk *pclk;
 
         void __iomem *regs;
 
-        long tshut_temp;
+        int tshut_temp;
         enum tshut_mode tshut_mode;
         enum tshut_polarity tshut_polarity;
 };
 
-/* TSADC V2 Sensor info define: */
+/* TSADC Sensor info define: */
 #define TSADCV2_AUTO_CON                        0x04
 #define TSADCV2_INT_EN                          0x08
 #define TSADCV2_INT_PD                          0x0c
@@ -117,6 +156,8 @@ struct rockchip_thermal_data {
 #define TSADCV2_INT_PD_CLEAR_MASK               ~BIT(8)
 
 #define TSADCV2_DATA_MASK                       0xfff
+#define TSADCV3_DATA_MASK                       0x3ff
+
 #define TSADCV2_HIGHT_INT_DEBOUNCE_COUNT        4
 #define TSADCV2_HIGHT_TSHUT_DEBOUNCE_COUNT      4
 #define TSADCV2_AUTO_PERIOD_TIME                250 /* msec */
@@ -124,7 +165,7 @@ struct rockchip_thermal_data {
 
 struct tsadc_table {
         u32 code;
-        long temp;
+        int temp;
 };
 
 static const struct tsadc_table v2_code_table[] = {
@@ -165,21 +206,61 @@ static const struct tsadc_table v2_code_table[] = {
         {3421, 125000},
 };
 
-static u32 rk_tsadcv2_temp_to_code(long temp)
+static const struct tsadc_table v3_code_table[] = {
+        {0, -40000},
+        {106, -40000},
+        {108, -35000},
+        {110, -30000},
+        {112, -25000},
+        {114, -20000},
+        {116, -15000},
+        {118, -10000},
+        {120, -5000},
+        {122, 0},
+        {124, 5000},
+        {126, 10000},
+        {128, 15000},
+        {130, 20000},
+        {132, 25000},
+        {134, 30000},
+        {136, 35000},
+        {138, 40000},
+        {140, 45000},
+        {142, 50000},
+        {144, 55000},
+        {146, 60000},
+        {148, 65000},
+        {150, 70000},
+        {152, 75000},
+        {154, 80000},
+        {156, 85000},
+        {158, 90000},
+        {160, 95000},
+        {162, 100000},
+        {163, 105000},
+        {165, 110000},
+        {167, 115000},
+        {169, 120000},
+        {171, 125000},
+        {TSADCV3_DATA_MASK, 125000},
+};
+
+static u32 rk_tsadcv2_temp_to_code(struct chip_tsadc_table table,
+                                   int temp)
 {
         int high, low, mid;
 
         low = 0;
-        high = ARRAY_SIZE(v2_code_table) - 1;
+        high = table.length - 1;
         mid = (high + low) / 2;
 
-        if (temp < v2_code_table[low].temp || temp > v2_code_table[high].temp)
+        if (temp < table.id[low].temp || temp > table.id[high].temp)
                 return 0;
 
         while (low <= high) {
-                if (temp == v2_code_table[mid].temp)
-                        return v2_code_table[mid].code;
-                else if (temp < v2_code_table[mid].temp)
+                if (temp == table.id[mid].temp)
+                        return table.id[mid].code;
+                else if (temp < table.id[mid].temp)
                         high = mid - 1;
                 else
                         low = mid + 1;
@@ -189,29 +270,54 @@ static u32 rk_tsadcv2_temp_to_code(long temp)
         return 0;
 }
 
-static int rk_tsadcv2_code_to_temp(u32 code, int *temp)
+static int rk_tsadcv2_code_to_temp(struct chip_tsadc_table table, u32 code,
+                                   int *temp)
 {
         unsigned int low = 1;
-        unsigned int high = ARRAY_SIZE(v2_code_table) - 1;
+        unsigned int high = table.length - 1;
         unsigned int mid = (low + high) / 2;
         unsigned int num;
         unsigned long denom;
 
-        BUILD_BUG_ON(ARRAY_SIZE(v2_code_table) < 2);
-
-        code &= TSADCV2_DATA_MASK;
-        if (code < v2_code_table[high].code)
-                return -EAGAIN;         /* Incorrect reading */
-
-        while (low <= high) {
-                if (code >= v2_code_table[mid].code &&
-                    code < v2_code_table[mid - 1].code)
-                        break;
-                else if (code < v2_code_table[mid].code)
-                        low = mid + 1;
-                else
-                        high = mid - 1;
-                mid = (low + high) / 2;
+        WARN_ON(table.length < 2);
+
+        switch (table.mode) {
+        case ADC_DECREMENT:
+                code &= table.data_mask;
+                if (code < table.id[high].code)
+                        return -EAGAIN;         /* Incorrect reading */
+
+                while (low <= high) {
+                        if (code >= table.id[mid].code &&
+                            code < table.id[mid - 1].code)
+                                break;
+                        else if (code < table.id[mid].code)
+                                low = mid + 1;
+                        else
+                                high = mid - 1;
+
+                        mid = (low + high) / 2;
+                }
+                break;
+        case ADC_INCREMENT:
+                code &= table.data_mask;
+                if (code < table.id[low].code)
+                        return -EAGAIN;         /* Incorrect reading */
+
+                while (low <= high) {
+                        if (code >= table.id[mid - 1].code &&
+                            code < table.id[mid].code)
+                                break;
+                        else if (code > table.id[mid].code)
+                                low = mid + 1;
+                        else
+                                high = mid - 1;
+
+                        mid = (low + high) / 2;
+                }
+                break;
+        default:
+                pr_err("Invalid the conversion table\n");
         }
 
         /*
@@ -220,24 +326,28 @@ static int rk_tsadcv2_code_to_temp(u32 code, int *temp)
          * temperature between 2 table entries is linear and interpolate
          * to produce less granular result.
          */
-        num = v2_code_table[mid].temp - v2_code_table[mid - 1].temp;
-        num *= v2_code_table[mid - 1].code - code;
-        denom = v2_code_table[mid - 1].code - v2_code_table[mid].code;
-        *temp = v2_code_table[mid - 1].temp + (num / denom);
+        num = table.id[mid].temp - v2_code_table[mid - 1].temp;
+        num *= abs(table.id[mid - 1].code - code);
+        denom = abs(table.id[mid - 1].code - table.id[mid].code);
+        *temp = table.id[mid - 1].temp + (num / denom);
 
         return 0;
 }
 
 /**
- * rk_tsadcv2_initialize - initialize TASDC Controller
- * (1) Set TSADCV2_AUTO_PERIOD, configure the interleave between
- * every two accessing of TSADC in normal operation.
- * (2) Set TSADCV2_AUTO_PERIOD_HT, configure the interleave between
- * every two accessing of TSADC after the temperature is higher
- * than COM_SHUT or COM_INT.
- * (3) Set TSADCV2_HIGH_INT_DEBOUNCE and TSADC_HIGHT_TSHUT_DEBOUNCE,
- * if the temperature is higher than COMP_INT or COMP_SHUT for
- * "debounce" times, TSADC controller will generate interrupt or TSHUT.
+ * rk_tsadcv2_initialize - initialize TASDC Controller.
+ *
+ * (1) Set TSADC_V2_AUTO_PERIOD:
+ *     Configure the interleave between every two accessing of
+ *     TSADC in normal operation.
+ *
+ * (2) Set TSADCV2_AUTO_PERIOD_HT:
+ *     Configure the interleave between every two accessing of
+ *     TSADC after the temperature is higher than COM_SHUT or COM_INT.
+ *
+ * (3) Set TSADCV2_HIGH_INT_DEBOUNCE and TSADC_HIGHT_TSHUT_DEBOUNCE:
+ *     If the temperature is higher than COMP_INT or COMP_SHUT for
+ *     "debounce" times, TSADC controller will generate interrupt or TSHUT.
  */
 static void rk_tsadcv2_initialize(void __iomem *regs,
                                   enum tshut_polarity tshut_polarity)
@@ -279,20 +389,22 @@ static void rk_tsadcv2_control(void __iomem *regs, bool enable)
         writel_relaxed(val, regs + TSADCV2_AUTO_CON);
 }
 
-static int rk_tsadcv2_get_temp(int chn, void __iomem *regs, int *temp)
+static int rk_tsadcv2_get_temp(struct chip_tsadc_table table,
+                               int chn, void __iomem *regs, int *temp)
 {
         u32 val;
 
         val = readl_relaxed(regs + TSADCV2_DATA(chn));
 
-        return rk_tsadcv2_code_to_temp(val, temp);
+        return rk_tsadcv2_code_to_temp(table, val, temp);
 }
 
-static void rk_tsadcv2_tshut_temp(int chn, void __iomem *regs, long temp)
+static void rk_tsadcv2_tshut_temp(struct chip_tsadc_table table,
+                                  int chn, void __iomem *regs, int temp)
 {
         u32 tshut_value, val;
 
-        tshut_value = rk_tsadcv2_temp_to_code(temp);
+        tshut_value = rk_tsadcv2_temp_to_code(table, temp);
         writel_relaxed(tshut_value, regs + TSADCV2_COMP_SHUT(chn));
 
         /* TSHUT will be valid */
@@ -318,6 +430,10 @@ static void rk_tsadcv2_tshut_mode(int chn, void __iomem *regs,
 }
 
 static const struct rockchip_tsadc_chip rk3288_tsadc_data = {
+        .chn_id[SENSOR_CPU] = 1, /* cpu sensor is channel 1 */
+        .chn_id[SENSOR_GPU] = 2, /* gpu sensor is channel 2 */
+        .chn_num = 2, /* two channels for tsadc */
+
         .tshut_mode = TSHUT_MODE_GPIO, /* default TSHUT via GPIO give PMIC */
         .tshut_polarity = TSHUT_LOW_ACTIVE, /* default TSHUT LOW ACTIVE */
         .tshut_temp = 95000,
@@ -328,6 +444,37 @@ static const struct rockchip_tsadc_chip rk3288_tsadc_data = {
         .get_temp = rk_tsadcv2_get_temp,
         .set_tshut_temp = rk_tsadcv2_tshut_temp,
         .set_tshut_mode = rk_tsadcv2_tshut_mode,
+
+        .table = {
+                .id = v2_code_table,
+                .length = ARRAY_SIZE(v2_code_table),
+                .data_mask = TSADCV2_DATA_MASK,
+                .mode = ADC_DECREMENT,
+        },
+};
+
+static const struct rockchip_tsadc_chip rk3368_tsadc_data = {
+        .chn_id[SENSOR_CPU] = 0, /* cpu sensor is channel 0 */
+        .chn_id[SENSOR_GPU] = 1, /* gpu sensor is channel 1 */
+        .chn_num = 2, /* two channels for tsadc */
+
+        .tshut_mode = TSHUT_MODE_GPIO, /* default TSHUT via GPIO give PMIC */
+        .tshut_polarity = TSHUT_LOW_ACTIVE, /* default TSHUT LOW ACTIVE */
+        .tshut_temp = 95000,
+
+        .initialize = rk_tsadcv2_initialize,
+        .irq_ack = rk_tsadcv2_irq_ack,
+        .control = rk_tsadcv2_control,
+        .get_temp = rk_tsadcv2_get_temp,
+        .set_tshut_temp = rk_tsadcv2_tshut_temp,
+        .set_tshut_mode = rk_tsadcv2_tshut_mode,
+
+        .table = {
+                .id = v3_code_table,
+                .length = ARRAY_SIZE(v3_code_table),
+                .data_mask = TSADCV3_DATA_MASK,
+                .mode = ADC_INCREMENT,
+        },
 };
 
 static const struct of_device_id of_rockchip_thermal_match[] = {
@@ -335,6 +482,10 @@ static const struct of_device_id of_rockchip_thermal_match[] = {
                 .compatible = "rockchip,rk3288-tsadc",
                 .data = (void *)&rk3288_tsadc_data,
         },
+        {
+                .compatible = "rockchip,rk3368-tsadc",
+                .data = (void *)&rk3368_tsadc_data,
+        },
         { /* end */ },
 };
 MODULE_DEVICE_TABLE(of, of_rockchip_thermal_match);
@@ -357,7 +508,7 @@ static irqreturn_t rockchip_thermal_alarm_irq_thread(int irq, void *dev)
 
         thermal->chip->irq_ack(thermal->regs);
 
-        for (i = 0; i < ARRAY_SIZE(thermal->sensors); i++)
+        for (i = 0; i < thermal->chip->chn_num; i++)
                 thermal_zone_device_update(thermal->sensors[i].tzd);
 
         return IRQ_HANDLED;
@@ -370,7 +521,8 @@ static int rockchip_thermal_get_temp(void *_sensor, int *out_temp)
         const struct rockchip_tsadc_chip *tsadc = sensor->thermal->chip;
         int retval;
 
-        retval = tsadc->get_temp(sensor->id, thermal->regs, out_temp);
+        retval = tsadc->get_temp(tsadc->table,
+                                 sensor->id, thermal->regs, out_temp);
         dev_dbg(&thermal->pdev->dev, "sensor %d - temp: %d, retval: %d\n",
                 sensor->id, *out_temp, retval);
 
@@ -389,7 +541,7 @@ static int rockchip_configure_from_dt(struct device *dev,
 
         if (of_property_read_u32(np, "rockchip,hw-tshut-temp", &shut_temp)) {
                 dev_warn(dev,
-                         "Missing tshut temp property, using default %ld\n",
+                         "Missing tshut temp property, using default %d\n",
                          thermal->chip->tshut_temp);
                 thermal->tshut_temp = thermal->chip->tshut_temp;
         } else {
@@ -397,7 +549,7 @@ static int rockchip_configure_from_dt(struct device *dev,
         }
 
         if (thermal->tshut_temp > INT_MAX) {
-                dev_err(dev, "Invalid tshut temperature specified: %ld\n",
+                dev_err(dev, "Invalid tshut temperature specified: %d\n",
                         thermal->tshut_temp);
                 return -ERANGE;
         }
@@ -442,13 +594,14 @@ static int
 rockchip_thermal_register_sensor(struct platform_device *pdev,
                                  struct rockchip_thermal_data *thermal,
                                  struct rockchip_thermal_sensor *sensor,
-                                 enum sensor_id id)
+                                 int id)
 {
         const struct rockchip_tsadc_chip *tsadc = thermal->chip;
         int error;
 
         tsadc->set_tshut_mode(id, thermal->regs, thermal->tshut_mode);
-        tsadc->set_tshut_temp(id, thermal->regs, thermal->tshut_temp);
+        tsadc->set_tshut_temp(tsadc->table, id, thermal->regs,
+                              thermal->tshut_temp);
 
         sensor->thermal = thermal;
         sensor->id = id;
@@ -481,7 +634,7 @@ static int rockchip_thermal_probe(struct platform_device *pdev)
         const struct of_device_id *match;
         struct resource *res;
         int irq;
-        int i;
+        int i, j;
         int error;
 
         match = of_match_node(of_rockchip_thermal_match, np);
@@ -556,22 +709,19 @@ static int rockchip_thermal_probe(struct platform_device *pdev)
 
         thermal->chip->initialize(thermal->regs, thermal->tshut_polarity);
 
-        error = rockchip_thermal_register_sensor(pdev, thermal,
-                                                 &thermal->sensors[0],
-                                                 SENSOR_CPU);
-        if (error) {
-                dev_err(&pdev->dev,
-                        "failed to register CPU thermal sensor: %d\n", error);
-                goto err_disable_pclk;
-        }
-
-        error = rockchip_thermal_register_sensor(pdev, thermal,
-                                                 &thermal->sensors[1],
-                                                 SENSOR_GPU);
-        if (error) {
-                dev_err(&pdev->dev,
-                        "failed to register GPU thermal sensor: %d\n", error);
-                goto err_unregister_cpu_sensor;
+        for (i = 0; i < thermal->chip->chn_num; i++) {
+                error = rockchip_thermal_register_sensor(pdev, thermal,
+                                                &thermal->sensors[i],
+                                                thermal->chip->chn_id[i]);
+                if (error) {
+                        dev_err(&pdev->dev,
+                                "failed to register sensor[%d] : error = %d\n",
+                                i, error);
+                        for (j = 0; j < i; j++)
+                                thermal_zone_of_sensor_unregister(&pdev->dev,
+                                                thermal->sensors[j].tzd);
+                        goto err_disable_pclk;
+                }
         }
 
         error = devm_request_threaded_irq(&pdev->dev, irq, NULL,
@@ -581,22 +731,23 @@ static int rockchip_thermal_probe(struct platform_device *pdev)
         if (error) {
                 dev_err(&pdev->dev,
                         "failed to request tsadc irq: %d\n", error);
-                goto err_unregister_gpu_sensor;
+                goto err_unregister_sensor;
         }
 
         thermal->chip->control(thermal->regs, true);
 
-        for (i = 0; i < ARRAY_SIZE(thermal->sensors); i++)
+        for (i = 0; i < thermal->chip->chn_num; i++)
                 rockchip_thermal_toggle_sensor(&thermal->sensors[i], true);
 
         platform_set_drvdata(pdev, thermal);
 
         return 0;
 
-err_unregister_gpu_sensor:
-        thermal_zone_of_sensor_unregister(&pdev->dev, thermal->sensors[1].tzd);
-err_unregister_cpu_sensor:
-        thermal_zone_of_sensor_unregister(&pdev->dev, thermal->sensors[0].tzd);
+err_unregister_sensor:
+        while (i--)
+                thermal_zone_of_sensor_unregister(&pdev->dev,
+                                                  thermal->sensors[i].tzd);
+
 err_disable_pclk:
         clk_disable_unprepare(thermal->pclk);
 err_disable_clk:
@@ -610,7 +761,7 @@ static int rockchip_thermal_remove(struct platform_device *pdev)
         struct rockchip_thermal_data *thermal = platform_get_drvdata(pdev);
         int i;
 
-        for (i = 0; i < ARRAY_SIZE(thermal->sensors); i++) {
+        for (i = 0; i < thermal->chip->chn_num; i++) {
                 struct rockchip_thermal_sensor *sensor = &thermal->sensors[i];
 
                 rockchip_thermal_toggle_sensor(sensor, false);
@@ -631,7 +782,7 @@ static int __maybe_unused rockchip_thermal_suspend(struct device *dev)
         struct rockchip_thermal_data *thermal = platform_get_drvdata(pdev);
         int i;
 
-        for (i = 0; i < ARRAY_SIZE(thermal->sensors); i++)
+        for (i = 0; i < thermal->chip->chn_num; i++)
                 rockchip_thermal_toggle_sensor(&thermal->sensors[i], false);
 
         thermal->chip->control(thermal->regs, false);
@@ -663,18 +814,19 @@ static int __maybe_unused rockchip_thermal_resume(struct device *dev)
 
         thermal->chip->initialize(thermal->regs, thermal->tshut_polarity);
 
-        for (i = 0; i < ARRAY_SIZE(thermal->sensors); i++) {
-                enum sensor_id id = thermal->sensors[i].id;
+        for (i = 0; i < thermal->chip->chn_num; i++) {
+                int id = thermal->sensors[i].id;
 
                 thermal->chip->set_tshut_mode(id, thermal->regs,
                                               thermal->tshut_mode);
-                thermal->chip->set_tshut_temp(id, thermal->regs,
+                thermal->chip->set_tshut_temp(thermal->chip->table,
+                                              id, thermal->regs,
                                               thermal->tshut_temp);
         }
 
         thermal->chip->control(thermal->regs, true);
 
-        for (i = 0; i < ARRAY_SIZE(thermal->sensors); i++)
+        for (i = 0; i < thermal->chip->chn_num; i++)
                 rockchip_thermal_toggle_sensor(&thermal->sensors[i], true);
 
         pinctrl_pm_select_default_state(dev);
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index b30e7423549b..26ca4f910cb0 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1838,6 +1838,11 @@ static const struct usb_device_id acm_ids[] = {
         },
 #endif
 
+        /* Exclude Infineon Flash Loader utility */
+        { USB_DEVICE(0x058b, 0x0041),
+        .driver_info = IGNORE_DEVICE,
+        },
+
         /* control interfaces without any protocol set */
         { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM,
                 USB_CDC_PROTO_NONE) },
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 7caff020106e..5050760f5e17 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -115,7 +115,8 @@ static void usb_parse_ss_endpoint_companion(struct device *ddev, int cfgno,
                    USB_SS_MULT(desc->bmAttributes) > 3) {
                 dev_warn(ddev, "Isoc endpoint has Mult of %d in "
                                 "config %d interface %d altsetting %d ep %d: "
-                                "setting to 3\n", desc->bmAttributes + 1,
+                                "setting to 3\n",
+                                USB_SS_MULT(desc->bmAttributes),
                                 cfgno, inum, asnum, ep->desc.bEndpointAddress);
                 ep->ss_ep_comp.bmAttributes = 2;
         }
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index bdeadc112d29..a5cc032ef77a 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -124,6 +124,10 @@ struct usb_hub *usb_hub_to_struct_hub(struct usb_device *hdev)
 
 int usb_device_supports_lpm(struct usb_device *udev)
 {
+        /* Some devices have trouble with LPM */
+        if (udev->quirks & USB_QUIRK_NO_LPM)
+                return 0;
+
         /* USB 2.1 (and greater) devices indicate LPM support through
          * their USB 2.0 Extended Capabilities BOS descriptor.
          */
@@ -4512,6 +4516,8 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
                 goto fail;
         }
 
+        usb_detect_quirks(udev);
+
         if (udev->wusb == 0 && le16_to_cpu(udev->descriptor.bcdUSB) >= 0x0201) {
                 retval = usb_get_bos_descriptor(udev);
                 if (!retval) {
@@ -4710,7 +4716,6 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
                 if (status < 0)
                         goto loop;
 
-                usb_detect_quirks(udev);
                 if (udev->quirks & USB_QUIRK_DELAY_INIT)
                         msleep(1000);
 
@@ -5326,9 +5331,6 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
         if (udev->usb2_hw_lpm_enabled == 1)
                 usb_set_usb2_hardware_lpm(udev, 0);
 
-        bos = udev->bos;
-        udev->bos = NULL;
-
         /* Disable LPM and LTM while we reset the device and reinstall the alt
          * settings.  Device-initiated LPM settings, and system exit latency
          * settings are cleared when the device is reset, so we have to set
@@ -5337,15 +5339,18 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
         ret = usb_unlocked_disable_lpm(udev);
         if (ret) {
                 dev_err(&udev->dev, "%s Failed to disable LPM\n.", __func__);
-                goto re_enumerate;
+                goto re_enumerate_no_bos;
         }
         ret = usb_disable_ltm(udev);
         if (ret) {
                 dev_err(&udev->dev, "%s Failed to disable LTM\n.",
                                 __func__);
-                goto re_enumerate;
+                goto re_enumerate_no_bos;
         }
 
+        bos = udev->bos;
+        udev->bos = NULL;
+
         for (i = 0; i < SET_CONFIG_TRIES; ++i) {
 
                 /* ep0 maxpacket size may change; let the HCD know about it.
@@ -5442,10 +5447,11 @@ done:
         return 0;
 
 re_enumerate:
-        /* LPM state doesn't matter when we're about to destroy the device. */
-        hub_port_logical_disconnect(parent_hub, port1);
         usb_release_bos_descriptor(udev);
         udev->bos = bos;
+re_enumerate_no_bos:
+        /* LPM state doesn't matter when we're about to destroy the device. */
+        hub_port_logical_disconnect(parent_hub, port1);
         return -ENODEV;
 }
 
diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c
index 210618319f10..5487fe308f01 100644
--- a/drivers/usb/core/port.c
+++ b/drivers/usb/core/port.c
@@ -206,7 +206,7 @@ static int link_peers(struct usb_port *left, struct usb_port *right)
                 else
                         method = "default";
 
-                pr_warn("usb: failed to peer %s and %s by %s (%s:%s) (%s:%s)\n",
+                pr_debug("usb: failed to peer %s and %s by %s (%s:%s) (%s:%s)\n",
                         dev_name(&left->dev), dev_name(&right->dev), method,
                         dev_name(&left->dev),
                         lpeer ? dev_name(&lpeer->dev) : "none",
@@ -265,7 +265,7 @@ static void link_peers_report(struct usb_port *left, struct usb_port *right)
         if (rc == 0) {
                 dev_dbg(&left->dev, "peered to %s\n", dev_name(&right->dev));
         } else {
-                dev_warn(&left->dev, "failed to peer to %s (%d)\n",
+                dev_dbg(&left->dev, "failed to peer to %s (%d)\n",
                                 dev_name(&right->dev), rc);
                 pr_warn_once("usb: port power management may be unreliable\n");
                 usb_port_block_power_off = 1;
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index f5a381945db2..6dc810bce295 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -125,6 +125,9 @@ static const struct usb_device_id usb_quirk_list[] = {
         { USB_DEVICE(0x04f3, 0x016f), .driver_info =
                         USB_QUIRK_DEVICE_QUALIFIER },
 
+        { USB_DEVICE(0x04f3, 0x21b8), .driver_info =
+                        USB_QUIRK_DEVICE_QUALIFIER },
+
         /* Roland SC-8820 */
         { USB_DEVICE(0x0582, 0x0007), .driver_info = USB_QUIRK_RESET_RESUME },
 
@@ -199,6 +202,12 @@ static const struct usb_device_id usb_quirk_list[] = {
         { USB_DEVICE(0x1a0a, 0x0200), .driver_info =
                         USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL },
 
+        /* Blackmagic Design Intensity Shuttle */
+        { USB_DEVICE(0x1edb, 0xbd3b), .driver_info = USB_QUIRK_NO_LPM },
+
+        /* Blackmagic Design UltraStudio SDI */
+        { USB_DEVICE(0x1edb, 0xbd4f), .driver_info = USB_QUIRK_NO_LPM },
+
         { }  /* terminating entry must be last */
 };
 
diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c
index e61d773cf65e..39c1cbf0e75d 100644
--- a/drivers/usb/dwc2/platform.c
+++ b/drivers/usb/dwc2/platform.c
@@ -125,9 +125,11 @@ static int __dwc2_lowlevel_hw_enable(struct dwc2_hsotg *hsotg)
         if (ret)
                 return ret;
 
-        ret = clk_prepare_enable(hsotg->clk);
-        if (ret)
-                return ret;
+        if (hsotg->clk) {
+                ret = clk_prepare_enable(hsotg->clk);
+                if (ret)
+                        return ret;
+        }
 
         if (hsotg->uphy)
                 ret = usb_phy_init(hsotg->uphy);
@@ -175,7 +177,8 @@ static int __dwc2_lowlevel_hw_disable(struct dwc2_hsotg *hsotg)
         if (ret)
                 return ret;
 
-        clk_disable_unprepare(hsotg->clk);
+        if (hsotg->clk)
+                clk_disable_unprepare(hsotg->clk);
 
         ret = regulator_bulk_disable(ARRAY_SIZE(hsotg->supplies),
                                      hsotg->supplies);
@@ -212,14 +215,41 @@ static int dwc2_lowlevel_hw_init(struct dwc2_hsotg *hsotg)
          */
         hsotg->phy = devm_phy_get(hsotg->dev, "usb2-phy");
         if (IS_ERR(hsotg->phy)) {
-                hsotg->phy = NULL;
+                ret = PTR_ERR(hsotg->phy);
+                switch (ret) {
+                case -ENODEV:
+                case -ENOSYS:
+                        hsotg->phy = NULL;
+                        break;
+                case -EPROBE_DEFER:
+                        return ret;
+                default:
+                        dev_err(hsotg->dev, "error getting phy %d\n", ret);
+                        return ret;
+                }
+        }
+
+        if (!hsotg->phy) {
                 hsotg->uphy = devm_usb_get_phy(hsotg->dev, USB_PHY_TYPE_USB2);
-                if (IS_ERR(hsotg->uphy))
-                        hsotg->uphy = NULL;
-                else
-                        hsotg->plat = dev_get_platdata(hsotg->dev);
+                if (IS_ERR(hsotg->uphy)) {
+                        ret = PTR_ERR(hsotg->uphy);
+                        switch (ret) {
+                        case -ENODEV:
+                        case -ENXIO:
+                                hsotg->uphy = NULL;
+                                break;
+                        case -EPROBE_DEFER:
+                                return ret;
+                        default:
+                                dev_err(hsotg->dev, "error getting usb phy %d\n",
+                                        ret);
+                                return ret;
+                        }
+                }
         }
 
+        hsotg->plat = dev_get_platdata(hsotg->dev);
+
         if (hsotg->phy) {
                 /*
                  * If using the generic PHY framework, check if the PHY bus
@@ -229,11 +259,6 @@ static int dwc2_lowlevel_hw_init(struct dwc2_hsotg *hsotg)
                         hsotg->phyif = GUSBCFG_PHYIF8;
         }
 
-        if (!hsotg->phy && !hsotg->uphy && !hsotg->plat) {
-                dev_err(hsotg->dev, "no platform data or transceiver defined\n");
-                return -EPROBE_DEFER;
-        }
-
         /* Clock */
         hsotg->clk = devm_clk_get(hsotg->dev, "otg");
         if (IS_ERR(hsotg->clk)) {
@@ -342,20 +367,6 @@ static int dwc2_driver_probe(struct platform_device *dev)
         if (retval)
                 return retval;
 
-        irq = platform_get_irq(dev, 0);
-        if (irq < 0) {
-                dev_err(&dev->dev, "missing IRQ resource\n");
-                return irq;
-        }
-
-        dev_dbg(hsotg->dev, "registering common handler for irq%d\n",
-                irq);
-        retval = devm_request_irq(hsotg->dev, irq,
-                                  dwc2_handle_common_intr, IRQF_SHARED,
-                                  dev_name(hsotg->dev), hsotg);
-        if (retval)
-                return retval;
-
         res = platform_get_resource(dev, IORESOURCE_MEM, 0);
         hsotg->regs = devm_ioremap_resource(&dev->dev, res);
         if (IS_ERR(hsotg->regs))
@@ -390,6 +401,20 @@ static int dwc2_driver_probe(struct platform_device *dev)
 
         dwc2_set_all_params(hsotg->core_params, -1);
 
+        irq = platform_get_irq(dev, 0);
+        if (irq < 0) {
+                dev_err(&dev->dev, "missing IRQ resource\n");
+                return irq;
+        }
+
+        dev_dbg(hsotg->dev, "registering common handler for irq%d\n",
+                irq);
+        retval = devm_request_irq(hsotg->dev, irq,
+                                  dwc2_handle_common_intr, IRQF_SHARED,
+                                  dev_name(hsotg->dev), hsotg);
+        if (retval)
+                return retval;
+
         retval = dwc2_lowlevel_hw_enable(hsotg);
         if (retval)
                 return retval;
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index e24a01cc98df..a58376fd65fe 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -1078,6 +1078,7 @@ static int __dwc3_gadget_ep_queue(struct dwc3_ep *dep, struct dwc3_request *req)
          * little bit faster.
          */
         if (!usb_endpoint_xfer_isoc(dep->endpoint.desc) &&
+                        !usb_endpoint_xfer_int(dep->endpoint.desc) &&
                         !(dep->flags & DWC3_EP_BUSY)) {
                 ret = __dwc3_gadget_kick_transfer(dep, 0, true);
                 goto out;
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index adc6d52efa46..cf43e9e18368 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -423,7 +423,7 @@ static ssize_t __ffs_ep0_read_events(struct ffs_data *ffs, char __user *buf,
         spin_unlock_irq(&ffs->ev.waitq.lock);
         mutex_unlock(&ffs->mutex);
 
-        return unlikely(__copy_to_user(buf, events, size)) ? -EFAULT : size;
+        return unlikely(copy_to_user(buf, events, size)) ? -EFAULT : size;
 }
 
 static ssize_t ffs_ep0_read(struct file *file, char __user *buf,
@@ -513,7 +513,7 @@ static ssize_t ffs_ep0_read(struct file *file, char __user *buf,
 
                 /* unlocks spinlock */
                 ret = __ffs_ep0_queue_wait(ffs, data, len);
-                if (likely(ret > 0) && unlikely(__copy_to_user(buf, data, len)))
+                if (likely(ret > 0) && unlikely(copy_to_user(buf, data, len)))
                         ret = -EFAULT;
                 goto done_mutex;
 
@@ -3493,7 +3493,7 @@ static char *ffs_prepare_buffer(const char __user *buf, size_t len)
         if (unlikely(!data))
                 return ERR_PTR(-ENOMEM);
 
-        if (unlikely(__copy_from_user(data, buf, len))) {
+        if (unlikely(copy_from_user(data, buf, len))) {
                 kfree(data);
                 return ERR_PTR(-EFAULT);
         }
diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c
index 42acb45e1ab4..898a570319f1 100644
--- a/drivers/usb/gadget/function/f_midi.c
+++ b/drivers/usb/gadget/function/f_midi.c
@@ -370,6 +370,7 @@ static int f_midi_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
                 if (err) {
                         ERROR(midi, "%s queue req: %d\n",
                                     midi->out_ep->name, err);
+                        free_ep_req(midi->out_ep, req);
                 }
         }
 
@@ -545,7 +546,7 @@ static void f_midi_transmit(struct f_midi *midi, struct usb_request *req)
                 }
         }
 
-        if (req->length > 0) {
+        if (req->length > 0 && ep->enabled) {
                 int err;
 
                 err = usb_ep_queue(ep, req, GFP_ATOMIC);
diff --git a/drivers/usb/gadget/function/uvc_configfs.c b/drivers/usb/gadget/function/uvc_configfs.c
index 289ebca316d3..ad8c9b05572d 100644
--- a/drivers/usb/gadget/function/uvc_configfs.c
+++ b/drivers/usb/gadget/function/uvc_configfs.c
@@ -20,7 +20,7 @@
 #define UVC_ATTR(prefix, cname, aname) \
 static struct configfs_attribute prefix##attr_##cname = { \
         .ca_name        = __stringify(aname),                           \
-        .ca_mode        = S_IRUGO,                                      \
+        .ca_mode        = S_IRUGO | S_IWUGO,                            \
         .ca_owner       = THIS_MODULE,                                  \
         .show           = prefix##cname##_show,                         \
         .store          = prefix##cname##_store,                        \
diff --git a/drivers/usb/gadget/udc/pxa27x_udc.c b/drivers/usb/gadget/udc/pxa27x_udc.c
index 670ac0b12f00..001a3b74a993 100644
--- a/drivers/usb/gadget/udc/pxa27x_udc.c
+++ b/drivers/usb/gadget/udc/pxa27x_udc.c
@@ -2536,6 +2536,9 @@ static int pxa_udc_suspend(struct platform_device *_dev, pm_message_t state)
         udc->pullup_resume = udc->pullup_on;
         dplus_pullup(udc, 0);
 
+        if (udc->driver)
+                udc->driver->disconnect(&udc->gadget);
+
         return 0;
 }
 
diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c
index 342ffd140122..8c6e15bd6ff0 100644
--- a/drivers/usb/host/ohci-at91.c
+++ b/drivers/usb/host/ohci-at91.c
@@ -473,6 +473,8 @@ static int ohci_hcd_at91_drv_probe(struct platform_device *pdev)
         if (!pdata)
                 return -ENOMEM;
 
+        pdev->dev.platform_data = pdata;
+
         if (!of_property_read_u32(np, "num-ports", &ports))
                 pdata->ports = ports;
 
@@ -483,6 +485,7 @@ static int ohci_hcd_at91_drv_probe(struct platform_device *pdev)
                  */
                 if (i >= pdata->ports) {
                         pdata->vbus_pin[i] = -EINVAL;
+                        pdata->overcurrent_pin[i] = -EINVAL;
                         continue;
                 }
 
@@ -513,10 +516,8 @@ static int ohci_hcd_at91_drv_probe(struct platform_device *pdev)
         }
 
         at91_for_each_port(i) {
-                if (i >= pdata->ports) {
-                        pdata->overcurrent_pin[i] = -EINVAL;
-                        continue;
-                }
+                if (i >= pdata->ports)
+                        break;
 
                 pdata->overcurrent_pin[i] =
                         of_get_named_gpio_flags(np, "atmel,oc-gpio", i, &flags);
@@ -552,8 +553,6 @@ static int ohci_hcd_at91_drv_probe(struct platform_device *pdev)
                 }
         }
 
-        pdev->dev.platform_data = pdata;
-
         device_init_wakeup(&pdev->dev, 1);
         return usb_hcd_at91_probe(&ohci_at91_hc_driver, pdev);
 }
diff --git a/drivers/usb/host/whci/qset.c b/drivers/usb/host/whci/qset.c
index dc31c425ce01..9f1c0538b211 100644
--- a/drivers/usb/host/whci/qset.c
+++ b/drivers/usb/host/whci/qset.c
@@ -377,6 +377,10 @@ static int qset_fill_page_list(struct whc *whc, struct whc_std *std, gfp_t mem_f
         if (std->pl_virt == NULL)
                 return -ENOMEM;
         std->dma_addr = dma_map_single(whc->wusbhc.dev, std->pl_virt, pl_len, DMA_TO_DEVICE);
+        if (dma_mapping_error(whc->wusbhc.dev, std->dma_addr)) {
+                kfree(std->pl_virt);
+                return -EFAULT;
+        }
 
         for (p = 0; p < std->num_pointers; p++) {
                 std->pl_virt[p].buf_ptr = cpu_to_le64(dma_addr);
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 0230965fb78c..f980c239eded 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -733,8 +733,30 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd,
                 if ((raw_port_status & PORT_RESET) ||
                                 !(raw_port_status & PORT_PE))
                         return 0xffffffff;
-                if (time_after_eq(jiffies,
-                                        bus_state->resume_done[wIndex])) {
+                /* did port event handler already start resume timing? */
+                if (!bus_state->resume_done[wIndex]) {
+                        /* If not, maybe we are in a host initated resume? */
+                        if (test_bit(wIndex, &bus_state->resuming_ports)) {
+                                /* Host initated resume doesn't time the resume
+                                 * signalling using resume_done[].
+                                 * It manually sets RESUME state, sleeps 20ms
+                                 * and sets U0 state. This should probably be
+                                 * changed, but not right now.
+                                 */
+                        } else {
+                                /* port resume was discovered now and here,
+                                 * start resume timing
+                                 */
+                                unsigned long timeout = jiffies +
+                                        msecs_to_jiffies(USB_RESUME_TIMEOUT);
+
+                                set_bit(wIndex, &bus_state->resuming_ports);
+                                bus_state->resume_done[wIndex] = timeout;
+                                mod_timer(&hcd->rh_timer, timeout);
+                        }
+                /* Has resume been signalled for USB_RESUME_TIME yet? */
+                } else if (time_after_eq(jiffies,
+                                         bus_state->resume_done[wIndex])) {
                         int time_left;
 
                         xhci_dbg(xhci, "Resume USB2 port %d\n",
@@ -775,13 +797,26 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd,
                 } else {
                         /*
                          * The resume has been signaling for less than
-                         * 20ms. Report the port status as SUSPEND,
-                         * let the usbcore check port status again
-                         * and clear resume signaling later.
+                         * USB_RESUME_TIME. Report the port status as SUSPEND,
+                         * let the usbcore check port status again and clear
+                         * resume signaling later.
                          */
                         status |= USB_PORT_STAT_SUSPEND;
                 }
         }
+        /*
+         * Clear stale usb2 resume signalling variables in case port changed
+         * state during resume signalling. For example on error
+         */
+        if ((bus_state->resume_done[wIndex] ||
+             test_bit(wIndex, &bus_state->resuming_ports)) &&
+            (raw_port_status & PORT_PLS_MASK) != XDEV_U3 &&
+            (raw_port_status & PORT_PLS_MASK) != XDEV_RESUME) {
+                bus_state->resume_done[wIndex] = 0;
+                clear_bit(wIndex, &bus_state->resuming_ports);
+        }
+
+
         if ((raw_port_status & PORT_PLS_MASK) == XDEV_U0 &&
             (raw_port_status & PORT_POWER)) {
                 if (bus_state->suspended_ports & (1 << wIndex)) {
@@ -1115,6 +1150,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
                                 if ((temp & PORT_PE) == 0)
                                         goto error;
 
+                                set_bit(wIndex, &bus_state->resuming_ports);
                                 xhci_set_link_state(xhci, port_array, wIndex,
                                                         XDEV_RESUME);
                                 spin_unlock_irqrestore(&xhci->lock, flags);
@@ -1122,6 +1158,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue,
                                 spin_lock_irqsave(&xhci->lock, flags);
                                 xhci_set_link_state(xhci, port_array, wIndex,
                                                         XDEV_U0);
+                                clear_bit(wIndex, &bus_state->resuming_ports);
                         }
                         bus_state->port_c_suspend |= 1 << wIndex;
 
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 17f6897acde2..c62109091d12 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -188,10 +188,14 @@ static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev)
                 0xb7, 0x0c, 0x34, 0xac, 0x01, 0xe9, 0xbf, 0x45,
                 0xb7, 0xe6, 0x2b, 0x34, 0xec, 0x93, 0x1e, 0x23,
         };
-        acpi_evaluate_dsm(ACPI_HANDLE(&dev->dev), intel_dsm_uuid, 3, 1, NULL);
+        union acpi_object *obj;
+
+        obj = acpi_evaluate_dsm(ACPI_HANDLE(&dev->dev), intel_dsm_uuid, 3, 1,
+                                NULL);
+        ACPI_FREE(obj);
 }
 #else
-        static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev) { }
+static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev) { }
 #endif /* CONFIG_ACPI */
 
 /* called during probe() after chip reset completes */
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 6c5e8133cf87..eeaa6c6bd540 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -1583,7 +1583,8 @@ static void handle_port_status(struct xhci_hcd *xhci,
                          */
                         bogus_port_status = true;
                         goto cleanup;
-                } else {
+                } else if (!test_bit(faked_port_index,
+                                     &bus_state->resuming_ports)) {
                         xhci_dbg(xhci, "resume HS port %d\n", port_id);
                         bus_state->resume_done[faked_port_index] = jiffies +
                                 msecs_to_jiffies(USB_RESUME_TIMEOUT);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index dfa44d3e8eee..3f912705dcef 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -4778,8 +4778,16 @@ int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev,
         ctrl_ctx->add_flags |= cpu_to_le32(SLOT_FLAG);
         slot_ctx = xhci_get_slot_ctx(xhci, config_cmd->in_ctx);
         slot_ctx->dev_info |= cpu_to_le32(DEV_HUB);
+        /*
+         * refer to section 6.2.2: MTT should be 0 for full speed hub,
+         * but it may be already set to 1 when setup an xHCI virtual
+         * device, so clear it anyway.
+         */
         if (tt->multi)
                 slot_ctx->dev_info |= cpu_to_le32(DEV_MTT);
+        else if (hdev->speed == USB_SPEED_FULL)
+                slot_ctx->dev_info &= cpu_to_le32(~DEV_MTT);
+
         if (xhci->hci_version > 0x95) {
                 xhci_dbg(xhci, "xHCI version %x needs hub "
                                 "TT think time and number of ports\n",
diff --git a/drivers/usb/musb/Kconfig b/drivers/usb/musb/Kconfig
index 1f2037bbeb0d..45c83baf675d 100644
--- a/drivers/usb/musb/Kconfig
+++ b/drivers/usb/musb/Kconfig
@@ -159,7 +159,7 @@ config USB_TI_CPPI_DMA
 
 config USB_TI_CPPI41_DMA
         bool 'TI CPPI 4.1 (AM335x)'
-        depends on ARCH_OMAP
+        depends on ARCH_OMAP && DMADEVICES
         select TI_CPPI41
 
 config USB_TUSB_OMAP_DMA
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 18cfc0a361cb..ee9ff7028b92 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -2017,7 +2017,6 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
         /* We need musb_read/write functions initialized for PM */
         pm_runtime_use_autosuspend(musb->controller);
         pm_runtime_set_autosuspend_delay(musb->controller, 200);
-        pm_runtime_irq_safe(musb->controller);
         pm_runtime_enable(musb->controller);
 
         /* The musb_platform_init() call:
@@ -2095,6 +2094,7 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
 #ifndef CONFIG_MUSB_PIO_ONLY
         if (!musb->ops->dma_init || !musb->ops->dma_exit) {
                 dev_err(dev, "DMA controller not set\n");
+                status = -ENODEV;
                 goto fail2;
         }
         musb_dma_controller_create = musb->ops->dma_init;
@@ -2218,6 +2218,12 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl)
 
         pm_runtime_put(musb->controller);
 
+        /*
+         * For why this is currently needed, see commit 3e43a0725637
+         * ("usb: musb: core: add pm_runtime_irq_safe()")
+         */
+        pm_runtime_irq_safe(musb->controller);
+
         return 0;
 
 fail5:
diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c
index 80eb991c2506..0d19a6d61a71 100644
--- a/drivers/usb/phy/phy-msm-usb.c
+++ b/drivers/usb/phy/phy-msm-usb.c
@@ -1506,7 +1506,6 @@ static int msm_otg_read_dt(struct platform_device *pdev, struct msm_otg *motg)
 {
         struct msm_otg_platform_data *pdata;
         struct extcon_dev *ext_id, *ext_vbus;
-        const struct of_device_id *id;
         struct device_node *node = pdev->dev.of_node;
         struct property *prop;
         int len, ret, words;
@@ -1518,8 +1517,9 @@ static int msm_otg_read_dt(struct platform_device *pdev, struct msm_otg *motg)
 
         motg->pdata = pdata;
 
-        id = of_match_device(msm_otg_dt_match, &pdev->dev);
-        pdata->phy_type = (enum msm_usb_phy_type) id->data;
+        pdata->phy_type = (enum msm_usb_phy_type)of_device_get_match_data(&pdev->dev);
+        if (!pdata->phy_type)
+                return 1;
 
         motg->link_rst = devm_reset_control_get(&pdev->dev, "link");
         if (IS_ERR(motg->link_rst))
diff --git a/drivers/usb/phy/phy-mxs-usb.c b/drivers/usb/phy/phy-mxs-usb.c
index b7536af777ab..c2936dc48ca7 100644
--- a/drivers/usb/phy/phy-mxs-usb.c
+++ b/drivers/usb/phy/phy-mxs-usb.c
@@ -143,12 +143,17 @@ static const struct mxs_phy_data imx6sx_phy_data = {
         .flags = MXS_PHY_DISCONNECT_LINE_WITHOUT_VBUS,
 };
 
+static const struct mxs_phy_data imx6ul_phy_data = {
+        .flags = MXS_PHY_DISCONNECT_LINE_WITHOUT_VBUS,
+};
+
 static const struct of_device_id mxs_phy_dt_ids[] = {
         { .compatible = "fsl,imx6sx-usbphy", .data = &imx6sx_phy_data, },
         { .compatible = "fsl,imx6sl-usbphy", .data = &imx6sl_phy_data, },
         { .compatible = "fsl,imx6q-usbphy", .data = &imx6q_phy_data, },
         { .compatible = "fsl,imx23-usbphy", .data = &imx23_phy_data, },
         { .compatible = "fsl,vf610-usbphy", .data = &vf610_phy_data, },
+        { .compatible = "fsl,imx6ul-usbphy", .data = &imx6ul_phy_data, },
         { /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, mxs_phy_dt_ids);
diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c
index de4f97d84a82..8f7a78e70975 100644
--- a/drivers/usb/renesas_usbhs/mod_gadget.c
+++ b/drivers/usb/renesas_usbhs/mod_gadget.c
@@ -131,7 +131,8 @@ static void __usbhsg_queue_pop(struct usbhsg_uep *uep,
         struct device *dev = usbhsg_gpriv_to_dev(gpriv);
         struct usbhs_priv *priv = usbhsg_gpriv_to_priv(gpriv);
 
-        dev_dbg(dev, "pipe %d : queue pop\n", usbhs_pipe_number(pipe));
+        if (pipe)
+                dev_dbg(dev, "pipe %d : queue pop\n", usbhs_pipe_number(pipe));
 
         ureq->req.status = status;
         spin_unlock(usbhs_priv_to_lock(priv));
@@ -685,7 +686,13 @@ static int usbhsg_ep_dequeue(struct usb_ep *ep, struct usb_request *req)
         struct usbhsg_request *ureq = usbhsg_req_to_ureq(req);
         struct usbhs_pipe *pipe = usbhsg_uep_to_pipe(uep);
 
-        usbhs_pkt_pop(pipe, usbhsg_ureq_to_pkt(ureq));
+        if (pipe)
+                usbhs_pkt_pop(pipe, usbhsg_ureq_to_pkt(ureq));
+
+        /*
+         * To dequeue a request, this driver should call the usbhsg_queue_pop()
+         * even if the pipe is NULL.
+         */
         usbhsg_queue_pop(uep, ureq, -ECONNRESET);
 
         return 0;
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index eac7ccaa3c85..7d4f51a32e66 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -132,7 +132,6 @@ static const struct usb_device_id id_table[] = {
         { USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */
         { USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */
         { USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */
-        { USB_DEVICE(0x10C4, 0xEA80) }, /* Silicon Labs factory default */
         { USB_DEVICE(0x10C4, 0xEA71) }, /* Infinity GPS-MIC-1 Radio Monophone */
         { USB_DEVICE(0x10C4, 0xF001) }, /* Elan Digital Systems USBscope50 */
         { USB_DEVICE(0x10C4, 0xF002) }, /* Elan Digital Systems USBwave12 */
diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c
index 3658662898fc..a204782ae530 100644
--- a/drivers/usb/serial/usb-serial-simple.c
+++ b/drivers/usb/serial/usb-serial-simple.c
@@ -53,6 +53,7 @@ DEVICE(funsoft, FUNSOFT_IDS);
 
 /* Infineon Flashloader driver */
 #define FLASHLOADER_IDS()               \
+        { USB_DEVICE_INTERFACE_CLASS(0x058b, 0x0041, USB_CLASS_CDC_DATA) }, \
         { USB_DEVICE(0x8087, 0x0716) }
 DEVICE(flashloader, FLASHLOADER_IDS);
 
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index e69151664436..5c66d3f7a6d0 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -796,6 +796,10 @@ static int uas_slave_configure(struct scsi_device *sdev)
         if (devinfo->flags & US_FL_NO_REPORT_OPCODES)
                 sdev->no_report_opcodes = 1;
 
+        /* A few buggy USB-ATA bridges don't understand FUA */
+        if (devinfo->flags & US_FL_BROKEN_FUA)
+                sdev->broken_fua = 1;
+
         scsi_change_queue_depth(sdev, devinfo->qdepth - 2);
         return 0;
 }
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 6b2479123de7..7ffe4209067b 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -1987,7 +1987,7 @@ UNUSUAL_DEV(  0x14cd, 0x6600, 0x0201, 0x0201,
                 US_FL_IGNORE_RESIDUE ),
 
 /* Reported by Michael Büsch <m@bues.ch> */
-UNUSUAL_DEV(  0x152d, 0x0567, 0x0114, 0x0114,
+UNUSUAL_DEV(  0x152d, 0x0567, 0x0114, 0x0116,
                 "JMicron",
                 "USB to ATA/ATAPI Bridge",
                 USB_SC_DEVICE, USB_PR_DEVICE, NULL,
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index c85ea530085f..ccc113e83d88 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -132,7 +132,7 @@ UNUSUAL_DEV(0x152d, 0x0567, 0x0000, 0x9999,
                 "JMicron",
                 "JMS567",
                 USB_SC_DEVICE, USB_PR_DEVICE, NULL,
-                US_FL_NO_REPORT_OPCODES),
+                US_FL_BROKEN_FUA | US_FL_NO_REPORT_OPCODES),
 
 /* Reported-by: Hans de Goede <hdegoede@redhat.com> */
 UNUSUAL_DEV(0x2109, 0x0711, 0x0000, 0x9999,
diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index da6e2ce77495..850d86ca685b 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -31,21 +31,6 @@ menuconfig VFIO
 
           If you don't know what to do here, say N.
 
