Merge branch 'linux-linaro-lsk-v4.4-android' of git://git.linaro.org/kernel/linux-linaro-stable.git

* linux-linaro-lsk-v4.4-android: (434 commits)
  Linux 4.4.52
  kvm: vmx: ensure VMCS is current while enabling PML
  Revert "usb: chipidea: imx: enable CI_HDRC_SET_NON_ZERO_TTHA"
  rtlwifi: rtl_usb: Fix for URB leaking when doing ifconfig up/down
  block: fix double-free in the failure path of cgwb_bdi_init()
  goldfish: Sanitize the broken interrupt handler
  x86/platform/goldfish: Prevent unconditional loading
  USB: serial: ark3116: fix register-accessor error handling
  USB: serial: opticon: fix CTS retrieval at open
  USB: serial: spcp8x5: fix modem-status handling
  USB: serial: ftdi_sio: fix line-status over-reporting
  USB: serial: ftdi_sio: fix extreme low-latency setting
  USB: serial: ftdi_sio: fix modem-status error handling
  USB: serial: cp210x: add new IDs for GE Bx50v3 boards
  USB: serial: mos7840: fix another NULL-deref at open
  tty: serial: msm: Fix module autoload
  net: socket: fix recvmmsg not returning error from sock_error
  ip: fix IP_CHECKSUM handling
  irda: Fix lockdep annotations in hashbin_delete().
  dccp: fix freeing skb too early for IPV6_RECVPKTINFO
  ...

Conflicts:
	drivers/mmc/core/mmc.c
	drivers/usb/dwc3/ep0.c
	drivers/usb/host/xhci.h

Change-Id: Icf331a68162ab686d01996a3f43fa2e97543f62e

Documentation/devicetree/bindings/clock/imx31-clock.txt

@@ -77,7 +77,7 @@ Examples:
 clks: ccm@53f80000{
 	compatible = "fsl,imx31-ccm";
 	reg = <0x53f80000 0x4000>;
-	interrupts = <0 31 0x04 0 53 0x04>;
+	interrupts = <31>, <53>;
 	#clock-cells = <1>;
 };
 

Documentation/kernel-parameters.txt

@@ -1261,6 +1261,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			When zero, profiling data is discarded and associated
 			debugfs files are removed at module unload time.
 
+	goldfish	[X86] Enable the goldfish android emulator platform.
+			Don't use this when you are not running on the
+			android emulator
+
 	gpt		[EFI] Forces disk with valid GPT signature but
 			invalid Protective MBR to be treated as GPT. If the
 			primary GPT is corrupted, it enables the backup/alternate

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 41
+SUBLEVEL = 52
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 

android/configs/android-recommended.cfg

@@ -8,6 +8,7 @@
 # CONFIG_VT is not set
 CONFIG_ANDROID_TIMED_GPIO=y
 CONFIG_ARM_KERNMEM_PERMS=y
+CONFIG_ARM64_SW_TTBR0_PAN=y
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y

arch/arc/include/asm/delay.h

@@ -26,7 +26,9 @@ static inline void __delay(unsigned long loops)
 	"	lp  1f			\n"
 	"	nop			\n"
 	"1:				\n"
-	: : "r"(loops));
+	:
+        : "r"(loops)
+        : "lp_count");
 }
 
 extern void __bad_udelay(void);

arch/arc/kernel/unaligned.c

@@ -241,8 +241,9 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs,
 	if (state.fault)
 		goto fault;
 
+	/* clear any remanants of delay slot */
 	if (delay_mode(regs)) {
-		regs->ret = regs->bta;
+		regs->ret = regs->bta & ~1U;
 		regs->status32 &= ~STATUS_DE_MASK;
 	} else {
 		regs->ret += state.instr_len;

arch/arm/boot/dts/da850-evm.dts

@@ -85,6 +85,7 @@
 				#size-cells = <1>;
 				compatible = "m25p64";
 				spi-max-frequency = <30000000>;
+				m25p,fast-read;
 				reg = <0>;
 				partition@0 {
 					label = "U-Boot-SPL";

arch/arm/boot/dts/imx31.dtsi

@@ -30,11 +30,11 @@
 		};
 	};
 
-	avic: avic-interrupt-controller@60000000 {
+	avic: interrupt-controller@68000000 {
 		compatible = "fsl,imx31-avic", "fsl,avic";
 		interrupt-controller;
 		#interrupt-cells = <1>;
-		reg = <0x60000000 0x100000>;
+		reg = <0x68000000 0x100000>;
 	};
 
 	soc {
@@ -110,13 +110,6 @@
 				interrupts = <19>;
 				clocks = <&clks 25>;
 			};
-
-			clks: ccm@53f80000{
-				compatible = "fsl,imx31-ccm";
-				reg = <0x53f80000 0x4000>;
-				interrupts = <0 31 0x04 0 53 0x04>;
-				#clock-cells = <1>;
-			};
 		};
 
 		aips@53f00000 { /* AIPS2 */
@@ -126,6 +119,13 @@
 			reg = <0x53f00000 0x100000>;
 			ranges;
 
+			clks: ccm@53f80000{
+				compatible = "fsl,imx31-ccm";
+				reg = <0x53f80000 0x4000>;
+				interrupts = <31>, <53>;
+				#clock-cells = <1>;
+			};
+
 			gpt: timer@53f90000 {
 				compatible = "fsl,imx31-gpt";
 				reg = <0x53f90000 0x4000>;

arch/arm/boot/dts/imx6qdl-nitrogen6_max.dtsi

@@ -319,8 +319,6 @@
 		compatible = "fsl,imx6q-nitrogen6_max-sgtl5000",
 			     "fsl,imx-audio-sgtl5000";
 		model = "imx6q-nitrogen6_max-sgtl5000";
-		pinctrl-names = "default";
-		pinctrl-0 = <&pinctrl_sgtl5000>;
 		ssi-controller = <&ssi1>;
 		audio-codec = <&codec>;
 		audio-routing =
@@ -401,6 +399,8 @@
 
 	codec: sgtl5000@0a {
 		compatible = "fsl,sgtl5000";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_sgtl5000>;
 		reg = <0x0a>;
 		clocks = <&clks 201>;
 		VDDA-supply = <&reg_2p5v>;

arch/arm/boot/dts/r8a7794.dtsi

@@ -1023,7 +1023,7 @@
 		mstp7_clks: mstp7_clks@e615014c {
 			compatible = "renesas,r8a7794-mstp-clocks", "renesas,cpg-mstp-clocks";
 			reg = <0 0xe615014c 0 4>, <0 0xe61501c4 0 4>;
-			clocks = <&mp_clk>, <&mp_clk>,
+			clocks = <&mp_clk>, <&hp_clk>,
 				 <&zs_clk>, <&p_clk>, <&p_clk>, <&zs_clk>,
 				 <&zs_clk>, <&p_clk>, <&p_clk>, <&p_clk>, <&p_clk>;
 			#clock-cells = <1>;

arch/arm/crypto/aes-ce-glue.c

@@ -87,8 +87,13 @@ static int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 		u32 *rki = ctx->key_enc + (i * kwords);
 		u32 *rko = rki + kwords;
 
+#ifndef CONFIG_CPU_BIG_ENDIAN
 		rko[0] = ror32(ce_aes_sub(rki[kwords - 1]), 8);
 		rko[0] = rko[0] ^ rki[0] ^ rcon[i];
+#else
+		rko[0] = rol32(ce_aes_sub(rki[kwords - 1]), 8);
+		rko[0] = rko[0] ^ rki[0] ^ (rcon[i] << 24);
+#endif
 		rko[1] = rko[0] ^ rki[1];
 		rko[2] = rko[1] ^ rki[2];
 		rko[3] = rko[2] ^ rki[3];

arch/arm/include/asm/cputype.h

@@ -81,6 +81,9 @@
 #define ARM_CPU_XSCALE_ARCH_V2		0x4000
 #define ARM_CPU_XSCALE_ARCH_V3		0x6000
 
+/* Qualcomm implemented cores */
+#define ARM_CPU_PART_SCORPION		0x510002d0
+
 extern unsigned int processor_id;
 
 #ifdef CONFIG_CPU_CP15

arch/arm/kernel/hw_breakpoint.c

@@ -1066,6 +1066,22 @@ static int __init arch_hw_breakpoint_init(void)
 		return 0;
 	}
 
+	/*
+	 * Scorpion CPUs (at least those in APQ8060) seem to set DBGPRSR.SPD
+	 * whenever a WFI is issued, even if the core is not powered down, in
+	 * violation of the architecture.  When DBGPRSR.SPD is set, accesses to
+	 * breakpoint and watchpoint registers are treated as undefined, so
+	 * this results in boot time and runtime failures when these are
+	 * accessed and we unexpectedly take a trap.
+	 *
+	 * It's not clear if/how this can be worked around, so we blacklist
+	 * Scorpion CPUs to avoid these issues.
+	*/
+	if (read_cpuid_part() == ARM_CPU_PART_SCORPION) {
+		pr_info("Scorpion CPU detected. Hardware breakpoints and watchpoints disabled\n");
+		return 0;
+	}
+
 	has_ossr = core_has_os_save_restore();
 
 	/* Determine how many BRPs/WRPs are available. */

arch/arm/kernel/ptrace.c

@@ -600,7 +600,7 @@ static int gpr_set(struct task_struct *target,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct pt_regs newregs;
+	struct pt_regs newregs = *task_pt_regs(target);
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 &newregs,

arch/arm/kernel/smp_tlb.c

@@ -9,6 +9,7 @@
  */
 #include <linux/preempt.h>
 #include <linux/smp.h>
+#include <linux/uaccess.h>
 
 #include <asm/smp_plat.h>
 #include <asm/tlbflush.h>
@@ -40,8 +41,11 @@ static inline void ipi_flush_tlb_mm(void *arg)
 static inline void ipi_flush_tlb_page(void *arg)
 {
 	struct tlb_args *ta = (struct tlb_args *)arg;
+	unsigned int __ua_flags = uaccess_save_and_enable();
 
 	local_flush_tlb_page(ta->ta_vma, ta->ta_start);
+
+	uaccess_restore(__ua_flags);
 }
 
 static inline void ipi_flush_tlb_kernel_page(void *arg)
@@ -54,8 +58,11 @@ static inline void ipi_flush_tlb_kernel_page(void *arg)
 static inline void ipi_flush_tlb_range(void *arg)
 {
 	struct tlb_args *ta = (struct tlb_args *)arg;
+	unsigned int __ua_flags = uaccess_save_and_enable();
 
 	local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end);
+
+	uaccess_restore(__ua_flags);
 }
 
 static inline void ipi_flush_tlb_kernel_range(void *arg)

arch/arm/lib/getuser.S

@@ -67,7 +67,7 @@ ENTRY(__get_user_4)
 ENDPROC(__get_user_4)
 
 ENTRY(__get_user_8)
-	check_uaccess r0, 8, r1, r2, __get_user_bad
+	check_uaccess r0, 8, r1, r2, __get_user_bad8
 #ifdef CONFIG_THUMB2_KERNEL
 5: TUSER(ldr)	r2, [r0]
 6: TUSER(ldr)	r3, [r0, #4]

arch/arm/mach-davinci/da850.c

@@ -298,6 +298,16 @@ static struct clk emac_clk = {
 	.gpsc		= 1,
 };
 
+/*
+ * In order to avoid adding the emac_clk to the clock lookup table twice (and
+ * screwing up the linked list in the process) create a separate clock for
+ * mdio inheriting the rate from emac_clk.
+ */
+static struct clk mdio_clk = {
+	.name		= "mdio",
+	.parent		= &emac_clk,
+};
+
 static struct clk mcasp_clk = {
 	.name		= "mcasp",
 	.parent		= &pll0_sysclk2,
@@ -462,7 +472,7 @@ static struct clk_lookup da850_clks[] = {
 	CLK(NULL,		"arm",		&arm_clk),
 	CLK(NULL,		"rmii",		&rmii_clk),
 	CLK("davinci_emac.1",	NULL,		&emac_clk),
-	CLK("davinci_mdio.0",	"fck",		&emac_clk),
+	CLK("davinci_mdio.0",	"fck",		&mdio_clk),
 	CLK("davinci-mcasp.0",	NULL,		&mcasp_clk),
 	CLK("da8xx_lcdc.0",	"fck",		&lcdc_clk),
 	CLK("da830-mmc.0",	NULL,		&mmcsd0_clk),

arch/arm/mach-omap2/omap-mpuss-lowpower.c

@@ -243,10 +243,9 @@ int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state)
 		save_state = 1;
 		break;
 	case PWRDM_POWER_RET:
-		if (IS_PM44XX_ERRATUM(PM_OMAP4_CPU_OSWR_DISABLE)) {
+		if (IS_PM44XX_ERRATUM(PM_OMAP4_CPU_OSWR_DISABLE))
 			save_state = 0;
-			break;
-		}
+		break;
 	default:
 		/*
 		 * CPUx CSWR is invalid hardware state. Also CPUx OSWR

arch/arm/mach-ux500/pm.c

@@ -134,8 +134,8 @@ bool prcmu_pending_irq(void)
  */
 bool prcmu_is_cpu_in_wfi(int cpu)
 {
-	return readl(PRCM_ARM_WFI_STANDBY) & cpu ? PRCM_ARM_WFI_STANDBY_WFI1 :
-		     PRCM_ARM_WFI_STANDBY_WFI0;
+	return readl(PRCM_ARM_WFI_STANDBY) &
+		(cpu ? PRCM_ARM_WFI_STANDBY_WFI1 : PRCM_ARM_WFI_STANDBY_WFI0);
 }
 
 /*

arch/arm/mach-zynq/common.c

@@ -59,7 +59,7 @@ void __iomem *zynq_scu_base;
 static void __init zynq_memory_init(void)
 {
 	if (!__pa(PAGE_OFFSET))
-		memblock_reserve(__pa(PAGE_OFFSET), __pa(swapper_pg_dir));
+		memblock_reserve(__pa(PAGE_OFFSET), 0x80000);
 }
 
 static struct platform_device zynq_cpuidle_device = {

arch/arm/mm/fault.c

@@ -610,9 +610,9 @@ static int __init early_abort_handler(unsigned long addr, unsigned int fsr,
 
 void __init early_abt_enable(void)
 {
-	fsr_info[22].fn = early_abort_handler;
+	fsr_info[FSR_FS_AEA].fn = early_abort_handler;
 	local_abt_enable();
-	fsr_info[22].fn = do_bad;
+	fsr_info[FSR_FS_AEA].fn = do_bad;
 }
 
 #ifndef CONFIG_ARM_LPAE

arch/arm/mm/fault.h

@@ -11,11 +11,15 @@
 #define FSR_FS5_0		(0x3f)
 
