Merge branch 'linus' into sched/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

261 files changed, 3538 insertions, 1846 deletions

diff --git a/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt b/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-ibt-bmc.txt
index fbbacd958240..6f28969af9dc 100644
--- a/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-bt-bmc.txt
+++ b/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-ibt-bmc.txt
@@ -6,7 +6,7 @@ perform in-band IPMI communication with their host.
 
 Required properties:
 
-- compatible : should be "aspeed,ast2400-bt-bmc"
+- compatible : should be "aspeed,ast2400-ibt-bmc"
 - reg: physical address and size of the registers
 
 Optional properties:
@@ -17,7 +17,7 @@ Optional properties:
 Example:
 
 	ibt@1e789140 {
-		compatible = "aspeed,ast2400-bt-bmc";
+		compatible = "aspeed,ast2400-ibt-bmc";
 		reg = <0x1e789140 0x18>;
 		interrupts = <8>;
 	};
diff --git a/Documentation/devicetree/bindings/sound/omap-abe-twl6040.txt b/Documentation/devicetree/bindings/sound/omap-abe-twl6040.txt
index fd40c852d7c7..462b04e8209f 100644
--- a/Documentation/devicetree/bindings/sound/omap-abe-twl6040.txt
+++ b/Documentation/devicetree/bindings/sound/omap-abe-twl6040.txt
@@ -12,7 +12,7 @@ Required properties:
 
 Optional properties:
 - ti,dmic: phandle for the OMAP dmic node if the machine have it connected
-- ti,jack_detection: Need to be present if the board capable to detect jack
+- ti,jack-detection: Need to be present if the board capable to detect jack
   insertion, removal.
 
 Available audio endpoints for the audio-routing table:
diff --git a/Documentation/i2c/i2c-topology b/Documentation/i2c/i2c-topology
index e0aefeece551..1a014fede0b7 100644
--- a/Documentation/i2c/i2c-topology
+++ b/Documentation/i2c/i2c-topology
@@ -326,7 +326,7 @@ Two parent-locked sibling muxes
 
 This is a good topology.
 
-                                   .--------.
+                                    .--------.
                    .----------.  .--| dev D1 |
                    |  parent- |--'  '--------'
                 .--|  locked  |     .--------.
@@ -350,7 +350,7 @@ Mux-locked and parent-locked sibling muxes
 
 This is a good topology.
 
-                                   .--------.
+                                    .--------.
                    .----------.  .--| dev D1 |
                    |   mux-   |--'  '--------'
                 .--|  locked  |     .--------.
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 739db9ab16b2..6bbceb9a3a19 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -777,6 +777,17 @@ Gets the current timestamp of kvmclock as seen by the current guest. In
 conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios
 such as migration.
 
+When KVM_CAP_ADJUST_CLOCK is passed to KVM_CHECK_EXTENSION, it returns the
+set of bits that KVM can return in struct kvm_clock_data's flag member.
+
+The only flag defined now is KVM_CLOCK_TSC_STABLE.  If set, the returned
+value is the exact kvmclock value seen by all VCPUs at the instant
+when KVM_GET_CLOCK was called.  If clear, the returned value is simply
+CLOCK_MONOTONIC plus a constant offset; the offset can be modified
+with KVM_SET_CLOCK.  KVM will try to make all VCPUs follow this clock,
+but the exact value read by each VCPU could differ, because the host
+TSC is not stable.
+
 struct kvm_clock_data {
 	__u64 clock;  /* kvmclock current value */
 	__u32 flags;
diff --git a/MAINTAINERS b/MAINTAINERS
index 2a58eeac9452..ad9b965e5e44 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7084,6 +7084,7 @@ F:	drivers/scsi/53c700*
 LED SUBSYSTEM
 M:	Richard Purdie <rpurdie@rpsys.net>
 M:	Jacek Anaszewski <j.anaszewski@samsung.com>
+M:	Pavel Machek <pavel@ucw.cz>
 L:	linux-leds@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/j.anaszewski/linux-leds.git
 S:	Maintained
diff --git a/Makefile b/Makefile
index 247430abfc73..0ede48ba5aaf 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 9
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
 NAME = Psychotic Stoned Sheep
 
 # *DOCUMENTATION*
@@ -399,11 +399,12 @@ KBUILD_CFLAGS   := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
 		   -fno-strict-aliasing -fno-common \
 		   -Werror-implicit-function-declaration \
 		   -Wno-format-security \
-		   -std=gnu89
+		   -std=gnu89 $(call cc-option,-fno-PIE)
+
 
 KBUILD_AFLAGS_KERNEL :=
 KBUILD_CFLAGS_KERNEL :=
-KBUILD_AFLAGS   := -D__ASSEMBLY__
+KBUILD_AFLAGS   := -D__ASSEMBLY__ $(call cc-option,-fno-PIE)
 KBUILD_AFLAGS_MODULE  := -DMODULE
 KBUILD_CFLAGS_MODULE  := -DMODULE
 KBUILD_LDFLAGS_MODULE := -T $(srctree)/scripts/module-common.lds
diff --git a/arch/arm/boot/dts/imx53-qsb.dts b/arch/arm/boot/dts/imx53-qsb.dts
index dec4b073ceb1..379939699164 100644
--- a/arch/arm/boot/dts/imx53-qsb.dts
+++ b/arch/arm/boot/dts/imx53-qsb.dts
@@ -64,8 +64,8 @@
 			};
 
 			ldo3_reg: ldo3 {
-				regulator-min-microvolt = <600000>;
-				regulator-max-microvolt = <1800000>;
+				regulator-min-microvolt = <1725000>;
+				regulator-max-microvolt = <3300000>;
 				regulator-always-on;
 			};
 
@@ -76,8 +76,8 @@
 			};
 
 			ldo5_reg: ldo5 {
-				regulator-min-microvolt = <1725000>;
-				regulator-max-microvolt = <3300000>;
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3600000>;
 				regulator-always-on;
 			};
 
@@ -100,14 +100,14 @@
 			};
 
 			ldo9_reg: ldo9 {
-				regulator-min-microvolt = <1200000>;
+				regulator-min-microvolt = <1250000>;
 				regulator-max-microvolt = <3600000>;
 				regulator-always-on;
 			};
 
 			ldo10_reg: ldo10 {
-				regulator-min-microvolt = <1250000>;
-				regulator-max-microvolt = <3650000>;
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <3600000>;
 				regulator-always-on;
 			};
 		};
diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi
index 0ff1c2de95bf..26cce4d18405 100644
--- a/arch/arm/boot/dts/logicpd-som-lv.dtsi
+++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi
@@ -13,6 +13,11 @@
 		};
 	};
 
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0x80000000 0>;
+	};
+
 	wl12xx_vmmc: wl12xx_vmmc {
 		compatible = "regulator-fixed";
 		regulator-name = "vwl1271";
diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index 731ec37aed5b..8f9a69ca818c 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -13,9 +13,9 @@
 		};
 	};
 
-	memory@0 {
+	memory@80000000 {
 		device_type = "memory";
-		reg = <0 0>;
+		reg = <0x80000000 0>;
 	};
 
 	leds {
diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi
index 6365635fea5c..4caadb253249 100644
--- a/arch/arm/boot/dts/omap5-board-common.dtsi
+++ b/arch/arm/boot/dts/omap5-board-common.dtsi
@@ -124,6 +124,7 @@
 		compatible = "ti,abe-twl6040";
 		ti,model = "omap5-uevm";
 
+		ti,jack-detection;
 		ti,mclk-freq = <19200000>;
 
 		ti,mcpdm = <&mcpdm>;
@@ -415,7 +416,7 @@
 			ti,backup-battery-charge-high-current;
 		};
 
-		gpadc {
+		gpadc: gpadc {
 			compatible = "ti,palmas-gpadc";
 			interrupts = <18 0
 				      16 0
@@ -475,8 +476,8 @@
 				smps6_reg: smps6 {
 					/* VDD_DDR3 - over VDD_SMPS6 */
 					regulator-name = "smps6";
-					regulator-min-microvolt = <1200000>;
-					regulator-max-microvolt = <1200000>;
+					regulator-min-microvolt = <1350000>;
+					regulator-max-microvolt = <1350000>;
 					regulator-always-on;
 					regulator-boot-on;
 				};
diff --git a/arch/arm/boot/dts/stih410-b2260.dts b/arch/arm/boot/dts/stih410-b2260.dts
index ef2ff2f518f6..7fb507fcba7e 100644
--- a/arch/arm/boot/dts/stih410-b2260.dts
+++ b/arch/arm/boot/dts/stih410-b2260.dts
@@ -74,7 +74,7 @@
 		/* Low speed expansion connector */
 		spi0: spi@9844000 {
 			label = "LS-SPI0";
-			cs-gpio = <&pio30 3 0>;
+			cs-gpios = <&pio30 3 0>;
 			status = "okay";
 		};
 
diff --git a/arch/arm/boot/dts/sun8i-a23-a33.dtsi b/arch/arm/boot/dts/sun8i-a23-a33.dtsi
index 48fc24f36fcb..300a1bd5a6ec 100644
--- a/arch/arm/boot/dts/sun8i-a23-a33.dtsi
+++ b/arch/arm/boot/dts/sun8i-a23-a33.dtsi
@@ -282,11 +282,15 @@
 			uart1_pins_a: uart1@0 {
 				allwinner,pins = "PG6", "PG7";
 				allwinner,function = "uart1";
+				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
 			uart1_pins_cts_rts_a: uart1-cts-rts@0 {
 				allwinner,pins = "PG8", "PG9";
 				allwinner,function = "uart1";
+				allwinner,drive = <SUN4I_PINCTRL_10_MA>;
+				allwinner,pull = <SUN4I_PINCTRL_NO_PULL>;
 			};
 
 			mmc0_pins_a: mmc0@0 {
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index bc698383e822..9688ec0c6ef4 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -74,6 +74,26 @@ void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long
 		dump_mem("", "Exception stack", frame + 4, frame + 4 + sizeof(struct pt_regs));
 }
 
+void dump_backtrace_stm(u32 *stack, u32 instruction)
+{
+	char str[80], *p;
+	unsigned int x;
+	int reg;
+
+	for (reg = 10, x = 0, p = str; reg >= 0; reg--) {
+		if (instruction & BIT(reg)) {
+			p += sprintf(p, " r%d:%08x", reg, *stack--);
+			if (++x == 6) {
+				x = 0;
+				p = str;
+				printk("%s\n", str);
+			}
+		}
+	}
+	if (p != str)
+		printk("%s\n", str);
+}
+
 #ifndef CONFIG_ARM_UNWIND
 /*
  * Stack pointers should always be within the kernels view of
diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S
index 7fa487ef7e2f..37b2a11af345 100644
--- a/arch/arm/kernel/vmlinux-xip.lds.S
+++ b/arch/arm/kernel/vmlinux-xip.lds.S
@@ -3,6 +3,9 @@
  * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>
  */
 
+/* No __ro_after_init data in the .rodata section - which will always be ro */
+#define RO_AFTER_INIT_DATA
+
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/cache.h>
 #include <asm/thread_info.h>
@@ -223,6 +226,8 @@ SECTIONS
 		. = ALIGN(PAGE_SIZE);
 		__init_end = .;
 
+		*(.data..ro_after_init)
+
 		NOSAVE_DATA
 		CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES)
 		READ_MOSTLY_DATA(L1_CACHE_BYTES)
diff --git a/arch/arm/lib/backtrace.S b/arch/arm/lib/backtrace.S
index fab5a50503ae..7d7952e5a3b1 100644
--- a/arch/arm/lib/backtrace.S
+++ b/arch/arm/lib/backtrace.S
@@ -10,6 +10,7 @@
  * 27/03/03 Ian Molton Clean up CONFIG_CPU
  *
  */
+#include <linux/kern_levels.h>
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 		.text
@@ -83,13 +84,13 @@ for_each_frame:	tst	frame, mask		@ Check for address exceptions
 		teq	r3, r1, lsr #11
 		ldreq	r0, [frame, #-8]	@ get sp
 		subeq	r0, r0, #4		@ point at the last arg
-		bleq	.Ldumpstm		@ dump saved registers
+		bleq	dump_backtrace_stm	@ dump saved registers
 
 1004:		ldr	r1, [sv_pc, #0]		@ if stmfd sp!, {..., fp, ip, lr, pc}
 		ldr	r3, .Ldsi		@ instruction exists,
 		teq	r3, r1, lsr #11
 		subeq	r0, frame, #16
-		bleq	.Ldumpstm		@ dump saved registers
+		bleq	dump_backtrace_stm	@ dump saved registers
 
 		teq	sv_fp, #0		@ zero saved fp means
 		beq	no_frame		@ no further frames
@@ -112,38 +113,6 @@ ENDPROC(c_backtrace)
 		.long	1004b, 1006b
 		.popsection
 
-#define instr r4
-#define reg   r5
-#define stack r6
-
-.Ldumpstm:	stmfd	sp!, {instr, reg, stack, r7, lr}
-		mov	stack, r0
-		mov	instr, r1
-		mov	reg, #10
-		mov	r7, #0
-1:		mov	r3, #1
- ARM(		tst	instr, r3, lsl reg	)
- THUMB(		lsl	r3, reg			)
- THUMB(		tst	instr, r3		)
-		beq	2f
-		add	r7, r7, #1
-		teq	r7, #6
-		moveq	r7, #0
-		adr	r3, .Lcr
-		addne	r3, r3, #1		@ skip newline
-		ldr	r2, [stack], #-4
-		mov	r1, reg
-		adr	r0, .Lfp
-		bl	printk
-2:		subs	reg, reg, #1
-		bpl	1b
-		teq	r7, #0
-		adrne	r0, .Lcr
-		blne	printk
-		ldmfd	sp!, {instr, reg, stack, r7, pc}
-
-.Lfp:		.asciz	" r%d:%08x%s"
-.Lcr:		.asciz	"\n"
 .Lbad:		.asciz	"Backtrace aborted due to bad frame pointer <%p>\n"
 		.align
 .Ldsi:		.word	0xe92dd800 >> 11	@ stmfd sp!, {... fp, ip, lr, pc}
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index a9afeebd59f2..0465338183c7 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -71,6 +71,7 @@ config SOC_AM43XX
 	select HAVE_ARM_TWD
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_775420
+	select OMAP_INTERCONNECT
 
 config SOC_DRA7XX
 	bool "TI DRA7XX"
diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c
index 2abd53ae3e7a..cc6d9fa60924 100644
--- a/arch/arm/mach-omap2/id.c
+++ b/arch/arm/mach-omap2/id.c
@@ -205,11 +205,15 @@ void __init omap2xxx_check_revision(void)
 
 #define OMAP3_SHOW_FEATURE(feat)		\
 	if (omap3_has_ ##feat())		\
-		printk(#feat" ");
+		n += scnprintf(buf + n, sizeof(buf) - n, #feat " ");
 
 static void __init omap3_cpuinfo(void)
 {
 	const char *cpu_name;
+	char buf[64];
+	int n = 0;
+
+	memset(buf, 0, sizeof(buf));
 
 	/*
 	 * OMAP3430 and OMAP3530 are assumed to be same.
@@ -241,10 +245,10 @@ static void __init omap3_cpuinfo(void)
 		cpu_name = "OMAP3503";
 	}
 
-	sprintf(soc_name, "%s", cpu_name);
+	scnprintf(soc_name, sizeof(soc_name), "%s", cpu_name);
 
 	/* Print verbose information */
-	pr_info("%s %s (", soc_name, soc_rev);
+	n += scnprintf(buf, sizeof(buf) - n, "%s %s (", soc_name, soc_rev);
 
 	OMAP3_SHOW_FEATURE(l2cache);
 	OMAP3_SHOW_FEATURE(iva);
@@ -252,8 +256,10 @@ static void __init omap3_cpuinfo(void)
 	OMAP3_SHOW_FEATURE(neon);
 	OMAP3_SHOW_FEATURE(isp);
 	OMAP3_SHOW_FEATURE(192mhz_clk);
-
-	printk(")\n");
+	if (*(buf + n - 1) == ' ')
+		n--;
+	n += scnprintf(buf + n, sizeof(buf) - n, ")\n");
+	pr_info("%s", buf);
 }
 
 #define OMAP3_CHECK_FEATURE(status,feat)				\
diff --git a/arch/arm/mach-omap2/prm3xxx.c b/arch/arm/mach-omap2/prm3xxx.c
index 62680aad2126..718981bb80cd 100644
--- a/arch/arm/mach-omap2/prm3xxx.c
+++ b/arch/arm/mach-omap2/prm3xxx.c
@@ -319,6 +319,9 @@ void __init omap3_prm_init_pm(bool has_uart4, bool has_iva)
 	if (has_uart4) {
 		en_uart4_mask = OMAP3630_EN_UART4_MASK;
 		grpsel_uart4_mask = OMAP3630_GRPSEL_UART4_MASK;
+	} else {
+		en_uart4_mask = 0;
+		grpsel_uart4_mask = 0;
 	}
 
 	/* Enable wakeups in PER */
diff --git a/arch/arm/mach-omap2/voltage.c b/arch/arm/mach-omap2/voltage.c
index cba8cada8c81..cd15dbd62671 100644
--- a/arch/arm/mach-omap2/voltage.c
+++ b/arch/arm/mach-omap2/voltage.c
@@ -87,6 +87,12 @@ int voltdm_scale(struct voltagedomain *voltdm,
 		return -ENODATA;
 	}
 
+	if (!voltdm->volt_data) {
+		pr_err("%s: No voltage data defined for vdd_%s\n",
+			__func__, voltdm->name);
+		return -ENODATA;
+	}
+
 	/* Adjust voltage to the exact voltage from the OPP table */
 	for (i = 0; voltdm->volt_data[i].volt_nominal != 0; i++) {
 		if (voltdm->volt_data[i].volt_nominal >= target_volt) {
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ab4f74536057..ab7710002ba6 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1167,7 +1167,7 @@ static int __init dma_debug_do_init(void)
 	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
 	return 0;
 }
-fs_initcall(dma_debug_do_init);
+core_initcall(dma_debug_do_init);
 
 #ifdef CONFIG_ARM_DMA_USE_IOMMU
 
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index f6d333f09bfe..8dea61640cc1 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -96,7 +96,7 @@ ENTRY(cpu_cm7_proc_fin)
 	ret	lr
 ENDPROC(cpu_cm7_proc_fin)
 
-	.section ".text.init", #alloc, #execinstr
+	.section ".init.text", #alloc, #execinstr
 
 __v7m_cm7_setup:
 	mov	r8, #(V7M_SCB_CCR_DC | V7M_SCB_CCR_IC| V7M_SCB_CCR_BP)
diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
index c4762538ec01..e9bd58793464 100644
--- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
@@ -105,7 +105,7 @@
 				status = "disabled";
 			};
 
-			nb_perih_clk: nb-periph-clk@13000{
+			nb_periph_clk: nb-periph-clk@13000 {
 				compatible = "marvell,armada-3700-periph-clock-nb";
 				reg = <0x13000 0x100>;
 				clocks = <&tbg 0>, <&tbg 1>, <&tbg 2>,
@@ -113,7 +113,7 @@
 				#clock-cells = <1>;
 			};
 
-			sb_perih_clk: sb-periph-clk@18000{
+			sb_periph_clk: sb-periph-clk@18000 {
 				compatible = "marvell,armada-3700-periph-clock-sb";
 				reg = <0x18000 0x100>;
 				clocks = <&tbg 0>, <&tbg 1>, <&tbg 2>,
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
index 842fb333285c..6bf9e241179b 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
@@ -130,8 +130,8 @@
 				reg = <0x700600 0x50>;
 				#address-cells = <0x1>;
 				#size-cells = <0x0>;
-				cell-index = <1>;
-				clocks = <&cps_syscon0 0 3>;
+				cell-index = <3>;
+				clocks = <&cps_syscon0 1 21>;
 				status = "disabled";
 			};
 
@@ -140,7 +140,7 @@
 				reg = <0x700680 0x50>;
 				#address-cells = <1>;
 				#size-cells = <0>;
-				cell-index = <2>;
+				cell-index = <4>;
 				clocks = <&cps_syscon0 1 21>;
 				status = "disabled";
 			};
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 2065f46fa740..38b6a2b49d68 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -46,7 +46,15 @@
 #define	ARMV8_PMU_EVTYPE_MASK	0xc800ffff	/* Mask for writable bits */
 #define	ARMV8_PMU_EVTYPE_EVENT	0xffff		/* Mask for EVENT bits */
 
-#define ARMV8_PMU_EVTYPE_EVENT_SW_INCR	0	/* Software increment event */
+/*
+ * PMUv3 event types: required events
+ */
+#define ARMV8_PMUV3_PERFCTR_SW_INCR				0x00
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL			0x03
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE				0x04
+#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED				0x10
+#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES				0x11
+#define ARMV8_PMUV3_PERFCTR_BR_PRED				0x12
 
 /*
  * Event filters for PMUv3
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index a9310a69fffd..57ae9d9ed9bb 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -31,17 +31,9 @@
 
 /*
  * ARMv8 PMUv3 Performance Events handling code.
- * Common event types.
+ * Common event types (some are defined in asm/perf_event.h).
  */
 
-/* Required events. */
-#define ARMV8_PMUV3_PERFCTR_SW_INCR				0x00
-#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL			0x03
-#define ARMV8_PMUV3_PERFCTR_L1D_CACHE				0x04
-#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED				0x10
-#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES				0x11
-#define ARMV8_PMUV3_PERFCTR_BR_PRED				0x12
-
 /* At least one of the following is required. */
 #define ARMV8_PMUV3_PERFCTR_INST_RETIRED			0x08
 #define ARMV8_PMUV3_PERFCTR_INST_SPEC				0x1B
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index f302fdb3a030..87e7e6608cd8 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -597,8 +597,14 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
 
 			idx = ARMV8_PMU_CYCLE_IDX;
 		} else {
-			BUG();
+			return false;
 		}
+	} else if (r->CRn == 0 && r->CRm == 9) {
+		/* PMCCNTR */
+		if (pmu_access_event_counter_el0_disabled(vcpu))
+			return false;
+
+		idx = ARMV8_PMU_CYCLE_IDX;
 	} else if (r->CRn == 14 && (r->CRm & 12) == 8) {
 		/* PMEVCNTRn_EL0 */
 		if (pmu_access_event_counter_el0_disabled(vcpu))
@@ -606,7 +612,7 @@ static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
 
 		idx = ((r->CRm & 3) << 3) | (r->Op2 & 7);
 	} else {
-		BUG();
+		return false;
 	}
 
 	if (!pmu_counter_idx_valid(vcpu, idx))
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 84d49b197c32..9a3eee661297 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -91,7 +91,7 @@
  */
 #define LOAD_HANDLER(reg, label)					\
 	ld	reg,PACAKBASE(r13);	/* get high part of &label */	\
-	ori	reg,reg,(FIXED_SYMBOL_ABS_ADDR(label))@l;
+	ori	reg,reg,FIXED_SYMBOL_ABS_ADDR(label);
 
 #define __LOAD_HANDLER(reg, label)					\
 	ld	reg,PACAKBASE(r13);					\
@@ -158,14 +158,17 @@ BEGIN_FTR_SECTION_NESTED(943)						\
 	std	ra,offset(r13);						\
 END_FTR_SECTION_NESTED(ftr,ftr,943)
 
-#define EXCEPTION_PROLOG_0(area)					\
-	GET_PACA(r13);							\
+#define EXCEPTION_PROLOG_0_PACA(area)					\
 	std	r9,area+EX_R9(r13);	/* save r9 */			\
 	OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR);			\
 	HMT_MEDIUM;							\
 	std	r10,area+EX_R10(r13);	/* save r10 - r12 */		\
 	OPT_GET_SPR(r10, SPRN_CFAR, CPU_FTR_CFAR)
 
+#define EXCEPTION_PROLOG_0(area)					\
+	GET_PACA(r13);							\
+	EXCEPTION_PROLOG_0_PACA(area)
+
 #define __EXCEPTION_PROLOG_1(area, extra, vec)				\
 	OPT_SAVE_REG_TO_PACA(area+EX_PPR, r9, CPU_FTR_HAS_PPR);		\
 	OPT_SAVE_REG_TO_PACA(area+EX_CFAR, r10, CPU_FTR_CFAR);		\
@@ -196,6 +199,12 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	EXCEPTION_PROLOG_1(area, extra, vec);				\
 	EXCEPTION_PROLOG_PSERIES_1(label, h);
 
+/* Have the PACA in r13 already */
+#define EXCEPTION_PROLOG_PSERIES_PACA(area, label, h, extra, vec)	\
+	EXCEPTION_PROLOG_0_PACA(area);					\
+	EXCEPTION_PROLOG_1(area, extra, vec);				\
+	EXCEPTION_PROLOG_PSERIES_1(label, h);
+
 #define __KVMTEST(h, n)							\
 	lbz	r10,HSTATE_IN_GUEST(r13);				\
 	cmpwi	r10,0;							\
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 0132831b3081..c56ea8c84abb 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -460,5 +460,6 @@
 
 #define PPC_SLBIA(IH)	stringify_in_c(.long PPC_INST_SLBIA | \
 				       ((IH & 0x7) << 21))
+#define PPC_INVALIDATE_ERAT	PPC_SLBIA(7)
 
 #endif /* _ASM_POWERPC_PPC_OPCODE_H */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 08ba447a4b3d..1ba82ea90230 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -116,7 +116,9 @@ EXC_VIRT_NONE(0x4000, 0x4100)
 
 EXC_REAL_BEGIN(system_reset, 0x100, 0x200)
 	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
+	GET_PACA(r13)
+	clrrdi	r13,r13,1 /* Last bit of HSPRG0 is set if waking from winkle */
+	EXCEPTION_PROLOG_PSERIES_PACA(PACA_EXGEN, system_reset_common, EXC_STD,
 				 IDLETEST, 0x100)
 
 EXC_REAL_END(system_reset, 0x100, 0x200)
@@ -124,6 +126,9 @@ EXC_VIRT_NONE(0x4100, 0x4200)
 
 #ifdef CONFIG_PPC_P7_NAP
 EXC_COMMON_BEGIN(system_reset_idle_common)
+BEGIN_FTR_SECTION
+	GET_PACA(r13) /* Restore HSPRG0 to get the winkle bit in r13 */
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	bl	pnv_restore_hyp_resource
 
 	li	r0,PNV_THREAD_RUNNING
@@ -169,7 +174,7 @@ EXC_REAL_BEGIN(machine_check, 0x200, 0x300)
 	SET_SCRATCH0(r13)		/* save r13 */
 	/*
 	 * Running native on arch 2.06 or later, we may wakeup from winkle
-	 * inside machine check. If yes, then last bit of HSPGR0 would be set
+	 * inside machine check. If yes, then last bit of HSPRG0 would be set
 	 * to 1. Hence clear it unconditionally.
 	 */
 	GET_PACA(r13)
@@ -388,7 +393,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
 	/*
 	 * Go back to winkle. Please note that this thread was woken up in
 	 * machine check from winkle and have not restored the per-subcore
-	 * state. Hence before going back to winkle, set last bit of HSPGR0
+	 * state. Hence before going back to winkle, set last bit of HSPRG0
 	 * to 1. This will make sure that if this thread gets woken up
 	 * again at reset vector 0x100 then it will get chance to restore
 	 * the subcore state.
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index ce6dc61b15b2..49a680d5ae37 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1215,7 +1215,7 @@ static void show_instructions(struct pt_regs *regs)
 		int instr;
 
 		if (!(i % 8))
-			printk("\n");
+			pr_cont("\n");
 
 #if !defined(CONFIG_BOOKE)
 		/* If executing with the IMMU off, adjust pc rather
@@ -1227,18 +1227,18 @@ static void show_instructions(struct pt_regs *regs)
 
 		if (!__kernel_text_address(pc) ||
 		     probe_kernel_address((unsigned int __user *)pc, instr)) {
-			printk(KERN_CONT "XXXXXXXX ");
+			pr_cont("XXXXXXXX ");
 		} else {
 			if (regs->nip == pc)
-				printk(KERN_CONT "<%08x> ", instr);
+				pr_cont("<%08x> ", instr);
 			else
-				printk(KERN_CONT "%08x ", instr);
+				pr_cont("%08x ", instr);
 		}
 
 		pc += sizeof(int);
 	}
 
-	printk("\n");
+	pr_cont("\n");
 }
 
 struct regbit {
@@ -1282,7 +1282,7 @@ static void print_bits(unsigned long val, struct regbit *bits, const char *sep)
 
 	for (; bits->bit; ++bits)
 		if (val & bits->bit) {
-			printk("%s%s", s, bits->name);
+			pr_cont("%s%s", s, bits->name);
 			s = sep;
 		}
 }
@@ -1305,9 +1305,9 @@ static void print_tm_bits(unsigned long val)
  *   T: Transactional	(bit 34)
  */
 	if (val & (MSR_TM | MSR_TS_S | MSR_TS_T)) {
-		printk(",TM[");
+		pr_cont(",TM[");
 		print_bits(val, msr_tm_bits, "");
-		printk("]");
+		pr_cont("]");
 	}
 }
 #else
@@ -1316,10 +1316,10 @@ static void print_tm_bits(unsigned long val) {}
 
 static void print_msr_bits(unsigned long val)
 {
-	printk("<");
+	pr_cont("<");
 	print_bits(val, msr_bits, ",");
 	print_tm_bits(val);
-	printk(">");
+	pr_cont(">");
 }
 
 #ifdef CONFIG_PPC64
@@ -1347,29 +1347,29 @@ void show_regs(struct pt_regs * regs)
 	printk("  CR: %08lx  XER: %08lx\n", regs->ccr, regs->xer);
 	trap = TRAP(regs);
 	if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR))
-		printk("CFAR: "REG" ", regs->orig_gpr3);
+		pr_cont("CFAR: "REG" ", regs->orig_gpr3);
 	if (trap == 0x200 || trap == 0x300 || trap == 0x600)
 #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
-		printk("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr);
+		pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr);
 #else
-		printk("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
+		pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr);
 #endif
 #ifdef CONFIG_PPC64
-	printk("SOFTE: %ld ", regs->softe);
+	pr_cont("SOFTE: %ld ", regs->softe);
 #endif
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	if (MSR_TM_ACTIVE(regs->msr))
-		printk("\nPACATMSCRATCH: %016llx ", get_paca()->tm_scratch);
+		pr_cont("\nPACATMSCRATCH: %016llx ", get_paca()->tm_scratch);
 #endif
 
 	for (i = 0;  i < 32;  i++) {
 		if ((i % REGS_PER_LINE) == 0)
-			printk("\nGPR%02d: ", i);
-		printk(REG " ", regs->gpr[i]);
+			pr_cont("\nGPR%02d: ", i);
+		pr_cont(REG " ", regs->gpr[i]);
 		if (i == LAST_VOLATILE && !FULL_REGS(regs))
 			break;
 	}
-	printk("\n");
+	pr_cont("\n");
 #ifdef CONFIG_KALLSYMS
 	/*
 	 * Lookup NIP late so we have the best change of getting the
@@ -1900,14 +1900,14 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
 			printk("["REG"] ["REG"] %pS", sp, ip, (void *)ip);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 			if ((ip == rth) && curr_frame >= 0) {
-				printk(" (%pS)",
+				pr_cont(" (%pS)",
 				       (void *)current->ret_stack[curr_frame].ret);
 				curr_frame--;
 			}
 #endif
 			if (firstframe)
-				printk(" (unreliable)");
-			printk("\n");
+				pr_cont(" (unreliable)");
+			pr_cont("\n");
 		}
 		firstframe = 0;
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 7ac8e6eaab5b..8d586cff8a41 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -226,17 +226,25 @@ static void __init configure_exceptions(void)
 		if (firmware_has_feature(FW_FEATURE_OPAL))
 			opal_configure_cores();
 
-		/* Enable AIL if supported, and we are in hypervisor mode */
-		if (early_cpu_has_feature(CPU_FTR_HVMODE) &&
-		    early_cpu_has_feature(CPU_FTR_ARCH_207S)) {
-			unsigned long lpcr = mfspr(SPRN_LPCR);
-			mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3);
-		}
+		/* AIL on native is done in cpu_ready_for_interrupts() */
 	}
 }
 
 static void cpu_ready_for_interrupts(void)
 {
+	/*
+	 * Enable AIL if supported, and we are in hypervisor mode. This
+	 * is called once for every processor.
+	 *
+	 * If we are not in hypervisor mode the job is done once for
+	 * the whole partition in configure_exceptions().
+	 */
+	if (early_cpu_has_feature(CPU_FTR_HVMODE) &&
+	    early_cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		unsigned long lpcr = mfspr(SPRN_LPCR);
+		mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3);
+	}
+
 	/* Set IR and DR in PACA MSR */
 	get_paca()->kernel_msr = MSR_KERNEL;
 }
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 44d3c3a38e3e..5503078090cd 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -1029,6 +1029,10 @@ void hash__early_init_mmu_secondary(void)
 {
 	/* Initialize hash table for that CPU */
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+
+		if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+			update_hid_for_hash();
+
 		if (!cpu_has_feature(CPU_FTR_ARCH_300))
 			mtspr(SPRN_SDR1, _SDR1);
 		else
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index ed7bddc456b7..688b54517655 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -388,6 +388,10 @@ void radix__early_init_mmu_secondary(void)
 	 * update partition table control register and UPRT
 	 */
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+
+		if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+			update_hid_for_radix();
+
 		lpcr = mfspr(SPRN_LPCR);
 		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
 
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index bda8c43be78a..3493cf4e0452 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -50,6 +50,8 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 	for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) {
 		__tlbiel_pid(pid, set, ric);
 	}
+	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+		asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
 	return;
 }
 
@@ -83,6 +85,8 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid,
 	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
 	asm volatile("ptesync": : :"memory");
+	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+		asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
 }
 
 static inline void _tlbie_va(unsigned long va, unsigned long pid,
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index b23c76b42d6e..165ecdd24d22 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -43,6 +43,7 @@ config SPARC
 	select ARCH_HAS_SG_CHAIN
 	select CPU_NO_EFFICIENT_FFS
 	select HAVE_ARCH_HARDENED_USERCOPY
+	select PROVE_LOCKING_SMALL if PROVE_LOCKING
 
 config SPARC32
 	def_bool !64BIT
@@ -89,6 +90,14 @@ config ARCH_DEFCONFIG
 config ARCH_PROC_KCORE_TEXT
 	def_bool y
 
+config ARCH_ATU
+	bool
+	default y if SPARC64
+
+config ARCH_DMA_ADDR_T_64BIT
+	bool
+	default y if ARCH_ATU
+
 config IOMMU_HELPER
 	bool
 	default y if SPARC64
@@ -304,6 +313,20 @@ config ARCH_SPARSEMEM_ENABLE
 config ARCH_SPARSEMEM_DEFAULT
 	def_bool y if SPARC64
 
+config FORCE_MAX_ZONEORDER
+	int "Maximum zone order"
+	default "13"
+	help
+	  The kernel memory allocator divides physically contiguous memory
+	  blocks into "zones", where each zone is a power of two number of
+	  pages.  This option selects the largest power of two that the kernel
+	  keeps in the memory allocator.  If you need to allocate very large
+	  blocks of physically contiguous memory, then you may need to
+	  increase this value.
+
+	  This config option is actually maximum order plus one. For example,
+	  a value of 13 means that the largest free memory block is 2^12 pages.
+
 source "mm/Kconfig"
 
 if SPARC64
diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h
index 666d5ba230d2..73cb8978df58 100644
--- a/arch/sparc/include/asm/hypervisor.h
+++ b/arch/sparc/include/asm/hypervisor.h
@@ -2335,6 +2335,348 @@ unsigned long sun4v_vintr_set_target(unsigned long dev_handle,
  */
 #define HV_FAST_PCI_MSG_SETVALID	0xd3
 
+/* PCI IOMMU v2 definitions and services
+ *
+ * While the PCI IO definitions above is valid IOMMU v2 adds new PCI IO
+ * definitions and services.
+ *
+ *	CTE		Clump Table Entry. First level table entry in the ATU.
+ *
+ *	pci_device_list
+ *			A 32-bit aligned list of pci_devices.
+ *
+ *	pci_device_listp
+ *			real address of a pci_device_list. 32-bit aligned.
+ *
+ *	iotte		IOMMU translation table entry.
+ *
+ *	iotte_attributes
+ *			IO Attributes for IOMMU v2 mappings. In addition to
+ *			read, write IOMMU v2 supports relax ordering
+ *
+ *	io_page_list	A 64-bit aligned list of real addresses. Each real
+ *			address in an io_page_list must be properly aligned
+ *			to the pagesize of the given IOTSB.
+ *
+ *	io_page_list_p	Real address of an io_page_list, 64-bit aligned.
+ *
+ *	IOTSB		IO Translation Storage Buffer. An aligned table of
+ *			IOTTEs. Each IOTSB has a pagesize, table size, and
+ *			virtual address associated with it that must match
+ *			a pagesize and table size supported by the un-derlying
+ *			hardware implementation. The alignment requirements
+ *			for an IOTSB depend on the pagesize used for that IOTSB.
+ *			Each IOTTE in an IOTSB maps one pagesize-sized page.
+ *			The size of the IOTSB dictates how large of a virtual
+ *			address space the IOTSB is capable of mapping.
+ *
+ *	iotsb_handle	An opaque identifier for an IOTSB. A devhandle plus
+ *			iotsb_handle represents a binding of an IOTSB to a
+ *			PCI root complex.
+ *
+ *	iotsb_index	Zero-based IOTTE number within an IOTSB.
+ */
+
+/* The index_count argument consists of two fields:
+ * bits 63:48 #iottes and bits 47:0 iotsb_index
+ */
+#define HV_PCI_IOTSB_INDEX_COUNT(__iottes, __iotsb_index) \
+	(((u64)(__iottes) << 48UL) | ((u64)(__iotsb_index)))
+
+/* pci_iotsb_conf()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_CONF
+ * ARG0:	devhandle
+ * ARG1:	r_addr
+ * ARG2:	size
+ * ARG3:	pagesize
+ * ARG4:	iova
+ * RET0:	status
+ * RET1:	iotsb_handle
+ * ERRORS:	EINVAL		Invalid devhandle, size, iova, or pagesize
+ *		EBADALIGN	r_addr is not properly aligned
+ *		ENORADDR	r_addr is not a valid real address
+ *		ETOOMANY	No further IOTSBs may be configured
+ *		EBUSY		Duplicate devhandle, raddir, iova combination
+ *
+ * Create an IOTSB suitable for the PCI root complex identified by devhandle,
+ * for the DMA virtual address defined by the argument iova.
+ *
+ * r_addr is the properly aligned base address of the IOTSB and size is the
+ * IOTSB (table) size in bytes.The IOTSB is required to be zeroed prior to
+ * being configured. If it contains any values other than zeros then the
+ * behavior is undefined.
+ *
+ * pagesize is the size of each page in the IOTSB. Note that the combination of
+ * size (table size) and pagesize must be valid.
+ *
+ * virt is the DMA virtual address this IOTSB will map.
+ *
+ * If successful, the opaque 64-bit handle iotsb_handle is returned in ret1.
+ * Once configured, privileged access to the IOTSB memory is prohibited and
+ * creates undefined behavior. The only permitted access is indirect via these
+ * services.
+ */
+#define HV_FAST_PCI_IOTSB_CONF		0x190
+
+/* pci_iotsb_info()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_INFO
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * RET0:	status
+ * RET1:	r_addr
+ * RET2:	size
+ * RET3:	pagesize
+ * RET4:	iova
+ * RET5:	#bound
+ * ERRORS:	EINVAL	Invalid devhandle or iotsb_handle
+ *
+ * This service returns configuration information about an IOTSB previously
+ * created with pci_iotsb_conf.
+ *
+ * iotsb_handle value 0 may be used with this service to inquire about the
+ * legacy IOTSB that may or may not exist. If the service succeeds, the return
+ * values describe the legacy IOTSB and I/O virtual addresses mapped by that
+ * table. However, the table base address r_addr may contain the value -1 which
+ * indicates a memory range that cannot be accessed or be reclaimed.
+ *
+ * The return value #bound contains the number of PCI devices that iotsb_handle
+ * is currently bound to.
+ */
+#define HV_FAST_PCI_IOTSB_INFO		0x191
+
+/* pci_iotsb_unconf()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_UNCONF
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * RET0:	status
+ * ERRORS:	EINVAL	Invalid devhandle or iotsb_handle
+ *		EBUSY	The IOTSB is bound and may not be unconfigured
+ *
+ * This service unconfigures the IOTSB identified by the devhandle and
+ * iotsb_handle arguments, previously created with pci_iotsb_conf.
+ * The IOTSB must not be currently bound to any device or the service will fail
+ *
+ * If the call succeeds, iotsb_handle is no longer valid.
+ */
+#define HV_FAST_PCI_IOTSB_UNCONF	0x192
+
+/* pci_iotsb_bind()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_BIND
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * ARG2:	pci_device
+ * RET0:	status
+ * ERRORS:	EINVAL	Invalid devhandle, iotsb_handle, or pci_device
+ *		EBUSY	A PCI function is already bound to an IOTSB at the same
+ *			address range as specified by devhandle, iotsb_handle.
+ *
+ * This service binds the PCI function specified by the argument pci_device to
+ * the IOTSB specified by the arguments devhandle and iotsb_handle.
+ *
+ * The PCI device function is bound to the specified IOTSB with the IOVA range
+ * specified when the IOTSB was configured via pci_iotsb_conf. If the function
+ * is already bound then it is unbound first.
+ */
+#define HV_FAST_PCI_IOTSB_BIND		0x193
+
+/* pci_iotsb_unbind()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_UNBIND
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * ARG2:	pci_device
+ * RET0:	status
+ * ERRORS:	EINVAL	Invalid devhandle, iotsb_handle, or pci_device
+ *		ENOMAP	The PCI function was not bound to the specified IOTSB
+ *
+ * This service unbinds the PCI device specified by the argument pci_device
+ * from the IOTSB identified  * by the arguments devhandle and iotsb_handle.
+ *
+ * If the PCI device is not bound to the specified IOTSB then this service will
+ * fail with status ENOMAP
+ */
+#define HV_FAST_PCI_IOTSB_UNBIND	0x194
+
+/* pci_iotsb_get_binding()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_GET_BINDING
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * ARG2:	iova
+ * RET0:	status
+ * RET1:	iotsb_handle
+ * ERRORS:	EINVAL	Invalid devhandle, pci_device, or iova
+ *		ENOMAP	The PCI function is not bound to an IOTSB at iova
+ *
+ * This service returns the IOTSB binding, iotsb_handle, for a given pci_device
+ * and DMA virtual address, iova.
+ *
+ * iova must be the base address of a DMA virtual address range as defined by
+ * the iommu-address-ranges property in the root complex device node defined
+ * by the argument devhandle.
+ */
+#define HV_FAST_PCI_IOTSB_GET_BINDING	0x195
+
+/* pci_iotsb_map()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_MAP
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * ARG2:	index_count
+ * ARG3:	iotte_attributes
+ * ARG4:	io_page_list_p
+ * RET0:	status
+ * RET1:	#mapped
+ * ERRORS:	EINVAL		Invalid devhandle, iotsb_handle, #iottes,
+ *				iotsb_index or iotte_attributes
+ *		EBADALIGN	Improperly aligned io_page_list_p or I/O page
+ *				address in the I/O page list.
+ *		ENORADDR	Invalid io_page_list_p or I/O page address in
+ *				the I/O page list.
+ *
+ * This service creates and flushes mappings in the IOTSB defined by the
+ * arguments devhandle, iotsb.
+ *
+ * The index_count argument consists of two fields. Bits 63:48 contain #iotte
+ * and bits 47:0 contain iotsb_index
+ *
+ * The first mapping is created in the IOTSB index specified by iotsb_index.
+ * Subsequent mappings are  created at iotsb_index+1 and so on.
+ *
+ * The attributes of each mapping are defined by the argument iotte_attributes.
+ *
+ * The io_page_list_p specifies the real address of the 64-bit-aligned list of
+ * #iottes I/O page addresses. Each page address must be a properly aligned
+ * real address of a page to be mapped in the IOTSB. The first entry in the I/O
+ * page list contains the real address of the first page, the 2nd entry for the
+ * 2nd page, and so on.
+ *
+ * #iottes must be greater than zero.
+ *
+ * The return value #mapped is the actual number of mappings created, which may
+ * be less than or equal to the argument #iottes. If the function returns
+ * successfully with a #mapped value less than the requested #iottes then the
+ * caller should continue to invoke the service with updated iotsb_index,
+ * #iottes, and io_page_list_p arguments until all pages are mapped.
+ *
+ * This service must not be used to demap a mapping. In other words, all
+ * mappings must be valid and have  one or both of the RW attribute bits set.
+ *
+ * Note:
+ * It is implementation-defined whether I/O page real address validity checking
+ * is done at time mappings are established or deferred until they are
+ * accessed.
+ */
+#define HV_FAST_PCI_IOTSB_MAP		0x196
+
+/* pci_iotsb_map_one()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_MAP_ONE
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * ARG2:	iotsb_index
+ * ARG3:	iotte_attributes
+ * ARG4:	r_addr
+ * RET0:	status
+ * ERRORS:	EINVAL		Invalid devhandle,iotsb_handle, iotsb_index
+ *				or iotte_attributes
+ *		EBADALIGN	Improperly aligned r_addr
+ *		ENORADDR	Invalid r_addr
+ *
+ * This service creates and flushes a single mapping in the IOTSB defined by the
+ * arguments devhandle, iotsb.
+ *
+ * The mapping for the page at r_addr is created at the IOTSB index specified by
+ * iotsb_index with  the attributes iotte_attributes.
+ *
+ * This service must not be used to demap a mapping. In other words, the mapping
+ * must be valid and have one or both of the RW attribute bits set.
+ *
+ * Note:
+ * It is implementation-defined whether I/O page real address validity checking
+ * is done at time mappings are established or deferred until they are
+ * accessed.
+ */
+#define HV_FAST_PCI_IOTSB_MAP_ONE	0x197
+
+/* pci_iotsb_demap()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_DEMAP
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * ARG2:	iotsb_index
+ * ARG3:	#iottes
+ * RET0:	status
+ * RET1:	#unmapped
+ * ERRORS:	EINVAL	Invalid devhandle, iotsb_handle, iotsb_index or #iottes
+ *
+ * This service unmaps and flushes up to #iottes mappings starting at index
+ * iotsb_index from the IOTSB defined by the arguments devhandle, iotsb.
+ *
+ * #iottes must be greater than zero.
+ *
+ * The actual number of IOTTEs unmapped is returned in #unmapped and may be less
+ * than or equal to the requested number of IOTTEs, #iottes.
+ *
+ * If #unmapped is less than #iottes, the caller should continue to invoke this
+ * service with updated iotsb_index and #iottes arguments until all pages are
+ * demapped.
+ */
+#define HV_FAST_PCI_IOTSB_DEMAP		0x198
+
+/* pci_iotsb_getmap()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_GETMAP
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * ARG2:	iotsb_index
+ * RET0:	status
+ * RET1:	r_addr
+ * RET2:	iotte_attributes
+ * ERRORS:	EINVAL	Invalid devhandle, iotsb_handle, or iotsb_index
+ *		ENOMAP	No mapping was found
+ *
+ * This service returns the mapping specified by index iotsb_index from the
+ * IOTSB defined by the arguments devhandle, iotsb.
+ *
+ * Upon success, the real address of the mapping shall be returned in
+ * r_addr and thethe IOTTE mapping attributes shall be returned in
+ * iotte_attributes.
+ *
+ * The return value iotte_attributes may not include optional features used in
+ * the call to create the  mapping.
+ */
+#define HV_FAST_PCI_IOTSB_GETMAP	0x199
+
+/* pci_iotsb_sync_mappings()
+ * TRAP:	HV_FAST_TRAP
+ * FUNCTION:	HV_FAST_PCI_IOTSB_SYNC_MAPPINGS
+ * ARG0:	devhandle
+ * ARG1:	iotsb_handle
+ * ARG2:	iotsb_index
+ * ARG3:	#iottes
+ * RET0:	status
+ * RET1:	#synced
+ * ERROS:	EINVAL	Invalid devhandle, iotsb_handle, iotsb_index, or #iottes
+ *
+ * This service synchronizes #iottes mappings starting at index iotsb_index in
+ * the IOTSB defined by the arguments devhandle, iotsb.
+ *
+ * #iottes must be greater than zero.
+ *
+ * The actual number of IOTTEs synchronized is returned in #synced, which may
+ * be less than or equal to the requested number, #iottes.
+ *
+ * Upon a successful return, #synced is less than #iottes, the caller should
+ * continue to invoke this service with updated iotsb_index and #iottes
+ * arguments until all pages are synchronized.
+ */
+#define HV_FAST_PCI_IOTSB_SYNC_MAPPINGS	0x19a
+
 /* Logical Domain Channel services.  */
 
 #define LDC_CHANNEL_DOWN		0
@@ -2993,6 +3335,7 @@ unsigned long sun4v_m7_set_perfreg(unsigned long reg_num,
 #define HV_GRP_SDIO			0x0108
 #define HV_GRP_SDIO_ERR			0x0109
 #define HV_GRP_REBOOT_DATA		0x0110
+#define HV_GRP_ATU			0x0111
 #define HV_GRP_M7_PERF			0x0114
 #define HV_GRP_NIAG_PERF		0x0200
 #define HV_GRP_FIRE_PERF		0x0201
diff --git a/arch/sparc/include/asm/iommu_64.h b/arch/sparc/include/asm/iommu_64.h
index cd0d69fa7592..f24f356f2503 100644
--- a/arch/sparc/include/asm/iommu_64.h
+++ b/arch/sparc/include/asm/iommu_64.h
@@ -24,8 +24,36 @@ struct iommu_arena {
 	unsigned int	limit;
 };
 
+#define ATU_64_SPACE_SIZE 0x800000000 /* 32G */
+
+/* Data structures for SPARC ATU architecture */
+struct atu_iotsb {
+	void	*table;		/* IOTSB table base virtual addr*/
+	u64	ra;		/* IOTSB table real addr */
+	u64	dvma_size;	/* ranges[3].size or OS slected 32G size */
+	u64	dvma_base;	/* ranges[3].base */
+	u64	table_size;	/* IOTSB table size */
+	u64	page_size;	/* IO PAGE size for IOTSB */
+	u32	iotsb_num;	/* tsbnum is same as iotsb_handle */
+};
+
+struct atu_ranges {
+	u64	base;
+	u64	size;
+};
+
+struct atu {
+	struct	atu_ranges	*ranges;
+	struct	atu_iotsb	*iotsb;
+	struct	iommu_map_table	tbl;
+	u64			base;
+	u64			size;
+	u64			dma_addr_mask;
+};
+
 struct iommu {
 	struct iommu_map_table	tbl;
+	struct atu		*atu;
 	spinlock_t		lock;
 	u32			dma_addr_mask;
 	iopte_t			*page_table;
diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c
index 662500fa555f..267731234ce8 100644
--- a/arch/sparc/kernel/hvapi.c
+++ b/arch/sparc/kernel/hvapi.c
@@ -39,6 +39,7 @@ static struct api_info api_table[] = {
 	{ .group = HV_GRP_SDIO,					},
 	{ .group = HV_GRP_SDIO_ERR,				},
 	{ .group = HV_GRP_REBOOT_DATA,				},
+	{ .group = HV_GRP_ATU,		.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_NIAG_PERF,	.flags = FLAG_PRE_API	},
 	{ .group = HV_GRP_FIRE_PERF,				},
 	{ .group = HV_GRP_N2_CPU,				},
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 5c615abff030..852a3291db96 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -760,8 +760,12 @@ int dma_supported(struct device *dev, u64 device_mask)
 	struct iommu *iommu = dev->archdata.iommu;
 	u64 dma_addr_mask = iommu->dma_addr_mask;
 
-	if (device_mask >= (1UL << 32UL))
-		return 0;
+	if (device_mask > DMA_BIT_MASK(32)) {
+		if (iommu->atu)
+			dma_addr_mask = iommu->atu->dma_addr_mask;
+		else
+			return 0;
+	}
 
 	if ((device_mask & dma_addr_mask) == dma_addr_mask)
 		return 1;
diff --git a/arch/sparc/kernel/iommu_common.h b/arch/sparc/kernel/iommu_common.h
index b40cec252905..828493329f68 100644
--- a/arch/sparc/kernel/iommu_common.h
+++ b/arch/sparc/kernel/iommu_common.h
@@ -13,7 +13,6 @@
 #include <linux/scatterlist.h>
 #include <linux/device.h>
 #include <linux/iommu-helper.h>
-#include <linux/scatterlist.h>
 
 #include <asm/iommu.h>
 
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index db57d8acdc01..06981cc716b6 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -44,6 +44,9 @@ static struct vpci_version vpci_versions[] = {
 	{ .major = 1, .minor = 1 },
 };
 
+static unsigned long vatu_major = 1;
+static unsigned long vatu_minor = 1;
+
 #define PGLIST_NENTS	(PAGE_SIZE / sizeof(u64))
 
 struct iommu_batch {
@@ -69,34 +72,57 @@ static inline void iommu_batch_start(struct device *dev, unsigned long prot, uns
 }
 
 /* Interrupts must be disabled.  */
-static long iommu_batch_flush(struct iommu_batch *p)
+static long iommu_batch_flush(struct iommu_batch *p, u64 mask)
 {
 	struct pci_pbm_info *pbm = p->dev->archdata.host_controller;
+	u64 *pglist = p->pglist;
+	u64 index_count;
 	unsigned long devhandle = pbm->devhandle;
 	unsigned long prot = p->prot;
 	unsigned long entry = p->entry;
-	u64 *pglist = p->pglist;
 	unsigned long npages = p->npages;
+	unsigned long iotsb_num;
+	unsigned long ret;
+	long num;
 
 	/* VPCI maj=1, min=[0,1] only supports read and write */
 	if (vpci_major < 2)
 		prot &= (HV_PCI_MAP_ATTR_READ | HV_PCI_MAP_ATTR_WRITE);
 
 	while (npages != 0) {
-		long num;
-
-		num = pci_sun4v_iommu_map(devhandle, HV_PCI_TSBID(0, entry),
-					  npages, prot, __pa(pglist));
-		if (unlikely(num < 0)) {
-			if (printk_ratelimit())
-				printk("iommu_batch_flush: IOMMU map of "
-				       "[%08lx:%08llx:%lx:%lx:%lx] failed with "
-				       "status %ld\n",
-				       devhandle, HV_PCI_TSBID(0, entry),
-				       npages, prot, __pa(pglist), num);
-			return -1;
+		if (mask <= DMA_BIT_MASK(32)) {
+			num = pci_sun4v_iommu_map(devhandle,
+						  HV_PCI_TSBID(0, entry),
+						  npages,
+						  prot,
+						  __pa(pglist));
+			if (unlikely(num < 0)) {
+				pr_err_ratelimited("%s: IOMMU map of [%08lx:%08llx:%lx:%lx:%lx] failed with status %ld\n",
+						   __func__,
+						   devhandle,
+						   HV_PCI_TSBID(0, entry),
+						   npages, prot, __pa(pglist),
+						   num);
+				return -1;
+			}
+		} else {
+			index_count = HV_PCI_IOTSB_INDEX_COUNT(npages, entry),
+			iotsb_num = pbm->iommu->atu->iotsb->iotsb_num;
+			ret = pci_sun4v_iotsb_map(devhandle,
+						  iotsb_num,
+						  index_count,
+						  prot,
+						  __pa(pglist),
+						  &num);
+			if (unlikely(ret != HV_EOK)) {
+				pr_err_ratelimited("%s: ATU map of [%08lx:%lx:%llx:%lx:%lx] failed with status %ld\n",
+						   __func__,
+						   devhandle, iotsb_num,
+						   index_count, prot,
+						   __pa(pglist), ret);
+				return -1;
+			}
 		}
-
 		entry += num;
 		npages -= num;
 		pglist += num;
@@ -108,19 +134,19 @@ static long iommu_batch_flush(struct iommu_batch *p)
 	return 0;
 }
 
-static inline void iommu_batch_new_entry(unsigned long entry)
+static inline void iommu_batch_new_entry(unsigned long entry, u64 mask)
 {
 	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	if (p->entry + p->npages == entry)
 		return;
 	if (p->entry != ~0UL)
-		iommu_batch_flush(p);
+		iommu_batch_flush(p, mask);
 	p->entry = entry;
 }
 
 /* Interrupts must be disabled.  */
-static inline long iommu_batch_add(u64 phys_page)
+static inline long iommu_batch_add(u64 phys_page, u64 mask)
 {
 	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
@@ -128,28 +154,31 @@ static inline long iommu_batch_add(u64 phys_page)
 
 	p->pglist[p->npages++] = phys_page;
 	if (p->npages == PGLIST_NENTS)
-		return iommu_batch_flush(p);
+		return iommu_batch_flush(p, mask);
 
 	return 0;
 }
 
 /* Interrupts must be disabled.  */
-static inline long iommu_batch_end(void)
+static inline long iommu_batch_end(u64 mask)
 {
 	struct iommu_batch *p = this_cpu_ptr(&iommu_batch);
 
 	BUG_ON(p->npages >= PGLIST_NENTS);
 
-	return iommu_batch_flush(p);
+	return iommu_batch_flush(p, mask);
 }
 
 static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
 				   dma_addr_t *dma_addrp, gfp_t gfp,
 				   unsigned long attrs)
 {
+	u64 mask;
 	unsigned long flags, order, first_page, npages, n;
 	unsigned long prot = 0;
 	struct iommu *iommu;
+	struct atu *atu;
+	struct iommu_map_table *tbl;
 	struct page *page;
 	void *ret;
 	long entry;
@@ -174,14 +203,21 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
 	memset((char *)first_page, 0, PAGE_SIZE << order);
 
 	iommu = dev->archdata.iommu;
+	atu = iommu->atu;
+
+	mask = dev->coherent_dma_mask;
+	if (mask <= DMA_BIT_MASK(32))
+		tbl = &iommu->tbl;
+	else
+		tbl = &atu->tbl;
 
