kernel-alx/patches-4.9/0105-4.9.6-all-fixes.patch

diff --git a/Documentation/devicetree/bindings/clock/imx31-clock.txt b/Documentation/devicetree/bindings/clock/imx31-clock.txt
index 19df842c694f..8163d565f697 100644
--- a/Documentation/devicetree/bindings/clock/imx31-clock.txt
+++ b/Documentation/devicetree/bindings/clock/imx31-clock.txt
@@ -77,7 +77,7 @@ Examples:
 clks: ccm@53f80000{
 	compatible = "fsl,imx31-ccm";
 	reg = <0x53f80000 0x4000>;
-	interrupts = <0 31 0x04 0 53 0x04>;
+	interrupts = <31>, <53>;
 	#clock-cells = <1>;
 };
 
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 37babf91f2cb..922dec8fa07e 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3998,10 +3998,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			it if 0 is given (See Documentation/cgroup-v1/memory.txt)
 
 	swiotlb=	[ARM,IA-64,PPC,MIPS,X86]
-			Format: { <int> | force }
+			Format: { <int> | force | noforce }
 			<int> -- Number of I/O TLB slabs
 			force -- force using of bounce buffers even if they
 			         wouldn't be automatically used by the kernel
+			noforce -- Never use bounce buffers (for debugging)
 
 	switches=	[HW,M68k]
 
diff --git a/Makefile b/Makefile
index 2a8af8af7b27..ef95231d1625 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 9
-SUBLEVEL = 5
+SUBLEVEL = 6
 EXTRAVERSION =
 NAME = Roaring Lionus
 
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index bd204bfa29ed..249e10190d20 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -28,7 +28,7 @@ config ARC
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
 	select HAVE_MEMBLOCK
-	select HAVE_MOD_ARCH_SPECIFIC if ARC_DW2_UNWIND
+	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_OPROFILE
 	select HAVE_PERF_EVENTS
 	select HANDLE_DOMAIN_IRQ
diff --git a/arch/arc/include/asm/module.h b/arch/arc/include/asm/module.h
index 6e91d8b339c3..567590ea8f6c 100644
--- a/arch/arc/include/asm/module.h
+++ b/arch/arc/include/asm/module.h
@@ -14,13 +14,13 @@
 
 #include <asm-generic/module.h>
 
-#ifdef CONFIG_ARC_DW2_UNWIND
 struct mod_arch_specific {
+#ifdef CONFIG_ARC_DW2_UNWIND
 	void *unw_info;
 	int unw_sec_idx;
+#endif
 	const char *secstr;
 };
-#endif
 
 #define MODULE_PROC_FAMILY "ARC700"
 
diff --git a/arch/arc/kernel/module.c b/arch/arc/kernel/module.c
index 42e964db2967..3d99a6091332 100644
--- a/arch/arc/kernel/module.c
+++ b/arch/arc/kernel/module.c
@@ -32,8 +32,8 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
 #ifdef CONFIG_ARC_DW2_UNWIND
 	mod->arch.unw_sec_idx = 0;
 	mod->arch.unw_info = NULL;
-	mod->arch.secstr = secstr;
 #endif
+	mod->arch.secstr = secstr;
 	return 0;
 }
 
@@ -113,8 +113,10 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 
 	}
 
+#ifdef CONFIG_ARC_DW2_UNWIND
 	if (strcmp(module->arch.secstr+sechdrs[tgtsec].sh_name, ".eh_frame") == 0)
 		module->arch.unw_sec_idx = tgtsec;
+#endif
 
 	return 0;
 
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index c558ba75cbcc..7037201c5e3a 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -485,6 +485,7 @@ dtb-$(CONFIG_ARCH_OMAP3) += \
 	am3517-evm.dtb \
 	am3517_mt_ventoux.dtb \
 	logicpd-torpedo-37xx-devkit.dtb \
+	logicpd-som-lv-37xx-devkit.dtb \
 	omap3430-sdp.dtb \
 	omap3-beagle.dtb \
 	omap3-beagle-xm.dtb \
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 194d884c9de1..795c1467fa50 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -16,6 +16,7 @@
 	interrupt-parent = <&intc>;
 	#address-cells = <1>;
 	#size-cells = <1>;
+	chosen { };
 
 	aliases {
 		i2c0 = &i2c0;
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index a275fa956813..a20a71d9d22e 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -16,6 +16,7 @@
 	interrupt-parent = <&wakeupgen>;
 	#address-cells = <1>;
 	#size-cells = <1>;
+	chosen { };
 
 	memory@0 {
 		device_type = "memory";
diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi
index 46d46d894a44..74dd21b7373c 100644
--- a/arch/arm/boot/dts/bcm283x.dtsi
+++ b/arch/arm/boot/dts/bcm283x.dtsi
@@ -104,7 +104,7 @@
 			reg = <0x7e104000 0x10>;
 		};
 
-		mailbox: mailbox@7e00b800 {
+		mailbox: mailbox@7e00b880 {
 			compatible = "brcm,bcm2835-mbox";
 			reg = <0x7e00b880 0x40>;
 			interrupts = <0 1>;
diff --git a/arch/arm/boot/dts/da850-evm.dts b/arch/arm/boot/dts/da850-evm.dts
index 41de15fe15a2..78492a0bbbab 100644
--- a/arch/arm/boot/dts/da850-evm.dts
+++ b/arch/arm/boot/dts/da850-evm.dts
@@ -99,6 +99,7 @@
 				#size-cells = <1>;
 				compatible = "m25p64";
 				spi-max-frequency = <30000000>;
+				m25p,fast-read;
 				reg = <0>;
 				partition@0 {
 					label = "U-Boot-SPL";
diff --git a/arch/arm/boot/dts/dm814x.dtsi b/arch/arm/boot/dts/dm814x.dtsi
index ff90a6ce6bdc..d87efab24fa2 100644
--- a/arch/arm/boot/dts/dm814x.dtsi
+++ b/arch/arm/boot/dts/dm814x.dtsi
@@ -12,6 +12,7 @@
 	interrupt-parent = <&intc>;
 	#address-cells = <1>;
 	#size-cells = <1>;
+	chosen { };
 
 	aliases {
 		i2c0 = &i2c1;
diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi
index f1e0f771ff29..cbdfbc4e4a26 100644
--- a/arch/arm/boot/dts/dm816x.dtsi
+++ b/arch/arm/boot/dts/dm816x.dtsi
@@ -12,6 +12,7 @@
 	interrupt-parent = <&intc>;
 	#address-cells = <1>;
 	#size-cells = <1>;
+	chosen { };
 
 	aliases {
 		i2c0 = &i2c1;
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index d4fcd68f6349..064d84f87e45 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -18,6 +18,7 @@
 
 	compatible = "ti,dra7xx";
 	interrupt-parent = <&crossbar_mpu>;
+	chosen { };
 
 	aliases {
 		i2c0 = &i2c1;
@@ -1376,6 +1377,7 @@
 			phy-names = "sata-phy";
 			clocks = <&sata_ref_clk>;
 			ti,hwmods = "sata";
+			ports-implemented = <0x1>;
 		};
 
 		rtc: rtc@48838000 {
diff --git a/arch/arm/boot/dts/imx31.dtsi b/arch/arm/boot/dts/imx31.dtsi
index 1ce7ae94e7ad..11e9e6bd8abb 100644
--- a/arch/arm/boot/dts/imx31.dtsi
+++ b/arch/arm/boot/dts/imx31.dtsi
@@ -30,11 +30,11 @@
 		};
 	};
 
-	avic: avic-interrupt-controller@60000000 {
+	avic: interrupt-controller@68000000 {
 		compatible = "fsl,imx31-avic", "fsl,avic";
 		interrupt-controller;
 		#interrupt-cells = <1>;
-		reg = <0x60000000 0x100000>;
+		reg = <0x68000000 0x100000>;
 	};
 
 	soc {
@@ -118,13 +118,6 @@
 				interrupts = <19>;
 				clocks = <&clks 25>;
 			};
-
-			clks: ccm@53f80000{
-				compatible = "fsl,imx31-ccm";
-				reg = <0x53f80000 0x4000>;
-				interrupts = <0 31 0x04 0 53 0x04>;
-				#clock-cells = <1>;
-			};
 		};
 
 		aips@53f00000 { /* AIPS2 */
@@ -134,6 +127,13 @@
 			reg = <0x53f00000 0x100000>;
 			ranges;
 
+			clks: ccm@53f80000{
+				compatible = "fsl,imx31-ccm";
+				reg = <0x53f80000 0x4000>;
+				interrupts = <31>, <53>;
+				#clock-cells = <1>;
+			};
+
 			gpt: timer@53f90000 {
 				compatible = "fsl,imx31-gpt";
 				reg = <0x53f90000 0x4000>;
diff --git a/arch/arm/boot/dts/imx6q-cm-fx6.dts b/arch/arm/boot/dts/imx6q-cm-fx6.dts
index 59bc5a4dce17..a150bca84daa 100644
--- a/arch/arm/boot/dts/imx6q-cm-fx6.dts
+++ b/arch/arm/boot/dts/imx6q-cm-fx6.dts
@@ -183,7 +183,6 @@
 			MX6QDL_PAD_ENET_REF_CLK__ENET_TX_CLK	0x1b0b0
 			MX6QDL_PAD_ENET_MDIO__ENET_MDIO		0x1b0b0
 			MX6QDL_PAD_ENET_MDC__ENET_MDC		0x1b0b0
-			MX6QDL_PAD_GPIO_16__ENET_REF_CLK	0x4001b0a8
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
index b0b3220a1fd9..01166ba36f27 100644
--- a/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi
@@ -319,8 +319,6 @@
 		compatible = "fsl,imx6q-nitrogen6_max-sgtl5000",
 			     "fsl,imx-audio-sgtl5000";
 		model = "imx6q-nitrogen6_max-sgtl5000";
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_sgtl5000>;
 		ssi-controller = <&ssi1>;
 		audio-codec = <&codec>;
 		audio-routing =
@@ -402,6 +400,8 @@
 
 	codec: sgtl5000@0a {
 		compatible = "fsl,sgtl5000";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_sgtl5000>;
 		reg = <0x0a>;
 		clocks = <&clks IMX6QDL_CLK_CKO>;
 		VDDA-supply = <&reg_2p5v>;
diff --git a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts
index da8598402ab8..38faa90007d7 100644
--- a/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts
+++ b/arch/arm/boot/dts/logicpd-som-lv-37xx-devkit.dts
@@ -158,7 +158,7 @@
 &mmc1 {
 	interrupts-extended = <&intc 83 &omap3_pmx_core 0x11a>;
 	pinctrl-names = "default";
-	pinctrl-0 = <&mmc1_pins &mmc1_cd>;
+	pinctrl-0 = <&mmc1_pins>;
 	wp-gpios = <&gpio4 30 GPIO_ACTIVE_HIGH>;		/* gpio_126 */
 	cd-gpios = <&gpio4 14 IRQ_TYPE_LEVEL_LOW>;		/* gpio_110 */
 	vmmc-supply = <&vmmc1>;
@@ -193,7 +193,8 @@
 			OMAP3_CORE1_IOPAD(0x214a, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat1.sdmmc1_dat1 */
 			OMAP3_CORE1_IOPAD(0x214c, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat2.sdmmc1_dat2 */
 			OMAP3_CORE1_IOPAD(0x214e, PIN_INPUT | MUX_MODE0)	/* sdmmc1_dat3.sdmmc1_dat3 */
-			OMAP3_CORE1_IOPAD(0x2132, PIN_INPUT_PULLUP | MUX_MODE4)	/* cam_strobe.gpio_126 sdmmc1_wp*/
+			OMAP3_CORE1_IOPAD(0x2132, PIN_INPUT_PULLUP | MUX_MODE4)	/* cam_strobe.gpio_126 */
+			OMAP3_CORE1_IOPAD(0x212c, PIN_INPUT_PULLUP | MUX_MODE4)	/* cam_d11.gpio_110 */
 		>;
 	};
 
@@ -242,12 +243,6 @@
 			OMAP3_WKUP_IOPAD(0x2a16, PIN_OUTPUT | PIN_OFF_OUTPUT_LOW | MUX_MODE4)       /* sys_boot6.gpio_8 */
 		>;
 	};
-
-	mmc1_cd: pinmux_mmc1_cd {
-		pinctrl-single,pins = <
-			OMAP3_WKUP_IOPAD(0x212c, PIN_INPUT_PULLUP | MUX_MODE4)	/* cam_d11.gpio_110 */
-		>;
-	};
 };
 
 
diff --git a/arch/arm/boot/dts/omap2.dtsi b/arch/arm/boot/dts/omap2.dtsi
index 4f793a025a72..f1d6de8b3c19 100644
--- a/arch/arm/boot/dts/omap2.dtsi
+++ b/arch/arm/boot/dts/omap2.dtsi
@@ -17,6 +17,7 @@
 	interrupt-parent = <&intc>;
 	#address-cells = <1>;
 	#size-cells = <1>;
+	chosen { };
 
 	aliases {
 		serial0 = &uart1;
diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi
index 353d818ce5a6..2008648b8c9f 100644
--- a/arch/arm/boot/dts/omap3.dtsi
+++ b/arch/arm/boot/dts/omap3.dtsi
@@ -17,6 +17,7 @@
 	interrupt-parent = <&intc>;
 	#address-cells = <1>;
 	#size-cells = <1>;
+	chosen { };
 
 	aliases {
 		i2c0 = &i2c1;
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index 0ced079b7ae3..9c289ddab3df 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -15,6 +15,7 @@
 	interrupt-parent = <&wakeupgen>;
 	#address-cells = <1>;
 	#size-cells = <1>;
+	chosen { };
 
 	aliases {
 		i2c0 = &i2c1;
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index 25262118ec3d..1d1d8e90cd80 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -17,6 +17,7 @@
 
 	compatible = "ti,omap5";
 	interrupt-parent = <&wakeupgen>;
+	chosen { };
 
 	aliases {
 		i2c0 = &i2c1;
@@ -985,6 +986,7 @@
 			phy-names = "sata-phy";
 			clocks = <&sata_ref_clk>;
 			ti,hwmods = "sata";
+			ports-implemented = <0x1>;
 		};
 
 		dss: dss@58000000 {
diff --git a/arch/arm/boot/dts/r8a7794.dtsi b/arch/arm/boot/dts/r8a7794.dtsi
index 725ecb3c5fb4..7e860d3737ff 100644
--- a/arch/arm/boot/dts/r8a7794.dtsi
+++ b/arch/arm/boot/dts/r8a7794.dtsi
@@ -319,7 +319,7 @@
 				  "ch12";
 		clocks = <&mstp5_clks R8A7794_CLK_AUDIO_DMAC0>;
 		clock-names = "fck";
-		power-domains = <&cpg_clocks>;
+		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 		#dma-cells = <1>;
 		dma-channels = <13>;
 	};
@@ -1025,8 +1025,7 @@
 			clocks = <&extal_clk &usb_extal_clk>;
 			#clock-cells = <1>;
 			clock-output-names = "main", "pll0", "pll1", "pll3",
-					     "lb", "qspi", "sdh", "sd0", "z",
-					     "rcan";
+					     "lb", "qspi", "sdh", "sd0", "rcan";
 			#power-domain-cells = <0>;
 		};
 		/* Variable factor clocks */
@@ -1483,7 +1482,7 @@
 			      "mix.0", "mix.1",
 			      "dvc.0", "dvc.1",
 			      "clk_a", "clk_b", "clk_c", "clk_i";
-		power-domains = <&cpg_clocks>;
+		power-domains = <&sysc R8A7794_PD_ALWAYS_ON>;
 
 		status = "disabled";
 
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index 522b5feb4eaa..b62eaeb147aa 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -94,6 +94,9 @@
 #define ARM_CPU_XSCALE_ARCH_V2		0x4000
 #define ARM_CPU_XSCALE_ARCH_V3		0x6000
 
+/* Qualcomm implemented cores */
+#define ARM_CPU_PART_SCORPION		0x510002d0
+
 extern unsigned int processor_id;
 
 #ifdef CONFIG_CPU_CP15
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index b8df45883cf7..25538a935874 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -1066,6 +1066,22 @@ static int __init arch_hw_breakpoint_init(void)
 		return 0;
 	}
 
+	/*
+	 * Scorpion CPUs (at least those in APQ8060) seem to set DBGPRSR.SPD
+	 * whenever a WFI is issued, even if the core is not powered down, in
+	 * violation of the architecture.  When DBGPRSR.SPD is set, accesses to
+	 * breakpoint and watchpoint registers are treated as undefined, so
+	 * this results in boot time and runtime failures when these are
+	 * accessed and we unexpectedly take a trap.
+	 *
+	 * It's not clear if/how this can be worked around, so we blacklist
+	 * Scorpion CPUs to avoid these issues.
+	*/
+	if (read_cpuid_part() == ARM_CPU_PART_SCORPION) {
+		pr_info("Scorpion CPU detected. Hardware breakpoints and watchpoints disabled\n");
+		return 0;
+	}
+
 	has_ossr = core_has_os_save_restore();
 
 	/* Determine how many BRPs/WRPs are available. */
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index 22313cb53362..9af0701f7094 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -9,6 +9,7 @@
  */
 #include <linux/preempt.h>
 #include <linux/smp.h>
+#include <linux/uaccess.h>
 
 #include <asm/smp_plat.h>
 #include <asm/tlbflush.h>
@@ -40,8 +41,11 @@ static inline void ipi_flush_tlb_mm(void *arg)
 static inline void ipi_flush_tlb_page(void *arg)
 {
 	struct tlb_args *ta = (struct tlb_args *)arg;
+	unsigned int __ua_flags = uaccess_save_and_enable();
 
 	local_flush_tlb_page(ta->ta_vma, ta->ta_start);
+
+	uaccess_restore(__ua_flags);
 }
 
 static inline void ipi_flush_tlb_kernel_page(void *arg)
@@ -54,8 +58,11 @@ static inline void ipi_flush_tlb_kernel_page(void *arg)
 static inline void ipi_flush_tlb_range(void *arg)
 {
 	struct tlb_args *ta = (struct tlb_args *)arg;
+	unsigned int __ua_flags = uaccess_save_and_enable();
 
 	local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end);
+
+	uaccess_restore(__ua_flags);
 }
 
 static inline void ipi_flush_tlb_kernel_range(void *arg)
diff --git a/arch/arm/mach-ux500/pm.c b/arch/arm/mach-ux500/pm.c
index 8538910db202..a970e7fcba9e 100644
--- a/arch/arm/mach-ux500/pm.c
+++ b/arch/arm/mach-ux500/pm.c
@@ -134,8 +134,8 @@ bool prcmu_pending_irq(void)
  */
 bool prcmu_is_cpu_in_wfi(int cpu)
 {
-	return readl(PRCM_ARM_WFI_STANDBY) & cpu ? PRCM_ARM_WFI_STANDBY_WFI1 :
-		     PRCM_ARM_WFI_STANDBY_WFI0;
+	return readl(PRCM_ARM_WFI_STANDBY) &
+		(cpu ? PRCM_ARM_WFI_STANDBY_WFI1 : PRCM_ARM_WFI_STANDBY_WFI0);
 }
 
 /*
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index b71086d25195..53211a0acf0f 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -217,7 +217,7 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define _virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 #else
 #define __virt_to_pgoff(kaddr)	(((u64)(kaddr) & ~PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page))
-#define __page_to_voff(page)	(((u64)(page) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
+#define __page_to_voff(kaddr)	(((u64)(kaddr) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
 
 #define page_to_virt(page)	((void *)((__page_to_voff(page)) | PAGE_OFFSET))
 #define virt_to_page(vaddr)	((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START))
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index b5c3933ed441..d1ff83dfe5de 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -77,6 +77,7 @@ struct user_fpsimd_state {
 	__uint128_t	vregs[32];
 	__u32		fpsr;
 	__u32		fpcr;
+	__u32		__reserved[2];
 };
 
 struct user_hwdebug_state {
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 223d54a4d66b..79b0fe24d5b7 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -624,7 +624,7 @@ el0_inv:
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
 	mov	x2, x25
-	bl	bad_mode
+	bl	bad_el0_sync
 	b	ret_to_user
 ENDPROC(el0_sync)
 
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index e0c81da60f76..8eedeef375d6 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -550,6 +550,8 @@ static int hw_break_set(struct task_struct *target,
 	/* (address, ctrl) registers */
 	limit = regset->n * regset->size;
 	while (count && offset < limit) {
+		if (count < PTRACE_HBP_ADDR_SZ)
+			return -EINVAL;
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &addr,
 					 offset, offset + PTRACE_HBP_ADDR_SZ);
 		if (ret)
@@ -559,6 +561,8 @@ static int hw_break_set(struct task_struct *target,
 			return ret;
 		offset += PTRACE_HBP_ADDR_SZ;
 
+		if (!count)
+			break;
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl,
 					 offset, offset + PTRACE_HBP_CTRL_SZ);
 		if (ret)
@@ -595,7 +599,7 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct user_pt_regs newregs;
+	struct user_pt_regs newregs = task_pt_regs(target)->user_regs;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newregs, 0, -1);
 	if (ret)
@@ -625,7 +629,8 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct user_fpsimd_state newstate;
+	struct user_fpsimd_state newstate =
+		target->thread.fpsimd_state.user_fpsimd;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, 0, -1);
 	if (ret)
@@ -649,7 +654,7 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	unsigned long tls;
+	unsigned long tls = target->thread.tp_value;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
 	if (ret)
@@ -675,7 +680,8 @@ static int system_call_set(struct task_struct *target,
 			   unsigned int pos, unsigned int count,
 			   const void *kbuf, const void __user *ubuf)
 {
-	int syscallno, ret;
+	int syscallno = task_pt_regs(target)->syscallno;
+	int ret;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &syscallno, 0, -1);
 	if (ret)
@@ -947,7 +953,7 @@ static int compat_tls_set(struct task_struct *target,
 			  const void __user *ubuf)
 {
 	int ret;
-	compat_ulong_t tls;
+	compat_ulong_t tls = target->thread.tp_value;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
 	if (ret)
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index c9986b3e0a96..11e5eae088ab 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -596,17 +596,34 @@ const char *esr_get_class_string(u32 esr)
 }
 