-menuconfig VFIO_NOIOMMU
-        bool "VFIO No-IOMMU support"
-        depends on VFIO
-        help
-          VFIO is built on the ability to isolate devices using the IOMMU.
-          Only with an IOMMU can userspace access to DMA capable devices be
-          considered secure.  VFIO No-IOMMU mode enables IOMMU groups for
-          devices without IOMMU backing for the purpose of re-using the VFIO
-          infrastructure in a non-secure mode.  Use of this mode will result
-          in an unsupportable kernel and will therefore taint the kernel.
-          Device assignment to virtual machines is also not possible with
-          this mode since there is no IOMMU to provide DMA translation.
-
-          If you don't know what to do here, say N.
-
 source "drivers/vfio/pci/Kconfig"
 source "drivers/vfio/platform/Kconfig"
 source "virt/lib/Kconfig"
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 32b88bd2c82c..56bf6dbb93db 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -940,13 +940,13 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
         if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
                 return -EINVAL;
 
-        group = vfio_iommu_group_get(&pdev->dev);
+        group = iommu_group_get(&pdev->dev);
         if (!group)
                 return -EINVAL;
 
         vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
         if (!vdev) {
-                vfio_iommu_group_put(group, &pdev->dev);
+                iommu_group_put(group);
                 return -ENOMEM;
         }
 
@@ -957,7 +957,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
         ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev);
         if (ret) {
-                vfio_iommu_group_put(group, &pdev->dev);
+                iommu_group_put(group);
                 kfree(vdev);
                 return ret;
         }
@@ -993,7 +993,7 @@ static void vfio_pci_remove(struct pci_dev *pdev)
         if (!vdev)
                 return;
 
-        vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev);
+        iommu_group_put(pdev->dev.iommu_group);
         kfree(vdev);
 
         if (vfio_pci_is_vga(pdev)) {
@@ -1035,7 +1035,7 @@ static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
         return PCI_ERS_RESULT_CAN_RECOVER;
 }
 
-static struct pci_error_handlers vfio_err_handlers = {
+static const struct pci_error_handlers vfio_err_handlers = {
         .error_detected = vfio_pci_aer_err_detected,
 };
 
diff --git a/drivers/vfio/platform/vfio_platform.c b/drivers/vfio/platform/vfio_platform.c
index f1625dcfbb23..b1cc3a768784 100644
--- a/drivers/vfio/platform/vfio_platform.c
+++ b/drivers/vfio/platform/vfio_platform.c
@@ -92,7 +92,6 @@ static struct platform_driver vfio_platform_driver = {
         .remove         = vfio_platform_remove,
         .driver = {
                 .name   = "vfio-platform",
-                .owner  = THIS_MODULE,
         },
 };
 
diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c
index a1c50d630792..418cdd9ba3f4 100644
--- a/drivers/vfio/platform/vfio_platform_common.c
+++ b/drivers/vfio/platform/vfio_platform_common.c
@@ -51,13 +51,10 @@ static vfio_platform_reset_fn_t vfio_platform_lookup_reset(const char *compat,
 
 static void vfio_platform_get_reset(struct vfio_platform_device *vdev)
 {
-        char modname[256];
-
         vdev->reset = vfio_platform_lookup_reset(vdev->compat,
                                                 &vdev->reset_module);
         if (!vdev->reset) {
-                snprintf(modname, 256, "vfio-reset:%s", vdev->compat);
-                request_module(modname);
+                request_module("vfio-reset:%s", vdev->compat);
                 vdev->reset = vfio_platform_lookup_reset(vdev->compat,
                                                          &vdev->reset_module);
         }
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index de632da2e22f..6070b793cbcb 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -62,7 +62,6 @@ struct vfio_container {
         struct rw_semaphore             group_lock;
         struct vfio_iommu_driver        *iommu_driver;
         void                            *iommu_data;
-        bool                            noiommu;
 };
 
 struct vfio_unbound_dev {
@@ -85,7 +84,6 @@ struct vfio_group {
         struct list_head                unbound_list;
         struct mutex                    unbound_lock;
         atomic_t                        opened;
-        bool                            noiommu;
 };
 
 struct vfio_device {
@@ -97,147 +95,6 @@ struct vfio_device {
         void                            *device_data;
 };
 
-#ifdef CONFIG_VFIO_NOIOMMU
-static bool noiommu __read_mostly;
-module_param_named(enable_unsafe_noiommu_support,
-                   noiommu, bool, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode.  This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel.  If you do not know what this is for, step away. (default: false)");
-#endif
-
-/*
- * vfio_iommu_group_{get,put} are only intended for VFIO bus driver probe
- * and remove functions, any use cases other than acquiring the first
- * reference for the purpose of calling vfio_add_group_dev() or removing
- * that symmetric reference after vfio_del_group_dev() should use the raw
- * iommu_group_{get,put} functions.  In particular, vfio_iommu_group_put()
- * removes the device from the dummy group and cannot be nested.
- */
-struct iommu_group *vfio_iommu_group_get(struct device *dev)
-{
-        struct iommu_group *group;
-        int __maybe_unused ret;
-
-        group = iommu_group_get(dev);
-
-#ifdef CONFIG_VFIO_NOIOMMU
-        /*
-         * With noiommu enabled, an IOMMU group will be created for a device
-         * that doesn't already have one and doesn't have an iommu_ops on their
-         * bus.  We use iommu_present() again in the main code to detect these
-         * fake groups.
-         */
-        if (group || !noiommu || iommu_present(dev->bus))
-                return group;
-
-        group = iommu_group_alloc();
-        if (IS_ERR(group))
-                return NULL;
-
-        iommu_group_set_name(group, "vfio-noiommu");
-        ret = iommu_group_add_device(group, dev);
-        iommu_group_put(group);
-        if (ret)
-                return NULL;
-
-        /*
-         * Where to taint?  At this point we've added an IOMMU group for a
-         * device that is not backed by iommu_ops, therefore any iommu_
-         * callback using iommu_ops can legitimately Oops.  So, while we may
-         * be about to give a DMA capable device to a user without IOMMU
-         * protection, which is clearly taint-worthy, let's go ahead and do
-         * it here.
-         */
-        add_taint(TAINT_USER, LOCKDEP_STILL_OK);
-        dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n");
-#endif
-
-        return group;
-}
-EXPORT_SYMBOL_GPL(vfio_iommu_group_get);
-
-void vfio_iommu_group_put(struct iommu_group *group, struct device *dev)
-{
-#ifdef CONFIG_VFIO_NOIOMMU
-        if (!iommu_present(dev->bus))
-                iommu_group_remove_device(dev);
-#endif
-
-        iommu_group_put(group);
-}
-EXPORT_SYMBOL_GPL(vfio_iommu_group_put);
-
-#ifdef CONFIG_VFIO_NOIOMMU
-static void *vfio_noiommu_open(unsigned long arg)
-{
-        if (arg != VFIO_NOIOMMU_IOMMU)
-                return ERR_PTR(-EINVAL);
-        if (!capable(CAP_SYS_RAWIO))
-                return ERR_PTR(-EPERM);
-
-        return NULL;
-}
-
-static void vfio_noiommu_release(void *iommu_data)
-{
-}
-
-static long vfio_noiommu_ioctl(void *iommu_data,
-                               unsigned int cmd, unsigned long arg)
-{
-        if (cmd == VFIO_CHECK_EXTENSION)
-                return arg == VFIO_NOIOMMU_IOMMU ? 1 : 0;
-
-        return -ENOTTY;
-}
-
-static int vfio_iommu_present(struct device *dev, void *unused)
-{
-        return iommu_present(dev->bus) ? 1 : 0;
-}
-
-static int vfio_noiommu_attach_group(void *iommu_data,
-                                     struct iommu_group *iommu_group)
-{
-        return iommu_group_for_each_dev(iommu_group, NULL,
-                                        vfio_iommu_present) ? -EINVAL : 0;
-}
-
-static void vfio_noiommu_detach_group(void *iommu_data,
-                                      struct iommu_group *iommu_group)
-{
-}
-
-static struct vfio_iommu_driver_ops vfio_noiommu_ops = {
-        .name = "vfio-noiommu",
-        .owner = THIS_MODULE,
-        .open = vfio_noiommu_open,
-        .release = vfio_noiommu_release,
-        .ioctl = vfio_noiommu_ioctl,
-        .attach_group = vfio_noiommu_attach_group,
-        .detach_group = vfio_noiommu_detach_group,
-};
-
-static struct vfio_iommu_driver vfio_noiommu_driver = {
-        .ops = &vfio_noiommu_ops,
-};
-
-/*
- * Wrap IOMMU drivers, the noiommu driver is the one and only driver for
- * noiommu groups (and thus containers) and not available for normal groups.
- */
-#define vfio_for_each_iommu_driver(con, pos)                            \
-        for (pos = con->noiommu ? &vfio_noiommu_driver :                \
-             list_first_entry(&vfio.iommu_drivers_list,                 \
-                              struct vfio_iommu_driver, vfio_next);     \
-             (con->noiommu ? pos != NULL :                              \
-                        &pos->vfio_next != &vfio.iommu_drivers_list);   \
-              pos = con->noiommu ? NULL : list_next_entry(pos, vfio_next))
-#else
-#define vfio_for_each_iommu_driver(con, pos)                            \
-        list_for_each_entry(pos, &vfio.iommu_drivers_list, vfio_next)
-#endif
-
-
 /**
  * IOMMU driver registration
  */
@@ -342,8 +199,7 @@ static void vfio_group_unlock_and_free(struct vfio_group *group)
 /**
  * Group objects - create, release, get, put, search
  */
-static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
-                                            bool noiommu)
+static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group)
 {
         struct vfio_group *group, *tmp;
         struct device *dev;
@@ -361,7 +217,6 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
         atomic_set(&group->container_users, 0);
         atomic_set(&group->opened, 0);
         group->iommu_group = iommu_group;
-        group->noiommu = noiommu;
 
         group->nb.notifier_call = vfio_iommu_group_notifier;
 
@@ -397,8 +252,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
 
         dev = device_create(vfio.class, NULL,
                             MKDEV(MAJOR(vfio.group_devt), minor),
-                            group, "%s%d", noiommu ? "noiommu-" : "",
-                            iommu_group_id(iommu_group));
+                            group, "%d", iommu_group_id(iommu_group));
         if (IS_ERR(dev)) {
                 vfio_free_group_minor(minor);
                 vfio_group_unlock_and_free(group);
@@ -682,7 +536,7 @@ static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev)
                 return 0;
 
         /* TODO Prevent device auto probing */
-        WARN("Device %s added to live group %d!\n", dev_name(dev),
+        WARN(1, "Device %s added to live group %d!\n", dev_name(dev),
              iommu_group_id(group->iommu_group));
 
         return 0;
@@ -786,8 +640,7 @@ int vfio_add_group_dev(struct device *dev,
 
         group = vfio_group_get_from_iommu(iommu_group);
         if (!group) {
-                group = vfio_create_group(iommu_group,
-                                          !iommu_present(dev->bus));
+                group = vfio_create_group(iommu_group);
                 if (IS_ERR(group)) {
                         iommu_group_put(iommu_group);
                         return PTR_ERR(group);
@@ -999,7 +852,8 @@ static long vfio_ioctl_check_extension(struct vfio_container *container,
                  */
                 if (!driver) {
                         mutex_lock(&vfio.iommu_drivers_lock);
-                        vfio_for_each_iommu_driver(container, driver) {
+                        list_for_each_entry(driver, &vfio.iommu_drivers_list,
+                                            vfio_next) {
                                 if (!try_module_get(driver->ops->owner))
                                         continue;
 
@@ -1068,7 +922,7 @@ static long vfio_ioctl_set_iommu(struct vfio_container *container,
         }
 
         mutex_lock(&vfio.iommu_drivers_lock);
-        vfio_for_each_iommu_driver(container, driver) {
+        list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) {
                 void *data;
 
                 if (!try_module_get(driver->ops->owner))
@@ -1333,9 +1187,6 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd)
         if (atomic_read(&group->container_users))
                 return -EINVAL;
 
-        if (group->noiommu && !capable(CAP_SYS_RAWIO))
-                return -EPERM;
-
         f = fdget(container_fd);
         if (!f.file)
                 return -EBADF;
@@ -1351,13 +1202,6 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd)
 
         down_write(&container->group_lock);
 
-        /* Real groups and fake groups cannot mix */
-        if (!list_empty(&container->group_list) &&
-            container->noiommu != group->noiommu) {
-                ret = -EPERM;
-                goto unlock_out;
-        }
-
         driver = container->iommu_driver;
         if (driver) {
                 ret = driver->ops->attach_group(container->iommu_data,
@@ -1367,7 +1211,6 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd)
         }
 
         group->container = container;
-        container->noiommu = group->noiommu;
         list_add(&group->container_next, &container->group_list);
 
         /* Get a reference on the container and mark a user within the group */
@@ -1398,9 +1241,6 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
             !group->container->iommu_driver || !vfio_group_viable(group))
                 return -EINVAL;
 
-        if (group->noiommu && !capable(CAP_SYS_RAWIO))
-                return -EPERM;
-
         device = vfio_device_get_from_name(group, buf);
         if (!device)
                 return -ENODEV;
@@ -1443,10 +1283,6 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
 
         fd_install(ret, filep);
 
-        if (group->noiommu)
-                dev_warn(device->dev, "vfio-noiommu device opened by user "
-                         "(%s:%d)\n", current->comm, task_pid_nr(current));
-
         return ret;
 }
 
@@ -1535,11 +1371,6 @@ static int vfio_group_fops_open(struct inode *inode, struct file *filep)
         if (!group)
                 return -ENODEV;
 
-        if (group->noiommu && !capable(CAP_SYS_RAWIO)) {
-                vfio_group_put(group);
-                return -EPERM;
-        }
-
         /* Do we need multiple instances of the group open?  Seems not. */
         opened = atomic_cmpxchg(&group->opened, 0, 1);
         if (opened) {
@@ -1702,11 +1533,6 @@ struct vfio_group *vfio_group_get_external_user(struct file *filep)
         if (!atomic_inc_not_zero(&group->container_users))
                 return ERR_PTR(-EINVAL);
 
-        if (group->noiommu) {
-                atomic_dec(&group->container_users);
-                return ERR_PTR(-EPERM);
-        }
-
         if (!group->container->iommu_driver ||
                         !vfio_group_viable(group)) {
                 atomic_dec(&group->container_users);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index eec2f11809ff..ad2146a9ab2d 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -819,7 +819,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp)
                 BUILD_BUG_ON(__alignof__ *vq->used > VRING_USED_ALIGN_SIZE);
                 if ((a.avail_user_addr & (VRING_AVAIL_ALIGN_SIZE - 1)) ||
                     (a.used_user_addr & (VRING_USED_ALIGN_SIZE - 1)) ||
-                    (a.log_guest_addr & (sizeof(u64) - 1))) {
+                    (a.log_guest_addr & (VRING_USED_ALIGN_SIZE - 1))) {
                         r = -EINVAL;
                         break;
                 }
@@ -1369,7 +1369,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
         /* Grab the next descriptor number they're advertising, and increment
          * the index we've seen. */
         if (unlikely(__get_user(ring_head,
-                                &vq->avail->ring[last_avail_idx % vq->num]))) {
+                                &vq->avail->ring[last_avail_idx & (vq->num - 1)]))) {
                 vq_err(vq, "Failed to read head: idx %d address %p\n",
                        last_avail_idx,
                        &vq->avail->ring[last_avail_idx % vq->num]);
@@ -1489,7 +1489,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
         u16 old, new;
         int start;
 
-        start = vq->last_used_idx % vq->num;
+        start = vq->last_used_idx & (vq->num - 1);
         used = vq->used->ring + start;
         if (count == 1) {
                 if (__put_user(heads[0].id, &used->id)) {
@@ -1531,7 +1531,7 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
 {
         int start, n, r;
 
-        start = vq->last_used_idx % vq->num;
+        start = vq->last_used_idx & (vq->num - 1);
         n = vq->num - start;
         if (n < count) {
                 r = __vhost_add_used_n(vq, heads, n);
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index b1877d73fa56..7062bb0975a5 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -412,6 +412,7 @@ static int virtio_init(void)
 static void __exit virtio_exit(void)
 {
         bus_unregister(&virtio_bus);
+        ida_destroy(&virtio_index_ida);
 }
 core_initcall(virtio_init);
 module_exit(virtio_exit);
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 096b857e7b75..ee663c458b20 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -80,6 +80,12 @@ struct vring_virtqueue {
         /* Last used index we've seen. */
         u16 last_used_idx;
 
+        /* Last written value to avail->flags */
+        u16 avail_flags_shadow;
+
+        /* Last written value to avail->idx in guest byte order */
+        u16 avail_idx_shadow;
+
         /* How to notify other side. FIXME: commonalize hcalls! */
         bool (*notify)(struct virtqueue *vq);
 
@@ -109,7 +115,7 @@ static struct vring_desc *alloc_indirect(struct virtqueue *_vq,
          * otherwise virt_to_phys will give us bogus addresses in the
          * virtqueue.
          */
-        gfp &= ~(__GFP_HIGHMEM | __GFP_HIGH);
+        gfp &= ~__GFP_HIGHMEM;
 
         desc = kmalloc(total_sg * sizeof(struct vring_desc), gfp);
         if (!desc)
@@ -235,13 +241,14 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 
         /* Put entry in available array (but don't update avail->idx until they
          * do sync). */
-        avail = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) & (vq->vring.num - 1);
+        avail = vq->avail_idx_shadow & (vq->vring.num - 1);
         vq->vring.avail->ring[avail] = cpu_to_virtio16(_vq->vdev, head);
 
         /* Descriptors and available array need to be set before we expose the
          * new available array entries. */
         virtio_wmb(vq->weak_barriers);
-        vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) + 1);
+        vq->avail_idx_shadow++;
+        vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
         vq->num_added++;
 
         pr_debug("Added buffer head %i to %p\n", head, vq);
@@ -354,8 +361,8 @@ bool virtqueue_kick_prepare(struct virtqueue *_vq)
          * event. */
         virtio_mb(vq->weak_barriers);
 
-        old = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - vq->num_added;
-        new = virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx);
+        old = vq->avail_idx_shadow - vq->num_added;
+        new = vq->avail_idx_shadow;
         vq->num_added = 0;
 
 #ifdef DEBUG
@@ -510,7 +517,7 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
         /* If we expect an interrupt for the next entry, tell host
          * by writing event index and flush out the write before
          * the read in the next get_buf call. */
-        if (!(vq->vring.avail->flags & cpu_to_virtio16(_vq->vdev, VRING_AVAIL_F_NO_INTERRUPT))) {
+        if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
                 vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, vq->last_used_idx);
                 virtio_mb(vq->weak_barriers);
         }
@@ -537,7 +544,11 @@ void virtqueue_disable_cb(struct virtqueue *_vq)
 {
         struct vring_virtqueue *vq = to_vvq(_vq);
 
-        vq->vring.avail->flags |= cpu_to_virtio16(_vq->vdev, VRING_AVAIL_F_NO_INTERRUPT);
+        if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
+                vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
+                vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+        }
+
 }
 EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
 
@@ -565,7 +576,10 @@ unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
         /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
          * either clear the flags bit or point the event index at the next
          * entry. Always do both to keep code simple. */
-        vq->vring.avail->flags &= cpu_to_virtio16(_vq->vdev, ~VRING_AVAIL_F_NO_INTERRUPT);
+        if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
+                vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
+                vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+        }
         vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
         END_USE(vq);
         return last_used_idx;
@@ -633,9 +647,12 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
         /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
          * either clear the flags bit or point the event index at the next
          * entry. Always do both to keep code simple. */
-        vq->vring.avail->flags &= cpu_to_virtio16(_vq->vdev, ~VRING_AVAIL_F_NO_INTERRUPT);
+        if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
+                vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
+                vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
+        }
         /* TODO: tune this threshold */
-        bufs = (u16)(virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - vq->last_used_idx) * 3 / 4;
+        bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;
         vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs);
         virtio_mb(vq->weak_barriers);
         if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->vring.used->idx) - vq->last_used_idx) > bufs)) {
@@ -670,7 +687,8 @@ void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
                 /* detach_buf clears data, so grab it now. */
                 buf = vq->data[i];
                 detach_buf(vq, i);
-                vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, virtio16_to_cpu(_vq->vdev, vq->vring.avail->idx) - 1);
+                vq->avail_idx_shadow--;
+                vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
                 END_USE(vq);
                 return buf;
         }
@@ -735,6 +753,8 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
         vq->weak_barriers = weak_barriers;
         vq->broken = false;
         vq->last_used_idx = 0;
+        vq->avail_flags_shadow = 0;
+        vq->avail_idx_shadow = 0;
         vq->num_added = 0;
         list_add_tail(&vq->vq.list, &vdev->vqs);
 #ifdef DEBUG
@@ -746,8 +766,10 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
         vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
 
         /* No callback?  Tell other side not to bother us. */
-        if (!callback)
-                vq->vring.avail->flags |= cpu_to_virtio16(vdev, VRING_AVAIL_F_NO_INTERRUPT);
+        if (!callback) {
+                vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
+                vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
+        }
 
         /* Put everything in free lists. */
         vq->free_head = 0;
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 7a8a6c6952e9..1c427beffadd 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -446,7 +446,7 @@ config MAX63XX_WATCHDOG
 
 config IMX2_WDT
         tristate "IMX2+ Watchdog"
-        depends on ARCH_MXC
+        depends on ARCH_MXC || ARCH_LAYERSCAPE
         select REGMAP_MMIO
         select WATCHDOG_CORE
         help
diff --git a/drivers/watchdog/mtk_wdt.c b/drivers/watchdog/mtk_wdt.c
index 6ad9df948711..b751f43d76ed 100644
--- a/drivers/watchdog/mtk_wdt.c
+++ b/drivers/watchdog/mtk_wdt.c
@@ -123,6 +123,7 @@ static int mtk_wdt_stop(struct watchdog_device *wdt_dev)
 
         reg = readl(wdt_base + WDT_MODE);
         reg &= ~WDT_MODE_EN;
+        reg |= WDT_MODE_KEY;
         iowrite32(reg, wdt_base + WDT_MODE);
 
         return 0;
diff --git a/drivers/watchdog/omap_wdt.c b/drivers/watchdog/omap_wdt.c
index d96bee017fd3..6f17c935a6cf 100644
--- a/drivers/watchdog/omap_wdt.c
+++ b/drivers/watchdog/omap_wdt.c
@@ -205,7 +205,7 @@ static int omap_wdt_set_timeout(struct watchdog_device *wdog,
 
 static unsigned int omap_wdt_get_timeleft(struct watchdog_device *wdog)
 {
-        struct omap_wdt_dev *wdev = watchdog_get_drvdata(wdog);
+        struct omap_wdt_dev *wdev = to_omap_wdt_dev(wdog);
         void __iomem *base = wdev->base;
         u32 value;
 
diff --git a/drivers/watchdog/pnx4008_wdt.c b/drivers/watchdog/pnx4008_wdt.c
index 4224b3ec83a5..313cd1c6fda0 100644
--- a/drivers/watchdog/pnx4008_wdt.c
+++ b/drivers/watchdog/pnx4008_wdt.c
@@ -80,7 +80,7 @@ static unsigned int heartbeat = DEFAULT_HEARTBEAT;
 
 static DEFINE_SPINLOCK(io_lock);
 static void __iomem     *wdt_base;
-struct clk              *wdt_clk;
+static struct clk       *wdt_clk;
 
 static int pnx4008_wdt_start(struct watchdog_device *wdd)
 {
@@ -161,7 +161,7 @@ static int pnx4008_wdt_probe(struct platform_device *pdev)
         if (IS_ERR(wdt_clk))
                 return PTR_ERR(wdt_clk);
 
-        ret = clk_enable(wdt_clk);
+        ret = clk_prepare_enable(wdt_clk);
         if (ret)
                 return ret;
 
@@ -184,7 +184,7 @@ static int pnx4008_wdt_probe(struct platform_device *pdev)
         return 0;
 
 disable_clk:
-        clk_disable(wdt_clk);
+        clk_disable_unprepare(wdt_clk);
         return ret;
 }
 
@@ -192,7 +192,7 @@ static int pnx4008_wdt_remove(struct platform_device *pdev)
 {
         watchdog_unregister_device(&pnx4008_wdd);
 
-        clk_disable(wdt_clk);
+        clk_disable_unprepare(wdt_clk);
 
         return 0;
 }
diff --git a/drivers/watchdog/tegra_wdt.c b/drivers/watchdog/tegra_wdt.c
index 7f97cdd53f29..9ec57608da82 100644
--- a/drivers/watchdog/tegra_wdt.c
+++ b/drivers/watchdog/tegra_wdt.c
@@ -140,8 +140,10 @@ static int tegra_wdt_set_timeout(struct watchdog_device *wdd,
 {
         wdd->timeout = timeout;
 
-        if (watchdog_active(wdd))
+        if (watchdog_active(wdd)) {
+                tegra_wdt_stop(wdd);
                 return tegra_wdt_start(wdd);
+        }
 
         return 0;
 }
diff --git a/drivers/watchdog/w83977f_wdt.c b/drivers/watchdog/w83977f_wdt.c
index 91bf55a20024..20e2bba10400 100644
--- a/drivers/watchdog/w83977f_wdt.c
+++ b/drivers/watchdog/w83977f_wdt.c
@@ -224,7 +224,7 @@ static int wdt_keepalive(void)
 
 static int wdt_set_timeout(int t)
 {
-        int tmrval;
+        unsigned int tmrval;
 
         /*
          * Convert seconds to watchdog counter time units, rounding up.
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 849500e4e14d..524c22146429 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -39,6 +39,7 @@
 #include <asm/irq.h>
 #include <asm/idle.h>
 #include <asm/io_apic.h>
+#include <asm/i8259.h>
 #include <asm/xen/pci.h>
 #endif
 #include <asm/sync_bitops.h>
@@ -420,7 +421,7 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi)
                 return xen_allocate_irq_dynamic();
 
         /* Legacy IRQ descriptors are already allocated by the arch. */
-        if (gsi < NR_IRQS_LEGACY)
+        if (gsi < nr_legacy_irqs())
                 irq = gsi;
         else
                 irq = irq_alloc_desc_at(gsi, -1);
@@ -446,7 +447,7 @@ static void xen_free_irq(unsigned irq)
         kfree(info);
 
         /* Legacy IRQ descriptors are managed by the arch. */
-        if (irq < NR_IRQS_LEGACY)
+        if (irq < nr_legacy_irqs())
                 return;
 
         irq_free_desc(irq);
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
index 00f40f051d95..38272ad24551 100644
--- a/drivers/xen/evtchn.c
+++ b/drivers/xen/evtchn.c
@@ -49,6 +49,8 @@
 #include <linux/init.h>
 #include <linux/mutex.h>
 #include <linux/cpu.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
 
 #include <xen/xen.h>
 #include <xen/events.h>
@@ -58,10 +60,10 @@
 struct per_user_data {
         struct mutex bind_mutex; /* serialize bind/unbind operations */
         struct rb_root evtchns;
+        unsigned int nr_evtchns;
 
         /* Notification ring, accessed via /dev/xen/evtchn. */
-#define EVTCHN_RING_SIZE     (PAGE_SIZE / sizeof(evtchn_port_t))
-#define EVTCHN_RING_MASK(_i) ((_i)&(EVTCHN_RING_SIZE-1))
+        unsigned int ring_size;
         evtchn_port_t *ring;
         unsigned int ring_cons, ring_prod, ring_overflow;
         struct mutex ring_cons_mutex; /* protect against concurrent readers */
@@ -80,10 +82,41 @@ struct user_evtchn {
         bool enabled;
 };
 
+static evtchn_port_t *evtchn_alloc_ring(unsigned int size)
+{
+        evtchn_port_t *ring;
+        size_t s = size * sizeof(*ring);
+
+        ring = kmalloc(s, GFP_KERNEL);
+        if (!ring)
+                ring = vmalloc(s);
+
+        return ring;
+}
+
+static void evtchn_free_ring(evtchn_port_t *ring)
+{
+        kvfree(ring);
+}
+
+static unsigned int evtchn_ring_offset(struct per_user_data *u,
+                                       unsigned int idx)
+{
+        return idx & (u->ring_size - 1);
+}
+
+static evtchn_port_t *evtchn_ring_entry(struct per_user_data *u,
+                                        unsigned int idx)
+{
+        return u->ring + evtchn_ring_offset(u, idx);
+}
+
 static int add_evtchn(struct per_user_data *u, struct user_evtchn *evtchn)
 {
         struct rb_node **new = &(u->evtchns.rb_node), *parent = NULL;
 
+        u->nr_evtchns++;
+
         while (*new) {
                 struct user_evtchn *this;
 
@@ -107,6 +140,7 @@ static int add_evtchn(struct per_user_data *u, struct user_evtchn *evtchn)
 
 static void del_evtchn(struct per_user_data *u, struct user_evtchn *evtchn)
 {
+        u->nr_evtchns--;
         rb_erase(&evtchn->node, &u->evtchns);
         kfree(evtchn);
 }
@@ -144,8 +178,8 @@ static irqreturn_t evtchn_interrupt(int irq, void *data)
 
         spin_lock(&u->ring_prod_lock);
 
-        if ((u->ring_prod - u->ring_cons) < EVTCHN_RING_SIZE) {
-                u->ring[EVTCHN_RING_MASK(u->ring_prod)] = evtchn->port;
+        if ((u->ring_prod - u->ring_cons) < u->ring_size) {
+                *evtchn_ring_entry(u, u->ring_prod) = evtchn->port;
                 wmb(); /* Ensure ring contents visible */
                 if (u->ring_cons == u->ring_prod++) {
                         wake_up_interruptible(&u->evtchn_wait);
@@ -200,10 +234,10 @@ static ssize_t evtchn_read(struct file *file, char __user *buf,
         }
 
         /* Byte lengths of two chunks. Chunk split (if any) is at ring wrap. */
-        if (((c ^ p) & EVTCHN_RING_SIZE) != 0) {
-                bytes1 = (EVTCHN_RING_SIZE - EVTCHN_RING_MASK(c)) *
+        if (((c ^ p) & u->ring_size) != 0) {
+                bytes1 = (u->ring_size - evtchn_ring_offset(u, c)) *
                         sizeof(evtchn_port_t);
-                bytes2 = EVTCHN_RING_MASK(p) * sizeof(evtchn_port_t);
+                bytes2 = evtchn_ring_offset(u, p) * sizeof(evtchn_port_t);
         } else {
                 bytes1 = (p - c) * sizeof(evtchn_port_t);
                 bytes2 = 0;
@@ -219,7 +253,7 @@ static ssize_t evtchn_read(struct file *file, char __user *buf,
 
         rc = -EFAULT;
         rmb(); /* Ensure that we see the port before we copy it. */
-        if (copy_to_user(buf, &u->ring[EVTCHN_RING_MASK(c)], bytes1) ||
+        if (copy_to_user(buf, evtchn_ring_entry(u, c), bytes1) ||
             ((bytes2 != 0) &&
              copy_to_user(&buf[bytes1], &u->ring[0], bytes2)))
                 goto unlock_out;
@@ -278,6 +312,66 @@ static ssize_t evtchn_write(struct file *file, const char __user *buf,
         return rc;
 }
 
+static int evtchn_resize_ring(struct per_user_data *u)
+{
+        unsigned int new_size;
+        evtchn_port_t *new_ring, *old_ring;
+        unsigned int p, c;
+
+        /*
+         * Ensure the ring is large enough to capture all possible
+         * events. i.e., one free slot for each bound event.
+         */
+        if (u->nr_evtchns <= u->ring_size)
+                return 0;
+
+        if (u->ring_size == 0)
+                new_size = 64;
+        else
+                new_size = 2 * u->ring_size;
+
+        new_ring = evtchn_alloc_ring(new_size);
+        if (!new_ring)
+                return -ENOMEM;
+
+        old_ring = u->ring;
+
+        /*
+         * Access to the ring contents is serialized by either the
+         * prod /or/ cons lock so take both when resizing.
+         */
+        mutex_lock(&u->ring_cons_mutex);
+        spin_lock_irq(&u->ring_prod_lock);
+
+        /*
+         * Copy the old ring contents to the new ring.
+         *
+         * If the ring contents crosses the end of the current ring,
+         * it needs to be copied in two chunks.
+         *
+         * +---------+    +------------------+
+         * |34567  12| -> |       1234567    |
+         * +-----p-c-+    +------------------+
+         */
+        p = evtchn_ring_offset(u, u->ring_prod);
+        c = evtchn_ring_offset(u, u->ring_cons);
+        if (p < c) {
+                memcpy(new_ring + c, u->ring + c, (u->ring_size - c) * sizeof(*u->ring));
+                memcpy(new_ring + u->ring_size, u->ring, p * sizeof(*u->ring));
+        } else
+                memcpy(new_ring + c, u->ring + c, (p - c) * sizeof(*u->ring));
+
+        u->ring = new_ring;
+        u->ring_size = new_size;
+
+        spin_unlock_irq(&u->ring_prod_lock);
+        mutex_unlock(&u->ring_cons_mutex);
+
+        evtchn_free_ring(old_ring);
+
+        return 0;
+}
+
 static int evtchn_bind_to_user(struct per_user_data *u, int port)
 {
         struct user_evtchn *evtchn;
@@ -305,6 +399,10 @@ static int evtchn_bind_to_user(struct per_user_data *u, int port)
         if (rc < 0)
                 goto err;
 
+        rc = evtchn_resize_ring(u);
+        if (rc < 0)
+                goto err;
+
         rc = bind_evtchn_to_irqhandler(port, evtchn_interrupt, 0,
                                        u->name, evtchn);
         if (rc < 0)
@@ -503,13 +601,6 @@ static int evtchn_open(struct inode *inode, struct file *filp)
 
         init_waitqueue_head(&u->evtchn_wait);
 
-        u->ring = (evtchn_port_t *)__get_free_page(GFP_KERNEL);
-        if (u->ring == NULL) {
-                kfree(u->name);
-                kfree(u);
-                return -ENOMEM;
-        }
-
         mutex_init(&u->bind_mutex);
         mutex_init(&u->ring_cons_mutex);
         spin_lock_init(&u->ring_prod_lock);
@@ -532,7 +623,7 @@ static int evtchn_release(struct inode *inode, struct file *filp)
                 evtchn_unbind_from_user(u, evtchn);
         }
 
-        free_page((unsigned long)u->ring);
+        evtchn_free_ring(u->ring);
         kfree(u->name);
         kfree(u);
 
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 2ea0b3b2a91d..1be5dd048622 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -804,7 +804,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 
         vma->vm_ops = &gntdev_vmops;
 
-        vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
+        vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP | VM_IO;
 
         if (use_ptemod)
                 vma->vm_flags |= VM_DONTCOPY;
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 699941e90667..511078586fa1 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -451,9 +451,9 @@ void v9fs_evict_inode(struct inode *inode)
 {
         struct v9fs_inode *v9inode = V9FS_I(inode);
 
-        truncate_inode_pages_final(inode->i_mapping);
+        truncate_inode_pages_final(&inode->i_data);
         clear_inode(inode);
-        filemap_fdatawrite(inode->i_mapping);
+        filemap_fdatawrite(&inode->i_data);
 
         v9fs_cache_inode_put_cookie(inode);
         /* clunk the fid stashed in writeback_fid */
diff --git a/fs/block_dev.c b/fs/block_dev.c
index c25639e907bd..44d4a1e9244e 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1523,11 +1523,14 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
                 WARN_ON_ONCE(bdev->bd_holders);
                 sync_blockdev(bdev);
                 kill_bdev(bdev);
+
+                bdev_write_inode(bdev);
                 /*
-                 * ->release can cause the queue to disappear, so flush all
-                 * dirty data before.
+                 * Detaching bdev inode from its wb in __destroy_inode()
+                 * is too late: the queue which embeds its bdi (along with
+                 * root wb) can be gone as soon as we put_disk() below.
                  */
-                bdev_write_inode(bdev);
+                inode_detach_wb(bdev->bd_inode);
         }
         if (bdev->bd_contains == bdev) {
                 if (disk->fops->release)
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 6dcdb2ec9211..d453d62ab0c6 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -355,7 +355,7 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
 
         index = srcu_read_lock(&fs_info->subvol_srcu);
 
-        root = btrfs_read_fs_root_no_name(fs_info, &root_key);
+        root = btrfs_get_fs_root(fs_info, &root_key, false);
         if (IS_ERR(root)) {
                 srcu_read_unlock(&fs_info->subvol_srcu, index);
                 ret = PTR_ERR(root);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 8c58191249cc..35489e7129a7 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3416,6 +3416,7 @@ int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans,
 struct btrfs_block_group_cache *btrfs_lookup_block_group(
                                                  struct btrfs_fs_info *info,
                                                  u64 bytenr);
+void btrfs_get_block_group(struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
 int get_block_group_index(struct btrfs_block_group_cache *cache);
 struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
@@ -3479,6 +3480,9 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
                            struct btrfs_root *root, u64 bytes_used,
                            u64 type, u64 chunk_objectid, u64 chunk_offset,
                            u64 size);
+struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
+                                struct btrfs_fs_info *fs_info,
+                                const u64 chunk_offset);
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
                              struct btrfs_root *root, u64 group_start,
                              struct extent_map *em);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index acf3ed11cfb6..4b89680a1923 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -124,7 +124,7 @@ static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits)
         return (cache->flags & bits) == bits;
 }
 
-static void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
+void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
 {
         atomic_inc(&cache->count);
 }
@@ -5915,19 +5915,6 @@ static int update_block_group(struct btrfs_trans_handle *trans,
                         set_extent_dirty(info->pinned_extents,
                                          bytenr, bytenr + num_bytes - 1,
                                          GFP_NOFS | __GFP_NOFAIL);
-                        /*
-                         * No longer have used bytes in this block group, queue
-                         * it for deletion.
-                         */
-                        if (old_val == 0) {
-                                spin_lock(&info->unused_bgs_lock);
-                                if (list_empty(&cache->bg_list)) {
-                                        btrfs_get_block_group(cache);
-                                        list_add_tail(&cache->bg_list,
-                                                      &info->unused_bgs);
-                                }
-                                spin_unlock(&info->unused_bgs_lock);
-                        }
                 }
 
                 spin_lock(&trans->transaction->dirty_bgs_lock);
@@ -5939,6 +5926,22 @@ static int update_block_group(struct btrfs_trans_handle *trans,
                 }
                 spin_unlock(&trans->transaction->dirty_bgs_lock);
 
+                /*
+                 * No longer have used bytes in this block group, queue it for
+                 * deletion. We do this after adding the block group to the
+                 * dirty list to avoid races between cleaner kthread and space
+                 * cache writeout.
+                 */
+                if (!alloc && old_val == 0) {
+                        spin_lock(&info->unused_bgs_lock);
+                        if (list_empty(&cache->bg_list)) {
+                                btrfs_get_block_group(cache);
+                                list_add_tail(&cache->bg_list,
+                                              &info->unused_bgs);
+                        }
+                        spin_unlock(&info->unused_bgs_lock);
+                }
+
                 btrfs_put_block_group(cache);
                 total -= num_bytes;
                 bytenr += num_bytes;
@@ -8105,21 +8108,47 @@ reada:
 }
 
 /*
- * TODO: Modify related function to add related node/leaf to dirty_extent_root,
- * for later qgroup accounting.
- *
- * Current, this function does nothing.
+ * These may not be seen by the usual inc/dec ref code so we have to
+ * add them here.
  */
+static int record_one_subtree_extent(struct btrfs_trans_handle *trans,
+                                     struct btrfs_root *root, u64 bytenr,
+                                     u64 num_bytes)
+{
+        struct btrfs_qgroup_extent_record *qrecord;
+        struct btrfs_delayed_ref_root *delayed_refs;
+
+        qrecord = kmalloc(sizeof(*qrecord), GFP_NOFS);
+        if (!qrecord)
+                return -ENOMEM;
+
+        qrecord->bytenr = bytenr;
+        qrecord->num_bytes = num_bytes;
+        qrecord->old_roots = NULL;
+
+        delayed_refs = &trans->transaction->delayed_refs;
+        spin_lock(&delayed_refs->lock);
+        if (btrfs_qgroup_insert_dirty_extent(delayed_refs, qrecord))
+                kfree(qrecord);
+        spin_unlock(&delayed_refs->lock);
+
+        return 0;
+}
+
 static int account_leaf_items(struct btrfs_trans_handle *trans,
                               struct btrfs_root *root,
                               struct extent_buffer *eb)
 {
         int nr = btrfs_header_nritems(eb);
-        int i, extent_type;
+        int i, extent_type, ret;
         struct btrfs_key key;
         struct btrfs_file_extent_item *fi;
         u64 bytenr, num_bytes;
 
+        /* We can be called directly from walk_up_proc() */
+        if (!root->fs_info->quota_enabled)
+                return 0;
+
         for (i = 0; i < nr; i++) {
                 btrfs_item_key_to_cpu(eb, &key, i);
 
@@ -8138,6 +8167,10 @@ static int account_leaf_items(struct btrfs_trans_handle *trans,
                         continue;
 
                 num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi);
+
+                ret = record_one_subtree_extent(trans, root, bytenr, num_bytes);
+                if (ret)
+                        return ret;
         }
         return 0;
 }
@@ -8206,8 +8239,6 @@ static int adjust_slots_upwards(struct btrfs_root *root,
 
 /*
  * root_eb is the subtree root and is locked before this function is called.
- * TODO: Modify this function to mark all (including complete shared node)
- * to dirty_extent_root to allow it get accounted in qgroup.
  */
 static int account_shared_subtree(struct btrfs_trans_handle *trans,
                                   struct btrfs_root *root,
@@ -8285,6 +8316,11 @@ walk_down:
                         btrfs_tree_read_lock(eb);
                         btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
                         path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
+
+                        ret = record_one_subtree_extent(trans, root, child_bytenr,
+                                                        root->nodesize);
+                        if (ret)
+                                goto out;
                 }
 
                 if (level == 0) {
@@ -10256,6 +10292,47 @@ out:
         return ret;
 }
 
+struct btrfs_trans_handle *
+btrfs_start_trans_remove_block_group(struct btrfs_fs_info *fs_info,
+                                     const u64 chunk_offset)
+{
+        struct extent_map_tree *em_tree = &fs_info->mapping_tree.map_tree;
+        struct extent_map *em;
+        struct map_lookup *map;
+        unsigned int num_items;
+
+        read_lock(&em_tree->lock);
+        em = lookup_extent_mapping(em_tree, chunk_offset, 1);
+        read_unlock(&em_tree->lock);
+        ASSERT(em && em->start == chunk_offset);
+
+        /*
+         * We need to reserve 3 + N units from the metadata space info in order
+         * to remove a block group (done at btrfs_remove_chunk() and at
+         * btrfs_remove_block_group()), which are used for:
+         *
+         * 1 unit for adding the free space inode's orphan (located in the tree
+         * of tree roots).
+         * 1 unit for deleting the block group item (located in the extent
+         * tree).
+         * 1 unit for deleting the free space item (located in tree of tree
+         * roots).
+         * N units for deleting N device extent items corresponding to each
+         * stripe (located in the device tree).
+         *
+         * In order to remove a block group we also need to reserve units in the
+         * system space info in order to update the chunk tree (update one or
+         * more device items and remove one chunk item), but this is done at
+         * btrfs_remove_chunk() through a call to check_system_chunk().
+         */
+        map = (struct map_lookup *)em->bdev;
+        num_items = 3 + map->num_stripes;
+        free_extent_map(em);
+
+        return btrfs_start_transaction_fallback_global_rsv(fs_info->extent_root,
+                                                           num_items, 1);
+}
+
 /*
  * Process the unused_bgs list and remove any that don't have any allocated
  * space inside of them.
@@ -10322,8 +10399,8 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
                  * Want to do this before we do anything else so we can recover
                  * properly if we fail to join the transaction.
                  */
-                /* 1 for btrfs_orphan_reserve_metadata() */
-                trans = btrfs_start_transaction(root, 1);
+                trans = btrfs_start_trans_remove_block_group(fs_info,
+                                                     block_group->key.objectid);
                 if (IS_ERR(trans)) {
                         btrfs_dec_block_group_ro(root, block_group);
                         ret = PTR_ERR(trans);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 977e715f0bf2..72e73461c064 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1882,8 +1882,13 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
         struct btrfs_log_ctx ctx;
         int ret = 0;
         bool full_sync = 0;
-        const u64 len = end - start + 1;
+        u64 len;
 
+        /*
+         * The range length can be represented by u64, we have to do the typecasts
+         * to avoid signed overflow if it's [0, LLONG_MAX] eg. from fsync()
+         */
+        len = (u64)end - (u64)start + 1;
         trace_btrfs_sync_file(file, datasync);
 
         /*
@@ -2071,8 +2076,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
                         }
                 }
                 if (!full_sync) {
-                        ret = btrfs_wait_ordered_range(inode, start,
-                                                       end - start + 1);
+                        ret = btrfs_wait_ordered_range(inode, start, len);
                         if (ret) {
                                 btrfs_end_transaction(trans, root);
                                 goto out;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 994490d5fa64..a70c5790f8f5 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4046,9 +4046,7 @@ int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
  */
 static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir)
 {
-        struct btrfs_trans_handle *trans;
         struct btrfs_root *root = BTRFS_I(dir)->root;
-        int ret;
 
         /*
          * 1 for the possible orphan item
@@ -4057,27 +4055,7 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir)
          * 1 for the inode ref
          * 1 for the inode
          */
-        trans = btrfs_start_transaction(root, 5);
-        if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
-                return trans;
-
-        if (PTR_ERR(trans) == -ENOSPC) {
-                u64 num_bytes = btrfs_calc_trans_metadata_size(root, 5);
-
-                trans = btrfs_start_transaction(root, 0);
-                if (IS_ERR(trans))
-                        return trans;
-                ret = btrfs_cond_migrate_bytes(root->fs_info,
-                                               &root->fs_info->trans_block_rsv,
-                                               num_bytes, 5);
-                if (ret) {
-                        btrfs_end_transaction(trans, root);
-                        return ERR_PTR(ret);
-                }
-                trans->block_rsv = &root->fs_info->trans_block_rsv;
-                trans->bytes_reserved = num_bytes;
-        }
-        return trans;
+        return btrfs_start_transaction_fallback_global_rsv(root, 5, 5);
 }
 
 static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 93e12c18ffd7..5279fdae7142 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -993,9 +993,10 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
         mutex_lock(&fs_info->qgroup_ioctl_lock);
         if (!fs_info->quota_root)
                 goto out;
-        spin_lock(&fs_info->qgroup_lock);
         fs_info->quota_enabled = 0;
         fs_info->pending_quota_state = 0;
+        btrfs_qgroup_wait_for_completion(fs_info);
+        spin_lock(&fs_info->qgroup_lock);
         quota_root = fs_info->quota_root;
         fs_info->quota_root = NULL;
         fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON;
@@ -1461,6 +1462,8 @@ struct btrfs_qgroup_extent_record
         struct btrfs_qgroup_extent_record *entry;
         u64 bytenr = record->bytenr;
 
+        assert_spin_locked(&delayed_refs->lock);
+
         while (*p) {
                 parent_node = *p;
                 entry = rb_entry(parent_node, struct btrfs_qgroup_extent_record,
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 2907a77fb1f6..b091d94ceef6 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3432,7 +3432,9 @@ out:
 static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
                                           struct btrfs_device *scrub_dev,
                                           u64 chunk_offset, u64 length,
-                                          u64 dev_offset, int is_dev_replace)
+                                          u64 dev_offset,
+                                          struct btrfs_block_group_cache *cache,
+                                          int is_dev_replace)
 {
         struct btrfs_mapping_tree *map_tree =
                 &sctx->dev_root->fs_info->mapping_tree;
@@ -3445,8 +3447,18 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
         em = lookup_extent_mapping(&map_tree->map_tree, chunk_offset, 1);
         read_unlock(&map_tree->map_tree.lock);
 
-        if (!em)
-                return -EINVAL;
+        if (!em) {
+                /*
+                 * Might have been an unused block group deleted by the cleaner
+                 * kthread or relocation.
+                 */
+                spin_lock(&cache->lock);
+                if (!cache->removed)
+                        ret = -EINVAL;
+                spin_unlock(&cache->lock);
+
+                return ret;
+        }
 
         map = (struct map_lookup *)em->bdev;
         if (em->start != chunk_offset)
@@ -3483,6 +3495,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
         u64 length;
         u64 chunk_offset;
         int ret = 0;
+        int ro_set;
         int slot;
         struct extent_buffer *l;
         struct btrfs_key key;
@@ -3568,7 +3581,21 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
                 scrub_pause_on(fs_info);
                 ret = btrfs_inc_block_group_ro(root, cache);
                 scrub_pause_off(fs_info);
-                if (ret) {
+
+                if (ret == 0) {
+                        ro_set = 1;
+                } else if (ret == -ENOSPC) {
+                        /*
+                         * btrfs_inc_block_group_ro return -ENOSPC when it
+                         * failed in creating new chunk for metadata.
+                         * It is not a problem for scrub/replace, because
+                         * metadata are always cowed, and our scrub paused
+                         * commit_transactions.
+                         */
+                        ro_set = 0;
+                } else {
+                        btrfs_warn(fs_info, "failed setting block group ro, ret=%d\n",
+                                   ret);
                         btrfs_put_block_group(cache);
                         break;
                 }
@@ -3577,7 +3604,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
                 dev_replace->cursor_left = found_key.offset;
                 dev_replace->item_needs_writeback = 1;
                 ret = scrub_chunk(sctx, scrub_dev, chunk_offset, length,
-                                  found_key.offset, is_dev_replace);
+                                  found_key.offset, cache, is_dev_replace);
 
                 /*
                  * flush, submit all pending read and write bios, afterwards
@@ -3611,7 +3638,30 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 
                 scrub_pause_off(fs_info);
 
-                btrfs_dec_block_group_ro(root, cache);
+                if (ro_set)
+                        btrfs_dec_block_group_ro(root, cache);
+
+                /*
+                 * We might have prevented the cleaner kthread from deleting
+                 * this block group if it was already unused because we raced
+                 * and set it to RO mode first. So add it back to the unused
+                 * list, otherwise it might not ever be deleted unless a manual
+                 * balance is triggered or it becomes used and unused again.
+                 */
+                spin_lock(&cache->lock);
+                if (!cache->removed && !cache->ro && cache->reserved == 0 &&
+                    btrfs_block_group_used(&cache->item) == 0) {
+                        spin_unlock(&cache->lock);
+                        spin_lock(&fs_info->unused_bgs_lock);
+                        if (list_empty(&cache->bg_list)) {
+                                btrfs_get_block_group(cache);
+                                list_add_tail(&cache->bg_list,
+                                              &fs_info->unused_bgs);
+                        }
+                        spin_unlock(&fs_info->unused_bgs_lock);
+                } else {
+                        spin_unlock(&cache->lock);
+                }
 
                 btrfs_put_block_group(cache);
                 if (ret)
diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c
index c8c3d70c31ff..8b72b005bfb9 100644
--- a/fs/btrfs/tests/free-space-tests.c
+++ b/fs/btrfs/tests/free-space-tests.c
@@ -898,8 +898,10 @@ int btrfs_test_free_space_cache(void)
         }
 
         root = btrfs_alloc_dummy_root();
-        if (!root)
+        if (IS_ERR(root)) {
+                ret = PTR_ERR(root);
                 goto out;
+        }
 
         root->fs_info = btrfs_alloc_dummy_fs_info();
         if (!root->fs_info)
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 418c6a2ad7d8..3367a3c6f214 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -592,6 +592,38 @@ struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
         return start_transaction(root, num_items, TRANS_START,
                                  BTRFS_RESERVE_FLUSH_ALL);
 }
+struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
+                                        struct btrfs_root *root,
+                                        unsigned int num_items,
+                                        int min_factor)
+{
+        struct btrfs_trans_handle *trans;
+        u64 num_bytes;
+        int ret;
+
+        trans = btrfs_start_transaction(root, num_items);
+        if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
+                return trans;
+
+        trans = btrfs_start_transaction(root, 0);
+        if (IS_ERR(trans))
+                return trans;
+
+        num_bytes = btrfs_calc_trans_metadata_size(root, num_items);
+        ret = btrfs_cond_migrate_bytes(root->fs_info,
+                                       &root->fs_info->trans_block_rsv,
+                                       num_bytes,
+                                       min_factor);
+        if (ret) {
+                btrfs_end_transaction(trans, root);
+                return ERR_PTR(ret);
+        }
+
+        trans->block_rsv = &root->fs_info->trans_block_rsv;
+        trans->bytes_reserved = num_bytes;
+
+        return trans;
+}
 
 struct btrfs_trans_handle *btrfs_start_transaction_lflush(
                                         struct btrfs_root *root,
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index b05b2f64d913..0da21ca9b3fb 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -185,6 +185,10 @@ int btrfs_end_transaction(struct btrfs_trans_handle *trans,
                           struct btrfs_root *root);
 struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
                                                    unsigned int num_items);
+struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
+                                        struct btrfs_root *root,
+                                        unsigned int num_items,
+                                        int min_factor);
 struct btrfs_trans_handle *btrfs_start_transaction_lflush(
                                         struct btrfs_root *root,
                                         unsigned int num_items);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a6df8fdc1312..456452206609 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1973,8 +1973,7 @@ void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
         if (srcdev->writeable) {
                 fs_devices->rw_devices--;
                 /* zero out the old super if it is writable */
-                btrfs_scratch_superblocks(srcdev->bdev,
-                                        rcu_str_deref(srcdev->name));
+                btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str);
         }
 
         if (srcdev->bdev)
@@ -2024,8 +2023,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
         btrfs_sysfs_rm_device_link(fs_info->fs_devices, tgtdev);
 
         if (tgtdev->bdev) {
-                btrfs_scratch_superblocks(tgtdev->bdev,
-                                        rcu_str_deref(tgtdev->name));
+                btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str);
                 fs_info->fs_devices->open_devices--;
         }
         fs_info->fs_devices->num_devices--;
@@ -2853,7 +2851,8 @@ static int btrfs_relocate_chunk(struct btrfs_root *root, u64 chunk_offset)
         if (ret)
                 return ret;
 
-        trans = btrfs_start_transaction(root, 0);
+        trans = btrfs_start_trans_remove_block_group(root->fs_info,
+                                                     chunk_offset);
         if (IS_ERR(trans)) {
                 ret = PTR_ERR(trans);
                 btrfs_std_error(root->fs_info, ret, NULL);
@@ -3123,7 +3122,7 @@ static int chunk_profiles_filter(u64 chunk_type,
         return 1;
 }
 
-static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
+static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
                               struct btrfs_balance_args *bargs)
 {
         struct btrfs_block_group_cache *cache;
@@ -3156,7 +3155,7 @@ static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
         return ret;
 }
 
-static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info,
+static int chunk_usage_filter(struct btrfs_fs_info *fs_info,
                 u64 chunk_offset, struct btrfs_balance_args *bargs)
 {
         struct btrfs_block_group_cache *cache;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index ec5712372732..d5c84f6b1353 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -382,7 +382,7 @@ struct map_lookup {
 #define BTRFS_BALANCE_ARGS_LIMIT        (1ULL << 5)
 #define BTRFS_BALANCE_ARGS_LIMIT_RANGE  (1ULL << 6)
 #define BTRFS_BALANCE_ARGS_STRIPES_RANGE (1ULL << 7)
-#define BTRFS_BALANCE_ARGS_USAGE_RANGE  (1ULL << 8)
+#define BTRFS_BALANCE_ARGS_USAGE_RANGE  (1ULL << 10)
 
 #define BTRFS_BALANCE_ARGS_MASK                 \
         (BTRFS_BALANCE_ARGS_PROFILES |          \
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 6b66dd5d1540..a329f5ba35aa 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1831,11 +1831,11 @@ cifs_invalidate_mapping(struct inode *inode)
  * @word: long word containing the bit lock
  */
 static int
-cifs_wait_bit_killable(struct wait_bit_key *key)
+cifs_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
-        if (fatal_signal_pending(current))
-                return -ERESTARTSYS;
         freezable_schedule_unsafe();
+        if (signal_pending_state(mode, current))
+                return -ERESTARTSYS;
         return 0;
 }
 
diff --git a/fs/direct-io.c b/fs/direct-io.c
index cb5337d8c273..602e8441bc0f 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1169,6 +1169,16 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
                 }
         }
 