 #ifdef CONFIG_ARM_LPAE
+#define FSR_FS_AEA		17
+
 static inline int fsr_fs(unsigned int fsr)
 {
 	return fsr & FSR_FS5_0;
 }
 #else
+#define FSR_FS_AEA		22
+
 static inline int fsr_fs(unsigned int fsr)
 {
 	return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6;

arch/arm64/Kconfig

@@ -720,7 +720,7 @@ config SETEND_EMULATION
 endif
 
 config ARM64_SW_TTBR0_PAN
-	bool "Emulate Priviledged Access Never using TTBR0_EL1 switching"
+	bool "Emulate Privileged Access Never using TTBR0_EL1 switching"
 	help
 	  Enabling this option prevents the kernel from accessing
 	  user-space memory directly by pointing TTBR0_EL1 to a reserved

arch/arm64/crypto/aes-ce-ccm-core.S

@@ -9,6 +9,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 	.text
 	.arch	armv8-a+crypto
@@ -19,7 +20,7 @@
 	 */
 ENTRY(ce_aes_ccm_auth_data)
 	ldr	w8, [x3]			/* leftover from prev round? */
-	ld1	{v0.2d}, [x0]			/* load mac */
+	ld1	{v0.16b}, [x0]			/* load mac */
 	cbz	w8, 1f
 	sub	w8, w8, #16
 	eor	v1.16b, v1.16b, v1.16b
@@ -31,7 +32,7 @@ ENTRY(ce_aes_ccm_auth_data)
 	beq	8f				/* out of input? */
 	cbnz	w8, 0b
 	eor	v0.16b, v0.16b, v1.16b
-1:	ld1	{v3.2d}, [x4]			/* load first round key */
+1:	ld1	{v3.16b}, [x4]			/* load first round key */
 	prfm	pldl1strm, [x1]
 	cmp	w5, #12				/* which key size? */
 	add	x6, x4, #16
@@ -41,17 +42,17 @@ ENTRY(ce_aes_ccm_auth_data)
 	mov	v5.16b, v3.16b
 	b	4f
 2:	mov	v4.16b, v3.16b
-	ld1	{v5.2d}, [x6], #16		/* load 2nd round key */
+	ld1	{v5.16b}, [x6], #16		/* load 2nd round key */
 3:	aese	v0.16b, v4.16b
 	aesmc	v0.16b, v0.16b
-4:	ld1	{v3.2d}, [x6], #16		/* load next round key */
+4:	ld1	{v3.16b}, [x6], #16		/* load next round key */
 	aese	v0.16b, v5.16b
 	aesmc	v0.16b, v0.16b
-5:	ld1	{v4.2d}, [x6], #16		/* load next round key */
+5:	ld1	{v4.16b}, [x6], #16		/* load next round key */
 	subs	w7, w7, #3
 	aese	v0.16b, v3.16b
 	aesmc	v0.16b, v0.16b
-	ld1	{v5.2d}, [x6], #16		/* load next round key */
+	ld1	{v5.16b}, [x6], #16		/* load next round key */
 	bpl	3b
 	aese	v0.16b, v4.16b
 	subs	w2, w2, #16			/* last data? */
@@ -60,7 +61,7 @@ ENTRY(ce_aes_ccm_auth_data)
 	ld1	{v1.16b}, [x1], #16		/* load next input block */
 	eor	v0.16b, v0.16b, v1.16b		/* xor with mac */
 	bne	1b
-6:	st1	{v0.2d}, [x0]			/* store mac */
+6:	st1	{v0.16b}, [x0]			/* store mac */
 	beq	10f
 	adds	w2, w2, #16
 	beq	10f
@@ -79,7 +80,7 @@ ENTRY(ce_aes_ccm_auth_data)
 	adds	w7, w7, #1
 	bne	9b
 	eor	v0.16b, v0.16b, v1.16b
-	st1	{v0.2d}, [x0]
+	st1	{v0.16b}, [x0]
 10:	str	w8, [x3]
 	ret
 ENDPROC(ce_aes_ccm_auth_data)
@@ -89,27 +90,27 @@ ENDPROC(ce_aes_ccm_auth_data)
 	 * 			 u32 rounds);
 	 */
 ENTRY(ce_aes_ccm_final)
-	ld1	{v3.2d}, [x2], #16		/* load first round key */
-	ld1	{v0.2d}, [x0]			/* load mac */
+	ld1	{v3.16b}, [x2], #16		/* load first round key */
+	ld1	{v0.16b}, [x0]			/* load mac */
 	cmp	w3, #12				/* which key size? */
 	sub	w3, w3, #2			/* modified # of rounds */
-	ld1	{v1.2d}, [x1]			/* load 1st ctriv */
+	ld1	{v1.16b}, [x1]			/* load 1st ctriv */
 	bmi	0f
 	bne	3f
 	mov	v5.16b, v3.16b
 	b	2f
 0:	mov	v4.16b, v3.16b
-1:	ld1	{v5.2d}, [x2], #16		/* load next round key */
+1:	ld1	{v5.16b}, [x2], #16		/* load next round key */
 	aese	v0.16b, v4.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v4.16b
 	aesmc	v1.16b, v1.16b
-2:	ld1	{v3.2d}, [x2], #16		/* load next round key */
+2:	ld1	{v3.16b}, [x2], #16		/* load next round key */
 	aese	v0.16b, v5.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v5.16b
 	aesmc	v1.16b, v1.16b
-3:	ld1	{v4.2d}, [x2], #16		/* load next round key */
+3:	ld1	{v4.16b}, [x2], #16		/* load next round key */
 	subs	w3, w3, #3
 	aese	v0.16b, v3.16b
 	aesmc	v0.16b, v0.16b
@@ -120,47 +121,47 @@ ENTRY(ce_aes_ccm_final)
 	aese	v1.16b, v4.16b
 	/* final round key cancels out */
 	eor	v0.16b, v0.16b, v1.16b		/* en-/decrypt the mac */
-	st1	{v0.2d}, [x0]			/* store result */
+	st1	{v0.16b}, [x0]			/* store result */
 	ret
 ENDPROC(ce_aes_ccm_final)
 
 	.macro	aes_ccm_do_crypt,enc
 	ldr	x8, [x6, #8]			/* load lower ctr */
-	ld1	{v0.2d}, [x5]			/* load mac */
-	rev	x8, x8				/* keep swabbed ctr in reg */
+	ld1	{v0.16b}, [x5]			/* load mac */
+CPU_LE(	rev	x8, x8			)	/* keep swabbed ctr in reg */
 0:	/* outer loop */
-	ld1	{v1.1d}, [x6]			/* load upper ctr */
+	ld1	{v1.8b}, [x6]			/* load upper ctr */
 	prfm	pldl1strm, [x1]
 	add	x8, x8, #1
 	rev	x9, x8
 	cmp	w4, #12				/* which key size? */
 	sub	w7, w4, #2			/* get modified # of rounds */
 	ins	v1.d[1], x9			/* no carry in lower ctr */
-	ld1	{v3.2d}, [x3]			/* load first round key */
+	ld1	{v3.16b}, [x3]			/* load first round key */
 	add	x10, x3, #16
 	bmi	1f
 	bne	4f
 	mov	v5.16b, v3.16b
 	b	3f
 1:	mov	v4.16b, v3.16b
-	ld1	{v5.2d}, [x10], #16		/* load 2nd round key */
+	ld1	{v5.16b}, [x10], #16		/* load 2nd round key */
 2:	/* inner loop: 3 rounds, 2x interleaved */
 	aese	v0.16b, v4.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v4.16b
 	aesmc	v1.16b, v1.16b
-3:	ld1	{v3.2d}, [x10], #16		/* load next round key */
+3:	ld1	{v3.16b}, [x10], #16		/* load next round key */
 	aese	v0.16b, v5.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v5.16b
 	aesmc	v1.16b, v1.16b
-4:	ld1	{v4.2d}, [x10], #16		/* load next round key */
+4:	ld1	{v4.16b}, [x10], #16		/* load next round key */
 	subs	w7, w7, #3
 	aese	v0.16b, v3.16b
 	aesmc	v0.16b, v0.16b
 	aese	v1.16b, v3.16b
 	aesmc	v1.16b, v1.16b
-	ld1	{v5.2d}, [x10], #16		/* load next round key */
+	ld1	{v5.16b}, [x10], #16		/* load next round key */
 	bpl	2b
 	aese	v0.16b, v4.16b
 	aese	v1.16b, v4.16b
@@ -177,14 +178,14 @@ ENDPROC(ce_aes_ccm_final)
 	eor	v0.16b, v0.16b, v2.16b		/* xor mac with pt ^ rk[last] */
 	st1	{v1.16b}, [x0], #16		/* write output block */
 	bne	0b
-	rev	x8, x8
-	st1	{v0.2d}, [x5]			/* store mac */
+CPU_LE(	rev	x8, x8			)
+	st1	{v0.16b}, [x5]			/* store mac */
 	str	x8, [x6, #8]			/* store lsb end of ctr (BE) */
 5:	ret
 
 6:	eor	v0.16b, v0.16b, v5.16b		/* final round mac */
 	eor	v1.16b, v1.16b, v5.16b		/* final round enc */
-	st1	{v0.2d}, [x5]			/* store mac */
+	st1	{v0.16b}, [x5]			/* store mac */
 	add	w2, w2, #16			/* process partial tail block */
 7:	ldrb	w9, [x1], #1			/* get 1 byte of input */
 	umov	w6, v1.b[0]			/* get top crypted ctr byte */

arch/arm64/crypto/aes-ce-cipher.c

@@ -47,24 +47,24 @@ static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 	kernel_neon_begin_partial(4);
 
 	__asm__("	ld1	{v0.16b}, %[in]			;"
-		"	ld1	{v1.2d}, [%[key]], #16		;"
+		"	ld1	{v1.16b}, [%[key]], #16		;"
 		"	cmp	%w[rounds], #10			;"
 		"	bmi	0f				;"
 		"	bne	3f				;"
 		"	mov	v3.16b, v1.16b			;"
 		"	b	2f				;"
 		"0:	mov	v2.16b, v1.16b			;"
-		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	ld1	{v3.16b}, [%[key]], #16		;"
 		"1:	aese	v0.16b, v2.16b			;"
 		"	aesmc	v0.16b, v0.16b			;"
-		"2:	ld1	{v1.2d}, [%[key]], #16		;"
+		"2:	ld1	{v1.16b}, [%[key]], #16		;"
 		"	aese	v0.16b, v3.16b			;"
 		"	aesmc	v0.16b, v0.16b			;"
-		"3:	ld1	{v2.2d}, [%[key]], #16		;"
+		"3:	ld1	{v2.16b}, [%[key]], #16		;"
 		"	subs	%w[rounds], %w[rounds], #3	;"
 		"	aese	v0.16b, v1.16b			;"
 		"	aesmc	v0.16b, v0.16b			;"
-		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	ld1	{v3.16b}, [%[key]], #16		;"
 		"	bpl	1b				;"
 		"	aese	v0.16b, v2.16b			;"
 		"	eor	v0.16b, v0.16b, v3.16b		;"
@@ -92,24 +92,24 @@ static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 	kernel_neon_begin_partial(4);
 
 	__asm__("	ld1	{v0.16b}, %[in]			;"
-		"	ld1	{v1.2d}, [%[key]], #16		;"
+		"	ld1	{v1.16b}, [%[key]], #16		;"
 		"	cmp	%w[rounds], #10			;"
 		"	bmi	0f				;"
 		"	bne	3f				;"
 		"	mov	v3.16b, v1.16b			;"
 		"	b	2f				;"
 		"0:	mov	v2.16b, v1.16b			;"
-		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	ld1	{v3.16b}, [%[key]], #16		;"
 		"1:	aesd	v0.16b, v2.16b			;"
 		"	aesimc	v0.16b, v0.16b			;"
-		"2:	ld1	{v1.2d}, [%[key]], #16		;"
+		"2:	ld1	{v1.16b}, [%[key]], #16		;"
 		"	aesd	v0.16b, v3.16b			;"
 		"	aesimc	v0.16b, v0.16b			;"
-		"3:	ld1	{v2.2d}, [%[key]], #16		;"
+		"3:	ld1	{v2.16b}, [%[key]], #16		;"
 		"	subs	%w[rounds], %w[rounds], #3	;"
 		"	aesd	v0.16b, v1.16b			;"
 		"	aesimc	v0.16b, v0.16b			;"
-		"	ld1	{v3.2d}, [%[key]], #16		;"
+		"	ld1	{v3.16b}, [%[key]], #16		;"
 		"	bpl	1b				;"
 		"	aesd	v0.16b, v2.16b			;"
 		"	eor	v0.16b, v0.16b, v3.16b		;"
@@ -173,7 +173,12 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
 		u32 *rki = ctx->key_enc + (i * kwords);
 		u32 *rko = rki + kwords;
 
+#ifndef CONFIG_CPU_BIG_ENDIAN
 		rko[0] = ror32(aes_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0];
+#else
+		rko[0] = rol32(aes_sub(rki[kwords - 1]), 8) ^ (rcon[i] << 24) ^
+			 rki[0];
+#endif
 		rko[1] = rko[0] ^ rki[1];
 		rko[2] = rko[1] ^ rki[2];
 		rko[3] = rko[2] ^ rki[3];

arch/arm64/crypto/aes-ce.S

@@ -10,6 +10,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #define AES_ENTRY(func)		ENTRY(ce_ ## func)
 #define AES_ENDPROC(func)	ENDPROC(ce_ ## func)

arch/arm64/crypto/aes-modes.S

@@ -193,15 +193,16 @@ AES_ENTRY(aes_cbc_encrypt)
 	cbz		w6, .Lcbcencloop
 
 	ld1		{v0.16b}, [x5]			/* get iv */
-	enc_prepare	w3, x2, x5
+	enc_prepare	w3, x2, x6
 
 .Lcbcencloop:
 	ld1		{v1.16b}, [x1], #16		/* get next pt block */
 	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with iv */
-	encrypt_block	v0, w3, x2, x5, w6
+	encrypt_block	v0, w3, x2, x6, w7
 	st1		{v0.16b}, [x0], #16
 	subs		w4, w4, #1
 	bne		.Lcbcencloop
+	st1		{v0.16b}, [x5]			/* return iv */
 	ret
 AES_ENDPROC(aes_cbc_encrypt)
 
@@ -211,7 +212,7 @@ AES_ENTRY(aes_cbc_decrypt)
 	cbz		w6, .LcbcdecloopNx
 
 	ld1		{v7.16b}, [x5]			/* get iv */
-	dec_prepare	w3, x2, x5
+	dec_prepare	w3, x2, x6
 
 .LcbcdecloopNx:
 #if INTERLEAVE >= 2
@@ -248,7 +249,7 @@ AES_ENTRY(aes_cbc_decrypt)
 .Lcbcdecloop:
 	ld1		{v1.16b}, [x1], #16		/* get next ct block */
 	mov		v0.16b, v1.16b			/* ...and copy to v0 */
-	decrypt_block	v0, w3, x2, x5, w6
+	decrypt_block	v0, w3, x2, x6, w7
 	eor		v0.16b, v0.16b, v7.16b		/* xor with iv => pt */
 	mov		v7.16b, v1.16b			/* ct is next iv */
 	st1		{v0.16b}, [x0], #16
@@ -256,6 +257,7 @@ AES_ENTRY(aes_cbc_decrypt)
 	bne		.Lcbcdecloop
 .Lcbcdecout:
 	FRAME_POP
+	st1		{v7.16b}, [x5]			/* return iv */
 	ret
 AES_ENDPROC(aes_cbc_decrypt)
 