-	entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages, NULL,
+	entry = iommu_tbl_range_alloc(dev, tbl, npages, NULL,
 				      (unsigned long)(-1), 0);
 
 	if (unlikely(entry == IOMMU_ERROR_CODE))
 		goto range_alloc_fail;
 
-	*dma_addrp = (iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT));
+	*dma_addrp = (tbl->table_map_base + (entry << IO_PAGE_SHIFT));
 	ret = (void *) first_page;
 	first_page = __pa(first_page);
 
@@ -193,12 +229,12 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
 			  entry);
 
 	for (n = 0; n < npages; n++) {
-		long err = iommu_batch_add(first_page + (n * PAGE_SIZE));
+		long err = iommu_batch_add(first_page + (n * PAGE_SIZE), mask);
 		if (unlikely(err < 0L))
 			goto iommu_map_fail;
 	}
 
-	if (unlikely(iommu_batch_end() < 0L))
+	if (unlikely(iommu_batch_end(mask) < 0L))
 		goto iommu_map_fail;
 
 	local_irq_restore(flags);
@@ -206,25 +242,71 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
 	return ret;
 
 iommu_map_fail:
-	iommu_tbl_range_free(&iommu->tbl, *dma_addrp, npages, IOMMU_ERROR_CODE);
+	iommu_tbl_range_free(tbl, *dma_addrp, npages, IOMMU_ERROR_CODE);
 
 range_alloc_fail:
 	free_pages(first_page, order);
 	return NULL;
 }
 
-static void dma_4v_iommu_demap(void *demap_arg, unsigned long entry,
-			       unsigned long npages)
+unsigned long dma_4v_iotsb_bind(unsigned long devhandle,
+				unsigned long iotsb_num,
+				struct pci_bus *bus_dev)
+{
+	struct pci_dev *pdev;
+	unsigned long err;
+	unsigned int bus;
+	unsigned int device;
+	unsigned int fun;
+
+	list_for_each_entry(pdev, &bus_dev->devices, bus_list) {
+		if (pdev->subordinate) {
+			/* No need to bind pci bridge */
+			dma_4v_iotsb_bind(devhandle, iotsb_num,
+					  pdev->subordinate);
+		} else {
+			bus = bus_dev->number;
+			device = PCI_SLOT(pdev->devfn);
+			fun = PCI_FUNC(pdev->devfn);
+			err = pci_sun4v_iotsb_bind(devhandle, iotsb_num,
+						   HV_PCI_DEVICE_BUILD(bus,
+								       device,
+								       fun));
+
+			/* If bind fails for one device it is going to fail
+			 * for rest of the devices because we are sharing
+			 * IOTSB. So in case of failure simply return with
+			 * error.
+			 */
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static void dma_4v_iommu_demap(struct device *dev, unsigned long devhandle,
+			       dma_addr_t dvma, unsigned long iotsb_num,
+			       unsigned long entry, unsigned long npages)
 {
-	u32 devhandle = *(u32 *)demap_arg;
 	unsigned long num, flags;
+	unsigned long ret;
 
 	local_irq_save(flags);
 	do {
-		num = pci_sun4v_iommu_demap(devhandle,
-					    HV_PCI_TSBID(0, entry),
-					    npages);
-
+		if (dvma <= DMA_BIT_MASK(32)) {
+			num = pci_sun4v_iommu_demap(devhandle,
+						    HV_PCI_TSBID(0, entry),
+						    npages);
+		} else {
+			ret = pci_sun4v_iotsb_demap(devhandle, iotsb_num,
+						    entry, npages, &num);
+			if (unlikely(ret != HV_EOK)) {
+				pr_err_ratelimited("pci_iotsb_demap() failed with error: %ld\n",
+						   ret);
+			}
+		}
 		entry += num;
 		npages -= num;
 	} while (npages != 0);
@@ -236,16 +318,28 @@ static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu,
 {
 	struct pci_pbm_info *pbm;
 	struct iommu *iommu;
+	struct atu *atu;
+	struct iommu_map_table *tbl;
 	unsigned long order, npages, entry;
+	unsigned long iotsb_num;
 	u32 devhandle;
 
 	npages = IO_PAGE_ALIGN(size) >> IO_PAGE_SHIFT;
 	iommu = dev->archdata.iommu;
 	pbm = dev->archdata.host_controller;
+	atu = iommu->atu;
 	devhandle = pbm->devhandle;
-	entry = ((dvma - iommu->tbl.table_map_base) >> IO_PAGE_SHIFT);
-	dma_4v_iommu_demap(&devhandle, entry, npages);
-	iommu_tbl_range_free(&iommu->tbl, dvma, npages, IOMMU_ERROR_CODE);
+
+	if (dvma <= DMA_BIT_MASK(32)) {
+		tbl = &iommu->tbl;
+		iotsb_num = 0; /* we don't care for legacy iommu */
+	} else {
+		tbl = &atu->tbl;
+		iotsb_num = atu->iotsb->iotsb_num;
+	}
+	entry = ((dvma - tbl->table_map_base) >> IO_PAGE_SHIFT);
+	dma_4v_iommu_demap(dev, devhandle, dvma, iotsb_num, entry, npages);
+	iommu_tbl_range_free(tbl, dvma, npages, IOMMU_ERROR_CODE);
 	order = get_order(size);
 	if (order < 10)
 		free_pages((unsigned long)cpu, order);
@@ -257,13 +351,17 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
 				  unsigned long attrs)
 {
 	struct iommu *iommu;
+	struct atu *atu;
+	struct iommu_map_table *tbl;
+	u64 mask;
 	unsigned long flags, npages, oaddr;
 	unsigned long i, base_paddr;
-	u32 bus_addr, ret;
 	unsigned long prot;
+	dma_addr_t bus_addr, ret;
 	long entry;
 
 	iommu = dev->archdata.iommu;
+	atu = iommu->atu;
 
 	if (unlikely(direction == DMA_NONE))
 		goto bad;
@@ -272,13 +370,19 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
 	npages = IO_PAGE_ALIGN(oaddr + sz) - (oaddr & IO_PAGE_MASK);
 	npages >>= IO_PAGE_SHIFT;
 
-	entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages, NULL,
+	mask = *dev->dma_mask;
+	if (mask <= DMA_BIT_MASK(32))
+		tbl = &iommu->tbl;
+	else
+		tbl = &atu->tbl;
+
+	entry = iommu_tbl_range_alloc(dev, tbl, npages, NULL,
 				      (unsigned long)(-1), 0);
 
 	if (unlikely(entry == IOMMU_ERROR_CODE))
 		goto bad;
 
-	bus_addr = (iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT));
+	bus_addr = (tbl->table_map_base + (entry << IO_PAGE_SHIFT));
 	ret = bus_addr | (oaddr & ~IO_PAGE_MASK);
 	base_paddr = __pa(oaddr & IO_PAGE_MASK);
 	prot = HV_PCI_MAP_ATTR_READ;
@@ -293,11 +397,11 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
 	iommu_batch_start(dev, prot, entry);
 
 	for (i = 0; i < npages; i++, base_paddr += IO_PAGE_SIZE) {
-		long err = iommu_batch_add(base_paddr);
+		long err = iommu_batch_add(base_paddr, mask);
 		if (unlikely(err < 0L))
 			goto iommu_map_fail;
 	}
-	if (unlikely(iommu_batch_end() < 0L))
+	if (unlikely(iommu_batch_end(mask) < 0L))
 		goto iommu_map_fail;
 
 	local_irq_restore(flags);
@@ -310,7 +414,7 @@ bad:
 	return DMA_ERROR_CODE;
 
 iommu_map_fail:
-	iommu_tbl_range_free(&iommu->tbl, bus_addr, npages, IOMMU_ERROR_CODE);
+	iommu_tbl_range_free(tbl, bus_addr, npages, IOMMU_ERROR_CODE);
 	return DMA_ERROR_CODE;
 }
 
@@ -320,7 +424,10 @@ static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr,
 {
 	struct pci_pbm_info *pbm;
 	struct iommu *iommu;
+	struct atu *atu;
+	struct iommu_map_table *tbl;
 	unsigned long npages;
+	unsigned long iotsb_num;
 	long entry;
 	u32 devhandle;
 
@@ -332,14 +439,23 @@ static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr,
 
 	iommu = dev->archdata.iommu;
 	pbm = dev->archdata.host_controller;
+	atu = iommu->atu;
 	devhandle = pbm->devhandle;
 
 	npages = IO_PAGE_ALIGN(bus_addr + sz) - (bus_addr & IO_PAGE_MASK);
 	npages >>= IO_PAGE_SHIFT;
 	bus_addr &= IO_PAGE_MASK;
-	entry = (bus_addr - iommu->tbl.table_map_base) >> IO_PAGE_SHIFT;
-	dma_4v_iommu_demap(&devhandle, entry, npages);
-	iommu_tbl_range_free(&iommu->tbl, bus_addr, npages, IOMMU_ERROR_CODE);
+
+	if (bus_addr <= DMA_BIT_MASK(32)) {
+		iotsb_num = 0; /* we don't care for legacy iommu */
+		tbl = &iommu->tbl;
+	} else {
+		iotsb_num = atu->iotsb->iotsb_num;
+		tbl = &atu->tbl;
+	}
+	entry = (bus_addr - tbl->table_map_base) >> IO_PAGE_SHIFT;
+	dma_4v_iommu_demap(dev, devhandle, bus_addr, iotsb_num, entry, npages);
+	iommu_tbl_range_free(tbl, bus_addr, npages, IOMMU_ERROR_CODE);
 }
 
 static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
@@ -353,12 +469,17 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 	unsigned long seg_boundary_size;
 	int outcount, incount, i;
 	struct iommu *iommu;
+	struct atu *atu;
+	struct iommu_map_table *tbl;
+	u64 mask;
 	unsigned long base_shift;
 	long err;
 
 	BUG_ON(direction == DMA_NONE);
 
 	iommu = dev->archdata.iommu;
+	atu = iommu->atu;
+
 	if (nelems == 0 || !iommu)
 		return 0;
 	
@@ -384,7 +505,15 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 	max_seg_size = dma_get_max_seg_size(dev);
 	seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
 				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
-	base_shift = iommu->tbl.table_map_base >> IO_PAGE_SHIFT;
+
+	mask = *dev->dma_mask;
+	if (mask <= DMA_BIT_MASK(32))
+		tbl = &iommu->tbl;
+	else
+		tbl = &atu->tbl;
+
+	base_shift = tbl->table_map_base >> IO_PAGE_SHIFT;
+
 	for_each_sg(sglist, s, nelems, i) {
 		unsigned long paddr, npages, entry, out_entry = 0, slen;
 
@@ -397,27 +526,26 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 		/* Allocate iommu entries for that segment */
 		paddr = (unsigned long) SG_ENT_PHYS_ADDRESS(s);
 		npages = iommu_num_pages(paddr, slen, IO_PAGE_SIZE);
-		entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages,
+		entry = iommu_tbl_range_alloc(dev, tbl, npages,
 					      &handle, (unsigned long)(-1), 0);
 
 		/* Handle failure */
 		if (unlikely(entry == IOMMU_ERROR_CODE)) {
-			if (printk_ratelimit())
-				printk(KERN_INFO "iommu_alloc failed, iommu %p paddr %lx"
-				       " npages %lx\n", iommu, paddr, npages);
+			pr_err_ratelimited("iommu_alloc failed, iommu %p paddr %lx npages %lx\n",
+					   tbl, paddr, npages);
 			goto iommu_map_failed;
 		}
 
-		iommu_batch_new_entry(entry);
+		iommu_batch_new_entry(entry, mask);
 
 		/* Convert entry to a dma_addr_t */
-		dma_addr = iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT);
+		dma_addr = tbl->table_map_base + (entry << IO_PAGE_SHIFT);
 		dma_addr |= (s->offset & ~IO_PAGE_MASK);
 
 		/* Insert into HW table */
 		paddr &= IO_PAGE_MASK;
 		while (npages--) {
-			err = iommu_batch_add(paddr);
+			err = iommu_batch_add(paddr, mask);
 			if (unlikely(err < 0L))
 				goto iommu_map_failed;
 			paddr += IO_PAGE_SIZE;
@@ -452,7 +580,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 		dma_next = dma_addr + slen;
 	}
 
-	err = iommu_batch_end();
+	err = iommu_batch_end(mask);
 
 	if (unlikely(err < 0L))
 		goto iommu_map_failed;
@@ -475,7 +603,7 @@ iommu_map_failed:
 			vaddr = s->dma_address & IO_PAGE_MASK;
 			npages = iommu_num_pages(s->dma_address, s->dma_length,
 						 IO_PAGE_SIZE);
-			iommu_tbl_range_free(&iommu->tbl, vaddr, npages,
+			iommu_tbl_range_free(tbl, vaddr, npages,
 					     IOMMU_ERROR_CODE);
 			/* XXX demap? XXX */
 			s->dma_address = DMA_ERROR_CODE;
@@ -496,13 +624,16 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	struct pci_pbm_info *pbm;
 	struct scatterlist *sg;
 	struct iommu *iommu;
+	struct atu *atu;
 	unsigned long flags, entry;
+	unsigned long iotsb_num;
 	u32 devhandle;
 
 	BUG_ON(direction == DMA_NONE);
 
 	iommu = dev->archdata.iommu;
 	pbm = dev->archdata.host_controller;
+	atu = iommu->atu;
 	devhandle = pbm->devhandle;
 	
 	local_irq_save(flags);
@@ -512,15 +643,24 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
 		dma_addr_t dma_handle = sg->dma_address;
 		unsigned int len = sg->dma_length;
 		unsigned long npages;
-		struct iommu_map_table *tbl = &iommu->tbl;
+		struct iommu_map_table *tbl;
 		unsigned long shift = IO_PAGE_SHIFT;
 
 		if (!len)
 			break;
 		npages = iommu_num_pages(dma_handle, len, IO_PAGE_SIZE);
+
+		if (dma_handle <= DMA_BIT_MASK(32)) {
+			iotsb_num = 0; /* we don't care for legacy iommu */
+			tbl = &iommu->tbl;
+		} else {
+			iotsb_num = atu->iotsb->iotsb_num;
+			tbl = &atu->tbl;
+		}
 		entry = ((dma_handle - tbl->table_map_base) >> shift);
-		dma_4v_iommu_demap(&devhandle, entry, npages);
-		iommu_tbl_range_free(&iommu->tbl, dma_handle, npages,
+		dma_4v_iommu_demap(dev, devhandle, dma_handle, iotsb_num,
+				   entry, npages);
+		iommu_tbl_range_free(tbl, dma_handle, npages,
 				     IOMMU_ERROR_CODE);
 		sg = sg_next(sg);
 	}
@@ -581,6 +721,132 @@ static unsigned long probe_existing_entries(struct pci_pbm_info *pbm,
 	return cnt;
 }
 
+static int pci_sun4v_atu_alloc_iotsb(struct pci_pbm_info *pbm)
+{
+	struct atu *atu = pbm->iommu->atu;
+	struct atu_iotsb *iotsb;
+	void *table;
+	u64 table_size;
+	u64 iotsb_num;
+	unsigned long order;
+	unsigned long err;
+
+	iotsb = kzalloc(sizeof(*iotsb), GFP_KERNEL);
+	if (!iotsb) {
+		err = -ENOMEM;
+		goto out_err;
+	}
+	atu->iotsb = iotsb;
+
+	/* calculate size of IOTSB */
+	table_size = (atu->size / IO_PAGE_SIZE) * 8;
+	order = get_order(table_size);
+	table = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
+	if (!table) {
+		err = -ENOMEM;
+		goto table_failed;
+	}
+	iotsb->table = table;
+	iotsb->ra = __pa(table);
+	iotsb->dvma_size = atu->size;
+	iotsb->dvma_base = atu->base;
+	iotsb->table_size = table_size;
+	iotsb->page_size = IO_PAGE_SIZE;
+
+	/* configure and register IOTSB with HV */
+	err = pci_sun4v_iotsb_conf(pbm->devhandle,
+				   iotsb->ra,
+				   iotsb->table_size,
+				   iotsb->page_size,
+				   iotsb->dvma_base,
+				   &iotsb_num);
+	if (err) {
+		pr_err(PFX "pci_iotsb_conf failed error: %ld\n", err);
+		goto iotsb_conf_failed;
+	}
+	iotsb->iotsb_num = iotsb_num;
+
+	err = dma_4v_iotsb_bind(pbm->devhandle, iotsb_num, pbm->pci_bus);
+	if (err) {
+		pr_err(PFX "pci_iotsb_bind failed error: %ld\n", err);
+		goto iotsb_conf_failed;
+	}
+
+	return 0;
+
+iotsb_conf_failed:
+	free_pages((unsigned long)table, order);
+table_failed:
+	kfree(iotsb);
+out_err:
+	return err;
+}
+
+static int pci_sun4v_atu_init(struct pci_pbm_info *pbm)
+{
+	struct atu *atu = pbm->iommu->atu;
+	unsigned long err;
+	const u64 *ranges;
+	u64 map_size, num_iotte;
+	u64 dma_mask;
+	const u32 *page_size;
+	int len;
+
+	ranges = of_get_property(pbm->op->dev.of_node, "iommu-address-ranges",
+				 &len);
+	if (!ranges) {
+		pr_err(PFX "No iommu-address-ranges\n");
+		return -EINVAL;
+	}
+
+	page_size = of_get_property(pbm->op->dev.of_node, "iommu-pagesizes",
+				    NULL);
+	if (!page_size) {
+		pr_err(PFX "No iommu-pagesizes\n");
+		return -EINVAL;
+	}
+
+	/* There are 4 iommu-address-ranges supported. Each range is pair of
+	 * {base, size}. The ranges[0] and ranges[1] are 32bit address space
+	 * while ranges[2] and ranges[3] are 64bit space.  We want to use 64bit
+	 * address ranges to support 64bit addressing. Because 'size' for
+	 * address ranges[2] and ranges[3] are same we can select either of
+	 * ranges[2] or ranges[3] for mapping. However due to 'size' is too
+	 * large for OS to allocate IOTSB we are using fix size 32G
+	 * (ATU_64_SPACE_SIZE) which is more than enough for all PCIe devices
+	 * to share.
+	 */
+	atu->ranges = (struct atu_ranges *)ranges;
+	atu->base = atu->ranges[3].base;
+	atu->size = ATU_64_SPACE_SIZE;
+
+	/* Create IOTSB */
+	err = pci_sun4v_atu_alloc_iotsb(pbm);
+	if (err) {
+		pr_err(PFX "Error creating ATU IOTSB\n");
+		return err;
+	}
+
+	/* Create ATU iommu map.
+	 * One bit represents one iotte in IOTSB table.
+	 */
+	dma_mask = (roundup_pow_of_two(atu->size) - 1UL);
+	num_iotte = atu->size / IO_PAGE_SIZE;
+	map_size = num_iotte / 8;
+	atu->tbl.table_map_base = atu->base;
+	atu->dma_addr_mask = dma_mask;
+	atu->tbl.map = kzalloc(map_size, GFP_KERNEL);
+	if (!atu->tbl.map)
+		return -ENOMEM;
+
+	iommu_tbl_pool_init(&atu->tbl, num_iotte, IO_PAGE_SHIFT,
+			    NULL, false /* no large_pool */,
+			    0 /* default npools */,
+			    false /* want span boundary checking */);
+
+	return 0;
+}
+
 static int pci_sun4v_iommu_init(struct pci_pbm_info *pbm)
 {
 	static const u32 vdma_default[] = { 0x80000000, 0x80000000 };
@@ -918,6 +1184,18 @@ static int pci_sun4v_pbm_init(struct pci_pbm_info *pbm,
 
 	pci_sun4v_scan_bus(pbm, &op->dev);
 
+	/* if atu_init fails its not complete failure.
+	 * we can still continue using legacy iommu.
+	 */
+	if (pbm->iommu->atu) {
+		err = pci_sun4v_atu_init(pbm);
+		if (err) {
+			kfree(pbm->iommu->atu);
+			pbm->iommu->atu = NULL;
+			pr_err(PFX "ATU init failed, err=%d\n", err);
+		}
+	}
+
 	pbm->next = pci_pbm_root;
 	pci_pbm_root = pbm;
 
@@ -931,8 +1209,10 @@ static int pci_sun4v_probe(struct platform_device *op)
 	struct pci_pbm_info *pbm;
 	struct device_node *dp;
 	struct iommu *iommu;
+	struct atu *atu;
 	u32 devhandle;
 	int i, err = -ENODEV;
+	static bool hv_atu = true;
 
 	dp = op->dev.of_node;
 
@@ -954,6 +1234,19 @@ static int pci_sun4v_probe(struct platform_device *op)
 		pr_info(PFX "Registered hvapi major[%lu] minor[%lu]\n",
 			vpci_major, vpci_minor);
 
+		err = sun4v_hvapi_register(HV_GRP_ATU, vatu_major, &vatu_minor);
+		if (err) {
+			/* don't return an error if we fail to register the
+			 * ATU group, but ATU hcalls won't be available.
+			 */
+			hv_atu = false;
+			pr_err(PFX "Could not register hvapi ATU err=%d\n",
+			       err);
+		} else {
+			pr_info(PFX "Registered hvapi ATU major[%lu] minor[%lu]\n",
+				vatu_major, vatu_minor);
+		}
+
 		dma_ops = &sun4v_dma_ops;
 	}
 
@@ -991,6 +1284,14 @@ static int pci_sun4v_probe(struct platform_device *op)
 	}
 
 	pbm->iommu = iommu;
+	iommu->atu = NULL;
+	if (hv_atu) {
+		atu = kzalloc(sizeof(*atu), GFP_KERNEL);
+		if (!atu)
+			pr_err(PFX "Could not allocate atu\n");
+		else
+			iommu->atu = atu;
+	}
 
 	err = pci_sun4v_pbm_init(pbm, op, devhandle);
 	if (err)
@@ -1001,6 +1302,7 @@ static int pci_sun4v_probe(struct platform_device *op)
 	return 0;
 
 out_free_iommu:
+	kfree(iommu->atu);
 	kfree(pbm->iommu);
 
 out_free_controller:
diff --git a/arch/sparc/kernel/pci_sun4v.h b/arch/sparc/kernel/pci_sun4v.h
index 5642212390b2..22603a4e48bf 100644
--- a/arch/sparc/kernel/pci_sun4v.h
+++ b/arch/sparc/kernel/pci_sun4v.h
@@ -89,4 +89,25 @@ unsigned long pci_sun4v_msg_setvalid(unsigned long devhandle,
 				     unsigned long msinum,
 				     unsigned long valid);
 
+/* Sun4v HV IOMMU v2 APIs */
+unsigned long pci_sun4v_iotsb_conf(unsigned long devhandle,
+				   unsigned long ra,
+				   unsigned long table_size,
+				   unsigned long page_size,
+				   unsigned long dvma_base,
+				   u64 *iotsb_num);
+unsigned long pci_sun4v_iotsb_bind(unsigned long devhandle,
+				   unsigned long iotsb_num,
+				   unsigned int pci_device);
+unsigned long pci_sun4v_iotsb_map(unsigned long devhandle,
+				  unsigned long iotsb_num,
+				  unsigned long iotsb_index_iottes,
+				  unsigned long io_attributes,
+				  unsigned long io_page_list_pa,
+				  long *mapped);
+unsigned long pci_sun4v_iotsb_demap(unsigned long devhandle,
+				    unsigned long iotsb_num,
+				    unsigned long iotsb_index,
+				    unsigned long iottes,
+				    unsigned long *demapped);
 #endif /* !(_PCI_SUN4V_H) */
diff --git a/arch/sparc/kernel/pci_sun4v_asm.S b/arch/sparc/kernel/pci_sun4v_asm.S
index e606d46c6815..578f09657916 100644
--- a/arch/sparc/kernel/pci_sun4v_asm.S
+++ b/arch/sparc/kernel/pci_sun4v_asm.S
@@ -360,3 +360,71 @@ ENTRY(pci_sun4v_msg_setvalid)
 	 mov	%o0, %o0
 ENDPROC(pci_sun4v_msg_setvalid)
 
+	/*
+	 * %o0:	devhandle
+	 * %o1:	r_addr
+	 * %o2:	size
+	 * %o3:	pagesize
+	 * %o4:	virt
+	 * %o5: &iotsb_num/&iotsb_handle
+	 *
+	 * returns %o0:	status
+	 *         %o1:	iotsb_num/iotsb_handle
+	 */
+ENTRY(pci_sun4v_iotsb_conf)
+	mov	%o5, %g1
+	mov	HV_FAST_PCI_IOTSB_CONF, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 stx	%o1, [%g1]
+ENDPROC(pci_sun4v_iotsb_conf)
+
+	/*
+	 * %o0:	devhandle
+	 * %o1:	iotsb_num/iotsb_handle
+	 * %o2:	pci_device
+	 *
+	 * returns %o0:	status
+	 */
+ENTRY(pci_sun4v_iotsb_bind)
+	mov	HV_FAST_PCI_IOTSB_BIND, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 nop
+ENDPROC(pci_sun4v_iotsb_bind)
+
+	/*
+	 * %o0:	devhandle
+	 * %o1:	iotsb_num/iotsb_handle
+	 * %o2:	index_count
+	 * %o3:	iotte_attributes
+	 * %o4:	io_page_list_p
+	 * %o5: &mapped
+	 *
+	 * returns %o0:	status
+	 *         %o1:	#mapped
+	 */
+ENTRY(pci_sun4v_iotsb_map)
+	mov	%o5, %g1
+	mov	HV_FAST_PCI_IOTSB_MAP, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 stx	%o1, [%g1]
+ENDPROC(pci_sun4v_iotsb_map)
+
+	/*
+	 * %o0:	devhandle
+	 * %o1:	iotsb_num/iotsb_handle
+	 * %o2:	iotsb_index
+	 * %o3:	#iottes
+	 * %o4: &demapped
+	 *
+	 * returns %o0:	status
+	 *         %o1:	#demapped
+	 */
+ENTRY(pci_sun4v_iotsb_demap)
+	mov	HV_FAST_PCI_IOTSB_DEMAP, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 stx	%o1, [%o4]
+ENDPROC(pci_sun4v_iotsb_demap)
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index c3c12efe0bc0..9c0c8fd0b292 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -89,7 +89,7 @@ asmlinkage void do_sigreturn(struct pt_regs *regs)
 	sf = (struct signal_frame __user *) regs->u_regs[UREG_FP];
 
 	/* 1. Make sure we are not getting garbage from the user */
-	if (!invalid_frame_pointer(sf, sizeof(*sf)))
+	if (invalid_frame_pointer(sf, sizeof(*sf)))
 		goto segv_and_exit;
 
 	if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP]))
@@ -150,7 +150,7 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs)
 
 	synchronize_user_stack();
 	sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP];
-	if (!invalid_frame_pointer(sf, sizeof(*sf)))
+	if (invalid_frame_pointer(sf, sizeof(*sf)))
 		goto segv;
 
 	if (get_user(ufp, &sf->regs.u_regs[UREG_FP]))
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 439784b7b7ac..37aa537b3ad8 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -802,8 +802,10 @@ struct mdesc_mblock {
 };
 static struct mdesc_mblock *mblocks;
 static int num_mblocks;
+static int find_numa_node_for_addr(unsigned long pa,
+				   struct node_mem_mask *pnode_mask);
 
-static unsigned long ra_to_pa(unsigned long addr)
+static unsigned long __init ra_to_pa(unsigned long addr)
 {
 	int i;
 
@@ -819,8 +821,11 @@ static unsigned long ra_to_pa(unsigned long addr)
 	return addr;
 }
 
-static int find_node(unsigned long addr)
+static int __init find_node(unsigned long addr)
 {
+	static bool search_mdesc = true;
+	static struct node_mem_mask last_mem_mask = { ~0UL, ~0UL };
+	static int last_index;
 	int i;
 
 	addr = ra_to_pa(addr);
@@ -830,13 +835,30 @@ static int find_node(unsigned long addr)
 		if ((addr & p->mask) == p->val)
 			return i;
 	}
-	/* The following condition has been observed on LDOM guests.*/
-	WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node"
-		" rule. Some physical memory will be owned by node 0.");
-	return 0;
+	/* The following condition has been observed on LDOM guests because
+	 * node_masks only contains the best latency mask and value.
+	 * LDOM guest's mdesc can contain a single latency group to
+	 * cover multiple address range. Print warning message only if the
+	 * address cannot be found in node_masks nor mdesc.
+	 */
+	if ((search_mdesc) &&
+	    ((addr & last_mem_mask.mask) != last_mem_mask.val)) {
+		/* find the available node in the mdesc */
+		last_index = find_numa_node_for_addr(addr, &last_mem_mask);
+		numadbg("find_node: latency group for address 0x%lx is %d\n",
+			addr, last_index);
+		if ((last_index < 0) || (last_index >= num_node_masks)) {
+			/* WARN_ONCE() and use default group 0 */
+			WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node rule. Some physical memory will be owned by node 0.");
+			search_mdesc = false;
+			last_index = 0;
+		}
+	}
+
+	return last_index;
 }
 
-static u64 memblock_nid_range(u64 start, u64 end, int *nid)
+static u64 __init memblock_nid_range(u64 start, u64 end, int *nid)
 {
 	*nid = find_node(start);
 	start += PAGE_SIZE;
@@ -1160,6 +1182,41 @@ int __node_distance(int from, int to)
 	return numa_latency[from][to];
 }
 
+static int find_numa_node_for_addr(unsigned long pa,
+				   struct node_mem_mask *pnode_mask)
+{
+	struct mdesc_handle *md = mdesc_grab();
+	u64 node, arc;
+	int i = 0;
+
+	node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups");
+	if (node == MDESC_NODE_NULL)
+		goto out;
+
+	mdesc_for_each_node_by_name(md, node, "group") {
+		mdesc_for_each_arc(arc, md, node, MDESC_ARC_TYPE_FWD) {
+			u64 target = mdesc_arc_target(md, arc);
+			struct mdesc_mlgroup *m = find_mlgroup(target);
+
+			if (!m)
+				continue;
+			if ((pa & m->mask) == m->match) {
+				if (pnode_mask) {
+					pnode_mask->mask = m->mask;
+					pnode_mask->val = m->match;
+				}
+				mdesc_release(md);
+				return i;
+			}
+		}
+		i++;
+	}
+
+out:
+	mdesc_release(md);
+	return -1;
+}
+
 static int __init find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
 {
 	int i;
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 536ccfcc01c6..34d9e15857c3 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -40,8 +40,8 @@ GCOV_PROFILE := n
 UBSAN_SANITIZE :=n
 
 LDFLAGS := -m elf_$(UTS_MACHINE)
-ifeq ($(CONFIG_RELOCATABLE),y)
-# If kernel is relocatable, build compressed kernel as PIE.
+# Compressed kernel should be built as PIE since it may be loaded at any
+# address by the bootloader.
 ifeq ($(CONFIG_X86_32),y)
 LDFLAGS += $(call ld-option, -pie) $(call ld-option, --no-dynamic-linker)
 else
@@ -51,7 +51,6 @@ else
 LDFLAGS += $(shell $(LD) --help 2>&1 | grep -q "\-z noreloc-overflow" \
 	&& echo "-z noreloc-overflow -pie --no-dynamic-linker")
 endif
-endif
 LDFLAGS_vmlinux := -T
 
 hostprogs-y	:= mkpiggy
diff --git a/arch/x86/boot/cpu.c b/arch/x86/boot/cpu.c
index 26240dde081e..4224ede43b4e 100644
--- a/arch/x86/boot/cpu.c
+++ b/arch/x86/boot/cpu.c
@@ -87,6 +87,12 @@ int validate_cpu(void)
 		return -1;
 	}
 
+	if (CONFIG_X86_MINIMUM_CPU_FAMILY <= 4 && !IS_ENABLED(CONFIG_M486) &&
+	    !has_eflag(X86_EFLAGS_ID)) {
+		printf("This kernel requires a CPU with the CPUID instruction.  Build with CONFIG_M486=y to run on this CPU.\n");
+		return -1;
+	}
+
 	if (err_flags) {
 		puts("This kernel requires the following features "
 		     "not present on the CPU:\n");
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 9b7cf5c28f5f..85f854b98a9d 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -112,7 +112,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		for (; stack < stack_info.end; stack++) {
 			unsigned long real_addr;
 			int reliable = 0;
-			unsigned long addr = *stack;
+			unsigned long addr = READ_ONCE_NOCHECK(*stack);
 			unsigned long *ret_addr_p =
 				unwind_get_return_address_ptr(&state);
 
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 47004010ad5d..ebb4e95fbd74 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -521,14 +521,14 @@ void fpu__clear(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
 
-	if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) {
-		/* FPU state will be reallocated lazily at the first use. */
-		fpu__drop(fpu);
-	} else {
-		if (!fpu->fpstate_active) {
-			fpu__activate_curr(fpu);
-			user_fpu_begin();
-		}
+	fpu__drop(fpu);
+
+	/*
+	 * Make sure fpstate is cleared and initialized.
+	 */
+	if (static_cpu_has(X86_FEATURE_FPU)) {
+		fpu__activate_curr(fpu);
+		user_fpu_begin();
 		copy_init_fpstate_to_fpregs();
 	}
 }
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index b6b2f0264af3..2dabea46f039 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -665,14 +665,17 @@ __PAGE_ALIGNED_BSS
 initial_pg_pmd:
 	.fill 1024*KPMDS,4,0
 #else
-ENTRY(initial_page_table)
+.globl initial_page_table
+initial_page_table:
 	.fill 1024,4,0
 #endif
 initial_pg_fixmap:
 	.fill 1024,4,0
-ENTRY(empty_zero_page)
+.globl empty_zero_page
+empty_zero_page:
 	.fill 4096,1,0
-ENTRY(swapper_pg_dir)
+.globl swapper_pg_dir
+swapper_pg_dir:
 	.fill 1024,4,0
 EXPORT_SYMBOL(empty_zero_page)
 
diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c
index 764a29f84de7..85195d447a92 100644
--- a/arch/x86/kernel/sysfb_simplefb.c
+++ b/arch/x86/kernel/sysfb_simplefb.c
@@ -66,13 +66,36 @@ __init int create_simplefb(const struct screen_info *si,
 {
 	struct platform_device *pd;
 	struct resource res;
-	unsigned long len;
+	u64 base, size;
+	u32 length;
 
-	/* don't use lfb_size as it may contain the whole VMEM instead of only
-	 * the part that is occupied by the framebuffer */
-	len = mode->height * mode->stride;
-	len = PAGE_ALIGN(len);
-	if (len > (u64)si->lfb_size << 16) {
+	/*
+	 * If the 64BIT_BASE capability is set, ext_lfb_base will contain the
+	 * upper half of the base address. Assemble the address, then make sure
+	 * it is valid and we can actually access it.
+	 */
+	base = si->lfb_base;
+	if (si->capabilities & VIDEO_CAPABILITY_64BIT_BASE)
+		base |= (u64)si->ext_lfb_base << 32;
+	if (!base || (u64)(resource_size_t)base != base) {
+		printk(KERN_DEBUG "sysfb: inaccessible VRAM base\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Don't use lfb_size as IORESOURCE size, since it may contain the
+	 * entire VMEM, and thus require huge mappings. Use just the part we
+	 * need, that is, the part where the framebuffer is located. But verify
+	 * that it does not exceed the advertised VMEM.
+	 * Note that in case of VBE, the lfb_size is shifted by 16 bits for
+	 * historical reasons.
+	 */
+	size = si->lfb_size;
+	if (si->orig_video_isVGA == VIDEO_TYPE_VLFB)
+		size <<= 16;
+	length = mode->height * mode->stride;
+	length = PAGE_ALIGN(length);
+	if (length > size) {
 		printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n");
 		return -EINVAL;
 	}
@@ -81,8 +104,8 @@ __init int create_simplefb(const struct screen_info *si,
 	memset(&res, 0, sizeof(res));
 	res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 	res.name = simplefb_resname;
-	res.start = si->lfb_base;
-	res.end = si->lfb_base + len - 1;
+	res.start = base;
+	res.end = res.start + length - 1;
 	if (res.end <= res.start)
 		return -EINVAL;
 
diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c
index 2d721e533cf4..b80e8bf43cc6 100644
--- a/arch/x86/kernel/unwind_guess.c
+++ b/arch/x86/kernel/unwind_guess.c
@@ -7,11 +7,13 @@
 
 unsigned long unwind_get_return_address(struct unwind_state *state)
 {
+	unsigned long addr = READ_ONCE_NOCHECK(*state->sp);
+
 	if (unwind_done(state))
 		return 0;
 
 	return ftrace_graph_ret_addr(state->task, &state->graph_idx,
-				     *state->sp, state->sp);
+				     addr, state->sp);
 }
 EXPORT_SYMBOL_GPL(unwind_get_return_address);
 
@@ -23,8 +25,10 @@ bool unwind_next_frame(struct unwind_state *state)
 		return false;
 
 	do {
+		unsigned long addr = READ_ONCE_NOCHECK(*state->sp);
+
 		for (state->sp++; state->sp < info->end; state->sp++)
-			if (__kernel_text_address(*state->sp))
+			if (__kernel_text_address(addr))
 				return true;
 
 		state->sp = info->next_sp;
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 25810b144b58..4da03030d5a7 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -156,6 +156,16 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 }
 
 
+static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
+		    struct kvm *kvm, int irq_source_id, int level,
+		    bool line_status)
+{
+	if (!level)
+		return -1;
+
+	return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
+}
+
 int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 			      struct kvm *kvm, int irq_source_id, int level,
 			      bool line_status)
@@ -163,18 +173,26 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 	struct kvm_lapic_irq irq;
 	int r;
 
-	if (unlikely(e->type != KVM_IRQ_ROUTING_MSI))
-		return -EWOULDBLOCK;
+	switch (e->type) {
+	case KVM_IRQ_ROUTING_HV_SINT:
+		return kvm_hv_set_sint(e, kvm, irq_source_id, level,
+				       line_status);
 
-	if (kvm_msi_route_invalid(kvm, e))
-		return -EINVAL;
+	case KVM_IRQ_ROUTING_MSI:
+		if (kvm_msi_route_invalid(kvm, e))
+			return -EINVAL;
 
-	kvm_set_msi_irq(kvm, e, &irq);
+		kvm_set_msi_irq(kvm, e, &irq);
 
-	if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
-		return r;
-	else
-		return -EWOULDBLOCK;
+		if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
+			return r;
+		break;
+
+	default:
+		break;
+	}
+
+	return -EWOULDBLOCK;
 }
 
 int kvm_request_irq_source_id(struct kvm *kvm)
@@ -254,16 +272,6 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
-static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
-		    struct kvm *kvm, int irq_source_id, int level,
-		    bool line_status)
-{
-	if (!level)
-		return -1;
-
-	return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
-}
-
 int kvm_set_routing_entry(struct kvm *kvm,
 			  struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue)
@@ -423,18 +431,6 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
-int kvm_arch_set_irq(struct kvm_kernel_irq_routing_entry *irq, struct kvm *kvm,
-		     int irq_source_id, int level, bool line_status)
-{
-	switch (irq->type) {
-	case KVM_IRQ_ROUTING_HV_SINT:
-		return kvm_hv_set_sint(irq, kvm, irq_source_id, level,
-				       line_status);
-	default:
-		return -EWOULDBLOCK;
-	}
-}
-
 void kvm_arch_irq_routing_update(struct kvm *kvm)
 {
 	kvm_hv_irq_routing_update(kvm);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3017de0431bd..04c5d96b1d67 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -210,7 +210,18 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 	struct kvm_shared_msrs *locals
 		= container_of(urn, struct kvm_shared_msrs, urn);
 	struct kvm_shared_msr_values *values;
+	unsigned long flags;
 
+	/*
+	 * Disabling irqs at this point since the following code could be
+	 * interrupted and executed through kvm_arch_hardware_disable()
+	 */
+	local_irq_save(flags);
+	if (locals->registered) {
+		locals->registered = false;
+		user_return_notifier_unregister(urn);
+	}
+	local_irq_restore(flags);
 	for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
 		values = &locals->values[slot];
 		if (values->host != values->curr) {
@@ -218,8 +229,6 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 			values->curr = values->host;
 		}
 	}
-	locals->registered = false;
-	user_return_notifier_unregister(urn);
 }
 
 static void shared_msr_update(unsigned slot, u32 msr)
@@ -1724,18 +1733,23 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 
 static u64 __get_kvmclock_ns(struct kvm *kvm)
 {
-	struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, 0);
 	struct kvm_arch *ka = &kvm->arch;
-	s64 ns;
+	struct pvclock_vcpu_time_info hv_clock;
 
-	if (vcpu->arch.hv_clock.flags & PVCLOCK_TSC_STABLE_BIT) {
-		u64 tsc = kvm_read_l1_tsc(vcpu, rdtsc());
-		ns = __pvclock_read_cycles(&vcpu->arch.hv_clock, tsc);
-	} else {
-		ns = ktime_get_boot_ns() + ka->kvmclock_offset;
+	spin_lock(&ka->pvclock_gtod_sync_lock);
+	if (!ka->use_master_clock) {
+		spin_unlock(&ka->pvclock_gtod_sync_lock);
+		return ktime_get_boot_ns() + ka->kvmclock_offset;
 	}
 
-	return ns;
+	hv_clock.tsc_timestamp = ka->master_cycle_now;
+	hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
+	spin_unlock(&ka->pvclock_gtod_sync_lock);
+
+	kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
+			   &hv_clock.tsc_shift,
+			   &hv_clock.tsc_to_system_mul);
+	return __pvclock_read_cycles(&hv_clock, rdtsc());
 }
 
 u64 get_kvmclock_ns(struct kvm *kvm)
@@ -2596,7 +2610,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_PIT_STATE2:
 	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
 	case KVM_CAP_XEN_HVM:
-	case KVM_CAP_ADJUST_CLOCK:
 	case KVM_CAP_VCPU_EVENTS:
 	case KVM_CAP_HYPERV:
 	case KVM_CAP_HYPERV_VAPIC:
@@ -2623,6 +2636,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #endif
 		r = 1;
 		break;
+	case KVM_CAP_ADJUST_CLOCK:
+		r = KVM_CLOCK_TSC_STABLE;
+		break;
 	case KVM_CAP_X86_SMM:
 		/* SMBASE is usually relocated above 1M on modern chipsets,
 		 * and SMM handlers might indeed rely on 4G segment limits,
@@ -3415,6 +3431,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	};
 	case KVM_SET_VAPIC_ADDR: {
 		struct kvm_vapic_addr va;
+		int idx;
 
 		r = -EINVAL;
 		if (!lapic_in_kernel(vcpu))
@@ -3422,7 +3439,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&va, argp, sizeof va))
 			goto out;
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 	case KVM_X86_SETUP_MCE: {
@@ -4103,9 +4122,11 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		struct kvm_clock_data user_ns;
 		u64 now_ns;
 
-		now_ns = get_kvmclock_ns(kvm);
+		local_irq_disable();
+		now_ns = __get_kvmclock_ns(kvm);
 		user_ns.clock = now_ns;
-		user_ns.flags = 0;
+		user_ns.flags = kvm->arch.use_master_clock ? KVM_CLOCK_TSC_STABLE : 0;
+		local_irq_enable();
 		memset(&user_ns.pad, 0, sizeof(user_ns.pad));
 
 		r = -EFAULT;
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 79ae939970d3..fcd06f7526de 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -135,7 +135,12 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr)
 	if (early_recursion_flag > 2)
 		goto halt_loop;
 
-	if (regs->cs != __KERNEL_CS)
+	/*
+	 * Old CPUs leave the high bits of CS on the stack
+	 * undefined.  I'm not sure which CPUs do this, but at least
+	 * the 486 DX works this way.
+	 */
+	if ((regs->cs & 0xFFFF) != __KERNEL_CS)
 		goto fail;
 
 	/*
diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile
index 429d08be7848..dd6cfa4ad3ac 100644
--- a/arch/x86/platform/intel-mid/device_libs/Makefile
+++ b/arch/x86/platform/intel-mid/device_libs/Makefile
@@ -28,4 +28,4 @@ obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_pcal9555a.o
 obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o
 # MISC Devices
 obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o
-obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_wdt.o
+obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_mrfld_wdt.o
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
index de734134bc8d..3f1f1c77d090 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
@@ -1,5 +1,5 @@
 /*
- * platform_wdt.c: Watchdog platform library file
+ * Intel Merrifield watchdog platform device library file
  *
  * (C) Copyright 2014 Intel Corporation
  * Author: David Cohen <david.a.cohen@linux.intel.com>
@@ -14,7 +14,9 @@
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/platform_data/intel-mid_wdt.h>
+
 #include <asm/intel-mid.h>
+#include <asm/intel_scu_ipc.h>
 #include <asm/io_apic.h>
 
 #define TANGIER_EXT_TIMER0_MSI 15
@@ -50,14 +52,34 @@ static struct intel_mid_wdt_pdata tangier_pdata = {
 	.probe = tangier_probe,
 };
 
-static int __init register_mid_wdt(void)
+static int wdt_scu_status_change(struct notifier_block *nb,
+				 unsigned long code, void *data)
 {
-	if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER) {
-		wdt_dev.dev.platform_data = &tangier_pdata;
-		return platform_device_register(&wdt_dev);
+	if (code == SCU_DOWN) {
+		platform_device_unregister(&wdt_dev);
+		return 0;
 	}
 
-	return -ENODEV;
+	return platform_device_register(&wdt_dev);
 }
 
+static struct notifier_block wdt_scu_notifier = {
+	.notifier_call	= wdt_scu_status_change,
+};
+
+static int __init register_mid_wdt(void)
+{
+	if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER)
+		return -ENODEV;
+
+	wdt_dev.dev.platform_data = &tangier_pdata;
+
+	/*
+	 * We need to be sure that the SCU IPC is ready before watchdog device
+	 * can be registered:
+	 */
+	intel_scu_notifier_add(&wdt_scu_notifier);
+
+	return 0;
+}
 rootfs_initcall(register_mid_wdt);
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index ac58c1616408..555b9fa0ad43 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -16,6 +16,7 @@ KCOV_INSTRUMENT := n
 
 KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -MD -Os -mcmodel=large
 KBUILD_CFLAGS += -m$(BITS)
+KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
 
 $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 		$(call if_changed,ld)
diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h
index de9b14b2d348..cd400af4a6b2 100644
--- a/arch/xtensa/include/uapi/asm/unistd.h
+++ b/arch/xtensa/include/uapi/asm/unistd.h
@@ -767,7 +767,14 @@ __SYSCALL(346, sys_preadv2, 6)
 #define __NR_pwritev2				347
 __SYSCALL(347, sys_pwritev2, 6)
 
-#define __NR_syscall_count			348
+#define __NR_pkey_mprotect			348
+__SYSCALL(348, sys_pkey_mprotect, 4)
+#define __NR_pkey_alloc				349
+__SYSCALL(349, sys_pkey_alloc, 2)
+#define __NR_pkey_free				350
+__SYSCALL(350, sys_pkey_free, 1)
+
+#define __NR_syscall_count			351
 
 /*
  * sysxtensa syscall handler
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index 9a5bcd0381a7..be81e69b25bc 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -172,10 +172,11 @@ void __init time_init(void)
 {
 	of_clk_init(NULL);
 #ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT
-	printk("Calibrating CPU frequency ");
+	pr_info("Calibrating CPU frequency ");
 	calibrate_ccount();
-	printk("%d.%02d MHz\n", (int)ccount_freq/1000000,
-			(int)(ccount_freq/10000)%100);
+	pr_cont("%d.%02d MHz\n",
+		(int)ccount_freq / 1000000,
+		(int)(ccount_freq / 10000) % 100);
 #else
 	ccount_freq = CONFIG_XTENSA_CPU_CLOCK*1000000UL;
 #endif
@@ -210,9 +211,8 @@ irqreturn_t timer_interrupt(int irq, void *dev_id)
 void calibrate_delay(void)
 {
 	loops_per_jiffy = ccount_freq / HZ;
-	printk("Calibrating delay loop (skipped)... "
-	       "%lu.%02lu BogoMIPS preset\n",
-	       loops_per_jiffy/(1000000/HZ),
-	       (loops_per_jiffy/(10000/HZ)) % 100);
+	pr_info("Calibrating delay loop (skipped)... %lu.%02lu BogoMIPS preset\n",
+		loops_per_jiffy / (1000000 / HZ),
+		(loops_per_jiffy / (10000 / HZ)) % 100);
 }
 #endif
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index d02fc304b31c..ce37d5b899fe 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -465,26 +465,25 @@ void show_regs(struct pt_regs * regs)
 
 	for (i = 0; i < 16; i++) {
 		if ((i % 8) == 0)
-			printk(KERN_INFO "a%02d:", i);
-		printk(KERN_CONT " %08lx", regs->areg[i]);
+			pr_info("a%02d:", i);
+		pr_cont(" %08lx", regs->areg[i]);
 	}
-	printk(KERN_CONT "\n");
-
-	printk("pc: %08lx, ps: %08lx, depc: %08lx, excvaddr: %08lx\n",
-	       regs->pc, regs->ps, regs->depc, regs->excvaddr);
-	printk("lbeg: %08lx, lend: %08lx lcount: %08lx, sar: %08lx\n",
-	       regs->lbeg, regs->lend, regs->lcount, regs->sar);
+	pr_cont("\n");
+	pr_info("pc: %08lx, ps: %08lx, depc: %08lx, excvaddr: %08lx\n",
+		regs->pc, regs->ps, regs->depc, regs->excvaddr);
+	pr_info("lbeg: %08lx, lend: %08lx lcount: %08lx, sar: %08lx\n",
+		regs->lbeg, regs->lend, regs->lcount, regs->sar);
 	if (user_mode(regs))
-		printk("wb: %08lx, ws: %08lx, wmask: %08lx, syscall: %ld\n",
-		       regs->windowbase, regs->windowstart, regs->wmask,
-		       regs->syscall);
+		pr_cont("wb: %08lx, ws: %08lx, wmask: %08lx, syscall: %ld\n",
+			regs->windowbase, regs->windowstart, regs->wmask,
+			regs->syscall);
 }
 
 static int show_trace_cb(struct stackframe *frame, void *data)
 {
 	if (kernel_text_address(frame->pc)) {
-		printk(" [<%08lx>] ", frame->pc);
-		print_symbol("%s\n", frame->pc);
+		pr_cont(" [<%08lx>]", frame->pc);
+		print_symbol(" %s\n", frame->pc);
 	}
 	return 0;
 }
@@ -494,19 +493,13 @@ void show_trace(struct task_struct *task, unsigned long *sp)
 	if (!sp)
 		sp = stack_pointer(task);
 
-	printk("Call Trace:");
-#ifdef CONFIG_KALLSYMS
-	printk("\n");
-#endif
+	pr_info("Call Trace:\n");
 	walk_stackframe(sp, show_trace_cb, NULL);
-	printk("\n");
+#ifndef CONFIG_KALLSYMS
+	pr_cont("\n");
+#endif
 }
 
-/*
- * This routine abuses get_user()/put_user() to reference pointers
- * with at least a bit of error checking ...
- */
-
 static int kstack_depth_to_print = 24;
 
 void show_stack(struct task_struct *task, unsigned long *sp)
@@ -518,52 +511,29 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 		sp = stack_pointer(task);
 	stack = sp;
 
-	printk("\nStack: ");
+	pr_info("Stack:\n");
 
 	for (i = 0; i < kstack_depth_to_print; i++) {
 		if (kstack_end(sp))
 			break;
-		if (i && ((i % 8) == 0))
-			printk("\n       ");
-		printk("%08lx ", *sp++);
+		pr_cont(" %08lx", *sp++);
+		if (i % 8 == 7)
+			pr_cont("\n");
 	}
-	printk("\n");
 	show_trace(task, stack);
 }
 
-void show_code(unsigned int *pc)
-{
-	long i;
-
-	printk("\nCode:");
-
-	for(i = -3 ; i < 6 ; i++) {
-		unsigned long insn;
-		if (__get_user(insn, pc + i)) {
-			printk(" (Bad address in pc)\n");
-			break;
-		}
-		printk("%c%08lx%c",(i?' ':'<'),insn,(i?' ':'>'));
-	}
-}
-
 DEFINE_SPINLOCK(die_lock);
 
 void die(const char * str, struct pt_regs * regs, long err)
 {
 	static int die_counter;
-	int nl = 0;
 
 	console_verbose();
 	spin_lock_irq(&die_lock);
 
-	printk("%s: sig: %ld [#%d]\n", str, err, ++die_counter);
-#ifdef CONFIG_PREEMPT
-	printk("PREEMPT ");
-	nl = 1;
-#endif
-	if (nl)
-		printk("\n");
+	pr_info("%s: sig: %ld [#%d]%s\n", str, err, ++die_counter,
+		IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "");
 	show_regs(regs);
 	if (!user_mode(regs))
 		show_stack(NULL, (unsigned long*)regs->areg[1]);
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 2d8466f9e49b..05e21b464433 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -214,23 +214,26 @@ static int hash_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 	ahash_request_set_crypt(&ctx->req, NULL, ctx->result, 0);
 
-	if (ctx->more) {
+	if (!result) {
+		err = af_alg_wait_for_completion(
+				crypto_ahash_init(&ctx->req),
+				&ctx->completion);
+		if (err)
+			goto unlock;
+	}
+
+	if (!result || ctx->more) {
 		ctx->more = 0;
 		err = af_alg_wait_for_completion(crypto_ahash_final(&ctx->req),
 						 &ctx->completion);
 		if (err)
 			goto unlock;
-	} else if (!result) {
-		err = af_alg_wait_for_completion(
-				crypto_ahash_digest(&ctx->req),
-				&ctx->completion);
 	}
 
 	err = memcpy_to_msg(msg, ctx->result, len);
 
-	hash_free_result(sk, ctx);
-
 unlock:
+	hash_free_result(sk, ctx);
 	release_sock(sk);
 
 	return err ?: len;
diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c
index 046c4d0394ee..5fb838e592dc 100644
--- a/drivers/acpi/acpica/tbfadt.c
+++ b/drivers/acpi/acpica/tbfadt.c
@@ -480,19 +480,17 @@ static void acpi_tb_convert_fadt(void)
 	u32 i;
 
 	/*
-	 * For ACPI 1.0 FADTs (revision 1), ensure that reserved fields which
+	 * For ACPI 1.0 FADTs (revision 1 or 2), ensure that reserved fields which
 	 * should be zero are indeed zero. This will workaround BIOSs that
 	 * inadvertently place values in these fields.
 	 *
 	 * The ACPI 1.0 reserved fields that will be zeroed are the bytes located
 	 * at offset 45, 55, 95, and the word located at offset 109, 110.
 	 *
-	 * Note: The FADT revision value is unreliable because of BIOS errors.
-	 * The table length is instead used as the final word on the version.
-	 *
-	 * Note: FADT revision 3 is the ACPI 2.0 version of the FADT.
+	 * Note: The FADT revision value is unreliable. Only the length can be
+	 * trusted.
 	 */
-	if (acpi_gbl_FADT.header.length <= ACPI_FADT_V3_SIZE) {
+	if (acpi_gbl_FADT.header.length <= ACPI_FADT_V2_SIZE) {
 		acpi_gbl_FADT.preferred_profile = 0;
 		acpi_gbl_FADT.pstate_control = 0;
 		acpi_gbl_FADT.cst_control = 0;
diff --git a/drivers/char/ipmi/bt-bmc.c b/drivers/char/ipmi/bt-bmc.c
index b49e61320952..fc9e8891eae3 100644
--- a/drivers/char/ipmi/bt-bmc.c
+++ b/drivers/char/ipmi/bt-bmc.c
@@ -484,7 +484,7 @@ static int bt_bmc_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id bt_bmc_match[] = {
-	{ .compatible = "aspeed,ast2400-bt-bmc" },
+	{ .compatible = "aspeed,ast2400-ibt-bmc" },
 	{ },
 };
 
@@ -502,4 +502,4 @@ module_platform_driver(bt_bmc_driver);
 MODULE_DEVICE_TABLE(of, bt_bmc_match);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Alistair Popple <alistair@popple.id.au>");
-MODULE_DESCRIPTION("Linux device interface to the BT interface");
+MODULE_DESCRIPTION("Linux device interface to the IPMI BT interface");
diff --git a/drivers/clk/berlin/bg2.c b/drivers/clk/berlin/bg2.c
index edf3b96b3b73..1d99292e2039 100644
--- a/drivers/clk/berlin/bg2.c
+++ b/drivers/clk/berlin/bg2.c
@@ -685,7 +685,7 @@ static void __init berlin2_clock_setup(struct device_node *np)
 	}
 
 	/* register clk-provider */
-	of_clk_add_hw_provider(np, of_clk_hw_onecell_get, &clk_data);
+	of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_data);
 
 	return;
 
diff --git a/drivers/clk/berlin/bg2q.c b/drivers/clk/berlin/bg2q.c
index 0718e831475f..3b784b593afd 100644
--- a/drivers/clk/berlin/bg2q.c
+++ b/drivers/clk/berlin/bg2q.c
@@ -382,7 +382,7 @@ static void __init berlin2q_clock_setup(struct device_node *np)
 	}
 
 	/* register clk-provider */
-	of_clk_add_hw_provider(np, of_clk_hw_onecell_get, &clk_data);
+	of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_data);
 
 	return;
 
diff --git a/drivers/clk/clk-efm32gg.c b/drivers/clk/clk-efm32gg.c
index 8802a2dd56ac..f674778fb3ac 100644
--- a/drivers/clk/clk-efm32gg.c
+++ b/drivers/clk/clk-efm32gg.c
@@ -82,6 +82,6 @@ static void __init efm32gg_cmu_init(struct device_node *np)
 	hws[clk_HFPERCLKDAC0] = clk_hw_register_gate(NULL, "HFPERCLK.DAC0",
 			"HFXO", 0, base + CMU_HFPERCLKEN0, 17, 0, NULL);
 
-	of_clk_add_hw_provider(np, of_clk_hw_onecell_get, &clk_data);
+	of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_data);
 }
 CLK_OF_DECLARE(efm32ggcmu, "efm32gg,cmu", efm32gg_cmu_init);
diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c
index 79596463e0d9..4a82a49cff5e 100644
--- a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c
+++ b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c
@@ -191,6 +191,8 @@ static struct clk_div_table axi_div_table[] = {
 static SUNXI_CCU_DIV_TABLE(axi_clk, "axi", "cpu",
 			   0x050, 0, 3, axi_div_table, 0);
 