 /*
- * bad_mode handles the impossible case in the exception vector.
+ * bad_mode handles the impossible case in the exception vector. This is always
+ * fatal.
  */
 asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 {
-	siginfo_t info;
-	void __user *pc = (void __user *)instruction_pointer(regs);
 	console_verbose();
 
 	pr_crit("Bad mode in %s handler detected on CPU%d, code 0x%08x -- %s\n",
 		handler[reason], smp_processor_id(), esr,
 		esr_get_class_string(esr));
+
+	die("Oops - bad mode", regs, 0);
+	local_irq_disable();
+	panic("bad mode");
+}
+
+/*
+ * bad_el0_sync handles unexpected, but potentially recoverable synchronous
+ * exceptions taken from EL0. Unlike bad_mode, this returns.
+ */
+asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
+{
+	siginfo_t info;
+	void __user *pc = (void __user *)instruction_pointer(regs);
+	console_verbose();
+
+	pr_crit("Bad EL0 synchronous exception detected on CPU%d, code 0x%08x -- %s\n",
+		smp_processor_id(), esr, esr_get_class_string(esr));
 	__show_regs(regs);
 
 	info.si_signo = SIGILL;
@@ -614,7 +631,10 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 	info.si_code  = ILL_ILLOPC;
 	info.si_addr  = pc;
 
-	arm64_notify_die("Oops - bad mode", regs, &info, 0);
+	current->thread.fault_address = 0;
+	current->thread.fault_code = 0;
+
+	force_sig_info(info.si_signo, &info, current);
 }
 
 void __pte_error(const char *file, int line, unsigned long val)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 3f74d0d98de6..02265a589ef5 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -524,7 +524,8 @@ EXPORT_SYMBOL(dummy_dma_ops);
 
 static int __init arm64_dma_init(void)
 {
-	if (swiotlb_force || max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+	if (swiotlb_force == SWIOTLB_FORCE ||
+	    max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
 		swiotlb = 1;
 
 	return atomic_pool_init();
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 212c4d1e2f26..380ebe705093 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -401,8 +401,11 @@ static void __init free_unused_memmap(void)
  */
 void __init mem_init(void)
 {
-	if (swiotlb_force || max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+	if (swiotlb_force == SWIOTLB_FORCE ||
+	    max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
 		swiotlb_init(1);
+	else
+		swiotlb_force = SWIOTLB_NO_FORCE;
 
 	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
 
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index c56ea8c84abb..c4ced1d01d57 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -157,7 +157,7 @@
 #define PPC_INST_MCRXR			0x7c000400
 #define PPC_INST_MCRXR_MASK		0xfc0007fe
 #define PPC_INST_MFSPR_PVR		0x7c1f42a6
-#define PPC_INST_MFSPR_PVR_MASK		0xfc1fffff
+#define PPC_INST_MFSPR_PVR_MASK		0xfc1ffffe
 #define PPC_INST_MFTMR			0x7c0002dc
 #define PPC_INST_MSGSND			0x7c00019c
 #define PPC_INST_MSGCLR			0x7c0001dc
@@ -174,13 +174,13 @@
 #define PPC_INST_RFDI			0x4c00004e
 #define PPC_INST_RFMCI			0x4c00004c
 #define PPC_INST_MFSPR_DSCR		0x7c1102a6
-#define PPC_INST_MFSPR_DSCR_MASK	0xfc1fffff
+#define PPC_INST_MFSPR_DSCR_MASK	0xfc1ffffe
 #define PPC_INST_MTSPR_DSCR		0x7c1103a6
-#define PPC_INST_MTSPR_DSCR_MASK	0xfc1fffff
+#define PPC_INST_MTSPR_DSCR_MASK	0xfc1ffffe
 #define PPC_INST_MFSPR_DSCR_USER	0x7c0302a6
-#define PPC_INST_MFSPR_DSCR_USER_MASK	0xfc1fffff
+#define PPC_INST_MFSPR_DSCR_USER_MASK	0xfc1ffffe
 #define PPC_INST_MTSPR_DSCR_USER	0x7c0303a6
-#define PPC_INST_MTSPR_DSCR_USER_MASK	0xfc1fffff
+#define PPC_INST_MTSPR_DSCR_USER_MASK	0xfc1ffffe
 #define PPC_INST_MFVSRD			0x7c000066
 #define PPC_INST_MTVSRD			0x7c000166
 #define PPC_INST_SLBFEE			0x7c0007a7
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index b1ec62f2cc31..5c8f12fe9721 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -463,6 +463,10 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 
 	flush_fp_to_thread(target);
 
+	for (i = 0; i < 32 ; i++)
+		buf[i] = target->thread.TS_FPR(i);
+	buf[32] = target->thread.fp_state.fpscr;
+
 	/* copy to local buffer then write that out */
 	i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
 	if (i)
@@ -672,6 +676,9 @@ static int vsr_set(struct task_struct *target, const struct user_regset *regset,
 	flush_altivec_to_thread(target);
 	flush_vsx_to_thread(target);
 
+	for (i = 0; i < 32 ; i++)
+		buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
+
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 buf, 0, 32 * sizeof(double));
 	if (!ret)
@@ -1019,6 +1026,10 @@ static int tm_cfpr_set(struct task_struct *target,
 	flush_fp_to_thread(target);
 	flush_altivec_to_thread(target);
 
+	for (i = 0; i < 32; i++)
+		buf[i] = target->thread.TS_CKFPR(i);
+	buf[32] = target->thread.ckfp_state.fpscr;
+
 	/* copy to local buffer then write that out */
 	i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
 	if (i)
@@ -1283,6 +1294,9 @@ static int tm_cvsx_set(struct task_struct *target,
 	flush_altivec_to_thread(target);
 	flush_vsx_to_thread(target);
 
+	for (i = 0; i < 32 ; i++)
+		buf[i] = target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
+
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 buf, 0, 32 * sizeof(double));
 	if (!ret)
diff --git a/arch/powerpc/perf/power9-events-list.h b/arch/powerpc/perf/power9-events-list.h
index 6447dc1c3d89..929b56d47ad9 100644
--- a/arch/powerpc/perf/power9-events-list.h
+++ b/arch/powerpc/perf/power9-events-list.h
@@ -16,7 +16,7 @@ EVENT(PM_CYC,					0x0001e)
 EVENT(PM_ICT_NOSLOT_CYC,			0x100f8)
 EVENT(PM_CMPLU_STALL,				0x1e054)
 EVENT(PM_INST_CMPL,				0x00002)
-EVENT(PM_BRU_CMPL,				0x40060)
+EVENT(PM_BRU_CMPL,				0x10012)
 EVENT(PM_BR_MPRED_CMPL,				0x400f6)
 
 /* All L1 D cache load references counted at finish, gated by reject */
diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
index d38e86fd5720..60c57657c772 100644
--- a/arch/powerpc/sysdev/xics/icp-opal.c
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -20,6 +20,7 @@
 #include <asm/xics.h>
 #include <asm/io.h>
 #include <asm/opal.h>
+#include <asm/kvm_ppc.h>
 
 static void icp_opal_teardown_cpu(void)
 {
@@ -39,7 +40,26 @@ static void icp_opal_flush_ipi(void)
 	 * Should we be flagging idle loop instead?
 	 * Or creating some task to be scheduled?
 	 */
-	opal_int_eoi((0x00 << 24) | XICS_IPI);
+	if (opal_int_eoi((0x00 << 24) | XICS_IPI) > 0)
+		force_external_irq_replay();
+}
+
+static unsigned int icp_opal_get_xirr(void)
+{
+	unsigned int kvm_xirr;
+	__be32 hw_xirr;
+	int64_t rc;
+
+	/* Handle an interrupt latched by KVM first */
+	kvm_xirr = kvmppc_get_xics_latch();
+	if (kvm_xirr)
+		return kvm_xirr;
+
+	/* Then ask OPAL */
+	rc = opal_int_get_xirr(&hw_xirr, false);
+	if (rc < 0)
+		return 0;
+	return be32_to_cpu(hw_xirr);
 }
 
 static unsigned int icp_opal_get_irq(void)
@@ -47,12 +67,8 @@ static unsigned int icp_opal_get_irq(void)
 	unsigned int xirr;
 	unsigned int vec;
 	unsigned int irq;
-	int64_t rc;
 
-	rc = opal_int_get_xirr(&xirr, false);
-	if (rc < 0)
-		return 0;
-	xirr = be32_to_cpu(xirr);
+	xirr = icp_opal_get_xirr();
 	vec = xirr & 0x00ffffff;
 	if (vec == XICS_IRQ_SPURIOUS)
 		return 0;
@@ -67,7 +83,8 @@ static unsigned int icp_opal_get_irq(void)
 	xics_mask_unknown_vec(vec);
 
 	/* We might learn about it later, so EOI it */
-	opal_int_eoi(xirr);
+	if (opal_int_eoi(xirr) > 0)
+		force_external_irq_replay();
 
 	return 0;
 }
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 9c7a1ecfe6bd..47a1de77b18d 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -916,7 +916,7 @@ static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr)
 	memcpy(&mach->fac_mask, kvm->arch.model.fac_mask,
 	       S390_ARCH_FAC_LIST_SIZE_BYTE);
 	memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list,
-	       S390_ARCH_FAC_LIST_SIZE_BYTE);
+	       sizeof(S390_lowcore.stfle_fac_list));
 	if (copy_to_user((void __user *)attr->addr, mach, sizeof(*mach)))
 		ret = -EFAULT;
 	kfree(mach);
@@ -1437,7 +1437,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	/* Populate the facility mask initially. */
 	memcpy(kvm->arch.model.fac_mask, S390_lowcore.stfle_fac_list,
-	       S390_ARCH_FAC_LIST_SIZE_BYTE);
+	       sizeof(S390_lowcore.stfle_fac_list));
 	for (i = 0; i < S390_ARCH_FAC_LIST_SIZE_U64; i++) {
 		if (i < kvm_s390_fac_list_mask_size())
 			kvm->arch.model.fac_mask[i] &= kvm_s390_fac_list_mask[i];
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 48e6d84f173e..3d8ff40ecc6f 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1876,6 +1876,7 @@ static struct irq_chip ioapic_chip __read_mostly = {
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_eoi		= ioapic_ack_level,
 	.irq_set_affinity	= ioapic_set_affinity,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
@@ -1887,6 +1888,7 @@ static struct irq_chip ioapic_ir_chip __read_mostly = {
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_eoi		= ioapic_ir_ack_level,
 	.irq_set_affinity	= ioapic_set_affinity,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index b47edb8f5256..8da13d4e77cc 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -70,7 +70,7 @@ int __init pci_swiotlb_detect_override(void)
 {
 	int use_swiotlb = swiotlb | swiotlb_force;
 
-	if (swiotlb_force)
+	if (swiotlb_force == SWIOTLB_FORCE)
 		swiotlb = 1;
 
 	return use_swiotlb;
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 3cd69832d7f4..3961103e9176 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -114,6 +114,16 @@ static const struct dmi_system_id pci_crs_quirks[] __initconst = {
 			DMI_MATCH(DMI_BIOS_VERSION, "6JET85WW (1.43 )"),
 		},
 	},
+	/* https://bugzilla.kernel.org/show_bug.cgi?id=42606 */
+	{
+		.callback = set_nouse_crs,
+		.ident = "Supermicro X8DTH",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Supermicro"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X8DTH-i/6/iF/6F"),
+			DMI_MATCH(DMI_BIOS_VERSION, "2.0a"),
+		},
+	},
 
 	/* https://bugzilla.kernel.org/show_bug.cgi?id=15362 */
 	{
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index 0e98e5d241d0..5f8b4b0302b6 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -49,7 +49,7 @@ int __init pci_xen_swiotlb_detect(void)
 	 * activate this IOMMU. If running as PV privileged, activate it
 	 * irregardless.
 	 */
-	if ((xen_initial_domain() || swiotlb || swiotlb_force))
+	if (xen_initial_domain() || swiotlb || swiotlb_force == SWIOTLB_FORCE)
 		xen_swiotlb = 1;
 
 	/* If we are running under Xen, we MUST disable the native SWIOTLB.
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 8f3488b80896..7f6fed9f0703 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -495,6 +495,7 @@ static int exynos4_mct_dying_cpu(unsigned int cpu)
 	if (mct_int_type == MCT_INT_SPI) {
 		if (evt->irq != -1)
 			disable_irq_nosync(evt->irq);
+		exynos4_mct_write(0x1, mevt->base + MCT_L_INT_CSTAT_OFFSET);
 	} else {
 		disable_percpu_irq(mct_irqs[MCT_L0_IRQ]);
 	}
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index bf3ea7603a58..712592cef1a2 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -593,11 +593,16 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	list_add(&devfreq->node, &devfreq_list);
 
 	governor = find_devfreq_governor(devfreq->governor_name);
-	if (!IS_ERR(governor))
-		devfreq->governor = governor;
-	if (devfreq->governor)
-		err = devfreq->governor->event_handler(devfreq,
-					DEVFREQ_GOV_START, NULL);
+	if (IS_ERR(governor)) {
+		dev_err(dev, "%s: Unable to find governor for the device\n",
+			__func__);
+		err = PTR_ERR(governor);
+		goto err_init;
+	}
+
+	devfreq->governor = governor;
+	err = devfreq->governor->event_handler(devfreq, DEVFREQ_GOV_START,
+						NULL);
 	if (err) {
 		dev_err(dev, "%s: Unable to start governor for the device\n",
 			__func__);
diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c
index 29866f7e6d7e..1b21bb60e797 100644
--- a/drivers/devfreq/exynos-bus.c
+++ b/drivers/devfreq/exynos-bus.c
@@ -498,7 +498,7 @@ static int exynos_bus_probe(struct platform_device *pdev)
 	if (IS_ERR(bus->devfreq)) {
 		dev_err(dev,
 			"failed to add devfreq dev with passive governor\n");
-		ret = -EPROBE_DEFER;
+		ret = PTR_ERR(bus->devfreq);
 		goto err;
 	}
 
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 030fe05ed43b..9f3dbc8c63d2 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -448,6 +448,9 @@ struct dma_pl330_chan {
 
 	/* for cyclic capability */
 	bool cyclic;
+
+	/* for runtime pm tracking */
+	bool active;
 };
 
 struct pl330_dmac {
@@ -2031,6 +2034,7 @@ static void pl330_tasklet(unsigned long data)
 		_stop(pch->thread);
 		spin_unlock(&pch->thread->dmac->lock);
 		power_down = true;
+		pch->active = false;
 	} else {
 		/* Make sure the PL330 Channel thread is active */
 		spin_lock(&pch->thread->dmac->lock);
@@ -2050,6 +2054,7 @@ static void pl330_tasklet(unsigned long data)
 			desc->status = PREP;
 			list_move_tail(&desc->node, &pch->work_list);
 			if (power_down) {
+				pch->active = true;
 				spin_lock(&pch->thread->dmac->lock);
 				_start(pch->thread);
 				spin_unlock(&pch->thread->dmac->lock);
@@ -2164,6 +2169,7 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	unsigned long flags;
 	struct pl330_dmac *pl330 = pch->dmac;
 	LIST_HEAD(list);
+	bool power_down = false;
 
 	pm_runtime_get_sync(pl330->ddma.dev);
 	spin_lock_irqsave(&pch->lock, flags);
@@ -2174,6 +2180,8 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	pch->thread->req[0].desc = NULL;
 	pch->thread->req[1].desc = NULL;
 	pch->thread->req_running = -1;
+	power_down = pch->active;
+	pch->active = false;
 
 	/* Mark all desc done */
 	list_for_each_entry(desc, &pch->submitted_list, node) {
@@ -2191,6 +2199,8 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	list_splice_tail_init(&pch->completed_list, &pl330->desc_pool);
 	spin_unlock_irqrestore(&pch->lock, flags);
 	pm_runtime_mark_last_busy(pl330->ddma.dev);
+	if (power_down)
+		pm_runtime_put_autosuspend(pl330->ddma.dev);
 	pm_runtime_put_autosuspend(pl330->ddma.dev);
 
 	return 0;
@@ -2350,6 +2360,7 @@ static void pl330_issue_pending(struct dma_chan *chan)
 		 * updated on work_list emptiness status.
 		 */
 		WARN_ON(list_empty(&pch->submitted_list));
+		pch->active = true;
 		pm_runtime_get_sync(pch->dmac->ddma.dev);
 	}
 	list_splice_tail_init(&pch->submitted_list, &pch->work_list);
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 2e441d0ccd79..4c357d475465 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -986,6 +986,7 @@ static void rcar_dmac_free_chan_resources(struct dma_chan *chan)
 {
 	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
 	struct rcar_dmac *dmac = to_rcar_dmac(chan->device);
+	struct rcar_dmac_chan_map *map = &rchan->map;
 	struct rcar_dmac_desc_page *page, *_page;
 	struct rcar_dmac_desc *desc;
 	LIST_HEAD(list);
@@ -1019,6 +1020,13 @@ static void rcar_dmac_free_chan_resources(struct dma_chan *chan)
 		free_page((unsigned long)page);
 	}
 
+	/* Remove slave mapping if present. */
+	if (map->slave.xfer_size) {
+		dma_unmap_resource(chan->device->dev, map->addr,
+				   map->slave.xfer_size, map->dir, 0);
+		map->slave.xfer_size = 0;
+	}
+
 	pm_runtime_put(chan->device->dev);
 }
 
diff --git a/drivers/hid/hid-corsair.c b/drivers/hid/hid-corsair.c
index 717704e9ae07..c0303f61c26a 100644
--- a/drivers/hid/hid-corsair.c
+++ b/drivers/hid/hid-corsair.c
@@ -148,26 +148,36 @@ static enum led_brightness k90_backlight_get(struct led_classdev *led_cdev)
 	struct usb_interface *usbif = to_usb_interface(dev->parent);
 	struct usb_device *usbdev = interface_to_usbdev(usbif);
 	int brightness;
-	char data[8];
+	char *data;
+
+	data = kmalloc(8, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
 
 	ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0),
 			      K90_REQUEST_STATUS,
 			      USB_DIR_IN | USB_TYPE_VENDOR |
 			      USB_RECIP_DEVICE, 0, 0, data, 8,
 			      USB_CTRL_SET_TIMEOUT);
-	if (ret < 0) {
+	if (ret < 5) {
 		dev_warn(dev, "Failed to get K90 initial state (error %d).\n",
 			 ret);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 	brightness = data[4];
 	if (brightness < 0 || brightness > 3) {
 		dev_warn(dev,
 			 "Read invalid backlight brightness: %02hhx.\n",
 			 data[4]);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
-	return brightness;
+	ret = brightness;
+out:
+	kfree(data);
+
+	return ret;
 }
 
 static enum led_brightness k90_record_led_get(struct led_classdev *led_cdev)
@@ -253,17 +263,22 @@ static ssize_t k90_show_macro_mode(struct device *dev,
 	struct usb_interface *usbif = to_usb_interface(dev->parent);
 	struct usb_device *usbdev = interface_to_usbdev(usbif);
 	const char *macro_mode;
-	char data[8];
+	char *data;
+
+	data = kmalloc(2, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
 
 	ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0),
 			      K90_REQUEST_GET_MODE,
 			      USB_DIR_IN | USB_TYPE_VENDOR |
 			      USB_RECIP_DEVICE, 0, 0, data, 2,
 			      USB_CTRL_SET_TIMEOUT);
-	if (ret < 0) {
+	if (ret < 1) {
 		dev_warn(dev, "Failed to get K90 initial mode (error %d).\n",
 			 ret);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
 	switch (data[0]) {
@@ -277,10 +292,15 @@ static ssize_t k90_show_macro_mode(struct device *dev,
 	default:
 		dev_warn(dev, "K90 in unknown mode: %02hhx.\n",
 			 data[0]);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
-	return snprintf(buf, PAGE_SIZE, "%s\n", macro_mode);
+	ret = snprintf(buf, PAGE_SIZE, "%s\n", macro_mode);
+out:
+	kfree(data);
+
+	return ret;
 }
 
 static ssize_t k90_store_macro_mode(struct device *dev,
@@ -320,26 +340,36 @@ static ssize_t k90_show_current_profile(struct device *dev,
 	struct usb_interface *usbif = to_usb_interface(dev->parent);
 	struct usb_device *usbdev = interface_to_usbdev(usbif);
 	int current_profile;
-	char data[8];
+	char *data;
+
+	data = kmalloc(8, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
 