+        /* Once we sampled i_size check for reads beyond EOF */
+        dio->i_size = i_size_read(inode);
+        if (iov_iter_rw(iter) == READ && offset >= dio->i_size) {
+                if (dio->flags & DIO_LOCKING)
+                        mutex_unlock(&inode->i_mutex);
+                kmem_cache_free(dio_cache, dio);
+                retval = 0;
+                goto out;
+        }
+
         /*
          * For file extending writes updating i_size before data writeouts
          * complete can expose uninitialized blocks in dumb filesystems.
@@ -1222,7 +1232,6 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
         sdio.next_block_for_io = -1;
 
         dio->iocb = iocb;
-        dio->i_size = i_size_read(inode);
 
         spin_lock_init(&dio->bio_lock);
         dio->refcount = 1;
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 87e9d796cf7d..3a37bd3f9637 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -421,7 +421,7 @@ static void lowcomms_write_space(struct sock *sk)
 
         if (test_and_clear_bit(CF_APP_LIMITED, &con->flags)) {
                 con->sock->sk->sk_write_pending--;
-                clear_bit(SOCK_ASYNC_NOSPACE, &con->sock->flags);
+                clear_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags);
         }
 
         if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags))
@@ -1448,7 +1448,7 @@ static void send_to_sock(struct connection *con)
                                               msg_flags);
                         if (ret == -EAGAIN || ret == 0) {
                                 if (ret == -EAGAIN &&
-                                    test_bit(SOCK_ASYNC_NOSPACE, &con->sock->flags) &&
+                                    test_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags) &&
                                     !test_and_set_bit(CF_APP_LIMITED, &con->flags)) {
                                         /* Notify TCP that we're limited by the
                                          * application window size.
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 73c64daa0f55..60f03b78914e 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -592,10 +592,7 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
                         }
                         unlock_page(page);
                 }
-                if (PageDirty(page) || PageWriteback(page))
-                        *uptodate = true;
-                else
-                        *uptodate = PageUptodate(page);
+                *uptodate = PageUptodate(page);
                 EXOFS_DBGMSG2("index=0x%lx uptodate=%d\n", index, *uptodate);
                 return page;
         } else {
diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c
index af06830bfc00..1a0835073663 100644
--- a/fs/ext4/crypto.c
+++ b/fs/ext4/crypto.c
@@ -389,7 +389,7 @@ int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex)
         struct ext4_crypto_ctx  *ctx;
         struct page             *ciphertext_page = NULL;
         struct bio              *bio;
-        ext4_lblk_t             lblk = ex->ee_block;
+        ext4_lblk_t             lblk = le32_to_cpu(ex->ee_block);
         ext4_fsblk_t            pblk = ext4_ext_pblock(ex);
         unsigned int            len = ext4_ext_get_actual_len(ex);
         int                     ret, err = 0;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 750063f7a50c..cc7ca4e87144 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -26,6 +26,7 @@
 #include <linux/seqlock.h>
 #include <linux/mutex.h>
 #include <linux/timer.h>
+#include <linux/version.h>
 #include <linux/wait.h>
 #include <linux/blockgroup_lock.h>
 #include <linux/percpu_counter.h>
@@ -727,19 +728,55 @@ struct move_extent {
         <= (EXT4_GOOD_OLD_INODE_SIZE +                  \
             (einode)->i_extra_isize))                   \
 
+/*
+ * We use an encoding that preserves the times for extra epoch "00":
+ *
+ * extra  msb of                         adjust for signed
+ * epoch  32-bit                         32-bit tv_sec to
+ * bits   time    decoded 64-bit tv_sec  64-bit tv_sec      valid time range
+ * 0 0    1    -0x80000000..-0x00000001  0x000000000 1901-12-13..1969-12-31
+ * 0 0    0    0x000000000..0x07fffffff  0x000000000 1970-01-01..2038-01-19
+ * 0 1    1    0x080000000..0x0ffffffff  0x100000000 2038-01-19..2106-02-07
+ * 0 1    0    0x100000000..0x17fffffff  0x100000000 2106-02-07..2174-02-25
+ * 1 0    1    0x180000000..0x1ffffffff  0x200000000 2174-02-25..2242-03-16
+ * 1 0    0    0x200000000..0x27fffffff  0x200000000 2242-03-16..2310-04-04
+ * 1 1    1    0x280000000..0x2ffffffff  0x300000000 2310-04-04..2378-04-22
+ * 1 1    0    0x300000000..0x37fffffff  0x300000000 2378-04-22..2446-05-10
+ *
+ * Note that previous versions of the kernel on 64-bit systems would
+ * incorrectly use extra epoch bits 1,1 for dates between 1901 and
+ * 1970.  e2fsck will correct this, assuming that it is run on the
+ * affected filesystem before 2242.
+ */
+
 static inline __le32 ext4_encode_extra_time(struct timespec *time)
 {
-       return cpu_to_le32((sizeof(time->tv_sec) > 4 ?
-                           (time->tv_sec >> 32) & EXT4_EPOCH_MASK : 0) |
-                          ((time->tv_nsec << EXT4_EPOCH_BITS) & EXT4_NSEC_MASK));
+        u32 extra = sizeof(time->tv_sec) > 4 ?
+                ((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK : 0;
+        return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS));
 }
 
 static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
 {
-       if (sizeof(time->tv_sec) > 4)
-               time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK)
-                               << 32;
-       time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
+        if (unlikely(sizeof(time->tv_sec) > 4 &&
+                        (extra & cpu_to_le32(EXT4_EPOCH_MASK)))) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(4,20,0)
+                /* Handle legacy encoding of pre-1970 dates with epoch
+                 * bits 1,1.  We assume that by kernel version 4.20,
+                 * everyone will have run fsck over the affected
+                 * filesystems to correct the problem.  (This
+                 * backwards compatibility may be removed before this
+                 * time, at the discretion of the ext4 developers.)
+                 */
+                u64 extra_bits = le32_to_cpu(extra) & EXT4_EPOCH_MASK;
+                if (extra_bits == 3 && ((time->tv_sec) & 0x80000000) != 0)
+                        extra_bits = 0;
+                time->tv_sec += extra_bits << 32;
+#else
+                time->tv_sec += (u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK) << 32;
+#endif
+        }
+        time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS;
 }
 
 #define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode)                          \
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index abe2401ce405..e8e7af62ac95 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -52,7 +52,7 @@ static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cook
         /* Symlink is encrypted */
         sd = (struct ext4_encrypted_symlink_data *)caddr;
         cstr.name = sd->encrypted_path;
-        cstr.len  = le32_to_cpu(sd->len);
+        cstr.len  = le16_to_cpu(sd->len);
         if ((cstr.len +
              sizeof(struct ext4_encrypted_symlink_data) - 1) >
             max_size) {
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 1b57c72f4a00..1420a3c614af 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -358,7 +358,7 @@ static int name##_open(struct inode *inode, struct file *file) \
         return single_open(file, ext4_seq_##name##_show, PDE_DATA(inode)); \
 } \
 \
-const struct file_operations ext4_seq_##name##_fops = { \
+static const struct file_operations ext4_seq_##name##_fops = { \
         .owner          = THIS_MODULE, \
         .open           = name##_open, \
         .read           = seq_read, \
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index eae2c11268bc..8e3ee1936c7e 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -549,6 +549,8 @@ static int cuse_channel_release(struct inode *inode, struct file *file)
                 unregister_chrdev_region(cc->cdev->dev, 1);
                 cdev_del(cc->cdev);
         }
+        /* Base reference is now owned by "fud" */
+        fuse_conn_put(&cc->fc);
 
         rc = fuse_dev_release(inode, file);     /* puts the base reference */
 
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index e0faf8f2c868..570ca4053c80 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1049,6 +1049,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
                 tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes);
                 flush_dcache_page(page);
 
+                iov_iter_advance(ii, tmp);
                 if (!tmp) {
                         unlock_page(page);
                         page_cache_release(page);
@@ -1061,7 +1062,6 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
                 req->page_descs[req->num_pages].length = tmp;
                 req->num_pages++;
 
-                iov_iter_advance(ii, tmp);
                 count += tmp;
                 pos += tmp;
                 offset += tmp;
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 89463eee6791..ca181e81c765 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1009,7 +1009,8 @@ out:
 }
 
 /* Fast check whether buffer is already attached to the required transaction */
-static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh)
+static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh,
+                                                        bool undo)
 {
         struct journal_head *jh;
         bool ret = false;
@@ -1036,6 +1037,9 @@ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh)
         jh = READ_ONCE(bh->b_private);
         if (!jh)
                 goto out;
+        /* For undo access buffer must have data copied */
+        if (undo && !jh->b_committed_data)
+                goto out;
         if (jh->b_transaction != handle->h_transaction &&
             jh->b_next_transaction != handle->h_transaction)
                 goto out;
@@ -1073,7 +1077,7 @@ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh)
         struct journal_head *jh;
         int rc;
 
-        if (jbd2_write_access_granted(handle, bh))
+        if (jbd2_write_access_granted(handle, bh, false))
                 return 0;
 
         jh = jbd2_journal_add_journal_head(bh);
@@ -1210,7 +1214,7 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
         char *committed_data = NULL;
 
         JBUFFER_TRACE(jh, "entry");
-        if (jbd2_write_access_granted(handle, bh))
+        if (jbd2_write_access_granted(handle, bh, true))
                 return 0;
 
         jh = jbd2_journal_add_journal_head(bh);
@@ -2152,6 +2156,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
 
                 if (!buffer_dirty(bh)) {
                         /* bdflush has written it.  We can drop it now */
+                        __jbd2_journal_remove_checkpoint(jh);
                         goto zap_buffer;
                 }
 
@@ -2181,6 +2186,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
                                 /* The orphan record's transaction has
                                  * committed.  We can cleanse this buffer */
                                 clear_buffer_jbddirty(bh);
+                                __jbd2_journal_remove_checkpoint(jh);
                                 goto zap_buffer;
                         }
                 }
diff --git a/fs/namei.c b/fs/namei.c
index d84d7c7515fc..0c3974cd3ecd 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1996,7 +1996,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
         nd->last_type = LAST_ROOT; /* if there are only slashes... */
         nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
         nd->depth = 0;
-        nd->total_link_count = 0;
         if (flags & LOOKUP_ROOT) {
                 struct dentry *root = nd->root.dentry;
                 struct inode *inode = root->d_inode;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 326d9e10d833..c7e8b87da5b2 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -75,11 +75,11 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
  * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks
  * @word: long word containing the bit lock
  */
-int nfs_wait_bit_killable(struct wait_bit_key *key)
+int nfs_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
-        if (fatal_signal_pending(current))
-                return -ERESTARTSYS;
         freezable_schedule_unsafe();
+        if (signal_pending_state(mode, current))
+                return -ERESTARTSYS;
         return 0;
 }
 EXPORT_SYMBOL_GPL(nfs_wait_bit_killable);
@@ -618,7 +618,10 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
                 nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC);
                 nfs_vmtruncate(inode, attr->ia_size);
         }
-        nfs_update_inode(inode, fattr);
+        if (fattr->valid)
+                nfs_update_inode(inode, fattr);
+        else
+                NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR;
         spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL_GPL(nfs_setattr_update_inode);
@@ -1824,7 +1827,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
                 if ((long)fattr->gencount - (long)nfsi->attr_gencount > 0)
                         nfsi->attr_gencount = fattr->gencount;
         }
-        invalid &= ~NFS_INO_INVALID_ATTR;
+
+        /* Don't declare attrcache up to date if there were no attrs! */
+        if (fattr->valid != 0)
+                invalid &= ~NFS_INO_INVALID_ATTR;
+
         /* Don't invalidate the data if we were to blame */
         if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
                                 || S_ISLNK(inode->i_mode)))
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 56cfde26fb9c..9dea85f7f918 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -379,7 +379,7 @@ extern int nfs_drop_inode(struct inode *);
 extern void nfs_clear_inode(struct inode *);
 extern void nfs_evict_inode(struct inode *);
 void nfs_zap_acl_cache(struct inode *inode);
-extern int nfs_wait_bit_killable(struct wait_bit_key *key);
+extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode);
 
 /* super.c */
 extern const struct super_operations nfs_sops;
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 3e92a3cde15d..6b1ce9825430 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -14,7 +14,7 @@
 #include "pnfs.h"
 #include "internal.h"
 
-#define NFSDBG_FACILITY NFSDBG_PNFS
+#define NFSDBG_FACILITY NFSDBG_PROC
 
 static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file,
                                 fmode_t fmode)
@@ -284,6 +284,7 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
                 .dst_fh = NFS_FH(dst_inode),
                 .src_offset = src_offset,
                 .dst_offset = dst_offset,
+                .count = count,
                 .dst_bitmask = server->cache_consistency_bitmask,
         };
         struct nfs42_clone_res res = {
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 223bedda64ae..10410e8b5853 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -33,7 +33,7 @@ static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
                 return ret;
         idr_preload(GFP_KERNEL);
         spin_lock(&nn->nfs_client_lock);
-        ret = idr_alloc(&nn->cb_ident_idr, clp, 0, 0, GFP_NOWAIT);
+        ret = idr_alloc(&nn->cb_ident_idr, clp, 1, 0, GFP_NOWAIT);
         if (ret >= 0)
                 clp->cl_cb_ident = ret;
         spin_unlock(&nn->nfs_client_lock);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 4aa571956cd6..db9b5fea5b3e 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -7,6 +7,7 @@
 #include <linux/file.h>
 #include <linux/falloc.h>
 #include <linux/nfs_fs.h>
+#include <uapi/linux/btrfs.h>   /* BTRFS_IOC_CLONE/BTRFS_IOC_CLONE_RANGE */
 #include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
@@ -203,6 +204,7 @@ nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd,
         struct fd src_file;
         struct inode *src_inode;
         unsigned int bs = server->clone_blksize;
+        bool same_inode = false;
         int ret;
 
         /* dst file must be opened for writing */
@@ -221,10 +223,8 @@ nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd,
 
         src_inode = file_inode(src_file.file);
 
-        /* src and dst must be different files */
-        ret = -EINVAL;
         if (src_inode == dst_inode)
-                goto out_fput;
+                same_inode = true;
 
         /* src file must be opened for reading */
         if (!(src_file.file->f_mode & FMODE_READ))
@@ -249,8 +249,16 @@ nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd,
                         goto out_fput;
         }
 
+        /* verify if ranges are overlapped within the same file */
+        if (same_inode) {
+                if (dst_off + count > src_off && dst_off < src_off + count)
+                        goto out_fput;
+        }
+
         /* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */
-        if (dst_inode < src_inode) {
+        if (same_inode) {
+                mutex_lock(&src_inode->i_mutex);
+        } else if (dst_inode < src_inode) {
                 mutex_lock_nested(&dst_inode->i_mutex, I_MUTEX_PARENT);
                 mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_CHILD);
         } else {
@@ -275,7 +283,9 @@ nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd,
                 truncate_inode_pages_range(&dst_inode->i_data, dst_off, dst_off + count - 1);
 
 out_unlock:
-        if (dst_inode < src_inode) {
+        if (same_inode) {
+                mutex_unlock(&src_inode->i_mutex);
+        } else if (dst_inode < src_inode) {
                 mutex_unlock(&src_inode->i_mutex);
                 mutex_unlock(&dst_inode->i_mutex);
         } else {
@@ -291,46 +301,31 @@ out_drop_write:
 
 static long nfs42_ioctl_clone_range(struct file *dst_file, void __user *argp)
 {
-        struct nfs_ioctl_clone_range_args args;
+        struct btrfs_ioctl_clone_range_args args;
 
         if (copy_from_user(&args, argp, sizeof(args)))
                 return -EFAULT;
 
-        return nfs42_ioctl_clone(dst_file, args.src_fd, args.src_off, args.dst_off, args.count);
-}
-#else
-static long nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd,
-                u64 src_off, u64 dst_off, u64 count)
-{
-        return -ENOTTY;
-}
-
-static long nfs42_ioctl_clone_range(struct file *dst_file, void __user *argp)
-{
-        return -ENOTTY;
+        return nfs42_ioctl_clone(dst_file, args.src_fd, args.src_offset,
+                                 args.dest_offset, args.src_length);
 }
-#endif /* CONFIG_NFS_V4_2 */
 
 long nfs4_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
         void __user *argp = (void __user *)arg;
 
         switch (cmd) {
-        case NFS_IOC_CLONE:
+        case BTRFS_IOC_CLONE:
                 return nfs42_ioctl_clone(file, arg, 0, 0, 0);
-        case NFS_IOC_CLONE_RANGE:
+        case BTRFS_IOC_CLONE_RANGE:
                 return nfs42_ioctl_clone_range(file, argp);
         }
 
         return -ENOTTY;
 }
+#endif /* CONFIG_NFS_V4_2 */
 
 const struct file_operations nfs4_file_operations = {
-#ifdef CONFIG_NFS_V4_2
-        .llseek         = nfs4_file_llseek,
-#else
-        .llseek         = nfs_file_llseek,
-#endif
         .read_iter      = nfs_file_read,
         .write_iter     = nfs_file_write,
         .mmap           = nfs_file_mmap,
@@ -342,14 +337,14 @@ const struct file_operations nfs4_file_operations = {
         .flock          = nfs_flock,
         .splice_read    = nfs_file_splice_read,
         .splice_write   = iter_file_splice_write,
-#ifdef CONFIG_NFS_V4_2
-        .fallocate      = nfs42_fallocate,
-#endif /* CONFIG_NFS_V4_2 */
         .check_flags    = nfs_check_flags,
         .setlease       = simple_nosetlease,
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_NFS_V4_2
+        .llseek         = nfs4_file_llseek,
+        .fallocate      = nfs42_fallocate,
         .unlocked_ioctl = nfs4_ioctl,
-#else
         .compat_ioctl   = nfs4_ioctl,
-#endif /* CONFIG_COMPAT */
+#else
+        .llseek         = nfs_file_llseek,
+#endif
 };
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 765a03559363..89818036f035 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7866,7 +7866,7 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
                         spin_unlock(&inode->i_lock);
                 goto out_restart;
         }
-        if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN)
+        if (nfs4_async_handle_error(task, server, state, &lgp->timeout) == -EAGAIN)
                 goto out_restart;
 out:
         dprintk("<-- %s\n", __func__);
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index dfed4f5c8fcc..4e4441216804 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3615,6 +3615,7 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
         status = 0;
         if (unlikely(!(bitmap[0] & FATTR4_WORD0_FS_LOCATIONS)))
                 goto out;
+        bitmap[0] &= ~FATTR4_WORD0_FS_LOCATIONS;
         status = -EIO;
         /* Ignore borken servers that return unrequested attrs */
         if (unlikely(res == NULL))
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 5c0c6b58157f..9aebffb40505 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -476,10 +476,7 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
                 }
                 unlock_page(page);
         }
-        if (PageDirty(page) || PageWriteback(page))
-                *uptodate = true;
-        else
-                *uptodate = PageUptodate(page);
+        *uptodate = PageUptodate(page);
         dprintk("%s: index=0x%lx uptodate=%d\n", __func__, index, *uptodate);
         return page;
 }
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index fe3ddd20ff89..452a011ba0d8 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -129,7 +129,7 @@ __nfs_iocounter_wait(struct nfs_io_counter *c)
                 set_bit(NFS_IO_INPROGRESS, &c->flags);
                 if (atomic_read(&c->io_count) == 0)
                         break;
-                ret = nfs_wait_bit_killable(&q.key);
+                ret = nfs_wait_bit_killable(&q.key, TASK_KILLABLE);
         } while (atomic_read(&c->io_count) != 0 && !ret);
         finish_wait(wq, &q.wait);
         return ret;
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 93496c059837..bec0384499f7 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -872,33 +872,38 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 
         dprintk("--> %s\n", __func__);
 
-        lgp = kzalloc(sizeof(*lgp), gfp_flags);
-        if (lgp == NULL)
-                return NULL;
+        /*
+         * Synchronously retrieve layout information from server and
+         * store in lseg. If we race with a concurrent seqid morphing
+         * op, then re-send the LAYOUTGET.
+         */
+        do {
+                lgp = kzalloc(sizeof(*lgp), gfp_flags);
+                if (lgp == NULL)
+                        return NULL;
+
+                i_size = i_size_read(ino);
+
+                lgp->args.minlength = PAGE_CACHE_SIZE;
+                if (lgp->args.minlength > range->length)
+                        lgp->args.minlength = range->length;
+                if (range->iomode == IOMODE_READ) {
+                        if (range->offset >= i_size)
+                                lgp->args.minlength = 0;
+                        else if (i_size - range->offset < lgp->args.minlength)
+                                lgp->args.minlength = i_size - range->offset;
+                }
+                lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
+                lgp->args.range = *range;
+                lgp->args.type = server->pnfs_curr_ld->id;
+                lgp->args.inode = ino;
+                lgp->args.ctx = get_nfs_open_context(ctx);
+                lgp->gfp_flags = gfp_flags;
+                lgp->cred = lo->plh_lc_cred;
 
-        i_size = i_size_read(ino);
+                lseg = nfs4_proc_layoutget(lgp, gfp_flags);
+        } while (lseg == ERR_PTR(-EAGAIN));
 
-        lgp->args.minlength = PAGE_CACHE_SIZE;
-        if (lgp->args.minlength > range->length)
-                lgp->args.minlength = range->length;
-        if (range->iomode == IOMODE_READ) {
-                if (range->offset >= i_size)
-                        lgp->args.minlength = 0;
-                else if (i_size - range->offset < lgp->args.minlength)
-                        lgp->args.minlength = i_size - range->offset;
-        }
-        lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
-        lgp->args.range = *range;
-        lgp->args.type = server->pnfs_curr_ld->id;
-        lgp->args.inode = ino;
-        lgp->args.ctx = get_nfs_open_context(ctx);
-        lgp->gfp_flags = gfp_flags;
-        lgp->cred = lo->plh_lc_cred;
-
-        /* Synchronously retrieve layout information from server and
-         * store in lseg.
-         */
-        lseg = nfs4_proc_layoutget(lgp, gfp_flags);
         if (IS_ERR(lseg)) {
                 switch (PTR_ERR(lseg)) {
                 case -ENOMEM:
@@ -1461,11 +1466,11 @@ static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx,
 }
 
 /* stop waiting if someone clears NFS_LAYOUT_RETRY_LAYOUTGET bit. */
-static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key)
+static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key, int mode)
 {
         if (!test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, key->flags))
                 return 1;
-        return nfs_wait_bit_killable(key);
+        return nfs_wait_bit_killable(key, mode);
 }
 
 static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo)
@@ -1687,6 +1692,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
                 /* existing state ID, make sure the sequence number matches. */
                 if (pnfs_layout_stateid_blocked(lo, &res->stateid)) {
                         dprintk("%s forget reply due to sequence\n", __func__);
+                        status = -EAGAIN;
                         goto out_forget_reply;
                 }
                 pnfs_set_layout_stateid(lo, &res->stateid, false);
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index a03f6f433075..3123408da935 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -367,13 +367,11 @@ static int ocfs2_mknod(struct inode *dir,
                 goto leave;
         }
 
-        status = posix_acl_create(dir, &mode, &default_acl, &acl);
+        status = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
         if (status) {
                 mlog_errno(status);
                 goto leave;
         }
-        /* update inode->i_mode after mask with "umask". */
-        inode->i_mode = mode;
 
         handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb,
                                                             S_ISDIR(mode),
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 871fcb67be97..0a8983492d91 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -195,8 +195,7 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
 
 static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
                               struct dentry *dentry, struct path *lowerpath,
-                              struct kstat *stat, struct iattr *attr,
-                              const char *link)
+                              struct kstat *stat, const char *link)
 {
         struct inode *wdir = workdir->d_inode;
         struct inode *udir = upperdir->d_inode;
@@ -240,8 +239,6 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
 
         mutex_lock(&newdentry->d_inode->i_mutex);
         err = ovl_set_attr(newdentry, stat);
-        if (!err && attr)
-                err = notify_change(newdentry, attr, NULL);
         mutex_unlock(&newdentry->d_inode->i_mutex);
         if (err)
                 goto out_cleanup;
@@ -286,8 +283,7 @@ out_cleanup:
  * that point the file will have already been copied up anyway.
  */
 int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
-                    struct path *lowerpath, struct kstat *stat,
-                    struct iattr *attr)
+                    struct path *lowerpath, struct kstat *stat)
 {
         struct dentry *workdir = ovl_workdir(dentry);
         int err;
@@ -345,26 +341,19 @@ int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
         }
         upperdentry = ovl_dentry_upper(dentry);
         if (upperdentry) {
-                unlock_rename(workdir, upperdir);
+                /* Raced with another copy-up?  Nothing to do, then... */
                 err = 0;
-                /* Raced with another copy-up?  Do the setattr here */
-                if (attr) {
-                        mutex_lock(&upperdentry->d_inode->i_mutex);
-                        err = notify_change(upperdentry, attr, NULL);
-                        mutex_unlock(&upperdentry->d_inode->i_mutex);
-                }
-                goto out_put_cred;
+                goto out_unlock;
         }
 
         err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath,
-                                 stat, attr, link);
+                                 stat, link);
         if (!err) {
                 /* Restore timestamps on parent (best effort) */
                 ovl_set_timestamps(upperdir, &pstat);
         }
 out_unlock:
         unlock_rename(workdir, upperdir);
-out_put_cred:
         revert_creds(old_cred);
         put_cred(override_cred);
 
@@ -406,7 +395,7 @@ int ovl_copy_up(struct dentry *dentry)
                 ovl_path_lower(next, &lowerpath);
                 err = vfs_getattr(&lowerpath, &stat);
                 if (!err)
-                        err = ovl_copy_up_one(parent, next, &lowerpath, &stat, NULL);
+                        err = ovl_copy_up_one(parent, next, &lowerpath, &stat);
 
                 dput(parent);
                 dput(next);
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index ec0c2a050043..4060ffde8722 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -12,8 +12,7 @@
 #include <linux/xattr.h>
 #include "overlayfs.h"
 
-static int ovl_copy_up_last(struct dentry *dentry, struct iattr *attr,
-                            bool no_data)
+static int ovl_copy_up_truncate(struct dentry *dentry)
 {
         int err;
         struct dentry *parent;
@@ -30,10 +29,8 @@ static int ovl_copy_up_last(struct dentry *dentry, struct iattr *attr,
         if (err)
                 goto out_dput_parent;
 
-        if (no_data)
-                stat.size = 0;
-
-        err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat, attr);
+        stat.size = 0;
+        err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat);
 
 out_dput_parent:
         dput(parent);
@@ -49,13 +46,13 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
         if (err)
                 goto out;
 
-        upperdentry = ovl_dentry_upper(dentry);
-        if (upperdentry) {
+        err = ovl_copy_up(dentry);
+        if (!err) {
+                upperdentry = ovl_dentry_upper(dentry);
+
                 mutex_lock(&upperdentry->d_inode->i_mutex);
                 err = notify_change(upperdentry, attr, NULL);
                 mutex_unlock(&upperdentry->d_inode->i_mutex);
-        } else {
-                err = ovl_copy_up_last(dentry, attr, false);
         }
         ovl_drop_write(dentry);
 out:
@@ -353,7 +350,7 @@ struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags)
                         return ERR_PTR(err);
 
                 if (file_flags & O_TRUNC)
-                        err = ovl_copy_up_last(dentry, NULL, true);
+                        err = ovl_copy_up_truncate(dentry);
                 else
                         err = ovl_copy_up(dentry);
                 ovl_drop_write(dentry);
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index ea5a40b06e3a..e17154aeaae4 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -194,7 +194,6 @@ void ovl_cleanup(struct inode *dir, struct dentry *dentry);
 /* copy_up.c */
 int ovl_copy_up(struct dentry *dentry);
 int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
-                    struct path *lowerpath, struct kstat *stat,
-                    struct iattr *attr);
+                    struct path *lowerpath, struct kstat *stat);
 int ovl_copy_xattr(struct dentry *old, struct dentry *new);
 int ovl_set_attr(struct dentry *upper, struct kstat *stat);
diff --git a/fs/splice.c b/fs/splice.c
index 801c21cd77fe..4cf700d50b40 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -809,6 +809,13 @@ static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_des
  */
 static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd)
 {
+        /*
+         * Check for signal early to make process killable when there are
+         * always buffers available
+         */
+        if (signal_pending(current))
+                return -ERESTARTSYS;
+
         while (!pipe->nrbufs) {
                 if (!pipe->writers)
                         return 0;
@@ -884,6 +891,7 @@ ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd,
 
         splice_from_pipe_begin(sd);
         do {
+                cond_resched();
                 ret = splice_from_pipe_next(pipe, sd);
                 if (ret > 0)
                         ret = splice_from_pipe_feed(pipe, sd, actor);
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 590ad9206e3f..02fa1dcc5969 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -162,15 +162,8 @@ void sysv_set_inode(struct inode *inode, dev_t rdev)
                 inode->i_fop = &sysv_dir_operations;
                 inode->i_mapping->a_ops = &sysv_aops;
         } else if (S_ISLNK(inode->i_mode)) {
-                if (inode->i_blocks) {
-                        inode->i_op = &sysv_symlink_inode_operations;
-                        inode->i_mapping->a_ops = &sysv_aops;
-                } else {
-                        inode->i_op = &simple_symlink_inode_operations;
-                        inode->i_link = (char *)SYSV_I(inode)->i_data;
-                        nd_terminate_link(inode->i_link, inode->i_size,
-                                sizeof(SYSV_I(inode)->i_data) - 1);
-                }
+                inode->i_op = &sysv_symlink_inode_operations;
+                inode->i_mapping->a_ops = &sysv_aops;
         } else
                 init_special_inode(inode, inode->i_mode, rdev);
 }
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index db284bff29dc..9dbb739cafa0 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -5,7 +5,7 @@
  * Copyright 2001 Red Hat, Inc.
  * Based on code from mm/memory.c Copyright Linus Torvalds and others.
  *
- * Copyright 2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright 2011 Red Hat, Inc., Peter Zijlstra
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 0b921ae06cd8..0a271ca1f7c7 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -309,6 +309,11 @@ struct drm_file {
         unsigned universal_planes:1;
         /* true if client understands atomic properties */
         unsigned atomic:1;
+        /*
+         * This client is allowed to gain master privileges for @master.
+         * Protected by struct drm_device::master_mutex.
+         */
+        unsigned allowed_master:1;
 
         struct pid *pid;
         kuid_t uid;
@@ -910,6 +915,7 @@ extern int drm_open(struct inode *inode, struct file *filp);
 extern ssize_t drm_read(struct file *filp, char __user *buffer,
                         size_t count, loff_t *offset);
 extern int drm_release(struct inode *inode, struct file *filp);
+extern int drm_new_set_master(struct drm_device *dev, struct drm_file *fpriv);
 
                                 /* Mapping support (drm_vm.h) */
 extern unsigned int drm_poll(struct file *filp, struct poll_table_struct *wait);
@@ -947,6 +953,10 @@ extern void drm_send_vblank_event(struct drm_device *dev, unsigned int pipe,
                                   struct drm_pending_vblank_event *e);
 extern void drm_crtc_send_vblank_event(struct drm_crtc *crtc,
                                        struct drm_pending_vblank_event *e);
+extern void drm_arm_vblank_event(struct drm_device *dev, unsigned int pipe,
+                                 struct drm_pending_vblank_event *e);
+extern void drm_crtc_arm_vblank_event(struct drm_crtc *crtc,
+                                      struct drm_pending_vblank_event *e);
 extern bool drm_handle_vblank(struct drm_device *dev, unsigned int pipe);
 extern bool drm_crtc_handle_vblank(struct drm_crtc *crtc);
 extern int drm_vblank_get(struct drm_device *dev, unsigned int pipe);
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 9c747cb14ad8..d2f41477f8ae 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -342,10 +342,10 @@ int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid,
                                struct irq_phys_map *map, bool level);
 void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
 int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
-int kvm_vgic_vcpu_active_irq(struct kvm_vcpu *vcpu);
 struct irq_phys_map *kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu,
                                            int virt_irq, int irq);
 int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map);
+bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, struct irq_phys_map *map);
 
 #define irqchip_in_kernel(k)    (!!((k)->arch.vgic.in_kernel))
 #define vgic_initialized(k)     (!!((k)->arch.vgic.nr_cpus))
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 054833939995..1991aea2ec4c 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -870,8 +870,8 @@ static inline int acpi_dev_get_property(struct acpi_device *adev,
 }
 
 static inline int acpi_node_get_property_reference(struct fwnode_handle *fwnode,
-                                const char *name, const char *cells_name,
-                                size_t index, struct acpi_reference_args *args)
+                                const char *name, size_t index,
+                                struct acpi_reference_args *args)
 {
         return -ENXIO;
 }
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 2b8ed123ad36..defeaac0745f 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -107,7 +107,7 @@ static inline __u64 ror64(__u64 word, unsigned int shift)
  */
 static inline __u32 rol32(__u32 word, unsigned int shift)
 {
-        return (word << shift) | (word >> (32 - shift));
+        return (word << shift) | (word >> ((-shift) & 31));
 }
 
 /**
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c0d2b7927c1f..0169ba2e2e64 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -254,6 +254,7 @@ struct queue_limits {
         unsigned long           virt_boundary_mask;
 
         unsigned int            max_hw_sectors;
+        unsigned int            max_dev_sectors;
         unsigned int            chunk_sectors;
         unsigned int            max_sectors;
         unsigned int            max_segment_size;
@@ -773,7 +774,6 @@ extern void blk_rq_set_block_pc(struct request *);
 extern void blk_requeue_request(struct request_queue *, struct request *);
 extern void blk_add_request_payload(struct request *rq, struct page *page,
                 unsigned int len);
-extern int blk_rq_check_limits(struct request_queue *q, struct request *rq);
 extern int blk_lld_busy(struct request_queue *q);
 extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
                              struct bio_set *bs, gfp_t gfp_mask,
@@ -960,7 +960,6 @@ extern struct request_queue *blk_init_allocated_queue(struct request_queue *,
 extern void blk_cleanup_queue(struct request_queue *);
 extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
 extern void blk_queue_bounce_limit(struct request_queue *, u64);
-extern void blk_limits_max_hw_sectors(struct queue_limits *, unsigned int);
 extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_max_segments(struct request_queue *, unsigned short);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index de464e6683b6..83d1926c61e4 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -40,6 +40,7 @@ struct bpf_map {
         struct user_struct *user;
         const struct bpf_map_ops *ops;
         struct work_struct work;
+        atomic_t usercnt;
 };
 
 struct bpf_map_type_list {
@@ -167,8 +168,10 @@ struct bpf_prog *bpf_prog_get(u32 ufd);
 void bpf_prog_put(struct bpf_prog *prog);
 void bpf_prog_put_rcu(struct bpf_prog *prog);
 
-struct bpf_map *bpf_map_get(u32 ufd);
+struct bpf_map *bpf_map_get_with_uref(u32 ufd);
 struct bpf_map *__bpf_map_get(struct fd f);
+void bpf_map_inc(struct bpf_map *map, bool uref);
+void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 
 extern int sysctl_unprivileged_bpf_disabled;
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 60d44b26276d..06b77f9dd3f2 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -90,7 +90,6 @@ enum {
  */
 struct cgroup_file {
         /* do not access any fields from outside cgroup core */
-        struct list_head node;                  /* anchored at css->files */
         struct kernfs_node *kn;
 };
 
@@ -134,9 +133,6 @@ struct cgroup_subsys_state {
          */
         u64 serial_nr;
 
-        /* all cgroup_files associated with this css */
-        struct list_head files;
-
         /* percpu_ref killing and RCU release */
         struct rcu_head rcu_head;
         struct work_struct destroy_work;
@@ -426,12 +422,9 @@ struct cgroup_subsys {
         void (*css_reset)(struct cgroup_subsys_state *css);
         void (*css_e_css_changed)(struct cgroup_subsys_state *css);
 
-        int (*can_attach)(struct cgroup_subsys_state *css,
-                          struct cgroup_taskset *tset);
-        void (*cancel_attach)(struct cgroup_subsys_state *css,
-                              struct cgroup_taskset *tset);
-        void (*attach)(struct cgroup_subsys_state *css,
-                       struct cgroup_taskset *tset);
+        int (*can_attach)(struct cgroup_taskset *tset);
+        void (*cancel_attach)(struct cgroup_taskset *tset);
+        void (*attach)(struct cgroup_taskset *tset);
         int (*can_fork)(struct task_struct *task, void **priv_p);
         void (*cancel_fork)(struct task_struct *task, void *priv);
         void (*fork)(struct task_struct *task, void *priv);
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 22e3754f89c5..cb91b44f5f78 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -88,6 +88,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
 int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_rm_cftypes(struct cftype *cfts);
+void cgroup_file_notify(struct cgroup_file *cfile);
 
 char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
 int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry);
@@ -119,8 +120,10 @@ struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state
 struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos,
                                                      struct cgroup_subsys_state *css);
 
-struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset);
-struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset);
+struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
+                                         struct cgroup_subsys_state **dst_cssp);
+struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
+                                        struct cgroup_subsys_state **dst_cssp);
 
 void css_task_iter_start(struct cgroup_subsys_state *css,
                          struct css_task_iter *it);
@@ -235,30 +238,39 @@ void css_task_iter_end(struct css_task_iter *it);
 /**
  * cgroup_taskset_for_each - iterate cgroup_taskset
  * @task: the loop cursor
+ * @dst_css: the destination css
  * @tset: taskset to iterate
  *
  * @tset may contain multiple tasks and they may belong to multiple
- * processes.  When there are multiple tasks in @tset, if a task of a
- * process is in @tset, all tasks of the process are in @tset.  Also, all
- * are guaranteed to share the same source and destination csses.
+ * processes.
+ *
+ * On the v2 hierarchy, there may be tasks from multiple processes and they
+ * may not share the source or destination csses.
+ *
+ * On traditional hierarchies, when there are multiple tasks in @tset, if a
+ * task of a process is in @tset, all tasks of the process are in @tset.
+ * Also, all are guaranteed to share the same source and destination csses.
  *
  * Iteration is not in any specific order.
  */
-#define cgroup_taskset_for_each(task, tset)                             \
-        for ((task) = cgroup_taskset_first((tset)); (task);             \
-             (task) = cgroup_taskset_next((tset)))
+#define cgroup_taskset_for_each(task, dst_css, tset)                    \
+        for ((task) = cgroup_taskset_first((tset), &(dst_css));         \
+             (task);                                                    \
+             (task) = cgroup_taskset_next((tset), &(dst_css)))
 
 /**
  * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset
  * @leader: the loop cursor
+ * @dst_css: the destination css
  * @tset: takset to iterate
  *
  * Iterate threadgroup leaders of @tset.  For single-task migrations, @tset
  * may not contain any.
  */
-#define cgroup_taskset_for_each_leader(leader, tset)                    \
-        for ((leader) = cgroup_taskset_first((tset)); (leader);         \
-             (leader) = cgroup_taskset_next((tset)))                    \
+#define cgroup_taskset_for_each_leader(leader, dst_css, tset)           \
+        for ((leader) = cgroup_taskset_first((tset), &(dst_css));       \
+             (leader);                                                  \
+             (leader) = cgroup_taskset_next((tset), &(dst_css)))        \
                 if ((leader) != (leader)->group_leader)                 \
                         ;                                               \
                 else
@@ -516,19 +528,6 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
         pr_cont_kernfs_path(cgrp->kn);
 }
 
-/**
- * cgroup_file_notify - generate a file modified event for a cgroup_file
- * @cfile: target cgroup_file
- *
- * @cfile must have been obtained by setting cftype->file_offset.
- */
-static inline void cgroup_file_notify(struct cgroup_file *cfile)
-{
-        /* might not have been created due to one of the CFTYPE selector flags */
-        if (cfile->kn)
-                kernfs_notify(cfile->kn);
-}
-
 #else /* !CONFIG_CGROUPS */
 
 struct cgroup_subsys_state;
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index ef4c5b1a860f..177c7680c1a8 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -77,6 +77,7 @@ struct cpufreq_policy {
         unsigned int            suspend_freq; /* freq to set during suspend */
 
         unsigned int            policy; /* see above */
+        unsigned int            last_policy; /* policy before unplug */
         struct cpufreq_governor *governor; /* see below */
         void                    *governor_data;
         bool                    governor_enabled; /* governor start/stop flag */
diff --git a/include/linux/dns_resolver.h b/include/linux/dns_resolver.h
index cc92268af89a..6ac3cad9aef1 100644
--- a/include/linux/dns_resolver.h
+++ b/include/linux/dns_resolver.h
@@ -27,7 +27,7 @@
 #ifdef __KERNEL__
 
 extern int dns_query(const char *type, const char *name, size_t namelen,
-                     const char *options, char **_result, time_t *_expiry);
+                     const char *options, char **_result, time64_t *_expiry);
 
 #endif /* KERNEL */
 
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 0ef2a97ccdb5..402753bccafa 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -227,7 +227,7 @@ struct ipv6_pinfo {
         struct ipv6_ac_socklist *ipv6_ac_list;
         struct ipv6_fl_socklist __rcu *ipv6_fl_list;
 
-        struct ipv6_txoptions   *opt;
+        struct ipv6_txoptions __rcu     *opt;
         struct sk_buff          *pktoptions;
         struct sk_buff          *rxpmtu;
         struct inet6_cork       cork;
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index c9ae0c6ec050..d5d798b35c1f 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -330,6 +330,7 @@ struct rdists {
 };
 
 struct irq_domain;
+struct device_node;
 int its_cpu_init(void);
 int its_init(struct device_node *node, struct rdists *rdists,
              struct irq_domain *domain);
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 8dde55974f18..0536524bb9eb 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -5,7 +5,7 @@
  * Jump label support
  *
  * Copyright (C) 2009-2012 Jason Baron <jbaron@redhat.com>
- * Copyright (C) 2011-2012 Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra
  *
  * DEPRECATED API:
  *
diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h
index d0a1f99e24e3..4894c6888bc6 100644
--- a/include/linux/kmemleak.h
+++ b/include/linux/kmemleak.h
@@ -25,7 +25,7 @@
 
 #ifdef CONFIG_DEBUG_KMEMLEAK
 
-extern void kmemleak_init(void) __ref;
+extern void kmemleak_init(void) __init;
 extern void kmemleak_alloc(const void *ptr, size_t size, int min_count,
                            gfp_t gfp) __ref;
 extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
diff --git a/include/linux/kref.h b/include/linux/kref.h
index 484604d184be..e15828fd71f1 100644
--- a/include/linux/kref.h
+++ b/include/linux/kref.h
@@ -19,7 +19,6 @@
 #include <linux/atomic.h>
 #include <linux/kernel.h>
 #include <linux/mutex.h>
-#include <linux/spinlock.h>
 
 struct kref {
         atomic_t refcount;
@@ -99,38 +98,6 @@ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)
         return kref_sub(kref, 1, release);
 }
 
-/**
- * kref_put_spinlock_irqsave - decrement refcount for object.
- * @kref: object.
- * @release: pointer to the function that will clean up the object when the
- *           last reference to the object is released.
- *           This pointer is required, and it is not acceptable to pass kfree
- *           in as this function.
- * @lock: lock to take in release case
- *
- * Behaves identical to kref_put with one exception.  If the reference count
- * drops to zero, the lock will be taken atomically wrt dropping the reference
- * count.  The release function has to call spin_unlock() without _irqrestore.
- */
-static inline int kref_put_spinlock_irqsave(struct kref *kref,
-                void (*release)(struct kref *kref),
-                spinlock_t *lock)
-{
-        unsigned long flags;
-
-        WARN_ON(release == NULL);
-        if (atomic_add_unless(&kref->refcount, -1, 1))
-                return 0;
-        spin_lock_irqsave(lock, flags);
-        if (atomic_dec_and_test(&kref->refcount)) {
-                release(kref);
-                local_irq_restore(flags);
-                return 1;
-        }
-        spin_unlock_irqrestore(lock, flags);
-        return 0;
-}
-
 static inline int kref_put_mutex(struct kref *kref,
                                  void (*release)(struct kref *kref),
                                  struct mutex *lock)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 5706a2108f0a..c923350ca20a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -460,6 +460,17 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
              (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \
              idx++)
 
+static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id)
+{
+        struct kvm_vcpu *vcpu;
+        int i;
+
+        kvm_for_each_vcpu(i, vcpu, kvm)
+                if (vcpu->vcpu_id == id)
+                        return vcpu;
+        return NULL;
+}
+
 #define kvm_for_each_memslot(memslot, slots)    \
         for (memslot = &slots->memslots[0];     \
               memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 83577f8fd15b..600c1e0626a5 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -210,6 +210,7 @@ enum {
         ATA_FLAG_SLAVE_POSS     = (1 << 0), /* host supports slave dev */
                                             /* (doesn't imply presence) */
         ATA_FLAG_SATA           = (1 << 1),
+        ATA_FLAG_NO_LOG_PAGE    = (1 << 5), /* do not issue log page read */
         ATA_FLAG_NO_ATAPI       = (1 << 6), /* No ATAPI support */
         ATA_FLAG_PIO_DMA        = (1 << 7), /* PIO cmds via DMA */
         ATA_FLAG_PIO_LBA48      = (1 << 8), /* Host DMA engine is LBA28 only */
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 69c9057e1ab8..034117b3be5f 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -50,15 +50,21 @@ enum {
         NVM_IO_DUAL_ACCESS      = 0x1,
         NVM_IO_QUAD_ACCESS      = 0x2,
 
+        /* NAND Access Modes */
         NVM_IO_SUSPEND          = 0x80,
         NVM_IO_SLC_MODE         = 0x100,
         NVM_IO_SCRAMBLE_DISABLE = 0x200,
+
+        /* Block Types */
+        NVM_BLK_T_FREE          = 0x0,
+        NVM_BLK_T_BAD           = 0x1,
+        NVM_BLK_T_DEV           = 0x2,
+        NVM_BLK_T_HOST          = 0x4,
 };
 
 struct nvm_id_group {
         u8      mtype;
         u8      fmtype;
-        u16     res16;
         u8      num_ch;
         u8      num_lun;
         u8      num_pln;
@@ -74,9 +80,9 @@ struct nvm_id_group {
         u32     tbet;
         u32     tbem;
         u32     mpos;
+        u32     mccap;
         u16     cpar;
-        u8      res[913];
-} __packed;
+};
 
 struct nvm_addr_format {
         u8      ch_offset;
@@ -91,19 +97,15 @@ struct nvm_addr_format {
         u8      pg_len;
         u8      sect_offset;
         u8      sect_len;
-        u8      res[4];
 };
 
 struct nvm_id {
         u8      ver_id;
         u8      vmnt;
         u8      cgrps;
-        u8      res[5];
         u32     cap;
         u32     dom;
         struct nvm_addr_format ppaf;
-        u8      ppat;
-        u8      resv[224];
         struct nvm_id_group groups[4];
 } __packed;
 
@@ -123,39 +125,28 @@ struct nvm_tgt_instance {
 #define NVM_VERSION_MINOR 0
 #define NVM_VERSION_PATCH 0
 
-#define NVM_SEC_BITS (8)
-#define NVM_PL_BITS  (6)
-#define NVM_PG_BITS  (16)
 #define NVM_BLK_BITS (16)
-#define NVM_LUN_BITS (10)
+#define NVM_PG_BITS  (16)
+#define NVM_SEC_BITS (8)
+#define NVM_PL_BITS  (8)
+#define NVM_LUN_BITS (8)
 #define NVM_CH_BITS  (8)
 
 struct ppa_addr {
+        /* Generic structure for all addresses */
         union {
-                /* Channel-based PPA format in nand 4x2x2x2x8x10 */
-                struct {
-                        u64 ch          : 4;
-                        u64 sec         : 2; /* 4 sectors per page */
-                        u64 pl          : 2; /* 4 planes per LUN */
-                        u64 lun         : 2; /* 4 LUNs per channel */
-                        u64 pg          : 8; /* 256 pages per block */
-                        u64 blk         : 10;/* 1024 blocks per plane */
-                        u64 resved              : 36;
-                } chnl;
-
-                /* Generic structure for all addresses */
                 struct {
+                        u64 blk         : NVM_BLK_BITS;
+                        u64 pg          : NVM_PG_BITS;
                         u64 sec         : NVM_SEC_BITS;
                         u64 pl          : NVM_PL_BITS;
-                        u64 pg          : NVM_PG_BITS;
-                        u64 blk         : NVM_BLK_BITS;
                         u64 lun         : NVM_LUN_BITS;
                         u64 ch          : NVM_CH_BITS;
                 } g;
 
                 u64 ppa;
         };
-} __packed;
+};
 
 struct nvm_rq {
         struct nvm_tgt_instance *ins;
@@ -191,18 +182,18 @@ static inline void *nvm_rq_to_pdu(struct nvm_rq *rqdata)
 struct nvm_block;
 
 typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *);
-typedef int (nvm_bb_update_fn)(u32, void *, unsigned int, void *);
-typedef int (nvm_id_fn)(struct request_queue *, struct nvm_id *);
-typedef int (nvm_get_l2p_tbl_fn)(struct request_queue *, u64, u32,
+typedef int (nvm_bb_update_fn)(struct ppa_addr, int, u8 *, void *);
+typedef int (nvm_id_fn)(struct nvm_dev *, struct nvm_id *);
+typedef int (nvm_get_l2p_tbl_fn)(struct nvm_dev *, u64, u32,
                                 nvm_l2p_update_fn *, void *);
-typedef int (nvm_op_bb_tbl_fn)(struct request_queue *, int, unsigned int,
+typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, int,
                                 nvm_bb_update_fn *, void *);
-typedef int (nvm_op_set_bb_fn)(struct request_queue *, struct nvm_rq *, int);
-typedef int (nvm_submit_io_fn)(struct request_queue *, struct nvm_rq *);
-typedef int (nvm_erase_blk_fn)(struct request_queue *, struct nvm_rq *);
-typedef void *(nvm_create_dma_pool_fn)(struct request_queue *, char *);
+typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct nvm_rq *, int);
+typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *);
+typedef int (nvm_erase_blk_fn)(struct nvm_dev *, struct nvm_rq *);
+typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *);
 typedef void (nvm_destroy_dma_pool_fn)(void *);
-typedef void *(nvm_dev_dma_alloc_fn)(struct request_queue *, void *, gfp_t,
+typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t,
                                                                 dma_addr_t *);
 typedef void (nvm_dev_dma_free_fn)(void *, void*, dma_addr_t);
 
@@ -210,7 +201,7 @@ struct nvm_dev_ops {
         nvm_id_fn               *identity;
         nvm_get_l2p_tbl_fn      *get_l2p_tbl;
         nvm_op_bb_tbl_fn        *get_bb_tbl;
-        nvm_op_set_bb_fn        *set_bb;
+        nvm_op_set_bb_fn        *set_bb_tbl;
 
         nvm_submit_io_fn        *submit_io;
         nvm_erase_blk_fn        *erase_block;
@@ -220,7 +211,7 @@ struct nvm_dev_ops {
         nvm_dev_dma_alloc_fn    *dev_dma_alloc;
         nvm_dev_dma_free_fn     *dev_dma_free;
 
-        uint8_t                 max_phys_sect;
+        unsigned int            max_phys_sect;
 };
 
 struct nvm_lun {
@@ -229,7 +220,9 @@ struct nvm_lun {
         int lun_id;
         int chnl_id;
 
+        unsigned int nr_inuse_blocks;   /* Number of used blocks */
         unsigned int nr_free_blocks;    /* Number of unused blocks */
+        unsigned int nr_bad_blocks;     /* Number of bad blocks */
         struct nvm_block *blocks;
 
         spinlock_t lock;
@@ -263,8 +256,7 @@ struct nvm_dev {
         int blks_per_lun;
         int sec_size;
         int oob_size;
-        int addr_mode;
-        struct nvm_addr_format addr_format;
+        struct nvm_addr_format ppaf;
 
         /* Calculated/Cached values. These do not reflect the actual usable
          * blocks at run-time.
@@ -290,118 +282,45 @@ struct nvm_dev {
         char name[DISK_NAME_LEN];
 };
 
-/* fallback conversion */
-static struct ppa_addr __generic_to_linear_addr(struct nvm_dev *dev,
-                                                        struct ppa_addr r)
+static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev,
+                                                struct ppa_addr r)
 {
         struct ppa_addr l;
 
-        l.ppa = r.g.sec +
-                r.g.pg  * dev->sec_per_pg +
-                r.g.blk * (dev->pgs_per_blk *
-                                dev->sec_per_pg) +
-                r.g.lun * (dev->blks_per_lun *
-                                dev->pgs_per_blk *
-                                dev->sec_per_pg) +
-                r.g.ch * (dev->blks_per_lun *
-                                dev->pgs_per_blk *
-                                dev->luns_per_chnl *
-                                dev->sec_per_pg);
+        l.ppa = ((u64)r.g.blk) << dev->ppaf.blk_offset;
+        l.ppa |= ((u64)r.g.pg) << dev->ppaf.pg_offset;
+        l.ppa |= ((u64)r.g.sec) << dev->ppaf.sect_offset;
+        l.ppa |= ((u64)r.g.pl) << dev->ppaf.pln_offset;
+        l.ppa |= ((u64)r.g.lun) << dev->ppaf.lun_offset;
+        l.ppa |= ((u64)r.g.ch) << dev->ppaf.ch_offset;
 
         return l;
 }
 
-/* fallback conversion */
-static struct ppa_addr __linear_to_generic_addr(struct nvm_dev *dev,
-                                                        struct ppa_addr r)
+static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev,
+                                                struct ppa_addr r)
 {
         struct ppa_addr l;
-        int secs, pgs, blks, luns;
-        sector_t ppa = r.ppa;
-
-        l.ppa = 0;
-
-        div_u64_rem(ppa, dev->sec_per_pg, &secs);
-        l.g.sec = secs;
 