+#define SUN6I_A31_AHB1_REG  0x054
+
 static const char * const ahb1_parents[] = { "osc32k", "osc24M",
 					     "axi", "pll-periph" };
 
@@ -1230,6 +1232,16 @@ static void __init sun6i_a31_ccu_setup(struct device_node *node)
 	val &= BIT(16);
 	writel(val, reg + SUN6I_A31_PLL_MIPI_REG);
 
+	/* Force AHB1 to PLL6 / 3 */
+	val = readl(reg + SUN6I_A31_AHB1_REG);
+	/* set PLL6 pre-div = 3 */
+	val &= ~GENMASK(7, 6);
+	val |= 0x2 << 6;
+	/* select PLL6 / pre-div */
+	val &= ~GENMASK(13, 12);
+	val |= 0x3 << 12;
+	writel(val, reg + SUN6I_A31_AHB1_REG);
+
 	sunxi_ccu_probe(node, reg, &sun6i_a31_ccu_desc);
 
 	ccu_mux_notifier_register(pll_cpu_clk.common.hw.clk,
diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c
index 838b22aa8b67..f2c9274b8bd5 100644
--- a/drivers/clk/sunxi/clk-sunxi.c
+++ b/drivers/clk/sunxi/clk-sunxi.c
@@ -373,7 +373,7 @@ static void sun4i_get_apb1_factors(struct factors_request *req)
 	else
 		calcp = 3;
 
-	calcm = (req->parent_rate >> calcp) - 1;
+	calcm = (div >> calcp) - 1;
 
 	req->rate = (req->parent_rate >> calcp) / (calcm + 1);
 	req->m = calcm;
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index 156aad167cd6..954a64c7757b 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -137,7 +137,7 @@ static void dbg_dump_sg(const char *level, const char *prefix_str,
 		}
 
 		buf = it_page + it->offset;
-		len = min(tlen, it->length);
+		len = min_t(size_t, tlen, it->length);
 		print_hex_dump(level, prefix_str, prefix_type, rowsize,
 			       groupsize, buf, len, ascii);
 		tlen -= len;
@@ -4583,6 +4583,15 @@ static int __init caam_algapi_init(void)
 		if (!aes_inst && (alg_sel == OP_ALG_ALGSEL_AES))
 				continue;
 
+		/*
+		 * Check support for AES modes not available
+		 * on LP devices.
+		 */
+		if ((cha_vid & CHA_ID_LS_AES_MASK) == CHA_ID_LS_AES_LP)
+			if ((alg->class1_alg_type & OP_ALG_AAI_MASK) ==
+			     OP_ALG_AAI_XTS)
+				continue;
+
 		t_alg = caam_alg_alloc(alg);
 		if (IS_ERR(t_alg)) {
 			err = PTR_ERR(t_alg);
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index af63a6bcf564..141aefbe37ec 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -306,6 +306,7 @@ config MMP_TDMA
 	depends on ARCH_MMP || COMPILE_TEST
 	select DMA_ENGINE
 	select MMP_SRAM if ARCH_MMP
+	select GENERIC_ALLOCATOR
 	help
 	  Support the MMP Two-Channel DMA engine.
 	  This engine used for MMP Audio DMA and pxa910 SQU.
diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c
index bac5f023013b..d5ba43a87a68 100644
--- a/drivers/dma/cppi41.c
+++ b/drivers/dma/cppi41.c
@@ -317,6 +317,12 @@ static irqreturn_t cppi41_irq(int irq, void *data)
 
 		while (val) {
 			u32 desc, len;
+			int error;
+
+			error = pm_runtime_get(cdd->ddev.dev);
+			if (error < 0)
+				dev_err(cdd->ddev.dev, "%s pm runtime get: %i\n",
+					__func__, error);
 
 			q_num = __fls(val);
 			val &= ~(1 << q_num);
@@ -338,7 +344,6 @@ static irqreturn_t cppi41_irq(int irq, void *data)
 			dma_cookie_complete(&c->txd);
 			dmaengine_desc_get_callback_invoke(&c->txd, NULL);
 
-			/* Paired with cppi41_dma_issue_pending */
 			pm_runtime_mark_last_busy(cdd->ddev.dev);
 			pm_runtime_put_autosuspend(cdd->ddev.dev);
 		}
@@ -362,8 +367,13 @@ static int cppi41_dma_alloc_chan_resources(struct dma_chan *chan)
 	int error;
 
 	error = pm_runtime_get_sync(cdd->ddev.dev);
-	if (error < 0)
+	if (error < 0) {
+		dev_err(cdd->ddev.dev, "%s pm runtime get: %i\n",
+			__func__, error);
+		pm_runtime_put_noidle(cdd->ddev.dev);
+
 		return error;
+	}
 
 	dma_cookie_init(chan);
 	dma_async_tx_descriptor_init(&c->txd, chan);
@@ -385,8 +395,11 @@ static void cppi41_dma_free_chan_resources(struct dma_chan *chan)
 	int error;
 
 	error = pm_runtime_get_sync(cdd->ddev.dev);
-	if (error < 0)
+	if (error < 0) {
+		pm_runtime_put_noidle(cdd->ddev.dev);
+
 		return;
+	}
 
 	WARN_ON(!list_empty(&cdd->pending));
 
@@ -460,9 +473,9 @@ static void cppi41_dma_issue_pending(struct dma_chan *chan)
 	struct cppi41_dd *cdd = c->cdd;
 	int error;
 
-	/* PM runtime paired with dmaengine_desc_get_callback_invoke */
 	error = pm_runtime_get(cdd->ddev.dev);
 	if ((error != -EINPROGRESS) && error < 0) {
+		pm_runtime_put_noidle(cdd->ddev.dev);
 		dev_err(cdd->ddev.dev, "Failed to pm_runtime_get: %i\n",
 			error);
 
@@ -473,6 +486,9 @@ static void cppi41_dma_issue_pending(struct dma_chan *chan)
 		push_desc_queue(c);
 	else
 		pending_desc(c);
+
+	pm_runtime_mark_last_busy(cdd->ddev.dev);
+	pm_runtime_put_autosuspend(cdd->ddev.dev);
 }
 
 static u32 get_host_pd0(u32 length)
@@ -1059,8 +1075,8 @@ err_chans:
 	deinit_cppi41(dev, cdd);
 err_init_cppi:
 	pm_runtime_dont_use_autosuspend(dev);
-	pm_runtime_put_sync(dev);
 err_get_sync:
+	pm_runtime_put_sync(dev);
 	pm_runtime_disable(dev);
 	iounmap(cdd->usbss_mem);
 	iounmap(cdd->ctrl_mem);
@@ -1072,7 +1088,12 @@ err_get_sync:
 static int cppi41_dma_remove(struct platform_device *pdev)
 {
 	struct cppi41_dd *cdd = platform_get_drvdata(pdev);
+	int error;
 
+	error = pm_runtime_get_sync(&pdev->dev);
+	if (error < 0)
+		dev_err(&pdev->dev, "%s could not pm_runtime_get: %i\n",
+			__func__, error);
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&cdd->ddev);
 
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index e18a58068bca..77242b37ef87 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -1628,6 +1628,7 @@ static int edma_alloc_chan_resources(struct dma_chan *chan)
 	if (echan->slot[0] < 0) {
 		dev_err(dev, "Entry slot allocation failed for channel %u\n",
 			EDMA_CHAN_SLOT(echan->ch_num));
+		ret = echan->slot[0];
 		goto err_slot;
 	}
 
diff --git a/drivers/dma/sun6i-dma.c b/drivers/dma/sun6i-dma.c
index 83461994e418..a2358780ab2c 100644
--- a/drivers/dma/sun6i-dma.c
+++ b/drivers/dma/sun6i-dma.c
@@ -578,7 +578,7 @@ static struct dma_async_tx_descriptor *sun6i_dma_prep_dma_memcpy(
 
 	burst = convert_burst(8);
 	width = convert_buswidth(DMA_SLAVE_BUSWIDTH_4_BYTES);
-	v_lli->cfg |= DMA_CHAN_CFG_SRC_DRQ(DRQ_SDRAM) |
+	v_lli->cfg = DMA_CHAN_CFG_SRC_DRQ(DRQ_SDRAM) |
 		DMA_CHAN_CFG_DST_DRQ(DRQ_SDRAM) |
 		DMA_CHAN_CFG_DST_LINEAR_MODE |
 		DMA_CHAN_CFG_SRC_LINEAR_MODE |
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index d011cb89d25e..ed37e5908b91 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -22,10 +22,6 @@ menuconfig GPIOLIB
 
 if GPIOLIB
 
-config GPIO_DEVRES
-	def_bool y
-	depends on HAS_IOMEM
-
 config OF_GPIO
 	def_bool y
 	depends on OF
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index ab28a2daeacc..d074c2299393 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -2,7 +2,7 @@
 
 ccflags-$(CONFIG_DEBUG_GPIO)	+= -DDEBUG
 
-obj-$(CONFIG_GPIO_DEVRES)	+= devres.o
+obj-$(CONFIG_GPIOLIB)		+= devres.o
 obj-$(CONFIG_GPIOLIB)		+= gpiolib.o
 obj-$(CONFIG_GPIOLIB)		+= gpiolib-legacy.o
 obj-$(CONFIG_OF_GPIO)		+= gpiolib-of.o
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index e422568e14ad..fe731f094257 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -372,14 +372,15 @@ static void pca953x_gpio_set_multiple(struct gpio_chip *gc,
 
 	bank_shift = fls((chip->gpio_chip.ngpio - 1) / BANK_SZ);
 
-	memcpy(reg_val, chip->reg_output, NBANK(chip));
 	mutex_lock(&chip->i2c_lock);
+	memcpy(reg_val, chip->reg_output, NBANK(chip));
 	for (bank = 0; bank < NBANK(chip); bank++) {
 		bank_mask = mask[bank / sizeof(*mask)] >>
 			   ((bank % sizeof(*mask)) * 8);
 		if (bank_mask) {
 			bank_val = bits[bank / sizeof(*bits)] >>
 				  ((bank % sizeof(*bits)) * 8);
+			bank_val &= bank_mask;
 			reg_val[bank] = (reg_val[bank] & ~bank_mask) | bank_val;
 		}
 	}
@@ -607,7 +608,6 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
 
 	if (client->irq && irq_base != -1
 			&& (chip->driver_data & PCA_INT)) {
-
 		ret = pca953x_read_regs(chip,
 					chip->regs->input, chip->irq_stat);
 		if (ret)
diff --git a/drivers/gpio/gpio-tc3589x.c b/drivers/gpio/gpio-tc3589x.c
index 5a5a6cb00eea..d6e21f1a70a9 100644
--- a/drivers/gpio/gpio-tc3589x.c
+++ b/drivers/gpio/gpio-tc3589x.c
@@ -97,7 +97,7 @@ static int tc3589x_gpio_get_direction(struct gpio_chip *chip,
 	if (ret < 0)
 		return ret;
 
-	return !!(ret & BIT(pos));
+	return !(ret & BIT(pos));
 }
 
 static int tc3589x_gpio_set_single_ended(struct gpio_chip *chip,
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 93ed0e00c578..868128a676ba 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2737,8 +2737,11 @@ int gpiochip_lock_as_irq(struct gpio_chip *chip, unsigned int offset)
 	if (IS_ERR(desc))
 		return PTR_ERR(desc);
 
-	/* Flush direction if something changed behind our back */
-	if (chip->get_direction) {
+	/*
+	 * If it's fast: flush the direction setting if something changed
+	 * behind our back
+	 */
+	if (!chip->can_sleep && chip->get_direction) {
 		int dir = chip->get_direction(chip, offset);
 
 		if (dir)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 039b57e4644c..496f72b134eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -459,6 +459,7 @@ struct amdgpu_bo {
 	u64				metadata_flags;
 	void				*metadata;
 	u32				metadata_size;
+	unsigned			prime_shared_count;
 	/* list of all virtual address to which this bo
 	 * is associated to
 	 */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 651115dcce12..c02db01f6583 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -132,7 +132,7 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev,
 		entry->priority = min(info[i].bo_priority,
 				      AMDGPU_BO_LIST_MAX_PRIORITY);
 		entry->tv.bo = &entry->robj->tbo;
-		entry->tv.shared = true;
+		entry->tv.shared = !entry->robj->prime_shared_count;
 
 		if (entry->robj->prefered_domains == AMDGPU_GEM_DOMAIN_GDS)
 			gds_obj = entry->robj;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7ca07e7b25c1..3161d77bf299 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -658,12 +658,10 @@ static bool amdgpu_vpost_needed(struct amdgpu_device *adev)
 		return false;
 
 	if (amdgpu_passthrough(adev)) {
-		/* for FIJI: In whole GPU pass-through virtualization case
-		 * old smc fw won't clear some registers (e.g. MEM_SIZE, BIOS_SCRATCH)
-		 * so amdgpu_card_posted return false and driver will incorrectly skip vPost.
-		 * but if we force vPost do in pass-through case, the driver reload will hang.
-		 * whether doing vPost depends on amdgpu_card_posted if smc version is above
-		 * 00160e00 for FIJI.
+		/* for FIJI: In whole GPU pass-through virtualization case, after VM reboot
+		 * some old smc fw still need driver do vPost otherwise gpu hang, while
+		 * those smc fw version above 22.15 doesn't have this flaw, so we force
+		 * vpost executed for smc version below 22.15
 		 */
 		if (adev->asic_type == CHIP_FIJI) {
 			int err;
@@ -674,22 +672,11 @@ static bool amdgpu_vpost_needed(struct amdgpu_device *adev)
 				return true;
 
 			fw_ver = *((uint32_t *)adev->pm.fw->data + 69);
-			if (fw_ver >= 0x00160e00)
-				return !amdgpu_card_posted(adev);
+			if (fw_ver < 0x00160e00)
+				return true;
 		}
-	} else {
-		/* in bare-metal case, amdgpu_card_posted return false
-		 * after system reboot/boot, and return true if driver
-		 * reloaded.
-		 * we shouldn't do vPost after driver reload otherwise GPU
-		 * could hang.
-		 */
-		if (amdgpu_card_posted(adev))
-			return false;
 	}
-
-	/* we assume vPost is neede for all other cases */
-	return true;
+	return !amdgpu_card_posted(adev);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index 7700dc22f243..3826d5aea0a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -74,20 +74,36 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
 	if (ret)
 		return ERR_PTR(ret);
 
+	bo->prime_shared_count = 1;
 	return &bo->gem_base;
 }
 
 int amdgpu_gem_prime_pin(struct drm_gem_object *obj)
 {
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
-	int ret = 0;
+	long ret = 0;
 
 	ret = amdgpu_bo_reserve(bo, false);
 	if (unlikely(ret != 0))
 		return ret;
 
+	/*
+	 * Wait for all shared fences to complete before we switch to future
+	 * use of exclusive fence on this prime shared bo.
+	 */
+	ret = reservation_object_wait_timeout_rcu(bo->tbo.resv, true, false,
+						  MAX_SCHEDULE_TIMEOUT);
+	if (unlikely(ret < 0)) {
+		DRM_DEBUG_PRIME("Fence wait failed: %li\n", ret);
+		amdgpu_bo_unreserve(bo);
+		return ret;
+	}
+
 	/* pin buffer into GTT */
 	ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT, NULL);
+	if (likely(ret == 0))
+		bo->prime_shared_count++;
+
 	amdgpu_bo_unreserve(bo);
 	return ret;
 }
@@ -102,6 +118,8 @@ void amdgpu_gem_prime_unpin(struct drm_gem_object *obj)
 		return;
 
 	amdgpu_bo_unpin(bo);
+	if (bo->prime_shared_count)
+		bo->prime_shared_count--;
 	amdgpu_bo_unreserve(bo);
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index b0c929dd8beb..13f2b705ea49 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -1469,8 +1469,6 @@ static int smu7_get_evv_voltages(struct pp_hwmgr *hwmgr)
 						table_info->vddgfx_lookup_table, vv_id, &sclk)) {
 				if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
 							PHM_PlatformCaps_ClockStretcher)) {
-					if (table_info == NULL)
-						return -EINVAL;
 					sclk_table = table_info->vdd_dep_on_sclk;
 
 					for (j = 1; j < sclk_table->count; j++) {
diff --git a/drivers/gpu/drm/arc/arcpgu_hdmi.c b/drivers/gpu/drm/arc/arcpgu_hdmi.c
index b7a8b2ac4055..b69c66b4897e 100644
--- a/drivers/gpu/drm/arc/arcpgu_hdmi.c
+++ b/drivers/gpu/drm/arc/arcpgu_hdmi.c
@@ -14,170 +14,45 @@
  *
  */
 
-#include <drm/drm_crtc_helper.h>
+#include <drm/drm_crtc.h>
 #include <drm/drm_encoder_slave.h>
-#include <drm/drm_atomic_helper.h>
 
 #include "arcpgu.h"
 
-struct arcpgu_drm_connector {
-	struct drm_connector connector;
-	struct drm_encoder_slave *encoder_slave;
-};
-
-static int arcpgu_drm_connector_get_modes(struct drm_connector *connector)
-{
-	const struct drm_encoder_slave_funcs *sfuncs;
-	struct drm_encoder_slave *slave;
-	struct arcpgu_drm_connector *con =
-		container_of(connector, struct arcpgu_drm_connector, connector);
-
-	slave = con->encoder_slave;
-	if (slave == NULL) {
-		dev_err(connector->dev->dev,
-			"connector_get_modes: cannot find slave encoder for connector\n");
-		return 0;
-	}
-
-	sfuncs = slave->slave_funcs;
-	if (sfuncs->get_modes == NULL)
-		return 0;
-
-	return sfuncs->get_modes(&slave->base, connector);
-}
-
-static enum drm_connector_status
-arcpgu_drm_connector_detect(struct drm_connector *connector, bool force)
-{
-	enum drm_connector_status status = connector_status_unknown;
-	const struct drm_encoder_slave_funcs *sfuncs;
-	struct drm_encoder_slave *slave;
-
-	struct arcpgu_drm_connector *con =
-		container_of(connector, struct arcpgu_drm_connector, connector);
-
-	slave = con->encoder_slave;
-	if (slave == NULL) {
-		dev_err(connector->dev->dev,
-			"connector_detect: cannot find slave encoder for connector\n");
-		return status;
-	}
-
-	sfuncs = slave->slave_funcs;
-	if (sfuncs && sfuncs->detect)
-		return sfuncs->detect(&slave->base, connector);
-
-	dev_err(connector->dev->dev, "connector_detect: could not detect slave funcs\n");
-	return status;
-}
-
-static void arcpgu_drm_connector_destroy(struct drm_connector *connector)
-{
-	drm_connector_unregister(connector);
-	drm_connector_cleanup(connector);
-}
-
-static const struct drm_connector_helper_funcs
-arcpgu_drm_connector_helper_funcs = {
-	.get_modes = arcpgu_drm_connector_get_modes,
-};
-
-static const struct drm_connector_funcs arcpgu_drm_connector_funcs = {
-	.dpms = drm_helper_connector_dpms,
-	.reset = drm_atomic_helper_connector_reset,
-	.detect = arcpgu_drm_connector_detect,
-	.fill_modes = drm_helper_probe_single_connector_modes,
-	.destroy = arcpgu_drm_connector_destroy,
-	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
-	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
-};
-
-static struct drm_encoder_helper_funcs arcpgu_drm_encoder_helper_funcs = {
-	.dpms = drm_i2c_encoder_dpms,
-	.mode_fixup = drm_i2c_encoder_mode_fixup,
-	.mode_set = drm_i2c_encoder_mode_set,
-	.prepare = drm_i2c_encoder_prepare,
-	.commit = drm_i2c_encoder_commit,
-	.detect = drm_i2c_encoder_detect,
-};
-
 static struct drm_encoder_funcs arcpgu_drm_encoder_funcs = {
 	.destroy = drm_encoder_cleanup,
 };
 
 int arcpgu_drm_hdmi_init(struct drm_device *drm, struct device_node *np)
 {
-	struct arcpgu_drm_connector *arcpgu_connector;
-	struct drm_i2c_encoder_driver *driver;
-	struct drm_encoder_slave *encoder;
-	struct drm_connector *connector;
-	struct i2c_client *i2c_slave;
-	int ret;
+	struct drm_encoder *encoder;
+	struct drm_bridge *bridge;
+
+	int ret = 0;
 
 	encoder = devm_kzalloc(drm->dev, sizeof(*encoder), GFP_KERNEL);
 	if (encoder == NULL)
 		return -ENOMEM;
 
-	i2c_slave = of_find_i2c_device_by_node(np);
-	if (!i2c_slave || !i2c_get_clientdata(i2c_slave)) {
-		dev_err(drm->dev, "failed to find i2c slave encoder\n");
-		return -EPROBE_DEFER;
-	}
-
-	if (i2c_slave->dev.driver == NULL) {
-		dev_err(drm->dev, "failed to find i2c slave driver\n");
+	/* Locate drm bridge from the hdmi encoder DT node */
+	bridge = of_drm_find_bridge(np);
+	if (!bridge)
 		return -EPROBE_DEFER;
-	}
 
-	driver =
-	    to_drm_i2c_encoder_driver(to_i2c_driver(i2c_slave->dev.driver));
-	ret = driver->encoder_init(i2c_slave, drm, encoder);
-	if (ret) {
-		dev_err(drm->dev, "failed to initialize i2c encoder slave\n");
-		return ret;
-	}
-
-	encoder->base.possible_crtcs = 1;
-	encoder->base.possible_clones = 0;
-	ret = drm_encoder_init(drm, &encoder->base, &arcpgu_drm_encoder_funcs,
+	encoder->possible_crtcs = 1;
+	encoder->possible_clones = 0;
+	ret = drm_encoder_init(drm, encoder, &arcpgu_drm_encoder_funcs,
 			       DRM_MODE_ENCODER_TMDS, NULL);
 	if (ret)
 		return ret;
 
-	drm_encoder_helper_add(&encoder->base,
-			       &arcpgu_drm_encoder_helper_funcs);
-
-	arcpgu_connector = devm_kzalloc(drm->dev, sizeof(*arcpgu_connector),
-					GFP_KERNEL);
-	if (!arcpgu_connector) {
-		ret = -ENOMEM;
-		goto error_encoder_cleanup;
-	}
-
-	connector = &arcpgu_connector->connector;
-	drm_connector_helper_add(connector, &arcpgu_drm_connector_helper_funcs);
-	ret = drm_connector_init(drm, connector, &arcpgu_drm_connector_funcs,
-			DRM_MODE_CONNECTOR_HDMIA);
-	if (ret < 0) {
-		dev_err(drm->dev, "failed to initialize drm connector\n");
-		goto error_encoder_cleanup;
-	}
+	/* Link drm_bridge to encoder */
+	bridge->encoder = encoder;
+	encoder->bridge = bridge;
 
-	ret = drm_mode_connector_attach_encoder(connector, &encoder->base);
-	if (ret < 0) {
-		dev_err(drm->dev, "could not attach connector to encoder\n");
-		drm_connector_unregister(connector);
-		goto error_connector_cleanup;
-	}
-
-	arcpgu_connector->encoder_slave = encoder;
-
-	return 0;
-
-error_connector_cleanup:
-	drm_connector_cleanup(connector);
+	ret = drm_bridge_attach(drm, bridge);
+	if (ret)
+		drm_encoder_cleanup(encoder);
 
-error_encoder_cleanup:
-	drm_encoder_cleanup(&encoder->base);
 	return ret;
 }
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c
index b2d5e188b1b8..deb57435cc89 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c
@@ -25,8 +25,13 @@
 static void fsl_dcu_drm_crtc_atomic_flush(struct drm_crtc *crtc,
 					  struct drm_crtc_state *old_crtc_state)
 {
+	struct drm_device *dev = crtc->dev;
+	struct fsl_dcu_drm_device *fsl_dev = dev->dev_private;
 	struct drm_pending_vblank_event *event = crtc->state->event;
 
+	regmap_write(fsl_dev->regmap,
+		     DCU_UPDATE_MODE, DCU_UPDATE_MODE_READREG);
+
 	if (event) {
 		crtc->state->event = NULL;
 
@@ -39,11 +44,15 @@ static void fsl_dcu_drm_crtc_atomic_flush(struct drm_crtc *crtc,
 	}
 }
 
-static void fsl_dcu_drm_disable_crtc(struct drm_crtc *crtc)
+static void fsl_dcu_drm_crtc_atomic_disable(struct drm_crtc *crtc,
+					struct drm_crtc_state *old_crtc_state)
 {
 	struct drm_device *dev = crtc->dev;
 	struct fsl_dcu_drm_device *fsl_dev = dev->dev_private;
 
+	/* always disable planes on the CRTC */
+	drm_atomic_helper_disable_planes_on_crtc(old_crtc_state, true);
+
 	drm_crtc_vblank_off(crtc);
 
 	regmap_update_bits(fsl_dev->regmap, DCU_DCU_MODE,
@@ -122,8 +131,8 @@ static void fsl_dcu_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
 }
 
 static const struct drm_crtc_helper_funcs fsl_dcu_drm_crtc_helper_funcs = {
+	.atomic_disable = fsl_dcu_drm_crtc_atomic_disable,
 	.atomic_flush = fsl_dcu_drm_crtc_atomic_flush,
-	.disable = fsl_dcu_drm_disable_crtc,
 	.enable = fsl_dcu_drm_crtc_enable,
 	.mode_set_nofb = fsl_dcu_drm_crtc_mode_set_nofb,
 };
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
index e04efbed1a54..cc2fde2ae5ef 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c
@@ -59,8 +59,6 @@ static int fsl_dcu_drm_irq_init(struct drm_device *dev)
 
 	regmap_write(fsl_dev->regmap, DCU_INT_STATUS, 0);
 	regmap_write(fsl_dev->regmap, DCU_INT_MASK, ~0);
-	regmap_write(fsl_dev->regmap, DCU_UPDATE_MODE,
-		     DCU_UPDATE_MODE_READREG);
 
 	return ret;
 }
@@ -139,8 +137,6 @@ static irqreturn_t fsl_dcu_drm_irq(int irq, void *arg)
 		drm_handle_vblank(dev, 0);
 
 	regmap_write(fsl_dev->regmap, DCU_INT_STATUS, int_status);
-	regmap_write(fsl_dev->regmap, DCU_UPDATE_MODE,
-		     DCU_UPDATE_MODE_READREG);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
index 9e6f7d8112b3..a99f48847420 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c
@@ -160,11 +160,6 @@ static void fsl_dcu_drm_plane_atomic_update(struct drm_plane *plane,
 			     DCU_LAYER_POST_SKIP(0) |
 			     DCU_LAYER_PRE_SKIP(0));
 	}
-	regmap_update_bits(fsl_dev->regmap, DCU_DCU_MODE,
-			   DCU_MODE_DCU_MODE_MASK,
-			   DCU_MODE_DCU_MODE(DCU_MODE_NORMAL));
-	regmap_write(fsl_dev->regmap,
-		     DCU_UPDATE_MODE, DCU_UPDATE_MODE_READREG);
 
 	return;
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 7adb4c77cc7f..a218c2e395e7 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1281,6 +1281,12 @@ i915_gem_validate_context(struct drm_device *dev, struct drm_file *file,
 	return ctx;
 }
 
+static bool gpu_write_needs_clflush(struct drm_i915_gem_object *obj)
+{
+	return !(obj->cache_level == I915_CACHE_NONE ||
+		 obj->cache_level == I915_CACHE_WT);
+}
+
 void i915_vma_move_to_active(struct i915_vma *vma,
 			     struct drm_i915_gem_request *req,
 			     unsigned int flags)
@@ -1311,6 +1317,8 @@ void i915_vma_move_to_active(struct i915_vma *vma,
 
 		/* update for the implicit flush after a batch */
 		obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS;
+		if (!obj->cache_dirty && gpu_write_needs_clflush(obj))
+			obj->cache_dirty = true;
 	}
 
 	if (flags & EXEC_OBJECT_NEEDS_FENCE)
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 1f8af87c6294..cf2560708e03 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -1143,7 +1143,7 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
 	if (!child)
 		return;
 
-	aux_channel = child->raw[25];
+	aux_channel = child->common.aux_channel;
 	ddc_pin = child->common.ddc_pin;
 
 	is_dvi = child->common.device_type & DEVICE_TYPE_TMDS_DVI_SIGNALING;
@@ -1673,7 +1673,8 @@ bool intel_bios_is_port_edp(struct drm_i915_private *dev_priv, enum port port)
 	return false;
 }
 
-bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *dev_priv, enum port port)
+static bool child_dev_is_dp_dual_mode(const union child_device_config *p_child,
+				      enum port port)
 {
 	static const struct {
 		u16 dp, hdmi;
@@ -1687,22 +1688,35 @@ bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *dev_priv, enum por
 		[PORT_D] = { DVO_PORT_DPD, DVO_PORT_HDMID, },
 		[PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, },
 	};
-	int i;
 
 	if (port == PORT_A || port >= ARRAY_SIZE(port_mapping))
 		return false;
 
-	if (!dev_priv->vbt.child_dev_num)
+	if ((p_child->common.device_type & DEVICE_TYPE_DP_DUAL_MODE_BITS) !=
+	    (DEVICE_TYPE_DP_DUAL_MODE & DEVICE_TYPE_DP_DUAL_MODE_BITS))
 		return false;
 
+	if (p_child->common.dvo_port == port_mapping[port].dp)
+		return true;
+
+	/* Only accept a HDMI dvo_port as DP++ if it has an AUX channel */
+	if (p_child->common.dvo_port == port_mapping[port].hdmi &&
+	    p_child->common.aux_channel != 0)
+		return true;
+
+	return false;
+}
+
+bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *dev_priv,
+				     enum port port)
+{
+	int i;
+
 	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
 		const union child_device_config *p_child =
 			&dev_priv->vbt.child_dev[i];
 
-		if ((p_child->common.dvo_port == port_mapping[port].dp ||
-		     p_child->common.dvo_port == port_mapping[port].hdmi) &&
-		    (p_child->common.device_type & DEVICE_TYPE_DP_DUAL_MODE_BITS) ==
-		    (DEVICE_TYPE_DP_DUAL_MODE & DEVICE_TYPE_DP_DUAL_MODE_BITS))
+		if (child_dev_is_dp_dual_mode(p_child, port))
 			return true;
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 3581b5a7f716..bf344d08356a 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -4463,21 +4463,11 @@ static enum drm_connector_status
 intel_dp_detect(struct drm_connector *connector, bool force)
 {
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct intel_encoder *intel_encoder = &intel_dig_port->base;
 	enum drm_connector_status status = connector->status;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
 		      connector->base.id, connector->name);
 
-	if (intel_dp->is_mst) {
-		/* MST devices are disconnected from a monitor POV */
-		intel_dp_unset_edid(intel_dp);
-		if (intel_encoder->type != INTEL_OUTPUT_EDP)
-			intel_encoder->type = INTEL_OUTPUT_DP;
-		return connector_status_disconnected;
-	}
-
 	/* If full detect is not performed yet, do a full detect */
 	if (!intel_dp->detect_done)
 		status = intel_dp_long_pulse(intel_dp->attached_connector);
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 73a521fdf1bd..dbed12c484c9 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -358,7 +358,7 @@ vlv_update_plane(struct drm_plane *dplane,
 	int plane = intel_plane->plane;
 	u32 sprctl;
 	u32 sprsurf_offset, linear_offset;
-	unsigned int rotation = dplane->state->rotation;
+	unsigned int rotation = plane_state->base.rotation;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 	int crtc_x = plane_state->base.dst.x1;
 	int crtc_y = plane_state->base.dst.y1;
diff --git a/drivers/gpu/drm/i915/intel_vbt_defs.h b/drivers/gpu/drm/i915/intel_vbt_defs.h
index 68db9621f1f0..8886cab19f98 100644
--- a/drivers/gpu/drm/i915/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/intel_vbt_defs.h
@@ -280,7 +280,8 @@ struct common_child_dev_config {
 	u8 dp_support:1;
 	u8 tmds_support:1;
 	u8 support_reserved:5;
-	u8 not_common3[12];
+	u8 aux_channel;
+	u8 not_common3[11];
 	u8 iboost_level;
 } __packed;
 
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
index 019b7ca392d7..f75c5b5a536c 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
@@ -80,6 +80,7 @@ static void mtk_ovl_enable_vblank(struct mtk_ddp_comp *comp,
 						 ddp_comp);
 
 	priv->crtc = crtc;
+	writel(0x0, comp->regs + DISP_REG_OVL_INTSTA);
 	writel_relaxed(OVL_FME_CPL_INT, comp->regs + DISP_REG_OVL_INTEN);
 }
 
diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c
index 0186e500d2a5..90fb831ef031 100644
--- a/drivers/gpu/drm/mediatek/mtk_dpi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dpi.c
@@ -432,11 +432,16 @@ static int mtk_dpi_set_display_mode(struct mtk_dpi *dpi,
 	unsigned long pll_rate;
 	unsigned int factor;
 
+	/* let pll_rate can fix the valid range of tvdpll (1G~2GHz) */
 	pix_rate = 1000UL * mode->clock;
-	if (mode->clock <= 74000)
+	if (mode->clock <= 27000)
+		factor = 16 * 3;
+	else if (mode->clock <= 84000)
 		factor = 8 * 3;
-	else
+	else if (mode->clock <= 167000)
 		factor = 4 * 3;
+	else
+		factor = 2 * 3;
 	pll_rate = pix_rate * factor;
 
 	dev_dbg(dpi->dev, "Want PLL %lu Hz, pixel clock %lu Hz\n",
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index 71227deef21b..0e8c4d9af340 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1133,12 +1133,6 @@ static int mtk_hdmi_output_set_display_mode(struct mtk_hdmi *hdmi,
 	phy_power_on(hdmi->phy);
 	mtk_hdmi_aud_output_config(hdmi, mode);
 
-	mtk_hdmi_setup_audio_infoframe(hdmi);
-	mtk_hdmi_setup_avi_infoframe(hdmi, mode);
-	mtk_hdmi_setup_spd_infoframe(hdmi, "mediatek", "On-chip HDMI");
-	if (mode->flags & DRM_MODE_FLAG_3D_MASK)
-		mtk_hdmi_setup_vendor_specific_infoframe(hdmi, mode);
-
 	mtk_hdmi_hw_vid_black(hdmi, false);
 	mtk_hdmi_hw_aud_unmute(hdmi);
 	mtk_hdmi_hw_send_av_unmute(hdmi);
@@ -1401,6 +1395,16 @@ static void mtk_hdmi_bridge_pre_enable(struct drm_bridge *bridge)
 	hdmi->powered = true;
 }
 
+static void mtk_hdmi_send_infoframe(struct mtk_hdmi *hdmi,
+				    struct drm_display_mode *mode)
+{
+	mtk_hdmi_setup_audio_infoframe(hdmi);
+	mtk_hdmi_setup_avi_infoframe(hdmi, mode);
+	mtk_hdmi_setup_spd_infoframe(hdmi, "mediatek", "On-chip HDMI");
+	if (mode->flags & DRM_MODE_FLAG_3D_MASK)
+		mtk_hdmi_setup_vendor_specific_infoframe(hdmi, mode);
+}
+
 static void mtk_hdmi_bridge_enable(struct drm_bridge *bridge)
 {
 	struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge);
@@ -1409,6 +1413,7 @@ static void mtk_hdmi_bridge_enable(struct drm_bridge *bridge)
 	clk_prepare_enable(hdmi->clk[MTK_HDMI_CLK_HDMI_PLL]);
 	clk_prepare_enable(hdmi->clk[MTK_HDMI_CLK_HDMI_PIXEL]);
 	phy_power_on(hdmi->phy);
+	mtk_hdmi_send_infoframe(hdmi, &hdmi->mode);
 
 	hdmi->enabled = true;
 }
diff --git a/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c b/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c
index 8a24754b440f..51cb9cfb6646 100644
--- a/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c
+++ b/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c
@@ -265,6 +265,9 @@ static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
 	unsigned int pre_div;
 	unsigned int div;
+	unsigned int pre_ibias;
+	unsigned int hdmi_ibias;
+	unsigned int imp_en;
 
 	dev_dbg(hdmi_phy->dev, "%s: %lu Hz, parent: %lu Hz\n", __func__,
 		rate, parent_rate);
@@ -298,18 +301,31 @@ static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 			  (0x1 << PLL_BR_SHIFT),
 			  RG_HDMITX_PLL_BP | RG_HDMITX_PLL_BC |
 			  RG_HDMITX_PLL_BR);
-	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON3, RG_HDMITX_PRD_IMP_EN);
+	if (rate < 165000000) {
+		mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON3,
+					RG_HDMITX_PRD_IMP_EN);
+		pre_ibias = 0x3;
+		imp_en = 0x0;
+		hdmi_ibias = hdmi_phy->ibias;
+	} else {
+		mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON3,
+				      RG_HDMITX_PRD_IMP_EN);
+		pre_ibias = 0x6;
+		imp_en = 0xf;
+		hdmi_ibias = hdmi_phy->ibias_up;
+	}
 	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON4,
-			  (0x3 << PRD_IBIAS_CLK_SHIFT) |
-			  (0x3 << PRD_IBIAS_D2_SHIFT) |
-			  (0x3 << PRD_IBIAS_D1_SHIFT) |
-			  (0x3 << PRD_IBIAS_D0_SHIFT),
+			  (pre_ibias << PRD_IBIAS_CLK_SHIFT) |
+			  (pre_ibias << PRD_IBIAS_D2_SHIFT) |
+			  (pre_ibias << PRD_IBIAS_D1_SHIFT) |
+			  (pre_ibias << PRD_IBIAS_D0_SHIFT),
 			  RG_HDMITX_PRD_IBIAS_CLK |
 			  RG_HDMITX_PRD_IBIAS_D2 |
 			  RG_HDMITX_PRD_IBIAS_D1 |
 			  RG_HDMITX_PRD_IBIAS_D0);
 	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON3,
-			  (0x0 << DRV_IMP_EN_SHIFT), RG_HDMITX_DRV_IMP_EN);
+			  (imp_en << DRV_IMP_EN_SHIFT),
+			  RG_HDMITX_DRV_IMP_EN);
 	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6,
 			  (hdmi_phy->drv_imp_clk << DRV_IMP_CLK_SHIFT) |
 			  (hdmi_phy->drv_imp_d2 << DRV_IMP_D2_SHIFT) |
@@ -318,12 +334,14 @@ static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 			  RG_HDMITX_DRV_IMP_CLK | RG_HDMITX_DRV_IMP_D2 |
 			  RG_HDMITX_DRV_IMP_D1 | RG_HDMITX_DRV_IMP_D0);
 	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON5,
-			  (hdmi_phy->ibias << DRV_IBIAS_CLK_SHIFT) |
-			  (hdmi_phy->ibias << DRV_IBIAS_D2_SHIFT) |
-			  (hdmi_phy->ibias << DRV_IBIAS_D1_SHIFT) |
-			  (hdmi_phy->ibias << DRV_IBIAS_D0_SHIFT),
-			  RG_HDMITX_DRV_IBIAS_CLK | RG_HDMITX_DRV_IBIAS_D2 |
-			  RG_HDMITX_DRV_IBIAS_D1 | RG_HDMITX_DRV_IBIAS_D0);
+			  (hdmi_ibias << DRV_IBIAS_CLK_SHIFT) |
+			  (hdmi_ibias << DRV_IBIAS_D2_SHIFT) |
+			  (hdmi_ibias << DRV_IBIAS_D1_SHIFT) |
+			  (hdmi_ibias << DRV_IBIAS_D0_SHIFT),
+			  RG_HDMITX_DRV_IBIAS_CLK |
+			  RG_HDMITX_DRV_IBIAS_D2 |
+			  RG_HDMITX_DRV_IBIAS_D1 |
+			  RG_HDMITX_DRV_IBIAS_D0);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 0da9862ad8ed..70e9fd59c5a2 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -142,9 +142,9 @@ static int sun4i_drv_bind(struct device *dev)
 
 	/* Create our layers */
 	drv->layers = sun4i_layers_init(drm);
-	if (!drv->layers) {
+	if (IS_ERR(drv->layers)) {
 		dev_err(drm->dev, "Couldn't create the planes\n");
-		ret = -EINVAL;
+		ret = PTR_ERR(drv->layers);
 		goto free_drm;
 	}
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c
index c3ff10f559cc..d198ad7e5323 100644
--- a/drivers/gpu/drm/sun4i/sun4i_rgb.c
+++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c
@@ -152,15 +152,13 @@ static void sun4i_rgb_encoder_enable(struct drm_encoder *encoder)
 
 	DRM_DEBUG_DRIVER("Enabling RGB output\n");
 
-	if (!IS_ERR(tcon->panel)) {
+	if (!IS_ERR(tcon->panel))
 		drm_panel_prepare(tcon->panel);
-		drm_panel_enable(tcon->panel);
-	}
-
-	/* encoder->bridge can be NULL; drm_bridge_enable checks for it */
-	drm_bridge_enable(encoder->bridge);
 
 	sun4i_tcon_channel_enable(tcon, 0);
+
+	if (!IS_ERR(tcon->panel))
+		drm_panel_enable(tcon->panel);
 }
 
 static void sun4i_rgb_encoder_disable(struct drm_encoder *encoder)
@@ -171,15 +169,13 @@ static void sun4i_rgb_encoder_disable(struct drm_encoder *encoder)
 
 	DRM_DEBUG_DRIVER("Disabling RGB output\n");
 
-	sun4i_tcon_channel_disable(tcon, 0);
+	if (!IS_ERR(tcon->panel))
+		drm_panel_disable(tcon->panel);
 
-	/* encoder->bridge can be NULL; drm_bridge_disable checks for it */
-	drm_bridge_disable(encoder->bridge);
+	sun4i_tcon_channel_disable(tcon, 0);
 
-	if (!IS_ERR(tcon->panel)) {
-		drm_panel_disable(tcon->panel);
+	if (!IS_ERR(tcon->panel))
 		drm_panel_unprepare(tcon->panel);
-	}
 }
 
 static void sun4i_rgb_encoder_mode_set(struct drm_encoder *encoder,
diff --git a/drivers/i2c/Kconfig b/drivers/i2c/Kconfig
index d223650a97e4..11edabf425ae 100644
--- a/drivers/i2c/Kconfig
+++ b/drivers/i2c/Kconfig
@@ -59,7 +59,6 @@ config I2C_CHARDEV
 
 config I2C_MUX
 	tristate "I2C bus multiplexing support"
-	depends on HAS_IOMEM
 	help
 	  Say Y here if you want the I2C core to support the ability to
 	  handle multiplexed I2C bus topologies, by presenting each
diff --git a/drivers/i2c/busses/i2c-digicolor.c b/drivers/i2c/busses/i2c-digicolor.c
index 49f2084f7bb5..50813a24c541 100644
--- a/drivers/i2c/busses/i2c-digicolor.c
+++ b/drivers/i2c/busses/i2c-digicolor.c
@@ -347,7 +347,7 @@ static int dc_i2c_probe(struct platform_device *pdev)
 
 	ret = i2c_add_adapter(&i2c->adap);
 	if (ret < 0) {
-		clk_unprepare(i2c->clk);
+		clk_disable_unprepare(i2c->clk);
 		return ret;
 	}
 
diff --git a/drivers/i2c/muxes/Kconfig b/drivers/i2c/muxes/Kconfig
index e280c8ecc0b5..96de9ce5669b 100644
--- a/drivers/i2c/muxes/Kconfig
+++ b/drivers/i2c/muxes/Kconfig
@@ -63,6 +63,7 @@ config I2C_MUX_PINCTRL
 
 config I2C_MUX_REG
 	tristate "Register-based I2C multiplexer"
+	depends on HAS_IOMEM
 	help
 	  If you say yes to this option, support will be included for a
 	  register based I2C multiplexer. This driver provides access to
diff --git a/drivers/i2c/muxes/i2c-demux-pinctrl.c b/drivers/i2c/muxes/i2c-demux-pinctrl.c
index b3893f6282ba..3e6fe1760d82 100644
--- a/drivers/i2c/muxes/i2c-demux-pinctrl.c
+++ b/drivers/i2c/muxes/i2c-demux-pinctrl.c
@@ -69,10 +69,28 @@ static int i2c_demux_activate_master(struct i2c_demux_pinctrl_priv *priv, u32 ne
 		goto err_with_revert;
 	}
 
-	p = devm_pinctrl_get_select(adap->dev.parent, priv->bus_name);
+	/*
+	 * Check if there are pinctrl states at all. Note: we cant' use
+	 * devm_pinctrl_get_select() because we need to distinguish between
+	 * the -ENODEV from devm_pinctrl_get() and pinctrl_lookup_state().
+	 */
+	p = devm_pinctrl_get(adap->dev.parent);
 	if (IS_ERR(p)) {
 		ret = PTR_ERR(p);
-		goto err_with_put;
+		/* continue if just no pinctrl states (e.g. i2c-gpio), otherwise exit */
+		if (ret != -ENODEV)
+			goto err_with_put;
+	} else {
+		/* there are states. check and use them */
+		struct pinctrl_state *s = pinctrl_lookup_state(p, priv->bus_name);
+
+		if (IS_ERR(s)) {
+			ret = PTR_ERR(s);
+			goto err_with_put;
+		}
+		ret = pinctrl_select_state(p, s);
+		if (ret < 0)
+			goto err_with_put;
 	}
 
 	priv->chan[new_chan].parent_adap = adap;
diff --git a/drivers/i2c/muxes/i2c-mux-pca954x.c b/drivers/i2c/muxes/i2c-mux-pca954x.c
index 1091346f2480..8bc3d36d2837 100644
--- a/drivers/i2c/muxes/i2c-mux-pca954x.c
+++ b/drivers/i2c/muxes/i2c-mux-pca954x.c
@@ -268,9 +268,9 @@ static int pca954x_probe(struct i2c_client *client,
 				/* discard unconfigured channels */
 				break;
 			idle_disconnect_pd = pdata->modes[num].deselect_on_exit;
-			data->deselect |= (idle_disconnect_pd
-					   || idle_disconnect_dt) << num;
 		}
+		data->deselect |= (idle_disconnect_pd ||
+				   idle_disconnect_dt) << num;
 
 		ret = i2c_mux_add_adapter(muxc, force, num, class);
 
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index b136d3acc5bd..0f58f46dbad7 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -699,13 +699,16 @@ EXPORT_SYMBOL(rdma_addr_cancel);
 struct resolve_cb_context {
 	struct rdma_dev_addr *addr;
 	struct completion comp;
+	int status;
 };
 
 static void resolve_cb(int status, struct sockaddr *src_addr,
 	     struct rdma_dev_addr *addr, void *context)
 {
-	memcpy(((struct resolve_cb_context *)context)->addr, addr, sizeof(struct
-				rdma_dev_addr));
+	if (!status)
+		memcpy(((struct resolve_cb_context *)context)->addr,
+		       addr, sizeof(struct rdma_dev_addr));
+	((struct resolve_cb_context *)context)->status = status;
 	complete(&((struct resolve_cb_context *)context)->comp);
 }
 
@@ -743,6 +746,10 @@ int rdma_addr_find_l2_eth_by_grh(const union ib_gid *sgid,
 
 	wait_for_completion(&ctx.comp);
 
+	ret = ctx.status;
+	if (ret)
+		return ret;
+
 	memcpy(dmac, dev_addr.dst_dev_addr, ETH_ALEN);
 	dev = dev_get_by_index(&init_net, dev_addr.bound_dev_if);
 	if (!dev)
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index c99525512b34..71c7c4c328ef 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -80,6 +80,8 @@ static struct ib_cm {
 	__be32 random_id_operand;
 	struct list_head timewait_list;
 	struct workqueue_struct *wq;
+	/* Sync on cm change port state */
+	spinlock_t state_lock;
 } cm;
 
 /* Counter indexes ordered by attribute ID */
@@ -161,6 +163,8 @@ struct cm_port {
 	struct ib_mad_agent *mad_agent;
 	struct kobject port_obj;
 	u8 port_num;
+	struct list_head cm_priv_prim_list;
+	struct list_head cm_priv_altr_list;
 	struct cm_counter_group counter_group[CM_COUNTER_GROUPS];
 };
 
@@ -241,6 +245,12 @@ struct cm_id_private {
 	u8 service_timeout;
 	u8 target_ack_delay;
 
+	struct list_head prim_list;
+	struct list_head altr_list;
+	/* Indicates that the send port mad is registered and av is set */
+	int prim_send_port_not_ready;
+	int altr_send_port_not_ready;
+
 	struct list_head work_list;
 	atomic_t work_count;
 };
@@ -259,20 +269,47 @@ static int cm_alloc_msg(struct cm_id_private *cm_id_priv,
 	struct ib_mad_agent *mad_agent;
 	struct ib_mad_send_buf *m;
 	struct ib_ah *ah;
+	struct cm_av *av;
+	unsigned long flags, flags2;
+	int ret = 0;
 
+	/* don't let the port to be released till the agent is down */
+	spin_lock_irqsave(&cm.state_lock, flags2);
+	spin_lock_irqsave(&cm.lock, flags);
+	if (!cm_id_priv->prim_send_port_not_ready)
+		av = &cm_id_priv->av;
+	else if (!cm_id_priv->altr_send_port_not_ready &&
+		 (cm_id_priv->alt_av.port))
+		av = &cm_id_priv->alt_av;
+	else {
+		pr_info("%s: not valid CM id\n", __func__);
+		ret = -ENODEV;
+		spin_unlock_irqrestore(&cm.lock, flags);
+		goto out;
+	}
+	spin_unlock_irqrestore(&cm.lock, flags);
+	/* Make sure the port haven't released the mad yet */
 	mad_agent = cm_id_priv->av.port->mad_agent;
-	ah = ib_create_ah(mad_agent->qp->pd, &cm_id_priv->av.ah_attr);
-	if (IS_ERR(ah))
-		return PTR_ERR(ah);
+	if (!mad_agent) {
+		pr_info("%s: not a valid MAD agent\n", __func__);
+		ret = -ENODEV;
+		goto out;
+	}
+	ah = ib_create_ah(mad_agent->qp->pd, &av->ah_attr);
+	if (IS_ERR(ah)) {
+		ret = PTR_ERR(ah);
+		goto out;
+	}
 
 	m = ib_create_send_mad(mad_agent, cm_id_priv->id.remote_cm_qpn,
-			       cm_id_priv->av.pkey_index,
+			       av->pkey_index,
 			       0, IB_MGMT_MAD_HDR, IB_MGMT_MAD_DATA,
 			       GFP_ATOMIC,
 			       IB_MGMT_BASE_VERSION);
 	if (IS_ERR(m)) {
 		ib_destroy_ah(ah);
-		return PTR_ERR(m);
+		ret = PTR_ERR(m);
+		goto out;
 	}
 
 	/* Timeout set by caller if response is expected. */
@@ -282,7 +319,10 @@ static int cm_alloc_msg(struct cm_id_private *cm_id_priv,
 	atomic_inc(&cm_id_priv->refcount);
 	m->context[0] = cm_id_priv;
 	*msg = m;
-	return 0;
+
+out:
+	spin_unlock_irqrestore(&cm.state_lock, flags2);
+	return ret;
 }
 
 static int cm_alloc_response_msg(struct cm_port *port,
@@ -352,7 +392,8 @@ static void cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc,
 			   grh, &av->ah_attr);
 }
 
-static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av)
+static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av,
+			      struct cm_id_private *cm_id_priv)
 {
 	struct cm_device *cm_dev;
 	struct cm_port *port = NULL;
@@ -387,7 +428,17 @@ static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av)
 			     &av->ah_attr);
 	av->timeout = path->packet_life_time + 1;
 
-	return 0;
+	spin_lock_irqsave(&cm.lock, flags);
+	if (&cm_id_priv->av == av)
+		list_add_tail(&cm_id_priv->prim_list, &port->cm_priv_prim_list);
+	else if (&cm_id_priv->alt_av == av)
+		list_add_tail(&cm_id_priv->altr_list, &port->cm_priv_altr_list);
+	else
+		ret = -EINVAL;
+
+	spin_unlock_irqrestore(&cm.lock, flags);
+
+	return ret;
 }
 
 static int cm_alloc_id(struct cm_id_private *cm_id_priv)
@@ -677,6 +728,8 @@ struct ib_cm_id *ib_create_cm_id(struct ib_device *device,
 	spin_lock_init(&cm_id_priv->lock);
 	init_completion(&cm_id_priv->comp);
 	INIT_LIST_HEAD(&cm_id_priv->work_list);
+	INIT_LIST_HEAD(&cm_id_priv->prim_list);
+	INIT_LIST_HEAD(&cm_id_priv->altr_list);
 	atomic_set(&cm_id_priv->work_count, -1);
 	atomic_set(&cm_id_priv->refcount, 1);
 	return &cm_id_priv->id;
@@ -892,6 +945,15 @@ retest:
 		break;
 	}
 
+	spin_lock_irq(&cm.lock);
+	if (!list_empty(&cm_id_priv->altr_list) &&
+	    (!cm_id_priv->altr_send_port_not_ready))
+		list_del(&cm_id_priv->altr_list);
+	if (!list_empty(&cm_id_priv->prim_list) &&
+	    (!cm_id_priv->prim_send_port_not_ready))
+		list_del(&cm_id_priv->prim_list);
+	spin_unlock_irq(&cm.lock);
+
 	cm_free_id(cm_id->local_id);
 	cm_deref_id(cm_id_priv);
 	wait_for_completion(&cm_id_priv->comp);
@@ -1192,12 +1254,13 @@ int ib_send_cm_req(struct ib_cm_id *cm_id,
 		goto out;
 	}
 
-	ret = cm_init_av_by_path(param->primary_path, &cm_id_priv->av);
+	ret = cm_init_av_by_path(param->primary_path, &cm_id_priv->av,
+				 cm_id_priv);
 	if (ret)
 		goto error1;
 	if (param->alternate_path) {
 		ret = cm_init_av_by_path(param->alternate_path,
-					 &cm_id_priv->alt_av);
+					 &cm_id_priv->alt_av, cm_id_priv);
 		if (ret)
 			goto error1;
 	}
@@ -1653,7 +1716,8 @@ static int cm_req_handler(struct cm_work *work)
 			dev_put(gid_attr.ndev);
 		}
 		work->path[0].gid_type = gid_attr.gid_type;
-		ret = cm_init_av_by_path(&work->path[0], &cm_id_priv->av);
+		ret = cm_init_av_by_path(&work->path[0], &cm_id_priv->av,
+					 cm_id_priv);
 	}
 	if (ret) {
 		int err = ib_get_cached_gid(work->port->cm_dev->ib_device,
@@ -1672,7 +1736,8 @@ static int cm_req_handler(struct cm_work *work)
 		goto rejected;
 	}
 	if (req_msg->alt_local_lid) {
-		ret = cm_init_av_by_path(&work->path[1], &cm_id_priv->alt_av);
+		ret = cm_init_av_by_path(&work->path[1], &cm_id_priv->alt_av,
+					 cm_id_priv);
 		if (ret) {
 			ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_ALT_GID,
 				       &work->path[0].sgid,
@@ -2727,7 +2792,8 @@ int ib_send_cm_lap(struct ib_cm_id *cm_id,
 		goto out;
 	}
 
-	ret = cm_init_av_by_path(alternate_path, &cm_id_priv->alt_av);
+	ret = cm_init_av_by_path(alternate_path, &cm_id_priv->alt_av,
+				 cm_id_priv);
 	if (ret)
 		goto out;
 	cm_id_priv->alt_av.timeout =
@@ -2839,7 +2905,8 @@ static int cm_lap_handler(struct cm_work *work)
 	cm_init_av_for_response(work->port, work->mad_recv_wc->wc,
 				work->mad_recv_wc->recv_buf.grh,
 				&cm_id_priv->av);
-	cm_init_av_by_path(param->alternate_path, &cm_id_priv->alt_av);
+	cm_init_av_by_path(param->alternate_path, &cm_id_priv->alt_av,
+			   cm_id_priv);
 	ret = atomic_inc_and_test(&cm_id_priv->work_count);
 	if (!ret)
 		list_add_tail(&work->list, &cm_id_priv->work_list);
@@ -3031,7 +3098,7 @@ int ib_send_cm_sidr_req(struct ib_cm_id *cm_id,
 		return -EINVAL;
 
 	cm_id_priv = container_of(cm_id, struct cm_id_private, id);
-	ret = cm_init_av_by_path(param->path, &cm_id_priv->av);
+	ret = cm_init_av_by_path(param->path, &cm_id_priv->av, cm_id_priv);
 	if (ret)
 		goto out;
 
@@ -3468,7 +3535,9 @@ out:
 static int cm_migrate(struct ib_cm_id *cm_id)
 {
 	struct cm_id_private *cm_id_priv;
+	struct cm_av tmp_av;
 	unsigned long flags;
+	int tmp_send_port_not_ready;
 	int ret = 0;
 
 	cm_id_priv = container_of(cm_id, struct cm_id_private, id);
@@ -3477,7 +3546,14 @@ static int cm_migrate(struct ib_cm_id *cm_id)
 	    (cm_id->lap_state == IB_CM_LAP_UNINIT ||
 	     cm_id->lap_state == IB_CM_LAP_IDLE)) {
 		cm_id->lap_state = IB_CM_LAP_IDLE;
+		/* Swap address vector */
+		tmp_av = cm_id_priv->av;
 		cm_id_priv->av = cm_id_priv->alt_av;
+		cm_id_priv->alt_av = tmp_av;
+		/* Swap port send ready state */
+		tmp_send_port_not_ready = cm_id_priv->prim_send_port_not_ready;
+		cm_id_priv->prim_send_port_not_ready = cm_id_priv->altr_send_port_not_ready;
+		cm_id_priv->altr_send_port_not_ready = tmp_send_port_not_ready;
 	} else
 		ret = -EINVAL;
 	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
@@ -3888,6 +3964,9 @@ static void cm_add_one(struct ib_device *ib_device)
 		port->cm_dev = cm_dev;
 		port->port_num = i;
 