 	ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0),
 			      K90_REQUEST_STATUS,
 			      USB_DIR_IN | USB_TYPE_VENDOR |
 			      USB_RECIP_DEVICE, 0, 0, data, 8,
 			      USB_CTRL_SET_TIMEOUT);
-	if (ret < 0) {
+	if (ret < 8) {
 		dev_warn(dev, "Failed to get K90 initial state (error %d).\n",
 			 ret);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 	current_profile = data[7];
 	if (current_profile < 1 || current_profile > 3) {
 		dev_warn(dev, "Read invalid current profile: %02hhx.\n",
 			 data[7]);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", current_profile);
+	ret = snprintf(buf, PAGE_SIZE, "%d\n", current_profile);
+out:
+	kfree(data);
+
+	return ret;
 }
 
 static ssize_t k90_store_current_profile(struct device *dev,
diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index 1a2984c28b95..ae04826e82fc 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -770,12 +770,8 @@ static int _gid_table_setup_one(struct ib_device *ib_dev)
 	int err = 0;
 
 	table = kcalloc(ib_dev->phys_port_cnt, sizeof(*table), GFP_KERNEL);
-
-	if (!table) {
-		pr_warn("failed to allocate ib gid cache for %s\n",
-			ib_dev->name);
+	if (!table)
 		return -ENOMEM;
-	}
 
 	for (port = 0; port < ib_dev->phys_port_cnt; port++) {
 		u8 rdma_port = port + rdma_start_port(ib_dev);
@@ -1170,14 +1166,13 @@ int ib_cache_setup_one(struct ib_device *device)
 					  GFP_KERNEL);
 	if (!device->cache.pkey_cache ||
 	    !device->cache.lmc_cache) {
-		pr_warn("Couldn't allocate cache for %s\n", device->name);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto free;
 	}
 
 	err = gid_table_setup_one(device);
 	if (err)
-		/* Allocated memory will be cleaned in the release function */
-		return err;
+		goto free;
 
 	for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p)
 		ib_cache_update(device, p + rdma_start_port(device));
@@ -1192,6 +1187,9 @@ int ib_cache_setup_one(struct ib_device *device)
 
 err:
 	gid_table_cleanup_one(device);
+free:
+	kfree(device->cache.pkey_cache);
+	kfree(device->cache.lmc_cache);
 	return err;
 }
 
diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index b9bf0759f10a..8dfc76f8cbb4 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -114,7 +114,9 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
 		       !(1 << ah->av.eth.stat_rate & dev->caps.stat_rate_support))
 			--ah->av.eth.stat_rate;
 	}
-
+	ah->av.eth.sl_tclass_flowlabel |=
+			cpu_to_be32((ah_attr->grh.traffic_class << 20) |
+				    ah_attr->grh.flow_label);
 	/*
 	 * HW requires multicast LID so we just choose one.
 	 */
@@ -122,7 +124,7 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
 		ah->av.ib.dlid = cpu_to_be16(0xc000);
 
 	memcpy(ah->av.eth.dgid, ah_attr->grh.dgid.raw, 16);
-	ah->av.eth.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 29);
+	ah->av.eth.sl_tclass_flowlabel |= cpu_to_be32(ah_attr->sl << 29);
 
 	return &ah->ibah;
 }
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 1672907ff219..18d309e40f1b 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -702,10 +702,18 @@ static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port,
 
 	/* If a grh is present, we demux according to it */
 	if (wc->wc_flags & IB_WC_GRH) {
-		slave = mlx4_ib_find_real_gid(ibdev, port, grh->dgid.global.interface_id);
-		if (slave < 0) {
-			mlx4_ib_warn(ibdev, "failed matching grh\n");
-			return -ENOENT;
+		if (grh->dgid.global.interface_id ==
+			cpu_to_be64(IB_SA_WELL_KNOWN_GUID) &&
+		    grh->dgid.global.subnet_prefix == cpu_to_be64(
+			atomic64_read(&dev->sriov.demux[port - 1].subnet_prefix))) {
+			slave = 0;
+		} else {
+			slave = mlx4_ib_find_real_gid(ibdev, port,
+						      grh->dgid.global.interface_id);
+			if (slave < 0) {
+				mlx4_ib_warn(ibdev, "failed matching grh\n");
+				return -ENOENT;
+			}
 		}
 	}
 	/* Class-specific handling */
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index b597e8227591..46ad99595fd2 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -697,9 +697,11 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port,
 	if (err)
 		goto out;
 
-	props->active_width	=  (((u8 *)mailbox->buf)[5] == 0x40) ?
-						IB_WIDTH_4X : IB_WIDTH_1X;
-	props->active_speed	= IB_SPEED_QDR;
+	props->active_width	=  (((u8 *)mailbox->buf)[5] == 0x40) ||
+				   (((u8 *)mailbox->buf)[5] == 0x20 /*56Gb*/) ?
+					   IB_WIDTH_4X : IB_WIDTH_1X;
+	props->active_speed	=  (((u8 *)mailbox->buf)[5] == 0x20 /*56Gb*/) ?
+					   IB_SPEED_FDR : IB_SPEED_QDR;
 	props->port_cap_flags	= IB_PORT_CM_SUP | IB_PORT_IP_BASED_GIDS;
 	props->gid_tbl_len	= mdev->dev->caps.gid_table_len[port];
 	props->max_msg_sz	= mdev->dev->caps.max_msg_sz;
@@ -2820,14 +2822,19 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 			goto err_steer_qp_release;
 		}
 
-		bitmap_zero(ibdev->ib_uc_qpns_bitmap, ibdev->steer_qpn_count);
-
-		err = mlx4_FLOW_STEERING_IB_UC_QP_RANGE(
-				dev, ibdev->steer_qpn_base,
-				ibdev->steer_qpn_base +
-				ibdev->steer_qpn_count - 1);
-		if (err)
-			goto err_steer_free_bitmap;
+		if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DMFS_IPOIB) {
+			bitmap_zero(ibdev->ib_uc_qpns_bitmap,
+				    ibdev->steer_qpn_count);
+			err = mlx4_FLOW_STEERING_IB_UC_QP_RANGE(
+					dev, ibdev->steer_qpn_base,
+					ibdev->steer_qpn_base +
+					ibdev->steer_qpn_count - 1);
+			if (err)
+				goto err_steer_free_bitmap;
+		} else {
+			bitmap_fill(ibdev->ib_uc_qpns_bitmap,
+				    ibdev->steer_qpn_count);
+		}
 	}
 
 	for (j = 1; j <= ibdev->dev->caps.num_ports; j++)
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 570bc866b1d6..c22454383976 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1280,7 +1280,8 @@ static int _mlx4_ib_destroy_qp(struct ib_qp *qp)
 	if (is_qp0(dev, mqp))
 		mlx4_CLOSE_PORT(dev->dev, mqp->port);
 
-	if (dev->qp1_proxy[mqp->port - 1] == mqp) {
+	if (mqp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI &&
+	    dev->qp1_proxy[mqp->port - 1] == mqp) {
 		mutex_lock(&dev->qp1_proxy_lock[mqp->port - 1]);
 		dev->qp1_proxy[mqp->port - 1] = NULL;
 		mutex_unlock(&dev->qp1_proxy_lock[mqp->port - 1]);
@@ -1764,14 +1765,14 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		u8 port_num = mlx4_is_bonded(to_mdev(ibqp->device)->dev) ? 1 :
 			attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
 		union ib_gid gid;
-		struct ib_gid_attr gid_attr;
+		struct ib_gid_attr gid_attr = {.gid_type = IB_GID_TYPE_IB};
 		u16 vlan = 0xffff;
 		u8 smac[ETH_ALEN];
 		int status = 0;
 		int is_eth = rdma_cap_eth_ah(&dev->ib_dev, port_num) &&
 			attr->ah_attr.ah_flags & IB_AH_GRH;
 
-		if (is_eth) {
+		if (is_eth && attr->ah_attr.ah_flags & IB_AH_GRH) {
 			int index = attr->ah_attr.grh.sgid_index;
 
 			status = ib_get_cached_gid(ibqp->device, port_num,
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 32b09f059c84..4cab29ea394c 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -496,6 +496,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 	struct mlx5_core_dev *mdev = dev->mdev;
 	int err = -ENOMEM;
+	int max_sq_desc;
 	int max_rq_sg;
 	int max_sq_sg;
 	u64 min_page_size = 1ull << MLX5_CAP_GEN(mdev, log_pg_sz);
@@ -618,9 +619,10 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	props->max_qp_wr	   = 1 << MLX5_CAP_GEN(mdev, log_max_qp_sz);
 	max_rq_sg =  MLX5_CAP_GEN(mdev, max_wqe_sz_rq) /
 		     sizeof(struct mlx5_wqe_data_seg);
-	max_sq_sg = (MLX5_CAP_GEN(mdev, max_wqe_sz_sq) -
-		     sizeof(struct mlx5_wqe_ctrl_seg)) /
-		     sizeof(struct mlx5_wqe_data_seg);
+	max_sq_desc = min_t(int, MLX5_CAP_GEN(mdev, max_wqe_sz_sq), 512);
+	max_sq_sg = (max_sq_desc - sizeof(struct mlx5_wqe_ctrl_seg) -
+		     sizeof(struct mlx5_wqe_raddr_seg)) /
+		sizeof(struct mlx5_wqe_data_seg);
 	props->max_sge = min(max_rq_sg, max_sq_sg);
 	props->max_sge_rd	   = MLX5_MAX_SGE_RD;
 	props->max_cq		   = 1 << MLX5_CAP_GEN(mdev, log_max_cq);
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 4e9012463c37..be2d02b6a6aa 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -628,7 +628,8 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 		ent->order = i + 2;
 		ent->dev = dev;
 
-		if (dev->mdev->profile->mask & MLX5_PROF_MASK_MR_CACHE)
+		if ((dev->mdev->profile->mask & MLX5_PROF_MASK_MR_CACHE) &&
+		    (mlx5_core_is_pf(dev->mdev)))
 			limit = dev->mdev->profile->mr_cache[i].limit;
 		else
 			limit = 0;
@@ -646,6 +647,33 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 	return 0;
 }
 
+static void wait_for_async_commands(struct mlx5_ib_dev *dev)
+{
+	struct mlx5_mr_cache *cache = &dev->cache;
+	struct mlx5_cache_ent *ent;
+	int total = 0;
+	int i;
+	int j;
+
+	for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) {
+		ent = &cache->ent[i];
+		for (j = 0 ; j < 1000; j++) {
+			if (!ent->pending)
+				break;
+			msleep(50);
+		}
+	}
+	for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) {
+		ent = &cache->ent[i];
+		total += ent->pending;
+	}
+
+	if (total)
+		mlx5_ib_warn(dev, "aborted while there are %d pending mr requests\n", total);
+	else
+		mlx5_ib_warn(dev, "done with all pending requests\n");
+}
+
 int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev)
 {
 	int i;
@@ -659,6 +687,7 @@ int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev)
 		clean_keys(dev, i);
 
 	destroy_workqueue(dev->cache.wq);
+	wait_for_async_commands(dev);
 	del_timer_sync(&dev->delay_timer);
 
 	return 0;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index d1e921816bfe..aee3942ec68d 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -351,6 +351,29 @@ static int calc_send_wqe(struct ib_qp_init_attr *attr)
 		return ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB);
 }
 
+static int get_send_sge(struct ib_qp_init_attr *attr, int wqe_size)
+{
+	int max_sge;
+
+	if (attr->qp_type == IB_QPT_RC)
+		max_sge = (min_t(int, wqe_size, 512) -
+			   sizeof(struct mlx5_wqe_ctrl_seg) -
+			   sizeof(struct mlx5_wqe_raddr_seg)) /
+			sizeof(struct mlx5_wqe_data_seg);
+	else if (attr->qp_type == IB_QPT_XRC_INI)
+		max_sge = (min_t(int, wqe_size, 512) -
+			   sizeof(struct mlx5_wqe_ctrl_seg) -
+			   sizeof(struct mlx5_wqe_xrc_seg) -
+			   sizeof(struct mlx5_wqe_raddr_seg)) /
+			sizeof(struct mlx5_wqe_data_seg);
+	else
+		max_sge = (wqe_size - sq_overhead(attr)) /
+			sizeof(struct mlx5_wqe_data_seg);
+
+	return min_t(int, max_sge, wqe_size - sq_overhead(attr) /
+		     sizeof(struct mlx5_wqe_data_seg));
+}
+
 static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
 			struct mlx5_ib_qp *qp)
 {
@@ -387,7 +410,11 @@ static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
 		return -ENOMEM;
 	}
 	qp->sq.wqe_shift = ilog2(MLX5_SEND_WQE_BB);
-	qp->sq.max_gs = attr->cap.max_send_sge;
+	qp->sq.max_gs = get_send_sge(attr, wqe_size);
+	if (qp->sq.max_gs < attr->cap.max_send_sge)
+		return -ENOMEM;
+
+	attr->cap.max_send_sge = qp->sq.max_gs;
 	qp->sq.max_post = wq_size / wqe_size;
 	attr->cap.max_send_wr = qp->sq.max_post;
 
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 3857dbd9c956..729b0696626e 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -282,6 +282,7 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 	mlx5_ib_dbg(dev, "desc_size 0x%x, req wr 0x%x, srq size 0x%x, max_gs 0x%x, max_avail_gather 0x%x\n",
 		    desc_size, init_attr->attr.max_wr, srq->msrq.max, srq->msrq.max_gs,
 		    srq->msrq.max_avail_gather);
+	in.type = init_attr->srq_type;
 
 	if (pd->uobject)
 		err = create_srq_user(pd, srq, &in, udata, buf_size);
@@ -294,7 +295,6 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 		goto err_srq;
 	}
 
-	in.type = init_attr->srq_type;
 	in.log_size = ilog2(srq->msrq.max);
 	in.wqe_shift = srq->msrq.wqe_shift - 4;
 	if (srq->wq_sig)
diff --git a/drivers/infiniband/sw/rxe/rxe_param.h b/drivers/infiniband/sw/rxe/rxe_param.h
index f459c43a77c8..13ed2cc6eaa2 100644
--- a/drivers/infiniband/sw/rxe/rxe_param.h
+++ b/drivers/infiniband/sw/rxe/rxe_param.h
@@ -82,7 +82,7 @@ enum rxe_device_param {
 	RXE_MAX_SGE			= 32,
 	RXE_MAX_SGE_RD			= 32,
 	RXE_MAX_CQ			= 16384,
-	RXE_MAX_LOG_CQE			= 13,
+	RXE_MAX_LOG_CQE			= 15,
 	RXE_MAX_MR			= 2 * 1024,
 	RXE_MAX_PD			= 0x7ffc,
 	RXE_MAX_QP_RD_ATOM		= 128,
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index 22bd9630dcd9..9f46be52335e 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -548,23 +548,23 @@ static void update_wqe_psn(struct rxe_qp *qp,
 static void save_state(struct rxe_send_wqe *wqe,
 		       struct rxe_qp *qp,
 		       struct rxe_send_wqe *rollback_wqe,
-		       struct rxe_qp *rollback_qp)
+		       u32 *rollback_psn)
 {
 	rollback_wqe->state     = wqe->state;
 	rollback_wqe->first_psn = wqe->first_psn;
 	rollback_wqe->last_psn  = wqe->last_psn;
-	rollback_qp->req.psn    = qp->req.psn;
+	*rollback_psn		= qp->req.psn;
 }
 
 static void rollback_state(struct rxe_send_wqe *wqe,
 			   struct rxe_qp *qp,
 			   struct rxe_send_wqe *rollback_wqe,
-			   struct rxe_qp *rollback_qp)
+			   u32 rollback_psn)
 {
 	wqe->state     = rollback_wqe->state;
 	wqe->first_psn = rollback_wqe->first_psn;
 	wqe->last_psn  = rollback_wqe->last_psn;
-	qp->req.psn    = rollback_qp->req.psn;
+	qp->req.psn    = rollback_psn;
 }
 
 static void update_state(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
@@ -593,8 +593,8 @@ int rxe_requester(void *arg)
 	int mtu;
 	int opcode;
 	int ret;
-	struct rxe_qp rollback_qp;
 	struct rxe_send_wqe rollback_wqe;
+	u32 rollback_psn;
 
 next_wqe:
 	if (unlikely(!qp->valid || qp->req.state == QP_STATE_ERROR))
@@ -719,7 +719,7 @@ int rxe_requester(void *arg)
 	 * rxe_xmit_packet().
 	 * Otherwise, completer might initiate an unjustified retry flow.
 	 */
-	save_state(wqe, qp, &rollback_wqe, &rollback_qp);
+	save_state(wqe, qp, &rollback_wqe, &rollback_psn);
 	update_wqe_state(qp, wqe, &pkt);
 	update_wqe_psn(qp, wqe, &pkt, payload);
 	ret = rxe_xmit_packet(to_rdev(qp->ibqp.device), qp, &pkt, skb);
@@ -727,7 +727,7 @@ int rxe_requester(void *arg)
 		qp->need_req_skb = 1;
 		kfree_skb(skb);
 
-		rollback_state(wqe, qp, &rollback_wqe, &rollback_qp);
+		rollback_state(wqe, qp, &rollback_wqe, rollback_psn);
 
 		if (ret == -EAGAIN) {
 			rxe_run_task(&qp->req.task, 1);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 339a1eecdfe3..81a8080c18b3 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1054,8 +1054,6 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_
 
 	tx_qp = ib_create_qp(priv->pd, &attr);
 	if (PTR_ERR(tx_qp) == -EINVAL) {
-		ipoib_warn(priv, "can't use GFP_NOIO for QPs on device %s, using GFP_KERNEL\n",
-			   priv->ca->name);
 		attr.create_flags &= ~IB_QP_CREATE_USE_GFP_NOIO;
 		tx_qp = ib_create_qp(priv->pd, &attr);
 	}
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 6d7de9bfed9a..b93fe83a0b63 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -1346,6 +1346,18 @@ static void alps_process_packet_ss4_v2(struct psmouse *psmouse)
 
 	priv->multi_packet = 0;
 
+	/* Report trackstick */
+	if (alps_get_pkt_id_ss4_v2(packet) == SS4_PACKET_ID_STICK) {
+		if (priv->flags & ALPS_DUALPOINT) {
+			input_report_key(dev2, BTN_LEFT, f->ts_left);
+			input_report_key(dev2, BTN_RIGHT, f->ts_right);
+			input_report_key(dev2, BTN_MIDDLE, f->ts_middle);
+			input_sync(dev2);
+		}
+		return;
+	}
+
+	/* Report touchpad */
 	alps_report_mt_data(psmouse, (f->fingers <= 4) ? f->fingers : 4);
 
 	input_mt_report_finger_count(dev, f->fingers);
@@ -1356,13 +1368,6 @@ static void alps_process_packet_ss4_v2(struct psmouse *psmouse)
 
 	input_report_abs(dev, ABS_PRESSURE, f->pressure);
 	input_sync(dev);
-
-	if (priv->flags & ALPS_DUALPOINT) {
-		input_report_key(dev2, BTN_LEFT, f->ts_left);
-		input_report_key(dev2, BTN_RIGHT, f->ts_right);
-		input_report_key(dev2, BTN_MIDDLE, f->ts_middle);
-		input_sync(dev2);
-	}
 }
 
 static bool alps_is_valid_package_ss4_v2(struct psmouse *psmouse)
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index ce4a96fccc43..5ff803efdc03 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -93,7 +93,7 @@ config VIDEO_OMAP3_DEBUG
 
 config VIDEO_PXA27x
 	tristate "PXA27x Quick Capture Interface driver"
-	depends on VIDEO_DEV && HAS_DMA
+	depends on VIDEO_DEV && VIDEO_V4L2 && HAS_DMA
 	depends on PXA27x || COMPILE_TEST
 	select VIDEOBUF2_DMA_SG
 	select SG_SPLIT
diff --git a/drivers/media/platform/blackfin/ppi.c b/drivers/media/platform/blackfin/ppi.c
index cff63e511e6d..b8f3d9fa66e9 100644
--- a/drivers/media/platform/blackfin/ppi.c
+++ b/drivers/media/platform/blackfin/ppi.c
@@ -214,6 +214,8 @@ static int ppi_set_params(struct ppi_if *ppi, struct ppi_params *params)
 	if (params->dlen > 24 || params->dlen <= 0)
 		return -EINVAL;
 	pctrl = devm_pinctrl_get(ppi->dev);
+	if (IS_ERR(pctrl))
+		return PTR_ERR(pctrl);
 	pstate = pinctrl_lookup_state(pctrl,
 				      pin_state[(params->dlen + 7) / 8 - 1]);
 	if (pinctrl_select_state(pctrl, pstate))
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc.c b/drivers/media/platform/s5p-mfc/s5p_mfc.c
index 3436eda58855..27e7cf65c2a7 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc.c
@@ -926,10 +926,11 @@ static int s5p_mfc_release(struct file *file)
 	mfc_debug_enter();
 	if (dev)
 		mutex_lock(&dev->mfc_mutex);
-	s5p_mfc_clock_on();
 	vb2_queue_release(&ctx->vq_src);
 	vb2_queue_release(&ctx->vq_dst);
 	if (dev) {
+		s5p_mfc_clock_on();
+
 		/* Mark context as idle */
 		clear_work_bit_irqsave(ctx);
 		/*
@@ -951,9 +952,9 @@ static int s5p_mfc_release(struct file *file)
 			if (s5p_mfc_power_off() < 0)
 				mfc_err("Power off failed\n");
 		}
+		mfc_debug(2, "Shutting down clock\n");
+		s5p_mfc_clock_off();
 	}
-	mfc_debug(2, "Shutting down clock\n");
-	s5p_mfc_clock_off();
 	if (dev)
 		dev->ctx[ctx->num] = NULL;
 	s5p_mfc_dec_ctrls_delete(ctx);
diff --git a/drivers/media/platform/sti/hva/hva-hw.c b/drivers/media/platform/sti/hva/hva-hw.c
index d341d4994528..cf2a8d884536 100644
--- a/drivers/media/platform/sti/hva/hva-hw.c
+++ b/drivers/media/platform/sti/hva/hva-hw.c
@@ -305,16 +305,16 @@ int hva_hw_probe(struct platform_device *pdev, struct hva_dev *hva)
 	/* get memory for registers */
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	hva->regs = devm_ioremap_resource(dev, regs);
-	if (IS_ERR_OR_NULL(hva->regs)) {
+	if (IS_ERR(hva->regs)) {
 		dev_err(dev, "%s     failed to get regs\n", HVA_PREFIX);
 		return PTR_ERR(hva->regs);
 	}
 