-        sector_div(ppa, dev->sec_per_pg);
-        div_u64_rem(ppa, dev->sec_per_blk, &pgs);
-        l.g.pg = pgs;
-
-        sector_div(ppa, dev->pgs_per_blk);
-        div_u64_rem(ppa, dev->blks_per_lun, &blks);
-        l.g.blk = blks;
-
-        sector_div(ppa, dev->blks_per_lun);
-        div_u64_rem(ppa, dev->luns_per_chnl, &luns);
-        l.g.lun = luns;
-
-        sector_div(ppa, dev->luns_per_chnl);
-        l.g.ch = ppa;
-
-        return l;
-}
-
-static struct ppa_addr __generic_to_chnl_addr(struct ppa_addr r)
-{
-        struct ppa_addr l;
-
-        l.ppa = 0;
-
-        l.chnl.sec = r.g.sec;
-        l.chnl.pl = r.g.pl;
-        l.chnl.pg = r.g.pg;
-        l.chnl.blk = r.g.blk;
-        l.chnl.lun = r.g.lun;
-        l.chnl.ch = r.g.ch;
-
-        return l;
-}
-
-static struct ppa_addr __chnl_to_generic_addr(struct ppa_addr r)
-{
-        struct ppa_addr l;
-
-        l.ppa = 0;
-
-        l.g.sec = r.chnl.sec;
-        l.g.pl = r.chnl.pl;
-        l.g.pg = r.chnl.pg;
-        l.g.blk = r.chnl.blk;
-        l.g.lun = r.chnl.lun;
-        l.g.ch = r.chnl.ch;
+        /*
+         * (r.ppa << X offset) & X len bitmask. X eq. blk, pg, etc.
+         */
+        l.g.blk = (r.ppa >> dev->ppaf.blk_offset) &
+                                        (((1 << dev->ppaf.blk_len) - 1));
+        l.g.pg |= (r.ppa >> dev->ppaf.pg_offset) &
+                                        (((1 << dev->ppaf.pg_len) - 1));
+        l.g.sec |= (r.ppa >> dev->ppaf.sect_offset) &
+                                        (((1 << dev->ppaf.sect_len) - 1));
+        l.g.pl |= (r.ppa >> dev->ppaf.pln_offset) &
+                                        (((1 << dev->ppaf.pln_len) - 1));
+        l.g.lun |= (r.ppa >> dev->ppaf.lun_offset) &
+                                        (((1 << dev->ppaf.lun_len) - 1));
+        l.g.ch |= (r.ppa >> dev->ppaf.ch_offset) &
+                                        (((1 << dev->ppaf.ch_len) - 1));
 
         return l;
 }
 
-static inline struct ppa_addr addr_to_generic_mode(struct nvm_dev *dev,
-                                                struct ppa_addr gppa)
-{
-        switch (dev->addr_mode) {
-        case NVM_ADDRMODE_LINEAR:
-                return __linear_to_generic_addr(dev, gppa);
-        case NVM_ADDRMODE_CHANNEL:
-                return __chnl_to_generic_addr(gppa);
-        default:
-                BUG();
-        }
-        return gppa;
-}
-
-static inline struct ppa_addr generic_to_addr_mode(struct nvm_dev *dev,
-                                                struct ppa_addr gppa)
-{
-        switch (dev->addr_mode) {
-        case NVM_ADDRMODE_LINEAR:
-                return __generic_to_linear_addr(dev, gppa);
-        case NVM_ADDRMODE_CHANNEL:
-                return __generic_to_chnl_addr(gppa);
-        default:
-                BUG();
-        }
-        return gppa;
-}
-
 static inline int ppa_empty(struct ppa_addr ppa_addr)
 {
         return (ppa_addr.ppa == ADDR_EMPTY);
@@ -468,7 +387,7 @@ typedef int (nvmm_end_io_fn)(struct nvm_rq *, int);
 typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *,
                                                                 unsigned long);
 typedef struct nvm_lun *(nvmm_get_lun_fn)(struct nvm_dev *, int);
-typedef void (nvmm_free_blocks_print_fn)(struct nvm_dev *);
+typedef void (nvmm_lun_info_print_fn)(struct nvm_dev *);
 
 struct nvmm_type {
         const char *name;
@@ -492,7 +411,7 @@ struct nvmm_type {
         nvmm_get_lun_fn *get_lun;
 
         /* Statistics */
-        nvmm_free_blocks_print_fn *free_blocks_print;
+        nvmm_lun_info_print_fn *lun_info_print;
         struct list_head list;
 };
 
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 70400dc7660f..c57e424d914b 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -2,7 +2,7 @@
  * Runtime locking correctness validator
  *
  *  Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * see Documentation/locking/lockdep-design.txt for more details.
  */
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 7501626ab529..d3133be12d92 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -427,6 +427,17 @@ enum {
 };
 
 enum {
+        /*
+         * Max wqe size for rdma read is 512 bytes, so this
+         * limits our max_sge_rd as the wqe needs to fit:
+         * - ctrl segment (16 bytes)
+         * - rdma segment (16 bytes)
+         * - scatter elements (16 bytes each)
+         */
+        MLX4_MAX_SGE_RD = (512 - 16 - 16) / 16
+};
+
+enum {
         MLX4_DEV_PMC_SUBTYPE_GUID_INFO   = 0x14,
         MLX4_DEV_PMC_SUBTYPE_PORT_INFO   = 0x15,
         MLX4_DEV_PMC_SUBTYPE_PKEY_TABLE  = 0x16,
diff --git a/include/linux/net.h b/include/linux/net.h
index 70ac5e28e6b7..0b4ac7da583a 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -34,8 +34,12 @@ struct inode;
 struct file;
 struct net;
 
-#define SOCK_ASYNC_NOSPACE      0
-#define SOCK_ASYNC_WAITDATA     1
+/* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located
+ * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected.
+ * Eventually all flags will be in sk->sk_wq_flags.
+ */
+#define SOCKWQ_ASYNC_NOSPACE    0
+#define SOCKWQ_ASYNC_WAITDATA   1
 #define SOCK_NOSPACE            2
 #define SOCK_PASSCRED           3
 #define SOCK_PASSSEC            4
@@ -89,6 +93,7 @@ struct socket_wq {
         /* Note: wait MUST be first field of socket_wq */
         wait_queue_head_t       wait;
         struct fasync_struct    *fasync_list;
+        unsigned long           flags; /* %SOCKWQ_ASYNC_NOSPACE, etc */
         struct rcu_head         rcu;
 } ____cacheline_aligned_in_smp;
 
@@ -96,7 +101,7 @@ struct socket_wq {
  *  struct socket - general BSD socket
  *  @state: socket state (%SS_CONNECTED, etc)
  *  @type: socket type (%SOCK_STREAM, etc)
- *  @flags: socket flags (%SOCK_ASYNC_NOSPACE, etc)
+ *  @flags: socket flags (%SOCK_NOSPACE, etc)
  *  @ops: protocol specific socket operations
  *  @file: File back pointer for gc
  *  @sk: internal networking protocol agnostic socket representation
@@ -202,7 +207,7 @@ enum {
         SOCK_WAKE_URG,
 };
 
-int sock_wake_async(struct socket *sk, int how, int band);
+int sock_wake_async(struct socket_wq *sk_wq, int how, int band);
 int sock_register(const struct net_proto_family *fam);
 void sock_unregister(int family);
 int __sock_create(struct net *net, int family, int type, int proto,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 67bfac1abfc1..3b5d134e945a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1398,7 +1398,8 @@ enum netdev_priv_flags {
  *      @dma:           DMA channel
  *      @mtu:           Interface MTU value
  *      @type:          Interface hardware type
- *      @hard_header_len: Hardware header length
+ *      @hard_header_len: Hardware header length, which means that this is the
+ *                        minimum size of a packet.
  *
  *      @needed_headroom: Extra headroom the hardware may need, but not in all
  *                        cases can this be guaranteed
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 570d630f98ae..11bbae44f4cb 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -251,6 +251,7 @@ struct nfs4_layoutget {
         struct nfs4_layoutget_res res;
         struct rpc_cred *cred;
         gfp_t gfp_flags;
+        long timeout;
 };
 
 struct nfs4_getdeviceinfo_args {
diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index 039f2eec49ce..1e0deb8e8494 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -46,12 +46,14 @@ extern int of_irq_get(struct device_node *dev, int index);
 extern int of_irq_get_byname(struct device_node *dev, const char *name);
 extern int of_irq_to_resource_table(struct device_node *dev,
                 struct resource *res, int nr_irqs);
+extern struct device_node *of_irq_find_parent(struct device_node *child);
 extern struct irq_domain *of_msi_get_domain(struct device *dev,
                                             struct device_node *np,
                                             enum irq_domain_bus_token token);
 extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev,
                                                        u32 rid);
 extern void of_msi_configure(struct device *dev, struct device_node *np);
+u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in);
 #else
 static inline int of_irq_count(struct device_node *dev)
 {
@@ -70,6 +72,11 @@ static inline int of_irq_to_resource_table(struct device_node *dev,
 {
         return 0;
 }
+static inline void *of_irq_find_parent(struct device_node *child)
+{
+        return NULL;
+}
+
 static inline struct irq_domain *of_msi_get_domain(struct device *dev,
                                                    struct device_node *np,
                                                    enum irq_domain_bus_token token)
@@ -84,6 +91,11 @@ static inline struct irq_domain *of_msi_map_get_device_domain(struct device *dev
 static inline void of_msi_configure(struct device *dev, struct device_node *np)
 {
 }
+static inline u32 of_msi_map_rid(struct device *dev,
+                                 struct device_node *msi_np, u32 rid_in)
+{
+        return rid_in;
+}
 #endif
 
 #if defined(CONFIG_OF_IRQ) || defined(CONFIG_SPARC)
@@ -93,7 +105,6 @@ static inline void of_msi_configure(struct device *dev, struct device_node *np)
  * so declare it here regardless of the CONFIG_OF_IRQ setting.
  */
 extern unsigned int irq_of_parse_and_map(struct device_node *node, int index);
-u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in);
 
 #else /* !CONFIG_OF && !CONFIG_SPARC */
 static inline unsigned int irq_of_parse_and_map(struct device_node *dev,
@@ -101,12 +112,6 @@ static inline unsigned int irq_of_parse_and_map(struct device_node *dev,
 {
         return 0;
 }
-
-static inline u32 of_msi_map_rid(struct device *dev,
-                                 struct device_node *msi_np, u32 rid_in)
-{
-        return rid_in;
-}
 #endif /* !CONFIG_OF */
 
 #endif /* __OF_IRQ_H */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index e828e7b4afec..6ae25aae88fd 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -412,9 +412,18 @@ struct pci_host_bridge {
         void (*release_fn)(struct pci_host_bridge *);
         void *release_data;
         unsigned int ignore_reset_delay:1;      /* for entire hierarchy */
+        /* Resource alignment requirements */
+        resource_size_t (*align_resource)(struct pci_dev *dev,
+                        const struct resource *res,
+                        resource_size_t start,
+                        resource_size_t size,
+                        resource_size_t align);
 };
 
 #define to_pci_host_bridge(n) container_of(n, struct pci_host_bridge, dev)
+
+struct pci_host_bridge *pci_find_host_bridge(struct pci_bus *bus);
+
 void pci_set_host_bridge_release(struct pci_host_bridge *bridge,
                      void (*release_fn)(struct pci_host_bridge *),
                      void *release_data);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index d841d33bcdc9..f9828a48f16a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -697,9 +697,11 @@ struct perf_cgroup {
  * if there is no cgroup event for the current CPU context.
  */
 static inline struct perf_cgroup *
-perf_cgroup_from_task(struct task_struct *task)
+perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx)
 {
-        return container_of(task_css(task, perf_event_cgrp_id),
+        return container_of(task_css_check(task, perf_event_cgrp_id,
+                                           ctx ? lockdep_is_held(&ctx->lock)
+                                               : true),
                             struct perf_cgroup, css);
 }
 #endif /* CONFIG_CGROUP_PERF */
diff --git a/include/linux/proportions.h b/include/linux/proportions.h
index 5440f64d2942..21221338ad18 100644
--- a/include/linux/proportions.h
+++ b/include/linux/proportions.h
@@ -1,7 +1,7 @@
 /*
  * FLoating proportions
  *
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * This file contains the public data structure and API definitions.
  */
diff --git a/include/linux/scpi_protocol.h b/include/linux/scpi_protocol.h
index 80af3cd35ae4..72ce932c69b2 100644
--- a/include/linux/scpi_protocol.h
+++ b/include/linux/scpi_protocol.h
@@ -71,7 +71,7 @@ struct scpi_ops {
         int (*sensor_get_value)(u16, u32 *);
 };
 
-#if IS_ENABLED(CONFIG_ARM_SCPI_PROTOCOL)
+#if IS_REACHABLE(CONFIG_ARM_SCPI_PROTOCOL)
 struct scpi_ops *get_scpi_ops(void);
 #else
 static inline struct scpi_ops *get_scpi_ops(void) { return NULL; }
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 0adedca24c5b..0e1b1540597a 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -99,7 +99,7 @@ static inline int try_stop_cpus(const struct cpumask *cpumask,
  * grabbing every spinlock (and more).  So the "read" side to such a
  * lock is anything which disables preemption.
  */
-#if defined(CONFIG_STOP_MACHINE) && defined(CONFIG_SMP)
+#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU)
 
 /**
  * stop_machine: freeze the machine on all CPUs and run this function
@@ -118,7 +118,7 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus);
 
 int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
                                    const struct cpumask *cpus);
-#else    /* CONFIG_STOP_MACHINE && CONFIG_SMP */
+#else   /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
 
 static inline int stop_machine(cpu_stop_fn_t fn, void *data,
                                  const struct cpumask *cpus)
@@ -137,5 +137,5 @@ static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
         return stop_machine(fn, data, cpus);
 }
 
-#endif  /* CONFIG_STOP_MACHINE && CONFIG_SMP */
+#endif  /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
 #endif  /* _LINUX_STOP_MACHINE */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a156b82dd14c..c2b66a277e98 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -524,7 +524,7 @@ asmlinkage long sys_chown(const char __user *filename,
 asmlinkage long sys_lchown(const char __user *filename,
                                 uid_t user, gid_t group);
 asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group);
-#ifdef CONFIG_UID16
+#ifdef CONFIG_HAVE_UID16
 asmlinkage long sys_chown16(const char __user *filename,
                                 old_uid_t user, old_gid_t group);
 asmlinkage long sys_lchown16(const char __user *filename,
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 4014a59828fc..613c29bd6baf 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -438,7 +438,8 @@ static inline void thermal_zone_device_unregister(
 static inline int thermal_zone_bind_cooling_device(
         struct thermal_zone_device *tz, int trip,
         struct thermal_cooling_device *cdev,
-        unsigned long upper, unsigned long lower)
+        unsigned long upper, unsigned long lower,
+        unsigned int weight)
 { return -ENODEV; }
 static inline int thermal_zone_unbind_cooling_device(
         struct thermal_zone_device *tz, int trip,
diff --git a/include/linux/types.h b/include/linux/types.h
index 70d8500bddf1..70dd3dfde631 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -35,7 +35,7 @@ typedef __kernel_gid16_t        gid16_t;
 
 typedef unsigned long           uintptr_t;
 
-#ifdef CONFIG_UID16
+#ifdef CONFIG_HAVE_UID16
 /* This is defined by include/asm-{arch}/posix_types.h */
 typedef __kernel_old_uid_t      old_uid_t;
 typedef __kernel_old_gid_t      old_gid_t;
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 0bdc72f36905..4a29c75b146e 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -21,7 +21,7 @@
  * Authors:
  *      Srikar Dronamraju
  *      Jim Keniston
- * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/errno.h>
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index 9948c874e3f1..1d0043dc34e4 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -47,4 +47,7 @@
 /* device generates spurious wakeup, ignore remote wakeup capability */
 #define USB_QUIRK_IGNORE_REMOTE_WAKEUP          BIT(9)
 
+/* device can't handle Link Power Management */
+#define USB_QUIRK_NO_LPM                        BIT(10)
+
 #endif /* __LINUX_USB_QUIRKS_H */
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 610a86a892b8..ddb440975382 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -44,9 +44,6 @@ struct vfio_device_ops {
         void    (*request)(void *device_data, unsigned int count);
 };
 
-extern struct iommu_group *vfio_iommu_group_get(struct device *dev);
-extern void vfio_iommu_group_put(struct iommu_group *group, struct device *dev);
-
 extern int vfio_add_group_dev(struct device *dev,
                               const struct vfio_device_ops *ops,
                               void *device_data);
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 1e1bf9f963a9..513b36f04dfd 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -145,7 +145,7 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old)
         list_del(&old->task_list);
 }
 
-typedef int wait_bit_action_f(struct wait_bit_key *);
+typedef int wait_bit_action_f(struct wait_bit_key *, int mode);
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
@@ -960,10 +960,10 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
         } while (0)
 
 
-extern int bit_wait(struct wait_bit_key *);
-extern int bit_wait_io(struct wait_bit_key *);
-extern int bit_wait_timeout(struct wait_bit_key *);
-extern int bit_wait_io_timeout(struct wait_bit_key *);
+extern int bit_wait(struct wait_bit_key *, int);
+extern int bit_wait_io(struct wait_bit_key *, int);
+extern int bit_wait_timeout(struct wait_bit_key *, int);
+extern int bit_wait_io_timeout(struct wait_bit_key *, int);
 
 /**
  * wait_on_bit - wait for a bit to be cleared
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index b36d837c701e..2a91a0561a47 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -62,6 +62,7 @@ struct unix_sock {
 #define UNIX_GC_CANDIDATE       0
 #define UNIX_GC_MAYBE_CYCLE     1
         struct socket_wq        peer_wq;
+        wait_queue_t            peer_wake;
 };
 
 static inline struct unix_sock *unix_sk(const struct sock *sk)
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 2bfb2ad2fab1..877f682989b8 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -133,27 +133,18 @@ void rt6_clean_tohost(struct net *net, struct in6_addr *gateway);
 /*
  *      Store a destination cache entry in a socket
  */
-static inline void __ip6_dst_store(struct sock *sk, struct dst_entry *dst,
-                                   const struct in6_addr *daddr,
-                                   const struct in6_addr *saddr)
+static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst,
+                                 const struct in6_addr *daddr,
+                                 const struct in6_addr *saddr)
 {
         struct ipv6_pinfo *np = inet6_sk(sk);
-        struct rt6_info *rt = (struct rt6_info *) dst;
 
+        np->dst_cookie = rt6_get_cookie((struct rt6_info *)dst);
         sk_setup_caps(sk, dst);
         np->daddr_cache = daddr;
 #ifdef CONFIG_IPV6_SUBTREES
         np->saddr_cache = saddr;
 #endif
-        np->dst_cookie = rt6_get_cookie(rt);
-}
-
-static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst,
-                                 struct in6_addr *daddr, struct in6_addr *saddr)
-{
-        spin_lock(&sk->sk_dst_lock);
-        __ip6_dst_store(sk, dst, daddr, saddr);
-        spin_unlock(&sk->sk_dst_lock);
 }
 
 static inline bool ipv6_unicast_destination(const struct sk_buff *skb)
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index e1a10b0ac0b0..9a5c9f013784 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -205,6 +205,7 @@ extern rwlock_t ip6_ra_lock;
  */
 
 struct ipv6_txoptions {
+        atomic_t                refcnt;
         /* Length of this structure */
         int                     tot_len;
 
@@ -217,7 +218,7 @@ struct ipv6_txoptions {
         struct ipv6_opt_hdr     *dst0opt;
         struct ipv6_rt_hdr      *srcrt; /* Routing Header */
         struct ipv6_opt_hdr     *dst1opt;
-
+        struct rcu_head         rcu;
         /* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */
 };
 
@@ -252,6 +253,24 @@ struct ipv6_fl_socklist {
         struct rcu_head                 rcu;
 };
 
+static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np)
+{
+        struct ipv6_txoptions *opt;
+
+        rcu_read_lock();
+        opt = rcu_dereference(np->opt);
+        if (opt && !atomic_inc_not_zero(&opt->refcnt))
+                opt = NULL;
+        rcu_read_unlock();
+        return opt;
+}
+
+static inline void txopt_put(struct ipv6_txoptions *opt)
+{
+        if (opt && atomic_dec_and_test(&opt->refcnt))
+                kfree_rcu(opt, rcu);
+}
+
 struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label);
 struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
                                          struct ip6_flowlabel *fl,
@@ -490,6 +509,7 @@ struct ip6_create_arg {
         u32 user;
         const struct in6_addr *src;
         const struct in6_addr *dst;
+        int iif;
         u8 ecn;
 };
 
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 82045fca388b..760bc4d5a2cf 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2003,8 +2003,10 @@ enum ieee80211_hw_flags {
  *      it shouldn't be set.
  *
  * @max_tx_aggregation_subframes: maximum number of subframes in an
- *      aggregate an HT driver will transmit, used by the peer as a
- *      hint to size its reorder buffer.
+ *      aggregate an HT driver will transmit. Though ADDBA will advertise
+ *      a constant value of 64 as some older APs can crash if the window
+ *      size is smaller (an example is LinkSys WRT120N with FW v1.0.07
+ *      build 002 Jun 18 2012).
  *
  * @offchannel_tx_hw_queue: HW queue ID to use for offchannel TX
  *      (if %IEEE80211_HW_QUEUE_CONTROL is set)
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index bf3937431030..2d8edaad29cb 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -181,8 +181,7 @@ void ndisc_cleanup(void);
 int ndisc_rcv(struct sk_buff *skb);
 
 void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
-                   const struct in6_addr *daddr, const struct in6_addr *saddr,
-                   struct sk_buff *oskb);
+                   const struct in6_addr *daddr, const struct in6_addr *saddr);
 
 void ndisc_send_rs(struct net_device *dev,
                    const struct in6_addr *saddr, const struct in6_addr *daddr);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 4c79ce8c1f92..b2a8e6338576 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -61,6 +61,9 @@ struct Qdisc {
                                       */
 #define TCQ_F_WARN_NONWC        (1 << 16)
 #define TCQ_F_CPUSTATS          0x20 /* run using percpu statistics */
+#define TCQ_F_NOPARENT          0x40 /* root of its hierarchy :
+                                      * qdisc_tree_decrease_qlen() should stop.
+                                      */
         u32                     limit;
         const struct Qdisc_ops  *ops;
         struct qdisc_size_table __rcu *stab;
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 495c87e367b3..7bbb71081aeb 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -775,10 +775,10 @@ struct sctp_transport {
                 hb_sent:1,
 
                 /* Is the Path MTU update pending on this tranport */
-                pmtu_pending:1;
+                pmtu_pending:1,
 
-        /* Has this transport moved the ctsn since we last sacked */
-        __u32 sack_generation;
+                /* Has this transport moved the ctsn since we last sacked */
+                sack_generation:1;
         u32 dst_cookie;
 
         struct flowi fl;
@@ -1482,19 +1482,19 @@ struct sctp_association {
                         prsctp_capable:1,   /* Can peer do PR-SCTP? */
                         auth_capable:1;     /* Is peer doing SCTP-AUTH? */
 
-                /* Ack State   : This flag indicates if the next received
+                /* sack_needed : This flag indicates if the next received
                  *             : packet is to be responded to with a
-                 *             : SACK. This is initializedto 0.  When a packet
-                 *             : is received it is incremented. If this value
+                 *             : SACK. This is initialized to 0.  When a packet
+                 *             : is received sack_cnt is incremented. If this value
                  *             : reaches 2 or more, a SACK is sent and the
                  *             : value is reset to 0. Note: This is used only
                  *             : when no DATA chunks are received out of
                  *             : order.  When DATA chunks are out of order,
                  *             : SACK's are not delayed (see Section 6).
                  */
-                __u8    sack_needed;     /* Do we need to sack the peer? */
+                __u8    sack_needed:1,     /* Do we need to sack the peer? */
+                        sack_generation:1;
                 __u32   sack_cnt;
-                __u32   sack_generation;
 
                 __u32   adaptation_ind;  /* Adaptation Code point. */
 
diff --git a/include/net/sock.h b/include/net/sock.h
index 7f89e4ba18d1..52d27ee924f4 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -254,7 +254,6 @@ struct cg_proto;
   *     @sk_wq: sock wait queue and async head
   *     @sk_rx_dst: receive input route used by early demux
   *     @sk_dst_cache: destination cache
-  *     @sk_dst_lock: destination cache lock
   *     @sk_policy: flow policy
   *     @sk_receive_queue: incoming packets
   *     @sk_wmem_alloc: transmit queue bytes committed
@@ -384,14 +383,16 @@ struct sock {
         int                     sk_rcvbuf;
 
         struct sk_filter __rcu  *sk_filter;
-        struct socket_wq __rcu  *sk_wq;
-
+        union {
+                struct socket_wq __rcu  *sk_wq;
+                struct socket_wq        *sk_wq_raw;
+        };
 #ifdef CONFIG_XFRM
         struct xfrm_policy      *sk_policy[2];
 #endif
         struct dst_entry        *sk_rx_dst;
         struct dst_entry __rcu  *sk_dst_cache;
-        spinlock_t              sk_dst_lock;
+        /* Note: 32bit hole on 64bit arches */
         atomic_t                sk_wmem_alloc;
         atomic_t                sk_omem_alloc;
         int                     sk_sndbuf;
@@ -2005,10 +2006,27 @@ static inline unsigned long sock_wspace(struct sock *sk)
         return amt;
 }
 
-static inline void sk_wake_async(struct sock *sk, int how, int band)
+/* Note:
+ *  We use sk->sk_wq_raw, from contexts knowing this
+ *  pointer is not NULL and cannot disappear/change.
+ */
+static inline void sk_set_bit(int nr, struct sock *sk)
 {
-        if (sock_flag(sk, SOCK_FASYNC))
-                sock_wake_async(sk->sk_socket, how, band);
+        set_bit(nr, &sk->sk_wq_raw->flags);
+}
+
+static inline void sk_clear_bit(int nr, struct sock *sk)
+{
+        clear_bit(nr, &sk->sk_wq_raw->flags);
+}
+
+static inline void sk_wake_async(const struct sock *sk, int how, int band)
+{
+        if (sock_flag(sk, SOCK_FASYNC)) {
+                rcu_read_lock();
+                sock_wake_async(rcu_dereference(sk->sk_wq), how, band);
+                rcu_read_unlock();
+        }
 }
 
 /* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might
diff --git a/include/rdma/ib_mad.h b/include/rdma/ib_mad.h
index 188df91d5851..ec9b44dd3d80 100644
--- a/include/rdma/ib_mad.h
+++ b/include/rdma/ib_mad.h
@@ -237,6 +237,8 @@ struct ib_vendor_mad {
         u8                      data[IB_MGMT_VENDOR_DATA];
 };
 
+#define IB_MGMT_CLASSPORTINFO_ATTR_ID   cpu_to_be16(0x0001)
+
 struct ib_class_port_info {
         u8                      base_version;
         u8                      class_version;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 9a68a19532ba..120da1d7f57e 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1271,6 +1271,7 @@ struct ib_uobject {
         int                     id;             /* index into kernel idr */
         struct kref             ref;
         struct rw_semaphore     mutex;          /* protects .live */
+        struct rcu_head         rcu;            /* kfree_rcu() overhead */
         int                     live;
 };
 
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index ed527121031d..fcfa3d7f5e7e 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -668,6 +668,9 @@ struct Scsi_Host {
         unsigned use_blk_mq:1;
         unsigned use_cmd_list:1;
 
+        /* Host responded with short (<36 bytes) INQUIRY result */
+        unsigned short_inquiry:1;
+
         /*
          * Optional work queue to be utilized by the transport
          */
diff --git a/include/sound/hda_register.h b/include/sound/hda_register.h
index 2ae8812d7b1a..94dc6a9772e0 100644
--- a/include/sound/hda_register.h
+++ b/include/sound/hda_register.h
@@ -93,6 +93,9 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 };
 #define AZX_REG_HSW_EM4                 0x100c
 #define AZX_REG_HSW_EM5                 0x1010
 
+/* Skylake/Broxton display HD-A controller Extended Mode registers */
+#define AZX_REG_SKL_EM4L                0x1040
+
 /* PCI space */
 #define AZX_PCIREG_TCSEL                0x44
 
diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index 7855cfe46b69..95a937eafb79 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -398,6 +398,7 @@ int snd_soc_dapm_del_routes(struct snd_soc_dapm_context *dapm,
 int snd_soc_dapm_weak_routes(struct snd_soc_dapm_context *dapm,
                              const struct snd_soc_dapm_route *route, int num);
 void snd_soc_dapm_free_widget(struct snd_soc_dapm_widget *w);
+void snd_soc_dapm_reset_cache(struct snd_soc_dapm_context *dapm);
 
 /* dapm events */
 void snd_soc_dapm_stream_event(struct snd_soc_pcm_runtime *rtd, int stream,
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 0a2c74008e53..aabf0aca0171 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -474,7 +474,7 @@ struct se_cmd {
         struct completion       cmd_wait_comp;
         const struct target_core_fabric_ops *se_tfo;
         sense_reason_t          (*execute_cmd)(struct se_cmd *);
-        sense_reason_t (*transport_complete_callback)(struct se_cmd *, bool);
+        sense_reason_t (*transport_complete_callback)(struct se_cmd *, bool, int *);
         void                    *protocol_data;
 
         unsigned char           *t_task_cdb;
diff --git a/include/uapi/linux/nfs.h b/include/uapi/linux/nfs.h
index 654bae3f1a38..5e6296160361 100644
--- a/include/uapi/linux/nfs.h
+++ b/include/uapi/linux/nfs.h
@@ -33,17 +33,6 @@
 
 #define NFS_PIPE_DIRNAME "nfs"
 
-/* NFS ioctls */
-/* Let's follow btrfs lead on CLONE to avoid messing userspace */
-#define NFS_IOC_CLONE           _IOW(0x94, 9, int)
-#define NFS_IOC_CLONE_RANGE     _IOW(0x94, 13, int)
-
-struct nfs_ioctl_clone_range_args {
-        __s64 src_fd;
-        __u64 src_off, count;
-        __u64 dst_off;
-};
-
 /*
  * NFS stats. The good thing with these values is that NFSv3 errors are
  * a superset of NFSv2 errors (with the exception of NFSERR_WFLUSH which
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 751b69f858c8..9fd7b5d8df2f 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -39,13 +39,6 @@
 #define VFIO_SPAPR_TCE_v2_IOMMU         7
 
 /*
- * The No-IOMMU IOMMU offers no translation or isolation for devices and
- * supports no ioctls outside of VFIO_CHECK_EXTENSION.  Use of VFIO's No-IOMMU
- * code will taint the host kernel and should be used with extreme caution.
- */
-#define VFIO_NOIOMMU_IOMMU              8
-
-/*
  * The IOCTL interface is designed for extensibility by embedding the
  * structure length (argsz) and flags into structures passed between
  * kernel and userspace.  We therefore use the _IO() macro for these
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index 85dedca3dcfb..eeba75395f7d 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -343,7 +343,6 @@ struct ipu_client_platformdata {
         int di;
         int dc;
         int dp;
-        int dmfc;
         int dma[2];
 };
 
diff --git a/init/Kconfig b/init/Kconfig
index c24b6f767bf0..235c7a2c0d20 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -2030,13 +2030,6 @@ config INIT_ALL_POSSIBLE
           it was better to provide this option than to break all the archs
           and have several arch maintainers pursuing me down dark alleys.
 
-config STOP_MACHINE
-        bool
-        default y
-        depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU
-        help
-          Need stop_machine() primitive.
-
 source "block/Kconfig"
 
 config PREEMPT_NOTIFIERS
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 3f4c99e06c6b..b0799bced518 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -28,11 +28,17 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
             attr->value_size == 0)
                 return ERR_PTR(-EINVAL);
 
+        if (attr->value_size >= 1 << (KMALLOC_SHIFT_MAX - 1))
+                /* if value_size is bigger, the user space won't be able to
+                 * access the elements.
+                 */
+                return ERR_PTR(-E2BIG);
+
         elem_size = round_up(attr->value_size, 8);
 
         /* check round_up into zero and u32 overflow */
         if (elem_size == 0 ||
-            attr->max_entries > (U32_MAX - sizeof(*array)) / elem_size)
+            attr->max_entries > (U32_MAX - PAGE_SIZE - sizeof(*array)) / elem_size)
                 return ERR_PTR(-ENOMEM);
 
         array_size = sizeof(*array) + attr->max_entries * elem_size;
@@ -105,7 +111,7 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
                 /* all elements already exist */
                 return -EEXIST;
 
-        memcpy(array->value + array->elem_size * index, value, array->elem_size);
+        memcpy(array->value + array->elem_size * index, value, map->value_size);
         return 0;
 }
 
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 19909b22b4f8..34777b3746fa 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -64,12 +64,35 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
                  */
                 goto free_htab;
 
-        err = -ENOMEM;
+        if (htab->map.value_size >= (1 << (KMALLOC_SHIFT_MAX - 1)) -
+            MAX_BPF_STACK - sizeof(struct htab_elem))
+                /* if value_size is bigger, the user space won't be able to
+                 * access the elements via bpf syscall. This check also makes
+                 * sure that the elem_size doesn't overflow and it's
+                 * kmalloc-able later in htab_map_update_elem()
+                 */
+                goto free_htab;
+
+        htab->elem_size = sizeof(struct htab_elem) +
+                          round_up(htab->map.key_size, 8) +
+                          htab->map.value_size;
+
         /* prevent zero size kmalloc and check for u32 overflow */
         if (htab->n_buckets == 0 ||
             htab->n_buckets > U32_MAX / sizeof(struct hlist_head))
                 goto free_htab;
 
+        if ((u64) htab->n_buckets * sizeof(struct hlist_head) +
+            (u64) htab->elem_size * htab->map.max_entries >=
+            U32_MAX - PAGE_SIZE)
+                /* make sure page count doesn't overflow */
+                goto free_htab;
+
+        htab->map.pages = round_up(htab->n_buckets * sizeof(struct hlist_head) +
+                                   htab->elem_size * htab->map.max_entries,
+                                   PAGE_SIZE) >> PAGE_SHIFT;
+
+        err = -ENOMEM;
         htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct hlist_head),
                                       GFP_USER | __GFP_NOWARN);
 
@@ -85,13 +108,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
         raw_spin_lock_init(&htab->lock);
         htab->count = 0;
 
-        htab->elem_size = sizeof(struct htab_elem) +
-                          round_up(htab->map.key_size, 8) +
-                          htab->map.value_size;
-
-        htab->map.pages = round_up(htab->n_buckets * sizeof(struct hlist_head) +
-                                   htab->elem_size * htab->map.max_entries,
-                                   PAGE_SIZE) >> PAGE_SHIFT;
         return &htab->map;
 
 free_htab:
@@ -222,7 +238,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
         WARN_ON_ONCE(!rcu_read_lock_held());
 
         /* allocate new element outside of lock */
-        l_new = kmalloc(htab->elem_size, GFP_ATOMIC);
+        l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN);
         if (!l_new)
                 return -ENOMEM;
 
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index be6d726e31c9..5a8a797d50b7 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -34,7 +34,7 @@ static void *bpf_any_get(void *raw, enum bpf_type type)
                 atomic_inc(&((struct bpf_prog *)raw)->aux->refcnt);
                 break;
         case BPF_TYPE_MAP:
-                atomic_inc(&((struct bpf_map *)raw)->refcnt);
+                bpf_map_inc(raw, true);
                 break;
         default:
                 WARN_ON_ONCE(1);
@@ -51,7 +51,7 @@ static void bpf_any_put(void *raw, enum bpf_type type)
                 bpf_prog_put(raw);
                 break;
         case BPF_TYPE_MAP:
-                bpf_map_put(raw);
+                bpf_map_put_with_uref(raw);
                 break;
         default:
                 WARN_ON_ONCE(1);
@@ -64,7 +64,7 @@ static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type)
         void *raw;
 
         *type = BPF_TYPE_MAP;
-        raw = bpf_map_get(ufd);
+        raw = bpf_map_get_with_uref(ufd);
         if (IS_ERR(raw)) {
                 *type = BPF_TYPE_PROG;
                 raw = bpf_prog_get(ufd);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0d3313d02a7e..3b39550d8485 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -82,6 +82,14 @@ static void bpf_map_free_deferred(struct work_struct *work)
         map->ops->map_free(map);
 }
 
+static void bpf_map_put_uref(struct bpf_map *map)
+{
+        if (atomic_dec_and_test(&map->usercnt)) {
+                if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
+                        bpf_fd_array_map_clear(map);
+        }
+}
+
 /* decrement map refcnt and schedule it for freeing via workqueue
  * (unrelying map implementation ops->map_free() might sleep)
  */
@@ -93,17 +101,15 @@ void bpf_map_put(struct bpf_map *map)
         }
 }
 
-static int bpf_map_release(struct inode *inode, struct file *filp)
+void bpf_map_put_with_uref(struct bpf_map *map)
 {
-        struct bpf_map *map = filp->private_data;
-
-        if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
-                /* prog_array stores refcnt-ed bpf_prog pointers
-                 * release them all when user space closes prog_array_fd
-                 */
-                bpf_fd_array_map_clear(map);
-
+        bpf_map_put_uref(map);
         bpf_map_put(map);
+}
+
+static int bpf_map_release(struct inode *inode, struct file *filp)
+{
+        bpf_map_put_with_uref(filp->private_data);
         return 0;
 }
 
@@ -142,6 +148,7 @@ static int map_create(union bpf_attr *attr)
                 return PTR_ERR(map);
 
         atomic_set(&map->refcnt, 1);
+        atomic_set(&map->usercnt, 1);
 
         err = bpf_map_charge_memlock(map);
         if (err)
@@ -174,7 +181,14 @@ struct bpf_map *__bpf_map_get(struct fd f)
         return f.file->private_data;
 }
 
-struct bpf_map *bpf_map_get(u32 ufd)
+void bpf_map_inc(struct bpf_map *map, bool uref)
+{
+        atomic_inc(&map->refcnt);
+        if (uref)
+                atomic_inc(&map->usercnt);
+}
+
+struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 {
         struct fd f = fdget(ufd);
         struct bpf_map *map;
@@ -183,7 +197,7 @@ struct bpf_map *bpf_map_get(u32 ufd)
         if (IS_ERR(map))
                 return map;
 
-        atomic_inc(&map->refcnt);
+        bpf_map_inc(map, true);
         fdput(f);
 
         return map;
@@ -226,7 +240,7 @@ static int map_lookup_elem(union bpf_attr *attr)
                 goto free_key;
 
         err = -ENOMEM;
-        value = kmalloc(map->value_size, GFP_USER);
+        value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN);
         if (!value)
                 goto free_key;
 
@@ -285,7 +299,7 @@ static int map_update_elem(union bpf_attr *attr)
                 goto free_key;
 
         err = -ENOMEM;
-        value = kmalloc(map->value_size, GFP_USER);
+        value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN);
         if (!value)
                 goto free_key;
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c6073056badf..a7945d10b378 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2021,8 +2021,7 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
                          * will be used by the valid program until it's unloaded
                          * and all maps are released in free_bpf_prog_info()
                          */
-                        atomic_inc(&map->refcnt);
-
+                        bpf_map_inc(map, false);
                         fdput(f);
 next_insn:
                         insn++;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index f1603c153890..470f6536b9e8 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -98,6 +98,12 @@ static DEFINE_SPINLOCK(css_set_lock);
 static DEFINE_SPINLOCK(cgroup_idr_lock);
 
 /*
+ * Protects cgroup_file->kn for !self csses.  It synchronizes notifications
+ * against file removal/re-creation across css hiding.
+ */
+static DEFINE_SPINLOCK(cgroup_file_kn_lock);
+
+/*
  * Protects cgroup_subsys->release_agent_path.  Modifying it also requires
  * cgroup_mutex.  Reading requires either cgroup_mutex or this spinlock.
  */
@@ -754,9 +760,11 @@ static void put_css_set_locked(struct css_set *cset)
         if (!atomic_dec_and_test(&cset->refcount))
                 return;
 
-        /* This css_set is dead. unlink it and release cgroup refcounts */
-        for_each_subsys(ss, ssid)
+        /* This css_set is dead. unlink it and release cgroup and css refs */
+        for_each_subsys(ss, ssid) {
                 list_del(&cset->e_cset_node[ssid]);
+                css_put(cset->subsys[ssid]);
+        }
         hash_del(&cset->hlist);
         css_set_count--;
 
@@ -1056,9 +1064,13 @@ static struct css_set *find_css_set(struct css_set *old_cset,
         key = css_set_hash(cset->subsys);
         hash_add(css_set_table, &cset->hlist, key);
 
-        for_each_subsys(ss, ssid)
+        for_each_subsys(ss, ssid) {
+                struct cgroup_subsys_state *css = cset->subsys[ssid];
+
                 list_add_tail(&cset->e_cset_node[ssid],
-                              &cset->subsys[ssid]->cgroup->e_csets[ssid]);
+                              &css->cgroup->e_csets[ssid]);
+                css_get(css);
+        }
 
         spin_unlock_bh(&css_set_lock);
 
@@ -1393,6 +1405,16 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
         char name[CGROUP_FILE_NAME_MAX];
 
         lockdep_assert_held(&cgroup_mutex);
+
+        if (cft->file_offset) {
+                struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss);
+                struct cgroup_file *cfile = (void *)css + cft->file_offset;
+
+                spin_lock_irq(&cgroup_file_kn_lock);
+                cfile->kn = NULL;
+                spin_unlock_irq(&cgroup_file_kn_lock);
+        }
+
         kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));
 }
 
@@ -1856,7 +1878,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 
         INIT_LIST_HEAD(&cgrp->self.sibling);
         INIT_LIST_HEAD(&cgrp->self.children);
-        INIT_LIST_HEAD(&cgrp->self.files);
         INIT_LIST_HEAD(&cgrp->cset_links);
         INIT_LIST_HEAD(&cgrp->pidlists);
         mutex_init(&cgrp->pidlist_mutex);
@@ -2216,6 +2237,9 @@ struct cgroup_taskset {
         struct list_head        src_csets;
         struct list_head        dst_csets;
 
+        /* the subsys currently being processed */
+        int                     ssid;
+
         /*
          * Fields for cgroup_taskset_*() iteration.
          *
@@ -2278,25 +2302,29 @@ static void cgroup_taskset_add(struct task_struct *task,
 /**
  * cgroup_taskset_first - reset taskset and return the first task
  * @tset: taskset of interest
+ * @dst_cssp: output variable for the destination css
  *
  * @tset iteration is initialized and the first task is returned.
  */
-struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
+struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
+                                         struct cgroup_subsys_state **dst_cssp)
 {
         tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node);
         tset->cur_task = NULL;
 
-        return cgroup_taskset_next(tset);
+        return cgroup_taskset_next(tset, dst_cssp);
 }
 
 /**
  * cgroup_taskset_next - iterate to the next task in taskset
  * @tset: taskset of interest
+ * @dst_cssp: output variable for the destination css
  *
  * Return the next task in @tset.  Iteration must have been initialized
  * with cgroup_taskset_first().
  */
-struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
+struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
+                                        struct cgroup_subsys_state **dst_cssp)
 {
         struct css_set *cset = tset->cur_cset;
         struct task_struct *task = tset->cur_task;
@@ -2311,6 +2339,18 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
                 if (&task->cg_list != &cset->mg_tasks) {
                         tset->cur_cset = cset;
                         tset->cur_task = task;
+
+                        /*
+                         * This function may be called both before and
+                         * after cgroup_taskset_migrate().  The two cases
+                         * can be distinguished by looking at whether @cset
+                         * has its ->mg_dst_cset set.
+                         */
+                        if (cset->mg_dst_cset)
+                                *dst_cssp = cset->mg_dst_cset->subsys[tset->ssid];
+                        else
+                                *dst_cssp = cset->subsys[tset->ssid];
+
                         return task;
                 }
 
@@ -2346,7 +2386,8 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
         /* check that we can legitimately attach to the cgroup */
         for_each_e_css(css, i, dst_cgrp) {
                 if (css->ss->can_attach) {
-                        ret = css->ss->can_attach(css, tset);
+                        tset->ssid = i;
+                        ret = css->ss->can_attach(tset);
                         if (ret) {
                                 failed_css = css;
                                 goto out_cancel_attach;
@@ -2379,9 +2420,12 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
          */
         tset->csets = &tset->dst_csets;
 
-        for_each_e_css(css, i, dst_cgrp)
-                if (css->ss->attach)
-                        css->ss->attach(css, tset);
+        for_each_e_css(css, i, dst_cgrp) {
+                if (css->ss->attach) {
+                        tset->ssid = i;
+                        css->ss->attach(tset);
+                }
+        }
 
         ret = 0;
         goto out_release_tset;
@@ -2390,8 +2434,10 @@ out_cancel_attach:
         for_each_e_css(css, i, dst_cgrp) {
                 if (css == failed_css)
                         break;
-                if (css->ss->cancel_attach)
-                        css->ss->cancel_attach(css, tset);
+                if (css->ss->cancel_attach) {
+                        tset->ssid = i;
+                        css->ss->cancel_attach(tset);
+                }
         }
 out_release_tset:
         spin_lock_bh(&css_set_lock);
@@ -3313,9 +3359,9 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
         if (cft->file_offset) {
                 struct cgroup_file *cfile = (void *)css + cft->file_offset;
 
-                kernfs_get(kn);
+                spin_lock_irq(&cgroup_file_kn_lock);
                 cfile->kn = kn;
-                list_add(&cfile->node, &css->files);
+                spin_unlock_irq(&cgroup_file_kn_lock);
         }
 
         return 0;
@@ -3553,6 +3599,22 @@ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 }
 
 /**
+ * cgroup_file_notify - generate a file modified event for a cgroup_file
+ * @cfile: target cgroup_file
+ *
+ * @cfile must have been obtained by setting cftype->file_offset.
+ */
+void cgroup_file_notify(struct cgroup_file *cfile)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&cgroup_file_kn_lock, flags);
+        if (cfile->kn)
+                kernfs_notify(cfile->kn);
+        spin_unlock_irqrestore(&cgroup_file_kn_lock, flags);
+}
+
+/**
  * cgroup_task_count - count the number of tasks in a cgroup.
  * @cgrp: the cgroup in question
  *
@@ -4613,13 +4675,9 @@ static void css_free_work_fn(struct work_struct *work)
                 container_of(work, struct cgroup_subsys_state, destroy_work);
         struct cgroup_subsys *ss = css->ss;
         struct cgroup *cgrp = css->cgroup;
-        struct cgroup_file *cfile;
 
         percpu_ref_exit(&css->refcnt);
 
-        list_for_each_entry(cfile, &css->files, node)
-                kernfs_put(cfile->kn);
-
         if (ss) {
                 /* css free path */
                 int id = css->id;
@@ -4724,7 +4782,6 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
         css->ss = ss;
         INIT_LIST_HEAD(&css->sibling);
         INIT_LIST_HEAD(&css->children);
-        INIT_LIST_HEAD(&css->files);
         css->serial_nr = css_serial_nr_next++;
 
         if (cgroup_parent(cgrp)) {
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index f1b30ad5dc6d..2d3df82c54f2 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -155,12 +155,10 @@ static void freezer_css_free(struct cgroup_subsys_state *css)
  * @freezer->lock.  freezer_attach() makes the new tasks conform to the
  * current state and all following state changes can see the new tasks.
  */
-static void freezer_attach(struct cgroup_subsys_state *new_css,
-                           struct cgroup_taskset *tset)
+static void freezer_attach(struct cgroup_taskset *tset)
 {
-        struct freezer *freezer = css_freezer(new_css);
         struct task_struct *task;
-        bool clear_frozen = false;
+        struct cgroup_subsys_state *new_css;
 
         mutex_lock(&freezer_mutex);
 
@@ -174,22 +172,21 @@ static void freezer_attach(struct cgroup_subsys_state *new_css,
          * current state before executing the following - !frozen tasks may
          * be visible in a FROZEN cgroup and frozen tasks in a THAWED one.
          */
-        cgroup_taskset_for_each(task, tset) {
+        cgroup_taskset_for_each(task, new_css, tset) {
+                struct freezer *freezer = css_freezer(new_css);
+
                 if (!(freezer->state & CGROUP_FREEZING)) {
                         __thaw_task(task);
                 } else {
                         freeze_task(task);
-                        freezer->state &= ~CGROUP_FROZEN;
-                        clear_frozen = true;
+                        /* clear FROZEN and propagate upwards */
+                        while (freezer && (freezer->state & CGROUP_FROZEN)) {
+                                freezer->state &= ~CGROUP_FROZEN;
+                                freezer = parent_freezer(freezer);
+                        }
                 }
         }
 
-        /* propagate FROZEN clearing upwards */
-        while (clear_frozen && (freezer = parent_freezer(freezer))) {
-                freezer->state &= ~CGROUP_FROZEN;
-                clear_frozen = freezer->state & CGROUP_FREEZING;
-        }
-
         mutex_unlock(&freezer_mutex);
 }
 
diff --git a/kernel/cgroup_pids.c b/kernel/cgroup_pids.c
index cdd8df4e991c..b50d5a167fda 100644
--- a/kernel/cgroup_pids.c
+++ b/kernel/cgroup_pids.c
@@ -106,7 +106,7 @@ static void pids_uncharge(struct pids_cgroup *pids, int num)
 {
         struct pids_cgroup *p;
 
-        for (p = pids; p; p = parent_pids(p))
+        for (p = pids; parent_pids(p); p = parent_pids(p))
                 pids_cancel(p, num);
 }
 
@@ -123,7 +123,7 @@ static void pids_charge(struct pids_cgroup *pids, int num)
 {
         struct pids_cgroup *p;
 
-        for (p = pids; p; p = parent_pids(p))
+        for (p = pids; parent_pids(p); p = parent_pids(p))
                 atomic64_add(num, &p->counter);
 }
 
@@ -140,7 +140,7 @@ static int pids_try_charge(struct pids_cgroup *pids, int num)
 {
         struct pids_cgroup *p, *q;
 
-        for (p = pids; p; p = parent_pids(p)) {
+        for (p = pids; parent_pids(p); p = parent_pids(p)) {
                 int64_t new = atomic64_add_return(num, &p->counter);
 
                 /*
@@ -162,13 +162,13 @@ revert:
         return -EAGAIN;
 }
 
-static int pids_can_attach(struct cgroup_subsys_state *css,
-                           struct cgroup_taskset *tset)
+static int pids_can_attach(struct cgroup_taskset *tset)
 {
-        struct pids_cgroup *pids = css_pids(css);
         struct task_struct *task;
+        struct cgroup_subsys_state *dst_css;
 
-        cgroup_taskset_for_each(task, tset) {
+        cgroup_taskset_for_each(task, dst_css, tset) {
+                struct pids_cgroup *pids = css_pids(dst_css);
                 struct cgroup_subsys_state *old_css;
                 struct pids_cgroup *old_pids;
 
@@ -187,13 +187,13 @@ static int pids_can_attach(struct cgroup_subsys_state *css,
         return 0;
 }
 
-static void pids_cancel_attach(struct cgroup_subsys_state *css,
-                               struct cgroup_taskset *tset)
+static void pids_cancel_attach(struct cgroup_taskset *tset)
 {
-        struct pids_cgroup *pids = css_pids(css);
         struct task_struct *task;
+        struct cgroup_subsys_state *dst_css;
 
-        cgroup_taskset_for_each(task, tset) {
+        cgroup_taskset_for_each(task, dst_css, tset) {
+                struct pids_cgroup *pids = css_pids(dst_css);
                 struct cgroup_subsys_state *old_css;
                 struct pids_cgroup *old_pids;
 
@@ -205,65 +205,28 @@ static void pids_cancel_attach(struct cgroup_subsys_state *css,
         }
 }
 
+/*
+ * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies
+ * on threadgroup_change_begin() held by the copy_process().
+ */
 static int pids_can_fork(struct task_struct *task, void **priv_p)
 {
         struct cgroup_subsys_state *css;
         struct pids_cgroup *pids;
-        int err;
 
-        /*
-         * Use the "current" task_css for the pids subsystem as the tentative
-         * css. It is possible we will charge the wrong hierarchy, in which
-         * case we will forcefully revert/reapply the charge on the right
-         * hierarchy after it is committed to the task proper.
-         */
-        css = task_get_css(current, pids_cgrp_id);
+        css = task_css_check(current, pids_cgrp_id, true);
         pids = css_pids(css);
-
-        err = pids_try_charge(pids, 1);
-        if (err)
-                goto err_css_put;
-
-        *priv_p = css;
-        return 0;
-
-err_css_put:
-        css_put(css);
-        return err;
+        return pids_try_charge(pids, 1);
 }
 
 static void pids_cancel_fork(struct task_struct *task, void *priv)
 {
-        struct cgroup_subsys_state *css = priv;
-        struct pids_cgroup *pids = css_pids(css);
-
-        pids_uncharge(pids, 1);
-        css_put(css);
-}
-
-static void pids_fork(struct task_struct *task, void *priv)
-{
         struct cgroup_subsys_state *css;
-        struct cgroup_subsys_state *old_css = priv;
         struct pids_cgroup *pids;
-        struct pids_cgroup *old_pids = css_pids(old_css);
 
-        css = task_get_css(task, pids_cgrp_id);
+        css = task_css_check(current, pids_cgrp_id, true);
         pids = css_pids(css);
-
-        /*
-         * If the association has changed, we have to revert and reapply the
-         * charge/uncharge on the wrong hierarchy to the current one. Since
-         * the association can only change due to an organisation event, its
-         * okay for us to ignore the limit in this case.
-         */
-        if (pids != old_pids) {
-                pids_uncharge(old_pids, 1);
-                pids_charge(pids, 1);
-        }
-
-        css_put(css);
-        css_put(old_css);
+        pids_uncharge(pids, 1);
 }
 
 static void pids_free(struct task_struct *task)
@@ -335,6 +298,7 @@ static struct cftype pids_files[] = {
         {
                 .name = "current",
                 .read_s64 = pids_current_read,
+                .flags = CFTYPE_NOT_ON_ROOT,
         },
         { }     /* terminate */
 };
@@ -346,7 +310,6 @@ struct cgroup_subsys pids_cgrp_subsys = {
         .cancel_attach  = pids_cancel_attach,
         .can_fork       = pids_can_fork,
         .cancel_fork    = pids_cancel_fork,
-        .fork           = pids_fork,
         .free           = pids_free,
         .legacy_cftypes = pids_files,
         .dfl_cftypes    = pids_files,
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 10ae73611d80..02a8ea5c9963 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1429,15 +1429,16 @@ static int fmeter_getrate(struct fmeter *fmp)
 static struct cpuset *cpuset_attach_old_cs;
 
 /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */
-static int cpuset_can_attach(struct cgroup_subsys_state *css,
-                             struct cgroup_taskset *tset)
+static int cpuset_can_attach(struct cgroup_taskset *tset)
 {
-        struct cpuset *cs = css_cs(css);
+        struct cgroup_subsys_state *css;
+        struct cpuset *cs;
         struct task_struct *task;
         int ret;
 
         /* used later by cpuset_attach() */
-        cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset));
+        cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css));
+        cs = css_cs(css);
 
         mutex_lock(&cpuset_mutex);
 
@@ -1447,7 +1448,7 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css,
             (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
                 goto out_unlock;
 
-        cgroup_taskset_for_each(task, tset) {
+        cgroup_taskset_for_each(task, css, tset) {
                 ret = task_can_attach(task, cs->cpus_allowed);
                 if (ret)
                         goto out_unlock;
@@ -1467,9 +1468,14 @@ out_unlock:
         return ret;
 }
 
-static void cpuset_cancel_attach(struct cgroup_subsys_state *css,
-                                 struct cgroup_taskset *tset)
+static void cpuset_cancel_attach(struct cgroup_taskset *tset)
 {
+        struct cgroup_subsys_state *css;
+        struct cpuset *cs;
+
+        cgroup_taskset_first(tset, &css);
+        cs = css_cs(css);
+
         mutex_lock(&cpuset_mutex);
         css_cs(css)->attach_in_progress--;
         mutex_unlock(&cpuset_mutex);
@@ -1482,16 +1488,19 @@ static void cpuset_cancel_attach(struct cgroup_subsys_state *css,
  */
 static cpumask_var_t cpus_attach;
 