+		INIT_LIST_HEAD(&port->cm_priv_prim_list);
+		INIT_LIST_HEAD(&port->cm_priv_altr_list);
+
 		ret = cm_create_port_fs(port);
 		if (ret)
 			goto error1;
@@ -3945,6 +4024,8 @@ static void cm_remove_one(struct ib_device *ib_device, void *client_data)
 {
 	struct cm_device *cm_dev = client_data;
 	struct cm_port *port;
+	struct cm_id_private *cm_id_priv;
+	struct ib_mad_agent *cur_mad_agent;
 	struct ib_port_modify port_modify = {
 		.clr_port_cap_mask = IB_PORT_CM_SUP
 	};
@@ -3968,15 +4049,27 @@ static void cm_remove_one(struct ib_device *ib_device, void *client_data)
 
 		port = cm_dev->port[i-1];
 		ib_modify_port(ib_device, port->port_num, 0, &port_modify);
+		/* Mark all the cm_id's as not valid */
+		spin_lock_irq(&cm.lock);
+		list_for_each_entry(cm_id_priv, &port->cm_priv_altr_list, altr_list)
+			cm_id_priv->altr_send_port_not_ready = 1;
+		list_for_each_entry(cm_id_priv, &port->cm_priv_prim_list, prim_list)
+			cm_id_priv->prim_send_port_not_ready = 1;
+		spin_unlock_irq(&cm.lock);
 		/*
 		 * We flush the queue here after the going_down set, this
 		 * verify that no new works will be queued in the recv handler,
 		 * after that we can call the unregister_mad_agent
 		 */
 		flush_workqueue(cm.wq);
-		ib_unregister_mad_agent(port->mad_agent);
+		spin_lock_irq(&cm.state_lock);
+		cur_mad_agent = port->mad_agent;
+		port->mad_agent = NULL;
+		spin_unlock_irq(&cm.state_lock);
+		ib_unregister_mad_agent(cur_mad_agent);
 		cm_remove_port_fs(port);
 	}
+
 	device_unregister(cm_dev->device);
 	kfree(cm_dev);
 }
@@ -3989,6 +4082,7 @@ static int __init ib_cm_init(void)
 	INIT_LIST_HEAD(&cm.device_list);
 	rwlock_init(&cm.device_lock);
 	spin_lock_init(&cm.lock);
+	spin_lock_init(&cm.state_lock);
 	cm.listen_service_table = RB_ROOT;
 	cm.listen_service_id = be64_to_cpu(IB_CM_ASSIGN_SERVICE_ID);
 	cm.remote_id_table = RB_ROOT;
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 89a6b0546804..2a6fc47a1dfb 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -2438,6 +2438,18 @@ static int iboe_tos_to_sl(struct net_device *ndev, int tos)
 	return 0;
 }
 
+static enum ib_gid_type cma_route_gid_type(enum rdma_network_type network_type,
+					   unsigned long supported_gids,
+					   enum ib_gid_type default_gid)
+{
+	if ((network_type == RDMA_NETWORK_IPV4 ||
+	     network_type == RDMA_NETWORK_IPV6) &&
+	    test_bit(IB_GID_TYPE_ROCE_UDP_ENCAP, &supported_gids))
+		return IB_GID_TYPE_ROCE_UDP_ENCAP;
+
+	return default_gid;
+}
+
 static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 {
 	struct rdma_route *route = &id_priv->id.route;
@@ -2463,6 +2475,8 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 	route->num_paths = 1;
 
 	if (addr->dev_addr.bound_dev_if) {
+		unsigned long supported_gids;
+
 		ndev = dev_get_by_index(&init_net, addr->dev_addr.bound_dev_if);
 		if (!ndev) {
 			ret = -ENODEV;
@@ -2486,7 +2500,12 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 
 		route->path_rec->net = &init_net;
 		route->path_rec->ifindex = ndev->ifindex;
-		route->path_rec->gid_type = id_priv->gid_type;
+		supported_gids = roce_gid_type_mask_support(id_priv->id.device,
+							    id_priv->id.port_num);
+		route->path_rec->gid_type =
+			cma_route_gid_type(addr->dev_addr.network,
+					   supported_gids,
+					   id_priv->gid_type);
 	}
 	if (!ndev) {
 		ret = -ENODEV;
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 224ad274ea0b..84b4eff90395 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -175,7 +175,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 
 	cur_base = addr & PAGE_MASK;
 
-	if (npages == 0) {
+	if (npages == 0 || npages > UINT_MAX) {
 		ret = -EINVAL;
 		goto out;
 	}
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 0012fa58c105..44b1104eb168 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -262,12 +262,9 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
 			container_of(uobj, struct ib_uqp_object, uevent.uobject);
 
 		idr_remove_uobj(&ib_uverbs_qp_idr, uobj);
-		if (qp != qp->real_qp) {
-			ib_close_qp(qp);
-		} else {
+		if (qp == qp->real_qp)
 			ib_uverbs_detach_umcast(qp, uqp);
-			ib_destroy_qp(qp);
-		}
+		ib_destroy_qp(qp);
 		ib_uverbs_release_uevent(file, &uqp->uevent);
 		kfree(uqp);
 	}
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index 867b8cf82be8..19c6477af19f 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -666,18 +666,6 @@ skip_cqe:
 	return ret;
 }
 
-static void invalidate_mr(struct c4iw_dev *rhp, u32 rkey)
-{
-	struct c4iw_mr *mhp;
-	unsigned long flags;
-
-	spin_lock_irqsave(&rhp->lock, flags);
-	mhp = get_mhp(rhp, rkey >> 8);
-	if (mhp)
-		mhp->attr.state = 0;
-	spin_unlock_irqrestore(&rhp->lock, flags);
-}
-
 /*
  * Get one cq entry from c4iw and map it to openib.
  *
@@ -733,7 +721,7 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc)
 		    CQE_OPCODE(&cqe) == FW_RI_SEND_WITH_SE_INV) {
 			wc->ex.invalidate_rkey = CQE_WRID_STAG(&cqe);
 			wc->wc_flags |= IB_WC_WITH_INVALIDATE;
-			invalidate_mr(qhp->rhp, wc->ex.invalidate_rkey);
+			c4iw_invalidate_mr(qhp->rhp, wc->ex.invalidate_rkey);
 		}
 	} else {
 		switch (CQE_OPCODE(&cqe)) {
@@ -762,7 +750,8 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc)
 
 			/* Invalidate the MR if the fastreg failed */
 			if (CQE_STATUS(&cqe) != T4_ERR_SUCCESS)
-				invalidate_mr(qhp->rhp, CQE_WRID_FR_STAG(&cqe));
+				c4iw_invalidate_mr(qhp->rhp,
+						   CQE_WRID_FR_STAG(&cqe));
 			break;
 		default:
 			printk(KERN_ERR MOD "Unexpected opcode %d "
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 7e7f79e55006..4788e1a46fde 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -999,6 +999,6 @@ extern int db_coalescing_threshold;
 extern int use_dsgl;
 void c4iw_drain_rq(struct ib_qp *qp);
 void c4iw_drain_sq(struct ib_qp *qp);
-
+void c4iw_invalidate_mr(struct c4iw_dev *rhp, u32 rkey);
 
 #endif
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 80e27749420a..410408f886c1 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -770,3 +770,15 @@ int c4iw_dereg_mr(struct ib_mr *ib_mr)
 	kfree(mhp);
 	return 0;
 }
+
+void c4iw_invalidate_mr(struct c4iw_dev *rhp, u32 rkey)
+{
+	struct c4iw_mr *mhp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rhp->lock, flags);
+	mhp = get_mhp(rhp, rkey >> 8);
+	if (mhp)
+		mhp->attr.state = 0;
+	spin_unlock_irqrestore(&rhp->lock, flags);
+}
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index f57deba6717c..b7ac97b27c88 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -706,12 +706,8 @@ static int build_memreg(struct t4_sq *sq, union t4_wr *wqe,
 	return 0;
 }
 
-static int build_inv_stag(struct c4iw_dev *dev, union t4_wr *wqe,
-			  struct ib_send_wr *wr, u8 *len16)
+static int build_inv_stag(union t4_wr *wqe, struct ib_send_wr *wr, u8 *len16)
 {
-	struct c4iw_mr *mhp = get_mhp(dev, wr->ex.invalidate_rkey >> 8);
-
-	mhp->attr.state = 0;
 	wqe->inv.stag_inv = cpu_to_be32(wr->ex.invalidate_rkey);
 	wqe->inv.r2 = 0;
 	*len16 = DIV_ROUND_UP(sizeof wqe->inv, 16);
@@ -797,11 +793,13 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 	spin_lock_irqsave(&qhp->lock, flag);
 	if (t4_wq_in_error(&qhp->wq)) {
 		spin_unlock_irqrestore(&qhp->lock, flag);
+		*bad_wr = wr;
 		return -EINVAL;
 	}
 	num_wrs = t4_sq_avail(&qhp->wq);
 	if (num_wrs == 0) {
 		spin_unlock_irqrestore(&qhp->lock, flag);
+		*bad_wr = wr;
 		return -ENOMEM;
 	}
 	while (wr) {
@@ -840,10 +838,13 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		case IB_WR_RDMA_READ_WITH_INV:
 			fw_opcode = FW_RI_RDMA_READ_WR;
 			swsqe->opcode = FW_RI_READ_REQ;
-			if (wr->opcode == IB_WR_RDMA_READ_WITH_INV)
+			if (wr->opcode == IB_WR_RDMA_READ_WITH_INV) {
+				c4iw_invalidate_mr(qhp->rhp,
+						   wr->sg_list[0].lkey);
 				fw_flags = FW_RI_RDMA_READ_INVALIDATE;
-			else
+			} else {
 				fw_flags = 0;
+			}
 			err = build_rdma_read(wqe, wr, &len16);
 			if (err)
 				break;
@@ -876,7 +877,8 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 				fw_flags |= FW_RI_LOCAL_FENCE_FLAG;
 			fw_opcode = FW_RI_INV_LSTAG_WR;
 			swsqe->opcode = FW_RI_LOCAL_INV;
-			err = build_inv_stag(qhp->rhp, wqe, wr, &len16);
+			err = build_inv_stag(wqe, wr, &len16);
+			c4iw_invalidate_mr(qhp->rhp, wr->ex.invalidate_rkey);
 			break;
 		default:
 			PDBG("%s post of type=%d TBD!\n", __func__,
@@ -934,11 +936,13 @@ int c4iw_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 	spin_lock_irqsave(&qhp->lock, flag);
 	if (t4_wq_in_error(&qhp->wq)) {
 		spin_unlock_irqrestore(&qhp->lock, flag);
+		*bad_wr = wr;
 		return -EINVAL;
 	}
 	num_wrs = t4_rq_avail(&qhp->wq);
 	if (num_wrs == 0) {
 		spin_unlock_irqrestore(&qhp->lock, flag);
+		*bad_wr = wr;
 		return -ENOMEM;
 	}
 	while (wr) {
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index a26a9a0bfc41..67ea85a56945 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -775,75 +775,3 @@ void hfi1_put_proc_affinity(int cpu)
 	}
 	mutex_unlock(&affinity->lock);
 }
-
-int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf,
-			   size_t count)
-{
-	struct hfi1_affinity_node *entry;
-	cpumask_var_t mask;
-	int ret, i;
-
-	mutex_lock(&node_affinity.lock);
-	entry = node_affinity_lookup(dd->node);
-
-	if (!entry) {
-		ret = -EINVAL;
-		goto unlock;
-	}
-
-	ret = zalloc_cpumask_var(&mask, GFP_KERNEL);
-	if (!ret) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
-
-	ret = cpulist_parse(buf, mask);
-	if (ret)
-		goto out;
-
-	if (!cpumask_subset(mask, cpu_online_mask) || cpumask_empty(mask)) {
-		dd_dev_warn(dd, "Invalid CPU mask\n");
-		ret = -EINVAL;
-		goto out;
-	}
-
-	/* reset the SDMA interrupt affinity details */
-	init_cpu_mask_set(&entry->def_intr);
-	cpumask_copy(&entry->def_intr.mask, mask);
-
-	/* Reassign the affinity for each SDMA interrupt. */
-	for (i = 0; i < dd->num_msix_entries; i++) {
-		struct hfi1_msix_entry *msix;
-
-		msix = &dd->msix_entries[i];
-		if (msix->type != IRQ_SDMA)
-			continue;
-
-		ret = get_irq_affinity(dd, msix);
-
-		if (ret)
-			break;
-	}
-out:
-	free_cpumask_var(mask);
-unlock:
-	mutex_unlock(&node_affinity.lock);
-	return ret ? ret : strnlen(buf, PAGE_SIZE);
-}
-
-int hfi1_get_sdma_affinity(struct hfi1_devdata *dd, char *buf)
-{
-	struct hfi1_affinity_node *entry;
-
-	mutex_lock(&node_affinity.lock);
-	entry = node_affinity_lookup(dd->node);
-
-	if (!entry) {
-		mutex_unlock(&node_affinity.lock);
-		return -EINVAL;
-	}
-
-	cpumap_print_to_pagebuf(true, buf, &entry->def_intr.mask);
-	mutex_unlock(&node_affinity.lock);
-	return strnlen(buf, PAGE_SIZE);
-}
diff --git a/drivers/infiniband/hw/hfi1/affinity.h b/drivers/infiniband/hw/hfi1/affinity.h
index b89ea3c0ee1a..42e63316afd1 100644
--- a/drivers/infiniband/hw/hfi1/affinity.h
+++ b/drivers/infiniband/hw/hfi1/affinity.h
@@ -102,10 +102,6 @@ int hfi1_get_proc_affinity(int);
 /* Release a CPU used by a user process. */
 void hfi1_put_proc_affinity(int);
 
-int hfi1_get_sdma_affinity(struct hfi1_devdata *dd, char *buf);
-int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf,
-			   size_t count);
-
 struct hfi1_affinity_node {
 	int node;
 	struct cpu_mask_set def_intr;
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 9bf5f23544d4..24d0820873cf 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -6301,19 +6301,8 @@ void set_up_vl15(struct hfi1_devdata *dd, u8 vau, u16 vl15buf)
 	/* leave shared count at zero for both global and VL15 */
 	write_global_credit(dd, vau, vl15buf, 0);
 
-	/* We may need some credits for another VL when sending packets
-	 * with the snoop interface. Dividing it down the middle for VL15
-	 * and VL0 should suffice.
-	 */
-	if (unlikely(dd->hfi1_snoop.mode_flag == HFI1_PORT_SNOOP_MODE)) {
-		write_csr(dd, SEND_CM_CREDIT_VL15, (u64)(vl15buf >> 1)
-		    << SEND_CM_CREDIT_VL15_DEDICATED_LIMIT_VL_SHIFT);
-		write_csr(dd, SEND_CM_CREDIT_VL, (u64)(vl15buf >> 1)
-		    << SEND_CM_CREDIT_VL_DEDICATED_LIMIT_VL_SHIFT);
-	} else {
-		write_csr(dd, SEND_CM_CREDIT_VL15, (u64)vl15buf
-			<< SEND_CM_CREDIT_VL15_DEDICATED_LIMIT_VL_SHIFT);
-	}
+	write_csr(dd, SEND_CM_CREDIT_VL15, (u64)vl15buf
+		  << SEND_CM_CREDIT_VL15_DEDICATED_LIMIT_VL_SHIFT);
 }
 
 /*
@@ -9915,9 +9904,6 @@ static void set_lidlmc(struct hfi1_pportdata *ppd)
 	u32 mask = ~((1U << ppd->lmc) - 1);
 	u64 c1 = read_csr(ppd->dd, DCC_CFG_PORT_CONFIG1);
 
-	if (dd->hfi1_snoop.mode_flag)
-		dd_dev_info(dd, "Set lid/lmc while snooping");
-
 	c1 &= ~(DCC_CFG_PORT_CONFIG1_TARGET_DLID_SMASK
 		| DCC_CFG_PORT_CONFIG1_DLID_MASK_SMASK);
 	c1 |= ((ppd->lid & DCC_CFG_PORT_CONFIG1_TARGET_DLID_MASK)
@@ -12112,7 +12098,7 @@ static void update_synth_timer(unsigned long opaque)
 	mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME);
 }
 
-#define C_MAX_NAME 13 /* 12 chars + one for /0 */
+#define C_MAX_NAME 16 /* 15 chars + one for /0 */
 static int init_cntrs(struct hfi1_devdata *dd)
 {
 	int i, rcv_ctxts, j;
@@ -14463,7 +14449,7 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev,
 	 * Any error printing is already done by the init code.
 	 * On return, we have the chip mapped.
 	 */
-	ret = hfi1_pcie_ddinit(dd, pdev, ent);
+	ret = hfi1_pcie_ddinit(dd, pdev);
 	if (ret < 0)
 		goto bail_free;
 
@@ -14691,6 +14677,11 @@ struct hfi1_devdata *hfi1_init_dd(struct pci_dev *pdev,
 	if (ret)
 		goto bail_free_cntrs;
 
+	init_completion(&dd->user_comp);
+
+	/* The user refcount starts with one to inidicate an active device */
+	atomic_set(&dd->user_refcount, 1);
+
 	goto bail;
 
 bail_free_rcverr:
diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h
index 92345259a8f4..043fd21dc5f3 100644
--- a/drivers/infiniband/hw/hfi1/chip.h
+++ b/drivers/infiniband/hw/hfi1/chip.h
@@ -320,6 +320,9 @@
 /* DC_DC8051_CFG_MODE.GENERAL bits */
 #define DISABLE_SELF_GUID_CHECK 0x2
 
+/* Bad L2 frame error code */
+#define BAD_L2_ERR      0x6
+
 /*
  * Eager buffer minimum and maximum sizes supported by the hardware.
  * All power-of-two sizes in between are supported as well.
diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c
index 6563e4d38b80..c5efff29c147 100644
--- a/drivers/infiniband/hw/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -599,7 +599,6 @@ static void __prescan_rxq(struct hfi1_packet *packet)
 					 dd->rhf_offset;
 		struct rvt_qp *qp;
 		struct ib_header *hdr;
-		struct ib_other_headers *ohdr;
 		struct rvt_dev_info *rdi = &dd->verbs_dev.rdi;
 		u64 rhf = rhf_to_cpu(rhf_addr);
 		u32 etype = rhf_rcv_type(rhf), qpn, bth1;
@@ -615,18 +614,21 @@ static void __prescan_rxq(struct hfi1_packet *packet)
 		if (etype != RHF_RCV_TYPE_IB)
 			goto next;
 
-		hdr = hfi1_get_msgheader(dd, rhf_addr);
+		packet->hdr = hfi1_get_msgheader(dd, rhf_addr);
+		hdr = packet->hdr;
 
 		lnh = be16_to_cpu(hdr->lrh[0]) & 3;
 
-		if (lnh == HFI1_LRH_BTH)
-			ohdr = &hdr->u.oth;
-		else if (lnh == HFI1_LRH_GRH)
-			ohdr = &hdr->u.l.oth;
-		else
+		if (lnh == HFI1_LRH_BTH) {
+			packet->ohdr = &hdr->u.oth;
+		} else if (lnh == HFI1_LRH_GRH) {
+			packet->ohdr = &hdr->u.l.oth;
+			packet->rcv_flags |= HFI1_HAS_GRH;
+		} else {
 			goto next; /* just in case */
+		}
 
-		bth1 = be32_to_cpu(ohdr->bth[1]);
+		bth1 = be32_to_cpu(packet->ohdr->bth[1]);
 		is_ecn = !!(bth1 & (HFI1_FECN_SMASK | HFI1_BECN_SMASK));
 
 		if (!is_ecn)
@@ -646,7 +648,7 @@ static void __prescan_rxq(struct hfi1_packet *packet)
 
 		/* turn off BECN, FECN */
 		bth1 &= ~(HFI1_FECN_SMASK | HFI1_BECN_SMASK);
-		ohdr->bth[1] = cpu_to_be32(bth1);
+		packet->ohdr->bth[1] = cpu_to_be32(bth1);
 next:
 		update_ps_mdata(&mdata, rcd);
 	}
@@ -1360,12 +1362,25 @@ int process_receive_ib(struct hfi1_packet *packet)
 
 int process_receive_bypass(struct hfi1_packet *packet)
 {
+	struct hfi1_devdata *dd = packet->rcd->dd;
+
 	if (unlikely(rhf_err_flags(packet->rhf)))
 		handle_eflags(packet);
 
-	dd_dev_err(packet->rcd->dd,
+	dd_dev_err(dd,
 		   "Bypass packets are not supported in normal operation. Dropping\n");
-	incr_cntr64(&packet->rcd->dd->sw_rcv_bypass_packet_errors);
+	incr_cntr64(&dd->sw_rcv_bypass_packet_errors);
+	if (!(dd->err_info_rcvport.status_and_code & OPA_EI_STATUS_SMASK)) {
+		u64 *flits = packet->ebuf;
+
+		if (flits && !(packet->rhf & RHF_LEN_ERR)) {
+			dd->err_info_rcvport.packet_flit1 = flits[0];
+			dd->err_info_rcvport.packet_flit2 =
+				packet->tlen > sizeof(flits[0]) ? flits[1] : 0;
+		}
+		dd->err_info_rcvport.status_and_code |=
+			(OPA_EI_STATUS_SMASK | BAD_L2_ERR);
+	}
 	return RHF_RCV_CONTINUE;
 }
 
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index 677efa0e8cd6..bd786b7bd30b 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -172,6 +172,9 @@ static int hfi1_file_open(struct inode *inode, struct file *fp)
 					       struct hfi1_devdata,
 					       user_cdev);
 
+	if (!atomic_inc_not_zero(&dd->user_refcount))
+		return -ENXIO;
+
 	/* Just take a ref now. Not all opens result in a context assign */
 	kobject_get(&dd->kobj);
 
@@ -183,11 +186,17 @@ static int hfi1_file_open(struct inode *inode, struct file *fp)
 		fd->rec_cpu_num = -1; /* no cpu affinity by default */
 		fd->mm = current->mm;
 		atomic_inc(&fd->mm->mm_count);
-	}
+		fp->private_data = fd;
+	} else {
+		fp->private_data = NULL;
+
+		if (atomic_dec_and_test(&dd->user_refcount))
+			complete(&dd->user_comp);
 
-	fp->private_data = fd;
+		return -ENOMEM;
+	}
 
-	return fd ? 0 : -ENOMEM;
+	return 0;
 }
 
 static long hfi1_file_ioctl(struct file *fp, unsigned int cmd,
@@ -798,6 +807,10 @@ static int hfi1_file_close(struct inode *inode, struct file *fp)
 done:
 	mmdrop(fdata->mm);
 	kobject_put(&dd->kobj);
+
+	if (atomic_dec_and_test(&dd->user_refcount))
+		complete(&dd->user_comp);
+
 	kfree(fdata);
 	return 0;
 }
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 7eef11b316ff..cc87fd4e534b 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -367,26 +367,6 @@ struct hfi1_packet {
 	u8 etype;
 };
 
-/*
- * Private data for snoop/capture support.
- */
-struct hfi1_snoop_data {
-	int mode_flag;
-	struct cdev cdev;
-	struct device *class_dev;
-	/* protect snoop data */
-	spinlock_t snoop_lock;
-	struct list_head queue;
-	wait_queue_head_t waitq;
-	void *filter_value;
-	int (*filter_callback)(void *hdr, void *data, void *value);
-	u64 dcc_cfg; /* saved value of DCC Cfg register */
-};
-
-/* snoop mode_flag values */
-#define HFI1_PORT_SNOOP_MODE     1U
-#define HFI1_PORT_CAPTURE_MODE   2U
-
 struct rvt_sge_state;
 
 /*
@@ -613,8 +593,6 @@ struct hfi1_pportdata {
 	struct mutex hls_lock;
 	u32 host_link_state;
 
-	spinlock_t            sdma_alllock ____cacheline_aligned_in_smp;
-
 	u32 lstate;	/* logical link state */
 
 	/* these are the "32 bit" regs */
@@ -1104,8 +1082,6 @@ struct hfi1_devdata {
 	char *portcntrnames;
 	size_t portcntrnameslen;
 
-	struct hfi1_snoop_data hfi1_snoop;
-
 	struct err_info_rcvport err_info_rcvport;
 	struct err_info_constraint err_info_rcv_constraint;
 	struct err_info_constraint err_info_xmit_constraint;
@@ -1141,8 +1117,8 @@ struct hfi1_devdata {
 	rhf_rcv_function_ptr normal_rhf_rcv_functions[8];
 
 	/*
-	 * Handlers for outgoing data so that snoop/capture does not
-	 * have to have its hooks in the send path
+	 * Capability to have different send engines simply by changing a
+	 * pointer value.
 	 */
 	send_routine process_pio_send;
 	send_routine process_dma_send;
@@ -1174,6 +1150,10 @@ struct hfi1_devdata {
 	spinlock_t aspm_lock;
 	/* Number of verbs contexts which have disabled ASPM */
 	atomic_t aspm_disabled_cnt;
+	/* Keeps track of user space clients */
+	atomic_t user_refcount;
+	/* Used to wait for outstanding user space clients before dev removal */
+	struct completion user_comp;
 
 	struct hfi1_affinity *affinity;
 	struct rhashtable sdma_rht;
@@ -1221,8 +1201,6 @@ struct hfi1_devdata *hfi1_lookup(int unit);
 extern u32 hfi1_cpulist_count;
 extern unsigned long *hfi1_cpulist;
 
-extern unsigned int snoop_drop_send;
-extern unsigned int snoop_force_capture;
 int hfi1_init(struct hfi1_devdata *, int);
 int hfi1_count_units(int *npresentp, int *nupp);
 int hfi1_count_active_units(void);
@@ -1557,13 +1535,6 @@ void set_up_vl15(struct hfi1_devdata *dd, u8 vau, u16 vl15buf);
 void reset_link_credits(struct hfi1_devdata *dd);
 void assign_remote_cm_au_table(struct hfi1_devdata *dd, u8 vcu);
 
-int snoop_recv_handler(struct hfi1_packet *packet);
-int snoop_send_dma_handler(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
-			   u64 pbc);
-int snoop_send_pio_handler(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
-			   u64 pbc);
-void snoop_inline_pio_send(struct hfi1_devdata *dd, struct pio_buf *pbuf,
-			   u64 pbc, const void *from, size_t count);
 int set_buffer_control(struct hfi1_pportdata *ppd, struct buffer_control *bc);
 
 static inline struct hfi1_devdata *dd_from_ppd(struct hfi1_pportdata *ppd)
@@ -1763,8 +1734,7 @@ int qsfp_dump(struct hfi1_pportdata *ppd, char *buf, int len);
 
 int hfi1_pcie_init(struct pci_dev *, const struct pci_device_id *);
 void hfi1_pcie_cleanup(struct pci_dev *);
-int hfi1_pcie_ddinit(struct hfi1_devdata *, struct pci_dev *,
-		     const struct pci_device_id *);
+int hfi1_pcie_ddinit(struct hfi1_devdata *, struct pci_dev *);
 void hfi1_pcie_ddcleanup(struct hfi1_devdata *);
 void hfi1_pcie_flr(struct hfi1_devdata *);
 int pcie_speeds(struct hfi1_devdata *);
@@ -1799,8 +1769,6 @@ int kdeth_process_expected(struct hfi1_packet *packet);
 int kdeth_process_eager(struct hfi1_packet *packet);
 int process_receive_invalid(struct hfi1_packet *packet);
 
-extern rhf_rcv_function_ptr snoop_rhf_rcv_functions[8];
-
 void update_sge(struct rvt_sge_state *ss, u32 length);
 
 /* global module parameter variables */
@@ -1827,9 +1795,6 @@ extern struct mutex hfi1_mutex;
 #define DRIVER_NAME		"hfi1"
 #define HFI1_USER_MINOR_BASE     0
 #define HFI1_TRACE_MINOR         127
-#define HFI1_DIAGPKT_MINOR       128
-#define HFI1_DIAG_MINOR_BASE     129
-#define HFI1_SNOOP_CAPTURE_BASE  200
 #define HFI1_NMINORS             255
 
 #define PCI_VENDOR_ID_INTEL 0x8086
@@ -1848,7 +1813,13 @@ extern struct mutex hfi1_mutex;
 static inline u64 hfi1_pkt_default_send_ctxt_mask(struct hfi1_devdata *dd,
 						  u16 ctxt_type)
 {
-	u64 base_sc_integrity =
+	u64 base_sc_integrity;
+
+	/* No integrity checks if HFI1_CAP_NO_INTEGRITY is set */
+	if (HFI1_CAP_IS_KSET(NO_INTEGRITY))
+		return 0;
+
+	base_sc_integrity =
 	SEND_CTXT_CHECK_ENABLE_DISALLOW_BYPASS_BAD_PKT_LEN_SMASK
 	| SEND_CTXT_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK
 	| SEND_CTXT_CHECK_ENABLE_DISALLOW_TOO_LONG_BYPASS_PACKETS_SMASK
@@ -1863,7 +1834,6 @@ static inline u64 hfi1_pkt_default_send_ctxt_mask(struct hfi1_devdata *dd,
 	| SEND_CTXT_CHECK_ENABLE_CHECK_VL_MAPPING_SMASK
 	| SEND_CTXT_CHECK_ENABLE_CHECK_OPCODE_SMASK
 	| SEND_CTXT_CHECK_ENABLE_CHECK_SLID_SMASK
-	| SEND_CTXT_CHECK_ENABLE_CHECK_JOB_KEY_SMASK
 	| SEND_CTXT_CHECK_ENABLE_CHECK_VL_SMASK
 	| SEND_CTXT_CHECK_ENABLE_CHECK_ENABLE_SMASK;
 
@@ -1872,18 +1842,23 @@ static inline u64 hfi1_pkt_default_send_ctxt_mask(struct hfi1_devdata *dd,
 	else
 		base_sc_integrity |= HFI1_PKT_KERNEL_SC_INTEGRITY;
 
-	if (is_ax(dd))
-		/* turn off send-side job key checks - A0 */
-		return base_sc_integrity &
-		       ~SEND_CTXT_CHECK_ENABLE_CHECK_JOB_KEY_SMASK;
+	/* turn on send-side job key checks if !A0 */
+	if (!is_ax(dd))
+		base_sc_integrity |= SEND_CTXT_CHECK_ENABLE_CHECK_JOB_KEY_SMASK;
+
 	return base_sc_integrity;
 }
 
 static inline u64 hfi1_pkt_base_sdma_integrity(struct hfi1_devdata *dd)
 {
-	u64 base_sdma_integrity =
+	u64 base_sdma_integrity;
+
+	/* No integrity checks if HFI1_CAP_NO_INTEGRITY is set */
+	if (HFI1_CAP_IS_KSET(NO_INTEGRITY))
+		return 0;
+
+	base_sdma_integrity =
 	SEND_DMA_CHECK_ENABLE_DISALLOW_BYPASS_BAD_PKT_LEN_SMASK
-	| SEND_DMA_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK
 	| SEND_DMA_CHECK_ENABLE_DISALLOW_TOO_LONG_BYPASS_PACKETS_SMASK
 	| SEND_DMA_CHECK_ENABLE_DISALLOW_TOO_LONG_IB_PACKETS_SMASK
 	| SEND_DMA_CHECK_ENABLE_DISALLOW_BAD_PKT_LEN_SMASK
@@ -1895,14 +1870,18 @@ static inline u64 hfi1_pkt_base_sdma_integrity(struct hfi1_devdata *dd)
 	| SEND_DMA_CHECK_ENABLE_CHECK_VL_MAPPING_SMASK
 	| SEND_DMA_CHECK_ENABLE_CHECK_OPCODE_SMASK
 	| SEND_DMA_CHECK_ENABLE_CHECK_SLID_SMASK
-	| SEND_DMA_CHECK_ENABLE_CHECK_JOB_KEY_SMASK
 	| SEND_DMA_CHECK_ENABLE_CHECK_VL_SMASK
 	| SEND_DMA_CHECK_ENABLE_CHECK_ENABLE_SMASK;
 
-	if (is_ax(dd))
-		/* turn off send-side job key checks - A0 */
-		return base_sdma_integrity &
-		       ~SEND_DMA_CHECK_ENABLE_CHECK_JOB_KEY_SMASK;
+	if (!HFI1_CAP_IS_KSET(STATIC_RATE_CTRL))
+		base_sdma_integrity |=
+		SEND_DMA_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK;
+
+	/* turn on send-side job key checks if !A0 */
+	if (!is_ax(dd))
+		base_sdma_integrity |=
+			SEND_DMA_CHECK_ENABLE_CHECK_JOB_KEY_SMASK;
+
 	return base_sdma_integrity;
 }
 
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 60db61536fed..e3b5bc93bc70 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -144,6 +144,8 @@ int hfi1_create_ctxts(struct hfi1_devdata *dd)
 		struct hfi1_ctxtdata *rcd;
 
 		ppd = dd->pport + (i % dd->num_pports);
+
+		/* dd->rcd[i] gets assigned inside the callee */
 		rcd = hfi1_create_ctxtdata(ppd, i, dd->node);
 		if (!rcd) {
 			dd_dev_err(dd,
@@ -169,8 +171,6 @@ int hfi1_create_ctxts(struct hfi1_devdata *dd)
 		if (!rcd->sc) {
 			dd_dev_err(dd,
 				   "Unable to allocate kernel send context, failing\n");
-			dd->rcd[rcd->ctxt] = NULL;
-			hfi1_free_ctxtdata(dd, rcd);
 			goto nomem;
 		}
 
@@ -178,9 +178,6 @@ int hfi1_create_ctxts(struct hfi1_devdata *dd)
 		if (ret < 0) {
 			dd_dev_err(dd,
 				   "Failed to setup kernel receive context, failing\n");
-			sc_free(rcd->sc);
-			dd->rcd[rcd->ctxt] = NULL;
-			hfi1_free_ctxtdata(dd, rcd);
 			ret = -EFAULT;
 			goto bail;
 		}
@@ -196,6 +193,10 @@ int hfi1_create_ctxts(struct hfi1_devdata *dd)
 nomem:
 	ret = -ENOMEM;
 bail:
+	if (dd->rcd) {
+		for (i = 0; i < dd->num_rcv_contexts; ++i)
+			hfi1_free_ctxtdata(dd, dd->rcd[i]);
+	}
 	kfree(dd->rcd);
 	dd->rcd = NULL;
 	return ret;
@@ -216,7 +217,7 @@ struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt,
 	    dd->num_rcv_contexts - dd->first_user_ctxt)
 		kctxt_ngroups = (dd->rcv_entries.nctxt_extra -
 				 (dd->num_rcv_contexts - dd->first_user_ctxt));
-	rcd = kzalloc(sizeof(*rcd), GFP_KERNEL);
+	rcd = kzalloc_node(sizeof(*rcd), GFP_KERNEL, numa);
 	if (rcd) {
 		u32 rcvtids, max_entries;
 
@@ -261,13 +262,6 @@ struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt,
 		}
 		rcd->eager_base = base * dd->rcv_entries.group_size;
 
-		/* Validate and initialize Rcv Hdr Q variables */
-		if (rcvhdrcnt % HDRQ_INCREMENT) {
-			dd_dev_err(dd,
-				   "ctxt%u: header queue count %d must be divisible by %lu\n",
-				   rcd->ctxt, rcvhdrcnt, HDRQ_INCREMENT);
-			goto bail;
-		}
 		rcd->rcvhdrq_cnt = rcvhdrcnt;
 		rcd->rcvhdrqentsize = hfi1_hdrq_entsize;
 		/*
@@ -506,7 +500,6 @@ void hfi1_init_pportdata(struct pci_dev *pdev, struct hfi1_pportdata *ppd,
 	INIT_WORK(&ppd->qsfp_info.qsfp_work, qsfp_event);
 
 	mutex_init(&ppd->hls_lock);
-	spin_lock_init(&ppd->sdma_alllock);
 	spin_lock_init(&ppd->qsfp_info.qsfp_lock);
 
 	ppd->qsfp_info.ppd = ppd;
@@ -1399,28 +1392,43 @@ static void postinit_cleanup(struct hfi1_devdata *dd)
 	hfi1_free_devdata(dd);
 }
 
+static int init_validate_rcvhdrcnt(struct device *dev, uint thecnt)
+{
+	if (thecnt <= HFI1_MIN_HDRQ_EGRBUF_CNT) {
+		hfi1_early_err(dev, "Receive header queue count too small\n");
+		return -EINVAL;
+	}
+
+	if (thecnt > HFI1_MAX_HDRQ_EGRBUF_CNT) {
+		hfi1_early_err(dev,
+			       "Receive header queue count cannot be greater than %u\n",
+			       HFI1_MAX_HDRQ_EGRBUF_CNT);
+		return -EINVAL;
+	}
+
+	if (thecnt % HDRQ_INCREMENT) {
+		hfi1_early_err(dev, "Receive header queue count %d must be divisible by %lu\n",
+			       thecnt, HDRQ_INCREMENT);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int ret = 0, j, pidx, initfail;
-	struct hfi1_devdata *dd = ERR_PTR(-EINVAL);
+	struct hfi1_devdata *dd;
 	struct hfi1_pportdata *ppd;
 
 	/* First, lock the non-writable module parameters */
 	HFI1_CAP_LOCK();
 
 	/* Validate some global module parameters */
-	if (rcvhdrcnt <= HFI1_MIN_HDRQ_EGRBUF_CNT) {
-		hfi1_early_err(&pdev->dev, "Header queue  count too small\n");
-		ret = -EINVAL;
-		goto bail;
-	}
-	if (rcvhdrcnt > HFI1_MAX_HDRQ_EGRBUF_CNT) {
-		hfi1_early_err(&pdev->dev,
-			       "Receive header queue count cannot be greater than %u\n",
-			       HFI1_MAX_HDRQ_EGRBUF_CNT);
-		ret = -EINVAL;
+	ret = init_validate_rcvhdrcnt(&pdev->dev, rcvhdrcnt);
+	if (ret)
 		goto bail;
-	}
+
 	/* use the encoding function as a sanitization check */
 	if (!encode_rcv_header_entry_size(hfi1_hdrq_entsize)) {
 		hfi1_early_err(&pdev->dev, "Invalid HdrQ Entry size %u\n",
@@ -1461,26 +1469,25 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ret)
 		goto bail;
 
-	/*
-	 * Do device-specific initialization, function table setup, dd
-	 * allocation, etc.
-	 */
-	switch (ent->device) {
-	case PCI_DEVICE_ID_INTEL0:
-	case PCI_DEVICE_ID_INTEL1:
-		dd = hfi1_init_dd(pdev, ent);
-		break;
-	default:
+	if (!(ent->device == PCI_DEVICE_ID_INTEL0 ||
+	      ent->device == PCI_DEVICE_ID_INTEL1)) {
 		hfi1_early_err(&pdev->dev,
 			       "Failing on unknown Intel deviceid 0x%x\n",
 			       ent->device);
 		ret = -ENODEV;
+		goto clean_bail;
 	}
 
-	if (IS_ERR(dd))
+	/*
+	 * Do device-specific initialization, function table setup, dd
+	 * allocation, etc.
+	 */
+	dd = hfi1_init_dd(pdev, ent);
+
+	if (IS_ERR(dd)) {
 		ret = PTR_ERR(dd);
-	if (ret)
 		goto clean_bail; /* error already printed */
+	}
 
 	ret = create_workqueues(dd);
 	if (ret)
@@ -1538,12 +1545,31 @@ bail:
 	return ret;
 }
 
+static void wait_for_clients(struct hfi1_devdata *dd)
+{
+	/*
+	 * Remove the device init value and complete the device if there is
+	 * no clients or wait for active clients to finish.
+	 */
+	if (atomic_dec_and_test(&dd->user_refcount))
+		complete(&dd->user_comp);
+
+	wait_for_completion(&dd->user_comp);
+}
+
 static void remove_one(struct pci_dev *pdev)
 {
 	struct hfi1_devdata *dd = pci_get_drvdata(pdev);
 
 	/* close debugfs files before ib unregister */
 	hfi1_dbg_ibdev_exit(&dd->verbs_dev);
+
+	/* remove the /dev hfi1 interface */
+	hfi1_device_remove(dd);
+
+	/* wait for existing user space clients to finish */
+	wait_for_clients(dd);
+
 	/* unregister from IB core */
 	hfi1_unregister_ib_device(dd);
 
@@ -1558,8 +1584,6 @@ static void remove_one(struct pci_dev *pdev)
 	/* wait until all of our (qsfp) queue_work() calls complete */
 	flush_workqueue(ib_wq);
 
-	hfi1_device_remove(dd);
-
 	postinit_cleanup(dd);
 }
 
diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 89c68da1c273..4ac8f330c5cb 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -157,8 +157,7 @@ void hfi1_pcie_cleanup(struct pci_dev *pdev)
  * fields required to re-initialize after a chip reset, or for
  * various other purposes
  */
-int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev,
-		     const struct pci_device_id *ent)
+int hfi1_pcie_ddinit(struct hfi1_devdata *dd, struct pci_dev *pdev)
 {
 	unsigned long len;
 	resource_size_t addr;
diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c
index 50a3a36d9363..d89b8745d4c1 100644
--- a/drivers/infiniband/hw/hfi1/pio.c
+++ b/drivers/infiniband/hw/hfi1/pio.c
@@ -668,19 +668,12 @@ void sc_set_cr_threshold(struct send_context *sc, u32 new_threshold)
 void set_pio_integrity(struct send_context *sc)
 {
 	struct hfi1_devdata *dd = sc->dd;
-	u64 reg = 0;
 	u32 hw_context = sc->hw_context;
 	int type = sc->type;
 
-	/*
-	 * No integrity checks if HFI1_CAP_NO_INTEGRITY is set, or if
-	 * we're snooping.
-	 */
-	if (likely(!HFI1_CAP_IS_KSET(NO_INTEGRITY)) &&
-	    dd->hfi1_snoop.mode_flag != HFI1_PORT_SNOOP_MODE)
-		reg = hfi1_pkt_default_send_ctxt_mask(dd, type);
-
-	write_kctxt_csr(dd, hw_context, SC(CHECK_ENABLE), reg);
+	write_kctxt_csr(dd, hw_context,
+			SC(CHECK_ENABLE),
+			hfi1_pkt_default_send_ctxt_mask(dd, type));
 }
 
 static u32 get_buffers_allocated(struct send_context *sc)
diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index 8bc5013f39a1..83198a8a8797 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -89,7 +89,7 @@ void hfi1_add_rnr_timer(struct rvt_qp *qp, u32 to)
 
 	lockdep_assert_held(&qp->s_lock);
 	qp->s_flags |= RVT_S_WAIT_RNR;
-	qp->s_timer.expires = jiffies + usecs_to_jiffies(to);
+	priv->s_rnr_timer.expires = jiffies + usecs_to_jiffies(to);
 	add_timer(&priv->s_rnr_timer);
 }
 
diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index fd39bcaa062d..9cbe52d21077 100644
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -2009,11 +2009,6 @@ static void sdma_hw_start_up(struct sdma_engine *sde)
 	write_sde_csr(sde, SD(ENG_ERR_CLEAR), reg);
 }
 
-#define CLEAR_STATIC_RATE_CONTROL_SMASK(r) \
-(r &= ~SEND_DMA_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK)
-
-#define SET_STATIC_RATE_CONTROL_SMASK(r) \
-(r |= SEND_DMA_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK)
 /*
  * set_sdma_integrity
  *
@@ -2022,19 +2017,9 @@ static void sdma_hw_start_up(struct sdma_engine *sde)
 static void set_sdma_integrity(struct sdma_engine *sde)
 {
 	struct hfi1_devdata *dd = sde->dd;
-	u64 reg;
-
-	if (unlikely(HFI1_CAP_IS_KSET(NO_INTEGRITY)))
-		return;
-
-	reg = hfi1_pkt_base_sdma_integrity(dd);
-
-	if (HFI1_CAP_IS_KSET(STATIC_RATE_CTRL))
-		CLEAR_STATIC_RATE_CONTROL_SMASK(reg);
-	else
-		SET_STATIC_RATE_CONTROL_SMASK(reg);
 
-	write_sde_csr(sde, SD(CHECK_ENABLE), reg);
+	write_sde_csr(sde, SD(CHECK_ENABLE),
+		      hfi1_pkt_base_sdma_integrity(dd));
 }
 
 static void init_sdma_regs(
diff --git a/drivers/infiniband/hw/hfi1/sysfs.c b/drivers/infiniband/hw/hfi1/sysfs.c
index edba22461a9c..919a5474e651 100644
--- a/drivers/infiniband/hw/hfi1/sysfs.c
+++ b/drivers/infiniband/hw/hfi1/sysfs.c
@@ -49,7 +49,6 @@
 #include "hfi.h"
 #include "mad.h"
 #include "trace.h"
-#include "affinity.h"
 
 /*
  * Start of per-port congestion control structures and support code
@@ -623,27 +622,6 @@ static ssize_t show_tempsense(struct device *device,
 	return ret;
 }
 
-static ssize_t show_sdma_affinity(struct device *device,
-				  struct device_attribute *attr, char *buf)
-{
-	struct hfi1_ibdev *dev =
-		container_of(device, struct hfi1_ibdev, rdi.ibdev.dev);
-	struct hfi1_devdata *dd = dd_from_dev(dev);
-
-	return hfi1_get_sdma_affinity(dd, buf);
-}
-
-static ssize_t store_sdma_affinity(struct device *device,
-				   struct device_attribute *attr,
-				   const char *buf, size_t count)
-{
-	struct hfi1_ibdev *dev =
-		container_of(device, struct hfi1_ibdev, rdi.ibdev.dev);
-	struct hfi1_devdata *dd = dd_from_dev(dev);
-
-	return hfi1_set_sdma_affinity(dd, buf, count);
-}
-
 /*
  * end of per-unit (or driver, in some cases, but replicated
  * per unit) functions
@@ -658,8 +636,6 @@ static DEVICE_ATTR(serial, S_IRUGO, show_serial, NULL);
 static DEVICE_ATTR(boardversion, S_IRUGO, show_boardversion, NULL);
 static DEVICE_ATTR(tempsense, S_IRUGO, show_tempsense, NULL);
 static DEVICE_ATTR(chip_reset, S_IWUSR, NULL, store_chip_reset);
-static DEVICE_ATTR(sdma_affinity, S_IWUSR | S_IRUGO, show_sdma_affinity,
-		   store_sdma_affinity);
 
 static struct device_attribute *hfi1_attributes[] = {
 	&dev_attr_hw_rev,
@@ -670,7 +646,6 @@ static struct device_attribute *hfi1_attributes[] = {
 	&dev_attr_boardversion,
 	&dev_attr_tempsense,
 	&dev_attr_chip_reset,
-	&dev_attr_sdma_affinity,
 };
 
 int hfi1_create_port_files(struct ib_device *ibdev, u8 port_num,
diff --git a/drivers/infiniband/hw/hfi1/trace_rx.h b/drivers/infiniband/hw/hfi1/trace_rx.h
index 11e02b228922..f77e59fb43fe 100644
--- a/drivers/infiniband/hw/hfi1/trace_rx.h
+++ b/drivers/infiniband/hw/hfi1/trace_rx.h
@@ -253,66 +253,6 @@ TRACE_EVENT(hfi1_mmu_invalidate,
 		      )
 	    );
 
-#define SNOOP_PRN \
-	"slid %.4x dlid %.4x qpn 0x%.6x opcode 0x%.2x,%s " \
-	"svc lvl %d pkey 0x%.4x [header = %d bytes] [data = %d bytes]"
-
-TRACE_EVENT(snoop_capture,
-	    TP_PROTO(struct hfi1_devdata *dd,
-		     int hdr_len,
-		     struct ib_header *hdr,
-		     int data_len,
-		     void *data),
-	    TP_ARGS(dd, hdr_len, hdr, data_len, data),
-	    TP_STRUCT__entry(
-			     DD_DEV_ENTRY(dd)
-			     __field(u16, slid)
-			     __field(u16, dlid)
-			     __field(u32, qpn)
-			     __field(u8, opcode)
-			     __field(u8, sl)
-			     __field(u16, pkey)
-			     __field(u32, hdr_len)
-			     __field(u32, data_len)
-			     __field(u8, lnh)
-			     __dynamic_array(u8, raw_hdr, hdr_len)
-			     __dynamic_array(u8, raw_pkt, data_len)
-			     ),
-	    TP_fast_assign(
-		struct ib_other_headers *ohdr;
-
-		__entry->lnh = (u8)(be16_to_cpu(hdr->lrh[0]) & 3);
-		if (__entry->lnh == HFI1_LRH_BTH)
-		ohdr = &hdr->u.oth;
-		else
-		ohdr = &hdr->u.l.oth;
-		DD_DEV_ASSIGN(dd);
-		__entry->slid = be16_to_cpu(hdr->lrh[3]);
-		__entry->dlid = be16_to_cpu(hdr->lrh[1]);
-		__entry->qpn = be32_to_cpu(ohdr->bth[1]) & RVT_QPN_MASK;
-		__entry->opcode = (be32_to_cpu(ohdr->bth[0]) >> 24) & 0xff;
-		__entry->sl = (u8)(be16_to_cpu(hdr->lrh[0]) >> 4) & 0xf;
-		__entry->pkey =	be32_to_cpu(ohdr->bth[0]) & 0xffff;
-		__entry->hdr_len = hdr_len;
-		__entry->data_len = data_len;
-		memcpy(__get_dynamic_array(raw_hdr), hdr, hdr_len);
-		memcpy(__get_dynamic_array(raw_pkt), data, data_len);
-		),
-	    TP_printk(
-		"[%s] " SNOOP_PRN,
-		__get_str(dev),
-		__entry->slid,
-		__entry->dlid,
-		__entry->qpn,
-		__entry->opcode,
-		show_ib_opcode(__entry->opcode),
-		__entry->sl,
-		__entry->pkey,
-		__entry->hdr_len,
-		__entry->data_len
-		)
-);
-
 #endif /* __HFI1_TRACE_RX_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c
index a761f804111e..77697d690f3e 100644
--- a/drivers/infiniband/hw/hfi1/user_sdma.c
+++ b/drivers/infiniband/hw/hfi1/user_sdma.c
@@ -1144,7 +1144,7 @@ static int pin_vector_pages(struct user_sdma_request *req,
 	rb_node = hfi1_mmu_rb_extract(pq->handler,
 				      (unsigned long)iovec->iov.iov_base,
 				      iovec->iov.iov_len);
-	if (rb_node && !IS_ERR(rb_node))
+	if (rb_node)
 		node = container_of(rb_node, struct sdma_mmu_node, rb);
 	else
 		rb_node = NULL;
diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index 5fc623362731..b9bf0759f10a 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -102,7 +102,10 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
 	if (vlan_tag < 0x1000)
 		vlan_tag |= (ah_attr->sl & 7) << 13;
 	ah->av.eth.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));
-	ah->av.eth.gid_index = mlx4_ib_gid_index_to_real_index(ibdev, ah_attr->port_num, ah_attr->grh.sgid_index);
+	ret = mlx4_ib_gid_index_to_real_index(ibdev, ah_attr->port_num, ah_attr->grh.sgid_index);
+	if (ret < 0)
+		return ERR_PTR(ret);
+	ah->av.eth.gid_index = ret;
 	ah->av.eth.vlan = cpu_to_be16(vlan_tag);
 	ah->av.eth.hop_limit = ah_attr->grh.hop_limit;
 	if (ah_attr->static_rate) {
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 1ea686b9e0f9..6a0fec357dae 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -253,11 +253,14 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
 	if (context)
 		if (ib_copy_to_udata(udata, &cq->mcq.cqn, sizeof (__u32))) {
 			err = -EFAULT;
-			goto err_dbmap;
+			goto err_cq_free;
 		}
 
 	return &cq->ibcq;
 
+err_cq_free:
+	mlx4_cq_free(dev->dev, &cq->mcq);
+
 err_dbmap:
 	if (context)
 		mlx4_ib_db_unmap_user(to_mucontext(context), &cq->db);
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 79d017baf6f4..fcd04b881ec1 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -932,8 +932,7 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
 		if (err)
 			goto err_create;
 	} else {
-		/* for now choose 64 bytes till we have a proper interface */
-		cqe_size = 64;
+		cqe_size = cache_line_size() == 128 ? 128 : 64;
 		err = create_cq_kernel(dev, cq, entries, cqe_size, &cqb,
 				       &index, &inlen);
 		if (err)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 63036c731626..32b09f059c84 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2311,14 +2311,14 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
 {
 	struct mlx5_ib_dev *ibdev = (struct mlx5_ib_dev *)context;
 	struct ib_event ibev;
-
+	bool fatal = false;
 	u8 port = 0;
 
 	switch (event) {
 	case MLX5_DEV_EVENT_SYS_ERROR:
-		ibdev->ib_active = false;
 		ibev.event = IB_EVENT_DEVICE_FATAL;
 		mlx5_ib_handle_internal_error(ibdev);
+		fatal = true;
 		break;
 
 	case MLX5_DEV_EVENT_PORT_UP:
@@ -2370,6 +2370,9 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, void *context,
 
 	if (ibdev->ib_active)
 		ib_dispatch_event(&ibev);
+
+	if (fatal)
+		ibdev->ib_active = false;
 }
 
 static void get_ext_port_caps(struct mlx5_ib_dev *dev)
@@ -3115,7 +3118,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	}
 	err = init_node_data(dev);
 	if (err)
-		goto err_dealloc;
+		goto err_free_port;
 
 	mutex_init(&dev->flow_db.lock);
 	mutex_init(&dev->cap_mask_mutex);
@@ -3125,7 +3128,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	if (ll == IB_LINK_LAYER_ETHERNET) {
 		err = mlx5_enable_roce(dev);
 		if (err)
-			goto err_dealloc;
+			goto err_free_port;
 	}
 
 	err = create_dev_resources(&dev->devr);
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index dcdcd195fe53..7d689903c87c 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -626,6 +626,8 @@ struct mlx5_ib_dev {
 	struct mlx5_ib_resources	devr;
 	struct mlx5_mr_cache		cache;
 	struct timer_list		delay_timer;
+	/* Prevents soft lock on massive reg MRs */
+	struct mutex			slow_path_mutex;
 	int				fill_delay;
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 	struct ib_odp_caps	odp_caps;
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index d4ad672b905b..4e9012463c37 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -610,6 +610,7 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
 	int err;
 	int i;
 
+	mutex_init(&dev->slow_path_mutex);
 	cache->wq = alloc_ordered_workqueue("mkey_cache", WQ_MEM_RECLAIM);
 	if (!cache->wq) {
 		mlx5_ib_warn(dev, "failed to create work queue\n");
@@ -1182,9 +1183,12 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 		goto error;
 	}
 
-	if (!mr)
+	if (!mr) {
+		mutex_lock(&dev->slow_path_mutex);
 		mr = reg_create(NULL, pd, virt_addr, length, umem, ncont,
 				page_shift, access_flags);
+		mutex_unlock(&dev->slow_path_mutex);
+	}
 
 	if (IS_ERR(mr)) {
 		err = PTR_ERR(mr);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 7ce97daf26c6..d1e921816bfe 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -2051,8 +2051,8 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd,
 
 		mlx5_ib_dbg(dev, "ib qpnum 0x%x, mlx qpn 0x%x, rcqn 0x%x, scqn 0x%x\n",
 			    qp->ibqp.qp_num, qp->trans_qp.base.mqp.qpn,
-			    to_mcq(init_attr->recv_cq)->mcq.cqn,
-			    to_mcq(init_attr->send_cq)->mcq.cqn);
+			    init_attr->recv_cq ? to_mcq(init_attr->recv_cq)->mcq.cqn : -1,
+			    init_attr->send_cq ? to_mcq(init_attr->send_cq)->mcq.cqn : -1);
 
 		qp->trans_qp.xrcdn = xrcdn;
 
@@ -4814,6 +4814,14 @@ struct ib_rwq_ind_table *mlx5_ib_create_rwq_ind_table(struct ib_device *device,
 				 udata->inlen))
 		return ERR_PTR(-EOPNOTSUPP);
 
+	if (init_attr->log_ind_tbl_size >
+	    MLX5_CAP_GEN(dev->mdev, log_max_rqt_size)) {
+		mlx5_ib_dbg(dev, "log_ind_tbl_size = %d is bigger than supported = %d\n",
+			    init_attr->log_ind_tbl_size,
+			    MLX5_CAP_GEN(dev->mdev, log_max_rqt_size));
+		return ERR_PTR(-EINVAL);
+	}
+
 	min_resp_len = offsetof(typeof(resp), reserved) + sizeof(resp.reserved);
 	if (udata->outlen && udata->outlen < min_resp_len)
 		return ERR_PTR(-EINVAL);
diff --git a/drivers/infiniband/sw/rdmavt/dma.c b/drivers/infiniband/sw/rdmavt/dma.c
index 01f71caa3ac4..f2cefb0d9180 100644
--- a/drivers/infiniband/sw/rdmavt/dma.c
+++ b/drivers/infiniband/sw/rdmavt/dma.c
@@ -90,9 +90,6 @@ static u64 rvt_dma_map_page(struct ib_device *dev, struct page *page,
 	if (WARN_ON(!valid_dma_direction(direction)))
 		return BAD_DMA_ADDRESS;
 
-	if (offset + size > PAGE_SIZE)
-		return BAD_DMA_ADDRESS;
-
 	addr = (u64)page_address(page);
 	if (addr)
 		addr += offset;
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index b8258e4f0aea..ffff5a54cb34 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -243,10 +243,8 @@ static struct socket *rxe_setup_udp_tunnel(struct net *net, __be16 port,
 {
 	int err;
 	struct socket *sock;
-	struct udp_port_cfg udp_cfg;
-	struct udp_tunnel_sock_cfg tnl_cfg;
-
-	memset(&udp_cfg, 0, sizeof(udp_cfg));
+	struct udp_port_cfg udp_cfg = {0};
+	struct udp_tunnel_sock_cfg tnl_cfg = {0};
 
 	if (ipv6) {
 		udp_cfg.family = AF_INET6;
@@ -264,10 +262,8 @@ static struct socket *rxe_setup_udp_tunnel(struct net *net, __be16 port,
 		return ERR_PTR(err);
 	}
 