 	/* get memory for esram */
 	esram = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	if (IS_ERR_OR_NULL(esram)) {
+	if (!esram) {
 		dev_err(dev, "%s     failed to get esram\n", HVA_PREFIX);
-		return PTR_ERR(esram);
+		return -ENODEV;
 	}
 	hva->esram_addr = esram->start;
 	hva->esram_size = resource_size(esram);
diff --git a/drivers/media/rc/ite-cir.c b/drivers/media/rc/ite-cir.c
index 0f301903aa6f..63165d324fff 100644
--- a/drivers/media/rc/ite-cir.c
+++ b/drivers/media/rc/ite-cir.c
@@ -263,6 +263,8 @@ static void ite_set_carrier_params(struct ite_dev *dev)
 
 			if (allowance > ITE_RXDCR_MAX)
 				allowance = ITE_RXDCR_MAX;
+
+			use_demodulator = true;
 		}
 	}
 
diff --git a/drivers/media/spi/gs1662.c b/drivers/media/spi/gs1662.c
index d76f36233f43..5143a90219c0 100644
--- a/drivers/media/spi/gs1662.c
+++ b/drivers/media/spi/gs1662.c
@@ -453,10 +453,9 @@ static int gs_probe(struct spi_device *spi)
 static int gs_remove(struct spi_device *spi)
 {
 	struct v4l2_subdev *sd = spi_get_drvdata(spi);
-	struct gs *gs = to_gs(sd);
 
 	v4l2_device_unregister_subdev(sd);
-	kfree(gs);
+
 	return 0;
 }
 
diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c
index 44ecebd1ea8c..c8b8ac66ff7e 100644
--- a/drivers/mmc/host/mxs-mmc.c
+++ b/drivers/mmc/host/mxs-mmc.c
@@ -309,6 +309,9 @@ static void mxs_mmc_ac(struct mxs_mmc_host *host)
 	cmd0 = BF_SSP(cmd->opcode, CMD0_CMD);
 	cmd1 = cmd->arg;
 
+	if (cmd->opcode == MMC_STOP_TRANSMISSION)
+		cmd0 |= BM_SSP_CMD0_APPEND_8CYC;
+
 	if (host->sdio_irq_en) {
 		ctrl0 |= BM_SSP_CTRL0_SDIO_IRQ_CHECK;
 		cmd0 |= BM_SSP_CMD0_CONT_CLKING_EN | BM_SSP_CMD0_SLOW_CLKING_EN;
@@ -417,8 +420,7 @@ static void mxs_mmc_adtc(struct mxs_mmc_host *host)
 		       ssp->base + HW_SSP_BLOCK_SIZE);
 	}
 
-	if ((cmd->opcode == MMC_STOP_TRANSMISSION) ||
-	    (cmd->opcode == SD_IO_RW_EXTENDED))
+	if (cmd->opcode == SD_IO_RW_EXTENDED)
 		cmd0 |= BM_SSP_CMD0_APPEND_8CYC;
 
 	cmd1 = cmd->arg;
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index 81d4dc034793..fddd0be196f4 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -394,7 +394,8 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 	/* Power on the SDHCI controller and its children */
 	acpi_device_fix_up_power(device);
 	list_for_each_entry(child, &device->children, node)
-		acpi_device_fix_up_power(child);
+		if (child->status.present && child->status.enabled)
+			acpi_device_fix_up_power(child);
 
 	if (acpi_bus_get_status(device) || !device->status.present)
 		return -ENODEV;
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 7b7a887b4709..b254090b8a1b 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -537,7 +537,7 @@ config MTD_NAND_FSMC
 	  Flexible Static Memory Controller (FSMC)
 
 config MTD_NAND_XWAY
-	tristate "Support for NAND on Lantiq XWAY SoC"
+	bool "Support for NAND on Lantiq XWAY SoC"
 	depends on LANTIQ && SOC_TYPE_XWAY
 	help
 	  Enables support for NAND Flash chips on Lantiq XWAY SoCs. NAND is attached
diff --git a/drivers/mtd/nand/lpc32xx_mlc.c b/drivers/mtd/nand/lpc32xx_mlc.c
index 852388171f20..bc6e49af063a 100644
--- a/drivers/mtd/nand/lpc32xx_mlc.c
+++ b/drivers/mtd/nand/lpc32xx_mlc.c
@@ -776,7 +776,7 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	init_completion(&host->comp_controller);
 
 	host->irq = platform_get_irq(pdev, 0);
-	if ((host->irq < 0) || (host->irq >= NR_IRQS)) {
+	if (host->irq < 0) {
 		dev_err(&pdev->dev, "failed to get platform irq\n");
 		res = -EINVAL;
 		goto err_exit3;
diff --git a/drivers/mtd/nand/xway_nand.c b/drivers/mtd/nand/xway_nand.c
index 1f2948c0c458..895101a5e686 100644
--- a/drivers/mtd/nand/xway_nand.c
+++ b/drivers/mtd/nand/xway_nand.c
@@ -232,7 +232,6 @@ static const struct of_device_id xway_nand_match[] = {
 	{ .compatible = "lantiq,nand-xway" },
 	{},
 };
-MODULE_DEVICE_TABLE(of, xway_nand_match);
 
 static struct platform_driver xway_nand_driver = {
 	.probe	= xway_nand_probe,
@@ -243,6 +242,4 @@ static struct platform_driver xway_nand_driver = {
 	},
 };
 
-module_platform_driver(xway_nand_driver);
-
-MODULE_LICENSE("GPL");
+builtin_platform_driver(xway_nand_driver);
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index d403ba7b8f43..d489fbd07c12 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -1077,12 +1077,14 @@ static int cqspi_setup_flash(struct cqspi_st *cqspi, struct device_node *np)
 
 	/* Get flash device data */
 	for_each_available_child_of_node(dev->of_node, np) {
-		if (of_property_read_u32(np, "reg", &cs)) {
+		ret = of_property_read_u32(np, "reg", &cs);
+		if (ret) {
 			dev_err(dev, "Couldn't determine chip select.\n");
 			goto err;
 		}
 
-		if (cs > CQSPI_MAX_CHIPSELECT) {
+		if (cs >= CQSPI_MAX_CHIPSELECT) {
+			ret = -EINVAL;
 			dev_err(dev, "Chip select %d out of range.\n", cs);
 			goto err;
 		}
diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c
index 1056ed142411..f186e0460cde 100644
--- a/drivers/net/ieee802154/atusb.c
+++ b/drivers/net/ieee802154/atusb.c
@@ -112,13 +112,26 @@ static int atusb_read_reg(struct atusb *atusb, uint8_t reg)
 {
 	struct usb_device *usb_dev = atusb->usb_dev;
 	int ret;
+	uint8_t *buffer;
 	uint8_t value;
 
+	buffer = kmalloc(1, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
 	dev_dbg(&usb_dev->dev, "atusb: reg = 0x%x\n", reg);
 	ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0),
 				ATUSB_REG_READ, ATUSB_REQ_FROM_DEV,
-				0, reg, &value, 1, 1000);
-	return ret >= 0 ? value : ret;
+				0, reg, buffer, 1, 1000);
+
+	if (ret >= 0) {
+		value = buffer[0];
+		kfree(buffer);
+		return value;
+	} else {
+		kfree(buffer);
+		return ret;
+	}
 }
 
 static int atusb_write_subreg(struct atusb *atusb, uint8_t reg, uint8_t mask,
@@ -587,9 +600,13 @@ static struct ieee802154_ops atusb_ops = {
 static int atusb_get_and_show_revision(struct atusb *atusb)
 {
 	struct usb_device *usb_dev = atusb->usb_dev;
-	unsigned char buffer[3];
+	unsigned char *buffer;
 	int ret;
 
+	buffer = kmalloc(3, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
 	/* Get a couple of the ATMega Firmware values */
 	ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0),
 				ATUSB_ID, ATUSB_REQ_FROM_DEV, 0, 0,
@@ -605,15 +622,20 @@ static int atusb_get_and_show_revision(struct atusb *atusb)
 		dev_info(&usb_dev->dev, "Please update to version 0.2 or newer");
 	}
 
+	kfree(buffer);
 	return ret;
 }
 
 static int atusb_get_and_show_build(struct atusb *atusb)
 {
 	struct usb_device *usb_dev = atusb->usb_dev;
-	char build[ATUSB_BUILD_SIZE + 1];
+	char *build;
 	int ret;
 
+	build = kmalloc(ATUSB_BUILD_SIZE + 1, GFP_KERNEL);
+	if (!build)
+		return -ENOMEM;
+
 	ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0),
 				ATUSB_BUILD, ATUSB_REQ_FROM_DEV, 0, 0,
 				build, ATUSB_BUILD_SIZE, 1000);
@@ -622,6 +644,7 @@ static int atusb_get_and_show_build(struct atusb *atusb)
 		dev_info(&usb_dev->dev, "Firmware: build %s\n", build);
 	}
 
+	kfree(build);
 	return ret;
 }
 
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index abe5c6bc756c..1480734c2d6e 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -957,6 +957,7 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
 {
 	resource_size_t allocated = 0, available = 0;
 	struct nd_region *nd_region = to_nd_region(dev->parent);
+	struct nd_namespace_common *ndns = to_ndns(dev);
 	struct nd_mapping *nd_mapping;
 	struct nvdimm_drvdata *ndd;
 	struct nd_label_id label_id;
@@ -964,7 +965,7 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
 	u8 *uuid = NULL;
 	int rc, i;
 
-	if (dev->driver || to_ndns(dev)->claim)
+	if (dev->driver || ndns->claim)
 		return -EBUSY;
 
 	if (is_namespace_pmem(dev)) {
@@ -1034,20 +1035,16 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
 
 		nd_namespace_pmem_set_resource(nd_region, nspm,
 				val * nd_region->ndr_mappings);
-	} else if (is_namespace_blk(dev)) {
-		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
-
-		/*
-		 * Try to delete the namespace if we deleted all of its
-		 * allocation, this is not the seed device for the
-		 * region, and it is not actively claimed by a btt
-		 * instance.
-		 */
-		if (val == 0 && nd_region->ns_seed != dev
-				&& !nsblk->common.claim)
-			nd_device_unregister(dev, ND_ASYNC);
 	}
 
+	/*
+	 * Try to delete the namespace if we deleted all of its
+	 * allocation, this is not the seed device for the region, and
+	 * it is not actively claimed by a btt instance.
+	 */
+	if (val == 0 && nd_region->ns_seed != dev && !ndns->claim)
+		nd_device_unregister(dev, ND_ASYNC);
+
 	return rc;
 }
 
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index bed19994c1e9..af8f6e92e885 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -807,11 +807,6 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
 {
 	u32 val;
 
-	/* get iATU unroll support */
-	pp->iatu_unroll_enabled = dw_pcie_iatu_unroll_enabled(pp);
-	dev_dbg(pp->dev, "iATU unroll: %s\n",
-		pp->iatu_unroll_enabled ? "enabled" : "disabled");
-
 	/* set the number of lanes */
 	val = dw_pcie_readl_rc(pp, PCIE_PORT_LINK_CONTROL);
 	val &= ~PORT_LINK_MODE_MASK;
@@ -882,6 +877,11 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
 	 * we should not program the ATU here.
 	 */
 	if (!pp->ops->rd_other_conf) {
+		/* get iATU unroll support */
+		pp->iatu_unroll_enabled = dw_pcie_iatu_unroll_enabled(pp);
+		dev_dbg(pp->dev, "iATU unroll: %s\n",
+			pp->iatu_unroll_enabled ? "enabled" : "disabled");
+
 		dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX0,
 					  PCIE_ATU_TYPE_MEM, pp->mem_base,
 					  pp->mem_bus_addr, pp->mem_size);
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 104c46d53121..300770cdc084 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1050,6 +1050,7 @@ void set_pcie_port_type(struct pci_dev *pdev)
 	pos = pci_find_capability(pdev, PCI_CAP_ID_EXP);
 	if (!pos)
 		return;
+
 	pdev->pcie_cap = pos;
 	pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, &reg16);
 	pdev->pcie_flags_reg = reg16;
@@ -1057,13 +1058,14 @@ void set_pcie_port_type(struct pci_dev *pdev)
 	pdev->pcie_mpss = reg16 & PCI_EXP_DEVCAP_PAYLOAD;
 
 	/*
-	 * A Root Port is always the upstream end of a Link.  No PCIe
-	 * component has two Links.  Two Links are connected by a Switch
-	 * that has a Port on each Link and internal logic to connect the
-	 * two Ports.
+	 * A Root Port or a PCI-to-PCIe bridge is always the upstream end
+	 * of a Link.  No PCIe component has two Links.  Two Links are
+	 * connected by a Switch that has a Port on each Link and internal
+	 * logic to connect the two Ports.
 	 */
 	type = pci_pcie_type(pdev);
-	if (type == PCI_EXP_TYPE_ROOT_PORT)
+	if (type == PCI_EXP_TYPE_ROOT_PORT ||
+	    type == PCI_EXP_TYPE_PCIE_BRIDGE)
 		pdev->has_secondary_link = 1;
 	else if (type == PCI_EXP_TYPE_UPSTREAM ||
 		 type == PCI_EXP_TYPE_DOWNSTREAM) {
diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c
index b6ea9ffa7381..e0a629eaceab 100644
--- a/drivers/rpmsg/rpmsg_core.c
+++ b/drivers/rpmsg/rpmsg_core.c
@@ -411,8 +411,8 @@ int rpmsg_register_device(struct rpmsg_device *rpdev)
 	struct device *dev = &rpdev->dev;
 	int ret;
 
-	dev_set_name(&rpdev->dev, "%s:%s",
-		     dev_name(dev->parent), rpdev->id.name);
+	dev_set_name(&rpdev->dev, "%s.%s.%d.%d", dev_name(dev->parent),
+		     rpdev->id.name, rpdev->src, rpdev->dst);
 
 	rpdev->dev.bus = &rpmsg_bus;
 	rpdev->dev.release = rpmsg_release_device;
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index 608140f16d98..e3b911c895b4 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -45,6 +45,7 @@
 
 #define	INITIAL_SRP_LIMIT	800
 #define	DEFAULT_MAX_SECTORS	256
+#define MAX_TXU			1024 * 1024
 
 static uint max_vdma_size = MAX_H_COPY_RDMA;
 
@@ -1239,7 +1240,7 @@ static long ibmvscsis_adapter_info(struct scsi_info *vscsi,
 	}
 
 	info = dma_alloc_coherent(&vscsi->dma_dev->dev, sizeof(*info), &token,
-				  GFP_KERNEL);
+				  GFP_ATOMIC);
 	if (!info) {
 		dev_err(&vscsi->dev, "bad dma_alloc_coherent %p\n",
 			iue->target);
@@ -1291,7 +1292,7 @@ static long ibmvscsis_adapter_info(struct scsi_info *vscsi,
 	info->mad_version = cpu_to_be32(MAD_VERSION_1);
 	info->os_type = cpu_to_be32(LINUX);
 	memset(&info->port_max_txu[0], 0, sizeof(info->port_max_txu));
-	info->port_max_txu[0] = cpu_to_be32(128 * PAGE_SIZE);
+	info->port_max_txu[0] = cpu_to_be32(MAX_TXU);
 
 	dma_wmb();
 	rc = h_copy_rdma(sizeof(*info), vscsi->dds.window[LOCAL].liobn,
@@ -1357,7 +1358,7 @@ static int ibmvscsis_cap_mad(struct scsi_info *vscsi, struct iu_entry *iue)
 	}
 
 	cap = dma_alloc_coherent(&vscsi->dma_dev->dev, olen, &token,
-				 GFP_KERNEL);
+				 GFP_ATOMIC);
 	if (!cap) {
 		dev_err(&vscsi->dev, "bad dma_alloc_coherent %p\n",
 			iue->target);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 3e71bc1b4a80..7008061c4b5b 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -393,6 +393,7 @@ struct MPT3SAS_TARGET {
  * @eedp_enable: eedp support enable bit
  * @eedp_type: 0(type_1), 1(type_2), 2(type_3)
  * @eedp_block_length: block size
+ * @ata_command_pending: SATL passthrough outstanding for device
  */
 struct MPT3SAS_DEVICE {
 	struct MPT3SAS_TARGET *sas_target;
@@ -402,6 +403,17 @@ struct MPT3SAS_DEVICE {
 	u8	block;
 	u8	tlr_snoop_check;
 	u8	ignore_delay_remove;
+	/*
+	 * Bug workaround for SATL handling: the mpt2/3sas firmware
+	 * doesn't return BUSY or TASK_SET_FULL for subsequent
+	 * commands while a SATL pass through is in operation as the
+	 * spec requires, it simply does nothing with them until the
+	 * pass through completes, causing them possibly to timeout if
+	 * the passthrough is a long executing command (like format or
+	 * secure erase).  This variable allows us to do the right
+	 * thing while a SATL command is pending.
+	 */
+	unsigned long ata_command_pending;
 };
 
 #define MPT3_CMD_NOT_USED	0x8000	/* free */
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 1c4744e78173..f84a6087cebd 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -3885,9 +3885,18 @@ _scsih_temp_threshold_events(struct MPT3SAS_ADAPTER *ioc,
 	}
 }
 
-static inline bool ata_12_16_cmd(struct scsi_cmnd *scmd)
+static int _scsih_set_satl_pending(struct scsi_cmnd *scmd, bool pending)
 {
-	return (scmd->cmnd[0] == ATA_12 || scmd->cmnd[0] == ATA_16);
+	struct MPT3SAS_DEVICE *priv = scmd->device->hostdata;
+
+	if (scmd->cmnd[0] != ATA_12 && scmd->cmnd[0] != ATA_16)
+		return 0;
+
+	if (pending)
+		return test_and_set_bit(0, &priv->ata_command_pending);
+
+	clear_bit(0, &priv->ata_command_pending);
+	return 0;
 }
 
 /**
@@ -3911,9 +3920,7 @@ _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc)
 		if (!scmd)
 			continue;
 		count++;
-		if (ata_12_16_cmd(scmd))
-			scsi_internal_device_unblock(scmd->device,
-							SDEV_RUNNING);
+		_scsih_set_satl_pending(scmd, false);
 		mpt3sas_base_free_smid(ioc, smid);
 		scsi_dma_unmap(scmd);
 		if (ioc->pci_error_recovery)
@@ -4044,13 +4051,6 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 	if (ioc->logging_level & MPT_DEBUG_SCSI)
 		scsi_print_command(scmd);
 
-	/*
-	 * Lock the device for any subsequent command until command is
-	 * done.
-	 */
-	if (ata_12_16_cmd(scmd))
-		scsi_internal_device_block(scmd->device);
-
 	sas_device_priv_data = scmd->device->hostdata;
 	if (!sas_device_priv_data || !sas_device_priv_data->sas_target) {
 		scmd->result = DID_NO_CONNECT << 16;
@@ -4064,6 +4064,19 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 		return 0;
 	}
 
+	/*
+	 * Bug work around for firmware SATL handling.  The loop
+	 * is based on atomic operations and ensures consistency
+	 * since we're lockless at this point
+	 */
+	do {
+		if (test_bit(0, &sas_device_priv_data->ata_command_pending)) {
+			scmd->result = SAM_STAT_BUSY;
+			scmd->scsi_done(scmd);
+			return 0;
+		}
+	} while (_scsih_set_satl_pending(scmd, true));
+
 	sas_target_priv_data = sas_device_priv_data->sas_target;
 
 	/* invalid device handle */
@@ -4626,8 +4639,7 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	if (scmd == NULL)
 		return 1;
 
-	if (ata_12_16_cmd(scmd))
-		scsi_internal_device_unblock(scmd->device, SDEV_RUNNING);
+	_scsih_set_satl_pending(scmd, false);
 
 	mpi_request = mpt3sas_base_get_msg_frame(ioc, smid);
 
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 56d6142852a5..078d797cb492 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -3489,7 +3489,7 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len,
 				sizeof(struct ct6_dsd), 0,
 				SLAB_HWCACHE_ALIGN, NULL);
 			if (!ctx_cachep)
-				goto fail_free_gid_list;
+				goto fail_free_srb_mempool;
 		}
 		ha->ctx_mempool = mempool_create_slab_pool(SRB_MIN_REQ,
 			ctx_cachep);
@@ -3642,7 +3642,7 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len,
 	ha->loop_id_map = kzalloc(BITS_TO_LONGS(LOOPID_MAP_SIZE) * sizeof(long),
 	    GFP_KERNEL);
 	if (!ha->loop_id_map)
-		goto fail_async_pd;
+		goto fail_loop_id_map;
 	else {
 		qla2x00_set_reserved_loop_ids(ha);
 		ql_dbg_pci(ql_dbg_init, ha->pdev, 0x0123,
@@ -3651,6 +3651,8 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len,
 
 	return 0;
 
+fail_loop_id_map:
+	dma_pool_free(ha->s_dma_pool, ha->async_pd, ha->async_pd_dma);
 fail_async_pd:
 	dma_pool_free(ha->s_dma_pool, ha->ex_init_cb, ha->ex_init_cb_dma);
 fail_ex_init_cb:
@@ -3678,6 +3680,10 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len,
 	dma_pool_free(ha->s_dma_pool, ha->ms_iocb, ha->ms_iocb_dma);
 	ha->ms_iocb = NULL;
 	ha->ms_iocb_dma = 0;
+
+	if (ha->sns_cmd)
+		dma_free_coherent(&ha->pdev->dev, sizeof(struct sns_cmd_pkt),
+		    ha->sns_cmd, ha->sns_cmd_dma);
 fail_dma_pool:
 	if (IS_QLA82XX(ha) || ql2xenabledif) {
 		dma_pool_destroy(ha->fcp_cmnd_dma_pool);
@@ -3695,10 +3701,12 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len,
 	kfree(ha->nvram);
 	ha->nvram = NULL;
 fail_free_ctx_mempool:
-	mempool_destroy(ha->ctx_mempool);
+	if (ha->ctx_mempool)
+		mempool_destroy(ha->ctx_mempool);
 	ha->ctx_mempool = NULL;
 fail_free_srb_mempool:
-	mempool_destroy(ha->srb_mempool);
+	if (ha->srb_mempool)
+		mempool_destroy(ha->srb_mempool);
 	ha->srb_mempool = NULL;
 fail_free_gid_list:
 	dma_free_coherent(&ha->pdev->dev, qla2x00_gid_list_size(ha),
diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c
index 8c9a35c91705..50adabbb5808 100644
--- a/drivers/scsi/ses.c
+++ b/drivers/scsi/ses.c
@@ -587,7 +587,7 @@ static void ses_match_to_enclosure(struct enclosure_device *edev,
 
 	ses_enclosure_data_process(edev, to_scsi_device(edev->edev.parent), 0);
 