@@ -267,24 +269,15 @@ AES_ENDPROC(aes_cbc_decrypt)
 
 AES_ENTRY(aes_ctr_encrypt)
 	FRAME_PUSH
-	cbnz		w6, .Lctrfirst		/* 1st time around? */
-	umov		x5, v4.d[1]		/* keep swabbed ctr in reg */
-	rev		x5, x5
-#if INTERLEAVE >= 2
-	cmn		w5, w4			/* 32 bit overflow? */
-	bcs		.Lctrinc
-	add		x5, x5, #1		/* increment BE ctr */
-	b		.LctrincNx
-#else
-	b		.Lctrinc
-#endif
-.Lctrfirst:
+	cbz		w6, .Lctrnotfirst	/* 1st time around? */
 	enc_prepare	w3, x2, x6
 	ld1		{v4.16b}, [x5]
-	umov		x5, v4.d[1]		/* keep swabbed ctr in reg */
-	rev		x5, x5
+
+.Lctrnotfirst:
+	umov		x8, v4.d[1]		/* keep swabbed ctr in reg */
+	rev		x8, x8
 #if INTERLEAVE >= 2
-	cmn		w5, w4			/* 32 bit overflow? */
+	cmn		w8, w4			/* 32 bit overflow? */
 	bcs		.Lctrloop
 .LctrloopNx:
 	subs		w4, w4, #INTERLEAVE
@@ -292,11 +285,11 @@ AES_ENTRY(aes_ctr_encrypt)
 #if INTERLEAVE == 2
 	mov		v0.8b, v4.8b
 	mov		v1.8b, v4.8b
-	rev		x7, x5
-	add		x5, x5, #1
+	rev		x7, x8
+	add		x8, x8, #1
 	ins		v0.d[1], x7
-	rev		x7, x5
-	add		x5, x5, #1
+	rev		x7, x8
+	add		x8, x8, #1
 	ins		v1.d[1], x7
 	ld1		{v2.16b-v3.16b}, [x1], #32	/* get 2 input blocks */
 	do_encrypt_block2x
@@ -305,7 +298,7 @@ AES_ENTRY(aes_ctr_encrypt)
 	st1		{v0.16b-v1.16b}, [x0], #32
 #else
 	ldr		q8, =0x30000000200000001	/* addends 1,2,3[,0] */
-	dup		v7.4s, w5
+	dup		v7.4s, w8
 	mov		v0.16b, v4.16b
 	add		v7.4s, v7.4s, v8.4s
 	mov		v1.16b, v4.16b
@@ -323,18 +316,12 @@ AES_ENTRY(aes_ctr_encrypt)
 	eor		v2.16b, v7.16b, v2.16b
 	eor		v3.16b, v5.16b, v3.16b
 	st1		{v0.16b-v3.16b}, [x0], #64
-	add		x5, x5, #INTERLEAVE
+	add		x8, x8, #INTERLEAVE
 #endif
-	cbz		w4, .LctroutNx
-.LctrincNx:
-	rev		x7, x5
+	rev		x7, x8
 	ins		v4.d[1], x7
+	cbz		w4, .Lctrout
 	b		.LctrloopNx
-.LctroutNx:
-	sub		x5, x5, #1
-	rev		x7, x5
-	ins		v4.d[1], x7
-	b		.Lctrout
 .Lctr1x:
 	adds		w4, w4, #INTERLEAVE
 	beq		.Lctrout
@@ -342,30 +329,39 @@ AES_ENTRY(aes_ctr_encrypt)
 .Lctrloop:
 	mov		v0.16b, v4.16b
 	encrypt_block	v0, w3, x2, x6, w7
+
+	adds		x8, x8, #1		/* increment BE ctr */
+	rev		x7, x8
+	ins		v4.d[1], x7
+	bcs		.Lctrcarry		/* overflow? */
+
+.Lctrcarrydone:
 	subs		w4, w4, #1
 	bmi		.Lctrhalfblock		/* blocks < 0 means 1/2 block */
 	ld1		{v3.16b}, [x1], #16
 	eor		v3.16b, v0.16b, v3.16b
 	st1		{v3.16b}, [x0], #16
-	beq		.Lctrout
-.Lctrinc:
-	adds		x5, x5, #1		/* increment BE ctr */
-	rev		x7, x5
-	ins		v4.d[1], x7
-	bcc		.Lctrloop		/* no overflow? */
+	bne		.Lctrloop
+
+.Lctrout:
+	st1		{v4.16b}, [x5]		/* return next CTR value */
+	FRAME_POP
+	ret
+
+.Lctrhalfblock:
+	ld1		{v3.8b}, [x1]
+	eor		v3.8b, v0.8b, v3.8b
+	st1		{v3.8b}, [x0]
+	FRAME_POP
+	ret
+
+.Lctrcarry:
 	umov		x7, v4.d[0]		/* load upper word of ctr  */
 	rev		x7, x7			/* ... to handle the carry */
 	add		x7, x7, #1
 	rev		x7, x7
 	ins		v4.d[0], x7
-	b		.Lctrloop
-.Lctrhalfblock:
-	ld1		{v3.8b}, [x1]
-	eor		v3.8b, v0.8b, v3.8b
-	st1		{v3.8b}, [x0]
-.Lctrout:
-	FRAME_POP
-	ret
+	b		.Lctrcarrydone
 AES_ENDPROC(aes_ctr_encrypt)
 	.ltorg
 
@@ -386,7 +382,8 @@ AES_ENDPROC(aes_ctr_encrypt)
 	.endm
 
 .Lxts_mul_x:
-	.word		1, 0, 0x87, 0
+CPU_LE(	.quad		1, 0x87		)
+CPU_BE(	.quad		0x87, 1		)
 
 AES_ENTRY(aes_xts_encrypt)
 	FRAME_PUSH

arch/arm64/crypto/aes-neon.S

@@ -9,6 +9,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 #define AES_ENTRY(func)		ENTRY(neon_ ## func)
 #define AES_ENDPROC(func)	ENDPROC(neon_ ## func)
@@ -83,13 +84,13 @@
 	.endm
 
 	.macro		do_block, enc, in, rounds, rk, rkp, i
-	ld1		{v15.16b}, [\rk]
+	ld1		{v15.4s}, [\rk]
 	add		\rkp, \rk, #16
 	mov		\i, \rounds
 1111:	eor		\in\().16b, \in\().16b, v15.16b		/* ^round key */
 	tbl		\in\().16b, {\in\().16b}, v13.16b	/* ShiftRows */
 	sub_bytes	\in
-	ld1		{v15.16b}, [\rkp], #16
+	ld1		{v15.4s}, [\rkp], #16
 	subs		\i, \i, #1
 	beq		2222f
 	.if		\enc == 1
@@ -229,7 +230,7 @@
 	.endm
 
 	.macro		do_block_2x, enc, in0, in1 rounds, rk, rkp, i
-	ld1		{v15.16b}, [\rk]
+	ld1		{v15.4s}, [\rk]
 	add		\rkp, \rk, #16
 	mov		\i, \rounds
 1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
@@ -237,7 +238,7 @@
 	sub_bytes_2x	\in0, \in1
 	tbl		\in0\().16b, {\in0\().16b}, v13.16b	/* ShiftRows */
 	tbl		\in1\().16b, {\in1\().16b}, v13.16b	/* ShiftRows */
-	ld1		{v15.16b}, [\rkp], #16
+	ld1		{v15.4s}, [\rkp], #16
 	subs		\i, \i, #1
 	beq		2222f
 	.if		\enc == 1
@@ -254,7 +255,7 @@
 	.endm
 
 	.macro		do_block_4x, enc, in0, in1, in2, in3, rounds, rk, rkp, i
-	ld1		{v15.16b}, [\rk]
+	ld1		{v15.4s}, [\rk]
 	add		\rkp, \rk, #16
 	mov		\i, \rounds
 1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
@@ -266,7 +267,7 @@
 	tbl		\in1\().16b, {\in1\().16b}, v13.16b	/* ShiftRows */
 	tbl		\in2\().16b, {\in2\().16b}, v13.16b	/* ShiftRows */
 	tbl		\in3\().16b, {\in3\().16b}, v13.16b	/* ShiftRows */
-	ld1		{v15.16b}, [\rkp], #16
+	ld1		{v15.4s}, [\rkp], #16
 	subs		\i, \i, #1
 	beq		2222f
 	.if		\enc == 1
@@ -306,12 +307,16 @@
 	.text
 	.align		4
 .LForward_ShiftRows:
-	.byte		0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3
-	.byte		0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb
+CPU_LE(	.byte		0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3	)
+CPU_LE(	.byte		0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb	)
+CPU_BE(	.byte		0xb, 0x6, 0x1, 0xc, 0x7, 0x2, 0xd, 0x8	)
+CPU_BE(	.byte		0x3, 0xe, 0x9, 0x4, 0xf, 0xa, 0x5, 0x0	)
 
 .LReverse_ShiftRows:
-	.byte		0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb
-	.byte		0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3
+CPU_LE(	.byte		0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb	)
+CPU_LE(	.byte		0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3	)
+CPU_BE(	.byte		0x3, 0x6, 0x9, 0xc, 0xf, 0x2, 0x5, 0x8	)
+CPU_BE(	.byte		0xb, 0xe, 0x1, 0x4, 0x7, 0xa, 0xd, 0x0	)
 
 .LForward_Sbox:
 	.byte		0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5

arch/arm64/crypto/ghash-ce-core.S

@@ -29,8 +29,8 @@
 	 *			   struct ghash_key const *k, const char *head)
 	 */
 ENTRY(pmull_ghash_update)
-	ld1		{SHASH.16b}, [x3]
-	ld1		{XL.16b}, [x1]
+	ld1		{SHASH.2d}, [x3]
+	ld1		{XL.2d}, [x1]
 	movi		MASK.16b, #0xe1
 	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
 	shl		MASK.2d, MASK.2d, #57
@@ -74,6 +74,6 @@ CPU_LE(	rev64		T1.16b, T1.16b	)
 
 	cbnz		w0, 0b
 
-	st1		{XL.16b}, [x1]
+	st1		{XL.2d}, [x1]
 	ret
 ENDPROC(pmull_ghash_update)

arch/arm64/crypto/sha1-ce-core.S

@@ -78,7 +78,7 @@ ENTRY(sha1_ce_transform)
 	ld1r		{k3.4s}, [x6]
 
 	/* load state */
-	ldr		dga, [x0]
+	ld1		{dgav.4s}, [x0]
 	ldr		dgb, [x0, #16]
 
 	/* load sha1_ce_state::finalize */
@@ -144,7 +144,7 @@ CPU_LE(	rev32		v11.16b, v11.16b	)
 	b		1b
 
 	/* store new state */
-3:	str		dga, [x0]
+3:	st1		{dgav.4s}, [x0]
 	str		dgb, [x0, #16]
 	ret
 ENDPROC(sha1_ce_transform)

arch/arm64/crypto/sha2-ce-core.S

@@ -85,7 +85,7 @@ ENTRY(sha2_ce_transform)
 	ld1		{v12.4s-v15.4s}, [x8]
 
 	/* load state */
-	ldp		dga, dgb, [x0]
+	ld1		{dgav.4s, dgbv.4s}, [x0]
 
 	/* load sha256_ce_state::finalize */
 	ldr		w4, [x0, #:lo12:sha256_ce_offsetof_finalize]
@@ -148,6 +148,6 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 	b		1b
 
 	/* store new state */
-3:	stp		dga, dgb, [x0]
+3:	st1		{dgav.4s, dgbv.4s}, [x0]
 	ret
 ENDPROC(sha2_ce_transform)

arch/arm64/include/asm/alternative.h

@@ -2,6 +2,7 @@
 #define __ASM_ALTERNATIVE_H
 
 #include <asm/cpufeature.h>
+#include <asm/insn.h>
 
 #ifndef __ASSEMBLY__
 
@@ -90,24 +91,15 @@ void apply_alternatives(void *start, size_t length);
 .endm
 
 /*
- * Begin an alternative code sequence.
+ * Alternative sequences
  *
- * The code that follows this macro will be assembled and linked as
- * normal. There are no restrictions on this code.
- */
-.macro alternative_if_not cap
-	.pushsection .altinstructions, "a"
-	altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f
-	.popsection
-661:
-.endm
-
-/*
- * Provide the alternative code sequence.
+ * The code for the case where the capability is not present will be
+ * assembled and linked as normal. There are no restrictions on this
+ * code.
  *
- * The code that follows this macro is assembled into a special
- * section to be used for dynamic patching. Code that follows this
- * macro must:
+ * The code for the case where the capability is present will be
+ * assembled into a special section to be used for dynamic patching.
+ * Code for that case must:
  *
  * 1. Be exactly the same length (in bytes) as the default code
  *    sequence.
@@ -116,8 +108,38 @@ void apply_alternatives(void *start, size_t length);
  *    alternative sequence it is defined in (branches into an
  *    alternative sequence are not fixed up).
  */
+
+/*
+ * Begin an alternative code sequence.
+ */
+.macro alternative_if_not cap
+	.set .Lasm_alt_mode, 0
+	.pushsection .altinstructions, "a"
+	altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f
+	.popsection
+661:
+.endm
+
+.macro alternative_if cap
+	.set .Lasm_alt_mode, 1
+	.pushsection .altinstructions, "a"
+	altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f
+	.popsection
+	.pushsection .altinstr_replacement, "ax"
+	.align 2	/* So GAS knows label 661 is suitably aligned */
+661:
+.endm
+
+/*
+ * Provide the other half of the alternative code sequence.
+ */
 .macro alternative_else
-662:	.pushsection .altinstr_replacement, "ax"
+662:
+	.if .Lasm_alt_mode==0
+	.pushsection .altinstr_replacement, "ax"
+	.else
+	.popsection
+	.endif
 663:
 .endm
 
@@ -125,11 +147,25 @@ void apply_alternatives(void *start, size_t length);
  * Complete an alternative code sequence.
  */
 .macro alternative_endif
-664:	.popsection
+664:
+	.if .Lasm_alt_mode==0
+	.popsection
+	.endif
 	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
 .endm
 