-	tnl_cfg.sk_user_data = NULL;
 	tnl_cfg.encap_type = 1;
 	tnl_cfg.encap_rcv = rxe_udp_encap_recv;
-	tnl_cfg.encap_destroy = NULL;
 
 	/* Setup UDP tunnel */
 	setup_udp_tunnel_sock(net, sock, &tnl_cfg);
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index b8036cfbce04..c3e60e4bde6e 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -522,6 +522,7 @@ static void rxe_qp_reset(struct rxe_qp *qp)
 	if (qp->sq.queue) {
 		__rxe_do_task(&qp->comp.task);
 		__rxe_do_task(&qp->req.task);
+		rxe_queue_reset(qp->sq.queue);
 	}
 
 	/* cleanup attributes */
@@ -573,6 +574,7 @@ void rxe_qp_error(struct rxe_qp *qp)
 {
 	qp->req.state = QP_STATE_ERROR;
 	qp->resp.state = QP_STATE_ERROR;
+	qp->attr.qp_state = IB_QPS_ERR;
 
 	/* drain work and packet queues */
 	rxe_run_task(&qp->resp.task, 1);
diff --git a/drivers/infiniband/sw/rxe/rxe_queue.c b/drivers/infiniband/sw/rxe/rxe_queue.c
index 08274254eb88..d14bf496d62d 100644
--- a/drivers/infiniband/sw/rxe/rxe_queue.c
+++ b/drivers/infiniband/sw/rxe/rxe_queue.c
@@ -84,6 +84,15 @@ err1:
 	return -EINVAL;
 }
 
+inline void rxe_queue_reset(struct rxe_queue *q)
+{
+	/* queue is comprised from header and the memory
+	 * of the actual queue. See "struct rxe_queue_buf" in rxe_queue.h
+	 * reset only the queue itself and not the management header
+	 */
+	memset(q->buf->data, 0, q->buf_size - sizeof(struct rxe_queue_buf));
+}
+
 struct rxe_queue *rxe_queue_init(struct rxe_dev *rxe,
 				 int *num_elem,
 				 unsigned int elem_size)
diff --git a/drivers/infiniband/sw/rxe/rxe_queue.h b/drivers/infiniband/sw/rxe/rxe_queue.h
index 239fd609c31e..8c8641c87817 100644
--- a/drivers/infiniband/sw/rxe/rxe_queue.h
+++ b/drivers/infiniband/sw/rxe/rxe_queue.h
@@ -84,6 +84,8 @@ int do_mmap_info(struct rxe_dev *rxe,
 		 size_t buf_size,
 		 struct rxe_mmap_info **ip_p);
 
+void rxe_queue_reset(struct rxe_queue *q);
+
 struct rxe_queue *rxe_queue_init(struct rxe_dev *rxe,
 				 int *num_elem,
 				 unsigned int elem_size);
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index 832846b73ea0..22bd9630dcd9 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -696,7 +696,8 @@ next_wqe:
 						       qp->req.wqe_index);
 			wqe->state = wqe_state_done;
 			wqe->status = IB_WC_SUCCESS;
-			goto complete;
+			__rxe_do_task(&qp->comp.task);
+			return 0;
 		}
 		payload = mtu;
 	}
@@ -745,13 +746,17 @@ err:
 	wqe->status = IB_WC_LOC_PROT_ERR;
 	wqe->state = wqe_state_error;
 
-complete:
-	if (qp_type(qp) != IB_QPT_RC) {
-		while (rxe_completer(qp) == 0)
-			;
-	}
-
-	return 0;
+	/*
+	 * IBA Spec. Section 10.7.3.1 SIGNALED COMPLETIONS
+	 * ---------8<---------8<-------------
+	 * ...Note that if a completion error occurs, a Work Completion
+	 * will always be generated, even if the signaling
+	 * indicator requests an Unsignaled Completion.
+	 * ---------8<---------8<-------------
+	 */
+	wqe->wr.send_flags |= IB_SEND_SIGNALED;
+	__rxe_do_task(&qp->comp.task);
+	return -EAGAIN;
 
 exit:
 	return -EAGAIN;
diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c
index 08c87fadca8c..1f32688c312d 100644
--- a/drivers/mailbox/pcc.c
+++ b/drivers/mailbox/pcc.c
@@ -65,6 +65,7 @@
 #include <linux/mailbox_controller.h>
 #include <linux/mailbox_client.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
+#include <acpi/pcc.h>
 
 #include "mailbox.h"
 
@@ -267,6 +268,8 @@ struct mbox_chan *pcc_mbox_request_channel(struct mbox_client *cl,
 	if (chan->txdone_method == TXDONE_BY_POLL && cl->knows_txdone)
 		chan->txdone_method |= TXDONE_BY_ACK;
 
+	spin_unlock_irqrestore(&chan->lock, flags);
+
 	if (pcc_doorbell_irq[subspace_id] > 0) {
 		int rc;
 
@@ -275,12 +278,11 @@ struct mbox_chan *pcc_mbox_request_channel(struct mbox_client *cl,
 		if (unlikely(rc)) {
 			dev_err(dev, "failed to register PCC interrupt %d\n",
 				pcc_doorbell_irq[subspace_id]);
+			pcc_mbox_free_channel(chan);
 			chan = ERR_PTR(rc);
 		}
 	}
 
-	spin_unlock_irqrestore(&chan->lock, flags);
-
 	return chan;
 }
 EXPORT_SYMBOL_GPL(pcc_mbox_request_channel);
@@ -304,20 +306,19 @@ void pcc_mbox_free_channel(struct mbox_chan *chan)
 		return;
 	}
 
+	if (pcc_doorbell_irq[id] > 0)
+		devm_free_irq(chan->mbox->dev, pcc_doorbell_irq[id], chan);
+
 	spin_lock_irqsave(&chan->lock, flags);
 	chan->cl = NULL;
 	chan->active_req = NULL;
 	if (chan->txdone_method == (TXDONE_BY_POLL | TXDONE_BY_ACK))
 		chan->txdone_method = TXDONE_BY_POLL;
 
-	if (pcc_doorbell_irq[id] > 0)
-		devm_free_irq(chan->mbox->dev, pcc_doorbell_irq[id], chan);
-
 	spin_unlock_irqrestore(&chan->lock, flags);
 }
 EXPORT_SYMBOL_GPL(pcc_mbox_free_channel);
 
-
 /**
  * pcc_send_data - Called from Mailbox Controller code. Used
  *		here only to ring the channel doorbell. The PCC client
diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c
index 3228fd182a99..9ff243970e93 100644
--- a/drivers/mfd/intel-lpss-pci.c
+++ b/drivers/mfd/intel-lpss-pci.c
@@ -123,19 +123,6 @@ static const struct intel_lpss_platform_info apl_i2c_info = {
 	.properties = apl_i2c_properties,
 };
 
-static const struct intel_lpss_platform_info kbl_info = {
-	.clk_rate = 120000000,
-};
-
-static const struct intel_lpss_platform_info kbl_uart_info = {
-	.clk_rate = 120000000,
-	.clk_con_id = "baudclk",
-};
-
-static const struct intel_lpss_platform_info kbl_i2c_info = {
-	.clk_rate = 133000000,
-};
-
 static const struct pci_device_id intel_lpss_pci_ids[] = {
 	/* BXT A-Step */
 	{ PCI_VDEVICE(INTEL, 0x0aac), (kernel_ulong_t)&bxt_i2c_info },
@@ -207,15 +194,15 @@ static const struct pci_device_id intel_lpss_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0xa161), (kernel_ulong_t)&spt_i2c_info },
 	{ PCI_VDEVICE(INTEL, 0xa166), (kernel_ulong_t)&spt_uart_info },
 	/* KBL-H */
-	{ PCI_VDEVICE(INTEL, 0xa2a7), (kernel_ulong_t)&kbl_uart_info },
-	{ PCI_VDEVICE(INTEL, 0xa2a8), (kernel_ulong_t)&kbl_uart_info },
-	{ PCI_VDEVICE(INTEL, 0xa2a9), (kernel_ulong_t)&kbl_info },
-	{ PCI_VDEVICE(INTEL, 0xa2aa), (kernel_ulong_t)&kbl_info },
-	{ PCI_VDEVICE(INTEL, 0xa2e0), (kernel_ulong_t)&kbl_i2c_info },
-	{ PCI_VDEVICE(INTEL, 0xa2e1), (kernel_ulong_t)&kbl_i2c_info },
-	{ PCI_VDEVICE(INTEL, 0xa2e2), (kernel_ulong_t)&kbl_i2c_info },
-	{ PCI_VDEVICE(INTEL, 0xa2e3), (kernel_ulong_t)&kbl_i2c_info },
-	{ PCI_VDEVICE(INTEL, 0xa2e6), (kernel_ulong_t)&kbl_uart_info },
+	{ PCI_VDEVICE(INTEL, 0xa2a7), (kernel_ulong_t)&spt_uart_info },
+	{ PCI_VDEVICE(INTEL, 0xa2a8), (kernel_ulong_t)&spt_uart_info },
+	{ PCI_VDEVICE(INTEL, 0xa2a9), (kernel_ulong_t)&spt_info },
+	{ PCI_VDEVICE(INTEL, 0xa2aa), (kernel_ulong_t)&spt_info },
+	{ PCI_VDEVICE(INTEL, 0xa2e0), (kernel_ulong_t)&spt_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0xa2e1), (kernel_ulong_t)&spt_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0xa2e2), (kernel_ulong_t)&spt_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0xa2e3), (kernel_ulong_t)&spt_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0xa2e6), (kernel_ulong_t)&spt_uart_info },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, intel_lpss_pci_ids);
diff --git a/drivers/mfd/intel-lpss.c b/drivers/mfd/intel-lpss.c
index 41b113875d64..70c646b0097d 100644
--- a/drivers/mfd/intel-lpss.c
+++ b/drivers/mfd/intel-lpss.c
@@ -502,9 +502,6 @@ int intel_lpss_suspend(struct device *dev)
 	for (i = 0; i < LPSS_PRIV_REG_COUNT; i++)
 		lpss->priv_ctx[i] = readl(lpss->priv + i * 4);
 
-	/* Put the device into reset state */
-	writel(0, lpss->priv + LPSS_PRIV_RESETS);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(intel_lpss_suspend);
diff --git a/drivers/mfd/intel_soc_pmic_bxtwc.c b/drivers/mfd/intel_soc_pmic_bxtwc.c
index 43e54b7e908f..f9a8c5203873 100644
--- a/drivers/mfd/intel_soc_pmic_bxtwc.c
+++ b/drivers/mfd/intel_soc_pmic_bxtwc.c
@@ -86,6 +86,7 @@ enum bxtwc_irqs_level2 {
 	BXTWC_THRM2_IRQ,
 	BXTWC_BCU_IRQ,
 	BXTWC_ADC_IRQ,
+	BXTWC_USBC_IRQ,
 	BXTWC_CHGR0_IRQ,
 	BXTWC_CHGR1_IRQ,
 	BXTWC_GPIO0_IRQ,
@@ -111,7 +112,8 @@ static const struct regmap_irq bxtwc_regmap_irqs_level2[] = {
 	REGMAP_IRQ_REG(BXTWC_THRM2_IRQ, 2, 0xff),
 	REGMAP_IRQ_REG(BXTWC_BCU_IRQ, 3, 0x1f),
 	REGMAP_IRQ_REG(BXTWC_ADC_IRQ, 4, 0xff),
-	REGMAP_IRQ_REG(BXTWC_CHGR0_IRQ, 5, 0x3f),
+	REGMAP_IRQ_REG(BXTWC_USBC_IRQ, 5, BIT(5)),
+	REGMAP_IRQ_REG(BXTWC_CHGR0_IRQ, 5, 0x1f),
 	REGMAP_IRQ_REG(BXTWC_CHGR1_IRQ, 6, 0x1f),
 	REGMAP_IRQ_REG(BXTWC_GPIO0_IRQ, 7, 0xff),
 	REGMAP_IRQ_REG(BXTWC_GPIO1_IRQ, 8, 0x3f),
@@ -146,7 +148,7 @@ static struct resource adc_resources[] = {
 };
 
 static struct resource usbc_resources[] = {
-	DEFINE_RES_IRQ_NAMED(BXTWC_CHGR0_IRQ, "USBC"),
+	DEFINE_RES_IRQ(BXTWC_USBC_IRQ),
 };
 
 static struct resource charger_resources[] = {
diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c
index 3ac486a597f3..c57e407020f1 100644
--- a/drivers/mfd/mfd-core.c
+++ b/drivers/mfd/mfd-core.c
@@ -399,6 +399,8 @@ int mfd_clone_cell(const char *cell, const char **clones, size_t n_clones)
 					clones[i]);
 	}
 
+	put_device(dev);
+
 	return 0;
 }
 EXPORT_SYMBOL(mfd_clone_cell);
diff --git a/drivers/mfd/stmpe.c b/drivers/mfd/stmpe.c
index cfdae8a3d779..b0c7bcdaf5df 100644
--- a/drivers/mfd/stmpe.c
+++ b/drivers/mfd/stmpe.c
@@ -851,6 +851,8 @@ static int stmpe_reset(struct stmpe *stmpe)
 	if (ret < 0)
 		return ret;
 
+	msleep(10);
+
 	timeout = jiffies + msecs_to_jiffies(100);
 	while (time_before(jiffies, timeout)) {
 		ret = __stmpe_reg_read(stmpe, stmpe->regs[STMPE_IDX_SYS_CTRL]);
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 7717b19dc806..947adda3397d 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -962,9 +962,10 @@ static void b53_vlan_add(struct dsa_switch *ds, int port,
 
 		vl->members |= BIT(port) | BIT(cpu_port);
 		if (untagged)
-			vl->untag |= BIT(port) | BIT(cpu_port);
+			vl->untag |= BIT(port);
 		else
-			vl->untag &= ~(BIT(port) | BIT(cpu_port));
+			vl->untag &= ~BIT(port);
+		vl->untag &= ~BIT(cpu_port);
 
 		b53_set_vlan_entry(dev, vid, vl);
 		b53_fast_age_vlan(dev, vid);
@@ -973,8 +974,6 @@ static void b53_vlan_add(struct dsa_switch *ds, int port,
 	if (pvid) {
 		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port),
 			    vlan->vid_end);
-		b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(cpu_port),
-			    vlan->vid_end);
 		b53_fast_age_vlan(dev, vid);
 	}
 }
@@ -984,7 +983,6 @@ static int b53_vlan_del(struct dsa_switch *ds, int port,
 {
 	struct b53_device *dev = ds->priv;
 	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
-	unsigned int cpu_port = dev->cpu_port;
 	struct b53_vlan *vl;
 	u16 vid;
 	u16 pvid;
@@ -997,8 +995,6 @@ static int b53_vlan_del(struct dsa_switch *ds, int port,
 		b53_get_vlan_entry(dev, vid, vl);
 
 		vl->members &= ~BIT(port);
-		if ((vl->members & BIT(cpu_port)) == BIT(cpu_port))
-			vl->members = 0;
 
 		if (pvid == vid) {
 			if (is5325(dev) || is5365(dev))
@@ -1007,18 +1003,14 @@ static int b53_vlan_del(struct dsa_switch *ds, int port,
 				pvid = 0;
 		}
 
-		if (untagged) {
+		if (untagged)
 			vl->untag &= ~(BIT(port));
-			if ((vl->untag & BIT(cpu_port)) == BIT(cpu_port))
-				vl->untag = 0;
-		}
 
 		b53_set_vlan_entry(dev, vid, vl);
 		b53_fast_age_vlan(dev, vid);
 	}
 
 	b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), pvid);
-	b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(cpu_port), pvid);
 	b53_fast_age_vlan(dev, pvid);
 
 	return 0;
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index b0da9693f28a..be865b4dada2 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -460,7 +460,7 @@ static void arc_emac_set_rx_mode(struct net_device *ndev)
 		if (ndev->flags & IFF_ALLMULTI) {
 			arc_reg_set(priv, R_LAFL, ~0);
 			arc_reg_set(priv, R_LAFH, ~0);
-		} else {
+		} else if (ndev->flags & IFF_MULTICAST) {
 			struct netdev_hw_addr *ha;
 			unsigned int filter[2] = { 0, 0 };
 			int bit;
@@ -472,6 +472,9 @@ static void arc_emac_set_rx_mode(struct net_device *ndev)
 
 			arc_reg_set(priv, R_LAFL, filter[0]);
 			arc_reg_set(priv, R_LAFH, filter[1]);
+		} else {
+			arc_reg_set(priv, R_LAFL, 0);
+			arc_reg_set(priv, R_LAFH, 0);
 		}
 	}
 }
@@ -764,8 +767,6 @@ int arc_emac_probe(struct net_device *ndev, int interface)
 	ndev->netdev_ops = &arc_emac_netdev_ops;
 	ndev->ethtool_ops = &arc_emac_ethtool_ops;
 	ndev->watchdog_timeo = TX_TIMEOUT;
-	/* FIXME :: no multicast support yet */
-	ndev->flags &= ~IFF_MULTICAST;
 
 	priv = netdev_priv(ndev);
 	priv->dev = dev;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c6909660e097..e18635b2a002 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4934,6 +4934,10 @@ static void bnxt_del_napi(struct bnxt *bp)
 		napi_hash_del(&bnapi->napi);
 		netif_napi_del(&bnapi->napi);
 	}
+	/* We called napi_hash_del() before netif_napi_del(), we need
+	 * to respect an RCU grace period before freeing napi structures.
+	 */
+	synchronize_net();
 }
 
 static void bnxt_init_napi(struct bnxt *bp)
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index b32444a3ed79..533653bd7aec 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -2673,6 +2673,12 @@ static int at91ether_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		lp->skb_length = skb->len;
 		lp->skb_physaddr = dma_map_single(NULL, skb->data, skb->len,
 							DMA_TO_DEVICE);
+		if (dma_mapping_error(NULL, lp->skb_physaddr)) {
+			dev_kfree_skb_any(skb);
+			dev->stats.tx_dropped++;
+			netdev_err(dev, "%s: DMA mapping error\n", __func__);
+			return NETDEV_TX_OK;
+		}
 
 		/* Set address of the data in the Transmit Address register */
 		macb_writel(lp, TAR, lp->skb_physaddr);
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index 30426109711c..86bd93ce2ea3 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -47,7 +47,7 @@
 
 /* Min/Max packet size */
 #define	NIC_HW_MIN_FRS			64
-#define	NIC_HW_MAX_FRS			9200 /* 9216 max packet including FCS */
+#define	NIC_HW_MAX_FRS			9190 /* Excluding L2 header and FCS */
 
 /* Max pkinds */
 #define	NIC_MAX_PKIND			16
@@ -178,11 +178,11 @@ enum tx_stats_reg_offset {
 
 struct nicvf_hw_stats {
 	u64 rx_bytes;
+	u64 rx_frames;
 	u64 rx_ucast_frames;
 	u64 rx_bcast_frames;
 	u64 rx_mcast_frames;
-	u64 rx_fcs_errors;
-	u64 rx_l2_errors;
+	u64 rx_drops;
 	u64 rx_drop_red;
 	u64 rx_drop_red_bytes;
 	u64 rx_drop_overrun;
@@ -191,6 +191,19 @@ struct nicvf_hw_stats {
 	u64 rx_drop_mcast;
 	u64 rx_drop_l3_bcast;
 	u64 rx_drop_l3_mcast;
+	u64 rx_fcs_errors;
+	u64 rx_l2_errors;
+
+	u64 tx_bytes;
+	u64 tx_frames;
+	u64 tx_ucast_frames;
+	u64 tx_bcast_frames;
+	u64 tx_mcast_frames;
+	u64 tx_drops;
+};
+
+struct nicvf_drv_stats {
+	/* CQE Rx errs */
 	u64 rx_bgx_truncated_pkts;
 	u64 rx_jabber_errs;
 	u64 rx_fcs_errs;
@@ -216,34 +229,30 @@ struct nicvf_hw_stats {
 	u64 rx_l4_pclp;
 	u64 rx_truncated_pkts;
 
-	u64 tx_bytes_ok;
-	u64 tx_ucast_frames_ok;
-	u64 tx_bcast_frames_ok;
-	u64 tx_mcast_frames_ok;
-	u64 tx_drops;
-};
-
-struct nicvf_drv_stats {
-	/* Rx */
-	u64 rx_frames_ok;
-	u64 rx_frames_64;
-	u64 rx_frames_127;
-	u64 rx_frames_255;
-	u64 rx_frames_511;
-	u64 rx_frames_1023;
-	u64 rx_frames_1518;
-	u64 rx_frames_jumbo;
-	u64 rx_drops;
-
+	/* CQE Tx errs */
+	u64 tx_desc_fault;
+	u64 tx_hdr_cons_err;
+	u64 tx_subdesc_err;
+	u64 tx_max_size_exceeded;
+	u64 tx_imm_size_oflow;
+	u64 tx_data_seq_err;
+	u64 tx_mem_seq_err;
+	u64 tx_lock_viol;
+	u64 tx_data_fault;
+	u64 tx_tstmp_conflict;
+	u64 tx_tstmp_timeout;
+	u64 tx_mem_fault;
+	u64 tx_csum_overlap;
+	u64 tx_csum_overflow;
+
+	/* driver debug stats */
 	u64 rcv_buffer_alloc_failures;
-
-	/* Tx */
-	u64 tx_frames_ok;
-	u64 tx_drops;
 	u64 tx_tso;
 	u64 tx_timeout;
 	u64 txq_stop;
 	u64 txq_wake;
+
+	struct u64_stats_sync   syncp;
 };
 
 struct nicvf {
@@ -282,7 +291,6 @@ struct nicvf {
 
 	u8			node;
 	u8			cpi_alg;
-	u16			mtu;
 	bool			link_up;
 	u8			duplex;
 	u32			speed;
@@ -298,7 +306,7 @@ struct nicvf {
 
 	/* Stats */
 	struct nicvf_hw_stats   hw_stats;
-	struct nicvf_drv_stats  drv_stats;
+	struct nicvf_drv_stats  __percpu *drv_stats;
 	struct bgx_stats	bgx_stats;
 
 	/* MSI-X  */
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 2bbf4cbf08b2..6677b96e1f3f 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -11,6 +11,7 @@
 #include <linux/pci.h>
 #include <linux/etherdevice.h>
 #include <linux/of.h>
+#include <linux/if_vlan.h>
 
 #include "nic_reg.h"
 #include "nic.h"
@@ -260,18 +261,31 @@ static void nic_get_bgx_stats(struct nicpf *nic, struct bgx_stats_msg *bgx)
 /* Update hardware min/max frame size */
 static int nic_update_hw_frs(struct nicpf *nic, int new_frs, int vf)
 {
-	if ((new_frs > NIC_HW_MAX_FRS) || (new_frs < NIC_HW_MIN_FRS)) {
-		dev_err(&nic->pdev->dev,
-			"Invalid MTU setting from VF%d rejected, should be between %d and %d\n",
-			   vf, NIC_HW_MIN_FRS, NIC_HW_MAX_FRS);
+	int bgx, lmac, lmac_cnt;
+	u64 lmac_credits;
+
+	if ((new_frs > NIC_HW_MAX_FRS) || (new_frs < NIC_HW_MIN_FRS))
 		return 1;
-	}
-	new_frs += ETH_HLEN;
-	if (new_frs <= nic->pkind.maxlen)
-		return 0;
 
-	nic->pkind.maxlen = new_frs;
-	nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG, *(u64 *)&nic->pkind);
+	bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+	lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+	lmac += bgx * MAX_LMAC_PER_BGX;
+
+	new_frs += VLAN_ETH_HLEN + ETH_FCS_LEN + 4;
+
+	/* Update corresponding LMAC credits */
+	lmac_cnt = bgx_get_lmac_count(nic->node, bgx);
+	lmac_credits = nic_reg_read(nic, NIC_PF_LMAC_0_7_CREDIT + (lmac * 8));
+	lmac_credits &= ~(0xFFFFFULL << 12);
+	lmac_credits |= (((((48 * 1024) / lmac_cnt) - new_frs) / 16) << 12);
+	nic_reg_write(nic, NIC_PF_LMAC_0_7_CREDIT + (lmac * 8), lmac_credits);
+
+	/* Enforce MTU in HW
+	 * This config is supported only from 88xx pass 2.0 onwards.
+	 */
+	if (!pass1_silicon(nic->pdev))
+		nic_reg_write(nic,
+			      NIC_PF_LMAC_0_7_CFG2 + (lmac * 8), new_frs);
 	return 0;
 }
 
@@ -464,7 +478,7 @@ static int nic_init_hw(struct nicpf *nic)
 
 	/* PKIND configuration */
 	nic->pkind.minlen = 0;
-	nic->pkind.maxlen = NIC_HW_MAX_FRS + ETH_HLEN;
+	nic->pkind.maxlen = NIC_HW_MAX_FRS + VLAN_ETH_HLEN + ETH_FCS_LEN + 4;
 	nic->pkind.lenerr_en = 1;
 	nic->pkind.rx_hdr = 0;
 	nic->pkind.hdr_sl = 0;
@@ -837,6 +851,7 @@ static int nic_reset_stat_counters(struct nicpf *nic,
 			nic_reg_write(nic, reg_addr, 0);
 		}
 	}
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h
index edf779f5a227..80d46337cf29 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_reg.h
+++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h
@@ -106,6 +106,7 @@
 #define   NIC_PF_MPI_0_2047_CFG			(0x210000)
 #define   NIC_PF_RSSI_0_4097_RQ			(0x220000)
 #define   NIC_PF_LMAC_0_7_CFG			(0x240000)
+#define   NIC_PF_LMAC_0_7_CFG2			(0x240100)
 #define   NIC_PF_LMAC_0_7_SW_XOFF		(0x242000)
 #define   NIC_PF_LMAC_0_7_CREDIT		(0x244000)
 #define   NIC_PF_CHAN_0_255_TX_CFG		(0x400000)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index ad4fddb55421..432bf6be57cb 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -36,11 +36,11 @@ struct nicvf_stat {
 
 static const struct nicvf_stat nicvf_hw_stats[] = {
 	NICVF_HW_STAT(rx_bytes),
+	NICVF_HW_STAT(rx_frames),
 	NICVF_HW_STAT(rx_ucast_frames),
 	NICVF_HW_STAT(rx_bcast_frames),
 	NICVF_HW_STAT(rx_mcast_frames),
-	NICVF_HW_STAT(rx_fcs_errors),
-	NICVF_HW_STAT(rx_l2_errors),
+	NICVF_HW_STAT(rx_drops),
 	NICVF_HW_STAT(rx_drop_red),
 	NICVF_HW_STAT(rx_drop_red_bytes),
 	NICVF_HW_STAT(rx_drop_overrun),
@@ -49,50 +49,59 @@ static const struct nicvf_stat nicvf_hw_stats[] = {
 	NICVF_HW_STAT(rx_drop_mcast),
 	NICVF_HW_STAT(rx_drop_l3_bcast),
 	NICVF_HW_STAT(rx_drop_l3_mcast),
-	NICVF_HW_STAT(rx_bgx_truncated_pkts),
-	NICVF_HW_STAT(rx_jabber_errs),
-	NICVF_HW_STAT(rx_fcs_errs),
-	NICVF_HW_STAT(rx_bgx_errs),
-	NICVF_HW_STAT(rx_prel2_errs),
-	NICVF_HW_STAT(rx_l2_hdr_malformed),
-	NICVF_HW_STAT(rx_oversize),
-	NICVF_HW_STAT(rx_undersize),
-	NICVF_HW_STAT(rx_l2_len_mismatch),
-	NICVF_HW_STAT(rx_l2_pclp),
-	NICVF_HW_STAT(rx_ip_ver_errs),
-	NICVF_HW_STAT(rx_ip_csum_errs),
-	NICVF_HW_STAT(rx_ip_hdr_malformed),
-	NICVF_HW_STAT(rx_ip_payload_malformed),
-	NICVF_HW_STAT(rx_ip_ttl_errs),
-	NICVF_HW_STAT(rx_l3_pclp),
-	NICVF_HW_STAT(rx_l4_malformed),
-	NICVF_HW_STAT(rx_l4_csum_errs),
-	NICVF_HW_STAT(rx_udp_len_errs),
-	NICVF_HW_STAT(rx_l4_port_errs),
-	NICVF_HW_STAT(rx_tcp_flag_errs),
-	NICVF_HW_STAT(rx_tcp_offset_errs),
-	NICVF_HW_STAT(rx_l4_pclp),
-	NICVF_HW_STAT(rx_truncated_pkts),
-	NICVF_HW_STAT(tx_bytes_ok),
-	NICVF_HW_STAT(tx_ucast_frames_ok),
-	NICVF_HW_STAT(tx_bcast_frames_ok),
-	NICVF_HW_STAT(tx_mcast_frames_ok),
+	NICVF_HW_STAT(rx_fcs_errors),
+	NICVF_HW_STAT(rx_l2_errors),
+	NICVF_HW_STAT(tx_bytes),
+	NICVF_HW_STAT(tx_frames),
+	NICVF_HW_STAT(tx_ucast_frames),
+	NICVF_HW_STAT(tx_bcast_frames),
+	NICVF_HW_STAT(tx_mcast_frames),
+	NICVF_HW_STAT(tx_drops),
 };
 
 static const struct nicvf_stat nicvf_drv_stats[] = {
-	NICVF_DRV_STAT(rx_frames_ok),
-	NICVF_DRV_STAT(rx_frames_64),
-	NICVF_DRV_STAT(rx_frames_127),
-	NICVF_DRV_STAT(rx_frames_255),
-	NICVF_DRV_STAT(rx_frames_511),
-	NICVF_DRV_STAT(rx_frames_1023),
-	NICVF_DRV_STAT(rx_frames_1518),
-	NICVF_DRV_STAT(rx_frames_jumbo),
-	NICVF_DRV_STAT(rx_drops),
+	NICVF_DRV_STAT(rx_bgx_truncated_pkts),
+	NICVF_DRV_STAT(rx_jabber_errs),
+	NICVF_DRV_STAT(rx_fcs_errs),
+	NICVF_DRV_STAT(rx_bgx_errs),
+	NICVF_DRV_STAT(rx_prel2_errs),
+	NICVF_DRV_STAT(rx_l2_hdr_malformed),
+	NICVF_DRV_STAT(rx_oversize),
+	NICVF_DRV_STAT(rx_undersize),
+	NICVF_DRV_STAT(rx_l2_len_mismatch),
+	NICVF_DRV_STAT(rx_l2_pclp),
+	NICVF_DRV_STAT(rx_ip_ver_errs),
+	NICVF_DRV_STAT(rx_ip_csum_errs),
+	NICVF_DRV_STAT(rx_ip_hdr_malformed),
+	NICVF_DRV_STAT(rx_ip_payload_malformed),
+	NICVF_DRV_STAT(rx_ip_ttl_errs),
+	NICVF_DRV_STAT(rx_l3_pclp),
+	NICVF_DRV_STAT(rx_l4_malformed),
+	NICVF_DRV_STAT(rx_l4_csum_errs),
+	NICVF_DRV_STAT(rx_udp_len_errs),
+	NICVF_DRV_STAT(rx_l4_port_errs),
+	NICVF_DRV_STAT(rx_tcp_flag_errs),
+	NICVF_DRV_STAT(rx_tcp_offset_errs),
+	NICVF_DRV_STAT(rx_l4_pclp),
+	NICVF_DRV_STAT(rx_truncated_pkts),
+
+	NICVF_DRV_STAT(tx_desc_fault),
+	NICVF_DRV_STAT(tx_hdr_cons_err),
+	NICVF_DRV_STAT(tx_subdesc_err),
+	NICVF_DRV_STAT(tx_max_size_exceeded),
+	NICVF_DRV_STAT(tx_imm_size_oflow),
+	NICVF_DRV_STAT(tx_data_seq_err),
+	NICVF_DRV_STAT(tx_mem_seq_err),
+	NICVF_DRV_STAT(tx_lock_viol),
+	NICVF_DRV_STAT(tx_data_fault),
+	NICVF_DRV_STAT(tx_tstmp_conflict),
+	NICVF_DRV_STAT(tx_tstmp_timeout),
+	NICVF_DRV_STAT(tx_mem_fault),
+	NICVF_DRV_STAT(tx_csum_overlap),
+	NICVF_DRV_STAT(tx_csum_overflow),
+
 	NICVF_DRV_STAT(rcv_buffer_alloc_failures),
-	NICVF_DRV_STAT(tx_frames_ok),
 	NICVF_DRV_STAT(tx_tso),
-	NICVF_DRV_STAT(tx_drops),
 	NICVF_DRV_STAT(tx_timeout),
 	NICVF_DRV_STAT(txq_stop),
 	NICVF_DRV_STAT(txq_wake),
@@ -278,8 +287,8 @@ static void nicvf_get_ethtool_stats(struct net_device *netdev,
 				    struct ethtool_stats *stats, u64 *data)
 {
 	struct nicvf *nic = netdev_priv(netdev);
-	int stat;
-	int sqs;
+	int stat, tmp_stats;
+	int sqs, cpu;
 
 	nicvf_update_stats(nic);
 
@@ -289,9 +298,13 @@ static void nicvf_get_ethtool_stats(struct net_device *netdev,
 	for (stat = 0; stat < nicvf_n_hw_stats; stat++)
 		*(data++) = ((u64 *)&nic->hw_stats)
 				[nicvf_hw_stats[stat].index];
-	for (stat = 0; stat < nicvf_n_drv_stats; stat++)
-		*(data++) = ((u64 *)&nic->drv_stats)
-				[nicvf_drv_stats[stat].index];
+	for (stat = 0; stat < nicvf_n_drv_stats; stat++) {
+		tmp_stats = 0;
+		for_each_possible_cpu(cpu)
+			tmp_stats += ((u64 *)per_cpu_ptr(nic->drv_stats, cpu))
+				     [nicvf_drv_stats[stat].index];
+		*(data++) = tmp_stats;
+	}
 
 	nicvf_get_qset_stats(nic, stats, &data);
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 45a13f718863..8a37012c9c89 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -69,25 +69,6 @@ static inline u8 nicvf_netdev_qidx(struct nicvf *nic, u8 qidx)
 		return qidx;
 }
 
-static inline void nicvf_set_rx_frame_cnt(struct nicvf *nic,
-					  struct sk_buff *skb)
-{
-	if (skb->len <= 64)
-		nic->drv_stats.rx_frames_64++;
-	else if (skb->len <= 127)
-		nic->drv_stats.rx_frames_127++;
-	else if (skb->len <= 255)
-		nic->drv_stats.rx_frames_255++;
-	else if (skb->len <= 511)
-		nic->drv_stats.rx_frames_511++;
-	else if (skb->len <= 1023)
-		nic->drv_stats.rx_frames_1023++;
-	else if (skb->len <= 1518)
-		nic->drv_stats.rx_frames_1518++;
-	else
-		nic->drv_stats.rx_frames_jumbo++;
-}
-
 /* The Cavium ThunderX network controller can *only* be found in SoCs
  * containing the ThunderX ARM64 CPU implementation.  All accesses to the device
  * registers on this platform are implicitly strongly ordered with respect
@@ -492,9 +473,6 @@ int nicvf_set_real_num_queues(struct net_device *netdev,
 static int nicvf_init_resources(struct nicvf *nic)
 {
 	int err;
-	union nic_mbx mbx = {};
-
-	mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE;
 
 	/* Enable Qset */
 	nicvf_qset_config(nic, true);
@@ -507,14 +485,10 @@ static int nicvf_init_resources(struct nicvf *nic)
 		return err;
 	}
 
-	/* Send VF config done msg to PF */
-	nicvf_write_to_mbx(nic, &mbx);
-
 	return 0;
 }
 
 static void nicvf_snd_pkt_handler(struct net_device *netdev,
-				  struct cmp_queue *cq,
 				  struct cqe_send_t *cqe_tx,
 				  int cqe_type, int budget,
 				  unsigned int *tx_pkts, unsigned int *tx_bytes)
@@ -536,7 +510,7 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev,
 		   __func__, cqe_tx->sq_qs, cqe_tx->sq_idx,
 		   cqe_tx->sqe_ptr, hdr->subdesc_cnt);
 
-	nicvf_check_cqe_tx_errs(nic, cq, cqe_tx);
+	nicvf_check_cqe_tx_errs(nic, cqe_tx);
 	skb = (struct sk_buff *)sq->skbuff[cqe_tx->sqe_ptr];
 	if (skb) {
 		/* Check for dummy descriptor used for HW TSO offload on 88xx */
@@ -630,8 +604,6 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 		return;
 	}
 
-	nicvf_set_rx_frame_cnt(nic, skb);
-
 	nicvf_set_rxhash(netdev, cqe_rx, skb);
 
 	skb_record_rx_queue(skb, rq_idx);
@@ -703,7 +675,7 @@ loop:
 			work_done++;
 		break;
 		case CQE_TYPE_SEND:
-			nicvf_snd_pkt_handler(netdev, cq,
+			nicvf_snd_pkt_handler(netdev,
 					      (void *)cq_desc, CQE_TYPE_SEND,
 					      budget, &tx_pkts, &tx_bytes);
 			tx_done++;
@@ -740,7 +712,7 @@ done:
 		nic = nic->pnicvf;
 		if (netif_tx_queue_stopped(txq) && netif_carrier_ok(netdev)) {
 			netif_tx_start_queue(txq);
-			nic->drv_stats.txq_wake++;
+			this_cpu_inc(nic->drv_stats->txq_wake);
 			if (netif_msg_tx_err(nic))
 				netdev_warn(netdev,
 					    "%s: Transmit queue wakeup SQ%d\n",
@@ -1084,7 +1056,7 @@ static netdev_tx_t nicvf_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	if (!netif_tx_queue_stopped(txq) && !nicvf_sq_append_skb(nic, skb)) {
 		netif_tx_stop_queue(txq);
-		nic->drv_stats.txq_stop++;
+		this_cpu_inc(nic->drv_stats->txq_stop);
 		if (netif_msg_tx_err(nic))
 			netdev_warn(netdev,
 				    "%s: Transmit ring full, stopping SQ%d\n",
@@ -1189,14 +1161,24 @@ int nicvf_stop(struct net_device *netdev)
 	return 0;
 }
 
+static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu)
+{
+	union nic_mbx mbx = {};
+
+	mbx.frs.msg = NIC_MBOX_MSG_SET_MAX_FRS;
+	mbx.frs.max_frs = mtu;
+	mbx.frs.vf_id = nic->vf_id;
+
+	return nicvf_send_msg_to_pf(nic, &mbx);
+}
+
 int nicvf_open(struct net_device *netdev)
 {
-	int err, qidx;
+	int cpu, err, qidx;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct queue_set *qs = nic->qs;
 	struct nicvf_cq_poll *cq_poll = NULL;
-
-	nic->mtu = netdev->mtu;
+	union nic_mbx mbx = {};
 
 	netif_carrier_off(netdev);
 
@@ -1248,9 +1230,17 @@ int nicvf_open(struct net_device *netdev)
 	if (nic->sqs_mode)
 		nicvf_get_primary_vf_struct(nic);
 
-	/* Configure receive side scaling */
-	if (!nic->sqs_mode)
+	/* Configure receive side scaling and MTU */
+	if (!nic->sqs_mode) {
 		nicvf_rss_init(nic);
+		if (nicvf_update_hw_max_frs(nic, netdev->mtu))
+			goto cleanup;
+
+		/* Clear percpu stats */
+		for_each_possible_cpu(cpu)
+			memset(per_cpu_ptr(nic->drv_stats, cpu), 0,
+			       sizeof(struct nicvf_drv_stats));
+	}
 
 	err = nicvf_register_interrupts(nic);
 	if (err)
@@ -1276,8 +1266,9 @@ int nicvf_open(struct net_device *netdev)
 	for (qidx = 0; qidx < qs->rbdr_cnt; qidx++)
 		nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx);
 
-	nic->drv_stats.txq_stop = 0;
-	nic->drv_stats.txq_wake = 0;
+	/* Send VF config done msg to PF */
+	mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE;
+	nicvf_write_to_mbx(nic, &mbx);
 
 	return 0;
 cleanup:
@@ -1297,17 +1288,6 @@ napi_del:
 	return err;
 }
 
-static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu)
-{
-	union nic_mbx mbx = {};
-
-	mbx.frs.msg = NIC_MBOX_MSG_SET_MAX_FRS;
-	mbx.frs.max_frs = mtu;
-	mbx.frs.vf_id = nic->vf_id;
-
-	return nicvf_send_msg_to_pf(nic, &mbx);
-}
-
 static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct nicvf *nic = netdev_priv(netdev);
@@ -1318,10 +1298,13 @@ static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
 	if (new_mtu < NIC_HW_MIN_FRS)
 		return -EINVAL;
 
+	netdev->mtu = new_mtu;
+
+	if (!netif_running(netdev))
+		return 0;
+
 	if (nicvf_update_hw_max_frs(nic, new_mtu))
 		return -EINVAL;
-	netdev->mtu = new_mtu;
-	nic->mtu = new_mtu;
 
 	return 0;
 }
@@ -1379,9 +1362,10 @@ void nicvf_update_lmac_stats(struct nicvf *nic)
 
 void nicvf_update_stats(struct nicvf *nic)
 {
-	int qidx;
+	int qidx, cpu;
+	u64 tmp_stats = 0;
 	struct nicvf_hw_stats *stats = &nic->hw_stats;
-	struct nicvf_drv_stats *drv_stats = &nic->drv_stats;
+	struct nicvf_drv_stats *drv_stats;
 	struct queue_set *qs = nic->qs;
 
 #define GET_RX_STATS(reg) \
@@ -1404,21 +1388,33 @@ void nicvf_update_stats(struct nicvf *nic)
 	stats->rx_drop_l3_bcast = GET_RX_STATS(RX_DRP_L3BCAST);
 	stats->rx_drop_l3_mcast = GET_RX_STATS(RX_DRP_L3MCAST);
 
-	stats->tx_bytes_ok = GET_TX_STATS(TX_OCTS);
-	stats->tx_ucast_frames_ok = GET_TX_STATS(TX_UCAST);
-	stats->tx_bcast_frames_ok = GET_TX_STATS(TX_BCAST);
-	stats->tx_mcast_frames_ok = GET_TX_STATS(TX_MCAST);
+	stats->tx_bytes = GET_TX_STATS(TX_OCTS);
+	stats->tx_ucast_frames = GET_TX_STATS(TX_UCAST);
+	stats->tx_bcast_frames = GET_TX_STATS(TX_BCAST);
+	stats->tx_mcast_frames = GET_TX_STATS(TX_MCAST);
 	stats->tx_drops = GET_TX_STATS(TX_DROP);
 
-	drv_stats->tx_frames_ok = stats->tx_ucast_frames_ok +
-				  stats->tx_bcast_frames_ok +
-				  stats->tx_mcast_frames_ok;
-	drv_stats->rx_frames_ok = stats->rx_ucast_frames +
-				  stats->rx_bcast_frames +
-				  stats->rx_mcast_frames;
-	drv_stats->rx_drops = stats->rx_drop_red +
-			      stats->rx_drop_overrun;
-	drv_stats->tx_drops = stats->tx_drops;
+	/* On T88 pass 2.0, the dummy SQE added for TSO notification
+	 * via CQE has 'dont_send' set. Hence HW drops the pkt pointed
+	 * pointed by dummy SQE and results in tx_drops counter being
+	 * incremented. Subtracting it from tx_tso counter will give
+	 * exact tx_drops counter.
+	 */
+	if (nic->t88 && nic->hw_tso) {
+		for_each_possible_cpu(cpu) {
+			drv_stats = per_cpu_ptr(nic->drv_stats, cpu);
+			tmp_stats += drv_stats->tx_tso;
+		}
+		stats->tx_drops = tmp_stats - stats->tx_drops;
+	}
+	stats->tx_frames = stats->tx_ucast_frames +
+			   stats->tx_bcast_frames +
+			   stats->tx_mcast_frames;
+	stats->rx_frames = stats->rx_ucast_frames +
+			   stats->rx_bcast_frames +
+			   stats->rx_mcast_frames;
+	stats->rx_drops = stats->rx_drop_red +
+			  stats->rx_drop_overrun;
 
 	/* Update RQ and SQ stats */
 	for (qidx = 0; qidx < qs->rq_cnt; qidx++)
@@ -1432,18 +1428,17 @@ static struct rtnl_link_stats64 *nicvf_get_stats64(struct net_device *netdev,
 {
 	struct nicvf *nic = netdev_priv(netdev);
 	struct nicvf_hw_stats *hw_stats = &nic->hw_stats;
-	struct nicvf_drv_stats *drv_stats = &nic->drv_stats;
 
 	nicvf_update_stats(nic);
 
 	stats->rx_bytes = hw_stats->rx_bytes;
-	stats->rx_packets = drv_stats->rx_frames_ok;
-	stats->rx_dropped = drv_stats->rx_drops;
+	stats->rx_packets = hw_stats->rx_frames;
+	stats->rx_dropped = hw_stats->rx_drops;
 	stats->multicast = hw_stats->rx_mcast_frames;
 
-	stats->tx_bytes = hw_stats->tx_bytes_ok;
-	stats->tx_packets = drv_stats->tx_frames_ok;
-	stats->tx_dropped = drv_stats->tx_drops;
+	stats->tx_bytes = hw_stats->tx_bytes;
+	stats->tx_packets = hw_stats->tx_frames;
+	stats->tx_dropped = hw_stats->tx_drops;
 
 	return stats;
 }
@@ -1456,7 +1451,7 @@ static void nicvf_tx_timeout(struct net_device *dev)
 		netdev_warn(dev, "%s: Transmit timed out, resetting\n",
 			    dev->name);
 
-	nic->drv_stats.tx_timeout++;
+	this_cpu_inc(nic->drv_stats->tx_timeout);
 	schedule_work(&nic->reset_task);
 }
 
@@ -1590,6 +1585,12 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_free_netdev;
 	}
 
+	nic->drv_stats = netdev_alloc_pcpu_stats(struct nicvf_drv_stats);
+	if (!nic->drv_stats) {
+		err = -ENOMEM;
+		goto err_free_netdev;
+	}
+
 	err = nicvf_set_qset_resources(nic);
 	if (err)
 		goto err_free_netdev;
@@ -1648,6 +1649,8 @@ err_unregister_interrupts:
 	nicvf_unregister_interrupts(nic);
 err_free_netdev:
 	pci_set_drvdata(pdev, NULL);
+	if (nic->drv_stats)
+		free_percpu(nic->drv_stats);
 	free_netdev(netdev);
 err_release_regions:
 	pci_release_regions(pdev);
@@ -1675,6 +1678,8 @@ static void nicvf_remove(struct pci_dev *pdev)
 		unregister_netdev(pnetdev);
 	nicvf_unregister_interrupts(nic);
 	pci_set_drvdata(pdev, NULL);
+	if (nic->drv_stats)
+		free_percpu(nic->drv_stats);
 	free_netdev(netdev);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index a4fc50155881..747ef0882976 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -104,7 +104,8 @@ static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp,
 		nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN,
 					   order);
 		if (!nic->rb_page) {
-			nic->drv_stats.rcv_buffer_alloc_failures++;
+			this_cpu_inc(nic->pnicvf->drv_stats->
+				     rcv_buffer_alloc_failures);
 			return -ENOMEM;
 		}
 		nic->rb_page_offset = 0;
@@ -270,7 +271,8 @@ refill:
 			      rbdr_idx, new_rb);
 next_rbdr:
 	/* Re-enable RBDR interrupts only if buffer allocation is success */
-	if (!nic->rb_alloc_fail && rbdr->enable)
+	if (!nic->rb_alloc_fail && rbdr->enable &&
+	    netif_running(nic->pnicvf->netdev))
 		nicvf_enable_intr(nic, NICVF_INTR_RBDR, rbdr_idx);
 
 	if (rbdr_idx)
@@ -361,6 +363,8 @@ static int nicvf_init_snd_queue(struct nicvf *nic,
 
 static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
 {
+	struct sk_buff *skb;
+
 	if (!sq)
 		return;
 	if (!sq->dmem.base)
@@ -371,6 +375,15 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
 				  sq->dmem.q_len * TSO_HEADER_SIZE,
 				  sq->tso_hdrs, sq->tso_hdrs_phys);
 
+	/* Free pending skbs in the queue */
+	smp_rmb();
+	while (sq->head != sq->tail) {
+		skb = (struct sk_buff *)sq->skbuff[sq->head];
+		if (skb)
+			dev_kfree_skb_any(skb);
+		sq->head++;
+		sq->head &= (sq->dmem.q_len - 1);
+	}
 	kfree(sq->skbuff);
 	nicvf_free_q_desc_mem(nic, &sq->dmem);
 }
@@ -483,9 +496,12 @@ static void nicvf_reset_rcv_queue_stats(struct nicvf *nic)
 {
 	union nic_mbx mbx = {};
 
-	/* Reset all RXQ's stats */
+	/* Reset all RQ/SQ and VF stats */
 	mbx.reset_stat.msg = NIC_MBOX_MSG_RESET_STAT_COUNTER;
+	mbx.reset_stat.rx_stat_mask = 0x3FFF;
+	mbx.reset_stat.tx_stat_mask = 0x1F;
 	mbx.reset_stat.rq_stat_mask = 0xFFFF;
+	mbx.reset_stat.sq_stat_mask = 0xFFFF;
 	nicvf_send_msg_to_pf(nic, &mbx);
 }
 
@@ -538,9 +554,12 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs,
 	mbx.rq.cfg = (1ULL << 62) | (RQ_CQ_DROP << 8);
 	nicvf_send_msg_to_pf(nic, &mbx);
 
-	nicvf_queue_reg_write(nic, NIC_QSET_RQ_GEN_CFG, 0, 0x00);
-	if (!nic->sqs_mode)
+	if (!nic->sqs_mode && (qidx == 0)) {
+		/* Enable checking L3/L4 length and TCP/UDP checksums */
+		nicvf_queue_reg_write(nic, NIC_QSET_RQ_GEN_CFG, 0,
+				      (BIT(24) | BIT(23) | BIT(21)));
 		nicvf_config_vlan_stripping(nic, nic->netdev->features);
+	}
 
 	/* Enable Receive queue */
 	memset(&rq_cfg, 0, sizeof(struct rq_cfg));
@@ -1029,7 +1048,7 @@ nicvf_sq_add_hdr_subdesc(struct nicvf *nic, struct snd_queue *sq, int qentry,
 		hdr->tso_max_paysize = skb_shinfo(skb)->gso_size;
 		/* For non-tunneled pkts, point this to L2 ethertype */
 		hdr->inner_l3_offset = skb_network_offset(skb) - 2;
-		nic->drv_stats.tx_tso++;
+		this_cpu_inc(nic->pnicvf->drv_stats->tx_tso);
 	}
 }
 
@@ -1161,7 +1180,7 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq,
 
 	nicvf_sq_doorbell(nic, skb, sq_num, desc_cnt);
 
-	nic->drv_stats.tx_tso++;
+	this_cpu_inc(nic->pnicvf->drv_stats->tx_tso);
 	return 1;
 }
 
@@ -1422,8 +1441,6 @@ void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx)
 /* Check for errors in the receive cmp.queue entry */
 int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 {
-	struct nicvf_hw_stats *stats = &nic->hw_stats;
-
 	if (!cqe_rx->err_level && !cqe_rx->err_opcode)
 		return 0;
 
@@ -1435,76 +1452,76 @@ int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 
 	switch (cqe_rx->err_opcode) {
 	case CQ_RX_ERROP_RE_PARTIAL:
-		stats->rx_bgx_truncated_pkts++;
+		this_cpu_inc(nic->drv_stats->rx_bgx_truncated_pkts);
 		break;
 	case CQ_RX_ERROP_RE_JABBER:
-		stats->rx_jabber_errs++;
+		this_cpu_inc(nic->drv_stats->rx_jabber_errs);
 		break;
 	case CQ_RX_ERROP_RE_FCS:
-		stats->rx_fcs_errs++;
+		this_cpu_inc(nic->drv_stats->rx_fcs_errs);
 		break;
 	case CQ_RX_ERROP_RE_RX_CTL:
-		stats->rx_bgx_errs++;
+		this_cpu_inc(nic->drv_stats->rx_bgx_errs);
 		break;
 	case CQ_RX_ERROP_PREL2_ERR:
-		stats->rx_prel2_errs++;
+		this_cpu_inc(nic->drv_stats->rx_prel2_errs);
 		break;
 	case CQ_RX_ERROP_L2_MAL:
-		stats->rx_l2_hdr_malformed++;
+		this_cpu_inc(nic->drv_stats->rx_l2_hdr_malformed);
 		break;
 	case CQ_RX_ERROP_L2_OVERSIZE:
-		stats->rx_oversize++;
+		this_cpu_inc(nic->drv_stats->rx_oversize);
 		break;
 	case CQ_RX_ERROP_L2_UNDERSIZE:
-		stats->rx_undersize++;
+		this_cpu_inc(nic->drv_stats->rx_undersize);
 		break;
 	case CQ_RX_ERROP_L2_LENMISM:
-		stats->rx_l2_len_mismatch++;
+		this_cpu_inc(nic->drv_stats->rx_l2_len_mismatch);
 		break;
 	case CQ_RX_ERROP_L2_PCLP:
-		stats->rx_l2_pclp++;
+		this_cpu_inc(nic->drv_stats->rx_l2_pclp);
 		break;
 	case CQ_RX_ERROP_IP_NOT:
-		stats->rx_ip_ver_errs++;
+		this_cpu_inc(nic->drv_stats->rx_ip_ver_errs);
 		break;
 	case CQ_RX_ERROP_IP_CSUM_ERR:
-		stats->rx_ip_csum_errs++;
+		this_cpu_inc(nic->drv_stats->rx_ip_csum_errs);
 		break;
 	case CQ_RX_ERROP_IP_MAL:
-		stats->rx_ip_hdr_malformed++;
+		this_cpu_inc(nic->drv_stats->rx_ip_hdr_malformed);
 		break;
 	case CQ_RX_ERROP_IP_MALD:
-		stats->rx_ip_payload_malformed++;
+		this_cpu_inc(nic->drv_stats->rx_ip_payload_malformed);
 		break;
 	case CQ_RX_ERROP_IP_HOP:
-		stats->rx_ip_ttl_errs++;
+		this_cpu_inc(nic->drv_stats->rx_ip_ttl_errs);
 		break;
 	case CQ_RX_ERROP_L3_PCLP:
-		stats->rx_l3_pclp++;
+		this_cpu_inc(nic->drv_stats->rx_l3_pclp);
 		break;
 	case CQ_RX_ERROP_L4_MAL:
-		stats->rx_l4_malformed++;
+		this_cpu_inc(nic->drv_stats->rx_l4_malformed);
 		break;
 	case CQ_RX_ERROP_L4_CHK:
-		stats->rx_l4_csum_errs++;
+		this_cpu_inc(nic->drv_stats->rx_l4_csum_errs);
 		break;
 	case CQ_RX_ERROP_UDP_LEN:
-		stats->rx_udp_len_errs++;
+		this_cpu_inc(nic->drv_stats->rx_udp_len_errs);
 		break;
 	case CQ_RX_ERROP_L4_PORT:
-		stats->rx_l4_port_errs++;
+		this_cpu_inc(nic->drv_stats->rx_l4_port_errs);
 		break;
 	case CQ_RX_ERROP_TCP_FLAG:
-		stats->rx_tcp_flag_errs++;
+		this_cpu_inc(nic->drv_stats->rx_tcp_flag_errs);
 		break;
 	case CQ_RX_ERROP_TCP_OFFSET:
-		stats->rx_tcp_offset_errs++;
+		this_cpu_inc(nic->drv_stats->rx_tcp_offset_errs);
 		break;
 	case CQ_RX_ERROP_L4_PCLP:
-		stats->rx_l4_pclp++;
+		this_cpu_inc(nic->drv_stats->rx_l4_pclp);
 		break;
 	case CQ_RX_ERROP_RBDR_TRUNC:
-		stats->rx_truncated_pkts++;
+		this_cpu_inc(nic->drv_stats->rx_truncated_pkts);
 		break;
 	}
 
@@ -1512,53 +1529,52 @@ int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx)
 }
 