-static void cpuset_attach(struct cgroup_subsys_state *css,
-                          struct cgroup_taskset *tset)
+static void cpuset_attach(struct cgroup_taskset *tset)
 {
         /* static buf protected by cpuset_mutex */
         static nodemask_t cpuset_attach_nodemask_to;
         struct task_struct *task;
         struct task_struct *leader;
-        struct cpuset *cs = css_cs(css);
+        struct cgroup_subsys_state *css;
+        struct cpuset *cs;
         struct cpuset *oldcs = cpuset_attach_old_cs;
 
+        cgroup_taskset_first(tset, &css);
+        cs = css_cs(css);
+
         mutex_lock(&cpuset_mutex);
 
         /* prepare for attach */
@@ -1502,7 +1511,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 
         guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
 
-        cgroup_taskset_for_each(task, tset) {
+        cgroup_taskset_for_each(task, css, tset) {
                 /*
                  * can_attach beforehand should guarantee that this doesn't
                  * fail.  TODO: have a better way to handle failure here
@@ -1518,7 +1527,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
          * sleep and should be moved outside migration path proper.
          */
         cpuset_attach_nodemask_to = cs->effective_mems;
-        cgroup_taskset_for_each_leader(leader, tset) {
+        cgroup_taskset_for_each_leader(leader, css, tset) {
                 struct mm_struct *mm = get_task_mm(leader);
 
                 if (mm) {
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index d659487254d5..9c418002b8c1 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -3,7 +3,7 @@
  *
  *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
  *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
- *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
  *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  *
  * For licensing details see kernel-base/COPYING
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 36babfd20648..ef2d6ea10736 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3,7 +3,7 @@
  *
  *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
  *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
- *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
  *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  *
  * For licensing details see kernel-base/COPYING
@@ -435,7 +435,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event)
         if (!is_cgroup_event(event))
                 return;
 
-        cgrp = perf_cgroup_from_task(current);
+        cgrp = perf_cgroup_from_task(current, event->ctx);
         /*
          * Do not update time when cgroup is not active
          */
@@ -458,7 +458,7 @@ perf_cgroup_set_timestamp(struct task_struct *task,
         if (!task || !ctx->nr_cgroups)
                 return;
 
-        cgrp = perf_cgroup_from_task(task);
+        cgrp = perf_cgroup_from_task(task, ctx);
         info = this_cpu_ptr(cgrp->info);
         info->timestamp = ctx->timestamp;
 }
@@ -489,7 +489,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode)
          * we reschedule only in the presence of cgroup
          * constrained events.
          */
-        rcu_read_lock();
 
         list_for_each_entry_rcu(pmu, &pmus, entry) {
                 cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
@@ -522,8 +521,10 @@ static void perf_cgroup_switch(struct task_struct *task, int mode)
                                  * set cgrp before ctxsw in to allow
                                  * event_filter_match() to not have to pass
                                  * task around
+                                 * we pass the cpuctx->ctx to perf_cgroup_from_task()
+                                 * because cgorup events are only per-cpu
                                  */
-                                cpuctx->cgrp = perf_cgroup_from_task(task);
+                                cpuctx->cgrp = perf_cgroup_from_task(task, &cpuctx->ctx);
                                 cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
                         }
                         perf_pmu_enable(cpuctx->ctx.pmu);
@@ -531,8 +532,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode)
                 }
         }
 
-        rcu_read_unlock();
-
         local_irq_restore(flags);
 }
 
@@ -542,17 +541,20 @@ static inline void perf_cgroup_sched_out(struct task_struct *task,
         struct perf_cgroup *cgrp1;
         struct perf_cgroup *cgrp2 = NULL;
 
+        rcu_read_lock();
         /*
          * we come here when we know perf_cgroup_events > 0
+         * we do not need to pass the ctx here because we know
+         * we are holding the rcu lock
          */
-        cgrp1 = perf_cgroup_from_task(task);
+        cgrp1 = perf_cgroup_from_task(task, NULL);
 
         /*
          * next is NULL when called from perf_event_enable_on_exec()
          * that will systematically cause a cgroup_switch()
          */
         if (next)
-                cgrp2 = perf_cgroup_from_task(next);
+                cgrp2 = perf_cgroup_from_task(next, NULL);
 
         /*
          * only schedule out current cgroup events if we know
@@ -561,6 +563,8 @@ static inline void perf_cgroup_sched_out(struct task_struct *task,
          */
         if (cgrp1 != cgrp2)
                 perf_cgroup_switch(task, PERF_CGROUP_SWOUT);
+
+        rcu_read_unlock();
 }
 
 static inline void perf_cgroup_sched_in(struct task_struct *prev,
@@ -569,13 +573,16 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev,
         struct perf_cgroup *cgrp1;
         struct perf_cgroup *cgrp2 = NULL;
 
+        rcu_read_lock();
         /*
          * we come here when we know perf_cgroup_events > 0
+         * we do not need to pass the ctx here because we know
+         * we are holding the rcu lock
          */
-        cgrp1 = perf_cgroup_from_task(task);
+        cgrp1 = perf_cgroup_from_task(task, NULL);
 
         /* prev can never be NULL */
-        cgrp2 = perf_cgroup_from_task(prev);
+        cgrp2 = perf_cgroup_from_task(prev, NULL);
 
         /*
          * only need to schedule in cgroup events if we are changing
@@ -584,6 +591,8 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev,
          */
         if (cgrp1 != cgrp2)
                 perf_cgroup_switch(task, PERF_CGROUP_SWIN);
+
+        rcu_read_unlock();
 }
 
 static inline int perf_cgroup_connect(int fd, struct perf_event *event,
@@ -4216,7 +4225,14 @@ retry:
                 goto retry;
         }
 
-        __perf_event_period(&pe);
+        if (event->attr.freq) {
+                event->attr.sample_freq = value;
+        } else {
+                event->attr.sample_period = value;
+                event->hw.sample_period = value;
+        }
+
+        local64_set(&event->hw.period_left, 0);
         raw_spin_unlock_irq(&ctx->lock);
 
         return 0;
@@ -5667,6 +5683,17 @@ perf_event_aux_ctx(struct perf_event_context *ctx,
 }
 
 static void
+perf_event_aux_task_ctx(perf_event_aux_output_cb output, void *data,
+                        struct perf_event_context *task_ctx)
+{
+        rcu_read_lock();
+        preempt_disable();
+        perf_event_aux_ctx(task_ctx, output, data);
+        preempt_enable();
+        rcu_read_unlock();
+}
+
+static void
 perf_event_aux(perf_event_aux_output_cb output, void *data,
                struct perf_event_context *task_ctx)
 {
@@ -5675,14 +5702,23 @@ perf_event_aux(perf_event_aux_output_cb output, void *data,
         struct pmu *pmu;
         int ctxn;
 
+        /*
+         * If we have task_ctx != NULL we only notify
+         * the task context itself. The task_ctx is set
+         * only for EXIT events before releasing task
+         * context.
+         */
+        if (task_ctx) {
+                perf_event_aux_task_ctx(output, data, task_ctx);
+                return;
+        }
+
         rcu_read_lock();
         list_for_each_entry_rcu(pmu, &pmus, entry) {
                 cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
                 if (cpuctx->unique_pmu != pmu)
                         goto next;
                 perf_event_aux_ctx(&cpuctx->ctx, output, data);
-                if (task_ctx)
-                        goto next;
                 ctxn = pmu->task_ctx_nr;
                 if (ctxn < 0)
                         goto next;
@@ -5692,12 +5728,6 @@ perf_event_aux(perf_event_aux_output_cb output, void *data,
 next:
                 put_cpu_ptr(pmu->pmu_cpu_context);
         }
-
-        if (task_ctx) {
-                preempt_disable();
-                perf_event_aux_ctx(task_ctx, output, data);
-                preempt_enable();
-        }
         rcu_read_unlock();
 }
 
@@ -8787,10 +8817,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
         struct perf_event_context *child_ctx, *clone_ctx = NULL;
         unsigned long flags;
 
-        if (likely(!child->perf_event_ctxp[ctxn])) {
-                perf_event_task(child, NULL, 0);
+        if (likely(!child->perf_event_ctxp[ctxn]))
                 return;
-        }
 
         local_irq_save(flags);
         /*
@@ -8874,6 +8902,14 @@ void perf_event_exit_task(struct task_struct *child)
 
         for_each_task_context_nr(ctxn)
                 perf_event_exit_task_context(child, ctxn);
+
+        /*
+         * The perf_event_exit_task_context calls perf_event_task
+         * with child's task_ctx, which generates EXIT events for
+         * child contexts and sets child->perf_event_ctxp[] to NULL.
+         * At this point we need to send EXIT events to cpu contexts.
+         */
+        perf_event_task(child, NULL, 0);
 }
 
 static void perf_free_event(struct perf_event *event,
@@ -9452,16 +9488,18 @@ static void perf_cgroup_css_free(struct cgroup_subsys_state *css)
 static int __perf_cgroup_move(void *info)
 {
         struct task_struct *task = info;
+        rcu_read_lock();
         perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN);
+        rcu_read_unlock();
         return 0;
 }
 
-static void perf_cgroup_attach(struct cgroup_subsys_state *css,
-                               struct cgroup_taskset *tset)
+static void perf_cgroup_attach(struct cgroup_taskset *tset)
 {
         struct task_struct *task;
+        struct cgroup_subsys_state *css;
 
-        cgroup_taskset_for_each(task, tset)
+        cgroup_taskset_for_each(task, css, tset)
                 task_function_call(task, __perf_cgroup_move, task);
 }
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index b5d1ea79c595..adfdc0536117 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -3,7 +3,7 @@
  *
  *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
  *  Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
- *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra
  *  Copyright  ©  2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  *
  * For licensing details see kernel-base/COPYING
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 4e5e9798aa0c..7dad84913abf 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -19,7 +19,7 @@
  * Authors:
  *      Srikar Dronamraju
  *      Jim Keniston
- * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/kernel.h>
diff --git a/kernel/fork.c b/kernel/fork.c
index f97f2c449f5c..fce002ee3ddf 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1368,8 +1368,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
         p->real_start_time = ktime_get_boot_ns();
         p->io_context = NULL;
         p->audit_context = NULL;
-        if (clone_flags & CLONE_THREAD)
-                threadgroup_change_begin(current);
+        threadgroup_change_begin(current);
         cgroup_fork(p);
 #ifdef CONFIG_NUMA
         p->mempolicy = mpol_dup(p->mempolicy);
@@ -1610,8 +1609,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
         proc_fork_connector(p);
         cgroup_post_fork(p, cgrp_ss_priv);
-        if (clone_flags & CLONE_THREAD)
-                threadgroup_change_end(current);
+        threadgroup_change_end(current);
         perf_event_fork(p);
 
         trace_task_newtask(p, clone_flags);
@@ -1652,8 +1650,7 @@ bad_fork_cleanup_policy:
         mpol_put(p->mempolicy);
 bad_fork_cleanup_threadgroup_lock:
 #endif
-        if (clone_flags & CLONE_THREAD)
-                threadgroup_change_end(current);
+        threadgroup_change_end(current);
         delayacct_tsk_free(p);
 bad_fork_cleanup_count:
         atomic_dec(&p->cred->user->processes);
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index cbf9fb899d92..bcf107ce0854 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra
  *
  * Provides a framework for enqueueing and running callbacks from hardirq
  * context. The enqueueing is NMI-safe.
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index f7dd15d537f9..05254eeb4b4e 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -2,7 +2,7 @@
  * jump label support
  *
  * Copyright (C) 2009 Jason Baron <jbaron@redhat.com>
- * Copyright (C) 2011 Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2011 Peter Zijlstra
  *
  */
 #include <linux/memory.h>
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index deae3907ac1e..60ace56618f6 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -6,7 +6,7 @@
  * Started by Ingo Molnar:
  *
  *  Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * this code maps all the lock dependencies as they occur in a live kernel
  * and will warn about the following classes of locking bugs:
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index d83d798bef95..dbb61a302548 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -6,7 +6,7 @@
  * Started by Ingo Molnar:
  *
  *  Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * Code for /proc/lockdep and /proc/lockdep_stats:
  *
diff --git a/kernel/pid.c b/kernel/pid.c
index ca368793808e..78b3d9f80d44 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -467,7 +467,7 @@ struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
         rcu_read_lock();
         if (type != PIDTYPE_PID)
                 task = task->group_leader;
-        pid = get_pid(task->pids[type].pid);
+        pid = get_pid(rcu_dereference(task->pids[type].pid));
         rcu_read_unlock();
         return pid;
 }
@@ -528,7 +528,7 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
         if (likely(pid_alive(task))) {
                 if (type != PIDTYPE_PID)
                         task = task->group_leader;
-                nr = pid_nr_ns(task->pids[type].pid, ns);
+                nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns);
         }
         rcu_read_unlock();
 
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c0a205101c23..caf4041f5b0a 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -1,7 +1,7 @@
 /*
  * sched_clock for unstable cpu clocks
  *
- *  Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra
  *
  *  Updates and enhancements:
  *    Copyright (C) 2008 Red Hat, Inc. Steven Rostedt <srostedt@redhat.com>
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4d568ac9319e..732e993b564b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1947,13 +1947,38 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 #ifdef CONFIG_SMP
         /*
+         * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
+         * possible to, falsely, observe p->on_cpu == 0.
+         *
+         * One must be running (->on_cpu == 1) in order to remove oneself
+         * from the runqueue.
+         *
+         *  [S] ->on_cpu = 1;   [L] ->on_rq
+         *      UNLOCK rq->lock
+         *                      RMB
+         *      LOCK   rq->lock
+         *  [S] ->on_rq = 0;    [L] ->on_cpu
+         *
+         * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock
+         * from the consecutive calls to schedule(); the first switching to our
+         * task, the second putting it to sleep.
+         */
+        smp_rmb();
+
+        /*
          * If the owning (remote) cpu is still in the middle of schedule() with
          * this task as prev, wait until its done referencing the task.
          */
         while (p->on_cpu)
                 cpu_relax();
         /*
-         * Pairs with the smp_wmb() in finish_lock_switch().
+         * Combined with the control dependency above, we have an effective
+         * smp_load_acquire() without the need for full barriers.
+         *
+         * Pairs with the smp_store_release() in finish_lock_switch().
+         *
+         * This ensures that tasks getting woken will be fully ordered against
+         * their previous state and preserve Program Order.
          */
         smp_rmb();
 
@@ -2039,7 +2064,6 @@ out:
  */
 int wake_up_process(struct task_struct *p)
 {
-        WARN_ON(task_is_stopped_or_traced(p));
         return try_to_wake_up(p, TASK_NORMAL, 0);
 }
 EXPORT_SYMBOL(wake_up_process);
@@ -5847,13 +5871,13 @@ static int init_rootdomain(struct root_domain *rd)
 {
         memset(rd, 0, sizeof(*rd));
 
-        if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
+        if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL))
                 goto out;
-        if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
+        if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL))
                 goto free_span;
-        if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
+        if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
                 goto free_online;
-        if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+        if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
                 goto free_dlo_mask;
 
         init_dl_bw(&rd->dl_bw);
@@ -8217,12 +8241,12 @@ static void cpu_cgroup_fork(struct task_struct *task, void *private)
         sched_move_task(task);
 }
 
-static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
-                                 struct cgroup_taskset *tset)
+static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
 {
         struct task_struct *task;
+        struct cgroup_subsys_state *css;
 
-        cgroup_taskset_for_each(task, tset) {
+        cgroup_taskset_for_each(task, css, tset) {
 #ifdef CONFIG_RT_GROUP_SCHED
                 if (!sched_rt_can_attach(css_tg(css), task))
                         return -EINVAL;
@@ -8235,12 +8259,12 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
         return 0;
 }
 
-static void cpu_cgroup_attach(struct cgroup_subsys_state *css,
-                              struct cgroup_taskset *tset)
+static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 {
         struct task_struct *task;
+        struct cgroup_subsys_state *css;
 
-        cgroup_taskset_for_each(task, tset)
+        cgroup_taskset_for_each(task, css, tset)
                 sched_move_task(task);
 }
 
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 26a54461bf59..05de80b48586 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -788,6 +788,9 @@ cputime_t task_gtime(struct task_struct *t)
         unsigned int seq;
         cputime_t gtime;
 
+        if (!context_tracking_is_enabled())
+                return t->gtime;
+
         do {
                 seq = read_seqbegin(&t->vtime_seqlock);
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f04fda8f669c..90e26b11deaa 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -17,7 +17,7 @@
  *  Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
  *
  *  Adaptive scheduling granularity, math enhancements by Peter Zijlstra
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/latencytop.h>
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index e3cc16312046..8ec86abe0ea1 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -64,7 +64,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
         raw_spin_unlock(&rt_b->rt_runtime_lock);
 }
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(HAVE_RT_PUSH_IPI)
 static void push_irq_work_func(struct irq_work *work);
 #endif
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index efd3bfc7e347..b242775bf670 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1073,6 +1073,9 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
          * We must ensure this doesn't happen until the switch is completely
          * finished.
          *
+         * In particular, the load of prev->state in finish_task_switch() must
+         * happen before this.
+         *
          * Pairs with the control dependency and rmb in try_to_wake_up().
          */
         smp_store_release(&prev->on_cpu, 0);
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 052e02672d12..f15d6b6a538a 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -392,7 +392,7 @@ __wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q,
         do {
                 prepare_to_wait(wq, &q->wait, mode);
                 if (test_bit(q->key.bit_nr, q->key.flags))
-                        ret = (*action)(&q->key);
+                        ret = (*action)(&q->key, mode);
         } while (test_bit(q->key.bit_nr, q->key.flags) && !ret);
         finish_wait(wq, &q->wait);
         return ret;
@@ -431,7 +431,7 @@ __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
                 prepare_to_wait_exclusive(wq, &q->wait, mode);
                 if (!test_bit(q->key.bit_nr, q->key.flags))
                         continue;
-                ret = action(&q->key);
+                ret = action(&q->key, mode);
                 if (!ret)
                         continue;
                 abort_exclusive_wait(wq, &q->wait, mode, &q->key);
@@ -581,44 +581,44 @@ void wake_up_atomic_t(atomic_t *p)
 }
 EXPORT_SYMBOL(wake_up_atomic_t);
 
-__sched int bit_wait(struct wait_bit_key *word)
+__sched int bit_wait(struct wait_bit_key *word, int mode)
 {
-        if (signal_pending_state(current->state, current))
-                return 1;
         schedule();
+        if (signal_pending_state(mode, current))
+                return -EINTR;
         return 0;
 }
 EXPORT_SYMBOL(bit_wait);
 
-__sched int bit_wait_io(struct wait_bit_key *word)
+__sched int bit_wait_io(struct wait_bit_key *word, int mode)
 {
-        if (signal_pending_state(current->state, current))
-                return 1;
         io_schedule();
+        if (signal_pending_state(mode, current))
+                return -EINTR;
         return 0;
 }
 EXPORT_SYMBOL(bit_wait_io);
 
-__sched int bit_wait_timeout(struct wait_bit_key *word)
+__sched int bit_wait_timeout(struct wait_bit_key *word, int mode)
 {
         unsigned long now = READ_ONCE(jiffies);
-        if (signal_pending_state(current->state, current))
-                return 1;
         if (time_after_eq(now, word->timeout))
                 return -EAGAIN;
         schedule_timeout(word->timeout - now);
+        if (signal_pending_state(mode, current))
+                return -EINTR;
         return 0;
 }
 EXPORT_SYMBOL_GPL(bit_wait_timeout);
 
-__sched int bit_wait_io_timeout(struct wait_bit_key *word)
+__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode)
 {
         unsigned long now = READ_ONCE(jiffies);
-        if (signal_pending_state(current->state, current))
-                return 1;
         if (time_after_eq(now, word->timeout))
                 return -EAGAIN;
         io_schedule_timeout(word->timeout - now);
+        if (signal_pending_state(mode, current))
+                return -EINTR;
         return 0;
 }
 EXPORT_SYMBOL_GPL(bit_wait_io_timeout);
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 867bc20e1ef1..a3bbaee77c58 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -531,7 +531,7 @@ static int __init cpu_stop_init(void)
 }
 early_initcall(cpu_stop_init);
 
-#ifdef CONFIG_STOP_MACHINE
+#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU)
 
 static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus)
 {
@@ -631,4 +631,4 @@ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
         return ret ?: done.ret;
 }
 
-#endif  /* CONFIG_STOP_MACHINE */
+#endif  /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 75f1d05ea82d..9c6045a27ba3 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1887,12 +1887,6 @@ rb_event_index(struct ring_buffer_event *event)
         return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE;
 }
 
-static void rb_reset_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
-{
-        cpu_buffer->read_stamp = cpu_buffer->reader_page->page->time_stamp;
-        cpu_buffer->reader_page->read = 0;
-}
-
 static void rb_inc_iter(struct ring_buffer_iter *iter)
 {
         struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
@@ -2803,8 +2797,11 @@ rb_reserve_next_event(struct ring_buffer *buffer,
 
         event = __rb_reserve_next(cpu_buffer, &info);
 
-        if (unlikely(PTR_ERR(event) == -EAGAIN))
+        if (unlikely(PTR_ERR(event) == -EAGAIN)) {
+                if (info.add_timestamp)
+                        info.length -= RB_LEN_TIME_EXTEND;
                 goto again;
+        }
 
         if (!event)
                 goto out_fail;
@@ -3626,7 +3623,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 
         /* Finally update the reader page to the new head */
         cpu_buffer->reader_page = reader;
-        rb_reset_reader_page(cpu_buffer);
+        cpu_buffer->reader_page->read = 0;
 
         if (overwrite != cpu_buffer->last_overrun) {
                 cpu_buffer->lost_events = overwrite - cpu_buffer->last_overrun;
@@ -3636,6 +3633,10 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
         goto again;
 
  out:
+        /* Update the read_stamp on the first event */
+        if (reader && reader->read == 0)
+                cpu_buffer->read_stamp = reader->page->time_stamp;
+
         arch_spin_unlock(&cpu_buffer->lock);
         local_irq_restore(flags);
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index abfc903e741e..cc9f7a9319be 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -1,7 +1,7 @@
 /*
  * trace event based perf event profiling/tracing
  *
- * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra
  * Copyright (C) 2009-2010 Frederic Weisbecker <fweisbec@gmail.com>
  */
 
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 6bbc5f652355..4f6ef6912e00 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -582,6 +582,12 @@ static void __ftrace_clear_event_pids(struct trace_array *tr)
         unregister_trace_sched_wakeup(event_filter_pid_sched_wakeup_probe_pre, tr);
         unregister_trace_sched_wakeup(event_filter_pid_sched_wakeup_probe_post, tr);
 
+        unregister_trace_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre, tr);
+        unregister_trace_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post, tr);
+
+        unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_pre, tr);
+        unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_post, tr);
+
         list_for_each_entry(file, &tr->events, list) {
                 clear_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags);
         }
@@ -1729,6 +1735,16 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
                                                  tr, INT_MAX);
                 register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_post,
                                                  tr, 0);
+
+                register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre,
+                                                     tr, INT_MAX);
+                register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post,
+                                                     tr, 0);
+
+                register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_pre,
+                                                 tr, INT_MAX);
+                register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_post,
+                                                 tr, 0);
         }
 
         /*
diff --git a/lib/btree.c b/lib/btree.c
index 4264871ea1a0..f93a945274af 100644
--- a/lib/btree.c
+++ b/lib/btree.c
@@ -5,7 +5,7 @@
  *
  * Copyright (c) 2007-2008 Joern Engel <joern@logfs.org>
  * Bits and pieces stolen from Peter Zijlstra's code, which is
- * Copyright 2007, Red Hat Inc. Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright 2007, Red Hat Inc. Peter Zijlstra
  * GPLv2
  *
  * see http://programming.kicks-ass.net/kernel-patches/vma_lookup/btree.patch
diff --git a/lib/proportions.c b/lib/proportions.c
index 6f724298f67a..efa54f259ea9 100644
--- a/lib/proportions.c
+++ b/lib/proportions.c
@@ -1,7 +1,7 @@
 /*
  * Floating proportions
  *
- *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * Description:
  *
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 8ed2ffd963c5..7340353f8aea 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -957,8 +957,9 @@ EXPORT_SYMBOL(congestion_wait);
  * jiffies for either a BDI to exit congestion of the given @sync queue
  * or a write to complete.
  *
- * In the absence of zone congestion, cond_resched() is called to yield
- * the processor if necessary but otherwise does not sleep.
+ * In the absence of zone congestion, a short sleep or a cond_resched is
+ * performed to yield the processor and to allow other subsystems to make
+ * a forward progress.
  *
  * The return value is 0 if the sleep is for the full timeout. Otherwise,
  * it is the number of jiffies that were still remaining when the function
@@ -978,7 +979,19 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout)
          */
         if (atomic_read(&nr_wb_congested[sync]) == 0 ||
             !test_bit(ZONE_CONGESTED, &zone->flags)) {
-                cond_resched();
+
+                /*
+                 * Memory allocation/reclaim might be called from a WQ
+                 * context and the current implementation of the WQ
+                 * concurrency control doesn't recognize that a particular
+                 * WQ is congested if the worker thread is looping without
+                 * ever sleeping. Therefore we have to do a short sleep
+                 * here rather than calling cond_resched().
+                 */
+                if (current->flags & PF_WQ_WORKER)
+                        schedule_timeout(1);
+                else
+                        cond_resched();
 
                 /* In case we scheduled, work out time remaining */
                 ret = timeout - (jiffies - start);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 827bb02a43a4..ef6963b577fd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -372,8 +372,10 @@ retry_locked:
                 spin_unlock(&resv->lock);
 
                 trg = kmalloc(sizeof(*trg), GFP_KERNEL);
-                if (!trg)
+                if (!trg) {
+                        kfree(nrg);
                         return -ENOMEM;
+                }
 
                 spin_lock(&resv->lock);
                 list_add(&trg->link, &resv->region_cache);
@@ -483,8 +485,16 @@ static long region_del(struct resv_map *resv, long f, long t)
 retry:
         spin_lock(&resv->lock);
         list_for_each_entry_safe(rg, trg, head, link) {
-                if (rg->to <= f)
+                /*
+                 * Skip regions before the range to be deleted.  file_region
+                 * ranges are normally of the form [from, to).  However, there
+                 * may be a "placeholder" entry in the map which is of the form
+                 * (from, to) with from == to.  Check for placeholder entries
+                 * at the beginning of the range to be deleted.
+                 */
+                if (rg->to <= f && (rg->to != rg->from || rg->to != f))
                         continue;
+
                 if (rg->from >= t)
                         break;
 
@@ -1886,7 +1896,10 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
                 page = __alloc_buddy_huge_page_with_mpol(h, vma, addr);
                 if (!page)
                         goto out_uncharge_cgroup;
-
+                if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) {
+                        SetPagePrivate(page);
+                        h->resv_huge_pages--;
+                }
                 spin_lock(&hugetlb_lock);
                 list_move(&page->lru, &h->hugepage_activelist);
                 /* Fall through */
@@ -3693,12 +3706,12 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                 } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
                         return VM_FAULT_HWPOISON_LARGE |
                                 VM_FAULT_SET_HINDEX(hstate_index(h));
+        } else {
+                ptep = huge_pte_alloc(mm, address, huge_page_size(h));
+                if (!ptep)
+                        return VM_FAULT_OOM;
         }
 
-        ptep = huge_pte_alloc(mm, address, huge_page_size(h));
-        if (!ptep)
-                return VM_FAULT_OOM;
-
         mapping = vma->vm_file->f_mapping;
         idx = vma_hugecache_offset(h, vma, address);
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9acfb165eb52..e234c21a5e6c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2128,7 +2128,7 @@ done_restock:
          */
         do {
                 if (page_counter_read(&memcg->memory) > memcg->high) {
-                        current->memcg_nr_pages_over_high += nr_pages;
+                        current->memcg_nr_pages_over_high += batch;
                         set_notify_resume(current);
                         break;
                 }
@@ -4779,23 +4779,18 @@ static void mem_cgroup_clear_mc(void)
         spin_unlock(&mc.lock);
 }
 
-static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
-                                 struct cgroup_taskset *tset)
+static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
 {
-        struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+        struct cgroup_subsys_state *css;
+        struct mem_cgroup *memcg;
         struct mem_cgroup *from;
         struct task_struct *leader, *p;
         struct mm_struct *mm;
         unsigned long move_flags;
         int ret = 0;
 
-        /*
-         * We are now commited to this value whatever it is. Changes in this
-         * tunable will only affect upcoming migrations, not the current one.
-         * So we need to save it, and keep it going.
-         */
-        move_flags = READ_ONCE(memcg->move_charge_at_immigrate);
-        if (!move_flags)
+        /* charge immigration isn't supported on the default hierarchy */
+        if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
                 return 0;
 
         /*
@@ -4805,13 +4800,23 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
          * multiple.
          */
         p = NULL;
-        cgroup_taskset_for_each_leader(leader, tset) {
+        cgroup_taskset_for_each_leader(leader, css, tset) {
                 WARN_ON_ONCE(p);
                 p = leader;
+                memcg = mem_cgroup_from_css(css);
         }
         if (!p)
                 return 0;
 
+        /*
+         * We are now commited to this value whatever it is. Changes in this
+         * tunable will only affect upcoming migrations, not the current one.
+         * So we need to save it, and keep it going.
+         */
+        move_flags = READ_ONCE(memcg->move_charge_at_immigrate);
+        if (!move_flags)
+                return 0;
+
         from = mem_cgroup_from_task(p);
 
         VM_BUG_ON(from == memcg);
@@ -4842,8 +4847,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
         return ret;
 }
 
-static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css,
-                                     struct cgroup_taskset *tset)
+static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset)
 {
         if (mc.to)
                 mem_cgroup_clear_mc();
@@ -4985,10 +4989,10 @@ retry:
         atomic_dec(&mc.from->moving_account);
 }
 
-static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
-                                 struct cgroup_taskset *tset)
+static void mem_cgroup_move_task(struct cgroup_taskset *tset)
 {
-        struct task_struct *p = cgroup_taskset_first(tset);
+        struct cgroup_subsys_state *css;
+        struct task_struct *p = cgroup_taskset_first(tset, &css);
         struct mm_struct *mm = get_task_mm(p);
 
         if (mm) {
@@ -5000,17 +5004,14 @@ static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
                 mem_cgroup_clear_mc();
 }
 #else   /* !CONFIG_MMU */
-static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
-                                 struct cgroup_taskset *tset)
+static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
 {
         return 0;
 }
-static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css,
-                                     struct cgroup_taskset *tset)
+static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset)
 {
 }
-static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
-                                 struct cgroup_taskset *tset)
+static void mem_cgroup_move_task(struct cgroup_taskset *tset)
 {
 }
 #endif
@@ -5511,11 +5512,11 @@ void mem_cgroup_uncharge_list(struct list_head *page_list)
  * mem_cgroup_replace_page - migrate a charge to another page
  * @oldpage: currently charged page
  * @newpage: page to transfer the charge to
- * @lrucare: either or both pages might be on the LRU already
  *
  * Migrate the charge from @oldpage to @newpage.
  *
  * Both pages must be locked, @newpage->mapping must be set up.
+ * Either or both pages might be on the LRU already.
  */
 void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage)
 {
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index d13a33918fa2..c12680993ff3 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -608,6 +608,8 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p,
                         continue;
                 if (unlikely(p->flags & PF_KTHREAD))
                         continue;
+                if (is_global_init(p))
+                        continue;
                 if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
                         continue;
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 3e4d65445fa7..d15d88c8efa1 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2,7 +2,7 @@
  * mm/page-writeback.c
  *
  * Copyright (C) 2002, Linus Torvalds.
- * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
  *
  * Contains functions related to writing back dirty pages at the
  * address_space level.
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 17a3c66639a9..9d666df5ef95 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3647,8 +3647,9 @@ static void show_migration_types(unsigned char type)
 {
         static const char types[MIGRATE_TYPES] = {
                 [MIGRATE_UNMOVABLE]     = 'U',
-                [MIGRATE_RECLAIMABLE]   = 'E',
                 [MIGRATE_MOVABLE]       = 'M',
+                [MIGRATE_RECLAIMABLE]   = 'E',
+                [MIGRATE_HIGHATOMIC]    = 'H',
 #ifdef CONFIG_CMA
                 [MIGRATE_CMA]           = 'C',
 #endif
diff --git a/mm/shmem.c b/mm/shmem.c
index 9187eee4128b..2afcdbbdb685 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -843,14 +843,14 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
                 list_add_tail(&info->swaplist, &shmem_swaplist);
 
         if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {
-                swap_shmem_alloc(swap);
-                shmem_delete_from_page_cache(page, swp_to_radix_entry(swap));
-
                 spin_lock(&info->lock);
-                info->swapped++;
                 shmem_recalc_inode(inode);
+                info->swapped++;
                 spin_unlock(&info->lock);
 
+                swap_shmem_alloc(swap);
+                shmem_delete_from_page_cache(page, swp_to_radix_entry(swap));
+
                 mutex_unlock(&shmem_swaplist_mutex);
                 BUG_ON(page_mapped(page));
                 swap_writepage(page, wbc);
@@ -1078,7 +1078,7 @@ repeat:
         if (sgp != SGP_WRITE && sgp != SGP_FALLOC &&
             ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
                 error = -EINVAL;
-                goto failed;
+                goto unlock;
         }
 
         if (page && sgp == SGP_WRITE)
@@ -1246,11 +1246,15 @@ clear:
         /* Perhaps the file has been truncated since we checked */
         if (sgp != SGP_WRITE && sgp != SGP_FALLOC &&
             ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
+                if (alloced) {
+                        ClearPageDirty(page);
+                        delete_from_page_cache(page);
+                        spin_lock(&info->lock);
+                        shmem_recalc_inode(inode);
+                        spin_unlock(&info->lock);
+                }
                 error = -EINVAL;
-                if (alloced)
-                        goto trunc;
-                else
-                        goto failed;
+                goto unlock;
         }
         *pagep = page;
         return 0;
@@ -1258,23 +1262,13 @@ clear:
         /*
          * Error recovery.
          */
-trunc:
-        info = SHMEM_I(inode);
-        ClearPageDirty(page);
-        delete_from_page_cache(page);
-        spin_lock(&info->lock);
-        info->alloced--;
-        inode->i_blocks -= BLOCKS_PER_PAGE;
-        spin_unlock(&info->lock);
 decused:
-        sbinfo = SHMEM_SB(inode->i_sb);
         if (sbinfo->max_blocks)
                 percpu_counter_add(&sbinfo->used_blocks, -1);
 unacct:
         shmem_unacct_blocks(info->flags, 1);
 failed:
-        if (swap.val && error != -EINVAL &&
-            !shmem_confirm_swap(mapping, index, swap))
+        if (swap.val && !shmem_confirm_swap(mapping, index, swap))
                 error = -EEXIST;
 unlock:
         if (page) {
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 879a2be23325..0d5712b0206c 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -921,8 +921,8 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat,
 #ifdef CONFIG_PROC_FS
 static char * const migratetype_names[MIGRATE_TYPES] = {
         "Unmovable",
-        "Reclaimable",
         "Movable",
+        "Reclaimable",
         "HighAtomic",
 #ifdef CONFIG_CMA
         "CMA",
@@ -1379,6 +1379,7 @@ static const struct file_operations proc_vmstat_file_operations = {
 #endif /* CONFIG_PROC_FS */
 
 #ifdef CONFIG_SMP
+static struct workqueue_struct *vmstat_wq;
 static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
 int sysctl_stat_interval __read_mostly = HZ;
 static cpumask_var_t cpu_stat_off;
@@ -1391,7 +1392,7 @@ static void vmstat_update(struct work_struct *w)
                  * to occur in the future. Keep on running the
                  * update worker thread.
                  */
-                schedule_delayed_work_on(smp_processor_id(),
+                queue_delayed_work_on(smp_processor_id(), vmstat_wq,
                         this_cpu_ptr(&vmstat_work),
                         round_jiffies_relative(sysctl_stat_interval));
         } else {
@@ -1460,7 +1461,7 @@ static void vmstat_shepherd(struct work_struct *w)
                 if (need_update(cpu) &&
                         cpumask_test_and_clear_cpu(cpu, cpu_stat_off))
 
-                        schedule_delayed_work_on(cpu,
+                        queue_delayed_work_on(cpu, vmstat_wq,
                                 &per_cpu(vmstat_work, cpu), 0);
 
         put_online_cpus();
@@ -1549,6 +1550,7 @@ static int __init setup_vmstat(void)
 
         start_shepherd_timer();
         cpu_notifier_register_done();
+        vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
 #endif
 #ifdef CONFIG_PROC_FS
         proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index a3bffd1ec2b4..70306cc9d814 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -271,11 +271,11 @@ static long bt_sock_data_wait(struct sock *sk, long timeo)
                 if (signal_pending(current) || !timeo)
                         break;
 
-                set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+                sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
                 release_sock(sk);
                 timeo = schedule_timeout(timeo);
                 lock_sock(sk);
-                clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+                sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
         }
 
         __set_current_state(TASK_RUNNING);
@@ -441,7 +441,7 @@ unsigned int bt_sock_poll(struct file *file, struct socket *sock,
         if (!test_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags) && sock_writeable(sk))
                 mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
         else
-                set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+                sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
         return mask;
 }
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index c91353841e40..ffed8a1d4f27 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -3027,8 +3027,13 @@ static void smp_ready_cb(struct l2cap_chan *chan)
 
         BT_DBG("chan %p", chan);
 
+        /* No need to call l2cap_chan_hold() here since we already own
+         * the reference taken in smp_new_conn_cb(). This is just the
+         * first time that we tie it to a specific pointer. The code in
+         * l2cap_core.c ensures that there's no risk this function wont
+         * get called if smp_new_conn_cb was previously called.
+         */
         conn->smp = chan;
-        l2cap_chan_hold(chan);
 
         if (hcon->type == ACL_LINK && test_bit(HCI_CONN_ENCRYPT, &hcon->flags))
                 bredr_pairing(chan);
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index cc858919108e..aa209b1066c9 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -323,7 +323,7 @@ static long caif_stream_data_wait(struct sock *sk, long timeo)
                         !timeo)
                         break;
 
-                set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+                sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
                 release_sock(sk);
                 timeo = schedule_timeout(timeo);
                 lock_sock(sk);
@@ -331,7 +331,7 @@ static long caif_stream_data_wait(struct sock *sk, long timeo)
                 if (sock_flag(sk, SOCK_DEAD))
                         break;
 
-                clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+                sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
         }
 
         finish_wait(sk_sleep(sk), &wait);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 617088aee21d..d62af69ad844 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -785,7 +785,7 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
         if (sock_writeable(sk))
                 mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
         else
-                set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+                sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
         return mask;
 }
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index e6af42da28d9..f18ae91b652e 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2215,7 +2215,7 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
         ndm->ndm_pad2    = 0;
         ndm->ndm_flags   = pn->flags | NTF_PROXY;
         ndm->ndm_type    = RTN_UNICAST;
-        ndm->ndm_ifindex = pn->dev->ifindex;
+        ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0;
         ndm->ndm_state   = NUD_NONE;
 
         if (nla_put(skb, NDA_DST, tbl->key_len, pn->key))
@@ -2333,7 +2333,7 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
                 if (h > s_h)
                         s_idx = 0;
                 for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) {
-                        if (dev_net(n->dev) != net)
+                        if (pneigh_net(n) != net)
                                 continue;
                         if (idx < s_idx)
                                 goto next;
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 6441f47b1a8f..d9ee8d08a3a6 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -56,7 +56,7 @@ static void cgrp_css_free(struct cgroup_subsys_state *css)
         kfree(css_cls_state(css));
 }
 
-static int update_classid(const void *v, struct file *file, unsigned n)
+static int update_classid_sock(const void *v, struct file *file, unsigned n)
 {
         int err;
         struct socket *sock = sock_from_file(file, &err);
@@ -67,18 +67,27 @@ static int update_classid(const void *v, struct file *file, unsigned n)
         return 0;
 }
 
-static void cgrp_attach(struct cgroup_subsys_state *css,
-                        struct cgroup_taskset *tset)
+static void update_classid(struct cgroup_subsys_state *css, void *v)
 {
-        struct cgroup_cls_state *cs = css_cls_state(css);
-        void *v = (void *)(unsigned long)cs->classid;
+        struct css_task_iter it;
         struct task_struct *p;
 
-        cgroup_taskset_for_each(p, tset) {
+        css_task_iter_start(css, &it);
+        while ((p = css_task_iter_next(&it))) {
                 task_lock(p);
-                iterate_fd(p->files, 0, update_classid, v);
+                iterate_fd(p->files, 0, update_classid_sock, v);
                 task_unlock(p);
         }
+        css_task_iter_end(&it);
+}
+
+static void cgrp_attach(struct cgroup_taskset *tset)
+{
+        struct cgroup_subsys_state *css;
+
+        cgroup_taskset_first(tset, &css);
+        update_classid(css,
+                       (void *)(unsigned long)css_cls_state(css)->classid);
 }
 
 static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft)
@@ -89,8 +98,11 @@ static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft)
 static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
                          u64 value)
 {
-        css_cls_state(css)->classid = (u32) value;
+        struct cgroup_cls_state *cs = css_cls_state(css);
+
+        cs->classid = (u32)value;
 
+        update_classid(css, (void *)(unsigned long)cs->classid);
         return 0;
 }
 
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index cbd0a199bf52..40fd09fe06ae 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -218,13 +218,14 @@ static int update_netprio(const void *v, struct file *file, unsigned n)
         return 0;
 }
 
-static void net_prio_attach(struct cgroup_subsys_state *css,
-                            struct cgroup_taskset *tset)
+static void net_prio_attach(struct cgroup_taskset *tset)
 {
         struct task_struct *p;
-        void *v = (void *)(unsigned long)css->cgroup->id;
+        struct cgroup_subsys_state *css;
+
+        cgroup_taskset_for_each(p, css, tset) {
+                void *v = (void *)(unsigned long)css->cgroup->id;
 
-        cgroup_taskset_for_each(p, tset) {
                 task_lock(p);
                 iterate_fd(p->files, 0, update_netprio, v);
                 task_unlock(p);
diff --git a/net/core/scm.c b/net/core/scm.c
index 3b6899b7d810..8a1741b14302 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -305,6 +305,8 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
                         err = put_user(cmlen, &cm->cmsg_len);
                 if (!err) {
                         cmlen = CMSG_SPACE(i*sizeof(int));
+                        if (msg->msg_controllen < cmlen)
+                                cmlen = msg->msg_controllen;
                         msg->msg_control += cmlen;
                         msg->msg_controllen -= cmlen;
                 }
diff --git a/net/core/sock.c b/net/core/sock.c
index 1e4dd54bfb5a..e31dfcee1729 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1530,7 +1530,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
                 skb_queue_head_init(&newsk->sk_receive_queue);
                 skb_queue_head_init(&newsk->sk_write_queue);
 
-                spin_lock_init(&newsk->sk_dst_lock);
                 rwlock_init(&newsk->sk_callback_lock);
                 lockdep_set_class_and_name(&newsk->sk_callback_lock,
                                 af_callback_keys + newsk->sk_family,
@@ -1607,7 +1606,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 {
         u32 max_segs = 1;
 
-        __sk_dst_set(sk, dst);
+        sk_dst_set(sk, dst);
         sk->sk_route_caps = dst->dev->features;
         if (sk->sk_route_caps & NETIF_F_GSO)
                 sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
@@ -1815,7 +1814,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
 {
         DEFINE_WAIT(wait);
 
-        clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+        sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
         for (;;) {
                 if (!timeo)
                         break;
@@ -1861,7 +1860,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
                 if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf)
                         break;
 
-                set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+                sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
                 set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
                 err = -EAGAIN;
                 if (!timeo)
@@ -2048,9 +2047,9 @@ int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)
         DEFINE_WAIT(wait);
 
         prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-        set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+        sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
         rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb);
-        clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+        sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
         finish_wait(sk_sleep(sk), &wait);
         return rc;
 }
@@ -2388,7 +2387,6 @@ void sock_init_data(struct socket *sock, struct sock *sk)
         } else
                 sk->sk_wq       =       NULL;
 
-        spin_lock_init(&sk->sk_dst_lock);
         rwlock_init(&sk->sk_callback_lock);
         lockdep_set_class_and_name(&sk->sk_callback_lock,
                         af_callback_keys + sk->sk_family,
diff --git a/net/core/stream.c b/net/core/stream.c
index d70f77a0c889..b96f7a79e544 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -39,7 +39,7 @@ void sk_stream_write_space(struct sock *sk)
                         wake_up_interruptible_poll(&wq->wait, POLLOUT |
                                                 POLLWRNORM | POLLWRBAND);
                 if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN))
-                        sock_wake_async(sock, SOCK_WAKE_SPACE, POLL_OUT);
+                        sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT);
                 rcu_read_unlock();
         }
 }
@@ -126,7 +126,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
                 current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2;
 
         while (1) {
-                set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+                sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
                 prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 
@@ -139,7 +139,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
                 }
                 if (signal_pending(current))
                         goto do_interrupted;
-                clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+                sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
                 if (sk_stream_memory_free(sk) && !vm_wait)
                         break;
 
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index db5fc2440a23..9c6d0508e63a 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -202,7 +202,9 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req
         security_req_classify_flow(req, flowi6_to_flowi(&fl6));
 
 
-        final_p = fl6_update_dst(&fl6, np->opt, &final);
+        rcu_read_lock();
+        final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
+        rcu_read_unlock();
 
         dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
         if (IS_ERR(dst)) {
@@ -219,7 +221,10 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req
                                                          &ireq->ir_v6_loc_addr,
                                                          &ireq->ir_v6_rmt_addr);
                 fl6.daddr = ireq->ir_v6_rmt_addr;
-                err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+                rcu_read_lock();
+                err = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+                               np->tclass);
+                rcu_read_unlock();
                 err = net_xmit_eval(err);
         }
 
@@ -387,6 +392,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
         struct inet_request_sock *ireq = inet_rsk(req);
         struct ipv6_pinfo *newnp;
         const struct ipv6_pinfo *np = inet6_sk(sk);
+        struct ipv6_txoptions *opt;
         struct inet_sock *newinet;
         struct dccp6_sock *newdp6;
         struct sock *newsk;
@@ -453,7 +459,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
          * comment in that function for the gory details. -acme
          */
 
-        __ip6_dst_store(newsk, dst, NULL, NULL);
+        ip6_dst_store(newsk, dst, NULL, NULL);
         newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM |
                                                       NETIF_F_TSO);
         newdp6 = (struct dccp6_sock *)newsk;
@@ -488,13 +494,15 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
          * Yes, keeping reference count would be much more clever, but we make
          * one more one thing there: reattach optmem to newsk.
          */
-        if (np->opt != NULL)
-                newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+        opt = rcu_dereference(np->opt);
+        if (opt) {
+                opt = ipv6_dup_options(newsk, opt);
+                RCU_INIT_POINTER(newnp->opt, opt);
+        }
         inet_csk(newsk)->icsk_ext_hdr_len = 0;
-        if (newnp->opt != NULL)
-                inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
-                                                     newnp->opt->opt_flen);
+        if (opt)
+                inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+                                                    opt->opt_flen;
 
         dccp_sync_mss(newsk, dst_mtu(dst));
 
@@ -757,6 +765,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
         struct ipv6_pinfo *np = inet6_sk(sk);
         struct dccp_sock *dp = dccp_sk(sk);
         struct in6_addr *saddr = NULL, *final_p, final;
+        struct ipv6_txoptions *opt;
         struct flowi6 fl6;
         struct dst_entry *dst;
         int addr_type;
@@ -856,7 +865,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
         fl6.fl6_sport = inet->inet_sport;
         security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-        final_p = fl6_update_dst(&fl6, np->opt, &final);
+        opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+        final_p = fl6_update_dst(&fl6, opt, &final);
 
         dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
         if (IS_ERR(dst)) {
@@ -873,12 +883,11 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
         np->saddr = *saddr;
         inet->inet_rcv_saddr = LOOPBACK4_IPV6;
 
-        __ip6_dst_store(sk, dst, NULL, NULL);
+        ip6_dst_store(sk, dst, NULL, NULL);
 
         icsk->icsk_ext_hdr_len = 0;
-        if (np->opt != NULL)
-                icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
-                                          np->opt->opt_nflen);
+        if (opt)
+                icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen;
 
         inet->inet_dport = usin->sin6_port;
 
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index b5cf13a28009..41e65804ddf5 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -339,8 +339,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock,
                         if (sk_stream_is_writeable(sk)) {
                                 mask |= POLLOUT | POLLWRNORM;
                         } else {  /* send SIGIO later */
-                                set_bit(SOCK_ASYNC_NOSPACE,
-                                        &sk->sk_socket->flags);
+                                sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
                                 set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 
                                 /* Race breaker. If space is freed after
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 675cf94e04f8..eebf5ac8ce18 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1747,9 +1747,9 @@ static int dn_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
                 }
 
                 prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-                set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+                sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
                 sk_wait_event(sk, &timeo, dn_data_ready(sk, queue, flags, target));
-                clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+                sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
                 finish_wait(sk_sleep(sk), &wait);
         }
 
@@ -2004,10 +2004,10 @@ static int dn_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
                         }
 
                         prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-                        set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+                        sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
                         sk_wait_event(sk, &timeo,
                                       !dn_queue_too_long(scp, queue, flags));
-                        clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+                        sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
                         finish_wait(sk_sleep(sk), &wait);
                         continue;
                 }
diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c
index 4677b6fa6dda..ecc28cff08ab 100644
--- a/net/dns_resolver/dns_query.c
+++ b/net/dns_resolver/dns_query.c
@@ -67,7 +67,7 @@
  * Returns the size of the result on success, -ve error code otherwise.
  */
 int dns_query(const char *type, const char *name, size_t namelen,
-              const char *options, char **_result, time_t *_expiry)
+              const char *options, char **_result, time64_t *_expiry)
 {
         struct key *rkey;
         const struct user_key_payload *upayload;
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 35a9788bb3ae..c7d1adca30d8 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -312,7 +312,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master, u8 type)
         return;
 
 out:
-        WARN_ON_ONCE("HSR: Could not send supervision frame\n");
+        WARN_ONCE(1, "HSR: Could not send supervision frame\n");
         kfree_skb(skb);
 }
 
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 6baf36e11808..05e4cba14162 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2126,7 +2126,7 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
         ASSERT_RTNL();
 
         in_dev = ip_mc_find_dev(net, imr);
-        if (!in_dev) {
+        if (!imr->imr_ifindex && !imr->imr_address.s_addr && !in_dev) {
                 ret = -ENODEV;
                 goto out;
         }
@@ -2147,7 +2147,8 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
 
                 *imlp = iml->next_rcu;
 
-                ip_mc_dec_group(in_dev, group);
+                if (in_dev)
+                        ip_mc_dec_group(in_dev, group);
 
                 /* decrease mem now to avoid the memleak warning */
                 atomic_sub(sizeof(*iml), &sk->sk_omem_alloc);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 92dd4b74d513..c3a38353f5dc 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -134,7 +134,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
                               struct mfc_cache *c, struct rtmsg *rtm);
 static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
                                  int cmd);
-static void mroute_clean_tables(struct mr_table *mrt);
+static void mroute_clean_tables(struct mr_table *mrt, bool all);
 static void ipmr_expire_process(unsigned long arg);
 
 #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -350,7 +350,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
 static void ipmr_free_table(struct mr_table *mrt)
 {
         del_timer_sync(&mrt->ipmr_expire_timer);
-        mroute_clean_tables(mrt);
+        mroute_clean_tables(mrt, true);
         kfree(mrt);
 }
 
@@ -441,10 +441,6 @@ struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v)
         return dev;
 
 failure:
-        /* allow the register to be completed before unregistering. */
-        rtnl_unlock();
-        rtnl_lock();
-
         unregister_netdevice(dev);
         return NULL;
 }
@@ -540,10 +536,6 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
         return dev;
 
 failure:
-        /* allow the register to be completed before unregistering. */
-        rtnl_unlock();
-        rtnl_lock();
-
         unregister_netdevice(dev);
         return NULL;
 }
@@ -1208,7 +1200,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
  *      Close the multicast socket, and clear the vif tables etc
  */
 
-static void mroute_clean_tables(struct mr_table *mrt)
+static void mroute_clean_tables(struct mr_table *mrt, bool all)
 {
         int i;
         LIST_HEAD(list);
@@ -1217,8 +1209,9 @@ static void mroute_clean_tables(struct mr_table *mrt)
         /* Shut down all active vif entries */
 
         for (i = 0; i < mrt->maxvif; i++) {
-                if (!(mrt->vif_table[i].flags & VIFF_STATIC))
-                        vif_delete(mrt, i, 0, &list);
+                if (!all && (mrt->vif_table[i].flags & VIFF_STATIC))
+                        continue;
+                vif_delete(mrt, i, 0, &list);
         }
         unregister_netdevice_many(&list);
 
@@ -1226,7 +1219,7 @@ static void mroute_clean_tables(struct mr_table *mrt)
 
         for (i = 0; i < MFC_LINES; i++) {
                 list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) {
-                        if (c->mfc_flags & MFC_STATIC)
+                        if (!all && (c->mfc_flags & MFC_STATIC))
                                 continue;
                         list_del_rcu(&c->list);
                         mroute_netlink_event(mrt, c, RTM_DELROUTE);
@@ -1261,7 +1254,7 @@ static void mrtsock_destruct(struct sock *sk)
                                                     NETCONFA_IFINDEX_ALL,
                                                     net->ipv4.devconf_all);
                         RCU_INIT_POINTER(mrt->mroute_sk, NULL);
-                        mroute_clean_tables(mrt);
+                        mroute_clean_tables(mrt, false);
                 }
         }
         rtnl_unlock();
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c1728771cf89..c82cca18c90f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -517,8 +517,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
                         if (sk_stream_is_writeable(sk)) {
                                 mask |= POLLOUT | POLLWRNORM;
                         } else {  /* send SIGIO later */
-                                set_bit(SOCK_ASYNC_NOSPACE,
-                                        &sk->sk_socket->flags);
+                                sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
                                 set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 
                                 /* Race breaker. If space is freed after
@@ -906,7 +905,7 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
                         goto out_err;
         }
 