-	if (scsi_is_sas_rphy(&sdev->sdev_gendev))
+	if (scsi_is_sas_rphy(sdev->sdev_target->dev.parent))
 		efd.addr = sas_get_address(sdev);
 
 	if (efd.addr) {
diff --git a/drivers/soc/ti/wkup_m3_ipc.c b/drivers/soc/ti/wkup_m3_ipc.c
index 8823cc81ae45..5bb376009d98 100644
--- a/drivers/soc/ti/wkup_m3_ipc.c
+++ b/drivers/soc/ti/wkup_m3_ipc.c
@@ -459,6 +459,7 @@ static int wkup_m3_ipc_probe(struct platform_device *pdev)
 
 	if (IS_ERR(task)) {
 		dev_err(dev, "can't create rproc_boot thread\n");
+		ret = PTR_ERR(task);
 		goto err_put_rproc;
 	}
 
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index dd7b5b47291d..d6239fa718be 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -1690,6 +1690,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 		pxa2xx_spi_write(drv_data, SSCR1, tmp);
 		tmp = SSCR0_SCR(2) | SSCR0_Motorola | SSCR0_DataSize(8);
 		pxa2xx_spi_write(drv_data, SSCR0, tmp);
+		break;
 	default:
 		tmp = SSCR1_RxTresh(RX_THRESH_DFLT) |
 		      SSCR1_TxTresh(TX_THRESH_DFLT);
diff --git a/drivers/staging/media/s5p-cec/s5p_cec.c b/drivers/staging/media/s5p-cec/s5p_cec.c
index 1780a08b73c9..58d756231136 100644
--- a/drivers/staging/media/s5p-cec/s5p_cec.c
+++ b/drivers/staging/media/s5p-cec/s5p_cec.c
@@ -231,7 +231,7 @@ static int s5p_cec_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static int s5p_cec_runtime_suspend(struct device *dev)
+static int __maybe_unused s5p_cec_runtime_suspend(struct device *dev)
 {
 	struct s5p_cec_dev *cec = dev_get_drvdata(dev);
 
@@ -239,7 +239,7 @@ static int s5p_cec_runtime_suspend(struct device *dev)
 	return 0;
 }
 
-static int s5p_cec_runtime_resume(struct device *dev)
+static int __maybe_unused s5p_cec_runtime_resume(struct device *dev)
 {
 	struct s5p_cec_dev *cec = dev_get_drvdata(dev);
 	int ret;
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 87e6035c9e81..8e7a3d646531 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -392,7 +392,7 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	if (dma_capable(dev, dev_addr, size) &&
 	    !range_straddles_page_boundary(phys, size) &&
 		!xen_arch_need_swiotlb(dev, phys, dev_addr) &&
-		!swiotlb_force) {
+		(swiotlb_force != SWIOTLB_FORCE)) {
 		/* we are not interested in the dma_addr returned by
 		 * xen_dma_map_page, only in the potential cache flushes executed
 		 * by the function. */
@@ -549,7 +549,7 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 		phys_addr_t paddr = sg_phys(sg);
 		dma_addr_t dev_addr = xen_phys_to_bus(paddr);
 
-		if (swiotlb_force ||
+		if (swiotlb_force == SWIOTLB_FORCE ||
 		    xen_arch_need_swiotlb(hwdev, paddr, dev_addr) ||
 		    !dma_capable(hwdev, dev_addr, sg->length) ||
 		    range_straddles_page_boundary(paddr, sg->length)) {
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 16e6ded0b7f2..f3f21105b860 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2507,9 +2507,20 @@ int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
 			if (err < 0)
 				ret = err;
 		} else {
-			ret = wait_event_interruptible(ci->i_cap_wq,
-					try_get_cap_refs(ci, need, want, endoff,
-							 true, &_got, &err));
+			DEFINE_WAIT_FUNC(wait, woken_wake_function);
+			add_wait_queue(&ci->i_cap_wq, &wait);
+
+			while (!try_get_cap_refs(ci, need, want, endoff,
+						 true, &_got, &err)) {
+				if (signal_pending(current)) {
+					ret = -ERESTARTSYS;
+					break;
+				}
+				wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+			}
+
+			remove_wait_queue(&ci->i_cap_wq, &wait);
+
 			if (err == -EAGAIN)
 				continue;
 			if (err < 0)
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index a594c7879cc2..1afa11191000 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1255,7 +1255,8 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 		struct ceph_mds_client *mdsc =
 			ceph_sb_to_client(dir->i_sb)->mdsc;
 		struct ceph_mds_request *req;
-		int op, mask, err;
+		int op, err;
+		u32 mask;
 
 		if (flags & LOOKUP_RCU)
 			return -ECHILD;
@@ -1270,7 +1271,7 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 			mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED;
 			if (ceph_security_xattr_wanted(dir))
 				mask |= CEPH_CAP_XATTR_SHARED;
-			req->r_args.getattr.mask = mask;
+			req->r_args.getattr.mask = cpu_to_le32(mask);
 
 			err = ceph_mdsc_do_request(mdsc, NULL, req);
 			switch (err) {
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index ef4d04647325..12f2252f6c98 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -305,7 +305,8 @@ static int frag_tree_split_cmp(const void *l, const void *r)
 {
 	struct ceph_frag_tree_split *ls = (struct ceph_frag_tree_split*)l;
 	struct ceph_frag_tree_split *rs = (struct ceph_frag_tree_split*)r;
-	return ceph_frag_compare(ls->frag, rs->frag);
+	return ceph_frag_compare(le32_to_cpu(ls->frag),
+				 le32_to_cpu(rs->frag));
 }
 
 static bool is_frag_child(u32 f, struct ceph_inode_frag *frag)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 815acd1a56d4..6a26c7bd1286 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -288,12 +288,13 @@ static int parse_reply_info_extra(void **p, void *end,
 				  struct ceph_mds_reply_info_parsed *info,
 				  u64 features)
 {
-	if (info->head->op == CEPH_MDS_OP_GETFILELOCK)
+	u32 op = le32_to_cpu(info->head->op);
+
+	if (op == CEPH_MDS_OP_GETFILELOCK)
 		return parse_reply_info_filelock(p, end, info, features);
-	else if (info->head->op == CEPH_MDS_OP_READDIR ||
-		 info->head->op == CEPH_MDS_OP_LSSNAP)
+	else if (op == CEPH_MDS_OP_READDIR || op == CEPH_MDS_OP_LSSNAP)
 		return parse_reply_info_dir(p, end, info, features);
-	else if (info->head->op == CEPH_MDS_OP_CREATE)
+	else if (op == CEPH_MDS_OP_CREATE)
 		return parse_reply_info_create(p, end, info, features);
 	else
 		return -EIO;
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 70ea57c7b6bb..4e06a27ed7f8 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -2025,7 +2025,6 @@ static void end_requests(struct fuse_conn *fc, struct list_head *head)
 		struct fuse_req *req;
 		req = list_entry(head->next, struct fuse_req, list);
 		req->out.h.error = -ECONNABORTED;
-		clear_bit(FR_PENDING, &req->flags);
 		clear_bit(FR_SENT, &req->flags);
 		list_del_init(&req->list);
 		request_end(fc, req);
@@ -2103,6 +2102,8 @@ void fuse_abort_conn(struct fuse_conn *fc)
 		spin_lock(&fiq->waitq.lock);
 		fiq->connected = 0;
 		list_splice_init(&fiq->pending, &to_end2);
+		list_for_each_entry(req, &to_end2, list)
+			clear_bit(FR_PENDING, &req->flags);
 		while (forget_pending(fiq))
 			kfree(dequeue_forget(fiq, 1, NULL));
 		wake_up_all_locked(&fiq->waitq);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 096f79997f75..642c57b8de7b 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -68,7 +68,7 @@ static u64 time_to_jiffies(u64 sec, u32 nsec)
 	if (sec || nsec) {
 		struct timespec64 ts = {
 			sec,
-			max_t(u32, nsec, NSEC_PER_SEC - 1)
+			min_t(u32, nsec, NSEC_PER_SEC - 1)
 		};
 
 		return get_jiffies_64() + timespec64_to_jiffies(&ts);
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 595522022aca..c9d48dc78495 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -922,11 +922,10 @@ int simple_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	int error;
 
 	if (type == ACL_TYPE_ACCESS) {
-		error = posix_acl_equiv_mode(acl, &inode->i_mode);
-		if (error < 0)
-			return 0;
-		if (error == 0)
-			acl = NULL;
+		error = posix_acl_update_mode(inode,
+				&inode->i_mode, &acl);
+		if (error)
+			return error;
 	}
 
 	inode->i_ctime = current_time(inode);
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index fa9a20cc60d6..fe5e8d4970ae 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -34,6 +34,11 @@
 #include <linux/slab.h>
 #include "ubifs.h"
 
+static int try_read_node(const struct ubifs_info *c, void *buf, int type,
+			 int len, int lnum, int offs);
+static int fallible_read_node(struct ubifs_info *c, const union ubifs_key *key,
+			      struct ubifs_zbranch *zbr, void *node);
+
 /*
  * Returned codes of 'matches_name()' and 'fallible_matches_name()' functions.
  * @NAME_LESS: name corresponding to the first argument is less than second
@@ -402,7 +407,19 @@ static int tnc_read_node_nm(struct ubifs_info *c, struct ubifs_zbranch *zbr,
 		return 0;
 	}
 
-	err = ubifs_tnc_read_node(c, zbr, node);
+	if (c->replaying) {
+		err = fallible_read_node(c, &zbr->key, zbr, node);
+		/*
+		 * When the node was not found, return -ENOENT, 0 otherwise.
+		 * Negative return codes stay as-is.
+		 */
+		if (err == 0)
+			err = -ENOENT;
+		else if (err == 1)
+			err = 0;
+	} else {
+		err = ubifs_tnc_read_node(c, zbr, node);
+	}
 	if (err)
 		return err;
 
@@ -2766,7 +2783,11 @@ struct ubifs_dent_node *ubifs_tnc_next_ent(struct ubifs_info *c,
 	if (nm->name) {
 		if (err) {
 			/* Handle collisions */
-			err = resolve_collision(c, key, &znode, &n, nm);
+			if (c->replaying)
+				err = fallible_resolve_collision(c, key, &znode, &n,
+							 nm, 0);
+			else
+				err = resolve_collision(c, key, &znode, &n, nm);
 			dbg_tnc("rc returned %d, znode %p, n %d",
 				err, znode, n);
 			if (unlikely(err < 0))
diff --git a/include/dt-bindings/clock/r8a7794-clock.h b/include/dt-bindings/clock/r8a7794-clock.h
index 9d02f5317c7c..88e64846cf37 100644
--- a/include/dt-bindings/clock/r8a7794-clock.h
+++ b/include/dt-bindings/clock/r8a7794-clock.h
@@ -20,8 +20,7 @@
 #define R8A7794_CLK_QSPI		5
 #define R8A7794_CLK_SDH			6
 #define R8A7794_CLK_SD0			7
-#define R8A7794_CLK_Z			8
-#define R8A7794_CLK_RCAN		9
+#define R8A7794_CLK_RCAN		8
 
 /* MSTP0 */
 #define R8A7794_CLK_MSIOF0		0
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 321f9ed552a9..01f71e1d2e94 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -444,6 +444,10 @@ bool __rcu_is_watching(void);
 #error "Unknown RCU implementation specified to kernel configuration"
 #endif
 
+#define RCU_SCHEDULER_INACTIVE	0
+#define RCU_SCHEDULER_INIT	1
+#define RCU_SCHEDULER_RUNNING	2
+
 /*
  * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic
  * initialization and destruction of rcu_head on the stack. rcu_head structures
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index e5d193440374..7440290f64ac 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -66,6 +66,7 @@ struct svc_xprt {
 #define XPT_LISTENER	10		/* listening endpoint */
 #define XPT_CACHE_AUTH	11		/* cache auth info */
 #define XPT_LOCAL	12		/* connection from loopback interface */
+#define XPT_KILL_TEMP   13		/* call xpo_kill_temp_xprt before closing */
 
 	struct svc_serv		*xpt_server;	/* service for transport */
 	atomic_t    	    	xpt_reserved;	/* space on outq that is rsvd */
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 5f81f8a187f2..d2613536fd03 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -9,7 +9,13 @@ struct device;
 struct page;
 struct scatterlist;
 
-extern int swiotlb_force;
+enum swiotlb_force {
+	SWIOTLB_NORMAL,		/* Default - depending on HW DMA mask etc. */
+	SWIOTLB_FORCE,		/* swiotlb=force */
+	SWIOTLB_NO_FORCE,	/* swiotlb=noforce */
+};
+
+extern enum swiotlb_force swiotlb_force;
 
 /*
  * Maximum allowable number of contiguous slabs to map,
diff --git a/include/trace/events/swiotlb.h b/include/trace/events/swiotlb.h
index 7ea4c5e7c448..288c0c54a2b4 100644
--- a/include/trace/events/swiotlb.h
+++ b/include/trace/events/swiotlb.h
@@ -11,16 +11,16 @@ TRACE_EVENT(swiotlb_bounced,
 	TP_PROTO(struct device *dev,
 		 dma_addr_t dev_addr,
 		 size_t size,
-		 int swiotlb_force),
+		 enum swiotlb_force swiotlb_force),
 
 	TP_ARGS(dev, dev_addr, size, swiotlb_force),
 
 	TP_STRUCT__entry(
-		__string(	dev_name,	dev_name(dev)	)
-		__field(	u64,	dma_mask		)
-		__field(	dma_addr_t,	dev_addr	)
-		__field(	size_t,	size			)
-		__field(	int,	swiotlb_force		)
+		__string(	dev_name,	dev_name(dev)		)
+		__field(	u64,	dma_mask			)
+		__field(	dma_addr_t,	dev_addr		)
+		__field(	size_t,	size				)
+		__field(	enum swiotlb_force,	swiotlb_force	)
 	),
 
 	TP_fast_assign(
@@ -37,7 +37,10 @@ TRACE_EVENT(swiotlb_bounced,
 		__entry->dma_mask,
 		(unsigned long long)__entry->dev_addr,
 		__entry->size,
-		__entry->swiotlb_force ? "swiotlb_force" : "" )
+		__print_symbolic(__entry->swiotlb_force,
+			{ SWIOTLB_NORMAL,	"NORMAL" },
+			{ SWIOTLB_FORCE,	"FORCE" },
+			{ SWIOTLB_NO_FORCE,	"NO_FORCE" }))
 );
 
 #endif /*  _TRACE_SWIOTLB_H */
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 80adef7d4c3d..0d6ff3e471be 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -136,6 +136,7 @@ int rcu_jiffies_till_stall_check(void);
 #define TPS(x)  tracepoint_string(x)
 
 void rcu_early_boot_tests(void);
+void rcu_test_sync_prims(void);
 
 /*
  * This function really isn't for public consumption, but RCU is special in
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 1898559e6b60..b23a4d076f3d 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -185,9 +185,6 @@ static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused
  * benefits of doing might_sleep() to reduce latency.)
  *
  * Cool, huh?  (Due to Josh Triplett.)
- *
- * But we want to make this a static inline later.  The cond_resched()
- * currently makes this problematic.
  */
 void synchronize_sched(void)
 {
@@ -195,7 +192,6 @@ void synchronize_sched(void)
 			 lock_is_held(&rcu_lock_map) ||
 			 lock_is_held(&rcu_sched_lock_map),
 			 "Illegal synchronize_sched() in RCU read-side critical section");
-	cond_resched();
 }
 EXPORT_SYMBOL_GPL(synchronize_sched);
 
diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h
index 196f0302e2f4..c64b827ecbca 100644
--- a/kernel/rcu/tiny_plugin.h
+++ b/kernel/rcu/tiny_plugin.h
@@ -60,12 +60,17 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active);
 
 /*
  * During boot, we forgive RCU lockdep issues.  After this function is
- * invoked, we start taking RCU lockdep issues seriously.
+ * invoked, we start taking RCU lockdep issues seriously.  Note that unlike
+ * Tree RCU, Tiny RCU transitions directly from RCU_SCHEDULER_INACTIVE
+ * to RCU_SCHEDULER_RUNNING, skipping the RCU_SCHEDULER_INIT stage.
+ * The reason for this is that Tiny RCU does not need kthreads, so does
+ * not have to care about the fact that the scheduler is half-initialized
+ * at a certain phase of the boot process.
  */
 void __init rcu_scheduler_starting(void)
 {
 	WARN_ON(nr_context_switches() > 0);
-	rcu_scheduler_active = 1;
+	rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
 }
 
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 69a5611a7e7c..10f62c6f48e7 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -127,13 +127,16 @@ int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
 int sysctl_panic_on_rcu_stall __read_mostly;
 
 /*
- * The rcu_scheduler_active variable transitions from zero to one just
- * before the first task is spawned.  So when this variable is zero, RCU
- * can assume that there is but one task, allowing RCU to (for example)
+ * The rcu_scheduler_active variable is initialized to the value
+ * RCU_SCHEDULER_INACTIVE and transitions RCU_SCHEDULER_INIT just before the
+ * first task is spawned.  So when this variable is RCU_SCHEDULER_INACTIVE,
+ * RCU can assume that there is but one task, allowing RCU to (for example)
  * optimize synchronize_rcu() to a simple barrier().  When this variable
- * is one, RCU must actually do all the hard work required to detect real
- * grace periods.  This variable is also used to suppress boot-time false
- * positives from lockdep-RCU error checking.
+ * is RCU_SCHEDULER_INIT, RCU must actually do all the hard work required
+ * to detect real grace periods.  This variable is also used to suppress
+ * boot-time false positives from lockdep-RCU error checking.  Finally, it
+ * transitions from RCU_SCHEDULER_INIT to RCU_SCHEDULER_RUNNING after RCU
+ * is fully initialized, including all of its kthreads having been spawned.
  */
 int rcu_scheduler_active __read_mostly;
 EXPORT_SYMBOL_GPL(rcu_scheduler_active);
@@ -3985,18 +3988,22 @@ static int __init rcu_spawn_gp_kthread(void)
 early_initcall(rcu_spawn_gp_kthread);
 
 /*
- * This function is invoked towards the end of the scheduler's initialization
- * process.  Before this is called, the idle task might contain
- * RCU read-side critical sections (during which time, this idle
- * task is booting the system).  After this function is called, the
- * idle tasks are prohibited from containing RCU read-side critical
- * sections.  This function also enables RCU lockdep checking.
+ * This function is invoked towards the end of the scheduler's
+ * initialization process.  Before this is called, the idle task might
+ * contain synchronous grace-period primitives (during which time, this idle
+ * task is booting the system, and such primitives are no-ops).  After this
+ * function is called, any synchronous grace-period primitives are run as
+ * expedited, with the requesting task driving the grace period forward.
+ * A later core_initcall() rcu_exp_runtime_mode() will switch to full
+ * runtime RCU functionality.
  */
 void rcu_scheduler_starting(void)
 {
 	WARN_ON(num_online_cpus() != 1);
 	WARN_ON(nr_context_switches() > 0);
-	rcu_scheduler_active = 1;
+	rcu_test_sync_prims();
+	rcu_scheduler_active = RCU_SCHEDULER_INIT;
+	rcu_test_sync_prims();
 }
 
 /*
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 24343eb87b58..78eba4120d46 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -522,18 +522,28 @@ struct rcu_exp_work {
 };
 
 /*
+ * Common code to drive an expedited grace period forward, used by
+ * workqueues and mid-boot-time tasks.
+ */
+static void rcu_exp_sel_wait_wake(struct rcu_state *rsp,
+				  smp_call_func_t func, unsigned long s)
+{
+	/* Initialize the rcu_node tree in preparation for the wait. */
+	sync_rcu_exp_select_cpus(rsp, func);
+
+	/* Wait and clean up, including waking everyone. */
+	rcu_exp_wait_wake(rsp, s);
+}
+
+/*
  * Work-queue handler to drive an expedited grace period forward.
  */
 static void wait_rcu_exp_gp(struct work_struct *wp)
 {
 	struct rcu_exp_work *rewp;
 
-	/* Initialize the rcu_node tree in preparation for the wait. */
 	rewp = container_of(wp, struct rcu_exp_work, rew_work);
-	sync_rcu_exp_select_cpus(rewp->rew_rsp, rewp->rew_func);
-
-	/* Wait and clean up, including waking everyone. */
-	rcu_exp_wait_wake(rewp->rew_rsp, rewp->rew_s);
+	rcu_exp_sel_wait_wake(rewp->rew_rsp, rewp->rew_func, rewp->rew_s);
 }
 
 /*
@@ -559,12 +569,18 @@ static void _synchronize_rcu_expedited(struct rcu_state *rsp,
 	if (exp_funnel_lock(rsp, s))
 		return;  /* Someone else did our work for us. */
 
-	/* Marshall arguments and schedule the expedited grace period. */
-	rew.rew_func = func;
-	rew.rew_rsp = rsp;
-	rew.rew_s = s;
-	INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp);
-	schedule_work(&rew.rew_work);
+	/* Ensure that load happens before action based on it. */
+	if (unlikely(rcu_scheduler_active == RCU_SCHEDULER_INIT)) {
+		/* Direct call during scheduler init and early_initcalls(). */
+		rcu_exp_sel_wait_wake(rsp, func, s);
+	} else {
+		/* Marshall arguments & schedule the expedited grace period. */
+		rew.rew_func = func;
+		rew.rew_rsp = rsp;
+		rew.rew_s = s;
+		INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp);
+		schedule_work(&rew.rew_work);
+	}
 