+/*
+ * Provides a trivial alternative or default sequence consisting solely
+ * of NOPs. The number of NOPs is chosen automatically to match the
+ * previous case.
+ */
+.macro alternative_else_nop_endif
+alternative_else
+	nops	(662b-661b) / AARCH64_INSN_SIZE
+alternative_endif
+.endm
+
 #define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...)	\
 	alternative_insn insn1, insn2, cap, IS_ENABLED(cfg)
 

arch/arm64/include/asm/assembler.h

@@ -107,6 +107,15 @@
 	dmb	\opt
 	.endm
 
+/*
+ * NOP sequence
+ */
+	.macro	nops, num
+	.rept	\num
+	nop
+	.endr
+	.endm
+
 /*
  * Emit an entry into the exception table
  */
@@ -383,15 +392,11 @@ alternative_endif
  */
 	.macro	post_ttbr0_update_workaround
 #ifdef CONFIG_CAVIUM_ERRATUM_27456
-alternative_if_not ARM64_WORKAROUND_CAVIUM_27456
-	nop
-	nop
-	nop
-alternative_else
+alternative_if ARM64_WORKAROUND_CAVIUM_27456
 	ic	iallu
 	dsb	nsh
 	isb
-alternative_endif
+alternative_else_nop_endif
 #endif
 	.endm
 

arch/arm64/include/asm/barrier.h

@@ -20,6 +20,9 @@
 
 #ifndef __ASSEMBLY__
 
+#define __nops(n)	".rept	" #n "\nnop\n.endr\n"
+#define nops(n)		asm volatile(__nops(n))
+
 #define sev()		asm volatile("sev" : : : "memory")
 #define wfe()		asm volatile("wfe" : : : "memory")
 #define wfi()		asm volatile("wfi" : : : "memory")

arch/arm64/include/asm/futex.h

@@ -21,10 +21,7 @@
 #include <linux/futex.h>
 #include <linux/uaccess.h>
 
-#include <asm/alternative.h>
-#include <asm/cpufeature.h>
 #include <asm/errno.h>
-#include <asm/sysreg.h>
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg)		\
 do {									\

arch/arm64/include/asm/mmu_context.h

@@ -218,9 +218,11 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	 * Update the saved TTBR0_EL1 of the scheduled-in task as the previous
 	 * value may have not been initialised yet (activate_mm caller) or the
 	 * ASID has changed since the last run (following the context switch
-	 * of another thread of the same process).
+	 * of another thread of the same process). Avoid setting the reserved
+	 * TTBR0_EL1 to swapper_pg_dir (init_mm; e.g. via idle_task_exit).
 	 */
-	update_saved_ttbr0(tsk, next);
+	if (next != &init_mm)
+		update_saved_ttbr0(tsk, next);
 }
 
 #define deactivate_mm(tsk,mm)	do { } while (0)

arch/arm64/include/asm/ptrace.h

@@ -21,8 +21,6 @@
 
 #include <uapi/asm/ptrace.h>
 
-#define _PSR_PAN_BIT		22
-
 /* Current Exception Level values, as contained in CurrentEL */
 #define CurrentEL_EL1		(1 << 2)
 #define CurrentEL_EL2		(2 << 2)

arch/arm64/include/asm/thread_info.h

@@ -47,10 +47,10 @@ typedef unsigned long mm_segment_t;
 struct thread_info {
 	unsigned long		flags;		/* low level flags */
 	mm_segment_t		addr_limit;	/* address limit */
+	struct task_struct	*task;		/* main task structure */
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 	u64			ttbr0;		/* saved TTBR0_EL1 */
 #endif
-	struct task_struct	*task;		/* main task structure */
 	int			preempt_count;	/* 0 => preemptable, <0 => bug */
 	int			cpu;		/* cpu */
 };

arch/arm64/include/asm/uaccess.h

@@ -18,6 +18,10 @@
 #ifndef __ASM_UACCESS_H
 #define __ASM_UACCESS_H
 
+#include <asm/alternative.h>
+#include <asm/kernel-pgtable.h>
+#include <asm/sysreg.h>
+
 #ifndef __ASSEMBLY__
 
 /*
@@ -26,11 +30,8 @@
 #include <linux/string.h>
 #include <linux/thread_info.h>
 
-#include <asm/alternative.h>
 #include <asm/cpufeature.h>
-#include <asm/kernel-pgtable.h>
 #include <asm/ptrace.h>
-#include <asm/sysreg.h>
 #include <asm/errno.h>
 #include <asm/memory.h>
 #include <asm/compiler.h>
@@ -130,7 +131,7 @@ static inline void set_fs(mm_segment_t fs)
  * User access enabling/disabling.
  */
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
-static inline void uaccess_ttbr0_disable(void)
+static inline void __uaccess_ttbr0_disable(void)
 {
 	unsigned long ttbr;
 
@@ -140,7 +141,7 @@ static inline void uaccess_ttbr0_disable(void)
 	isb();
 }
 
-static inline void uaccess_ttbr0_enable(void)
+static inline void __uaccess_ttbr0_enable(void)
 {
 	unsigned long flags;
 
@@ -154,30 +155,44 @@ static inline void uaccess_ttbr0_enable(void)
 	isb();
 	local_irq_restore(flags);
 }
-#else
-static inline void uaccess_ttbr0_disable(void)
+
+static inline bool uaccess_ttbr0_disable(void)
 {
+	if (!system_uses_ttbr0_pan())
+		return false;
+	__uaccess_ttbr0_disable();
+	return true;
 }
 
-static inline void uaccess_ttbr0_enable(void)
+static inline bool uaccess_ttbr0_enable(void)
 {
+	if (!system_uses_ttbr0_pan())
+		return false;
+	__uaccess_ttbr0_enable();
+	return true;
+}
+#else
+static inline bool uaccess_ttbr0_disable(void)
+{
+	return false;
+}
+
+static inline bool uaccess_ttbr0_enable(void)
+{
+	return false;
 }
 #endif
 
 #define __uaccess_disable(alt)						\
 do {									\
-	if (system_uses_ttbr0_pan())					\
-		uaccess_ttbr0_disable();				\
-	else								\
+	if (!uaccess_ttbr0_disable())					\
 		asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), alt,		\
 				CONFIG_ARM64_PAN));			\
 } while (0)
 
 #define __uaccess_enable(alt)						\
 do {									\
-	if (system_uses_ttbr0_pan())					\
-		uaccess_ttbr0_enable();					\
-	else								\
+	if (!uaccess_ttbr0_enable())					\
 		asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), alt,		\
 				CONFIG_ARM64_PAN));			\
 } while (0)
@@ -407,69 +422,62 @@ extern __must_check long strnlen_user(const char __user *str, long n);
 
 #else	/* __ASSEMBLY__ */
 
-#include <asm/alternative.h>
 #include <asm/assembler.h>
-#include <asm/kernel-pgtable.h>
 
 /*
  * User access enabling/disabling macros.
  */
-	.macro	uaccess_ttbr0_disable, tmp1
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	.macro	__uaccess_ttbr0_disable, tmp1
 	mrs	\tmp1, ttbr1_el1		// swapper_pg_dir
 	add	\tmp1, \tmp1, #SWAPPER_DIR_SIZE	// reserved_ttbr0 at the end of swapper_pg_dir
 	msr	ttbr0_el1, \tmp1		// set reserved TTBR0_EL1
 	isb
 	.endm
 
-	.macro	uaccess_ttbr0_enable, tmp1
+	.macro	__uaccess_ttbr0_enable, tmp1
 	get_thread_info \tmp1
-	ldr	\tmp1, [\tmp1, #TI_TTBR0]	// load saved TTBR0_EL1
+	ldr	\tmp1, [\tmp1, #TSK_TI_TTBR0]	// load saved TTBR0_EL1
 	msr	ttbr0_el1, \tmp1		// set the non-PAN TTBR0_EL1
 	isb
 	.endm
 
+	.macro	uaccess_ttbr0_disable, tmp1
+alternative_if_not ARM64_HAS_PAN
+	__uaccess_ttbr0_disable \tmp1
+alternative_else_nop_endif
+	.endm
+
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+alternative_if_not ARM64_HAS_PAN
+	save_and_disable_irq \tmp2		// avoid preemption
+	__uaccess_ttbr0_enable \tmp1
+	restore_irq \tmp2
+alternative_else_nop_endif
+	.endm
+#else
+	.macro	uaccess_ttbr0_disable, tmp1
+	.endm
+
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+	.endm
+#endif
+
 /*
  * These macros are no-ops when UAO is present.
  */
 	.macro	uaccess_disable_not_uao, tmp1
-#ifdef CONFIG_ARM64_SW_TTBR0_PAN
-alternative_if_not ARM64_HAS_PAN
 	uaccess_ttbr0_disable \tmp1
-alternative_else
-	nop
-	nop
-	nop
-	nop
-alternative_endif
-#endif
-alternative_if_not ARM64_ALT_PAN_NOT_UAO
-	nop
-alternative_else
+alternative_if ARM64_ALT_PAN_NOT_UAO
 	SET_PSTATE_PAN(1)
-alternative_endif
+alternative_else_nop_endif
 	.endm
 
 	.macro	uaccess_enable_not_uao, tmp1, tmp2
-#ifdef CONFIG_ARM64_SW_TTBR0_PAN
-alternative_if_not ARM64_HAS_PAN
-	save_and_disable_irq \tmp2		// avoid preemption
-	uaccess_ttbr0_enable \tmp1
-	restore_irq \tmp2
-alternative_else
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-alternative_endif
-#endif
-alternative_if_not ARM64_ALT_PAN_NOT_UAO
-	nop
-alternative_else
+	uaccess_ttbr0_enable \tmp1, \tmp2
+alternative_if ARM64_ALT_PAN_NOT_UAO
 	SET_PSTATE_PAN(0)
-alternative_endif
+alternative_else_nop_endif
 	.endm
 
 #endif	/* __ASSEMBLY__ */

arch/arm64/include/uapi/asm/ptrace.h

@@ -77,6 +77,7 @@ struct user_fpsimd_state {
 	__uint128_t	vregs[32];
 	__u32		fpsr;
 	__u32		fpcr;
+	__u32		__reserved[2];
 };
 
 struct user_hwdebug_state {

arch/arm64/kernel/armv8_deprecated.c

@@ -14,7 +14,6 @@
 #include <linux/slab.h>
 #include <linux/sysctl.h>
 
-#include <asm/alternative.h>
 #include <asm/cpufeature.h>
 #include <asm/insn.h>
 #include <asm/opcodes.h>

arch/arm64/kernel/asm-offsets.c

@@ -38,11 +38,11 @@ int main(void)
   DEFINE(TI_FLAGS,		offsetof(struct thread_info, flags));
   DEFINE(TI_PREEMPT,		offsetof(struct thread_info, preempt_count));
   DEFINE(TI_ADDR_LIMIT,		offsetof(struct thread_info, addr_limit));
-#ifdef CONFIG_ARM64_SW_TTBR0_PAN
-  DEFINE(TI_TTBR0,		offsetof(struct thread_info, ttbr0));
-#endif
   DEFINE(TI_TASK,		offsetof(struct thread_info, task));
   DEFINE(TI_CPU,		offsetof(struct thread_info, cpu));
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+  DEFINE(TSK_TI_TTBR0,		offsetof(struct thread_info, ttbr0));
+#endif
   BLANK();
   DEFINE(THREAD_CPU_CONTEXT,	offsetof(struct task_struct, thread.cpu_context));
   BLANK();

arch/arm64/kernel/entry.S

@@ -120,11 +120,9 @@
 	 * feature as all TTBR0_EL1 accesses are disabled, not just those to
 	 * user mappings.
 	 */
-alternative_if_not ARM64_HAS_PAN
-	nop
-alternative_else
+alternative_if ARM64_HAS_PAN
 	b	1f				// skip TTBR0 PAN
-alternative_endif
+alternative_else_nop_endif
 
 	.if	\el != 0
 	mrs	x21, ttbr0_el1
@@ -134,7 +132,7 @@ alternative_endif
 	and	x23, x23, #~PSR_PAN_BIT		// Clear the emulated PAN in the saved SPSR
 	.endif
 
-	uaccess_ttbr0_disable x21
+	__uaccess_ttbr0_disable x21
 1:
 #endif
 
@@ -181,17 +179,15 @@ alternative_endif
 	 * Restore access to TTBR0_EL1. If returning to EL0, no need for SPSR
 	 * PAN bit checking.
 	 */
-alternative_if_not ARM64_HAS_PAN
-	nop
-alternative_else
+alternative_if ARM64_HAS_PAN
 	b	2f				// skip TTBR0 PAN
-alternative_endif
+alternative_else_nop_endif
 
 	.if	\el != 0
-	tbnz	x22, #_PSR_PAN_BIT, 1f		// Skip re-enabling TTBR0 access if previously disabled
+	tbnz	x22, #22, 1f			// Skip re-enabling TTBR0 access if the PSR_PAN_BIT is set
 	.endif
 
-	uaccess_ttbr0_enable x0
+	__uaccess_ttbr0_enable x0
 
 	.if	\el == 0
 	/*
@@ -681,7 +677,7 @@ el0_inv:
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
 	mov	x2, x25
-	bl	bad_mode
+	bl	bad_el0_sync
 	b	ret_to_user
 ENDPROC(el0_sync)
 

arch/arm64/kernel/ptrace.c

@@ -550,6 +550,8 @@ static int hw_break_set(struct task_struct *target,
 	/* (address, ctrl) registers */
 	limit = regset->n * regset->size;
 	while (count && offset < limit) {
+		if (count < PTRACE_HBP_ADDR_SZ)
+			return -EINVAL;
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &addr,
 					 offset, offset + PTRACE_HBP_ADDR_SZ);
 		if (ret)
@@ -559,6 +561,8 @@ static int hw_break_set(struct task_struct *target,
 			return ret;
 		offset += PTRACE_HBP_ADDR_SZ;
 
+		if (!count)
+			break;
 		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl,
 					 offset, offset + PTRACE_HBP_CTRL_SZ);
 		if (ret)
@@ -595,7 +599,7 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct user_pt_regs newregs;
+	struct user_pt_regs newregs = task_pt_regs(target)->user_regs;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newregs, 0, -1);
 	if (ret)
@@ -625,7 +629,8 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct user_fpsimd_state newstate;
+	struct user_fpsimd_state newstate =
+		target->thread.fpsimd_state.user_fpsimd;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, 0, -1);
 	if (ret)
@@ -649,7 +654,7 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	unsigned long tls;
+	unsigned long tls = target->thread.tp_value;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
 	if (ret)
@@ -675,7 +680,8 @@ static int system_call_set(struct task_struct *target,
 			   unsigned int pos, unsigned int count,
 			   const void *kbuf, const void __user *ubuf)
 {
-	int syscallno, ret;
+	int syscallno = task_pt_regs(target)->syscallno;
+	int ret;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &syscallno, 0, -1);
 	if (ret)
@@ -947,7 +953,7 @@ static int compat_tls_set(struct task_struct *target,
 			  const void __user *ubuf)
 {
 	int ret;
-	compat_ulong_t tls;
+	compat_ulong_t tls = target->thread.tp_value;
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
 	if (ret)

arch/arm64/kernel/traps.c

@@ -469,16 +469,33 @@ const char *esr_get_class_string(u32 esr)
 }
 
 /*
- * bad_mode handles the impossible case in the exception vector.
+ * bad_mode handles the impossible case in the exception vector. This is always
+ * fatal.
  */
 asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
+{
+	console_verbose();
+
+	pr_crit("Bad mode in %s handler detected, code 0x%08x -- %s\n",
+		handler[reason], esr, esr_get_class_string(esr));
+
+	die("Oops - bad mode", regs, 0);
+	local_irq_disable();
+	panic("bad mode");
+}
+
+/*
+ * bad_el0_sync handles unexpected, but potentially recoverable synchronous
+ * exceptions taken from EL0. Unlike bad_mode, this returns.
+ */
+asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
 {
 	siginfo_t info;
 	void __user *pc = (void __user *)instruction_pointer(regs);
 	console_verbose();
 