-        clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+        sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
         mss_now = tcp_send_mss(sk, &size_goal, flags);
         copied = 0;
@@ -1134,7 +1133,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
         }
 
         /* This should be in poll */
-        clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+        sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
         mss_now = tcp_send_mss(sk, &size_goal, flags);
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fdd88c3803a6..2d656eef7f8e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4481,19 +4481,34 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
 int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 {
         struct sk_buff *skb;
+        int err = -ENOMEM;
+        int data_len = 0;
         bool fragstolen;
 
         if (size == 0)
                 return 0;
 
-        skb = alloc_skb(size, sk->sk_allocation);
+        if (size > PAGE_SIZE) {
+                int npages = min_t(size_t, size >> PAGE_SHIFT, MAX_SKB_FRAGS);
+
+                data_len = npages << PAGE_SHIFT;
+                size = data_len + (size & ~PAGE_MASK);
+        }
+        skb = alloc_skb_with_frags(size - data_len, data_len,
+                                   PAGE_ALLOC_COSTLY_ORDER,
+                                   &err, sk->sk_allocation);
         if (!skb)
                 goto err;
 
+        skb_put(skb, size - data_len);
+        skb->data_len = data_len;
+        skb->len = size;
+
         if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
                 goto err_free;
 
-        if (memcpy_from_msg(skb_put(skb, size), msg, size))
+        err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
+        if (err)
                 goto err_free;
 
         TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
@@ -4509,7 +4524,8 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 err_free:
         kfree_skb(skb);
 err:
-        return -ENOMEM;
+        return err;
+
 }
 
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
@@ -5667,6 +5683,7 @@ discard:
                 }
 
                 tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+                tp->copied_seq = tp->rcv_nxt;
                 tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
 
                 /* RFC1323: The window in SYN & SYN/ACK segments is
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ba09016d1bfd..db003438aaf5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -921,7 +921,8 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
         }
 
         md5sig = rcu_dereference_protected(tp->md5sig_info,
-                                           sock_owned_by_user(sk));
+                                           sock_owned_by_user(sk) ||
+                                           lockdep_is_held(&sk->sk_lock.slock));
         if (!md5sig) {
                 md5sig = kmalloc(sizeof(*md5sig), gfp);
                 if (!md5sig)
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index c9c716a483e4..193ba1fa8a9a 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -168,7 +168,7 @@ static int tcp_write_timeout(struct sock *sk)
                         dst_negative_advice(sk);
                         if (tp->syn_fastopen || tp->syn_data)
                                 tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
-                        if (tp->syn_data)
+                        if (tp->syn_data && icsk->icsk_retransmits == 1)
                                 NET_INC_STATS_BH(sock_net(sk),
                                                  LINUX_MIB_TCPFASTOPENACTIVEFAIL);
                 }
@@ -176,6 +176,18 @@ static int tcp_write_timeout(struct sock *sk)
                 syn_set = true;
         } else {
                 if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) {
+                        /* Some middle-boxes may black-hole Fast Open _after_
+                         * the handshake. Therefore we conservatively disable
+                         * Fast Open on this path on recurring timeouts with
+                         * few or zero bytes acked after Fast Open.
+                         */
+                        if (tp->syn_data_acked &&
+                            tp->bytes_acked <= tp->rx_opt.mss_clamp) {
+                                tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
+                                if (icsk->icsk_retransmits == sysctl_tcp_retries1)
+                                        NET_INC_STATS_BH(sock_net(sk),
+                                                         LINUX_MIB_TCPFASTOPENACTIVEFAIL);
+                        }
                         /* Black hole detection */
                         tcp_mtu_probing(icsk, sk);
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 24ec14f9825c..0c7b0e61b917 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -100,7 +100,6 @@
 #include <linux/slab.h>
 #include <net/tcp_states.h>
 #include <linux/skbuff.h>
-#include <linux/netdevice.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <net/net_namespace.h>
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index d84742f003a9..61f26851655c 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3642,7 +3642,7 @@ static void addrconf_dad_work(struct work_struct *w)
 
         /* send a neighbour solicitation for our addr */
         addrconf_addr_solict_mult(&ifp->addr, &mcaddr);
-        ndisc_send_ns(ifp->idev->dev, &ifp->addr, &mcaddr, &in6addr_any, NULL);
+        ndisc_send_ns(ifp->idev->dev, &ifp->addr, &mcaddr, &in6addr_any);
 out:
         in6_ifa_put(ifp);
         rtnl_unlock();
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 44bb66bde0e2..8ec0df75f1c4 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -428,9 +428,11 @@ void inet6_destroy_sock(struct sock *sk)
 
         /* Free tx options */
 
-        opt = xchg(&np->opt, NULL);
-        if (opt)
-                sock_kfree_s(sk, opt, opt->tot_len);
+        opt = xchg((__force struct ipv6_txoptions **)&np->opt, NULL);
+        if (opt) {
+                atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+                txopt_put(opt);
+        }
 }
 EXPORT_SYMBOL_GPL(inet6_destroy_sock);
 
@@ -659,7 +661,10 @@ int inet6_sk_rebuild_header(struct sock *sk)
                 fl6.fl6_sport = inet->inet_sport;
                 security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-                final_p = fl6_update_dst(&fl6, np->opt, &final);
+                rcu_read_lock();
+                final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt),
+                                         &final);
+                rcu_read_unlock();
 
                 dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
                 if (IS_ERR(dst)) {
@@ -668,7 +673,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
                         return PTR_ERR(dst);
                 }
 
-                __ip6_dst_store(sk, dst, NULL, NULL);
+                ip6_dst_store(sk, dst, NULL, NULL);
         }
 
         return 0;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index d70b0238f468..517c55b01ba8 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -167,8 +167,10 @@ ipv4_connected:
 
         security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-        opt = flowlabel ? flowlabel->opt : np->opt;
+        rcu_read_lock();
+        opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt);
         final_p = fl6_update_dst(&fl6, opt, &final);
+        rcu_read_unlock();
 
         dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
         err = 0;
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index ce203b0402be..ea7c4d64a00a 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -727,6 +727,7 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
                         *((char **)&opt2->dst1opt) += dif;
                 if (opt2->srcrt)
                         *((char **)&opt2->srcrt) += dif;
+                atomic_set(&opt2->refcnt, 1);
         }
         return opt2;
 }
@@ -790,7 +791,7 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
                 return ERR_PTR(-ENOBUFS);
 
         memset(opt2, 0, tot_len);
-
+        atomic_set(&opt2->refcnt, 1);
         opt2->tot_len = tot_len;
         p = (char *)(opt2 + 1);
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 36c5a98b0472..0a37ddc7af51 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -834,11 +834,6 @@ void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6,
         security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
 }
 
-/*
- * Special lock-class for __icmpv6_sk:
- */
-static struct lock_class_key icmpv6_socket_sk_dst_lock_key;
-
 static int __net_init icmpv6_sk_init(struct net *net)
 {
         struct sock *sk;
@@ -860,15 +855,6 @@ static int __net_init icmpv6_sk_init(struct net *net)
 
                 net->ipv6.icmp_sk[i] = sk;
 
-                /*
-                 * Split off their lock-class, because sk->sk_dst_lock
-                 * gets used from softirqs, which is safe for
-                 * __icmpv6_sk (because those never get directly used
-                 * via userspace syscalls), but unsafe for normal sockets.
-                 */
-                lockdep_set_class(&sk->sk_dst_lock,
-                                  &icmpv6_socket_sk_dst_lock_key);
-
                 /* Enough space for 2 64K ICMP packets, including
                  * sk_buff struct overhead.
                  */
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 5d1c7cee2cb2..a7ca2cde2ecb 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -78,7 +78,9 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
         memset(fl6, 0, sizeof(*fl6));
         fl6->flowi6_proto = proto;
         fl6->daddr = ireq->ir_v6_rmt_addr;
-        final_p = fl6_update_dst(fl6, np->opt, &final);
+        rcu_read_lock();
+        final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+        rcu_read_unlock();
         fl6->saddr = ireq->ir_v6_loc_addr;
         fl6->flowi6_oif = ireq->ir_iif;
         fl6->flowi6_mark = ireq->ir_mark;
@@ -109,14 +111,6 @@ void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr)
 EXPORT_SYMBOL_GPL(inet6_csk_addr2sockaddr);
 
 static inline
-void __inet6_csk_dst_store(struct sock *sk, struct dst_entry *dst,
-                           const struct in6_addr *daddr,
-                           const struct in6_addr *saddr)
-{
-        __ip6_dst_store(sk, dst, daddr, saddr);
-}
-
-static inline
 struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie)
 {
         return __sk_dst_check(sk, cookie);
@@ -142,14 +136,16 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
         fl6->fl6_dport = inet->inet_dport;
         security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
 
-        final_p = fl6_update_dst(fl6, np->opt, &final);
+        rcu_read_lock();
+        final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+        rcu_read_unlock();
 
         dst = __inet6_csk_dst_check(sk, np->dst_cookie);
         if (!dst) {
                 dst = ip6_dst_lookup_flow(sk, fl6, final_p);
 
                 if (!IS_ERR(dst))
-                        __inet6_csk_dst_store(sk, dst, NULL, NULL);
+                        ip6_dst_store(sk, dst, NULL, NULL);
         }
         return dst;
 }
@@ -175,7 +171,8 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused
         /* Restore final destination back after routing done */
         fl6.daddr = sk->sk_v6_daddr;
 
-        res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+        res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+                       np->tclass);
         rcu_read_unlock();
         return res;
 }
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index eabffbb89795..137fca42aaa6 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -177,7 +177,7 @@ void ip6_tnl_dst_reset(struct ip6_tnl *t)
         int i;
 
         for_each_possible_cpu(i)
-                ip6_tnl_per_cpu_dst_set(raw_cpu_ptr(t->dst_cache), NULL);
+                ip6_tnl_per_cpu_dst_set(per_cpu_ptr(t->dst_cache, i), NULL);
 }
 EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset);
 
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index ad19136086dd..a10e77103c88 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -118,7 +118,7 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
                               int cmd);
 static int ip6mr_rtm_dumproute(struct sk_buff *skb,
                                struct netlink_callback *cb);
-static void mroute_clean_tables(struct mr6_table *mrt);
+static void mroute_clean_tables(struct mr6_table *mrt, bool all);
 static void ipmr_expire_process(unsigned long arg);
 
 #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
@@ -334,7 +334,7 @@ static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
 static void ip6mr_free_table(struct mr6_table *mrt)
 {
         del_timer_sync(&mrt->ipmr_expire_timer);
-        mroute_clean_tables(mrt);
+        mroute_clean_tables(mrt, true);
         kfree(mrt);
 }
 
@@ -765,10 +765,6 @@ static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt)
         return dev;
 
 failure:
-        /* allow the register to be completed before unregistering. */
-        rtnl_unlock();
-        rtnl_lock();
-
         unregister_netdevice(dev);
         return NULL;
 }
@@ -1542,7 +1538,7 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
  *      Close the multicast socket, and clear the vif tables etc
  */
 
-static void mroute_clean_tables(struct mr6_table *mrt)
+static void mroute_clean_tables(struct mr6_table *mrt, bool all)
 {
         int i;
         LIST_HEAD(list);
@@ -1552,8 +1548,9 @@ static void mroute_clean_tables(struct mr6_table *mrt)
          *      Shut down all active vif entries
          */
         for (i = 0; i < mrt->maxvif; i++) {
-                if (!(mrt->vif6_table[i].flags & VIFF_STATIC))
-                        mif6_delete(mrt, i, &list);
+                if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
+                        continue;
+                mif6_delete(mrt, i, &list);
         }
         unregister_netdevice_many(&list);
 
@@ -1562,7 +1559,7 @@ static void mroute_clean_tables(struct mr6_table *mrt)
          */
         for (i = 0; i < MFC6_LINES; i++) {
                 list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) {
-                        if (c->mfc_flags & MFC_STATIC)
+                        if (!all && (c->mfc_flags & MFC_STATIC))
                                 continue;
                         write_lock_bh(&mrt_lock);
                         list_del(&c->list);
@@ -1625,7 +1622,7 @@ int ip6mr_sk_done(struct sock *sk)
                                                      net->ipv6.devconf_all);
                         write_unlock_bh(&mrt_lock);
 
-                        mroute_clean_tables(mrt);
+                        mroute_clean_tables(mrt, false);
                         err = 0;
                         break;
                 }
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 63e6956917c9..4449ad1f8114 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -111,7 +111,8 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
                         icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
                 }
         }
-        opt = xchg(&inet6_sk(sk)->opt, opt);
+        opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt,
+                   opt);
         sk_dst_reset(sk);
 
         return opt;
@@ -231,9 +232,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
                                 sk->sk_socket->ops = &inet_dgram_ops;
                                 sk->sk_family = PF_INET;
                         }
-                        opt = xchg(&np->opt, NULL);
-                        if (opt)
-                                sock_kfree_s(sk, opt, opt->tot_len);
+                        opt = xchg((__force struct ipv6_txoptions **)&np->opt,
+                                   NULL);
+                        if (opt) {
+                                atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+                                txopt_put(opt);
+                        }
                         pktopt = xchg(&np->pktoptions, NULL);
                         kfree_skb(pktopt);
 
@@ -403,7 +407,8 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
                 if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
                         break;
 
-                opt = ipv6_renew_options(sk, np->opt, optname,
+                opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+                opt = ipv6_renew_options(sk, opt, optname,
                                          (struct ipv6_opt_hdr __user *)optval,
                                          optlen);
                 if (IS_ERR(opt)) {
@@ -432,8 +437,10 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
                 retv = 0;
                 opt = ipv6_update_options(sk, opt);
 sticky_done:
-                if (opt)
-                        sock_kfree_s(sk, opt, opt->tot_len);
+                if (opt) {
+                        atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+                        txopt_put(opt);
+                }
                 break;
         }
 
@@ -486,6 +493,7 @@ sticky_done:
                         break;
 
                 memset(opt, 0, sizeof(*opt));
+                atomic_set(&opt->refcnt, 1);
                 opt->tot_len = sizeof(*opt) + optlen;
                 retv = -EFAULT;
                 if (copy_from_user(opt+1, optval, optlen))
@@ -502,8 +510,10 @@ update:
                 retv = 0;
                 opt = ipv6_update_options(sk, opt);
 done:
-                if (opt)
-                        sock_kfree_s(sk, opt, opt->tot_len);
+                if (opt) {
+                        atomic_sub(opt->tot_len, &sk->sk_omem_alloc);
+                        txopt_put(opt);
+                }
                 break;
         }
         case IPV6_UNICAST_HOPS:
@@ -1110,10 +1120,11 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
         case IPV6_RTHDR:
         case IPV6_DSTOPTS:
         {
+                struct ipv6_txoptions *opt;
 
                 lock_sock(sk);
-                len = ipv6_getsockopt_sticky(sk, np->opt,
-                                             optname, optval, len);
+                opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+                len = ipv6_getsockopt_sticky(sk, opt, optname, optval, len);
                 release_sock(sk);
                 /* check if ipv6_getsockopt_sticky() returns err code */
                 if (len < 0)
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 3e0f855e1bea..d6161e1c48c8 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -556,8 +556,7 @@ static void ndisc_send_unsol_na(struct net_device *dev)
 }
 
 void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
-                   const struct in6_addr *daddr, const struct in6_addr *saddr,
-                   struct sk_buff *oskb)
+                   const struct in6_addr *daddr, const struct in6_addr *saddr)
 {
         struct sk_buff *skb;
         struct in6_addr addr_buf;
@@ -593,9 +592,6 @@ void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
                 ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
                                        dev->dev_addr);
 
-        if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE) && oskb)
-                skb_dst_copy(skb, oskb);
-
         ndisc_send_skb(skb, daddr, saddr);
 }
 
@@ -682,12 +678,12 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb)
                                   "%s: trying to ucast probe in NUD_INVALID: %pI6\n",
                                   __func__, target);
                 }
-                ndisc_send_ns(dev, target, target, saddr, skb);
+                ndisc_send_ns(dev, target, target, saddr);
         } else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) {
                 neigh_app_ns(neigh);
         } else {
                 addrconf_addr_solict_mult(target, &mcaddr);
-                ndisc_send_ns(dev, target, &mcaddr, saddr, skb);
+                ndisc_send_ns(dev, target, &mcaddr, saddr);
         }
 }
 
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index d5efeb87350e..bab4441ed4e4 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -190,7 +190,7 @@ static void nf_ct_frag6_expire(unsigned long data)
 /* Creation primitives. */
 static inline struct frag_queue *fq_find(struct net *net, __be32 id,
                                          u32 user, struct in6_addr *src,
-                                         struct in6_addr *dst, u8 ecn)
+                                         struct in6_addr *dst, int iif, u8 ecn)
 {
         struct inet_frag_queue *q;
         struct ip6_create_arg arg;
@@ -200,6 +200,7 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id,
         arg.user = user;
         arg.src = src;
         arg.dst = dst;
+        arg.iif = iif;
         arg.ecn = ecn;
 
         local_bh_disable();
@@ -601,7 +602,7 @@ struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 use
         fhdr = (struct frag_hdr *)skb_transport_header(clone);
 
         fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
-                     ip6_frag_ecn(hdr));
+                     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
         if (fq == NULL) {
                 pr_debug("Can't find and can't create new queue\n");
                 goto ret_orig;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index dc65ec198f7c..99140986e887 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -733,6 +733,7 @@ static int raw6_getfrag(void *from, char *to, int offset, int len, int odd,
 
 static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
+        struct ipv6_txoptions *opt_to_free = NULL;
         struct ipv6_txoptions opt_space;
         DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
         struct in6_addr *daddr, *final_p, final;
@@ -839,8 +840,10 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
                 if (!(opt->opt_nflen|opt->opt_flen))
                         opt = NULL;
         }
-        if (!opt)
-                opt = np->opt;
+        if (!opt) {
+                opt = txopt_get(np);
+                opt_to_free = opt;
+                }
         if (flowlabel)
                 opt = fl6_merge_options(&opt_space, flowlabel, opt);
         opt = ipv6_fixup_options(&opt_space, opt);
@@ -906,6 +909,7 @@ done:
         dst_release(dst);
 out:
         fl6_sock_release(flowlabel);
+        txopt_put(opt_to_free);
         return err < 0 ? err : len;
 do_confirm:
         dst_confirm(dst);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 44e21a03cfc3..45f5ae51de65 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -108,7 +108,10 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
         return  fq->id == arg->id &&
                 fq->user == arg->user &&
                 ipv6_addr_equal(&fq->saddr, arg->src) &&
-                ipv6_addr_equal(&fq->daddr, arg->dst);
+                ipv6_addr_equal(&fq->daddr, arg->dst) &&
+                (arg->iif == fq->iif ||
+                 !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
+                                               IPV6_ADDR_LINKLOCAL)));
 }
 EXPORT_SYMBOL(ip6_frag_match);
 
@@ -180,7 +183,7 @@ static void ip6_frag_expire(unsigned long data)
 
 static struct frag_queue *
 fq_find(struct net *net, __be32 id, const struct in6_addr *src,
-        const struct in6_addr *dst, u8 ecn)
+        const struct in6_addr *dst, int iif, u8 ecn)
 {
         struct inet_frag_queue *q;
         struct ip6_create_arg arg;
@@ -190,6 +193,7 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src,
         arg.user = IP6_DEFRAG_LOCAL_DELIVER;
         arg.src = src;
         arg.dst = dst;
+        arg.iif = iif;
         arg.ecn = ecn;
 
         hash = inet6_hash_frag(id, src, dst);
@@ -551,7 +555,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
         }
 
         fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
-                     ip6_frag_ecn(hdr));
+                     skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
         if (fq) {
                 int ret;
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 6f01fe122abd..826e6aa44f8d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -523,7 +523,7 @@ static void rt6_probe_deferred(struct work_struct *w)
                 container_of(w, struct __rt6_probe_work, work);
 
         addrconf_addr_solict_mult(&work->target, &mcaddr);
-        ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, NULL);
+        ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL);
         dev_put(work->dev);
         kfree(work);
 }
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index bb8f2fa1c7fb..eaf7ac496d50 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -222,7 +222,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
                 memset(&fl6, 0, sizeof(fl6));
                 fl6.flowi6_proto = IPPROTO_TCP;
                 fl6.daddr = ireq->ir_v6_rmt_addr;
-                final_p = fl6_update_dst(&fl6, np->opt, &final);
+                final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final);
                 fl6.saddr = ireq->ir_v6_loc_addr;
                 fl6.flowi6_oif = sk->sk_bound_dev_if;
                 fl6.flowi6_mark = ireq->ir_mark;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c5429a636f1a..e7aab561b7b4 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -120,6 +120,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
         struct ipv6_pinfo *np = inet6_sk(sk);
         struct tcp_sock *tp = tcp_sk(sk);
         struct in6_addr *saddr = NULL, *final_p, final;
+        struct ipv6_txoptions *opt;
         struct flowi6 fl6;
         struct dst_entry *dst;
         int addr_type;
@@ -235,7 +236,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
         fl6.fl6_dport = usin->sin6_port;
         fl6.fl6_sport = inet->inet_sport;
 
-        final_p = fl6_update_dst(&fl6, np->opt, &final);
+        opt = rcu_dereference_protected(np->opt, sock_owned_by_user(sk));
+        final_p = fl6_update_dst(&fl6, opt, &final);
 
         security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
@@ -255,7 +257,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
         inet->inet_rcv_saddr = LOOPBACK4_IPV6;
 
         sk->sk_gso_type = SKB_GSO_TCPV6;
-        __ip6_dst_store(sk, dst, NULL, NULL);
+        ip6_dst_store(sk, dst, NULL, NULL);
 
         if (tcp_death_row.sysctl_tw_recycle &&
             !tp->rx_opt.ts_recent_stamp &&
@@ -263,9 +265,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
                 tcp_fetch_timewait_stamp(sk, dst);
 
         icsk->icsk_ext_hdr_len = 0;
-        if (np->opt)
-                icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
-                                          np->opt->opt_nflen);
+        if (opt)
+                icsk->icsk_ext_hdr_len = opt->opt_flen +
+                                         opt->opt_nflen;
 
         tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
 
@@ -461,7 +463,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
                 if (np->repflow && ireq->pktopts)
                         fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
 
-                err = ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
+                err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt),
+                               np->tclass);
                 err = net_xmit_eval(err);
         }
 
@@ -972,6 +975,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
         struct inet_request_sock *ireq;
         struct ipv6_pinfo *newnp;
         const struct ipv6_pinfo *np = inet6_sk(sk);
+        struct ipv6_txoptions *opt;
         struct tcp6_sock *newtcp6sk;
         struct inet_sock *newinet;
         struct tcp_sock *newtp;
@@ -1056,7 +1060,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
          */
 
         newsk->sk_gso_type = SKB_GSO_TCPV6;
-        __ip6_dst_store(newsk, dst, NULL, NULL);
+        ip6_dst_store(newsk, dst, NULL, NULL);
         inet6_sk_rx_dst_set(newsk, skb);
 
         newtcp6sk = (struct tcp6_sock *)newsk;
@@ -1098,13 +1102,15 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
            but we make one more one thing there: reattach optmem
            to newsk.
          */
-        if (np->opt)
-                newnp->opt = ipv6_dup_options(newsk, np->opt);
-
+        opt = rcu_dereference(np->opt);
+        if (opt) {
+                opt = ipv6_dup_options(newsk, opt);
+                RCU_INIT_POINTER(newnp->opt, opt);
+        }
         inet_csk(newsk)->icsk_ext_hdr_len = 0;
-        if (newnp->opt)
-                inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
-                                                     newnp->opt->opt_flen);
+        if (opt)
+                inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
+                                                    opt->opt_flen;
 
         tcp_ca_openreq_child(newsk, dst);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 01bcb49619ee..9da3287a3923 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1110,6 +1110,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
         DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
         struct in6_addr *daddr, *final_p, final;
         struct ipv6_txoptions *opt = NULL;
+        struct ipv6_txoptions *opt_to_free = NULL;
         struct ip6_flowlabel *flowlabel = NULL;
         struct flowi6 fl6;
         struct dst_entry *dst;
@@ -1263,8 +1264,10 @@ do_udp_sendmsg:
                         opt = NULL;
                 connected = 0;
         }
-        if (!opt)
-                opt = np->opt;
+        if (!opt) {
+                opt = txopt_get(np);
+                opt_to_free = opt;
+        }
         if (flowlabel)
                 opt = fl6_merge_options(&opt_space, flowlabel, opt);
         opt = ipv6_fixup_options(&opt_space, opt);
@@ -1373,6 +1376,7 @@ release_dst:
 out:
         dst_release(dst);
         fl6_sock_release(flowlabel);
+        txopt_put(opt_to_free);
         if (!err)
                 return len;
         /*
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index fcb2752419c6..435608c4306d 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1483,7 +1483,7 @@ unsigned int iucv_sock_poll(struct file *file, struct socket *sock,
         if (sock_writeable(sk) && iucv_below_msglim(sk))
                 mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
         else
-                set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+                sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
         return mask;
 }
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index aca38d8aed8e..a2c8747d2936 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -486,6 +486,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
         DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
         struct in6_addr *daddr, *final_p, final;
         struct ipv6_pinfo *np = inet6_sk(sk);
+        struct ipv6_txoptions *opt_to_free = NULL;
         struct ipv6_txoptions *opt = NULL;
         struct ip6_flowlabel *flowlabel = NULL;
         struct dst_entry *dst = NULL;
@@ -575,8 +576,10 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
                         opt = NULL;
         }
 
-        if (opt == NULL)
-                opt = np->opt;
+        if (!opt) {
+                opt = txopt_get(np);
+                opt_to_free = opt;
+        }
         if (flowlabel)
                 opt = fl6_merge_options(&opt_space, flowlabel, opt);
         opt = ipv6_fixup_options(&opt_space, opt);
@@ -631,6 +634,7 @@ done:
         dst_release(dst);
 out:
         fl6_sock_release(flowlabel);
+        txopt_put(opt_to_free);
 
         return err < 0 ? err : len;
 
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index a758eb84e8f0..ff757181b0a8 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -500,7 +500,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
         /* send AddBA request */
         ieee80211_send_addba_request(sdata, sta->sta.addr, tid,
                                      tid_tx->dialog_token, start_seq_num,
-                                     local->hw.max_tx_aggregation_subframes,
+                                     IEEE80211_MAX_AMPDU_BUF,
                                      tid_tx->timeout);
 }
 
@@ -926,6 +926,7 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local,
         amsdu = capab & IEEE80211_ADDBA_PARAM_AMSDU_MASK;
         tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2;
         buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6;
+        buf_size = min(buf_size, local->hw.max_tx_aggregation_subframes);
 
         mutex_lock(&sta->ampdu_mlme.mtx);
 
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index c2bd1b6a6922..da471eef07bb 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3454,8 +3454,12 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
                         goto out_unlock;
                 }
         } else {
-                /* for cookie below */
-                ack_skb = skb;
+                /* Assign a dummy non-zero cookie, it's not sent to
+                 * userspace in this case but we rely on its value
+                 * internally in the need_offchan case to distinguish
+                 * mgmt-tx from remain-on-channel.
+                 */
+                *cookie = 0xffffffff;
         }
 
         if (!need_offchan) {
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index d0dc1bfaeec2..c9e325d2e120 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -76,7 +76,8 @@ bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata)
 void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata,
                               bool update_bss)
 {
-        if (__ieee80211_recalc_txpower(sdata) || update_bss)
+        if (__ieee80211_recalc_txpower(sdata) ||
+            (update_bss && ieee80211_sdata_running(sdata)))
                 ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_TXPOWER);
 }
 
@@ -1861,6 +1862,7 @@ void ieee80211_if_remove(struct ieee80211_sub_if_data *sdata)
                 unregister_netdevice(sdata->dev);
         } else {
                 cfg80211_unregister_wdev(&sdata->wdev);
+                ieee80211_teardown_sdata(sdata);
                 kfree(sdata);
         }
 }
@@ -1870,7 +1872,6 @@ void ieee80211_sdata_stop(struct ieee80211_sub_if_data *sdata)
         if (WARN_ON_ONCE(!test_bit(SDATA_STATE_RUNNING, &sdata->state)))
                 return;
         ieee80211_do_stop(sdata, true);
-        ieee80211_teardown_sdata(sdata);
 }
 
 void ieee80211_remove_interfaces(struct ieee80211_local *local)
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 858f6b1cb149..175ffcf7fb06 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -541,8 +541,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
                            NL80211_FEATURE_HT_IBSS |
                            NL80211_FEATURE_VIF_TXPOWER |
                            NL80211_FEATURE_MAC_ON_CREATE |
-                           NL80211_FEATURE_USERSPACE_MPM |
-                           NL80211_FEATURE_FULL_AP_CLIENT_STATE;
+                           NL80211_FEATURE_USERSPACE_MPM;
 
         if (!ops->hw_scan)
                 wiphy->features |= NL80211_FEATURE_LOW_PRIORITY_SCAN |
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index b890e225a8f1..b3b44a5dd375 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -779,10 +779,8 @@ void mesh_plink_broken(struct sta_info *sta)
 static void mesh_path_node_reclaim(struct rcu_head *rp)
 {
         struct mpath_node *node = container_of(rp, struct mpath_node, rcu);
-        struct ieee80211_sub_if_data *sdata = node->mpath->sdata;
 
         del_timer_sync(&node->mpath->timer);
-        atomic_dec(&sdata->u.mesh.mpaths);
         kfree(node->mpath);
         kfree(node);
 }
@@ -790,8 +788,9 @@ static void mesh_path_node_reclaim(struct rcu_head *rp)
 /* needs to be called with the corresponding hashwlock taken */
 static void __mesh_path_del(struct mesh_table *tbl, struct mpath_node *node)
 {
-        struct mesh_path *mpath;
-        mpath = node->mpath;
+        struct mesh_path *mpath = node->mpath;
+        struct ieee80211_sub_if_data *sdata = node->mpath->sdata;
+
         spin_lock(&mpath->state_lock);
         mpath->flags |= MESH_PATH_RESOLVING;
         if (mpath->is_gate)
@@ -799,6 +798,7 @@ static void __mesh_path_del(struct mesh_table *tbl, struct mpath_node *node)
         hlist_del_rcu(&node->list);
         call_rcu(&node->rcu, mesh_path_node_reclaim);
         spin_unlock(&mpath->state_lock);
+        atomic_dec(&sdata->u.mesh.mpaths);
         atomic_dec(&tbl->entries);
 }
 
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 4aeca4b0c3cb..a413e52f7691 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -597,8 +597,8 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
                 /* We need to ensure power level is at max for scanning. */
                 ieee80211_hw_config(local, 0);
 
-                if ((req->channels[0]->flags &
-                     IEEE80211_CHAN_NO_IR) ||
+                if ((req->channels[0]->flags & (IEEE80211_CHAN_NO_IR |
+                                                IEEE80211_CHAN_RADAR)) ||
                     !req->n_ssids) {
                         next_delay = IEEE80211_PASSIVE_CHANNEL_TIME;
                 } else {
@@ -645,7 +645,7 @@ ieee80211_scan_get_channel_time(struct ieee80211_channel *chan)
          * TODO: channel switching also consumes quite some time,
          * add that delay as well to get a better estimation
          */
-        if (chan->flags & IEEE80211_CHAN_NO_IR)
+        if (chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR))
                 return IEEE80211_PASSIVE_CHANNEL_TIME;
         return IEEE80211_PROBE_DELAY + IEEE80211_CHANNEL_TIME;
 }
@@ -777,7 +777,8 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local,
          *
          * In any case, it is not necessary for a passive scan.
          */
-        if (chan->flags & IEEE80211_CHAN_NO_IR || !scan_req->n_ssids) {
+        if ((chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) ||
+            !scan_req->n_ssids) {
                 *next_delay = IEEE80211_PASSIVE_CHANNEL_TIME;
                 local->next_scan_state = SCAN_DECISION;
                 return;
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index b7de0da46acd..ecf0a0196f18 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -572,7 +572,7 @@ static unsigned int llcp_sock_poll(struct file *file, struct socket *sock,
         if (sock_writeable(sk) && sk->sk_state == LLCP_CONNECTED)
                 mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
         else
-                set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+                sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
         pr_debug("mask 0x%x\n", mask);
 
diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c
index a7a80a6b77b0..653d073bae45 100644
--- a/net/openvswitch/dp_notify.c
+++ b/net/openvswitch/dp_notify.c
@@ -58,7 +58,7 @@ void ovs_dp_notify_wq(struct work_struct *work)
                         struct hlist_node *n;
 
                         hlist_for_each_entry_safe(vport, n, &dp->ports[i], dp_hash_node) {
-                                if (vport->ops->type != OVS_VPORT_TYPE_NETDEV)
+                                if (vport->ops->type == OVS_VPORT_TYPE_INTERNAL)
                                         continue;
 
                                 if (!(vport->dev->priv_flags & IFF_OVS_DATAPATH))
diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c
index efb736bb6855..e41cd12d9b2d 100644
--- a/net/openvswitch/vport-geneve.c
+++ b/net/openvswitch/vport-geneve.c
@@ -117,7 +117,6 @@ static struct vport_ops ovs_geneve_vport_ops = {
         .destroy        = ovs_netdev_tunnel_destroy,
         .get_options    = geneve_get_options,
         .send           = dev_queue_xmit,
-        .owner          = THIS_MODULE,
 };
 
 static int __init ovs_geneve_tnl_init(void)
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index c3257d78d3d2..7f8897f33a67 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -89,7 +89,6 @@ static struct vport_ops ovs_gre_vport_ops = {
         .create         = gre_create,
         .send           = dev_queue_xmit,
         .destroy        = ovs_netdev_tunnel_destroy,
-        .owner          = THIS_MODULE,
 };
 
 static int __init ovs_gre_tnl_init(void)
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index b327368a3848..6b0190b987ec 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -180,9 +180,13 @@ void ovs_netdev_tunnel_destroy(struct vport *vport)
         if (vport->dev->priv_flags & IFF_OVS_DATAPATH)
                 ovs_netdev_detach_dev(vport);
 
-        /* Early release so we can unregister the device */
+        /* We can be invoked by both explicit vport deletion and
+         * underlying netdev deregistration; delete the link only
+         * if it's not already shutting down.
+         */
+        if (vport->dev->reg_state == NETREG_REGISTERED)
+                rtnl_delete_link(vport->dev);
         dev_put(vport->dev);
-        rtnl_delete_link(vport->dev);
         vport->dev = NULL;
         rtnl_unlock();
 
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 0ac0fd004d7e..31cbc8c5c7db 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -71,7 +71,7 @@ static struct hlist_head *hash_bucket(const struct net *net, const char *name)
         return &dev_table[hash & (VPORT_HASH_BUCKETS - 1)];
 }
 
-int ovs_vport_ops_register(struct vport_ops *ops)
+int __ovs_vport_ops_register(struct vport_ops *ops)
 {
         int err = -EEXIST;
         struct vport_ops *o;
@@ -87,7 +87,7 @@ errout:
         ovs_unlock();
         return err;
 }
-EXPORT_SYMBOL_GPL(ovs_vport_ops_register);
+EXPORT_SYMBOL_GPL(__ovs_vport_ops_register);
 
 void ovs_vport_ops_unregister(struct vport_ops *ops)
 {
@@ -256,8 +256,8 @@ int ovs_vport_set_options(struct vport *vport, struct nlattr *options)
  *
  * @vport: vport to delete.
  *
- * Detaches @vport from its datapath and destroys it.  It is possible to fail
- * for reasons such as lack of memory.  ovs_mutex must be held.
+ * Detaches @vport from its datapath and destroys it.  ovs_mutex must
+ * be held.
  */
 void ovs_vport_del(struct vport *vport)
 {
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index bdfd82a7c064..8ea3a96980ac 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -196,7 +196,13 @@ static inline const char *ovs_vport_name(struct vport *vport)
         return vport->dev->name;
 }
 
-int ovs_vport_ops_register(struct vport_ops *ops);
+int __ovs_vport_ops_register(struct vport_ops *ops);
+#define ovs_vport_ops_register(ops)             \
+        ({                                      \
+                (ops)->owner = THIS_MODULE;     \
+                __ovs_vport_ops_register(ops);  \
+        })
+
 void ovs_vport_ops_unregister(struct vport_ops *ops);
 
 static inline struct rtable *ovs_tunnel_route_lookup(struct net *net,
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 1cf928fb573e..992396aa635c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2329,8 +2329,8 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 static bool ll_header_truncated(const struct net_device *dev, int len)
 {
         /* net device doesn't like empty head */
-        if (unlikely(len <= dev->hard_header_len)) {
-                net_warn_ratelimited("%s: packet size is too short (%d <= %d)\n",
+        if (unlikely(len < dev->hard_header_len)) {
+                net_warn_ratelimited("%s: packet size is too short (%d < %d)\n",
                                      current->comm, len, dev->hard_header_len);
                 return true;
         }
diff --git a/net/rds/connection.c b/net/rds/connection.c
index d4564036a339..e3b118cae81d 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -186,12 +186,6 @@ static struct rds_connection *__rds_conn_create(struct net *net,
                 }
         }
 
-        if (trans == NULL) {
-                kmem_cache_free(rds_conn_slab, conn);
-                conn = ERR_PTR(-ENODEV);
-                goto out;
-        }
-
         conn->c_trans = trans;
 
         ret = trans->conn_alloc(conn, gfp);
diff --git a/net/rds/send.c b/net/rds/send.c
index 827155c2ead1..c9cdb358ea88 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1013,11 +1013,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
                 release_sock(sk);
         }
 
-        /* racing with another thread binding seems ok here */
+        lock_sock(sk);
         if (daddr == 0 || rs->rs_bound_addr == 0) {
+                release_sock(sk);
                 ret = -ENOTCONN; /* XXX not a great errno */
                 goto out;
         }
+        release_sock(sk);
 
         if (payload_len > rds_sk_sndbuf(rs)) {
                 ret = -EMSGSIZE;
diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/ar-ack.c
index e0547f521f20..adc555e0323d 100644
--- a/net/rxrpc/ar-ack.c
+++ b/net/rxrpc/ar-ack.c
@@ -723,8 +723,10 @@ process_further:
 
                         if ((call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY ||
                              call->state == RXRPC_CALL_SERVER_AWAIT_ACK) &&
-                            hard > tx)
+                            hard > tx) {
+                                call->acks_hard = tx;
                                 goto all_acked;
+                        }
 
                         smp_rmb();
                         rxrpc_rotate_tx_window(call, hard - 1);
diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c
index a40d3afe93b7..14c4e12c47b0 100644
--- a/net/rxrpc/ar-output.c
+++ b/net/rxrpc/ar-output.c
@@ -531,7 +531,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
         timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
         /* this should be in poll */
-        clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+        sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
         if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
                 return -EPIPE;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index f43c8f33f09e..7ec667dd4ce1 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -253,7 +253,8 @@ int qdisc_set_default(const char *name)
 }
 
 /* We know handle. Find qdisc among all qdisc's attached to device
-   (root qdisc, all its children, children of children etc.)
+ * (root qdisc, all its children, children of children etc.)
+ * Note: caller either uses rtnl or rcu_read_lock()
  */
 
 static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
@@ -264,7 +265,7 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle)
             root->handle == handle)
                 return root;
 
-        list_for_each_entry(q, &root->list, list) {
+        list_for_each_entry_rcu(q, &root->list, list) {
                 if (q->handle == handle)
                         return q;
         }
@@ -277,15 +278,18 @@ void qdisc_list_add(struct Qdisc *q)
                 struct Qdisc *root = qdisc_dev(q)->qdisc;
 
                 WARN_ON_ONCE(root == &noop_qdisc);
-                list_add_tail(&q->list, &root->list);
+                ASSERT_RTNL();
+                list_add_tail_rcu(&q->list, &root->list);
         }
 }
 EXPORT_SYMBOL(qdisc_list_add);
 
 void qdisc_list_del(struct Qdisc *q)
 {
-        if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
-                list_del(&q->list);
+        if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) {
+                ASSERT_RTNL();
+                list_del_rcu(&q->list);
+        }
 }
 EXPORT_SYMBOL(qdisc_list_del);
 
@@ -750,14 +754,18 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
         if (n == 0)
                 return;
         drops = max_t(int, n, 0);
+        rcu_read_lock();
         while ((parentid = sch->parent)) {
                 if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS))
-                        return;
+                        break;
 
+                if (sch->flags & TCQ_F_NOPARENT)
+                        break;
+                /* TODO: perform the search on a per txq basis */
                 sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid));
                 if (sch == NULL) {
-                        WARN_ON(parentid != TC_H_ROOT);
-                        return;
+                        WARN_ON_ONCE(parentid != TC_H_ROOT);
+                        break;
                 }
                 cops = sch->ops->cl_ops;
                 if (cops->qlen_notify) {
@@ -768,6 +776,7 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
                 sch->q.qlen -= n;
                 __qdisc_qstats_drop(sch, drops);
         }
+        rcu_read_unlock();
 }
 EXPORT_SYMBOL(qdisc_tree_decrease_qlen);
 
@@ -941,7 +950,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
                 }
                 lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock);
                 if (!netif_is_multiqueue(dev))
-                        sch->flags |= TCQ_F_ONETXQUEUE;
+                        sch->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
         }
 
         sch->handle = handle;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index cb5d4ad32946..e82a1ad80aa5 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -737,7 +737,7 @@ static void attach_one_default_qdisc(struct net_device *dev,
                 return;
         }
         if (!netif_is_multiqueue(dev))
-                qdisc->flags |= TCQ_F_ONETXQUEUE;
+                qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
         dev_queue->qdisc_sleeping = qdisc;
 }
 
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index f3cbaecd283a..3e82f047caaf 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -63,7 +63,7 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt)
                 if (qdisc == NULL)
                         goto err;
                 priv->qdiscs[ntx] = qdisc;
-                qdisc->flags |= TCQ_F_ONETXQUEUE;
+                qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
         }
 
         sch->flags |= TCQ_F_MQROOT;
@@ -156,7 +156,7 @@ static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
 
         *old = dev_graft_qdisc(dev_queue, new);
         if (new)
-                new->flags |= TCQ_F_ONETXQUEUE;
+                new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
         if (dev->flags & IFF_UP)
                 dev_activate(dev);
         return 0;
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 3811a745452c..ad70ecf57ce7 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -132,7 +132,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt)
                         goto err;
                 }
                 priv->qdiscs[i] = qdisc;
-                qdisc->flags |= TCQ_F_ONETXQUEUE;
+                qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
         }
 
         /* If the mqprio options indicate that hardware should own
@@ -209,7 +209,7 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
         *old = dev_graft_qdisc(dev_queue, new);
 
         if (new)
-                new->flags |= TCQ_F_ONETXQUEUE;
+                new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
 
         if (dev->flags & IFF_UP)
                 dev_activate(dev);
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index e917d27328ea..acb45b8c2a9d 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -209,6 +209,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
         struct sock *sk = skb->sk;
         struct ipv6_pinfo *np = inet6_sk(sk);
         struct flowi6 *fl6 = &transport->fl.u.ip6;
+        int res;
 
         pr_debug("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", __func__, skb,
                  skb->len, &fl6->saddr, &fl6->daddr);
@@ -220,7 +221,10 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 
         SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
 
-        return ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
+        rcu_read_lock();
+        res = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt), np->tclass);
+        rcu_read_unlock();
+        return res;
 }
 
 /* Returns the dst cache entry for the given source and destination ip
@@ -262,7 +266,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
                 pr_debug("src=%pI6 - ", &fl6->saddr);
         }
 
-        final_p = fl6_update_dst(fl6, np->opt, &final);
+        rcu_read_lock();
+        final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
+        rcu_read_unlock();
+
         dst = ip6_dst_lookup_flow(sk, fl6, final_p);
         if (!asoc || saddr)
                 goto out;
@@ -321,7 +328,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
         if (baddr) {
                 fl6->saddr = baddr->v6.sin6_addr;
                 fl6->fl6_sport = baddr->v6.sin6_port;
-                final_p = fl6_update_dst(fl6, np->opt, &final);
+                final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
                 dst = ip6_dst_lookup_flow(sk, fl6, final_p);
         }
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 897c01c029ca..03c8256063ec 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -972,7 +972,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
                 return -EFAULT;
 
         /* Alloc space for the address array in kernel memory.  */
-        kaddrs = kmalloc(addrs_size, GFP_KERNEL);
+        kaddrs = kmalloc(addrs_size, GFP_USER | __GFP_NOWARN);
         if (unlikely(!kaddrs))
                 return -ENOMEM;
 
@@ -4928,7 +4928,7 @@ static int sctp_getsockopt_local_addrs(struct sock *sk, int len,
         to = optval + offsetof(struct sctp_getaddrs, addrs);
         space_left = len - offsetof(struct sctp_getaddrs, addrs);
 
-        addrs = kmalloc(space_left, GFP_KERNEL);
+        addrs = kmalloc(space_left, GFP_USER | __GFP_NOWARN);
         if (!addrs)
                 return -ENOMEM;
 
@@ -6458,7 +6458,7 @@ unsigned int sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
         if (sctp_writeable(sk)) {
                 mask |= POLLOUT | POLLWRNORM;
         } else {
-                set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+                sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
                 /*
                  * Since the socket is not locked, the buffer
                  * might be made available after the writeable check and
@@ -6801,26 +6801,30 @@ no_packet:
 static void __sctp_write_space(struct sctp_association *asoc)
 {
         struct sock *sk = asoc->base.sk;
-        struct socket *sock = sk->sk_socket;
 
-        if ((sctp_wspace(asoc) > 0) && sock) {
-                if (waitqueue_active(&asoc->wait))
-                        wake_up_interruptible(&asoc->wait);
+        if (sctp_wspace(asoc) <= 0)
+                return;
+
+        if (waitqueue_active(&asoc->wait))
+                wake_up_interruptible(&asoc->wait);
 
-                if (sctp_writeable(sk)) {
-                        wait_queue_head_t *wq = sk_sleep(sk);
+        if (sctp_writeable(sk)) {
+                struct socket_wq *wq;
 
-                        if (wq && waitqueue_active(wq))
-                                wake_up_interruptible(wq);
+                rcu_read_lock();
+                wq = rcu_dereference(sk->sk_wq);
+                if (wq) {
+                        if (waitqueue_active(&wq->wait))
+                                wake_up_interruptible(&wq->wait);
 
                         /* Note that we try to include the Async I/O support
                          * here by modeling from the current TCP/UDP code.
                          * We have not tested with it yet.
                          */
                         if (!(sk->sk_shutdown & SEND_SHUTDOWN))
-                                sock_wake_async(sock,
-                                                SOCK_WAKE_SPACE, POLL_OUT);
+                                sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT);
                 }
+                rcu_read_unlock();
         }
 }
 
@@ -7375,6 +7379,13 @@ struct proto sctp_prot = {
 
 #if IS_ENABLED(CONFIG_IPV6)
 
+#include <net/transp_v6.h>
+static void sctp_v6_destroy_sock(struct sock *sk)
+{
+        sctp_destroy_sock(sk);
+        inet6_destroy_sock(sk);
+}
+
 struct proto sctpv6_prot = {
         .name           = "SCTPv6",
         .owner          = THIS_MODULE,
@@ -7384,7 +7395,7 @@ struct proto sctpv6_prot = {
         .accept         = sctp_accept,
         .ioctl          = sctp_ioctl,
         .init           = sctp_init_sock,
-        .destroy        = sctp_destroy_sock,
+        .destroy        = sctp_v6_destroy_sock,
         .shutdown       = sctp_shutdown,
         .setsockopt     = sctp_setsockopt,
         .getsockopt     = sctp_getsockopt,
diff --git a/net/socket.c b/net/socket.c
index dd2c247c99e3..456fadb3d819 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1056,27 +1056,20 @@ static int sock_fasync(int fd, struct file *filp, int on)
         return 0;
 }
 
-/* This function may be called only under socket lock or callback_lock or rcu_lock */
+/* This function may be called only under rcu_lock */
 
-int sock_wake_async(struct socket *sock, int how, int band)
+int sock_wake_async(struct socket_wq *wq, int how, int band)
 {
-        struct socket_wq *wq;
-
-        if (!sock)
-                return -1;
-        rcu_read_lock();
-        wq = rcu_dereference(sock->wq);
-        if (!wq || !wq->fasync_list) {
-                rcu_read_unlock();
+        if (!wq || !wq->fasync_list)
                 return -1;
-        }
+
         switch (how) {
         case SOCK_WAKE_WAITD:
-                if (test_bit(SOCK_ASYNC_WAITDATA, &sock->flags))
+                if (test_bit(SOCKWQ_ASYNC_WAITDATA, &wq->flags))
                         break;
                 goto call_kill;
         case SOCK_WAKE_SPACE:
-                if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags))
+                if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags))
                         break;
                 /* fall through */
         case SOCK_WAKE_IO:
@@ -1086,7 +1079,7 @@ call_kill:
         case SOCK_WAKE_URG:
                 kill_fasync(&wq->fasync_list, SIGURG, band);
         }
-        rcu_read_unlock();
+
         return 0;
 }
 EXPORT_SYMBOL(sock_wake_async);
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index f14f24ee9983..73ad57a59989 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -250,11 +250,11 @@ void rpc_destroy_wait_queue(struct rpc_wait_queue *queue)
 }
 EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue);
 
-static int rpc_wait_bit_killable(struct wait_bit_key *key)
+static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
-        if (fatal_signal_pending(current))
-                return -ERESTARTSYS;
         freezable_schedule_unsafe();
+        if (signal_pending_state(mode, current))
+                return -ERESTARTSYS;
         return 0;
 }
 
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index bc5b7b5032ca..cc9852897395 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1364,6 +1364,19 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req,
         memcpy(&rqstp->rq_arg, &req->rq_rcv_buf, sizeof(rqstp->rq_arg));
         memcpy(&rqstp->rq_res, &req->rq_snd_buf, sizeof(rqstp->rq_res));
 
+        /* Adjust the argument buffer length */
+        rqstp->rq_arg.len = req->rq_private_buf.len;
+        if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len) {
+                rqstp->rq_arg.head[0].iov_len = rqstp->rq_arg.len;
+                rqstp->rq_arg.page_len = 0;
+        } else if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len +
+                        rqstp->rq_arg.page_len)
+                rqstp->rq_arg.page_len = rqstp->rq_arg.len -
+                        rqstp->rq_arg.head[0].iov_len;
+        else
+                rqstp->rq_arg.len = rqstp->rq_arg.head[0].iov_len +
+                        rqstp->rq_arg.page_len;
+
         /* reset result send buffer "put" position */
         resv->iov_len = 0;
 
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 1d1a70498910..2ffaf6a79499 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -398,7 +398,7 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen,
         if (unlikely(!sock))
                 return -ENOTSOCK;
 
-        clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
+        clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags);
         if (base != 0) {
                 addr = NULL;
                 addrlen = 0;
@@ -442,7 +442,7 @@ static void xs_nospace_callback(struct rpc_task *task)
         struct sock_xprt *transport = container_of(task->tk_rqstp->rq_xprt, struct sock_xprt, xprt);
 
         transport->inet->sk_write_pending--;
-        clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
+        clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags);
 }
 
 /**
@@ -467,7 +467,7 @@ static int xs_nospace(struct rpc_task *task)
 
         /* Don't race with disconnect */
         if (xprt_connected(xprt)) {
-                if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) {
+                if (test_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags)) {
                         /*
                          * Notify TCP that we're limited by the application
                          * window size
@@ -478,7 +478,7 @@ static int xs_nospace(struct rpc_task *task)
                         xprt_wait_for_buffer_space(task, xs_nospace_callback);
                 }
         } else {
-                clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
+                clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags);
                 ret = -ENOTCONN;
         }
 
@@ -626,7 +626,7 @@ process_status:
         case -EPERM:
                 /* When the server has died, an ICMP port unreachable message
                  * prompts ECONNREFUSED. */
-                clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
+                clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags);
         }
 
         return status;
@@ -715,7 +715,7 @@ static int xs_tcp_send_request(struct rpc_task *task)
         case -EADDRINUSE:
         case -ENOBUFS:
         case -EPIPE:
-                clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
+                clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags);
         }
 
         return status;
@@ -1618,7 +1618,7 @@ static void xs_write_space(struct sock *sk)
 
         if (unlikely(!(xprt = xprt_from_sock(sk))))
                 return;
-        if (test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags) == 0)
+        if (test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags) == 0)
                 return;
 
         xprt_write_space(xprt);
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 9efbdbde2b08..91aea071ab27 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -191,6 +191,7 @@ void tipc_link_add_bc_peer(struct tipc_link *snd_l,
 
         snd_l->ackers++;
         rcv_l->acked = snd_l->snd_nxt - 1;
+        snd_l->state = LINK_ESTABLISHED;
         tipc_link_build_bc_init_msg(uc_l, xmitq);
 }
 
@@ -206,6 +207,7 @@ void tipc_link_remove_bc_peer(struct tipc_link *snd_l,
         rcv_l->state = LINK_RESET;
         if (!snd_l->ackers) {
                 tipc_link_reset(snd_l);
+                snd_l->state = LINK_RESET;
                 __skb_queue_purge(xmitq);
         }
 }
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 552dbaba9cf3..b53246fb0412 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -105,6 +105,7 @@ struct tipc_sock {
 static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb);
 static void tipc_data_ready(struct sock *sk);
 static void tipc_write_space(struct sock *sk);
+static void tipc_sock_destruct(struct sock *sk);
 static int tipc_release(struct socket *sock);
 static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags);
 static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p);
@@ -381,6 +382,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
         sk->sk_rcvbuf = sysctl_tipc_rmem[1];
         sk->sk_data_ready = tipc_data_ready;
         sk->sk_write_space = tipc_write_space;
+        sk->sk_destruct = tipc_sock_destruct;
         tsk->conn_timeout = CONN_TIMEOUT_DEFAULT;
         tsk->sent_unacked = 0;
         atomic_set(&tsk->dupl_rcvcnt, 0);
@@ -470,9 +472,6 @@ static int tipc_release(struct socket *sock)
                 tipc_node_remove_conn(net, dnode, tsk->portid);
         }
 
-        /* Discard any remaining (connection-based) messages in receive queue */
-        __skb_queue_purge(&sk->sk_receive_queue);
-
         /* Reject any messages that accumulated in backlog queue */
         sock->state = SS_DISCONNECTING;
         release_sock(sk);
@@ -1515,6 +1514,11 @@ static void tipc_data_ready(struct sock *sk)
         rcu_read_unlock();
 }
 