 	/* Wait for expedited grace period to complete. */
 	rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
@@ -666,6 +682,8 @@ void synchronize_rcu_expedited(void)
 {
 	struct rcu_state *rsp = rcu_state_p;
 
+	if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
+		return;
 	_synchronize_rcu_expedited(rsp, sync_rcu_exp_handler);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
@@ -683,3 +701,15 @@ void synchronize_rcu_expedited(void)
 EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
 
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
+
+/*
+ * Switch to run-time mode once Tree RCU has fully initialized.
+ */
+static int __init rcu_exp_runtime_mode(void)
+{
+	rcu_test_sync_prims();
+	rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
+	rcu_test_sync_prims();
+	return 0;
+}
+core_initcall(rcu_exp_runtime_mode);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 85c5a883c6e3..56583e764ebf 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -670,7 +670,7 @@ void synchronize_rcu(void)
 			 lock_is_held(&rcu_lock_map) ||
 			 lock_is_held(&rcu_sched_lock_map),
 			 "Illegal synchronize_rcu() in RCU read-side critical section");
-	if (!rcu_scheduler_active)
+	if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
 		return;
 	if (rcu_gp_is_expedited())
 		synchronize_rcu_expedited();
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index f19271dce0a9..4f6db7e6a117 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -121,11 +121,14 @@ EXPORT_SYMBOL(rcu_read_lock_sched_held);
  * Should expedited grace-period primitives always fall back to their
  * non-expedited counterparts?  Intended for use within RCU.  Note
  * that if the user specifies both rcu_expedited and rcu_normal, then
- * rcu_normal wins.
+ * rcu_normal wins.  (Except during the time period during boot from
+ * when the first task is spawned until the rcu_exp_runtime_mode()
+ * core_initcall() is invoked, at which point everything is expedited.)
  */
 bool rcu_gp_is_normal(void)
 {
-	return READ_ONCE(rcu_normal);
+	return READ_ONCE(rcu_normal) &&
+	       rcu_scheduler_active != RCU_SCHEDULER_INIT;
 }
 EXPORT_SYMBOL_GPL(rcu_gp_is_normal);
 
@@ -135,13 +138,14 @@ static atomic_t rcu_expedited_nesting =
 /*
  * Should normal grace-period primitives be expedited?  Intended for
  * use within RCU.  Note that this function takes the rcu_expedited
- * sysfs/boot variable into account as well as the rcu_expedite_gp()
- * nesting.  So looping on rcu_unexpedite_gp() until rcu_gp_is_expedited()
- * returns false is a -really- bad idea.
+ * sysfs/boot variable and rcu_scheduler_active into account as well
+ * as the rcu_expedite_gp() nesting.  So looping on rcu_unexpedite_gp()
+ * until rcu_gp_is_expedited() returns false is a -really- bad idea.
  */
 bool rcu_gp_is_expedited(void)
 {
-	return rcu_expedited || atomic_read(&rcu_expedited_nesting);
+	return rcu_expedited || atomic_read(&rcu_expedited_nesting) ||
+	       rcu_scheduler_active == RCU_SCHEDULER_INIT;
 }
 EXPORT_SYMBOL_GPL(rcu_gp_is_expedited);
 
@@ -257,7 +261,7 @@ EXPORT_SYMBOL_GPL(rcu_callback_map);
 
 int notrace debug_lockdep_rcu_enabled(void)
 {
-	return rcu_scheduler_active && debug_locks &&
+	return rcu_scheduler_active != RCU_SCHEDULER_INACTIVE && debug_locks &&
 	       current->lockdep_recursion == 0;
 }
 EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);
@@ -591,7 +595,7 @@ EXPORT_SYMBOL_GPL(call_rcu_tasks);
 void synchronize_rcu_tasks(void)
 {
 	/* Complain if the scheduler has not started.  */
-	RCU_LOCKDEP_WARN(!rcu_scheduler_active,
+	RCU_LOCKDEP_WARN(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
 			 "synchronize_rcu_tasks called too soon");
 
 	/* Wait for the grace period. */
@@ -813,6 +817,23 @@ static void rcu_spawn_tasks_kthread(void)
 
 #endif /* #ifdef CONFIG_TASKS_RCU */
 
+/*
+ * Test each non-SRCU synchronous grace-period wait API.  This is
+ * useful just after a change in mode for these primitives, and
+ * during early boot.
+ */
+void rcu_test_sync_prims(void)
+{
+	if (!IS_ENABLED(CONFIG_PROVE_RCU))
+		return;
+	synchronize_rcu();
+	synchronize_rcu_bh();
+	synchronize_sched();
+	synchronize_rcu_expedited();
+	synchronize_rcu_bh_expedited();
+	synchronize_sched_expedited();
+}
+
 #ifdef CONFIG_PROVE_RCU
 
 /*
@@ -865,6 +886,7 @@ void rcu_early_boot_tests(void)
 		early_boot_test_call_rcu_bh();
 	if (rcu_self_test_sched)
 		early_boot_test_call_rcu_sched();
+	rcu_test_sync_prims();
 }
 
 static int rcu_verify_early_boot_tests(void)
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 22e13a0e19d7..ad1d2962d129 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -53,7 +53,7 @@
  */
 #define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
 
-int swiotlb_force;
+enum swiotlb_force swiotlb_force;
 
 /*
  * Used to do a quick range check in swiotlb_tbl_unmap_single and
@@ -106,8 +106,12 @@ setup_io_tlb_npages(char *str)
 	}
 	if (*str == ',')
 		++str;
-	if (!strcmp(str, "force"))
-		swiotlb_force = 1;
+	if (!strcmp(str, "force")) {
+		swiotlb_force = SWIOTLB_FORCE;
+	} else if (!strcmp(str, "noforce")) {
+		swiotlb_force = SWIOTLB_NO_FORCE;
+		io_tlb_nslabs = 1;
+	}
 
 	return 0;
 }
@@ -541,8 +545,15 @@ static phys_addr_t
 map_single(struct device *hwdev, phys_addr_t phys, size_t size,
 	   enum dma_data_direction dir)
 {
-	dma_addr_t start_dma_addr = phys_to_dma(hwdev, io_tlb_start);
+	dma_addr_t start_dma_addr;
+
+	if (swiotlb_force == SWIOTLB_NO_FORCE) {
+		dev_warn_ratelimited(hwdev, "Cannot do DMA to address %pa\n",
+				     &phys);
+		return SWIOTLB_MAP_ERROR;
+	}
 
+	start_dma_addr = phys_to_dma(hwdev, io_tlb_start);
 	return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size, dir);
 }
 
@@ -707,6 +718,9 @@ static void
 swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir,
 	     int do_panic)
 {
+	if (swiotlb_force == SWIOTLB_NO_FORCE)
+		return;
+
 	/*
 	 * Ran out of IOMMU space for this operation. This is very bad.
 	 * Unfortunately the drivers cannot handle this operation properly.
@@ -749,7 +763,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 	 * we can safely return the device addr and not worry about bounce
 	 * buffering it.
 	 */
-	if (dma_capable(dev, dev_addr, size) && !swiotlb_force)
+	if (dma_capable(dev, dev_addr, size) && swiotlb_force != SWIOTLB_FORCE)
 		return dev_addr;
 
 	trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
@@ -888,7 +902,7 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
 		phys_addr_t paddr = sg_phys(sg);
 		dma_addr_t dev_addr = phys_to_dma(hwdev, paddr);
 
-		if (swiotlb_force ||
+		if (swiotlb_force == SWIOTLB_FORCE ||
 		    !dma_capable(hwdev, dev_addr, sg->length)) {
 			phys_addr_t map = map_single(hwdev, sg_phys(sg),
 						     sg->length, dir);
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index a0905f04bd13..b216131915e7 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -39,56 +39,58 @@ static int ceph_x_should_authenticate(struct ceph_auth_client *ac)
 	return need != 0;
 }
 
+static int ceph_x_encrypt_offset(void)
+{
+	return sizeof(u32) + sizeof(struct ceph_x_encrypt_header);
+}
+
 static int ceph_x_encrypt_buflen(int ilen)
 {
-	return sizeof(struct ceph_x_encrypt_header) + ilen + 16 +
-		sizeof(u32);
+	return ceph_x_encrypt_offset() + ilen + 16;
 }
 
-static int ceph_x_encrypt(struct ceph_crypto_key *secret,
-			  void *ibuf, int ilen, void *obuf, size_t olen)
+static int ceph_x_encrypt(struct ceph_crypto_key *secret, void *buf,
+			  int buf_len, int plaintext_len)
 {
-	struct ceph_x_encrypt_header head = {
-		.struct_v = 1,
-		.magic = cpu_to_le64(CEPHX_ENC_MAGIC)
-	};
-	size_t len = olen - sizeof(u32);
+	struct ceph_x_encrypt_header *hdr = buf + sizeof(u32);
+	int ciphertext_len;
 	int ret;
 
-	ret = ceph_encrypt2(secret, obuf + sizeof(u32), &len,
-			    &head, sizeof(head), ibuf, ilen);
+	hdr->struct_v = 1;
+	hdr->magic = cpu_to_le64(CEPHX_ENC_MAGIC);
+
+	ret = ceph_crypt(secret, true, buf + sizeof(u32), buf_len - sizeof(u32),
+			 plaintext_len + sizeof(struct ceph_x_encrypt_header),
+			 &ciphertext_len);
 	if (ret)
 		return ret;
-	ceph_encode_32(&obuf, len);
-	return len + sizeof(u32);
+
+	ceph_encode_32(&buf, ciphertext_len);
+	return sizeof(u32) + ciphertext_len;
 }
 
-static int ceph_x_decrypt(struct ceph_crypto_key *secret,
-			  void **p, void *end, void **obuf, size_t olen)
+static int ceph_x_decrypt(struct ceph_crypto_key *secret, void **p, void *end)
 {
-	struct ceph_x_encrypt_header head;
-	size_t head_len = sizeof(head);
-	int len, ret;
-
-	len = ceph_decode_32(p);
-	if (*p + len > end)
-		return -EINVAL;
+	struct ceph_x_encrypt_header *hdr = *p + sizeof(u32);
+	int ciphertext_len, plaintext_len;
+	int ret;
 
-	dout("ceph_x_decrypt len %d\n", len);
-	if (*obuf == NULL) {
-		*obuf = kmalloc(len, GFP_NOFS);
-		if (!*obuf)
-			return -ENOMEM;
-		olen = len;
-	}
+	ceph_decode_32_safe(p, end, ciphertext_len, e_inval);
+	ceph_decode_need(p, end, ciphertext_len, e_inval);
 
-	ret = ceph_decrypt2(secret, &head, &head_len, *obuf, &olen, *p, len);
+	ret = ceph_crypt(secret, false, *p, end - *p, ciphertext_len,
+			 &plaintext_len);
 	if (ret)
 		return ret;
-	if (head.struct_v != 1 || le64_to_cpu(head.magic) != CEPHX_ENC_MAGIC)
+
+	if (hdr->struct_v != 1 || le64_to_cpu(hdr->magic) != CEPHX_ENC_MAGIC)
 		return -EPERM;
-	*p += len;
-	return olen;
+
+	*p += ciphertext_len;
+	return plaintext_len - sizeof(struct ceph_x_encrypt_header);
+
+e_inval:
+	return -EINVAL;
 }
 
 /*
@@ -143,13 +145,10 @@ static int process_one_ticket(struct ceph_auth_client *ac,
 	int type;
 	u8 tkt_struct_v, blob_struct_v;
 	struct ceph_x_ticket_handler *th;
-	void *dbuf = NULL;
 	void *dp, *dend;
 	int dlen;
 	char is_enc;
 	struct timespec validity;
-	struct ceph_crypto_key old_key;
-	void *ticket_buf = NULL;
 	void *tp, *tpend;
 	void **ptp;
 	struct ceph_crypto_key new_session_key;
@@ -174,20 +173,17 @@ static int process_one_ticket(struct ceph_auth_client *ac,
 	}
 
 	/* blob for me */
-	dlen = ceph_x_decrypt(secret, p, end, &dbuf, 0);
-	if (dlen <= 0) {
-		ret = dlen;
+	dp = *p + ceph_x_encrypt_offset();
+	ret = ceph_x_decrypt(secret, p, end);
+	if (ret < 0)
 		goto out;
-	}
-	dout(" decrypted %d bytes\n", dlen);
-	dp = dbuf;
-	dend = dp + dlen;
+	dout(" decrypted %d bytes\n", ret);
+	dend = dp + ret;
 
 	tkt_struct_v = ceph_decode_8(&dp);
 	if (tkt_struct_v != 1)
 		goto bad;
 
-	memcpy(&old_key, &th->session_key, sizeof(old_key));
 	ret = ceph_crypto_key_decode(&new_session_key, &dp, dend);
 	if (ret)
 		goto out;
@@ -203,15 +199,13 @@ static int process_one_ticket(struct ceph_auth_client *ac,
 	ceph_decode_8_safe(p, end, is_enc, bad);
 	if (is_enc) {
 		/* encrypted */
-		dout(" encrypted ticket\n");
-		dlen = ceph_x_decrypt(&old_key, p, end, &ticket_buf, 0);
-		if (dlen < 0) {
-			ret = dlen;
+		tp = *p + ceph_x_encrypt_offset();
+		ret = ceph_x_decrypt(&th->session_key, p, end);
+		if (ret < 0)
 			goto out;
-		}
-		tp = ticket_buf;
+		dout(" encrypted ticket, decrypted %d bytes\n", ret);
 		ptp = &tp;
-		tpend = *ptp + dlen;
+		tpend = tp + ret;
 	} else {
 		/* unencrypted */
 		ptp = p;
@@ -242,8 +236,6 @@ static int process_one_ticket(struct ceph_auth_client *ac,
 	xi->have_keys |= th->service;
 
 out:
-	kfree(ticket_buf);
-	kfree(dbuf);
 	return ret;
 
 bad:
@@ -294,7 +286,7 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
 {
 	int maxlen;
 	struct ceph_x_authorize_a *msg_a;
-	struct ceph_x_authorize_b msg_b;
+	struct ceph_x_authorize_b *msg_b;
 	void *p, *end;
 	int ret;
 	int ticket_blob_len =
@@ -308,8 +300,8 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
 	if (ret)
 		goto out_au;
 
-	maxlen = sizeof(*msg_a) + sizeof(msg_b) +
-		ceph_x_encrypt_buflen(ticket_blob_len);
+	maxlen = sizeof(*msg_a) + ticket_blob_len +
+		ceph_x_encrypt_buflen(sizeof(*msg_b));
 	dout("  need len %d\n", maxlen);
 	if (au->buf && au->buf->alloc_len < maxlen) {
 		ceph_buffer_put(au->buf);
@@ -343,18 +335,19 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
 	p += ticket_blob_len;
 	end = au->buf->vec.iov_base + au->buf->vec.iov_len;
 
+	msg_b = p + ceph_x_encrypt_offset();
+	msg_b->struct_v = 1;
 	get_random_bytes(&au->nonce, sizeof(au->nonce));
-	msg_b.struct_v = 1;
-	msg_b.nonce = cpu_to_le64(au->nonce);
-	ret = ceph_x_encrypt(&au->session_key, &msg_b, sizeof(msg_b),
-			     p, end - p);
+	msg_b->nonce = cpu_to_le64(au->nonce);
+	ret = ceph_x_encrypt(&au->session_key, p, end - p, sizeof(*msg_b));
 	if (ret < 0)
 		goto out_au;
+
 	p += ret;
+	WARN_ON(p > end);
 	au->buf->vec.iov_len = p - au->buf->vec.iov_base;
 	dout(" built authorizer nonce %llx len %d\n", au->nonce,
 	     (int)au->buf->vec.iov_len);
-	BUG_ON(au->buf->vec.iov_len > maxlen);
 	return 0;
 
 out_au:
@@ -452,8 +445,9 @@ static int ceph_x_build_request(struct ceph_auth_client *ac,
 	if (need & CEPH_ENTITY_TYPE_AUTH) {
 		struct ceph_x_authenticate *auth = (void *)(head + 1);
 		void *p = auth + 1;
-		struct ceph_x_challenge_blob tmp;
-		char tmp_enc[40];
+		void *enc_buf = xi->auth_authorizer.enc_buf;
+		struct ceph_x_challenge_blob *blob = enc_buf +
+							ceph_x_encrypt_offset();
 		u64 *u;
 
 		if (p > end)
@@ -464,16 +458,16 @@ static int ceph_x_build_request(struct ceph_auth_client *ac,
 
 		/* encrypt and hash */
 		get_random_bytes(&auth->client_challenge, sizeof(u64));
-		tmp.client_challenge = auth->client_challenge;
-		tmp.server_challenge = cpu_to_le64(xi->server_challenge);
-		ret = ceph_x_encrypt(&xi->secret, &tmp, sizeof(tmp),
-				     tmp_enc, sizeof(tmp_enc));
+		blob->client_challenge = auth->client_challenge;
+		blob->server_challenge = cpu_to_le64(xi->server_challenge);
+		ret = ceph_x_encrypt(&xi->secret, enc_buf, CEPHX_AU_ENC_BUF_LEN,
+				     sizeof(*blob));
 		if (ret < 0)
 			return ret;
 
 		auth->struct_v = 1;
 		auth->key = 0;
-		for (u = (u64 *)tmp_enc; u + 1 <= (u64 *)(tmp_enc + ret); u++)
+		for (u = (u64 *)enc_buf; u + 1 <= (u64 *)(enc_buf + ret); u++)
 			auth->key ^= *(__le64 *)u;
 		dout(" server_challenge %llx client_challenge %llx key %llx\n",
 		     xi->server_challenge, le64_to_cpu(auth->client_challenge),
@@ -600,8 +594,8 @@ static int ceph_x_create_authorizer(
 	auth->authorizer = (struct ceph_authorizer *) au;
 	auth->authorizer_buf = au->buf->vec.iov_base;
 	auth->authorizer_buf_len = au->buf->vec.iov_len;
-	auth->authorizer_reply_buf = au->reply_buf;
-	auth->authorizer_reply_buf_len = sizeof (au->reply_buf);
+	auth->authorizer_reply_buf = au->enc_buf;
+	auth->authorizer_reply_buf_len = CEPHX_AU_ENC_BUF_LEN;
 	auth->sign_message = ac->ops->sign_message;
 	auth->check_message_signature = ac->ops->check_message_signature;
 
@@ -632,24 +626,22 @@ static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac,
 					  struct ceph_authorizer *a, size_t len)
 {
 	struct ceph_x_authorizer *au = (void *)a;
-	int ret = 0;
-	struct ceph_x_authorize_reply reply;
-	void *preply = &reply;
-	void *p = au->reply_buf;
-	void *end = p + sizeof(au->reply_buf);
+	void *p = au->enc_buf;
+	struct ceph_x_authorize_reply *reply = p + ceph_x_encrypt_offset();
+	int ret;
 
-	ret = ceph_x_decrypt(&au->session_key, &p, end, &preply, sizeof(reply));
+	ret = ceph_x_decrypt(&au->session_key, &p, p + CEPHX_AU_ENC_BUF_LEN);
 	if (ret < 0)
 		return ret;
-	if (ret != sizeof(reply))
+	if (ret != sizeof(*reply))
 		return -EPERM;
 
-	if (au->nonce + 1 != le64_to_cpu(reply.nonce_plus_one))
+	if (au->nonce + 1 != le64_to_cpu(reply->nonce_plus_one))
 		ret = -EPERM;
 	else
 		ret = 0;
 	dout("verify_authorizer_reply nonce %llx got %llx ret %d\n",
-	     au->nonce, le64_to_cpu(reply.nonce_plus_one), ret);
+	     au->nonce, le64_to_cpu(reply->nonce_plus_one), ret);
 	return ret;
 }
 
@@ -704,35 +696,48 @@ static void ceph_x_invalidate_authorizer(struct ceph_auth_client *ac,
 	invalidate_ticket(ac, CEPH_ENTITY_TYPE_AUTH);
 }
 
-static int calcu_signature(struct ceph_x_authorizer *au,
-			   struct ceph_msg *msg, __le64 *sig)
+static int calc_signature(struct ceph_x_authorizer *au, struct ceph_msg *msg,
+			  __le64 *psig)
 {
+	void *enc_buf = au->enc_buf;
+	struct {
+		__le32 len;
+		__le32 header_crc;
+		__le32 front_crc;
+		__le32 middle_crc;
+		__le32 data_crc;
+	} __packed *sigblock = enc_buf + ceph_x_encrypt_offset();
 	int ret;
-	char tmp_enc[40];
-	__le32 tmp[5] = {
-		cpu_to_le32(16), msg->hdr.crc, msg->footer.front_crc,
-		msg->footer.middle_crc, msg->footer.data_crc,
-	};
-	ret = ceph_x_encrypt(&au->session_key, &tmp, sizeof(tmp),
-			     tmp_enc, sizeof(tmp_enc));
+
+	sigblock->len = cpu_to_le32(4*sizeof(u32));
+	sigblock->header_crc = msg->hdr.crc;
+	sigblock->front_crc = msg->footer.front_crc;
+	sigblock->middle_crc = msg->footer.middle_crc;
+	sigblock->data_crc =  msg->footer.data_crc;
+	ret = ceph_x_encrypt(&au->session_key, enc_buf, CEPHX_AU_ENC_BUF_LEN,
+			     sizeof(*sigblock));
 	if (ret < 0)
 		return ret;
-	*sig = *(__le64*)(tmp_enc + 4);
+
+	*psig = *(__le64 *)(enc_buf + sizeof(u32));
 	return 0;
 }
 
 static int ceph_x_sign_message(struct ceph_auth_handshake *auth,
 			       struct ceph_msg *msg)
 {
+	__le64 sig;
 	int ret;
 
 	if (ceph_test_opt(from_msgr(msg->con->msgr), NOMSGSIGN))
 		return 0;
 