-	pr_crit("Bad mode in %s handler detected, code 0x%08x -- %s\n",
-		handler[reason], esr, esr_get_class_string(esr));
+	pr_crit("Bad EL0 synchronous exception detected on CPU%d, code 0x%08x -- %s\n",
+		smp_processor_id(), esr, esr_get_class_string(esr));
 	__show_regs(regs);
 
 	info.si_signo = SIGILL;
@@ -486,7 +503,10 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 	info.si_code  = ILL_ILLOPC;
 	info.si_addr  = pc;
 
-	arm64_notify_die("Oops - bad mode", regs, &info, 0);
+	current->thread.fault_address = 0;
+	current->thread.fault_code = 0;
+
+	force_sig_info(info.si_signo, &info, current);
 }
 
 void __pte_error(const char *file, int line, unsigned long val)

arch/arm64/lib/clear_user.S

@@ -17,9 +17,6 @@
  */
 #include <linux/linkage.h>
 
-#include <asm/assembler.h>
-#include <asm/cpufeature.h>
-#include <asm/sysreg.h>
 #include <asm/uaccess.h>
 
 	.text

arch/arm64/lib/copy_from_user.S

@@ -16,10 +16,7 @@
 
 #include <linux/linkage.h>
 
-#include <asm/assembler.h>
 #include <asm/cache.h>
-#include <asm/cpufeature.h>
-#include <asm/sysreg.h>
 #include <asm/uaccess.h>
 
 /*

arch/arm64/lib/copy_in_user.S

@@ -18,10 +18,7 @@
 
 #include <linux/linkage.h>
 
-#include <asm/assembler.h>
 #include <asm/cache.h>
-#include <asm/cpufeature.h>
-#include <asm/sysreg.h>
 #include <asm/uaccess.h>
 
 /*

arch/arm64/lib/copy_to_user.S

@@ -16,10 +16,7 @@
 
 #include <linux/linkage.h>
 
-#include <asm/assembler.h>
 #include <asm/cache.h>
-#include <asm/cpufeature.h>
-#include <asm/sysreg.h>
 #include <asm/uaccess.h>
 
 /*

arch/arm64/mm/cache.S

@@ -23,6 +23,7 @@
 #include <asm/assembler.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative.h>
+#include <asm/uaccess.h>
 
 /*
  *	flush_icache_range(start,end)
@@ -48,6 +49,7 @@ ENTRY(flush_icache_range)
  *	- end     - virtual end address of region
  */
 ENTRY(__flush_cache_user_range)
+	uaccess_ttbr0_enable x2, x3
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	bic	x4, x0, x3
@@ -69,10 +71,12 @@ USER(9f, ic	ivau, x4	)		// invalidate I line PoU
 	dsb	ish
 	isb
 	mov	x0, #0
+1:
+	uaccess_ttbr0_disable x1
 	ret
 9:
 	mov	x0, #-EFAULT
-	ret
+	b	1b
 ENDPROC(flush_icache_range)
 ENDPROC(__flush_cache_user_range)
 

arch/arm64/mm/fault.c

@@ -510,10 +510,10 @@ static const struct fault_info {
 	{ do_bad,		SIGBUS,  0,		"unknown 17"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 18"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 19"			},
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
 	{ do_bad,		SIGBUS,  0,		"synchronous parity error"	},
 	{ do_bad,		SIGBUS,  0,		"unknown 25"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 26"			},

arch/arm64/xen/hypercall.S

@@ -90,7 +90,6 @@ ENTRY(privcmd_call)
 	mov x2, x3
 	mov x3, x4
 	mov x4, x5
-#ifdef CONFIG_ARM64_SW_TTBR0_PAN
 	/*
 	 * Privcmd calls are issued by the userspace. The kernel needs to
 	 * enable access to TTBR0_EL1 as the hypervisor would issue stage 1
@@ -99,15 +98,12 @@ ENTRY(privcmd_call)
 	 * need the explicit uaccess_enable/disable if the TTBR0 PAN emulation
 	 * is enabled (it implies that hardware UAO and PAN disabled).
 	 */
-	uaccess_enable_not_uao x6, x7
-#endif
+	uaccess_ttbr0_enable x6, x7
 	hvc XEN_IMM
 
-#ifdef CONFIG_ARM64_SW_TTBR0_PAN
 	/*
 	 * Disable userspace access from kernel once the hyp call completed.
 	 */
-	uaccess_disable_not_uao x6
-#endif
+	uaccess_ttbr0_disable x6
 	ret
 ENDPROC(privcmd_call);

arch/cris/boot/rescue/Makefile

@@ -10,6 +10,9 @@
 
 asflags-y += $(LINUXINCLUDE)
 ccflags-y += -O2 $(LINUXINCLUDE)
+
+ifdef CONFIG_ETRAX_AXISFLASHMAP
+
 arch-$(CONFIG_ETRAX_ARCH_V10) = v10
 arch-$(CONFIG_ETRAX_ARCH_V32) = v32
 
@@ -28,6 +31,11 @@ $(obj)/rescue.bin: $(obj)/rescue.o FORCE
 	$(call if_changed,objcopy)
 	cp -p $(obj)/rescue.bin $(objtree)
 
+else
+$(obj)/rescue.bin:
+
+endif
+
 $(obj)/testrescue.bin: $(obj)/testrescue.o
 	$(OBJCOPY) $(OBJCOPYFLAGS) $(obj)/testrescue.o tr.bin
 # Pad it to 784 bytes

arch/mips/kvm/mips.c

@@ -324,8 +324,8 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 #endif
 
 	/* Invalidate the icache for these ranges */
-	local_flush_icache_range((unsigned long)gebase,
-				(unsigned long)gebase + ALIGN(size, PAGE_SIZE));
+	flush_icache_range((unsigned long)gebase,
+			   (unsigned long)gebase + ALIGN(size, PAGE_SIZE));
 
 	/*
 	 * Allocate comm page for guest kernel, a TLB will be reserved for

arch/parisc/include/asm/bitops.h

@@ -6,7 +6,7 @@
 #endif
 
 #include <linux/compiler.h>
-#include <asm/types.h>		/* for BITS_PER_LONG/SHIFT_PER_LONG */
+#include <asm/types.h>
 #include <asm/byteorder.h>
 #include <asm/barrier.h>
 #include <linux/atomic.h>
@@ -17,6 +17,12 @@
  * to include/asm-i386/bitops.h or kerneldoc
  */
 
+#if __BITS_PER_LONG == 64
+#define SHIFT_PER_LONG 6
+#else
+#define SHIFT_PER_LONG 5
+#endif
+
 #define CHOP_SHIFTCOUNT(x) (((unsigned long) (x)) & (BITS_PER_LONG - 1))
 
 

arch/parisc/include/uapi/asm/bitsperlong.h

@@ -3,10 +3,8 @@
 
 #if defined(__LP64__)
 #define __BITS_PER_LONG 64
-#define SHIFT_PER_LONG 6
 #else
 #define __BITS_PER_LONG 32
-#define SHIFT_PER_LONG 5
 #endif
 
 #include <asm-generic/bitsperlong.h>

arch/parisc/include/uapi/asm/swab.h

@@ -1,6 +1,7 @@
 #ifndef _PARISC_SWAB_H
 #define _PARISC_SWAB_H
 
+#include <asm/bitsperlong.h>
 #include <linux/types.h>
 #include <linux/compiler.h>
 
@@ -38,7 +39,7 @@ static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 }
 #define __arch_swab32 __arch_swab32
 
-#if BITS_PER_LONG > 32
+#if __BITS_PER_LONG > 32
 /*
 ** From "PA-RISC 2.0 Architecture", HP Professional Books.
 ** See Appendix I page 8 , "Endian Byte Swapping".
@@ -61,6 +62,6 @@ static inline __attribute_const__ __u64 __arch_swab64(__u64 x)
 	return x;
 }
 #define __arch_swab64 __arch_swab64
-#endif /* BITS_PER_LONG > 32 */
+#endif /* __BITS_PER_LONG > 32 */
 
 #endif /* _PARISC_SWAB_H */

arch/powerpc/kernel/eeh_driver.c

@@ -485,7 +485,7 @@ static void *eeh_pe_detach_dev(void *data, void *userdata)
 static void *__eeh_clear_pe_frozen_state(void *data, void *flag)
 {
 	struct eeh_pe *pe = (struct eeh_pe *)data;
-	bool *clear_sw_state = flag;
+	bool clear_sw_state = *(bool *)flag;
 	int i, rc = 1;
 
 	for (i = 0; rc && i < 3; i++)

arch/powerpc/kernel/ibmebus.c

@@ -180,6 +180,7 @@ static int ibmebus_create_device(struct device_node *dn)
 static int ibmebus_create_devices(const struct of_device_id *matches)
 {
 	struct device_node *root, *child;
+	struct device *dev;
 	int ret = 0;
 
 	root = of_find_node_by_path("/");
@@ -188,9 +189,12 @@ static int ibmebus_create_devices(const struct of_device_id *matches)
 		if (!of_match_node(matches, child))
 			continue;
 
-		if (bus_find_device(&ibmebus_bus_type, NULL, child,
-				    ibmebus_match_node))
+		dev = bus_find_device(&ibmebus_bus_type, NULL, child,
+				      ibmebus_match_node);
+		if (dev) {
+			put_device(dev);
 			continue;
+		}
 
 		ret = ibmebus_create_device(child);
 		if (ret) {
@@ -262,6 +266,7 @@ static ssize_t ibmebus_store_probe(struct bus_type *bus,
 				   const char *buf, size_t count)
 {
 	struct device_node *dn = NULL;
+	struct device *dev;
 	char *path;
 	ssize_t rc = 0;
 
@@ -269,8 +274,10 @@ static ssize_t ibmebus_store_probe(struct bus_type *bus,
 	if (!path)
 		return -ENOMEM;
 
-	if (bus_find_device(&ibmebus_bus_type, NULL, path,
-			    ibmebus_match_path)) {
+	dev = bus_find_device(&ibmebus_bus_type, NULL, path,
+			      ibmebus_match_path);
+	if (dev) {
+		put_device(dev);
 		printk(KERN_WARNING "%s: %s has already been probed\n",
 		       __func__, path);
 		rc = -EEXIST;
@@ -307,6 +314,7 @@ static ssize_t ibmebus_store_remove(struct bus_type *bus,
 	if ((dev = bus_find_device(&ibmebus_bus_type, NULL, path,
 				   ibmebus_match_path))) {
 		of_device_unregister(to_platform_device(dev));
+		put_device(dev);
 
 		kfree(path);
 		return count;

arch/powerpc/kernel/misc_32.S

@@ -313,7 +313,7 @@ _GLOBAL(flush_instruction_cache)
 	lis	r3, KERNELBASE@h
 	iccci	0,r3
 #endif
-#elif CONFIG_FSL_BOOKE
+#elif defined(CONFIG_FSL_BOOKE)
 BEGIN_FTR_SECTION
 	mfspr   r3,SPRN_L1CSR0
 	ori     r3,r3,L1CSR0_CFI|L1CSR0_CLFC

arch/powerpc/kernel/prom_init.c

@@ -2664,6 +2664,9 @@ static void __init prom_find_boot_cpu(void)
 
 	cpu_pkg = call_prom("instance-to-package", 1, 1, prom_cpu);
 
+	if (!PHANDLE_VALID(cpu_pkg))
+		return;
+
 	prom_getprop(cpu_pkg, "reg", &rval, sizeof(rval));
 	prom.cpu = be32_to_cpu(rval);
 

arch/s390/crypto/prng.c

@@ -565,8 +565,10 @@ static ssize_t prng_tdes_read(struct file *file, char __user *ubuf,
 		prng_data->prngws.byte_counter += n;
 		prng_data->prngws.reseed_counter += n;
 
-		if (copy_to_user(ubuf, prng_data->buf, chunk))
-			return -EFAULT;
+		if (copy_to_user(ubuf, prng_data->buf, chunk)) {
+			ret = -EFAULT;
+			break;
+		}
 
 		nbytes -= chunk;
 		ret += chunk;

arch/s390/kernel/ptrace.c

@@ -963,6 +963,11 @@ static int s390_fpregs_set(struct task_struct *target,
 	if (target == current)
 		save_fpu_regs();
 
+	if (MACHINE_HAS_VX)
+		convert_vx_to_fp(fprs, target->thread.fpu.vxrs);
+	else
+		memcpy(&fprs, target->thread.fpu.fprs, sizeof(fprs));
+
 	/* If setting FPC, must validate it first. */
 	if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) {
 		u32 ufpc[2] = { target->thread.fpu.fpc, 0 };
@@ -1067,6 +1072,9 @@ static int s390_vxrs_low_set(struct task_struct *target,
 	if (target == current)
 		save_fpu_regs();
 
+	for (i = 0; i < __NUM_VXRS_LOW; i++)
+		vxrs[i] = *((__u64 *)(target->thread.fpu.vxrs + i) + 1);
+
 	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
 	if (rc == 0)
 		for (i = 0; i < __NUM_VXRS_LOW; i++)

arch/tile/kernel/ptrace.c

@@ -111,7 +111,7 @@ static int tile_gpr_set(struct task_struct *target,
 			  const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct pt_regs regs;
+	struct pt_regs regs = *task_pt_regs(target);
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &regs, 0,
 				 sizeof(regs));

arch/x86/kernel/apic/io_apic.c

@@ -2115,6 +2115,7 @@ static inline void __init check_timer(void)
 			if (idx != -1 && irq_trigger(idx))
 				unmask_ioapic_irq(irq_get_chip_data(0));
 		}
+		irq_domain_deactivate_irq(irq_data);
 		irq_domain_activate_irq(irq_data);
 		if (timer_irq_works()) {
 			if (disable_timer_pin_1 > 0)
@@ -2136,6 +2137,7 @@ static inline void __init check_timer(void)
 		 * legacy devices should be connected to IO APIC #0
 		 */
 		replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2);
+		irq_domain_deactivate_irq(irq_data);
 		irq_domain_activate_irq(irq_data);
 		legacy_pic->unmask(0);
 		if (timer_irq_works()) {

arch/x86/kernel/cpu/common.c

@@ -1129,7 +1129,7 @@ static __init int setup_disablecpuid(char *arg)
 {
 	int bit;
 