+static void tipc_sock_destruct(struct sock *sk)
+{
+        __skb_queue_purge(&sk->sk_receive_queue);
+}
+
 /**
  * filter_connect - Handle all incoming messages for a connection-based socket
  * @tsk: TIPC socket
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index ad2719ad4c1b..70c03271b798 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -158,8 +158,11 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb,
         struct udp_media_addr *src = (struct udp_media_addr *)&b->addr.value;
         struct rtable *rt;
 
-        if (skb_headroom(skb) < UDP_MIN_HEADROOM)
-                pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC);
+        if (skb_headroom(skb) < UDP_MIN_HEADROOM) {
+                err = pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC);
+                if (err)
+                        goto tx_error;
+        }
 
         skb_set_inner_protocol(skb, htons(ETH_P_TIPC));
         ub = rcu_dereference_rtnl(b->media_ptr);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 955ec152cb71..45aebd966978 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -326,6 +326,118 @@ found:
         return s;
 }
 
+/* Support code for asymmetrically connected dgram sockets
+ *
+ * If a datagram socket is connected to a socket not itself connected
+ * to the first socket (eg, /dev/log), clients may only enqueue more
+ * messages if the present receive queue of the server socket is not
+ * "too large". This means there's a second writeability condition
+ * poll and sendmsg need to test. The dgram recv code will do a wake
+ * up on the peer_wait wait queue of a socket upon reception of a
+ * datagram which needs to be propagated to sleeping would-be writers
+ * since these might not have sent anything so far. This can't be
+ * accomplished via poll_wait because the lifetime of the server
+ * socket might be less than that of its clients if these break their
+ * association with it or if the server socket is closed while clients
+ * are still connected to it and there's no way to inform "a polling
+ * implementation" that it should let go of a certain wait queue
+ *
+ * In order to propagate a wake up, a wait_queue_t of the client
+ * socket is enqueued on the peer_wait queue of the server socket
+ * whose wake function does a wake_up on the ordinary client socket
+ * wait queue. This connection is established whenever a write (or
+ * poll for write) hit the flow control condition and broken when the
+ * association to the server socket is dissolved or after a wake up
+ * was relayed.
+ */
+
+static int unix_dgram_peer_wake_relay(wait_queue_t *q, unsigned mode, int flags,
+                                      void *key)
+{
+        struct unix_sock *u;
+        wait_queue_head_t *u_sleep;
+
+        u = container_of(q, struct unix_sock, peer_wake);
+
+        __remove_wait_queue(&unix_sk(u->peer_wake.private)->peer_wait,
+                            q);
+        u->peer_wake.private = NULL;
+
+        /* relaying can only happen while the wq still exists */
+        u_sleep = sk_sleep(&u->sk);
+        if (u_sleep)
+                wake_up_interruptible_poll(u_sleep, key);
+
+        return 0;
+}
+
+static int unix_dgram_peer_wake_connect(struct sock *sk, struct sock *other)
+{
+        struct unix_sock *u, *u_other;
+        int rc;
+
+        u = unix_sk(sk);
+        u_other = unix_sk(other);
+        rc = 0;
+        spin_lock(&u_other->peer_wait.lock);
+
+        if (!u->peer_wake.private) {
+                u->peer_wake.private = other;
+                __add_wait_queue(&u_other->peer_wait, &u->peer_wake);
+
+                rc = 1;
+        }
+
+        spin_unlock(&u_other->peer_wait.lock);
+        return rc;
+}
+
+static void unix_dgram_peer_wake_disconnect(struct sock *sk,
+                                            struct sock *other)
+{
+        struct unix_sock *u, *u_other;
+
+        u = unix_sk(sk);
+        u_other = unix_sk(other);
+        spin_lock(&u_other->peer_wait.lock);
+
+        if (u->peer_wake.private == other) {
+                __remove_wait_queue(&u_other->peer_wait, &u->peer_wake);
+                u->peer_wake.private = NULL;
+        }
+
+        spin_unlock(&u_other->peer_wait.lock);
+}
+
+static void unix_dgram_peer_wake_disconnect_wakeup(struct sock *sk,
+                                                   struct sock *other)
+{
+        unix_dgram_peer_wake_disconnect(sk, other);
+        wake_up_interruptible_poll(sk_sleep(sk),
+                                   POLLOUT |
+                                   POLLWRNORM |
+                                   POLLWRBAND);
+}
+
+/* preconditions:
+ *      - unix_peer(sk) == other
+ *      - association is stable
+ */
+static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other)
+{
+        int connected;
+
+        connected = unix_dgram_peer_wake_connect(sk, other);
+
+        if (unix_recvq_full(other))
+                return 1;
+
+        if (connected)
+                unix_dgram_peer_wake_disconnect(sk, other);
+
+        return 0;
+}
+
 static int unix_writable(const struct sock *sk)
 {
         return sk->sk_state != TCP_LISTEN &&
@@ -431,6 +543,8 @@ static void unix_release_sock(struct sock *sk, int embrion)
                         skpair->sk_state_change(skpair);
                         sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP);
                 }
+
+                unix_dgram_peer_wake_disconnect(sk, skpair);
                 sock_put(skpair); /* It may now die */
                 unix_peer(sk) = NULL;
         }
@@ -666,6 +780,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern)
         INIT_LIST_HEAD(&u->link);
         mutex_init(&u->readlock); /* single task reading lock */
         init_waitqueue_head(&u->peer_wait);
+        init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
         unix_insert_socket(unix_sockets_unbound(sk), sk);
 out:
         if (sk == NULL)
@@ -1033,6 +1148,8 @@ restart:
         if (unix_peer(sk)) {
                 struct sock *old_peer = unix_peer(sk);
                 unix_peer(sk) = other;
+                unix_dgram_peer_wake_disconnect_wakeup(sk, old_peer);
+
                 unix_state_double_unlock(sk, other);
 
                 if (other != old_peer)
@@ -1434,6 +1551,14 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen
         return err;
 }
 
+static bool unix_passcred_enabled(const struct socket *sock,
+                                  const struct sock *other)
+{
+        return test_bit(SOCK_PASSCRED, &sock->flags) ||
+               !other->sk_socket ||
+               test_bit(SOCK_PASSCRED, &other->sk_socket->flags);
+}
+
 /*
  * Some apps rely on write() giving SCM_CREDENTIALS
  * We include credentials if source or destination socket
@@ -1444,14 +1569,41 @@ static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock,
 {
         if (UNIXCB(skb).pid)
                 return;
-        if (test_bit(SOCK_PASSCRED, &sock->flags) ||
-            !other->sk_socket ||
-            test_bit(SOCK_PASSCRED, &other->sk_socket->flags)) {
+        if (unix_passcred_enabled(sock, other)) {
                 UNIXCB(skb).pid  = get_pid(task_tgid(current));
                 current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid);
         }
 }
 
+static int maybe_init_creds(struct scm_cookie *scm,
+                            struct socket *socket,
+                            const struct sock *other)
+{
+        int err;
+        struct msghdr msg = { .msg_controllen = 0 };
+
+        err = scm_send(socket, &msg, scm, false);
+        if (err)
+                return err;
+
+        if (unix_passcred_enabled(socket, other)) {
+                scm->pid = get_pid(task_tgid(current));
+                current_uid_gid(&scm->creds.uid, &scm->creds.gid);
+        }
+        return err;
+}
+
+static bool unix_skb_scm_eq(struct sk_buff *skb,
+                            struct scm_cookie *scm)
+{
+        const struct unix_skb_parms *u = &UNIXCB(skb);
+
+        return u->pid == scm->pid &&
+               uid_eq(u->uid, scm->creds.uid) &&
+               gid_eq(u->gid, scm->creds.gid) &&
+               unix_secdata_eq(scm, skb);
+}
+
 /*
  *      Send AF_UNIX data.
  */
@@ -1472,6 +1624,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
         struct scm_cookie scm;
         int max_level;
         int data_len = 0;
+        int sk_locked;
 
         wait_for_unix_gc();
         err = scm_send(sock, msg, &scm, false);
@@ -1550,12 +1703,14 @@ restart:
                 goto out_free;
         }
 
+        sk_locked = 0;
         unix_state_lock(other);
+restart_locked:
         err = -EPERM;
         if (!unix_may_send(sk, other))
                 goto out_unlock;
 
-        if (sock_flag(other, SOCK_DEAD)) {
+        if (unlikely(sock_flag(other, SOCK_DEAD))) {
                 /*
                  *      Check with 1003.1g - what should
                  *      datagram error
@@ -1563,10 +1718,14 @@ restart:
                 unix_state_unlock(other);
                 sock_put(other);
 
+                if (!sk_locked)
+                        unix_state_lock(sk);
+
                 err = 0;
-                unix_state_lock(sk);
                 if (unix_peer(sk) == other) {
                         unix_peer(sk) = NULL;
+                        unix_dgram_peer_wake_disconnect_wakeup(sk, other);
+
                         unix_state_unlock(sk);
 
                         unix_dgram_disconnected(sk, other);
@@ -1592,21 +1751,38 @@ restart:
                         goto out_unlock;
         }
 
-        if (unix_peer(other) != sk && unix_recvq_full(other)) {
-                if (!timeo) {
-                        err = -EAGAIN;
-                        goto out_unlock;
+        if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
+                if (timeo) {
+                        timeo = unix_wait_for_peer(other, timeo);
+
+                        err = sock_intr_errno(timeo);
+                        if (signal_pending(current))
+                                goto out_free;
+
+                        goto restart;
                 }
 
-                timeo = unix_wait_for_peer(other, timeo);
+                if (!sk_locked) {
+                        unix_state_unlock(other);
+                        unix_state_double_lock(sk, other);
+                }
 
-                err = sock_intr_errno(timeo);
-                if (signal_pending(current))
-                        goto out_free;
+                if (unix_peer(sk) != other ||
+                    unix_dgram_peer_wake_me(sk, other)) {
+                        err = -EAGAIN;
+                        sk_locked = 1;
+                        goto out_unlock;
+                }
 
-                goto restart;
+                if (!sk_locked) {
+                        sk_locked = 1;
+                        goto restart_locked;
+                }
         }
 
+        if (unlikely(sk_locked))
+                unix_state_unlock(sk);
+
         if (sock_flag(other, SOCK_RCVTSTAMP))
                 __net_timestamp(skb);
         maybe_add_creds(skb, sock, other);
@@ -1620,6 +1796,8 @@ restart:
         return len;
 
 out_unlock:
+        if (sk_locked)
+                unix_state_unlock(sk);
         unix_state_unlock(other);
 out_free:
         kfree_skb(skb);
@@ -1741,8 +1919,10 @@ out_err:
 static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page,
                                     int offset, size_t size, int flags)
 {
-        int err = 0;
-        bool send_sigpipe = true;
+        int err;
+        bool send_sigpipe = false;
+        bool init_scm = true;
+        struct scm_cookie scm;
         struct sock *other, *sk = socket->sk;
         struct sk_buff *skb, *newskb = NULL, *tail = NULL;
 
@@ -1760,7 +1940,7 @@ alloc_skb:
                 newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT,
                                               &err, 0);
                 if (!newskb)
-                        return err;
+                        goto err;
         }
 
         /* we must acquire readlock as we modify already present
@@ -1769,12 +1949,12 @@ alloc_skb:
         err = mutex_lock_interruptible(&unix_sk(other)->readlock);
         if (err) {
                 err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS;
-                send_sigpipe = false;
                 goto err;
         }
 
         if (sk->sk_shutdown & SEND_SHUTDOWN) {
                 err = -EPIPE;
+                send_sigpipe = true;
                 goto err_unlock;
         }
 
@@ -1783,17 +1963,27 @@ alloc_skb:
         if (sock_flag(other, SOCK_DEAD) ||
             other->sk_shutdown & RCV_SHUTDOWN) {
                 err = -EPIPE;
+                send_sigpipe = true;
                 goto err_state_unlock;
         }
 
+        if (init_scm) {
+                err = maybe_init_creds(&scm, socket, other);
+                if (err)
+                        goto err_state_unlock;
+                init_scm = false;
+        }
+
         skb = skb_peek_tail(&other->sk_receive_queue);
         if (tail && tail == skb) {
                 skb = newskb;
-        } else if (!skb) {
-                if (newskb)
+        } else if (!skb || !unix_skb_scm_eq(skb, &scm)) {
+                if (newskb) {
                         skb = newskb;
-                else
+                } else {
+                        tail = skb;
                         goto alloc_skb;
+                }
         } else if (newskb) {
                 /* this is fast path, we don't necessarily need to
                  * call to kfree_skb even though with newskb == NULL
@@ -1814,6 +2004,9 @@ alloc_skb:
         atomic_add(size, &sk->sk_wmem_alloc);
 
         if (newskb) {
+                err = unix_scm_to_skb(&scm, skb, false);
+                if (err)
+                        goto err_state_unlock;
                 spin_lock(&other->sk_receive_queue.lock);
                 __skb_queue_tail(&other->sk_receive_queue, newskb);
                 spin_unlock(&other->sk_receive_queue.lock);
@@ -1823,7 +2016,7 @@ alloc_skb:
         mutex_unlock(&unix_sk(other)->readlock);
 
         other->sk_data_ready(other);
-
+        scm_destroy(&scm);
         return size;
 
 err_state_unlock:
@@ -1834,6 +2027,8 @@ err:
         kfree_skb(newskb);
         if (send_sigpipe && !(flags & MSG_NOSIGNAL))
                 send_sig(SIGPIPE, current, 0);
+        if (!init_scm)
+                scm_destroy(&scm);
         return err;
 }
 
@@ -1996,7 +2191,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
                     !timeo)
                         break;
 
-                set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+                sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
                 unix_state_unlock(sk);
                 timeo = freezable_schedule_timeout(timeo);
                 unix_state_lock(sk);
@@ -2004,7 +2199,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
                 if (sock_flag(sk, SOCK_DEAD))
                         break;
 
-                clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+                sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
         }
 
         finish_wait(sk_sleep(sk), &wait);
@@ -2137,10 +2332,7 @@ unlock:
 
                 if (check_creds) {
                         /* Never glue messages from different writers */
-                        if ((UNIXCB(skb).pid  != scm.pid) ||
-                            !uid_eq(UNIXCB(skb).uid, scm.creds.uid) ||
-                            !gid_eq(UNIXCB(skb).gid, scm.creds.gid) ||
-                            !unix_secdata_eq(&scm, skb))
+                        if (!unix_skb_scm_eq(skb, &scm))
                                 break;
                 } else if (test_bit(SOCK_PASSCRED, &sock->flags)) {
                         /* Copy credentials */
@@ -2476,20 +2668,22 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
                 return mask;
 
         writable = unix_writable(sk);
-        other = unix_peer_get(sk);
-        if (other) {
-                if (unix_peer(other) != sk) {
-                        sock_poll_wait(file, &unix_sk(other)->peer_wait, wait);
-                        if (unix_recvq_full(other))
-                                writable = 0;
-                }
-                sock_put(other);
+        if (writable) {
+                unix_state_lock(sk);
+
+                other = unix_peer(sk);
+                if (other && unix_peer(other) != sk &&
+                    unix_recvq_full(other) &&
+                    unix_dgram_peer_wake_me(sk, other))
+                        writable = 0;
+
+                unix_state_unlock(sk);
         }
 
         if (writable)
                 mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
         else
-                set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+                sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
         return mask;
 }
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 1a10d8ac8162..dacf71a43ad4 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -62,7 +62,7 @@ vmlinux_link()
                         -Wl,--start-group                                    \
                                  ${KBUILD_VMLINUX_MAIN}                      \
                         -Wl,--end-group                                      \
-                        -lutil ${1}
+                        -lutil -lrt ${1}
                 rm -f linux
         fi
 }
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 927db9f35ad6..696ccfa08d10 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -845,6 +845,8 @@ static int encrypted_update(struct key *key, struct key_preparsed_payload *prep)
         size_t datalen = prep->datalen;
         int ret = 0;
 
+        if (test_bit(KEY_FLAG_NEGATIVE, &key->flags))
+                return -ENOKEY;
         if (datalen <= 0 || datalen > 32767 || !prep->data)
                 return -EINVAL;
 
diff --git a/security/keys/trusted.c b/security/keys/trusted.c
index 903dace648a1..16dec53184b6 100644
--- a/security/keys/trusted.c
+++ b/security/keys/trusted.c
@@ -1007,13 +1007,16 @@ static void trusted_rcu_free(struct rcu_head *rcu)
  */
 static int trusted_update(struct key *key, struct key_preparsed_payload *prep)
 {
-        struct trusted_key_payload *p = key->payload.data[0];
+        struct trusted_key_payload *p;
         struct trusted_key_payload *new_p;
         struct trusted_key_options *new_o;
         size_t datalen = prep->datalen;
         char *datablob;
         int ret = 0;
 
+        if (test_bit(KEY_FLAG_NEGATIVE, &key->flags))
+                return -ENOKEY;
+        p = key->payload.data[0];
         if (!p->migratable)
                 return -EPERM;
         if (datalen <= 0 || datalen > 32767 || !prep->data)
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index 28cb30f80256..8705d79b2c6f 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -120,7 +120,10 @@ int user_update(struct key *key, struct key_preparsed_payload *prep)
 
         if (ret == 0) {
                 /* attach the new data, displacing the old */
-                zap = key->payload.data[0];
+                if (!test_bit(KEY_FLAG_NEGATIVE, &key->flags))
+                        zap = key->payload.data[0];
+                else
+                        zap = NULL;
                 rcu_assign_keypointer(key, upayload);
                 key->expiry = 0;
         }
diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c
index 18643bf9894d..456e1a9bcfde 100644
--- a/security/selinux/ss/conditional.c
+++ b/security/selinux/ss/conditional.c
@@ -638,7 +638,7 @@ void cond_compute_av(struct avtab *ctab, struct avtab_key *key,
 {
         struct avtab_node *node;
 
-        if (!ctab || !key || !avd || !xperms)
+        if (!ctab || !key || !avd)
                 return;
 
         for (node = avtab_search_node(ctab, key); node;
@@ -657,7 +657,7 @@ void cond_compute_av(struct avtab *ctab, struct avtab_key *key,
                 if ((u16)(AVTAB_AUDITALLOW|AVTAB_ENABLED) ==
                     (node->key.specified & (AVTAB_AUDITALLOW|AVTAB_ENABLED)))
                         avd->auditallow |= node->datum.u.data;
-                if ((node->key.specified & AVTAB_ENABLED) &&
+                if (xperms && (node->key.specified & AVTAB_ENABLED) &&
                                 (node->key.specified & AVTAB_XPERMS))
                         services_compute_xperms_drivers(xperms, node);
         }
diff --git a/sound/firewire/dice/dice.c b/sound/firewire/dice/dice.c
index 5d99436dfcae..0cda05c72f50 100644
--- a/sound/firewire/dice/dice.c
+++ b/sound/firewire/dice/dice.c
@@ -12,9 +12,11 @@ MODULE_AUTHOR("Clemens Ladisch <clemens@ladisch.de>");
 MODULE_LICENSE("GPL v2");
 
 #define OUI_WEISS               0x001c6a
+#define OUI_LOUD                0x000ff2
 
 #define DICE_CATEGORY_ID        0x04
 #define WEISS_CATEGORY_ID       0x00
+#define LOUD_CATEGORY_ID        0x10
 
 static int dice_interface_check(struct fw_unit *unit)
 {
@@ -57,6 +59,8 @@ static int dice_interface_check(struct fw_unit *unit)
         }
         if (vendor == OUI_WEISS)
                 category = WEISS_CATEGORY_ID;
+        else if (vendor == OUI_LOUD)
+                category = LOUD_CATEGORY_ID;
         else
                 category = DICE_CATEGORY_ID;
         if (device->config_rom[3] != ((vendor << 8) | category) ||
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 8a7fbdcb4072..bff5c8b329d1 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -312,6 +312,10 @@ enum {
         (AZX_DCAPS_INTEL_PCH | AZX_DCAPS_SEPARATE_STREAM_TAG |\
          AZX_DCAPS_I915_POWERWELL)
 
+#define AZX_DCAPS_INTEL_BROXTON \
+        (AZX_DCAPS_INTEL_PCH | AZX_DCAPS_SEPARATE_STREAM_TAG |\
+         AZX_DCAPS_I915_POWERWELL)
+
 /* quirks for ATI SB / AMD Hudson */
 #define AZX_DCAPS_PRESET_ATI_SB \
         (AZX_DCAPS_NO_TCSEL | AZX_DCAPS_SYNC_WRITE | AZX_DCAPS_POSFIX_LPIB |\
@@ -351,6 +355,8 @@ enum {
                                         ((pci)->device == 0x0d0c) || \
                                         ((pci)->device == 0x160c))
 
+#define IS_BROXTON(pci) ((pci)->device == 0x5a98)
+
 static char *driver_short_names[] = {
         [AZX_DRIVER_ICH] = "HDA Intel",
         [AZX_DRIVER_PCH] = "HDA Intel PCH",
@@ -502,15 +508,36 @@ static void azx_init_pci(struct azx *chip)
         }
 }
 
+/*
+ * In BXT-P A0, HD-Audio DMA requests is later than expected,
+ * and makes an audio stream sensitive to system latencies when
+ * 24/32 bits are playing.
+ * Adjusting threshold of DMA fifo to force the DMA request
+ * sooner to improve latency tolerance at the expense of power.
+ */
+static void bxt_reduce_dma_latency(struct azx *chip)
+{
+        u32 val;
+
+        val = azx_readl(chip, SKL_EM4L);
+        val &= (0x3 << 20);
+        azx_writel(chip, SKL_EM4L, val);
+}
+
 static void hda_intel_init_chip(struct azx *chip, bool full_reset)
 {
         struct hdac_bus *bus = azx_bus(chip);
+        struct pci_dev *pci = chip->pci;
 
         if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
                 snd_hdac_set_codec_wakeup(bus, true);
         azx_init_chip(chip, full_reset);
         if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
                 snd_hdac_set_codec_wakeup(bus, false);
+
+        /* reduce dma latency to avoid noise */
+        if (IS_BROXTON(pci))
+                bxt_reduce_dma_latency(chip);
 }
 
 /* calculate runtime delay from LPIB */
@@ -2124,6 +2151,9 @@ static const struct pci_device_id azx_ids[] = {
         /* Sunrise Point-LP */
         { PCI_DEVICE(0x8086, 0x9d70),
           .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
+        /* Broxton-P(Apollolake) */
+        { PCI_DEVICE(0x8086, 0x5a98),
+          .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_BROXTON },
         /* Haswell */
         { PCI_DEVICE(0x8086, 0x0a0c),
           .driver_data = AZX_DRIVER_HDMI | AZX_DCAPS_INTEL_HASWELL },
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index f8a12ca477f1..4ef2259f88ca 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -778,7 +778,8 @@ static const struct hda_pintbl alienware_pincfgs[] = {
 };
 
 static const struct snd_pci_quirk ca0132_quirks[] = {
-        SND_PCI_QUIRK(0x1028, 0x0685, "Alienware 15", QUIRK_ALIENWARE),
+        SND_PCI_QUIRK(0x1028, 0x0685, "Alienware 15 2015", QUIRK_ALIENWARE),
+        SND_PCI_QUIRK(0x1028, 0x0688, "Alienware 17 2015", QUIRK_ALIENWARE),
         {}
 };
 
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index c8b8ef5246a6..ef198903c0c3 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -955,6 +955,7 @@ static int patch_conexant_auto(struct hda_codec *codec)
  */
 
 static const struct hda_device_id snd_hda_id_conexant[] = {
+        HDA_CODEC_ENTRY(0x14f12008, "CX8200", patch_conexant_auto),
         HDA_CODEC_ENTRY(0x14f15045, "CX20549 (Venice)", patch_conexant_auto),
         HDA_CODEC_ENTRY(0x14f15047, "CX20551 (Waikiki)", patch_conexant_auto),
         HDA_CODEC_ENTRY(0x14f15051, "CX20561 (Hermosa)", patch_conexant_auto),
@@ -972,9 +973,9 @@ static const struct hda_device_id snd_hda_id_conexant[] = {
         HDA_CODEC_ENTRY(0x14f150ac, "CX20652", patch_conexant_auto),
         HDA_CODEC_ENTRY(0x14f150b8, "CX20664", patch_conexant_auto),
         HDA_CODEC_ENTRY(0x14f150b9, "CX20665", patch_conexant_auto),
-        HDA_CODEC_ENTRY(0x14f150f1, "CX20721", patch_conexant_auto),
+        HDA_CODEC_ENTRY(0x14f150f1, "CX21722", patch_conexant_auto),
         HDA_CODEC_ENTRY(0x14f150f2, "CX20722", patch_conexant_auto),
-        HDA_CODEC_ENTRY(0x14f150f3, "CX20723", patch_conexant_auto),
+        HDA_CODEC_ENTRY(0x14f150f3, "CX21724", patch_conexant_auto),
         HDA_CODEC_ENTRY(0x14f150f4, "CX20724", patch_conexant_auto),
         HDA_CODEC_ENTRY(0x14f1510f, "CX20751/2", patch_conexant_auto),
         HDA_CODEC_ENTRY(0x14f15110, "CX20751/2", patch_conexant_auto),
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 60cd9e700909..4b6fb668c91c 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -2352,6 +2352,12 @@ static void intel_pin_eld_notify(void *audio_ptr, int port)
         struct hda_codec *codec = audio_ptr;
         int pin_nid = port + 0x04;
 
+        /* skip notification during system suspend (but not in runtime PM);
+         * the state will be updated at resume
+         */
+        if (snd_power_get_state(codec->card) != SNDRV_CTL_POWER_D0)
+                return;
+
         check_presence_and_report(codec, pin_nid);
 }
 
@@ -2378,7 +2384,8 @@ static int patch_generic_hdmi(struct hda_codec *codec)
          * can cover the codec power request, and so need not set this flag.
          * For previous platforms, there is no such power well feature.
          */
-        if (is_valleyview_plus(codec) || is_skylake(codec))
+        if (is_valleyview_plus(codec) || is_skylake(codec) ||
+                        is_broxton(codec))
                 codec->core.link_power_control = 1;
 
         if (is_haswell_plus(codec) || is_valleyview_plus(codec)) {
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 2f7b065f9ac4..8dd2ac13b3af 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -1759,6 +1759,7 @@ enum {
         ALC882_FIXUP_NO_PRIMARY_HP,
         ALC887_FIXUP_ASUS_BASS,
         ALC887_FIXUP_BASS_CHMAP,
+        ALC882_FIXUP_DISABLE_AAMIX,
 };
 
 static void alc889_fixup_coef(struct hda_codec *codec,
@@ -1920,6 +1921,8 @@ static void alc882_fixup_no_primary_hp(struct hda_codec *codec,
 
 static void alc_fixup_bass_chmap(struct hda_codec *codec,
                                  const struct hda_fixup *fix, int action);
+static void alc_fixup_disable_aamix(struct hda_codec *codec,
+                                    const struct hda_fixup *fix, int action);
 
 static const struct hda_fixup alc882_fixups[] = {
         [ALC882_FIXUP_ABIT_AW9D_MAX] = {
@@ -2151,6 +2154,10 @@ static const struct hda_fixup alc882_fixups[] = {
                 .type = HDA_FIXUP_FUNC,
                 .v.func = alc_fixup_bass_chmap,
         },
+        [ALC882_FIXUP_DISABLE_AAMIX] = {
+                .type = HDA_FIXUP_FUNC,
+                .v.func = alc_fixup_disable_aamix,
+        },
 };
 
 static const struct snd_pci_quirk alc882_fixup_tbl[] = {
@@ -2218,6 +2225,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
         SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD),
         SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
         SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE),
+        SND_PCI_QUIRK(0x1458, 0xa182, "Gigabyte Z170X-UD3", ALC882_FIXUP_DISABLE_AAMIX),
         SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX),
         SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
         SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD),
@@ -4196,6 +4204,18 @@ static void alc_fixup_tpt440_dock(struct hda_codec *codec,
         }
 }
 
+/* additional fixup for Thinkpad T440s noise problem */
+static void alc_fixup_tpt440(struct hda_codec *codec,
+                                  const struct hda_fixup *fix, int action)
+{
+        struct alc_spec *spec = codec->spec;
+
+        if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+                spec->shutup = alc_no_shutup; /* reduce click noise */
+                spec->gen.mixer_nid = 0; /* reduce background noise */
+        }
+}
+
 static void alc_shutup_dell_xps13(struct hda_codec *codec)
 {
         struct alc_spec *spec = codec->spec;
@@ -4570,6 +4590,7 @@ enum {
         ALC255_FIXUP_HEADSET_MODE_NO_HP_MIC,
         ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
         ALC292_FIXUP_TPT440_DOCK,
+        ALC292_FIXUP_TPT440,
         ALC283_FIXUP_BXBT2807_MIC,
         ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED,
         ALC282_FIXUP_ASPIRE_V5_PINS,
@@ -4587,6 +4608,8 @@ enum {
         ALC292_FIXUP_DISABLE_AAMIX,
         ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
         ALC275_FIXUP_DELL_XPS,
+        ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE,
+        ALC293_FIXUP_LENOVO_SPK_NOISE,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -5041,6 +5064,12 @@ static const struct hda_fixup alc269_fixups[] = {
                 .chained = true,
                 .chain_id = ALC269_FIXUP_LIMIT_INT_MIC_BOOST
         },
+        [ALC292_FIXUP_TPT440] = {
+                .type = HDA_FIXUP_FUNC,
+                .v.func = alc_fixup_tpt440,
+                .chained = true,
+                .chain_id = ALC292_FIXUP_TPT440_DOCK,
+        },
         [ALC283_FIXUP_BXBT2807_MIC] = {
                 .type = HDA_FIXUP_PINS,
                 .v.pins = (const struct hda_pintbl[]) {
@@ -5167,6 +5196,23 @@ static const struct hda_fixup alc269_fixups[] = {
                         {}
                 }
         },
+        [ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE] = {
+                .type = HDA_FIXUP_VERBS,
+                .v.verbs = (const struct hda_verb[]) {
+                        /* Disable pass-through path for FRONT 14h */
+                        {0x20, AC_VERB_SET_COEF_INDEX, 0x36},
+                        {0x20, AC_VERB_SET_PROC_COEF, 0x1737},
+                        {}
+                },
+                .chained = true,
+                .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE
+        },
+        [ALC293_FIXUP_LENOVO_SPK_NOISE] = {
+                .type = HDA_FIXUP_FUNC,
+                .v.func = alc_fixup_disable_aamix,
+                .chained = true,
+                .chain_id = ALC269_FIXUP_THINKPAD_ACPI
+        },
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -5180,8 +5226,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
         SND_PCI_QUIRK(0x1025, 0x0742, "Acer AO756", ALC271_FIXUP_HP_GATE_MIC_JACK),
         SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
         SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
+        SND_PCI_QUIRK(0x1025, 0x106d, "Acer Cloudbook 14", ALC283_FIXUP_CHROME_BOOK),
         SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z),
         SND_PCI_QUIRK(0x1028, 0x054b, "Dell XPS one 2710", ALC275_FIXUP_DELL_XPS),
+        SND_PCI_QUIRK(0x1028, 0x05bd, "Dell Latitude E6440", ALC292_FIXUP_DELL_E7X),
         SND_PCI_QUIRK(0x1028, 0x05ca, "Dell Latitude E7240", ALC292_FIXUP_DELL_E7X),
         SND_PCI_QUIRK(0x1028, 0x05cb, "Dell Latitude E7440", ALC292_FIXUP_DELL_E7X),
         SND_PCI_QUIRK(0x1028, 0x05da, "Dell Vostro 5460", ALC290_FIXUP_SUBWOOFER),
@@ -5204,6 +5252,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
         SND_PCI_QUIRK(0x1028, 0x06de, "Dell", ALC292_FIXUP_DISABLE_AAMIX),
         SND_PCI_QUIRK(0x1028, 0x06df, "Dell", ALC292_FIXUP_DISABLE_AAMIX),
         SND_PCI_QUIRK(0x1028, 0x06e0, "Dell", ALC292_FIXUP_DISABLE_AAMIX),
+        SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
         SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
         SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
         SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
@@ -5302,7 +5351,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
         SND_PCI_QUIRK(0x17aa, 0x21fb, "Thinkpad T430s", ALC269_FIXUP_LENOVO_DOCK),
         SND_PCI_QUIRK(0x17aa, 0x2203, "Thinkpad X230 Tablet", ALC269_FIXUP_LENOVO_DOCK),
         SND_PCI_QUIRK(0x17aa, 0x2208, "Thinkpad T431s", ALC269_FIXUP_LENOVO_DOCK),
-        SND_PCI_QUIRK(0x17aa, 0x220c, "Thinkpad T440s", ALC292_FIXUP_TPT440_DOCK),
+        SND_PCI_QUIRK(0x17aa, 0x220c, "Thinkpad T440s", ALC292_FIXUP_TPT440),
         SND_PCI_QUIRK(0x17aa, 0x220e, "Thinkpad T440p", ALC292_FIXUP_TPT440_DOCK),
         SND_PCI_QUIRK(0x17aa, 0x2210, "Thinkpad T540p", ALC292_FIXUP_TPT440_DOCK),
         SND_PCI_QUIRK(0x17aa, 0x2211, "Thinkpad W541", ALC292_FIXUP_TPT440_DOCK),
@@ -5311,6 +5360,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
         SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
         SND_PCI_QUIRK(0x17aa, 0x2223, "ThinkPad T550", ALC292_FIXUP_TPT440_DOCK),
         SND_PCI_QUIRK(0x17aa, 0x2226, "ThinkPad X250", ALC292_FIXUP_TPT440_DOCK),
+        SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE),
         SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
         SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP),
         SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -5320,6 +5370,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
         SND_PCI_QUIRK(0x17aa, 0x5034, "Thinkpad T450", ALC292_FIXUP_TPT440_DOCK),
         SND_PCI_QUIRK(0x17aa, 0x5036, "Thinkpad T450s", ALC292_FIXUP_TPT440_DOCK),
         SND_PCI_QUIRK(0x17aa, 0x503c, "Thinkpad L450", ALC292_FIXUP_TPT440_DOCK),
+        SND_PCI_QUIRK(0x17aa, 0x504b, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE),
         SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
         SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K),
         SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD),
@@ -5400,6 +5451,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
         {.id = ALC283_FIXUP_CHROME_BOOK, .name = "alc283-dac-wcaps"},
         {.id = ALC283_FIXUP_SENSE_COMBO_JACK, .name = "alc283-sense-combo"},
         {.id = ALC292_FIXUP_TPT440_DOCK, .name = "tpt440-dock"},
+        {.id = ALC292_FIXUP_TPT440, .name = "tpt440"},
         {}
 };
 
@@ -6386,6 +6438,7 @@ static const struct hda_fixup alc662_fixups[] = {
 static const struct snd_pci_quirk alc662_fixup_tbl[] = {
         SND_PCI_QUIRK(0x1019, 0x9087, "ECS", ALC662_FIXUP_ASUS_MODE2),
         SND_PCI_QUIRK(0x1025, 0x022f, "Acer Aspire One", ALC662_FIXUP_INV_DMIC),
+        SND_PCI_QUIRK(0x1025, 0x0241, "Packard Bell DOTS", ALC662_FIXUP_INV_DMIC),
         SND_PCI_QUIRK(0x1025, 0x0308, "Acer Aspire 8942G", ALC662_FIXUP_ASPIRE),
         SND_PCI_QUIRK(0x1025, 0x031c, "Gateway NV79", ALC662_FIXUP_SKU_IGNORE),
         SND_PCI_QUIRK(0x1025, 0x0349, "eMachines eM250", ALC662_FIXUP_INV_DMIC),
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 826122d8acee..2c7c5eb8b1e9 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -3110,6 +3110,29 @@ static void stac92hd71bxx_fixup_hp_hdx(struct hda_codec *codec,
         spec->gpio_led = 0x08;
 }
 
+static bool is_hp_output(struct hda_codec *codec, hda_nid_t pin)
+{
+        unsigned int pin_cfg = snd_hda_codec_get_pincfg(codec, pin);
+
+        /* count line-out, too, as BIOS sets often so */
+        return get_defcfg_connect(pin_cfg) != AC_JACK_PORT_NONE &&
+                (get_defcfg_device(pin_cfg) == AC_JACK_LINE_OUT ||
+                 get_defcfg_device(pin_cfg) == AC_JACK_HP_OUT);
+}
+
+static void fixup_hp_headphone(struct hda_codec *codec, hda_nid_t pin)
+{
+        unsigned int pin_cfg = snd_hda_codec_get_pincfg(codec, pin);
+
+        /* It was changed in the BIOS to just satisfy MS DTM.
+         * Lets turn it back into slaved HP
+         */
+        pin_cfg = (pin_cfg & (~AC_DEFCFG_DEVICE)) |
+                (AC_JACK_HP_OUT << AC_DEFCFG_DEVICE_SHIFT);
+        pin_cfg = (pin_cfg & (~(AC_DEFCFG_DEF_ASSOC | AC_DEFCFG_SEQUENCE))) |
+                0x1f;
+        snd_hda_codec_set_pincfg(codec, pin, pin_cfg);
+}
 
 static void stac92hd71bxx_fixup_hp(struct hda_codec *codec,
                                    const struct hda_fixup *fix, int action)
@@ -3119,22 +3142,12 @@ static void stac92hd71bxx_fixup_hp(struct hda_codec *codec,
         if (action != HDA_FIXUP_ACT_PRE_PROBE)
                 return;
 
-        if (hp_blike_system(codec->core.subsystem_id)) {
-                unsigned int pin_cfg = snd_hda_codec_get_pincfg(codec, 0x0f);
-                if (get_defcfg_device(pin_cfg) == AC_JACK_LINE_OUT ||
-                        get_defcfg_device(pin_cfg) == AC_JACK_SPEAKER  ||
-                        get_defcfg_device(pin_cfg) == AC_JACK_HP_OUT) {
-                        /* It was changed in the BIOS to just satisfy MS DTM.
-                         * Lets turn it back into slaved HP
-                         */
-                        pin_cfg = (pin_cfg & (~AC_DEFCFG_DEVICE))
-                                        | (AC_JACK_HP_OUT <<
-                                                AC_DEFCFG_DEVICE_SHIFT);
-                        pin_cfg = (pin_cfg & (~(AC_DEFCFG_DEF_ASSOC
-                                                        | AC_DEFCFG_SEQUENCE)))
-                                                                | 0x1f;
-                        snd_hda_codec_set_pincfg(codec, 0x0f, pin_cfg);
-                }
+        /* when both output A and F are assigned, these are supposedly
+         * dock and built-in headphones; fix both pin configs
+         */
+        if (is_hp_output(codec, 0x0a) && is_hp_output(codec, 0x0f)) {
+                fixup_hp_headphone(codec, 0x0a);
+                fixup_hp_headphone(codec, 0x0f);
         }
 
         if (find_mute_led_cfg(codec, 1))
diff --git a/sound/pci/rme96.c b/sound/pci/rme96.c
index 714df906249e..41c31db65039 100644
--- a/sound/pci/rme96.c
+++ b/sound/pci/rme96.c
@@ -741,10 +741,11 @@ snd_rme96_playback_setrate(struct rme96 *rme96,
         {
                 /* change to/from double-speed: reset the DAC (if available) */
                 snd_rme96_reset_dac(rme96);
+                return 1; /* need to restore volume */
         } else {
                 writel(rme96->wcreg, rme96->iobase + RME96_IO_CONTROL_REGISTER);
+                return 0;
         }
-        return 0;
 }
 
 static int
@@ -980,6 +981,7 @@ snd_rme96_playback_hw_params(struct snd_pcm_substream *substream,
         struct rme96 *rme96 = snd_pcm_substream_chip(substream);
         struct snd_pcm_runtime *runtime = substream->runtime;
         int err, rate, dummy;
+        bool apply_dac_volume = false;
 
         runtime->dma_area = (void __force *)(rme96->iobase +
                                              RME96_IO_PLAY_BUFFER);
@@ -993,24 +995,26 @@ snd_rme96_playback_hw_params(struct snd_pcm_substream *substream,
         {
                 /* slave clock */
                 if ((int)params_rate(params) != rate) {
-                        spin_unlock_irq(&rme96->lock);
-                        return -EIO;                    
-                }
-        } else if ((err = snd_rme96_playback_setrate(rme96, params_rate(params))) < 0) {
-                spin_unlock_irq(&rme96->lock);
-                return err;
-        }
-        if ((err = snd_rme96_playback_setformat(rme96, params_format(params))) < 0) {
-                spin_unlock_irq(&rme96->lock);
-                return err;
+                        err = -EIO;
+                        goto error;
+                }
+        } else {
+                err = snd_rme96_playback_setrate(rme96, params_rate(params));
+                if (err < 0)
+                        goto error;
+                apply_dac_volume = err > 0; /* need to restore volume later? */
         }
+
+        err = snd_rme96_playback_setformat(rme96, params_format(params));
+        if (err < 0)
+                goto error;
         snd_rme96_setframelog(rme96, params_channels(params), 1);
         if (rme96->capture_periodsize != 0) {
                 if (params_period_size(params) << rme96->playback_frlog !=
                     rme96->capture_periodsize)
                 {
-                        spin_unlock_irq(&rme96->lock);
-                        return -EBUSY;
+                        err = -EBUSY;
+                        goto error;
                 }
         }
         rme96->playback_periodsize =
@@ -1021,9 +1025,16 @@ snd_rme96_playback_hw_params(struct snd_pcm_substream *substream,
                 rme96->wcreg &= ~(RME96_WCR_PRO | RME96_WCR_DOLBY | RME96_WCR_EMP);
                 writel(rme96->wcreg |= rme96->wcreg_spdif_stream, rme96->iobase + RME96_IO_CONTROL_REGISTER);
         }
+
+        err = 0;
+ error:
         spin_unlock_irq(&rme96->lock);
-                
-        return 0;
+        if (apply_dac_volume) {
+                usleep_range(3000, 10000);
+                snd_rme96_apply_dac_volume(rme96);
+        }
+
+        return err;
 }
 
 static int
diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c
index 9929efc6b9aa..b3ea24d64c50 100644
--- a/sound/soc/codecs/arizona.c
+++ b/sound/soc/codecs/arizona.c
@@ -1023,24 +1023,18 @@ void arizona_init_dvfs(struct arizona_priv *priv)
 }
 EXPORT_SYMBOL_GPL(arizona_init_dvfs);
 
-static unsigned int arizona_sysclk_48k_rates[] = {
+static unsigned int arizona_opclk_ref_48k_rates[] = {
         6144000,
         12288000,
         24576000,
         49152000,
-        73728000,
-        98304000,
-        147456000,
 };
 
-static unsigned int arizona_sysclk_44k1_rates[] = {
+static unsigned int arizona_opclk_ref_44k1_rates[] = {
         5644800,
         11289600,
         22579200,
         45158400,
-        67737600,
-        90316800,
-        135475200,
 };
 
 static int arizona_set_opclk(struct snd_soc_codec *codec, unsigned int clk,
@@ -1065,11 +1059,11 @@ static int arizona_set_opclk(struct snd_soc_codec *codec, unsigned int clk,
         }
 
         if (refclk % 8000)
-                rates = arizona_sysclk_44k1_rates;
+                rates = arizona_opclk_ref_44k1_rates;
         else
-                rates = arizona_sysclk_48k_rates;
+                rates = arizona_opclk_ref_48k_rates;
 
-        for (ref = 0; ref < ARRAY_SIZE(arizona_sysclk_48k_rates) &&
+        for (ref = 0; ref < ARRAY_SIZE(arizona_opclk_ref_48k_rates) &&
                      rates[ref] <= refclk; ref++) {
                 div = 1;
                 while (rates[ref] / div >= freq && div < 32) {
diff --git a/sound/soc/codecs/es8328.c b/sound/soc/codecs/es8328.c
index 969e337dc17c..84f5eb07a91b 100644
--- a/sound/soc/codecs/es8328.c
+++ b/sound/soc/codecs/es8328.c
@@ -205,18 +205,18 @@ static const struct snd_kcontrol_new es8328_right_line_controls =
 
 /* Left Mixer */
 static const struct snd_kcontrol_new es8328_left_mixer_controls[] = {
-        SOC_DAPM_SINGLE("Playback Switch", ES8328_DACCONTROL17, 8, 1, 0),
-        SOC_DAPM_SINGLE("Left Bypass Switch", ES8328_DACCONTROL17, 7, 1, 0),
-        SOC_DAPM_SINGLE("Right Playback Switch", ES8328_DACCONTROL18, 8, 1, 0),
-        SOC_DAPM_SINGLE("Right Bypass Switch", ES8328_DACCONTROL18, 7, 1, 0),
+        SOC_DAPM_SINGLE("Playback Switch", ES8328_DACCONTROL17, 7, 1, 0),
+        SOC_DAPM_SINGLE("Left Bypass Switch", ES8328_DACCONTROL17, 6, 1, 0),
+        SOC_DAPM_SINGLE("Right Playback Switch", ES8328_DACCONTROL18, 7, 1, 0),
+        SOC_DAPM_SINGLE("Right Bypass Switch", ES8328_DACCONTROL18, 6, 1, 0),
 };
 
 /* Right Mixer */
 static const struct snd_kcontrol_new es8328_right_mixer_controls[] = {
-        SOC_DAPM_SINGLE("Left Playback Switch", ES8328_DACCONTROL19, 8, 1, 0),
-        SOC_DAPM_SINGLE("Left Bypass Switch", ES8328_DACCONTROL19, 7, 1, 0),
-        SOC_DAPM_SINGLE("Playback Switch", ES8328_DACCONTROL20, 8, 1, 0),
-        SOC_DAPM_SINGLE("Right Bypass Switch", ES8328_DACCONTROL20, 7, 1, 0),
+        SOC_DAPM_SINGLE("Left Playback Switch", ES8328_DACCONTROL19, 7, 1, 0),
+        SOC_DAPM_SINGLE("Left Bypass Switch", ES8328_DACCONTROL19, 6, 1, 0),
+        SOC_DAPM_SINGLE("Playback Switch", ES8328_DACCONTROL20, 7, 1, 0),
+        SOC_DAPM_SINGLE("Right Bypass Switch", ES8328_DACCONTROL20, 6, 1, 0),
 };
 
 static const char * const es8328_pga_sel[] = {
diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c
index 7fc7b4e3f444..c1b87c5800b1 100644
--- a/sound/soc/codecs/nau8825.c
+++ b/sound/soc/codecs/nau8825.c
@@ -1271,6 +1271,36 @@ static int nau8825_i2c_remove(struct i2c_client *client)
         return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int nau8825_suspend(struct device *dev)
+{
+        struct i2c_client *client = to_i2c_client(dev);
+        struct nau8825 *nau8825 = dev_get_drvdata(dev);
+
+        disable_irq(client->irq);
+        regcache_cache_only(nau8825->regmap, true);
+        regcache_mark_dirty(nau8825->regmap);
+
+        return 0;
+}
+
+static int nau8825_resume(struct device *dev)
+{
+        struct i2c_client *client = to_i2c_client(dev);
+        struct nau8825 *nau8825 = dev_get_drvdata(dev);
+
+        regcache_cache_only(nau8825->regmap, false);
+        regcache_sync(nau8825->regmap);
+        enable_irq(client->irq);
+
+        return 0;
+}
+#endif
+
+static const struct dev_pm_ops nau8825_pm = {
+        SET_SYSTEM_SLEEP_PM_OPS(nau8825_suspend, nau8825_resume)
+};
+
 static const struct i2c_device_id nau8825_i2c_ids[] = {
         { "nau8825", 0 },
         { }
@@ -1297,6 +1327,7 @@ static struct i2c_driver nau8825_driver = {
                 .name = "nau8825",
                 .of_match_table = of_match_ptr(nau8825_of_ids),
                 .acpi_match_table = ACPI_PTR(nau8825_acpi_match),
+                .pm = &nau8825_pm,
         },
         .probe = nau8825_i2c_probe,
         .remove = nau8825_i2c_remove,
diff --git a/sound/soc/codecs/rl6231.c b/sound/soc/codecs/rl6231.c
index aca479fa7670..1dc68ab08a17 100644
--- a/sound/soc/codecs/rl6231.c
+++ b/sound/soc/codecs/rl6231.c
@@ -80,8 +80,10 @@ int rl6231_calc_dmic_clk(int rate)
         }
 
         for (i = 0; i < ARRAY_SIZE(div); i++) {
-                /* find divider that gives DMIC frequency below 3MHz */
-                if (3000000 * div[i] >= rate)
+                if ((div[i] % 3) == 0)
+                        continue;
+                /* find divider that gives DMIC frequency below 3.072MHz */
+                if (3072000 * div[i] >= rate)
                         return i;
         }
 
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index 28132375e427..ef76940f9dcb 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -245,7 +245,7 @@ struct rt5645_priv {
         struct snd_soc_jack *hp_jack;
         struct snd_soc_jack *mic_jack;
         struct snd_soc_jack *btn_jack;
-        struct delayed_work jack_detect_work;
+        struct delayed_work jack_detect_work, rcclock_work;
         struct regulator_bulk_data supplies[ARRAY_SIZE(rt5645_supply_names)];
         struct rt5645_eq_param_s *eq_param;
 
@@ -565,12 +565,33 @@ static int rt5645_hweq_put(struct snd_kcontrol *kcontrol,
         .put = rt5645_hweq_put \
 }
 
+static int rt5645_spk_put_volsw(struct snd_kcontrol *kcontrol,
+                struct snd_ctl_elem_value *ucontrol)
+{
+        struct snd_soc_component *component = snd_kcontrol_chip(kcontrol);
+        struct rt5645_priv *rt5645 = snd_soc_component_get_drvdata(component);
+        int ret;
+
+        cancel_delayed_work_sync(&rt5645->rcclock_work);
+
+        regmap_update_bits(rt5645->regmap, RT5645_MICBIAS,
+                RT5645_PWR_CLK25M_MASK, RT5645_PWR_CLK25M_PU);
+
+        ret = snd_soc_put_volsw(kcontrol, ucontrol);
+
+        queue_delayed_work(system_power_efficient_wq, &rt5645->rcclock_work,
+                msecs_to_jiffies(200));
+
+        return ret;
+}
+
 static const struct snd_kcontrol_new rt5645_snd_controls[] = {
         /* Speaker Output Volume */
         SOC_DOUBLE("Speaker Channel Switch", RT5645_SPK_VOL,
                 RT5645_VOL_L_SFT, RT5645_VOL_R_SFT, 1, 1),
-        SOC_DOUBLE_TLV("Speaker Playback Volume", RT5645_SPK_VOL,
-                RT5645_L_VOL_SFT, RT5645_R_VOL_SFT, 39, 1, out_vol_tlv),
+        SOC_DOUBLE_EXT_TLV("Speaker Playback Volume", RT5645_SPK_VOL,
+                RT5645_L_VOL_SFT, RT5645_R_VOL_SFT, 39, 1, snd_soc_get_volsw,
+                rt5645_spk_put_volsw, out_vol_tlv),
 
         /* ClassD modulator Speaker Gain Ratio */
         SOC_SINGLE_TLV("Speaker ClassD Playback Volume", RT5645_SPO_CLSD_RATIO,
@@ -1498,7 +1519,7 @@ static void hp_amp_power(struct snd_soc_codec *codec, int on)
                                 regmap_write(rt5645->regmap, RT5645_PR_BASE +
                                         RT5645_MAMP_INT_REG2, 0xfc00);
                                 snd_soc_write(codec, RT5645_DEPOP_M2, 0x1140);
-                                msleep(40);
+                                msleep(70);
                                 rt5645->hp_on = true;
                         } else {
                                 /* depop parameters */
@@ -3122,6 +3143,15 @@ static void rt5645_jack_detect_work(struct work_struct *work)
                                 SND_JACK_BTN_2 | SND_JACK_BTN_3);
 }
 
+static void rt5645_rcclock_work(struct work_struct *work)
+{
+        struct rt5645_priv *rt5645 =
+                container_of(work, struct rt5645_priv, rcclock_work.work);
+
+        regmap_update_bits(rt5645->regmap, RT5645_MICBIAS,
+                RT5645_PWR_CLK25M_MASK, RT5645_PWR_CLK25M_PD);
+}
+
 static irqreturn_t rt5645_irq(int irq, void *data)
 {
         struct rt5645_priv *rt5645 = data;
@@ -3348,6 +3378,27 @@ static const struct dmi_system_id dmi_platform_intel_braswell[] = {
                         DMI_MATCH(DMI_PRODUCT_NAME, "Reks"),
                 },
         },
+        {
+                .ident = "Google Edgar",
+                .callback = strago_quirk_cb,
+                .matches = {
+                        DMI_MATCH(DMI_PRODUCT_NAME, "Edgar"),
+                },
+        },
+        {
+                .ident = "Google Wizpig",
+                .callback = strago_quirk_cb,
+                .matches = {
+                        DMI_MATCH(DMI_PRODUCT_NAME, "Wizpig"),
+                },
+        },
+        {
+                .ident = "Google Terra",
+                .callback = strago_quirk_cb,
+                .matches = {
+                        DMI_MATCH(DMI_PRODUCT_NAME, "Terra"),
+                },
+        },
         { }
 };
 
@@ -3587,6 +3638,7 @@ static int rt5645_i2c_probe(struct i2c_client *i2c,
         }
 