-	ret = calcu_signature((struct ceph_x_authorizer *)auth->authorizer,
-			      msg, &msg->footer.sig);
-	if (ret < 0)
+	ret = calc_signature((struct ceph_x_authorizer *)auth->authorizer,
+			     msg, &sig);
+	if (ret)
 		return ret;
+
+	msg->footer.sig = sig;
 	msg->footer.flags |= CEPH_MSG_FOOTER_SIGNED;
 	return 0;
 }
@@ -746,9 +751,9 @@ static int ceph_x_check_message_signature(struct ceph_auth_handshake *auth,
 	if (ceph_test_opt(from_msgr(msg->con->msgr), NOMSGSIGN))
 		return 0;
 
-	ret = calcu_signature((struct ceph_x_authorizer *)auth->authorizer,
-			      msg, &sig_check);
-	if (ret < 0)
+	ret = calc_signature((struct ceph_x_authorizer *)auth->authorizer,
+			     msg, &sig_check);
+	if (ret)
 		return ret;
 	if (sig_check == msg->footer.sig)
 		return 0;
diff --git a/net/ceph/auth_x.h b/net/ceph/auth_x.h
index 21a5af904bae..48e9ad41bd2a 100644
--- a/net/ceph/auth_x.h
+++ b/net/ceph/auth_x.h
@@ -24,6 +24,7 @@ struct ceph_x_ticket_handler {
 	unsigned long renew_after, expires;
 };
 
+#define CEPHX_AU_ENC_BUF_LEN	128  /* big enough for encrypted blob */
 
 struct ceph_x_authorizer {
 	struct ceph_authorizer base;
@@ -32,7 +33,7 @@ struct ceph_x_authorizer {
 	unsigned int service;
 	u64 nonce;
 	u64 secret_id;
-	char reply_buf[128];  /* big enough for encrypted blob */
+	char enc_buf[CEPHX_AU_ENC_BUF_LEN] __aligned(8);
 };
 
 struct ceph_x_info {
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index db2847ac5f12..292e33bd916e 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -13,14 +13,60 @@
 #include <linux/ceph/decode.h>
 #include "crypto.h"
 
+/*
+ * Set ->key and ->tfm.  The rest of the key should be filled in before
+ * this function is called.
+ */
+static int set_secret(struct ceph_crypto_key *key, void *buf)
+{
+	unsigned int noio_flag;
+	int ret;
+
+	key->key = NULL;
+	key->tfm = NULL;
+
+	switch (key->type) {
+	case CEPH_CRYPTO_NONE:
+		return 0; /* nothing to do */
+	case CEPH_CRYPTO_AES:
+		break;
+	default:
+		return -ENOTSUPP;
+	}
+
+	WARN_ON(!key->len);
+	key->key = kmemdup(buf, key->len, GFP_NOIO);
+	if (!key->key) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	/* crypto_alloc_skcipher() allocates with GFP_KERNEL */
+	noio_flag = memalloc_noio_save();
+	key->tfm = crypto_alloc_skcipher("cbc(aes)", 0, CRYPTO_ALG_ASYNC);
+	memalloc_noio_restore(noio_flag);
+	if (IS_ERR(key->tfm)) {
+		ret = PTR_ERR(key->tfm);
+		key->tfm = NULL;
+		goto fail;
+	}
+
+	ret = crypto_skcipher_setkey(key->tfm, key->key, key->len);
+	if (ret)
+		goto fail;
+
+	return 0;
+
+fail:
+	ceph_crypto_key_destroy(key);
+	return ret;
+}
+
 int ceph_crypto_key_clone(struct ceph_crypto_key *dst,
 			  const struct ceph_crypto_key *src)
 {
 	memcpy(dst, src, sizeof(struct ceph_crypto_key));
-	dst->key = kmemdup(src->key, src->len, GFP_NOFS);
-	if (!dst->key)
-		return -ENOMEM;
-	return 0;
+	return set_secret(dst, src->key);
 }
 
 int ceph_crypto_key_encode(struct ceph_crypto_key *key, void **p, void *end)
@@ -37,16 +83,16 @@ int ceph_crypto_key_encode(struct ceph_crypto_key *key, void **p, void *end)
 
 int ceph_crypto_key_decode(struct ceph_crypto_key *key, void **p, void *end)
 {
+	int ret;
+
 	ceph_decode_need(p, end, 2*sizeof(u16) + sizeof(key->created), bad);
 	key->type = ceph_decode_16(p);
 	ceph_decode_copy(p, &key->created, sizeof(key->created));
 	key->len = ceph_decode_16(p);
 	ceph_decode_need(p, end, key->len, bad);
-	key->key = kmalloc(key->len, GFP_NOFS);
-	if (!key->key)
-		return -ENOMEM;
-	ceph_decode_copy(p, key->key, key->len);
-	return 0;
+	ret = set_secret(key, *p);
+	*p += key->len;
+	return ret;
 
 bad:
 	dout("failed to decode crypto key\n");
@@ -80,9 +126,14 @@ int ceph_crypto_key_unarmor(struct ceph_crypto_key *key, const char *inkey)
 	return 0;
 }
 
-static struct crypto_skcipher *ceph_crypto_alloc_cipher(void)
+void ceph_crypto_key_destroy(struct ceph_crypto_key *key)
 {
-	return crypto_alloc_skcipher("cbc(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (key) {
+		kfree(key->key);
+		key->key = NULL;
+		crypto_free_skcipher(key->tfm);
+		key->tfm = NULL;
+	}
 }
 
 static const u8 *aes_iv = (u8 *)CEPH_AES_IV;
@@ -157,372 +208,82 @@ static void teardown_sgtable(struct sg_table *sgt)
 		sg_free_table(sgt);
 }
 
-static int ceph_aes_encrypt(const void *key, int key_len,
-			    void *dst, size_t *dst_len,
-			    const void *src, size_t src_len)
-{
-	struct scatterlist sg_in[2], prealloc_sg;
-	struct sg_table sg_out;
-	struct crypto_skcipher *tfm = ceph_crypto_alloc_cipher();
-	SKCIPHER_REQUEST_ON_STACK(req, tfm);
-	int ret;
-	char iv[AES_BLOCK_SIZE];
-	size_t zero_padding = (0x10 - (src_len & 0x0f));
-	char pad[16];
-
-	if (IS_ERR(tfm))
-		return PTR_ERR(tfm);
-
-	memset(pad, zero_padding, zero_padding);
-
-	*dst_len = src_len + zero_padding;
-
-	sg_init_table(sg_in, 2);
-	sg_set_buf(&sg_in[0], src, src_len);
-	sg_set_buf(&sg_in[1], pad, zero_padding);
-	ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len);
-	if (ret)
-		goto out_tfm;
-
-	crypto_skcipher_setkey((void *)tfm, key, key_len);
-	memcpy(iv, aes_iv, AES_BLOCK_SIZE);
-
-	skcipher_request_set_tfm(req, tfm);
-	skcipher_request_set_callback(req, 0, NULL, NULL);
-	skcipher_request_set_crypt(req, sg_in, sg_out.sgl,
-				   src_len + zero_padding, iv);
-
-	/*
-	print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1,
-		       key, key_len, 1);
-	print_hex_dump(KERN_ERR, "enc src: ", DUMP_PREFIX_NONE, 16, 1,
-			src, src_len, 1);
-	print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1,
-			pad, zero_padding, 1);
-	*/
-	ret = crypto_skcipher_encrypt(req);
-	skcipher_request_zero(req);
-	if (ret < 0) {
-		pr_err("ceph_aes_crypt failed %d\n", ret);
-		goto out_sg;
-	}
-	/*
-	print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1,
-		       dst, *dst_len, 1);
-	*/
-
-out_sg:
-	teardown_sgtable(&sg_out);
-out_tfm:
-	crypto_free_skcipher(tfm);
-	return ret;
-}
-
-static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
-			     size_t *dst_len,
-			     const void *src1, size_t src1_len,
-			     const void *src2, size_t src2_len)
-{
-	struct scatterlist sg_in[3], prealloc_sg;
-	struct sg_table sg_out;
-	struct crypto_skcipher *tfm = ceph_crypto_alloc_cipher();
-	SKCIPHER_REQUEST_ON_STACK(req, tfm);
-	int ret;
-	char iv[AES_BLOCK_SIZE];
-	size_t zero_padding = (0x10 - ((src1_len + src2_len) & 0x0f));
-	char pad[16];
-
-	if (IS_ERR(tfm))
-		return PTR_ERR(tfm);
-
-	memset(pad, zero_padding, zero_padding);
-
-	*dst_len = src1_len + src2_len + zero_padding;
-
-	sg_init_table(sg_in, 3);
-	sg_set_buf(&sg_in[0], src1, src1_len);
-	sg_set_buf(&sg_in[1], src2, src2_len);
-	sg_set_buf(&sg_in[2], pad, zero_padding);
-	ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len);
-	if (ret)
-		goto out_tfm;
-
-	crypto_skcipher_setkey((void *)tfm, key, key_len);
-	memcpy(iv, aes_iv, AES_BLOCK_SIZE);
-
-	skcipher_request_set_tfm(req, tfm);
-	skcipher_request_set_callback(req, 0, NULL, NULL);
-	skcipher_request_set_crypt(req, sg_in, sg_out.sgl,
-				   src1_len + src2_len + zero_padding, iv);
-
-	/*
-	print_hex_dump(KERN_ERR, "enc  key: ", DUMP_PREFIX_NONE, 16, 1,
-		       key, key_len, 1);
-	print_hex_dump(KERN_ERR, "enc src1: ", DUMP_PREFIX_NONE, 16, 1,
-			src1, src1_len, 1);
-	print_hex_dump(KERN_ERR, "enc src2: ", DUMP_PREFIX_NONE, 16, 1,
-			src2, src2_len, 1);
-	print_hex_dump(KERN_ERR, "enc  pad: ", DUMP_PREFIX_NONE, 16, 1,
-			pad, zero_padding, 1);
-	*/
-	ret = crypto_skcipher_encrypt(req);
-	skcipher_request_zero(req);
-	if (ret < 0) {
-		pr_err("ceph_aes_crypt2 failed %d\n", ret);
-		goto out_sg;
-	}
-	/*
-	print_hex_dump(KERN_ERR, "enc  out: ", DUMP_PREFIX_NONE, 16, 1,
-		       dst, *dst_len, 1);
-	*/
-
-out_sg:
-	teardown_sgtable(&sg_out);
-out_tfm:
-	crypto_free_skcipher(tfm);
-	return ret;
-}
-
-static int ceph_aes_decrypt(const void *key, int key_len,
-			    void *dst, size_t *dst_len,
-			    const void *src, size_t src_len)
+static int ceph_aes_crypt(const struct ceph_crypto_key *key, bool encrypt,
+			  void *buf, int buf_len, int in_len, int *pout_len)
 {
-	struct sg_table sg_in;
-	struct scatterlist sg_out[2], prealloc_sg;
-	struct crypto_skcipher *tfm = ceph_crypto_alloc_cipher();
-	SKCIPHER_REQUEST_ON_STACK(req, tfm);
-	char pad[16];
-	char iv[AES_BLOCK_SIZE];
+	SKCIPHER_REQUEST_ON_STACK(req, key->tfm);
+	struct sg_table sgt;
+	struct scatterlist prealloc_sg;
+	char iv[AES_BLOCK_SIZE] __aligned(8);
+	int pad_byte = AES_BLOCK_SIZE - (in_len & (AES_BLOCK_SIZE - 1));
+	int crypt_len = encrypt ? in_len + pad_byte : in_len;
 	int ret;
-	int last_byte;
-
-	if (IS_ERR(tfm))
-		return PTR_ERR(tfm);
 
-	sg_init_table(sg_out, 2);
-	sg_set_buf(&sg_out[0], dst, *dst_len);
-	sg_set_buf(&sg_out[1], pad, sizeof(pad));
-	ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len);
+	WARN_ON(crypt_len > buf_len);
+	if (encrypt)
+		memset(buf + in_len, pad_byte, pad_byte);
+	ret = setup_sgtable(&sgt, &prealloc_sg, buf, crypt_len);
 	if (ret)
-		goto out_tfm;
+		return ret;
 
-	crypto_skcipher_setkey((void *)tfm, key, key_len);
 	memcpy(iv, aes_iv, AES_BLOCK_SIZE);
-
-	skcipher_request_set_tfm(req, tfm);
+	skcipher_request_set_tfm(req, key->tfm);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
-	skcipher_request_set_crypt(req, sg_in.sgl, sg_out,
-				   src_len, iv);
+	skcipher_request_set_crypt(req, sgt.sgl, sgt.sgl, crypt_len, iv);
 
 	/*
-	print_hex_dump(KERN_ERR, "dec key: ", DUMP_PREFIX_NONE, 16, 1,
-		       key, key_len, 1);
-	print_hex_dump(KERN_ERR, "dec  in: ", DUMP_PREFIX_NONE, 16, 1,
-		       src, src_len, 1);
+	print_hex_dump(KERN_ERR, "key: ", DUMP_PREFIX_NONE, 16, 1,
+		       key->key, key->len, 1);
+	print_hex_dump(KERN_ERR, " in: ", DUMP_PREFIX_NONE, 16, 1,
+		       buf, crypt_len, 1);
 	*/
-	ret = crypto_skcipher_decrypt(req);
-	skcipher_request_zero(req);
-	if (ret < 0) {
-		pr_err("ceph_aes_decrypt failed %d\n", ret);
-		goto out_sg;
-	}
-
-	if (src_len <= *dst_len)
-		last_byte = ((char *)dst)[src_len - 1];
+	if (encrypt)
+		ret = crypto_skcipher_encrypt(req);
 	else
-		last_byte = pad[src_len - *dst_len - 1];
-	if (last_byte <= 16 && src_len >= last_byte) {
-		*dst_len = src_len - last_byte;
-	} else {
-		pr_err("ceph_aes_decrypt got bad padding %d on src len %d\n",
-		       last_byte, (int)src_len);
-		return -EPERM;  /* bad padding */
-	}
-	/*
-	print_hex_dump(KERN_ERR, "dec out: ", DUMP_PREFIX_NONE, 16, 1,
-		       dst, *dst_len, 1);
-	*/
-
-out_sg:
-	teardown_sgtable(&sg_in);
-out_tfm:
-	crypto_free_skcipher(tfm);
-	return ret;
-}
-
-static int ceph_aes_decrypt2(const void *key, int key_len,
-			     void *dst1, size_t *dst1_len,
-			     void *dst2, size_t *dst2_len,
-			     const void *src, size_t src_len)
-{
-	struct sg_table sg_in;
-	struct scatterlist sg_out[3], prealloc_sg;
-	struct crypto_skcipher *tfm = ceph_crypto_alloc_cipher();
-	SKCIPHER_REQUEST_ON_STACK(req, tfm);
-	char pad[16];
-	char iv[AES_BLOCK_SIZE];
-	int ret;
-	int last_byte;
-
-	if (IS_ERR(tfm))
-		return PTR_ERR(tfm);
-
-	sg_init_table(sg_out, 3);
-	sg_set_buf(&sg_out[0], dst1, *dst1_len);
-	sg_set_buf(&sg_out[1], dst2, *dst2_len);
-	sg_set_buf(&sg_out[2], pad, sizeof(pad));
-	ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len);
-	if (ret)
-		goto out_tfm;
-
-	crypto_skcipher_setkey((void *)tfm, key, key_len);
-	memcpy(iv, aes_iv, AES_BLOCK_SIZE);
-
-	skcipher_request_set_tfm(req, tfm);
-	skcipher_request_set_callback(req, 0, NULL, NULL);
-	skcipher_request_set_crypt(req, sg_in.sgl, sg_out,
-				   src_len, iv);
-
-	/*
-	print_hex_dump(KERN_ERR, "dec  key: ", DUMP_PREFIX_NONE, 16, 1,
-		       key, key_len, 1);
-	print_hex_dump(KERN_ERR, "dec   in: ", DUMP_PREFIX_NONE, 16, 1,
-		       src, src_len, 1);
-	*/
-	ret = crypto_skcipher_decrypt(req);
+		ret = crypto_skcipher_decrypt(req);
 	skcipher_request_zero(req);
-	if (ret < 0) {
-		pr_err("ceph_aes_decrypt failed %d\n", ret);
-		goto out_sg;
-	}
-
-	if (src_len <= *dst1_len)
-		last_byte = ((char *)dst1)[src_len - 1];
-	else if (src_len <= *dst1_len + *dst2_len)
-		last_byte = ((char *)dst2)[src_len - *dst1_len - 1];
-	else
-		last_byte = pad[src_len - *dst1_len - *dst2_len - 1];
-	if (last_byte <= 16 && src_len >= last_byte) {
-		src_len -= last_byte;
-	} else {
-		pr_err("ceph_aes_decrypt got bad padding %d on src len %d\n",
-		       last_byte, (int)src_len);
-		return -EPERM;  /* bad padding */
-	}
-
-	if (src_len < *dst1_len) {
-		*dst1_len = src_len;
-		*dst2_len = 0;
-	} else {
-		*dst2_len = src_len - *dst1_len;
+	if (ret) {
+		pr_err("%s %scrypt failed: %d\n", __func__,
+		       encrypt ? "en" : "de", ret);
+		goto out_sgt;
 	}
 	/*
-	print_hex_dump(KERN_ERR, "dec  out1: ", DUMP_PREFIX_NONE, 16, 1,
-		       dst1, *dst1_len, 1);
-	print_hex_dump(KERN_ERR, "dec  out2: ", DUMP_PREFIX_NONE, 16, 1,
-		       dst2, *dst2_len, 1);
+	print_hex_dump(KERN_ERR, "out: ", DUMP_PREFIX_NONE, 16, 1,
+		       buf, crypt_len, 1);
 	*/
 
-out_sg:
-	teardown_sgtable(&sg_in);
-out_tfm:
-	crypto_free_skcipher(tfm);
-	return ret;
-}
-
-
-int ceph_decrypt(struct ceph_crypto_key *secret, void *dst, size_t *dst_len,
-		 const void *src, size_t src_len)
-{
-	switch (secret->type) {
-	case CEPH_CRYPTO_NONE:
-		if (*dst_len < src_len)
-			return -ERANGE;
-		memcpy(dst, src, src_len);
-		*dst_len = src_len;
-		return 0;
-
-	case CEPH_CRYPTO_AES:
-		return ceph_aes_decrypt(secret->key, secret->len, dst,
-					dst_len, src, src_len);
-
-	default:
-		return -EINVAL;
-	}
-}
-
-int ceph_decrypt2(struct ceph_crypto_key *secret,
-			void *dst1, size_t *dst1_len,
-			void *dst2, size_t *dst2_len,
-			const void *src, size_t src_len)
-{
-	size_t t;
-
-	switch (secret->type) {
-	case CEPH_CRYPTO_NONE:
-		if (*dst1_len + *dst2_len < src_len)
-			return -ERANGE;
-		t = min(*dst1_len, src_len);
-		memcpy(dst1, src, t);
-		*dst1_len = t;
-		src += t;
-		src_len -= t;
-		if (src_len) {
-			t = min(*dst2_len, src_len);
-			memcpy(dst2, src, t);
-			*dst2_len = t;
+	if (encrypt) {
+		*pout_len = crypt_len;
+	} else {
+		pad_byte = *(char *)(buf + in_len - 1);
+		if (pad_byte > 0 && pad_byte <= AES_BLOCK_SIZE &&
+		    in_len >= pad_byte) {
+			*pout_len = in_len - pad_byte;
+		} else {
+			pr_err("%s got bad padding %d on in_len %d\n",
+			       __func__, pad_byte, in_len);
+			ret = -EPERM;
+			goto out_sgt;
 		}
-		return 0;
-
-	case CEPH_CRYPTO_AES:
-		return ceph_aes_decrypt2(secret->key, secret->len,
-					 dst1, dst1_len, dst2, dst2_len,
-					 src, src_len);
-
-	default:
-		return -EINVAL;
 	}
-}
-
-int ceph_encrypt(struct ceph_crypto_key *secret, void *dst, size_t *dst_len,
-		 const void *src, size_t src_len)
-{
-	switch (secret->type) {
-	case CEPH_CRYPTO_NONE:
-		if (*dst_len < src_len)
-			return -ERANGE;
-		memcpy(dst, src, src_len);
-		*dst_len = src_len;
-		return 0;
 
-	case CEPH_CRYPTO_AES:
-		return ceph_aes_encrypt(secret->key, secret->len, dst,
-					dst_len, src, src_len);
-
-	default:
-		return -EINVAL;
-	}
+out_sgt:
+	teardown_sgtable(&sgt);
+	return ret;
 }
 
-int ceph_encrypt2(struct ceph_crypto_key *secret, void *dst, size_t *dst_len,
-		  const void *src1, size_t src1_len,
-		  const void *src2, size_t src2_len)
+int ceph_crypt(const struct ceph_crypto_key *key, bool encrypt,
+	       void *buf, int buf_len, int in_len, int *pout_len)
 {
-	switch (secret->type) {
+	switch (key->type) {
 	case CEPH_CRYPTO_NONE:
-		if (*dst_len < src1_len + src2_len)
-			return -ERANGE;
-		memcpy(dst, src1, src1_len);
-		memcpy(dst + src1_len, src2, src2_len);
-		*dst_len = src1_len + src2_len;
+		*pout_len = in_len;
 		return 0;
-
 	case CEPH_CRYPTO_AES:
-		return ceph_aes_encrypt2(secret->key, secret->len, dst, dst_len,
-					 src1, src1_len, src2, src2_len);
-
+		return ceph_aes_crypt(key, encrypt, buf, buf_len, in_len,
+				      pout_len);
 	default:
-		return -EINVAL;
+		return -ENOTSUPP;
 	}
 }
 
diff --git a/net/ceph/crypto.h b/net/ceph/crypto.h
index 2e9cab09f37b..58d83aa7740f 100644
--- a/net/ceph/crypto.h
+++ b/net/ceph/crypto.h
@@ -12,37 +12,19 @@ struct ceph_crypto_key {
 	struct ceph_timespec created;
 	int len;
 	void *key;
+	struct crypto_skcipher *tfm;
 };
 