 /* Check for errors in the send cmp.queue entry */
-int nicvf_check_cqe_tx_errs(struct nicvf *nic,
-			    struct cmp_queue *cq, struct cqe_send_t *cqe_tx)
+int nicvf_check_cqe_tx_errs(struct nicvf *nic, struct cqe_send_t *cqe_tx)
 {
-	struct cmp_queue_stats *stats = &cq->stats;
-
 	switch (cqe_tx->send_status) {
 	case CQ_TX_ERROP_GOOD:
-		stats->tx.good++;
 		return 0;
 	case CQ_TX_ERROP_DESC_FAULT:
-		stats->tx.desc_fault++;
+		this_cpu_inc(nic->drv_stats->tx_desc_fault);
 		break;
 	case CQ_TX_ERROP_HDR_CONS_ERR:
-		stats->tx.hdr_cons_err++;
+		this_cpu_inc(nic->drv_stats->tx_hdr_cons_err);
 		break;
 	case CQ_TX_ERROP_SUBDC_ERR:
-		stats->tx.subdesc_err++;
+		this_cpu_inc(nic->drv_stats->tx_subdesc_err);
+		break;
+	case CQ_TX_ERROP_MAX_SIZE_VIOL:
+		this_cpu_inc(nic->drv_stats->tx_max_size_exceeded);
 		break;
 	case CQ_TX_ERROP_IMM_SIZE_OFLOW:
-		stats->tx.imm_size_oflow++;
+		this_cpu_inc(nic->drv_stats->tx_imm_size_oflow);
 		break;
 	case CQ_TX_ERROP_DATA_SEQUENCE_ERR:
-		stats->tx.data_seq_err++;
+		this_cpu_inc(nic->drv_stats->tx_data_seq_err);
 		break;
 	case CQ_TX_ERROP_MEM_SEQUENCE_ERR:
-		stats->tx.mem_seq_err++;
+		this_cpu_inc(nic->drv_stats->tx_mem_seq_err);
 		break;
 	case CQ_TX_ERROP_LOCK_VIOL:
-		stats->tx.lock_viol++;
+		this_cpu_inc(nic->drv_stats->tx_lock_viol);
 		break;
 	case CQ_TX_ERROP_DATA_FAULT:
-		stats->tx.data_fault++;
+		this_cpu_inc(nic->drv_stats->tx_data_fault);
 		break;
 	case CQ_TX_ERROP_TSTMP_CONFLICT:
-		stats->tx.tstmp_conflict++;
+		this_cpu_inc(nic->drv_stats->tx_tstmp_conflict);
 		break;
 	case CQ_TX_ERROP_TSTMP_TIMEOUT:
-		stats->tx.tstmp_timeout++;
+		this_cpu_inc(nic->drv_stats->tx_tstmp_timeout);
 		break;
 	case CQ_TX_ERROP_MEM_FAULT:
-		stats->tx.mem_fault++;
+		this_cpu_inc(nic->drv_stats->tx_mem_fault);
 		break;
 	case CQ_TX_ERROP_CK_OVERLAP:
-		stats->tx.csum_overlap++;
+		this_cpu_inc(nic->drv_stats->tx_csum_overlap);
 		break;
 	case CQ_TX_ERROP_CK_OFLOW:
-		stats->tx.csum_overflow++;
+		this_cpu_inc(nic->drv_stats->tx_csum_overflow);
 		break;
 	}
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index 869f3386028b..2e3c940c1093 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -158,6 +158,7 @@ enum CQ_TX_ERROP_E {
 	CQ_TX_ERROP_DESC_FAULT = 0x10,
 	CQ_TX_ERROP_HDR_CONS_ERR = 0x11,
 	CQ_TX_ERROP_SUBDC_ERR = 0x12,
+	CQ_TX_ERROP_MAX_SIZE_VIOL = 0x13,
 	CQ_TX_ERROP_IMM_SIZE_OFLOW = 0x80,
 	CQ_TX_ERROP_DATA_SEQUENCE_ERR = 0x81,
 	CQ_TX_ERROP_MEM_SEQUENCE_ERR = 0x82,
@@ -171,25 +172,6 @@ enum CQ_TX_ERROP_E {
 	CQ_TX_ERROP_ENUM_LAST = 0x8a,
 };
 
-struct cmp_queue_stats {
-	struct tx_stats {
-		u64 good;
-		u64 desc_fault;
-		u64 hdr_cons_err;
-		u64 subdesc_err;
-		u64 imm_size_oflow;
-		u64 data_seq_err;
-		u64 mem_seq_err;
-		u64 lock_viol;
-		u64 data_fault;
-		u64 tstmp_conflict;
-		u64 tstmp_timeout;
-		u64 mem_fault;
-		u64 csum_overlap;
-		u64 csum_overflow;
-	} tx;
-} ____cacheline_aligned_in_smp;
-
 enum RQ_SQ_STATS {
 	RQ_SQ_STATS_OCTS,
 	RQ_SQ_STATS_PKTS,
@@ -241,7 +223,6 @@ struct cmp_queue {
 	spinlock_t	lock;  /* lock to serialize processing CQEs */
 	void		*desc;
 	struct q_desc_mem   dmem;
-	struct cmp_queue_stats	stats;
 	int		irq;
 } ____cacheline_aligned_in_smp;
 
@@ -336,6 +317,5 @@ u64  nicvf_queue_reg_read(struct nicvf *nic,
 void nicvf_update_rq_stats(struct nicvf *nic, int rq_idx);
 void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx);
 int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx);
-int nicvf_check_cqe_tx_errs(struct nicvf *nic,
-			    struct cmp_queue *cq, struct cqe_send_t *cqe_tx);
+int nicvf_check_cqe_tx_errs(struct nicvf *nic, struct cqe_send_t *cqe_tx);
 #endif /* NICVF_QUEUES_H */
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 8bbaedbb7b94..050e21fbb147 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -1242,8 +1242,8 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_read_config_word(pdev, PCI_DEVICE_ID, &sdevid);
 	if (sdevid != PCI_DEVICE_ID_THUNDER_RGX) {
-		bgx->bgx_id =
-		    (pci_resource_start(pdev, PCI_CFG_REG_BAR_NUM) >> 24) & 1;
+		bgx->bgx_id = (pci_resource_start(pdev,
+			PCI_CFG_REG_BAR_NUM) >> 24) & BGX_ID_MASK;
 		bgx->bgx_id += nic_get_node_id(pdev) * MAX_BGX_PER_NODE;
 		bgx->max_lmac = MAX_LMAC_PER_BGX;
 		bgx_vnic[bgx->bgx_id] = bgx;
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index d59c71e4a000..01cc7c859131 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -28,6 +28,8 @@
 #define    MAX_DMAC_PER_LMAC			8
 #define    MAX_FRAME_SIZE			9216
 
+#define	   BGX_ID_MASK				0x3
+
 #define    MAX_DMAC_PER_LMAC_TNS_BYPASS_MODE	2
 
 /* Registers */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 1e74fd6085df..e19a0ca8e5dd 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -2951,7 +2951,6 @@ void free_rspq_fl(struct adapter *adap, struct sge_rspq *rq,
 		   rq->cntxt_id, fl_id, 0xffff);
 	dma_free_coherent(adap->pdev_dev, (rq->size + 1) * rq->iqe_len,
 			  rq->desc, rq->phys_addr);
-	napi_hash_del(&rq->napi);
 	netif_napi_del(&rq->napi);
 	rq->netdev = NULL;
 	rq->cntxt_id = rq->abs_id = 0;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index cece8a08edca..93aa2939142a 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -2813,7 +2813,6 @@ static void be_evt_queues_destroy(struct be_adapter *adapter)
 		if (eqo->q.created) {
 			be_eq_clean(eqo);
 			be_cmd_q_destroy(adapter, &eqo->q, QTYPE_EQ);
-			napi_hash_del(&eqo->napi);
 			netif_napi_del(&eqo->napi);
 			free_cpumask_var(eqo->affinity_mask);
 		}
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index f05ea56dcff2..941c8e2c944e 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -5220,6 +5220,19 @@ static SIMPLE_DEV_PM_OPS(sky2_pm_ops, sky2_suspend, sky2_resume);
 
 static void sky2_shutdown(struct pci_dev *pdev)
 {
+	struct sky2_hw *hw = pci_get_drvdata(pdev);
+	int port;
+
+	for (port = 0; port < hw->ports; port++) {
+		struct net_device *ndev = hw->dev[port];
+
+		rtnl_lock();
+		if (netif_running(ndev)) {
+			dev_close(ndev);
+			netif_device_detach(ndev);
+		}
+		rtnl_unlock();
+	}
 	sky2_suspend(&pdev->dev);
 	pci_wake_from_d3(pdev, device_may_wakeup(&pdev->dev));
 	pci_set_power_state(pdev, PCI_D3hot);
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 3818c5e06eba..4b78168a5f3c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -107,7 +107,7 @@ config DWMAC_STI
 config DWMAC_STM32
 	tristate "STM32 DWMAC support"
 	default ARCH_STM32
-	depends on OF && HAS_IOMEM
+	depends on OF && HAS_IOMEM && (ARCH_STM32 || COMPILE_TEST)
 	select MFD_SYSCON
 	---help---
 	  Support for ethernet controller on STM32 SOCs.
diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
index 2920e2ee3864..489ef146201e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
@@ -63,8 +63,8 @@
 #define TSE_PCS_SGMII_LINK_TIMER_0			0x0D40
 #define TSE_PCS_SGMII_LINK_TIMER_1			0x0003
 #define TSE_PCS_SW_RESET_TIMEOUT			100
-#define TSE_PCS_USE_SGMII_AN_MASK			BIT(2)
-#define TSE_PCS_USE_SGMII_ENA				BIT(1)
+#define TSE_PCS_USE_SGMII_AN_MASK			BIT(1)
+#define TSE_PCS_USE_SGMII_ENA				BIT(0)
 
 #define SGMII_ADAPTER_CTRL_REG				0x00
 #define SGMII_ADAPTER_DISABLE				0x0001
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index d3292c4a6eda..6d2de4e01f6d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -120,14 +120,17 @@ struct stmmac_extra_stats {
 	unsigned long ip_csum_bypassed;
 	unsigned long ipv4_pkt_rcvd;
 	unsigned long ipv6_pkt_rcvd;
-	unsigned long rx_msg_type_ext_no_ptp;
-	unsigned long rx_msg_type_sync;
-	unsigned long rx_msg_type_follow_up;
-	unsigned long rx_msg_type_delay_req;
-	unsigned long rx_msg_type_delay_resp;
-	unsigned long rx_msg_type_pdelay_req;
-	unsigned long rx_msg_type_pdelay_resp;
-	unsigned long rx_msg_type_pdelay_follow_up;
+	unsigned long no_ptp_rx_msg_type_ext;
+	unsigned long ptp_rx_msg_type_sync;
+	unsigned long ptp_rx_msg_type_follow_up;
+	unsigned long ptp_rx_msg_type_delay_req;
+	unsigned long ptp_rx_msg_type_delay_resp;
+	unsigned long ptp_rx_msg_type_pdelay_req;
+	unsigned long ptp_rx_msg_type_pdelay_resp;
+	unsigned long ptp_rx_msg_type_pdelay_follow_up;
+	unsigned long ptp_rx_msg_type_announce;
+	unsigned long ptp_rx_msg_type_management;
+	unsigned long ptp_rx_msg_pkt_reserved_type;
 	unsigned long ptp_frame_type;
 	unsigned long ptp_ver;
 	unsigned long timestamp_dropped;
@@ -482,11 +485,12 @@ struct stmmac_ops {
 /* PTP and HW Timer helpers */
 struct stmmac_hwtimestamp {
 	void (*config_hw_tstamping) (void __iomem *ioaddr, u32 data);
-	u32 (*config_sub_second_increment) (void __iomem *ioaddr, u32 clk_rate);
+	u32 (*config_sub_second_increment)(void __iomem *ioaddr, u32 ptp_clock,
+					   int gmac4);
 	int (*init_systime) (void __iomem *ioaddr, u32 sec, u32 nsec);
 	int (*config_addend) (void __iomem *ioaddr, u32 addend);
 	int (*adjust_systime) (void __iomem *ioaddr, u32 sec, u32 nsec,
-			       int add_sub);
+			       int add_sub, int gmac4);
 	 u64(*get_systime) (void __iomem *ioaddr);
 };
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/descs.h b/drivers/net/ethernet/stmicro/stmmac/descs.h
index 2e4c171a2b41..e3c86d422109 100644
--- a/drivers/net/ethernet/stmicro/stmmac/descs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/descs.h
@@ -155,14 +155,18 @@
 #define	ERDES4_L3_L4_FILT_NO_MATCH_MASK	GENMASK(27, 26)
 
 /* Extended RDES4 message type definitions */
-#define RDES_EXT_NO_PTP			0
-#define RDES_EXT_SYNC			1
-#define RDES_EXT_FOLLOW_UP		2
-#define RDES_EXT_DELAY_REQ		3
-#define RDES_EXT_DELAY_RESP		4
-#define RDES_EXT_PDELAY_REQ		5
-#define RDES_EXT_PDELAY_RESP		6
-#define RDES_EXT_PDELAY_FOLLOW_UP	7
+#define RDES_EXT_NO_PTP			0x0
+#define RDES_EXT_SYNC			0x1
+#define RDES_EXT_FOLLOW_UP		0x2
+#define RDES_EXT_DELAY_REQ		0x3
+#define RDES_EXT_DELAY_RESP		0x4
+#define RDES_EXT_PDELAY_REQ		0x5
+#define RDES_EXT_PDELAY_RESP		0x6
+#define RDES_EXT_PDELAY_FOLLOW_UP	0x7
+#define RDES_PTP_ANNOUNCE		0x8
+#define RDES_PTP_MANAGEMENT		0x9
+#define RDES_PTP_SIGNALING		0xa
+#define RDES_PTP_PKT_RESERVED_TYPE	0xf
 
 /* Basic descriptor structure for normal and alternate descriptors */
 struct dma_desc {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index a1b17cd7886b..a601f8d43b75 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -123,22 +123,29 @@ static int dwmac4_wrback_get_rx_status(void *data, struct stmmac_extra_stats *x,
 		x->ipv4_pkt_rcvd++;
 	if (rdes1 & RDES1_IPV6_HEADER)
 		x->ipv6_pkt_rcvd++;
-	if (message_type == RDES_EXT_SYNC)
-		x->rx_msg_type_sync++;
+
+	if (message_type == RDES_EXT_NO_PTP)
+		x->no_ptp_rx_msg_type_ext++;
+	else if (message_type == RDES_EXT_SYNC)
+		x->ptp_rx_msg_type_sync++;
 	else if (message_type == RDES_EXT_FOLLOW_UP)
-		x->rx_msg_type_follow_up++;
+		x->ptp_rx_msg_type_follow_up++;
 	else if (message_type == RDES_EXT_DELAY_REQ)
-		x->rx_msg_type_delay_req++;
+		x->ptp_rx_msg_type_delay_req++;
 	else if (message_type == RDES_EXT_DELAY_RESP)
-		x->rx_msg_type_delay_resp++;
+		x->ptp_rx_msg_type_delay_resp++;
 	else if (message_type == RDES_EXT_PDELAY_REQ)
-		x->rx_msg_type_pdelay_req++;
+		x->ptp_rx_msg_type_pdelay_req++;
 	else if (message_type == RDES_EXT_PDELAY_RESP)
-		x->rx_msg_type_pdelay_resp++;
+		x->ptp_rx_msg_type_pdelay_resp++;
 	else if (message_type == RDES_EXT_PDELAY_FOLLOW_UP)
-		x->rx_msg_type_pdelay_follow_up++;
-	else
-		x->rx_msg_type_ext_no_ptp++;
+		x->ptp_rx_msg_type_pdelay_follow_up++;
+	else if (message_type == RDES_PTP_ANNOUNCE)
+		x->ptp_rx_msg_type_announce++;
+	else if (message_type == RDES_PTP_MANAGEMENT)
+		x->ptp_rx_msg_type_management++;
+	else if (message_type == RDES_PTP_PKT_RESERVED_TYPE)
+		x->ptp_rx_msg_pkt_reserved_type++;
 
 	if (rdes1 & RDES1_PTP_PACKET_TYPE)
 		x->ptp_frame_type++;
@@ -204,14 +211,18 @@ static void dwmac4_rd_enable_tx_timestamp(struct dma_desc *p)
 
 static int dwmac4_wrback_get_tx_timestamp_status(struct dma_desc *p)
 {
-	return (p->des3 & TDES3_TIMESTAMP_STATUS)
-		>> TDES3_TIMESTAMP_STATUS_SHIFT;
+	/* Context type from W/B descriptor must be zero */
+	if (p->des3 & TDES3_CONTEXT_TYPE)
+		return -EINVAL;
+
+	/* Tx Timestamp Status is 1 so des0 and des1'll have valid values */
+	if (p->des3 & TDES3_TIMESTAMP_STATUS)
+		return 0;
+
+	return 1;
 }
 
-/*  NOTE: For RX CTX bit has to be checked before
- *  HAVE a specific function for TX and another one for RX
- */
-static u64 dwmac4_wrback_get_timestamp(void *desc, u32 ats)
+static inline u64 dwmac4_get_timestamp(void *desc, u32 ats)
 {
 	struct dma_desc *p = (struct dma_desc *)desc;
 	u64 ns;
@@ -223,12 +234,54 @@ static u64 dwmac4_wrback_get_timestamp(void *desc, u32 ats)
 	return ns;
 }
 
-static int dwmac4_context_get_rx_timestamp_status(void *desc, u32 ats)
+static int dwmac4_rx_check_timestamp(void *desc)
+{
+	struct dma_desc *p = (struct dma_desc *)desc;
+	u32 own, ctxt;
+	int ret = 1;
+
+	own = p->des3 & RDES3_OWN;
+	ctxt = ((p->des3 & RDES3_CONTEXT_DESCRIPTOR)
+		>> RDES3_CONTEXT_DESCRIPTOR_SHIFT);
+
+	if (likely(!own && ctxt)) {
+		if ((p->des0 == 0xffffffff) && (p->des1 == 0xffffffff))
+			/* Corrupted value */
+			ret = -EINVAL;
+		else
+			/* A valid Timestamp is ready to be read */
+			ret = 0;
+	}
+
+	/* Timestamp not ready */
+	return ret;
+}
+
+static int dwmac4_wrback_get_rx_timestamp_status(void *desc, u32 ats)
 {
 	struct dma_desc *p = (struct dma_desc *)desc;
+	int ret = -EINVAL;
+
+	/* Get the status from normal w/b descriptor */
+	if (likely(p->des3 & TDES3_RS1V)) {
+		if (likely(p->des1 & RDES1_TIMESTAMP_AVAILABLE)) {
+			int i = 0;
+
+			/* Check if timestamp is OK from context descriptor */
+			do {
+				ret = dwmac4_rx_check_timestamp(desc);
+				if (ret < 0)
+					goto exit;
+				i++;
 
-	return (p->des1 & RDES1_TIMESTAMP_AVAILABLE)
-		>> RDES1_TIMESTAMP_AVAILABLE_SHIFT;
+			} while ((ret == 1) || (i < 10));
+
+			if (i == 10)
+				ret = -EBUSY;
+		}
+	}
+exit:
+	return ret;
 }
 
 static void dwmac4_rd_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
@@ -373,8 +426,8 @@ const struct stmmac_desc_ops dwmac4_desc_ops = {
 	.get_rx_frame_len = dwmac4_wrback_get_rx_frame_len,
 	.enable_tx_timestamp = dwmac4_rd_enable_tx_timestamp,
 	.get_tx_timestamp_status = dwmac4_wrback_get_tx_timestamp_status,
-	.get_timestamp = dwmac4_wrback_get_timestamp,
-	.get_rx_timestamp_status = dwmac4_context_get_rx_timestamp_status,
+	.get_rx_timestamp_status = dwmac4_wrback_get_rx_timestamp_status,
+	.get_timestamp = dwmac4_get_timestamp,
 	.set_tx_ic = dwmac4_rd_set_tx_ic,
 	.prepare_tx_desc = dwmac4_rd_prepare_tx_desc,
 	.prepare_tso_tx_desc = dwmac4_rd_prepare_tso_tx_desc,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
index 0902a2edeaa9..9736c505211a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
@@ -59,10 +59,13 @@
 #define TDES3_CTXT_TCMSSV		BIT(26)
 
 /* TDES3 Common */
+#define	TDES3_RS1V			BIT(26)
+#define	TDES3_RS1V_SHIFT		26
 #define TDES3_LAST_DESCRIPTOR		BIT(28)
 #define TDES3_LAST_DESCRIPTOR_SHIFT	28
 #define TDES3_FIRST_DESCRIPTOR		BIT(29)
 #define TDES3_CONTEXT_TYPE		BIT(30)
+#define	TDES3_CONTEXT_TYPE_SHIFT	30
 
 /* TDS3 use for both format (read and write back) */
 #define TDES3_OWN			BIT(31)
@@ -117,6 +120,7 @@
 #define RDES3_LAST_DESCRIPTOR		BIT(28)
 #define RDES3_FIRST_DESCRIPTOR		BIT(29)
 #define RDES3_CONTEXT_DESCRIPTOR	BIT(30)
+#define RDES3_CONTEXT_DESCRIPTOR_SHIFT	30
 
 /* RDES3 (read format) */
 #define RDES3_BUFFER1_VALID_ADDR	BIT(24)
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 38f19c99cf59..e75549327c34 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -150,22 +150,30 @@ static void enh_desc_get_ext_status(void *data, struct stmmac_extra_stats *x,
 			x->ipv4_pkt_rcvd++;
 		if (rdes4 & ERDES4_IPV6_PKT_RCVD)
 			x->ipv6_pkt_rcvd++;
-		if (message_type == RDES_EXT_SYNC)
-			x->rx_msg_type_sync++;
+
+		if (message_type == RDES_EXT_NO_PTP)
+			x->no_ptp_rx_msg_type_ext++;
+		else if (message_type == RDES_EXT_SYNC)
+			x->ptp_rx_msg_type_sync++;
 		else if (message_type == RDES_EXT_FOLLOW_UP)
-			x->rx_msg_type_follow_up++;
+			x->ptp_rx_msg_type_follow_up++;
 		else if (message_type == RDES_EXT_DELAY_REQ)
-			x->rx_msg_type_delay_req++;
+			x->ptp_rx_msg_type_delay_req++;
 		else if (message_type == RDES_EXT_DELAY_RESP)
-			x->rx_msg_type_delay_resp++;
+			x->ptp_rx_msg_type_delay_resp++;
 		else if (message_type == RDES_EXT_PDELAY_REQ)
-			x->rx_msg_type_pdelay_req++;
+			x->ptp_rx_msg_type_pdelay_req++;
 		else if (message_type == RDES_EXT_PDELAY_RESP)
-			x->rx_msg_type_pdelay_resp++;
+			x->ptp_rx_msg_type_pdelay_resp++;
 		else if (message_type == RDES_EXT_PDELAY_FOLLOW_UP)
-			x->rx_msg_type_pdelay_follow_up++;
-		else
-			x->rx_msg_type_ext_no_ptp++;
+			x->ptp_rx_msg_type_pdelay_follow_up++;
+		else if (message_type == RDES_PTP_ANNOUNCE)
+			x->ptp_rx_msg_type_announce++;
+		else if (message_type == RDES_PTP_MANAGEMENT)
+			x->ptp_rx_msg_type_management++;
+		else if (message_type == RDES_PTP_PKT_RESERVED_TYPE)
+			x->ptp_rx_msg_pkt_reserved_type++;
+
 		if (rdes4 & ERDES4_PTP_FRAME_TYPE)
 			x->ptp_frame_type++;
 		if (rdes4 & ERDES4_PTP_VER)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index b15fc55f1b96..4d2a759b8465 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -129,6 +129,7 @@ struct stmmac_priv {
 	int irq_wake;
 	spinlock_t ptp_lock;
 	void __iomem *mmcaddr;
+	void __iomem *ptpaddr;
 	u32 rx_tail_addr;
 	u32 tx_tail_addr;
 	u32 mss;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 1e06173fc9d7..c5d0142adda2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -115,14 +115,17 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = {
 	STMMAC_STAT(ip_csum_bypassed),
 	STMMAC_STAT(ipv4_pkt_rcvd),
 	STMMAC_STAT(ipv6_pkt_rcvd),
-	STMMAC_STAT(rx_msg_type_ext_no_ptp),
-	STMMAC_STAT(rx_msg_type_sync),
-	STMMAC_STAT(rx_msg_type_follow_up),
-	STMMAC_STAT(rx_msg_type_delay_req),
-	STMMAC_STAT(rx_msg_type_delay_resp),
-	STMMAC_STAT(rx_msg_type_pdelay_req),
-	STMMAC_STAT(rx_msg_type_pdelay_resp),
-	STMMAC_STAT(rx_msg_type_pdelay_follow_up),
+	STMMAC_STAT(no_ptp_rx_msg_type_ext),
+	STMMAC_STAT(ptp_rx_msg_type_sync),
+	STMMAC_STAT(ptp_rx_msg_type_follow_up),
+	STMMAC_STAT(ptp_rx_msg_type_delay_req),
+	STMMAC_STAT(ptp_rx_msg_type_delay_resp),
+	STMMAC_STAT(ptp_rx_msg_type_pdelay_req),
+	STMMAC_STAT(ptp_rx_msg_type_pdelay_resp),
+	STMMAC_STAT(ptp_rx_msg_type_pdelay_follow_up),
+	STMMAC_STAT(ptp_rx_msg_type_announce),
+	STMMAC_STAT(ptp_rx_msg_type_management),
+	STMMAC_STAT(ptp_rx_msg_pkt_reserved_type),
 	STMMAC_STAT(ptp_frame_type),
 	STMMAC_STAT(ptp_ver),
 	STMMAC_STAT(timestamp_dropped),
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
index a77f68918010..10d6059b2f26 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c
@@ -34,21 +34,29 @@ static void stmmac_config_hw_tstamping(void __iomem *ioaddr, u32 data)
 }
 
 static u32 stmmac_config_sub_second_increment(void __iomem *ioaddr,
-					      u32 ptp_clock)
+					      u32 ptp_clock, int gmac4)
 {
 	u32 value = readl(ioaddr + PTP_TCR);
 	unsigned long data;
 
-	/* Convert the ptp_clock to nano second
-	 * formula = (2/ptp_clock) * 1000000000
-	 * where, ptp_clock = 50MHz.
+	/* For GMAC3.x, 4.x versions, convert the ptp_clock to nano second
+	 *	formula = (1/ptp_clock) * 1000000000
+	 * where ptp_clock is 50MHz if fine method is used to update system
 	 */
-	data = (2000000000ULL / ptp_clock);
+	if (value & PTP_TCR_TSCFUPDT)
+		data = (1000000000ULL / 50000000);
+	else
+		data = (1000000000ULL / ptp_clock);
 
 	/* 0.465ns accuracy */
 	if (!(value & PTP_TCR_TSCTRLSSR))
 		data = (data * 1000) / 465;
 
+	data &= PTP_SSIR_SSINC_MASK;
+
+	if (gmac4)
+		data = data << GMAC4_PTP_SSIR_SSINC_SHIFT;
+
 	writel(data, ioaddr + PTP_SSIR);
 
 	return data;
@@ -104,14 +112,30 @@ static int stmmac_config_addend(void __iomem *ioaddr, u32 addend)
 }
 
 static int stmmac_adjust_systime(void __iomem *ioaddr, u32 sec, u32 nsec,
-				 int add_sub)
+				 int add_sub, int gmac4)
 {
 	u32 value;
 	int limit;
 
+	if (add_sub) {
+		/* If the new sec value needs to be subtracted with
+		 * the system time, then MAC_STSUR reg should be
+		 * programmed with (2^32 – <new_sec_value>)
+		 */
+		if (gmac4)
+			sec = (100000000ULL - sec);
+
+		value = readl(ioaddr + PTP_TCR);
+		if (value & PTP_TCR_TSCTRLSSR)
+			nsec = (PTP_DIGITAL_ROLLOVER_MODE - nsec);
+		else
+			nsec = (PTP_BINARY_ROLLOVER_MODE - nsec);
+	}
+
 	writel(sec, ioaddr + PTP_STSUR);
-	writel(((add_sub << PTP_STNSUR_ADDSUB_SHIFT) | nsec),
-		ioaddr + PTP_STNSUR);
+	value = (add_sub << PTP_STNSUR_ADDSUB_SHIFT) | nsec;
+	writel(value, ioaddr + PTP_STNSUR);
+
 	/* issue command to initialize the system time value */
 	value = readl(ioaddr + PTP_TCR);
 	value |= PTP_TCR_TSUPDT;
@@ -134,8 +158,9 @@ static u64 stmmac_get_systime(void __iomem *ioaddr)
 {
 	u64 ns;
 
+	/* Get the TSSS value */
 	ns = readl(ioaddr + PTP_STNSR);
-	/* convert sec time value to nanosecond */
+	/* Get the TSS and convert sec time value to nanosecond */
 	ns += readl(ioaddr + PTP_STSR) * 1000000000ULL;
 
 	return ns;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index e2c94ec4edd0..1f9ec02fa7f8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -340,18 +340,17 @@ out:
 
 /* stmmac_get_tx_hwtstamp - get HW TX timestamps
  * @priv: driver private structure
- * @entry : descriptor index to be used.
+ * @p : descriptor pointer
  * @skb : the socket buffer
  * Description :
  * This function will read timestamp from the descriptor & pass it to stack.
  * and also perform some sanity checks.
  */
 static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv,
-				   unsigned int entry, struct sk_buff *skb)
+				   struct dma_desc *p, struct sk_buff *skb)
 {
 	struct skb_shared_hwtstamps shhwtstamp;
 	u64 ns;
-	void *desc = NULL;
 
 	if (!priv->hwts_tx_en)
 		return;
@@ -360,58 +359,55 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv,
 	if (likely(!skb || !(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)))
 		return;
 
-	if (priv->adv_ts)
-		desc = (priv->dma_etx + entry);
-	else
-		desc = (priv->dma_tx + entry);
-
 	/* check tx tstamp status */
-	if (!priv->hw->desc->get_tx_timestamp_status((struct dma_desc *)desc))
-		return;
+	if (!priv->hw->desc->get_tx_timestamp_status(p)) {
+		/* get the valid tstamp */
+		ns = priv->hw->desc->get_timestamp(p, priv->adv_ts);
 
-	/* get the valid tstamp */
-	ns = priv->hw->desc->get_timestamp(desc, priv->adv_ts);
+		memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps));
+		shhwtstamp.hwtstamp = ns_to_ktime(ns);
 
-	memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps));
-	shhwtstamp.hwtstamp = ns_to_ktime(ns);
-	/* pass tstamp to stack */
-	skb_tstamp_tx(skb, &shhwtstamp);
+		netdev_info(priv->dev, "get valid TX hw timestamp %llu\n", ns);
+		/* pass tstamp to stack */
+		skb_tstamp_tx(skb, &shhwtstamp);
+	}
 
 	return;
 }
 
 /* stmmac_get_rx_hwtstamp - get HW RX timestamps
  * @priv: driver private structure
- * @entry : descriptor index to be used.
+ * @p : descriptor pointer
+ * @np : next descriptor pointer
  * @skb : the socket buffer
  * Description :
  * This function will read received packet's timestamp from the descriptor
  * and pass it to stack. It also perform some sanity checks.
  */
-static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv,
-				   unsigned int entry, struct sk_buff *skb)
+static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p,
+				   struct dma_desc *np, struct sk_buff *skb)
 {
 	struct skb_shared_hwtstamps *shhwtstamp = NULL;
 	u64 ns;
-	void *desc = NULL;
 
 	if (!priv->hwts_rx_en)
 		return;
 
-	if (priv->adv_ts)
-		desc = (priv->dma_erx + entry);
-	else
-		desc = (priv->dma_rx + entry);
-
-	/* exit if rx tstamp is not valid */
-	if (!priv->hw->desc->get_rx_timestamp_status(desc, priv->adv_ts))
-		return;
+	/* Check if timestamp is available */
+	if (!priv->hw->desc->get_rx_timestamp_status(p, priv->adv_ts)) {
+		/* For GMAC4, the valid timestamp is from CTX next desc. */
+		if (priv->plat->has_gmac4)
+			ns = priv->hw->desc->get_timestamp(np, priv->adv_ts);
+		else
+			ns = priv->hw->desc->get_timestamp(p, priv->adv_ts);
 
-	/* get valid tstamp */
-	ns = priv->hw->desc->get_timestamp(desc, priv->adv_ts);
-	shhwtstamp = skb_hwtstamps(skb);
-	memset(shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps));
-	shhwtstamp->hwtstamp = ns_to_ktime(ns);
+		netdev_info(priv->dev, "get valid RX hw timestamp %llu\n", ns);
+		shhwtstamp = skb_hwtstamps(skb);
+		memset(shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps));
+		shhwtstamp->hwtstamp = ns_to_ktime(ns);
+	} else  {
+		netdev_err(priv->dev, "cannot get RX hw timestamp\n");
+	}
 }
 
 /**
@@ -598,17 +594,18 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 	priv->hwts_tx_en = config.tx_type == HWTSTAMP_TX_ON;
 
 	if (!priv->hwts_tx_en && !priv->hwts_rx_en)
-		priv->hw->ptp->config_hw_tstamping(priv->ioaddr, 0);
+		priv->hw->ptp->config_hw_tstamping(priv->ptpaddr, 0);
 	else {
 		value = (PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | PTP_TCR_TSCTRLSSR |
 			 tstamp_all | ptp_v2 | ptp_over_ethernet |
 			 ptp_over_ipv6_udp | ptp_over_ipv4_udp | ts_event_en |
 			 ts_master_en | snap_type_sel);
-		priv->hw->ptp->config_hw_tstamping(priv->ioaddr, value);
+		priv->hw->ptp->config_hw_tstamping(priv->ptpaddr, value);
 
 		/* program Sub Second Increment reg */
 		sec_inc = priv->hw->ptp->config_sub_second_increment(
-			priv->ioaddr, priv->clk_ptp_rate);
+			priv->ptpaddr, priv->clk_ptp_rate,
+			priv->plat->has_gmac4);
 		temp = div_u64(1000000000ULL, sec_inc);
 
 		/* calculate default added value:
@@ -618,14 +615,14 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 		 */
 		temp = (u64)(temp << 32);
 		priv->default_addend = div_u64(temp, priv->clk_ptp_rate);
-		priv->hw->ptp->config_addend(priv->ioaddr,
+		priv->hw->ptp->config_addend(priv->ptpaddr,
 					     priv->default_addend);
 
 		/* initialize system time */
 		ktime_get_real_ts64(&now);
 
 		/* lower 32 bits of tv_sec are safe until y2106 */
-		priv->hw->ptp->init_systime(priv->ioaddr, (u32)now.tv_sec,
+		priv->hw->ptp->init_systime(priv->ptpaddr, (u32)now.tv_sec,
 					    now.tv_nsec);
 	}
 
@@ -1340,7 +1337,7 @@ static void stmmac_tx_clean(struct stmmac_priv *priv)
 				priv->dev->stats.tx_packets++;
 				priv->xstats.tx_pkt_n++;
 			}
-			stmmac_get_tx_hwtstamp(priv, entry, skb);
+			stmmac_get_tx_hwtstamp(priv, p, skb);
 		}
 
 		if (likely(priv->tx_skbuff_dma[entry].buf)) {
@@ -1486,10 +1483,13 @@ static void stmmac_mmc_setup(struct stmmac_priv *priv)
 	unsigned int mode = MMC_CNTRL_RESET_ON_READ | MMC_CNTRL_COUNTER_RESET |
 			    MMC_CNTRL_PRESET | MMC_CNTRL_FULL_HALF_PRESET;
 
-	if (priv->synopsys_id >= DWMAC_CORE_4_00)
+	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+		priv->ptpaddr = priv->ioaddr + PTP_GMAC4_OFFSET;
 		priv->mmcaddr = priv->ioaddr + MMC_GMAC4_OFFSET;
-	else
+	} else {
+		priv->ptpaddr = priv->ioaddr + PTP_GMAC3_X_OFFSET;
 		priv->mmcaddr = priv->ioaddr + MMC_GMAC3_X_OFFSET;
+	}
 
 	dwmac_mmc_intr_all_mask(priv->mmcaddr);
 
@@ -2484,7 +2484,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 	if (netif_msg_rx_status(priv)) {
 		void *rx_head;
 
-		pr_debug("%s: descriptor ring:\n", __func__);
+		pr_info(">>>>>> %s: descriptor ring:\n", __func__);
 		if (priv->extend_desc)
 			rx_head = (void *)priv->dma_erx;
 		else
@@ -2495,6 +2495,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 	while (count < limit) {
 		int status;
 		struct dma_desc *p;
+		struct dma_desc *np;
 
 		if (priv->extend_desc)
 			p = (struct dma_desc *)(priv->dma_erx + entry);
@@ -2514,9 +2515,11 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 		next_entry = priv->cur_rx;
 
 		if (priv->extend_desc)
-			prefetch(priv->dma_erx + next_entry);
+			np = (struct dma_desc *)(priv->dma_erx + next_entry);
 		else
-			prefetch(priv->dma_rx + next_entry);
+			np = priv->dma_rx + next_entry;
+
+		prefetch(np);
 
 		if ((priv->extend_desc) && (priv->hw->desc->rx_extended_status))
 			priv->hw->desc->rx_extended_status(&priv->dev->stats,
@@ -2568,7 +2571,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 				frame_len -= ETH_FCS_LEN;
 
 			if (netif_msg_rx_status(priv)) {
-				pr_debug("\tdesc: %p [entry %d] buff=0x%x\n",
+				pr_info("\tdesc: %p [entry %d] buff=0x%x\n",
 					p, entry, des);
 				if (frame_len > ETH_FRAME_LEN)
 					pr_debug("\tframe size %d, COE: %d\n",
@@ -2625,13 +2628,13 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
 						 DMA_FROM_DEVICE);
 			}
 
-			stmmac_get_rx_hwtstamp(priv, entry, skb);
-
 			if (netif_msg_pktdata(priv)) {
 				pr_debug("frame received (%dbytes)", frame_len);
 				print_pkt(skb->data, frame_len);
 			}
 
+			stmmac_get_rx_hwtstamp(priv, p, np, skb);
+
 			stmmac_rx_vlan(priv->dev, skb);
 
 			skb->protocol = eth_type_trans(skb, priv->dev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index 1477471f8d44..3eb281d1db08 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -54,7 +54,7 @@ static int stmmac_adjust_freq(struct ptp_clock_info *ptp, s32 ppb)
 
 	spin_lock_irqsave(&priv->ptp_lock, flags);
 
-	priv->hw->ptp->config_addend(priv->ioaddr, addend);
+	priv->hw->ptp->config_addend(priv->ptpaddr, addend);
 
 	spin_unlock_irqrestore(&priv->ptp_lock, flags);
 
@@ -89,7 +89,8 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta)
 
 	spin_lock_irqsave(&priv->ptp_lock, flags);
 
-	priv->hw->ptp->adjust_systime(priv->ioaddr, sec, nsec, neg_adj);
+	priv->hw->ptp->adjust_systime(priv->ptpaddr, sec, nsec, neg_adj,
+				      priv->plat->has_gmac4);
 
 	spin_unlock_irqrestore(&priv->ptp_lock, flags);
 
@@ -114,7 +115,7 @@ static int stmmac_get_time(struct ptp_clock_info *ptp, struct timespec64 *ts)
 
 	spin_lock_irqsave(&priv->ptp_lock, flags);
 
-	ns = priv->hw->ptp->get_systime(priv->ioaddr);
+	ns = priv->hw->ptp->get_systime(priv->ptpaddr);
 
 	spin_unlock_irqrestore(&priv->ptp_lock, flags);
 
@@ -141,7 +142,7 @@ static int stmmac_set_time(struct ptp_clock_info *ptp,
 
 	spin_lock_irqsave(&priv->ptp_lock, flags);
 
-	priv->hw->ptp->init_systime(priv->ioaddr, ts->tv_sec, ts->tv_nsec);
+	priv->hw->ptp->init_systime(priv->ptpaddr, ts->tv_sec, ts->tv_nsec);
 
 	spin_unlock_irqrestore(&priv->ptp_lock, flags);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
index 4535df37c227..c06938c47af5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
@@ -22,51 +22,53 @@
   Author: Rayagond Kokatanur <rayagond@vayavyalabs.com>
 ******************************************************************************/
 
-#ifndef __STMMAC_PTP_H__
-#define __STMMAC_PTP_H__
+#ifndef	__STMMAC_PTP_H__
+#define	__STMMAC_PTP_H__
 
-/* IEEE 1588 PTP register offsets */
-#define PTP_TCR		0x0700	/* Timestamp Control Reg */
-#define PTP_SSIR	0x0704	/* Sub-Second Increment Reg */
-#define PTP_STSR	0x0708	/* System Time – Seconds Regr */
-#define PTP_STNSR	0x070C	/* System Time – Nanoseconds Reg */
-#define PTP_STSUR	0x0710	/* System Time – Seconds Update Reg */
-#define PTP_STNSUR	0x0714	/* System Time – Nanoseconds Update Reg */
-#define PTP_TAR		0x0718	/* Timestamp Addend Reg */
-#define PTP_TTSR	0x071C	/* Target Time Seconds Reg */
-#define PTP_TTNSR	0x0720	/* Target Time Nanoseconds Reg */
-#define	PTP_STHWSR	0x0724	/* System Time - Higher Word Seconds Reg */
-#define PTP_TSR		0x0728	/* Timestamp Status */
+#define	PTP_GMAC4_OFFSET	0xb00
+#define	PTP_GMAC3_X_OFFSET	0x700
 
-#define PTP_STNSUR_ADDSUB_SHIFT 31
+/* IEEE 1588 PTP register offsets */
+#define	PTP_TCR		0x00	/* Timestamp Control Reg */
+#define	PTP_SSIR	0x04	/* Sub-Second Increment Reg */
+#define	PTP_STSR	0x08	/* System Time – Seconds Regr */
+#define	PTP_STNSR	0x0c	/* System Time – Nanoseconds Reg */
+#define	PTP_STSUR	0x10	/* System Time – Seconds Update Reg */
+#define	PTP_STNSUR	0x14	/* System Time – Nanoseconds Update Reg */
+#define	PTP_TAR		0x18	/* Timestamp Addend Reg */
 
-/* PTP TCR defines */
-#define PTP_TCR_TSENA		0x00000001 /* Timestamp Enable */
-#define PTP_TCR_TSCFUPDT	0x00000002 /* Timestamp Fine/Coarse Update */
-#define PTP_TCR_TSINIT		0x00000004 /* Timestamp Initialize */
-#define PTP_TCR_TSUPDT		0x00000008 /* Timestamp Update */
-/* Timestamp Interrupt Trigger Enable */
-#define PTP_TCR_TSTRIG		0x00000010
-#define PTP_TCR_TSADDREG	0x00000020 /* Addend Reg Update */
-#define PTP_TCR_TSENALL		0x00000100 /* Enable Timestamp for All Frames */
-/* Timestamp Digital or Binary Rollover Control */
-#define PTP_TCR_TSCTRLSSR	0x00000200
+#define	PTP_STNSUR_ADDSUB_SHIFT	31
+#define	PTP_DIGITAL_ROLLOVER_MODE	0x3B9ACA00	/* 10e9-1 ns */
+#define	PTP_BINARY_ROLLOVER_MODE	0x80000000	/* ~0.466 ns */
 
+/* PTP Timestamp control register defines */
+#define	PTP_TCR_TSENA		BIT(0)	/* Timestamp Enable */
+#define	PTP_TCR_TSCFUPDT	BIT(1)	/* Timestamp Fine/Coarse Update */
+#define	PTP_TCR_TSINIT		BIT(2)	/* Timestamp Initialize */
+#define	PTP_TCR_TSUPDT		BIT(3)	/* Timestamp Update */
+#define	PTP_TCR_TSTRIG		BIT(4)	/* Timestamp Interrupt Trigger Enable */
+#define	PTP_TCR_TSADDREG	BIT(5)	/* Addend Reg Update */
+#define	PTP_TCR_TSENALL		BIT(8)	/* Enable Timestamp for All Frames */
+#define	PTP_TCR_TSCTRLSSR	BIT(9)	/* Digital or Binary Rollover Control */
 /* Enable PTP packet Processing for Version 2 Format */
-#define PTP_TCR_TSVER2ENA	0x00000400
+#define	PTP_TCR_TSVER2ENA	BIT(10)
 /* Enable Processing of PTP over Ethernet Frames */
-#define PTP_TCR_TSIPENA		0x00000800
+#define	PTP_TCR_TSIPENA		BIT(11)
 /* Enable Processing of PTP Frames Sent over IPv6-UDP */
-#define PTP_TCR_TSIPV6ENA	0x00001000
+#define	PTP_TCR_TSIPV6ENA	BIT(12)
 /* Enable Processing of PTP Frames Sent over IPv4-UDP */
-#define PTP_TCR_TSIPV4ENA	0x00002000
+#define	PTP_TCR_TSIPV4ENA	BIT(13)
 /* Enable Timestamp Snapshot for Event Messages */
-#define PTP_TCR_TSEVNTENA	0x00004000
+#define	PTP_TCR_TSEVNTENA	BIT(14)
 /* Enable Snapshot for Messages Relevant to Master */
-#define PTP_TCR_TSMSTRENA	0x00008000
+#define	PTP_TCR_TSMSTRENA	BIT(15)
 /* Select PTP packets for Taking Snapshots */
-#define PTP_TCR_SNAPTYPSEL_1	0x00010000
+#define	PTP_TCR_SNAPTYPSEL_1	GENMASK(17, 16)
 /* Enable MAC address for PTP Frame Filtering */
-#define PTP_TCR_TSENMACADDR	0x00040000
+#define	PTP_TCR_TSENMACADDR	BIT(18)
+
+/* SSIR defines */
+#define	PTP_SSIR_SSINC_MASK		0xff
+#define	GMAC4_PTP_SSIR_SSINC_SHIFT	16
 
-#endif /* __STMMAC_PTP_H__ */
+#endif	/* __STMMAC_PTP_H__ */
diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c
index aa4f9d2d8fa9..02f452730d52 100644
--- a/drivers/net/ethernet/sun/sunbmac.c
+++ b/drivers/net/ethernet/sun/sunbmac.c
@@ -623,6 +623,7 @@ static int bigmac_init_hw(struct bigmac *bp, int from_irq)
 	void __iomem *gregs        = bp->gregs;
 	void __iomem *cregs        = bp->creg;
 	void __iomem *bregs        = bp->bregs;
+	__u32 bblk_dvma = (__u32)bp->bblock_dvma;
 	unsigned char *e = &bp->dev->dev_addr[0];
 
 	/* Latch current counters into statistics. */
@@ -671,9 +672,9 @@ static int bigmac_init_hw(struct bigmac *bp, int from_irq)
 		    bregs + BMAC_XIFCFG);
 
 	/* Tell the QEC where the ring descriptors are. */
-	sbus_writel(bp->bblock_dvma + bib_offset(be_rxd, 0),
+	sbus_writel(bblk_dvma + bib_offset(be_rxd, 0),
 		    cregs + CREG_RXDS);
-	sbus_writel(bp->bblock_dvma + bib_offset(be_txd, 0),
+	sbus_writel(bblk_dvma + bib_offset(be_txd, 0),
 		    cregs + CREG_TXDS);
 
 	/* Setup the FIFO pointers into QEC local memory. */
diff --git a/drivers/net/ethernet/sun/sunbmac.h b/drivers/net/ethernet/sun/sunbmac.h
index 06dd21707353..532fc56830cf 100644
--- a/drivers/net/ethernet/sun/sunbmac.h
+++ b/drivers/net/ethernet/sun/sunbmac.h
@@ -291,7 +291,7 @@ struct bigmac {
 	void __iomem	*bregs;	/* BigMAC Registers                   */
 	void __iomem	*tregs;	/* BigMAC Transceiver                 */
 	struct bmac_init_block	*bmac_block;	/* RX and TX descriptors */
-	__u32			 bblock_dvma;	/* RX and TX descriptors */
+	dma_addr_t		bblock_dvma;	/* RX and TX descriptors */
 
 	spinlock_t		lock;
 
diff --git a/drivers/net/ethernet/sun/sunqe.c b/drivers/net/ethernet/sun/sunqe.c
index 9b825780b3be..9582948145c1 100644
--- a/drivers/net/ethernet/sun/sunqe.c
+++ b/drivers/net/ethernet/sun/sunqe.c
@@ -124,7 +124,7 @@ static void qe_init_rings(struct sunqe *qep)
 {
 	struct qe_init_block *qb = qep->qe_block;
 	struct sunqe_buffers *qbufs = qep->buffers;
-	__u32 qbufs_dvma = qep->buffers_dvma;
+	__u32 qbufs_dvma = (__u32)qep->buffers_dvma;
 	int i;
 
 	qep->rx_new = qep->rx_old = qep->tx_new = qep->tx_old = 0;
@@ -144,6 +144,7 @@ static int qe_init(struct sunqe *qep, int from_irq)
 	void __iomem *mregs = qep->mregs;
 	void __iomem *gregs = qecp->gregs;
 	unsigned char *e = &qep->dev->dev_addr[0];
+	__u32 qblk_dvma = (__u32)qep->qblock_dvma;
 	u32 tmp;
 	int i;
 
@@ -152,8 +153,8 @@ static int qe_init(struct sunqe *qep, int from_irq)
 		return -EAGAIN;
 
 	/* Setup initial rx/tx init block pointers. */
-	sbus_writel(qep->qblock_dvma + qib_offset(qe_rxd, 0), cregs + CREG_RXDS);
-	sbus_writel(qep->qblock_dvma + qib_offset(qe_txd, 0), cregs + CREG_TXDS);
+	sbus_writel(qblk_dvma + qib_offset(qe_rxd, 0), cregs + CREG_RXDS);
+	sbus_writel(qblk_dvma + qib_offset(qe_txd, 0), cregs + CREG_TXDS);
 
 	/* Enable/mask the various irq's. */
 	sbus_writel(0, cregs + CREG_RIMASK);
@@ -413,7 +414,7 @@ static void qe_rx(struct sunqe *qep)
 	struct net_device *dev = qep->dev;
 	struct qe_rxd *this;
 	struct sunqe_buffers *qbufs = qep->buffers;
-	__u32 qbufs_dvma = qep->buffers_dvma;
+	__u32 qbufs_dvma = (__u32)qep->buffers_dvma;
 	int elem = qep->rx_new;
 	u32 flags;
 
@@ -572,7 +573,7 @@ static int qe_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct sunqe *qep = netdev_priv(dev);
 	struct sunqe_buffers *qbufs = qep->buffers;
-	__u32 txbuf_dvma, qbufs_dvma = qep->buffers_dvma;
+	__u32 txbuf_dvma, qbufs_dvma = (__u32)qep->buffers_dvma;
 	unsigned char *txbuf;
 	int len, entry;
 
diff --git a/drivers/net/ethernet/sun/sunqe.h b/drivers/net/ethernet/sun/sunqe.h
index 581781b6b2fa..ae190b77431b 100644
--- a/drivers/net/ethernet/sun/sunqe.h
+++ b/drivers/net/ethernet/sun/sunqe.h
@@ -334,12 +334,12 @@ struct sunqe {
 	void __iomem			*qcregs;		/* QEC per-channel Registers   */
 	void __iomem			*mregs;		/* Per-channel MACE Registers  */
 	struct qe_init_block      	*qe_block;	/* RX and TX descriptors       */
-	__u32                      	qblock_dvma;	/* RX and TX descriptors       */
+	dma_addr_t			qblock_dvma;	/* RX and TX descriptors       */
 	spinlock_t			lock;		/* Protects txfull state       */
 	int                        	rx_new, rx_old;	/* RX ring extents	       */
 	int			   	tx_new, tx_old;	/* TX ring extents	       */
 	struct sunqe_buffers		*buffers;	/* CPU visible address.        */
-	__u32				buffers_dvma;	/* DVMA visible address.       */
+	dma_addr_t			buffers_dvma;	/* DVMA visible address.       */
 	struct sunqec			*parent;
 	u8				mconfig;	/* Base MACE mconfig value     */
 	struct platform_device		*op;		/* QE's OF device struct       */
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index c6cff3d2ff05..58947aae31c7 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -2375,8 +2375,11 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 			 * to the PHY is the Ethernet MAC DT node.
 			 */
 			ret = of_phy_register_fixed_link(slave_node);
-			if (ret)
+			if (ret) {
+				if (ret != -EPROBE_DEFER)
+					dev_err(&pdev->dev, "failed to register fixed-link phy: %d\n", ret);
 				return ret;
+			}
 			slave_data->phy_node = of_node_get(slave_node);
 		} else if (parp) {
 			u32 phyid;
@@ -2397,6 +2400,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 			}
 			snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
 				 PHY_ID_FMT, mdio->name, phyid);
+			put_device(&mdio->dev);
 		} else {
 			dev_err(&pdev->dev,
 				"No slave[%d] phy_id, phy-handle, or fixed-link property\n",
@@ -2440,6 +2444,46 @@ no_phy_slave:
 	return 0;
 }
 
+static void cpsw_remove_dt(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+	struct cpsw_platform_data *data = &cpsw->data;
+	struct device_node *node = pdev->dev.of_node;
+	struct device_node *slave_node;
+	int i = 0;
+
+	for_each_available_child_of_node(node, slave_node) {
+		struct cpsw_slave_data *slave_data = &data->slave_data[i];
+
+		if (strcmp(slave_node->name, "slave"))
+			continue;
+
+		if (of_phy_is_fixed_link(slave_node)) {
+			struct phy_device *phydev;
+
+			phydev = of_phy_find_device(slave_node);
+			if (phydev) {
+				fixed_phy_unregister(phydev);
+				/* Put references taken by
+				 * of_phy_find_device() and
+				 * of_phy_register_fixed_link().
+				 */
+				phy_device_free(phydev);
+				phy_device_free(phydev);
+			}
+		}
+
+		of_node_put(slave_data->phy_node);
+
+		i++;
+		if (i == data->slaves)
+			break;
+	}
+
+	of_platform_depopulate(&pdev->dev);
+}
+
 static int cpsw_probe_dual_emac(struct cpsw_priv *priv)
 {
 	struct cpsw_common		*cpsw = priv->cpsw;
@@ -2547,6 +2591,9 @@ static int cpsw_probe(struct platform_device *pdev)
 	int irq;
 
 	cpsw = devm_kzalloc(&pdev->dev, sizeof(struct cpsw_common), GFP_KERNEL);
+	if (!cpsw)
+		return -ENOMEM;
+
 	cpsw->dev = &pdev->dev;
 
 	ndev = alloc_etherdev_mq(sizeof(struct cpsw_priv), CPSW_MAX_QUEUES);
@@ -2584,11 +2631,19 @@ static int cpsw_probe(struct platform_device *pdev)
 	/* Select default pin state */
 	pinctrl_pm_select_default_state(&pdev->dev);
 
-	if (cpsw_probe_dt(&cpsw->data, pdev)) {
-		dev_err(&pdev->dev, "cpsw: platform data missing\n");
-		ret = -ENODEV;
+	/* Need to enable clocks with runtime PM api to access module
+	 * registers
+	 */
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(&pdev->dev);
 		goto clean_runtime_disable_ret;
 	}
+
+	ret = cpsw_probe_dt(&cpsw->data, pdev);
+	if (ret)
+		goto clean_dt_ret;
+
 	data = &cpsw->data;
 	cpsw->rx_ch_num = 1;
 	cpsw->tx_ch_num = 1;
@@ -2608,7 +2663,7 @@ static int cpsw_probe(struct platform_device *pdev)
 				    GFP_KERNEL);
 	if (!cpsw->slaves) {
 		ret = -ENOMEM;
-		goto clean_runtime_disable_ret;
+		goto clean_dt_ret;
 	}
 	for (i = 0; i < data->slaves; i++)
 		cpsw->slaves[i].slave_num = i;
@@ -2620,7 +2675,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	if (IS_ERR(clk)) {
 		dev_err(priv->dev, "fck is not found\n");
 		ret = -ENODEV;
-		goto clean_runtime_disable_ret;
+		goto clean_dt_ret;
 	}
 	cpsw->bus_freq_mhz = clk_get_rate(clk) / 1000000;
 
@@ -2628,26 +2683,17 @@ static int cpsw_probe(struct platform_device *pdev)
 	ss_regs = devm_ioremap_resource(&pdev->dev, ss_res);
 	if (IS_ERR(ss_regs)) {
 		ret = PTR_ERR(ss_regs);
-		goto clean_runtime_disable_ret;
+		goto clean_dt_ret;
 	}
 	cpsw->regs = ss_regs;
 
-	/* Need to enable clocks with runtime PM api to access module
-	 * registers
-	 */
-	ret = pm_runtime_get_sync(&pdev->dev);
-	if (ret < 0) {
-		pm_runtime_put_noidle(&pdev->dev);
-		goto clean_runtime_disable_ret;
-	}
 	cpsw->version = readl(&cpsw->regs->id_ver);
-	pm_runtime_put_sync(&pdev->dev);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 	cpsw->wr_regs = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(cpsw->wr_regs)) {
 		ret = PTR_ERR(cpsw->wr_regs);
-		goto clean_runtime_disable_ret;
+		goto clean_dt_ret;
 	}
 
 	memset(&dma_params, 0, sizeof(dma_params));
@@ -2684,7 +2730,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	default:
 		dev_err(priv->dev, "unknown version 0x%08x\n", cpsw->version);
 		ret = -ENODEV;
-		goto clean_runtime_disable_ret;
+		goto clean_dt_ret;
 	}
 	for (i = 0; i < cpsw->data.slaves; i++) {
 		struct cpsw_slave *slave = &cpsw->slaves[i];
@@ -2713,7 +2759,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	if (!cpsw->dma) {
 		dev_err(priv->dev, "error initializing dma\n");
 		ret = -ENOMEM;
-		goto clean_runtime_disable_ret;
+		goto clean_dt_ret;
 	}
 
 	cpsw->txch[0] = cpdma_chan_create(cpsw->dma, 0, cpsw_tx_handler, 0);
@@ -2811,16 +2857,23 @@ static int cpsw_probe(struct platform_device *pdev)
 		ret = cpsw_probe_dual_emac(priv);
 		if (ret) {
 			cpsw_err(priv, probe, "error probe slave 2 emac interface\n");
-			goto clean_ale_ret;
+			goto clean_unregister_netdev_ret;
 		}
 	}
 
+	pm_runtime_put(&pdev->dev);
+
 	return 0;
 
+clean_unregister_netdev_ret:
+	unregister_netdev(ndev);
 clean_ale_ret:
 	cpsw_ale_destroy(cpsw->ale);
 clean_dma_ret:
 	cpdma_ctlr_destroy(cpsw->dma);
+clean_dt_ret:
+	cpsw_remove_dt(pdev);
+	pm_runtime_put_sync(&pdev->dev);
 clean_runtime_disable_ret:
 	pm_runtime_disable(&pdev->dev);
 clean_ndev_ret:
@@ -2846,7 +2899,7 @@ static int cpsw_remove(struct platform_device *pdev)
 
 	cpsw_ale_destroy(cpsw->ale);
 	cpdma_ctlr_destroy(cpsw->dma);
-	of_platform_depopulate(&pdev->dev);
+	cpsw_remove_dt(pdev);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	if (cpsw->data.dual_emac)
diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index c649c101bbab..eb5167210681 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -279,7 +279,7 @@ EXPORT_SYMBOL_GPL(fixed_phy_register);
 void fixed_phy_unregister(struct phy_device *phy)
 {
 	phy_device_remove(phy);
-
+	of_node_put(phy->mdio.dev.of_node);
 	fixed_phy_del(phy->mdio.addr);
 }
 EXPORT_SYMBOL_GPL(fixed_phy_unregister);
diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index 2e37eb337d48..24b4a09468dd 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -62,6 +62,10 @@
 /* Vitesse Extended Page Access Register */
 #define MII_VSC82X4_EXT_PAGE_ACCESS	0x1f
 