         INIT_DELAYED_WORK(&rt5645->jack_detect_work, rt5645_jack_detect_work);
+        INIT_DELAYED_WORK(&rt5645->rcclock_work, rt5645_rcclock_work);
 
         if (rt5645->i2c->irq) {
                 ret = request_threaded_irq(rt5645->i2c->irq, NULL, rt5645_irq,
@@ -3621,6 +3673,7 @@ static int rt5645_i2c_remove(struct i2c_client *i2c)
                 free_irq(i2c->irq, rt5645);
 
         cancel_delayed_work_sync(&rt5645->jack_detect_work);
+        cancel_delayed_work_sync(&rt5645->rcclock_work);
 
         snd_soc_unregister_codec(&i2c->dev);
         regulator_bulk_disable(ARRAY_SIZE(rt5645->supplies), rt5645->supplies);
diff --git a/sound/soc/codecs/rt5670.h b/sound/soc/codecs/rt5670.h
index dc2b46236c5c..3f1b0f1df809 100644
--- a/sound/soc/codecs/rt5670.h
+++ b/sound/soc/codecs/rt5670.h
@@ -973,12 +973,12 @@
 #define RT5670_SCLK_SRC_MCLK                    (0x0 << 14)
 #define RT5670_SCLK_SRC_PLL1                    (0x1 << 14)
 #define RT5670_SCLK_SRC_RCCLK                   (0x2 << 14) /* 15MHz */
-#define RT5670_PLL1_SRC_MASK                    (0x3 << 12)
-#define RT5670_PLL1_SRC_SFT                     12
-#define RT5670_PLL1_SRC_MCLK                    (0x0 << 12)
-#define RT5670_PLL1_SRC_BCLK1                   (0x1 << 12)
-#define RT5670_PLL1_SRC_BCLK2                   (0x2 << 12)
-#define RT5670_PLL1_SRC_BCLK3                   (0x3 << 12)
+#define RT5670_PLL1_SRC_MASK                    (0x7 << 11)
+#define RT5670_PLL1_SRC_SFT                     11
+#define RT5670_PLL1_SRC_MCLK                    (0x0 << 11)
+#define RT5670_PLL1_SRC_BCLK1                   (0x1 << 11)
+#define RT5670_PLL1_SRC_BCLK2                   (0x2 << 11)
+#define RT5670_PLL1_SRC_BCLK3                   (0x3 << 11)
 #define RT5670_PLL1_PD_MASK                     (0x1 << 3)
 #define RT5670_PLL1_PD_SFT                      3
 #define RT5670_PLL1_PD_1                        (0x0 << 3)
diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c
index b4cd7e3bf5f8..69d987a9935c 100644
--- a/sound/soc/codecs/rt5677.c
+++ b/sound/soc/codecs/rt5677.c
@@ -1386,90 +1386,90 @@ static const struct snd_kcontrol_new rt5677_dac_r_mix[] = {
 };
 
 static const struct snd_kcontrol_new rt5677_sto1_dac_l_mix[] = {
-        SOC_DAPM_SINGLE("ST L Switch", RT5677_STO1_DAC_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("ST L Switch", RT5677_STO1_DAC_MIXER,
                         RT5677_M_ST_DAC1_L_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC1 L Switch", RT5677_STO1_DAC_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC1 L Switch", RT5677_STO1_DAC_MIXER,
                         RT5677_M_DAC1_L_STO_L_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC2 L Switch", RT5677_STO1_DAC_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC2 L Switch", RT5677_STO1_DAC_MIXER,
                         RT5677_M_DAC2_L_STO_L_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC1 R Switch", RT5677_STO1_DAC_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC1 R Switch", RT5677_STO1_DAC_MIXER,
                         RT5677_M_DAC1_R_STO_L_SFT, 1, 1),
 };
 
 static const struct snd_kcontrol_new rt5677_sto1_dac_r_mix[] = {
-        SOC_DAPM_SINGLE("ST R Switch", RT5677_STO1_DAC_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("ST R Switch", RT5677_STO1_DAC_MIXER,
                         RT5677_M_ST_DAC1_R_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC1 R Switch", RT5677_STO1_DAC_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC1 R Switch", RT5677_STO1_DAC_MIXER,
                         RT5677_M_DAC1_R_STO_R_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC2 R Switch", RT5677_STO1_DAC_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC2 R Switch", RT5677_STO1_DAC_MIXER,
                         RT5677_M_DAC2_R_STO_R_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC1 L Switch", RT5677_STO1_DAC_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC1 L Switch", RT5677_STO1_DAC_MIXER,
                         RT5677_M_DAC1_L_STO_R_SFT, 1, 1),
 };
 
 static const struct snd_kcontrol_new rt5677_mono_dac_l_mix[] = {
-        SOC_DAPM_SINGLE("ST L Switch", RT5677_MONO_DAC_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("ST L Switch", RT5677_MONO_DAC_MIXER,
                         RT5677_M_ST_DAC2_L_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC1 L Switch", RT5677_MONO_DAC_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC1 L Switch", RT5677_MONO_DAC_MIXER,
                         RT5677_M_DAC1_L_MONO_L_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC2 L Switch", RT5677_MONO_DAC_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC2 L Switch", RT5677_MONO_DAC_MIXER,
                         RT5677_M_DAC2_L_MONO_L_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC2 R Switch", RT5677_MONO_DAC_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC2 R Switch", RT5677_MONO_DAC_MIXER,
                         RT5677_M_DAC2_R_MONO_L_SFT, 1, 1),
 };
 
 static const struct snd_kcontrol_new rt5677_mono_dac_r_mix[] = {
-        SOC_DAPM_SINGLE("ST R Switch", RT5677_MONO_DAC_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("ST R Switch", RT5677_MONO_DAC_MIXER,
                         RT5677_M_ST_DAC2_R_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC1 R Switch", RT5677_MONO_DAC_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC1 R Switch", RT5677_MONO_DAC_MIXER,
                         RT5677_M_DAC1_R_MONO_R_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC2 R Switch", RT5677_MONO_DAC_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC2 R Switch", RT5677_MONO_DAC_MIXER,
                         RT5677_M_DAC2_R_MONO_R_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC2 L Switch", RT5677_MONO_DAC_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC2 L Switch", RT5677_MONO_DAC_MIXER,
                         RT5677_M_DAC2_L_MONO_R_SFT, 1, 1),
 };
 
 static const struct snd_kcontrol_new rt5677_dd1_l_mix[] = {
-        SOC_DAPM_SINGLE("Sto DAC Mix L Switch", RT5677_DD1_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("Sto DAC Mix L Switch", RT5677_DD1_MIXER,
                         RT5677_M_STO_L_DD1_L_SFT, 1, 1),
-        SOC_DAPM_SINGLE("Mono DAC Mix L Switch", RT5677_DD1_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("Mono DAC Mix L Switch", RT5677_DD1_MIXER,
                         RT5677_M_MONO_L_DD1_L_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC3 L Switch", RT5677_DD1_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC3 L Switch", RT5677_DD1_MIXER,
                         RT5677_M_DAC3_L_DD1_L_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC3 R Switch", RT5677_DD1_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC3 R Switch", RT5677_DD1_MIXER,
                         RT5677_M_DAC3_R_DD1_L_SFT, 1, 1),
 };
 
 static const struct snd_kcontrol_new rt5677_dd1_r_mix[] = {
-        SOC_DAPM_SINGLE("Sto DAC Mix R Switch", RT5677_DD1_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("Sto DAC Mix R Switch", RT5677_DD1_MIXER,
                         RT5677_M_STO_R_DD1_R_SFT, 1, 1),
-        SOC_DAPM_SINGLE("Mono DAC Mix R Switch", RT5677_DD1_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("Mono DAC Mix R Switch", RT5677_DD1_MIXER,
                         RT5677_M_MONO_R_DD1_R_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC3 R Switch", RT5677_DD1_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC3 R Switch", RT5677_DD1_MIXER,
                         RT5677_M_DAC3_R_DD1_R_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC3 L Switch", RT5677_DD1_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC3 L Switch", RT5677_DD1_MIXER,
                         RT5677_M_DAC3_L_DD1_R_SFT, 1, 1),
 };
 
 static const struct snd_kcontrol_new rt5677_dd2_l_mix[] = {
-        SOC_DAPM_SINGLE("Sto DAC Mix L Switch", RT5677_DD2_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("Sto DAC Mix L Switch", RT5677_DD2_MIXER,
                         RT5677_M_STO_L_DD2_L_SFT, 1, 1),
-        SOC_DAPM_SINGLE("Mono DAC Mix L Switch", RT5677_DD2_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("Mono DAC Mix L Switch", RT5677_DD2_MIXER,
                         RT5677_M_MONO_L_DD2_L_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC4 L Switch", RT5677_DD2_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC4 L Switch", RT5677_DD2_MIXER,
                         RT5677_M_DAC4_L_DD2_L_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC4 R Switch", RT5677_DD2_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC4 R Switch", RT5677_DD2_MIXER,
                         RT5677_M_DAC4_R_DD2_L_SFT, 1, 1),
 };
 
 static const struct snd_kcontrol_new rt5677_dd2_r_mix[] = {
-        SOC_DAPM_SINGLE("Sto DAC Mix R Switch", RT5677_DD2_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("Sto DAC Mix R Switch", RT5677_DD2_MIXER,
                         RT5677_M_STO_R_DD2_R_SFT, 1, 1),
-        SOC_DAPM_SINGLE("Mono DAC Mix R Switch", RT5677_DD2_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("Mono DAC Mix R Switch", RT5677_DD2_MIXER,
                         RT5677_M_MONO_R_DD2_R_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC4 R Switch", RT5677_DD2_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC4 R Switch", RT5677_DD2_MIXER,
                         RT5677_M_DAC4_R_DD2_R_SFT, 1, 1),
-        SOC_DAPM_SINGLE("DAC4 L Switch", RT5677_DD2_MIXER,
+        SOC_DAPM_SINGLE_AUTODISABLE("DAC4 L Switch", RT5677_DD2_MIXER,
                         RT5677_M_DAC4_L_DD2_R_SFT, 1, 1),
 };
 
@@ -2596,6 +2596,21 @@ static int rt5677_vref_event(struct snd_soc_dapm_widget *w,
         return 0;
 }
 
+static int rt5677_filter_power_event(struct snd_soc_dapm_widget *w,
+        struct snd_kcontrol *kcontrol, int event)
+{
+        switch (event) {
+        case SND_SOC_DAPM_POST_PMU:
+                msleep(50);
+                break;
+
+        default:
+                return 0;
+        }
+
+        return 0;
+}
+
 static const struct snd_soc_dapm_widget rt5677_dapm_widgets[] = {
         SND_SOC_DAPM_SUPPLY("PLL1", RT5677_PWR_ANLG2, RT5677_PWR_PLL1_BIT,
                 0, rt5677_set_pll1_event, SND_SOC_DAPM_PRE_PMU |
@@ -3072,19 +3087,26 @@ static const struct snd_soc_dapm_widget rt5677_dapm_widgets[] = {
 
         /* DAC Mixer */
         SND_SOC_DAPM_SUPPLY("dac stereo1 filter", RT5677_PWR_DIG2,
-                RT5677_PWR_DAC_S1F_BIT, 0, NULL, 0),
+                RT5677_PWR_DAC_S1F_BIT, 0, rt5677_filter_power_event,
+                SND_SOC_DAPM_POST_PMU),
         SND_SOC_DAPM_SUPPLY("dac mono2 left filter", RT5677_PWR_DIG2,
-                RT5677_PWR_DAC_M2F_L_BIT, 0, NULL, 0),
+                RT5677_PWR_DAC_M2F_L_BIT, 0, rt5677_filter_power_event,
+                SND_SOC_DAPM_POST_PMU),
         SND_SOC_DAPM_SUPPLY("dac mono2 right filter", RT5677_PWR_DIG2,
-                RT5677_PWR_DAC_M2F_R_BIT, 0, NULL, 0),
+                RT5677_PWR_DAC_M2F_R_BIT, 0, rt5677_filter_power_event,
+                SND_SOC_DAPM_POST_PMU),
         SND_SOC_DAPM_SUPPLY("dac mono3 left filter", RT5677_PWR_DIG2,
-                RT5677_PWR_DAC_M3F_L_BIT, 0, NULL, 0),
+                RT5677_PWR_DAC_M3F_L_BIT, 0, rt5677_filter_power_event,
+                SND_SOC_DAPM_POST_PMU),
         SND_SOC_DAPM_SUPPLY("dac mono3 right filter", RT5677_PWR_DIG2,
-                RT5677_PWR_DAC_M3F_R_BIT, 0, NULL, 0),
+                RT5677_PWR_DAC_M3F_R_BIT, 0, rt5677_filter_power_event,
+                SND_SOC_DAPM_POST_PMU),
         SND_SOC_DAPM_SUPPLY("dac mono4 left filter", RT5677_PWR_DIG2,
-                RT5677_PWR_DAC_M4F_L_BIT, 0, NULL, 0),
+                RT5677_PWR_DAC_M4F_L_BIT, 0, rt5677_filter_power_event,
+                SND_SOC_DAPM_POST_PMU),
         SND_SOC_DAPM_SUPPLY("dac mono4 right filter", RT5677_PWR_DIG2,
-                RT5677_PWR_DAC_M4F_R_BIT, 0, NULL, 0),
+                RT5677_PWR_DAC_M4F_R_BIT, 0, rt5677_filter_power_event,
+                SND_SOC_DAPM_POST_PMU),
 
         SND_SOC_DAPM_MIXER("Stereo DAC MIXL", SND_SOC_NOPM, 0, 0,
                 rt5677_sto1_dac_l_mix, ARRAY_SIZE(rt5677_sto1_dac_l_mix)),
diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index 056375339ea3..5380798883b5 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -229,7 +229,7 @@ SOC_DOUBLE_R_TLV("Capture Volume", WM8960_LINVOL, WM8960_RINVOL,
 SOC_DOUBLE_R("Capture Volume ZC Switch", WM8960_LINVOL, WM8960_RINVOL,
         6, 1, 0),
 SOC_DOUBLE_R("Capture Switch", WM8960_LINVOL, WM8960_RINVOL,
-        7, 1, 0),
+        7, 1, 1),
 
 SOC_SINGLE_TLV("Right Input Boost Mixer RINPUT3 Volume",
                WM8960_INBMIX1, 4, 7, 0, lineinboost_tlv),
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index 39ebd7bf4f53..a7e79784fc16 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -365,8 +365,8 @@ static const struct reg_default wm8962_reg[] = {
         { 16924, 0x0059 },   /* R16924 - HDBASS_PG_1 */
         { 16925, 0x999A },   /* R16925 - HDBASS_PG_0 */
 
-        { 17048, 0x0083 },   /* R17408 - HPF_C_1 */
-        { 17049, 0x98AD },   /* R17409 - HPF_C_0 */
+        { 17408, 0x0083 },   /* R17408 - HPF_C_1 */
+        { 17409, 0x98AD },   /* R17409 - HPF_C_0 */
 
         { 17920, 0x007F },   /* R17920 - ADCL_RETUNE_C1_1 */
         { 17921, 0xFFFF },   /* R17921 - ADCL_RETUNE_C1_0 */
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index 4495a40a9468..c1c9c2e3525b 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -681,8 +681,8 @@ static int davinci_mcasp_set_tdm_slot(struct snd_soc_dai *dai,
         }
 
         mcasp->tdm_slots = slots;
-        mcasp->tdm_mask[SNDRV_PCM_STREAM_PLAYBACK] = rx_mask;
-        mcasp->tdm_mask[SNDRV_PCM_STREAM_CAPTURE] = tx_mask;
+        mcasp->tdm_mask[SNDRV_PCM_STREAM_PLAYBACK] = tx_mask;
+        mcasp->tdm_mask[SNDRV_PCM_STREAM_CAPTURE] = rx_mask;
         mcasp->slot_width = slot_width;
 
         return davinci_mcasp_set_ch_constraints(mcasp);
@@ -908,6 +908,14 @@ static int mcasp_i2s_hw_param(struct davinci_mcasp *mcasp, int stream,
                 mcasp_set_bits(mcasp, DAVINCI_MCASP_RXFMT_REG, busel | RXORD);
                 mcasp_mod_bits(mcasp, DAVINCI_MCASP_RXFMCTL_REG,
                                FSRMOD(total_slots), FSRMOD(0x1FF));
+                /*
+                 * If McASP is set to be TX/RX synchronous and the playback is
+                 * not running already we need to configure the TX slots in
+                 * order to have correct FSX on the bus
+                 */
+                if (mcasp_is_synchronous(mcasp) && !mcasp->channels)
+                        mcasp_mod_bits(mcasp, DAVINCI_MCASP_TXFMCTL_REG,
+                                       FSXMOD(total_slots), FSXMOD(0x1FF));
         }
 
         return 0;
diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig
index 19c302b0d763..14dfdee05fd5 100644
--- a/sound/soc/fsl/Kconfig
+++ b/sound/soc/fsl/Kconfig
@@ -283,6 +283,8 @@ config SND_SOC_IMX_MC13783
 config SND_SOC_FSL_ASOC_CARD
         tristate "Generic ASoC Sound Card with ASRC support"
         depends on OF && I2C
+        # enforce SND_SOC_FSL_ASOC_CARD=m if SND_AC97_CODEC=m:
+        depends on SND_AC97_CODEC || SND_AC97_CODEC=n
         select SND_SOC_IMX_AUDMUX
         select SND_SOC_IMX_PCM_DMA
         select SND_SOC_FSL_ESAI
diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c
index a4435f5e3be9..ffd5f9acc849 100644
--- a/sound/soc/fsl/fsl_sai.c
+++ b/sound/soc/fsl/fsl_sai.c
@@ -454,7 +454,8 @@ static int fsl_sai_trigger(struct snd_pcm_substream *substream, int cmd,
          * Rx sync with Tx clocks: Clear SYNC for Tx, set it for Rx.
          * Tx sync with Rx clocks: Clear SYNC for Rx, set it for Tx.
          */
-        regmap_update_bits(sai->regmap, FSL_SAI_TCR2, FSL_SAI_CR2_SYNC, 0);
+        regmap_update_bits(sai->regmap, FSL_SAI_TCR2, FSL_SAI_CR2_SYNC,
+                           sai->synchronous[TX] ? FSL_SAI_CR2_SYNC : 0);
         regmap_update_bits(sai->regmap, FSL_SAI_RCR2, FSL_SAI_CR2_SYNC,
                            sai->synchronous[RX] ? FSL_SAI_CR2_SYNC : 0);
 
diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig
index 7b778ab85f8b..d430ef5a4f38 100644
--- a/sound/soc/intel/Kconfig
+++ b/sound/soc/intel/Kconfig
@@ -144,7 +144,7 @@ config SND_SOC_INTEL_SKYLAKE
 
 config SND_SOC_INTEL_SKL_RT286_MACH
         tristate "ASoC Audio driver for SKL with RT286 I2S mode"
-        depends on X86 && ACPI
+        depends on X86 && ACPI && I2C
         select SND_SOC_INTEL_SST
         select SND_SOC_INTEL_SKYLAKE
         select SND_SOC_RT286
diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c
index a7854c8fc523..ffea427aeca8 100644
--- a/sound/soc/intel/skylake/skl-topology.c
+++ b/sound/soc/intel/skylake/skl-topology.c
@@ -1240,6 +1240,7 @@ int skl_tplg_init(struct snd_soc_platform *platform, struct hdac_ext_bus *ebus)
          */
         ret = snd_soc_tplg_component_load(&platform->component,
                                         &skl_tplg_ops, fw, 0);
+        release_firmware(fw);
         if (ret < 0) {
                 dev_err(bus->dev, "tplg component load failed%d\n", ret);
                 return -EINVAL;
diff --git a/sound/soc/rockchip/rockchip_spdif.c b/sound/soc/rockchip/rockchip_spdif.c
index a38a3029062c..ac72ff5055bb 100644
--- a/sound/soc/rockchip/rockchip_spdif.c
+++ b/sound/soc/rockchip/rockchip_spdif.c
@@ -280,7 +280,7 @@ static int rk_spdif_probe(struct platform_device *pdev)
         int ret;
 
         match = of_match_node(rk_spdif_match, np);
-        if ((int) match->data == RK_SPDIF_RK3288) {
+        if (match->data == (void *)RK_SPDIF_RK3288) {
                 struct regmap *grf;
 
                 grf = syscon_regmap_lookup_by_phandle(np, "rockchip,grf");
diff --git a/sound/soc/rockchip/rockchip_spdif.h b/sound/soc/rockchip/rockchip_spdif.h
index 07f86a21046a..921b4095fb92 100644
--- a/sound/soc/rockchip/rockchip_spdif.h
+++ b/sound/soc/rockchip/rockchip_spdif.h
@@ -28,9 +28,9 @@
 #define SPDIF_CFGR_VDW(x)       (x << SPDIF_CFGR_VDW_SHIFT)
 #define SDPIF_CFGR_VDW_MASK     (0xf << SPDIF_CFGR_VDW_SHIFT)
 
-#define SPDIF_CFGR_VDW_16       SPDIF_CFGR_VDW(0x00)
-#define SPDIF_CFGR_VDW_20       SPDIF_CFGR_VDW(0x01)
-#define SPDIF_CFGR_VDW_24       SPDIF_CFGR_VDW(0x10)
+#define SPDIF_CFGR_VDW_16       SPDIF_CFGR_VDW(0x0)
+#define SPDIF_CFGR_VDW_20       SPDIF_CFGR_VDW(0x1)
+#define SPDIF_CFGR_VDW_24       SPDIF_CFGR_VDW(0x2)
 
 /*
  * DMACR
diff --git a/sound/soc/sh/rcar/gen.c b/sound/soc/sh/rcar/gen.c
index 76da7620904c..edcf4cc2e84f 100644
--- a/sound/soc/sh/rcar/gen.c
+++ b/sound/soc/sh/rcar/gen.c
@@ -235,7 +235,7 @@ static int rsnd_gen2_probe(struct platform_device *pdev,
                 RSND_GEN_S_REG(SCU_SYS_STATUS0, 0x1c8),
                 RSND_GEN_S_REG(SCU_SYS_INT_EN0, 0x1cc),
                 RSND_GEN_S_REG(SCU_SYS_STATUS1, 0x1d0),
-                RSND_GEN_S_REG(SCU_SYS_INT_EN1, 0x1c4),
+                RSND_GEN_S_REG(SCU_SYS_INT_EN1, 0x1d4),
                 RSND_GEN_M_REG(SRC_SWRSR,       0x200,  0x40),
                 RSND_GEN_M_REG(SRC_SRCIR,       0x204,  0x40),
                 RSND_GEN_M_REG(SRC_ADINR,       0x214,  0x40),
diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c
index 261b50217c48..68b439ed22d7 100644
--- a/sound/soc/sh/rcar/src.c
+++ b/sound/soc/sh/rcar/src.c
@@ -923,6 +923,7 @@ static int rsnd_src_pcm_new_gen2(struct rsnd_mod *mod,
                             struct snd_soc_pcm_runtime *rtd)
 {
         struct rsnd_dai *rdai = rsnd_io_to_rdai(io);
+        struct rsnd_mod *dvc = rsnd_io_to_mod_dvc(io);
         struct rsnd_src *src = rsnd_mod_to_src(mod);
         int ret;
 
@@ -937,6 +938,12 @@ static int rsnd_src_pcm_new_gen2(struct rsnd_mod *mod,
                 return 0;
 
         /*
+         * SRC In doesn't work if DVC was enabled
+         */
+        if (dvc && !rsnd_io_is_play(io))
+                return 0;
+
+        /*
          * enable sync convert
          */
         ret = rsnd_kctrl_new_s(mod, io, rtd,
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 24b096066a07..a1305f827a98 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -795,12 +795,12 @@ static void soc_resume_deferred(struct work_struct *work)
 
         dev_dbg(card->dev, "ASoC: resume work completed\n");
 
-        /* userspace can access us now we are back as we were before */
-        snd_power_change_state(card->snd_card, SNDRV_CTL_POWER_D0);
-
         /* Recheck all endpoints too, their state is affected by suspend */
         dapm_mark_endpoints_dirty(card);
         snd_soc_dapm_sync(&card->dapm);
+
+        /* userspace can access us now we are back as we were before */
+        snd_power_change_state(card->snd_card, SNDRV_CTL_POWER_D0);
 }
 
 /* powers up audio subsystem after a suspend */
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 016eba10b1ec..7d009428934a 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -2293,6 +2293,12 @@ void snd_soc_dapm_free_widget(struct snd_soc_dapm_widget *w)
         kfree(w);
 }
 
+void snd_soc_dapm_reset_cache(struct snd_soc_dapm_context *dapm)
+{
+        dapm->path_sink_cache.widget = NULL;
+        dapm->path_source_cache.widget = NULL;
+}
+
 /* free all dapm widgets and resources */
 static void dapm_free_widgets(struct snd_soc_dapm_context *dapm)
 {
@@ -2303,6 +2309,7 @@ static void dapm_free_widgets(struct snd_soc_dapm_context *dapm)
                         continue;
                 snd_soc_dapm_free_widget(w);
         }
+        snd_soc_dapm_reset_cache(dapm);
 }
 
 static struct snd_soc_dapm_widget *dapm_find_widget(
diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c
index ecd38e52285a..2f67ba6d7a8f 100644
--- a/sound/soc/soc-ops.c
+++ b/sound/soc/soc-ops.c
@@ -404,7 +404,7 @@ EXPORT_SYMBOL_GPL(snd_soc_get_volsw_sx);
 /**
  * snd_soc_put_volsw_sx - double mixer set callback
  * @kcontrol: mixer control
- * @uinfo: control element information
+ * @ucontrol: control element information
  *
  * Callback to set the value of a double mixer control that spans 2 registers.
  *
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index 8d7ec80af51b..6963ba20991c 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -531,7 +531,7 @@ static int soc_tplg_kcontrol_bind_io(struct snd_soc_tplg_ctl_hdr *hdr,
                 /* TLV bytes controls need standard kcontrol info handler,
                  * TLV callback and extended put/get handlers.
                  */
-                k->info = snd_soc_bytes_info;
+                k->info = snd_soc_bytes_info_ext;
                 k->tlv.c = snd_soc_bytes_tlv_callback;
 
                 ext_ops = tplg->bytes_ext_ops;
@@ -1805,6 +1805,7 @@ void snd_soc_tplg_widget_remove_all(struct snd_soc_dapm_context *dapm,
                 snd_soc_tplg_widget_remove(w);
                 snd_soc_dapm_free_widget(w);
         }
+        snd_soc_dapm_reset_cache(dapm);
 }
 EXPORT_SYMBOL_GPL(snd_soc_tplg_widget_remove_all);
 
diff --git a/sound/soc/sti/uniperif_player.c b/sound/soc/sti/uniperif_player.c
index 843f037a317d..5c2bc53f0a9b 100644
--- a/sound/soc/sti/uniperif_player.c
+++ b/sound/soc/sti/uniperif_player.c
@@ -669,6 +669,7 @@ static int uni_player_startup(struct snd_pcm_substream *substream,
 {
         struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
         struct uniperif *player = priv->dai_data.uni;
+        player->substream = substream;
 
         player->clk_adj = 0;
 
@@ -950,6 +951,8 @@ static void uni_player_shutdown(struct snd_pcm_substream *substream,
         if (player->state != UNIPERIF_STATE_STOPPED)
                 /* Stop the player */
                 uni_player_stop(player);
+
+        player->substream = NULL;
 }
 
 static int uni_player_parse_dt_clk_glue(struct platform_device *pdev,
@@ -989,7 +992,7 @@ static int uni_player_parse_dt(struct platform_device *pdev,
         if (!info)
                 return -ENOMEM;
 
-        if (of_property_read_u32(pnode, "version", &player->ver) ||
+        if (of_property_read_u32(pnode, "st,version", &player->ver) ||
             player->ver == SND_ST_UNIPERIF_VERSION_UNKNOWN) {
                 dev_err(dev, "Unknown uniperipheral version ");
                 return -EINVAL;
@@ -998,13 +1001,13 @@ static int uni_player_parse_dt(struct platform_device *pdev,
         if (player->ver >= SND_ST_UNIPERIF_VERSION_UNI_PLR_TOP_1_0)
                 info->underflow_enabled = 1;
 
-        if (of_property_read_u32(pnode, "uniperiph-id", &info->id)) {
+        if (of_property_read_u32(pnode, "st,uniperiph-id", &info->id)) {
                 dev_err(dev, "uniperipheral id not defined");
                 return -EINVAL;
         }
 
         /* Read the device mode property */
-        if (of_property_read_string(pnode, "mode", &mode)) {
+        if (of_property_read_string(pnode, "st,mode", &mode)) {
                 dev_err(dev, "uniperipheral mode not defined");
                 return -EINVAL;
         }
diff --git a/sound/soc/sti/uniperif_reader.c b/sound/soc/sti/uniperif_reader.c
index f791239a3087..8a0eb2050169 100644
--- a/sound/soc/sti/uniperif_reader.c
+++ b/sound/soc/sti/uniperif_reader.c
@@ -316,7 +316,7 @@ static int uni_reader_parse_dt(struct platform_device *pdev,
         if (!info)
                 return -ENOMEM;
 
-        if (of_property_read_u32(node, "version", &reader->ver) ||
+        if (of_property_read_u32(node, "st,version", &reader->ver) ||
             reader->ver == SND_ST_UNIPERIF_VERSION_UNKNOWN) {
                 dev_err(&pdev->dev, "Unknown uniperipheral version ");
                 return -EINVAL;
@@ -346,7 +346,6 @@ int uni_reader_init(struct platform_device *pdev,
         reader->hw = &uni_reader_pcm_hw;
         reader->dai_ops = &uni_reader_dai_ops;
 
-        dev_err(reader->dev, "%s: enter\n", __func__);
         ret = uni_reader_parse_dt(pdev, reader);
         if (ret < 0) {
                 dev_err(reader->dev, "Failed to parse DeviceTree");
diff --git a/sound/soc/sunxi/sun4i-codec.c b/sound/soc/sunxi/sun4i-codec.c
index bcbf4da168b6..1bb896d78d09 100644
--- a/sound/soc/sunxi/sun4i-codec.c
+++ b/sound/soc/sunxi/sun4i-codec.c
@@ -2,6 +2,7 @@
  * Copyright 2014 Emilio López <emilio@elopez.com.ar>
  * Copyright 2014 Jon Smirl <jonsmirl@gmail.com>
  * Copyright 2015 Maxime Ripard <maxime.ripard@free-electrons.com>
+ * Copyright 2015 Adam Sampson <ats@offog.org>
  *
  * Based on the Allwinner SDK driver, released under the GPL.
  *
@@ -404,7 +405,7 @@ static const struct snd_kcontrol_new sun4i_codec_pa_mute =
 static DECLARE_TLV_DB_SCALE(sun4i_codec_pa_volume_scale, -6300, 100, 1);
 
 static const struct snd_kcontrol_new sun4i_codec_widgets[] = {
-        SOC_SINGLE_TLV("PA Volume", SUN4I_CODEC_DAC_ACTL,
+        SOC_SINGLE_TLV("Power Amplifier Volume", SUN4I_CODEC_DAC_ACTL,
                        SUN4I_CODEC_DAC_ACTL_PA_VOL, 0x3F, 0,
                        sun4i_codec_pa_volume_scale),
 };
@@ -452,12 +453,12 @@ static const struct snd_soc_dapm_widget sun4i_codec_dapm_widgets[] = {
         SND_SOC_DAPM_SUPPLY("Mixer Enable", SUN4I_CODEC_DAC_ACTL,
                             SUN4I_CODEC_DAC_ACTL_MIXEN, 0, NULL, 0),
 
-        /* Pre-Amplifier */
-        SND_SOC_DAPM_MIXER("Pre-Amplifier", SUN4I_CODEC_ADC_ACTL,
+        /* Power Amplifier */
+        SND_SOC_DAPM_MIXER("Power Amplifier", SUN4I_CODEC_ADC_ACTL,
                            SUN4I_CODEC_ADC_ACTL_PA_EN, 0,
                            sun4i_codec_pa_mixer_controls,
                            ARRAY_SIZE(sun4i_codec_pa_mixer_controls)),
-        SND_SOC_DAPM_SWITCH("Pre-Amplifier Mute", SND_SOC_NOPM, 0, 0,
+        SND_SOC_DAPM_SWITCH("Power Amplifier Mute", SND_SOC_NOPM, 0, 0,
                             &sun4i_codec_pa_mute),
 
         SND_SOC_DAPM_OUTPUT("HP Right"),
@@ -480,16 +481,16 @@ static const struct snd_soc_dapm_route sun4i_codec_dapm_routes[] = {
         { "Left Mixer", NULL, "Mixer Enable" },
         { "Left Mixer", "Left DAC Playback Switch", "Left DAC" },
 
-        /* Pre-Amplifier Mixer Routes */
-        { "Pre-Amplifier", "Mixer Playback Switch", "Left Mixer" },
-        { "Pre-Amplifier", "Mixer Playback Switch", "Right Mixer" },
-        { "Pre-Amplifier", "DAC Playback Switch", "Left DAC" },
-        { "Pre-Amplifier", "DAC Playback Switch", "Right DAC" },
+        /* Power Amplifier Routes */
+        { "Power Amplifier", "Mixer Playback Switch", "Left Mixer" },
+        { "Power Amplifier", "Mixer Playback Switch", "Right Mixer" },
+        { "Power Amplifier", "DAC Playback Switch", "Left DAC" },
+        { "Power Amplifier", "DAC Playback Switch", "Right DAC" },
 
-        /* PA -> HP path */
-        { "Pre-Amplifier Mute", "Switch", "Pre-Amplifier" },
-        { "HP Right", NULL, "Pre-Amplifier Mute" },
-        { "HP Left", NULL, "Pre-Amplifier Mute" },
+        /* Headphone Output Routes */
+        { "Power Amplifier Mute", "Switch", "Power Amplifier" },
+        { "HP Right", NULL, "Power Amplifier Mute" },
+        { "HP Left", NULL, "Power Amplifier Mute" },
 };
 
 static struct snd_soc_codec_driver sun4i_codec_codec = {
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index 7661616f3636..5b4c58c3e2c5 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -174,6 +174,8 @@ struct snd_usb_midi_in_endpoint {
                 u8 running_status_length;
         } ports[0x10];
         u8 seen_f5;
+        bool in_sysex;
+        u8 last_cin;
         u8 error_resubmit;
         int current_port;
 };
@@ -468,6 +470,39 @@ static void snd_usbmidi_maudio_broken_running_status_input(
 }
 
 /*
+ * QinHeng CH345 is buggy: every second packet inside a SysEx has not CIN 4
+ * but the previously seen CIN, but still with three data bytes.
+ */
+static void ch345_broken_sysex_input(struct snd_usb_midi_in_endpoint *ep,
+                                     uint8_t *buffer, int buffer_length)
+{
+        unsigned int i, cin, length;
+
+        for (i = 0; i + 3 < buffer_length; i += 4) {
+                if (buffer[i] == 0 && i > 0)
+                        break;
+                cin = buffer[i] & 0x0f;
+                if (ep->in_sysex &&
+                    cin == ep->last_cin &&
+                    (buffer[i + 1 + (cin == 0x6)] & 0x80) == 0)
+                        cin = 0x4;
+#if 0
+                if (buffer[i + 1] == 0x90) {
+                        /*
+                         * Either a corrupted running status or a real note-on
+                         * message; impossible to detect reliably.
+                         */
+                }
+#endif
+                length = snd_usbmidi_cin_length[cin];
+                snd_usbmidi_input_data(ep, 0, &buffer[i + 1], length);
+                ep->in_sysex = cin == 0x4;
+                if (!ep->in_sysex)
+                        ep->last_cin = cin;
+        }
+}
+
+/*
  * CME protocol: like the standard protocol, but SysEx commands are sent as a
  * single USB packet preceded by a 0x0F byte.
  */
@@ -660,6 +695,12 @@ static struct usb_protocol_ops snd_usbmidi_cme_ops = {
         .output_packet = snd_usbmidi_output_standard_packet,
 };
 
+static struct usb_protocol_ops snd_usbmidi_ch345_broken_sysex_ops = {
+        .input = ch345_broken_sysex_input,
+        .output = snd_usbmidi_standard_output,
+        .output_packet = snd_usbmidi_output_standard_packet,
+};
+
 /*
  * AKAI MPD16 protocol:
  *
@@ -1341,6 +1382,7 @@ static int snd_usbmidi_out_endpoint_create(struct snd_usb_midi *umidi,
                  * Various chips declare a packet size larger than 4 bytes, but
                  * do not actually work with larger packets:
                  */
+        case USB_ID(0x0a67, 0x5011): /* Medeli DD305 */
         case USB_ID(0x0a92, 0x1020): /* ESI M4U */
         case USB_ID(0x1430, 0x474b): /* RedOctane GH MIDI INTERFACE */
         case USB_ID(0x15ca, 0x0101): /* Textech USB Midi Cable */
@@ -2378,6 +2420,10 @@ int snd_usbmidi_create(struct snd_card *card,
 
                 err = snd_usbmidi_detect_per_port_endpoints(umidi, endpoints);
                 break;
+        case QUIRK_MIDI_CH345:
+                umidi->usb_protocol_ops = &snd_usbmidi_ch345_broken_sysex_ops;
+                err = snd_usbmidi_detect_per_port_endpoints(umidi, endpoints);
+                break;
         default:
                 dev_err(&umidi->dev->dev, "invalid quirk type %d\n",
                         quirk->type);
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index 1a1e2e4df35e..c60a776e815d 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -2829,6 +2829,17 @@ YAMAHA_DEVICE(0x7010, "UB99"),
         .idProduct = 0x1020,
 },
 
+/* QinHeng devices */
+{
+        USB_DEVICE(0x1a86, 0x752d),
+        .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+                .vendor_name = "QinHeng",
+                .product_name = "CH345",
+                .ifnum = 1,
+                .type = QUIRK_MIDI_CH345
+        }
+},
+
 /* KeithMcMillen Stringport */
 {
         USB_DEVICE(0x1f38, 0x0001),
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 5ca80e7d30cd..7016ad898187 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -538,6 +538,7 @@ int snd_usb_create_quirk(struct snd_usb_audio *chip,
                 [QUIRK_MIDI_CME] = create_any_midi_quirk,
                 [QUIRK_MIDI_AKAI] = create_any_midi_quirk,
                 [QUIRK_MIDI_FTDI] = create_any_midi_quirk,
+                [QUIRK_MIDI_CH345] = create_any_midi_quirk,
                 [QUIRK_AUDIO_STANDARD_INTERFACE] = create_standard_audio_quirk,
                 [QUIRK_AUDIO_FIXED_ENDPOINT] = create_fixed_stream_quirk,
                 [QUIRK_AUDIO_EDIROL_UAXX] = create_uaxx_quirk,
diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h
index 15a12715bd05..b665d85555cb 100644
--- a/sound/usb/usbaudio.h
+++ b/sound/usb/usbaudio.h
@@ -95,6 +95,7 @@ enum quirk_type {
         QUIRK_MIDI_AKAI,
         QUIRK_MIDI_US122L,
         QUIRK_MIDI_FTDI,
+        QUIRK_MIDI_CH345,
         QUIRK_AUDIO_STANDARD_INTERFACE,
         QUIRK_AUDIO_FIXED_ENDPOINT,
         QUIRK_AUDIO_EDIROL_UAXX,
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 40ab4476c80a..51cf8256c6cd 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -420,8 +420,7 @@ static struct nfit_test_resource *nfit_test_lookup(resource_size_t addr)
 
 static int nfit_test0_alloc(struct nfit_test *t)
 {
-        size_t nfit_size = sizeof(struct acpi_table_nfit)
-                        + sizeof(struct acpi_nfit_system_address) * NUM_SPA
+        size_t nfit_size = sizeof(struct acpi_nfit_system_address) * NUM_SPA
                         + sizeof(struct acpi_nfit_memory_map) * NUM_MEM
                         + sizeof(struct acpi_nfit_control_region) * NUM_DCR
                         + sizeof(struct acpi_nfit_data_region) * NUM_BDW
@@ -471,8 +470,7 @@ static int nfit_test0_alloc(struct nfit_test *t)
 
 static int nfit_test1_alloc(struct nfit_test *t)
 {
-        size_t nfit_size = sizeof(struct acpi_table_nfit)
-                + sizeof(struct acpi_nfit_system_address)
+        size_t nfit_size = sizeof(struct acpi_nfit_system_address)
                 + sizeof(struct acpi_nfit_memory_map)
                 + sizeof(struct acpi_nfit_control_region);
 
@@ -488,39 +486,24 @@ static int nfit_test1_alloc(struct nfit_test *t)
         return 0;
 }
 
-static void nfit_test_init_header(struct acpi_table_nfit *nfit, size_t size)
-{
-        memcpy(nfit->header.signature, ACPI_SIG_NFIT, 4);
-        nfit->header.length = size;
-        nfit->header.revision = 1;
-        memcpy(nfit->header.oem_id, "LIBND", 6);
-        memcpy(nfit->header.oem_table_id, "TEST", 5);
-        nfit->header.oem_revision = 1;
-        memcpy(nfit->header.asl_compiler_id, "TST", 4);
-        nfit->header.asl_compiler_revision = 1;
-}
-
 static void nfit_test0_setup(struct nfit_test *t)
 {
         struct nvdimm_bus_descriptor *nd_desc;
         struct acpi_nfit_desc *acpi_desc;
         struct acpi_nfit_memory_map *memdev;
         void *nfit_buf = t->nfit_buf;
-        size_t size = t->nfit_size;
         struct acpi_nfit_system_address *spa;
         struct acpi_nfit_control_region *dcr;
         struct acpi_nfit_data_region *bdw;
         struct acpi_nfit_flush_address *flush;
         unsigned int offset;
 
-        nfit_test_init_header(nfit_buf, size);
-
         /*
          * spa0 (interleave first half of dimm0 and dimm1, note storage
          * does not actually alias the related block-data-window
          * regions)
          */
-        spa = nfit_buf + sizeof(struct acpi_table_nfit);
+        spa = nfit_buf;
         spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
         spa->header.length = sizeof(*spa);
         memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16);
@@ -533,7 +516,7 @@ static void nfit_test0_setup(struct nfit_test *t)
          * does not actually alias the related block-data-window
          * regions)
          */
-        spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa);
+        spa = nfit_buf + sizeof(*spa);
         spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
         spa->header.length = sizeof(*spa);
         memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16);
@@ -542,7 +525,7 @@ static void nfit_test0_setup(struct nfit_test *t)
         spa->length = SPA1_SIZE;
 
         /* spa2 (dcr0) dimm0 */
-        spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 2;
+        spa = nfit_buf + sizeof(*spa) * 2;
         spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
         spa->header.length = sizeof(*spa);
         memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
@@ -551,7 +534,7 @@ static void nfit_test0_setup(struct nfit_test *t)
         spa->length = DCR_SIZE;
 
         /* spa3 (dcr1) dimm1 */
-        spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 3;
+        spa = nfit_buf + sizeof(*spa) * 3;
         spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
         spa->header.length = sizeof(*spa);
         memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
@@ -560,7 +543,7 @@ static void nfit_test0_setup(struct nfit_test *t)
         spa->length = DCR_SIZE;
 
         /* spa4 (dcr2) dimm2 */
-        spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 4;
+        spa = nfit_buf + sizeof(*spa) * 4;
         spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
         spa->header.length = sizeof(*spa);
         memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
@@ -569,7 +552,7 @@ static void nfit_test0_setup(struct nfit_test *t)
         spa->length = DCR_SIZE;
 
         /* spa5 (dcr3) dimm3 */
-        spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 5;
+        spa = nfit_buf + sizeof(*spa) * 5;
         spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
         spa->header.length = sizeof(*spa);
         memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
@@ -578,7 +561,7 @@ static void nfit_test0_setup(struct nfit_test *t)
         spa->length = DCR_SIZE;
 
         /* spa6 (bdw for dcr0) dimm0 */
-        spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 6;
+        spa = nfit_buf + sizeof(*spa) * 6;
         spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
         spa->header.length = sizeof(*spa);
         memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
@@ -587,7 +570,7 @@ static void nfit_test0_setup(struct nfit_test *t)
         spa->length = DIMM_SIZE;
 
         /* spa7 (bdw for dcr1) dimm1 */
-        spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 7;
+        spa = nfit_buf + sizeof(*spa) * 7;
         spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
         spa->header.length = sizeof(*spa);
         memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
@@ -596,7 +579,7 @@ static void nfit_test0_setup(struct nfit_test *t)
         spa->length = DIMM_SIZE;
 
         /* spa8 (bdw for dcr2) dimm2 */
-        spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 8;
+        spa = nfit_buf + sizeof(*spa) * 8;
         spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
         spa->header.length = sizeof(*spa);
         memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
@@ -605,7 +588,7 @@ static void nfit_test0_setup(struct nfit_test *t)
         spa->length = DIMM_SIZE;
 
         /* spa9 (bdw for dcr3) dimm3 */
-        spa = nfit_buf + sizeof(struct acpi_table_nfit) + sizeof(*spa) * 9;
+        spa = nfit_buf + sizeof(*spa) * 9;
         spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
         spa->header.length = sizeof(*spa);
         memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
@@ -613,7 +596,7 @@ static void nfit_test0_setup(struct nfit_test *t)
         spa->address = t->dimm_dma[3];
         spa->length = DIMM_SIZE;
 
-        offset = sizeof(struct acpi_table_nfit) + sizeof(*spa) * 10;
+        offset = sizeof(*spa) * 10;
         /* mem-region0 (spa0, dimm0) */
         memdev = nfit_buf + offset;
         memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
@@ -1100,15 +1083,13 @@ static void nfit_test0_setup(struct nfit_test *t)
 
 static void nfit_test1_setup(struct nfit_test *t)
 {
-        size_t size = t->nfit_size, offset;
+        size_t offset;
         void *nfit_buf = t->nfit_buf;
         struct acpi_nfit_memory_map *memdev;
         struct acpi_nfit_control_region *dcr;
         struct acpi_nfit_system_address *spa;
 
-        nfit_test_init_header(nfit_buf, size);
-
-        offset = sizeof(struct acpi_table_nfit);
+        offset = 0;
         /* spa0 (flat range with no bdw aliasing) */
         spa = nfit_buf + offset;
         spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
diff --git a/tools/testing/selftests/futex/README b/tools/testing/selftests/futex/README
index 3224a049b196..0558bb9ce0a6 100644
--- a/tools/testing/selftests/futex/README
+++ b/tools/testing/selftests/futex/README
@@ -27,7 +27,7 @@ o The build system shall remain as simple as possible, avoiding any archive or
 o Where possible, any helper functions or other package-wide code shall be
   implemented in header files, avoiding the need to compile intermediate object
   files.
-o External dependendencies shall remain as minimal as possible. Currently gcc
+o External dependencies shall remain as minimal as possible. Currently gcc
   and glibc are the only dependencies.
 o Tests return 0 for success and < 0 for failure.
 
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index e38cc54942db..882fe83a3554 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -492,6 +492,9 @@ TEST_SIGNAL(KILL_one_arg_six, SIGSYS)
         pid_t parent = getppid();
         int fd;
         void *map1, *map2;
+        int page_size = sysconf(_SC_PAGESIZE);
+
+        ASSERT_LT(0, page_size);
 
         ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
         ASSERT_EQ(0, ret);
@@ -504,16 +507,16 @@ TEST_SIGNAL(KILL_one_arg_six, SIGSYS)
 
         EXPECT_EQ(parent, syscall(__NR_getppid));
         map1 = (void *)syscall(sysno,
-                NULL, PAGE_SIZE, PROT_READ, MAP_PRIVATE, fd, PAGE_SIZE);
+                NULL, page_size, PROT_READ, MAP_PRIVATE, fd, page_size);
         EXPECT_NE(MAP_FAILED, map1);
         /* mmap2() should never return. */
         map2 = (void *)syscall(sysno,
-                 NULL, PAGE_SIZE, PROT_READ, MAP_PRIVATE, fd, 0x0C0FFEE);
+                 NULL, page_size, PROT_READ, MAP_PRIVATE, fd, 0x0C0FFEE);
         EXPECT_EQ(MAP_FAILED, map2);
 
         /* The test failed, so clean up the resources. */
-        munmap(map1, PAGE_SIZE);
-        munmap(map2, PAGE_SIZE);
+        munmap(map1, page_size);
+        munmap(map2, page_size);
         close(fd);
 }
 
diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h
index 0a3da64638ce..4db7d5691ba7 100644
--- a/tools/virtio/linux/kernel.h
+++ b/tools/virtio/linux/kernel.h
@@ -110,4 +110,10 @@ static inline void free_page(unsigned long addr)
         (void) (&_min1 == &_min2);              \
         _min1 < _min2 ? _min1 : _min2; })
 
+/* TODO: empty stubs for now. Broken but enough for virtio_ring.c */
+#define list_add_tail(a, b) do {} while (0)
+#define list_del(a) do {} while (0)
+#define list_for_each_entry(a, b, c) while (0)
+/* end of stubs */
+
 #endif /* KERNEL_H */
diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h
index a3e07016a440..ee125e714053 100644
--- a/tools/virtio/linux/virtio.h
+++ b/tools/virtio/linux/virtio.h
@@ -3,12 +3,6 @@
 #include <linux/scatterlist.h>
 #include <linux/kernel.h>
 
-/* TODO: empty stubs for now. Broken but enough for virtio_ring.c */
-#define list_add_tail(a, b) do {} while (0)
-#define list_del(a) do {} while (0)
-#define list_for_each_entry(a, b, c) while (0)
-/* end of stubs */
-
 struct virtio_device {
         void *dev;
         u64 features;
diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h
index 806d683ab107..57a6964a1e35 100644
--- a/tools/virtio/linux/virtio_config.h
+++ b/tools/virtio/linux/virtio_config.h
@@ -40,33 +40,39 @@ static inline void __virtio_clear_bit(struct virtio_device *vdev,
 #define virtio_has_feature(dev, feature) \
         (__virtio_test_bit((dev), feature))
 
+static inline bool virtio_is_little_endian(struct virtio_device *vdev)
+{
+        return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) ||
+                virtio_legacy_is_little_endian();
+}
+
+/* Memory accessors */
 static inline u16 virtio16_to_cpu(struct virtio_device *vdev, __virtio16 val)
 {
-        return __virtio16_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+        return __virtio16_to_cpu(virtio_is_little_endian(vdev), val);
 }
 
 static inline __virtio16 cpu_to_virtio16(struct virtio_device *vdev, u16 val)
 {
-        return __cpu_to_virtio16(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+        return __cpu_to_virtio16(virtio_is_little_endian(vdev), val);
 }
 
 static inline u32 virtio32_to_cpu(struct virtio_device *vdev, __virtio32 val)
 {
-        return __virtio32_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+        return __virtio32_to_cpu(virtio_is_little_endian(vdev), val);
 }
 
 static inline __virtio32 cpu_to_virtio32(struct virtio_device *vdev, u32 val)
 {
-        return __cpu_to_virtio32(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+        return __cpu_to_virtio32(virtio_is_little_endian(vdev), val);
 }
 
 static inline u64 virtio64_to_cpu(struct virtio_device *vdev, __virtio64 val)
 {
-        return __virtio64_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+        return __virtio64_to_cpu(virtio_is_little_endian(vdev), val);
 }
 
 static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
 {
-        return __cpu_to_virtio64(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+        return __cpu_to_virtio64(virtio_is_little_endian(vdev), val);
 }
-
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 21a0ab2d8919..69bca185c471 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -221,17 +221,23 @@ void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
         kvm_timer_update_state(vcpu);
 
         /*
-         * If we enter the guest with the virtual input level to the VGIC
-         * asserted, then we have already told the VGIC what we need to, and
-         * we don't need to exit from the guest until the guest deactivates
-         * the already injected interrupt, so therefore we should set the
-         * hardware active state to prevent unnecessary exits from the guest.
-         *
-         * Conversely, if the virtual input level is deasserted, then always
-         * clear the hardware active state to ensure that hardware interrupts
-         * from the timer triggers a guest exit.
-         */
-        if (timer->irq.level)
+        * If we enter the guest with the virtual input level to the VGIC
+        * asserted, then we have already told the VGIC what we need to, and
+        * we don't need to exit from the guest until the guest deactivates
+        * the already injected interrupt, so therefore we should set the
+        * hardware active state to prevent unnecessary exits from the guest.
+        *
+        * Also, if we enter the guest with the virtual timer interrupt active,
+        * then it must be active on the physical distributor, because we set
+        * the HW bit and the guest must be able to deactivate the virtual and
+        * physical interrupt at the same time.
+        *
+        * Conversely, if the virtual input level is deasserted and the virtual
+        * interrupt is not active, then always clear the hardware active state
+        * to ensure that hardware interrupts from the timer triggers a guest
+        * exit.
+        */
+        if (timer->irq.level || kvm_vgic_map_is_active(vcpu, timer->map))
                 phys_active = true;
         else
                 phys_active = false;
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 533538385d5d..65461f821a75 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -1096,6 +1096,27 @@ static void vgic_retire_lr(int lr_nr, struct kvm_vcpu *vcpu)
         vgic_set_lr(vcpu, lr_nr, vlr);
 }
 
+static bool dist_active_irq(struct kvm_vcpu *vcpu)
+{
+        struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+        return test_bit(vcpu->vcpu_id, dist->irq_active_on_cpu);
+}
+
+bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, struct irq_phys_map *map)
+{
+        int i;
+
+        for (i = 0; i < vcpu->arch.vgic_cpu.nr_lr; i++) {
+                struct vgic_lr vlr = vgic_get_lr(vcpu, i);
+
+                if (vlr.irq == map->virt_irq && vlr.state & LR_STATE_ACTIVE)
+                        return true;
+        }
+
+        return dist_active_irq(vcpu);
+}
+
 /*
  * An interrupt may have been disabled after being made pending on the
  * CPU interface (the classic case is a timer running while we're
@@ -1248,7 +1269,7 @@ static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
          * may have been serviced from another vcpu. In all cases,
          * move along.
          */
-        if (!kvm_vgic_vcpu_pending_irq(vcpu) && !kvm_vgic_vcpu_active_irq(vcpu))
+        if (!kvm_vgic_vcpu_pending_irq(vcpu) && !dist_active_irq(vcpu))
                 goto epilog;
 
         /* SGIs */
@@ -1396,25 +1417,13 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
 static bool vgic_sync_hwirq(struct kvm_vcpu *vcpu, int lr, struct vgic_lr vlr)
 {
         struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-        struct irq_phys_map *map;
-        bool phys_active;
         bool level_pending;
-        int ret;
 
         if (!(vlr.state & LR_HW))
                 return false;
 
-        map = vgic_irq_map_search(vcpu, vlr.irq);
-        BUG_ON(!map);
-
-        ret = irq_get_irqchip_state(map->irq,
-                                    IRQCHIP_STATE_ACTIVE,
-                                    &phys_active);
-
-        WARN_ON(ret);
-
-        if (phys_active)
-                return 0;
+        if (vlr.state & LR_STATE_ACTIVE)
+                return false;
 
         spin_lock(&dist->lock);
         level_pending = process_queued_irq(vcpu, lr, vlr);
@@ -1479,17 +1488,6 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
         return test_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
 }
 
-int kvm_vgic_vcpu_active_irq(struct kvm_vcpu *vcpu)
-{
-        struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
-        if (!irqchip_in_kernel(vcpu->kvm))
-                return 0;
-
-        return test_bit(vcpu->vcpu_id, dist->irq_active_on_cpu);
-}
-
-
 void vgic_kick_vcpus(struct kvm *kvm)
 {
         struct kvm_vcpu *vcpu;