-static inline void ceph_crypto_key_destroy(struct ceph_crypto_key *key)
-{
-	if (key) {
-		kfree(key->key);
-		key->key = NULL;
-	}
-}
-
 int ceph_crypto_key_clone(struct ceph_crypto_key *dst,
 			  const struct ceph_crypto_key *src);
 int ceph_crypto_key_encode(struct ceph_crypto_key *key, void **p, void *end);
 int ceph_crypto_key_decode(struct ceph_crypto_key *key, void **p, void *end);
 int ceph_crypto_key_unarmor(struct ceph_crypto_key *key, const char *in);
+void ceph_crypto_key_destroy(struct ceph_crypto_key *key);
 
 /* crypto.c */
-int ceph_decrypt(struct ceph_crypto_key *secret,
-		 void *dst, size_t *dst_len,
-		 const void *src, size_t src_len);
-int ceph_encrypt(struct ceph_crypto_key *secret,
-		 void *dst, size_t *dst_len,
-		 const void *src, size_t src_len);
-int ceph_decrypt2(struct ceph_crypto_key *secret,
-		  void *dst1, size_t *dst1_len,
-		  void *dst2, size_t *dst2_len,
-		  const void *src, size_t src_len);
-int ceph_encrypt2(struct ceph_crypto_key *secret,
-		  void *dst, size_t *dst_len,
-		  const void *src1, size_t src1_len,
-		  const void *src2, size_t src2_len);
+int ceph_crypt(const struct ceph_crypto_key *key, bool encrypt,
+	       void *buf, int buf_len, int in_len, int *pout_len);
 int ceph_crypto_init(void);
 void ceph_crypto_shutdown(void);
 
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index a47bbc973f2d..2384b4aae064 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -3939,21 +3939,31 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx,
 	u64_stats_update_end(&stats->syncp);
 
 	if (fast_rx->internal_forward) {
-		struct sta_info *dsta = sta_info_get(rx->sdata, skb->data);
+		struct sk_buff *xmit_skb = NULL;
+		bool multicast = is_multicast_ether_addr(skb->data);
 
-		if (dsta) {
+		if (multicast) {
+			xmit_skb = skb_copy(skb, GFP_ATOMIC);
+		} else if (sta_info_get(rx->sdata, skb->data)) {
+			xmit_skb = skb;
+			skb = NULL;
+		}
+
+		if (xmit_skb) {
 			/*
 			 * Send to wireless media and increase priority by 256
 			 * to keep the received priority instead of
 			 * reclassifying the frame (see cfg80211_classify8021d).
 			 */
-			skb->priority += 256;
-			skb->protocol = htons(ETH_P_802_3);
-			skb_reset_network_header(skb);
-			skb_reset_mac_header(skb);
-			dev_queue_xmit(skb);
-			return true;
+			xmit_skb->priority += 256;
+			xmit_skb->protocol = htons(ETH_P_802_3);
+			skb_reset_network_header(xmit_skb);
+			skb_reset_mac_header(xmit_skb);
+			dev_queue_xmit(xmit_skb);
 		}
+
+		if (!skb)
+			return true;
 	}
 
 	/* deliver to local stack */
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 45662d7f0943..6fdffde28733 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -1489,7 +1489,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp)
 	case RPC_GSS_PROC_DESTROY:
 		if (gss_write_verf(rqstp, rsci->mechctx, gc->gc_seq))
 			goto auth_err;
-		rsci->h.expiry_time = get_seconds();
+		rsci->h.expiry_time = seconds_since_boot();
 		set_bit(CACHE_NEGATIVE, &rsci->h.flags);
 		if (resv->iov_len + 4 > PAGE_SIZE)
 			goto drop;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 3bc1d61694cb..9c9db55a0c1e 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -799,6 +799,8 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
 
 	if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) {
 		dprintk("svc_recv: found XPT_CLOSE\n");
+		if (test_and_clear_bit(XPT_KILL_TEMP, &xprt->xpt_flags))
+			xprt->xpt_ops->xpo_kill_temp_xprt(xprt);
 		svc_delete_xprt(xprt);
 		/* Leave XPT_BUSY set on the dead xprt: */
 		goto out;
@@ -1020,9 +1022,11 @@ void svc_age_temp_xprts_now(struct svc_serv *serv, struct sockaddr *server_addr)
 		le = to_be_closed.next;
 		list_del_init(le);
 		xprt = list_entry(le, struct svc_xprt, xpt_list);
-		dprintk("svc_age_temp_xprts_now: closing %p\n", xprt);
-		xprt->xpt_ops->xpo_kill_temp_xprt(xprt);
-		svc_close_xprt(xprt);
+		set_bit(XPT_CLOSE, &xprt->xpt_flags);
+		set_bit(XPT_KILL_TEMP, &xprt->xpt_flags);
+		dprintk("svc_age_temp_xprts_now: queuing xprt %p for closing\n",
+				xprt);
+		svc_xprt_enqueue(xprt);
 	}
 }
 EXPORT_SYMBOL_GPL(svc_age_temp_xprts_now);
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 26b26beef2d4..adbf52c6df83 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -421,7 +421,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg,
 			 IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
 			 IB_ACCESS_REMOTE_READ;
 
-	DECR_CQCOUNT(&r_xprt->rx_ep);
+	rpcrdma_set_signaled(&r_xprt->rx_ep, &reg_wr->wr);
 	rc = ib_post_send(ia->ri_id->qp, &reg_wr->wr, &bad_wr);
 	if (rc)
 		goto out_senderr;
@@ -486,7 +486,7 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
 	struct rpcrdma_mw *mw, *tmp;
 	struct rpcrdma_frmr *f;
-	int rc;
+	int count, rc;
 
 	dprintk("RPC:       %s: req %p\n", __func__, req);
 
@@ -496,6 +496,7 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	 * a single ib_post_send() call.
 	 */
 	f = NULL;
+	count = 0;
 	invalidate_wrs = pos = prev = NULL;
 	list_for_each_entry(mw, &req->rl_registered, mw_list) {
 		if ((rep->rr_wc_flags & IB_WC_WITH_INVALIDATE) &&
@@ -505,6 +506,7 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 		}
 
 		pos = __frwr_prepare_linv_wr(mw);
+		count++;
 
 		if (!invalidate_wrs)
 			invalidate_wrs = pos;
@@ -523,7 +525,12 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	f->fr_invwr.send_flags = IB_SEND_SIGNALED;
 	f->fr_cqe.done = frwr_wc_localinv_wake;
 	reinit_completion(&f->fr_linv_done);
-	INIT_CQCOUNT(&r_xprt->rx_ep);
+
+	/* Initialize CQ count, since there is always a signaled
+	 * WR being posted here.  The new cqcount depends on how
+	 * many SQEs are about to be consumed.
+	 */
+	rpcrdma_init_cqcount(&r_xprt->rx_ep, count);
 
 	/* Transport disconnect drains the receive CQ before it
 	 * replaces the QP. The RPC reply handler won't call us
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index ad1df979b3f0..a47c9bdef5fa 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -348,8 +348,6 @@ int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
 	atomic_inc(&rdma_stat_read);
 	return ret;
  err:
-	ib_dma_unmap_sg(xprt->sc_cm_id->device,
-			frmr->sg, frmr->sg_nents, frmr->direction);
 	svc_rdma_put_context(ctxt, 0);
 	svc_rdma_put_frmr(xprt, frmr);
 	return ret;
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index ec74289af7ec..8da7f6a4dfc3 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -223,8 +223,8 @@ rpcrdma_update_connect_private(struct rpcrdma_xprt *r_xprt,
 		cdata->inline_rsize = rsize;
 	if (wsize < cdata->inline_wsize)
 		cdata->inline_wsize = wsize;
-	pr_info("rpcrdma: max send %u, max recv %u\n",
-		cdata->inline_wsize, cdata->inline_rsize);
+	dprintk("RPC:       %s: max send %u, max recv %u\n",
+		__func__, cdata->inline_wsize, cdata->inline_rsize);
 	rpcrdma_set_max_header_sizes(r_xprt);
 }
 
@@ -532,7 +532,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 	ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 - 1;
 	if (ep->rep_cqinit <= 2)
 		ep->rep_cqinit = 0;	/* always signal? */
-	INIT_CQCOUNT(ep);
+	rpcrdma_init_cqcount(ep, 0);
 	init_waitqueue_head(&ep->rep_connect_wait);
 	INIT_DELAYED_WORK(&ep->rep_connect_worker, rpcrdma_connect_worker);
 
@@ -1311,13 +1311,7 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia,
 	dprintk("RPC:       %s: posting %d s/g entries\n",
 		__func__, send_wr->num_sge);
 
-	if (DECR_CQCOUNT(ep) > 0)
-		send_wr->send_flags = 0;
-	else { /* Provider must take a send completion every now and then */
-		INIT_CQCOUNT(ep);
-		send_wr->send_flags = IB_SEND_SIGNALED;
-	}
-
+	rpcrdma_set_signaled(ep, send_wr);
 	rc = ib_post_send(ia->ri_id->qp, send_wr, &send_wr_fail);
 	if (rc)
 		goto out_postsend_err;
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 6e1bba358203..f6ae1b22da47 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -95,8 +95,24 @@ struct rpcrdma_ep {
 	struct delayed_work	rep_connect_worker;
 };
 
-#define INIT_CQCOUNT(ep) atomic_set(&(ep)->rep_cqcount, (ep)->rep_cqinit)
-#define DECR_CQCOUNT(ep) atomic_sub_return(1, &(ep)->rep_cqcount)
+static inline void
+rpcrdma_init_cqcount(struct rpcrdma_ep *ep, int count)
+{
+	atomic_set(&ep->rep_cqcount, ep->rep_cqinit - count);
+}
+
+/* To update send queue accounting, provider must take a
+ * send completion every now and then.
+ */
+static inline void
+rpcrdma_set_signaled(struct rpcrdma_ep *ep, struct ib_send_wr *send_wr)
+{
+	send_wr->send_flags = 0;
+	if (unlikely(atomic_sub_return(1, &ep->rep_cqcount) <= 0)) {
+		rpcrdma_init_cqcount(ep, 0);
+		send_wr->send_flags = IB_SEND_SIGNALED;
+	}
+}
 
 /* Pre-allocate extra Work Requests for handling backward receives
  * and sends. This is a fixed value because the Work Queues are
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 72edf83d76b7..cffdd9cf3ebf 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -366,7 +366,7 @@ ifndef NO_SDT
 endif
 
 ifdef PERF_HAVE_JITDUMP
-  ifndef NO_DWARF
+  ifndef NO_LIBELF
     $(call detected,CONFIG_JITDUMP)
     CFLAGS += -DHAVE_JITDUMP
   endif
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index d1ce29be560e..cd7bc4d104e2 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -70,8 +70,8 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	OPT_UINTEGER(0, "ldlat", &perf_mem_events__loads_ldlat, "mem-loads latency"),
 	OPT_INCR('v', "verbose", &verbose,
 		 "be more verbose (show counter open errors, etc)"),
-	OPT_BOOLEAN('U', "--all-user", &all_user, "collect only user level data"),
-	OPT_BOOLEAN('K', "--all-kernel", &all_kernel, "collect only kernel level data"),
+	OPT_BOOLEAN('U', "all-user", &all_user, "collect only user level data"),
+	OPT_BOOLEAN('K', "all-kernel", &all_kernel, "collect only kernel level data"),
 	OPT_END()
 	};
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index c298bd3e1d90..21f8a81797a0 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1452,7 +1452,7 @@ static int trace__printf_interrupted_entry(struct trace *trace, struct perf_samp
 
 	duration = sample->time - ttrace->entry_time;
 
-	printed  = trace__fprintf_entry_head(trace, trace->current, duration, sample->time, trace->output);
+	printed  = trace__fprintf_entry_head(trace, trace->current, duration, ttrace->entry_time, trace->output);
 	printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str);
 	ttrace->entry_pending = false;
 
@@ -1499,7 +1499,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 
 	if (sc->is_exit) {
 		if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) {
-			trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
+			trace__fprintf_entry_head(trace, thread, 1, ttrace->entry_time, trace->output);
 			fprintf(trace->output, "%-70s)\n", ttrace->entry_str);
 		}
 	} else {
@@ -1592,7 +1592,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	if (trace->summary_only)
 		goto out;
 
-	trace__fprintf_entry_head(trace, thread, duration, sample->time, trace->output);
+	trace__fprintf_entry_head(trace, thread, duration, ttrace->entry_time, trace->output);
 
 	if (ttrace->entry_pending) {
 		fprintf(trace->output, "%-70s", ttrace->entry_str);
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index fd710ab33684..af1cfde6b97b 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -42,7 +42,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 
 	P_MMAP_FLAG(SHARED);
 	P_MMAP_FLAG(PRIVATE);
+#ifdef MAP_32BIT
 	P_MMAP_FLAG(32BIT);
+#endif
 	P_MMAP_FLAG(ANONYMOUS);
 	P_MMAP_FLAG(DENYWRITE);
 	P_MMAP_FLAG(EXECUTABLE);
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index eb60e613d795..1dc67efad634 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -120,7 +120,7 @@ libperf-y += demangle-rust.o
 ifdef CONFIG_JITDUMP
 libperf-$(CONFIG_LIBELF) += jitdump.o
 libperf-$(CONFIG_LIBELF) += genelf.o
-libperf-$(CONFIG_LIBELF) += genelf_debug.o
+libperf-$(CONFIG_DWARF) += genelf_debug.o
 endif
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 07fd30bc2f81..ae58b493af45 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -193,7 +193,6 @@ int perf_callchain_config(const char *var, const char *value)
 
 	if (!strcmp(var, "record-mode"))
 		return parse_callchain_record_opt(value, &callchain_param);
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
 	if (!strcmp(var, "dump-size")) {
 		unsigned long size = 0;
 		int ret;
@@ -203,7 +202,6 @@ int perf_callchain_config(const char *var, const char *value)
 
 		return ret;
 	}
-#endif
 	if (!strcmp(var, "print-type"))
 		return parse_callchain_mode(value);
 	if (!strcmp(var, "order"))
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 13e75549c440..47cfd1080975 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -11,11 +11,7 @@
 
 #define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace):\n\n"
 
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
 # define RECORD_MODE_HELP  HELP_PAD "record_mode:\tcall graph recording mode (fp|dwarf|lbr)\n"
-#else
-# define RECORD_MODE_HELP  HELP_PAD "record_mode:\tcall graph recording mode (fp|lbr)\n"
-#endif
 
 #define RECORD_SIZE_HELP						\
 	HELP_PAD "record_size:\tif record_mode is 'dwarf', max size of stack recording (<bytes>)\n" \
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index c1ef805c6a8f..14a73acc549c 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -19,7 +19,9 @@
 #include <limits.h>
 #include <fcntl.h>
 #include <err.h>
+#ifdef HAVE_DWARF_SUPPORT
 #include <dwarf.h>
+#endif
 
 #include "perf.h"
 #include "genelf.h"
@@ -157,7 +159,7 @@ gen_build_id(struct buildid_note *note, unsigned long load_addr, const void *cod
 int
 jit_write_elf(int fd, uint64_t load_addr, const char *sym,
 	      const void *code, int csize,
-	      void *debug, int nr_debug_entries)
+	      void *debug __maybe_unused, int nr_debug_entries __maybe_unused)
 {
 	Elf *e;
 	Elf_Data *d;
@@ -386,11 +388,14 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym,
 	shdr->sh_size = sizeof(bnote);
 	shdr->sh_entsize = 0;
 
+#ifdef HAVE_DWARF_SUPPORT
 	if (debug && nr_debug_entries) {
 		retval = jit_add_debug_info(e, load_addr, debug, nr_debug_entries);
 		if (retval)
 			goto error;
-	} else {
+	} else
+#endif
+	{
 		if (elf_update(e, ELF_C_WRITE) < 0) {
 			warnx("elf_update 4 failed");
 			goto error;
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index 2fbeb59c4bdd..5c933ac71451 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -4,8 +4,10 @@
 /* genelf.c */
 int jit_write_elf(int fd, uint64_t code_addr, const char *sym,
 		  const void *code, int csize, void *debug, int nr_debug_entries);
+#ifdef HAVE_DWARF_SUPPORT
 /* genelf_debug.c */
 int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries);
+#endif
 
 #if   defined(__arm__)
 #define GEN_ELF_ARCH	EM_ARM
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index aecff69a510d..f7b35e178582 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1459,7 +1459,8 @@ int dso__load(struct dso *dso, struct map *map)
 	 * Read the build id if possible. This is required for
 	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
 	 */
-	if (is_regular_file(dso->long_name) &&
+	if (!dso->has_build_id &&
+	    is_regular_file(dso->long_name) &&
 	    filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
 		dso__set_build_id(dso, build_id);
 
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 9df61059a85d..a2fd6e79d5a5 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -95,7 +95,8 @@ static void register_python_scripting(struct scripting_ops *scripting_ops)
 	if (err)
 		die("error registering py script extension");
 
-	scripting_context = malloc(sizeof(struct scripting_context));
+	if (scripting_context == NULL)
+		scripting_context = malloc(sizeof(*scripting_context));
 }
 
 #ifdef NO_LIBPYTHON
@@ -159,7 +160,8 @@ static void register_perl_scripting(struct scripting_ops *scripting_ops)
 	if (err)
 		die("error registering pl script extension");
 
-	scripting_context = malloc(sizeof(struct scripting_context));
+	if (scripting_context == NULL)
+		scripting_context = malloc(sizeof(*scripting_context));
 }
 
 #ifdef NO_LIBPERL
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
index c22860ab9733..30e1ac62e8cb 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -66,7 +66,7 @@ int pmc56_overflow(void)
 
 	FAIL_IF(ebb_event_enable(&event));
 
-	mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+	mtspr(SPRN_PMC2, pmc_sample_period(sample_period));
 	mtspr(SPRN_PMC5, 0);
 	mtspr(SPRN_PMC6, 0);
 
diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh
index 2e69ca812b4c..29b0d3920bfc 100755
--- a/tools/virtio/ringtest/run-on-all.sh
+++ b/tools/virtio/ringtest/run-on-all.sh
@@ -1,12 +1,13 @@
 #!/bin/sh
 
+CPUS_ONLINE=$(lscpu --online -p=cpu|grep -v -e '#')
 #use last CPU for host. Why not the first?
 #many devices tend to use cpu0 by default so
 #it tends to be busier
-HOST_AFFINITY=$(lscpu -p=cpu | tail -1)
+HOST_AFFINITY=$(echo "${CPUS_ONLINE}"|tail -n 1)
 
 #run command on all cpus
-for cpu in $(seq 0 $HOST_AFFINITY)
+for cpu in $CPUS_ONLINE
 do
 	#Don't run guest and host on same CPU
 	#It actually works ok if using signalling
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index 8cebfbc19e90..539d3f5cb619 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -268,15 +268,11 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm)
 {
 	struct vgic_dist *dist = &kvm->arch.vgic;
 
-	mutex_lock(&kvm->lock);
-
 	dist->ready = false;
 	dist->initialized = false;
 
 	kfree(dist->spis);
 	dist->nr_spis = 0;
-
-	mutex_unlock(&kvm->lock);
 }
 
 void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
@@ -286,7 +282,8 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
 	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
 }
 
-void kvm_vgic_destroy(struct kvm *kvm)
+/* To be called with kvm->lock held */
+static void __kvm_vgic_destroy(struct kvm *kvm)
 {
 	struct kvm_vcpu *vcpu;
 	int i;
@@ -297,6 +294,13 @@ void kvm_vgic_destroy(struct kvm *kvm)
 		kvm_vgic_vcpu_destroy(vcpu);
 }
 
+void kvm_vgic_destroy(struct kvm *kvm)
+{
+	mutex_lock(&kvm->lock);
+	__kvm_vgic_destroy(kvm);
+	mutex_unlock(&kvm->lock);
+}
+
 /**
  * vgic_lazy_init: Lazy init is only allowed if the GIC exposed to the guest
  * is a GICv2. A GICv3 must be explicitly initialized by the guest using the
@@ -348,6 +352,10 @@ int kvm_vgic_map_resources(struct kvm *kvm)
 		ret = vgic_v2_map_resources(kvm);
 	else
 		ret = vgic_v3_map_resources(kvm);
+
+	if (ret)
+		__kvm_vgic_destroy(kvm);
+
 out:
 	mutex_unlock(&kvm->lock);
 	return ret;
diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c
index 9bab86757fa4..834137e7b83f 100644
--- a/virt/kvm/arm/vgic/vgic-v2.c
+++ b/virt/kvm/arm/vgic/vgic-v2.c
@@ -293,8 +293,6 @@ int vgic_v2_map_resources(struct kvm *kvm)
 	dist->ready = true;
 
 out:
-	if (ret)
-		kvm_vgic_destroy(kvm);
 	return ret;
 }
 
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index 5c9f9745e6ca..e6b03fd8c374 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -302,8 +302,6 @@ int vgic_v3_map_resources(struct kvm *kvm)
 	dist->ready = true;
 
 out:
-	if (ret)
-		kvm_vgic_destroy(kvm);
 	return ret;
 }
 