-	if (get_option(&arg, &bit) && bit < NCAPINTS*32)
+	if (get_option(&arg, &bit) && bit >= 0 && bit < NCAPINTS * 32)
 		setup_clear_cpu_cap(bit);
 	else
 		return 0;

arch/x86/kernel/hpet.c

@@ -351,6 +351,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer)
 	} else {
 		struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
 
+		irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
 		irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
 		disable_irq(hdev->irq);
 		irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));

arch/x86/kernel/mcount_64.S

@@ -180,7 +180,8 @@ GLOBAL(ftrace_graph_call)
 	jmp ftrace_stub
 #endif
 
-GLOBAL(ftrace_stub)
+/* This is weak to keep gas from relaxing the jumps */
+WEAK(ftrace_stub)
 	retq
 END(ftrace_caller)
 

arch/x86/kvm/emulate.c

@@ -172,6 +172,7 @@
 #define NearBranch  ((u64)1 << 52)  /* Near branches */
 #define No16	    ((u64)1 << 53)  /* No 16 bit operand */
 #define IncSP       ((u64)1 << 54)  /* SP is incremented before ModRM calc */
+#define Aligned16   ((u64)1 << 55)  /* Aligned to 16 byte boundary (e.g. FXSAVE) */
 
 #define DstXacc     (DstAccLo | SrcAccHi | SrcWrite)
 
@@ -434,6 +435,26 @@ FOP_END;
 FOP_START(salc) "pushf; sbb %al, %al; popf \n\t" FOP_RET
 FOP_END;
 
+/*
+ * XXX: inoutclob user must know where the argument is being expanded.
+ *      Relying on CC_HAVE_ASM_GOTO would allow us to remove _fault.
+ */
+#define asm_safe(insn, inoutclob...) \
+({ \
+	int _fault = 0; \
+ \
+	asm volatile("1:" insn "\n" \
+	             "2:\n" \
+	             ".pushsection .fixup, \"ax\"\n" \
+	             "3: movl $1, %[_fault]\n" \
+	             "   jmp  2b\n" \
+	             ".popsection\n" \
+	             _ASM_EXTABLE(1b, 3b) \
+	             : [_fault] "+qm"(_fault) inoutclob ); \
+ \
+	_fault ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; \
+})
+
 static int emulator_check_intercept(struct x86_emulate_ctxt *ctxt,
 				    enum x86_intercept intercept,
 				    enum x86_intercept_stage stage)
@@ -620,21 +641,24 @@ static void set_segment_selector(struct x86_emulate_ctxt *ctxt, u16 selector,
  * depending on whether they're AVX encoded or not.
  *
  * Also included is CMPXCHG16B which is not a vector instruction, yet it is
- * subject to the same check.
+ * subject to the same check.  FXSAVE and FXRSTOR are checked here too as their
+ * 512 bytes of data must be aligned to a 16 byte boundary.
  */
-static bool insn_aligned(struct x86_emulate_ctxt *ctxt, unsigned size)
+static unsigned insn_alignment(struct x86_emulate_ctxt *ctxt, unsigned size)
 {
 	if (likely(size < 16))
-		return false;
+		return 1;
 
 	if (ctxt->d & Aligned)
-		return true;
+		return size;
 	else if (ctxt->d & Unaligned)
-		return false;
+		return 1;
 	else if (ctxt->d & Avx)
-		return false;
+		return 1;
+	else if (ctxt->d & Aligned16)
+		return 16;
 	else
-		return true;
+		return size;
 }
 
 static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
@@ -692,7 +716,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 		}
 		break;
 	}
-	if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0))
+	if (la & (insn_alignment(ctxt, size) - 1))
 		return emulate_gp(ctxt, 0);
 	return X86EMUL_CONTINUE;
 bad:
@@ -779,6 +803,20 @@ static int segmented_read_std(struct x86_emulate_ctxt *ctxt,
 	return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception);
 }
 
+static int segmented_write_std(struct x86_emulate_ctxt *ctxt,
+			       struct segmented_address addr,
+			       void *data,
+			       unsigned int size)
+{
+	int rc;
+	ulong linear;
+
+	rc = linearize(ctxt, addr, size, true, &linear);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+	return ctxt->ops->write_std(ctxt, linear, data, size, &ctxt->exception);
+}
+
 /*
  * Prefetch the remaining bytes of the instruction without crossing page
  * boundary if they are not in fetch_cache yet.
@@ -1532,7 +1570,6 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 				    &ctxt->exception);
 }
 
-/* Does not support long mode */
 static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 				     u16 selector, int seg, u8 cpl,
 				     enum x86_transfer_type transfer,
@@ -1569,20 +1606,34 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 
 	rpl = selector & 3;
 
-	/* NULL selector is not valid for TR, CS and SS (except for long mode) */
-	if ((seg == VCPU_SREG_CS
-	     || (seg == VCPU_SREG_SS
-		 && (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl))
-	     || seg == VCPU_SREG_TR)
-	    && null_selector)
-		goto exception;
-
 	/* TR should be in GDT only */
 	if (seg == VCPU_SREG_TR && (selector & (1 << 2)))
 		goto exception;
 
-	if (null_selector) /* for NULL selector skip all following checks */
+	/* NULL selector is not valid for TR, CS and (except for long mode) SS */
+	if (null_selector) {
+		if (seg == VCPU_SREG_CS || seg == VCPU_SREG_TR)
+			goto exception;
+
+		if (seg == VCPU_SREG_SS) {
+			if (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl)
+				goto exception;
+
+			/*
+			 * ctxt->ops->set_segment expects the CPL to be in
+			 * SS.DPL, so fake an expand-up 32-bit data segment.
+			 */
+			seg_desc.type = 3;
+			seg_desc.p = 1;
+			seg_desc.s = 1;
+			seg_desc.dpl = cpl;
+			seg_desc.d = 1;
+			seg_desc.g = 1;
+		}
+
+		/* Skip all following checks */
 		goto load;
+	}
 
 	ret = read_segment_descriptor(ctxt, selector, &seg_desc, &desc_addr);
 	if (ret != X86EMUL_CONTINUE)
@@ -1698,6 +1749,21 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 				   u16 selector, int seg)
 {
 	u8 cpl = ctxt->ops->cpl(ctxt);
+
+	/*
+	 * None of MOV, POP and LSS can load a NULL selector in CPL=3, but
+	 * they can load it at CPL<3 (Intel's manual says only LSS can,
+	 * but it's wrong).
+	 *
+	 * However, the Intel manual says that putting IST=1/DPL=3 in
+	 * an interrupt gate will result in SS=3 (the AMD manual instead
+	 * says it doesn't), so allow SS=3 in __load_segment_descriptor
+	 * and only forbid it here.
+	 */
+	if (seg == VCPU_SREG_SS && selector == 3 &&
+	    ctxt->mode == X86EMUL_MODE_PROT64)
+		return emulate_exception(ctxt, GP_VECTOR, 0, true);
+
 	return __load_segment_descriptor(ctxt, selector, seg, cpl,
 					 X86_TRANSFER_NONE, NULL);
 }
@@ -3646,8 +3712,8 @@ static int emulate_store_desc_ptr(struct x86_emulate_ctxt *ctxt,
 	}
 	/* Disable writeback. */
 	ctxt->dst.type = OP_NONE;
-	return segmented_write(ctxt, ctxt->dst.addr.mem,
-			       &desc_ptr, 2 + ctxt->op_bytes);
+	return segmented_write_std(ctxt, ctxt->dst.addr.mem,
+				   &desc_ptr, 2 + ctxt->op_bytes);
 }
 
 static int em_sgdt(struct x86_emulate_ctxt *ctxt)
@@ -3830,6 +3896,131 @@ static int em_movsxd(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
+static int check_fxsr(struct x86_emulate_ctxt *ctxt)
+{
+	u32 eax = 1, ebx, ecx = 0, edx;
+
+	ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+	if (!(edx & FFL(FXSR)))
+		return emulate_ud(ctxt);
+
+	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
+		return emulate_nm(ctxt);
+
+	/*
+	 * Don't emulate a case that should never be hit, instead of working
+	 * around a lack of fxsave64/fxrstor64 on old compilers.
+	 */
+	if (ctxt->mode >= X86EMUL_MODE_PROT64)
+		return X86EMUL_UNHANDLEABLE;
+
+	return X86EMUL_CONTINUE;
+}
+
+/*
+ * FXSAVE and FXRSTOR have 4 different formats depending on execution mode,
+ *  1) 16 bit mode
+ *  2) 32 bit mode
+ *     - like (1), but FIP and FDP (foo) are only 16 bit.  At least Intel CPUs
+ *       preserve whole 32 bit values, though, so (1) and (2) are the same wrt.
+ *       save and restore
+ *  3) 64-bit mode with REX.W prefix
+ *     - like (2), but XMM 8-15 are being saved and restored
+ *  4) 64-bit mode without REX.W prefix
+ *     - like (3), but FIP and FDP are 64 bit
+ *
+ * Emulation uses (3) for (1) and (2) and preserves XMM 8-15 to reach the
+ * desired result.  (4) is not emulated.
+ *
+ * Note: Guest and host CPUID.(EAX=07H,ECX=0H):EBX[bit 13] (deprecate FPU CS
+ * and FPU DS) should match.
+ */
+static int em_fxsave(struct x86_emulate_ctxt *ctxt)
+{
+	struct fxregs_state fx_state;
+	size_t size;
+	int rc;
+
+	rc = check_fxsr(ctxt);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	ctxt->ops->get_fpu(ctxt);
+
+	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
+
+	ctxt->ops->put_fpu(ctxt);
+
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR)
+		size = offsetof(struct fxregs_state, xmm_space[8 * 16/4]);
+	else
+		size = offsetof(struct fxregs_state, xmm_space[0]);
+
+	return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
+}
+
+static int fxrstor_fixup(struct x86_emulate_ctxt *ctxt,
+		struct fxregs_state *new)
+{
+	int rc = X86EMUL_CONTINUE;
+	struct fxregs_state old;
+
+	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(old));
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	/*
+	 * 64 bit host will restore XMM 8-15, which is not correct on non-64
+	 * bit guests.  Load the current values in order to preserve 64 bit
+	 * XMMs after fxrstor.
+	 */
+#ifdef CONFIG_X86_64
+	/* XXX: accessing XMM 8-15 very awkwardly */
+	memcpy(&new->xmm_space[8 * 16/4], &old.xmm_space[8 * 16/4], 8 * 16);
+#endif
+
+	/*
+	 * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but
+	 * does save and restore MXCSR.
+	 */
+	if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))
+		memcpy(new->xmm_space, old.xmm_space, 8 * 16);
+
+	return rc;
+}
+
+static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
+{
+	struct fxregs_state fx_state;
+	int rc;
+
+	rc = check_fxsr(ctxt);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, 512);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	if (fx_state.mxcsr >> 16)
+		return emulate_gp(ctxt, 0);
+
+	ctxt->ops->get_fpu(ctxt);
+
+	if (ctxt->mode < X86EMUL_MODE_PROT64)
+		rc = fxrstor_fixup(ctxt, &fx_state);
+
+	if (rc == X86EMUL_CONTINUE)
+		rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state));
+
+	ctxt->ops->put_fpu(ctxt);
+
+	return rc;
+}
+
 static bool valid_cr(int nr)
 {
 	switch (nr) {
@@ -4182,7 +4373,9 @@ static const struct gprefix pfx_0f_ae_7 = {
 };
 
 static const struct group_dual group15 = { {
-	N, N, N, N, N, N, N, GP(0, &pfx_0f_ae_7),
+	I(ModRM | Aligned16, em_fxsave),
+	I(ModRM | Aligned16, em_fxrstor),
+	N, N, N, N, N, GP(0, &pfx_0f_ae_7),
 }, {
 	N, N, N, N, N, N, N, N,
 } };
@@ -5054,21 +5247,13 @@ static bool string_insn_completed(struct x86_emulate_ctxt *ctxt)
 
 static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt)
 {
-	bool fault = false;
+	int rc;
 
 	ctxt->ops->get_fpu(ctxt);
-	asm volatile("1: fwait \n\t"
-		     "2: \n\t"
-		     ".pushsection .fixup,\"ax\" \n\t"
-		     "3: \n\t"
-		     "movb $1, %[fault] \n\t"
-		     "jmp 2b \n\t"
-		     ".popsection \n\t"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [fault]"+qm"(fault));
+	rc = asm_safe("fwait");
 	ctxt->ops->put_fpu(ctxt);
 
-	if (unlikely(fault))
+	if (unlikely(rc != X86EMUL_CONTINUE))
 		return emulate_exception(ctxt, MF_VECTOR, 0, false);
 
 	return X86EMUL_CONTINUE;

arch/x86/kvm/lapic.c

@@ -2187,3 +2187,9 @@ void kvm_lapic_init(void)
 	jump_label_rate_limit(&apic_hw_disabled, HZ);
 	jump_label_rate_limit(&apic_sw_disabled, HZ);
 }
+
+void kvm_lapic_exit(void)
+{
+	static_key_deferred_flush(&apic_hw_disabled);
+	static_key_deferred_flush(&apic_sw_disabled);
+}

arch/x86/kvm/lapic.h

@@ -95,6 +95,7 @@ static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
 
 int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);
 void kvm_lapic_init(void);
+void kvm_lapic_exit(void);
 
 static inline u32 kvm_apic_get_reg(struct kvm_lapic *apic, int reg_off)
 {

arch/x86/kvm/vmx.c

@@ -4867,6 +4867,12 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	if (vmx_xsaves_supported())
 		vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);
 
+	if (enable_pml) {
+		ASSERT(vmx->pml_pg);
+		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+	}
+
 	return 0;
 }
 
@@ -7839,22 +7845,6 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
 	*info2 = vmcs_read32(VM_EXIT_INTR_INFO);
 }
 
-static int vmx_create_pml_buffer(struct vcpu_vmx *vmx)
-{
-	struct page *pml_pg;
-
-	pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
-	if (!pml_pg)
-		return -ENOMEM;
-
-	vmx->pml_pg = pml_pg;
-
-	vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
-	vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
-
-	return 0;
-}
-
 static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx)
 {
 	if (vmx->pml_pg) {
@@ -8789,14 +8779,26 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_vcpu;
 
+	err = -ENOMEM;
+
+	/*
+	 * If PML is turned on, failure on enabling PML just results in failure
+	 * of creating the vcpu, therefore we can simplify PML logic (by
+	 * avoiding dealing with cases, such as enabling PML partially on vcpus
+	 * for the guest, etc.
+	 */
+	if (enable_pml) {
+		vmx->pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!vmx->pml_pg)
+			goto uninit_vcpu;
+	}
+
 	vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0])
 		     > PAGE_SIZE);
 