+/* Vitesse VSC8601 Extended PHY Control Register 1 */
+#define MII_VSC8601_EPHY_CTL		0x17
+#define MII_VSC8601_EPHY_CTL_RGMII_SKEW	(1 << 8)
+
 #define PHY_ID_VSC8234			0x000fc620
 #define PHY_ID_VSC8244			0x000fc6c0
 #define PHY_ID_VSC8514			0x00070670
@@ -111,6 +115,34 @@ static int vsc824x_config_init(struct phy_device *phydev)
 	return err;
 }
 
+/* This adds a skew for both TX and RX clocks, so the skew should only be
+ * applied to "rgmii-id" interfaces. It may not work as expected
+ * on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces. */
+static int vsc8601_add_skew(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = phy_read(phydev, MII_VSC8601_EPHY_CTL);
+	if (ret < 0)
+		return ret;
+
+	ret |= MII_VSC8601_EPHY_CTL_RGMII_SKEW;
+	return phy_write(phydev, MII_VSC8601_EPHY_CTL, ret);
+}
+
+static int vsc8601_config_init(struct phy_device *phydev)
+{
+	int ret = 0;
+
+	if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID)
+		ret = vsc8601_add_skew(phydev);
+
+	if (ret < 0)
+		return ret;
+
+	return genphy_config_init(phydev);
+}
+
 static int vsc824x_ack_interrupt(struct phy_device *phydev)
 {
 	int err = 0;
@@ -275,7 +307,7 @@ static struct phy_driver vsc82xx_driver[] = {
 	.phy_id_mask    = 0x000ffff0,
 	.features       = PHY_GBIT_FEATURES,
 	.flags          = PHY_HAS_INTERRUPT,
-	.config_init    = &genphy_config_init,
+	.config_init    = &vsc8601_config_init,
 	.config_aneg    = &genphy_config_aneg,
 	.read_status    = &genphy_read_status,
 	.ack_interrupt  = &vsc824x_ack_interrupt,
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index fd8b1e62301f..7276d5a95bd0 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1497,6 +1497,11 @@ static void virtnet_free_queues(struct virtnet_info *vi)
 		netif_napi_del(&vi->rq[i].napi);
 	}
 
+	/* We called napi_hash_del() before netif_napi_del(),
+	 * we need to respect an RCU grace period before freeing vi->rq
+	 */
+	synchronize_net();
+
 	kfree(vi->rq);
 	kfree(vi->sq);
 }
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 431f13b4faf6..d3bad5779376 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -826,7 +826,7 @@ static void mac80211_hwsim_set_tsf(struct ieee80211_hw *hw,
 		data->bcn_delta = do_div(delta, bcn_int);
 	} else {
 		data->tsf_offset -= delta;
-		data->bcn_delta = -do_div(delta, bcn_int);
+		data->bcn_delta = -(s64)do_div(delta, bcn_int);
 	}
 }
 
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 0248d0e21fee..5e52034ab010 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1242,20 +1242,16 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 
 	result = nvme_enable_ctrl(&dev->ctrl, cap);
 	if (result)
-		goto free_nvmeq;
+		return result;
 
 	nvmeq->cq_vector = 0;
 	result = queue_request_irq(nvmeq);
 	if (result) {
 		nvmeq->cq_vector = -1;
-		goto free_nvmeq;
+		return result;
 	}
 
 	return result;
-
- free_nvmeq:
-	nvme_free_queues(dev, 0);
-	return result;
 }
 
 static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
@@ -1317,10 +1313,8 @@ static int nvme_create_io_queues(struct nvme_dev *dev)
 	max = min(dev->max_qid, dev->queue_count - 1);
 	for (i = dev->online_queues; i <= max; i++) {
 		ret = nvme_create_queue(dev->queues[i], i);
-		if (ret) {
-			nvme_free_queues(dev, i);
+		if (ret)
 			break;
-		}
 	}
 
 	/*
@@ -1460,13 +1454,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	result = queue_request_irq(adminq);
 	if (result) {
 		adminq->cq_vector = -1;
-		goto free_queues;
+		return result;
 	}
 	return nvme_create_io_queues(dev);
-
- free_queues:
-	nvme_free_queues(dev, 1);
-	return result;
 }
 
 static void nvme_del_queue_end(struct request *req, int error)
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 5a8388177959..3d25add36d91 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -83,6 +83,7 @@ enum nvme_rdma_queue_flags {
 	NVME_RDMA_Q_CONNECTED = (1 << 0),
 	NVME_RDMA_IB_QUEUE_ALLOCATED = (1 << 1),
 	NVME_RDMA_Q_DELETING = (1 << 2),
+	NVME_RDMA_Q_LIVE = (1 << 3),
 };
 
 struct nvme_rdma_queue {
@@ -624,10 +625,18 @@ static int nvme_rdma_connect_io_queues(struct nvme_rdma_ctrl *ctrl)
 
 	for (i = 1; i < ctrl->queue_count; i++) {
 		ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
-		if (ret)
-			break;
+		if (ret) {
+			dev_info(ctrl->ctrl.device,
+				"failed to connect i/o queue: %d\n", ret);
+			goto out_free_queues;
+		}
+		set_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[i].flags);
 	}
 
+	return 0;
+
+out_free_queues:
+	nvme_rdma_free_io_queues(ctrl);
 	return ret;
 }
 
@@ -712,6 +721,8 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 	if (ret)
 		goto stop_admin_q;
 
+	set_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[0].flags);
+
 	ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
 	if (ret)
 		goto stop_admin_q;
@@ -761,8 +772,10 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
 
 	nvme_stop_keep_alive(&ctrl->ctrl);
 
-	for (i = 0; i < ctrl->queue_count; i++)
+	for (i = 0; i < ctrl->queue_count; i++) {
 		clear_bit(NVME_RDMA_Q_CONNECTED, &ctrl->queues[i].flags);
+		clear_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[i].flags);
+	}
 
 	if (ctrl->queue_count > 1)
 		nvme_stop_queues(&ctrl->ctrl);
@@ -1378,6 +1391,24 @@ nvme_rdma_timeout(struct request *rq, bool reserved)
 	return BLK_EH_HANDLED;
 }
 
+/*
+ * We cannot accept any other command until the Connect command has completed.
+ */
+static inline bool nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue,
+		struct request *rq)
+{
+	if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags))) {
+		struct nvme_command *cmd = (struct nvme_command *)rq->cmd;
+
+		if (rq->cmd_type != REQ_TYPE_DRV_PRIV ||
+		    cmd->common.opcode != nvme_fabrics_command ||
+		    cmd->fabrics.fctype != nvme_fabrics_type_connect)
+			return false;
+	}
+
+	return true;
+}
+
 static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 		const struct blk_mq_queue_data *bd)
 {
@@ -1394,6 +1425,9 @@ static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	WARN_ON_ONCE(rq->tag < 0);
 
+	if (!nvme_rdma_queue_is_ready(queue, rq))
+		return BLK_MQ_RQ_QUEUE_BUSY;
+
 	dev = queue->device->dev;
 	ib_dma_sync_single_for_cpu(dev, sqe->dma,
 			sizeof(struct nvme_command), DMA_TO_DEVICE);
@@ -1544,6 +1578,8 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl)
 	if (error)
 		goto out_cleanup_queue;
 
+	set_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[0].flags);
+
 	error = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->cap);
 	if (error) {
 		dev_err(ctrl->ctrl.device,
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index b4cacb6f0258..a21437a33adb 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -838,9 +838,13 @@ static void nvmet_fatal_error_handler(struct work_struct *work)
 
 void nvmet_ctrl_fatal_error(struct nvmet_ctrl *ctrl)
 {
-	ctrl->csts |= NVME_CSTS_CFS;
-	INIT_WORK(&ctrl->fatal_err_work, nvmet_fatal_error_handler);
-	schedule_work(&ctrl->fatal_err_work);
+	mutex_lock(&ctrl->lock);
+	if (!(ctrl->csts & NVME_CSTS_CFS)) {
+		ctrl->csts |= NVME_CSTS_CFS;
+		INIT_WORK(&ctrl->fatal_err_work, nvmet_fatal_error_handler);
+		schedule_work(&ctrl->fatal_err_work);
+	}
+	mutex_unlock(&ctrl->lock);
 }
 EXPORT_SYMBOL_GPL(nvmet_ctrl_fatal_error);
 
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index f8d23999e0f2..005ef5d17a19 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -951,6 +951,7 @@ err_destroy_cq:
 
 static void nvmet_rdma_destroy_queue_ib(struct nvmet_rdma_queue *queue)
 {
+	ib_drain_qp(queue->cm_id->qp);
 	rdma_destroy_qp(queue->cm_id);
 	ib_free_cq(queue->cq);
 }
@@ -1066,6 +1067,7 @@ nvmet_rdma_alloc_queue(struct nvmet_rdma_device *ndev,
 	spin_lock_init(&queue->rsp_wr_wait_lock);
 	INIT_LIST_HEAD(&queue->free_rsps);
 	spin_lock_init(&queue->rsps_lock);
+	INIT_LIST_HEAD(&queue->queue_list);
 
 	queue->idx = ida_simple_get(&nvmet_rdma_queue_ida, 0, 0, GFP_KERNEL);
 	if (queue->idx < 0) {
@@ -1244,7 +1246,6 @@ static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue)
 
 	if (disconnect) {
 		rdma_disconnect(queue->cm_id);
-		ib_drain_qp(queue->cm_id->qp);
 		schedule_work(&queue->release_work);
 	}
 }
@@ -1269,7 +1270,12 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id,
 {
 	WARN_ON_ONCE(queue->state != NVMET_RDMA_Q_CONNECTING);
 
-	pr_err("failed to connect queue\n");
+	mutex_lock(&nvmet_rdma_queue_mutex);
+	if (!list_empty(&queue->queue_list))
+		list_del_init(&queue->queue_list);
+	mutex_unlock(&nvmet_rdma_queue_mutex);
+
+	pr_err("failed to connect queue %d\n", queue->idx);
 	schedule_work(&queue->release_work);
 }
 
@@ -1352,7 +1358,13 @@ static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id,
 	case RDMA_CM_EVENT_ADDR_CHANGE:
 	case RDMA_CM_EVENT_DISCONNECTED:
 	case RDMA_CM_EVENT_TIMEWAIT_EXIT:
-		nvmet_rdma_queue_disconnect(queue);
+		/*
+		 * We might end up here when we already freed the qp
+		 * which means queue release sequence is in progress,
+		 * so don't get in the way...
+		 */
+		if (queue)
+			nvmet_rdma_queue_disconnect(queue);
 		break;
 	case RDMA_CM_EVENT_DEVICE_REMOVAL:
 		ret = nvmet_rdma_device_removal(cm_id, queue);
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index b470f7e3521d..5a3145a02547 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -292,6 +292,7 @@ struct phy_device *of_phy_find_device(struct device_node *phy_np)
 		mdiodev = to_mdio_device(d);
 		if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY)
 			return to_phy_device(d);
+		put_device(d);
 	}
 
 	return NULL;
@@ -456,8 +457,11 @@ int of_phy_register_fixed_link(struct device_node *np)
 		status.link = 1;
 		status.duplex = of_property_read_bool(fixed_link_node,
 						      "full-duplex");
-		if (of_property_read_u32(fixed_link_node, "speed", &status.speed))
+		if (of_property_read_u32(fixed_link_node, "speed",
+					 &status.speed)) {
+			of_node_put(fixed_link_node);
 			return -EINVAL;
+		}
 		status.pause = of_property_read_bool(fixed_link_node, "pause");
 		status.asym_pause = of_property_read_bool(fixed_link_node,
 							  "asym-pause");
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 8aa769a2d919..91b70bc46e7f 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -4010,7 +4010,10 @@ _scsih_eedp_error_handling(struct scsi_cmnd *scmd, u16 ioc_status)
 	    SAM_STAT_CHECK_CONDITION;
 }
 
-
+static inline bool ata_12_16_cmd(struct scsi_cmnd *scmd)
+{
+	return (scmd->cmnd[0] == ATA_12 || scmd->cmnd[0] == ATA_16);
+}
 
 /**
  * scsih_qcmd - main scsi request entry point
@@ -4038,6 +4041,13 @@ 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;
@@ -4613,6 +4623,9 @@ _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);
+
 	mpi_request = mpt3sas_base_get_msg_frame(ioc, smid);
 
 	if (mpi_reply == NULL) {
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 567fa080e261..56d6142852a5 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1456,15 +1456,20 @@ qla2x00_abort_all_cmds(scsi_qla_host_t *vha, int res)
 		for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) {
 			sp = req->outstanding_cmds[cnt];
 			if (sp) {
-				/* Get a reference to the sp and drop the lock.
-				 * The reference ensures this sp->done() call
-				 * - and not the call in qla2xxx_eh_abort() -
-				 * ends the SCSI command (with result 'res').
+				/* Don't abort commands in adapter during EEH
+				 * recovery as it's not accessible/responding.
 				 */
-				sp_get(sp);
-				spin_unlock_irqrestore(&ha->hardware_lock, flags);
-				qla2xxx_eh_abort(GET_CMD_SP(sp));
-				spin_lock_irqsave(&ha->hardware_lock, flags);
+				if (!ha->flags.eeh_busy) {
+					/* Get a reference to the sp and drop the lock.
+					 * The reference ensures this sp->done() call
+					 * - and not the call in qla2xxx_eh_abort() -
+					 * ends the SCSI command (with result 'res').
+					 */
+					sp_get(sp);
+					spin_unlock_irqrestore(&ha->hardware_lock, flags);
+					qla2xxx_eh_abort(GET_CMD_SP(sp));
+					spin_lock_irqsave(&ha->hardware_lock, flags);
+				}
 				req->outstanding_cmds[cnt] = NULL;
 				sp->done(vha, sp, res);
 			}
diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c
index 7a223074df3d..afada655f861 100644
--- a/drivers/thermal/intel_powerclamp.c
+++ b/drivers/thermal/intel_powerclamp.c
@@ -669,9 +669,16 @@ static struct thermal_cooling_device_ops powerclamp_cooling_ops = {
 	.set_cur_state = powerclamp_set_cur_state,
 };
 
+static const struct x86_cpu_id __initconst intel_powerclamp_ids[] = {
+	{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_MWAIT },
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, intel_powerclamp_ids);
+
 static int __init powerclamp_probe(void)
 {
-	if (!boot_cpu_has(X86_FEATURE_MWAIT)) {
+
+	if (!x86_match_cpu(intel_powerclamp_ids)) {
 		pr_err("CPU does not support MWAIT");
 		return -ENODEV;
 	}
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 9a28133ac3b8..9b774f4b50c8 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -39,65 +39,54 @@ static void fname_crypt_complete(struct crypto_async_request *req, int res)
 static int fname_encrypt(struct inode *inode,
 			const struct qstr *iname, struct fscrypt_str *oname)
 {
-	u32 ciphertext_len;
 	struct skcipher_request *req = NULL;
 	DECLARE_FS_COMPLETION_RESULT(ecr);
 	struct fscrypt_info *ci = inode->i_crypt_info;
 	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
 	char iv[FS_CRYPTO_BLOCK_SIZE];
-	struct scatterlist src_sg, dst_sg;
+	struct scatterlist sg;
 	int padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK);
-	char *workbuf, buf[32], *alloc_buf = NULL;
-	unsigned lim;
+	unsigned int lim;
+	unsigned int cryptlen;
 
 	lim = inode->i_sb->s_cop->max_namelen(inode);
 	if (iname->len <= 0 || iname->len > lim)
 		return -EIO;
 
-	ciphertext_len = max(iname->len, (u32)FS_CRYPTO_BLOCK_SIZE);
-	ciphertext_len = round_up(ciphertext_len, padding);
-	ciphertext_len = min(ciphertext_len, lim);
+	/*
+	 * Copy the filename to the output buffer for encrypting in-place and
+	 * pad it with the needed number of NUL bytes.
+	 */
+	cryptlen = max_t(unsigned int, iname->len, FS_CRYPTO_BLOCK_SIZE);
+	cryptlen = round_up(cryptlen, padding);
+	cryptlen = min(cryptlen, lim);
+	memcpy(oname->name, iname->name, iname->len);
+	memset(oname->name + iname->len, 0, cryptlen - iname->len);
 
-	if (ciphertext_len <= sizeof(buf)) {
-		workbuf = buf;
-	} else {
-		alloc_buf = kmalloc(ciphertext_len, GFP_NOFS);
-		if (!alloc_buf)
-			return -ENOMEM;
-		workbuf = alloc_buf;
-	}
+	/* Initialize the IV */
+	memset(iv, 0, FS_CRYPTO_BLOCK_SIZE);
 
-	/* Allocate request */
+	/* Set up the encryption request */
 	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(KERN_ERR
-			"%s: crypto_request_alloc() failed\n", __func__);
-		kfree(alloc_buf);
+			"%s: skcipher_request_alloc() failed\n", __func__);
 		return -ENOMEM;
 	}
 	skcipher_request_set_callback(req,
 			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 			fname_crypt_complete, &ecr);
+	sg_init_one(&sg, oname->name, cryptlen);
+	skcipher_request_set_crypt(req, &sg, &sg, cryptlen, iv);
 
-	/* Copy the input */
-	memcpy(workbuf, iname->name, iname->len);
-	if (iname->len < ciphertext_len)
-		memset(workbuf + iname->len, 0, ciphertext_len - iname->len);
-
-	/* Initialize IV */
-	memset(iv, 0, FS_CRYPTO_BLOCK_SIZE);
-
-	/* Create encryption request */
-	sg_init_one(&src_sg, workbuf, ciphertext_len);
-	sg_init_one(&dst_sg, oname->name, ciphertext_len);
-	skcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
+	/* Do the encryption */
 	res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
+		/* Request is being completed asynchronously; wait for it */
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
-	kfree(alloc_buf);
 	skcipher_request_free(req);
 	if (res < 0) {
 		printk_ratelimited(KERN_ERR
@@ -105,7 +94,7 @@ static int fname_encrypt(struct inode *inode,
 		return res;
 	}
 
-	oname->len = ciphertext_len;
+	oname->len = cryptlen;
 	return 0;
 }
 
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index 82f0285f5d08..67fb6d8876d0 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -185,7 +185,7 @@ int get_crypt_info(struct inode *inode)
 	struct crypto_skcipher *ctfm;
 	const char *cipher_str;
 	int keysize;
-	u8 raw_key[FS_MAX_KEY_SIZE];
+	u8 *raw_key = NULL;
 	int res;
 
 	res = fscrypt_initialize();
@@ -238,6 +238,15 @@ retry:
 	if (res)
 		goto out;
 
+	/*
+	 * This cannot be a stack buffer because it is passed to the scatterlist
+	 * crypto API as part of key derivation.
+	 */
+	res = -ENOMEM;
+	raw_key = kmalloc(FS_MAX_KEY_SIZE, GFP_NOFS);
+	if (!raw_key)
+		goto out;
+
 	if (fscrypt_dummy_context_enabled(inode)) {
 		memset(raw_key, 0x42, FS_AES_256_XTS_KEY_SIZE);
 		goto got_key;
@@ -276,7 +285,8 @@ got_key:
 	if (res)
 		goto out;
 
-	memzero_explicit(raw_key, sizeof(raw_key));
+	kzfree(raw_key);
+	raw_key = NULL;
 	if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) != NULL) {
 		put_crypt_info(crypt_info);
 		goto retry;
@@ -287,7 +297,7 @@ out:
 	if (res == -ENOKEY)
 		res = 0;
 	put_crypt_info(crypt_info);
-	memzero_explicit(raw_key, sizeof(raw_key));
+	kzfree(raw_key);
 	return res;
 }
 
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 282a51b07c57..a8a750f59621 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -235,6 +235,7 @@ struct ext4_io_submit {
 #define	EXT4_MAX_BLOCK_SIZE		65536
 #define EXT4_MIN_BLOCK_LOG_SIZE		10
 #define EXT4_MAX_BLOCK_LOG_SIZE		16
+#define EXT4_MAX_CLUSTER_LOG_SIZE	30
 #ifdef __KERNEL__
 # define EXT4_BLOCK_SIZE(s)		((s)->s_blocksize)
 #else
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 20da99da0a34..52b0530c5d65 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3565,7 +3565,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (blocksize < EXT4_MIN_BLOCK_SIZE ||
 	    blocksize > EXT4_MAX_BLOCK_SIZE) {
 		ext4_msg(sb, KERN_ERR,
-		       "Unsupported filesystem blocksize %d", blocksize);
+		       "Unsupported filesystem blocksize %d (%d log_block_size)",
+			 blocksize, le32_to_cpu(es->s_log_block_size));
+		goto failed_mount;
+	}
+	if (le32_to_cpu(es->s_log_block_size) >
+	    (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Invalid log block size: %u",
+			 le32_to_cpu(es->s_log_block_size));
 		goto failed_mount;
 	}
 
@@ -3697,6 +3705,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				 "block size (%d)", clustersize, blocksize);
 			goto failed_mount;
 		}
+		if (le32_to_cpu(es->s_log_cluster_size) >
+		    (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
+			ext4_msg(sb, KERN_ERR,
+				 "Invalid log cluster size: %u",
+				 le32_to_cpu(es->s_log_cluster_size));
+			goto failed_mount;
+		}
 		sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) -
 			le32_to_cpu(es->s_log_block_size);
 		sbi->s_clusters_per_group =
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 6a4d0e5418a1..b3ebe512d64c 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -286,6 +286,11 @@ const struct dentry_operations fuse_dentry_operations = {
 	.d_release	= fuse_dentry_release,
 };
 
+const struct dentry_operations fuse_root_dentry_operations = {
+	.d_init		= fuse_dentry_init,
+	.d_release	= fuse_dentry_release,
+};
+
 int fuse_valid_type(int m)
 {
 	return S_ISREG(m) || S_ISDIR(m) || S_ISLNK(m) || S_ISCHR(m) ||
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index abc66a6237fd..2401c5dabb2a 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1985,6 +1985,10 @@ static int fuse_write_end(struct file *file, struct address_space *mapping,
 {
 	struct inode *inode = page->mapping->host;
 
+	/* Haven't copied anything?  Skip zeroing, size extending, dirtying. */
+	if (!copied)
+		goto unlock;
+
 	if (!PageUptodate(page)) {
 		/* Zero any unwritten bytes at the end of the page */
 		size_t endoff = (pos + copied) & ~PAGE_MASK;
@@ -1995,6 +1999,8 @@ static int fuse_write_end(struct file *file, struct address_space *mapping,
 
 	fuse_write_update_size(inode, pos + copied);
 	set_page_dirty(page);
+
+unlock:
 	unlock_page(page);
 	put_page(page);
 
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 0dfbb136e59a..91307940c8ac 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -692,6 +692,7 @@ static inline u64 get_node_id(struct inode *inode)
 extern const struct file_operations fuse_dev_operations;
 
 extern const struct dentry_operations fuse_dentry_operations;
+extern const struct dentry_operations fuse_root_dentry_operations;
 
 /**
  * Inode to nodeid comparison.
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 17141099f2e7..6fe6a88ecb4a 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1131,10 +1131,11 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 
 	err = -ENOMEM;
 	root = fuse_get_root_inode(sb, d.rootmode);
+	sb->s_d_op = &fuse_root_dentry_operations;
 	root_dentry = d_make_root(root);
 	if (!root_dentry)
 		goto err_dev_free;
-	/* only now - we want root dentry with NULL ->d_op */
+	/* Root dentry doesn't have .d_revalidate */
 	sb->s_d_op = &fuse_dentry_operations;
 
 	init_req = fuse_request_alloc(0);
diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c
index d484068ca716..38887cc5577f 100644
--- a/fs/orangefs/orangefs-debugfs.c
+++ b/fs/orangefs/orangefs-debugfs.c
@@ -114,6 +114,7 @@ static const struct seq_operations help_debug_ops = {
 };
 
 const struct file_operations debug_help_fops = {
+	.owner		= THIS_MODULE,
 	.open           = orangefs_debug_help_open,
 	.read           = seq_read,
 	.release        = seq_release,
@@ -121,6 +122,7 @@ const struct file_operations debug_help_fops = {
 };
 
 static const struct file_operations kernel_debug_fops = {
+	.owner		= THIS_MODULE,
 	.open           = orangefs_debug_open,
 	.read           = orangefs_debug_read,
 	.write		= orangefs_debug_write,
diff --git a/fs/xattr.c b/fs/xattr.c
index 3368659c471e..2d13b4e62fae 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -170,7 +170,7 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name,
 		const void *value, size_t size, int flags)
 {
 	struct inode *inode = dentry->d_inode;
-	int error = -EOPNOTSUPP;
+	int error = -EAGAIN;
 	int issec = !strncmp(name, XATTR_SECURITY_PREFIX,
 				   XATTR_SECURITY_PREFIX_LEN);
 
@@ -183,15 +183,21 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name,
 			security_inode_post_setxattr(dentry, name, value,
 						     size, flags);
 		}
-	} else if (issec) {
-		const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
-
+	} else {
 		if (unlikely(is_bad_inode(inode)))
 			return -EIO;
-		error = security_inode_setsecurity(inode, suffix, value,
-						   size, flags);
-		if (!error)
-			fsnotify_xattr(dentry);
+	}
+	if (error == -EAGAIN) {
+		error = -EOPNOTSUPP;
+
+		if (issec) {
+			const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
+
+			error = security_inode_setsecurity(inode, suffix, value,
+							   size, flags);
+			if (!error)
+				fsnotify_xattr(dentry);
+		}
 	}
 
 	return error;
diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h
index 1b949e08015c..c19700e2a2fe 100644
--- a/include/acpi/actbl.h
+++ b/include/acpi/actbl.h
@@ -230,72 +230,62 @@ struct acpi_table_facs {
 /* Fields common to all versions of the FADT */
 
 struct acpi_table_fadt {
-	struct acpi_table_header header;	/* [V1] Common ACPI table header */
-	u32 facs;		/* [V1] 32-bit physical address of FACS */
-	u32 dsdt;		/* [V1] 32-bit physical address of DSDT */
-	u8 model;		/* [V1] System Interrupt Model (ACPI 1.0) - not used in ACPI 2.0+ */
-	u8 preferred_profile;	/* [V1] Conveys preferred power management profile to OSPM. */
-	u16 sci_interrupt;	/* [V1] System vector of SCI interrupt */
-	u32 smi_command;	/* [V1] 32-bit Port address of SMI command port */
-	u8 acpi_enable;		/* [V1] Value to write to SMI_CMD to enable ACPI */
-	u8 acpi_disable;	/* [V1] Value to write to SMI_CMD to disable ACPI */
-	u8 s4_bios_request;	/* [V1] Value to write to SMI_CMD to enter S4BIOS state */
-	u8 pstate_control;	/* [V1] Processor performance state control */
-	u32 pm1a_event_block;	/* [V1] 32-bit port address of Power Mgt 1a Event Reg Blk */
-	u32 pm1b_event_block;	/* [V1] 32-bit port address of Power Mgt 1b Event Reg Blk */
-	u32 pm1a_control_block;	/* [V1] 32-bit port address of Power Mgt 1a Control Reg Blk */
-	u32 pm1b_control_block;	/* [V1] 32-bit port address of Power Mgt 1b Control Reg Blk */
-	u32 pm2_control_block;	/* [V1] 32-bit port address of Power Mgt 2 Control Reg Blk */
-	u32 pm_timer_block;	/* [V1] 32-bit port address of Power Mgt Timer Ctrl Reg Blk */
-	u32 gpe0_block;		/* [V1] 32-bit port address of General Purpose Event 0 Reg Blk */
-	u32 gpe1_block;		/* [V1] 32-bit port address of General Purpose Event 1 Reg Blk */
-	u8 pm1_event_length;	/* [V1] Byte Length of ports at pm1x_event_block */
-	u8 pm1_control_length;	/* [V1] Byte Length of ports at pm1x_control_block */
-	u8 pm2_control_length;	/* [V1] Byte Length of ports at pm2_control_block */
-	u8 pm_timer_length;	/* [V1] Byte Length of ports at pm_timer_block */
-	u8 gpe0_block_length;	/* [V1] Byte Length of ports at gpe0_block */
-	u8 gpe1_block_length;	/* [V1] Byte Length of ports at gpe1_block */
-	u8 gpe1_base;		/* [V1] Offset in GPE number space where GPE1 events start */
-	u8 cst_control;		/* [V1] Support for the _CST object and C-States change notification */
-	u16 c2_latency;		/* [V1] Worst case HW latency to enter/exit C2 state */
-	u16 c3_latency;		/* [V1] Worst case HW latency to enter/exit C3 state */
-	u16 flush_size;		/* [V1] Processor memory cache line width, in bytes */
-	u16 flush_stride;	/* [V1] Number of flush strides that need to be read */
-	u8 duty_offset;		/* [V1] Processor duty cycle index in processor P_CNT reg */
-	u8 duty_width;		/* [V1] Processor duty cycle value bit width in P_CNT register */
-	u8 day_alarm;		/* [V1] Index to day-of-month alarm in RTC CMOS RAM */
-	u8 month_alarm;		/* [V1] Index to month-of-year alarm in RTC CMOS RAM */
-	u8 century;		/* [V1] Index to century in RTC CMOS RAM */
-	u16 boot_flags;		/* [V3] IA-PC Boot Architecture Flags (see below for individual flags) */
-	u8 reserved;		/* [V1] Reserved, must be zero */
-	u32 flags;		/* [V1] Miscellaneous flag bits (see below for individual flags) */
-	/* End of Version 1 FADT fields (ACPI 1.0) */
-
-	struct acpi_generic_address reset_register;	/* [V3] 64-bit address of the Reset register */
-	u8 reset_value;		/* [V3] Value to write to the reset_register port to reset the system */
-	u16 arm_boot_flags;	/* [V5] ARM-Specific Boot Flags (see below for individual flags) (ACPI 5.1) */
-	u8 minor_revision;	/* [V5] FADT Minor Revision (ACPI 5.1) */
-	u64 Xfacs;		/* [V3] 64-bit physical address of FACS */
-	u64 Xdsdt;		/* [V3] 64-bit physical address of DSDT */
-	struct acpi_generic_address xpm1a_event_block;	/* [V3] 64-bit Extended Power Mgt 1a Event Reg Blk address */
-	struct acpi_generic_address xpm1b_event_block;	/* [V3] 64-bit Extended Power Mgt 1b Event Reg Blk address */
-	struct acpi_generic_address xpm1a_control_block;	/* [V3] 64-bit Extended Power Mgt 1a Control Reg Blk address */
-	struct acpi_generic_address xpm1b_control_block;	/* [V3] 64-bit Extended Power Mgt 1b Control Reg Blk address */
-	struct acpi_generic_address xpm2_control_block;	/* [V3] 64-bit Extended Power Mgt 2 Control Reg Blk address */
-	struct acpi_generic_address xpm_timer_block;	/* [V3] 64-bit Extended Power Mgt Timer Ctrl Reg Blk address */
-	struct acpi_generic_address xgpe0_block;	/* [V3] 64-bit Extended General Purpose Event 0 Reg Blk address */
-	struct acpi_generic_address xgpe1_block;	/* [V3] 64-bit Extended General Purpose Event 1 Reg Blk address */
-	/* End of Version 3 FADT fields (ACPI 2.0) */
-
-	struct acpi_generic_address sleep_control;	/* [V4] 64-bit Sleep Control register (ACPI 5.0) */
-	/* End of Version 4 FADT fields (ACPI 3.0 and ACPI 4.0) (Field was originally reserved in ACPI 3.0) */
-
-	struct acpi_generic_address sleep_status;	/* [V5] 64-bit Sleep Status register (ACPI 5.0) */
-	/* End of Version 5 FADT fields (ACPI 5.0) */
-
-	u64 hypervisor_id;	/* [V6] Hypervisor Vendor ID (ACPI 6.0) */
-	/* End of Version 6 FADT fields (ACPI 6.0) */
-
+	struct acpi_table_header header;	/* Common ACPI table header */
+	u32 facs;		/* 32-bit physical address of FACS */
+	u32 dsdt;		/* 32-bit physical address of DSDT */
+	u8 model;		/* System Interrupt Model (ACPI 1.0) - not used in ACPI 2.0+ */
+	u8 preferred_profile;	/* Conveys preferred power management profile to OSPM. */
+	u16 sci_interrupt;	/* System vector of SCI interrupt */
+	u32 smi_command;	/* 32-bit Port address of SMI command port */
+	u8 acpi_enable;		/* Value to write to SMI_CMD to enable ACPI */
+	u8 acpi_disable;	/* Value to write to SMI_CMD to disable ACPI */
+	u8 s4_bios_request;	/* Value to write to SMI_CMD to enter S4BIOS state */
+	u8 pstate_control;	/* Processor performance state control */
+	u32 pm1a_event_block;	/* 32-bit port address of Power Mgt 1a Event Reg Blk */
+	u32 pm1b_event_block;	/* 32-bit port address of Power Mgt 1b Event Reg Blk */
+	u32 pm1a_control_block;	/* 32-bit port address of Power Mgt 1a Control Reg Blk */
+	u32 pm1b_control_block;	/* 32-bit port address of Power Mgt 1b Control Reg Blk */
+	u32 pm2_control_block;	/* 32-bit port address of Power Mgt 2 Control Reg Blk */
+	u32 pm_timer_block;	/* 32-bit port address of Power Mgt Timer Ctrl Reg Blk */
+	u32 gpe0_block;		/* 32-bit port address of General Purpose Event 0 Reg Blk */
+	u32 gpe1_block;		/* 32-bit port address of General Purpose Event 1 Reg Blk */
+	u8 pm1_event_length;	/* Byte Length of ports at pm1x_event_block */
+	u8 pm1_control_length;	/* Byte Length of ports at pm1x_control_block */
+	u8 pm2_control_length;	/* Byte Length of ports at pm2_control_block */
+	u8 pm_timer_length;	/* Byte Length of ports at pm_timer_block */
+	u8 gpe0_block_length;	/* Byte Length of ports at gpe0_block */
+	u8 gpe1_block_length;	/* Byte Length of ports at gpe1_block */
+	u8 gpe1_base;		/* Offset in GPE number space where GPE1 events start */
+	u8 cst_control;		/* Support for the _CST object and C-States change notification */
+	u16 c2_latency;		/* Worst case HW latency to enter/exit C2 state */
+	u16 c3_latency;		/* Worst case HW latency to enter/exit C3 state */
+	u16 flush_size;		/* Processor memory cache line width, in bytes */
+	u16 flush_stride;	/* Number of flush strides that need to be read */
+	u8 duty_offset;		/* Processor duty cycle index in processor P_CNT reg */
+	u8 duty_width;		/* Processor duty cycle value bit width in P_CNT register */
+	u8 day_alarm;		/* Index to day-of-month alarm in RTC CMOS RAM */
+	u8 month_alarm;		/* Index to month-of-year alarm in RTC CMOS RAM */
+	u8 century;		/* Index to century in RTC CMOS RAM */
+	u16 boot_flags;		/* IA-PC Boot Architecture Flags (see below for individual flags) */
+	u8 reserved;		/* Reserved, must be zero */
+	u32 flags;		/* Miscellaneous flag bits (see below for individual flags) */
+	struct acpi_generic_address reset_register;	/* 64-bit address of the Reset register */
+	u8 reset_value;		/* Value to write to the reset_register port to reset the system */
+	u16 arm_boot_flags;	/* ARM-Specific Boot Flags (see below for individual flags) (ACPI 5.1) */
+	u8 minor_revision;	/* FADT Minor Revision (ACPI 5.1) */
+	u64 Xfacs;		/* 64-bit physical address of FACS */
+	u64 Xdsdt;		/* 64-bit physical address of DSDT */
+	struct acpi_generic_address xpm1a_event_block;	/* 64-bit Extended Power Mgt 1a Event Reg Blk address */
+	struct acpi_generic_address xpm1b_event_block;	/* 64-bit Extended Power Mgt 1b Event Reg Blk address */
+	struct acpi_generic_address xpm1a_control_block;	/* 64-bit Extended Power Mgt 1a Control Reg Blk address */
+	struct acpi_generic_address xpm1b_control_block;	/* 64-bit Extended Power Mgt 1b Control Reg Blk address */
+	struct acpi_generic_address xpm2_control_block;	/* 64-bit Extended Power Mgt 2 Control Reg Blk address */
+	struct acpi_generic_address xpm_timer_block;	/* 64-bit Extended Power Mgt Timer Ctrl Reg Blk address */
+	struct acpi_generic_address xgpe0_block;	/* 64-bit Extended General Purpose Event 0 Reg Blk address */
+	struct acpi_generic_address xgpe1_block;	/* 64-bit Extended General Purpose Event 1 Reg Blk address */
+	struct acpi_generic_address sleep_control;	/* 64-bit Sleep Control register (ACPI 5.0) */
+	struct acpi_generic_address sleep_status;	/* 64-bit Sleep Status register (ACPI 5.0) */
+	u64 hypervisor_id;	/* Hypervisor Vendor ID (ACPI 6.0) */
 };
 
 /* Masks for FADT IA-PC Boot Architecture Flags (boot_flags) [Vx]=Introduced in this FADT revision */
@@ -311,8 +301,8 @@ struct acpi_table_fadt {
 
 /* Masks for FADT ARM Boot Architecture Flags (arm_boot_flags) ACPI 5.1 */
 
-#define ACPI_FADT_PSCI_COMPLIANT    (1)	/* 00: [V5] PSCI 0.2+ is implemented */
-#define ACPI_FADT_PSCI_USE_HVC      (1<<1)	/* 01: [V5] HVC must be used instead of SMC as the PSCI conduit */
+#define ACPI_FADT_PSCI_COMPLIANT    (1)	/* 00: [V5+] PSCI 0.2+ is implemented */
+#define ACPI_FADT_PSCI_USE_HVC      (1<<1)	/* 01: [V5+] HVC must be used instead of SMC as the PSCI conduit */
 
 /* Masks for FADT flags */
 
@@ -409,34 +399,20 @@ struct acpi_table_desc {
  * match the expected length. In other words, the length of the
  * FADT is the bottom line as to what the version really is.
  *
- * NOTE: There is no officialy released V2 of the FADT. This
- * version was used only for prototyping and testing during the
- * 32-bit to 64-bit transition. V3 was the first official 64-bit
- * version of the FADT.
- *
- * Update this list of defines when a new version of the FADT is
- * added to the ACPI specification. Note that the FADT version is
- * only incremented when new fields are appended to the existing
- * version. Therefore, the FADT version is competely independent
- * from the version of the ACPI specification where it is
- * defined.
- *
- * For reference, the various FADT lengths are as follows:
- *     FADT V1 size: 0x074      ACPI 1.0
- *     FADT V3 size: 0x0F4      ACPI 2.0
- *     FADT V4 size: 0x100      ACPI 3.0 and ACPI 4.0
- *     FADT V5 size: 0x10C      ACPI 5.0
- *     FADT V6 size: 0x114      ACPI 6.0
+ * For reference, the values below are as follows:
+ *     FADT V1 size: 0x074
+ *     FADT V2 size: 0x084
+ *     FADT V3 size: 0x0F4
+ *     FADT V4 size: 0x0F4
+ *     FADT V5 size: 0x10C
+ *     FADT V6 size: 0x114
  */
-#define ACPI_FADT_V1_SIZE       (u32) (ACPI_FADT_OFFSET (flags) + 4)	/* ACPI 1.0 */
-#define ACPI_FADT_V3_SIZE       (u32) (ACPI_FADT_OFFSET (sleep_control))	/* ACPI 2.0 */
-#define ACPI_FADT_V4_SIZE       (u32) (ACPI_FADT_OFFSET (sleep_status))	/* ACPI 3.0 and ACPI 4.0 */
-#define ACPI_FADT_V5_SIZE       (u32) (ACPI_FADT_OFFSET (hypervisor_id))	/* ACPI 5.0 */
-#define ACPI_FADT_V6_SIZE       (u32) (sizeof (struct acpi_table_fadt))	/* ACPI 6.0 */
-
-/* Update these when new FADT versions are added */
+#define ACPI_FADT_V1_SIZE       (u32) (ACPI_FADT_OFFSET (flags) + 4)
+#define ACPI_FADT_V2_SIZE       (u32) (ACPI_FADT_OFFSET (minor_revision) + 1)
+#define ACPI_FADT_V3_SIZE       (u32) (ACPI_FADT_OFFSET (sleep_control))
+#define ACPI_FADT_V5_SIZE       (u32) (ACPI_FADT_OFFSET (hypervisor_id))
+#define ACPI_FADT_V6_SIZE       (u32) (sizeof (struct acpi_table_fadt))
 
-#define ACPI_FADT_MAX_VERSION   6
 #define ACPI_FADT_CONFORMANCE   "ACPI 6.1 (FADT version 6)"
 
 #endif				/* __ACTBL_H__ */
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index a5d98d171866..e861a24f06f2 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -191,6 +191,9 @@
 #ifndef __init
 #define __init
 #endif
+#ifndef __iomem
+#define __iomem
+#endif
 
 /* Host-dependent types and defines for user-space ACPICA */
 
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 7035b997aaa5..6aaf425cebc3 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -14,7 +14,7 @@
   * are obviously wrong for any sort of memory access.
   */
 #define BPF_REGISTER_MAX_RANGE (1024 * 1024 * 1024)
-#define BPF_REGISTER_MIN_RANGE -(1024 * 1024 * 1024)
+#define BPF_REGISTER_MIN_RANGE -1
 
 struct bpf_reg_state {
 	enum bpf_reg_type type;
@@ -22,7 +22,8 @@ struct bpf_reg_state {
 	 * Used to determine if any memory access using this register will
 	 * result in a bad access.
 	 */
-	u64 min_value, max_value;
+	s64 min_value;
+	u64 max_value;
 	union {
 		/* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */
 		s64 imm;
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 9b9f65d99873..e35e6de633b9 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -22,7 +22,7 @@ extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned char *vec);
 extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 			 unsigned long new_addr, unsigned long old_end,
-			 pmd_t *old_pmd, pmd_t *new_pmd);
+			 pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush);
 extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, pgprot_t newprot,
 			int prot_numa);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index fe3ce46cfd03..19abba04ceca 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2594,6 +2594,7 @@ extern void sched_autogroup_create_attach(struct task_struct *p);
 extern void sched_autogroup_detach(struct task_struct *p);
 extern void sched_autogroup_fork(struct signal_struct *sig);
 extern void sched_autogroup_exit(struct signal_struct *sig);
+extern void sched_autogroup_exit_task(struct task_struct *p);
 #ifdef CONFIG_PROC_FS
 extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m);
 extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice);
@@ -2603,6 +2604,7 @@ static inline void sched_autogroup_create_attach(struct task_struct *p) { }
 static inline void sched_autogroup_detach(struct task_struct *p) { }
 static inline void sched_autogroup_fork(struct signal_struct *sig) { }
 static inline void sched_autogroup_exit(struct signal_struct *sig) { }
+static inline void sched_autogroup_exit_task(struct task_struct *p) { }
 #endif
 
 extern int yield_to(struct task_struct *p, bool preempt);
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index ab02a457da1f..e5d193440374 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -25,6 +25,7 @@ struct svc_xprt_ops {
 	void		(*xpo_detach)(struct svc_xprt *);
 	void		(*xpo_free)(struct svc_xprt *);
 	int		(*xpo_secure_port)(struct svc_rqst *);
+	void		(*xpo_kill_temp_xprt)(struct svc_xprt *);
 };
 
 struct svc_xprt_class {
diff --git a/include/net/gro_cells.h b/include/net/gro_cells.h
index d15214d673b2..2a1abbf8da74 100644
--- a/include/net/gro_cells.h
+++ b/include/net/gro_cells.h
@@ -68,6 +68,9 @@ static inline int gro_cells_init(struct gro_cells *gcells, struct net_device *de
 		struct gro_cell *cell = per_cpu_ptr(gcells->cells, i);
 
 		__skb_queue_head_init(&cell->napi_skbs);
+
+		set_bit(NAPI_STATE_NO_BUSY_POLL, &cell->napi.state);
+
 		netif_napi_add(dev, &cell->napi, gro_cell_poll, 64);
 		napi_enable(&cell->napi);
 	}
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index b9314b48e39f..f390c3bb05c5 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -243,6 +243,7 @@ int fib_table_dump(struct fib_table *table, struct sk_buff *skb,
 		   struct netlink_callback *cb);
 int fib_table_flush(struct net *net, struct fib_table *table);
 struct fib_table *fib_trie_unmerge(struct fib_table *main_tb);
+void fib_table_flush_external(struct fib_table *table);
 void fib_free_table(struct fib_table *tb);
 
 #ifndef CONFIG_IP_MULTIPLE_TABLES
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index fc4f757107df..0940598c002f 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -170,7 +170,7 @@ static inline struct net *copy_net_ns(unsigned long flags,
 extern struct list_head net_namespace_list;
 
 struct net *get_net_ns_by_pid(pid_t pid);
-struct net *get_net_ns_by_fd(int pid);
+struct net *get_net_ns_by_fd(int fd);
 
 #ifdef CONFIG_SYSCTL
 void ipx_register_sysctl(void);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 300ef255d1e0..4ee67cb99143 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -972,12 +972,19 @@ struct kvm_irqfd {
 	__u8  pad[16];
 };
 
+/* For KVM_CAP_ADJUST_CLOCK */
+
+/* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags.  */
+#define KVM_CLOCK_TSC_STABLE		2
+
 struct kvm_clock_data {
 	__u64 clock;
 	__u32 flags;
 	__u32 pad[9];
 };
 
+/* For KVM_CAP_SW_TLB */
+
 #define KVM_MMU_FSL_BOOKE_NOHV		0
 #define KVM_MMU_FSL_BOOKE_HV		1
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 99a7e5b388f2..6a936159c6e0 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -216,8 +216,8 @@ static void print_verifier_state(struct bpf_verifier_state *state)
 				reg->map_ptr->key_size,
 				reg->map_ptr->value_size);
 		if (reg->min_value != BPF_REGISTER_MIN_RANGE)
-			verbose(",min_value=%llu",
-				(unsigned long long)reg->min_value);
+			verbose(",min_value=%lld",
+				(long long)reg->min_value);
 		if (reg->max_value != BPF_REGISTER_MAX_RANGE)
 			verbose(",max_value=%llu",
 				(unsigned long long)reg->max_value);
@@ -758,7 +758,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
 			 * index'es we need to make sure that whatever we use
 			 * will have a set floor within our range.
 			 */
-			if ((s64)reg->min_value < 0) {
+			if (reg->min_value < 0) {
 				verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
 					regno);
 				return -EACCES;
@@ -1468,7 +1468,8 @@ static void check_reg_overflow(struct bpf_reg_state *reg)
 {
 	if (reg->max_value > BPF_REGISTER_MAX_RANGE)
 		reg->max_value = BPF_REGISTER_MAX_RANGE;
-	if ((s64)reg->min_value < BPF_REGISTER_MIN_RANGE)
+	if (reg->min_value < BPF_REGISTER_MIN_RANGE ||
+	    reg->min_value > BPF_REGISTER_MAX_RANGE)
 		reg->min_value = BPF_REGISTER_MIN_RANGE;
 }
 
@@ -1476,7 +1477,8 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 				    struct bpf_insn *insn)
 {
 	struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg;
-	u64 min_val = BPF_REGISTER_MIN_RANGE, max_val = BPF_REGISTER_MAX_RANGE;
+	s64 min_val = BPF_REGISTER_MIN_RANGE;
+	u64 max_val = BPF_REGISTER_MAX_RANGE;
 	bool min_set = false, max_set = false;
 	u8 opcode = BPF_OP(insn->code);
 
@@ -1512,22 +1514,43 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		return;
 	}
 
+	/* If one of our values was at the end of our ranges then we can't just
+	 * do our normal operations to the register, we need to set the values
+	 * to the min/max since they are undefined.
+	 */
+	if (min_val == BPF_REGISTER_MIN_RANGE)
+		dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
+	if (max_val == BPF_REGISTER_MAX_RANGE)
+		dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+
 	switch (opcode) {
 	case BPF_ADD:
-		dst_reg->min_value += min_val;
-		dst_reg->max_value += max_val;
+		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
+			dst_reg->min_value += min_val;
+		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
+			dst_reg->max_value += max_val;
 		break;
 	case BPF_SUB:
-		dst_reg->min_value -= min_val;
-		dst_reg->max_value -= max_val;
+		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
+			dst_reg->min_value -= min_val;
+		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
+			dst_reg->max_value -= max_val;
 		break;
 	case BPF_MUL:
-		dst_reg->min_value *= min_val;
-		dst_reg->max_value *= max_val;
+		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
+			dst_reg->min_value *= min_val;
+		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
+			dst_reg->max_value *= max_val;
 		break;
 	case BPF_AND:
-		/* & is special since it could end up with 0 bits set. */
-		dst_reg->min_value &= min_val;
+		/* Disallow AND'ing of negative numbers, ain't nobody got time
+		 * for that.  Otherwise the minimum is 0 and the max is the max
+		 * value we could AND against.
+		 */
+		if (min_val < 0)
+			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
+		else
+			dst_reg->min_value = 0;
 		dst_reg->max_value = max_val;
 		break;
 	case BPF_LSH:
@@ -1537,24 +1560,25 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		 */
 		if (min_val > ilog2(BPF_REGISTER_MAX_RANGE))
 			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
-		else
+		else if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
 			dst_reg->min_value <<= min_val;
 
 		if (max_val > ilog2(BPF_REGISTER_MAX_RANGE))
 			dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
-		else
+		else if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
 			dst_reg->max_value <<= max_val;
 		break;
 	case BPF_RSH:
-		dst_reg->min_value >>= min_val;
-		dst_reg->max_value >>= max_val;
-		break;
-	case BPF_MOD:
-		/* % is special since it is an unsigned modulus, so the floor
-		 * will always be 0.
+		/* RSH by a negative number is undefined, and the BPF_RSH is an
+		 * unsigned shift, so make the appropriate casts.
 		 */
-		dst_reg->min_value = 0;
-		dst_reg->max_value = max_val - 1;
+		if (min_val < 0 || dst_reg->min_value < 0)
+			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
+		else
+			dst_reg->min_value =
+				(u64)(dst_reg->min_value) >> min_val;
+		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
+			dst_reg->max_value >>= max_val;
 		break;
 	default:
 		reset_reg_range_values(regs, insn->dst_reg);
diff --git a/kernel/exit.c b/kernel/exit.c
index 9d68c45ebbe3..3076f3089919 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -836,6 +836,7 @@ void __noreturn do_exit(long code)
 	 */
 	perf_event_exit_task(tsk);
 
+	sched_autogroup_exit_task(tsk);
 	cgroup_exit(tsk);
 
 	/*
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index 51c4b24b6328..c2b88490d857 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -46,6 +46,14 @@ enum {
 		(LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ)
 
 /*
+ * CONFIG_PROVE_LOCKING_SMALL is defined for sparc. Sparc requires .text,
+ * .data and .bss to fit in required 32MB limit for the kernel. With
+ * PROVE_LOCKING we could go over this limit and cause system boot-up problems.
+ * So, reduce the static allocations for lockdeps related structures so that
+ * everything fits in current required size limit.
+ */
+#ifdef CONFIG_PROVE_LOCKING_SMALL
+/*
  * MAX_LOCKDEP_ENTRIES is the maximum number of lock dependencies
  * we track.
  *
@@ -54,18 +62,24 @@ enum {
  * table (if it's not there yet), and we check it for lock order
  * conflicts and deadlocks.
  */
+#define MAX_LOCKDEP_ENTRIES	16384UL
+#define MAX_LOCKDEP_CHAINS_BITS	15
+#define MAX_STACK_TRACE_ENTRIES	262144UL
+#else
 #define MAX_LOCKDEP_ENTRIES	32768UL
 
 #define MAX_LOCKDEP_CHAINS_BITS	16
-#define MAX_LOCKDEP_CHAINS	(1UL << MAX_LOCKDEP_CHAINS_BITS)
-
-#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5)
 
 /*
  * Stack-trace: tightly packed array of stack backtrace
  * addresses. Protected by the hash_lock.
  */
 #define MAX_STACK_TRACE_ENTRIES	524288UL
+#endif
+
+#define MAX_LOCKDEP_CHAINS	(1UL << MAX_LOCKDEP_CHAINS_BITS)
+
+#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5)
 
 extern struct list_head all_lock_classes;
 extern struct lock_chain lock_chains[];
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index a5d966cb8891..f1c8fd566246 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -111,10 +111,13 @@ bool task_wants_autogroup(struct task_struct *p, struct task_group *tg)
 {
 	if (tg != &root_task_group)
 		return false;
-
 	/*
-	 * We can only assume the task group can't go away on us if
-	 * autogroup_move_group() can see us on ->thread_group list.
+	 * If we race with autogroup_move_group() the caller can use the old
+	 * value of signal->autogroup but in this case sched_move_task() will
+	 * be called again before autogroup_kref_put().
+	 *
+	 * However, there is no way sched_autogroup_exit_task() could tell us
+	 * to avoid autogroup->tg, so we abuse PF_EXITING flag for this case.
 	 */
 	if (p->flags & PF_EXITING)
 		return false;
@@ -122,6 +125,16 @@ bool task_wants_autogroup(struct task_struct *p, struct task_group *tg)
 	return true;
 }
 
+void sched_autogroup_exit_task(struct task_struct *p)
+{
+	/*
+	 * We are going to call exit_notify() and autogroup_move_group() can't
+	 * see this thread after that: we can no longer use signal->autogroup.
+	 * See the PF_EXITING check in task_wants_autogroup().
+	 */
+	sched_move_task(p);
+}
+
 static void
 autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 {
@@ -138,13 +151,20 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 	}
 
 	p->signal->autogroup = autogroup_kref_get(ag);
-
-	if (!READ_ONCE(sysctl_sched_autogroup_enabled))
-		goto out;
-
+	/*
+	 * We can't avoid sched_move_task() after we changed signal->autogroup,
+	 * this process can already run with task_group() == prev->tg or we can
+	 * race with cgroup code which can read autogroup = prev under rq->lock.
+	 * In the latter case for_each_thread() can not miss a migrating thread,
+	 * cpu_cgroup_attach() must not be possible after cgroup_exit() and it
+	 * can't be removed from thread list, we hold ->siglock.
+	 *
+	 * If an exiting thread was already removed from thread list we rely on
+	 * sched_autogroup_exit_task().
+	 */
 	for_each_thread(p, t)
 		sched_move_task(t);
-out:
+
 	unlock_task_sighand(p, &flags);
 	autogroup_kref_put(prev);
 }
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index b01e547d4d04..a6c8db1d62f6 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1085,6 +1085,9 @@ config PROVE_LOCKING
 
 	 For more details, see Documentation/locking/lockdep-design.txt.
 