-	err = -ENOMEM;
-	if (!vmx->guest_msrs) {
-		goto uninit_vcpu;
-	}
+	if (!vmx->guest_msrs)
+		goto free_pml;
 
 	vmx->loaded_vmcs = &vmx->vmcs01;
 	vmx->loaded_vmcs->vmcs = alloc_vmcs();
@@ -8840,18 +8842,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	vmx->nested.current_vmptr = -1ull;
 	vmx->nested.current_vmcs12 = NULL;
 
-	/*
-	 * If PML is turned on, failure on enabling PML just results in failure
-	 * of creating the vcpu, therefore we can simplify PML logic (by
-	 * avoiding dealing with cases, such as enabling PML partially on vcpus
-	 * for the guest, etc.
-	 */
-	if (enable_pml) {
-		err = vmx_create_pml_buffer(vmx);
-		if (err)
-			goto free_vmcs;
-	}
-
 	return &vmx->vcpu;
 
 free_vmcs:
@@ -8859,6 +8849,8 @@ free_vmcs:
 	free_loaded_vmcs(vmx->loaded_vmcs);
 free_msrs:
 	kfree(vmx->guest_msrs);
+free_pml:
+	vmx_destroy_pml_buffer(vmx);
 uninit_vcpu:
 	kvm_vcpu_uninit(&vmx->vcpu);
 free_vcpu:

arch/x86/kvm/x86.c

@@ -2949,6 +2949,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 	memset(&events->reserved, 0, sizeof(events->reserved));
 }
 
+static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags);
+
 static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 					      struct kvm_vcpu_events *events)
 {
@@ -2981,10 +2983,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 		vcpu->arch.apic->sipi_vector = events->sipi_vector;
 
 	if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
+		u32 hflags = vcpu->arch.hflags;
 		if (events->smi.smm)
-			vcpu->arch.hflags |= HF_SMM_MASK;
+			hflags |= HF_SMM_MASK;
 		else
-			vcpu->arch.hflags &= ~HF_SMM_MASK;
+			hflags &= ~HF_SMM_MASK;
+		kvm_set_hflags(vcpu, hflags);
+
 		vcpu->arch.smi_pending = events->smi.pending;
 		if (events->smi.smm_inside_nmi)
 			vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
@@ -3052,6 +3057,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 	memcpy(dest, xsave, XSAVE_HDR_OFFSET);
 
 	/* Set XSTATE_BV */
+	xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE;
 	*(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv;
 
 	/*
@@ -5837,6 +5843,7 @@ out:
 
 void kvm_arch_exit(void)
 {
+	kvm_lapic_exit();
 	perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
 
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))

arch/x86/pci/acpi.c

@@ -114,6 +114,16 @@ static const struct dmi_system_id pci_crs_quirks[] __initconst = {
 			DMI_MATCH(DMI_BIOS_VERSION, "6JET85WW (1.43 )"),
 		},
 	},
+	/* https://bugzilla.kernel.org/show_bug.cgi?id=42606 */
+	{
+		.callback = set_nouse_crs,
+		.ident = "Supermicro X8DTH",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Supermicro"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X8DTH-i/6/iF/6F"),
+			DMI_MATCH(DMI_BIOS_VERSION, "2.0a"),
+		},
+	},
 
 	/* https://bugzilla.kernel.org/show_bug.cgi?id=15362 */
 	{

arch/x86/platform/goldfish/goldfish.c

@@ -42,10 +42,22 @@ static struct resource goldfish_pdev_bus_resources[] = {
 	}
 };
 
+static bool goldfish_enable __initdata;
+
+static int __init goldfish_setup(char *str)
+{
+	goldfish_enable = true;
+	return 0;
+}
+__setup("goldfish", goldfish_setup);
+
 static int __init goldfish_init(void)
 {
+	if (!goldfish_enable)
+		return -ENODEV;
+
 	platform_device_register_simple("goldfish_pdev_bus", -1,
-						goldfish_pdev_bus_resources, 2);
+					goldfish_pdev_bus_resources, 2);
 	return 0;
 }
 device_initcall(goldfish_init);

block/blk-mq.c

@@ -842,7 +842,7 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 		return WORK_CPU_UNBOUND;
 
 	if (--hctx->next_cpu_batch <= 0) {
-		int cpu = hctx->next_cpu, next_cpu;
+		int next_cpu;
 
 		next_cpu = cpumask_next(hctx->next_cpu, hctx->cpumask);
 		if (next_cpu >= nr_cpu_ids)
@@ -850,8 +850,6 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 
 		hctx->next_cpu = next_cpu;
 		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
-
-		return cpu;
 	}
 
 	return hctx->next_cpu;
@@ -1261,12 +1259,9 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_queue_split(q, &bio, q->bio_split);
 
-	if (!is_flush_fua && !blk_queue_nomerges(q)) {
-		if (blk_attempt_plug_merge(q, bio, &request_count,
-					   &same_queue_rq))
-			return BLK_QC_T_NONE;
-	} else
-		request_count = blk_plug_queued_count(q);
+	if (!is_flush_fua && !blk_queue_nomerges(q) &&
+	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
+		return BLK_QC_T_NONE;
 
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))
@@ -1357,9 +1352,11 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_queue_split(q, &bio, q->bio_split);
 
-	if (!is_flush_fua && !blk_queue_nomerges(q) &&
-	    blk_attempt_plug_merge(q, bio, &request_count, NULL))
-		return BLK_QC_T_NONE;
+	if (!is_flush_fua && !blk_queue_nomerges(q)) {
+		if (blk_attempt_plug_merge(q, bio, &request_count, NULL))
+			return BLK_QC_T_NONE;
+	} else
+		request_count = blk_plug_queued_count(q);
 
 	rq = blk_mq_map_request(q, bio, &data);
 	if (unlikely(!rq))

block/cfq-iosched.c

@@ -1572,7 +1572,7 @@ static struct blkcg_policy_data *cfq_cpd_alloc(gfp_t gfp)
 {
 	struct cfq_group_data *cgd;
 
-	cgd = kzalloc(sizeof(*cgd), GFP_KERNEL);
+	cgd = kzalloc(sizeof(*cgd), gfp);
 	if (!cgd)
 		return NULL;
 	return &cgd->cpd;

crypto/algapi.c

@@ -357,6 +357,7 @@ int crypto_register_alg(struct crypto_alg *alg)
 	struct crypto_larval *larval;
 	int err;
 
+	alg->cra_flags &= ~CRYPTO_ALG_DEAD;
 	err = crypto_check_alg(alg);
 	if (err)
 		return err;

drivers/acpi/apei/ghes.c

@@ -847,6 +847,8 @@ static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
 		if (ghes_read_estatus(ghes, 1)) {
 			ghes_clear_estatus(ghes);
 			continue;
+		} else {
+			ret = NMI_HANDLED;
 		}
 
 		sev = ghes_severity(ghes->estatus->error_severity);
@@ -858,12 +860,11 @@ static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
 
 		__process_error(ghes);
 		ghes_clear_estatus(ghes);
-
-		ret = NMI_HANDLED;
 	}
 
 #ifdef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
-	irq_work_queue(&ghes_proc_irq_work);
+	if (ret == NMI_HANDLED)
+		irq_work_queue(&ghes_proc_irq_work);
 #endif
 	atomic_dec(&ghes_in_nmi);
 	return ret;

drivers/android/binder.c

@@ -2048,7 +2048,7 @@ static void binder_transaction(struct binder_proc *proc,
 	if (!IS_ALIGNED(extra_buffers_size, sizeof(u64))) {
 		binder_user_error("%d:%d got transaction with unaligned buffers size, %lld\n",
 				  proc->pid, thread->pid,
-				  extra_buffers_size);
+				  (u64)extra_buffers_size);
 		return_error = BR_FAILED_REPLY;
 		goto err_bad_offset;
 	}

drivers/ata/libata-core.c

@@ -4139,10 +4139,10 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "ST380013AS",		"3.20",		ATA_HORKAGE_MAX_SEC_1024 },
 
 	/*
-	 * Device times out with higher max sects.
+	 * These devices time out with higher max sects.
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=121671
 	 */
-	{ "LITEON CX1-JB256-HP", NULL,		ATA_HORKAGE_MAX_SEC_1024 },
+	{ "LITEON CX1-JB*-HP",	NULL,		ATA_HORKAGE_MAX_SEC_1024 },
 
 	/* Devices we expect to fail diagnostics */
 

drivers/ata/sata_mv.c

@@ -4121,6 +4121,9 @@ static int mv_platform_probe(struct platform_device *pdev)
 	host->iomap = NULL;
 	hpriv->base = devm_ioremap(&pdev->dev, res->start,
 				   resource_size(res));
+	if (!hpriv->base)
+		return -ENOMEM;
+
 	hpriv->base -= SATAHC0_REG_BASE;
 
 	hpriv->clk = clk_get(&pdev->dev, NULL);

drivers/base/memory.c

@@ -388,30 +388,29 @@ static ssize_t show_valid_zones(struct device *dev,
 {
 	struct memory_block *mem = to_memory_block(dev);
 	unsigned long start_pfn, end_pfn;
+	unsigned long valid_start, valid_end;
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
-	struct page *first_page;
 	struct zone *zone;
 
 	start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	end_pfn = start_pfn + nr_pages;
-	first_page = pfn_to_page(start_pfn);
 
 	/* The block contains more than one zone can not be offlined. */
-	if (!test_pages_in_a_zone(start_pfn, end_pfn))
+	if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end))
 		return sprintf(buf, "none\n");
 
-	zone = page_zone(first_page);
+	zone = page_zone(pfn_to_page(valid_start));
 
 	if (zone_idx(zone) == ZONE_MOVABLE - 1) {
 		/*The mem block is the last memoryblock of this zone.*/
-		if (end_pfn == zone_end_pfn(zone))
+		if (valid_end == zone_end_pfn(zone))
 			return sprintf(buf, "%s %s\n",
 					zone->name, (zone + 1)->name);
 	}
 
 	if (zone_idx(zone) == ZONE_MOVABLE) {
 		/*The mem block is the first memoryblock of ZONE_MOVABLE.*/
-		if (start_pfn == zone->zone_start_pfn)
+		if (valid_start == zone->zone_start_pfn)
 			return sprintf(buf, "%s %s\n",
 					zone->name, (zone - 1)->name);
 	}

drivers/base/power/power.h

@@ -20,14 +20,22 @@ static inline void pm_runtime_early_init(struct device *dev)
 extern void pm_runtime_init(struct device *dev);
 extern void pm_runtime_remove(struct device *dev);
 
+#define WAKE_IRQ_DEDICATED_ALLOCATED	BIT(0)
+#define WAKE_IRQ_DEDICATED_MANAGED	BIT(1)
+#define WAKE_IRQ_DEDICATED_MASK		(WAKE_IRQ_DEDICATED_ALLOCATED | \
+					 WAKE_IRQ_DEDICATED_MANAGED)
+
 struct wake_irq {
 	struct device *dev;
+	unsigned int status;
 	int irq;
-	bool dedicated_irq:1;
 };
 
 extern void dev_pm_arm_wake_irq(struct wake_irq *wirq);
 extern void dev_pm_disarm_wake_irq(struct wake_irq *wirq);
+extern void dev_pm_enable_wake_irq_check(struct device *dev,
+					 bool can_change_status);
+extern void dev_pm_disable_wake_irq_check(struct device *dev);
 
 #ifdef CONFIG_PM_SLEEP
 
@@ -102,6 +110,15 @@ static inline void dev_pm_disarm_wake_irq(struct wake_irq *wirq)
 {
 }
 
+static inline void dev_pm_enable_wake_irq_check(struct device *dev,
+						bool can_change_status)
+{
+}
+
+static inline void dev_pm_disable_wake_irq_check(struct device *dev)
+{
+}
+
 #endif
 
 #ifdef CONFIG_PM_SLEEP

drivers/base/power/runtime.c

@@ -515,7 +515,7 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 
 	callback = RPM_GET_CALLBACK(dev, runtime_suspend);
 
-	dev_pm_enable_wake_irq(dev);
+	dev_pm_enable_wake_irq_check(dev, true);
 	retval = rpm_callback(callback, dev);
 	if (retval)
 		goto fail;
@@ -554,7 +554,7 @@ static int rpm_suspend(struct device *dev, int rpmflags)
 	return retval;
 
  fail:
-	dev_pm_disable_wake_irq(dev);
+	dev_pm_disable_wake_irq_check(dev);
 	__update_runtime_status(dev, RPM_ACTIVE);
 	dev->power.deferred_resume = false;
 	wake_up_all(&dev->power.wait_queue);
@@ -737,12 +737,12 @@ static int rpm_resume(struct device *dev, int rpmflags)
 
 	callback = RPM_GET_CALLBACK(dev, runtime_resume);
 
-	dev_pm_disable_wake_irq(dev);
+	dev_pm_disable_wake_irq_check(dev);
 	retval = rpm_callback(callback, dev);
 	if (retval) {
 		__update_runtime_status(dev, RPM_SUSPENDED);
 		pm_runtime_cancel_pending(dev);
-		dev_pm_enable_wake_irq(dev);
+		dev_pm_enable_wake_irq_check(dev, false);
 	} else {
  no_callback:
 		__update_runtime_status(dev, RPM_ACTIVE);

drivers/base/power/wakeirq.c

@@ -110,8 +110,10 @@ void dev_pm_clear_wake_irq(struct device *dev)
 	dev->power.wakeirq = NULL;
 	spin_unlock_irqrestore(&dev->power.lock, flags);
 
-	if (wirq->dedicated_irq)
+	if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED) {
 		free_irq(wirq->irq, wirq);
+		wirq->status &= ~WAKE_IRQ_DEDICATED_MASK;
+	}
 	kfree(wirq);
 }
 EXPORT_SYMBOL_GPL(dev_pm_clear_wake_irq);
@@ -179,7 +181,6 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
 
 	wirq->dev = dev;
 	wirq->irq = irq;
-	wirq->dedicated_irq = true;
 	irq_set_status_flags(irq, IRQ_NOAUTOEN);
 
 	/*
@@ -195,6 +196,8 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
 	if (err)
 		goto err_free_irq;
 
+	wirq->status = WAKE_IRQ_DEDICATED_ALLOCATED;
+
 	return err;
 
 err_free_irq:
@@ -210,9 +213,9 @@ EXPORT_SYMBOL_GPL(dev_pm_set_dedicated_wake_irq);
  * dev_pm_enable_wake_irq - Enable device wake-up interrupt
  * @dev: Device
  *
- * Called from the bus code or the device driver for
- * runtime_suspend() to enable the wake-up interrupt while
- * the device is running.
+ * Optionally called from the bus code or the device driver for
+ * runtime_resume() to override the PM runtime core managed wake-up
+ * interrupt handling to enable the wake-up interrupt.
  *
  * Note that for runtime_suspend()) the wake-up interrupts
  * should be unconditionally enabled unlike for suspend()
@@ -222,7 +225,7 @@ void dev_pm_enable_wake_irq(struct device *dev)
 {
 	struct wake_irq *wirq = dev->power.wakeirq;
 
-	if (wirq && wirq->dedicated_irq)
+	if (wirq && (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED))
 		enable_irq(wirq->irq);
 }
 EXPORT_SYMBOL_GPL(dev_pm_enable_wake_irq);
@@ -231,19 +234,72 @@ EXPORT_SYMBOL_GPL(dev_pm_enable_wake_irq);
  * dev_pm_disable_wake_irq - Disable device wake-up interrupt
  * @dev: Device
  *
- * Called from the bus code or the device driver for
- * runtime_resume() to disable the wake-up interrupt while
- * the device is running.
+ * Optionally called from the bus code or the device driver for
+ * runtime_suspend() to override the PM runtime core managed wake-up
+ * interrupt handling to disable the wake-up interrupt.
  */
 void dev_pm_disable_wake_irq(struct device *dev)
 {
 	struct wake_irq *wirq = dev->power.wakeirq;
 
-	if (wirq && wirq->dedicated_irq)
+	if (wirq && (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED))
 		disable_irq_nosync(wirq->irq);
 }
 EXPORT_SYMBOL_GPL(dev_pm_disable_wake_irq);
 
+/**
+ * dev_pm_enable_wake_irq_check - Checks and enables wake-up interrupt
+ * @dev: Device
+ * @can_change_status: Can change wake-up interrupt status
+ *
+ * Enables wakeirq conditionally. We need to enable wake-up interrupt
+ * lazily on the first rpm_suspend(). This is needed as the consumer device
+ * starts in RPM_SUSPENDED state, and the the first pm_runtime_get() would
+ * otherwise try to disable already disabled wakeirq. The wake-up interrupt
+ * starts disabled with IRQ_NOAUTOEN set.
+ *
+ * Should be only called from rpm_suspend() and rpm_resume() path.
+ * Caller must hold &dev->power.lock to change wirq->status
+ */
+void dev_pm_enable_wake_irq_check(struct device *dev,
+				  bool can_change_status)
+{
+	struct wake_irq *wirq = dev->power.wakeirq;
+
+	if (!wirq || !((wirq->status & WAKE_IRQ_DEDICATED_MASK)))
+		return;
+
+	if (likely(wirq->status & WAKE_IRQ_DEDICATED_MANAGED)) {
+		goto enable;
+	} else if (can_change_status) {
+		wirq->status |= WAKE_IRQ_DEDICATED_MANAGED;
+		goto enable;
+	}
+
+	return;
+
+enable:
+	enable_irq(wirq->irq);
+}
+
+/**
+ * dev_pm_disable_wake_irq_check - Checks and disables wake-up interrupt
+ * @dev: Device
+ *
+ * Disables wake-up interrupt conditionally based on status.
+ * Should be only called from rpm_suspend() and rpm_resume() path.
+ */
+void dev_pm_disable_wake_irq_check(struct device *dev)
+{
+	struct wake_irq *wirq = dev->power.wakeirq;
+
+	if (!wirq || !((wirq->status & WAKE_IRQ_DEDICATED_MASK)))
+		return;
+
+	if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED)
+		disable_irq_nosync(wirq->irq);
+}
+
 /**
  * dev_pm_arm_wake_irq - Arm device wake-up
  * @wirq: Device wake-up interrupt

drivers/bus/vexpress-config.c

@@ -171,6 +171,7 @@ static int vexpress_config_populate(struct device_node *node)
 {
 	struct device_node *bridge;
 	struct device *parent;
+	int ret;
 
 	bridge = of_parse_phandle(node, "arm,vexpress,config-bridge", 0);
 	if (!bridge)
@@ -181,7 +182,11 @@ static int vexpress_config_populate(struct device_node *node)
 	if (WARN_ON(!parent))
 		return -ENODEV;
 
-	return of_platform_populate(node, NULL, NULL, parent);
+	ret = of_platform_populate(node, NULL, NULL, parent);
+
+	put_device(parent);
+
+	return ret;
 }
 
 static int __init vexpress_config_init(void)

drivers/clk/clk-wm831x.c

@@ -247,7 +247,7 @@ static int wm831x_clkout_is_prepared(struct clk_hw *hw)
 	if (ret < 0) {
 		dev_err(wm831x->dev, "Unable to read CLOCK_CONTROL_1: %d\n",
 			ret);
-		return true;
+		return false;
 	}
 
 	return (ret & WM831X_CLKOUT_ENA) != 0;

drivers/clk/imx/clk-imx31.c

@@ -157,10 +157,8 @@ static void __init _mx31_clocks_init(unsigned long fref)
 	}
 }
 
-int __init mx31_clocks_init(void)
+int __init mx31_clocks_init(unsigned long fref)
 {
-	u32 fref = 26000000; /* default */
-
 	_mx31_clocks_init(fref);
 
 	clk_register_clkdev(clk[gpt_gate], "per", "imx-gpt.0");

drivers/clocksource/exynos_mct.c

@@ -482,6 +482,7 @@ static void exynos4_local_timer_stop(struct mct_clock_event_device *mevt)
 	if (mct_int_type == MCT_INT_SPI) {
 		if (evt->irq != -1)
 			disable_irq_nosync(evt->irq);
+		exynos4_mct_write(0x1, mevt->base + MCT_L_INT_CSTAT_OFFSET);
 	} else {
 		disable_percpu_irq(mct_irqs[MCT_L0_IRQ]);
 	}

drivers/cpufreq/powernv-cpufreq.c

@@ -373,8 +373,14 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
 	if (unlikely(rebooting) && new_index != get_nominal_index())
 		return 0;
 
-	if (!throttled)
+	if (!throttled) {
+		/* we don't want to be preempted while
+		 * checking if the CPU frequency has been throttled
+		 */
+		preempt_disable();
 		powernv_cpufreq_throttle_check(NULL);
+		preempt_enable();
+	}
 
 	freq_data.pstate_id = powernv_freqs[new_index].driver_data;
 

drivers/dma/pl330.c

@@ -449,6 +449,9 @@ struct dma_pl330_chan {
 
 	/* for cyclic capability */
 	bool cyclic;
+
+	/* for runtime pm tracking */
+	bool active;
 };
 
 struct pl330_dmac {
@@ -2040,6 +2043,7 @@ static void pl330_tasklet(unsigned long data)
 		_stop(pch->thread);
 		spin_unlock(&pch->thread->dmac->lock);
 		power_down = true;
+		pch->active = false;
 	} else {
 		/* Make sure the PL330 Channel thread is active */
 		spin_lock(&pch->thread->dmac->lock);
@@ -2061,6 +2065,7 @@ static void pl330_tasklet(unsigned long data)
 			desc->status = PREP;
 			list_move_tail(&desc->node, &pch->work_list);
 			if (power_down) {
+				pch->active = true;
 				spin_lock(&pch->thread->dmac->lock);
 				_start(pch->thread);
 				spin_unlock(&pch->thread->dmac->lock);
@@ -2175,6 +2180,7 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	unsigned long flags;
 	struct pl330_dmac *pl330 = pch->dmac;
 	LIST_HEAD(list);
+	bool power_down = false;
 
 	pm_runtime_get_sync(pl330->ddma.dev);
 	spin_lock_irqsave(&pch->lock, flags);
@@ -2185,6 +2191,8 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	pch->thread->req[0].desc = NULL;
 	pch->thread->req[1].desc = NULL;
 	pch->thread->req_running = -1;
+	power_down = pch->active;
+	pch->active = false;
 
 	/* Mark all desc done */
 	list_for_each_entry(desc, &pch->submitted_list, node) {
@@ -2202,6 +2210,8 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	list_splice_tail_init(&pch->completed_list, &pl330->desc_pool);
 	spin_unlock_irqrestore(&pch->lock, flags);
 	pm_runtime_mark_last_busy(pl330->ddma.dev);
+	if (power_down)
+		pm_runtime_put_autosuspend(pl330->ddma.dev);
 	pm_runtime_put_autosuspend(pl330->ddma.dev);
 
 	return 0;
@@ -2348,6 +2358,7 @@ static void pl330_issue_pending(struct dma_chan *chan)
 		 * updated on work_list emptiness status.
 		 */
 		WARN_ON(list_empty(&pch->submitted_list));
+		pch->active = true;
 		pm_runtime_get_sync(pch->dmac->ddma.dev);
 	}
 	list_splice_tail_init(&pch->submitted_list, &pch->work_list);

drivers/gpu/drm/drm_dp_mst_topology.c

@@ -1812,7 +1812,7 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr)
 				mgr->payloads[i].num_slots = req_payload.num_slots;
 			} else if (mgr->payloads[i].num_slots) {
 				mgr->payloads[i].num_slots = 0;
-				drm_dp_destroy_payload_step1(mgr, port, port->vcpi.vcpi, &mgr->payloads[i]);
+				drm_dp_destroy_payload_step1(mgr, port, mgr->payloads[i].vcpi, &mgr->payloads[i]);
 				req_payload.payload_state = mgr->payloads[i].payload_state;
 				mgr->payloads[i].start_slot = 0;
 			}

drivers/gpu/drm/drm_modes.c

@@ -1401,6 +1401,13 @@ drm_mode_create_from_cmdline_mode(struct drm_device *dev,
 		return NULL;
 
 	mode->type |= DRM_MODE_TYPE_USERDEF;
+	/* fix up 1368x768: GFT/CVT can't express 1366 width due to alignment */
+	if (cmd->xres == 1366 && mode->hdisplay == 1368) {
+		mode->hdisplay = 1366;
+		mode->hsync_start--;
+		mode->hsync_end--;
+		drm_mode_set_name(mode);
+	}
 	drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V);
 	return mode;
 }

drivers/gpu/drm/i915/intel_crt.c

@@ -445,6 +445,7 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector)
 	struct drm_i915_private *dev_priv = crt->base.base.dev->dev_private;
 	struct edid *edid;
 	struct i2c_adapter *i2c;
+	bool ret = false;
 
 	BUG_ON(crt->base.type != INTEL_OUTPUT_ANALOG);
 
@@ -461,17 +462,17 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector)
 		 */
 		if (!is_digital) {
 			DRM_DEBUG_KMS("CRT detected via DDC:0x50 [EDID]\n");
-			return true;
+			ret = true;
+		} else {
+			DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n");
 		}
-
-		DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n");
 	} else {
 		DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [no valid EDID found]\n");
 	}
 
 	kfree(edid);
 
-	return false;
+	return ret;
 }
 
 static enum drm_connector_status

drivers/gpu/drm/i915/intel_display.c

@@ -3948,10 +3948,10 @@ static void page_flip_completed(struct intel_crtc *intel_crtc)
 	drm_crtc_vblank_put(&intel_crtc->base);
 
 	wake_up_all(&dev_priv->pending_flip_queue);
-	queue_work(dev_priv->wq, &work->work);
-
 	trace_i915_flip_complete(intel_crtc->plane,
 				 work->pending_flip_obj);
+
+	queue_work(dev_priv->wq, &work->work);
 }
 
 void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc)

drivers/gpu/drm/nouveau/dispnv04/hw.c

@@ -222,6 +222,7 @@ nouveau_hw_get_clock(struct drm_device *dev, enum nvbios_pll_type plltype)
 		uint32_t mpllP;
 
 		pci_read_config_dword(pci_get_bus_and_slot(0, 3), 0x6c, &mpllP);
+		mpllP = (mpllP >> 8) & 0xf;
 		if (!mpllP)
 			mpllP = 4;
 
@@ -232,7 +233,7 @@ nouveau_hw_get_clock(struct drm_device *dev, enum nvbios_pll_type plltype)
 		uint32_t clock;
 
 		pci_read_config_dword(pci_get_bus_and_slot(0, 5), 0x4c, &clock);
-		return clock;
+		return clock / 1000;
 	}
 
 	ret = nouveau_hw_get_pllvals(dev, plltype, &pllvals);

drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c

@@ -59,7 +59,7 @@ gt215_hda_eld(NV50_DISP_MTHD_V1)
 			);
 		}
 		for (i = 0; i < size; i++)
-			nvkm_wr32(device, 0x61c440 + soff, (i << 8) | args->v0.data[0]);
+			nvkm_wr32(device, 0x61c440 + soff, (i << 8) | args->v0.data[i]);
 		for (; i < 0x60; i++)
 			nvkm_wr32(device, 0x61c440 + soff, (i << 8));
 		nvkm_mask(device, 0x61c448 + soff, 0x80000003, 0x80000003);

drivers/gpu/drm/radeon/radeon_cursor.c

@@ -146,6 +146,9 @@ static int radeon_cursor_move_locked(struct drm_crtc *crtc, int x, int y)
 	int xorigin = 0, yorigin = 0;
 	int w = radeon_crtc->cursor_width;
 
+	radeon_crtc->cursor_x = x;
+	radeon_crtc->cursor_y = y;
+
 	if (ASIC_IS_AVIVO(rdev)) {
 		/* avivo cursor are offset into the total surface */
 		x += crtc->x;
@@ -202,8 +205,8 @@ static int radeon_cursor_move_locked(struct drm_crtc *crtc, int x, int y)
 	}
 
 	if (x <= (crtc->x - w) || y <= (crtc->y - radeon_crtc->cursor_height) ||
-	    x >= (crtc->x + crtc->mode.crtc_hdisplay) ||
-	    y >= (crtc->y + crtc->mode.crtc_vdisplay))
+	    x >= (crtc->x + crtc->mode.hdisplay) ||
+	    y >= (crtc->y + crtc->mode.vdisplay))
 		goto out_of_bounds;
 
 	x += xorigin;
@@ -240,9 +243,6 @@ static int radeon_cursor_move_locked(struct drm_crtc *crtc, int x, int y)
 		       yorigin * 256);
 	}
 
-	radeon_crtc->cursor_x = x;
-	radeon_crtc->cursor_y = y;
-
 	if (radeon_crtc->cursor_out_of_bounds) {
 		radeon_crtc->cursor_out_of_bounds = false;
 		if (radeon_crtc->cursor_bo)

drivers/gpu/drm/radeon/si_dpm.c

@@ -3008,19 +3008,6 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 		    (rdev->pdev->device == 0x6817) ||
 		    (rdev->pdev->device == 0x6806))
 			max_mclk = 120000;
-	} else if (rdev->family == CHIP_VERDE) {
-		if ((rdev->pdev->revision == 0x81) ||
-		    (rdev->pdev->revision == 0x83) ||
-		    (rdev->pdev->revision == 0x87) ||
-		    (rdev->pdev->device == 0x6820) ||
-		    (rdev->pdev->device == 0x6821) ||
-		    (rdev->pdev->device == 0x6822) ||
-		    (rdev->pdev->device == 0x6823) ||
-		    (rdev->pdev->device == 0x682A) ||
-		    (rdev->pdev->device == 0x682B)) {
-			max_sclk = 75000;
-			max_mclk = 80000;
-		}
 	} else if (rdev->family == CHIP_OLAND) {
 		if ((rdev->pdev->revision == 0xC7) ||
 		    (rdev->pdev->revision == 0x80) ||