+config PROVE_LOCKING_SMALL
+	bool
+
 config LOCKDEP
 	bool
 	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index f0c7f1481bae..f2bd21b93dfc 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -683,10 +683,11 @@ static void pipe_advance(struct iov_iter *i, size_t size)
 	struct pipe_inode_info *pipe = i->pipe;
 	struct pipe_buffer *buf;
 	int idx = i->idx;
-	size_t off = i->iov_offset;
+	size_t off = i->iov_offset, orig_sz;
 	
 	if (unlikely(i->count < size))
 		size = i->count;
+	orig_sz = size;
 
 	if (size) {
 		if (off) /* make it relative to the beginning of buffer */
@@ -713,6 +714,7 @@ static void pipe_advance(struct iov_iter *i, size_t size)
 			pipe->nrbufs--;
 		}
 	}
+	i->count -= orig_sz;
 }
 
 void iov_iter_advance(struct iov_iter *i, size_t size)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index cdcd25cb30fe..eff3de359d50 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1426,11 +1426,12 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 
 bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		  unsigned long new_addr, unsigned long old_end,
-		  pmd_t *old_pmd, pmd_t *new_pmd)
+		  pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush)
 {
 	spinlock_t *old_ptl, *new_ptl;
 	pmd_t pmd;
 	struct mm_struct *mm = vma->vm_mm;
+	bool force_flush = false;
 
 	if ((old_addr & ~HPAGE_PMD_MASK) ||
 	    (new_addr & ~HPAGE_PMD_MASK) ||
@@ -1455,6 +1456,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		new_ptl = pmd_lockptr(mm, new_pmd);
 		if (new_ptl != old_ptl)
 			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
+		if (pmd_present(*old_pmd) && pmd_dirty(*old_pmd))
+			force_flush = true;
 		pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd);
 		VM_BUG_ON(!pmd_none(*new_pmd));
 
@@ -1467,6 +1470,10 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
 		if (new_ptl != old_ptl)
 			spin_unlock(new_ptl);
+		if (force_flush)
+			flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
+		else
+			*need_flush = true;
 		spin_unlock(old_ptl);
 		return true;
 	}
diff --git a/mm/mremap.c b/mm/mremap.c
index da22ad2a5678..6ccecc03f56a 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -104,11 +104,13 @@ static pte_t move_soft_dirty_pte(pte_t pte)
 static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 		unsigned long old_addr, unsigned long old_end,
 		struct vm_area_struct *new_vma, pmd_t *new_pmd,
-		unsigned long new_addr, bool need_rmap_locks)
+		unsigned long new_addr, bool need_rmap_locks, bool *need_flush)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *old_pte, *new_pte, pte;
 	spinlock_t *old_ptl, *new_ptl;
+	bool force_flush = false;
+	unsigned long len = old_end - old_addr;
 
 	/*
 	 * When need_rmap_locks is true, we take the i_mmap_rwsem and anon_vma
@@ -146,6 +148,14 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 				   new_pte++, new_addr += PAGE_SIZE) {
 		if (pte_none(*old_pte))
 			continue;
+
+		/*
+		 * We are remapping a dirty PTE, make sure to
+		 * flush TLB before we drop the PTL for the
+		 * old PTE or we may race with page_mkclean().
+		 */
+		if (pte_present(*old_pte) && pte_dirty(*old_pte))
+			force_flush = true;
 		pte = ptep_get_and_clear(mm, old_addr, old_pte);
 		pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr);
 		pte = move_soft_dirty_pte(pte);
@@ -156,6 +166,10 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	if (new_ptl != old_ptl)
 		spin_unlock(new_ptl);
 	pte_unmap(new_pte - 1);
+	if (force_flush)
+		flush_tlb_range(vma, old_end - len, old_end);
+	else
+		*need_flush = true;
 	pte_unmap_unlock(old_pte - 1, old_ptl);
 	if (need_rmap_locks)
 		drop_rmap_locks(vma);
@@ -201,13 +215,12 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 				if (need_rmap_locks)
 					take_rmap_locks(vma);
 				moved = move_huge_pmd(vma, old_addr, new_addr,
-						    old_end, old_pmd, new_pmd);
+						    old_end, old_pmd, new_pmd,
+						    &need_flush);
 				if (need_rmap_locks)
 					drop_rmap_locks(vma);
-				if (moved) {
-					need_flush = true;
+				if (moved)
 					continue;
-				}
 			}
 			split_huge_pmd(vma, old_pmd, old_addr);
 			if (pmd_trans_unstable(old_pmd))
@@ -220,11 +233,10 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 			extent = next - new_addr;
 		if (extent > LATENCY_LIMIT)
 			extent = LATENCY_LIMIT;
-		move_ptes(vma, old_pmd, old_addr, old_addr + extent,
-			  new_vma, new_pmd, new_addr, need_rmap_locks);
-		need_flush = true;
+		move_ptes(vma, old_pmd, old_addr, old_addr + extent, new_vma,
+			  new_pmd, new_addr, need_rmap_locks, &need_flush);
 	}
-	if (likely(need_flush))
+	if (need_flush)
 		flush_tlb_range(vma, old_end-len, old_addr);
 
 	mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end);
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index e034afbd1bb0..08ce36147c4c 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -652,6 +652,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface,
 			batadv_softif_destroy_sysfs(hard_iface->soft_iface);
 	}
 
+	hard_iface->soft_iface = NULL;
 	batadv_hardif_put(hard_iface);
 
 out:
diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c
index 2333777f919d..8af1611b8ab2 100644
--- a/net/batman-adv/tp_meter.c
+++ b/net/batman-adv/tp_meter.c
@@ -837,6 +837,7 @@ static int batadv_tp_send(void *arg)
 	primary_if = batadv_primary_if_get_selected(bat_priv);
 	if (unlikely(!primary_if)) {
 		err = BATADV_TP_REASON_DST_UNREACHABLE;
+		tp_vars->reason = err;
 		goto out;
 	}
 
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index f61c0e02a413..7001da910c6b 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -219,6 +219,8 @@ int peernet2id_alloc(struct net *net, struct net *peer)
 	bool alloc;
 	int id;
 
+	if (atomic_read(&net->count) == 0)
+		return NETNSA_NSID_NOT_ASSIGNED;
 	spin_lock_irqsave(&net->nsid_lock, flags);
 	alloc = atomic_read(&peer->count) == 0 ? false : true;
 	id = __peernet2id_alloc(net, peer, &alloc);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index db313ec7af32..a99917b5de33 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -840,18 +840,20 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
 	if (dev->dev.parent && dev_is_pci(dev->dev.parent) &&
 	    (ext_filter_mask & RTEXT_FILTER_VF)) {
 		int num_vfs = dev_num_vf(dev->dev.parent);
-		size_t size = nla_total_size(sizeof(struct nlattr));
-		size += nla_total_size(num_vfs * sizeof(struct nlattr));
+		size_t size = nla_total_size(0);
 		size += num_vfs *
-			(nla_total_size(sizeof(struct ifla_vf_mac)) +
-			 nla_total_size(MAX_VLAN_LIST_LEN *
-					sizeof(struct nlattr)) +
+			(nla_total_size(0) +
+			 nla_total_size(sizeof(struct ifla_vf_mac)) +
+			 nla_total_size(sizeof(struct ifla_vf_vlan)) +
+			 nla_total_size(0) + /* nest IFLA_VF_VLAN_LIST */
 			 nla_total_size(MAX_VLAN_LIST_LEN *
 					sizeof(struct ifla_vf_vlan_info)) +
 			 nla_total_size(sizeof(struct ifla_vf_spoofchk)) +
+			 nla_total_size(sizeof(struct ifla_vf_tx_rate)) +
 			 nla_total_size(sizeof(struct ifla_vf_rate)) +
 			 nla_total_size(sizeof(struct ifla_vf_link_state)) +
 			 nla_total_size(sizeof(struct ifla_vf_rss_query_en)) +
+			 nla_total_size(0) + /* nest IFLA_VF_STATS */
 			 /* IFLA_VF_STATS_RX_PACKETS */
 			 nla_total_size_64bit(sizeof(__u64)) +
 			 /* IFLA_VF_STATS_TX_PACKETS */
@@ -899,7 +901,8 @@ static size_t rtnl_port_size(const struct net_device *dev,
 
 static size_t rtnl_xdp_size(const struct net_device *dev)
 {
-	size_t xdp_size = nla_total_size(1);	/* XDP_ATTACHED */
+	size_t xdp_size = nla_total_size(0) +	/* nest IFLA_XDP */
+			  nla_total_size(1);	/* XDP_ATTACHED */
 
 	if (!dev->netdev_ops->ndo_xdp)
 		return 0;
@@ -1606,7 +1609,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 		head = &net->dev_index_head[h];
 		hlist_for_each_entry(dev, head, index_hlist) {
 			if (link_dump_filtered(dev, master_idx, kind_ops))
-				continue;
+				goto cont;
 			if (idx < s_idx)
 				goto cont;
 			err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
@@ -2849,7 +2852,10 @@ nla_put_failure:
 
 static inline size_t rtnl_fdb_nlmsg_size(void)
 {
-	return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN);
+	return NLMSG_ALIGN(sizeof(struct ndmsg)) +
+	       nla_total_size(ETH_ALEN) +	/* NDA_LLADDR */
+	       nla_total_size(sizeof(u16)) +	/* NDA_VLAN */
+	       0;
 }
 
 static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type,
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c3b80478226e..161fc0f0d752 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -151,7 +151,7 @@ static void fib_replace_table(struct net *net, struct fib_table *old,
 
 int fib_unmerge(struct net *net)
 {
-	struct fib_table *old, *new;
+	struct fib_table *old, *new, *main_table;
 
 	/* attempt to fetch local table if it has been allocated */
 	old = fib_get_table(net, RT_TABLE_LOCAL);
@@ -162,11 +162,21 @@ int fib_unmerge(struct net *net)
 	if (!new)
 		return -ENOMEM;
 
+	/* table is already unmerged */
+	if (new == old)
+		return 0;
+
 	/* replace merged table with clean table */
-	if (new != old) {
-		fib_replace_table(net, old, new);
-		fib_free_table(old);
-	}
+	fib_replace_table(net, old, new);
+	fib_free_table(old);
+
+	/* attempt to fetch main table if it has been allocated */
+	main_table = fib_get_table(net, RT_TABLE_MAIN);
+	if (!main_table)
+		return 0;
+
+	/* flush local entries from main table */
+	fib_table_flush_external(main_table);
 
 	return 0;
 }
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 4cff74d4133f..026f309c51e9 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1743,8 +1743,10 @@ struct fib_table *fib_trie_unmerge(struct fib_table *oldtb)
 				local_l = fib_find_node(lt, &local_tp, l->key);
 
 			if (fib_insert_alias(lt, local_tp, local_l, new_fa,
-					     NULL, l->key))
+					     NULL, l->key)) {
+				kmem_cache_free(fn_alias_kmem, new_fa);
 				goto out;
+			}
 		}
 
 		/* stop loop if key wrapped back to 0 */
@@ -1760,6 +1762,71 @@ out:
 	return NULL;
 }
 
+/* Caller must hold RTNL */
+void fib_table_flush_external(struct fib_table *tb)
+{
+	struct trie *t = (struct trie *)tb->tb_data;
+	struct key_vector *pn = t->kv;
+	unsigned long cindex = 1;
+	struct hlist_node *tmp;
+	struct fib_alias *fa;
+
+	/* walk trie in reverse order */
+	for (;;) {
+		unsigned char slen = 0;
+		struct key_vector *n;
+
+		if (!(cindex--)) {
+			t_key pkey = pn->key;
+
+			/* cannot resize the trie vector */
+			if (IS_TRIE(pn))
+				break;
+
+			/* resize completed node */
+			pn = resize(t, pn);
+			cindex = get_index(pkey, pn);
+
+			continue;
+		}
+
+		/* grab the next available node */
+		n = get_child(pn, cindex);
+		if (!n)
+			continue;
+
+		if (IS_TNODE(n)) {
+			/* record pn and cindex for leaf walking */
+			pn = n;
+			cindex = 1ul << n->bits;
+
+			continue;
+		}
+
+		hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) {
+			/* if alias was cloned to local then we just
+			 * need to remove the local copy from main
+			 */
+			if (tb->tb_id != fa->tb_id) {
+				hlist_del_rcu(&fa->fa_list);
+				alias_free_mem_rcu(fa);
+				continue;
+			}
+
+			/* record local slen */
+			slen = fa->fa_slen;
+		}
+
+		/* update leaf slen */
+		n->slen = slen;
+
+		if (hlist_empty(&n->leaf)) {
+			put_child_root(pn, n->key, NULL);
+			node_free(n);
+		}
+	}
+}
+
 /* Caller must hold RTNL. */
 int fib_table_flush(struct net *net, struct fib_table *tb)
 {
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 606cc3e85d2b..15db786d50ed 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -162,7 +162,7 @@ static int unsolicited_report_interval(struct in_device *in_dev)
 }
 
 static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im);
-static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr);
+static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im);
 static void igmpv3_clear_delrec(struct in_device *in_dev);
 static int sf_setstate(struct ip_mc_list *pmc);
 static void sf_markstate(struct ip_mc_list *pmc);
@@ -1130,10 +1130,15 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 	spin_unlock_bh(&in_dev->mc_tomb_lock);
 }
 
-static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr)
+/*
+ * restore ip_mc_list deleted records
+ */
+static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 {
 	struct ip_mc_list *pmc, *pmc_prev;
-	struct ip_sf_list *psf, *psf_next;
+	struct ip_sf_list *psf;
+	struct net *net = dev_net(in_dev->dev);
+	__be32 multiaddr = im->multiaddr;
 
 	spin_lock_bh(&in_dev->mc_tomb_lock);
 	pmc_prev = NULL;
@@ -1149,16 +1154,26 @@ static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr)
 			in_dev->mc_tomb = pmc->next;
 	}
 	spin_unlock_bh(&in_dev->mc_tomb_lock);
+
+	spin_lock_bh(&im->lock);
 	if (pmc) {
-		for (psf = pmc->tomb; psf; psf = psf_next) {
-			psf_next = psf->sf_next;
-			kfree(psf);
+		im->interface = pmc->interface;
+		im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+		im->sfmode = pmc->sfmode;
+		if (pmc->sfmode == MCAST_INCLUDE) {
+			im->tomb = pmc->tomb;
+			im->sources = pmc->sources;
+			for (psf = im->sources; psf; psf = psf->sf_next)
+				psf->sf_crcount = im->crcount;
 		}
 		in_dev_put(pmc->interface);
-		kfree(pmc);
 	}
+	spin_unlock_bh(&im->lock);
 }
 
+/*
+ * flush ip_mc_list deleted records
+ */
 static void igmpv3_clear_delrec(struct in_device *in_dev)
 {
 	struct ip_mc_list *pmc, *nextpmc;
@@ -1366,7 +1381,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
 	ip_mc_hash_add(in_dev, im);
 
 #ifdef CONFIG_IP_MULTICAST
-	igmpv3_del_delrec(in_dev, im->multiaddr);
+	igmpv3_del_delrec(in_dev, im);
 #endif
 	igmp_group_added(im);
 	if (!in_dev->dead)
@@ -1626,8 +1641,12 @@ void ip_mc_remap(struct in_device *in_dev)
 
 	ASSERT_RTNL();
 
-	for_each_pmc_rtnl(in_dev, pmc)
+	for_each_pmc_rtnl(in_dev, pmc) {
+#ifdef CONFIG_IP_MULTICAST
+		igmpv3_del_delrec(in_dev, pmc);
+#endif
 		igmp_group_added(pmc);
+	}
 }
 
 /* Device going down */
@@ -1648,7 +1667,6 @@ void ip_mc_down(struct in_device *in_dev)
 	in_dev->mr_gq_running = 0;
 	if (del_timer(&in_dev->mr_gq_timer))
 		__in_dev_put(in_dev);
-	igmpv3_clear_delrec(in_dev);
 #endif
 
 	ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS);
@@ -1688,8 +1706,12 @@ void ip_mc_up(struct in_device *in_dev)
 #endif
 	ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS);
 
-	for_each_pmc_rtnl(in_dev, pmc)
+	for_each_pmc_rtnl(in_dev, pmc) {
+#ifdef CONFIG_IP_MULTICAST
+		igmpv3_del_delrec(in_dev, pmc);
+#endif
 		igmp_group_added(pmc);
+	}
 }
 
 /*
@@ -1704,13 +1726,13 @@ void ip_mc_destroy_dev(struct in_device *in_dev)
 
 	/* Deactivate timers */
 	ip_mc_down(in_dev);
+#ifdef CONFIG_IP_MULTICAST
+	igmpv3_clear_delrec(in_dev);
+#endif
 
 	while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) {
 		in_dev->mc_list = i->next_rcu;
 		in_dev->mc_count--;
-
-		/* We've dropped the groups in ip_mc_down already */
-		ip_mc_clear_src(i);
 		ip_ma_put(i);
 	}
 }
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 1294af4e0127..f9038d6b109e 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -200,8 +200,10 @@ static void tcp_reinit_congestion_control(struct sock *sk,
 	icsk->icsk_ca_ops = ca;
 	icsk->icsk_ca_setsockopt = 1;
 
-	if (sk->sk_state != TCP_CLOSE)
+	if (sk->sk_state != TCP_CLOSE) {
+		memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 		tcp_init_congestion_control(sk);
+	}
 }
 
 /* Manage refcounts on socket close. */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d123d68f4d1d..0de9d5d2b9ae 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1652,10 +1652,10 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 
 	if (use_hash2) {
 		hash2_any = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum) &
-			    udp_table.mask;
-		hash2 = udp4_portaddr_hash(net, daddr, hnum) & udp_table.mask;
+			    udptable->mask;
+		hash2 = udp4_portaddr_hash(net, daddr, hnum) & udptable->mask;
 start_lookup:
-		hslot = &udp_table.hash2[hash2];
+		hslot = &udptable->hash2[hash2];
 		offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node);
 	}
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 87784560dc46..0a4759b89da2 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1034,6 +1034,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	int mtu;
 	unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen;
 	unsigned int max_headroom = psh_hlen;
+	bool use_cache = false;
 	u8 hop_limit;
 	int err = -1;
 
@@ -1066,7 +1067,15 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 
 		memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
 		neigh_release(neigh);
-	} else if (!fl6->flowi6_mark)
+	} else if (!(t->parms.flags &
+		     (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) {
+		/* enable the cache only only if the routing decision does
+		 * not depend on the current inner header value
+		 */
+		use_cache = true;
+	}
+
+	if (use_cache)
 		dst = dst_cache_get(&t->dst_cache);
 
 	if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr))
@@ -1150,7 +1159,7 @@ route_lookup:
 		if (t->encap.type != TUNNEL_ENCAP_NONE)
 			goto tx_err_dst_release;
 	} else {
-		if (!fl6->flowi6_mark && ndst)
+		if (use_cache && ndst)
 			dst_cache_set_ip6(&t->dst_cache, ndst, &fl6->saddr);
 	}
 	skb_dst_set(skb, dst);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index b2ef061e6836..e5056d4873d1 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -706,10 +706,10 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 
 	if (use_hash2) {
 		hash2_any = udp6_portaddr_hash(net, &in6addr_any, hnum) &
-			    udp_table.mask;
-		hash2 = udp6_portaddr_hash(net, daddr, hnum) & udp_table.mask;
+			    udptable->mask;
+		hash2 = udp6_portaddr_hash(net, daddr, hnum) & udptable->mask;
 start_lookup:
-		hslot = &udp_table.hash2[hash2];
+		hslot = &udptable->hash2[hash2];
 		offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node);
 	}
 
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 965f7e344cef..3dc97b4f982b 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -97,7 +97,7 @@ static int l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	unsigned int len = skb->len;
 	int ret = l2tp_xmit_skb(session, skb, session->hdr_len);
 
-	if (likely(ret == NET_XMIT_SUCCESS)) {
+	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
 		atomic_long_add(len, &priv->tx_bytes);
 		atomic_long_inc(&priv->tx_packets);
 	} else {
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index fce25afb652a..982f6c44ea01 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -251,8 +251,6 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	int ret;
 	int chk_addr_ret;
 
-	if (!sock_flag(sk, SOCK_ZAPPED))
-		return -EINVAL;
 	if (addr_len < sizeof(struct sockaddr_l2tpip))
 		return -EINVAL;
 	if (addr->l2tp_family != AF_INET)
@@ -267,6 +265,9 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	read_unlock_bh(&l2tp_ip_lock);
 
 	lock_sock(sk);
+	if (!sock_flag(sk, SOCK_ZAPPED))
+		goto out;
+
 	if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_l2tpip))
 		goto out;
 
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index ad3468c32b53..9978d01ba0ba 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -269,8 +269,6 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	int addr_type;
 	int err;
 
-	if (!sock_flag(sk, SOCK_ZAPPED))
-		return -EINVAL;
 	if (addr->l2tp_family != AF_INET6)
 		return -EINVAL;
 	if (addr_len < sizeof(*addr))
@@ -296,6 +294,9 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	lock_sock(sk);
 
 	err = -EINVAL;
+	if (!sock_flag(sk, SOCK_ZAPPED))
+		goto out_unlock;
+
 	if (sk->sk_state != TCP_CLOSE)
 		goto out_unlock;
 
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 78e9ecbc96e6..8e05032689f0 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -688,7 +688,7 @@ static void __sta_info_recalc_tim(struct sta_info *sta, bool ignore_pending)
 	}
 
 	/* No need to do anything if the driver does all */
-	if (!local->ops->set_tim)
+	if (ieee80211_hw_check(&local->hw, AP_LINK_PS))
 		return;
 
 	if (sta->dead)
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 1c56abc49627..bd5f4be89435 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1501,7 +1501,6 @@ static bool ieee80211_queue_skb(struct ieee80211_local *local,
 				struct sta_info *sta,
 				struct sk_buff *skb)
 {
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct fq *fq = &local->fq;
 	struct ieee80211_vif *vif;
 	struct txq_info *txqi;
@@ -1526,8 +1525,6 @@ static bool ieee80211_queue_skb(struct ieee80211_local *local,
 	if (!txqi)
 		return false;
 
-	info->control.vif = vif;
-
 	spin_lock_bh(&fq->lock);
 	ieee80211_txq_enqueue(local, txqi, skb);
 	spin_unlock_bh(&fq->lock);
@@ -3213,7 +3210,6 @@ static void ieee80211_xmit_fast_finish(struct ieee80211_sub_if_data *sdata,
 
 	if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) {
 		tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK;
-		*ieee80211_get_qos_ctl(hdr) = tid;
 		hdr->seq_ctrl = ieee80211_tx_next_seq(sta, tid);
 	} else {
 		info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ;
@@ -3338,6 +3334,11 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata,
 		      (tid_tx ? IEEE80211_TX_CTL_AMPDU : 0);
 	info->control.flags = IEEE80211_TX_CTRL_FAST_XMIT;
 
+	if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) {
+		tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK;
+		*ieee80211_get_qos_ctl(hdr) = tid;
+	}
+
 	__skb_queue_head_init(&tx.skbs);
 
 	tx.flags = IEEE80211_TX_UNICAST;
@@ -3426,6 +3427,11 @@ begin:
 		goto begin;
 	}
 
+	if (test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags))
+		info->flags |= IEEE80211_TX_CTL_AMPDU;
+	else
+		info->flags &= ~IEEE80211_TX_CTL_AMPDU;
+
 	if (info->control.flags & IEEE80211_TX_CTRL_FAST_XMIT) {
 		struct sta_info *sta = container_of(txq->sta, struct sta_info,
 						    sta);
diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c
index ee715764a828..6832bf6ab69f 100644
--- a/net/mac80211/vht.c
+++ b/net/mac80211/vht.c
@@ -270,6 +270,22 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
 		vht_cap->vht_mcs.tx_mcs_map |= cpu_to_le16(peer_tx << i * 2);
 	}
 
+	/*
+	 * This is a workaround for VHT-enabled STAs which break the spec
+	 * and have the VHT-MCS Rx map filled in with value 3 for all eight
+	 * spacial streams, an example is AR9462.
+	 *
+	 * As per spec, in section 22.1.1 Introduction to the VHT PHY
+	 * A VHT STA shall support at least single spactial stream VHT-MCSs
+	 * 0 to 7 (transmit and receive) in all supported channel widths.
+	 */
+	if (vht_cap->vht_mcs.rx_mcs_map == cpu_to_le16(0xFFFF)) {
+		vht_cap->vht_supported = false;
+		sdata_info(sdata, "Ignoring VHT IE from %pM due to invalid rx_mcs_map\n",
+			   sta->addr);
+		return;
+	}
+
 	/* finally set up the bandwidth */
 	switch (vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) {
 	case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ:
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 2b2a7974e4bb..8e93d4afe5ea 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -112,7 +112,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
 
 	for (it_chain = chain; (tp = rtnl_dereference(*it_chain)) != NULL;
 	     it_chain = &tp->next)
-		tfilter_notify(net, oskb, n, tp, 0, event, false);
+		tfilter_notify(net, oskb, n, tp, n->nlmsg_flags, event, false);
 }
 
 /* Select new prio value from the range, managed by kernel. */
@@ -430,7 +430,8 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb,
 	if (!skb)
 		return -ENOBUFS;
 
-	if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq, 0, event) <= 0) {
+	if (tcf_fill_node(net, skb, tp, fh, portid, n->nlmsg_seq,
+			  n->nlmsg_flags, event) <= 0) {
 		kfree_skb(skb);
 		return -EINVAL;
 	}
diff --git a/net/socket.c b/net/socket.c
index 272518b087c8..73dc69f9681e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -341,8 +341,23 @@ static const struct xattr_handler sockfs_xattr_handler = {
 	.get = sockfs_xattr_get,
 };
 
+static int sockfs_security_xattr_set(const struct xattr_handler *handler,
+				     struct dentry *dentry, struct inode *inode,
+				     const char *suffix, const void *value,
+				     size_t size, int flags)
+{
+	/* Handled by LSM. */
+	return -EAGAIN;
+}
+
+static const struct xattr_handler sockfs_security_xattr_handler = {
+	.prefix = XATTR_SECURITY_PREFIX,
+	.set = sockfs_security_xattr_set,
+};
+
 static const struct xattr_handler *sockfs_xattr_handlers[] = {
 	&sockfs_xattr_handler,
+	&sockfs_security_xattr_handler,
 	NULL
 };
 
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index c3f652395a80..3bc1d61694cb 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -1002,14 +1002,8 @@ static void svc_age_temp_xprts(unsigned long closure)
 void svc_age_temp_xprts_now(struct svc_serv *serv, struct sockaddr *server_addr)
 {
 	struct svc_xprt *xprt;
-	struct svc_sock *svsk;
-	struct socket *sock;
 	struct list_head *le, *next;
 	LIST_HEAD(to_be_closed);
-	struct linger no_linger = {
-		.l_onoff = 1,
-		.l_linger = 0,
-	};
 
 	spin_lock_bh(&serv->sv_lock);
 	list_for_each_safe(le, next, &serv->sv_tempsocks) {
@@ -1027,10 +1021,7 @@ void svc_age_temp_xprts_now(struct svc_serv *serv, struct sockaddr *server_addr)
 		list_del_init(le);
 		xprt = list_entry(le, struct svc_xprt, xpt_list);
 		dprintk("svc_age_temp_xprts_now: closing %p\n", xprt);
-		svsk = container_of(xprt, struct svc_sock, sk_xprt);
-		sock = svsk->sk_sock;
-		kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER,
-				  (char *)&no_linger, sizeof(no_linger));
+		xprt->xpt_ops->xpo_kill_temp_xprt(xprt);
 		svc_close_xprt(xprt);
 	}
 }
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 57625f64efd5..a4bc98265d88 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -438,6 +438,21 @@ static int svc_tcp_has_wspace(struct svc_xprt *xprt)
 	return !test_bit(SOCK_NOSPACE, &svsk->sk_sock->flags);
 }
 
+static void svc_tcp_kill_temp_xprt(struct svc_xprt *xprt)
+{
+	struct svc_sock *svsk;
+	struct socket *sock;
+	struct linger no_linger = {
+		.l_onoff = 1,
+		.l_linger = 0,
+	};
+
+	svsk = container_of(xprt, struct svc_sock, sk_xprt);
+	sock = svsk->sk_sock;
+	kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER,
+			  (char *)&no_linger, sizeof(no_linger));
+}
+
 /*
  * See net/ipv6/ip_sockglue.c : ip_cmsg_recv_pktinfo
  */
@@ -648,6 +663,10 @@ static struct svc_xprt *svc_udp_accept(struct svc_xprt *xprt)
 	return NULL;
 }
 
+static void svc_udp_kill_temp_xprt(struct svc_xprt *xprt)
+{
+}
+
 static struct svc_xprt *svc_udp_create(struct svc_serv *serv,
 				       struct net *net,
 				       struct sockaddr *sa, int salen,
@@ -667,6 +686,7 @@ static struct svc_xprt_ops svc_udp_ops = {
 	.xpo_has_wspace = svc_udp_has_wspace,
 	.xpo_accept = svc_udp_accept,
 	.xpo_secure_port = svc_sock_secure_port,
+	.xpo_kill_temp_xprt = svc_udp_kill_temp_xprt,
 };
 
 static struct svc_xprt_class svc_udp_class = {
@@ -1242,6 +1262,7 @@ static struct svc_xprt_ops svc_tcp_ops = {
 	.xpo_has_wspace = svc_tcp_has_wspace,
 	.xpo_accept = svc_tcp_accept,
 	.xpo_secure_port = svc_sock_secure_port,
+	.xpo_kill_temp_xprt = svc_tcp_kill_temp_xprt,
 };
 
 static struct svc_xprt_class svc_tcp_class = {
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 6864fb967038..1334de2715c2 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -67,6 +67,7 @@ static void svc_rdma_detach(struct svc_xprt *xprt);
 static void svc_rdma_free(struct svc_xprt *xprt);
 static int svc_rdma_has_wspace(struct svc_xprt *xprt);
 static int svc_rdma_secure_port(struct svc_rqst *);
+static void svc_rdma_kill_temp_xprt(struct svc_xprt *);
 
 static struct svc_xprt_ops svc_rdma_ops = {
 	.xpo_create = svc_rdma_create,
@@ -79,6 +80,7 @@ static struct svc_xprt_ops svc_rdma_ops = {
 	.xpo_has_wspace = svc_rdma_has_wspace,
 	.xpo_accept = svc_rdma_accept,
 	.xpo_secure_port = svc_rdma_secure_port,
+	.xpo_kill_temp_xprt = svc_rdma_kill_temp_xprt,
 };
 
 struct svc_xprt_class svc_rdma_class = {
@@ -1317,6 +1319,10 @@ static int svc_rdma_secure_port(struct svc_rqst *rqstp)
 	return 1;
 }
 
+static void svc_rdma_kill_temp_xprt(struct svc_xprt *xprt)
+{
+}
+
 int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr)
 {
 	struct ib_send_wr *bad_wr, *n_wr;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index f9f5f3c3dab5..db32777ab591 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/socket.c: TIPC socket API
  *
- * Copyright (c) 2001-2007, 2012-2015, Ericsson AB
+ * Copyright (c) 2001-2007, 2012-2016, Ericsson AB
  * Copyright (c) 2004-2008, 2010-2013, Wind River Systems
  * All rights reserved.
  *
@@ -129,54 +129,8 @@ static const struct proto_ops packet_ops;
 static const struct proto_ops stream_ops;
 static const struct proto_ops msg_ops;
 static struct proto tipc_proto;
-
 static const struct rhashtable_params tsk_rht_params;
 
-/*
- * Revised TIPC socket locking policy:
- *
- * Most socket operations take the standard socket lock when they start
- * and hold it until they finish (or until they need to sleep).  Acquiring
- * this lock grants the owner exclusive access to the fields of the socket
- * data structures, with the exception of the backlog queue.  A few socket
- * operations can be done without taking the socket lock because they only
- * read socket information that never changes during the life of the socket.
- *
- * Socket operations may acquire the lock for the associated TIPC port if they
- * need to perform an operation on the port.  If any routine needs to acquire
- * both the socket lock and the port lock it must take the socket lock first
- * to avoid the risk of deadlock.
- *
- * The dispatcher handling incoming messages cannot grab the socket lock in
- * the standard fashion, since invoked it runs at the BH level and cannot block.
- * Instead, it checks to see if the socket lock is currently owned by someone,
- * and either handles the message itself or adds it to the socket's backlog
- * queue; in the latter case the queued message is processed once the process
- * owning the socket lock releases it.
- *
- * NOTE: Releasing the socket lock while an operation is sleeping overcomes
- * the problem of a blocked socket operation preventing any other operations
- * from occurring.  However, applications must be careful if they have
- * multiple threads trying to send (or receive) on the same socket, as these
- * operations might interfere with each other.  For example, doing a connect
- * and a receive at the same time might allow the receive to consume the
- * ACK message meant for the connect.  While additional work could be done
- * to try and overcome this, it doesn't seem to be worthwhile at the present.
- *
- * NOTE: Releasing the socket lock while an operation is sleeping also ensures
- * that another operation that must be performed in a non-blocking manner is
- * not delayed for very long because the lock has already been taken.
- *
- * NOTE: This code assumes that certain fields of a port/socket pair are
- * constant over its lifetime; such fields can be examined without taking
- * the socket lock and/or port lock, and do not need to be re-read even
- * after resuming processing after waiting.  These fields include:
- *   - socket type
- *   - pointer to socket sk structure (aka tipc_sock structure)
- *   - pointer to port structure
- *   - port reference
- */
-
 static u32 tsk_own_node(struct tipc_sock *tsk)
 {
 	return msg_prevnode(&tsk->phdr);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 5d1c14a2f268..2358f2690ec5 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2199,7 +2199,8 @@ out:
  *	Sleep until more data has arrived. But check for races..
  */
 static long unix_stream_data_wait(struct sock *sk, long timeo,
-				  struct sk_buff *last, unsigned int last_len)
+				  struct sk_buff *last, unsigned int last_len,
+				  bool freezable)
 {
 	struct sk_buff *tail;
 	DEFINE_WAIT(wait);
@@ -2220,7 +2221,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
 
 		sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 		unix_state_unlock(sk);
-		timeo = freezable_schedule_timeout(timeo);
+		if (freezable)
+			timeo = freezable_schedule_timeout(timeo);
+		else
+			timeo = schedule_timeout(timeo);
 		unix_state_lock(sk);
 
 		if (sock_flag(sk, SOCK_DEAD))
@@ -2250,7 +2254,8 @@ struct unix_stream_read_state {
 	unsigned int splice_flags;
 };
 
-static int unix_stream_read_generic(struct unix_stream_read_state *state)
+static int unix_stream_read_generic(struct unix_stream_read_state *state,
+				    bool freezable)
 {
 	struct scm_cookie scm;
 	struct socket *sock = state->socket;
@@ -2330,7 +2335,7 @@ again:
 			mutex_unlock(&u->iolock);
 
 			timeo = unix_stream_data_wait(sk, timeo, last,
-						      last_len);
+						      last_len, freezable);
 
 			if (signal_pending(current)) {
 				err = sock_intr_errno(timeo);
@@ -2472,7 +2477,7 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg,
 		.flags = flags
 	};
 
-	return unix_stream_read_generic(&state);
+	return unix_stream_read_generic(&state, true);
 }
 
 static int unix_stream_splice_actor(struct sk_buff *skb,
@@ -2503,7 +2508,7 @@ static ssize_t unix_stream_splice_read(struct socket *sock,  loff_t *ppos,
 	    flags & SPLICE_F_NONBLOCK)
 		state.flags = MSG_DONTWAIT;
 
-	return unix_stream_read_generic(&state);
+	return unix_stream_read_generic(&state, false);
 }
 
 static int unix_shutdown(struct socket *sock, int mode)
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 08d2e948c9ad..f0c0c8a48c92 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -71,6 +71,7 @@ struct cfg80211_registered_device {
 	struct list_head bss_list;
 	struct rb_root bss_tree;
 	u32 bss_generation;
+	u32 bss_entries;
 	struct cfg80211_scan_request *scan_req; /* protected by RTNL */
 	struct sk_buff *scan_msg;
 	struct cfg80211_sched_scan_request __rcu *sched_scan_req;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index b5bd58d0f731..35ad69fd0838 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -57,6 +57,19 @@
  * also linked into the probe response struct.
  */
 
+/*
+ * Limit the number of BSS entries stored in mac80211. Each one is
+ * a bit over 4k at most, so this limits to roughly 4-5M of memory.
+ * If somebody wants to really attack this though, they'd likely
+ * use small beacons, and only one type of frame, limiting each of
+ * the entries to a much smaller size (in order to generate more
+ * entries in total, so overhead is bigger.)
+ */
+static int bss_entries_limit = 1000;
+module_param(bss_entries_limit, int, 0644);
+MODULE_PARM_DESC(bss_entries_limit,
+                 "limit to number of scan BSS entries (per wiphy, default 1000)");
+
 #define IEEE80211_SCAN_RESULT_EXPIRE	(30 * HZ)
 
 static void bss_free(struct cfg80211_internal_bss *bss)
@@ -137,6 +150,10 @@ static bool __cfg80211_unlink_bss(struct cfg80211_registered_device *rdev,
 
 	list_del_init(&bss->list);
 	rb_erase(&bss->rbn, &rdev->bss_tree);
+	rdev->bss_entries--;
+	WARN_ONCE((rdev->bss_entries == 0) ^ list_empty(&rdev->bss_list),
+		  "rdev bss entries[%d]/list[empty:%d] corruption\n",
+		  rdev->bss_entries, list_empty(&rdev->bss_list));
 	bss_ref_put(rdev, bss);
 	return true;
 }
@@ -163,6 +180,40 @@ static void __cfg80211_bss_expire(struct cfg80211_registered_device *rdev,
 		rdev->bss_generation++;
 }
 
+static bool cfg80211_bss_expire_oldest(struct cfg80211_registered_device *rdev)
+{
+	struct cfg80211_internal_bss *bss, *oldest = NULL;
+	bool ret;
+
+	lockdep_assert_held(&rdev->bss_lock);
+
+	list_for_each_entry(bss, &rdev->bss_list, list) {
+		if (atomic_read(&bss->hold))
+			continue;
+
+		if (!list_empty(&bss->hidden_list) &&
+		    !bss->pub.hidden_beacon_bss)
+			continue;
+
+		if (oldest && time_before(oldest->ts, bss->ts))
+			continue;
+		oldest = bss;
+	}
+
+	if (WARN_ON(!oldest))
+		return false;
+
+	/*
+	 * The callers make sure to increase rdev->bss_generation if anything
+	 * gets removed (and a new entry added), so there's no need to also do
+	 * it here.
+	 */
+
+	ret = __cfg80211_unlink_bss(rdev, oldest);
+	WARN_ON(!ret);
+	return ret;
+}
+
 void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
 			   bool send_message)
 {
@@ -689,6 +740,7 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev,
 	const u8 *ie;
 	int i, ssidlen;
 	u8 fold = 0;
+	u32 n_entries = 0;
 
 	ies = rcu_access_pointer(new->pub.beacon_ies);
 	if (WARN_ON(!ies))
@@ -712,6 +764,12 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev,
 	/* This is the bad part ... */
 
 	list_for_each_entry(bss, &rdev->bss_list, list) {
+		/*
+		 * we're iterating all the entries anyway, so take the
+		 * opportunity to validate the list length accounting
+		 */
+		n_entries++;
+
 		if (!ether_addr_equal(bss->pub.bssid, new->pub.bssid))
 			continue;
 		if (bss->pub.channel != new->pub.channel)
@@ -740,6 +798,10 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev,
 				   new->pub.beacon_ies);
 	}
 
+	WARN_ONCE(n_entries != rdev->bss_entries,
+		  "rdev bss entries[%d]/list[len:%d] corruption\n",
+		  rdev->bss_entries, n_entries);
+
 	return true;
 }
 
@@ -894,7 +956,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev,
 			}
 		}
 
+		if (rdev->bss_entries >= bss_entries_limit &&
+		    !cfg80211_bss_expire_oldest(rdev)) {
+			kfree(new);
+			goto drop;
+		}
+
 		list_add_tail(&new->list, &rdev->bss_list);
+		rdev->bss_entries++;
 		rb_insert_bss(rdev, new);
 		found = new;
 	}
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 5ea12afc7706..659b507b347d 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1158,7 +1158,8 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate)
 		   58500000,
 		   65000000,
 		   78000000,
-		   0,
+		/* not in the spec, but some devices use this: */
+		   86500000,
 		},
 		{  13500000,
 		   27000000,
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index de46ab03f063..7675d11ee65e 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -159,7 +159,8 @@ cmd_cpp_i_c       = $(CPP) $(c_flags) -o $@ $<
 $(obj)/%.i: $(src)/%.c FORCE
 	$(call if_changed_dep,cpp_i_c)
 
-cmd_gensymtypes =                                                           \
+# These mirror gensymtypes_S and co below, keep them in synch.
+cmd_gensymtypes_c =                                                         \
     $(CPP) -D__GENKSYMS__ $(c_flags) $< |                                   \
     $(GENKSYMS) $(if $(1), -T $(2))                                         \
      $(patsubst y,-s _,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX))             \
@@ -169,7 +170,7 @@ cmd_gensymtypes =                                                           \
 quiet_cmd_cc_symtypes_c = SYM $(quiet_modtag) $@
 cmd_cc_symtypes_c =                                                         \
     set -e;                                                                 \
-    $(call cmd_gensymtypes,true,$@) >/dev/null;                             \
+    $(call cmd_gensymtypes_c,true,$@) >/dev/null;                           \
     test -s $@ || rm -f $@
 
 $(obj)/%.symtypes : $(src)/%.c FORCE
@@ -198,9 +199,10 @@ else
 #   the actual value of the checksum generated by genksyms
 
 cmd_cc_o_c = $(CC) $(c_flags) -c -o $(@D)/.tmp_$(@F) $<
-cmd_modversions =								\
+
+cmd_modversions_c =								\
 	if $(OBJDUMP) -h $(@D)/.tmp_$(@F) | grep -q __ksymtab; then		\
-		$(call cmd_gensymtypes,$(KBUILD_SYMTYPES),$(@:.o=.symtypes))	\
+		$(call cmd_gensymtypes_c,$(KBUILD_SYMTYPES),$(@:.o=.symtypes))	\
 		    > $(@D)/.tmp_$(@F:.o=.ver);					\
 										\
 		$(LD) $(LDFLAGS) -r -o $@ $(@D)/.tmp_$(@F) 			\
@@ -268,13 +270,14 @@ endif # CONFIG_STACK_VALIDATION
 define rule_cc_o_c
 	$(call echo-cmd,checksrc) $(cmd_checksrc)			  \
 	$(call cmd_and_fixdep,cc_o_c)					  \
-	$(cmd_modversions)						  \
+	$(cmd_modversions_c)						  \
 	$(cmd_objtool)						          \
 	$(call echo-cmd,record_mcount) $(cmd_record_mcount)
 endef
 
 define rule_as_o_S
 	$(call cmd_and_fixdep,as_o_S)					  \
+	$(cmd_modversions_S)						  \
 	$(cmd_objtool)
 endef
 
@@ -314,6 +317,39 @@ modkern_aflags := $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL)
 $(real-objs-m)      : modkern_aflags := $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE)
 $(real-objs-m:.o=.s): modkern_aflags := $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE)
 
+# .S file exports must have their C prototypes defined in asm/asm-prototypes.h
+# or a file that it includes, in order to get versioned symbols. We build a
+# dummy C file that includes asm-prototypes and the EXPORT_SYMBOL lines from
+# the .S file (with trailing ';'), and run genksyms on that, to extract vers.
+#
+# This is convoluted. The .S file must first be preprocessed to run guards and
+# expand names, then the resulting exports must be constructed into plain
+# EXPORT_SYMBOL(symbol); to build our dummy C file, and that gets preprocessed
+# to make the genksyms input.
+#
+# These mirror gensymtypes_c and co above, keep them in synch.
+cmd_gensymtypes_S =                                                         \
+    (echo "\#include <linux/kernel.h>" ;                                    \
+     echo "\#include <asm/asm-prototypes.h>" ;                              \
+    $(CPP) $(a_flags) $< |                                                  \
+     grep "\<___EXPORT_SYMBOL\>" |                                          \
+     sed 's/.*___EXPORT_SYMBOL[[:space:]]*\([a-zA-Z0-9_]*\)[[:space:]]*,.*/EXPORT_SYMBOL(\1);/' ) | \
+    $(CPP) -D__GENKSYMS__ $(c_flags) -xc - |                                \
+    $(GENKSYMS) $(if $(1), -T $(2))                                         \
+     $(patsubst y,-s _,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX))             \
+     $(if $(KBUILD_PRESERVE),-p)                                            \
+     -r $(firstword $(wildcard $(2:.symtypes=.symref) /dev/null))
+
+quiet_cmd_cc_symtypes_S = SYM $(quiet_modtag) $@
+cmd_cc_symtypes_S =                                                         \
+    set -e;                                                                 \
+    $(call cmd_gensymtypes_S,true,$@) >/dev/null;                           \
+    test -s $@ || rm -f $@
+
+$(obj)/%.symtypes : $(src)/%.S FORCE
+	$(call cmd,cc_symtypes_S)
+
+
 quiet_cmd_cpp_s_S = CPP $(quiet_modtag) $@
 cmd_cpp_s_S       = $(CPP) $(a_flags) -o $@ $<
 
@@ -321,7 +357,37 @@ $(obj)/%.s: $(src)/%.S FORCE
 	$(call if_changed_dep,cpp_s_S)
 
 quiet_cmd_as_o_S = AS $(quiet_modtag)  $@
-cmd_as_o_S       = $(CC) $(a_flags) -c -o $@ $<
+
+ifndef CONFIG_MODVERSIONS
+cmd_as_o_S = $(CC) $(a_flags) -c -o $@ $<
+
+else
+
+ASM_PROTOTYPES := $(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/asm-prototypes.h)
+
+ifeq ($(ASM_PROTOTYPES),)
+cmd_as_o_S = $(CC) $(a_flags) -c -o $@ $<
+
+else
+
+# versioning matches the C process described above, with difference that
+# we parse asm-prototypes.h C header to get function definitions.
+
+cmd_as_o_S = $(CC) $(a_flags) -c -o $(@D)/.tmp_$(@F) $<
+
+cmd_modversions_S =								\
+	if $(OBJDUMP) -h $(@D)/.tmp_$(@F) | grep -q __ksymtab; then		\
+		$(call cmd_gensymtypes_S,$(KBUILD_SYMTYPES),$(@:.o=.symtypes))	\
+		    > $(@D)/.tmp_$(@F:.o=.ver);					\
+										\
+		$(LD) $(LDFLAGS) -r -o $@ $(@D)/.tmp_$(@F) 			\
+			-T $(@D)/.tmp_$(@F:.o=.ver);				\
+		rm -f $(@D)/.tmp_$(@F) $(@D)/.tmp_$(@F:.o=.ver);		\
+	else									\
+		mv -f $(@D)/.tmp_$(@F) $@;					\
+	fi;
+endif
+endif
 
 $(obj)/%.o: $(src)/%.S $(objtool_obj) FORCE
 	$(call if_changed_rule,as_o_S)
@@ -430,6 +496,9 @@ cmd_export_list = $(OBJDUMP) -h $< | \
 
 $(obj)/lib-ksyms.o: $(lib-target) FORCE
 	$(call if_changed,export_list)
+
+targets += $(obj)/lib-ksyms.o
+
 endif
 
 #
diff --git a/scripts/gcc-x86_64-has-stack-protector.sh b/scripts/gcc-x86_64-has-stack-protector.sh
index 973e8c141567..17867e723a51 100755
--- a/scripts/gcc-x86_64-has-stack-protector.sh
+++ b/scripts/gcc-x86_64-has-stack-protector.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -O0 -mcmodel=kernel -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
+echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
 if [ "$?" -eq "0" ] ; then
 	echo y
 else
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index fc3036b34e51..a4d90aa1045a 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -621,8 +621,8 @@ int aa_change_hat(const char *hats[], int count, u64 token, bool permtest)
 	/* released below */
 	cred = get_current_cred();
 	cxt = cred_cxt(cred);
-	profile = aa_cred_profile(cred);
-	previous_profile = cxt->previous;
+	profile = aa_get_newest_profile(aa_cred_profile(cred));
+	previous_profile = aa_get_newest_profile(cxt->previous);
 
 	if (unconfined(profile)) {
 		info = "unconfined";
@@ -718,6 +718,8 @@ audit:
 out:
 	aa_put_profile(hat);
 	kfree(name);
+	aa_put_profile(profile);
+	aa_put_profile(previous_profile);
 	put_cred(cred);
 
 	return error;
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 2f909dd8b7b8..ea81c08ddc7a 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -6907,8 +6907,6 @@ static const struct hda_fixup alc662_fixups[] = {
 		.v.pins = (const struct hda_pintbl[]) {
 			{ 0x15, 0x40f000f0 }, /* disabled */
 			{ 0x16, 0x40f000f0 }, /* disabled */
-			{ 0x18, 0x01014011 }, /* LO */
-			{ 0x1a, 0x01014012 }, /* LO */
 			{ }
 		}
 	},
diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c
index 6a23302297c9..4d9d320a7971 100644
--- a/sound/pci/hda/thinkpad_helper.c
+++ b/sound/pci/hda/thinkpad_helper.c
@@ -13,7 +13,8 @@ static void (*old_vmaster_hook)(void *, int);
 static bool is_thinkpad(struct hda_codec *codec)
 {
 	return (codec->core.subsystem_id >> 16 == 0x17aa) &&
-	       (acpi_dev_found("LEN0068") || acpi_dev_found("IBM0068"));
+	       (acpi_dev_found("LEN0068") || acpi_dev_found("LEN0268") ||
+		acpi_dev_found("IBM0068"));
 }
 
 static void update_tpacpi_mute_led(void *private_data, int enabled)
diff --git a/sound/usb/card.c b/sound/usb/card.c
index 9e5276d6dda0..2ddc034673a8 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -315,7 +315,8 @@ static int snd_usb_audio_free(struct snd_usb_audio *chip)
 		snd_usb_endpoint_free(ep);
 
 	mutex_destroy(&chip->mutex);
-	dev_set_drvdata(&chip->dev->dev, NULL);
+	if (!atomic_read(&chip->shutdown))
+		dev_set_drvdata(&chip->dev->dev, NULL);
 	kfree(chip);
 	return 0;
 }
diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config
index a538ff44b108..a1883bbb0144 100644
--- a/tools/power/acpi/Makefile.config
+++ b/tools/power/acpi/Makefile.config
@@ -8,18 +8,19 @@
 # as published by the Free Software Foundation; version 2
 # of the License.
 
-include ../../../../scripts/Makefile.include
-
-OUTPUT=./
-ifeq ("$(origin O)", "command line")
-	OUTPUT := $(O)/
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(shell pwd)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
 endif
 
-ifneq ($(OUTPUT),)
-# check that the output directory actually exists
-OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
-$(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
+include $(srctree)/../../scripts/Makefile.include
+
+OUTPUT=$(srctree)/
+ifeq ("$(origin O)", "command line")
+	OUTPUT := $(O)/power/acpi/
 endif
+#$(info Determined 'OUTPUT' to be $(OUTPUT))
 
 # --- CONFIGURATION BEGIN ---
 
@@ -70,8 +71,8 @@ WARNINGS := -Wall
 WARNINGS += $(call cc-supports,-Wstrict-prototypes)
 WARNINGS += $(call cc-supports,-Wdeclaration-after-statement)
 
-KERNEL_INCLUDE := ../../../include
-ACPICA_INCLUDE := ../../../drivers/acpi/acpica
+KERNEL_INCLUDE := $(OUTPUT)include
+ACPICA_INCLUDE := $(srctree)/../../../drivers/acpi/acpica
 CFLAGS += -D_LINUX -I$(KERNEL_INCLUDE) -I$(ACPICA_INCLUDE)
 CFLAGS += $(WARNINGS)
 
diff --git a/tools/power/acpi/Makefile.rules b/tools/power/acpi/Makefile.rules
index ec87a9e562c0..373738338f51 100644
--- a/tools/power/acpi/Makefile.rules
+++ b/tools/power/acpi/Makefile.rules
@@ -8,28 +8,42 @@
 # as published by the Free Software Foundation; version 2
 # of the License.
 
-$(OUTPUT)$(TOOL): $(TOOL_OBJS) FORCE
-	$(ECHO) "  LD      " $@
-	$(QUIET) $(LD) $(CFLAGS) $(LDFLAGS) $(TOOL_OBJS) -L$(OUTPUT) -o $@
+objdir := $(OUTPUT)tools/$(TOOL)/
+toolobjs := $(addprefix $(objdir),$(TOOL_OBJS))
+$(OUTPUT)$(TOOL): $(toolobjs) FORCE
+	$(ECHO) "  LD      " $(subst $(OUTPUT),,$@)
+	$(QUIET) $(LD) $(CFLAGS) $(LDFLAGS) $(toolobjs) -L$(OUTPUT) -o $@
+	$(ECHO) "  STRIP   " $(subst $(OUTPUT),,$@)
 	$(QUIET) $(STRIPCMD) $@
 
-$(OUTPUT)%.o: %.c
-	$(ECHO) "  CC      " $@
+$(KERNEL_INCLUDE):
+	$(ECHO) "  MKDIR   " $(subst $(OUTPUT),,$@)
+	$(QUIET) mkdir -p $(KERNEL_INCLUDE)
+	$(ECHO) "  CP      " $(subst $(OUTPUT),,$@)
+	$(QUIET) cp -rf $(srctree)/../../../include/acpi $(KERNEL_INCLUDE)/
+
+$(objdir)%.o: %.c $(KERNEL_INCLUDE)
+	$(ECHO) "  CC      " $(subst $(OUTPUT),,$@)
 	$(QUIET) $(CC) -c $(CFLAGS) -o $@ $<
 
 all: $(OUTPUT)$(TOOL)
 clean:
-	-find $(OUTPUT) \( -not -type d \) \
-	-and \( -name '*~' -o -name '*.[oas]' \) \
-	-type f -print \
-	 | xargs rm -f
-	-rm -f $(OUTPUT)$(TOOL)
+	$(ECHO) "  RMOBJ   " $(subst $(OUTPUT),,$(objdir))
+	$(QUIET) find $(objdir) \( -not -type d \)\
+		 -and \( -name '*~' -o -name '*.[oas]' \)\
+		 -type f -print | xargs rm -f
+	$(ECHO) "  RM      " $(TOOL)
+	$(QUIET) rm -f $(OUTPUT)$(TOOL)
+	$(ECHO) "  RMINC   " $(subst $(OUTPUT),,$(KERNEL_INCLUDE))
+	$(QUIET) rm -rf $(KERNEL_INCLUDE)
 
 install-tools:
-	$(INSTALL) -d $(DESTDIR)${sbindir}
-	$(INSTALL_PROGRAM) $(OUTPUT)$(TOOL) $(DESTDIR)${sbindir}
+	$(ECHO) "  INST    " $(TOOL)
+	$(QUIET) $(INSTALL) -d $(DESTDIR)$(sbindir)
+	$(QUIET) $(INSTALL_PROGRAM) $(OUTPUT)$(TOOL) $(DESTDIR)$(sbindir)
 uninstall-tools:
-	- rm -f $(DESTDIR)${sbindir}/$(TOOL)
+	$(ECHO) "  UNINST  " $(TOOL)
+	$(QUIET) rm -f $(DESTDIR)$(sbindir)/$(TOOL)
 
 install: all install-tools $(EXTRA_INSTALL)
 uninstall: uninstall-tools $(EXTRA_UNINSTALL)
diff --git a/tools/power/acpi/tools/acpidbg/Makefile b/tools/power/acpi/tools/acpidbg/Makefile
index 352df4b41ae9..f2d06e773eb4 100644
--- a/tools/power/acpi/tools/acpidbg/Makefile
+++ b/tools/power/acpi/tools/acpidbg/Makefile
@@ -17,9 +17,7 @@ vpath %.c \
 	../../os_specific/service_layers\
 	.
 CFLAGS += -DACPI_APPLICATION -DACPI_SINGLE_THREAD -DACPI_DEBUGGER\
-	-I.\
-	-I../../../../../drivers/acpi/acpica\
-	-I../../../../../include
+	-I.
 LDFLAGS += -lpthread
 TOOL_OBJS = \
 	acpidbg.o
diff --git a/tools/power/acpi/tools/acpidbg/acpidbg.c b/tools/power/acpi/tools/acpidbg/acpidbg.c
index a88ac45b7756..4308362d7068 100644
--- a/tools/power/acpi/tools/acpidbg/acpidbg.c
+++ b/tools/power/acpi/tools/acpidbg/acpidbg.c
@@ -12,10 +12,16 @@
 #include <acpi/acpi.h>
 
 /* Headers not included by include/acpi/platform/aclinux.h */
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <error.h>
 #include <stdbool.h>
 #include <fcntl.h>
 #include <assert.h>
-#include <linux/circ_buf.h>
+#include <sys/select.h>
+#include "../../../../../include/linux/circ_buf.h"
 
 #define ACPI_AML_FILE		"/sys/kernel/debug/acpi/acpidbg"
 #define ACPI_AML_SEC_TICK	1
diff --git a/tools/power/acpi/tools/acpidump/Makefile b/tools/power/acpi/tools/acpidump/Makefile
index 04b5db7c7c0b..f7c7af1f9258 100644
--- a/tools/power/acpi/tools/acpidump/Makefile
+++ b/tools/power/acpi/tools/acpidump/Makefile
@@ -19,9 +19,7 @@ vpath %.c \
 	./\
 	../../common\
 	../../os_specific/service_layers
-CFLAGS += -DACPI_DUMP_APP -I.\
-	-I../../../../../drivers/acpi/acpica\
-	-I../../../../../include
+CFLAGS += -DACPI_DUMP_APP -I.
 TOOL_OBJS = \
 	apdump.o\
 	apfiles.o\
@@ -49,7 +47,9 @@ TOOL_OBJS = \
 
 include ../../Makefile.rules
 
-install-man: ../../man/acpidump.8
-	$(INSTALL_DATA) -D $< $(DESTDIR)${mandir}/man8/acpidump.8
+install-man: $(srctree)/man/acpidump.8
+	$(ECHO) "  INST    " acpidump.8
+	$(QUIET) $(INSTALL_DATA) -D $< $(DESTDIR)$(mandir)/man8/acpidump.8
 uninstall-man:
-	- rm -f $(DESTDIR)${mandir}/man8/acpidump.8
+	$(ECHO) "  UNINST  " acpidump.8
+	$(QUIET) rm -f $(DESTDIR)$(mandir)/man8/acpidump.8
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index 6e9c40eea208..69ccce308458 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -305,7 +305,7 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
 			continue;
 		type = vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i)
 		       & ARMV8_PMU_EVTYPE_EVENT;
-		if ((type == ARMV8_PMU_EVTYPE_EVENT_SW_INCR)
+		if ((type == ARMV8_PMUV3_PERFCTR_SW_INCR)
 		    && (enable & BIT(i))) {
 			reg = vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) + 1;
 			reg = lower_32_bits(reg);
@@ -379,7 +379,8 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	eventsel = data & ARMV8_PMU_EVTYPE_EVENT;
 
 	/* Software increment event does't need to be backed by a perf event */
-	if (eventsel == ARMV8_PMU_EVTYPE_EVENT_SW_INCR)
+	if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR &&
+	    select_idx != ARMV8_PMU_CYCLE_IDX)
 		return;
 
 	memset(&attr, 0, sizeof(struct perf_event_attr));
@@ -391,7 +392,8 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0;
 	attr.exclude_hv = 1; /* Don't count EL2 events */
 	attr.exclude_host = 1; /* Don't count host events */
-	attr.config = eventsel;
+	attr.config = (select_idx == ARMV8_PMU_CYCLE_IDX) ?
+		ARMV8_PMUV3_PERFCTR_CPU_CYCLES : eventsel;
 
 	counter = kvm_pmu_get_counter_value(vcpu, select_idx);
 	/* The initial sample period (overflow count) of an event. */
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 8035cc1eb955..efeceb0a222d 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -91,6 +91,7 @@ static void async_pf_execute(struct work_struct *work)
 
 	spin_lock(&vcpu->async_pf.lock);
 	list_add_tail(&apf->link, &vcpu->async_pf.done);
+	apf->vcpu = NULL;
 	spin_unlock(&vcpu->async_pf.lock);
 
 	/*
@@ -113,6 +114,8 @@ static void async_pf_execute(struct work_struct *work)
 
 void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 {
+	spin_lock(&vcpu->async_pf.lock);
+
 	/* cancel outstanding work queue item */
 	while (!list_empty(&vcpu->async_pf.queue)) {
 		struct kvm_async_pf *work =
@@ -120,6 +123,14 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 					 typeof(*work), queue);
 		list_del(&work->queue);
 
+		/*
+		 * We know it's present in vcpu->async_pf.done, do
+		 * nothing here.
+		 */
+		if (!work->vcpu)
+			continue;
+
+		spin_unlock(&vcpu->async_pf.lock);
 #ifdef CONFIG_KVM_ASYNC_PF_SYNC
 		flush_work(&work->work);
 #else
@@ -129,9 +140,9 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 			kmem_cache_free(async_pf_cache, work);
 		}
 #endif
+		spin_lock(&vcpu->async_pf.lock);
 	}
 
-	spin_lock(&vcpu->async_pf.lock);
 	while (!list_empty(&vcpu->async_pf.done)) {
 		struct kvm_async_pf *work =
 			list_first_entry(&vcpu->async_pf.done,